From f0e8ab9e4cbe30b1246e85232c59e2ae05d6b9b4 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Fri, 18 Feb 2022 17:59:56 +0100
Subject: [PATCH 001/350] replace pysam in converters by command line tools

- removes popen call
- removes outdated pysam dependency

fixes https://github.com/galaxyproject/galaxy/issues/9672

if desired we can keep pysam (updated) and just replace the popen calls
---
 lib/galaxy/datatypes/converters/bgzip.py      | 53 -----------------
 .../interval_to_bgzip_converter.xml           | 25 ++++----
 .../converters/interval_to_tabix_converter.py | 59 -------------------
 .../interval_to_tabix_converter.xml           | 22 ++++---
 .../datatypes/converters/tabular_to_dbnsfp.py | 35 -----------
 .../converters/tabular_to_dbnsfp.xml          |  8 ++-
 .../datatypes/converters/vcf_to_vcf_bgzip.py  | 25 --------
 .../converters/vcf_to_vcf_bgzip_converter.xml |  7 ++-
 8 files changed, 40 insertions(+), 194 deletions(-)
 delete mode 100644 lib/galaxy/datatypes/converters/bgzip.py
 delete mode 100644 lib/galaxy/datatypes/converters/interval_to_tabix_converter.py
 delete mode 100644 lib/galaxy/datatypes/converters/tabular_to_dbnsfp.py
 delete mode 100644 lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip.py

diff --git a/lib/galaxy/datatypes/converters/bgzip.py b/lib/galaxy/datatypes/converters/bgzip.py
deleted file mode 100644
index 3e996c5442a..00000000000
--- a/lib/galaxy/datatypes/converters/bgzip.py
+++ /dev/null
@@ -1,53 +0,0 @@
-#!/usr/bin/env python
-
-"""
-Uses pysam to bgzip a file
-
-usage: %prog in_file out_file
-"""
-import optparse
-import subprocess
-import tempfile
-
-import pysam
-
-
-def main():
-    # Read options, args.
-    parser = optparse.OptionParser()
-    parser.add_option("-c", "--chr-col", type="int", dest="chrom_col")
-    parser.add_option("-s", "--start-col", type="int", dest="start_col")
-    parser.add_option("-e", "--end-col", type="int", dest="end_col")
-    parser.add_option("-P", "--preset", dest="preset")
-    (options, args) = parser.parse_args()
-    input_fname, output_fname = args
-
-    tmpfile = tempfile.NamedTemporaryFile()
-    sort_params = None
-
-    if options.chrom_col and options.start_col and options.end_col:
-        sort_params = [
-            "sort",
-            "-k{i},{i}".format(i=options.chrom_col),
-            "-k%(i)i,%(i)in" % {"i": options.start_col},
-            "-k%(i)i,%(i)in" % {"i": options.end_col},
-        ]
-    elif options.preset == "bed":
-        sort_params = ["sort", "-k1,1", "-k2,2n", "-k3,3n"]
-    elif options.preset == "vcf":
-        sort_params = ["sort", "-k1,1", "-k2,2n"]
-    elif options.preset == "gff":
-        sort_params = ["sort", "-s", "-k1,1", "-k4,4n"]  # stable sort on start column
-    # Skip any lines starting with "#" and "track"
-    grepped = subprocess.Popen(
-        ["grep", "-e", '^"#"', "-e", "^track", "-v", input_fname], stderr=subprocess.PIPE, stdout=subprocess.PIPE
-    )
-    after_sort = subprocess.Popen(sort_params, stdin=grepped.stdout, stderr=subprocess.PIPE, stdout=tmpfile)
-    grepped.stdout.close()
-    output, err = after_sort.communicate()
-
-    pysam.tabix_compress(tmpfile.name, output_fname, force=True)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 9eab8ea4c53..0650215db60 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -1,22 +1,27 @@
 <tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.1" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
-        <requirement type="package" version="8.25">coreutils</requirement>
+        <requirement type="package" version="9.0">coreutils</requirement>
+        <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
     <command><![CDATA[
-        python '$__tool_directory__/bgzip.py'
-        #if $input1.ext in ['bed', 'gff', 'vcf']
-            -P $input1.ext
+        grep -e '^"#"' -e '^track' -v '$input1' 
+        |
+        sort 
+        #if $input1.ext == "vcf"
+            -k1,1 -k2,2n
+        #elif $input1.ext == "gff"
+            -s -k1,1 -k4,4n
         #else
-            -c ${input1.metadata.chromCol}
-            -s ${input1.metadata.startCol}
-            -e ${input1.metadata.endCol}
+            -k${input1.metadata.chromCol},${input1.metadata.chromCol}
+            -k${input1.metadata.startCol},${input1.metadata.startCol}n
+            -k${input1.metadata.endCol},${input1.metadata.endCol}n
         #end if
-        '$input1' '$output1'
+        | 
+        bgzip -c > '$output1'
     ]]></command>
     <inputs>
-        <!-- gff because gff and vcf are not a subclass of interval -->
+        <!-- gff and vcf are not a subclass of interval -->
         <param format="gff,vcf,interval" name="input1" type="data" label="Choose Interval file"/>
     </inputs>
     <outputs>
diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.py b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.py
deleted file mode 100644
index 29e66b518a0..00000000000
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.py
+++ /dev/null
@@ -1,59 +0,0 @@
-#!/usr/bin/env python
-
-"""
-Uses pysam to index a bgzipped interval file with tabix
-Supported presets: bed, gff, vcf
-
-usage: %prog in_file out_file
-"""
-import optparse
-import os
-import sys
-
-import pysam
-
-
-def main():
-    # Read options, args.
-    parser = optparse.OptionParser()
-    parser.add_option("-c", "--chr-col", type="int", dest="chrom_col")
-    parser.add_option("-s", "--start-col", type="int", dest="start_col")
-    parser.add_option("-e", "--end-col", type="int", dest="end_col")
-    parser.add_option("-P", "--preset", dest="preset")
-    (options, args) = parser.parse_args()
-    _, bgzip_fname, out_fname = args
-    to_tabix(
-        bgzip_fname=bgzip_fname,
-        out_fname=out_fname,
-        preset=options.preset,
-        chrom_col=options.chrom_col,
-        start_col=options.start_col,
-        end_col=options.end_col,
-    )
-
-
-def to_tabix(bgzip_fname, out_fname, preset=None, chrom_col=None, start_col=None, end_col=None):
-    # Create index.
-    if preset:
-        # Preset type.
-        bgzip_fname = pysam.tabix_index(
-            filename=bgzip_fname, preset=preset, keep_original=True, index=out_fname, force=True
-        )
-    else:
-        # For interval files; column indices are 0-based.
-        bgzip_fname = pysam.tabix_index(
-            filename=bgzip_fname,
-            seq_col=(chrom_col - 1),
-            start_col=(start_col - 1),
-            end_col=(end_col - 1),
-            keep_original=True,
-            index=out_fname,
-            force=True,
-        )
-    if os.path.getsize(out_fname) == 0:
-        sys.exit("The converted tabix index file is empty, meaning the input data is invalid.")
-    return bgzip_fname
-
-
-if __name__ == "__main__":
-    main()
diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index 54dbd1ad28e..d1a67808f9c 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -1,18 +1,26 @@
 <tool id="CONVERTER_interval_to_tabix_0" name="Convert Interval to tabix" version="1.0.1" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
+        <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
     <command><![CDATA[
-        python '$__tool_directory__/interval_to_tabix_converter.py'
+        ln -s '$bgzip' input.bgz &&
+        tabix 
         #if $input1.ext in ['bed', 'gff', 'vcf']
-            -P $input1.ext
+            -p $input1.ext
         #else
-            -c ${input1.metadata.chromCol}
-            -s ${input1.metadata.startCol}
-            -e ${input1.metadata.endCol}
+             -s ${input1.metadata.chromCol}
+             -b ${input1.metadata.startCol}
+             -e ${input1.metadata.endCol}
         #end if
-        '$input1' '$bgzip' '$output1'
+        input.bgz
+        &&
+        if [ ! -s input.bgz.tbi ]; then
+            >&2 echo "The converted tabix index file is empty, meaning the input data is invalid.";
+            exit 1;
+        fi 
+        &&
+        mv input.bgz.tbi '$output1'
     ]]></command>
     <inputs>
         <!-- gff because gff and vcf are not a subclass of interval -->
diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.py b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.py
deleted file mode 100644
index a8c7c06ee5a..00000000000
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.py
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/usr/bin/env python
-"""
-Uses pysam to bgzip a file
-
-usage: %prog in_file out_file
-"""
-
-import optparse
-import os.path
-
-import pysam
-
-
-def main():
-    # Read options, args.
-    usage = "Usage: %prog [options] tabular_input_file bgzip_output_file"
-    parser = optparse.OptionParser(usage=usage)
-    parser.add_option("-c", "--chr-col", type="int", default=0, dest="chrom_col")
-    parser.add_option("-s", "--start-col", type="int", default=1, dest="start_col")
-    parser.add_option("-e", "--end-col", type="int", default=1, dest="end_col")
-    (options, args) = parser.parse_args()
-    if len(args) != 2:
-        parser.print_usage()
-        exit(1)
-    input_fname, output_fname = args
-    output_dir = os.path.dirname(output_fname)
-    if not os.path.exists(output_dir):
-        os.makedirs(output_dir)
-    pysam.tabix_compress(input_fname, output_fname, force=True)
-    # Column indices are 0-based.
-    pysam.tabix_index(output_fname, seq_col=options.chrom_col, start_col=options.start_col, end_col=options.end_col)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
index a0b7c255736..5fecb131ee2 100644
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
+++ b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
@@ -1,9 +1,13 @@
 <tool id="tabular_to_dbnsfp" name="Convert tabular to dbnsfp" version="1.0.1" profile="16.04">
     <description></description>
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
+        <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
-    <command>python '$__tool_directory__/tabular_to_dbnsfp.py' '$input' '$dbnsfp.extra_files_path/dbNSFP.gz'</command>
+    <command><![CDATA[
+        mkdir '$dbnsfp.extra_files_path' &&
+        bgzip -c '$input' > '$dbnsfp.extra_files_path/dbNSFP.gz' &&
+        tabix '$dbnsfp.extra_files_path/dbNSFP.gz'
+    ]]></command>
     <inputs>
         <param format="tabular" name="input" type="data" label="Choose a dbnsfp tabular file"/>
     </inputs>
diff --git a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip.py b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip.py
deleted file mode 100644
index 91ca2fe88bc..00000000000
--- a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip.py
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/usr/bin/env python
-
-"""
-Uses pysam to bgzip a vcf file as-is.
-Headers, which are important, are kept.
-Original ordering, which may be specifically needed  by tools or external display applications, is also maintained.
-
-usage: %prog in_file out_file
-"""
-import optparse
-
-import pysam
-
-
-def main():
-    # Read options, args.
-    parser = optparse.OptionParser()
-    (options, args) = parser.parse_args()
-    input_fname, output_fname = args
-
-    pysam.tabix_compress(input_fname, output_fname, force=True)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
index b680b973a48..cd08cee2664 100644
--- a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
@@ -1,10 +1,11 @@
 <tool id="CONVERTER_vcf_to_vcf_bgzip_0" name="Convert VCF to VCF_BGZIP" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
-        <requirement type="package" version="8.25">coreutils</requirement>
+        <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
-    <command>python '$__tool_directory__/vcf_to_vcf_bgzip.py' '$input1' '$output1'</command>
+    <command><![CDATA[
+        bgzip -c '$input1' > '$output1'
+    ]]></command>
     <inputs>
         <param format="vcf" name="input1" type="data" label="Choose Vcf file"/>
     </inputs>

From eb883e2f814631b44a9f8634de25026aa7cba24f Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Fri, 18 Feb 2022 18:03:47 +0100
Subject: [PATCH 002/350] temporarily add test-data

---
 test-data/2.tabix                                 | Bin 0 -> 247 bytes
 test-data/droPer1.tabix                           | Bin 0 -> 133 bytes
 .../tabix_filter_by_feature_count_out2.tabix      | Bin 0 -> 121 bytes
 test-data/tabix_to_maf_in.tabix                   | Bin 0 -> 148 bytes
 test-data/vcf_bgzip_to_maf_in.vcf_bgzip           | Bin 0 -> 717 bytes
 5 files changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 test-data/2.tabix
 create mode 100644 test-data/droPer1.tabix
 create mode 100644 test-data/tabix_filter_by_feature_count_out2.tabix
 create mode 100644 test-data/tabix_to_maf_in.tabix
 create mode 100644 test-data/vcf_bgzip_to_maf_in.vcf_bgzip

diff --git a/test-data/2.tabix b/test-data/2.tabix
new file mode 100644
index 0000000000000000000000000000000000000000..4f60dc49158739aa6df92a4f94f9df1120af2c6e
GIT binary patch
literal 247
zcmb2|=3rp}f&Xj_PR>jW%NgFD-pJb&Ai{d#x2al~-a=!GhPh#4B413d^c>RR@i?Te
zXux>X@~HN^-P?cGczcFUikTEM+2;D2X-i(WmsS3`zje#ZX}_gkf0$vvsl1*QY&6-#
zgEeUlvs5w}{xdMhqq)<F;q5^~Mxe=u6n-x^J0_O^v&4k2qAp_kPDM;D(hSTnMGOGy
COgoDJ

literal 0
HcmV?d00001

diff --git a/test-data/droPer1.tabix b/test-data/droPer1.tabix
new file mode 100644
index 0000000000000000000000000000000000000000..80aab7c82d91950376e8517485d5eeedbd2c4d9a
GIT binary patch
literal 133
zcmb2|=3rp}f&Xj_PR>jW84TQopHfm%5<nmY2on;LfH*B7At0@Rfsc)??a`&CD~l?e
zH&iSTU}jckX1d|<Qenjo-WWAmpDN#`87CXm`m~N6IB?X#Hlg_#J42Cu-HInb^X1Vj
Ll4f8A+Y2H96c{Hg

literal 0
HcmV?d00001

diff --git a/test-data/tabix_filter_by_feature_count_out2.tabix b/test-data/tabix_filter_by_feature_count_out2.tabix
new file mode 100644
index 0000000000000000000000000000000000000000..f750c2687772e13368cb66a9b83ef613b3c5f045
GIT binary patch
literal 121
zcmb2|=3rp}f&Xj_PR>jWF$}S%HVQg8Ft}VSZ&zEQrD&*rt<iy*sdUASo@5LAn{)SD
z^J}uqY>?vJb=x#z+g9<3Np^eR2rfIk_5a@$OMZPZoA$GSiI?T>nu$O&<<Sh6W?%-}
G1tI{PCMFO7

literal 0
HcmV?d00001

diff --git a/test-data/tabix_to_maf_in.tabix b/test-data/tabix_to_maf_in.tabix
new file mode 100644
index 0000000000000000000000000000000000000000..7674eb69a8858d970af4c7cb1d9be6ee368dc3e8
GIT binary patch
literal 148
zcmb2|=3rp}f&Xj_PR>jW<qX_~pHfm%5)u-U5)v9N@&Li9fLSve8xNjnXq*b9f;kqY
z7>4vR7`J?D>N@;`)!?J2z~h8hk`mLJBiHb(SirtYe%X7~Df5^_+dn4$s@<?-VZs!-
fr4wIF7rA7>z;Ivk)m(XI1_pUFd!-qGf=~be)!Q<N

literal 0
HcmV?d00001

diff --git a/test-data/vcf_bgzip_to_maf_in.vcf_bgzip b/test-data/vcf_bgzip_to_maf_in.vcf_bgzip
new file mode 100644
index 0000000000000000000000000000000000000000..90e7977846afeb7248389beea4c0665644b76875
GIT binary patch
literal 717
zcmV;;0y6y{iwFb&00000{{{d;LjnM>0%eg~Z=)~}g`X$C0tM}xn~ZG?i6b6pDI`*x
z=E8QL-PBExxD}kPD)q;&$dzuN%-}Qg%{jL1w=~mlWt}VIKi@?ke87A5;b*9f_8H<B
zM<{x>-IV)!qy7AImREbDOj;I;y4=<(f93<)v+Y{H=~@>X?NdaIby4QJS)^HMZsvEl
zGw$|myV|KHEw+B8YLlw0XWO%R^yJUigpyfd^j6oTKi}ssy0*$UYpwDs(~b2fH9IR*
zM)l7f;iB7-ltyJ%s4KI(D1wOGP!eUOGNd15na;Eo)%ty}i_Pa%6%b0+rcR43=?BF|
zH>OsZb<|&Jw**O)sV(WhzO3g9E7$Fc%`UBo^|DX1SBtXoMLuO0`BYVps$!jnRu#=2
zlKYkaPLcGNdzGc;(|XZa`PZV@xo-rL{)28B%j{HP3H;TD(wsussSj<vo<fP9R*ymA
z$4SRd`vm5*(%t)IH@36DI_=OAe$RKM)$29hlVrLi>?)b6D*J!f-E{Tz2#cpR%tBb*
zM-V(Du>2i7z|kPIX~A(E%mYM3dOF$Z<UNK!9qu92jf=uz!h;wBU}Hd-uYEoV7d~|+
zLFD5=Ov2mAltG-xcqzk$oGt;sP&y+?rJzJmpvQ7_E{9Y)Tnc$Z$qhZgJkAjYkU#(&
z-f4$Ij})ZdPr_JoDMmyf;1_Mbr7H*r9HMmE`Z}LdbjR+&j)PnX2p}d2xZcqaJD~80
z;+zv4xUM$|0za9Ax8K0@i%CYMD;X!u1NKEFlPKwkFknL_xsXl=%s4Xc9jpz&@w)l(
z!~7qvgd;sET;k$6M(31U>&tC%-SLiaJ;>8dT{g;4h#_>yEDoRz<-!`bsQ7{c9MZ$0
zfI}v!C)x2$Q1aeCwV*N^o&*2@ABzYC000000RIL6LPG)o8vp|U0000000000ze!v5

literal 0
HcmV?d00001


From e2e8a634c27b49f34e03e58f2249b4475de3af51 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 16 Jun 2022 12:14:03 +0200
Subject: [PATCH 003/350] bump tool versions

---
 lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml | 2 +-
 lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml | 2 +-
 lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml           | 2 +-
 lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml  | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 0650215db60..011e6e85c25 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.1" hidden="true" profile="16.04">
+<tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
         <requirement type="package" version="9.0">coreutils</requirement>
diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index d1a67808f9c..ab689d50711 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_interval_to_tabix_0" name="Convert Interval to tabix" version="1.0.1" hidden="true" profile="16.04">
+<tool id="CONVERTER_interval_to_tabix_0" name="Convert Interval to tabix" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
         <requirement type="package" version="1.14">htslib</requirement>
diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
index 5fecb131ee2..e567d3f4a93 100644
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
+++ b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
@@ -1,4 +1,4 @@
-<tool id="tabular_to_dbnsfp" name="Convert tabular to dbnsfp" version="1.0.1" profile="16.04">
+<tool id="tabular_to_dbnsfp" name="Convert tabular to dbnsfp" version="1.0.2" profile="16.04">
     <description></description>
     <requirements>
         <requirement type="package" version="1.14">htslib</requirement>
diff --git a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
index cd08cee2664..5536642f226 100644
--- a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_vcf_to_vcf_bgzip_0" name="Convert VCF to VCF_BGZIP" version="1.0.2" hidden="true" profile="16.04">
+<tool id="CONVERTER_vcf_to_vcf_bgzip_0" name="Convert VCF to VCF_BGZIP" version="1.0.3" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
         <requirement type="package" version="1.14">htslib</requirement>

From 035ea24f2800c1f0f8f57fbdfaa0bfbaccea2a8c Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 20 Jun 2022 11:46:06 +0200
Subject: [PATCH 004/350] update tests for interval2bgzip converter

- compare decompressed files
- and ensure file size
---
 .../interval_to_bgzip_converter.xml           | 27 ++++++++++++++-----
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 011e6e85c25..1addb2bc02a 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -1,5 +1,12 @@
 <tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
+    <macros>
+        <xml name="assert_size" tokens="value" token_delta="10">
+            <assert_contents>
+                <has_size value="@VALUE@" delta="@DELTA@"/>
+            </assert_contents>
+        </xml>
+    </macros>
     <requirements>
         <requirement type="package" version="9.0">coreutils</requirement>
         <requirement type="package" version="1.14">htslib</requirement>
@@ -30,27 +37,33 @@
     <tests>
         <test>
             <param name="input1" ftype="bed" value="droPer1.bed"/>
-            <output name="output1" ftype="bgzip" value="droPer1.bgzip"/>
+            <output name="output1" ftype="bgzip" value="droPer1.bgzip" decompress="true">
+                <expand macro="assert_size" value="131"/>
+            </output>
         </test>
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
             <output name="output1" ftype="bgzip">
-                <assert_contents>
-                    <has_size value="299" delta="10"/>
-                </assert_contents>
+                <expand macro="assert_size" value="299"/>
             </output>
         </test>
         <test>
             <param name="input1" ftype="gff" value="gff_filter_by_feature_count_out2.gff"/>
-            <output name="output1" ftype="bgzip" value="bgzip_filter_by_feature_count_out2.bgzip"/>
+            <output name="output1" ftype="bgzip" value="bgzip_filter_by_feature_count_out2.bgzip" decompress="true">
+                <expand macro="assert_size" value="638"/>
+            </output>
         </test>
         <test>
             <param name="input1" ftype="interval" value="2.interval"/>
-            <output name="output1" ftype="bgzip" value="2.bgzip"/>
+            <output name="output1" ftype="bgzip" value="2.bgzip" decompress="true">
+                <expand macro="assert_size" value="208"/>
+            </output>
         </test>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
-            <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip"/>
+            <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
+                <expand macro="assert_size" value="707"/>
+            </output>
         </test>
     </tests>
     <help>

From dc397a74b512e53313917644d40c0c827015c3fa Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 20 Jun 2022 12:09:07 +0200
Subject: [PATCH 005/350] remove interval2tabix unit test

not needed
---
 test/unit/data/datatypes/converters/__init__.py   |  0
 .../converters/test_interval_to_tabix.py          | 15 ---------------
 2 files changed, 15 deletions(-)
 delete mode 100644 test/unit/data/datatypes/converters/__init__.py
 delete mode 100644 test/unit/data/datatypes/converters/test_interval_to_tabix.py

diff --git a/test/unit/data/datatypes/converters/__init__.py b/test/unit/data/datatypes/converters/__init__.py
deleted file mode 100644
index e69de29bb2d..00000000000
diff --git a/test/unit/data/datatypes/converters/test_interval_to_tabix.py b/test/unit/data/datatypes/converters/test_interval_to_tabix.py
deleted file mode 100644
index b1ce9570d67..00000000000
--- a/test/unit/data/datatypes/converters/test_interval_to_tabix.py
+++ /dev/null
@@ -1,15 +0,0 @@
-import pysam
-
-from galaxy.datatypes.converters.interval_to_tabix_converter import to_tabix
-from ..util import (
-    get_input_files,
-    get_tmp_path,
-)
-
-
-def test_to_tabix():
-    with get_input_files("1.vcf") as input_files:
-        with get_tmp_path(suffix=".tbi") as index:
-            bgzip_fname = to_tabix(input_files[0], index, preset="vcf")
-            f = pysam.TabixFile(bgzip_fname, index=index)
-            f.close()

From ee5d4652dcbb1acf259cc7a5151ce3d28c118aff Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 20 Jun 2022 15:47:30 +0200
Subject: [PATCH 006/350] update tests for vcf_to_vcf_bgzip

---
 .../datatypes/converters/vcf_to_vcf_bgzip_converter.xml     | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
index 5536642f226..41617707e2b 100644
--- a/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_to_vcf_bgzip_converter.xml
@@ -15,7 +15,11 @@
     <tests>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
-            <output name="output1" ftype="vcf_bgzip" value="vcf_bgzip_to_maf_in.vcf_bgzip"/>
+            <output name="output1" ftype="vcf_bgzip" value="vcf_bgzip_to_maf_in.vcf_bgzip" decompress="true">
+                <assert_contents>
+                    <has_size value="717" delta="10"/>
+                </assert_contents>
+            </output>
         </test>
     </tests>
     <help>

From ed2b5a2439910b7d25daca0258e373d4916c0103 Mon Sep 17 00:00:00 2001
From: Martin Cech <marten@bx.psu.edu>
Date: Thu, 27 Oct 2022 12:55:27 -0700
Subject: [PATCH 007/350] move v-b-tooltip to a parent element to fix rendering

---
 .../DatasetInformation/DatasetSource.vue      |  8 +++---
 .../components/HistoryExport/ExportLink.vue   | 10 +++----
 .../components/Indices/SharingIndicators.vue  | 26 +++++++++----------
 .../components/License/LicenseSelector.vue    | 10 ++++---
 .../components/SchemaOrg/CreatorEditor.vue    | 12 ++++-----
 .../components/SchemaOrg/OrganizationForm.vue |  8 +++---
 .../SchemaOrg/OrganizationViewer.vue          |  4 +--
 .../src/components/SchemaOrg/PersonForm.vue   |  8 +++---
 .../src/components/SchemaOrg/PersonViewer.vue |  8 +++---
 9 files changed, 45 insertions(+), 49 deletions(-)

diff --git a/client/src/components/DatasetInformation/DatasetSource.vue b/client/src/components/DatasetInformation/DatasetSource.vue
index d7c210976c5..009614ef94e 100644
--- a/client/src/components/DatasetInformation/DatasetSource.vue
+++ b/client/src/components/DatasetInformation/DatasetSource.vue
@@ -1,13 +1,15 @@
 <template>
     <li class="dataset-source">
-        <a v-if="browserCompatUri" :href="sourceUri" target="_blank">
+        <a v-if="browserCompatUri" v-b-tooltip.hover title="Dataset Source URL" :href="sourceUri" target="_blank">
             {{ source.source_uri }}
-            <font-awesome-icon v-b-tooltip.hover title="Dataset Source URL" icon="external-link-alt" />
+            <font-awesome-icon icon="external-link-alt" />
         </a>
         <span v-else>
             {{ source.source_uri }}
         </span>
-        <font-awesome-icon v-b-tooltip.hover title="Copy URI" icon="copy" style="cursor: pointer" @click="copyLink" />
+        <span v-b-tooltip.hover title="Copy URI"
+            ><font-awesome-icon icon="copy" style="cursor: pointer" @click="copyLink"
+        /></span>
         <br />
         <DatasetSourceTransform :transform="source.transform" />
     </li>
diff --git a/client/src/components/HistoryExport/ExportLink.vue b/client/src/components/HistoryExport/ExportLink.vue
index fece9bbe0ce..b4bbdb95b82 100644
--- a/client/src/components/HistoryExport/ExportLink.vue
+++ b/client/src/components/HistoryExport/ExportLink.vue
@@ -3,13 +3,9 @@
         <b
             ><a class="generated-export-link" :href="link">{{ link }}</a></b
         >
-        <font-awesome-icon
-            v-b-tooltip.hover
-            title="Copy export URL to your clipboard"
-            class="copy-export-link"
-            icon="link"
-            style="cursor: pointer"
-            @click="copyUrl" />
+        <span v-b-tooltip.hover title="Copy export URL to your clipboard">
+            <font-awesome-icon class="copy-export-link" icon="link" style="cursor: pointer" @click="copyUrl" />
+        </span>
         <i
             title="Information about when the history export was generated is included in the job details. Additionally, if there are issues with export, the job details may help figure out the underlying problem or communicate issues to your Galaxy administrator.">
             (<b-link class="show-job-link" href="#" @click="showDetails">view job details</b-link>)
diff --git a/client/src/components/Indices/SharingIndicators.vue b/client/src/components/Indices/SharingIndicators.vue
index 38d754eb33c..98031f5f07f 100644
--- a/client/src/components/Indices/SharingIndicators.vue
+++ b/client/src/components/Indices/SharingIndicators.vue
@@ -1,19 +1,17 @@
 <template>
     <span>
-        <font-awesome-icon
-            v-if="object.published"
-            v-b-tooltip.hover
-            :title="'Published' | localize"
-            icon="globe"
-            class="sharing-indicator-published"
-            @click="$emit('filter', 'is:published')" />
-        <font-awesome-icon
-            v-if="object.shared"
-            v-b-tooltip.hover
-            :title="'Shared' | localize"
-            icon="share-alt"
-            class="sharing-indicator-shared"
-            @click="$emit('filter', 'is:shared_with_me')" />
+        <span v-if="object.published" v-b-tooltip.hover :title="'Published' | localize">
+            <font-awesome-icon
+                icon="globe"
+                class="sharing-indicator-published"
+                @click="$emit('filter', 'is:published')" />
+        </span>
+        <span v-if="object.shared" v-b-tooltip.hover :title="'Shared' | localize">
+            <font-awesome-icon
+                icon="share-alt"
+                class="sharing-indicator-shared"
+                @click="$emit('filter', 'is:shared_with_me')" />
+        </span>
     </span>
 </template>
 
diff --git a/client/src/components/License/LicenseSelector.vue b/client/src/components/License/LicenseSelector.vue
index 0d549e1a43d..a8b40612b78 100644
--- a/client/src/components/License/LicenseSelector.vue
+++ b/client/src/components/License/LicenseSelector.vue
@@ -4,8 +4,10 @@
         <b-form-select v-else v-model="license" :options="licenseOptions"></b-form-select>
         <License v-if="currentLicenseInfo" :license-id="license" :input-license-info="currentLicenseInfo">
             <template v-slot:buttons>
-                <font-awesome-icon v-b-tooltip.hover title="Save License" icon="save" @click="onSave" />
-                <font-awesome-icon v-b-tooltip.hover title="Cancel Edit" icon="times" @click="disableEdit" />
+                <span v-b-tooltip.hover title="Save License"><font-awesome-icon icon="save" @click="onSave" /></span>
+                <span v-b-tooltip.hover title="Cancel Edit"
+                    ><font-awesome-icon icon="times" @click="disableEdit"
+                /></span>
             </template>
         </License>
         <div v-else>
@@ -16,7 +18,9 @@
     <div v-else-if="license">
         <License :license-id="license">
             <template v-slot:buttons>
-                <font-awesome-icon v-b-tooltip.hover title="Edit License" icon="edit" @click="editLicense = true" />
+                <span v-b-tooltip.hover title="Edit License"
+                    ><font-awesome-icon icon="edit" @click="editLicense = true"
+                /></span>
             </template>
         </License>
     </div>
diff --git a/client/src/components/SchemaOrg/CreatorEditor.vue b/client/src/components/SchemaOrg/CreatorEditor.vue
index 6c164d80468..f79dc4e7ac9 100644
--- a/client/src/components/SchemaOrg/CreatorEditor.vue
+++ b/client/src/components/SchemaOrg/CreatorEditor.vue
@@ -10,12 +10,12 @@
             <div v-for="(creator, index) in creatorsCurrent" :key="index">
                 <CreatorViewer :creator="creator">
                     <template v-slot:buttons>
-                        <font-awesome-icon v-b-tooltip.hover title="Edit Creator" icon="edit" @click="onEdit(index)" />
-                        <font-awesome-icon
-                            v-b-tooltip.hover
-                            title="Remove Creator"
-                            icon="times"
-                            @click="onRemove(index)" />
+                        <span v-b-tooltip.hover title="Edit Creator"
+                            ><font-awesome-icon icon="edit" @click="onEdit(index)"
+                        /></span>
+                        <span v-b-tooltip.hover title="Remove Creator">
+                            <font-awesome-icon icon="times" @click="onRemove(index)" />
+                        </span>
                     </template>
                 </CreatorViewer>
             </div>
diff --git a/client/src/components/SchemaOrg/OrganizationForm.vue b/client/src/components/SchemaOrg/OrganizationForm.vue
index 4cd76c872bb..39a49d24cd4 100644
--- a/client/src/components/SchemaOrg/OrganizationForm.vue
+++ b/client/src/components/SchemaOrg/OrganizationForm.vue
@@ -3,11 +3,9 @@
     <b-form @submit="onSave" @reset="onReset">
         <div v-for="attribute in displayedAttributes" :key="attribute.key" role="group" class="form-group">
             <label :for="attribute.key">{{ attribute.label }}</label>
-            <font-awesome-icon
-                v-b-tooltip.hover
-                title="Hide Attribute"
-                icon="eye-slash"
-                @click="onHide(attribute.key)" />
+            <span v-b-tooltip.hover title="Hide Attribute"
+                ><font-awesome-icon icon="eye-slash" @click="onHide(attribute.key)"
+            /></span>
             <b-form-input
                 :id="attribute.key"
                 v-model="currentValues[attribute.key]"
diff --git a/client/src/components/SchemaOrg/OrganizationViewer.vue b/client/src/components/SchemaOrg/OrganizationViewer.vue
index a191efbf357..1b43c3dee9d 100644
--- a/client/src/components/SchemaOrg/OrganizationViewer.vue
+++ b/client/src/components/SchemaOrg/OrganizationViewer.vue
@@ -18,9 +18,9 @@
         <span v-else-if="email" itemprop="email" :content="organization.email">
             {{ email }}
         </span>
-        <a v-if="url" :href="url" target="_blank">
+        <a v-if="url" v-b-tooltip.hover title="Organization URL" :href="url" target="_blank">
             <link itemprop="url" :href="url" />
-            <font-awesome-icon v-b-tooltip.hover title="Organization URL" icon="external-link-alt" />
+            <font-awesome-icon icon="external-link-alt" />
         </a>
         <meta
             v-for="attribute in explicitMetaAttributes"
diff --git a/client/src/components/SchemaOrg/PersonForm.vue b/client/src/components/SchemaOrg/PersonForm.vue
index faeb7460d73..c145fc0d525 100644
--- a/client/src/components/SchemaOrg/PersonForm.vue
+++ b/client/src/components/SchemaOrg/PersonForm.vue
@@ -3,11 +3,9 @@
     <b-form @submit="onSave" @reset="onReset">
         <div v-for="attribute in displayedAttributes" :key="attribute.key" role="group" class="form-group">
             <label :for="attribute.key">{{ attribute.label }}</label>
-            <font-awesome-icon
-                v-b-tooltip.hover
-                title="Hide Attribute"
-                icon="eye-slash"
-                @click="onHide(attribute.key)" />
+            <span v-b-tooltip.hover title="Hide Attribute"
+                ><font-awesome-icon icon="eye-slash" @click="onHide(attribute.key)"
+            /></span>
             <b-form-input
                 :id="attribute.key"
                 v-model="currentValues[attribute.key]"
diff --git a/client/src/components/SchemaOrg/PersonViewer.vue b/client/src/components/SchemaOrg/PersonViewer.vue
index 89ac712d424..0c2f13213e5 100644
--- a/client/src/components/SchemaOrg/PersonViewer.vue
+++ b/client/src/components/SchemaOrg/PersonViewer.vue
@@ -21,13 +21,13 @@
         <span v-else itemprop="email" :content="person.email">
             {{ email }}
         </span>
-        <a v-if="orcidLink" :href="orcidLink" target="_blank">
+        <a v-if="orcidLink" v-b-tooltip.hover title="View orcid.org profile" :href="orcidLink" target="_blank">
             <link itemprop="identifier" :href="orcidLink" />
-            <font-awesome-icon v-b-tooltip.hover title="View orcid.org profile" :icon="['fab', 'orcid']" />
+            <font-awesome-icon :icon="['fab', 'orcid']" />
         </a>
-        <a v-if="url" :href="url" target="_blank">
+        <a v-if="url" v-b-tooltip.hover title="URL" :href="url" target="_blank">
             <link itemprop="url" :href="url" />
-            <font-awesome-icon v-b-tooltip.hover title="URL" icon="external-link-alt" />
+            <font-awesome-icon icon="external-link-alt" />
         </a>
         <meta
             v-for="attribute in explicitMetaAttributes"

From 7597d9cd7e5b20aa974d71a4121ae29990e61907 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 8 Aug 2022 12:11:33 +0200
Subject: [PATCH 008/350] added user api for beacon setting

---
 lib/galaxy/webapps/galaxy/api/users.py | 37 ++++++++++++++++++++++++++
 lib/galaxy/webapps/galaxy/buildapp.py  | 16 +++++++++++
 2 files changed, 53 insertions(+)

diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index b204c68b2c0..06dfdaad799 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -1065,3 +1065,40 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
         if user != trans.user and not trans.user_is_admin:
             raise exceptions.InsufficientPermissionsException("Access denied.")
         return user
+
+    @expose_api
+    def get_beacon(self, trans, id, payload=None, **kwd):
+        """
+        GET /api/users/{id}/beacon
+        Returns information about beacon share settings
+
+        :param id: the encoded id of the user
+        :type  id: str
+        """
+        user = self._get_user(trans, id)
+
+        enabled = user.preferences["beacon_enabled"] if "beacon_enabled" in user.preferences else False
+
+        return {"message": "benno ist ein cooler typ", "enabled": enabled}
+
+    @expose_api
+    def set_beacon(self, trans, id, payload=None, **kwd):
+        """
+        POST /api/users/{id}/beacon
+
+
+        :param id: the encoded id of the user
+        :type  id: str
+
+        :param payload: settings to persist
+        :type  payload: dict
+        """
+        payload = payload or {}
+        user = self._get_user(trans, id)
+
+        if "enabled" in payload:
+            user.preferences["beacon_enabled"] = payload["enabled"]
+            trans.sa_session.flush()
+            return {"message": "setting enabled..."}
+
+        return {"message": payload}
\ No newline at end of file
diff --git a/lib/galaxy/webapps/galaxy/buildapp.py b/lib/galaxy/webapps/galaxy/buildapp.py
index 8c8ba0fe7cc..8bdf8c2c899 100644
--- a/lib/galaxy/webapps/galaxy/buildapp.py
+++ b/lib/galaxy/webapps/galaxy/buildapp.py
@@ -914,6 +914,22 @@ def populate_api_routes(webapp, app):
         conditions=dict(method=["DELETE"]),
     )
 
+    webapp.mapper.connect(
+        "get_beacon",
+        "/api/users/{id}/beacon",
+        controller="users",
+        action="get_beacon",
+        conditions=dict(method=["GET"]),
+    )
+
+    webapp.mapper.connect(
+        "set_beacon",
+        "/api/users/{id}/beacon",
+        controller="users",
+        action="set_beacon",
+        conditions=dict(method=["POST"]),
+    )
+
     # ========================
     # ===== WEBHOOKS API =====
     # ========================

From 045e6e2ba689b7dcf0224f79c319bd65836e9db6 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 8 Aug 2022 12:13:54 +0200
Subject: [PATCH 009/350] added frontedn for beacon user setting

---
 .../components/User/UserBeaconSettings.vue    | 195 ++++++++++++++++++
 .../src/components/User/UserPreferences.vue   |  12 +-
 client/src/style/scss/overrides.scss          |   2 +-
 3 files changed, 207 insertions(+), 2 deletions(-)
 create mode 100644 client/src/components/User/UserBeaconSettings.vue

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
new file mode 100644
index 00000000000..7d2ddfdd53f
--- /dev/null
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -0,0 +1,195 @@
+<template>
+  <b-row class="ml-3 mb-1">
+    <i class="pref-icon pt-1 fa fa-lg fa-broadcast-tower" />
+    <div class="pref-content pr-1">
+      <a id="beacon-settings" href="javascript:void(0)"
+      ><b v-b-modal.modal-beacon v-localize>Manage Beacon</b></a
+      >
+      <div v-localize class="form-text text-muted">Contribute variants to Beacon</div>
+      <b-modal
+          size="xl"
+          id="modal-beacon"
+          ref="modal"
+          ok-only
+          title="Manage Beacon"
+          title-tag="h1"
+          @show="loadSettings">
+
+        <h3>About Beacon</h3>
+        <p>
+          A beacon is a web service that shares information about the occurrence of genetic variants.
+          A beacon answers questions of the form "Do you have information about the following mutation?" and responds with one of "Yes" or "No".
+
+          <b-link href="https://beacon-network.org/#/about">Learn more</b-link>
+        </p>
+
+
+        <b-alert show>Apart from the "Yes/No" response <span class="bold">no data will be shared</span></b-alert>
+
+
+
+        <h3>Participate</h3>
+        There is a beacon instance set up on this galaxy instance. To contribute variant information follow the steps below.
+
+        <div class="actual-settings">
+          <h4>Opt-in to variant sharing</h4>
+          <div class="setting-container">
+            <div class="setting-text">
+              <p v-if="!enabled"> you are currently not opted in</p>
+              <p v-if="enabled"> you have already opted in and you can share data</p>
+            </div>
+            <div class="setting-buttons">
+              <b-button v-if="!enabled" @click="optIn" variant="success">Opt-in</b-button>
+              <b-button v-if="enabled" @click="optOut" variant="danger">Opt-out</b-button>
+            </div>
+          </div>
+        </div>
+
+      </b-modal>
+    </div>
+  </b-row>
+</template>
+
+<script>
+import axios from "axios";
+import Vue from "vue";
+import BootstrapVue from "bootstrap-vue";
+import { userLogoutClient } from "layout/menu";
+Vue.use(BootstrapVue);
+
+export default {
+  props: {
+    root: {
+      type: String,
+      required: true,
+    },
+    userId: {
+      type: String,
+      required: true,
+    },
+  },
+  data() {
+    return {
+      enabled: false,
+    };
+  },
+  computed: {
+    showDeleteError() {
+      return this.deleteError !== "";
+    },
+  },
+  methods: {
+    async optIn() {
+      try {
+        await axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": true}).then(
+            response => {
+              // TODO check response
+              this.loadSettings();
+            }
+        );
+      } catch (e) {
+        console.log(e);
+      }
+    },
+    async optOut() {
+      try {
+        await axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": false}).then(
+            response => {
+              // TODO check response
+              this.loadSettings();
+            }
+        );
+      } catch (e) {
+        console.log(e);
+      }
+    },
+    async loadSettings() {
+      try {
+        await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
+            response => {
+              this.enabled = response.data.enabled == 1;
+            }
+        );
+      } catch (e) {
+        console.log(e);
+      }
+    },
+    checkFormValidity() {
+      const valid = this.$refs.form.checkValidity();
+      this.nameState = valid;
+      return valid;
+    },
+    resetModal() {
+      this.name = "";
+      this.nameState = null;
+    },
+    handleOk(bvModalEvt) {
+      // Prevent modal from closing
+      bvModalEvt.preventDefault();
+      // Trigger submit handler
+      this.handleSubmit();
+    },
+    async handleSubmit() {
+      if (!this.checkFormValidity()) {
+        return false;
+      }
+      if (this.email === this.name) {
+        this.nameState = true;
+        try {
+          await axios.delete(`${this.root}api/users/${this.userId}`);
+        } catch (e) {
+          if (e.response.status === 403) {
+            this.deleteError =
+                "User deletion must be configured on this instance in order to allow user self-deletion.  Please contact an administrator for assistance.";
+            return false;
+          }
+        }
+        userLogoutClient();
+      } else {
+        this.nameState = false;
+        return false;
+      }
+    },
+  },
+};
+</script>
+
+<style scoped>
+span.bold {
+  font-weight: bold;
+}
+.pref-icon {
+  width: 3rem;
+}
+
+.setting-container {
+  display: flex;
+  flex-flow: row;
+  justify-content: space-between;
+  align-items: center;
+}
+
+.setting-container div.setting-text {
+  width: 100%;
+  margin-bottom: 32px;
+}
+
+.setting-container div.setting-buttons {
+  display: flex;
+  width: 10rem;
+}
+
+.setting-container div.setting-buttons button {
+  margin-left: auto;
+  margin-right: 0;
+}
+
+.actual-settings {
+  padding: 8px 16px;
+  margin-top: 32px;
+  margin-bottom: 32px;
+  border: 1px solid #bdc6d0;
+  border-radius: 5px;
+  background-color: rgba(0, 0, 0, 0.04);
+}
+</style>
\ No newline at end of file
diff --git a/client/src/components/User/UserPreferences.vue b/client/src/components/User/UserPreferences.vue
index aab37c9cac4..5f83d93f53d 100644
--- a/client/src/components/User/UserPreferences.vue
+++ b/client/src/components/User/UserPreferences.vue
@@ -22,6 +22,15 @@
                 </div>
             </div>
         </b-row>
+
+      <ConfigProvider v-slot="{ config }">
+        <UserBeaconSettings
+            v-if="config"
+            :root="root"
+            :user-id="userId">>
+        </UserBeaconSettings>
+      </ConfigProvider>
+
         <b-row class="ml-3 mb-1">
             <i class="pref-icon pt-1 fa fa-lg fa-plus-square-o" />
             <div class="pref-content pr-1">
@@ -65,8 +74,8 @@ import { getUserPreferencesModel } from "components/User/UserPreferencesModel";
 import ConfigProvider from "components/providers/ConfigProvider";
 import { userLogoutAll } from "utils/logout";
 import UserDeletion from "./UserDeletion";
-
 import "@fortawesome/fontawesome-svg-core";
+import UserBeaconSettings from "./UserBeaconSettings";
 
 Vue.use(BootstrapVue);
 
@@ -74,6 +83,7 @@ export default {
     components: {
         ConfigProvider,
         UserDeletion,
+        UserBeaconSettings
     },
     props: {
         userId: {
diff --git a/client/src/style/scss/overrides.scss b/client/src/style/scss/overrides.scss
index dde16959fd4..fac01f3bf2d 100644
--- a/client/src/style/scss/overrides.scss
+++ b/client/src/style/scss/overrides.scss
@@ -89,7 +89,7 @@ button {
 // Modal -- wider by default, scroll like Trello
 
 .modal-dialog {
-    width: 690px;
+    // width: 690px; // by removing this, size can be set with the "size" attribute of the bootstrap component <b-modal>
     max-width: 900px; // BS4 sets this to 500px now, so width not respected.
 }
 

From 2d0781799371a27ba7a644dc796f5e976100dd14 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 8 Aug 2022 12:14:34 +0200
Subject: [PATCH 010/350] added endpoint to retrieve beacon histories

---
 lib/galaxy/webapps/galaxy/api/histories.py | 50 ++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/lib/galaxy/webapps/galaxy/api/histories.py b/lib/galaxy/webapps/galaxy/api/histories.py
index ef6f46287af..d0575af43c3 100644
--- a/lib/galaxy/webapps/galaxy/api/histories.py
+++ b/lib/galaxy/webapps/galaxy/api/histories.py
@@ -19,6 +19,7 @@ from fastapi import (
     Response,
     status,
 )
+from sqlalchemy import and_
 from pydantic.fields import Field
 from pydantic.main import BaseModel
 
@@ -30,6 +31,11 @@ from galaxy.schema import (
     FilterQueryParams,
     SerializationParams,
 )
+from galaxy.model import (
+    User,
+    UserPreference,
+    History
+)
 from galaxy.schema.fields import DecodedDatabaseIdField
 from galaxy.schema.schema import (
     AnyHistoryView,
@@ -155,6 +161,50 @@ class FastAPIHistories:
     ) -> List[AnyHistoryView]:
         return self.service.published(trans, serialization_params, filter_query_params)
 
+    @router.get(
+        "/api/histories/beacon",
+        summary="Returns the complete list of beacon histories",
+        status_code=status.HTTP_200_OK
+    )
+    def get_beacon_users(self, trans: ProvidesUserContext = DependsOnTrans):
+        """
+        Returns IDs of all beacon histories.
+
+        A beacon history is a history that has a special name and belongs to a user that has enabled the beacon_share
+        setting.
+
+            Note:
+                 This endpoint queries histories directly. We might want to move the query to the HistoryService or
+                 HistoryManager to be more in line with the other endpoints defined by this file.
+                 However, it is not likely for any of this code to be reused anywhere else.
+        """
+
+        # Prevent non-admin users querying beacon histories
+        if not trans.user_is_admin:
+            message = "Only admins can query beacon histories"
+            raise glx_exceptions.AdminRequiredException(message)
+
+        # Query beacon histories by "beacon_enabled" setting and hard coded name "___BEACON_PICKUP___"
+        query = trans.sa_session.query(User).join(History).filter(
+            User.preferences.any(and_(UserPreference.name == "beacon_enabled", UserPreference.value == 1))).filter(
+            History.name == "___BEACON_PICKUP___")
+
+        beacon_histories = []
+        for user in query:
+            for history in user.histories:
+                # only get "user_id" and "history_id" as consumed by the beacon-import script
+                beacon_histories.append(
+                    {
+                        "user_id": trans.security.encode_id(user.id),
+                        "history_id": trans.security.encode_id(history.id)
+                    }
+                )
+                # removing this break would mean supporting an arbitrary number of beacon histories per user
+                # with this break only the first history per user is added to the response
+                break
+
+        return {"beacon_histories": beacon_histories}
+
     @router.get(
         "/api/histories/shared_with_me",
         summary="Return all histories that are shared with the current user.",

From ebe7b4efdefc86b72dae97712d428c2e561c5b47 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 9 Aug 2022 09:22:31 +0200
Subject: [PATCH 011/350] fixing some strings

---
 lib/galaxy/webapps/galaxy/api/histories.py | 2 +-
 lib/galaxy/webapps/galaxy/api/users.py     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/api/histories.py b/lib/galaxy/webapps/galaxy/api/histories.py
index d0575af43c3..363afabecbf 100644
--- a/lib/galaxy/webapps/galaxy/api/histories.py
+++ b/lib/galaxy/webapps/galaxy/api/histories.py
@@ -166,7 +166,7 @@ class FastAPIHistories:
         summary="Returns the complete list of beacon histories",
         status_code=status.HTTP_200_OK
     )
-    def get_beacon_users(self, trans: ProvidesUserContext = DependsOnTrans):
+    def get_beacon_histories(self, trans: ProvidesUserContext = DependsOnTrans):
         """
         Returns IDs of all beacon histories.
 
diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index 06dfdaad799..f7037b80370 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -1079,7 +1079,7 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
 
         enabled = user.preferences["beacon_enabled"] if "beacon_enabled" in user.preferences else False
 
-        return {"message": "benno ist ein cooler typ", "enabled": enabled}
+        return {"enabled": enabled}
 
     @expose_api
     def set_beacon(self, trans, id, payload=None, **kwd):

From 2141f9dd3569c0951709f973e387dff54f21cf3f Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Thu, 25 Aug 2022 11:51:05 +0200
Subject: [PATCH 012/350] removed beacon history endpoint

---
 lib/galaxy/webapps/galaxy/api/histories.py | 44 ----------------------
 1 file changed, 44 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/api/histories.py b/lib/galaxy/webapps/galaxy/api/histories.py
index 363afabecbf..e99dc970dc4 100644
--- a/lib/galaxy/webapps/galaxy/api/histories.py
+++ b/lib/galaxy/webapps/galaxy/api/histories.py
@@ -161,50 +161,6 @@ class FastAPIHistories:
     ) -> List[AnyHistoryView]:
         return self.service.published(trans, serialization_params, filter_query_params)
 
-    @router.get(
-        "/api/histories/beacon",
-        summary="Returns the complete list of beacon histories",
-        status_code=status.HTTP_200_OK
-    )
-    def get_beacon_histories(self, trans: ProvidesUserContext = DependsOnTrans):
-        """
-        Returns IDs of all beacon histories.
-
-        A beacon history is a history that has a special name and belongs to a user that has enabled the beacon_share
-        setting.
-
-            Note:
-                 This endpoint queries histories directly. We might want to move the query to the HistoryService or
-                 HistoryManager to be more in line with the other endpoints defined by this file.
-                 However, it is not likely for any of this code to be reused anywhere else.
-        """
-
-        # Prevent non-admin users querying beacon histories
-        if not trans.user_is_admin:
-            message = "Only admins can query beacon histories"
-            raise glx_exceptions.AdminRequiredException(message)
-
-        # Query beacon histories by "beacon_enabled" setting and hard coded name "___BEACON_PICKUP___"
-        query = trans.sa_session.query(User).join(History).filter(
-            User.preferences.any(and_(UserPreference.name == "beacon_enabled", UserPreference.value == 1))).filter(
-            History.name == "___BEACON_PICKUP___")
-
-        beacon_histories = []
-        for user in query:
-            for history in user.histories:
-                # only get "user_id" and "history_id" as consumed by the beacon-import script
-                beacon_histories.append(
-                    {
-                        "user_id": trans.security.encode_id(user.id),
-                        "history_id": trans.security.encode_id(history.id)
-                    }
-                )
-                # removing this break would mean supporting an arbitrary number of beacon histories per user
-                # with this break only the first history per user is added to the response
-                break
-
-        return {"beacon_histories": beacon_histories}
-
     @router.get(
         "/api/histories/shared_with_me",
         summary="Return all histories that are shared with the current user.",

From 5bd9212560f7dfc2365ee990526c31c7e4023ce6 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Thu, 25 Aug 2022 11:51:55 +0200
Subject: [PATCH 013/350] added admin config for beacon sharing

---
 client/src/components/User/UserPreferences.vue |  2 +-
 doc/source/admin/galaxy_options.rst            | 11 +++++++++++
 lib/galaxy/config/sample/galaxy.yml.sample     |  4 ++++
 lib/galaxy/config/schemas/config_schema.yml    |  8 ++++++++
 lib/galaxy/managers/configuration.py           |  1 +
 lib/galaxy/webapps/galaxy/api/users.py         |  1 -
 6 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/client/src/components/User/UserPreferences.vue b/client/src/components/User/UserPreferences.vue
index 5f83d93f53d..58a43dbcda0 100644
--- a/client/src/components/User/UserPreferences.vue
+++ b/client/src/components/User/UserPreferences.vue
@@ -25,7 +25,7 @@
 
       <ConfigProvider v-slot="{ config }">
         <UserBeaconSettings
-            v-if="config"
+            v-if="config && config.enable_beacon_integration"
             :root="root"
             :user-id="userId">>
         </UserBeaconSettings>
diff --git a/doc/source/admin/galaxy_options.rst b/doc/source/admin/galaxy_options.rst
index 1631bc6482f..b0d714169d4 100644
--- a/doc/source/admin/galaxy_options.rst
+++ b/doc/source/admin/galaxy_options.rst
@@ -4995,4 +4995,15 @@
 :Type: bool
 
 
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+``enable_beacon_integration``
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+:Description:
+    Enables user preferences and api endpoint for the beacon
+    integration.
+:Default: ``false``
+:Type: bool
+
+
 
diff --git a/lib/galaxy/config/sample/galaxy.yml.sample b/lib/galaxy/config/sample/galaxy.yml.sample
index c7f1ea9cd4e..04a63b99c67 100644
--- a/lib/galaxy/config/sample/galaxy.yml.sample
+++ b/lib/galaxy/config/sample/galaxy.yml.sample
@@ -2659,3 +2659,7 @@ galaxy:
   # Display built-in converters in the tool panel.
   #display_builtin_converters: true
 
+  # Enables user preferences and api endpoint for the beacon
+  # integration.
+  #enable_beacon_integration: false
+
diff --git a/lib/galaxy/config/schemas/config_schema.yml b/lib/galaxy/config/schemas/config_schema.yml
index d063a0f9777..cd574ab4eac 100644
--- a/lib/galaxy/config/schemas/config_schema.yml
+++ b/lib/galaxy/config/schemas/config_schema.yml
@@ -3631,3 +3631,11 @@ mapping:
         default: true
         required: false
         desc: Display built-in converters in the tool panel.
+
+      enable_beacon_integration:
+        type: bool
+        default: false
+        required: true
+        desc: |
+          Enables user preferences and api endpoint for the beacon integration.
+
diff --git a/lib/galaxy/managers/configuration.py b/lib/galaxy/managers/configuration.py
index c0c1c3235af..c2d2a978b7d 100644
--- a/lib/galaxy/managers/configuration.py
+++ b/lib/galaxy/managers/configuration.py
@@ -155,6 +155,7 @@ class ConfigSerializer(base.ModelSerializer):
             "matomo_site_id": _use_config,
             "enable_unique_workflow_defaults": _use_config,
             "enable_beta_markdown_export": _use_config,
+            "enable_beacon_integration": _use_config,
             "use_legacy_history": _use_config,
             "simplified_workflow_run_ui": _use_config,
             "simplified_workflow_run_ui_target_history": _use_config,
diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index f7037b80370..0f7cb84bb14 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -1086,7 +1086,6 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
         """
         POST /api/users/{id}/beacon
 
-
         :param id: the encoded id of the user
         :type  id: str
 

From e17a450a9b010765b5f0bc2b0d0a4fbf78be4df5 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Thu, 25 Aug 2022 14:51:02 +0200
Subject: [PATCH 014/350] removed unused imports

---
 lib/galaxy/webapps/galaxy/api/histories.py | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/api/histories.py b/lib/galaxy/webapps/galaxy/api/histories.py
index e99dc970dc4..ef6f46287af 100644
--- a/lib/galaxy/webapps/galaxy/api/histories.py
+++ b/lib/galaxy/webapps/galaxy/api/histories.py
@@ -19,7 +19,6 @@ from fastapi import (
     Response,
     status,
 )
-from sqlalchemy import and_
 from pydantic.fields import Field
 from pydantic.main import BaseModel
 
@@ -31,11 +30,6 @@ from galaxy.schema import (
     FilterQueryParams,
     SerializationParams,
 )
-from galaxy.model import (
-    User,
-    UserPreference,
-    History
-)
 from galaxy.schema.fields import DecodedDatabaseIdField
 from galaxy.schema.schema import (
     AnyHistoryView,

From 16e2e162c9caa640fa637ff4445d31ad01234bf1 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Fri, 30 Sep 2022 13:05:59 +0200
Subject: [PATCH 015/350] adding buttons to create and switch to history

---
 .../components/User/UserBeaconSettings.vue    | 208 ++++++++++++------
 1 file changed, 145 insertions(+), 63 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 7d2ddfdd53f..d884c2d02fd 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -15,36 +15,96 @@
           title-tag="h1"
           @show="loadSettings">
 
-        <h3>About Beacon</h3>
+        <!-- Explanation text-->
         <p>
-          A beacon is a web service that shares information about the occurrence of genetic variants.
-          A beacon answers questions of the form "Do you have information about the following mutation?" and responds with one of "Yes" or "No".
-
-          <b-link href="https://beacon-network.org/#/about">Learn more</b-link>
+          This setting will enable the possibility to share your Variants (in VCF (vcf) or compressed VCF (vcf_gz))
+          with the entire community in a secure way without sharing the entire file or Galaxy history. This is possible
+          by utilizing the <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a>.
+          <br>
+          <br>
+          We turn Galaxy into a Beacon server and offer your variants anonymously via the Beacon Network. All shared
+          Variants will be merged to a single dataset. If someone searches in the Beacon Network for a specific variant
+          that is in one of your datasets our Galaxy server will return
+          <span class="cursive">“Yes, we have seen such a variant”</span>. Nothing more.
+          <br>
+          <br>
+          The user has the possibility to contact the Admin of the Galaxy server and we will in turn contact
+          you and ask if you want to contact this user and negotiate a potential data access.
+          Sharing is essential in Galaxy, secure sharing of sensitive data is now possible using Beacon.
         </p>
 
 
-        <b-alert show>Apart from the "Yes/No" response <span class="bold">no data will be shared</span></b-alert>
-
-
-
-        <h3>Participate</h3>
-        There is a beacon instance set up on this galaxy instance. To contribute variant information follow the steps below.
-
-        <div class="actual-settings">
-          <h4>Opt-in to variant sharing</h4>
-          <div class="setting-container">
-            <div class="setting-text">
-              <p v-if="!enabled"> you are currently not opted in</p>
-              <p v-if="enabled"> you have already opted in and you can share data</p>
+        <b-alert v-if="enabled" show>
+          <div class="flex-row space-between">
+            <div class="no-shrink">
+              Beacon sharing is <span class="bold">enabled</span> for your profile
             </div>
-            <div class="setting-buttons">
-              <b-button v-if="!enabled" @click="optIn" variant="success">Opt-in</b-button>
-              <b-button v-if="enabled" @click="optOut" variant="danger">Opt-out</b-button>
+            <div class="fill"></div>
+            <div class="no-shrink">
+              <b-button @click="optOut" variant="danger">Disable</b-button>
+            </div>
+          </div>
+        </b-alert>
+
+
+        <!-- Setting to show when beacon is disabled -->
+        <b-alert v-if="!enabled" show>
+          <div class="flex-row space-between">
+            <div class="no-shrink">
+              Beacon sharing is currently <span class="bold">disabled</span> - no data will be shared
+            </div>
+            <div class="fill"></div>
+            <div>
+              <b-button @click="optIn" variant="success">Enable</b-button>
+            </div>
+          </div>
+        </b-alert>
+
+        <div v-if="enabled">
+          <p>
+            If you this setting you can share data by copying VCF/VCF.gz files to a history called
+            <span class="cursive">___BEACON_PICKUP___</span>. The Beacon database is rebuild every day, this means if
+            you disable the option here, of if we remove the history, or data in the history, the variants will disappear
+            from the Beacon in the next 24h.
+          </p>
+        </div>
+
+
+        <!-- Detailed information about the beacon history -->
+        <div v-if="enabled" class="gray-box">
+          <!-- Case: History does not exist-->
+          <div v-if="!beaconHistory.id" class="flex-row">
+            <div class="no-shrink">
+              No beacon history found
+            </div>
+            <div class="fill"></div>
+            <div class="no-shrink">
+              <b-button @click="createBeaconHistory">Create Beacon History</b-button>
+            </div>
+          </div>
+
+          <!-- Case: History exists -->
+          <div v-if="beaconHistory.id" class="flex-row">
+            <div class="no-shrink">
+              Variant files are searched in your beacon history
+            </div>
+            <div class="fill"></div>
+            <div class="no-shrink">
+              <b-button @click="switchHistory(beaconHistory.id)">Switch to History</b-button>
             </div>
           </div>
         </div>
 
+        <div v-if="enabled">
+          <p>
+            Datasets must fulfill the following conditions in order to be processed
+          </p>
+          <ul>
+            <li>must be VCF or VCF.bzip format</li>
+            <li>must have a human reference assigned to it (e.g. hg19)</li>
+            <li>must define at least one sample</li>
+          </ul>
+        </div>
       </b-modal>
     </div>
   </b-row>
@@ -54,7 +114,6 @@
 import axios from "axios";
 import Vue from "vue";
 import BootstrapVue from "bootstrap-vue";
-import { userLogoutClient } from "layout/menu";
 Vue.use(BootstrapVue);
 
 export default {
@@ -71,20 +130,53 @@ export default {
   data() {
     return {
       enabled: false,
+      beaconHistory: {}
     };
   },
-  computed: {
-    showDeleteError() {
-      return this.deleteError !== "";
-    },
+  created() {
+      this.getBeaconHistory();
   },
   methods: {
+    switchHistory: function (id) {
+      // history/switch_to_history?hist_id=
+      axios
+           .get(`${this.root}history/switch_to_history?hist_id=${id}`)
+          .then(() => {
+            window.location.reload()
+          })
+          .catch((error) => {console.log(error)});
+    },
+    getBeaconHistory: function () {
+      axios
+          .get(this.root + "api/histories?q=name&qv=___BEACON_PICKUP___")
+          .then((response) => {
+            if (response.data.length > 0) {
+              // always select first match
+              this.beaconHistory = response.data[0];
+
+            }
+          })
+          .catch((error) => {console.log(error.response)});
+    },
+    async createBeaconHistory() {
+      const annotation = "Variant files will be collected from this history if beacon sharing is activated"
+      await axios
+          .post(this.root + "api/histories", {name: "___BEACON_PICKUP___"})
+          .then((response) => {
+            this.beaconHistory = response.data
+            axios.put(`${this.root}api/histories/${this.beaconHistory.id}`, {"annotation": annotation});
+          })
+          .catch((error) => {this.errorMessages.push(error.response.data.err_msg), console.log(error.response)});
+    },
     async optIn() {
       try {
         await axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": true}).then(
             response => {
               // TODO check response
               this.loadSettings();
+              if (!this.beaconHistory.id) {
+                this.createBeaconHistory()
+              }
             }
         );
       } catch (e) {
@@ -114,42 +206,6 @@ export default {
         console.log(e);
       }
     },
-    checkFormValidity() {
-      const valid = this.$refs.form.checkValidity();
-      this.nameState = valid;
-      return valid;
-    },
-    resetModal() {
-      this.name = "";
-      this.nameState = null;
-    },
-    handleOk(bvModalEvt) {
-      // Prevent modal from closing
-      bvModalEvt.preventDefault();
-      // Trigger submit handler
-      this.handleSubmit();
-    },
-    async handleSubmit() {
-      if (!this.checkFormValidity()) {
-        return false;
-      }
-      if (this.email === this.name) {
-        this.nameState = true;
-        try {
-          await axios.delete(`${this.root}api/users/${this.userId}`);
-        } catch (e) {
-          if (e.response.status === 403) {
-            this.deleteError =
-                "User deletion must be configured on this instance in order to allow user self-deletion.  Please contact an administrator for assistance.";
-            return false;
-          }
-        }
-        userLogoutClient();
-      } else {
-        this.nameState = false;
-        return false;
-      }
-    },
   },
 };
 </script>
@@ -184,7 +240,7 @@ span.bold {
   margin-right: 0;
 }
 
-.actual-settings {
+.gray-box {
   padding: 8px 16px;
   margin-top: 32px;
   margin-bottom: 32px;
@@ -192,4 +248,30 @@ span.bold {
   border-radius: 5px;
   background-color: rgba(0, 0, 0, 0.04);
 }
+
+.flex-row {
+  display: flex;
+  flex-flow: row;
+}
+
+.space-between {
+  justify-content: space-between;
+  align-items: center;
+}
+
+.cursive {
+  font-style: italic;
+}
+
+.bold {
+  font-weight: bolder;
+}
+
+.fill {
+  width: 100%;
+}
+
+.no-shrink {
+  flex-shrink: 0;
+}
 </style>
\ No newline at end of file

From 2be18dc3343211be4a301a0d2784a0b6fe2db8f0 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Thu, 6 Oct 2022 10:33:52 +0200
Subject: [PATCH 016/350] using global store to switch history

---
 client/src/components/User/UserBeaconSettings.vue | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index d884c2d02fd..939faef1bf7 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -111,6 +111,7 @@
 </template>
 
 <script>
+import store from "store"
 import axios from "axios";
 import Vue from "vue";
 import BootstrapVue from "bootstrap-vue";
@@ -137,14 +138,9 @@ export default {
       this.getBeaconHistory();
   },
   methods: {
-    switchHistory: function (id) {
+    switchHistory: async function (historyId) {
       // history/switch_to_history?hist_id=
-      axios
-           .get(`${this.root}history/switch_to_history?hist_id=${id}`)
-          .then(() => {
-            window.location.reload()
-          })
-          .catch((error) => {console.log(error)});
+      await store.dispatch("history/setCurrentHistory", historyId);
     },
     getBeaconHistory: function () {
       axios

From a356f457a8197d5d8611d2b7c0148d629d8930e9 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Fri, 21 Oct 2022 10:55:12 +0200
Subject: [PATCH 017/350] making "enable_beacon_integration" setting optional

---
 lib/galaxy/config/schemas/config_schema.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/config/schemas/config_schema.yml b/lib/galaxy/config/schemas/config_schema.yml
index cd574ab4eac..2da75d3c7e0 100644
--- a/lib/galaxy/config/schemas/config_schema.yml
+++ b/lib/galaxy/config/schemas/config_schema.yml
@@ -3635,7 +3635,7 @@ mapping:
       enable_beacon_integration:
         type: bool
         default: false
-        required: true
+        required: false
         desc: |
           Enables user preferences and api endpoint for the beacon integration.
 

From 0ffc5d0ec2effbf7f03d5b67783ddc0bfc9e1370 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Fri, 21 Oct 2022 10:55:31 +0200
Subject: [PATCH 018/350] cleanup

---
 .../components/User/UserBeaconSettings.vue    | 60 +++++++------------
 1 file changed, 23 insertions(+), 37 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 939faef1bf7..d90df4b6167 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -1,6 +1,6 @@
 <template>
   <b-row class="ml-3 mb-1">
-    <i class="pref-icon pt-1 fa fa-lg fa-broadcast-tower" />
+    <i class="pref-icon pt-1 fa fa-lg fa-broadcast-tower"/>
     <div class="pref-content pr-1">
       <a id="beacon-settings" href="javascript:void(0)"
       ><b v-b-modal.modal-beacon v-localize>Manage Beacon</b></a
@@ -63,8 +63,10 @@
         <div v-if="enabled">
           <p>
             If you this setting you can share data by copying VCF/VCF.gz files to a history called
-            <span class="cursive">___BEACON_PICKUP___</span>. The Beacon database is rebuild every day, this means if
-            you disable the option here, of if we remove the history, or data in the history, the variants will disappear
+            <span class="cursive">{{ beaconHistoryName }}</span>. The Beacon database is rebuild every day, this means
+            if
+            you disable the option here, of if we remove the history, or data in the history, the variants will
+            disappear
             from the Beacon in the next 24h.
           </p>
         </div>
@@ -115,6 +117,7 @@ import store from "store"
 import axios from "axios";
 import Vue from "vue";
 import BootstrapVue from "bootstrap-vue";
+
 Vue.use(BootstrapVue);
 
 export default {
@@ -131,20 +134,20 @@ export default {
   data() {
     return {
       enabled: false,
+      beaconHistoryName: "___BEACON_PICKUP___",
       beaconHistory: {}
     };
   },
   created() {
-      this.getBeaconHistory();
+    this.getBeaconHistory();
   },
   methods: {
     switchHistory: async function (historyId) {
-      // history/switch_to_history?hist_id=
       await store.dispatch("history/setCurrentHistory", historyId);
     },
     getBeaconHistory: function () {
       axios
-          .get(this.root + "api/histories?q=name&qv=___BEACON_PICKUP___")
+          .get(this.root + "api/histories?q=name&qv=" + this.beaconHistoryName)
           .then((response) => {
             if (response.data.length > 0) {
               // always select first match
@@ -152,21 +155,25 @@ export default {
 
             }
           })
-          .catch((error) => {console.log(error.response)});
+          .catch((error) => {
+            console.log(error.response)
+          });
     },
-    async createBeaconHistory() {
+    createBeaconHistory() {
       const annotation = "Variant files will be collected from this history if beacon sharing is activated"
-      await axios
-          .post(this.root + "api/histories", {name: "___BEACON_PICKUP___"})
+      axios
+          .post(this.root + "api/histories", {name: this.beaconHistoryName})
           .then((response) => {
             this.beaconHistory = response.data
             axios.put(`${this.root}api/histories/${this.beaconHistory.id}`, {"annotation": annotation});
           })
-          .catch((error) => {this.errorMessages.push(error.response.data.err_msg), console.log(error.response)});
+          .catch((error) => {
+            this.errorMessages.push(error.response.data.err_msg), console.log(error.response)
+          });
     },
-    async optIn() {
+    optIn() {
       try {
-        await axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": true}).then(
+        axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": true}).then(
             response => {
               // TODO check response
               this.loadSettings();
@@ -179,9 +186,9 @@ export default {
         console.log(e);
       }
     },
-    async optOut() {
+    optOut() {
       try {
-        await axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": false}).then(
+        axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": false}).then(
             response => {
               // TODO check response
               this.loadSettings();
@@ -210,32 +217,11 @@ export default {
 span.bold {
   font-weight: bold;
 }
+
 .pref-icon {
   width: 3rem;
 }
 
-.setting-container {
-  display: flex;
-  flex-flow: row;
-  justify-content: space-between;
-  align-items: center;
-}
-
-.setting-container div.setting-text {
-  width: 100%;
-  margin-bottom: 32px;
-}
-
-.setting-container div.setting-buttons {
-  display: flex;
-  width: 10rem;
-}
-
-.setting-container div.setting-buttons button {
-  margin-left: auto;
-  margin-right: 0;
-}
-
 .gray-box {
   padding: 8px 16px;
   margin-top: 32px;

From 8419c688a89c60502263e1614cf6a39694d54d69 Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 11:37:37 +0200
Subject: [PATCH 019/350] fixed spelling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: David López <46503462+davelopez@users.noreply.github.com>
---
 client/src/components/User/UserBeaconSettings.vue | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index d90df4b6167..66a0c4209d2 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -62,12 +62,12 @@
 
         <div v-if="enabled">
           <p>
-            If you this setting you can share data by copying VCF/VCF.gz files to a history called
-            <span class="cursive">{{ beaconHistoryName }}</span>. The Beacon database is rebuild every day, this means
-            if
-            you disable the option here, of if we remove the history, or data in the history, the variants will
+            If you enable this setting you can share data by copying VCF/VCF.gz files to a history called
+            <span class="cursive">{{ beaconHistoryName }}</span>. The Beacon database is rebuilt every day, which means
+            that if
+            you disable the option here, or if you remove the history or data in the history, the variants will
             disappear
-            from the Beacon in the next 24h.
+            from the Beacon within the next 24h.
           </p>
         </div>
 

From 3ddc7c7bf420e247e7259d2a5344ff857183646c Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 11:38:03 +0200
Subject: [PATCH 020/350] text improvement

Co-authored-by: Wolfgang Maier <maierw@posteo.de>
---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 66a0c4209d2..1e1f7f8acfc 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -104,7 +104,7 @@
           <ul>
             <li>must be VCF or VCF.bzip format</li>
             <li>must have a human reference assigned to it (e.g. hg19)</li>
-            <li>must define at least one sample</li>
+            <li>must define at least one sample in a dedicated genotype column</li>
           </ul>
         </div>
       </b-modal>

From a956a66c449e5f10427eedbbd8e9055ed6b37258 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 12:01:52 +0200
Subject: [PATCH 021/350] moving getBeaconHistory to modal open hook

---
 client/src/components/User/UserBeaconSettings.vue | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 1e1f7f8acfc..c62f737a051 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -13,7 +13,7 @@
           ok-only
           title="Manage Beacon"
           title-tag="h1"
-          @show="loadSettings">
+          @show="onOpenModal">
 
         <!-- Explanation text-->
         <p>
@@ -138,9 +138,6 @@ export default {
       beaconHistory: {}
     };
   },
-  created() {
-    this.getBeaconHistory();
-  },
   methods: {
     switchHistory: async function (historyId) {
       await store.dispatch("history/setCurrentHistory", historyId);
@@ -198,6 +195,10 @@ export default {
         console.log(e);
       }
     },
+    onOpenModal() {
+      this.loadSettings();
+      this.getBeaconHistory();
+    },
     async loadSettings() {
       try {
         await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(

From 095ade1a812eeb0543dbd36748e78876dea9ce95 Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 12:09:04 +0200
Subject: [PATCH 022/350] Update doc/source/admin/galaxy_options.rst

Co-authored-by: Wolfgang Maier <maierw@posteo.de>
---
 doc/source/admin/galaxy_options.rst | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/doc/source/admin/galaxy_options.rst b/doc/source/admin/galaxy_options.rst
index b0d714169d4..82144530c0d 100644
--- a/doc/source/admin/galaxy_options.rst
+++ b/doc/source/admin/galaxy_options.rst
@@ -5000,8 +5000,7 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 :Description:
-    Enables user preferences and api endpoint for the beacon
-    integration.
+    Enables user preferences and api endpoint for the beacon integration.
 :Default: ``false``
 :Type: bool
 

From 814bfdb44ca99641309030d9b0af894d299fd14f Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 12:09:25 +0200
Subject: [PATCH 023/350] typo

Co-authored-by: Wolfgang Maier <maierw@posteo.de>
---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index c62f737a051..ebd476afc15 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -102,7 +102,7 @@
             Datasets must fulfill the following conditions in order to be processed
           </p>
           <ul>
-            <li>must be VCF or VCF.bzip format</li>
+            <li>must be VCF or VCF.bgzip format</li>
             <li>must have a human reference assigned to it (e.g. hg19)</li>
             <li>must define at least one sample in a dedicated genotype column</li>
           </ul>

From 6cb062a1a2bf42887cc64d7613f77874ceb4febc Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Tue, 25 Oct 2022 12:09:42 +0200
Subject: [PATCH 024/350] Update
 client/src/components/User/UserBeaconSettings.vue

Co-authored-by: Wolfgang Maier <maierw@posteo.de>
---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index ebd476afc15..81864f4ea7e 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -157,7 +157,7 @@ export default {
           });
     },
     createBeaconHistory() {
-      const annotation = "Variant files will be collected from this history if beacon sharing is activated"
+      const annotation = "Variants will be collected from VCF datasets in this history if beacon sharing is activated"
       axios
           .post(this.root + "api/histories", {name: this.beaconHistoryName})
           .then((response) => {

From d769323fa03cec879d86b3ce3fa13ad308189f0f Mon Sep 17 00:00:00 2001
From: Paprikant <benno.weiss@gmail.com>
Date: Wed, 26 Oct 2022 10:21:58 +0200
Subject: [PATCH 025/350] Update
 client/src/components/User/UserBeaconSettings.vue

Co-authored-by: Wolfgang Maier <maierw@posteo.de>
---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 81864f4ea7e..c00ed4ea86f 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -88,7 +88,7 @@
           <!-- Case: History exists -->
           <div v-if="beaconHistory.id" class="flex-row">
             <div class="no-shrink">
-              Variant files are searched in your beacon history
+              Variant data to share gets discovered from your beacon history
             </div>
             <div class="fill"></div>
             <div class="no-shrink">

From d5e9b7e0543113c5a8100b6c1df4b732b11f5c13 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 26 Oct 2022 12:15:22 +0200
Subject: [PATCH 026/350] text rewritten

---
 .../components/User/UserBeaconSettings.vue    | 39 ++++++++++---------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index c00ed4ea86f..2437c470496 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -15,25 +15,26 @@
           title-tag="h1"
           @show="onOpenModal">
 
+
         <!-- Explanation text-->
         <p>
-          This setting will enable the possibility to share your Variants (in VCF (vcf) or compressed VCF (vcf_gz))
-          with the entire community in a secure way without sharing the entire file or Galaxy history. This is possible
-          by utilizing the <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a>.
+          The <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables safe
+          sharing of human genetic variants.<br>
           <br>
+          Galaxy lets you use the Beacon protocol to share genetic variants directly from your analysis with the scientific
+          community in the following anonymous way:<br>
           <br>
-          We turn Galaxy into a Beacon server and offer your variants anonymously via the Beacon Network. All shared
-          Variants will be merged to a single dataset. If someone searches in the Beacon Network for a specific variant
-          that is in one of your datasets our Galaxy server will return
-          <span class="cursive">“Yes, we have seen such a variant”</span>. Nothing more.
+          For participating users, we will merge variant lists to be shared into a single Beacon dataset and make that
+          dataset accessible through a Beacon server.<br>
+          If someone queries the server for a specific variant that is in our Beacon dataset, the server will reply with
+          <span class="cursive">“Yes, we have seen such a variant”</span>. Nothing more.<br>
           <br>
-          <br>
-          The user has the possibility to contact the Admin of the Galaxy server and we will in turn contact
-          you and ask if you want to contact this user and negotiate a potential data access.
-          Sharing is essential in Galaxy, secure sharing of sensitive data is now possible using Beacon.
+          The user that issued the query then has the possibility to contact a Galaxy server admin who can link the
+          variant call in question to particular Galaxy users. If you are among the users that shared the variant, the
+          admin will, in turn, contact you and ask if you want to contact the user that initiated the query to negotiate
+          further information exchange or data access.
         </p>
 
-
         <b-alert v-if="enabled" show>
           <div class="flex-row space-between">
             <div class="no-shrink">
@@ -62,12 +63,12 @@
 
         <div v-if="enabled">
           <p>
-            If you enable this setting you can share data by copying VCF/VCF.gz files to a history called
-            <span class="cursive">{{ beaconHistoryName }}</span>. The Beacon database is rebuilt every day, which means
-            that if
-            you disable the option here, or if you remove the history or data in the history, the variants will
-            disappear
-            from the Beacon within the next 24h.
+            You can share data by copying VCF or VCF.bgzip files to a history called
+            <span class="cursive">{{ beaconHistoryName }}</span>. <br>
+            <br>
+            The Beacon database is rebuilt periodically. Therefore, changes do not go into effect immediately.
+            If you disable beacon sharing or remove a dataset from the beacon history, the corresponding variants will
+            disappear from the beacon dataset during the next rebuild.
           </p>
         </div>
 
@@ -105,6 +106,8 @@
             <li>must be VCF or VCF.bgzip format</li>
             <li>must have a human reference assigned to it (e.g. hg19)</li>
             <li>must define at least one sample in a dedicated genotype column</li>
+            <li>must contain the info field <span class="cursive">AC</span>, with the total
+              number of alternate alleles in called genotypes</li>
           </ul>
         </div>
       </b-modal>

From ad0d732821db0cfb18b2919bedabfa0f54a86d25 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 26 Oct 2022 13:13:36 +0200
Subject: [PATCH 027/350] ran "make format"

---
 lib/galaxy/webapps/galaxy/api/users.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index 0f7cb84bb14..f7dcd306f21 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -1100,4 +1100,4 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
             trans.sa_session.flush()
             return {"message": "setting enabled..."}
 
-        return {"message": payload}
\ No newline at end of file
+        return {"message": payload}

From 2c6c8e88014a877fa4e73040b048583137afeecb Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Sun, 6 Nov 2022 10:31:40 +0100
Subject: [PATCH 028/350] reverting to fixed modal width

---
 client/src/style/scss/overrides.scss | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/style/scss/overrides.scss b/client/src/style/scss/overrides.scss
index fac01f3bf2d..dde16959fd4 100644
--- a/client/src/style/scss/overrides.scss
+++ b/client/src/style/scss/overrides.scss
@@ -89,7 +89,7 @@ button {
 // Modal -- wider by default, scroll like Trello
 
 .modal-dialog {
-    // width: 690px; // by removing this, size can be set with the "size" attribute of the bootstrap component <b-modal>
+    width: 690px;
     max-width: 900px; // BS4 sets this to 500px now, so width not respected.
 }
 

From 0c101c290346061382c5efcbcf69193f11e9281c Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 7 Nov 2022 10:16:41 +0100
Subject: [PATCH 029/350] changed modal to display all beacon histories

---
 .../components/User/UserBeaconSettings.vue    | 56 ++++++++++++-------
 1 file changed, 37 insertions(+), 19 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 2437c470496..d7ecd04efca 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -21,7 +21,8 @@
           The <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables safe
           sharing of human genetic variants.<br>
           <br>
-          Galaxy lets you use the Beacon protocol to share genetic variants directly from your analysis with the scientific
+          Galaxy lets you use the Beacon protocol to share genetic variants directly from your analysis with the
+          scientific
           community in the following anonymous way:<br>
           <br>
           For participating users, we will merge variant lists to be shared into a single Beacon dataset and make that
@@ -76,7 +77,7 @@
         <!-- Detailed information about the beacon history -->
         <div v-if="enabled" class="gray-box">
           <!-- Case: History does not exist-->
-          <div v-if="!beaconHistory.id" class="flex-row">
+          <div v-if="beaconHistories.length < 1" class="flex-row">
             <div class="no-shrink">
               No beacon history found
             </div>
@@ -87,9 +88,10 @@
           </div>
 
           <!-- Case: History exists -->
-          <div v-if="beaconHistory.id" class="flex-row">
+          <div v-for="beaconHistory in beaconHistories" :key="beaconHistory.id" class="flex-row history-entry"
+               :class="{'gray-border-bottom': beaconHistory.id !== beaconHistories[beaconHistories.length-1].id}">
             <div class="no-shrink">
-              Variant data to share gets discovered from your beacon history
+              History with {{ beaconHistory.contents.length }} datasets
             </div>
             <div class="fill"></div>
             <div class="no-shrink">
@@ -107,7 +109,8 @@
             <li>must have a human reference assigned to it (e.g. hg19)</li>
             <li>must define at least one sample in a dedicated genotype column</li>
             <li>must contain the info field <span class="cursive">AC</span>, with the total
-              number of alternate alleles in called genotypes</li>
+              number of alternate alleles in called genotypes
+            </li>
           </ul>
         </div>
       </b-modal>
@@ -138,34 +141,41 @@ export default {
     return {
       enabled: false,
       beaconHistoryName: "___BEACON_PICKUP___",
-      beaconHistory: {}
+      beaconHistories: [{}]
     };
   },
   methods: {
     switchHistory: async function (historyId) {
       await store.dispatch("history/setCurrentHistory", historyId);
     },
-    getBeaconHistory: function () {
+    getBeaconHistories: function () {
       axios
-          .get(this.root + "api/histories?q=name&qv=" + this.beaconHistoryName)
+          .get(this.root + "api/histories?&keys=id,contents&q=name&qv=" + this.beaconHistoryName)
           .then((response) => {
-            if (response.data.length > 0) {
-              // always select first match
-              this.beaconHistory = response.data[0];
-
-            }
+            this.beaconHistories = this.removeDeletedContents(response.data)
           })
           .catch((error) => {
             console.log(error.response)
           });
     },
-    createBeaconHistory() {
+    removeDeletedContents: function (beaconHistories) {
+      beaconHistories.forEach(
+          beaconHistory => {
+            beaconHistory.contents.splice(0, beaconHistory.contents.length, ...beaconHistory.contents.filter(
+                dataset => {
+                  return !dataset.deleted
+                }
+            ))
+          }
+      )
+      return beaconHistories
+    },
+    createBeaconHistory: function () {
       const annotation = "Variants will be collected from VCF datasets in this history if beacon sharing is activated"
       axios
           .post(this.root + "api/histories", {name: this.beaconHistoryName})
           .then((response) => {
-            this.beaconHistory = response.data
-            axios.put(`${this.root}api/histories/${this.beaconHistory.id}`, {"annotation": annotation});
+            axios.put(`${this.root}api/histories/${response.data.id}`, {"annotation": annotation});
           })
           .catch((error) => {
             this.errorMessages.push(error.response.data.err_msg), console.log(error.response)
@@ -177,8 +187,9 @@ export default {
             response => {
               // TODO check response
               this.loadSettings();
-              if (!this.beaconHistory.id) {
+              if (this.beaconHistories.length < 1) {
                 this.createBeaconHistory()
+                this.getBeaconHistories()
               }
             }
         );
@@ -200,7 +211,7 @@ export default {
     },
     onOpenModal() {
       this.loadSettings();
-      this.getBeaconHistory();
+      this.getBeaconHistories();
     },
     async loadSettings() {
       try {
@@ -227,7 +238,6 @@ span.bold {
 }
 
 .gray-box {
-  padding: 8px 16px;
   margin-top: 32px;
   margin-bottom: 32px;
   border: 1px solid #bdc6d0;
@@ -240,6 +250,14 @@ span.bold {
   flex-flow: row;
 }
 
+.history-entry {
+  padding: 8px;
+}
+
+.gray-border-bottom {
+  border-bottom: 1px solid #bdc6d0;
+}
+
 .space-between {
   justify-content: space-between;
   align-items: center;

From 45079c90041ec0eccbec6bd5b5c8adbe3312a211 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 7 Nov 2022 10:24:25 +0100
Subject: [PATCH 030/350] changed modal text to remove a factually untrue
 statement

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index d7ecd04efca..61befe82cc5 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -28,7 +28,7 @@
           For participating users, we will merge variant lists to be shared into a single Beacon dataset and make that
           dataset accessible through a Beacon server.<br>
           If someone queries the server for a specific variant that is in our Beacon dataset, the server will reply with
-          <span class="cursive">“Yes, we have seen such a variant”</span>. Nothing more.<br>
+          <span class="cursive">“Yes, we have seen such a variant”</span>.<br>
           <br>
           The user that issued the query then has the possibility to contact a Galaxy server admin who can link the
           variant call in question to particular Galaxy users. If you are among the users that shared the variant, the

From ef3f1569fa09ba2fe52a2739fa077a9aa8334250 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 7 Nov 2022 13:10:33 +0100
Subject: [PATCH 031/350] changing beacon history name

---
 .../components/User/UserBeaconSettings.vue    | 22 +++++++++++--------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 61befe82cc5..60b8e09c909 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -17,7 +17,7 @@
 
 
         <!-- Explanation text-->
-        <p>
+        <p>AAAA
           The <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables safe
           sharing of human genetic variants.<br>
           <br>
@@ -25,8 +25,8 @@
           scientific
           community in the following anonymous way:<br>
           <br>
-          For participating users, we will merge variant lists to be shared into a single Beacon dataset and make that
-          dataset accessible through a Beacon server.<br>
+          For participating users, we will merge variant lists to be shared into a single Beacon dataset per reference
+          genome and make that dataset accessible through a Beacon server.<br>
           If someone queries the server for a specific variant that is in our Beacon dataset, the server will reply with
           <span class="cursive">“Yes, we have seen such a variant”</span>.<br>
           <br>
@@ -65,7 +65,7 @@
         <div v-if="enabled">
           <p>
             You can share data by copying VCF or VCF.bgzip files to a history called
-            <span class="cursive">{{ beaconHistoryName }}</span>. <br>
+            <span class="cursive gray-background">{{ beaconHistoryName }}</span>. <br>
             <br>
             The Beacon database is rebuilt periodically. Therefore, changes do not go into effect immediately.
             If you disable beacon sharing or remove a dataset from the beacon history, the corresponding variants will
@@ -77,7 +77,7 @@
         <!-- Detailed information about the beacon history -->
         <div v-if="enabled" class="gray-box">
           <!-- Case: History does not exist-->
-          <div v-if="beaconHistories.length < 1" class="flex-row">
+          <div v-if="beaconHistories.length < 1" class="flex-row history-entry">
             <div class="no-shrink">
               No beacon history found
             </div>
@@ -90,7 +90,7 @@
           <!-- Case: History exists -->
           <div v-for="beaconHistory in beaconHistories" :key="beaconHistory.id" class="flex-row history-entry"
                :class="{'gray-border-bottom': beaconHistory.id !== beaconHistories[beaconHistories.length-1].id}">
-            <div class="no-shrink">
+            <div class="no-shrink" v-if="beaconHistory.contents">
               History with {{ beaconHistory.contents.length }} datasets
             </div>
             <div class="fill"></div>
@@ -140,7 +140,7 @@ export default {
   data() {
     return {
       enabled: false,
-      beaconHistoryName: "___BEACON_PICKUP___",
+      beaconHistoryName: "Beacon Export 📡",
       beaconHistories: [{}]
     };
   },
@@ -150,7 +150,7 @@ export default {
     },
     getBeaconHistories: function () {
       axios
-          .get(this.root + "api/histories?&keys=id,contents&q=name&qv=" + this.beaconHistoryName)
+          .get(this.root + "api/histories?&keys=id,contents&q=name&qv=" + encodeURI(this.beaconHistoryName))
           .then((response) => {
             this.beaconHistories = this.removeDeletedContents(response.data)
           })
@@ -175,7 +175,11 @@ export default {
       axios
           .post(this.root + "api/histories", {name: this.beaconHistoryName})
           .then((response) => {
-            axios.put(`${this.root}api/histories/${response.data.id}`, {"annotation": annotation});
+            axios.put(`${this.root}api/histories/${response.data.id}`, {"annotation": annotation}).then(
+                () => {
+                  this.getBeaconHistories()
+                }
+            );
           })
           .catch((error) => {
             this.errorMessages.push(error.response.data.err_msg), console.log(error.response)

From c761ff1e20f830d6845b069056e3b78b6607a2f8 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 7 Nov 2022 13:11:44 +0100
Subject: [PATCH 032/350] removing typo

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 60b8e09c909..d04ebf47435 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -17,7 +17,7 @@
 
 
         <!-- Explanation text-->
-        <p>AAAA
+        <p>
           The <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables safe
           sharing of human genetic variants.<br>
           <br>

From 4eead3f2183c4c6f8453510d0d2c625a0994ace7 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Mon, 7 Nov 2022 23:38:49 +0100
Subject: [PATCH 033/350] comparing to boolean true

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index d04ebf47435..b5057d84766 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -221,7 +221,7 @@ export default {
       try {
         await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
             response => {
-              this.enabled = response.data.enabled == 1;
+              this.enabled = response.data.enabled == true;
             }
         );
       } catch (e) {

From 2468329c84c83a069b5116376103ce997db67a39 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 9 Nov 2022 13:01:44 +0100
Subject: [PATCH 034/350] hotfix: allowing string "true" as well as boolean
 values

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index b5057d84766..b37ec23c408 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -221,7 +221,7 @@ export default {
       try {
         await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
             response => {
-              this.enabled = response.data.enabled == true;
+              this.enabled = response.data.enabled == true || response.data.enabled == "true" ;
             }
         );
       } catch (e) {

From f6ce66063210e133375cf18cc4b203a509e6c99e Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 9 Nov 2022 13:02:34 +0100
Subject: [PATCH 035/350] hotfix: allowing string "true" as well as boolean
 values

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index b37ec23c408..96a98be38e9 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -221,7 +221,7 @@ export default {
       try {
         await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
             response => {
-              this.enabled = response.data.enabled == true || response.data.enabled == "true" ;
+              this.enabled = response.data.enabled == true || response.data.enabled == "true";
             }
         );
       } catch (e) {

From e414cd79b91209a246aa619b0965a82a29448dd7 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 9 Nov 2022 23:02:19 +0100
Subject: [PATCH 036/350] ensure proper boolean values are returned

---
 client/src/components/User/UserBeaconSettings.vue | 2 +-
 lib/galaxy/webapps/galaxy/api/users.py            | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 96a98be38e9..8c024f7bc11 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -221,7 +221,7 @@ export default {
       try {
         await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
             response => {
-              this.enabled = response.data.enabled == true || response.data.enabled == "true";
+              this.enabled = response.data.enabled;
             }
         );
       } catch (e) {
diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index f7dcd306f21..c2b499921a5 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -45,6 +45,7 @@ from galaxy.tool_util.toolbox.filters import FilterFactory
 from galaxy.util import (
     docstring_trim,
     listify,
+    string_as_bool
 )
 from galaxy.web import (
     expose_api,
@@ -1077,7 +1078,7 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
         """
         user = self._get_user(trans, id)
 
-        enabled = user.preferences["beacon_enabled"] if "beacon_enabled" in user.preferences else False
+        enabled = string_as_bool(user.preferences["beacon_enabled"]) if "beacon_enabled" in user.preferences else False
 
         return {"enabled": enabled}
 

From 9865c2a4470f4f82a41b20df3998cced4eef6049 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 7 Dec 2022 12:09:53 +0100
Subject: [PATCH 037/350] migrate endpoints to fastapi and add tests

---
 lib/galaxy/schema/schema.py            |  8 +++
 lib/galaxy/webapps/galaxy/api/users.py | 72 +++++++++++++-------------
 lib/galaxy/webapps/galaxy/buildapp.py  | 16 ------
 lib/galaxy_test/api/test_users.py      | 19 +++++++
 4 files changed, 62 insertions(+), 53 deletions(-)

diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index c0cd7cef856..f252182492f 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -3016,6 +3016,14 @@ class UserEmail(Model):
     )
 
 
+class UserBeaconSetting(Model):
+    enabled: bool = Field(
+        ...,
+        title="Enabled",
+        description="True if beacon sharing is enabled",
+    )
+
+
 class SharingStatus(Model):
     id: DecodedDatabaseIdField = Field(
         ...,
diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index c2b499921a5..29a7fb10406 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -5,8 +5,10 @@ import copy
 import json
 import logging
 import re
+from typing import Any
 
 from fastapi import (
+    Body,
     Path,
     Response,
     status,
@@ -35,6 +37,7 @@ from galaxy.model import (
 )
 from galaxy.schema import APIKeyModel
 from galaxy.schema.fields import DecodedDatabaseIdField
+from galaxy.schema.schema import UserBeaconSetting
 from galaxy.security.validate_user_input import (
     validate_email,
     validate_password,
@@ -45,7 +48,6 @@ from galaxy.tool_util.toolbox.filters import FilterFactory
 from galaxy.util import (
     docstring_trim,
     listify,
-    string_as_bool
 )
 from galaxy.web import (
     expose_api,
@@ -139,6 +141,38 @@ class FastAPIHistories:
         self.service.delete_api_key(trans, user_id)
         return Response(status_code=status.HTTP_204_NO_CONTENT)
 
+    @router.get(
+        "/api/users/{user_id}/beacon",
+        summary="Returns information about beacon share settings",
+    )
+    def get_beacon(
+        self,
+        trans: ProvidesUserContext = DependsOnTrans,
+        user_id: DecodedDatabaseIdField = UserIdPathParam,
+    ) -> UserBeaconSetting:
+        user = self.service._get_user(trans, user_id)
+
+        enabled = user.preferences["beacon_enabled"] if "beacon_enabled" in user.preferences else False
+
+        return UserBeaconSetting(enabled=enabled)
+
+    @router.post(
+        "/api/users/{user_id}/beacon",
+        summary="Changes beacon setting",
+    )
+    def set_beacon(
+        self,
+        trans: ProvidesUserContext = DependsOnTrans,
+        user_id: DecodedDatabaseIdField = UserIdPathParam,
+        payload: UserBeaconSetting = Body(...),
+    ) -> UserBeaconSetting:
+        user = self.service._get_user(trans, user_id)
+
+        user.preferences["beacon_enabled"] = payload.enabled
+        trans.sa_session.flush()
+
+        return payload
+
 
 class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController, UsesFormDefinitionsMixin):
     user_manager: users.UserManager = depends(users.UserManager)
@@ -1066,39 +1100,3 @@ class UserAPIController(BaseGalaxyAPIController, UsesTagsMixin, BaseUIController
         if user != trans.user and not trans.user_is_admin:
             raise exceptions.InsufficientPermissionsException("Access denied.")
         return user
-
-    @expose_api
-    def get_beacon(self, trans, id, payload=None, **kwd):
-        """
-        GET /api/users/{id}/beacon
-        Returns information about beacon share settings
-
-        :param id: the encoded id of the user
-        :type  id: str
-        """
-        user = self._get_user(trans, id)
-
-        enabled = string_as_bool(user.preferences["beacon_enabled"]) if "beacon_enabled" in user.preferences else False
-
-        return {"enabled": enabled}
-
-    @expose_api
-    def set_beacon(self, trans, id, payload=None, **kwd):
-        """
-        POST /api/users/{id}/beacon
-
-        :param id: the encoded id of the user
-        :type  id: str
-
-        :param payload: settings to persist
-        :type  payload: dict
-        """
-        payload = payload or {}
-        user = self._get_user(trans, id)
-
-        if "enabled" in payload:
-            user.preferences["beacon_enabled"] = payload["enabled"]
-            trans.sa_session.flush()
-            return {"message": "setting enabled..."}
-
-        return {"message": payload}
diff --git a/lib/galaxy/webapps/galaxy/buildapp.py b/lib/galaxy/webapps/galaxy/buildapp.py
index 8bdf8c2c899..8c8ba0fe7cc 100644
--- a/lib/galaxy/webapps/galaxy/buildapp.py
+++ b/lib/galaxy/webapps/galaxy/buildapp.py
@@ -914,22 +914,6 @@ def populate_api_routes(webapp, app):
         conditions=dict(method=["DELETE"]),
     )
 
-    webapp.mapper.connect(
-        "get_beacon",
-        "/api/users/{id}/beacon",
-        controller="users",
-        action="get_beacon",
-        conditions=dict(method=["GET"]),
-    )
-
-    webapp.mapper.connect(
-        "set_beacon",
-        "/api/users/{id}/beacon",
-        controller="users",
-        action="set_beacon",
-        conditions=dict(method=["POST"]),
-    )
-
     # ========================
     # ===== WEBHOOKS API =====
     # ========================
diff --git a/lib/galaxy_test/api/test_users.py b/lib/galaxy_test/api/test_users.py
index 5701521921d..7f1ccba8bdf 100644
--- a/lib/galaxy_test/api/test_users.py
+++ b/lib/galaxy_test/api/test_users.py
@@ -233,3 +233,22 @@ class TestUsersApi(ApiTestCase):
         users = users_response.json()
         assert len(users) == 1
         return users[0]["id"]
+
+
+    def test_manage_beacon_settings(self):
+        user_id = self._get_current_user_id()
+
+        # Assert that beacon sharing is initially disabled
+        response = self._get(f"users/{user_id}/beacon")
+        user_beacon_settings = response.json()
+        assert not user_beacon_settings["enabled"]
+
+        # Check if post request is successful
+        response = self._post(f"users/{user_id}/beacon", data={"enabled": True}, json=True)
+        user_beacon_settings = response.json()
+        assert user_beacon_settings["enabled"]
+
+        # Check if the setting has been persisted
+        response = self._get(f"users/{user_id}/beacon")
+        user_beacon_settings = response.json()
+        assert user_beacon_settings["enabled"]
\ No newline at end of file

From 199f0362df54a6203f8955602957bf3fa621aaf2 Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Wed, 7 Dec 2022 12:30:30 +0100
Subject: [PATCH 038/350] make format

---
 lib/galaxy_test/api/test_users.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/lib/galaxy_test/api/test_users.py b/lib/galaxy_test/api/test_users.py
index 7f1ccba8bdf..fc17dea745a 100644
--- a/lib/galaxy_test/api/test_users.py
+++ b/lib/galaxy_test/api/test_users.py
@@ -234,7 +234,6 @@ class TestUsersApi(ApiTestCase):
         assert len(users) == 1
         return users[0]["id"]
 
-
     def test_manage_beacon_settings(self):
         user_id = self._get_current_user_id()
 
@@ -251,4 +250,4 @@ class TestUsersApi(ApiTestCase):
         # Check if the setting has been persisted
         response = self._get(f"users/{user_id}/beacon")
         user_beacon_settings = response.json()
-        assert user_beacon_settings["enabled"]
\ No newline at end of file
+        assert user_beacon_settings["enabled"]

From a09dc2bcd4dda963c30b251f86ede7ac3510e03c Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Sun, 11 Dec 2022 13:36:25 +0100
Subject: [PATCH 039/350] Revert "temporarily add test-data"

This reverts commit eb883e2f814631b44a9f8634de25026aa7cba24f.
---
 test-data/2.tabix                                 | Bin 247 -> 0 bytes
 test-data/droPer1.tabix                           | Bin 133 -> 0 bytes
 .../tabix_filter_by_feature_count_out2.tabix      | Bin 121 -> 0 bytes
 test-data/tabix_to_maf_in.tabix                   | Bin 148 -> 0 bytes
 test-data/vcf_bgzip_to_maf_in.vcf_bgzip           | Bin 717 -> 0 bytes
 5 files changed, 0 insertions(+), 0 deletions(-)
 delete mode 100644 test-data/2.tabix
 delete mode 100644 test-data/droPer1.tabix
 delete mode 100644 test-data/tabix_filter_by_feature_count_out2.tabix
 delete mode 100644 test-data/tabix_to_maf_in.tabix
 delete mode 100644 test-data/vcf_bgzip_to_maf_in.vcf_bgzip

diff --git a/test-data/2.tabix b/test-data/2.tabix
deleted file mode 100644
index 4f60dc49158739aa6df92a4f94f9df1120af2c6e..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 247
zcmb2|=3rp}f&Xj_PR>jW%NgFD-pJb&Ai{d#x2al~-a=!GhPh#4B413d^c>RR@i?Te
zXux>X@~HN^-P?cGczcFUikTEM+2;D2X-i(WmsS3`zje#ZX}_gkf0$vvsl1*QY&6-#
zgEeUlvs5w}{xdMhqq)<F;q5^~Mxe=u6n-x^J0_O^v&4k2qAp_kPDM;D(hSTnMGOGy
COgoDJ

diff --git a/test-data/droPer1.tabix b/test-data/droPer1.tabix
deleted file mode 100644
index 80aab7c82d91950376e8517485d5eeedbd2c4d9a..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 133
zcmb2|=3rp}f&Xj_PR>jW84TQopHfm%5<nmY2on;LfH*B7At0@Rfsc)??a`&CD~l?e
zH&iSTU}jckX1d|<Qenjo-WWAmpDN#`87CXm`m~N6IB?X#Hlg_#J42Cu-HInb^X1Vj
Ll4f8A+Y2H96c{Hg

diff --git a/test-data/tabix_filter_by_feature_count_out2.tabix b/test-data/tabix_filter_by_feature_count_out2.tabix
deleted file mode 100644
index f750c2687772e13368cb66a9b83ef613b3c5f045..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 121
zcmb2|=3rp}f&Xj_PR>jWF$}S%HVQg8Ft}VSZ&zEQrD&*rt<iy*sdUASo@5LAn{)SD
z^J}uqY>?vJb=x#z+g9<3Np^eR2rfIk_5a@$OMZPZoA$GSiI?T>nu$O&<<Sh6W?%-}
G1tI{PCMFO7

diff --git a/test-data/tabix_to_maf_in.tabix b/test-data/tabix_to_maf_in.tabix
deleted file mode 100644
index 7674eb69a8858d970af4c7cb1d9be6ee368dc3e8..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 148
zcmb2|=3rp}f&Xj_PR>jW<qX_~pHfm%5)u-U5)v9N@&Li9fLSve8xNjnXq*b9f;kqY
z7>4vR7`J?D>N@;`)!?J2z~h8hk`mLJBiHb(SirtYe%X7~Df5^_+dn4$s@<?-VZs!-
fr4wIF7rA7>z;Ivk)m(XI1_pUFd!-qGf=~be)!Q<N

diff --git a/test-data/vcf_bgzip_to_maf_in.vcf_bgzip b/test-data/vcf_bgzip_to_maf_in.vcf_bgzip
deleted file mode 100644
index 90e7977846afeb7248389beea4c0665644b76875..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 717
zcmV;;0y6y{iwFb&00000{{{d;LjnM>0%eg~Z=)~}g`X$C0tM}xn~ZG?i6b6pDI`*x
z=E8QL-PBExxD}kPD)q;&$dzuN%-}Qg%{jL1w=~mlWt}VIKi@?ke87A5;b*9f_8H<B
zM<{x>-IV)!qy7AImREbDOj;I;y4=<(f93<)v+Y{H=~@>X?NdaIby4QJS)^HMZsvEl
zGw$|myV|KHEw+B8YLlw0XWO%R^yJUigpyfd^j6oTKi}ssy0*$UYpwDs(~b2fH9IR*
zM)l7f;iB7-ltyJ%s4KI(D1wOGP!eUOGNd15na;Eo)%ty}i_Pa%6%b0+rcR43=?BF|
zH>OsZb<|&Jw**O)sV(WhzO3g9E7$Fc%`UBo^|DX1SBtXoMLuO0`BYVps$!jnRu#=2
zlKYkaPLcGNdzGc;(|XZa`PZV@xo-rL{)28B%j{HP3H;TD(wsussSj<vo<fP9R*ymA
z$4SRd`vm5*(%t)IH@36DI_=OAe$RKM)$29hlVrLi>?)b6D*J!f-E{Tz2#cpR%tBb*
zM-V(Du>2i7z|kPIX~A(E%mYM3dOF$Z<UNK!9qu92jf=uz!h;wBU}Hd-uYEoV7d~|+
zLFD5=Ov2mAltG-xcqzk$oGt;sP&y+?rJzJmpvQ7_E{9Y)Tnc$Z$qhZgJkAjYkU#(&
z-f4$Ij})ZdPr_JoDMmyf;1_Mbr7H*r9HMmE`Z}LdbjR+&j)PnX2p}d2xZcqaJD~80
z;+zv4xUM$|0za9Ax8K0@i%CYMD;X!u1NKEFlPKwkFknL_xsXl=%s4Xc9jpz&@w)l(
z!~7qvgd;sET;k$6M(31U>&tC%-SLiaJ;>8dT{g;4h#_>yEDoRz<-!`bsQ7{c9MZ$0
zfI}v!C)x2$Q1aeCwV*N^o&*2@ABzYC000000RIL6LPG)o8vp|U0000000000ze!v5


From 756d80915b64e6441f984641b7a488366669da52 Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 10:44:09 +0100
Subject: [PATCH 040/350] Use is_of_type

instead of .ext

Co-authored-by: Lucille Delisle <lucille.delisle@epfl.ch>
---
 .../datatypes/converters/interval_to_bgzip_converter.xml      | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 08205db87e1..d1d0a11b887 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -15,9 +15,9 @@
         grep -e '^"#"' -e '^track' -v '$input1' 
         |
         sort 
-        #if $input1.ext == "vcf"
+        #if $input1.is_of_type('vcf')
             -k1,1 -k2,2n
-        #elif $input1.ext == "gff"
+        #elif $input1.is_of_type('gff')
             -s -k1,1 -k4,4n
         #else
             -k${input1.metadata.chromCol},${input1.metadata.chromCol}

From bb4708cd5cac4b9fc10036d050dbfabe57a6d0cc Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 10:49:48 +0100
Subject: [PATCH 041/350] use is_of_type

Co-authored-by: Lucille Delisle <lucille.delisle@epfl.ch>
---
 .../datatypes/converters/interval_to_tabix_converter.xml  | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index ab689d50711..cd3e2711636 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -6,8 +6,12 @@
     <command><![CDATA[
         ln -s '$bgzip' input.bgz &&
         tabix 
-        #if $input1.ext in ['bed', 'gff', 'vcf']
-            -p $input1.ext
+        #if $input1.is_of_type('bed')
+            -p bed
+        #elif $input1.is_of_type('vcf')
+            -p vcf
+        #elif $input1.is_of_type('gff')
+            -p gff
         #else
              -s ${input1.metadata.chromCol}
              -b ${input1.metadata.startCol}

From 13b432d5142502d86ed92ad41754edf866b9d04f Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 10:58:33 +0100
Subject: [PATCH 042/350] treat missed 2tabix converter

---
 .../converters/vcf_bgzip_to_tabix_converter.xml  | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
index 0d459aa011e..7bc313f9b2d 100644
--- a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
@@ -1,9 +1,21 @@
 <tool id="CONVERTER_vcf_bgzip_to_tabix_0" name="Convert BGZ VCF to tabix" version="1.0.1" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
+        <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
-    <command>python '$__tool_directory__/interval_to_tabix_converter.py' -P 'vcf' '' '$input1' '$output1'</command>
+    <command><![CDATA[
+        ln -s '$input1' input.bgz &&
+        tabix 
+            -p vcf
+            input.bgz
+        &&
+        if [ ! -s input.bgz.tbi ]; then
+            >&2 echo "The converted tabix index file is empty, meaning the input data is invalid.";
+            exit 1;
+        fi
+        &&
+        mv input.bgz.tbi '$output1'
+    ]]></command>
     <inputs>
         <param format="vcf_bgzip" name="input1" type="data" label="Choose BGZIP'd VCF file"/>
     </inputs>

From dfd4e445d8bb1f9db6e399f4bb473e9129558f34 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 14:27:40 +0100
Subject: [PATCH 043/350] assume output size for 2tabix converter tests

---
 .../interval_to_tabix_converter.xml           | 46 ++++++++++++++++---
 .../vcf_bgzip_to_tabix_converter.xml          |  8 +++-
 2 files changed, 45 insertions(+), 9 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index cd3e2711636..aeaecbb2ba8 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -13,9 +13,10 @@
         #elif $input1.is_of_type('gff')
             -p gff
         #else
-             -s ${input1.metadata.chromCol}
-             -b ${input1.metadata.startCol}
-             -e ${input1.metadata.endCol}
+            -s ${input1.metadata.chromCol}
+            -b ${input1.metadata.startCol}
+            -e ${input1.metadata.endCol}
+            ## TODO --zero-based information missing in interval datatype
         #end if
         input.bgz
         &&
@@ -40,7 +41,14 @@
     <tests>
         <test>
             <param name="input1" ftype="bed" value="droPer1.bed"/>
-            <output name="output1" ftype="tabix" value="droPer1.tabix"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="133"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="-p bed"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
@@ -49,18 +57,42 @@
                     <has_size value="110" delta="10"/>
                 </assert_contents>
             </output>
+            <assert_command>
+                <has_text text="-p" negate="true"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="gff" value="gff_filter_by_feature_count_out2.gff"/>
-            <output name="output1" ftype="tabix" value="tabix_filter_by_feature_count_out2.tabix"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="120"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="-p gff"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="interval" value="2.interval"/>
-            <output name="output1" ftype="tabix" value="2.tabix"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="247"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="-p" negate="true"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
-            <output name="output1" ftype="tabix" value="tabix_to_maf_in.tabix"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="148"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="-p vcf"/>
+            </assert_command>
         </test>
     </tests>
     <help>
diff --git a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
index 7bc313f9b2d..e8e6dc4d213 100644
--- a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_vcf_bgzip_to_tabix_0" name="Convert BGZ VCF to tabix" version="1.0.1" hidden="true" profile="16.04">
+<tool id="CONVERTER_vcf_bgzip_to_tabix_0" name="Convert BGZ VCF to tabix" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
         <requirement type="package" version="1.14">htslib</requirement>
@@ -25,7 +25,11 @@
     <tests>
         <test>
             <param name="input1" ftype="vcf_bgzip" value="vcf_bgzip_to_maf_in.vcf_bgzip"/>
-            <output name="output1" ftype="tabix" value="tabix_to_maf_in_to_tabix.tabix"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="148"/>
+                </assert_contents>
+            </output>
         </test>
     </tests>
     <help>

From 7e452e22c5c0b11b14844b78e0b10e718b5176c5 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 16:32:54 +0100
Subject: [PATCH 044/350] extend test

---
 .../interval_to_bgzip_converter.xml           | 23 ++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index d1d0a11b887..67578c4fb8c 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.2" hidden="true" profile="16.04">
+<tool id="CONVERTER_interval_to_bgzip_0" name="Convert Interval to BGZIP" version="1.0.3" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <macros>
         <xml name="assert_size" tokens="value" token_delta="10">
@@ -18,6 +18,7 @@
         #if $input1.is_of_type('vcf')
             -k1,1 -k2,2n
         #elif $input1.is_of_type('gff')
+            ## stable sort on start column (only) ..
             -s -k1,1 -k4,4n
         #else
             -k${input1.metadata.chromCol},${input1.metadata.chromCol}
@@ -40,30 +41,46 @@
             <output name="output1" ftype="bgzip" value="droPer1.bgzip" decompress="true">
                 <expand macro="assert_size" value="131"/>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k2,2n -k3,3n"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
             <output name="output1" ftype="bgzip">
                 <expand macro="assert_size" value="299"/>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k2,2n -k3,3n"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="gff" value="gff_filter_by_feature_count_out2.gff"/>
             <output name="output1" ftype="bgzip" value="bgzip_filter_by_feature_count_out2.bgzip" decompress="true">
                 <expand macro="assert_size" value="638"/>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k4,4n"/>
+                <has_text text="-k5,5" negate="true"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="interval" value="2.interval"/>
             <output name="output1" ftype="bgzip" value="2.bgzip" decompress="true">
                 <expand macro="assert_size" value="208"/>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k2,2n -k3,3n"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
                 <expand macro="assert_size" value="707"/>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k2,2n"/>
+            </assert_command>
         </test>
         <test>
             <param name="input1" ftype="gtf" value="cufflinks_out1.gtf"/>
@@ -72,6 +89,10 @@
                     <has_size value="270" delta="10" />
                 </assert_contents>
             </output>
+            <assert_command>
+                <has_text text="-k1,1 -k4,4n"/>
+                <has_text text="-k5,5" negate="true"/>
+            </assert_command>
         </test>
     </tests>
     <help>

From 6bf13fd278da11435669aa20755cb256e26fc5b2 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 16:53:35 +0100
Subject: [PATCH 045/350] also treat cram to bam converter

---
 .../datatypes/converters/cram_to_bam.py       | 23 -------------------
 .../converters/cram_to_bam_converter.xml      |  6 ++---
 2 files changed, 3 insertions(+), 26 deletions(-)
 delete mode 100644 lib/galaxy/datatypes/converters/cram_to_bam.py

diff --git a/lib/galaxy/datatypes/converters/cram_to_bam.py b/lib/galaxy/datatypes/converters/cram_to_bam.py
deleted file mode 100644
index 08555f603e6..00000000000
--- a/lib/galaxy/datatypes/converters/cram_to_bam.py
+++ /dev/null
@@ -1,23 +0,0 @@
-#!/usr/bin/env python
-
-"""
-Uses pysam to convert a CRAM file to a sorted bam file.
-usage: %prog in_file out_file
-"""
-import optparse
-import os
-
-from pysam import sort  # type: ignore[attr-defined]
-
-
-def main():
-    # Read options, args.
-    parser = optparse.OptionParser()
-    (options, args) = parser.parse_args()
-    input_fname, output_fname = args
-    slots = os.getenv("GALAXY_SLOTS", 1)
-    sort(f"-@{slots}", "-o", output_fname, "-O", "bam", "-T", ".", input_fname)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
index ee464bb12b9..230c5d9d79f 100644
--- a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
+++ b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
@@ -1,9 +1,9 @@
 <tool id="CONVERTER_cram_to_bam_0" name="Convert CRAM to BAM" version="1.0.0" hidden="true" profile="16.04">
     <requirements>
-        <requirement type="package" version="0.15.4">pysam</requirement>
+        <requirement type="package" version="1.16.1">samtools</requirement>
     </requirements>
     <command><![CDATA[
-python '$__tool_directory__/cram_to_bam.py' '$input' '$output'
+        samtools sort '$input' -o '$output' --output-fmt BAM
     ]]></command>
     <inputs>
         <param format="cram" name="input" type="data" label="Choose CRAM file"/>
@@ -16,7 +16,7 @@ python '$__tool_directory__/cram_to_bam.py' '$input' '$output'
             <param name="input" ftype="cram" value="2.cram"/>
             <output name="output" ftype="bam">
                 <assert_contents>
-                    <has_size value="57232"/>
+                    <has_size min="55000" max="58000"/>
                 </assert_contents>
             </output>
         </test>

From ceb69e56c344905cc558539e36b4e9cba1f8e98f Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Mon, 12 Dec 2022 18:09:41 +0100
Subject: [PATCH 046/350] remove todo text

---
 lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index aeaecbb2ba8..894cd891807 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -16,7 +16,7 @@
             -s ${input1.metadata.chromCol}
             -b ${input1.metadata.startCol}
             -e ${input1.metadata.endCol}
-            ## TODO --zero-based information missing in interval datatype
+            ## --zero-based information missing in interval datatype
         #end if
         input.bgz
         &&

From c48bf1c9857d242488f411c82463bec5a9b28368 Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Tue, 13 Dec 2022 10:45:54 +0100
Subject: [PATCH 047/350] add test

Co-authored-by: Lucille Delisle <lucille.delisle@epfl.ch>
---
 .../converters/interval_to_tabix_converter.xml        | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index 894cd891807..ba80e126c66 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -94,6 +94,17 @@
                 <has_text text="-p vcf"/>
             </assert_command>
         </test>
+        <test>
+            <param name="input1" ftype="gtf" value="cufflinks_out1.gtf"/>
+            <output name="output1" ftype="tabix">
+                <assert_contents>
+                    <has_size value="125"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="-p gff"/>
+            </assert_command>
+        </test>        
     </tests>
     <help>
     </help>

From 04e191d6a7c930553dd2ae347a8b56429277f95f Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Tue, 13 Dec 2022 10:47:02 +0100
Subject: [PATCH 048/350] Fix tabix call

Co-authored-by: Lucille Delisle <lucille.delisle@epfl.ch>
---
 lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
index e567d3f4a93..7ece375289f 100644
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
+++ b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
@@ -6,7 +6,7 @@
     <command><![CDATA[
         mkdir '$dbnsfp.extra_files_path' &&
         bgzip -c '$input' > '$dbnsfp.extra_files_path/dbNSFP.gz' &&
-        tabix '$dbnsfp.extra_files_path/dbNSFP.gz'
+        tabix -s 1 -b 2 -e 2 '$dbnsfp.extra_files_path/dbNSFP.gz'
     ]]></command>
     <inputs>
         <param format="tabular" name="input" type="data" label="Choose a dbnsfp tabular file"/>

From 829ef5b95d83c301e07147ee03d443e6f3c7bb4b Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Thu, 15 Dec 2022 09:36:59 +0100
Subject: [PATCH 049/350] CONVERTER_cram_to_bam_0 bump

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 lib/galaxy/datatypes/converters/cram_to_bam_converter.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
index 230c5d9d79f..dd5dc11d5c3 100644
--- a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
+++ b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
@@ -1,4 +1,4 @@
-<tool id="CONVERTER_cram_to_bam_0" name="Convert CRAM to BAM" version="1.0.0" hidden="true" profile="16.04">
+<tool id="CONVERTER_cram_to_bam_0" name="Convert CRAM to BAM" version="1.0.1" hidden="true" profile="16.04">
     <requirements>
         <requirement type="package" version="1.16.1">samtools</requirement>
     </requirements>

From 3b15a2044809b2671ad03d71efc10ba17db13a2d Mon Sep 17 00:00:00 2001
From: Lucille Delisle <lucille.delisle@epfl.ch>
Date: Thu, 15 Dec 2022 21:34:15 +0100
Subject: [PATCH 050/350] use already existing index + test index

---
 .../interval_to_tabix_converter.xml           | 18 ++++++++++++++++-
 .../vcf_bgzip_to_tabix_converter.xml          | 20 ++++++++-----------
 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index ba80e126c66..d1a0fc41021 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -25,7 +25,8 @@
             exit 1;
         fi 
         &&
-        mv input.bgz.tbi '$output1'
+        cp input.bgz.tbi '$output1' &&
+        tabix -l input.bgz
     ]]></command>
     <inputs>
         <!-- gff because gff and vcf are not a subclass of interval -->
@@ -49,6 +50,9 @@
             <assert_command>
                 <has_text text="-p bed"/>
             </assert_command>
+            <assert_stdout>
+                <has_line line="super_1"/>
+            </assert_stdout>
         </test>
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
@@ -60,6 +64,9 @@
             <assert_command>
                 <has_text text="-p" negate="true"/>
             </assert_command>
+            <assert_stdout>
+                <has_line line="chr1"/>
+            </assert_stdout>
         </test>
         <test>
             <param name="input1" ftype="gff" value="gff_filter_by_feature_count_out2.gff"/>
@@ -71,6 +78,9 @@
             <assert_command>
                 <has_text text="-p gff"/>
             </assert_command>
+            <assert_stdout>
+                <has_line line="ctgA"/>
+            </assert_stdout>
         </test>
         <test>
             <param name="input1" ftype="interval" value="2.interval"/>
@@ -82,6 +92,9 @@
             <assert_command>
                 <has_text text="-p" negate="true"/>
             </assert_command>
+            <assert_stdout>
+                <has_line line="chrX"/>
+            </assert_stdout>
         </test>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
@@ -93,6 +106,9 @@
             <assert_command>
                 <has_text text="-p vcf"/>
             </assert_command>
+            <assert_stdout>
+                <has_line line="20"/>
+            </assert_stdout>
         </test>
         <test>
             <param name="input1" ftype="gtf" value="cufflinks_out1.gtf"/>
diff --git a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
index e8e6dc4d213..edd858cb8ef 100644
--- a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
@@ -4,17 +4,10 @@
         <requirement type="package" version="1.14">htslib</requirement>
     </requirements>
     <command><![CDATA[
-        ln -s '$input1' input.bgz &&
-        tabix 
-            -p vcf
-            input.bgz
-        &&
-        if [ ! -s input.bgz.tbi ]; then
-            >&2 echo "The converted tabix index file is empty, meaning the input data is invalid.";
-            exit 1;
-        fi
-        &&
-        mv input.bgz.tbi '$output1'
+        cp '$input1.metadata.tabix_index' '$output1' &&
+        ln -s '$input1' test.bgzip &&
+        ln -s '$output1' test.bgzip.tbi &&
+        tabix -l test.bgzip
     ]]></command>
     <inputs>
         <param format="vcf_bgzip" name="input1" type="data" label="Choose BGZIP'd VCF file"/>
@@ -27,9 +20,12 @@
             <param name="input1" ftype="vcf_bgzip" value="vcf_bgzip_to_maf_in.vcf_bgzip"/>
             <output name="output1" ftype="tabix">
                 <assert_contents>
-                    <has_size value="148"/>
+                    <has_size value="148" delta="10"/>
                 </assert_contents>
             </output>
+            <assert_stdout>
+                <has_line line="20"/>
+            </assert_stdout>
         </test>
     </tests>
     <help>

From b537fe90a72aee4da2cf7568ea9c8a96f78afb41 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 10:47:26 -0500
Subject: [PATCH 051/350] Move protocols into separate module

---
 lib/galaxy/datatypes/_protocols.py | 12 ++++++++++++
 lib/galaxy/datatypes/anvio.py      |  2 +-
 lib/galaxy/datatypes/assembly.py   |  2 +-
 lib/galaxy/datatypes/binary.py     |  2 +-
 lib/galaxy/datatypes/data.py       | 11 ++---------
 lib/galaxy/datatypes/genetics.py   |  2 +-
 lib/galaxy/datatypes/gis.py        |  2 +-
 lib/galaxy/datatypes/hdf5.py       |  6 ++----
 lib/galaxy/datatypes/images.py     |  2 +-
 lib/galaxy/datatypes/isa.py        |  6 ++----
 lib/galaxy/datatypes/neo4j.py      |  6 ++----
 lib/galaxy/datatypes/ngsindex.py   |  2 +-
 lib/galaxy/datatypes/proteomics.py |  6 ++----
 lib/galaxy/datatypes/spaln.py      |  6 ++----
 lib/galaxy/datatypes/text.py       |  2 +-
 lib/galaxy/datatypes/tracks.py     |  2 +-
 16 files changed, 33 insertions(+), 38 deletions(-)
 create mode 100644 lib/galaxy/datatypes/_protocols.py

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
new file mode 100644
index 00000000000..fcfb5eb6183
--- /dev/null
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -0,0 +1,12 @@
+"""
+Location of protocols used in datatypes
+"""
+
+from typing import Any
+
+from typing_extensions import Protocol
+
+
+class GeneratePrimaryFileDataset(Protocol):
+    extra_files_path: str
+    metadata: Any
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 5a3f40e1e2d..c46ae06c338 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -10,7 +10,7 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
 
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 7cfe64e165a..4e25c488fa9 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -13,7 +13,7 @@ from galaxy.datatypes import (
     data,
     sequence,
 )
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 6e12b0cc6ea..437c90cf186 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -33,10 +33,10 @@ from bx.seq.twobit import (
 
 from galaxy import util
 from galaxy.datatypes import metadata
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.data import (
     Data,
     DatatypeValidation,
-    GeneratePrimaryFileDataset,
     get_file_peek,
 )
 from galaxy.datatypes.dataproviders.column import (
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 859a3ebf187..6fdce26a1d3 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -20,12 +20,10 @@ from typing import (
 )
 
 from markupsafe import escape
-from typing_extensions import (
-    Literal,
-    Protocol,
-)
+from typing_extensions import Literal
 
 from galaxy import util
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
 )
@@ -83,11 +81,6 @@ DEFAULT_MAX_PEEK_SIZE = 1000000  # 1 MB
 Headers = Dict[str, Any]
 
 
-class GeneratePrimaryFileDataset(Protocol):
-    extra_files_path: str
-    metadata: Any
-
-
 class DatatypeConverterNotFoundException(Exception):
     pass
 
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index c8d999edd66..2afb8e74677 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -28,9 +28,9 @@ from urllib.parse import quote_plus
 from markupsafe import escape
 
 from galaxy.datatypes import metadata
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.data import (
     DatatypeValidation,
-    GeneratePrimaryFileDataset,
     Text,
 )
 from galaxy.datatypes.metadata import MetadataElement
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index ead789aa2d9..427756f611b 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -3,8 +3,8 @@ GIS classes
 """
 from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.binary import Binary
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
 
 if TYPE_CHECKING:
     from galaxy.model import DatasetInstance
diff --git a/lib/galaxy/datatypes/hdf5.py b/lib/galaxy/datatypes/hdf5.py
index 6a2b42c58be..8c37966bfbd 100644
--- a/lib/galaxy/datatypes/hdf5.py
+++ b/lib/galaxy/datatypes/hdf5.py
@@ -7,10 +7,8 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes.data import (
-    Data,
-    GeneratePrimaryFileDataset,
-)
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
 
 if TYPE_CHECKING:
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 8dd6f79b7c6..829ca50fc32 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -13,8 +13,8 @@ import mrcfile
 import numpy as np
 import tifffile
 
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.binary import Binary
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
 from galaxy.datatypes.metadata import (
     FileParameter,
     MetadataElement,
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index 6b5f81687d2..a72bea65f37 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -26,10 +26,8 @@ from isatools import (
 from markupsafe import escape
 
 from galaxy import util
-from galaxy.datatypes.data import (
-    Data,
-    GeneratePrimaryFileDataset,
-)
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes.data import Data
 from galaxy.util.compression_utils import CompressedFile
 from galaxy.util.sanitize_html import sanitize_html
 
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index 4c53dccb56a..1f45f059afe 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -4,10 +4,8 @@ Neo4j Composite Dataset
 import logging
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes.data import (
-    Data,
-    GeneratePrimaryFileDataset,
-)
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
 from galaxy.datatypes.metadata import MetadataElement
 
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index 198fb994b0f..9d0d35808b0 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -5,7 +5,7 @@ import logging
 import os
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from .metadata import MetadataElement
 from .text import Html
 
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 5135ab419dc..47b13b7c966 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -11,11 +11,9 @@ from typing import (
 )
 
 from galaxy.datatypes import data
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.binary import Binary
-from galaxy.datatypes.data import (
-    GeneratePrimaryFileDataset,
-    Text,
-)
+from galaxy.datatypes.data import Text
 from galaxy.datatypes.sequence import Sequence
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 6ce094e341d..b32c7e2b509 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -12,10 +12,8 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes.data import (
-    Data,
-    GeneratePrimaryFileDataset,
-)
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.util import smart_str
 
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 7e778a001c6..08c8d2b1219 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -17,8 +17,8 @@ from typing import (
 
 import yaml
 
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.data import (
-    GeneratePrimaryFileDataset,
     get_file_peek,
     Headers,
     Text,
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index bf5e29e6b8c..62ba622aa8f 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -4,7 +4,7 @@ Datatype classes for tracks/track views within galaxy.
 import logging
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes.data import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
 from galaxy.datatypes.text import Html
 from . import binary
 

From f5a629ebc6613e7d865e4811c13af72dde1e050b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 14:35:06 -0500
Subject: [PATCH 052/350] [wip] Add another protocol

---
 lib/galaxy/datatypes/_protocols.py | 18 +++++++++++++++++-
 lib/galaxy/datatypes/data.py       |  7 +++++--
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index fcfb5eb6183..0d7db20d8b9 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -1,12 +1,28 @@
 """
 Location of protocols used in datatypes
 """
-
 from typing import Any
 
 from typing_extensions import Protocol
 
 
+class HasExtraFilesPathProperty(Protocol):
+    @property
+    def extra_files_path(self):
+        ...
+
+
+class HasFilesNameProperty(Protocol):
+    @property
+    def file_name(self):
+        ...
+
+
+class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
+    name: str
+    extension: str
+
+
 class GeneratePrimaryFileDataset(Protocol):
     extra_files_path: str
     metadata: Any
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 6fdce26a1d3..a28d683f743 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -23,7 +23,10 @@ from markupsafe import escape
 from typing_extensions import Literal
 
 from galaxy import util
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t1,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
 )
@@ -339,7 +342,7 @@ class Data(metaclass=DataMeta):
         return error, msg, messagetype
 
     def _archive_composite_dataset(
-        self, trans, data: "DatasetInstance", headers: Headers, do_action: str = "zip"
+        self, trans, data: Dataset_t1, headers: Headers, do_action: str = "zip"
     ) -> Tuple[Union[ZipstreamWrapper, str], Headers]:
         # save a composite object into a compressed archive for downloading
         outfname = data.name[0:150]

From 1d04392c4212f759bebce56b5e80d50350ffed1f Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 15:37:53 -0500
Subject: [PATCH 053/350] Replace DatasetInstance in 3 methods in isa.py

_get_isa_folder_path
_get_main_file
_get_investigation
---
 lib/galaxy/datatypes/isa.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index a72bea65f37..27d64696498 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -26,7 +26,10 @@ from isatools import (
 from markupsafe import escape
 
 from galaxy import util
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    GeneratePrimaryFileDataset,
+    HasExtraFilesPathProperty,
+)
 from galaxy.datatypes.data import Data
 from galaxy.util.compression_utils import CompressedFile
 from galaxy.util.sanitize_html import sanitize_html
@@ -90,7 +93,7 @@ class _Isa(Data):
     # Get ISA folder path {{{2
     ################################################################
 
-    def _get_isa_folder_path(self, dataset: "DatasetInstance") -> str:
+    def _get_isa_folder_path(self, dataset: HasExtraFilesPathProperty) -> str:
         isa_folder = dataset.extra_files_path
         if not isa_folder:
             raise Exception("Unvalid dataset object, or no extra files path found for this dataset.")
@@ -99,7 +102,7 @@ class _Isa(Data):
     # Get main file {{{2
     ################################################################
 
-    def _get_main_file(self, dataset: "DatasetInstance") -> Optional[str]:
+    def _get_main_file(self, dataset: HasExtraFilesPathProperty) -> Optional[str]:
         """Get the main file of the ISA archive. Either the investigation file i_*.txt for ISA-Tab, or the JSON file for ISA-JSON."""
 
         main_file = None
@@ -125,7 +128,7 @@ class _Isa(Data):
     # Get investigation {{{2
     ################################################################
 
-    def _get_investigation(self, dataset: "DatasetInstance") -> Optional["Investigation"]:
+    def _get_investigation(self, dataset: HasExtraFilesPathProperty) -> Optional["Investigation"]:
         """Create a contained instance specific to the exact ISA type (Tab or Json).
         We will use it to parse and access information from the archive."""
 

From f0843f98c43a801705e5a9c97f0f0be050ac0078 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 15:43:48 -0500
Subject: [PATCH 054/350] Remove DatasetInstance from _get_remote_call_url

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/interval.py   | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 0d7db20d8b9..377d7110c52 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -18,6 +18,10 @@ class HasFilesNameProperty(Protocol):
         ...
 
 
+class HasId(Protocol):
+    id: int
+
+
 class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
     name: str
     extension: str
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 2c4e710d9e1..83cc770d547 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,6 +22,7 @@ from bx.intervals.io import (
 
 from galaxy import util
 from galaxy.datatypes import metadata
+from galaxy.datatypes._protocols import HasId
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
     DatasetDataProvider,
@@ -757,7 +758,7 @@ class Bed12(BedStrict):
 
 class _RemoteCallMixin:
     def _get_remote_call_url(
-        self, redirect_url: str, site_name: str, dataset: "DatasetInstance", type: str, app, base_url: str
+        self, redirect_url: str, site_name: str, dataset: HasId, type: str, app, base_url: str
     ) -> str:
         """Retrieve the URL to call out to an external site and retrieve data.
         This routes our external URL through a local galaxy instance which makes

From 17c2ec50c9bfd701ab92bfcb4f256d1c833fa382 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 15:46:16 -0500
Subject: [PATCH 055/350] Remove DatasetInstance from _peek

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/qiime2.py     | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 377d7110c52..824901a79c1 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -22,6 +22,10 @@ class HasId(Protocol):
     id: int
 
 
+class HasMetadata(Protocol):
+    metadata: Any
+
+
 class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
     name: str
     extension: str
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index 4a2ed5cc9dc..376c15a89a4 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -12,6 +12,7 @@ from typing import (
 
 import yaml
 
+from galaxy.datatypes._protocols import HasMetadata
 from galaxy.datatypes.binary import CompressedZipArchive
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -59,7 +60,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         return "".join(table)
 
-    def _peek(self, dataset: "DatasetInstance", simple: bool = False) -> List:
+    def _peek(self, dataset: HasMetadata, simple: bool = False) -> List:
         peek = [("Type", dataset.metadata.semantic_type), ("UUID", dataset.metadata.uuid)]
         if not simple:
             if dataset.metadata.semantic_type != "Visualization":

From c80c0f3e2c8df813365e01d3cc5bef42a0345bab Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 15:47:57 -0500
Subject: [PATCH 056/350] Refactor protocol

---
 lib/galaxy/datatypes/_protocols.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 824901a79c1..090efe274de 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -31,6 +31,5 @@ class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
     extension: str
 
 
-class GeneratePrimaryFileDataset(Protocol):
-    extra_files_path: str
-    metadata: Any
+class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
+    ...

From 2f1c478e05dbba4473cb93d5bb8d1b90ebb5601c Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 15:50:21 -0500
Subject: [PATCH 057/350] Remove DatasetInstance from _read_chunk

---
 lib/galaxy/datatypes/tabular.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 2aefc366321..98d99d82b69 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,6 +30,7 @@ from galaxy.datatypes import (
     data,
     metadata,
 )
+from galaxy.datatypes._protocols import HasFilesNameProperty
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -153,7 +154,7 @@ class TabularData(Text):
             }
         )
 
-    def _read_chunk(self, trans, dataset: "DatasetInstance", offset: int, ck_size: Optional[int] = None):
+    def _read_chunk(self, trans, dataset: HasFilesNameProperty, offset: int, ck_size: Optional[int] = None):
         with compression_utils.get_fileobj(dataset.file_name) as f:
             f.seek(offset)
             ck_data = f.read(ck_size or trans.app.config.display_chunk_size)

From b2ddff9c95ff5e4450bbbe870d7f3d2052b7c799 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 16:33:48 -0500
Subject: [PATCH 058/350] Remove DatasetInstance from _yield_user_file_content

---
 lib/galaxy/datatypes/_protocols.py | 6 ++++++
 lib/galaxy/datatypes/data.py       | 5 ++++-
 lib/galaxy/datatypes/text.py       | 9 +++++++--
 3 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 090efe274de..271602b2864 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -26,6 +26,12 @@ class HasMetadata(Protocol):
     metadata: Any
 
 
+class HasCreatingJobProperty(Protocol):
+    @property
+    def creating_job(self):
+        ...
+
+
 class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
     name: str
     extension: str
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index a28d683f743..bbf153ac78f 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -26,6 +26,7 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t1,
     GeneratePrimaryFileDataset,
+    HasCreatingJobProperty,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -570,7 +571,9 @@ class Data(metaclass=DataMeta):
                 result += indicate_data_truncated()
         return result
 
-    def _yield_user_file_content(self, trans, from_dataset: "DatasetInstance", filename: str, headers: Headers) -> IO:
+    def _yield_user_file_content(
+        self, trans, from_dataset: HasCreatingJobProperty, filename: str, headers: Headers
+    ) -> IO:
         """This method is responsible for sanitizing the HTML if needed."""
         if trans.app.config.sanitize_all_html and headers.get("content-type", None) == "text/html":
             # Sanitize anytime we respond with plain text/html content.
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 08c8d2b1219..2605c2944c2 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -17,7 +17,10 @@ from typing import (
 
 import yaml
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    GeneratePrimaryFileDataset,
+    HasCreatingJobProperty,
+)
 from galaxy.datatypes.data import (
     get_file_peek,
     Headers,
@@ -1094,7 +1097,9 @@ class Yaml(Text):
         """Returns the mime type of the datatype"""
         return "application/yaml"
 
-    def _yield_user_file_content(self, trans, from_dataset: "DatasetInstance", filename: str, headers: Headers) -> IO:
+    def _yield_user_file_content(
+        self, trans, from_dataset: HasCreatingJobProperty, filename: str, headers: Headers
+    ) -> IO:
         # Override non-standard application/yaml mediatype with
         # text/plain, so preview is shown in preview iframe,
         # instead of downloading the file.

From 9852eb75b74566c5f84c7d9d36b73b7bbbeb9087 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 16:38:50 -0500
Subject: [PATCH 059/350] Remove DatasetInstance from
 after|before_setting_metadata

---
 lib/galaxy/datatypes/_protocols.py | 5 +++++
 lib/galaxy/datatypes/data.py       | 5 +++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 271602b2864..a5a04db7999 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -32,6 +32,11 @@ class HasCreatingJobProperty(Protocol):
         ...
 
 
+class HasClearAssociatedFiles(Protocol):
+    def clear_associated_files(self, metadata_safe: bool = False, purge: bool = False) -> None:
+        ...
+
+
 class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
     name: str
     extension: str
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index bbf153ac78f..f6109f08a73 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -26,6 +26,7 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t1,
     GeneratePrimaryFileDataset,
+    HasClearAssociatedFiles,
     HasCreatingJobProperty,
 )
 from galaxy.datatypes.metadata import (
@@ -804,11 +805,11 @@ class Data(metaclass=DataMeta):
     # We need to clear associated files before we set metadata
     # so that as soon as metadata starts to be set, e.g. implicitly converted datasets are deleted and no longer available 'while' metadata is being set, not just after
     # We'll also clear after setting metadata, for backwards compatibility
-    def after_setting_metadata(self, dataset: "DatasetInstance") -> None:
+    def after_setting_metadata(self, dataset: HasClearAssociatedFiles) -> None:
         """This function is called on the dataset after metadata is set."""
         dataset.clear_associated_files(metadata_safe=True)
 
-    def before_setting_metadata(self, dataset: "DatasetInstance") -> None:
+    def before_setting_metadata(self, dataset: HasClearAssociatedFiles) -> None:
         """This function is called on the dataset before metadata is set."""
         dataset.clear_associated_files(metadata_safe=True)
 

From 6fbcebfd3060cf7f907f6bc1265f63fa224f12e0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 16:44:12 -0500
Subject: [PATCH 060/350] Remove DatasetInstance from count_data_lines

---
 lib/galaxy/datatypes/_protocols.py | 4 ++--
 lib/galaxy/datatypes/data.py       | 3 ++-
 lib/galaxy/datatypes/tabular.py    | 4 ++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index a5a04db7999..d82fa44215c 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -12,7 +12,7 @@ class HasExtraFilesPathProperty(Protocol):
         ...
 
 
-class HasFilesNameProperty(Protocol):
+class HasFileNameProperty(Protocol):
     @property
     def file_name(self):
         ...
@@ -37,7 +37,7 @@ class HasClearAssociatedFiles(Protocol):
         ...
 
 
-class Dataset_t1(HasExtraFilesPathProperty, HasFilesNameProperty, Protocol):
+class Dataset_t1(HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
     name: str
     extension: str
 
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index f6109f08a73..1d6e485d1be 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -28,6 +28,7 @@ from galaxy.datatypes._protocols import (
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
+    HasFileNameProperty,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -997,7 +998,7 @@ class Text(Data):
             log.error(f"Unable to estimate lines in file {dataset.file_name}")
             return None
 
-    def count_data_lines(self, dataset: "DatasetInstance") -> Optional[int]:
+    def count_data_lines(self, dataset: HasFileNameProperty) -> Optional[int]:
         """
         Count the number of lines of data in dataset,
         skipping all blank lines and comments.
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 98d99d82b69..6334b433e01 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,7 +30,7 @@ from galaxy.datatypes import (
     data,
     metadata,
 )
-from galaxy.datatypes._protocols import HasFilesNameProperty
+from galaxy.datatypes._protocols import HasFileNameProperty
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -154,7 +154,7 @@ class TabularData(Text):
             }
         )
 
-    def _read_chunk(self, trans, dataset: HasFilesNameProperty, offset: int, ck_size: Optional[int] = None):
+    def _read_chunk(self, trans, dataset: HasFileNameProperty, offset: int, ck_size: Optional[int] = None):
         with compression_utils.get_fileobj(dataset.file_name) as f:
             f.seek(offset)
             ck_data = f.read(ck_size or trans.app.config.display_chunk_size)

From 102376f1f0b9525df754c53c0918d6e10077d96b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 17:08:00 -0500
Subject: [PATCH 061/350] Remove DatasetInstance from dataprovider* methods

---
 lib/galaxy/datatypes/_protocols.py | 15 ++++++++++-----
 lib/galaxy/datatypes/data.py       | 19 +++++++------------
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index d82fa44215c..a828a66ad5f 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -37,10 +37,15 @@ class HasClearAssociatedFiles(Protocol):
         ...
 
 
-class Dataset_t1(HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
-    name: str
-    extension: str
-
-
 class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
     ...
+
+
+class Dataset_t1(HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
+    name: str
+    extension: str  # TODO reconcile: ext vs. extension
+
+
+class Dataset_t2(HasMetadata, HasFileNameProperty, Protocol):
+    datatype: Any
+    ext: str  # TODO reconcile: ext vs. extension
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 1d6e485d1be..f9abc777f09 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -25,6 +25,7 @@ from typing_extensions import Literal
 from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t1,
+    Dataset_t2,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -911,7 +912,7 @@ class Data(metaclass=DataMeta):
         """
         return data_format in self.dataproviders
 
-    def dataprovider(self, dataset: "DatasetInstance", data_format: str, **settings):
+    def dataprovider(self, dataset: Dataset_t2, data_format: str, **settings):
         """
         Base dataprovider factory for all datatypes that returns the proper provider
         for the given `data_format` or raises a `NoProviderAvailable`.
@@ -924,19 +925,17 @@ class Data(metaclass=DataMeta):
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
-    def base_dataprovider(self, dataset: "DatasetInstance", **settings) -> p_dataproviders.base.DataProvider:
+    def base_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.base.DataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.base.DataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk", p_dataproviders.chunk.ChunkDataProvider.settings)
-    def chunk_dataprovider(self, dataset: "DatasetInstance", **settings) -> p_dataproviders.chunk.ChunkDataProvider:
+    def chunk_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.ChunkDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk64", p_dataproviders.chunk.Base64ChunkDataProvider.settings)
-    def chunk64_dataprovider(
-        self, dataset: "DatasetInstance", **settings
-    ) -> p_dataproviders.chunk.Base64ChunkDataProvider:
+    def chunk64_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.chunk.Base64ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.Base64ChunkDataProvider(dataset_source, **settings)
 
@@ -1132,9 +1131,7 @@ class Text(Data):
 
     # ------------- Dataproviders
     @p_dataproviders.decorators.dataprovider_factory("line", p_dataproviders.line.FilteredLineDataProvider.settings)
-    def line_dataprovider(
-        self, dataset: "DatasetInstance", **settings
-    ) -> p_dataproviders.line.FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.line.FilteredLineDataProvider:
         """
         Returns an iterator over the dataset's lines (that have been stripped)
         optionally excluding blank lines and lines that start with a comment character.
@@ -1143,9 +1140,7 @@ class Text(Data):
         return p_dataproviders.line.FilteredLineDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("regex-line", p_dataproviders.line.RegexLineDataProvider.settings)
-    def regex_line_dataprovider(
-        self, dataset: "DatasetInstance", **settings
-    ) -> p_dataproviders.line.RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.line.RegexLineDataProvider:
         """
         Returns an iterator over the dataset's lines
         optionally including/excluding lines that match one or more regex filters.

From 8a19fa9b78181c2d1423572a44abe9f60aff3ef2 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 17:13:28 -0500
Subject: [PATCH 062/350] Remove DatasetInstance from binary.py::dataprovider*
 methods

---
 lib/galaxy/datatypes/binary.py | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 437c90cf186..37f26f53b53 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -33,7 +33,10 @@ from bx.seq.twobit import (
 
 from galaxy import util
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t2,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.data import (
     Data,
     DatatypeValidation,
@@ -801,25 +804,25 @@ class Bam(BamNative):
     # TODO:?? seems like there should be an easier way to do/inherit this - metadata.comment_char?
     # TODO: incorporate samtools options to control output: regions first, then flags, etc.
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: "DatasetInstance", **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> FilteredLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return FilteredLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: "DatasetInstance", **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: "DatasetInstance", **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return ColumnarDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return DictDataProvider(samtools_source, **settings)
@@ -837,20 +840,20 @@ class Bam(BamNative):
     #    return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: "DatasetInstance", **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
         # in this case we can use an option of samtools view to provide just what we need (w/o regex)
         samtools_source = SamtoolsDataProvider(dataset, "-H")
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", DictDataProvider.settings)
-    def id_seq_qual_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         settings["indeces"] = [0, 9, 10]
         settings["column_types"] = ["str", "str", "str"]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", ColumnarDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> ColumnarDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
         # GenomicRegionDataProvider currently requires a dataset as source - may not be necc.
         # TODO:?? consider (at least) the possible use of a kwarg: metadata_source (def. to source.dataset),
         #   or remove altogether...
@@ -864,14 +867,14 @@ class Bam(BamNative):
         return self.column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", DictDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         settings["indeces"] = [2, 3, 3]
         settings["column_types"] = ["str", "int", "int"]
         settings["column_names"] = ["chrom", "start", "end"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("samtools")
-    def samtools_dataprovider(self, dataset: "DatasetInstance", **settings) -> SamtoolsDataProvider:
+    def samtools_dataprovider(self, dataset: Dataset_t2, **settings) -> SamtoolsDataProvider:
         """Generic samtools interface - all options available through settings."""
         dataset_source = DatasetDataProvider(dataset)
         return SamtoolsDataProvider(dataset_source, **settings)
@@ -2398,17 +2401,17 @@ class SQlite(Binary):
             return f"SQLite Database ({nice_size(dataset.get_size())})"
 
     @dataproviders.decorators.dataprovider_factory("sqlite", SQliteDataProvider.settings)
-    def sqlite_dataprovider(self, dataset: "DatasetInstance", **settings) -> SQliteDataProvider:
+    def sqlite_dataprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-table", SQliteDataTableProvider.settings)
-    def sqlite_datatableprovider(self, dataset: "DatasetInstance", **settings) -> SQliteDataTableProvider:
+    def sqlite_datatableprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataTableProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataTableProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-dict", SQliteDataDictProvider.settings)
-    def sqlite_datadictprovider(self, dataset: "DatasetInstance", **settings) -> SQliteDataDictProvider:
+    def sqlite_datadictprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataDictProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataDictProvider(dataset_source, **settings)
 

From 467c2b5b6ab7e7a9a9f80e85ad87e5f541d5d538 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 17:18:23 -0500
Subject: [PATCH 063/350] Remove DatasetInstance from tabluar.py::dataprovider*
 methods

---
 lib/galaxy/datatypes/tabular.py | 41 ++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 6334b433e01..68e619f2aa7 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,7 +30,10 @@ from galaxy.datatypes import (
     data,
     metadata,
 )
-from galaxy.datatypes._protocols import HasFileNameProperty
+from galaxy.datatypes._protocols import (
+    Dataset_t2,
+    HasFileNameProperty,
+)
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -374,27 +377,27 @@ class TabularData(Text):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: "DatasetInstance", **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return ColumnarDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: "DatasetInstance", **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetColumnarDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetColumnarDataProvider(dataset, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return DictDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetDictDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetDictDataProvider(dataset, deliminator=delimiter, **settings)
@@ -865,55 +868,55 @@ class Sam(Tabular, _BamOrSam):
     # sam does not use '#' to indicate comments/headers - we need to strip out those headers from the std. providers
     # TODO:?? seems like there should be an easier way to do this - metadata.comment_char?
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: "DatasetInstance", **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> FilteredLineDataProvider:
         settings["comment_char"] = "@"
         return super().line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: "DatasetInstance", **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
         settings["comment_char"] = "@"
         return super().regex_line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: "DatasetInstance", **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: "DatasetInstance", **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         settings["comment_char"] = "@"
         return super().dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetDictDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: "DatasetInstance", **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         headers_source = RegexLineDataProvider(dataset_source, regex_list=["^@"])
         return RegexLineDataProvider(headers_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", dict_dataprovider.settings)
-    def id_seq_qual_dataprovider(self, dataset: "DatasetInstance", **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
         # provided as an example of a specified column dict (w/o metadata)
         settings["indeces"] = [0, 9, 10]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, True, **settings)
 
@@ -994,11 +997,11 @@ class Pileup(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1083,11 +1086,11 @@ class BaseVcf(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 1, 1, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 

From 7cb3920478f718eddaa4339cb8245a5b5b0dd185 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 12 Dec 2022 17:32:16 -0500
Subject: [PATCH 064/350] Start removing HDA from data.py

---
 lib/galaxy/datatypes/_protocols.py | 15 +++++++++++++++
 lib/galaxy/datatypes/data.py       |  6 ++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index a828a66ad5f..a904b38f0b9 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -49,3 +49,18 @@ class Dataset_t1(HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
 class Dataset_t2(HasMetadata, HasFileNameProperty, Protocol):
     datatype: Any
     ext: str  # TODO reconcile: ext vs. extension
+
+
+class Dataset_t3(Protocol):
+    hid: str
+    ext: str  # TODO reconcile: ext vs. extension
+
+
+class Dataset_t4(Protocol):
+    hid: str
+    name: str
+    extension: str  # TODO reconcile: ext vs. extension
+
+
+class Dataset_t5(HasFileNameProperty, Dataset_t4, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index f9abc777f09..4813d3cad3e 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -26,6 +26,8 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t1,
     Dataset_t2,
+    Dataset_t3,
+    Dataset_t4,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -597,7 +599,7 @@ class Data(metaclass=DataMeta):
 
     def _download_filename(
         self,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t4,
         to_ext: Optional[str] = None,
         hdca: Optional["HistoryDatasetCollectionAssociation"] = None,
         element_identifier: Optional[str] = None,
@@ -771,7 +773,7 @@ class Data(metaclass=DataMeta):
     def convert_dataset(
         self,
         trans,
-        original_dataset: "HistoryDatasetAssociation",
+        original_dataset: Dataset_t3,
         target_type: str,
         return_output: bool = False,
         visible: bool = True,

From ef6fa562757f38718c2c4ff2f4a73f9567024360 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 10:46:46 -0500
Subject: [PATCH 065/350] Remove DatasetInstance from display_info

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/data.py       | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index a904b38f0b9..d099767fbbe 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -26,6 +26,10 @@ class HasMetadata(Protocol):
     metadata: Any
 
 
+class HasInfo(Protocol):
+    info: str
+
+
 class HasCreatingJobProperty(Protocol):
     @property
     def creating_job(self):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 4813d3cad3e..26cddaa0aa2 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -32,6 +32,7 @@ from galaxy.datatypes._protocols import (
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
     HasFileNameProperty,
+    HasInfo,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -640,7 +641,7 @@ class Data(metaclass=DataMeta):
         except Exception:
             return "name unavailable"
 
-    def display_info(self, dataset: "DatasetInstance") -> str:
+    def display_info(self, dataset: HasInfo) -> str:
         """Returns formatted html of dataset info"""
         try:
             # Change new line chars to html

From e08af7de3a786a88aeaf4d25e9e73988a483fe92 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 10:49:16 -0500
Subject: [PATCH 066/350] Remove DatasetInstance from display_name

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/data.py       | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index d099767fbbe..2eb3558b98d 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -30,6 +30,10 @@ class HasInfo(Protocol):
     info: str
 
 
+class HasName(Protocol):
+    name: str
+
+
 class HasCreatingJobProperty(Protocol):
     @property
     def creating_job(self):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 26cddaa0aa2..53f6e882ad9 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -33,6 +33,7 @@ from galaxy.datatypes._protocols import (
     HasCreatingJobProperty,
     HasFileNameProperty,
     HasInfo,
+    HasName,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -634,7 +635,7 @@ class Data(metaclass=DataMeta):
 
         return string.Template(filename_pattern).substitute(**template_values)
 
-    def display_name(self, dataset: "DatasetInstance") -> str:
+    def display_name(self, dataset: HasName) -> str:
         """Returns formatted html of dataset name"""
         try:
             return escape(unicodify(dataset.name, "utf-8"))

From e47c94a95686fbf1465c74f640efa82f0c2a320c Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 10:50:50 -0500
Subject: [PATCH 067/350] Refactor protocols

---
 lib/galaxy/datatypes/_protocols.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 2eb3558b98d..55777bd6cbd 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -49,8 +49,7 @@ class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protoco
     ...
 
 
-class Dataset_t1(HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
-    name: str
+class Dataset_t1(HasName, HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
     extension: str  # TODO reconcile: ext vs. extension
 
 
@@ -64,9 +63,8 @@ class Dataset_t3(Protocol):
     ext: str  # TODO reconcile: ext vs. extension
 
 
-class Dataset_t4(Protocol):
+class Dataset_t4(HasName, Protocol):
     hid: str
-    name: str
     extension: str  # TODO reconcile: ext vs. extension
 
 

From c0fb64bba38a1d2656e15755efb3c6d820645d93 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 12:06:26 -0500
Subject: [PATCH 068/350] Remove DatasetInstance from interval dataprovider*
 methods

---
 lib/galaxy/datatypes/interval.py | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 83cc770d547..0e3622633c3 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,7 +22,10 @@ from bx.intervals.io import (
 
 from galaxy import util
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import HasId
+from galaxy.datatypes._protocols import (
+    Dataset_t2,
+    HasId,
+)
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
     DatasetDataProvider,
@@ -404,20 +407,20 @@ class Interval(Tabular):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: "DatasetInstance", **settings) -> IntervalDataProvider:
+    def interval_dataprovider(self, dataset: Dataset_t2, **settings) -> IntervalDataProvider:
         return IntervalDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> IntervalDataProvider:
+    def interval_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> IntervalDataProvider:
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -1033,20 +1036,20 @@ class Gff(Tabular, _RemoteCallMixin):
     # ------------- Dataproviders
     # redefine bc super is Tabular
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 3, 4, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: "DatasetInstance", **settings):
+    def interval_dataprovider(self, dataset: Dataset_t2, **settings):
         return IntervalDataProvider(dataset, 0, 3, 4, 6, 2, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: "DatasetInstance", **settings):
+    def interval_dict_dataprovider(self, dataset: Dataset_t2, **settings):
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -1444,12 +1447,12 @@ class Wiggle(Tabular, _RemoteCallMixin):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("wiggle", WiggleDataProvider.settings)
-    def wiggle_dataprovider(self, dataset: "DatasetInstance", **settings) -> WiggleDataProvider:
+    def wiggle_dataprovider(self, dataset: Dataset_t2, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return WiggleDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("wiggle-dict", WiggleDataProvider.settings)
-    def wiggle_dict_dataprovider(self, dataset: "DatasetInstance", **settings) -> WiggleDataProvider:
+    def wiggle_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         settings["named_columns"] = True
         return WiggleDataProvider(dataset_source, **settings)

From 61a3355d92c758ee187e2e0149275a3175e46ff6 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 12:09:24 -0500
Subject: [PATCH 069/350] Remove DatasetInstance from missing_meta

---
 lib/galaxy/datatypes/data.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 53f6e882ad9..c335476a11b 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -33,6 +33,7 @@ from galaxy.datatypes._protocols import (
     HasCreatingJobProperty,
     HasFileNameProperty,
     HasInfo,
+    HasMetadata,
     HasName,
 )
 from galaxy.datatypes.metadata import (
@@ -254,9 +255,7 @@ class Data(metaclass=DataMeta):
     def set_meta(self, dataset: "DatasetInstance", *, overwrite: bool = True, **kwd) -> None:
         """Unimplemented method, allows guessing of metadata from contents of file"""
 
-    def missing_meta(
-        self, dataset: "DatasetInstance", check: Optional[List] = None, skip: Optional[List] = None
-    ) -> bool:
+    def missing_meta(self, dataset: HasMetadata, check: Optional[List] = None, skip: Optional[List] = None) -> bool:
         """
         Checks for empty metadata values.
         Returns False if no non-optional metadata is missing and the missing metadata key otherwise.

From a92147acbb5a43cabeb5b248a330a7d01df5453e Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 12:14:08 -0500
Subject: [PATCH 070/350] Remove DatasetInstance from graph.py dataprovider*
 methods

---
 lib/galaxy/datatypes/graph.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index babdb0c8489..4a14f3828b5 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -7,6 +7,7 @@ from typing import (
     TYPE_CHECKING,
 )
 
+from galaxy.datatypes._protocols import Dataset_t2
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -63,7 +64,7 @@ class Xgmml(xml.GenericXml):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", XMLDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: "DatasetInstance", **settings) -> "XGMMLGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: Dataset_t2, **settings) -> "XGMMLGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return XGMMLGraphDataProvider(dataset_source, **settings)
 
@@ -103,7 +104,7 @@ class Sif(tabular.Tabular):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", ColumnarDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: "DatasetInstance", **settings) -> "SIFGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: Dataset_t2, **settings) -> "SIFGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return SIFGraphDataProvider(dataset_source, **settings)
 

From 3f6a7c5c704fab3120d5b4e60f995b1503ee1a1b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 12:23:48 -0500
Subject: [PATCH 071/350] Remove DatasetInstance from to_archive

---
 lib/galaxy/datatypes/_protocols.py | 5 +++++
 lib/galaxy/datatypes/binary.py     | 3 ++-
 lib/galaxy/datatypes/data.py       | 3 ++-
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 55777bd6cbd..a9ee8b1ba7b 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -70,3 +70,8 @@ class Dataset_t4(HasName, Protocol):
 
 class Dataset_t5(HasFileNameProperty, Dataset_t4, Protocol):
     ...
+
+
+class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, Protocol):
+    datatype: Any
+    extension: str  # TODO reconcile: ext vs. extension
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 37f26f53b53..e112173a1be 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -35,6 +35,7 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
+    Dataset_t6,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import (
@@ -563,7 +564,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return f"Binary bam alignments file ({nice_size(dataset.get_size())})"
 
-    def to_archive(self, dataset: "DatasetInstance", name: str = "") -> Iterable:
+    def to_archive(self, dataset: Dataset_t6, name: str = "") -> Iterable:
         rel_paths = []
         file_paths = []
         rel_paths.append(f"{name or dataset.file_name}.{dataset.extension}")
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index c335476a11b..dad85ea30a8 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -28,6 +28,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t3,
     Dataset_t4,
+    Dataset_t6,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -411,7 +412,7 @@ class Data(metaclass=DataMeta):
         headers["Content-Disposition"] = f'attachment; filename="{filename}"'
         return open(dataset.file_name, mode="rb"), headers
 
-    def to_archive(self, dataset: "DatasetInstance", name: str = "") -> Iterable:
+    def to_archive(self, dataset: Dataset_t6, name: str = "") -> Iterable:
         """
         Collect archive paths and file handles that need to be exported when archiving `dataset`.
 

From 4176de98216a9f3c0ab9b9ee64f1d4dbab2cd49d Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 12:25:44 -0500
Subject: [PATCH 072/350] Remove DatasetInstance from xml.py dataprovider*
 methods

---
 lib/galaxy/datatypes/xml.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index 00c1fe94ca0..c49c30d47e2 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -9,6 +9,7 @@ from typing import (
 )
 
 from galaxy import util
+from galaxy.datatypes._protocols import Dataset_t2
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
 from galaxy.datatypes.metadata import MetadataElement
@@ -81,7 +82,7 @@ class GenericXml(data.Text):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("xml", XMLDataProvider.settings)
-    def xml_dataprovider(self, dataset: "DatasetInstance", **settings) -> XMLDataProvider:
+    def xml_dataprovider(self, dataset: Dataset_t2, **settings) -> XMLDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return XMLDataProvider(dataset_source, **settings)
 

From ba9c040251835373269cd8d482bf47598fc799d1 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 13:43:18 -0500
Subject: [PATCH 073/350] Remove DatasetInstance from handle_dataset_as_image

---
 lib/galaxy/datatypes/_protocols.py | 8 ++++++++
 lib/galaxy/datatypes/data.py       | 3 ++-
 lib/galaxy/datatypes/images.py     | 7 +++++--
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index a9ee8b1ba7b..7d02a18df62 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -34,6 +34,10 @@ class HasName(Protocol):
     name: str
 
 
+class HasDataset(Protocol):
+    dataset: Any  # TODO tighten
+
+
 class HasCreatingJobProperty(Protocol):
     @property
     def creating_job(self):
@@ -75,3 +79,7 @@ class Dataset_t5(HasFileNameProperty, Dataset_t4, Protocol):
 class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, Protocol):
     datatype: Any
     extension: str  # TODO reconcile: ext vs. extension
+
+
+class Dataset_t7(HasDataset, HasName, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index dad85ea30a8..69c4179ef26 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -29,6 +29,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t3,
     Dataset_t4,
     Dataset_t6,
+    Dataset_t7,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -949,7 +950,7 @@ class Data(metaclass=DataMeta):
                 mime = DEFAULT_MIME_TYPE
         headers["content-type"] = mime
 
-    def handle_dataset_as_image(self, hda: "DatasetInstance") -> str:
+    def handle_dataset_as_image(self, hda: Dataset_t7) -> str:
         raise Exception("Unimplemented Method")
 
     def __getstate__(self) -> Dict[str, Any]:
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 829ca50fc32..6bafa94659c 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -13,7 +13,10 @@ import mrcfile
 import numpy as np
 import tifffile
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t7,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
     FileParameter,
@@ -68,7 +71,7 @@ class Image(data.Data):
         """Determine if the file is in this format"""
         return check_image_type(filename, self.image_formats)
 
-    def handle_dataset_as_image(self, hda: "DatasetInstance") -> str:
+    def handle_dataset_as_image(self, hda: Dataset_t7) -> str:
         dataset = hda.dataset
         name = hda.name or ""
         with open(dataset.file_name, "rb") as f:

From 559fcddfce3c977ccc773a8e0a449d6a97f45f29 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 14:39:26 -0500
Subject: [PATCH 074/350] Remove DatasetInstance from make_html_peek_rows

---
 lib/galaxy/datatypes/_protocols.py | 11 +++++++++++
 lib/galaxy/datatypes/tabular.py    |  3 ++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 7d02a18df62..e12b8a3f6a6 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -18,6 +18,12 @@ class HasFileNameProperty(Protocol):
         ...
 
 
+class HasPeekProperty(Protocol):
+    @property
+    def peek(self):
+        ...
+
+
 class HasId(Protocol):
     id: int
 
@@ -83,3 +89,8 @@ class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, Pr
 
 class Dataset_t7(HasDataset, HasName, Protocol):
     ...
+
+
+class Dataset_t8(HasMetadata, HasId, HasPeekProperty, Protocol):
+    def set_peek(self) -> None:
+        ...
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 68e619f2aa7..e724c43a059 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -32,6 +32,7 @@ from galaxy.datatypes import (
 )
 from galaxy.datatypes._protocols import (
     Dataset_t2,
+    Dataset_t8,
     HasFileNameProperty,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -304,7 +305,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek header: {util.unicodify(exc)}")
         return "".join(out)
 
-    def make_html_peek_rows(self, dataset: "DatasetInstance", skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_peek_rows(self, dataset: Dataset_t8, skipchars: Optional[List] = None, **kwargs) -> str:
         if skipchars is None:
             skipchars = []
         out = []

From 5e075e0346788e07d0109bd31debc22535183e61 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 14:57:50 -0500
Subject: [PATCH 075/350] Remove DatasetInstance from make_html_peek_header

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/tabular.py    | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index e12b8a3f6a6..279e5e0314a 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -94,3 +94,7 @@ class Dataset_t7(HasDataset, HasName, Protocol):
 class Dataset_t8(HasMetadata, HasId, HasPeekProperty, Protocol):
     def set_peek(self) -> None:
         ...
+
+
+class Dataset_t9(HasMetadata, HasId, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index e724c43a059..35567059ffc 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -33,6 +33,7 @@ from galaxy.datatypes import (
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t8,
+    Dataset_t9,
     HasFileNameProperty,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -251,7 +252,7 @@ class TabularData(Text):
 
     def make_html_peek_header(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t9,
         skipchars: Optional[List] = None,
         column_names: Optional[List] = None,
         column_number_format: str = "%s",

From 30b9815388b429b2f9ae880fe8a426ac7e39f599 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 15:17:23 -0500
Subject: [PATCH 076/350] Remove DatasetInstance from make_html_table

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/genetics.py   | 7 +++++--
 lib/galaxy/datatypes/mothur.py     | 3 ++-
 lib/galaxy/datatypes/sequence.py   | 3 ++-
 lib/galaxy/datatypes/tabular.py    | 5 +++--
 5 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 279e5e0314a..46b2f5e924b 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -98,3 +98,7 @@ class Dataset_t8(HasMetadata, HasId, HasPeekProperty, Protocol):
 
 class Dataset_t9(HasMetadata, HasId, Protocol):
     ...
+
+
+class Dataset_t10(Dataset_t8, HasFileNameProperty, HasName, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 2afb8e74677..895e8d0204f 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -28,7 +28,10 @@ from urllib.parse import quote_plus
 from markupsafe import escape
 
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t10,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.data import (
     DatatypeValidation,
     Text,
@@ -142,7 +145,7 @@ class GenomeGraphs(Tabular):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def make_html_table(self, dataset: "DatasetInstance", **kwargs) -> str:
+    def make_html_table(self, dataset: Dataset_t10, **kwargs) -> str:
         """
         Create HTML table, used for displaying peek
         """
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index a82771dcd8f..c6232fad9c5 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -9,6 +9,7 @@ from typing import (
     TYPE_CHECKING,
 )
 
+from galaxy.datatypes._protocols import Dataset_t10
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -1072,7 +1073,7 @@ class SffFlow(Tabular):
         except Exception as e:
             log.warning(f"SffFlow set_meta {e}")
 
-    def make_html_table(self, dataset: "DatasetInstance", skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_table(self, dataset: Dataset_t10, skipchars: Optional[List] = None, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 040d68ede75..f6e0ad2f996 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -25,6 +25,7 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes import metadata
+from galaxy.datatypes._protocols import Dataset_t10
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.metadata import (
@@ -1067,7 +1068,7 @@ class Maf(Alignment):
         """Returns formated html of peek"""
         return self.make_html_table(dataset)
 
-    def make_html_table(self, dataset: "DatasetInstance", skipchars: Optional[List] = None) -> str:
+    def make_html_table(self, dataset: Dataset_t10, skipchars: Optional[List] = None) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 35567059ffc..55480c0d82b 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -34,6 +34,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t8,
     Dataset_t9,
+    Dataset_t10,
     HasFileNameProperty,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -239,7 +240,7 @@ class TabularData(Text):
             markdown += indicate_data_truncated()
         return pre_formatted_contents(markdown)
 
-    def make_html_table(self, dataset: "DatasetInstance", **kwargs) -> str:
+    def make_html_table(self, dataset: Dataset_t10, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         try:
             out = ['<table cellspacing="0" cellpadding="3">']
@@ -1236,7 +1237,7 @@ class Eland(Tabular):
         ]
 
     def make_html_table(
-        self, dataset: "DatasetInstance", skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
+        self, dataset: Dataset_t10, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
     ) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []

From c71fae5137686f9b86fbfcd00130e117925e03a6 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 15:22:34 -0500
Subject: [PATCH 077/350] Remove DatasetInstance from estimate_file_lines

---
 lib/galaxy/datatypes/_protocols.py | 5 +++++
 lib/galaxy/datatypes/data.py       | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 46b2f5e924b..cdc9434d432 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -102,3 +102,8 @@ class Dataset_t9(HasMetadata, HasId, Protocol):
 
 class Dataset_t10(Dataset_t8, HasFileNameProperty, HasName, Protocol):
     ...
+
+
+class Dataset_t11(HasFileNameProperty, Protocol):
+    def get_size(self) -> str:
+        ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 69c4179ef26..e14550861de 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -30,6 +30,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t4,
     Dataset_t6,
     Dataset_t7,
+    Dataset_t11,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -988,7 +989,7 @@ class Text(Data):
         """
         dataset.metadata.data_lines = self.count_data_lines(dataset)
 
-    def estimate_file_lines(self, dataset: "DatasetInstance") -> Optional[int]:
+    def estimate_file_lines(self, dataset: Dataset_t11) -> Optional[int]:
         """
         Perform a rough estimate by extrapolating number of lines from a small read.
         """

From 63b63dbe5029759e76525d2c1294db7b757a8d98 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 15:26:35 -0500
Subject: [PATCH 078/350] Remove DatasetInstance from get_blurb

---
 lib/galaxy/datatypes/constructive_solid_geometry.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index 528921df9b0..a60bd306a39 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -14,6 +14,7 @@ from typing import (
 
 from galaxy import util
 from galaxy.datatypes import data
+from galaxy.datatypes._protocols import HasMetadata
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -449,7 +450,7 @@ class Vtk:
                 dataset.metadata.cells = int(line.split()[1])
         return dataset, dataset_type
 
-    def get_blurb(self, dataset: "DatasetInstance") -> str:
+    def get_blurb(self, dataset: HasMetadata) -> str:
         blurb = ""
         if dataset.metadata.vtk_version is not None:
             blurb += f"VTK Version {str(dataset.metadata.vtk_version)}"

From 9b27f90c0c662451200988273dcd4eb4f7413755 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 15:37:41 -0500
Subject: [PATCH 079/350] Remove DatasetInstance from get_chunk

---
 lib/galaxy/datatypes/binary.py  | 3 ++-
 lib/galaxy/datatypes/tabular.py | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index e112173a1be..a16599d1b97 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -37,6 +37,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t6,
     GeneratePrimaryFileDataset,
+    HasFileNameProperty,
 )
 from galaxy.datatypes.data import (
     Data,
@@ -607,7 +608,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         # Remove temp file and empty temporary directory
         os.rmdir(tmp_dir)
 
-    def get_chunk(self, trans, dataset: "DatasetInstance", offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
         if not offset == -1:
             try:
                 with pysam.AlignmentFile(dataset.file_name, "rb", check_sq=False) as bamfile:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 55480c0d82b..1cb8d3df92c 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -150,7 +150,7 @@ class TabularData(Text):
         except Exception:
             return False
 
-    def get_chunk(self, trans, dataset: "DatasetInstance", offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
         ck_data, last_read = self._read_chunk(trans, dataset, offset, ck_size)
         return dumps(
             {
@@ -1609,7 +1609,7 @@ class ConnectivityTable(Tabular):
                 i += 1
         return False
 
-    def get_chunk(self, trans, dataset: "DatasetInstance", offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
         ck_data, last_read = self._read_chunk(trans, dataset, offset, ck_size)
         try:
             # The ConnectivityTable format has several derivatives of which one is delimited by (multiple) spaces.

From df5a3110946f3ed673712266bb8e55ac7b46a77a Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 13 Dec 2022 15:50:35 -0500
Subject: [PATCH 080/350] Remove DatasetInstance from init_meta

---
 lib/galaxy/datatypes/binary.py   |  5 +++--
 lib/galaxy/datatypes/data.py     |  2 +-
 lib/galaxy/datatypes/genetics.py |  3 ++-
 lib/galaxy/datatypes/hdf5.py     | 15 ++++++---------
 lib/galaxy/datatypes/interval.py |  3 ++-
 lib/galaxy/datatypes/mothur.py   | 15 +++++++++------
 lib/galaxy/datatypes/sequence.py |  7 +++++--
 lib/galaxy/datatypes/tabular.py  |  3 ++-
 8 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index a16599d1b97..180d169c9c5 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -38,6 +38,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t6,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
+    HasMetadata,
 )
 from galaxy.datatypes.data import (
     Data,
@@ -533,7 +534,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         """
         pysam.merge("-O", "BAM", output_file, *split_files)  # type: ignore[attr-defined]
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
     def sniff(self, filename: str) -> bool:
@@ -2320,7 +2321,7 @@ class SQlite(Binary):
     file_ext = "sqlite"
     edam_format = "format_3621"
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index e14550861de..050243e2c9b 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -245,7 +245,7 @@ class Data(metaclass=DataMeta):
     def groom_dataset_content(self, file_name: str) -> None:
         """This function is called on an output dataset file if dataset_content_needs_grooming returns True."""
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         # Metadata should be left mostly uninitialized.  Dataset will
         # handle returning default values when metadata is not set.
         # copy_from allows metadata to be passed in that will be
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 895e8d0204f..6dacc6e6e5e 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -31,6 +31,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t10,
     GeneratePrimaryFileDataset,
+    HasMetadata,
 )
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -833,7 +834,7 @@ class RexpBase(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         if copy_from:
             dataset.metadata = copy_from.metadata
 
diff --git a/lib/galaxy/datatypes/hdf5.py b/lib/galaxy/datatypes/hdf5.py
index 8c37966bfbd..f44df906b48 100644
--- a/lib/galaxy/datatypes/hdf5.py
+++ b/lib/galaxy/datatypes/hdf5.py
@@ -2,18 +2,15 @@
 
 This datatype was created for use with the iSEE interactive tool.
 """
-from typing import (
-    Optional,
-    TYPE_CHECKING,
-)
+from typing import Optional
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    GeneratePrimaryFileDataset,
+    HasMetadata,
+)
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 class HDF5SummarizedExperiment(Data):
     """Composite datatype to represent HDF5SummarizedExperiment objects.
@@ -54,7 +51,7 @@ class HDF5SummarizedExperiment(Data):
             description="Summarized experiment data array",
         )
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         """Override parent init metadata."""
         Data.init_meta(self, dataset, copy_from=copy_from)
 
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 0e3622633c3..2c37e38ed9e 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -25,6 +25,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     HasId,
+    HasMetadata,
 )
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
@@ -127,7 +128,7 @@ class Interval(Tabular):
         Tabular.__init__(self, **kwd)
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Tabular.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index c6232fad9c5..d005ce2a5ca 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -9,7 +9,10 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes._protocols import Dataset_t10
+from galaxy.datatypes._protocols import (
+    Dataset_t10,
+    HasMetadata,
+)
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -127,7 +130,7 @@ class Sabund(Otu):
         """
         super().__init__(**kwd)
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -171,7 +174,7 @@ class GroupAbund(Otu):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
@@ -352,7 +355,7 @@ class DistanceMatrix(Text):
         no_value="?",
     )
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
@@ -377,7 +380,7 @@ class LowerTriangleDistanceMatrix(DistanceMatrix):
         """Initialize secondary structure map datatype"""
         super().__init__(**kwd)
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -442,7 +445,7 @@ class SquareDistanceMatrix(DistanceMatrix):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index f6e0ad2f996..e7cce7f83ac 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -25,7 +25,10 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import Dataset_t10
+from galaxy.datatypes._protocols import (
+    Dataset_t10,
+    HasMetadata,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.metadata import (
@@ -1012,7 +1015,7 @@ class Maf(Alignment):
         optional=True,
     )
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Alignment.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 1cb8d3df92c..7cf933a63eb 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -36,6 +36,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t9,
     Dataset_t10,
     HasFileNameProperty,
+    HasMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
@@ -944,7 +945,7 @@ class Pileup(Tabular):
     MetadataElement(name="endCol", default=2, desc="End column", param=metadata.ColumnParameter)
     MetadataElement(name="baseCol", default=3, desc="Reference base column", param=metadata.ColumnParameter)
 
-    def init_meta(self, dataset: "DatasetInstance", copy_from: Optional["DatasetInstance"] = None) -> None:
+    def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
     def display_peek(self, dataset: "DatasetInstance") -> str:

From c02886cf689ac3573a255a59275b4849dac97705 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 11:52:21 -0500
Subject: [PATCH 081/350] Remove DatasetInstance from as_ucsc_display_file

---
 lib/galaxy/datatypes/genetics.py | 3 ++-
 lib/galaxy/datatypes/interval.py | 6 +++---
 lib/galaxy/datatypes/tabular.py  | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 6dacc6e6e5e..afb0853d448 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -29,6 +29,7 @@ from markupsafe import escape
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
+    Dataset_t2,
     Dataset_t10,
     GeneratePrimaryFileDataset,
     HasMetadata,
@@ -88,7 +89,7 @@ class GenomeGraphs(Tabular):
         t[0] = "string"
         dataset.metadata.column_types = t
 
-    def as_ucsc_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
         """
         Returns file
         """
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 2c37e38ed9e..8fe68853d10 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -272,7 +272,7 @@ class Interval(Tabular):
             log.exception("Exception caught attempting to generate viewport for dataset '%d'", dataset.id)
         return (None, None, None)
 
-    def as_ucsc_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data"""
         with tempfile.NamedTemporaryFile(delete=False, mode="w") as fh:
             c, s, e, t, n = (
@@ -434,7 +434,7 @@ class BedGraph(Interval):
     track_type = "LineTrack"
     data_sources = {"data": "bigwig", "index": "bigwig"}
 
-    def as_ucsc_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
         """
         Returns file contents as is with no modifications.
         TODO: this is a functional stub and will need to be enhanced moving forward to provide additional support for bedgraph.
@@ -523,7 +523,7 @@ class Bed(Interval):
                         break
             Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def as_ucsc_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data. If bed 6+, treat as interval."""
         for line in open(dataset.file_name):
             line = line.strip()
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 7cf933a63eb..a3664572b01 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -590,7 +590,7 @@ class Tabular(TabularData):
     def as_gbrowse_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
-    def as_ucsc_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
 

From 434615da9736458f0c5d46ab1ce5edee0e6f27be Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 11:55:44 -0500
Subject: [PATCH 082/350] Remove DatasetInstance from as_gbrowse_display_file

---
 lib/galaxy/datatypes/tabular.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index a3664572b01..b3fac070bd7 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -587,7 +587,7 @@ class Tabular(TabularData):
         if column_names is not None:
             dataset.metadata.column_names = column_names
 
-    def as_gbrowse_display_file(self, dataset: "DatasetInstance", **kwd) -> Union[FileObjType, str]:
+    def as_gbrowse_display_file(self, dataset: HasFileNameProperty, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
     def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:

From 3e4e72350e9f62a1c4dc25c78877aa9a6fa0dbae Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 12:05:31 -0500
Subject: [PATCH 083/350] Remove DatasetInstance from as_display_type

---
 lib/galaxy/datatypes/data.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 050243e2c9b..a80e7a48747 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -723,7 +723,7 @@ class Data(metaclass=DataMeta):
         except Exception:
             return "unknown"
 
-    def as_display_type(self, dataset: "DatasetInstance", type: str, **kwd) -> Union[FileObjType, str]:
+    def as_display_type(self, dataset: Dataset_t2, type: str, **kwd) -> Union[FileObjType, str]:
         """Returns modified file contents for a particular display type"""
         try:
             if type in self.get_display_types():

From d8146c225da66d52fe093377116d68b8f30b741f Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 12:37:19 -0500
Subject: [PATCH 084/350] Remove DatasetInstance from displayable, add return
 type

---
 lib/galaxy/datatypes/_protocols.py |  8 ++++++++
 lib/galaxy/datatypes/interval.py   | 11 ++++++-----
 lib/galaxy/datatypes/tabular.py    |  3 ++-
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index cdc9434d432..5d6a8e426fe 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -107,3 +107,11 @@ class Dataset_t10(Dataset_t8, HasFileNameProperty, HasName, Protocol):
 class Dataset_t11(HasFileNameProperty, Protocol):
     def get_size(self) -> str:
         ...
+
+
+class Dataset_t12(HasDataset, HasMetadata, Protocol):
+    state: str
+    states: Any
+
+    def has_data(self) -> bool:
+        ...
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 8fe68853d10..a79ff816478 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -24,6 +24,7 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
+    Dataset_t12,
     HasId,
     HasMetadata,
 )
@@ -193,7 +194,7 @@ class Interval(Tabular):
                     else:
                         empty_line_count += 1
 
-    def displayable(self, dataset: "DatasetInstance"):
+    def displayable(self, dataset: Dataset_t12) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -218,7 +219,7 @@ class Interval(Tabular):
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if not self.displayable(dataset):
+        if not self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
             return (None, None, None)
         try:
             # If column indexes were not passwed, determine from metadata
@@ -890,7 +891,7 @@ class Gff(Tabular, _RemoteCallMixin):
         """
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if self.displayable(dataset):
+        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
             try:
                 seqid = None
                 start = sys.maxsize
@@ -1299,7 +1300,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if self.displayable(dataset):
+        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
             try:
                 chrom = None
                 start = sys.maxsize
@@ -1492,7 +1493,7 @@ class CustomTrack(Tabular):
         variable_step_wig = False
         chrom = None
         span = 1
-        if self.displayable(dataset):
+        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
             try:
                 with open(dataset.file_name) as fh:
                     for line in util.iter_start_of_line(fh, VIEWPORT_READLINE_BUFFER_SIZE):
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index b3fac070bd7..05c48b4bdce 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -35,6 +35,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t8,
     Dataset_t9,
     Dataset_t10,
+    Dataset_t12,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -139,7 +140,7 @@ class TabularData(Text):
         if dataset.metadata.comment_lines:
             dataset.blurb = f"{dataset.blurb}, {util.commaify(str(dataset.metadata.comment_lines))} comments"
 
-    def displayable(self, dataset: "DatasetInstance"):
+    def displayable(self, dataset: Dataset_t12) -> bool:
         try:
             return (
                 not dataset.dataset.purged

From 35f0b0b0e0ce53e9831acbcdd7df7fd0ff9c0b42 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 13:23:42 -0500
Subject: [PATCH 085/350] Remove DatasetInstance from
 get_estimated_display_viewport

---
 lib/galaxy/datatypes/_protocols.py |  6 +++++-
 lib/galaxy/datatypes/interval.py   | 19 ++++++++++---------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 5d6a8e426fe..40431c31eb4 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -110,8 +110,12 @@ class Dataset_t11(HasFileNameProperty, Protocol):
 
 
 class Dataset_t12(HasDataset, HasMetadata, Protocol):
-    state: str
+    state: Any  # TODO tighten (should be property)
     states: Any
 
     def has_data(self) -> bool:
         ...
+
+
+class Dataset_t13(Dataset_t12, HasFileNameProperty, HasId, HasMetadata, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index a79ff816478..3ecc30887af 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -25,6 +25,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t12,
+    Dataset_t13,
     HasId,
     HasMetadata,
 )
@@ -211,7 +212,7 @@ class Interval(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t13,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -219,7 +220,7 @@ class Interval(Tabular):
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if not self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
+        if not self.displayable(dataset):
             return (None, None, None)
         try:
             # If column indexes were not passwed, determine from metadata
@@ -444,7 +445,7 @@ class BedGraph(Interval):
 
     def get_estimated_display_viewport(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t13,
         chrom_col: Optional[int] = 0,
         start_col: Optional[int] = 1,
         end_col: Optional[int] = 2,
@@ -883,7 +884,7 @@ class Gff(Tabular, _RemoteCallMixin):
         return self.make_html_table(dataset, column_names=self.column_names)
 
     def get_estimated_display_viewport(
-        self, dataset: "DatasetInstance"
+        self, dataset: Dataset_t13
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """
         Return a chrom, start, stop tuple for viewing a file.  There are slight differences between gff 2 and gff 3
@@ -891,7 +892,7 @@ class Gff(Tabular, _RemoteCallMixin):
         """
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
+        if self.displayable(dataset):
             try:
                 seqid = None
                 start = sys.maxsize
@@ -1295,12 +1296,12 @@ class Wiggle(Tabular, _RemoteCallMixin):
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
     def get_estimated_display_viewport(
-        self, dataset: "DatasetInstance"
+        self, dataset: Dataset_t13
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
         max_line_count = max(viewport_feature_count, 500)  # maximum number of lines to check; includes comment lines
-        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
+        if self.displayable(dataset):
             try:
                 chrom = None
                 start = sys.maxsize
@@ -1481,7 +1482,7 @@ class CustomTrack(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t13,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -1493,7 +1494,7 @@ class CustomTrack(Tabular):
         variable_step_wig = False
         chrom = None
         span = 1
-        if self.displayable(dataset):  # type: ignore [arg-type]  # TODO FIX BEFORE MERGE
+        if self.displayable(dataset):
             try:
                 with open(dataset.file_name) as fh:
                     for line in util.iter_start_of_line(fh, VIEWPORT_READLINE_BUFFER_SIZE):

From 9d83435ca30bb141a3ab385c98147491ad52b18b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 13:35:58 -0500
Subject: [PATCH 086/350] Remove DatasetInstance from ucsc_links

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/genetics.py   | 3 ++-
 lib/galaxy/datatypes/interval.py   | 9 +++++----
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 40431c31eb4..748ca5c9371 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -119,3 +119,7 @@ class Dataset_t12(HasDataset, HasMetadata, Protocol):
 
 class Dataset_t13(Dataset_t12, HasFileNameProperty, HasId, HasMetadata, Protocol):
     ...
+
+
+class Dataset_t14(Dataset_t13, HasName, Protocol):
+    dbkey: str
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index afb0853d448..0fdbe29e115 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -31,6 +31,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t10,
+    Dataset_t14,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -95,7 +96,7 @@ class GenomeGraphs(Tabular):
         """
         return open(dataset.file_name, "rb")
 
-    def ucsc_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
         """
         from the ever-helpful angie hinrichs angie@soe.ucsc.edu
         a genome graphs call looks like this
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 3ecc30887af..e959b558f28 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -26,6 +26,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t12,
     Dataset_t13,
+    Dataset_t14,
     HasId,
     HasMetadata,
 )
@@ -321,7 +322,7 @@ class Interval(Tabular):
             },
         )
 
-    def ucsc_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
         """
         Generate links to UCSC genome browser sites based on the dbkey
         and content of dataset.
@@ -960,7 +961,7 @@ class Gff(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -1375,7 +1376,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def ucsc_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1544,7 +1545,7 @@ class CustomTrack(Tabular):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:

From 1091d98c3d65bf88072d303da63f2d10abe712a0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 13:40:19 -0500
Subject: [PATCH 087/350] Remove DatasetInstance from get_display_links

---
 lib/galaxy/datatypes/data.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index a80e7a48747..418342088d0 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -31,6 +31,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t6,
     Dataset_t7,
     Dataset_t11,
+    Dataset_t14,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -738,7 +739,7 @@ class Data(metaclass=DataMeta):
         return f"This display type ({type}) is not implemented for this datatype ({dataset.ext})."
 
     def get_display_links(
-        self, dataset: "DatasetInstance", type: str, app, base_url: str, target_frame: str = "_blank", **kwd
+        self, dataset: Dataset_t14, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
     ):
         """
         Returns a list of tuples of (name, link) for a particular display type.  No check on

From 962854048a06fc76a28d2b6094ff64a7349d40af Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 13:46:12 -0500
Subject: [PATCH 088/350] Remove DatasetInstance from gbrowse_links, refactor
 protocols

---
 lib/galaxy/datatypes/_protocols.py | 12 ++++++++++--
 lib/galaxy/datatypes/interval.py   |  5 +++--
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 748ca5c9371..9b9e1dc3432 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -55,6 +55,10 @@ class HasClearAssociatedFiles(Protocol):
         ...
 
 
+class HasDbKey(Protocol):
+    dbkey: str
+
+
 class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
     ...
 
@@ -121,5 +125,9 @@ class Dataset_t13(Dataset_t12, HasFileNameProperty, HasId, HasMetadata, Protocol
     ...
 
 
-class Dataset_t14(Dataset_t13, HasName, Protocol):
-    dbkey: str
+class Dataset_t14(Dataset_t13, HasName, HasDbKey, Protocol):
+    ...
+
+
+class Dataset_t15(Dataset_t13, HasDbKey, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index e959b558f28..d862424cf88 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -27,6 +27,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t12,
     Dataset_t13,
     Dataset_t14,
+    Dataset_t15,
     HasId,
     HasMetadata,
 )
@@ -974,7 +975,7 @@ class Gff(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def gbrowse_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: Dataset_t15, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -1363,7 +1364,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def gbrowse_links(self, dataset: "DatasetInstance", type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: Dataset_t15, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:

From 4b6191556ef774945cdab991ddf122895cbadea8 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 13:51:23 -0500
Subject: [PATCH 089/350] Remove DatasetInstance from get_converter_types,
 refactor protocols

---
 lib/galaxy/datatypes/_protocols.py | 10 ++++++----
 lib/galaxy/datatypes/data.py       |  5 ++---
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 9b9e1dc3432..6cc69e5b2cb 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -59,6 +59,10 @@ class HasDbKey(Protocol):
     dbkey: str
 
 
+class HasExt(Protocol):
+    ext: str  # TODO reconcile: ext vs. extension
+
+
 class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
     ...
 
@@ -67,14 +71,12 @@ class Dataset_t1(HasName, HasExtraFilesPathProperty, HasFileNameProperty, Protoc
     extension: str  # TODO reconcile: ext vs. extension
 
 
-class Dataset_t2(HasMetadata, HasFileNameProperty, Protocol):
+class Dataset_t2(HasMetadata, HasFileNameProperty, HasExt, Protocol):
     datatype: Any
-    ext: str  # TODO reconcile: ext vs. extension
 
 
-class Dataset_t3(Protocol):
+class Dataset_t3(HasExt, Protocol):
     hid: str
-    ext: str  # TODO reconcile: ext vs. extension
 
 
 class Dataset_t4(HasName, Protocol):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 418342088d0..bcbfbded4a1 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -35,6 +35,7 @@ from galaxy.datatypes._protocols import (
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
+    HasExt,
     HasFileNameProperty,
     HasInfo,
     HasMetadata,
@@ -761,9 +762,7 @@ class Data(metaclass=DataMeta):
             )
         return target_frame, []
 
-    def get_converter_types(
-        self, original_dataset: "DatasetInstance", datatypes_registry: "Registry"
-    ) -> Dict[str, Dict]:
+    def get_converter_types(self, original_dataset: HasExt, datatypes_registry: "Registry") -> Dict[str, Dict]:
         """Returns available converters by type for this dataset"""
         return datatypes_registry.get_converters_by_datatype(original_dataset.ext)
 

From f342da34a1671992591212bb6c3cfa75e4fedabd Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 14:20:40 -0500
Subject: [PATCH 090/350] Remove DatasetInstance from
 get_conversion_destination

Also:
- Remove DatasetInstance from find_conversion_destination_for_dataset_by_extensions
- Fix bug (dataset.ext > ext: dataset can be None)
- Add type ignore to model (until we type-check the model)
- Loosen type checking on return type of find_conversion_destination:
  the third item in the tuple is a DatasetInstance, so replace with Any
  to avoid forward ref for now.
---
 lib/galaxy/datatypes/_protocols.py | 5 +++++
 lib/galaxy/datatypes/data.py       | 5 +++--
 lib/galaxy/datatypes/registry.py   | 9 ++++++---
 lib/galaxy/model/__init__.py       | 2 +-
 4 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 6cc69e5b2cb..0d35818d5ed 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -133,3 +133,8 @@ class Dataset_t14(Dataset_t13, HasName, HasDbKey, Protocol):
 
 class Dataset_t15(Dataset_t13, HasDbKey, Protocol):
     ...
+
+
+class Dataset_t16(HasExt, Protocol):
+    def get_converted_files_by_type(self, file_type):
+        ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index bcbfbded4a1..e2c626a2e9b 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -32,6 +32,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t7,
     Dataset_t11,
     Dataset_t14,
+    Dataset_t16,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -767,8 +768,8 @@ class Data(metaclass=DataMeta):
         return datatypes_registry.get_converters_by_datatype(original_dataset.ext)
 
     def find_conversion_destination(
-        self, dataset, accepted_formats: List[str], datatypes_registry, **kwd
-    ) -> Tuple[bool, Optional[str], Optional["DatasetInstance"]]:
+        self, dataset: Dataset_t16, accepted_formats: List[str], datatypes_registry, **kwd
+    ) -> Tuple[bool, Optional[str], Any]:
         """Returns ( direct_match, converted_ext, existing converted dataset )"""
         return datatypes_registry.find_conversion_destination_for_dataset_by_extensions(
             dataset, accepted_formats, **kwd
diff --git a/lib/galaxy/datatypes/registry.py b/lib/galaxy/datatypes/registry.py
index 746761d9a74..f5bda77caf9 100644
--- a/lib/galaxy/datatypes/registry.py
+++ b/lib/galaxy/datatypes/registry.py
@@ -9,16 +9,19 @@ import pkgutil
 from pathlib import Path
 from string import Template
 from typing import (
+    cast,
     Dict,
     List,
     Optional,
     Tuple,
     TYPE_CHECKING,
+    Union,
 )
 
 import yaml
 
 import galaxy.util
+from galaxy.datatypes._protocols import Dataset_t16
 from galaxy.tool_util.edam_util import load_edam_tree
 from galaxy.util import RW_R__R__
 from galaxy.util.bunch import Bunch
@@ -832,7 +835,7 @@ class Registry:
         return None
 
     def find_conversion_destination_for_dataset_by_extensions(
-        self, dataset_or_ext, accepted_formats: List[str], converter_safe: bool = True
+        self, dataset_or_ext: Union[str, Dataset_t16], accepted_formats: List[str], converter_safe: bool = True
     ) -> Tuple[bool, Optional[str], Optional["DatasetInstance"]]:
         """
         returns (direct_match, converted_ext, converted_dataset)
@@ -841,7 +844,7 @@ class Registry:
         """
         if hasattr(dataset_or_ext, "ext"):
             ext = dataset_or_ext.ext
-            dataset = dataset_or_ext
+            dataset = cast(Dataset_t16, dataset_or_ext)
         else:
             ext = dataset_or_ext
             dataset = None
@@ -854,7 +857,7 @@ class Registry:
             convert_ext_datatype = self.get_datatype_by_extension(convert_ext)
             if convert_ext_datatype is None:
                 self.log.warning(
-                    f"Datatype class not found for extension '{convert_ext}', which is used as target for conversion from datatype '{dataset.ext}'"
+                    f"Datatype class not found for extension '{convert_ext}', which is used as target for conversion from datatype '{ext}'"
                 )
             elif convert_ext_datatype.matches_any(accepted_formats):
                 converted_dataset = dataset and dataset.get_converted_files_by_type(convert_ext)
diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index b6416d2d13b..ad491fd6c5f 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -4237,7 +4237,7 @@ class DatasetInstance(UsesCreateAndUpdateTime, _HasTable):
         self, accepted_formats: List[str], **kwd
     ) -> Tuple[bool, Optional[str], Optional["DatasetInstance"]]:
         """Returns ( target_ext, existing converted dataset )"""
-        return self.datatype.find_conversion_destination(self, accepted_formats, _get_datatypes_registry(), **kwd)
+        return self.datatype.find_conversion_destination(self, accepted_formats, _get_datatypes_registry(), **kwd)  # type: ignore[arg-type]
 
     def add_validation_error(self, validation_error):
         self.validation_errors.append(validation_error)

From e9458afd416d443fd0c5e936e627cf38671868e0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 14:41:35 -0500
Subject: [PATCH 091/350] Remove DatasetInstance from display_as_markdown

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/data.py       | 3 ++-
 lib/galaxy/datatypes/tabular.py    | 3 ++-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 0d35818d5ed..f0826d4df43 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -138,3 +138,7 @@ class Dataset_t15(Dataset_t13, HasDbKey, Protocol):
 class Dataset_t16(HasExt, Protocol):
     def get_converted_files_by_type(self, file_type):
         ...
+
+
+class Dataset_t17(Dataset_t7, Dataset_t10, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index e2c626a2e9b..950fa42e5e2 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -33,6 +33,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t11,
     Dataset_t14,
     Dataset_t16,
+    Dataset_t17,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -555,7 +556,7 @@ class Data(metaclass=DataMeta):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: "DatasetInstance") -> str:
+    def display_as_markdown(self, dataset_instance: Dataset_t17) -> str:
         """Prepare for embedding dataset into a basic Markdown document.
 
         This is a somewhat experimental interface and should not be implemented
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 05c48b4bdce..3a8d680ecc3 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -36,6 +36,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t9,
     Dataset_t10,
     Dataset_t12,
+    Dataset_t17,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -234,7 +235,7 @@ class TabularData(Text):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: "DatasetInstance") -> str:
+    def display_as_markdown(self, dataset_instance: Dataset_t17) -> str:
         with open(dataset_instance.file_name) as f:
             contents = f.read(data.DEFAULT_MAX_PEEK_SIZE)
         markdown = self.make_html_table(dataset_instance, peek=contents)

From 658ba2461344843169bb9f36b0701aaa4d5deb54 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 14:49:11 -0500
Subject: [PATCH 092/350] Remove DatasetInstance from
 get_writable_files_for_dataset

---
 lib/galaxy/datatypes/data.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 950fa42e5e2..66a31daa10d 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -860,7 +860,7 @@ class Data(metaclass=DataMeta):
             files[key] = value
         return files
 
-    def get_writable_files_for_dataset(self, dataset: "DatasetInstance") -> Dict:
+    def get_writable_files_for_dataset(self, dataset: Optional[HasMetadata]) -> Dict:
         files = {}
         if self.composite_type != "auto_primary_file":
             files[self.primary_file_name] = self.__new_composite_file(self.primary_file_name)
@@ -868,7 +868,7 @@ class Data(metaclass=DataMeta):
             files[key] = value
         return files
 
-    def get_composite_files(self, dataset=None):
+    def get_composite_files(self, dataset: Optional[HasMetadata] = None):
         def substitute_composite_key(key, composite_file):
             if composite_file.substitute_name_with_metadata:
                 if dataset:

From 62cd3636918a0417698d7bbfdd2360bdbaf6e08c Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 14:50:47 -0500
Subject: [PATCH 093/350] Remove DatasetInstance from set_index_file

---
 lib/galaxy/datatypes/binary.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 180d169c9c5..600b33a9bfa 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -983,7 +983,7 @@ class CRAM(Binary):
             log.warning("%s, get_cram_version Exception: %s", self, exc)
             return -1, -1
 
-    def set_index_file(self, dataset: "DatasetInstance", index_file) -> bool:
+    def set_index_file(self, dataset: HasFileNameProperty, index_file) -> bool:
         try:
             pysam.index(dataset.file_name, index_file.file_name)  # type: ignore [attr-defined]
             return True

From 3b63bf24ccef67e5808644c997e970de72fca144 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 14:53:51 -0500
Subject: [PATCH 094/350] Remove DatasetInstance from set_attribute_metadata

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/interval.py   | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index f0826d4df43..7cc7a524503 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -142,3 +142,7 @@ class Dataset_t16(HasExt, Protocol):
 
 class Dataset_t17(Dataset_t7, Dataset_t10, Protocol):
     ...
+
+
+class Dataset_t18(HasFileNameProperty, HasMetadata, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index d862424cf88..81940958e6d 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -28,6 +28,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t13,
     Dataset_t14,
     Dataset_t15,
+    Dataset_t18,
     HasId,
     HasMetadata,
 )
@@ -823,7 +824,7 @@ class Gff(Tabular, _RemoteCallMixin):
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
-    def set_attribute_metadata(self, dataset: "DatasetInstance") -> None:
+    def set_attribute_metadata(self, dataset: Dataset_t18) -> None:
         """
         Sets metadata elements for dataset's attributes.
         """

From 2d14c816c58b8cfe74da9a065b713511c528cb64 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 15:08:49 -0500
Subject: [PATCH 095/350] Remove DatasetInstance from validate; refactor
 protocols

---
 lib/galaxy/datatypes/_protocols.py | 15 +++++++++++----
 lib/galaxy/datatypes/binary.py     |  3 ++-
 lib/galaxy/datatypes/data.py       |  5 +++--
 lib/galaxy/datatypes/genetics.py   |  3 ++-
 lib/galaxy/datatypes/interval.py   |  3 ++-
 lib/galaxy/datatypes/sequence.py   |  3 ++-
 lib/galaxy/datatypes/tabular.py    |  3 ++-
 7 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 7cc7a524503..b5df4bc4ee6 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -63,6 +63,10 @@ class HasExt(Protocol):
     ext: str  # TODO reconcile: ext vs. extension
 
 
+class HasDatatype(Protocol):
+    datatype: Any
+
+
 class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
     ...
 
@@ -71,8 +75,8 @@ class Dataset_t1(HasName, HasExtraFilesPathProperty, HasFileNameProperty, Protoc
     extension: str  # TODO reconcile: ext vs. extension
 
 
-class Dataset_t2(HasMetadata, HasFileNameProperty, HasExt, Protocol):
-    datatype: Any
+class Dataset_t2(HasMetadata, HasFileNameProperty, HasExt, HasDatatype, Protocol):
+    ...
 
 
 class Dataset_t3(HasExt, Protocol):
@@ -88,8 +92,7 @@ class Dataset_t5(HasFileNameProperty, Dataset_t4, Protocol):
     ...
 
 
-class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, Protocol):
-    datatype: Any
+class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, HasDatatype, Protocol):
     extension: str  # TODO reconcile: ext vs. extension
 
 
@@ -146,3 +149,7 @@ class Dataset_t17(Dataset_t7, Dataset_t10, Protocol):
 
 class Dataset_t18(HasFileNameProperty, HasMetadata, Protocol):
     ...
+
+
+class Dataset_t19(Dataset_t18, HasDatatype, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 600b33a9bfa..cf292118c2d 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -36,6 +36,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t6,
+    Dataset_t19,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
     HasMetadata,
@@ -685,7 +686,7 @@ class BamNative(CompressedArchive, _BamOrSam):
                 headers,
             )
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         if not BamNative.is_bam(dataset.file_name):
             return DatatypeValidation.invalid("This dataset does not appear to a BAM file.")
         elif self.dataset_content_needs_grooming(dataset.file_name):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 66a31daa10d..22a822b78a8 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -34,6 +34,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t14,
     Dataset_t16,
     Dataset_t17,
+    Dataset_t19,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -125,7 +126,7 @@ class DatatypeValidation:
         return f"DatatypeValidation[state={self.state},message={self.message}]"
 
 
-def validate(dataset_instance: "DatasetInstance") -> DatatypeValidation:
+def validate(dataset_instance: Dataset_t19) -> DatatypeValidation:
     try:
         datatype_validation = dataset_instance.datatype.validate(dataset_instance)
     except Exception as e:
@@ -929,7 +930,7 @@ class Data(metaclass=DataMeta):
             return self.dataproviders[data_format](self, dataset, **settings)
         raise p_dataproviders.exceptions.NoProviderAvailable(self, data_format)
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 0fdbe29e115..290322df5ec 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -32,6 +32,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t10,
     Dataset_t14,
+    Dataset_t19,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -179,7 +180,7 @@ class GenomeGraphs(Tabular):
         except Exception as exc:
             return f"Can't create peek {exc}"
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         """
         Validate a gg file - all numeric after header row
         """
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 81940958e6d..fe8083fdb45 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -29,6 +29,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t14,
     Dataset_t15,
     Dataset_t18,
+    Dataset_t19,
     HasId,
     HasMetadata,
 )
@@ -358,7 +359,7 @@ class Interval(Tabular):
             ret_val.append((site_name, link))
         return ret_val
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         """Validate an interval file using the bx GenomicIntervalReader"""
         c, s, e, t = (
             dataset.metadata.chromCol,
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index e7cce7f83ac..6ba07d424de 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -27,6 +27,7 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t10,
+    Dataset_t19,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -878,7 +879,7 @@ class BaseFastq(Sequence):
                     return True
         return False
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         headers = iter_headers(dataset.file_name, sep="\n", count=-1)
         # check to see if the base qualities match
         if not self.quality_check(headers):
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 3a8d680ecc3..35e379312c5 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -37,6 +37,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t10,
     Dataset_t12,
     Dataset_t17,
+    Dataset_t19,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -1082,7 +1083,7 @@ class BaseVcf(Tabular):
         if exit_code != 0:
             raise Exception(f"Error merging VCF files: {stderr!r}")
 
-    def validate(self, dataset: "DatasetInstance", **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
         def validate_row(row):
             if len(row) < 8:
                 raise Exception("Not enough columns in row %s" % row.join("\t"))

From a8263b16e349b8936229477fd10389fdd28dad56 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 15:52:04 -0500
Subject: [PATCH 096/350] Remove DatasetInstance from display_peek

---
 lib/galaxy/datatypes/_protocols.py            |  8 ++
 lib/galaxy/datatypes/annotation.py            |  5 +-
 lib/galaxy/datatypes/anvio.py                 |  7 +-
 lib/galaxy/datatypes/binary.py                | 75 ++++++++++---------
 lib/galaxy/datatypes/blast.py                 |  5 +-
 .../datatypes/constructive_solid_geometry.py  |  9 ++-
 lib/galaxy/datatypes/data.py                  |  3 +-
 lib/galaxy/datatypes/flow.py                  |  3 +-
 lib/galaxy/datatypes/genetics.py              |  5 +-
 lib/galaxy/datatypes/gis.py                   |  7 +-
 lib/galaxy/datatypes/interval.py              |  9 ++-
 lib/galaxy/datatypes/isa.py                   |  3 +-
 lib/galaxy/datatypes/molecules.py             |  3 +-
 lib/galaxy/datatypes/msa.py                   |  5 +-
 lib/galaxy/datatypes/neo4j.py                 |  7 +-
 lib/galaxy/datatypes/ngsindex.py              |  7 +-
 lib/galaxy/datatypes/plant_tribes.py          |  5 +-
 lib/galaxy/datatypes/proteomics.py            | 17 +++--
 lib/galaxy/datatypes/qiime2.py                |  7 +-
 lib/galaxy/datatypes/sequence.py              |  3 +-
 lib/galaxy/datatypes/spaln.py                 |  7 +-
 lib/galaxy/datatypes/tabular.py               | 11 +--
 lib/galaxy/datatypes/text.py                  |  3 +-
 lib/galaxy/datatypes/tracks.py                |  7 +-
 24 files changed, 135 insertions(+), 86 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index b5df4bc4ee6..2b3873c4ae1 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -153,3 +153,11 @@ class Dataset_t18(HasFileNameProperty, HasMetadata, Protocol):
 
 class Dataset_t19(Dataset_t18, HasDatatype, Protocol):
     ...
+
+
+class Dataset_t20(HasMetadata, HasFileNameProperty, HasName, HasId, HasPeekProperty, Protocol):
+    def set_peek(self) -> None:
+        ...
+
+    def get_size(self) -> str:
+        ...
diff --git a/lib/galaxy/datatypes/annotation.py b/lib/galaxy/datatypes/annotation.py
index de5d113ff78..eae090b819d 100644
--- a/lib/galaxy/datatypes/annotation.py
+++ b/lib/galaxy/datatypes/annotation.py
@@ -2,6 +2,7 @@ import logging
 import tarfile
 from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.binary import CompressedArchive
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -32,7 +33,7 @@ class SnapHmm(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -62,7 +63,7 @@ class Augustus(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index c46ae06c338..931e2127255 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -10,7 +10,10 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
 
@@ -77,7 +80,7 @@ class AnvioComposite(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index cf292118c2d..e51b4136e07 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -37,6 +37,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t6,
     Dataset_t19,
+    Dataset_t20,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
     HasMetadata,
@@ -145,7 +146,7 @@ class Ab1(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -269,7 +270,7 @@ class CompressedArchive(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -326,7 +327,7 @@ class Bref3(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -386,7 +387,7 @@ class CompressedZipArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -561,7 +562,7 @@ class BamNative(CompressedArchive, _BamOrSam):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1137,7 +1138,7 @@ class H5(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1243,7 +1244,7 @@ class Loom(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1528,7 +1529,7 @@ class Anndata(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1581,7 +1582,7 @@ class Grib(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1624,7 +1625,7 @@ class GmxBinary(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1791,7 +1792,7 @@ class Biom2(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1844,7 +1845,7 @@ class Cool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1904,7 +1905,7 @@ class MCool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2012,7 +2013,7 @@ class H5MLM(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2182,7 +2183,7 @@ class Scf(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2210,7 +2211,7 @@ class Sff(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2247,7 +2248,7 @@ class BigWig(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2287,7 +2288,7 @@ class TwoBit(Binary):
         else:
             return super().set_peek(dataset)
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2398,7 +2399,7 @@ class SQlite(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2473,7 +2474,7 @@ class GeminiSQLite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2560,7 +2561,7 @@ class CuffDiffSQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2890,7 +2891,7 @@ class IdpDB(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2992,7 +2993,7 @@ class NcbiTaxonomySQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3036,7 +3037,7 @@ class ExcelXls(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3063,7 +3064,7 @@ class Sra(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3460,7 +3461,7 @@ class PostgresqlArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3514,7 +3515,7 @@ class Fast5Archive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3623,7 +3624,7 @@ class SearchGuiArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3646,7 +3647,7 @@ class NetCDF(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3702,7 +3703,7 @@ class Dcd(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3754,7 +3755,7 @@ class Vel(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3926,7 +3927,7 @@ class BafTar(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4036,7 +4037,7 @@ class Pretext(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4080,7 +4081,7 @@ class JP2(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4136,7 +4137,7 @@ class Npz(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4213,7 +4214,7 @@ class HexrdImagesNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4275,7 +4276,7 @@ class HexrdEtaOmeNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index fb571a023bb..1ac8f916956 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -41,6 +41,7 @@ from typing import (
     TYPE_CHECKING,
 )
 
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -204,7 +205,7 @@ class _BlastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -381,7 +382,7 @@ class LastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index a60bd306a39..5c7a0c1a88c 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -14,7 +14,10 @@ from typing import (
 
 from galaxy import util
 from galaxy.datatypes import data
-from galaxy.datatypes._protocols import HasMetadata
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    HasMetadata,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -134,7 +137,7 @@ class Ply:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -468,7 +471,7 @@ class Vtk:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 22a822b78a8..d84770304ab 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -35,6 +35,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t16,
     Dataset_t17,
     Dataset_t19,
+    Dataset_t20,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -316,7 +317,7 @@ class Data(metaclass=DataMeta):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML table, used for displaying peek"""
         out = ['<table cellspacing="0" cellpadding="3">']
         try:
diff --git a/lib/galaxy/datatypes/flow.py b/lib/galaxy/datatypes/flow.py
index e520be5a1ea..15c2bcae2e5 100644
--- a/lib/galaxy/datatypes/flow.py
+++ b/lib/galaxy/datatypes/flow.py
@@ -5,6 +5,7 @@ Flow analysis datatypes.
 import logging
 from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -32,7 +33,7 @@ class FCS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 290322df5ec..747606433fb 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -33,6 +33,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t10,
     Dataset_t14,
     Dataset_t19,
+    Dataset_t20,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -244,7 +245,7 @@ class rgTabList(Tabular):
         super().__init__(**kwd)
         self.column_names = []
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -917,7 +918,7 @@ class RexpBase(Html):
         except Exception as exc:
             return f"Can't create html table {unicodify(exc)}"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """
         Returns formatted html of peek
         """
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index 427756f611b..475f5c08691 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -3,7 +3,10 @@ GIS classes
 """
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.binary import Binary
 
 if TYPE_CHECKING:
@@ -92,7 +95,7 @@ class Shapefile(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index fe8083fdb45..f1f9fac770b 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -30,6 +30,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t15,
     Dataset_t18,
     Dataset_t19,
+    Dataset_t20,
     HasId,
     HasMetadata,
 )
@@ -312,7 +313,7 @@ class Interval(Tabular):
                     fh.write("%s\n" % "\t".join(tmp))
             return compression_utils.get_fileobj(fh.name, mode="rb")
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset,
@@ -883,7 +884,7 @@ class Gff(Tabular, _RemoteCallMixin):
                             pass
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -1392,7 +1393,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
@@ -1480,7 +1481,7 @@ class CustomTrack(Tabular):
     def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index 27d64696498..458a26ce76f 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -27,6 +27,7 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
+    Dataset_t20,
     GeneratePrimaryFileDataset,
     HasExtraFilesPathProperty,
 )
@@ -191,7 +192,7 @@ class _Isa(Data):
     # Display peek {{{2
     ################################################################
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create the HTML table used for displaying peek, from the peek text found by set_peek() method."""
 
         out = ['<table cellspacing="0" cellpadding="3">']
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index fa2d103353e..5abf141b51e 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -9,6 +9,7 @@ from typing import (
 )
 
 from galaxy.datatypes import metadata
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -540,7 +541,7 @@ class OBFS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 6dc5f3e5c03..ce56027245e 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -9,6 +9,7 @@ from typing import (
     TYPE_CHECKING,
 )
 
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -105,7 +106,7 @@ class Hmmer(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -149,7 +150,7 @@ class HmmerPress(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index 1f45f059afe..d0f8cf50b8b 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -4,7 +4,10 @@ Neo4j Composite Dataset
 import logging
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
 from galaxy.datatypes.metadata import MetadataElement
@@ -55,7 +58,7 @@ class Neo4j(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index 9d0d35808b0..bafbae4d492 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -5,7 +5,10 @@ import logging
 import os
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from .metadata import MetadataElement
 from .text import Html
 
@@ -70,7 +73,7 @@ class BowtieIndex(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index a0528fe0e3d..aff44b89c59 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -2,6 +2,7 @@ import logging
 import re
 from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import Dataset_t20
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -25,7 +26,7 @@ log = logging.getLogger(__name__)
 class Smat(Text):
     file_ext = "smat"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -97,7 +98,7 @@ class PlantTribesKsComponents(Tabular):
         no_value=0,
     )
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 47b13b7c966..00ec52a9c6f 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -11,7 +11,10 @@ from typing import (
 )
 
 from galaxy.datatypes import data
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.sequence import Sequence
@@ -200,7 +203,7 @@ class Kroenik(Tabular):
             "Modifications",
         ]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -239,7 +242,7 @@ class PepList(Tabular):
         super().__init__(**kwd)
         self.column_names = ["m/z", "rt(min)", "snr", "charge", "intensity"]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -276,7 +279,7 @@ class PSMS(Tabular):
         super().__init__(**kwd)
         self.column_names = ["PSMId", "score", "q-value", "posterior_error_prob", "peptide", "proteinIds"]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -336,7 +339,7 @@ class PepXmlReport(Tabular):
             "Interprophet Probability",
         ]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -377,7 +380,7 @@ class ProtXmlReport(Tabular):
             "Is Evidence?",
         ]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -926,7 +929,7 @@ class ThermoRAW(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index 376c15a89a4..b936790005c 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -12,7 +12,10 @@ from typing import (
 
 import yaml
 
-from galaxy.datatypes._protocols import HasMetadata
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    HasMetadata,
+)
 from galaxy.datatypes.binary import CompressedZipArchive
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -50,7 +53,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.peek = "\n".join(map(": ".join, self._peek(dataset)))
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         def make_row(item):
             return "<tr><th>%s</th><td>%s</td></td>" % tuple(html.escape(x) for x in item)
 
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 6ba07d424de..9f88bc0958b 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -28,6 +28,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t10,
     Dataset_t19,
+    Dataset_t20,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -1068,7 +1069,7 @@ class Maf(Alignment):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset)
 
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index b32c7e2b509..55b69f48eec 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -12,7 +12,10 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.util import smart_str
@@ -110,7 +113,7 @@ class _SpalnDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 35e379312c5..fb8326e44a4 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -38,6 +38,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t12,
     Dataset_t17,
     Dataset_t19,
+    Dataset_t20,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -348,7 +349,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek rows: {util.unicodify(exc)}")
         return "".join(out)
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formatted html of peek"""
         return self.make_html_table(dataset)
 
@@ -644,7 +645,7 @@ class Taxonomy(Tabular):
             "Subspecies",
         ]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -735,7 +736,7 @@ class Sam(Tabular, _BamOrSam):
             "OPT",
         ]
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -951,7 +952,7 @@ class Pileup(Tabular):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset, column_parameter_alias={"chromCol": "Chrom", "startCol": "Start", "baseCol": "Base"}
@@ -1053,7 +1054,7 @@ class BaseVcf(Tabular):
         headers = get_headers(fname_or_file_prefix, "\n", count=1)
         return headers[0][0].startswith("##fileformat=VCF")
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 2605c2944c2..6579d97fabc 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -18,6 +18,7 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
+    Dataset_t20,
     GeneratePrimaryFileDataset,
     HasCreatingJobProperty,
 )
@@ -131,7 +132,7 @@ class Json(Text):
                 return start.startswith("[") or start.startswith("{")
             return False
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index 62ba622aa8f..f0a8d68c38d 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -4,7 +4,10 @@ Datatype classes for tracks/track views within galaxy.
 import logging
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.text import Html
 from . import binary
 
@@ -55,7 +58,7 @@ class UCSCTrackHub(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: "DatasetInstance") -> str:
+    def display_peek(self, dataset: Dataset_t20) -> str:
         try:
             return dataset.peek
         except Exception:

From 728e3b194e9dbc9484acc2a4077ab4062b1bf574 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 16:34:27 -0500
Subject: [PATCH 097/350] Remove DatasetInstance from regenerate_primary_file

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/assembly.py   | 7 +++++--
 lib/galaxy/datatypes/genetics.py   | 7 ++++---
 lib/galaxy/datatypes/ngsindex.py   | 3 ++-
 lib/galaxy/datatypes/spaln.py      | 3 ++-
 lib/galaxy/datatypes/text.py       | 3 ++-
 6 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 2b3873c4ae1..dc0b29c7f24 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -161,3 +161,7 @@ class Dataset_t20(HasMetadata, HasFileNameProperty, HasName, HasId, HasPeekPrope
 
     def get_size(self) -> str:
         ...
+
+
+class Dataset_t22(HasFileNameProperty, HasMetadata, HasExtraFilesPathProperty, HasInfo, HasName, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 4e25c488fa9..2db90dba7a3 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -13,7 +13,10 @@ from galaxy.datatypes import (
     data,
     sequence,
 )
-from galaxy.datatypes._protocols import GeneratePrimaryFileDataset
+from galaxy.datatypes._protocols import (
+    Dataset_t22,
+    GeneratePrimaryFileDataset,
+)
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -192,7 +195,7 @@ class Velvet(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 747606433fb..6ea070a6d53 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -34,6 +34,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t14,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t22,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -327,7 +328,7 @@ class Rgenetics(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -608,7 +609,7 @@ class IdeasPre(Html):
         rval.append("</ul></body></html>\n")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         # Cannot do this until we are setting metadata.
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
@@ -821,7 +822,7 @@ class RexpBase(Html):
         except Exception:
             return "## rexpression get_file_peek: no file found"
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index bafbae4d492..fa1e592fe35 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -7,6 +7,7 @@ from typing import TYPE_CHECKING
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t22,
     GeneratePrimaryFileDataset,
 )
 from .metadata import MetadataElement
@@ -48,7 +49,7 @@ class BowtieIndex(Html):
         """
         return "<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>"
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 55b69f48eec..570c39feae6 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -14,6 +14,7 @@ from typing import (
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t22,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import Data
@@ -85,7 +86,7 @@ class _SpalnDb(Data):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 6579d97fabc..3ef8a9e2f31 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -19,6 +19,7 @@ import yaml
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t22,
     GeneratePrimaryFileDataset,
     HasCreatingJobProperty,
 )
@@ -875,7 +876,7 @@ class SnpSiftDbNSFP(Text):
         """
         return "<html><head><title>SnpSiftDbNSFP Composite Dataset</title></head></html>"
 
-    def regenerate_primary_file(self, dataset: "DatasetInstance") -> None:
+    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
         """
         cannot do this until we are setting metadata
         """

From 58d08ecebad61cbcff568008c301a42e191a2131 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 15 Dec 2022 17:14:09 -0500
Subject: [PATCH 098/350] Remove DatasetInstance from set_peek

---
 lib/galaxy/datatypes/_protocols.py            |  9 ++
 lib/galaxy/datatypes/annotation.py            | 13 ++-
 lib/galaxy/datatypes/anvio.py                 |  3 +-
 lib/galaxy/datatypes/binary.py                | 85 ++++++++++---------
 lib/galaxy/datatypes/blast.py                 | 16 ++--
 .../datatypes/constructive_solid_geometry.py  | 15 ++--
 lib/galaxy/datatypes/data.py                  |  5 +-
 lib/galaxy/datatypes/flow.py                  | 11 ++-
 lib/galaxy/datatypes/genetics.py              |  5 +-
 lib/galaxy/datatypes/gis.py                   |  8 +-
 lib/galaxy/datatypes/graph.py                 | 17 ++--
 lib/galaxy/datatypes/images.py                |  5 +-
 lib/galaxy/datatypes/isa.py                   |  8 +-
 lib/galaxy/datatypes/microarrays.py           |  3 +-
 lib/galaxy/datatypes/molecules.py             | 37 ++++----
 lib/galaxy/datatypes/msa.py                   | 15 ++--
 lib/galaxy/datatypes/neo4j.py                 |  7 +-
 lib/galaxy/datatypes/ngsindex.py              |  7 +-
 lib/galaxy/datatypes/phylip.py                |  3 +-
 lib/galaxy/datatypes/plant_tribes.py          |  9 +-
 lib/galaxy/datatypes/proteomics.py            | 17 ++--
 lib/galaxy/datatypes/qiime2.py                |  3 +-
 lib/galaxy/datatypes/sequence.py              | 11 +--
 lib/galaxy/datatypes/spaln.py                 |  3 +-
 lib/galaxy/datatypes/tabular.py               |  3 +-
 lib/galaxy/datatypes/text.py                  | 27 +++---
 lib/galaxy/datatypes/tracks.py                |  7 +-
 lib/galaxy/datatypes/triples.py               | 19 ++---
 lib/galaxy/datatypes/xml.py                   | 19 +++--
 29 files changed, 201 insertions(+), 189 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index dc0b29c7f24..7f42537c90c 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -165,3 +165,12 @@ class Dataset_t20(HasMetadata, HasFileNameProperty, HasName, HasId, HasPeekPrope
 
 class Dataset_t22(HasFileNameProperty, HasMetadata, HasExtraFilesPathProperty, HasInfo, HasName, Protocol):
     ...
+
+
+class Dataset_t23(HasDataset, HasFileNameProperty, HasMetadata, HasInfo, HasExtraFilesPathProperty, Protocol):
+    peek: Any  # TODO
+    blurb: str
+    extension: str  # TODO reconcile: ext vs. extension
+
+    def get_size(self) -> str:
+        ...
diff --git a/lib/galaxy/datatypes/annotation.py b/lib/galaxy/datatypes/annotation.py
index eae090b819d..1009bc9cbe3 100644
--- a/lib/galaxy/datatypes/annotation.py
+++ b/lib/galaxy/datatypes/annotation.py
@@ -1,8 +1,10 @@
 import logging
 import tarfile
-from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.binary import CompressedArchive
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -14,9 +16,6 @@ from galaxy.datatypes.sniff import (
 )
 from galaxy.util import nice_size
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -25,7 +24,7 @@ class SnapHmm(Text):
     file_ext = "snaphmm"
     edam_data = "data_1364"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "SNAP HMM model"
@@ -55,7 +54,7 @@ class Augustus(CompressedArchive):
     edam_data = "data_0950"
     compressed = True
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Augustus model"
             dataset.blurb = nice_size(dataset.get_size())
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 931e2127255..25d80635083 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -12,6 +12,7 @@ from typing import (
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.metadata import MetadataElement
@@ -71,7 +72,7 @@ class AnvioComposite(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Anvio database (multiple files)"
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index e51b4136e07..382861607fd 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -38,6 +38,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t6,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
     HasMetadata,
@@ -117,7 +118,7 @@ class Binary(data.Data):
     def register_unsniffable_binary_ext(ext):
         """Deprecated method."""
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
@@ -138,7 +139,7 @@ class Ab1(Binary):
     edam_format = "format_3000"
     edam_data = "data_0924"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ab1 sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -228,7 +229,7 @@ class Cel(Binary):
         elif header_bytes.decode("utf8", errors="ignore").startswith("[CEL]"):
             dataset.metadata.version = "3"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.blurb = f"Cel version: {dataset.metadata.version}"
             dataset.peek = get_file_peek(dataset.file_name)
@@ -262,7 +263,7 @@ class CompressedArchive(Binary):
     compressed = True
     is_binary = "maybe"  # type: ignore[assignment]  # https://github.com/python/mypy/issues/8796
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed binary file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -319,7 +320,7 @@ class Bref3(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith_bytes(self._magic)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bref3 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -379,7 +380,7 @@ class CompressedZipArchive(CompressedArchive):
 
     file_ext = "zip"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed zip file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -554,7 +555,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bam alignments file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -993,7 +994,7 @@ class CRAM(Binary):
             log.warning("%s, set_index_file Exception: %s", self, exc)
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CRAM binary alignment file"
             dataset.blurb = "binary data"
@@ -1130,7 +1131,7 @@ class H5(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary HDF5 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1236,7 +1237,7 @@ class Loom(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary Loom file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1501,7 +1502,7 @@ class Anndata(H5):
             if dataset.metadata.shape is None:
                 dataset.metadata.shape = (int(dataset.metadata.obs_size), int(dataset.metadata.var_size))
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             tmp = dataset.metadata
 
@@ -1574,7 +1575,7 @@ class Grib(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary GRIB file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1617,7 +1618,7 @@ class GmxBinary(Binary):
         # The first 4 bytes of any GROMACS binary file containing the magic number
         return file_prefix.magic_header(">1i") == self.magic_number
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary GROMACS {self.file_ext} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1777,7 +1778,7 @@ class Biom2(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, util.unicodify(e))
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Biom2 (HDF5) file"]
             try:
@@ -1837,7 +1838,7 @@ class Cool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1897,7 +1898,7 @@ class MCool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Multi-resolution Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -2004,7 +2005,7 @@ class H5MLM(H5):
             log.warning("%s, get model configuration Except: %s", self, e)
             return ""
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             repr = self.get_repr(dataset.file_name)
             dataset.peek = repr[: self.max_peek_size]
@@ -2150,7 +2151,7 @@ class HexrdMaterials(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Material SpaceGroup Lattice"]
             if dataset.metadata.materials:
@@ -2175,7 +2176,7 @@ class Scf(Binary):
     edam_data = "data_0924"
     file_ext = "scf"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary scf sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2203,7 +2204,7 @@ class Sff(Binary):
         # about the format, see http://www.ncbi.nlm.nih.gov/Traces/trace.cgi?cmd=show&f=formats&m=doc&s=format
         return file_prefix.startswith_bytes(b".sff")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sff file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2240,7 +2241,7 @@ class BigWig(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.magic_header("I") == self._magic
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary UCSC {self._name} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2281,7 +2282,7 @@ class TwoBit(Binary):
         magic = file_prefix.magic_header(">L")
         return magic == TWOBIT_MAGIC_NUMBER or magic == TWOBIT_MAGIC_NUMBER_SWAP
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary TwoBit format nucleotide file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2383,7 +2384,7 @@ class SQlite(Binary):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SQLite Database"
             lines = ["SQLite Database"]
@@ -2466,7 +2467,7 @@ class GeminiSQLite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Gemini SQLite Database, version %s" % (dataset.metadata.gemini_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2553,7 +2554,7 @@ class CuffDiffSQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CuffDiff SQLite Database, version %s" % (dataset.metadata.cuffdiff_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2883,7 +2884,7 @@ class IdpDB(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "IDPickerDB SQLite file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2982,7 +2983,7 @@ class NcbiTaxonomySQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "NCBI Taxonomy SQLite Database, version {} ({} taxons)".format(
                 getattr(dataset.metadata, "ncbitaxonomy_schema_version", "unknown"),
@@ -3029,7 +3030,7 @@ class ExcelXls(Binary):
         """Returns the mime type of the datatype"""
         return "application/vnd.ms-excel"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Microsoft Excel XLS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -3056,7 +3057,7 @@ class Sra(Binary):
         """
         return file_prefix.startswith_bytes(b"NCBI.sra")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sra file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3453,7 +3454,7 @@ class PostgresqlArchive(CompressedArchive):
                 return "postgresql/db/PG_VERSION" in temptar.getnames()
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"PostgreSQL Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "PostgreSQL version %s" % (dataset.metadata.version or "unknown")
@@ -3507,7 +3508,7 @@ class Fast5Archive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"FAST5 Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "%s sequences" % (dataset.metadata.fast5_count or "unknown")
@@ -3616,7 +3617,7 @@ class SearchGuiArchive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SearchGUI Archive, version %s" % (dataset.metadata.searchgui_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -3639,7 +3640,7 @@ class NetCDF(Binary):
     edam_format = "format_3650"
     edam_data = "data_0943"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary netCDF file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3695,7 +3696,7 @@ class Dcd(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM/NAMD dcd file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3747,7 +3748,7 @@ class Vel(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM velocity file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3844,7 +3845,7 @@ class ICM(Binary):
     file_ext = "icm"
     edam_data = "data_0950"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ICM (interpolated context model) file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3919,7 +3920,7 @@ class BafTar(CompressedArchive):
     def get_type(self) -> str:
         return "Bruker BAF directory archive"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = self.get_type()
             dataset.blurb = nice_size(dataset.get_size())
@@ -4029,7 +4030,7 @@ class Pretext(Binary):
         # file contains binary data.
         return file_prefix.startswith_bytes(b"pstm")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary pretext file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4073,7 +4074,7 @@ class JP2(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary JPEG 2000 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4129,7 +4130,7 @@ class Npz(CompressedArchive):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary Numpy npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4202,7 +4203,7 @@ class HexrdImagesNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Image npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4264,7 +4265,7 @@ class HexrdEtaOmeNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Eta-Ome npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index 1ac8f916956..152df30d991 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -41,7 +41,10 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -55,10 +58,7 @@ from .data import (
 from .xml import GenericXml
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 log = logging.getLogger(__name__)
 
@@ -71,7 +71,7 @@ class BlastXml(GenericXml):
     edam_format = "format_3331"
     edam_data = "data_0857"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
@@ -196,7 +196,7 @@ class BlastXml(GenericXml):
 class _BlastDb(Data):
     """Base class for BLAST database datatype."""
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "BLAST database (multiple files)"
@@ -373,7 +373,7 @@ class LastDb(Data):
     file_ext = "lastdb"
     composite_type = "basic"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "LAST database (multiple files)"
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index 5c7a0c1a88c..de8c08ace4d 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -16,6 +16,7 @@ from galaxy import util
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -129,7 +130,7 @@ class Ply:
                             element_tuple = (items[1], int(items[2]))
                             dataset.metadata.other_elements.append(element_tuple)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = f"Faces: {str(dataset.metadata.face)}, Vertices: {str(dataset.metadata.vertex)}"
@@ -463,7 +464,7 @@ class Vtk:
             blurb += str(dataset.metadata.dataset_type)
         return blurb or "VTK data"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = self.get_blurb(dataset)
@@ -572,7 +573,7 @@ class NeperTess(data.Text):
                     if i == 6:
                         dataset.metadata.cells = int(line)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=7)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -659,7 +660,7 @@ class NeperTesr(Binary):
                         dataset.metadata.cells = int(line)
                         break
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=9)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -705,7 +706,7 @@ class NeperPoints(data.Text):
             return None
         return dim
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         data.Text.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -728,7 +729,7 @@ class NeperPointsTabular(NeperPoints, Tabular):
             with open(dataset.file_name, errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         Tabular.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -784,7 +785,7 @@ class GmshMsh(Binary):
                         if len(fields) > 1:
                             dataset.metadata.format = "ASCII" if fields[1] == "0" else "binary"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=3)
             dataset.blurb = f"Gmsh verion: {str(dataset.metadata.version)} {str(dataset.metadata.format)}"
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index d84770304ab..18b10141894 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -36,6 +36,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t17,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -306,7 +307,7 @@ class Data(metaclass=DataMeta):
 
     max_optional_metadata_filesize = property(get_max_optional_metadata_filesize, set_max_optional_metadata_filesize)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -1028,7 +1029,7 @@ class Text(Data):
                 return None
         return data_lines
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """
         Set the peek.  This method is used by various subclasses of Text.
         """
diff --git a/lib/galaxy/datatypes/flow.py b/lib/galaxy/datatypes/flow.py
index 15c2bcae2e5..4d720575548 100644
--- a/lib/galaxy/datatypes/flow.py
+++ b/lib/galaxy/datatypes/flow.py
@@ -3,9 +3,11 @@ Flow analysis datatypes.
 """
 
 import logging
-from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -13,9 +15,6 @@ from galaxy.datatypes.sniff import (
 )
 from . import data
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -25,7 +24,7 @@ class FCS(Binary):
 
     file_ext = "fcs"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary FCS file"
             dataset.blurb = data.nice_size(dataset.get_size())
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 6ea070a6d53..67332c4d788 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -35,6 +35,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t19,
     Dataset_t20,
     Dataset_t22,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -390,7 +391,7 @@ class SNPMatrix(Rgenetics):
 
     file_ext = "snpmatrix"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary RGenetics file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -773,7 +774,7 @@ class RexpBase(Html):
             p = []
         return "\n".join(p)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """
         expects a .pheno file in the extra_files_dir - ugh
         note that R is weird and does not include the row.name in
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index 475f5c08691..dacbc8181c4 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -1,17 +1,13 @@
 """
 GIS classes
 """
-from typing import TYPE_CHECKING
-
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.binary import Binary
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 class Shapefile(Binary):
     """The Shapefile data format:
@@ -86,7 +82,7 @@ class Shapefile(Binary):
         rval.append("</ul></div></html>\n")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "Shapefile data"
diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index 4a14f3828b5..d0feb586fdd 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -2,12 +2,12 @@
 Graph content classes.
 """
 import logging
-from typing import (
-    List,
-    TYPE_CHECKING,
-)
+from typing import List
 
-from galaxy.datatypes._protocols import Dataset_t2
+from galaxy.datatypes._protocols import (
+    Dataset_t2,
+    Dataset_t23,
+)
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -19,9 +19,6 @@ from . import (
     xml,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -34,7 +31,7 @@ class Xgmml(xml.GenericXml):
 
     file_ext = "xgmml"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -82,7 +79,7 @@ class Sif(tabular.Tabular):
 
     file_ext = "sif"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 6bafa94659c..ba06ca67dc8 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -15,6 +15,7 @@ import tifffile
 
 from galaxy.datatypes._protocols import (
     Dataset_t7,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.binary import Binary
@@ -59,7 +60,7 @@ class Image(data.Data):
         super().__init__(**kwd)
         self.image_formats = [self.file_ext.upper()]
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Image in {dataset.extension} format"
             dataset.blurb = nice_size(dataset.get_size())
@@ -496,7 +497,7 @@ class Star(data.Text):
 
     file_ext = "star"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index 458a26ce76f..fe80b713dbc 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -28,6 +28,7 @@ from markupsafe import escape
 from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
     HasExtraFilesPathProperty,
 )
@@ -38,10 +39,7 @@ from galaxy.util.sanitize_html import sanitize_html
 if TYPE_CHECKING:
     from isatools.model import Investigation
 
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 # CONSTANTS {{{1
 ################################################################
@@ -166,7 +164,7 @@ class _Isa(Data):
     # Set peek {{{2
     ################################################################
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text. Get first lines of the main file and set it as the peek."""
 
         main_file = self._get_main_file(dataset)
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index aa8ba733a1a..a34d79e2d70 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -2,6 +2,7 @@ import logging
 from typing import TYPE_CHECKING
 
 from galaxy.datatypes import data
+from galaxy.datatypes._protocols import Dataset_t23
 from galaxy.datatypes.binary import Cel  # noqa: F401
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.metadata import MetadataElement
@@ -80,7 +81,7 @@ class GenericMicroarrayFile(data.Text):
         name="block_type", default=0, desc="Type of block", readonly=True, visible=True, optional=True, no_value=0
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.block_count == 1:
                 dataset.blurb = f"{dataset.metadata.file_type} {dataset.metadata.version_number}: Format {dataset.metadata.file_format}, 1 block, {dataset.metadata.number_of_optional_header_records} headers and {dataset.metadata.number_of_data_columns} columns"
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index 5abf141b51e..be652e1c438 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -9,7 +9,10 @@ from typing import (
 )
 
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -73,7 +76,7 @@ class GenericMolFile(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -532,7 +535,7 @@ class OBFS(Binary):
         self.add_composite_file("molecule.mol2", optional=True, is_binary=False, description="Molecule File")
         self.add_composite_file("molecule.cml", optional=True, is_binary=False, description="Molecule File")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "OpenBabel Fastsearch Index"
@@ -582,7 +585,7 @@ class PHAR(GenericMolFile):
 
     file_ext = "phar"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "pharmacophore"
@@ -651,7 +654,7 @@ class PDB(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -704,7 +707,7 @@ class PDBQT(GenericMolFile):
         else:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             root_numbers = count_special_lines("^ROOT", dataset.file_name)
             branch_numbers = count_special_lines("^BRANCH", dataset.file_name)
@@ -808,7 +811,7 @@ class PQR(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -926,7 +929,7 @@ class Cell(GenericMolFile):
                 dataset.metadata.is_periodic = bool(pbc.any())
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1093,7 +1096,7 @@ class CIF(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1291,7 +1294,7 @@ class XYZ(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1446,7 +1449,7 @@ class ExtendedXYZ(XYZ):
             blocks.append({"number_of_atoms": n_atoms, "comment": comment, "atom_data": atoms})
         return blocks
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         super().set_peek(dataset)
         dataset.blurb = "Extended " + dataset.blurb
 
@@ -1454,7 +1457,7 @@ class ExtendedXYZ(XYZ):
 class grd(Text):
     file_ext = "grd"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "grids for docking"
@@ -1466,7 +1469,7 @@ class grd(Text):
 class grdtgz(Binary):
     file_ext = "grd.tgz"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
             dataset.blurb = "compressed grids for docking"
@@ -1504,7 +1507,7 @@ class InChI(Tabular):
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1569,7 +1572,7 @@ class SMILES(Tabular):
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1605,7 +1608,7 @@ class CML(GenericXml):
         """
         dataset.metadata.number_of_molecules = count_special_lines(r"^\s*<molecule", dataset.file_name)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1763,7 +1766,7 @@ class GRO(GenericMolFile):
                 return False
         return True
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             atom_number = int(dataset.peek.split("\n")[1])
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index ce56027245e..c69c4ca97b7 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -9,7 +9,10 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -58,7 +61,7 @@ class InfernalCM(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_of_models == 1:
@@ -98,7 +101,7 @@ class Hmmer(Text):
     edam_data = "data_1364"
     edam_format = "format_1370"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "HMMER Database"
@@ -141,7 +144,7 @@ class HmmerPress(Binary):
     file_ext = "hmmpress"
     composite_type = "basic"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "HMMER Binary database"
@@ -185,7 +188,7 @@ class Stockholm_1_0(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -276,7 +279,7 @@ class MauveXmfa(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index d0f8cf50b8b..afce28d526a 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -2,19 +2,16 @@
 Neo4j Composite Dataset
 """
 import logging
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
 from galaxy.datatypes.metadata import MetadataElement
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 gal_Log = logging.getLogger(__name__)
 verbose = True
 
@@ -49,7 +46,7 @@ class Neo4j(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Neo4j database (multiple files)"
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index fa1e592fe35..5550bf3df9f 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -3,19 +3,16 @@ NGS indexes
 """
 import logging
 import os
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from .metadata import MetadataElement
 from .text import Html
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -66,7 +63,7 @@ class BowtieIndex(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Bowtie index file ({dataset.metadata.sequence_space})"
             dataset.blurb = f"{dataset.metadata.sequence_space} space"
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index 551043080cf..efaaa1f8a75 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -10,6 +10,7 @@ Phylip datatype sniffer
 from typing import TYPE_CHECKING
 
 from galaxy import util
+from galaxy.datatypes._protocols import Dataset_t23
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -49,7 +50,7 @@ class Phylip(Text):
         except Exception:
             raise Exception("Header does not correspond to PHYLIP header.")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index aff44b89c59..45de9b9c449 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -2,7 +2,10 @@ import logging
 import re
 from typing import TYPE_CHECKING
 
-from galaxy.datatypes._protocols import Dataset_t20
+from galaxy.datatypes._protocols import (
+    Dataset_t20,
+    Dataset_t23,
+)
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -32,7 +35,7 @@ class Smat(Text):
         except Exception:
             return f"ESTScan scores matrices ({nice_size(dataset.get_size())})"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "ESTScan scores matrices"
@@ -126,7 +129,7 @@ class PlantTribesKsComponents(Tabular):
         if len(significant_components) > 0:
             dataset.metadata.number_comp = max(significant_components)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_comp == 1:
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 00ec52a9c6f..50493a37f66 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -13,6 +13,7 @@ from typing import (
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.binary import Binary
@@ -107,7 +108,7 @@ class MzTab(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -158,7 +159,7 @@ class MzTab2(MzTab):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -678,7 +679,7 @@ class ProteomicsXml(GenericXml):
         pattern = r"<(\w*:)?%s" % self.root
         return re.search(pattern, line) is not None
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -847,7 +848,7 @@ class Mgf(Text):
     edam_format = "format_3651"
     file_ext = "mgf"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -877,7 +878,7 @@ class MascotDat(Text):
     edam_format = "format_3713"
     file_ext = "mascotdat"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -921,7 +922,7 @@ class ThermoRAW(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Thermo Finnigan RAW file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -963,7 +964,7 @@ class SPLibNoIndex(Text):
 
     file_ext = "splib_noindex"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1005,7 +1006,7 @@ class SPLib(Msp):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index b936790005c..64cc5abd927 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -14,6 +14,7 @@ import yaml
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     HasMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
@@ -45,7 +46,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.metadata.semantic_type_simple = _strip_properties(dataset.metadata.semantic_type)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if dataset.metadata.semantic_type == "Visualization":
             dataset.blurb = "QIIME 2 Visualization"
         else:
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 9f88bc0958b..952a06138d8 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -29,6 +29,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t10,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t23,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -77,7 +78,7 @@ class SequenceSplitLocations(data.Text):
 
     file_ext = "fqtoc"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             try:
                 parsed_data = json.load(open(dataset.file_name))
@@ -134,7 +135,7 @@ class Sequence(data.Text):
             dataset.metadata.data_lines = data_lines
             dataset.metadata.sequences = sequences
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -672,7 +673,7 @@ class Fastg(Sequence):
             return
         return Sequence.set_meta(self, dataset, overwrite=overwrite, **kwd)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -1055,7 +1056,7 @@ class Maf(Alignment):
         indexes.write(open(index_file.file_name, "wb"))
         dataset.metadata.maf_index = index_file
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1281,7 +1282,7 @@ class RNADotPlotMatrix(data.Data):
     edam_format = "format_3466"
     file_ext = "rna_eps"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "RNA Dot Plot format (Postscript derivative)"
             dataset.blurb = nice_size(dataset.get_size())
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 570c39feae6..700f0253711 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -15,6 +15,7 @@ from typing import (
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import Data
@@ -105,7 +106,7 @@ class _SpalnDb(Data):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "spaln database (multiple files)"
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index fb8326e44a4..67d9d4aa897 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -39,6 +39,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t17,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t23,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -137,7 +138,7 @@ class TabularData(Text):
     def set_meta(self, dataset: "DatasetInstance", *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         kwd.setdefault("line_wrap", False)
         super().set_peek(dataset, **kwd)
         if dataset.metadata.comment_lines:
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 3ef8a9e2f31..8b1f1d89e9b 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -20,6 +20,7 @@ import yaml
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
     HasCreatingJobProperty,
 )
@@ -60,7 +61,7 @@ class Html(Text):
     edam_format = "format_2331"
     file_ext = "html"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "HTML file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -96,7 +97,7 @@ class Json(Text):
     edam_format = "format_3464"
     file_ext = "json"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "JavaScript Object Notation (JSON)"
@@ -175,7 +176,7 @@ class ExpressionJson(Json):
 class Ipynb(Json):
     file_ext = "ipynb"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Jupyter Notebook"
@@ -394,7 +395,7 @@ class Biom1(Json):
         no_value=[],
     )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "Biological Observation Matrix v1"
@@ -493,7 +494,7 @@ class ImgtJson(Json):
 
     MetadataElement(name="taxon_names", default=[], desc="taxonID: names", readonly=True, visible=True, no_value=[])
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "IMGT Library"
@@ -559,7 +560,7 @@ class GeoJson(Json):
 
     file_ext = "geojson"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "GeoJSON"
@@ -620,7 +621,7 @@ class Obo(Text):
     edam_format = "format_2549"
     file_ext = "obo"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Open Biomedical Ontology (OBO)"
@@ -662,7 +663,7 @@ class Arff(Text):
     )
     MetadataElement(name="columns", default=0, desc="Number of columns", readonly=True, visible=True, no_value=0)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Attribute-Relation File Format (ARFF)"
@@ -914,7 +915,7 @@ class SnpSiftDbNSFP(Text):
                 unicodify(e),
             )
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"{dataset.metadata.reference_name} :  {','.join(dataset.metadata.annotation)}"
             dataset.blurb = f"{dataset.metadata.reference_name}"
@@ -1159,7 +1160,7 @@ class BCSLts(Json):
             is_bcsl_ts = self._looks_like_bcsl_ts(file_prefix)
         return is_bcsl_ts
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = "States: {}\nTransitions: {}\nUnique agents: {}\nInitial state: {}"
             ts = json.load(open(dataset.file_name, "r"))
@@ -1193,7 +1194,7 @@ class StormSample(Text):
         keywords = ["Storm-pars", "Result (initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Storm-pars sample results."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1218,7 +1219,7 @@ class StormCheck(Text):
         keywords = ["Storm ", "Result (for initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
@@ -1246,7 +1247,7 @@ class CTLresult(Text):
         keywords = ["Result:", "Number of satisfying states:"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index f0a8d68c38d..8488c06553a 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -2,18 +2,15 @@
 Datatype classes for tracks/track views within galaxy.
 """
 import logging
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
+    Dataset_t23,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.text import Html
 from . import binary
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -51,7 +48,7 @@ class UCSCTrackHub(Html):
         rval.append("</ul></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Track Hub structure: Visualization in UCSC Track Hub"
         else:
diff --git a/lib/galaxy/datatypes/triples.py b/lib/galaxy/datatypes/triples.py
index debd78bb366..e71f86460e8 100644
--- a/lib/galaxy/datatypes/triples.py
+++ b/lib/galaxy/datatypes/triples.py
@@ -3,8 +3,8 @@ Triple format classes
 """
 import logging
 import re
-from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import Dataset_t23
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -16,9 +16,6 @@ from . import (
     xml,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 TURTLE_PREFIX_PATTERN = re.compile(r"@prefix\s+[^:]*:\s+<[^>]*>\s\.")
@@ -40,7 +37,7 @@ class Triples(data.Data):
         """
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -65,7 +62,7 @@ class NTriples(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -89,7 +86,7 @@ class N3(data.Text, Triples):
         """
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -117,7 +114,7 @@ class Turtle(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -146,7 +143,7 @@ class Rdf(xml.GenericXml, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -172,7 +169,7 @@ class Jsonld(text.Json, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -196,7 +193,7 @@ class HDT(binary.Binary, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index c49c30d47e2..ded723b096e 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -9,7 +9,10 @@ from typing import (
 )
 
 from galaxy import util
-from galaxy.datatypes._protocols import Dataset_t2
+from galaxy.datatypes._protocols import (
+    Dataset_t2,
+    Dataset_t23,
+)
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
 from galaxy.datatypes.metadata import MetadataElement
@@ -40,7 +43,7 @@ class GenericXml(data.Text):
     edam_format = "format_2332"
     file_ext = "xml"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -93,7 +96,7 @@ class MEMEXml(GenericXml):
 
     file_ext = "memexml"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -109,7 +112,7 @@ class CisML(GenericXml):
 
     file_ext = "cisml"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -170,7 +173,7 @@ class Dzi(GenericXml):
                 dataset.metadata.width = elem.get("Width")
                 dataset.metadata.height = elem.get("Height")
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Deep Zoom Image"
@@ -203,7 +206,7 @@ class Phyloxml(GenericXml):
     edam_format = "format_3159"
     file_ext = "phyloxml"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -238,7 +241,7 @@ class Owl(GenericXml):
     edam_format = "format_3262"
     file_ext = "owl"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Web Ontology Language OWL"
@@ -263,7 +266,7 @@ class Sbml(GenericXml):
     edam_data = "data_2024"
     edam_format = "format_2585"
 
-    def set_peek(self, dataset: "DatasetInstance", **kwd) -> None:
+    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "System Biology Markup Language SBML"

From 20ad519a71bfd9c7d7ecbf7bd6e75712841c18b0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 16:45:26 -0500
Subject: [PATCH 099/350] Remove DatasetInstance from set_meta and friends

---
 lib/galaxy/datatypes/_protocols.py            | 13 ++++
 lib/galaxy/datatypes/anvio.py                 | 11 +--
 lib/galaxy/datatypes/assembly.py              |  7 +-
 lib/galaxy/datatypes/binary.py                | 74 +++++++++----------
 .../datatypes/constructive_solid_geometry.py  | 23 +++---
 lib/galaxy/datatypes/data.py                  |  5 +-
 lib/galaxy/datatypes/genetics.py              | 13 ++--
 lib/galaxy/datatypes/goldenpath.py            |  7 +-
 lib/galaxy/datatypes/images.py                | 11 +--
 lib/galaxy/datatypes/interval.py              | 21 +++---
 lib/galaxy/datatypes/media.py                 | 11 +--
 lib/galaxy/datatypes/microarrays.py           | 13 ++--
 lib/galaxy/datatypes/molecules.py             | 31 ++++----
 lib/galaxy/datatypes/mothur.py                | 21 +++---
 lib/galaxy/datatypes/msa.py                   | 11 +--
 lib/galaxy/datatypes/phylip.py                |  9 ++-
 lib/galaxy/datatypes/plant_tribes.py          |  7 +-
 lib/galaxy/datatypes/proteomics.py            | 11 +--
 lib/galaxy/datatypes/qiime2.py                |  9 +--
 lib/galaxy/datatypes/qualityscore.py          |  7 +-
 lib/galaxy/datatypes/sequence.py              | 20 +++--
 lib/galaxy/datatypes/spaln.py                 |  8 +-
 lib/galaxy/datatypes/speech.py                |  8 +-
 lib/galaxy/datatypes/tabular.py               | 28 ++++---
 lib/galaxy/datatypes/text.py                  | 20 +++--
 lib/galaxy/datatypes/xml.py                   | 11 +--
 26 files changed, 179 insertions(+), 231 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 7f42537c90c..1e0ec2e0059 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -174,3 +174,16 @@ class Dataset_t23(HasDataset, HasFileNameProperty, HasMetadata, HasInfo, HasExtr
 
     def get_size(self) -> str:
         ...
+
+
+class Dataset_t24(
+    HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, HasInfo, HasName, HasId, HasDataset, Protocol
+):
+    peek: Any  # TODO
+    blurb: str
+
+    def has_data(self) -> bool:
+        ...
+
+    def get_size(self) -> str:
+        ...
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 25d80635083..298b54ea17c 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -5,22 +5,17 @@ https://github.com/merenlab/anvio
 import glob
 import logging
 import os
-from typing import (
-    Optional,
-    TYPE_CHECKING,
-)
+from typing import Optional
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -101,7 +96,7 @@ class AnvioDB(AnvioComposite):
         if self._anvio_basename is not None:
             self.add_composite_file(self._anvio_basename, is_binary=True, optional=False)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the anvio_basename based upon actual extra_files_path contents.
         """
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 2db90dba7a3..053bc181edf 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -7,7 +7,6 @@ for velvet assembler tool in galaxy
 import logging
 import os
 import re
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes import (
     data,
@@ -15,6 +14,7 @@ from galaxy.datatypes import (
 )
 from galaxy.datatypes._protocols import (
     Dataset_t22,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.metadata import MetadataElement
@@ -24,9 +24,6 @@ from galaxy.datatypes.sniff import (
 )
 from galaxy.datatypes.text import Html
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -246,6 +243,6 @@ class Velvet(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         Html.set_meta(self, dataset, overwrite=overwrite, **kwd)
         self.regenerate_primary_file(dataset)
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 382861607fd..cc8cd766f78 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -39,6 +39,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t19,
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
     HasMetadata,
@@ -90,10 +91,7 @@ from . import (
 )
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
     from galaxy.util.compression_utils import FileObjType
 
 log = logging.getLogger(__name__)
@@ -216,7 +214,7 @@ class Cel(Binary):
             found_cel_3 = True
         return found_cel_3 or found_cel_4 or found_cel_agcc
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Cel file.
         """
@@ -419,7 +417,7 @@ class _BamOrSam:
     Helper class to set the metadata common to sam and bam files
     """
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         try:
             bam_file = pysam.AlignmentFile(dataset.file_name, mode="rb")
             # TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
@@ -524,7 +522,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         no_value={},
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         _BamOrSam().set_meta(dataset, overwrite=overwrite, **kwd)
 
     @staticmethod
@@ -778,7 +776,7 @@ class Bam(BamNative):
         return needs_sorting
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         # These metadata values are not accessible by users, always overwrite
         super().set_meta(dataset=dataset, overwrite=overwrite, **kwd)
@@ -964,7 +962,7 @@ class CRAM(Binary):
     )
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         major_version, minor_version = self.get_cram_version(dataset.file_name)
         if major_version != -1:
@@ -1047,7 +1045,7 @@ class Bcf(BaseBcf):
             return False
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """Creates the index for the BCF file."""
         # These metadata values are not accessible by users, always overwrite
@@ -1251,7 +1249,7 @@ class Loom(H5):
         except Exception:
             return f"Binary Loom file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as loom_file:
@@ -1396,7 +1394,7 @@ class Anndata(H5):
                 return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         with h5py.File(dataset.file_name, "r") as anndata_file:
             dataset.metadata.title = anndata_file.attrs.get("title")
@@ -1589,7 +1587,7 @@ class Grib(Binary):
         except Exception:
             return f"Binary GRIB file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the GRIB edition.
         """
@@ -1756,7 +1754,7 @@ class Biom2(H5):
                 return required_fields.issubset(f.attrs.keys())
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as f:
@@ -1942,7 +1940,7 @@ class H5MLM(H5):
     )
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         try:
             spec_key = "hyper_params"
@@ -2134,7 +2132,7 @@ class HexrdMaterials(H5):
                         return True
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as mat_file:
@@ -2327,7 +2325,7 @@ class SQlite(Binary):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         try:
             tables = []
             columns = dict()
@@ -2438,7 +2436,7 @@ class GeminiSQLite(SQlite):
     edam_format = "format_3622"
     edam_data = "data_3498"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2487,7 +2485,7 @@ class ChiraSQLite(SQlite):
 
     file_ext = "chira.sqlite"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2518,7 +2516,7 @@ class CuffDiffSQlite(SQlite):
     # TODO: Update this when/if there is a specific EDAM format for CuffDiff SQLite data.
     edam_format = "format_3621"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             genes = []
@@ -2574,7 +2572,7 @@ class MzSQlite(SQlite):
 
     file_ext = "mz.sqlite"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2611,7 +2609,7 @@ class PQP(SQlite):
 
     file_ext = "pqp"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2653,7 +2651,7 @@ class OSW(SQlite):
 
     file_ext = "osw"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2696,7 +2694,7 @@ class SQmass(SQlite):
 
     file_ext = "sqmass"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2720,7 +2718,7 @@ class BlibSQlite(SQlite):
     )
     file_ext = "blib"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2773,7 +2771,7 @@ class DlibSQlite(SQlite):
     )
     file_ext = "dlib"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2817,7 +2815,7 @@ class ElibSQlite(SQlite):
     )
     file_ext = "elib"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2868,7 +2866,7 @@ class IdpDB(SQlite):
 
     file_ext = "idpdb"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2913,7 +2911,7 @@ class GAFASQLite(SQlite):
     )
     file_ext = "gafa.sqlite"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2959,7 +2957,7 @@ class NcbiTaxonomySQlite(SQlite):
 
     file_ext = "ncbitaxonomy.sqlite"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -3106,7 +3104,7 @@ class RData(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3189,7 +3187,7 @@ class RDS(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3436,7 +3434,7 @@ class PostgresqlArchive(CompressedArchive):
     )
     file_ext = "postgresql"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3484,7 +3482,7 @@ class Fast5Archive(CompressedArchive):
     )
     file_ext = "fast5.tar"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3592,7 +3590,7 @@ class SearchGuiArchive(CompressedArchive):
     )
     file_ext = "searchgui_archive"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and zipfile.is_zipfile(dataset.file_name):
@@ -4122,7 +4120,7 @@ class Npz(CompressedArchive):
             return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         try:
             with np.load(dataset.file_name) as npz:
                 dataset.metadata.nfiles = len(npz.files)
@@ -4190,7 +4188,7 @@ class HexrdImagesNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4256,7 +4254,7 @@ class HexrdEtaOmeNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index de8c08ace4d..d6026a7c47b 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -17,6 +17,7 @@ from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -34,8 +35,6 @@ from galaxy.datatypes.tabular import Tabular
 if TYPE_CHECKING:
     from io import TextIOBase
 
-    from galaxy.model import DatasetInstance
-
 MAX_HEADER_LINES = 500
 MAX_LINE_LEN = 2000
 COLOR_OPTS = ["COLOR_SCALARS", "red", "green", "blue"]
@@ -107,7 +106,7 @@ class Ply:
                 break
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for line in fh:
@@ -287,7 +286,7 @@ class Vtk:
             return check_data_kind(line)
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             dataset.metadata.field_names = []
             dataset.metadata.field_components = {}
@@ -376,7 +375,7 @@ class Vtk:
             if len(field_components) > 0:
                 dataset.metadata.field_components = field_components
 
-    def set_initial_metadata(self, i: int, line: str, dataset: "DatasetInstance") -> "DatasetInstance":
+    def set_initial_metadata(self, i: int, line: str, dataset: Dataset_t24) -> Dataset_t24:
         if i == 0:
             # The first part of legacy VTK files is the file version and
             # identifier. This part contains the single line:
@@ -395,8 +394,8 @@ class Vtk:
         return dataset
 
     def set_structure_metadata(
-        self, line: str, dataset: "DatasetInstance", dataset_type: Optional[str]
-    ) -> Tuple["DatasetInstance", Optional[str]]:
+        self, line: str, dataset: Dataset_t24, dataset_type: Optional[str]
+    ) -> Tuple[Dataset_t24, Optional[str]]:
         """
         The fourth part of legacy VTK files is the dataset structure. The
         geometry part describes the geometry and topology of the dataset.
@@ -557,7 +556,7 @@ class NeperTess(data.Text):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tess")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -628,7 +627,7 @@ class NeperTesr(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tesr")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 field = ""
@@ -681,7 +680,7 @@ class NeperPoints(data.Text):
     def __init__(self, **kwd):
         data.Text.__init__(self, **kwd)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         data.Text.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -723,7 +722,7 @@ class NeperPointsTabular(NeperPoints, Tabular):
     def __init__(self, **kwd):
         Tabular.__init__(self, **kwd)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -769,7 +768,7 @@ class GmshMsh(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline().startswith("$MeshFormat")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 18b10141894..663d9b5cd9d 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -37,6 +37,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t19,
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -262,7 +263,7 @@ class Data(metaclass=DataMeta):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: "DatasetInstance", *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
         """Unimplemented method, allows guessing of metadata from contents of file"""
 
     def missing_meta(self, dataset: HasMetadata, check: Optional[List] = None, skip: Optional[List] = None) -> bool:
@@ -988,7 +989,7 @@ class Text(Data):
         """Returns the mime type of the datatype"""
         return "text/plain"
 
-    def set_meta(self, dataset: "DatasetInstance", *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 67332c4d788..33acaf0f303 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -20,7 +20,6 @@ from typing import (
     IO,
     List,
     Optional,
-    TYPE_CHECKING,
     Union,
 )
 from urllib.parse import quote_plus
@@ -36,6 +35,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
     HasMetadata,
 )
@@ -56,9 +56,6 @@ from galaxy.util import (
 )
 from galaxy.util.compression_utils import FileObjType
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 gal_Log = logging.getLogger(__name__)
 verbose = False
 
@@ -85,7 +82,7 @@ class GenomeGraphs(Tabular):
         super().__init__(**kwd)
         self.add_display_app("ucsc", "Genome Graph", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.markerCol = 1
         header = open(dataset.file_name).readlines()[0].strip().split("\t")
@@ -351,7 +348,7 @@ class Rgenetics(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         for lped/pbed eg
 
@@ -587,7 +584,7 @@ class IdeasPre(Html):
         self.add_composite_file("IDEAS_input_config.txt", description="IDEAS input config", is_binary=False)
         self.add_composite_file("tmp.tar.gz", description="Compressed archive of compressed bed files", is_binary=True)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         for fname in os.listdir(dataset.extra_files_path):
             if fname.startswith("chromosomes"):
@@ -844,7 +841,7 @@ class RexpBase(Html):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         NOTE we apply the tabular machinary to the phenodata extracted
         from a BioC eSet or affybatch.
diff --git a/lib/galaxy/datatypes/goldenpath.py b/lib/galaxy/datatypes/goldenpath.py
index d5ef0405449..af7aacb4078 100644
--- a/lib/galaxy/datatypes/goldenpath.py
+++ b/lib/galaxy/datatypes/goldenpath.py
@@ -3,10 +3,10 @@ import logging
 import os
 from typing import (
     Set,
-    TYPE_CHECKING,
     Union,
 )
 
+from galaxy.datatypes._protocols import Dataset_t24
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -14,9 +14,6 @@ from galaxy.datatypes.sniff import (
 )
 from .tabular import Tabular
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -27,7 +24,7 @@ class GoldenPath(Tabular):
     edam_format = "format_3693"
     file_ext = "agp"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         # AGPFile reads and validates entire file.
         AGPFile(dataset.file_name)
         super().set_meta(dataset, overwrite=overwrite, **kwd)
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index ba06ca67dc8..b0de83a5454 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -4,10 +4,7 @@ Image classes
 import base64
 import json
 import logging
-from typing import (
-    Optional,
-    TYPE_CHECKING,
-)
+from typing import Optional
 
 import mrcfile
 import numpy as np
@@ -16,6 +13,7 @@ import tifffile
 from galaxy.datatypes._protocols import (
     Dataset_t7,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.binary import Binary
@@ -33,9 +31,6 @@ from galaxy.util.image_util import check_image_type
 from . import data
 from .xml import GenericXml
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 # TODO: Uploading image files of various types is supported in Galaxy, but on
@@ -112,7 +107,7 @@ class OMETiff(Tiff):
     )
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         spec_key = "offsets"
         offsets_file = dataset.metadata.offsets
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index f1f9fac770b..dfffbf5073a 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -9,7 +9,6 @@ from typing import (
     List,
     Optional,
     Tuple,
-    TYPE_CHECKING,
     Union,
 )
 from urllib.parse import quote_plus
@@ -31,6 +30,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t18,
     Dataset_t19,
     Dataset_t20,
+    Dataset_t24,
     HasId,
     HasMetadata,
 )
@@ -60,9 +60,6 @@ from . import (
     dataproviders,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 # Contains the meta columns and the words that map to it; list aliases on the
@@ -139,7 +136,7 @@ class Interval(Tabular):
         Tabular.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: "DatasetInstance", *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
+        self, dataset: Dataset_t24, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
     ) -> None:
         """Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=0)
@@ -509,7 +506,7 @@ class Bed(Interval):
     )
     # do we need to repeat these? they are the same as should be inherited from interval type
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """Sets the metadata information for datasets previously determined to be in bed format."""
         if dataset.has_data():
             i = 0
@@ -742,7 +739,7 @@ class BedStrict(Bed):
         Tabular.__init__(self, **kwd)
         self.clear_display_apps()  # only new style display applications for this datatype
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)  # need column count first
         if dataset.metadata.columns >= 4:
             dataset.metadata.nameCol = 4
@@ -866,7 +863,7 @@ class Gff(Tabular, _RemoteCallMixin):
         dataset.metadata.attribute_types = attribute_types
         dataset.metadata.attributes = len(attribute_types)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
 
         i = 0
@@ -1085,7 +1082,7 @@ class Gff3(Gff):
         """Initialize datatype, by adding GBrowse display app"""
         Gff.__init__(self, **kwd)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
         i = 0
         with compression_utils.get_fileobj(dataset.file_name) as in_fh:
@@ -1397,7 +1394,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         max_data_lines = None
         i = 0
         for i, line in enumerate(open(dataset.file_name)):  # noqa: B007
@@ -1478,7 +1475,7 @@ class CustomTrack(Tabular):
         Tabular.__init__(self, **kwd)
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
     def display_peek(self, dataset: Dataset_t20) -> str:
@@ -1794,7 +1791,7 @@ class IntervalTabix(Interval):
     # Ideally the tabix_index would be regenerated when the metadataElements are updated
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         first_line_is_header: bool = False,
         metadata_tmp_files_dir: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/media.py b/lib/galaxy/datatypes/media.py
index 987df7fc928..a3cbde1560f 100644
--- a/lib/galaxy/datatypes/media.py
+++ b/lib/galaxy/datatypes/media.py
@@ -6,9 +6,9 @@ from functools import lru_cache
 from typing import (
     List,
     Tuple,
-    TYPE_CHECKING,
 )
 
+from galaxy.datatypes._protocols import Dataset_t24
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -16,9 +16,6 @@ from galaxy.datatypes.metadata import (
 )
 from galaxy.util import which
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 @lru_cache(maxsize=128)
 def _ffprobe(path):
@@ -75,7 +72,7 @@ class Audio(Binary):
         no_value=0,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
 
@@ -162,7 +159,7 @@ class Video(Binary):
             w = h = fps = 0
         return w, h, fps
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
             (w, h, fps) = self._get_resolution(streams)
@@ -283,7 +280,7 @@ class Wav(Audio):
         with wave.open(filename, "rb"):
             return True
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents."""
         try:
             with wave.open(dataset.dataset.file_name, "rb") as fd:
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index a34d79e2d70..a6ef527d0ad 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -1,8 +1,10 @@
 import logging
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes import data
-from galaxy.datatypes._protocols import Dataset_t23
+from galaxy.datatypes._protocols import (
+    Dataset_t23,
+    Dataset_t24,
+)
 from galaxy.datatypes.binary import Cel  # noqa: F401
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.metadata import MetadataElement
@@ -12,9 +14,6 @@ from galaxy.datatypes.sniff import (
     get_headers,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -121,7 +120,7 @@ class Gal(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix ArrayList" in headers[2][0]
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gal file.
         """
@@ -163,7 +162,7 @@ class Gpr(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix Results" in headers[2][0]
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gpr file.
         """
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index be652e1c438..062d31266c7 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -5,13 +5,13 @@ from typing import (
     Callable,
     Dict,
     List,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -33,9 +33,6 @@ from galaxy.util import (
     unicodify,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 # optional import to enhance metadata
 try:
     from ase import io as ase_io
@@ -208,7 +205,7 @@ class GenericMolFile(Text):
 class MOL(GenericMolFile):
     file_ext = "mol"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number molecules, in the case of MOL its always one.
         """
@@ -261,7 +258,7 @@ class SDF(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of molecules in dataset.
         """
@@ -344,7 +341,7 @@ class MOL2(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -430,7 +427,7 @@ class FPS(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -571,7 +568,7 @@ class OBFS(Binary):
 class DRF(GenericMolFile):
     file_ext = "drf"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -638,7 +635,7 @@ class PDB(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Find Chain_IDs for metadata.
         """
@@ -792,7 +789,7 @@ class PQR(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Find Optional Chain_IDs for metadata.
         """
@@ -889,7 +886,7 @@ class Cell(GenericMolFile):
                 return True
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1050,7 +1047,7 @@ class CIF(GenericMolFile):
                 return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1247,7 +1244,7 @@ class XYZ(GenericMolFile):
                     raise
         return blocks
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1501,7 +1498,7 @@ class InChI(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -1566,7 +1563,7 @@ class SMILES(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -1602,7 +1599,7 @@ class CML(GenericXml):
         no_value=0,
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index d005ce2a5ca..206f40d391b 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -6,11 +6,11 @@ import re
 from typing import (
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes._protocols import (
     Dataset_t10,
+    Dataset_t24,
     HasMetadata,
 )
 from galaxy.datatypes.data import Text
@@ -24,9 +24,6 @@ from galaxy.datatypes.sniff import (
 from galaxy.datatypes.tabular import Tabular
 from galaxy.util import unicodify
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -40,7 +37,7 @@ class Otu(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Otu files.
 
@@ -177,7 +174,7 @@ class GroupAbund(Otu):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         # See if file starts with header line
@@ -301,7 +298,7 @@ class AlignCheck(Tabular):
         self.column_types = ["str", "int", "int", "int", "int", "int", "int", "int"]
         self.comment_lines = 1
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         dataset.metadata.column_names = self.column_names
@@ -358,7 +355,7 @@ class DistanceMatrix(Text):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
         headers = iter_headers(dataset.file_name, sep="\t")
@@ -511,7 +508,7 @@ class PairwiseDistanceMatrix(DistanceMatrix, Tabular):
         self.column_names = ["Sequence", "Sequence", "Distance"]
         self.column_types = ["str", "str", "float"]
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -601,7 +598,7 @@ class Group(Tabular):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = None,
@@ -849,7 +846,7 @@ class CountTable(Tabular):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1061,7 +1058,7 @@ class SffFlow(Tabular):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index c69c4ca97b7..d3f2fd6d0af 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -6,12 +6,12 @@ from typing import (
     Callable,
     Dict,
     List,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -29,9 +29,6 @@ from galaxy.util import (
     unicodify,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 STOCKHOLM_SEARCH_PATTERN = re.compile(r"#\s+STOCKHOLM\s+1\.0")
@@ -85,7 +82,7 @@ class InfernalCM(Text):
         """
         return file_prefix.startswith("INFERNAL")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models and the version of CM file in dataset.
         """
@@ -202,7 +199,7 @@ class Stockholm_1_0(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.search(STOCKHOLM_SEARCH_PATTERN)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
 
         Set the number of models in dataset.
@@ -293,7 +290,7 @@ class MauveXmfa(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith("#FormatVersion Mauve1")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         dataset.metadata.number_of_models = generic_util.count_special_lines(
             "^#Sequence([[:digit:]]+)Entry", dataset.file_name
         )
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index efaaa1f8a75..0fd08b20966 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -10,7 +10,10 @@ Phylip datatype sniffer
 from typing import TYPE_CHECKING
 
 from galaxy import util
-from galaxy.datatypes._protocols import Dataset_t23
+from galaxy.datatypes._protocols import (
+    Dataset_t23,
+    Dataset_t24,
+)
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -25,8 +28,6 @@ from .metadata import MetadataElement
 if TYPE_CHECKING:
     from io import StringIO
 
-    from galaxy.model import DatasetInstance
-
 
 @build_sniff_from_prefix
 class Phylip(Text):
@@ -40,7 +41,7 @@ class Phylip(Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index 45de9b9c449..9e7451d8144 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -1,10 +1,10 @@
 import logging
 import re
-from typing import TYPE_CHECKING
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -19,9 +19,6 @@ from galaxy.datatypes.sniff import (
 from galaxy.datatypes.tabular import Tabular
 from galaxy.util import nice_size
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -107,7 +104,7 @@ class PlantTribesKsComponents(Tabular):
         except Exception:
             return f"Significant components in the Ks distribution ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of significant components in the Ks distribution.
         The dataset will always be on the order of less than 10 lines.
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 50493a37f66..b8f1bbc9586 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -7,13 +7,13 @@ from typing import (
     IO,
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.binary import Binary
@@ -30,9 +30,6 @@ from galaxy.datatypes.tabular import (
 from galaxy.datatypes.xml import GenericXml
 from galaxy.util import nice_size
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -396,7 +393,7 @@ class Dta(TabularData):
     file_ext = "dta"
     comment_lines = 0
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         column_types = []
         data_row: List = []
         data_lines = 0
@@ -469,7 +466,7 @@ class Dta2d(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         if dataset.has_data():
@@ -605,7 +602,7 @@ class Edta(TabularData):
                 line[idx] += str(idx // 4)
         return line
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         tpe = None
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index 64cc5abd927..dd67601d520 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -7,7 +7,6 @@ from typing import (
     Dict,
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 import yaml
@@ -15,6 +14,7 @@ import yaml
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     HasMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
@@ -25,9 +25,6 @@ from galaxy.datatypes.sniff import (
 )
 from galaxy.datatypes.tabular import Tabular
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 class _QIIME2ResultBase(CompressedZipArchive):
     """Base class for QIIME2Artifact and QIIME2Visualization"""
@@ -38,7 +35,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
     MetadataElement(name="format", optional=True, no_value="", readonly=True)
     MetadataElement(name="version", readonly=True)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         metadata = _get_metadata_from_archive(dataset.file_name)
         for key, value in metadata.items():
             if value:
@@ -120,7 +117,7 @@ class QIIME2Metadata(Tabular):
     def get_column_names(self, first_line: str) -> Optional[List[str]]:
         return first_line.strip().split("\t")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Let Galaxy's Tabular format handle most of this. We will just jump
         in at the last minute to (potentially) override some column types.
diff --git a/lib/galaxy/datatypes/qualityscore.py b/lib/galaxy/datatypes/qualityscore.py
index 49ddc9c3eff..9d116a2ebfe 100644
--- a/lib/galaxy/datatypes/qualityscore.py
+++ b/lib/galaxy/datatypes/qualityscore.py
@@ -2,17 +2,14 @@
 Qualityscore class
 """
 import logging
-from typing import TYPE_CHECKING
 
+from galaxy.datatypes._protocols import Dataset_t24
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
 )
 from . import data
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 
@@ -69,7 +66,7 @@ class QualityScoreSOLiD(QualityScore):
                     return False
         return goodblock > 0
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             return
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 952a06138d8..8610926c086 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -30,6 +30,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t19,
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -53,10 +54,7 @@ from galaxy.util.image_util import check_image_type
 from . import data
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 log = logging.getLogger(__name__)
 
@@ -115,7 +113,7 @@ class Sequence(data.Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -571,7 +569,7 @@ class csFasta(Sequence):
                     return False
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             dataset.metadata.sequences = None
@@ -648,7 +646,7 @@ class Fastg(Sequence):
                     break  # we found a non-empty line, but it's not a header
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         with open(dataset.file_name) as fh:
             for i, line in enumerate(fh):
                 if not line:
@@ -697,7 +695,7 @@ class BaseFastq(Sequence):
     file_ext = "fastq"
     bases_regexp = re.compile(r"^[NGTAC 0123\.]*$", re.IGNORECASE)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
@@ -1022,7 +1020,7 @@ class Maf(Alignment):
         Alignment.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """
         Parses and sets species, chromosomes, index from MAF file.
@@ -1149,7 +1147,7 @@ class MafCustomTrack(data.Text):
         name="vp_end", default="100", desc="Viewport End", readonly=True, optional=True, visible=False, no_value=""
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Parses and sets viewport metadata from MAF file.
         """
@@ -1320,7 +1318,7 @@ class DotBracket(Sequence):
     sequence_regexp = re.compile(r"^[ACGTURYKMSWBDHVN]+$", re.I)
     structure_regexp = re.compile(r"^[\(\)\.\[\]{}]+$")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 700f0253711..9c1c486c781 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -16,6 +16,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import Data
@@ -23,10 +24,7 @@ from galaxy.datatypes.metadata import MetadataElement
 from galaxy.util import smart_str
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 log = logging.getLogger(__name__)
 verbose = True
@@ -186,7 +184,7 @@ class _SpalnDb(Data):
             return None
         raise NotImplementedError("Can't split spaln database")
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         efp = dataset.extra_files_path
         for filename in os.listdir(efp):
diff --git a/lib/galaxy/datatypes/speech.py b/lib/galaxy/datatypes/speech.py
index 559cffee5d4..c66e44e1cba 100644
--- a/lib/galaxy/datatypes/speech.py
+++ b/lib/galaxy/datatypes/speech.py
@@ -1,5 +1,4 @@
-from typing import TYPE_CHECKING
-
+from galaxy.datatypes._protocols import Dataset_t24
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -7,9 +6,6 @@ from galaxy.datatypes.metadata import (
 )
 from galaxy.datatypes.sniff import get_headers
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 class TextGrid(Text):
     """Praat Textgrid file for speech annotations
@@ -102,7 +98,7 @@ class BPF(Text):
         "SAO",
     ]
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents"""
         types = set()
         with open(dataset.dataset.file_name) as fd:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 67d9d4aa897..847c05579e2 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -40,6 +40,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t19,
     Dataset_t20,
     Dataset_t23,
+    Dataset_t24,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -85,10 +86,7 @@ from galaxy.util.markdown import (
 from . import dataproviders
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 log = logging.getLogger(__name__)
 
@@ -135,7 +133,7 @@ class TabularData(Text):
     )
 
     @abc.abstractmethod
-    def set_meta(self, dataset: "DatasetInstance", *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
     def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
@@ -423,7 +421,7 @@ class Tabular(TabularData):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         *,
         overwrite: bool = True,
         skip: Optional[int] = None,
@@ -605,7 +603,7 @@ class SraManifest(Tabular):
     file_ext = "sra_manifest.tabular"
     data_line_offset = 1
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.comment_lines = 1
 
@@ -795,7 +793,7 @@ class Sam(Tabular, _BamOrSam):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1059,7 +1057,7 @@ class BaseVcf(Tabular):
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         line = None
         with compression_utils.get_fileobj(dataset.file_name) as fh:
@@ -1140,7 +1138,7 @@ class VcfGz(BaseVcf, binary.Binary):
             return binascii.hexlify(last28) == b"1f8b08040000000000ff0600424302001b0003000000000000000000"
 
     def set_meta(
-        self, dataset: "DatasetInstance", overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         # Creates the index for the VCF file.
@@ -1304,7 +1302,7 @@ class Eland(Tabular):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1466,7 +1464,7 @@ class BaseCSV(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         column_types = []
         header_row = []
         data_row = []
@@ -1548,7 +1546,7 @@ class ConnectivityTable(Tabular):
         self.column_names = ["base_index", "base", "neighbor_left", "neighbor_right", "partner", "natural_numbering"]
         self.column_types = ["int", "str", "int", "int", "int", "int"]
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
 
         with open(dataset.file_name) as fh:
@@ -1683,7 +1681,7 @@ class MatrixMarket(TabularData):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1811,7 +1809,7 @@ class CMAP(TabularData):
 
     def set_meta(
         self,
-        dataset: "DatasetInstance",
+        dataset: Dataset_t24,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 7,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 8b1f1d89e9b..18b01fe7938 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -21,6 +21,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t22,
     Dataset_t23,
+    Dataset_t24,
     GeneratePrimaryFileDataset,
     HasCreatingJobProperty,
 )
@@ -46,10 +47,7 @@ from galaxy.util import (
 )
 
 if TYPE_CHECKING:
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetAssociation,
-    )
+    from galaxy.model import HistoryDatasetAssociation
 
 log = logging.getLogger(__name__)
 
@@ -149,7 +147,7 @@ class ExpressionJson(Json):
         name="json_type", default=None, desc="JavaScript or JSON type of expression", readonly=True, visible=True
     )
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """ """
         if dataset.has_data():
             json_type = "null"
@@ -259,7 +257,7 @@ class Ipynb(Json):
                 )
             return open(ofilename, mode="rb"), headers
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models in dataset.
         """
@@ -432,7 +430,7 @@ class Biom1(Json):
             pass
         return is_biom
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the BIOM file.
         """
@@ -533,7 +531,7 @@ class ImgtJson(Json):
             pass
         return is_imgt
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the imgt file.
         """
@@ -699,7 +697,7 @@ class Arff(Text):
                     return True
         return False
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         """
         Trying to count the comment lines and the number of columns included.
         A typical ARFF data block looks like this:
@@ -784,7 +782,7 @@ class SnpEffDb(Text):
             pass
         return snpeff_version
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         data_dir = dataset.extra_files_path
         # search data_dir/genome_version for files
@@ -889,7 +887,7 @@ class SnpSiftDbNSFP(Text):
                 f.write("\n")
             f.write(annotations)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         try:
             efp = dataset.extra_files_path
             if os.path.exists(efp):
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index ded723b096e..ebc7e8c6ed5 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -3,15 +3,13 @@ XML format classes
 """
 import logging
 import re
-from typing import (
-    List,
-    TYPE_CHECKING,
-)
+from typing import List
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t2,
     Dataset_t23,
+    Dataset_t24,
 )
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -26,9 +24,6 @@ from . import (
     dataproviders,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 log = logging.getLogger(__name__)
 
 OWL_MARKER = re.compile(r"\<owl:")
@@ -156,7 +151,7 @@ class Dzi(GenericXml):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: "DatasetInstance", overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
         tree = util.parse_xml(dataset.file_name)
         root = tree.getroot()
         dataset.metadata.format = root.get("Format")

From dad66fd4a0106fb947af314b43e1795413dab864 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 17:50:52 -0500
Subject: [PATCH 100/350] Remove HDA from display_data

---
 lib/galaxy/datatypes/_protocols.py | 18 ++++++++++++++++++
 lib/galaxy/datatypes/binary.py     |  6 +++---
 lib/galaxy/datatypes/blast.py      |  7 ++-----
 lib/galaxy/datatypes/data.py       |  8 +++-----
 lib/galaxy/datatypes/isa.py        |  5 ++---
 lib/galaxy/datatypes/sequence.py   |  7 ++-----
 lib/galaxy/datatypes/spaln.py      |  7 ++-----
 lib/galaxy/datatypes/tabular.py    |  7 ++-----
 lib/galaxy/datatypes/text.py       |  9 +++------
 9 files changed, 37 insertions(+), 37 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 1e0ec2e0059..dddd50448ff 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -187,3 +187,21 @@ class Dataset_t24(
 
     def get_size(self) -> str:
         ...
+
+
+class Dataset_t25(
+    HasFileNameProperty,
+    HasDataset,
+    HasId,
+    HasMetadata,
+    HasCreatingJobProperty,
+    HasName,
+    HasExtraFilesPathProperty,
+    Protocol,
+):
+    datatype: Any
+    extension: str  # TODO reconcile: ext vs. extension
+    hid: str
+
+    def get_mime(self) -> str:
+        ...
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index cc8cd766f78..8fc94d900b8 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -40,6 +40,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     GeneratePrimaryFileDataset,
     HasFileNameProperty,
     HasMetadata,
@@ -91,7 +92,6 @@ from . import (
 )
 
 if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
     from galaxy.util.compression_utils import FileObjType
 
 log = logging.getLogger(__name__)
@@ -650,7 +650,7 @@ class BamNative(CompressedArchive, _BamOrSam):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -2021,7 +2021,7 @@ class H5MLM(H5):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index 152df30d991..860e1d1eec9 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -38,12 +38,12 @@ from typing import (
     Dict,
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t25,
 )
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -57,9 +57,6 @@ from .data import (
 )
 from .xml import GenericXml
 
-if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
-
 log = logging.getLogger(__name__)
 
 
@@ -215,7 +212,7 @@ class _BlastDb(Data):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 663d9b5cd9d..f6d9ff1f353 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -38,6 +38,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -81,7 +82,6 @@ if TYPE_CHECKING:
     from galaxy.datatypes.registry import Registry
     from galaxy.model import (
         DatasetInstance,
-        HistoryDatasetAssociation,
         HistoryDatasetCollectionAssociation,
     )
 
@@ -405,9 +405,7 @@ class Data(metaclass=DataMeta):
                 rpath = os.path.relpath(fpath, extra_files_path)
                 yield fpath, rpath
 
-    def _serve_raw(
-        self, dataset: "HistoryDatasetAssociation", to_ext: Optional[str], headers: Headers, **kwd
-    ) -> Tuple[IO, Headers]:
+    def _serve_raw(self, dataset: Dataset_t25, to_ext: Optional[str], headers: Headers, **kwd) -> Tuple[IO, Headers]:
         headers["Content-Length"] = str(os.stat(dataset.file_name).st_size)
         headers[
             "content-type"
@@ -447,7 +445,7 @@ class Data(metaclass=DataMeta):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index fe80b713dbc..ef3f226af3c 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -29,6 +29,7 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
+    Dataset_t25,
     GeneratePrimaryFileDataset,
     HasExtraFilesPathProperty,
 )
@@ -39,8 +40,6 @@ from galaxy.util.sanitize_html import sanitize_html
 if TYPE_CHECKING:
     from isatools.model import Investigation
 
-    from galaxy.model import HistoryDatasetAssociation
-
 # CONSTANTS {{{1
 ################################################################
 
@@ -270,7 +269,7 @@ class _Isa(Data):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 8610926c086..c5744b72401 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -17,7 +17,6 @@ from typing import (
     Iterable,
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 import bx.align.maf
@@ -31,6 +30,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -53,9 +53,6 @@ from galaxy.util.checkers import is_gzip
 from galaxy.util.image_util import check_image_type
 from . import data
 
-if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
-
 log = logging.getLogger(__name__)
 
 
@@ -776,7 +773,7 @@ class BaseFastq(Sequence):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 9c1c486c781..025d5b1aba0 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -9,7 +9,6 @@ from typing import (
     Dict,
     List,
     Optional,
-    TYPE_CHECKING,
 )
 
 from galaxy.datatypes._protocols import (
@@ -17,15 +16,13 @@ from galaxy.datatypes._protocols import (
     Dataset_t22,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     GeneratePrimaryFileDataset,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.util import smart_str
 
-if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
-
 log = logging.getLogger(__name__)
 verbose = True
 
@@ -123,7 +120,7 @@ class _SpalnDb(Data):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 847c05579e2..f0bf9b98918 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -17,7 +17,6 @@ from typing import (
     Dict,
     List,
     Optional,
-    TYPE_CHECKING,
     Union,
 )
 
@@ -41,6 +40,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t20,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     HasFileNameProperty,
     HasMetadata,
 )
@@ -85,9 +85,6 @@ from galaxy.util.markdown import (
 )
 from . import dataproviders
 
-if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
-
 log = logging.getLogger(__name__)
 
 MAX_DATA_LINES = 100000
@@ -179,7 +176,7 @@ class TabularData(Text):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 18b01fe7938..f4d46547bee 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -12,7 +12,6 @@ from typing import (
     IO,
     Optional,
     Tuple,
-    TYPE_CHECKING,
 )
 
 import yaml
@@ -22,6 +21,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t22,
     Dataset_t23,
     Dataset_t24,
+    Dataset_t25,
     GeneratePrimaryFileDataset,
     HasCreatingJobProperty,
 )
@@ -46,9 +46,6 @@ from galaxy.util import (
     unicodify,
 )
 
-if TYPE_CHECKING:
-    from galaxy.model import HistoryDatasetAssociation
-
 log = logging.getLogger(__name__)
 
 
@@ -201,7 +198,7 @@ class Ipynb(Json):
     def display_data(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -222,7 +219,7 @@ class Ipynb(Json):
     def _display_data_trusted(
         self,
         trans,
-        dataset: "HistoryDatasetAssociation",
+        dataset: Dataset_t25,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,

From 94ab15235f4275646dd48ca32a8806fa5ccb99f2 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 18:00:44 -0500
Subject: [PATCH 101/350] Remove DatasetInstance from registry.py

---
 lib/galaxy/datatypes/registry.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/registry.py b/lib/galaxy/datatypes/registry.py
index f5bda77caf9..ec017d862be 100644
--- a/lib/galaxy/datatypes/registry.py
+++ b/lib/galaxy/datatypes/registry.py
@@ -14,7 +14,6 @@ from typing import (
     List,
     Optional,
     Tuple,
-    TYPE_CHECKING,
     Union,
 )
 
@@ -40,9 +39,6 @@ from . import (
 )
 from .display_applications.application import DisplayApplication
 
-if TYPE_CHECKING:
-    from galaxy.model import DatasetInstance
-
 
 class ConfigurationError(Exception):
     pass
@@ -836,7 +832,7 @@ class Registry:
 
     def find_conversion_destination_for_dataset_by_extensions(
         self, dataset_or_ext: Union[str, Dataset_t16], accepted_formats: List[str], converter_safe: bool = True
-    ) -> Tuple[bool, Optional[str], Optional["DatasetInstance"]]:
+    ) -> Tuple[bool, Optional[str], Optional[Dataset_t16]]:
         """
         returns (direct_match, converted_ext, converted_dataset)
         - direct match is True iff no the data set already has an accepted format

From b74bb9d51cb3325e7b56aad09fc3be6066125514 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 18:04:34 -0500
Subject: [PATCH 102/350] Remove HDCA from data.py

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/data.py       | 8 +++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index dddd50448ff..2e75e1df0ad 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -205,3 +205,7 @@ class Dataset_t25(
 
     def get_mime(self) -> str:
         ...
+
+
+class Dataset_t26(HasName, Protocol):
+    hid: str
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index f6d9ff1f353..cf508a1d8e3 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -39,6 +39,7 @@ from galaxy.datatypes._protocols import (
     Dataset_t23,
     Dataset_t24,
     Dataset_t25,
+    Dataset_t26,
     GeneratePrimaryFileDataset,
     HasClearAssociatedFiles,
     HasCreatingJobProperty,
@@ -80,10 +81,7 @@ from . import (
 if TYPE_CHECKING:
     from galaxy.datatypes.display_applications.application import DisplayApplication
     from galaxy.datatypes.registry import Registry
-    from galaxy.model import (
-        DatasetInstance,
-        HistoryDatasetCollectionAssociation,
-    )
+    from galaxy.model import DatasetInstance
 
 XSS_VULNERABLE_MIME_TYPES = [
     "image/svg+xml",  # Unfiltered by Galaxy and may contain JS that would be executed by some browsers.
@@ -611,7 +609,7 @@ class Data(metaclass=DataMeta):
         self,
         dataset: Dataset_t4,
         to_ext: Optional[str] = None,
-        hdca: Optional["HistoryDatasetCollectionAssociation"] = None,
+        hdca: Optional[Dataset_t26] = None,
         element_identifier: Optional[str] = None,
         filename_pattern: Optional[str] = None,
     ) -> str:

From d475faeeee27904aecd0c99a17cb13f81b91678d Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 18:14:24 -0500
Subject: [PATCH 103/350] Remove last DatasetInstance import from datatypes

---
 lib/galaxy/datatypes/_protocols.py | 4 ++++
 lib/galaxy/datatypes/data.py       | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 2e75e1df0ad..95402e7ac85 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -209,3 +209,7 @@ class Dataset_t25(
 
 class Dataset_t26(HasName, Protocol):
     hid: str
+
+
+class Dataset_t0(Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index cf508a1d8e3..bbae546a639 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -24,6 +24,7 @@ from typing_extensions import Literal
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
+    Dataset_t0,
     Dataset_t1,
     Dataset_t2,
     Dataset_t3,
@@ -81,7 +82,6 @@ from . import (
 if TYPE_CHECKING:
     from galaxy.datatypes.display_applications.application import DisplayApplication
     from galaxy.datatypes.registry import Registry
-    from galaxy.model import DatasetInstance
 
 XSS_VULNERABLE_MIME_TYPES = [
     "image/svg+xml",  # Unfiltered by Galaxy and may contain JS that would be executed by some browsers.
@@ -708,7 +708,7 @@ class Data(metaclass=DataMeta):
     def get_display_application(self, key: str, default: Optional["DisplayApplication"] = None) -> "DisplayApplication":
         return self.display_applications.get(key, default)
 
-    def get_display_applications_by_dataset(self, dataset: "DatasetInstance", trans) -> Dict[str, "DisplayApplication"]:
+    def get_display_applications_by_dataset(self, dataset: Dataset_t0, trans) -> Dict[str, "DisplayApplication"]:
         rval = {}
         for key, value in self.display_applications.items():
             value = value.filter_by_dataset(dataset, trans)

From 232e9291dee7125e4677a2c6c99e7fce553ea639 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 16 Dec 2022 19:35:32 -0500
Subject: [PATCH 104/350] Refactor, rename protocols

---
 lib/galaxy/datatypes/_protocols.py            | 380 ++++++++++--------
 lib/galaxy/datatypes/annotation.py            |  12 +-
 lib/galaxy/datatypes/anvio.py                 |  16 +-
 lib/galaxy/datatypes/assembly.py              |  12 +-
 lib/galaxy/datatypes/binary.py                | 282 ++++++-------
 lib/galaxy/datatypes/blast.py                 |  18 +-
 .../datatypes/constructive_solid_geometry.py  |  44 +-
 lib/galaxy/datatypes/data.py                  | 110 ++---
 lib/galaxy/datatypes/flow.py                  |   8 +-
 lib/galaxy/datatypes/genetics.py              |  54 +--
 lib/galaxy/datatypes/gis.py                   |  12 +-
 lib/galaxy/datatypes/goldenpath.py            |   4 +-
 lib/galaxy/datatypes/graph.py                 |  12 +-
 lib/galaxy/datatypes/hdf5.py                  |   4 +-
 lib/galaxy/datatypes/images.py                |  18 +-
 lib/galaxy/datatypes/interval.py              |  96 ++---
 lib/galaxy/datatypes/isa.py                   |  24 +-
 lib/galaxy/datatypes/media.py                 |   8 +-
 lib/galaxy/datatypes/microarrays.py           |  10 +-
 lib/galaxy/datatypes/molecules.py             |  66 +--
 lib/galaxy/datatypes/mothur.py                |  22 +-
 lib/galaxy/datatypes/msa.py                   |  26 +-
 lib/galaxy/datatypes/neo4j.py                 |  12 +-
 lib/galaxy/datatypes/ngsindex.py              |  16 +-
 lib/galaxy/datatypes/phylip.py                |   8 +-
 lib/galaxy/datatypes/plant_tribes.py          |  16 +-
 lib/galaxy/datatypes/proteomics.py            |  48 +--
 lib/galaxy/datatypes/qiime2.py                |  14 +-
 lib/galaxy/datatypes/qualityscore.py          |   4 +-
 lib/galaxy/datatypes/registry.py              |   8 +-
 lib/galaxy/datatypes/sequence.py              |  44 +-
 lib/galaxy/datatypes/spaln.py                 |  24 +-
 lib/galaxy/datatypes/speech.py                |   4 +-
 lib/galaxy/datatypes/tabular.py               | 120 +++---
 lib/galaxy/datatypes/text.py                  |  68 ++--
 lib/galaxy/datatypes/tracks.py                |  12 +-
 lib/galaxy/datatypes/triples.py               |  16 +-
 lib/galaxy/datatypes/xml.py                   |  24 +-
 38 files changed, 861 insertions(+), 815 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 95402e7ac85..693c3b3ff01 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -6,48 +6,8 @@ from typing import Any
 from typing_extensions import Protocol
 
 
-class HasExtraFilesPathProperty(Protocol):
-    @property
-    def extra_files_path(self):
-        ...
-
-
-class HasFileNameProperty(Protocol):
-    @property
-    def file_name(self):
-        ...
-
-
-class HasPeekProperty(Protocol):
-    @property
-    def peek(self):
-        ...
-
-
-class HasId(Protocol):
-    id: int
-
-
-class HasMetadata(Protocol):
-    metadata: Any
-
-
-class HasInfo(Protocol):
-    info: str
-
-
-class HasName(Protocol):
-    name: str
-
-
-class HasDataset(Protocol):
-    dataset: Any  # TODO tighten
-
-
-class HasCreatingJobProperty(Protocol):
-    @property
-    def creating_job(self):
-        ...
+class HasBlurb(Protocol):
+    blurb: str
 
 
 class HasClearAssociatedFiles(Protocol):
@@ -55,161 +15,243 @@ class HasClearAssociatedFiles(Protocol):
         ...
 
 
-class HasDbKey(Protocol):
-    dbkey: str
+class HasCreatingJob(Protocol):
+    @property
+    def creating_job(self):
+        ...
 
 
-class HasExt(Protocol):
-    ext: str  # TODO reconcile: ext vs. extension
+class HasDataset(Protocol):
+    dataset: Any
 
 
 class HasDatatype(Protocol):
     datatype: Any
 
 
-class GeneratePrimaryFileDataset(HasExtraFilesPathProperty, HasMetadata, Protocol):
-    ...
+class HasDbKey(Protocol):
+    dbkey: str
 
 
-class Dataset_t1(HasName, HasExtraFilesPathProperty, HasFileNameProperty, Protocol):
-    extension: str  # TODO reconcile: ext vs. extension
+class HasExt(Protocol):
+    ext: str
 
 
-class Dataset_t2(HasMetadata, HasFileNameProperty, HasExt, HasDatatype, Protocol):
-    ...
+class HasExtension(Protocol):
+    extension: str
 
 
-class Dataset_t3(HasExt, Protocol):
-    hid: str
-
-
-class Dataset_t4(HasName, Protocol):
-    hid: str
-    extension: str  # TODO reconcile: ext vs. extension
-
-
-class Dataset_t5(HasFileNameProperty, Dataset_t4, Protocol):
-    ...
-
-
-class Dataset_t6(HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, HasDatatype, Protocol):
-    extension: str  # TODO reconcile: ext vs. extension
-
-
-class Dataset_t7(HasDataset, HasName, Protocol):
-    ...
-
-
-class Dataset_t8(HasMetadata, HasId, HasPeekProperty, Protocol):
-    def set_peek(self) -> None:
+class HasExtraFilesPath(Protocol):
+    @property
+    def extra_files_path(self):
         ...
 
 
-class Dataset_t9(HasMetadata, HasId, Protocol):
-    ...
+class HasFileName(Protocol):
+    file_name: Any
 
 
-class Dataset_t10(Dataset_t8, HasFileNameProperty, HasName, Protocol):
-    ...
-
-
-class Dataset_t11(HasFileNameProperty, Protocol):
-    def get_size(self) -> str:
-        ...
-
-
-class Dataset_t12(HasDataset, HasMetadata, Protocol):
-    state: Any  # TODO tighten (should be property)
-    states: Any
-
-    def has_data(self) -> bool:
-        ...
-
-
-class Dataset_t13(Dataset_t12, HasFileNameProperty, HasId, HasMetadata, Protocol):
-    ...
-
-
-class Dataset_t14(Dataset_t13, HasName, HasDbKey, Protocol):
-    ...
-
-
-class Dataset_t15(Dataset_t13, HasDbKey, Protocol):
-    ...
-
-
-class Dataset_t16(HasExt, Protocol):
+class HasGetConvertedFilesByType(Protocol):
     def get_converted_files_by_type(self, file_type):
         ...
 
 
-class Dataset_t17(Dataset_t7, Dataset_t10, Protocol):
-    ...
-
-
-class Dataset_t18(HasFileNameProperty, HasMetadata, Protocol):
-    ...
-
-
-class Dataset_t19(Dataset_t18, HasDatatype, Protocol):
-    ...
-
-
-class Dataset_t20(HasMetadata, HasFileNameProperty, HasName, HasId, HasPeekProperty, Protocol):
-    def set_peek(self) -> None:
-        ...
-
-    def get_size(self) -> str:
-        ...
-
-
-class Dataset_t22(HasFileNameProperty, HasMetadata, HasExtraFilesPathProperty, HasInfo, HasName, Protocol):
-    ...
-
-
-class Dataset_t23(HasDataset, HasFileNameProperty, HasMetadata, HasInfo, HasExtraFilesPathProperty, Protocol):
-    peek: Any  # TODO
-    blurb: str
-    extension: str  # TODO reconcile: ext vs. extension
-
-    def get_size(self) -> str:
-        ...
-
-
-class Dataset_t24(
-    HasMetadata, HasFileNameProperty, HasExtraFilesPathProperty, HasInfo, HasName, HasId, HasDataset, Protocol
-):
-    peek: Any  # TODO
-    blurb: str
-
-    def has_data(self) -> bool:
-        ...
-
-    def get_size(self) -> str:
-        ...
-
-
-class Dataset_t25(
-    HasFileNameProperty,
-    HasDataset,
-    HasId,
-    HasMetadata,
-    HasCreatingJobProperty,
-    HasName,
-    HasExtraFilesPathProperty,
-    Protocol,
-):
-    datatype: Any
-    extension: str  # TODO reconcile: ext vs. extension
-    hid: str
-
+class HasGetMime(Protocol):
     def get_mime(self) -> str:
         ...
 
 
-class Dataset_t26(HasName, Protocol):
+class HasGetSize(Protocol):
+    def get_size(self) -> str:
+        ...
+
+
+class HasHasData(Protocol):
+    def has_data(self) -> bool:
+        ...
+
+
+class HasHid(Protocol):
     hid: str
 
 
-class Dataset_t0(Protocol):
+class HasId(Protocol):
+    id: int
+
+
+class HasInfo(Protocol):
+    info: str
+
+
+class HasMetadata(Protocol):
+    metadata: Any
+
+
+class HasName(Protocol):
+    name: str
+
+
+class HasPeek(Protocol):
+    peek: Any
+
+
+class HasSetPeek(Protocol):
+    def set_peek(self) -> None:
+        ...
+
+
+class HasState(Protocol):
+    state: Any
+
+
+class HasStates(Protocol):
+    states: Any
+
+
+class DatasetProtocol0(Protocol):
+    ...
+
+
+class DatasetProtocol1(HasDataset, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol2(HasExt, HasHid, Protocol):
+    ...
+
+
+class DatasetProtocol3(HasFileName, HasGetSize, Protocol):
+    ...
+
+
+class DatasetProtocol4(HasFileName, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
+    ...
+
+
+class DatasetProtocol6(HasExtraFilesPath, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol7(HasId, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol8(HasHid, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol10(HasExtension, HasHid, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol11(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol12(HasExtension, HasExtraFilesPath, HasFileName, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol13(HasExtension, HasFileName, HasHid, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol14(HasId, HasMetadata, HasSetPeek, HasPeek, Protocol):
+    ...
+
+
+class DatasetProtocol15(HasDataset, HasHasData, HasMetadata, HasState, HasStates, Protocol):
+    ...
+
+
+class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol17(HasExtraFilesPath, HasFileName, HasInfo, HasMetadata, HasName, Protocol):
+    ...
+
+
+class DatasetProtocol18(HasFileName, HasId, HasMetadata, HasName, HasPeek, HasSetPeek, Protocol):
+    ...
+
+
+class DatasetProtocol19(HasDataset, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol):
+    ...
+
+
+class DatasetProtocol20(HasDataset, HasFileName, HasMetadata, HasId, HasName, HasPeek, HasSetPeek, Protocol):
+    ...
+
+
+class DatasetProtocol21(HasFileName, HasGetSize, HasId, HasMetadata, HasName, HasPeek, HasSetPeek, Protocol):
+    ...
+
+
+class DatasetProtocol22(
+    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol
+):
+    ...
+
+
+class DatasetProtocol23(
+    HasBlurb,
+    HasDataset,
+    HasExtension,
+    HasExtraFilesPath,
+    HasFileName,
+    HasGetSize,
+    HasInfo,
+    HasMetadata,
+    HasPeek,
+    Protocol,
+):
+    ...
+
+
+class DatasetProtocol24(
+    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
+):
+    ...
+
+
+class DatasetProtocol25(
+    HasBlurb,
+    HasDataset,
+    HasExtraFilesPath,
+    HasFileName,
+    HasGetSize,
+    HasHasData,
+    HasId,
+    HasInfo,
+    HasMetadata,
+    HasName,
+    HasPeek,
+    Protocol,
+):
+    ...
+
+
+class DatasetProtocol26(
+    HasCreatingJob,
+    HasDataset,
+    HasDatatype,
+    HasExtension,
+    HasExtraFilesPath,
+    HasFileName,
+    HasGetMime,
+    HasHid,
+    HasId,
+    HasMetadata,
+    HasName,
+    Protocol,
+):
     ...
diff --git a/lib/galaxy/datatypes/annotation.py b/lib/galaxy/datatypes/annotation.py
index 1009bc9cbe3..14440afd540 100644
--- a/lib/galaxy/datatypes/annotation.py
+++ b/lib/galaxy/datatypes/annotation.py
@@ -2,8 +2,8 @@ import logging
 import tarfile
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.binary import CompressedArchive
 from galaxy.datatypes.data import (
@@ -24,7 +24,7 @@ class SnapHmm(Text):
     file_ext = "snaphmm"
     edam_data = "data_1364"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "SNAP HMM model"
@@ -32,7 +32,7 @@ class SnapHmm(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -54,7 +54,7 @@ class Augustus(CompressedArchive):
     edam_data = "data_0950"
     compressed = True
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Augustus model"
             dataset.blurb = nice_size(dataset.get_size())
@@ -62,7 +62,7 @@ class Augustus(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 298b54ea17c..ac20938306c 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -8,10 +8,10 @@ import os
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
@@ -28,7 +28,7 @@ class AnvioComposite(Html):
     file_ext = "anvio_composite"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -67,7 +67,7 @@ class AnvioComposite(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Anvio database (multiple files)"
@@ -76,7 +76,7 @@ class AnvioComposite(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -96,7 +96,7 @@ class AnvioDB(AnvioComposite):
         if self._anvio_basename is not None:
             self.add_composite_file(self._anvio_basename, is_binary=True, optional=False)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the anvio_basename based upon actual extra_files_path contents.
         """
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 053bc181edf..2506a709704 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -13,9 +13,9 @@ from galaxy.datatypes import (
     sequence,
 )
 from galaxy.datatypes._protocols import (
-    Dataset_t22,
-    Dataset_t24,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol17,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -173,7 +173,7 @@ class Velvet(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         log.debug(f"Velvet log info  JJ generate_primary_file {dataset}")
         rval = ["<html><head><title>Velvet Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
@@ -192,7 +192,7 @@ class Velvet(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -243,6 +243,6 @@ class Velvet(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         Html.set_meta(self, dataset, overwrite=overwrite, **kwd)
         self.regenerate_primary_file(dataset)
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 8fc94d900b8..5f6e2daa9b1 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -34,15 +34,15 @@ from bx.seq.twobit import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t6,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
-    GeneratePrimaryFileDataset,
-    HasFileNameProperty,
+    DatasetProtocol6,
+    DatasetProtocol9,
+    DatasetProtocol11,
+    DatasetProtocol16,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
+    DatasetProtocol26,
+    HasFileName,
     HasMetadata,
 )
 from galaxy.datatypes.data import (
@@ -116,7 +116,7 @@ class Binary(data.Data):
     def register_unsniffable_binary_ext(ext):
         """Deprecated method."""
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
@@ -137,7 +137,7 @@ class Ab1(Binary):
     edam_format = "format_3000"
     edam_data = "data_0924"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ab1 sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -145,7 +145,7 @@ class Ab1(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -214,7 +214,7 @@ class Cel(Binary):
             found_cel_3 = True
         return found_cel_3 or found_cel_4 or found_cel_agcc
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Cel file.
         """
@@ -227,7 +227,7 @@ class Cel(Binary):
         elif header_bytes.decode("utf8", errors="ignore").startswith("[CEL]"):
             dataset.metadata.version = "3"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.blurb = f"Cel version: {dataset.metadata.version}"
             dataset.peek = get_file_peek(dataset.file_name)
@@ -261,7 +261,7 @@ class CompressedArchive(Binary):
     compressed = True
     is_binary = "maybe"  # type: ignore[assignment]  # https://github.com/python/mypy/issues/8796
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed binary file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -269,7 +269,7 @@ class CompressedArchive(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -318,7 +318,7 @@ class Bref3(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith_bytes(self._magic)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bref3 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -326,7 +326,7 @@ class Bref3(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -378,7 +378,7 @@ class CompressedZipArchive(CompressedArchive):
 
     file_ext = "zip"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed zip file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -386,7 +386,7 @@ class CompressedZipArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -417,7 +417,7 @@ class _BamOrSam:
     Helper class to set the metadata common to sam and bam files
     """
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         try:
             bam_file = pysam.AlignmentFile(dataset.file_name, mode="rb")
             # TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
@@ -522,7 +522,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         no_value={},
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         _BamOrSam().set_meta(dataset, overwrite=overwrite, **kwd)
 
     @staticmethod
@@ -553,7 +553,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bam alignments file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -561,13 +561,13 @@ class BamNative(CompressedArchive, _BamOrSam):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary bam alignments file ({nice_size(dataset.get_size())})"
 
-    def to_archive(self, dataset: Dataset_t6, name: str = "") -> Iterable:
+    def to_archive(self, dataset: DatasetProtocol16, name: str = "") -> Iterable:
         rel_paths = []
         file_paths = []
         rel_paths.append(f"{name or dataset.file_name}.{dataset.extension}")
@@ -610,7 +610,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         # Remove temp file and empty temporary directory
         os.rmdir(tmp_dir)
 
-    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileName, offset: int = 0, ck_size: Optional[int] = None) -> str:
         if not offset == -1:
             try:
                 with pysam.AlignmentFile(dataset.file_name, "rb", check_sq=False) as bamfile:
@@ -650,7 +650,7 @@ class BamNative(CompressedArchive, _BamOrSam):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -686,7 +686,7 @@ class BamNative(CompressedArchive, _BamOrSam):
                 headers,
             )
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         if not BamNative.is_bam(dataset.file_name):
             return DatatypeValidation.invalid("This dataset does not appear to a BAM file.")
         elif self.dataset_content_needs_grooming(dataset.file_name):
@@ -776,7 +776,7 @@ class Bam(BamNative):
         return needs_sorting
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         # These metadata values are not accessible by users, always overwrite
         super().set_meta(dataset=dataset, overwrite=overwrite, **kwd)
@@ -808,25 +808,25 @@ class Bam(BamNative):
     # TODO:?? seems like there should be an easier way to do/inherit this - metadata.comment_char?
     # TODO: incorporate samtools options to control output: regions first, then flags, etc.
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> FilteredLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return FilteredLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return ColumnarDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return DictDataProvider(samtools_source, **settings)
@@ -844,20 +844,20 @@ class Bam(BamNative):
     #    return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
         # in this case we can use an option of samtools view to provide just what we need (w/o regex)
         samtools_source = SamtoolsDataProvider(dataset, "-H")
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", DictDataProvider.settings)
-    def id_seq_qual_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         settings["indeces"] = [0, 9, 10]
         settings["column_types"] = ["str", "str", "str"]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", ColumnarDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
         # GenomicRegionDataProvider currently requires a dataset as source - may not be necc.
         # TODO:?? consider (at least) the possible use of a kwarg: metadata_source (def. to source.dataset),
         #   or remove altogether...
@@ -871,14 +871,14 @@ class Bam(BamNative):
         return self.column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", DictDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         settings["indeces"] = [2, 3, 3]
         settings["column_types"] = ["str", "int", "int"]
         settings["column_names"] = ["chrom", "start", "end"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("samtools")
-    def samtools_dataprovider(self, dataset: Dataset_t2, **settings) -> SamtoolsDataProvider:
+    def samtools_dataprovider(self, dataset: DatasetProtocol11, **settings) -> SamtoolsDataProvider:
         """Generic samtools interface - all options available through settings."""
         dataset_source = DatasetDataProvider(dataset)
         return SamtoolsDataProvider(dataset_source, **settings)
@@ -962,7 +962,7 @@ class CRAM(Binary):
     )
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         major_version, minor_version = self.get_cram_version(dataset.file_name)
         if major_version != -1:
@@ -984,7 +984,7 @@ class CRAM(Binary):
             log.warning("%s, get_cram_version Exception: %s", self, exc)
             return -1, -1
 
-    def set_index_file(self, dataset: HasFileNameProperty, index_file) -> bool:
+    def set_index_file(self, dataset: HasFileName, index_file) -> bool:
         try:
             pysam.index(dataset.file_name, index_file.file_name)  # type: ignore [attr-defined]
             return True
@@ -992,7 +992,7 @@ class CRAM(Binary):
             log.warning("%s, set_index_file Exception: %s", self, exc)
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CRAM binary alignment file"
             dataset.blurb = "binary data"
@@ -1045,7 +1045,7 @@ class Bcf(BaseBcf):
             return False
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """Creates the index for the BCF file."""
         # These metadata values are not accessible by users, always overwrite
@@ -1129,7 +1129,7 @@ class H5(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary HDF5 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1137,7 +1137,7 @@ class H5(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1235,7 +1235,7 @@ class Loom(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary Loom file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1243,13 +1243,13 @@ class Loom(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary Loom file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as loom_file:
@@ -1394,7 +1394,7 @@ class Anndata(H5):
                 return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         with h5py.File(dataset.file_name, "r") as anndata_file:
             dataset.metadata.title = anndata_file.attrs.get("title")
@@ -1500,7 +1500,7 @@ class Anndata(H5):
             if dataset.metadata.shape is None:
                 dataset.metadata.shape = (int(dataset.metadata.obs_size), int(dataset.metadata.var_size))
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             tmp = dataset.metadata
 
@@ -1528,7 +1528,7 @@ class Anndata(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1573,7 +1573,7 @@ class Grib(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary GRIB file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1581,13 +1581,13 @@ class Grib(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary GRIB file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the GRIB edition.
         """
@@ -1616,7 +1616,7 @@ class GmxBinary(Binary):
         # The first 4 bytes of any GROMACS binary file containing the magic number
         return file_prefix.magic_header(">1i") == self.magic_number
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary GROMACS {self.file_ext} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1624,7 +1624,7 @@ class GmxBinary(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1754,7 +1754,7 @@ class Biom2(H5):
                 return required_fields.issubset(f.attrs.keys())
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as f:
@@ -1776,7 +1776,7 @@ class Biom2(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, util.unicodify(e))
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Biom2 (HDF5) file"]
             try:
@@ -1791,7 +1791,7 @@ class Biom2(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1836,7 +1836,7 @@ class Cool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1844,7 +1844,7 @@ class Cool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1896,7 +1896,7 @@ class MCool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Multi-resolution Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1904,7 +1904,7 @@ class MCool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1940,7 +1940,7 @@ class H5MLM(H5):
     )
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         try:
             spec_key = "hyper_params"
@@ -2003,7 +2003,7 @@ class H5MLM(H5):
             log.warning("%s, get model configuration Except: %s", self, e)
             return ""
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             repr = self.get_repr(dataset.file_name)
             dataset.peek = repr[: self.max_peek_size]
@@ -2012,7 +2012,7 @@ class H5MLM(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2021,7 +2021,7 @@ class H5MLM(H5):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -2073,7 +2073,7 @@ class LudwigModel(Html):
             "training_progress.json", description="Training progress", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Ludwig Model Composite Dataset.</title></head><p/>"]
         rval.append("<div>This model dataset is composed of the following items:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -2132,7 +2132,7 @@ class HexrdMaterials(H5):
                         return True
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as mat_file:
@@ -2149,7 +2149,7 @@ class HexrdMaterials(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Material SpaceGroup Lattice"]
             if dataset.metadata.materials:
@@ -2174,7 +2174,7 @@ class Scf(Binary):
     edam_data = "data_0924"
     file_ext = "scf"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary scf sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2182,7 +2182,7 @@ class Scf(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2202,7 +2202,7 @@ class Sff(Binary):
         # about the format, see http://www.ncbi.nlm.nih.gov/Traces/trace.cgi?cmd=show&f=formats&m=doc&s=format
         return file_prefix.startswith_bytes(b".sff")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sff file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2210,7 +2210,7 @@ class Sff(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2239,7 +2239,7 @@ class BigWig(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.magic_header("I") == self._magic
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary UCSC {self._name} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2247,7 +2247,7 @@ class BigWig(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2280,14 +2280,14 @@ class TwoBit(Binary):
         magic = file_prefix.magic_header(">L")
         return magic == TWOBIT_MAGIC_NUMBER or magic == TWOBIT_MAGIC_NUMBER_SWAP
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary TwoBit format nucleotide file"
             dataset.blurb = nice_size(dataset.get_size())
         else:
             return super().set_peek(dataset)
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2325,7 +2325,7 @@ class SQlite(Binary):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         try:
             tables = []
             columns = dict()
@@ -2382,7 +2382,7 @@ class SQlite(Binary):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SQLite Database"
             lines = ["SQLite Database"]
@@ -2398,24 +2398,24 @@ class SQlite(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"SQLite Database ({nice_size(dataset.get_size())})"
 
     @dataproviders.decorators.dataprovider_factory("sqlite", SQliteDataProvider.settings)
-    def sqlite_dataprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataProvider:
+    def sqlite_dataprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-table", SQliteDataTableProvider.settings)
-    def sqlite_datatableprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataTableProvider:
+    def sqlite_datatableprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataTableProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataTableProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-dict", SQliteDataDictProvider.settings)
-    def sqlite_datadictprovider(self, dataset: Dataset_t2, **settings) -> SQliteDataDictProvider:
+    def sqlite_datadictprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataDictProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataDictProvider(dataset_source, **settings)
 
@@ -2436,7 +2436,7 @@ class GeminiSQLite(SQlite):
     edam_format = "format_3622"
     edam_data = "data_3498"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2465,7 +2465,7 @@ class GeminiSQLite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Gemini SQLite Database, version %s" % (dataset.metadata.gemini_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2473,7 +2473,7 @@ class GeminiSQLite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2485,7 +2485,7 @@ class ChiraSQLite(SQlite):
 
     file_ext = "chira.sqlite"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2516,7 +2516,7 @@ class CuffDiffSQlite(SQlite):
     # TODO: Update this when/if there is a specific EDAM format for CuffDiff SQLite data.
     edam_format = "format_3621"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             genes = []
@@ -2552,7 +2552,7 @@ class CuffDiffSQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CuffDiff SQLite Database, version %s" % (dataset.metadata.cuffdiff_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2560,7 +2560,7 @@ class CuffDiffSQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2572,7 +2572,7 @@ class MzSQlite(SQlite):
 
     file_ext = "mz.sqlite"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2609,7 +2609,7 @@ class PQP(SQlite):
 
     file_ext = "pqp"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2651,7 +2651,7 @@ class OSW(SQlite):
 
     file_ext = "osw"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2694,7 +2694,7 @@ class SQmass(SQlite):
 
     file_ext = "sqmass"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2718,7 +2718,7 @@ class BlibSQlite(SQlite):
     )
     file_ext = "blib"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2771,7 +2771,7 @@ class DlibSQlite(SQlite):
     )
     file_ext = "dlib"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2815,7 +2815,7 @@ class ElibSQlite(SQlite):
     )
     file_ext = "elib"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2866,7 +2866,7 @@ class IdpDB(SQlite):
 
     file_ext = "idpdb"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2882,7 +2882,7 @@ class IdpDB(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "IDPickerDB SQLite file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2890,7 +2890,7 @@ class IdpDB(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2911,7 +2911,7 @@ class GAFASQLite(SQlite):
     )
     file_ext = "gafa.sqlite"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2957,7 +2957,7 @@ class NcbiTaxonomySQlite(SQlite):
 
     file_ext = "ncbitaxonomy.sqlite"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2981,7 +2981,7 @@ class NcbiTaxonomySQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "NCBI Taxonomy SQLite Database, version {} ({} taxons)".format(
                 getattr(dataset.metadata, "ncbitaxonomy_schema_version", "unknown"),
@@ -2992,7 +2992,7 @@ class NcbiTaxonomySQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3028,7 +3028,7 @@ class ExcelXls(Binary):
         """Returns the mime type of the datatype"""
         return "application/vnd.ms-excel"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Microsoft Excel XLS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -3036,7 +3036,7 @@ class ExcelXls(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3055,7 +3055,7 @@ class Sra(Binary):
         """
         return file_prefix.startswith_bytes(b"NCBI.sra")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sra file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3063,7 +3063,7 @@ class Sra(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3104,7 +3104,7 @@ class RData(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3187,7 +3187,7 @@ class RDS(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3434,7 +3434,7 @@ class PostgresqlArchive(CompressedArchive):
     )
     file_ext = "postgresql"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3452,7 +3452,7 @@ class PostgresqlArchive(CompressedArchive):
                 return "postgresql/db/PG_VERSION" in temptar.getnames()
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"PostgreSQL Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "PostgreSQL version %s" % (dataset.metadata.version or "unknown")
@@ -3460,7 +3460,7 @@ class PostgresqlArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3482,7 +3482,7 @@ class Fast5Archive(CompressedArchive):
     )
     file_ext = "fast5.tar"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3506,7 +3506,7 @@ class Fast5Archive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"FAST5 Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "%s sequences" % (dataset.metadata.fast5_count or "unknown")
@@ -3514,7 +3514,7 @@ class Fast5Archive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3590,7 +3590,7 @@ class SearchGuiArchive(CompressedArchive):
     )
     file_ext = "searchgui_archive"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and zipfile.is_zipfile(dataset.file_name):
@@ -3615,7 +3615,7 @@ class SearchGuiArchive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SearchGUI Archive, version %s" % (dataset.metadata.searchgui_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -3623,7 +3623,7 @@ class SearchGuiArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3638,7 +3638,7 @@ class NetCDF(Binary):
     edam_format = "format_3650"
     edam_data = "data_0943"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary netCDF file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3646,7 +3646,7 @@ class NetCDF(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3694,7 +3694,7 @@ class Dcd(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM/NAMD dcd file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3702,7 +3702,7 @@ class Dcd(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3746,7 +3746,7 @@ class Vel(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM velocity file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3754,7 +3754,7 @@ class Vel(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3843,7 +3843,7 @@ class ICM(Binary):
     file_ext = "icm"
     edam_data = "data_0950"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ICM (interpolated context model) file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3918,7 +3918,7 @@ class BafTar(CompressedArchive):
     def get_type(self) -> str:
         return "Bruker BAF directory archive"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = self.get_type()
             dataset.blurb = nice_size(dataset.get_size())
@@ -3926,7 +3926,7 @@ class BafTar(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4028,7 +4028,7 @@ class Pretext(Binary):
         # file contains binary data.
         return file_prefix.startswith_bytes(b"pstm")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary pretext file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4036,7 +4036,7 @@ class Pretext(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4072,7 +4072,7 @@ class JP2(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary JPEG 2000 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4080,7 +4080,7 @@ class JP2(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4120,7 +4120,7 @@ class Npz(CompressedArchive):
             return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         try:
             with np.load(dataset.file_name) as npz:
                 dataset.metadata.nfiles = len(npz.files)
@@ -4128,7 +4128,7 @@ class Npz(CompressedArchive):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary Numpy npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4136,7 +4136,7 @@ class Npz(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4188,7 +4188,7 @@ class HexrdImagesNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4201,7 +4201,7 @@ class HexrdImagesNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Image npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4213,7 +4213,7 @@ class HexrdImagesNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4254,7 +4254,7 @@ class HexrdEtaOmeNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4263,7 +4263,7 @@ class HexrdEtaOmeNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Eta-Ome npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4275,7 +4275,7 @@ class HexrdEtaOmeNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index 860e1d1eec9..c34b1827498 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -41,9 +41,9 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t25,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol26,
 )
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -68,7 +68,7 @@ class BlastXml(GenericXml):
     edam_format = "format_3331"
     edam_data = "data_0857"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
@@ -193,7 +193,7 @@ class BlastXml(GenericXml):
 class _BlastDb(Data):
     """Base class for BLAST database datatype."""
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "BLAST database (multiple files)"
@@ -202,7 +202,7 @@ class _BlastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -212,7 +212,7 @@ class _BlastDb(Data):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -370,7 +370,7 @@ class LastDb(Data):
     file_ext = "lastdb"
     composite_type = "basic"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "LAST database (multiple files)"
@@ -379,7 +379,7 @@ class LastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index d6026a7c47b..a119f103f57 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -15,9 +15,9 @@ from typing import (
 from galaxy import util
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -106,7 +106,7 @@ class Ply:
                 break
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for line in fh:
@@ -129,7 +129,7 @@ class Ply:
                             element_tuple = (items[1], int(items[2]))
                             dataset.metadata.other_elements.append(element_tuple)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = f"Faces: {str(dataset.metadata.face)}, Vertices: {str(dataset.metadata.vertex)}"
@@ -137,7 +137,7 @@ class Ply:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -286,7 +286,7 @@ class Vtk:
             return check_data_kind(line)
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             dataset.metadata.field_names = []
             dataset.metadata.field_components = {}
@@ -375,7 +375,7 @@ class Vtk:
             if len(field_components) > 0:
                 dataset.metadata.field_components = field_components
 
-    def set_initial_metadata(self, i: int, line: str, dataset: Dataset_t24) -> Dataset_t24:
+    def set_initial_metadata(self, i: int, line: str, dataset: DatasetProtocol25) -> DatasetProtocol25:
         if i == 0:
             # The first part of legacy VTK files is the file version and
             # identifier. This part contains the single line:
@@ -394,8 +394,8 @@ class Vtk:
         return dataset
 
     def set_structure_metadata(
-        self, line: str, dataset: Dataset_t24, dataset_type: Optional[str]
-    ) -> Tuple[Dataset_t24, Optional[str]]:
+        self, line: str, dataset: DatasetProtocol25, dataset_type: Optional[str]
+    ) -> Tuple[DatasetProtocol25, Optional[str]]:
         """
         The fourth part of legacy VTK files is the dataset structure. The
         geometry part describes the geometry and topology of the dataset.
@@ -463,7 +463,7 @@ class Vtk:
             blurb += str(dataset.metadata.dataset_type)
         return blurb or "VTK data"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = self.get_blurb(dataset)
@@ -471,7 +471,7 @@ class Vtk:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -556,7 +556,7 @@ class NeperTess(data.Text):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tess")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -572,7 +572,7 @@ class NeperTess(data.Text):
                     if i == 6:
                         dataset.metadata.cells = int(line)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=7)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -627,7 +627,7 @@ class NeperTesr(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tesr")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 field = ""
@@ -659,7 +659,7 @@ class NeperTesr(Binary):
                         dataset.metadata.cells = int(line)
                         break
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=9)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -680,7 +680,7 @@ class NeperPoints(data.Text):
     def __init__(self, **kwd):
         data.Text.__init__(self, **kwd)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         data.Text.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -705,7 +705,7 @@ class NeperPoints(data.Text):
             return None
         return dim
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         data.Text.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -722,13 +722,13 @@ class NeperPointsTabular(NeperPoints, Tabular):
     def __init__(self, **kwd):
         Tabular.__init__(self, **kwd)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         Tabular.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -768,7 +768,7 @@ class GmshMsh(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline().startswith("$MeshFormat")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -784,7 +784,7 @@ class GmshMsh(Binary):
                         if len(fields) > 1:
                             dataset.metadata.format = "ASCII" if fields[1] == "0" else "binary"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=3)
             dataset.blurb = f"Gmsh verion: {str(dataset.metadata.version)} {str(dataset.metadata.format)}"
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index bbae546a639..bfe46f2676b 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -24,28 +24,28 @@ from typing_extensions import Literal
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Dataset_t0,
-    Dataset_t1,
-    Dataset_t2,
-    Dataset_t3,
-    Dataset_t4,
-    Dataset_t6,
-    Dataset_t7,
-    Dataset_t11,
-    Dataset_t14,
-    Dataset_t16,
-    Dataset_t17,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
-    Dataset_t26,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol0,
+    DatasetProtocol1,
+    DatasetProtocol2,
+    DatasetProtocol3,
+    DatasetProtocol5,
+    DatasetProtocol6,
+    DatasetProtocol8,
+    DatasetProtocol9,
+    DatasetProtocol10,
+    DatasetProtocol11,
+    DatasetProtocol12,
+    DatasetProtocol16,
+    DatasetProtocol20,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol24,
+    DatasetProtocol25,
+    DatasetProtocol26,
     HasClearAssociatedFiles,
-    HasCreatingJobProperty,
+    HasCreatingJob,
     HasExt,
-    HasFileNameProperty,
+    HasFileName,
     HasInfo,
     HasMetadata,
     HasName,
@@ -127,7 +127,7 @@ class DatatypeValidation:
         return f"DatatypeValidation[state={self.state},message={self.message}]"
 
 
-def validate(dataset_instance: Dataset_t19) -> DatatypeValidation:
+def validate(dataset_instance: DatasetProtocol9) -> DatatypeValidation:
     try:
         datatype_validation = dataset_instance.datatype.validate(dataset_instance)
     except Exception as e:
@@ -261,7 +261,7 @@ class Data(metaclass=DataMeta):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
         """Unimplemented method, allows guessing of metadata from contents of file"""
 
     def missing_meta(self, dataset: HasMetadata, check: Optional[List] = None, skip: Optional[List] = None) -> bool:
@@ -306,7 +306,7 @@ class Data(metaclass=DataMeta):
 
     max_optional_metadata_filesize = property(get_max_optional_metadata_filesize, set_max_optional_metadata_filesize)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -317,7 +317,7 @@ class Data(metaclass=DataMeta):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML table, used for displaying peek"""
         out = ['<table cellspacing="0" cellpadding="3">']
         try:
@@ -358,7 +358,7 @@ class Data(metaclass=DataMeta):
         return error, msg, messagetype
 
     def _archive_composite_dataset(
-        self, trans, data: Dataset_t1, headers: Headers, do_action: str = "zip"
+        self, trans, data: DatasetProtocol12, headers: Headers, do_action: str = "zip"
     ) -> Tuple[Union[ZipstreamWrapper, str], Headers]:
         # save a composite object into a compressed archive for downloading
         outfname = data.name[0:150]
@@ -403,7 +403,9 @@ class Data(metaclass=DataMeta):
                 rpath = os.path.relpath(fpath, extra_files_path)
                 yield fpath, rpath
 
-    def _serve_raw(self, dataset: Dataset_t25, to_ext: Optional[str], headers: Headers, **kwd) -> Tuple[IO, Headers]:
+    def _serve_raw(
+        self, dataset: DatasetProtocol26, to_ext: Optional[str], headers: Headers, **kwd
+    ) -> Tuple[IO, Headers]:
         headers["Content-Length"] = str(os.stat(dataset.file_name).st_size)
         headers[
             "content-type"
@@ -418,7 +420,7 @@ class Data(metaclass=DataMeta):
         headers["Content-Disposition"] = f'attachment; filename="{filename}"'
         return open(dataset.file_name, mode="rb"), headers
 
-    def to_archive(self, dataset: Dataset_t6, name: str = "") -> Iterable:
+    def to_archive(self, dataset: DatasetProtocol16, name: str = "") -> Iterable:
         """
         Collect archive paths and file handles that need to be exported when archiving `dataset`.
 
@@ -443,7 +445,7 @@ class Data(metaclass=DataMeta):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -556,7 +558,7 @@ class Data(metaclass=DataMeta):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: Dataset_t17) -> str:
+    def display_as_markdown(self, dataset_instance: DatasetProtocol20) -> str:
         """Prepare for embedding dataset into a basic Markdown document.
 
         This is a somewhat experimental interface and should not be implemented
@@ -584,9 +586,7 @@ class Data(metaclass=DataMeta):
                 result += indicate_data_truncated()
         return result
 
-    def _yield_user_file_content(
-        self, trans, from_dataset: HasCreatingJobProperty, filename: str, headers: Headers
-    ) -> IO:
+    def _yield_user_file_content(self, trans, from_dataset: HasCreatingJob, filename: str, headers: Headers) -> IO:
         """This method is responsible for sanitizing the HTML if needed."""
         if trans.app.config.sanitize_all_html and headers.get("content-type", None) == "text/html":
             # Sanitize anytime we respond with plain text/html content.
@@ -607,9 +607,9 @@ class Data(metaclass=DataMeta):
 
     def _download_filename(
         self,
-        dataset: Dataset_t4,
+        dataset: DatasetProtocol10,
         to_ext: Optional[str] = None,
-        hdca: Optional[Dataset_t26] = None,
+        hdca: Optional[DatasetProtocol8] = None,
         element_identifier: Optional[str] = None,
         filename_pattern: Optional[str] = None,
     ) -> str:
@@ -708,7 +708,7 @@ class Data(metaclass=DataMeta):
     def get_display_application(self, key: str, default: Optional["DisplayApplication"] = None) -> "DisplayApplication":
         return self.display_applications.get(key, default)
 
-    def get_display_applications_by_dataset(self, dataset: Dataset_t0, trans) -> Dict[str, "DisplayApplication"]:
+    def get_display_applications_by_dataset(self, dataset: DatasetProtocol0, trans) -> Dict[str, "DisplayApplication"]:
         rval = {}
         for key, value in self.display_applications.items():
             value = value.filter_by_dataset(dataset, trans)
@@ -727,7 +727,7 @@ class Data(metaclass=DataMeta):
         except Exception:
             return "unknown"
 
-    def as_display_type(self, dataset: Dataset_t2, type: str, **kwd) -> Union[FileObjType, str]:
+    def as_display_type(self, dataset: DatasetProtocol11, type: str, **kwd) -> Union[FileObjType, str]:
         """Returns modified file contents for a particular display type"""
         try:
             if type in self.get_display_types():
@@ -742,7 +742,7 @@ class Data(metaclass=DataMeta):
         return f"This display type ({type}) is not implemented for this datatype ({dataset.ext})."
 
     def get_display_links(
-        self, dataset: Dataset_t14, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
+        self, dataset: DatasetProtocol24, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
     ):
         """
         Returns a list of tuples of (name, link) for a particular display type.  No check on
@@ -769,7 +769,7 @@ class Data(metaclass=DataMeta):
         return datatypes_registry.get_converters_by_datatype(original_dataset.ext)
 
     def find_conversion_destination(
-        self, dataset: Dataset_t16, accepted_formats: List[str], datatypes_registry, **kwd
+        self, dataset: DatasetProtocol5, accepted_formats: List[str], datatypes_registry, **kwd
     ) -> Tuple[bool, Optional[str], Any]:
         """Returns ( direct_match, converted_ext, existing converted dataset )"""
         return datatypes_registry.find_conversion_destination_for_dataset_by_extensions(
@@ -779,7 +779,7 @@ class Data(metaclass=DataMeta):
     def convert_dataset(
         self,
         trans,
-        original_dataset: Dataset_t3,
+        original_dataset: DatasetProtocol2,
         target_type: str,
         return_output: bool = False,
         visible: bool = True,
@@ -883,7 +883,7 @@ class Data(metaclass=DataMeta):
             files[substitute_composite_key(key, value)] = value
         return files
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         raise Exception("generate_primary_file is not implemented for this datatype.")
 
     @property
@@ -920,7 +920,7 @@ class Data(metaclass=DataMeta):
         """
         return data_format in self.dataproviders
 
-    def dataprovider(self, dataset: Dataset_t2, data_format: str, **settings):
+    def dataprovider(self, dataset: DatasetProtocol11, data_format: str, **settings):
         """
         Base dataprovider factory for all datatypes that returns the proper provider
         for the given `data_format` or raises a `NoProviderAvailable`.
@@ -929,21 +929,23 @@ class Data(metaclass=DataMeta):
             return self.dataproviders[data_format](self, dataset, **settings)
         raise p_dataproviders.exceptions.NoProviderAvailable(self, data_format)
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
-    def base_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.base.DataProvider:
+    def base_dataprovider(self, dataset: DatasetProtocol11, **settings) -> p_dataproviders.base.DataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.base.DataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk", p_dataproviders.chunk.ChunkDataProvider.settings)
-    def chunk_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
+    def chunk_dataprovider(self, dataset: DatasetProtocol11, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.ChunkDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk64", p_dataproviders.chunk.Base64ChunkDataProvider.settings)
-    def chunk64_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.chunk.Base64ChunkDataProvider:
+    def chunk64_dataprovider(
+        self, dataset: DatasetProtocol11, **settings
+    ) -> p_dataproviders.chunk.Base64ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.Base64ChunkDataProvider(dataset_source, **settings)
 
@@ -953,7 +955,7 @@ class Data(metaclass=DataMeta):
                 mime = DEFAULT_MIME_TYPE
         headers["content-type"] = mime
 
-    def handle_dataset_as_image(self, hda: Dataset_t7) -> str:
+    def handle_dataset_as_image(self, hda: DatasetProtocol1) -> str:
         raise Exception("Unimplemented Method")
 
     def __getstate__(self) -> Dict[str, Any]:
@@ -985,13 +987,13 @@ class Text(Data):
         """Returns the mime type of the datatype"""
         return "text/plain"
 
-    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.data_lines = self.count_data_lines(dataset)
 
-    def estimate_file_lines(self, dataset: Dataset_t11) -> Optional[int]:
+    def estimate_file_lines(self, dataset: DatasetProtocol3) -> Optional[int]:
         """
         Perform a rough estimate by extrapolating number of lines from a small read.
         """
@@ -1005,7 +1007,7 @@ class Text(Data):
             log.error(f"Unable to estimate lines in file {dataset.file_name}")
             return None
 
-    def count_data_lines(self, dataset: HasFileNameProperty) -> Optional[int]:
+    def count_data_lines(self, dataset: HasFileName) -> Optional[int]:
         """
         Count the number of lines of data in dataset,
         skipping all blank lines and comments.
@@ -1026,7 +1028,7 @@ class Text(Data):
                 return None
         return data_lines
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """
         Set the peek.  This method is used by various subclasses of Text.
         """
@@ -1139,7 +1141,9 @@ class Text(Data):
 
     # ------------- Dataproviders
     @p_dataproviders.decorators.dataprovider_factory("line", p_dataproviders.line.FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.line.FilteredLineDataProvider:
+    def line_dataprovider(
+        self, dataset: DatasetProtocol11, **settings
+    ) -> p_dataproviders.line.FilteredLineDataProvider:
         """
         Returns an iterator over the dataset's lines (that have been stripped)
         optionally excluding blank lines and lines that start with a comment character.
@@ -1148,7 +1152,9 @@ class Text(Data):
         return p_dataproviders.line.FilteredLineDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("regex-line", p_dataproviders.line.RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> p_dataproviders.line.RegexLineDataProvider:
+    def regex_line_dataprovider(
+        self, dataset: DatasetProtocol11, **settings
+    ) -> p_dataproviders.line.RegexLineDataProvider:
         """
         Returns an iterator over the dataset's lines
         optionally including/excluding lines that match one or more regex filters.
diff --git a/lib/galaxy/datatypes/flow.py b/lib/galaxy/datatypes/flow.py
index 4d720575548..23ad9c1364a 100644
--- a/lib/galaxy/datatypes/flow.py
+++ b/lib/galaxy/datatypes/flow.py
@@ -5,8 +5,8 @@ Flow analysis datatypes.
 import logging
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.sniff import (
@@ -24,7 +24,7 @@ class FCS(Binary):
 
     file_ext = "fcs"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary FCS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -32,7 +32,7 @@ class FCS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 33acaf0f303..e3d745d32f0 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -28,15 +28,15 @@ from markupsafe import escape
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t10,
-    Dataset_t14,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t22,
-    Dataset_t23,
-    Dataset_t24,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol9,
+    DatasetProtocol11,
+    DatasetProtocol17,
+    DatasetProtocol18,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol24,
+    DatasetProtocol25,
     HasMetadata,
 )
 from galaxy.datatypes.data import (
@@ -82,7 +82,7 @@ class GenomeGraphs(Tabular):
         super().__init__(**kwd)
         self.add_display_app("ucsc", "Genome Graph", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.markerCol = 1
         header = open(dataset.file_name).readlines()[0].strip().split("\t")
@@ -91,13 +91,13 @@ class GenomeGraphs(Tabular):
         t[0] = "string"
         dataset.metadata.column_types = t
 
-    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
         """
         Returns file
         """
         return open(dataset.file_name, "rb")
 
-    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
         """
         from the ever-helpful angie hinrichs angie@soe.ucsc.edu
         a genome graphs call looks like this
@@ -149,7 +149,7 @@ class GenomeGraphs(Tabular):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def make_html_table(self, dataset: Dataset_t10, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol18, **kwargs) -> str:
         """
         Create HTML table, used for displaying peek
         """
@@ -180,7 +180,7 @@ class GenomeGraphs(Tabular):
         except Exception as exc:
             return f"Can't create peek {exc}"
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         """
         Validate a gg file - all numeric after header row
         """
@@ -244,7 +244,7 @@ class rgTabList(Tabular):
         super().__init__(**kwd)
         self.column_names = []
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -309,7 +309,7 @@ class Rgenetics(Html):
     composite_type = "auto_primary_file"
     file_ext = "rgenetics"
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Rgenetics Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -326,7 +326,7 @@ class Rgenetics(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -348,7 +348,7 @@ class Rgenetics(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         for lped/pbed eg
 
@@ -388,7 +388,7 @@ class SNPMatrix(Rgenetics):
 
     file_ext = "snpmatrix"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary RGenetics file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -584,7 +584,7 @@ class IdeasPre(Html):
         self.add_composite_file("IDEAS_input_config.txt", description="IDEAS input config", is_binary=False)
         self.add_composite_file("tmp.tar.gz", description="Compressed archive of compressed bed files", is_binary=True)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         for fname in os.listdir(dataset.extra_files_path):
             if fname.startswith("chromosomes"):
@@ -597,7 +597,7 @@ class IdeasPre(Html):
                 dataset.metadata.tmp_archive = os.path.join(dataset.extra_files_path, fname)
         self.regenerate_primary_file(dataset)
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
         rval.append("<ul>")
@@ -607,7 +607,7 @@ class IdeasPre(Html):
         rval.append("</ul></body></html>\n")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         # Cannot do this until we are setting metadata.
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
@@ -661,7 +661,7 @@ class RexpBase(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -771,7 +771,7 @@ class RexpBase(Html):
             p = []
         return "\n".join(p)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """
         expects a .pheno file in the extra_files_dir - ugh
         note that R is weird and does not include the row.name in
@@ -820,7 +820,7 @@ class RexpBase(Html):
         except Exception:
             return "## rexpression get_file_peek: no file found"
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -841,7 +841,7 @@ class RexpBase(Html):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         NOTE we apply the tabular machinary to the phenodata extracted
         from a BioC eSet or affybatch.
@@ -917,7 +917,7 @@ class RexpBase(Html):
         except Exception as exc:
             return f"Can't create html table {unicodify(exc)}"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """
         Returns formatted html of peek
         """
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index dacbc8181c4..62e04356517 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -2,9 +2,9 @@
 GIS classes
 """
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.binary import Binary
 
@@ -65,7 +65,7 @@ class Shapefile(Binary):
             "shapefile.shp.xml", description="Geospatial metadata in XML format (xml)", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Shapefile Galaxy Composite Dataset</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -82,7 +82,7 @@ class Shapefile(Binary):
         rval.append("</ul></div></html>\n")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "Shapefile data"
@@ -91,7 +91,7 @@ class Shapefile(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/goldenpath.py b/lib/galaxy/datatypes/goldenpath.py
index af7aacb4078..b121b81e039 100644
--- a/lib/galaxy/datatypes/goldenpath.py
+++ b/lib/galaxy/datatypes/goldenpath.py
@@ -6,7 +6,7 @@ from typing import (
     Union,
 )
 
-from galaxy.datatypes._protocols import Dataset_t24
+from galaxy.datatypes._protocols import DatasetProtocol25
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -24,7 +24,7 @@ class GoldenPath(Tabular):
     edam_format = "format_3693"
     file_ext = "agp"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         # AGPFile reads and validates entire file.
         AGPFile(dataset.file_name)
         super().set_meta(dataset, overwrite=overwrite, **kwd)
diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index d0feb586fdd..105fc8f86da 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -5,8 +5,8 @@ import logging
 from typing import List
 
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t23,
+    DatasetProtocol11,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
@@ -31,7 +31,7 @@ class Xgmml(xml.GenericXml):
 
     file_ext = "xgmml"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -61,7 +61,7 @@ class Xgmml(xml.GenericXml):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", XMLDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: Dataset_t2, **settings) -> "XGMMLGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: DatasetProtocol11, **settings) -> "XGMMLGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return XGMMLGraphDataProvider(dataset_source, **settings)
 
@@ -79,7 +79,7 @@ class Sif(tabular.Tabular):
 
     file_ext = "sif"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -101,7 +101,7 @@ class Sif(tabular.Tabular):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", ColumnarDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: Dataset_t2, **settings) -> "SIFGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: DatasetProtocol11, **settings) -> "SIFGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return SIFGraphDataProvider(dataset_source, **settings)
 
diff --git a/lib/galaxy/datatypes/hdf5.py b/lib/galaxy/datatypes/hdf5.py
index f44df906b48..78dd1b236ed 100644
--- a/lib/galaxy/datatypes/hdf5.py
+++ b/lib/galaxy/datatypes/hdf5.py
@@ -5,7 +5,7 @@ This datatype was created for use with the iSEE interactive tool.
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
     HasMetadata,
 )
 from galaxy.datatypes.data import Data
@@ -55,7 +55,7 @@ class HDF5SummarizedExperiment(Data):
         """Override parent init metadata."""
         Data.init_meta(self, dataset, copy_from=copy_from)
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """Generate primary file to represent dataset."""
         return f"""
               <html>
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index b0de83a5454..99c0bb4ab5c 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -11,10 +11,10 @@ import numpy as np
 import tifffile
 
 from galaxy.datatypes._protocols import (
-    Dataset_t7,
-    Dataset_t23,
-    Dataset_t24,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol1,
+    DatasetProtocol6,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
@@ -55,7 +55,7 @@ class Image(data.Data):
         super().__init__(**kwd)
         self.image_formats = [self.file_ext.upper()]
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Image in {dataset.extension} format"
             dataset.blurb = nice_size(dataset.get_size())
@@ -67,7 +67,7 @@ class Image(data.Data):
         """Determine if the file is in this format"""
         return check_image_type(filename, self.image_formats)
 
-    def handle_dataset_as_image(self, hda: Dataset_t7) -> str:
+    def handle_dataset_as_image(self, hda: DatasetProtocol1) -> str:
         dataset = hda.dataset
         name = hda.name or ""
         with open(dataset.file_name, "rb") as f:
@@ -107,7 +107,7 @@ class OMETiff(Tiff):
     )
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         spec_key = "offsets"
         offsets_file = dataset.metadata.offsets
@@ -382,7 +382,7 @@ class Analyze75(Binary):
 
         self.add_composite_file("t2m", description="The Analyze75 t2m file.", optional=True, is_binary=True)
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Analyze75 Composite Dataset.</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -492,7 +492,7 @@ class Star(data.Text):
 
     file_ext = "star"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index dfffbf5073a..9bd726029bf 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,15 +22,15 @@ from bx.intervals.io import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t12,
-    Dataset_t13,
-    Dataset_t14,
-    Dataset_t15,
-    Dataset_t18,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t24,
+    DatasetProtocol4,
+    DatasetProtocol9,
+    DatasetProtocol11,
+    DatasetProtocol15,
+    DatasetProtocol19,
+    DatasetProtocol21,
+    DatasetProtocol22,
+    DatasetProtocol24,
+    DatasetProtocol25,
     HasId,
     HasMetadata,
 )
@@ -136,7 +136,7 @@ class Interval(Tabular):
         Tabular.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: Dataset_t24, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
+        self, dataset: DatasetProtocol25, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
     ) -> None:
         """Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=0)
@@ -197,7 +197,7 @@ class Interval(Tabular):
                     else:
                         empty_line_count += 1
 
-    def displayable(self, dataset: Dataset_t12) -> bool:
+    def displayable(self, dataset: DatasetProtocol15) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -214,7 +214,7 @@ class Interval(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: Dataset_t13,
+        dataset: DatasetProtocol19,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -276,7 +276,7 @@ class Interval(Tabular):
             log.exception("Exception caught attempting to generate viewport for dataset '%d'", dataset.id)
         return (None, None, None)
 
-    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data"""
         with tempfile.NamedTemporaryFile(delete=False, mode="w") as fh:
             c, s, e, t, n = (
@@ -310,7 +310,7 @@ class Interval(Tabular):
                     fh.write("%s\n" % "\t".join(tmp))
             return compression_utils.get_fileobj(fh.name, mode="rb")
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset,
@@ -323,7 +323,7 @@ class Interval(Tabular):
             },
         )
 
-    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
         """
         Generate links to UCSC genome browser sites based on the dbkey
         and content of dataset.
@@ -357,7 +357,7 @@ class Interval(Tabular):
             ret_val.append((site_name, link))
         return ret_val
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         """Validate an interval file using the bx GenomicIntervalReader"""
         c, s, e, t = (
             dataset.metadata.chromCol,
@@ -412,20 +412,20 @@ class Interval(Tabular):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: Dataset_t2, **settings) -> IntervalDataProvider:
+    def interval_dataprovider(self, dataset: DatasetProtocol11, **settings) -> IntervalDataProvider:
         return IntervalDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> IntervalDataProvider:
+    def interval_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> IntervalDataProvider:
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -438,7 +438,7 @@ class BedGraph(Interval):
     track_type = "LineTrack"
     data_sources = {"data": "bigwig", "index": "bigwig"}
 
-    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
         """
         Returns file contents as is with no modifications.
         TODO: this is a functional stub and will need to be enhanced moving forward to provide additional support for bedgraph.
@@ -447,7 +447,7 @@ class BedGraph(Interval):
 
     def get_estimated_display_viewport(
         self,
-        dataset: Dataset_t13,
+        dataset: DatasetProtocol19,
         chrom_col: Optional[int] = 0,
         start_col: Optional[int] = 1,
         end_col: Optional[int] = 2,
@@ -506,7 +506,7 @@ class Bed(Interval):
     )
     # do we need to repeat these? they are the same as should be inherited from interval type
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """Sets the metadata information for datasets previously determined to be in bed format."""
         if dataset.has_data():
             i = 0
@@ -527,7 +527,7 @@ class Bed(Interval):
                         break
             Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data. If bed 6+, treat as interval."""
         for line in open(dataset.file_name):
             line = line.strip()
@@ -739,7 +739,7 @@ class BedStrict(Bed):
         Tabular.__init__(self, **kwd)
         self.clear_display_apps()  # only new style display applications for this datatype
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)  # need column count first
         if dataset.metadata.columns >= 4:
             dataset.metadata.nameCol = 4
@@ -823,7 +823,7 @@ class Gff(Tabular, _RemoteCallMixin):
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
-    def set_attribute_metadata(self, dataset: Dataset_t18) -> None:
+    def set_attribute_metadata(self, dataset: DatasetProtocol4) -> None:
         """
         Sets metadata elements for dataset's attributes.
         """
@@ -863,7 +863,7 @@ class Gff(Tabular, _RemoteCallMixin):
         dataset.metadata.attribute_types = attribute_types
         dataset.metadata.attributes = len(attribute_types)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
 
         i = 0
@@ -881,12 +881,12 @@ class Gff(Tabular, _RemoteCallMixin):
                             pass
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
     def get_estimated_display_viewport(
-        self, dataset: Dataset_t13
+        self, dataset: DatasetProtocol19
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """
         Return a chrom, start, stop tuple for viewing a file.  There are slight differences between gff 2 and gff 3
@@ -962,7 +962,7 @@ class Gff(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -975,7 +975,7 @@ class Gff(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def gbrowse_links(self, dataset: Dataset_t15, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: DatasetProtocol22, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -1041,20 +1041,20 @@ class Gff(Tabular, _RemoteCallMixin):
     # ------------- Dataproviders
     # redefine bc super is Tabular
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 3, 4, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: Dataset_t2, **settings):
+    def interval_dataprovider(self, dataset: DatasetProtocol11, **settings):
         return IntervalDataProvider(dataset, 0, 3, 4, 6, 2, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: Dataset_t2, **settings):
+    def interval_dict_dataprovider(self, dataset: DatasetProtocol11, **settings):
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -1082,7 +1082,7 @@ class Gff3(Gff):
         """Initialize datatype, by adding GBrowse display app"""
         Gff.__init__(self, **kwd)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
         i = 0
         with compression_utils.get_fileobj(dataset.file_name) as in_fh:
@@ -1298,7 +1298,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
     def get_estimated_display_viewport(
-        self, dataset: Dataset_t13
+        self, dataset: DatasetProtocol19
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
@@ -1364,7 +1364,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def gbrowse_links(self, dataset: Dataset_t15, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: DatasetProtocol22, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1377,7 +1377,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1390,11 +1390,11 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         max_data_lines = None
         i = 0
         for i, line in enumerate(open(dataset.file_name)):  # noqa: B007
@@ -1452,12 +1452,12 @@ class Wiggle(Tabular, _RemoteCallMixin):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("wiggle", WiggleDataProvider.settings)
-    def wiggle_dataprovider(self, dataset: Dataset_t2, **settings) -> WiggleDataProvider:
+    def wiggle_dataprovider(self, dataset: DatasetProtocol11, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return WiggleDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("wiggle-dict", WiggleDataProvider.settings)
-    def wiggle_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> WiggleDataProvider:
+    def wiggle_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         settings["named_columns"] = True
         return WiggleDataProvider(dataset_source, **settings)
@@ -1475,16 +1475,16 @@ class CustomTrack(Tabular):
         Tabular.__init__(self, **kwd)
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
     def get_estimated_display_viewport(
         self,
-        dataset: Dataset_t13,
+        dataset: DatasetProtocol19,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -1546,7 +1546,7 @@ class CustomTrack(Tabular):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: Dataset_t14, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1791,7 +1791,7 @@ class IntervalTabix(Interval):
     # Ideally the tabix_index would be regenerated when the metadataElements are updated
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         first_line_is_header: bool = False,
         metadata_tmp_files_dir: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index ef3f226af3c..9ea161bdf31 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -27,11 +27,11 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t25,
-    GeneratePrimaryFileDataset,
-    HasExtraFilesPathProperty,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol26,
+    HasExtraFilesPath,
 )
 from galaxy.datatypes.data import Data
 from galaxy.util.compression_utils import CompressedFile
@@ -91,7 +91,7 @@ class _Isa(Data):
     # Get ISA folder path {{{2
     ################################################################
 
-    def _get_isa_folder_path(self, dataset: HasExtraFilesPathProperty) -> str:
+    def _get_isa_folder_path(self, dataset: HasExtraFilesPath) -> str:
         isa_folder = dataset.extra_files_path
         if not isa_folder:
             raise Exception("Unvalid dataset object, or no extra files path found for this dataset.")
@@ -100,7 +100,7 @@ class _Isa(Data):
     # Get main file {{{2
     ################################################################
 
-    def _get_main_file(self, dataset: HasExtraFilesPathProperty) -> Optional[str]:
+    def _get_main_file(self, dataset: HasExtraFilesPath) -> Optional[str]:
         """Get the main file of the ISA archive. Either the investigation file i_*.txt for ISA-Tab, or the JSON file for ISA-JSON."""
 
         main_file = None
@@ -126,7 +126,7 @@ class _Isa(Data):
     # Get investigation {{{2
     ################################################################
 
-    def _get_investigation(self, dataset: HasExtraFilesPathProperty) -> Optional["Investigation"]:
+    def _get_investigation(self, dataset: HasExtraFilesPath) -> Optional["Investigation"]:
         """Create a contained instance specific to the exact ISA type (Tab or Json).
         We will use it to parse and access information from the archive."""
 
@@ -163,7 +163,7 @@ class _Isa(Data):
     # Set peek {{{2
     ################################################################
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text. Get first lines of the main file and set it as the peek."""
 
         main_file = self._get_main_file(dataset)
@@ -189,7 +189,7 @@ class _Isa(Data):
     # Display peek {{{2
     ################################################################
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create the HTML table used for displaying peek, from the peek text found by set_peek() method."""
 
         out = ['<table cellspacing="0" cellpadding="3">']
@@ -210,7 +210,7 @@ class _Isa(Data):
     # Generate primary file {{{2
     ################################################################
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """Generate the primary file. It is an HTML file containing description of the composite dataset
         as well as a list of the composite files that it contains."""
 
@@ -269,7 +269,7 @@ class _Isa(Data):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/media.py b/lib/galaxy/datatypes/media.py
index a3cbde1560f..36152920dd7 100644
--- a/lib/galaxy/datatypes/media.py
+++ b/lib/galaxy/datatypes/media.py
@@ -8,7 +8,7 @@ from typing import (
     Tuple,
 )
 
-from galaxy.datatypes._protocols import Dataset_t24
+from galaxy.datatypes._protocols import DatasetProtocol25
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -72,7 +72,7 @@ class Audio(Binary):
         no_value=0,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
 
@@ -159,7 +159,7 @@ class Video(Binary):
             w = h = fps = 0
         return w, h, fps
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
             (w, h, fps) = self._get_resolution(streams)
@@ -280,7 +280,7 @@ class Wav(Audio):
         with wave.open(filename, "rb"):
             return True
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents."""
         try:
             with wave.open(dataset.dataset.file_name, "rb") as fd:
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index a6ef527d0ad..89a435b5033 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -2,8 +2,8 @@ import logging
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.binary import Cel  # noqa: F401
 from galaxy.datatypes.data import get_file_peek
@@ -80,7 +80,7 @@ class GenericMicroarrayFile(data.Text):
         name="block_type", default=0, desc="Type of block", readonly=True, visible=True, optional=True, no_value=0
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.block_count == 1:
                 dataset.blurb = f"{dataset.metadata.file_type} {dataset.metadata.version_number}: Format {dataset.metadata.file_format}, 1 block, {dataset.metadata.number_of_optional_header_records} headers and {dataset.metadata.number_of_data_columns} columns"
@@ -120,7 +120,7 @@ class Gal(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix ArrayList" in headers[2][0]
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gal file.
         """
@@ -162,7 +162,7 @@ class Gpr(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix Results" in headers[2][0]
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gpr file.
         """
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index 062d31266c7..7062b384050 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -9,9 +9,9 @@ from typing import (
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -73,7 +73,7 @@ class GenericMolFile(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -205,7 +205,7 @@ class GenericMolFile(Text):
 class MOL(GenericMolFile):
     file_ext = "mol"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number molecules, in the case of MOL its always one.
         """
@@ -258,7 +258,7 @@ class SDF(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of molecules in dataset.
         """
@@ -341,7 +341,7 @@ class MOL2(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -427,7 +427,7 @@ class FPS(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -532,7 +532,7 @@ class OBFS(Binary):
         self.add_composite_file("molecule.mol2", optional=True, is_binary=False, description="Molecule File")
         self.add_composite_file("molecule.cml", optional=True, is_binary=False, description="Molecule File")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "OpenBabel Fastsearch Index"
@@ -541,7 +541,7 @@ class OBFS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -568,7 +568,7 @@ class OBFS(Binary):
 class DRF(GenericMolFile):
     file_ext = "drf"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -582,7 +582,7 @@ class PHAR(GenericMolFile):
 
     file_ext = "phar"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "pharmacophore"
@@ -635,7 +635,7 @@ class PDB(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Find Chain_IDs for metadata.
         """
@@ -651,7 +651,7 @@ class PDB(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -704,7 +704,7 @@ class PDBQT(GenericMolFile):
         else:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             root_numbers = count_special_lines("^ROOT", dataset.file_name)
             branch_numbers = count_special_lines("^BRANCH", dataset.file_name)
@@ -789,7 +789,7 @@ class PQR(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Find Optional Chain_IDs for metadata.
         """
@@ -808,7 +808,7 @@ class PQR(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -886,7 +886,7 @@ class Cell(GenericMolFile):
                 return True
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -926,7 +926,7 @@ class Cell(GenericMolFile):
                 dataset.metadata.is_periodic = bool(pbc.any())
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1047,7 +1047,7 @@ class CIF(GenericMolFile):
                 return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1093,7 +1093,7 @@ class CIF(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1244,7 +1244,7 @@ class XYZ(GenericMolFile):
                     raise
         return blocks
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1291,7 +1291,7 @@ class XYZ(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1446,7 +1446,7 @@ class ExtendedXYZ(XYZ):
             blocks.append({"number_of_atoms": n_atoms, "comment": comment, "atom_data": atoms})
         return blocks
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         super().set_peek(dataset)
         dataset.blurb = "Extended " + dataset.blurb
 
@@ -1454,7 +1454,7 @@ class ExtendedXYZ(XYZ):
 class grd(Text):
     file_ext = "grd"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "grids for docking"
@@ -1466,7 +1466,7 @@ class grd(Text):
 class grdtgz(Binary):
     file_ext = "grd.tgz"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
             dataset.blurb = "compressed grids for docking"
@@ -1498,13 +1498,13 @@ class InChI(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1563,13 +1563,13 @@ class SMILES(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1599,13 +1599,13 @@ class CML(GenericXml):
         no_value=0,
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = count_special_lines(r"^\s*<molecule", dataset.file_name)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1763,7 +1763,7 @@ class GRO(GenericMolFile):
                 return False
         return True
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             atom_number = int(dataset.peek.split("\n")[1])
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index 206f40d391b..49fc5317440 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -9,8 +9,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Dataset_t10,
-    Dataset_t24,
+    DatasetProtocol18,
+    DatasetProtocol25,
     HasMetadata,
 )
 from galaxy.datatypes.data import Text
@@ -37,7 +37,7 @@ class Otu(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Otu files.
 
@@ -174,7 +174,7 @@ class GroupAbund(Otu):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         # See if file starts with header line
@@ -298,7 +298,7 @@ class AlignCheck(Tabular):
         self.column_types = ["str", "int", "int", "int", "int", "int", "int", "int"]
         self.comment_lines = 1
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         dataset.metadata.column_names = self.column_names
@@ -355,7 +355,7 @@ class DistanceMatrix(Text):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
         headers = iter_headers(dataset.file_name, sep="\t")
@@ -508,7 +508,7 @@ class PairwiseDistanceMatrix(DistanceMatrix, Tabular):
         self.column_names = ["Sequence", "Sequence", "Distance"]
         self.column_types = ["str", "str", "float"]
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -598,7 +598,7 @@ class Group(Tabular):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = None,
@@ -846,7 +846,7 @@ class CountTable(Tabular):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1058,7 +1058,7 @@ class SffFlow(Tabular):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1073,7 +1073,7 @@ class SffFlow(Tabular):
         except Exception as e:
             log.warning(f"SffFlow set_meta {e}")
 
-    def make_html_table(self, dataset: Dataset_t10, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol18, skipchars: Optional[List] = None, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index d3f2fd6d0af..1254cb2c8dc 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -9,9 +9,9 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -58,7 +58,7 @@ class InfernalCM(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_of_models == 1:
@@ -82,7 +82,7 @@ class InfernalCM(Text):
         """
         return file_prefix.startswith("INFERNAL")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models and the version of CM file in dataset.
         """
@@ -98,7 +98,7 @@ class Hmmer(Text):
     edam_data = "data_1364"
     edam_format = "format_1370"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "HMMER Database"
@@ -106,7 +106,7 @@ class Hmmer(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -141,7 +141,7 @@ class HmmerPress(Binary):
     file_ext = "hmmpress"
     composite_type = "basic"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "HMMER Binary database"
@@ -150,7 +150,7 @@ class HmmerPress(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -185,7 +185,7 @@ class Stockholm_1_0(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -199,7 +199,7 @@ class Stockholm_1_0(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.search(STOCKHOLM_SEARCH_PATTERN)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
 
         Set the number of models in dataset.
@@ -276,7 +276,7 @@ class MauveXmfa(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -290,7 +290,7 @@ class MauveXmfa(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith("#FormatVersion Mauve1")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         dataset.metadata.number_of_models = generic_util.count_special_lines(
             "^#Sequence([[:digit:]]+)Entry", dataset.file_name
         )
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index afce28d526a..c4696deb5dc 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -4,9 +4,9 @@ Neo4j Composite Dataset
 import logging
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
@@ -23,7 +23,7 @@ class Neo4j(Html):
     stored in extra files path
     """
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -46,7 +46,7 @@ class Neo4j(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Neo4j database (multiple files)"
@@ -55,7 +55,7 @@ class Neo4j(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index 5550bf3df9f..b80d7235163 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -5,10 +5,10 @@ import logging
 import os
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t22,
-    Dataset_t23,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol17,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from .metadata import MetadataElement
 from .text import Html
@@ -39,14 +39,14 @@ class BowtieIndex(Html):
 
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
         """
         return "<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>"
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -63,7 +63,7 @@ class BowtieIndex(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Bowtie index file ({dataset.metadata.sequence_space})"
             dataset.blurb = f"{dataset.metadata.sequence_space} space"
@@ -71,7 +71,7 @@ class BowtieIndex(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index 0fd08b20966..9755baff5f3 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -11,8 +11,8 @@ from typing import TYPE_CHECKING
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -41,7 +41,7 @@ class Phylip(Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -51,7 +51,7 @@ class Phylip(Text):
         except Exception:
             raise Exception("Header does not correspond to PHYLIP header.")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index 9e7451d8144..f3f074d2278 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -2,9 +2,9 @@ import logging
 import re
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -26,13 +26,13 @@ log = logging.getLogger(__name__)
 class Smat(Text):
     file_ext = "smat"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"ESTScan scores matrices ({nice_size(dataset.get_size())})"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "ESTScan scores matrices"
@@ -98,13 +98,13 @@ class PlantTribesKsComponents(Tabular):
         no_value=0,
     )
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Significant components in the Ks distribution ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of significant components in the Ks distribution.
         The dataset will always be on the order of less than 10 lines.
@@ -126,7 +126,7 @@ class PlantTribesKsComponents(Tabular):
         if len(significant_components) > 0:
             dataset.metadata.number_comp = max(significant_components)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_comp == 1:
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index b8f1bbc9586..9b9267d3f48 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -11,10 +11,10 @@ from typing import (
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import Text
@@ -57,7 +57,7 @@ class Wiff(Binary):
             is_binary=True,
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Wiff Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -105,7 +105,7 @@ class MzTab(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -156,7 +156,7 @@ class MzTab2(MzTab):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -201,7 +201,7 @@ class Kroenik(Tabular):
             "Modifications",
         ]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -240,7 +240,7 @@ class PepList(Tabular):
         super().__init__(**kwd)
         self.column_names = ["m/z", "rt(min)", "snr", "charge", "intensity"]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -277,7 +277,7 @@ class PSMS(Tabular):
         super().__init__(**kwd)
         self.column_names = ["PSMId", "score", "q-value", "posterior_error_prob", "peptide", "proteinIds"]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -337,7 +337,7 @@ class PepXmlReport(Tabular):
             "Interprophet Probability",
         ]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -378,7 +378,7 @@ class ProtXmlReport(Tabular):
             "Is Evidence?",
         ]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -393,7 +393,7 @@ class Dta(TabularData):
     file_ext = "dta"
     comment_lines = 0
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         column_types = []
         data_row: List = []
         data_lines = 0
@@ -466,7 +466,7 @@ class Dta2d(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         if dataset.has_data():
@@ -602,7 +602,7 @@ class Edta(TabularData):
                 line[idx] += str(idx // 4)
         return line
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         tpe = None
@@ -676,7 +676,7 @@ class ProteomicsXml(GenericXml):
         pattern = r"<(\w*:)?%s" % self.root
         return re.search(pattern, line) is not None
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -845,7 +845,7 @@ class Mgf(Text):
     edam_format = "format_3651"
     file_ext = "mgf"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -875,7 +875,7 @@ class MascotDat(Text):
     edam_format = "format_3713"
     file_ext = "mascotdat"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -919,7 +919,7 @@ class ThermoRAW(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Thermo Finnigan RAW file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -927,7 +927,7 @@ class ThermoRAW(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -961,7 +961,7 @@ class SPLibNoIndex(Text):
 
     file_ext = "splib_noindex"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -986,7 +986,7 @@ class SPLib(Msp):
         self.add_composite_file("library.spidx", description="Spectrum index", is_binary=False)
         self.add_composite_file("library.pepidx", description="Peptide index", is_binary=False)
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Spectral Library Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -1003,7 +1003,7 @@ class SPLib(Msp):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1075,7 +1075,7 @@ class ImzML(Binary):
 
         self.add_composite_file("ibd", description="The mass spectral data component.", is_binary=True)
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>imzML Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index dd67601d520..e521652852a 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -12,9 +12,9 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
     HasMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
@@ -35,7 +35,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
     MetadataElement(name="format", optional=True, no_value="", readonly=True)
     MetadataElement(name="version", readonly=True)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         metadata = _get_metadata_from_archive(dataset.file_name)
         for key, value in metadata.items():
             if value:
@@ -43,7 +43,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.metadata.semantic_type_simple = _strip_properties(dataset.metadata.semantic_type)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if dataset.metadata.semantic_type == "Visualization":
             dataset.blurb = "QIIME 2 Visualization"
         else:
@@ -51,7 +51,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.peek = "\n".join(map(": ".join, self._peek(dataset)))
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         def make_row(item):
             return "<tr><th>%s</th><td>%s</td></td>" % tuple(html.escape(x) for x in item)
 
@@ -117,7 +117,7 @@ class QIIME2Metadata(Tabular):
     def get_column_names(self, first_line: str) -> Optional[List[str]]:
         return first_line.strip().split("\t")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Let Galaxy's Tabular format handle most of this. We will just jump
         in at the last minute to (potentially) override some column types.
diff --git a/lib/galaxy/datatypes/qualityscore.py b/lib/galaxy/datatypes/qualityscore.py
index 9d116a2ebfe..51694932f30 100644
--- a/lib/galaxy/datatypes/qualityscore.py
+++ b/lib/galaxy/datatypes/qualityscore.py
@@ -3,7 +3,7 @@ Qualityscore class
 """
 import logging
 
-from galaxy.datatypes._protocols import Dataset_t24
+from galaxy.datatypes._protocols import DatasetProtocol25
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -66,7 +66,7 @@ class QualityScoreSOLiD(QualityScore):
                     return False
         return goodblock > 0
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             return
diff --git a/lib/galaxy/datatypes/registry.py b/lib/galaxy/datatypes/registry.py
index ec017d862be..fd19d7d33ec 100644
--- a/lib/galaxy/datatypes/registry.py
+++ b/lib/galaxy/datatypes/registry.py
@@ -20,7 +20,7 @@ from typing import (
 import yaml
 
 import galaxy.util
-from galaxy.datatypes._protocols import Dataset_t16
+from galaxy.datatypes._protocols import DatasetProtocol5
 from galaxy.tool_util.edam_util import load_edam_tree
 from galaxy.util import RW_R__R__
 from galaxy.util.bunch import Bunch
@@ -831,8 +831,8 @@ class Registry:
         return None
 
     def find_conversion_destination_for_dataset_by_extensions(
-        self, dataset_or_ext: Union[str, Dataset_t16], accepted_formats: List[str], converter_safe: bool = True
-    ) -> Tuple[bool, Optional[str], Optional[Dataset_t16]]:
+        self, dataset_or_ext: Union[str, DatasetProtocol5], accepted_formats: List[str], converter_safe: bool = True
+    ) -> Tuple[bool, Optional[str], Optional[DatasetProtocol5]]:
         """
         returns (direct_match, converted_ext, converted_dataset)
         - direct match is True iff no the data set already has an accepted format
@@ -840,7 +840,7 @@ class Registry:
         """
         if hasattr(dataset_or_ext, "ext"):
             ext = dataset_or_ext.ext
-            dataset = cast(Dataset_t16, dataset_or_ext)
+            dataset = cast(DatasetProtocol5, dataset_or_ext)
         else:
             ext = dataset_or_ext
             dataset = None
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index c5744b72401..cdda4e82d47 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -25,12 +25,12 @@ from markupsafe import escape
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Dataset_t10,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
+    DatasetProtocol9,
+    DatasetProtocol18,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
+    DatasetProtocol26,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -73,7 +73,7 @@ class SequenceSplitLocations(data.Text):
 
     file_ext = "fqtoc"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             try:
                 parsed_data = json.load(open(dataset.file_name))
@@ -110,7 +110,7 @@ class Sequence(data.Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -130,7 +130,7 @@ class Sequence(data.Text):
             dataset.metadata.data_lines = data_lines
             dataset.metadata.sequences = sequences
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -566,7 +566,7 @@ class csFasta(Sequence):
                     return False
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             dataset.metadata.sequences = None
@@ -643,7 +643,7 @@ class Fastg(Sequence):
                     break  # we found a non-empty line, but it's not a header
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         with open(dataset.file_name) as fh:
             for i, line in enumerate(fh):
                 if not line:
@@ -668,7 +668,7 @@ class Fastg(Sequence):
             return
         return Sequence.set_meta(self, dataset, overwrite=overwrite, **kwd)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -692,7 +692,7 @@ class BaseFastq(Sequence):
     file_ext = "fastq"
     bases_regexp = re.compile(r"^[NGTAC 0123\.]*$", re.IGNORECASE)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
@@ -773,7 +773,7 @@ class BaseFastq(Sequence):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -876,7 +876,7 @@ class BaseFastq(Sequence):
                     return True
         return False
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         headers = iter_headers(dataset.file_name, sep="\n", count=-1)
         # check to see if the base qualities match
         if not self.quality_check(headers):
@@ -1017,7 +1017,7 @@ class Maf(Alignment):
         Alignment.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """
         Parses and sets species, chromosomes, index from MAF file.
@@ -1051,7 +1051,7 @@ class Maf(Alignment):
         indexes.write(open(index_file.file_name, "wb"))
         dataset.metadata.maf_index = index_file
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1065,11 +1065,11 @@ class Maf(Alignment):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset)
 
-    def make_html_table(self, dataset: Dataset_t10, skipchars: Optional[List] = None) -> str:
+    def make_html_table(self, dataset: DatasetProtocol18, skipchars: Optional[List] = None) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
@@ -1144,7 +1144,7 @@ class MafCustomTrack(data.Text):
         name="vp_end", default="100", desc="Viewport End", readonly=True, optional=True, visible=False, no_value=""
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Parses and sets viewport metadata from MAF file.
         """
@@ -1277,7 +1277,7 @@ class RNADotPlotMatrix(data.Data):
     edam_format = "format_3466"
     file_ext = "rna_eps"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "RNA Dot Plot format (Postscript derivative)"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1315,7 +1315,7 @@ class DotBracket(Sequence):
     sequence_regexp = re.compile(r"^[ACGTURYKMSWBDHVN]+$", re.I)
     structure_regexp = re.compile(r"^[\(\)\.\[\]{}]+$")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 025d5b1aba0..edaa8ad419a 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -12,12 +12,12 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t22,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol17,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
+    DatasetProtocol26,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
@@ -66,7 +66,7 @@ class _SpalnDb(Data):
             substitute_name_with_metadata="spalndb_name",
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         rval = ["<html><head><title>Spaln Database</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -82,7 +82,7 @@ class _SpalnDb(Data):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -101,7 +101,7 @@ class _SpalnDb(Data):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "spaln database (multiple files)"
@@ -110,7 +110,7 @@ class _SpalnDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -120,7 +120,7 @@ class _SpalnDb(Data):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -181,7 +181,7 @@ class _SpalnDb(Data):
             return None
         raise NotImplementedError("Can't split spaln database")
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         efp = dataset.extra_files_path
         for filename in os.listdir(efp):
diff --git a/lib/galaxy/datatypes/speech.py b/lib/galaxy/datatypes/speech.py
index c66e44e1cba..b2e65320998 100644
--- a/lib/galaxy/datatypes/speech.py
+++ b/lib/galaxy/datatypes/speech.py
@@ -1,4 +1,4 @@
-from galaxy.datatypes._protocols import Dataset_t24
+from galaxy.datatypes._protocols import DatasetProtocol25
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -98,7 +98,7 @@ class BPF(Text):
         "SAO",
     ]
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents"""
         types = set()
         with open(dataset.dataset.file_name) as fd:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index f0bf9b98918..4b1ae95a4eb 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,18 +30,18 @@ from galaxy.datatypes import (
     metadata,
 )
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t8,
-    Dataset_t9,
-    Dataset_t10,
-    Dataset_t12,
-    Dataset_t17,
-    Dataset_t19,
-    Dataset_t20,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
-    HasFileNameProperty,
+    DatasetProtocol7,
+    DatasetProtocol9,
+    DatasetProtocol11,
+    DatasetProtocol14,
+    DatasetProtocol15,
+    DatasetProtocol18,
+    DatasetProtocol20,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
+    DatasetProtocol26,
+    HasFileName,
     HasMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -130,16 +130,16 @@ class TabularData(Text):
     )
 
     @abc.abstractmethod
-    def set_meta(self, dataset: Dataset_t24, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         kwd.setdefault("line_wrap", False)
         super().set_peek(dataset, **kwd)
         if dataset.metadata.comment_lines:
             dataset.blurb = f"{dataset.blurb}, {util.commaify(str(dataset.metadata.comment_lines))} comments"
 
-    def displayable(self, dataset: Dataset_t12) -> bool:
+    def displayable(self, dataset: DatasetProtocol15) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -151,7 +151,7 @@ class TabularData(Text):
         except Exception:
             return False
 
-    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileName, offset: int = 0, ck_size: Optional[int] = None) -> str:
         ck_data, last_read = self._read_chunk(trans, dataset, offset, ck_size)
         return dumps(
             {
@@ -161,7 +161,7 @@ class TabularData(Text):
             }
         )
 
-    def _read_chunk(self, trans, dataset: HasFileNameProperty, offset: int, ck_size: Optional[int] = None):
+    def _read_chunk(self, trans, dataset: HasFileName, offset: int, ck_size: Optional[int] = None):
         with compression_utils.get_fileobj(dataset.file_name) as f:
             f.seek(offset)
             ck_data = f.read(ck_size or trans.app.config.display_chunk_size)
@@ -176,7 +176,7 @@ class TabularData(Text):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -233,7 +233,7 @@ class TabularData(Text):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: Dataset_t17) -> str:
+    def display_as_markdown(self, dataset_instance: DatasetProtocol20) -> str:
         with open(dataset_instance.file_name) as f:
             contents = f.read(data.DEFAULT_MAX_PEEK_SIZE)
         markdown = self.make_html_table(dataset_instance, peek=contents)
@@ -241,7 +241,7 @@ class TabularData(Text):
             markdown += indicate_data_truncated()
         return pre_formatted_contents(markdown)
 
-    def make_html_table(self, dataset: Dataset_t10, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol18, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         try:
             out = ['<table cellspacing="0" cellpadding="3">']
@@ -254,7 +254,7 @@ class TabularData(Text):
 
     def make_html_peek_header(
         self,
-        dataset: Dataset_t9,
+        dataset: DatasetProtocol7,
         skipchars: Optional[List] = None,
         column_names: Optional[List] = None,
         column_number_format: str = "%s",
@@ -308,7 +308,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek header: {util.unicodify(exc)}")
         return "".join(out)
 
-    def make_html_peek_rows(self, dataset: Dataset_t8, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_peek_rows(self, dataset: DatasetProtocol14, skipchars: Optional[List] = None, **kwargs) -> str:
         if skipchars is None:
             skipchars = []
         out = []
@@ -345,7 +345,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek rows: {util.unicodify(exc)}")
         return "".join(out)
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formatted html of peek"""
         return self.make_html_table(dataset)
 
@@ -381,27 +381,27 @@ class TabularData(Text):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return ColumnarDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetColumnarDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetColumnarDataProvider(dataset, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return DictDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetDictDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetDictDataProvider(dataset, deliminator=delimiter, **settings)
@@ -418,7 +418,7 @@ class Tabular(TabularData):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         *,
         overwrite: bool = True,
         skip: Optional[int] = None,
@@ -587,10 +587,10 @@ class Tabular(TabularData):
         if column_names is not None:
             dataset.metadata.column_names = column_names
 
-    def as_gbrowse_display_file(self, dataset: HasFileNameProperty, **kwd) -> Union[FileObjType, str]:
+    def as_gbrowse_display_file(self, dataset: HasFileName, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
-    def as_ucsc_display_file(self, dataset: Dataset_t2, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
 
@@ -600,7 +600,7 @@ class SraManifest(Tabular):
     file_ext = "sra_manifest.tabular"
     data_line_offset = 1
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.comment_lines = 1
 
@@ -641,7 +641,7 @@ class Taxonomy(Tabular):
             "Subspecies",
         ]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -732,7 +732,7 @@ class Sam(Tabular, _BamOrSam):
             "OPT",
         ]
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -790,7 +790,7 @@ class Sam(Tabular, _BamOrSam):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -872,55 +872,55 @@ class Sam(Tabular, _BamOrSam):
     # sam does not use '#' to indicate comments/headers - we need to strip out those headers from the std. providers
     # TODO:?? seems like there should be an easier way to do this - metadata.comment_char?
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: Dataset_t2, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> FilteredLineDataProvider:
         settings["comment_char"] = "@"
         return super().line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
         settings["comment_char"] = "@"
         return super().regex_line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: Dataset_t2, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         settings["comment_char"] = "@"
         return super().dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetDictDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: Dataset_t2, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         headers_source = RegexLineDataProvider(dataset_source, regex_list=["^@"])
         return RegexLineDataProvider(headers_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", dict_dataprovider.settings)
-    def id_seq_qual_dataprovider(self, dataset: Dataset_t2, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
         # provided as an example of a specified column dict (w/o metadata)
         settings["indeces"] = [0, 9, 10]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, True, **settings)
 
@@ -948,7 +948,7 @@ class Pileup(Tabular):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset, column_parameter_alias={"chromCol": "Chrom", "startCol": "Start", "baseCol": "Base"}
@@ -1001,11 +1001,11 @@ class Pileup(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1050,11 +1050,11 @@ class BaseVcf(Tabular):
         headers = get_headers(fname_or_file_prefix, "\n", count=1)
         return headers[0][0].startswith("##fileformat=VCF")
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         line = None
         with compression_utils.get_fileobj(dataset.file_name) as fh:
@@ -1080,7 +1080,7 @@ class BaseVcf(Tabular):
         if exit_code != 0:
             raise Exception(f"Error merging VCF files: {stderr!r}")
 
-    def validate(self, dataset: Dataset_t19, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
         def validate_row(row):
             if len(row) < 8:
                 raise Exception("Not enough columns in row %s" % row.join("\t"))
@@ -1090,11 +1090,11 @@ class BaseVcf(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 1, 1, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: Dataset_t2, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1135,7 +1135,7 @@ class VcfGz(BaseVcf, binary.Binary):
             return binascii.hexlify(last28) == b"1f8b08040000000000ff0600424302001b0003000000000000000000"
 
     def set_meta(
-        self, dataset: Dataset_t24, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         # Creates the index for the VCF file.
@@ -1238,7 +1238,7 @@ class Eland(Tabular):
         ]
 
     def make_html_table(
-        self, dataset: Dataset_t10, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
+        self, dataset: DatasetProtocol18, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
     ) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
@@ -1299,7 +1299,7 @@ class Eland(Tabular):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1461,7 +1461,7 @@ class BaseCSV(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         column_types = []
         header_row = []
         data_row = []
@@ -1543,7 +1543,7 @@ class ConnectivityTable(Tabular):
         self.column_names = ["base_index", "base", "neighbor_left", "neighbor_right", "partner", "natural_numbering"]
         self.column_types = ["int", "str", "int", "int", "int", "int"]
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
 
         with open(dataset.file_name) as fh:
@@ -1610,7 +1610,7 @@ class ConnectivityTable(Tabular):
                 i += 1
         return False
 
-    def get_chunk(self, trans, dataset: HasFileNameProperty, offset: int = 0, ck_size: Optional[int] = None) -> str:
+    def get_chunk(self, trans, dataset: HasFileName, offset: int = 0, ck_size: Optional[int] = None) -> str:
         ck_data, last_read = self._read_chunk(trans, dataset, offset, ck_size)
         try:
             # The ConnectivityTable format has several derivatives of which one is delimited by (multiple) spaces.
@@ -1678,7 +1678,7 @@ class MatrixMarket(TabularData):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1806,7 +1806,7 @@ class CMAP(TabularData):
 
     def set_meta(
         self,
-        dataset: Dataset_t24,
+        dataset: DatasetProtocol25,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 7,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index f4d46547bee..e10ab84120c 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -17,13 +17,13 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t22,
-    Dataset_t23,
-    Dataset_t24,
-    Dataset_t25,
-    GeneratePrimaryFileDataset,
-    HasCreatingJobProperty,
+    DatasetProtocol6,
+    DatasetProtocol17,
+    DatasetProtocol21,
+    DatasetProtocol23,
+    DatasetProtocol25,
+    DatasetProtocol26,
+    HasCreatingJob,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -56,7 +56,7 @@ class Html(Text):
     edam_format = "format_2331"
     file_ext = "html"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "HTML file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -92,7 +92,7 @@ class Json(Text):
     edam_format = "format_3464"
     file_ext = "json"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "JavaScript Object Notation (JSON)"
@@ -129,7 +129,7 @@ class Json(Text):
                 return start.startswith("[") or start.startswith("{")
             return False
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -144,7 +144,7 @@ class ExpressionJson(Json):
         name="json_type", default=None, desc="JavaScript or JSON type of expression", readonly=True, visible=True
     )
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """ """
         if dataset.has_data():
             json_type = "null"
@@ -171,7 +171,7 @@ class ExpressionJson(Json):
 class Ipynb(Json):
     file_ext = "ipynb"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Jupyter Notebook"
@@ -198,7 +198,7 @@ class Ipynb(Json):
     def display_data(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -219,7 +219,7 @@ class Ipynb(Json):
     def _display_data_trusted(
         self,
         trans,
-        dataset: Dataset_t25,
+        dataset: DatasetProtocol26,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -254,7 +254,7 @@ class Ipynb(Json):
                 )
             return open(ofilename, mode="rb"), headers
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models in dataset.
         """
@@ -390,7 +390,7 @@ class Biom1(Json):
         no_value=[],
     )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "Biological Observation Matrix v1"
@@ -427,7 +427,7 @@ class Biom1(Json):
             pass
         return is_biom
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the BIOM file.
         """
@@ -489,7 +489,7 @@ class ImgtJson(Json):
 
     MetadataElement(name="taxon_names", default=[], desc="taxonID: names", readonly=True, visible=True, no_value=[])
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "IMGT Library"
@@ -528,7 +528,7 @@ class ImgtJson(Json):
             pass
         return is_imgt
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the imgt file.
         """
@@ -555,7 +555,7 @@ class GeoJson(Json):
 
     file_ext = "geojson"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "GeoJSON"
@@ -616,7 +616,7 @@ class Obo(Text):
     edam_format = "format_2549"
     file_ext = "obo"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Open Biomedical Ontology (OBO)"
@@ -658,7 +658,7 @@ class Arff(Text):
     )
     MetadataElement(name="columns", default=0, desc="Number of columns", readonly=True, visible=True, no_value=0)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Attribute-Relation File Format (ARFF)"
@@ -694,7 +694,7 @@ class Arff(Text):
                     return True
         return False
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         """
         Trying to count the comment lines and the number of columns included.
         A typical ARFF data block looks like this:
@@ -779,7 +779,7 @@ class SnpEffDb(Text):
             pass
         return snpeff_version
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         data_dir = dataset.extra_files_path
         # search data_dir/genome_version for files
@@ -865,14 +865,14 @@ class SnpSiftDbNSFP(Text):
             "%s.gz.tbi", description="Tabix Index File", substitute_name_with_metadata="reference_name", is_binary=True
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
         """
         return "<html><head><title>SnpSiftDbNSFP Composite Dataset</title></head></html>"
 
-    def regenerate_primary_file(self, dataset: Dataset_t22) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -884,7 +884,7 @@ class SnpSiftDbNSFP(Text):
                 f.write("\n")
             f.write(annotations)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         try:
             efp = dataset.extra_files_path
             if os.path.exists(efp):
@@ -910,7 +910,7 @@ class SnpSiftDbNSFP(Text):
                 unicodify(e),
             )
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"{dataset.metadata.reference_name} :  {','.join(dataset.metadata.annotation)}"
             dataset.blurb = f"{dataset.metadata.reference_name}"
@@ -1095,9 +1095,7 @@ class Yaml(Text):
         """Returns the mime type of the datatype"""
         return "application/yaml"
 
-    def _yield_user_file_content(
-        self, trans, from_dataset: HasCreatingJobProperty, filename: str, headers: Headers
-    ) -> IO:
+    def _yield_user_file_content(self, trans, from_dataset: HasCreatingJob, filename: str, headers: Headers) -> IO:
         # Override non-standard application/yaml mediatype with
         # text/plain, so preview is shown in preview iframe,
         # instead of downloading the file.
@@ -1155,7 +1153,7 @@ class BCSLts(Json):
             is_bcsl_ts = self._looks_like_bcsl_ts(file_prefix)
         return is_bcsl_ts
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = "States: {}\nTransitions: {}\nUnique agents: {}\nInitial state: {}"
             ts = json.load(open(dataset.file_name, "r"))
@@ -1189,7 +1187,7 @@ class StormSample(Text):
         keywords = ["Storm-pars", "Result (initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Storm-pars sample results."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1214,7 +1212,7 @@ class StormCheck(Text):
         keywords = ["Storm ", "Result (for initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
@@ -1242,7 +1240,7 @@ class CTLresult(Text):
         keywords = ["Result:", "Number of satisfying states:"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index 8488c06553a..bdab7cb638a 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -4,9 +4,9 @@ Datatype classes for tracks/track views within galaxy.
 import logging
 
 from galaxy.datatypes._protocols import (
-    Dataset_t20,
-    Dataset_t23,
-    GeneratePrimaryFileDataset,
+    DatasetProtocol6,
+    DatasetProtocol21,
+    DatasetProtocol23,
 )
 from galaxy.datatypes.text import Html
 from . import binary
@@ -30,7 +30,7 @@ class UCSCTrackHub(Html):
     file_ext = "trackhub"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -48,14 +48,14 @@ class UCSCTrackHub(Html):
         rval.append("</ul></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Track Hub structure: Visualization in UCSC Track Hub"
         else:
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Dataset_t20) -> str:
+    def display_peek(self, dataset: DatasetProtocol21) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/triples.py b/lib/galaxy/datatypes/triples.py
index e71f86460e8..1a143676730 100644
--- a/lib/galaxy/datatypes/triples.py
+++ b/lib/galaxy/datatypes/triples.py
@@ -4,7 +4,7 @@ Triple format classes
 import logging
 import re
 
-from galaxy.datatypes._protocols import Dataset_t23
+from galaxy.datatypes._protocols import DatasetProtocol23
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -37,7 +37,7 @@ class Triples(data.Data):
         """
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -62,7 +62,7 @@ class NTriples(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -86,7 +86,7 @@ class N3(data.Text, Triples):
         """
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -114,7 +114,7 @@ class Turtle(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -143,7 +143,7 @@ class Rdf(xml.GenericXml, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -169,7 +169,7 @@ class Jsonld(text.Json, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -193,7 +193,7 @@ class HDT(binary.Binary, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index ebc7e8c6ed5..2ecc9cfe8df 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -7,9 +7,9 @@ from typing import List
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Dataset_t2,
-    Dataset_t23,
-    Dataset_t24,
+    DatasetProtocol11,
+    DatasetProtocol23,
+    DatasetProtocol25,
 )
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -38,7 +38,7 @@ class GenericXml(data.Text):
     edam_format = "format_2332"
     file_ext = "xml"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -80,7 +80,7 @@ class GenericXml(data.Text):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("xml", XMLDataProvider.settings)
-    def xml_dataprovider(self, dataset: Dataset_t2, **settings) -> XMLDataProvider:
+    def xml_dataprovider(self, dataset: DatasetProtocol11, **settings) -> XMLDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return XMLDataProvider(dataset_source, **settings)
 
@@ -91,7 +91,7 @@ class MEMEXml(GenericXml):
 
     file_ext = "memexml"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -107,7 +107,7 @@ class CisML(GenericXml):
 
     file_ext = "cisml"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -151,7 +151,7 @@ class Dzi(GenericXml):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: Dataset_t24, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
         tree = util.parse_xml(dataset.file_name)
         root = tree.getroot()
         dataset.metadata.format = root.get("Format")
@@ -168,7 +168,7 @@ class Dzi(GenericXml):
                 dataset.metadata.width = elem.get("Width")
                 dataset.metadata.height = elem.get("Height")
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Deep Zoom Image"
@@ -201,7 +201,7 @@ class Phyloxml(GenericXml):
     edam_format = "format_3159"
     file_ext = "phyloxml"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -236,7 +236,7 @@ class Owl(GenericXml):
     edam_format = "format_3262"
     file_ext = "owl"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Web Ontology Language OWL"
@@ -261,7 +261,7 @@ class Sbml(GenericXml):
     edam_data = "data_2024"
     edam_format = "format_2585"
 
-    def set_peek(self, dataset: Dataset_t23, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "System Biology Markup Language SBML"

From c62cce7b18c6a1e58b7f4d7f30db8a59524126fb Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 19 Dec 2022 18:09:39 -0500
Subject: [PATCH 105/350] Combine select protocols as Displayable

---
 lib/galaxy/datatypes/_protocols.py | 18 +-----------------
 lib/galaxy/datatypes/binary.py     |  6 +++---
 lib/galaxy/datatypes/blast.py      |  4 ++--
 lib/galaxy/datatypes/data.py       | 17 ++++++-----------
 lib/galaxy/datatypes/isa.py        |  4 ++--
 lib/galaxy/datatypes/sequence.py   |  4 ++--
 lib/galaxy/datatypes/spaln.py      |  4 ++--
 lib/galaxy/datatypes/tabular.py    |  4 ++--
 lib/galaxy/datatypes/text.py       |  6 +++---
 9 files changed, 23 insertions(+), 44 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 693c3b3ff01..656e33c10e3 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -140,30 +140,14 @@ class DatasetProtocol7(HasId, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol8(HasHid, HasName, Protocol):
-    ...
-
-
 class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol10(HasExtension, HasHid, HasName, Protocol):
-    ...
-
-
 class DatasetProtocol11(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol12(HasExtension, HasExtraFilesPath, HasFileName, HasName, Protocol):
-    ...
-
-
-class DatasetProtocol13(HasExtension, HasFileName, HasHid, HasName, Protocol):
-    ...
-
-
 class DatasetProtocol14(HasId, HasMetadata, HasSetPeek, HasPeek, Protocol):
     ...
 
@@ -240,7 +224,7 @@ class DatasetProtocol25(
     ...
 
 
-class DatasetProtocol26(
+class Displayable(
     HasCreatingJob,
     HasDataset,
     HasDatatype,
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 5f6e2daa9b1..a9727a85d4a 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -41,7 +41,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
     HasFileName,
     HasMetadata,
 )
@@ -650,7 +650,7 @@ class BamNative(CompressedArchive, _BamOrSam):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -2021,7 +2021,7 @@ class H5MLM(H5):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index c34b1827498..9782b1e3a16 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -43,7 +43,7 @@ from typing import (
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol26,
+    Displayable,
 )
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -212,7 +212,7 @@ class _BlastDb(Data):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index bfe46f2676b..220a792862a 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -30,18 +30,15 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol3,
     DatasetProtocol5,
     DatasetProtocol6,
-    DatasetProtocol8,
     DatasetProtocol9,
-    DatasetProtocol10,
     DatasetProtocol11,
-    DatasetProtocol12,
     DatasetProtocol16,
     DatasetProtocol20,
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol24,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
     HasClearAssociatedFiles,
     HasCreatingJob,
     HasExt,
@@ -358,7 +355,7 @@ class Data(metaclass=DataMeta):
         return error, msg, messagetype
 
     def _archive_composite_dataset(
-        self, trans, data: DatasetProtocol12, headers: Headers, do_action: str = "zip"
+        self, trans, data: Displayable, headers: Headers, do_action: str = "zip"
     ) -> Tuple[Union[ZipstreamWrapper, str], Headers]:
         # save a composite object into a compressed archive for downloading
         outfname = data.name[0:150]
@@ -403,9 +400,7 @@ class Data(metaclass=DataMeta):
                 rpath = os.path.relpath(fpath, extra_files_path)
                 yield fpath, rpath
 
-    def _serve_raw(
-        self, dataset: DatasetProtocol26, to_ext: Optional[str], headers: Headers, **kwd
-    ) -> Tuple[IO, Headers]:
+    def _serve_raw(self, dataset: Displayable, to_ext: Optional[str], headers: Headers, **kwd) -> Tuple[IO, Headers]:
         headers["Content-Length"] = str(os.stat(dataset.file_name).st_size)
         headers[
             "content-type"
@@ -445,7 +440,7 @@ class Data(metaclass=DataMeta):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -607,9 +602,9 @@ class Data(metaclass=DataMeta):
 
     def _download_filename(
         self,
-        dataset: DatasetProtocol10,
+        dataset: Displayable,
         to_ext: Optional[str] = None,
-        hdca: Optional[DatasetProtocol8] = None,
+        hdca: Optional[Displayable] = None,
         element_identifier: Optional[str] = None,
         filename_pattern: Optional[str] = None,
     ) -> str:
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index 9ea161bdf31..b57fff29b49 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -30,7 +30,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol26,
+    Displayable,
     HasExtraFilesPath,
 )
 from galaxy.datatypes.data import Data
@@ -269,7 +269,7 @@ class _Isa(Data):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index cdda4e82d47..5111ca9ba6c 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -30,7 +30,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
     HasMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -773,7 +773,7 @@ class BaseFastq(Sequence):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index edaa8ad419a..9814207dad5 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -17,7 +17,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
@@ -120,7 +120,7 @@ class _SpalnDb(Data):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 4b1ae95a4eb..1d11c53eb56 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -40,7 +40,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
     HasFileName,
     HasMetadata,
 )
@@ -176,7 +176,7 @@ class TabularData(Text):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index e10ab84120c..9b291b1d4db 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -22,7 +22,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol25,
-    DatasetProtocol26,
+    Displayable,
     HasCreatingJob,
 )
 from galaxy.datatypes.data import (
@@ -198,7 +198,7 @@ class Ipynb(Json):
     def display_data(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -219,7 +219,7 @@ class Ipynb(Json):
     def _display_data_trusted(
         self,
         trans,
-        dataset: DatasetProtocol26,
+        dataset: Displayable,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,

From 03760c7db9890e3f0ef77fe95376ec369bafef2b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Mon, 19 Dec 2022 19:19:18 -0500
Subject: [PATCH 106/350] Combine select protocols as SetsMetadata

---
 lib/galaxy/datatypes/_protocols.py            | 42 +++++------
 lib/galaxy/datatypes/anvio.py                 |  4 +-
 lib/galaxy/datatypes/assembly.py              |  7 +-
 lib/galaxy/datatypes/binary.py                | 70 +++++++++----------
 .../datatypes/constructive_solid_geometry.py  | 22 +++---
 lib/galaxy/datatypes/data.py                  |  6 +-
 lib/galaxy/datatypes/genetics.py              | 17 +++--
 lib/galaxy/datatypes/goldenpath.py            |  4 +-
 lib/galaxy/datatypes/images.py                |  4 +-
 lib/galaxy/datatypes/interval.py              | 21 +++---
 lib/galaxy/datatypes/media.py                 |  8 +--
 lib/galaxy/datatypes/microarrays.py           |  6 +-
 lib/galaxy/datatypes/molecules.py             | 28 ++++----
 lib/galaxy/datatypes/mothur.py                | 18 ++---
 lib/galaxy/datatypes/msa.py                   |  8 +--
 lib/galaxy/datatypes/ngsindex.py              |  4 +-
 lib/galaxy/datatypes/phylip.py                |  4 +-
 lib/galaxy/datatypes/plant_tribes.py          |  4 +-
 lib/galaxy/datatypes/proteomics.py            |  8 +--
 lib/galaxy/datatypes/qiime2.py                |  6 +-
 lib/galaxy/datatypes/qualityscore.py          |  4 +-
 lib/galaxy/datatypes/sequence.py              | 16 ++---
 lib/galaxy/datatypes/spaln.py                 |  7 +-
 lib/galaxy/datatypes/speech.py                |  4 +-
 lib/galaxy/datatypes/tabular.py               | 24 +++----
 lib/galaxy/datatypes/text.py                  | 19 +++--
 lib/galaxy/datatypes/xml.py                   |  4 +-
 27 files changed, 178 insertions(+), 191 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 656e33c10e3..786e1a12cdf 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -124,10 +124,6 @@ class DatasetProtocol3(HasFileName, HasGetSize, Protocol):
     ...
 
 
-class DatasetProtocol4(HasFileName, HasMetadata, Protocol):
-    ...
-
-
 class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
     ...
 
@@ -160,10 +156,6 @@ class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileNam
     ...
 
 
-class DatasetProtocol17(HasExtraFilesPath, HasFileName, HasInfo, HasMetadata, HasName, Protocol):
-    ...
-
-
 class DatasetProtocol18(HasFileName, HasId, HasMetadata, HasName, HasPeek, HasSetPeek, Protocol):
     ...
 
@@ -207,23 +199,6 @@ class DatasetProtocol24(
     ...
 
 
-class DatasetProtocol25(
-    HasBlurb,
-    HasDataset,
-    HasExtraFilesPath,
-    HasFileName,
-    HasGetSize,
-    HasHasData,
-    HasId,
-    HasInfo,
-    HasMetadata,
-    HasName,
-    HasPeek,
-    Protocol,
-):
-    ...
-
-
 class Displayable(
     HasCreatingJob,
     HasDataset,
@@ -239,3 +214,20 @@ class Displayable(
     Protocol,
 ):
     ...
+
+
+class SetsMetadata(
+    HasBlurb,
+    HasDataset,
+    HasExtraFilesPath,
+    HasFileName,
+    HasGetSize,
+    HasHasData,
+    HasId,
+    HasInfo,
+    HasMetadata,
+    HasName,
+    HasPeek,
+    Protocol,
+):
+    ...
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index ac20938306c..4f3841e57b7 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -11,7 +11,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
@@ -96,7 +96,7 @@ class AnvioDB(AnvioComposite):
         if self._anvio_basename is not None:
             self.add_composite_file(self._anvio_basename, is_binary=True, optional=False)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the anvio_basename based upon actual extra_files_path contents.
         """
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 2506a709704..58b0da92b12 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -14,8 +14,7 @@ from galaxy.datatypes import (
 )
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol17,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -192,7 +191,7 @@ class Velvet(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -243,6 +242,6 @@ class Velvet(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         Html.set_meta(self, dataset, overwrite=overwrite, **kwd)
         self.regenerate_primary_file(dataset)
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index a9727a85d4a..e4de0f5ee03 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -40,10 +40,10 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol16,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     Displayable,
     HasFileName,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import (
     Data,
@@ -214,7 +214,7 @@ class Cel(Binary):
             found_cel_3 = True
         return found_cel_3 or found_cel_4 or found_cel_agcc
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Cel file.
         """
@@ -417,7 +417,7 @@ class _BamOrSam:
     Helper class to set the metadata common to sam and bam files
     """
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         try:
             bam_file = pysam.AlignmentFile(dataset.file_name, mode="rb")
             # TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
@@ -522,7 +522,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         no_value={},
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         _BamOrSam().set_meta(dataset, overwrite=overwrite, **kwd)
 
     @staticmethod
@@ -776,7 +776,7 @@ class Bam(BamNative):
         return needs_sorting
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         # These metadata values are not accessible by users, always overwrite
         super().set_meta(dataset=dataset, overwrite=overwrite, **kwd)
@@ -962,7 +962,7 @@ class CRAM(Binary):
     )
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         major_version, minor_version = self.get_cram_version(dataset.file_name)
         if major_version != -1:
@@ -1045,7 +1045,7 @@ class Bcf(BaseBcf):
             return False
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """Creates the index for the BCF file."""
         # These metadata values are not accessible by users, always overwrite
@@ -1249,7 +1249,7 @@ class Loom(H5):
         except Exception:
             return f"Binary Loom file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as loom_file:
@@ -1394,7 +1394,7 @@ class Anndata(H5):
                 return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         with h5py.File(dataset.file_name, "r") as anndata_file:
             dataset.metadata.title = anndata_file.attrs.get("title")
@@ -1587,7 +1587,7 @@ class Grib(Binary):
         except Exception:
             return f"Binary GRIB file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the GRIB edition.
         """
@@ -1754,7 +1754,7 @@ class Biom2(H5):
                 return required_fields.issubset(f.attrs.keys())
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as f:
@@ -1940,7 +1940,7 @@ class H5MLM(H5):
     )
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         try:
             spec_key = "hyper_params"
@@ -2132,7 +2132,7 @@ class HexrdMaterials(H5):
                         return True
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as mat_file:
@@ -2325,7 +2325,7 @@ class SQlite(Binary):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         try:
             tables = []
             columns = dict()
@@ -2436,7 +2436,7 @@ class GeminiSQLite(SQlite):
     edam_format = "format_3622"
     edam_data = "data_3498"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2485,7 +2485,7 @@ class ChiraSQLite(SQlite):
 
     file_ext = "chira.sqlite"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2516,7 +2516,7 @@ class CuffDiffSQlite(SQlite):
     # TODO: Update this when/if there is a specific EDAM format for CuffDiff SQLite data.
     edam_format = "format_3621"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             genes = []
@@ -2572,7 +2572,7 @@ class MzSQlite(SQlite):
 
     file_ext = "mz.sqlite"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2609,7 +2609,7 @@ class PQP(SQlite):
 
     file_ext = "pqp"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2651,7 +2651,7 @@ class OSW(SQlite):
 
     file_ext = "osw"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2694,7 +2694,7 @@ class SQmass(SQlite):
 
     file_ext = "sqmass"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2718,7 +2718,7 @@ class BlibSQlite(SQlite):
     )
     file_ext = "blib"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2771,7 +2771,7 @@ class DlibSQlite(SQlite):
     )
     file_ext = "dlib"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2815,7 +2815,7 @@ class ElibSQlite(SQlite):
     )
     file_ext = "elib"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2866,7 +2866,7 @@ class IdpDB(SQlite):
 
     file_ext = "idpdb"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2911,7 +2911,7 @@ class GAFASQLite(SQlite):
     )
     file_ext = "gafa.sqlite"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2957,7 +2957,7 @@ class NcbiTaxonomySQlite(SQlite):
 
     file_ext = "ncbitaxonomy.sqlite"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -3104,7 +3104,7 @@ class RData(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3187,7 +3187,7 @@ class RDS(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3434,7 +3434,7 @@ class PostgresqlArchive(CompressedArchive):
     )
     file_ext = "postgresql"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3482,7 +3482,7 @@ class Fast5Archive(CompressedArchive):
     )
     file_ext = "fast5.tar"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3590,7 +3590,7 @@ class SearchGuiArchive(CompressedArchive):
     )
     file_ext = "searchgui_archive"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and zipfile.is_zipfile(dataset.file_name):
@@ -4120,7 +4120,7 @@ class Npz(CompressedArchive):
             return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         try:
             with np.load(dataset.file_name) as npz:
                 dataset.metadata.nfiles = len(npz.files)
@@ -4188,7 +4188,7 @@ class HexrdImagesNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4254,7 +4254,7 @@ class HexrdEtaOmeNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index a119f103f57..05ffdd61d17 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -17,8 +17,8 @@ from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -106,7 +106,7 @@ class Ply:
                 break
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for line in fh:
@@ -286,7 +286,7 @@ class Vtk:
             return check_data_kind(line)
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             dataset.metadata.field_names = []
             dataset.metadata.field_components = {}
@@ -375,7 +375,7 @@ class Vtk:
             if len(field_components) > 0:
                 dataset.metadata.field_components = field_components
 
-    def set_initial_metadata(self, i: int, line: str, dataset: DatasetProtocol25) -> DatasetProtocol25:
+    def set_initial_metadata(self, i: int, line: str, dataset: SetsMetadata) -> SetsMetadata:
         if i == 0:
             # The first part of legacy VTK files is the file version and
             # identifier. This part contains the single line:
@@ -394,8 +394,8 @@ class Vtk:
         return dataset
 
     def set_structure_metadata(
-        self, line: str, dataset: DatasetProtocol25, dataset_type: Optional[str]
-    ) -> Tuple[DatasetProtocol25, Optional[str]]:
+        self, line: str, dataset: SetsMetadata, dataset_type: Optional[str]
+    ) -> Tuple[SetsMetadata, Optional[str]]:
         """
         The fourth part of legacy VTK files is the dataset structure. The
         geometry part describes the geometry and topology of the dataset.
@@ -556,7 +556,7 @@ class NeperTess(data.Text):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tess")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -627,7 +627,7 @@ class NeperTesr(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tesr")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 field = ""
@@ -680,7 +680,7 @@ class NeperPoints(data.Text):
     def __init__(self, **kwd):
         data.Text.__init__(self, **kwd)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         data.Text.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -722,7 +722,7 @@ class NeperPointsTabular(NeperPoints, Tabular):
     def __init__(self, **kwd):
         Tabular.__init__(self, **kwd)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -768,7 +768,7 @@ class GmshMsh(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline().startswith("$MeshFormat")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 220a792862a..2d4c2fb9441 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -37,7 +37,6 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol24,
-    DatasetProtocol25,
     Displayable,
     HasClearAssociatedFiles,
     HasCreatingJob,
@@ -46,6 +45,7 @@ from galaxy.datatypes._protocols import (
     HasInfo,
     HasMetadata,
     HasName,
+    SetsMetadata,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -258,7 +258,7 @@ class Data(metaclass=DataMeta):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
         """Unimplemented method, allows guessing of metadata from contents of file"""
 
     def missing_meta(self, dataset: HasMetadata, check: Optional[List] = None, skip: Optional[List] = None) -> bool:
@@ -982,7 +982,7 @@ class Text(Data):
         """Returns the mime type of the datatype"""
         return "text/plain"
 
-    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index e3d745d32f0..6294827df36 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -31,13 +31,12 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
     DatasetProtocol11,
-    DatasetProtocol17,
     DatasetProtocol18,
     DatasetProtocol21,
     DatasetProtocol23,
     DatasetProtocol24,
-    DatasetProtocol25,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -82,7 +81,7 @@ class GenomeGraphs(Tabular):
         super().__init__(**kwd)
         self.add_display_app("ucsc", "Genome Graph", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.markerCol = 1
         header = open(dataset.file_name).readlines()[0].strip().split("\t")
@@ -326,7 +325,7 @@ class Rgenetics(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -348,7 +347,7 @@ class Rgenetics(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         for lped/pbed eg
 
@@ -584,7 +583,7 @@ class IdeasPre(Html):
         self.add_composite_file("IDEAS_input_config.txt", description="IDEAS input config", is_binary=False)
         self.add_composite_file("tmp.tar.gz", description="Compressed archive of compressed bed files", is_binary=True)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         for fname in os.listdir(dataset.extra_files_path):
             if fname.startswith("chromosomes"):
@@ -607,7 +606,7 @@ class IdeasPre(Html):
         rval.append("</ul></body></html>\n")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         # Cannot do this until we are setting metadata.
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
@@ -820,7 +819,7 @@ class RexpBase(Html):
         except Exception:
             return "## rexpression get_file_peek: no file found"
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -841,7 +840,7 @@ class RexpBase(Html):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         NOTE we apply the tabular machinary to the phenodata extracted
         from a BioC eSet or affybatch.
diff --git a/lib/galaxy/datatypes/goldenpath.py b/lib/galaxy/datatypes/goldenpath.py
index b121b81e039..e67d5fec964 100644
--- a/lib/galaxy/datatypes/goldenpath.py
+++ b/lib/galaxy/datatypes/goldenpath.py
@@ -6,7 +6,7 @@ from typing import (
     Union,
 )
 
-from galaxy.datatypes._protocols import DatasetProtocol25
+from galaxy.datatypes._protocols import SetsMetadata
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -24,7 +24,7 @@ class GoldenPath(Tabular):
     edam_format = "format_3693"
     file_ext = "agp"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         # AGPFile reads and validates entire file.
         AGPFile(dataset.file_name)
         super().set_meta(dataset, overwrite=overwrite, **kwd)
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 99c0bb4ab5c..06deb2e9252 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -14,7 +14,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol1,
     DatasetProtocol6,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
@@ -107,7 +107,7 @@ class OMETiff(Tiff):
     )
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         spec_key = "offsets"
         offsets_file = dataset.metadata.offsets
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 9bd726029bf..4608154ca09 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,7 +22,6 @@ from bx.intervals.io import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    DatasetProtocol4,
     DatasetProtocol9,
     DatasetProtocol11,
     DatasetProtocol15,
@@ -30,9 +29,9 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol22,
     DatasetProtocol24,
-    DatasetProtocol25,
     HasId,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
@@ -136,7 +135,7 @@ class Interval(Tabular):
         Tabular.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: DatasetProtocol25, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
+        self, dataset: SetsMetadata, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
     ) -> None:
         """Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=0)
@@ -506,7 +505,7 @@ class Bed(Interval):
     )
     # do we need to repeat these? they are the same as should be inherited from interval type
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """Sets the metadata information for datasets previously determined to be in bed format."""
         if dataset.has_data():
             i = 0
@@ -739,7 +738,7 @@ class BedStrict(Bed):
         Tabular.__init__(self, **kwd)
         self.clear_display_apps()  # only new style display applications for this datatype
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)  # need column count first
         if dataset.metadata.columns >= 4:
             dataset.metadata.nameCol = 4
@@ -823,7 +822,7 @@ class Gff(Tabular, _RemoteCallMixin):
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
-    def set_attribute_metadata(self, dataset: DatasetProtocol4) -> None:
+    def set_attribute_metadata(self, dataset: SetsMetadata) -> None:
         """
         Sets metadata elements for dataset's attributes.
         """
@@ -863,7 +862,7 @@ class Gff(Tabular, _RemoteCallMixin):
         dataset.metadata.attribute_types = attribute_types
         dataset.metadata.attributes = len(attribute_types)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
 
         i = 0
@@ -1082,7 +1081,7 @@ class Gff3(Gff):
         """Initialize datatype, by adding GBrowse display app"""
         Gff.__init__(self, **kwd)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
         i = 0
         with compression_utils.get_fileobj(dataset.file_name) as in_fh:
@@ -1394,7 +1393,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         max_data_lines = None
         i = 0
         for i, line in enumerate(open(dataset.file_name)):  # noqa: B007
@@ -1475,7 +1474,7 @@ class CustomTrack(Tabular):
         Tabular.__init__(self, **kwd)
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
     def display_peek(self, dataset: DatasetProtocol21) -> str:
@@ -1791,7 +1790,7 @@ class IntervalTabix(Interval):
     # Ideally the tabix_index would be regenerated when the metadataElements are updated
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         first_line_is_header: bool = False,
         metadata_tmp_files_dir: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/media.py b/lib/galaxy/datatypes/media.py
index 36152920dd7..2ff4e8905a4 100644
--- a/lib/galaxy/datatypes/media.py
+++ b/lib/galaxy/datatypes/media.py
@@ -8,7 +8,7 @@ from typing import (
     Tuple,
 )
 
-from galaxy.datatypes._protocols import DatasetProtocol25
+from galaxy.datatypes._protocols import SetsMetadata
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -72,7 +72,7 @@ class Audio(Binary):
         no_value=0,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
 
@@ -159,7 +159,7 @@ class Video(Binary):
             w = h = fps = 0
         return w, h, fps
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
             (w, h, fps) = self._get_resolution(streams)
@@ -280,7 +280,7 @@ class Wav(Audio):
         with wave.open(filename, "rb"):
             return True
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents."""
         try:
             with wave.open(dataset.dataset.file_name, "rb") as fd:
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index 89a435b5033..96e038eba18 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -3,7 +3,7 @@ import logging
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Cel  # noqa: F401
 from galaxy.datatypes.data import get_file_peek
@@ -120,7 +120,7 @@ class Gal(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix ArrayList" in headers[2][0]
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gal file.
         """
@@ -162,7 +162,7 @@ class Gpr(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix Results" in headers[2][0]
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gpr file.
         """
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index 7062b384050..124e082069d 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -11,7 +11,7 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -205,7 +205,7 @@ class GenericMolFile(Text):
 class MOL(GenericMolFile):
     file_ext = "mol"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number molecules, in the case of MOL its always one.
         """
@@ -258,7 +258,7 @@ class SDF(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of molecules in dataset.
         """
@@ -341,7 +341,7 @@ class MOL2(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -427,7 +427,7 @@ class FPS(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -568,7 +568,7 @@ class OBFS(Binary):
 class DRF(GenericMolFile):
     file_ext = "drf"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -635,7 +635,7 @@ class PDB(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Find Chain_IDs for metadata.
         """
@@ -789,7 +789,7 @@ class PQR(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Find Optional Chain_IDs for metadata.
         """
@@ -886,7 +886,7 @@ class Cell(GenericMolFile):
                 return True
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1047,7 +1047,7 @@ class CIF(GenericMolFile):
                 return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1244,7 +1244,7 @@ class XYZ(GenericMolFile):
                     raise
         return blocks
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1498,7 +1498,7 @@ class InChI(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -1563,7 +1563,7 @@ class SMILES(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -1599,7 +1599,7 @@ class CML(GenericXml):
         no_value=0,
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index 49fc5317440..814eb5dced6 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -10,8 +10,8 @@ from typing import (
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol18,
-    DatasetProtocol25,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import MetadataElement
@@ -37,7 +37,7 @@ class Otu(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Otu files.
 
@@ -174,7 +174,7 @@ class GroupAbund(Otu):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         # See if file starts with header line
@@ -298,7 +298,7 @@ class AlignCheck(Tabular):
         self.column_types = ["str", "int", "int", "int", "int", "int", "int", "int"]
         self.comment_lines = 1
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         dataset.metadata.column_names = self.column_names
@@ -355,7 +355,7 @@ class DistanceMatrix(Text):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
         headers = iter_headers(dataset.file_name, sep="\t")
@@ -508,7 +508,7 @@ class PairwiseDistanceMatrix(DistanceMatrix, Tabular):
         self.column_names = ["Sequence", "Sequence", "Distance"]
         self.column_types = ["str", "str", "float"]
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -598,7 +598,7 @@ class Group(Tabular):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = None,
@@ -846,7 +846,7 @@ class CountTable(Tabular):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1058,7 +1058,7 @@ class SffFlow(Tabular):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 1254cb2c8dc..6a51192df29 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -11,7 +11,7 @@ from typing import (
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -82,7 +82,7 @@ class InfernalCM(Text):
         """
         return file_prefix.startswith("INFERNAL")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models and the version of CM file in dataset.
         """
@@ -199,7 +199,7 @@ class Stockholm_1_0(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.search(STOCKHOLM_SEARCH_PATTERN)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
 
         Set the number of models in dataset.
@@ -290,7 +290,7 @@ class MauveXmfa(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith("#FormatVersion Mauve1")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         dataset.metadata.number_of_models = generic_util.count_special_lines(
             "^#Sequence([[:digit:]]+)Entry", dataset.file_name
         )
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index b80d7235163..faebf6d1948 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -6,9 +6,9 @@ import os
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol17,
     DatasetProtocol21,
     DatasetProtocol23,
+    SetsMetadata,
 )
 from .metadata import MetadataElement
 from .text import Html
@@ -46,7 +46,7 @@ class BowtieIndex(Html):
         """
         return "<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>"
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index 9755baff5f3..d160ca93a0b 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -12,7 +12,7 @@ from typing import TYPE_CHECKING
 from galaxy import util
 from galaxy.datatypes._protocols import (
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -41,7 +41,7 @@ class Phylip(Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index f3f074d2278..9045e08f4fe 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -4,7 +4,7 @@ import re
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -104,7 +104,7 @@ class PlantTribesKsComponents(Tabular):
         except Exception:
             return f"Significant components in the Ks distribution ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of significant components in the Ks distribution.
         The dataset will always be on the order of less than 10 lines.
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 9b9267d3f48..ed6706ff203 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -14,7 +14,7 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import Text
@@ -393,7 +393,7 @@ class Dta(TabularData):
     file_ext = "dta"
     comment_lines = 0
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         column_types = []
         data_row: List = []
         data_lines = 0
@@ -466,7 +466,7 @@ class Dta2d(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         if dataset.has_data():
@@ -602,7 +602,7 @@ class Edta(TabularData):
                 line[idx] += str(idx // 4)
         return line
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         tpe = None
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index e521652852a..2b162d688ee 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -14,8 +14,8 @@ import yaml
 from galaxy.datatypes._protocols import (
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
 from galaxy.datatypes.metadata import MetadataElement
@@ -35,7 +35,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
     MetadataElement(name="format", optional=True, no_value="", readonly=True)
     MetadataElement(name="version", readonly=True)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         metadata = _get_metadata_from_archive(dataset.file_name)
         for key, value in metadata.items():
             if value:
@@ -117,7 +117,7 @@ class QIIME2Metadata(Tabular):
     def get_column_names(self, first_line: str) -> Optional[List[str]]:
         return first_line.strip().split("\t")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Let Galaxy's Tabular format handle most of this. We will just jump
         in at the last minute to (potentially) override some column types.
diff --git a/lib/galaxy/datatypes/qualityscore.py b/lib/galaxy/datatypes/qualityscore.py
index 51694932f30..ccb3e3a6980 100644
--- a/lib/galaxy/datatypes/qualityscore.py
+++ b/lib/galaxy/datatypes/qualityscore.py
@@ -3,7 +3,7 @@ Qualityscore class
 """
 import logging
 
-from galaxy.datatypes._protocols import DatasetProtocol25
+from galaxy.datatypes._protocols import SetsMetadata
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -66,7 +66,7 @@ class QualityScoreSOLiD(QualityScore):
                     return False
         return goodblock > 0
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             return
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 5111ca9ba6c..1945b76726d 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -29,9 +29,9 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol18,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     Displayable,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import DatatypeValidation
@@ -110,7 +110,7 @@ class Sequence(data.Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -566,7 +566,7 @@ class csFasta(Sequence):
                     return False
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             dataset.metadata.sequences = None
@@ -643,7 +643,7 @@ class Fastg(Sequence):
                     break  # we found a non-empty line, but it's not a header
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         with open(dataset.file_name) as fh:
             for i, line in enumerate(fh):
                 if not line:
@@ -692,7 +692,7 @@ class BaseFastq(Sequence):
     file_ext = "fastq"
     bases_regexp = re.compile(r"^[NGTAC 0123\.]*$", re.IGNORECASE)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
@@ -1017,7 +1017,7 @@ class Maf(Alignment):
         Alignment.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """
         Parses and sets species, chromosomes, index from MAF file.
@@ -1144,7 +1144,7 @@ class MafCustomTrack(data.Text):
         name="vp_end", default="100", desc="Viewport End", readonly=True, optional=True, visible=False, no_value=""
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Parses and sets viewport metadata from MAF file.
         """
@@ -1315,7 +1315,7 @@ class DotBracket(Sequence):
     sequence_regexp = re.compile(r"^[ACGTURYKMSWBDHVN]+$", re.I)
     structure_regexp = re.compile(r"^[\(\)\.\[\]{}]+$")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 9814207dad5..b459808e7b7 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -13,11 +13,10 @@ from typing import (
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol17,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     Displayable,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
@@ -82,7 +81,7 @@ class _SpalnDb(Data):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -181,7 +180,7 @@ class _SpalnDb(Data):
             return None
         raise NotImplementedError("Can't split spaln database")
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         efp = dataset.extra_files_path
         for filename in os.listdir(efp):
diff --git a/lib/galaxy/datatypes/speech.py b/lib/galaxy/datatypes/speech.py
index b2e65320998..6eb0439911f 100644
--- a/lib/galaxy/datatypes/speech.py
+++ b/lib/galaxy/datatypes/speech.py
@@ -1,4 +1,4 @@
-from galaxy.datatypes._protocols import DatasetProtocol25
+from galaxy.datatypes._protocols import SetsMetadata
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -98,7 +98,7 @@ class BPF(Text):
         "SAO",
     ]
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents"""
         types = set()
         with open(dataset.dataset.file_name) as fd:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 1d11c53eb56..2a10c3e408a 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -39,10 +39,10 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol20,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     Displayable,
     HasFileName,
     HasMetadata,
+    SetsMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
@@ -130,7 +130,7 @@ class TabularData(Text):
     )
 
     @abc.abstractmethod
-    def set_meta(self, dataset: DatasetProtocol25, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
     def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
@@ -418,7 +418,7 @@ class Tabular(TabularData):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         *,
         overwrite: bool = True,
         skip: Optional[int] = None,
@@ -600,7 +600,7 @@ class SraManifest(Tabular):
     file_ext = "sra_manifest.tabular"
     data_line_offset = 1
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.comment_lines = 1
 
@@ -790,7 +790,7 @@ class Sam(Tabular, _BamOrSam):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1054,7 +1054,7 @@ class BaseVcf(Tabular):
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         line = None
         with compression_utils.get_fileobj(dataset.file_name) as fh:
@@ -1135,7 +1135,7 @@ class VcfGz(BaseVcf, binary.Binary):
             return binascii.hexlify(last28) == b"1f8b08040000000000ff0600424302001b0003000000000000000000"
 
     def set_meta(
-        self, dataset: DatasetProtocol25, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         # Creates the index for the VCF file.
@@ -1299,7 +1299,7 @@ class Eland(Tabular):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1461,7 +1461,7 @@ class BaseCSV(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         column_types = []
         header_row = []
         data_row = []
@@ -1543,7 +1543,7 @@ class ConnectivityTable(Tabular):
         self.column_names = ["base_index", "base", "neighbor_left", "neighbor_right", "partner", "natural_numbering"]
         self.column_types = ["int", "str", "int", "int", "int", "int"]
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
 
         with open(dataset.file_name) as fh:
@@ -1678,7 +1678,7 @@ class MatrixMarket(TabularData):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1806,7 +1806,7 @@ class CMAP(TabularData):
 
     def set_meta(
         self,
-        dataset: DatasetProtocol25,
+        dataset: SetsMetadata,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 7,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 9b291b1d4db..ab367905d11 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -18,12 +18,11 @@ import yaml
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol17,
     DatasetProtocol21,
     DatasetProtocol23,
-    DatasetProtocol25,
     Displayable,
     HasCreatingJob,
+    SetsMetadata,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -144,7 +143,7 @@ class ExpressionJson(Json):
         name="json_type", default=None, desc="JavaScript or JSON type of expression", readonly=True, visible=True
     )
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """ """
         if dataset.has_data():
             json_type = "null"
@@ -254,7 +253,7 @@ class Ipynb(Json):
                 )
             return open(ofilename, mode="rb"), headers
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models in dataset.
         """
@@ -427,7 +426,7 @@ class Biom1(Json):
             pass
         return is_biom
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the BIOM file.
         """
@@ -528,7 +527,7 @@ class ImgtJson(Json):
             pass
         return is_imgt
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the imgt file.
         """
@@ -694,7 +693,7 @@ class Arff(Text):
                     return True
         return False
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         """
         Trying to count the comment lines and the number of columns included.
         A typical ARFF data block looks like this:
@@ -779,7 +778,7 @@ class SnpEffDb(Text):
             pass
         return snpeff_version
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         data_dir = dataset.extra_files_path
         # search data_dir/genome_version for files
@@ -872,7 +871,7 @@ class SnpSiftDbNSFP(Text):
         """
         return "<html><head><title>SnpSiftDbNSFP Composite Dataset</title></head></html>"
 
-    def regenerate_primary_file(self, dataset: DatasetProtocol17) -> None:
+    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -884,7 +883,7 @@ class SnpSiftDbNSFP(Text):
                 f.write("\n")
             f.write(annotations)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         try:
             efp = dataset.extra_files_path
             if os.path.exists(efp):
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index 2ecc9cfe8df..8711751cef2 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -9,7 +9,7 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     DatasetProtocol11,
     DatasetProtocol23,
-    DatasetProtocol25,
+    SetsMetadata,
 )
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -151,7 +151,7 @@ class Dzi(GenericXml):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: DatasetProtocol25, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         tree = util.parse_xml(dataset.file_name)
         root = tree.getroot()
         dataset.metadata.format = root.get("Format")

From be1dd55222be25bea0865b79f505ed8309f22844 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 20 Dec 2022 15:41:31 -0500
Subject: [PATCH 107/350] Combine select protocols as Peekable

---
 lib/galaxy/datatypes/_protocols.py            |  57 ++-----
 lib/galaxy/datatypes/annotation.py            |  13 +-
 lib/galaxy/datatypes/anvio.py                 |   7 +-
 lib/galaxy/datatypes/binary.py                | 161 +++++++++---------
 lib/galaxy/datatypes/blast.py                 |  13 +-
 .../datatypes/constructive_solid_geometry.py  |  21 ++-
 lib/galaxy/datatypes/data.py                  |  15 +-
 lib/galaxy/datatypes/flow.py                  |   9 +-
 lib/galaxy/datatypes/genetics.py              |  14 +-
 lib/galaxy/datatypes/gis.py                   |   7 +-
 lib/galaxy/datatypes/graph.py                 |   6 +-
 lib/galaxy/datatypes/images.py                |   6 +-
 lib/galaxy/datatypes/interval.py              |  10 +-
 lib/galaxy/datatypes/isa.py                   |   7 +-
 lib/galaxy/datatypes/microarrays.py           |   4 +-
 lib/galaxy/datatypes/molecules.py             |  37 ++--
 lib/galaxy/datatypes/mothur.py                |   4 +-
 lib/galaxy/datatypes/msa.py                   |  17 +-
 lib/galaxy/datatypes/neo4j.py                 |   7 +-
 lib/galaxy/datatypes/ngsindex.py              |   7 +-
 lib/galaxy/datatypes/phylip.py                |   4 +-
 lib/galaxy/datatypes/plant_tribes.py          |  11 +-
 lib/galaxy/datatypes/proteomics.py            |  31 ++--
 lib/galaxy/datatypes/qiime2.py                |   7 +-
 lib/galaxy/datatypes/sequence.py              |  18 +-
 lib/galaxy/datatypes/spaln.py                 |   7 +-
 lib/galaxy/datatypes/tabular.py               |  29 ++--
 lib/galaxy/datatypes/text.py                  |  31 ++--
 lib/galaxy/datatypes/tracks.py                |   7 +-
 lib/galaxy/datatypes/triples.py               |  16 +-
 lib/galaxy/datatypes/xml.py                   |  16 +-
 31 files changed, 272 insertions(+), 327 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 786e1a12cdf..0c912506053 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -120,10 +120,6 @@ class DatasetProtocol2(HasExt, HasHid, Protocol):
     ...
 
 
-class DatasetProtocol3(HasFileName, HasGetSize, Protocol):
-    ...
-
-
 class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
     ...
 
@@ -132,10 +128,6 @@ class DatasetProtocol6(HasExtraFilesPath, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol7(HasId, HasMetadata, Protocol):
-    ...
-
-
 class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
     ...
 
@@ -144,10 +136,6 @@ class DatasetProtocol11(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol)
     ...
 
 
-class DatasetProtocol14(HasId, HasMetadata, HasSetPeek, HasPeek, Protocol):
-    ...
-
-
 class DatasetProtocol15(HasDataset, HasHasData, HasMetadata, HasState, HasStates, Protocol):
     ...
 
@@ -156,43 +144,16 @@ class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileNam
     ...
 
 
-class DatasetProtocol18(HasFileName, HasId, HasMetadata, HasName, HasPeek, HasSetPeek, Protocol):
-    ...
-
-
 class DatasetProtocol19(HasDataset, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol):
     ...
 
 
-class DatasetProtocol20(HasDataset, HasFileName, HasMetadata, HasId, HasName, HasPeek, HasSetPeek, Protocol):
-    ...
-
-
-class DatasetProtocol21(HasFileName, HasGetSize, HasId, HasMetadata, HasName, HasPeek, HasSetPeek, Protocol):
-    ...
-
-
 class DatasetProtocol22(
     HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol
 ):
     ...
 
 
-class DatasetProtocol23(
-    HasBlurb,
-    HasDataset,
-    HasExtension,
-    HasExtraFilesPath,
-    HasFileName,
-    HasGetSize,
-    HasInfo,
-    HasMetadata,
-    HasPeek,
-    Protocol,
-):
-    ...
-
-
 class DatasetProtocol24(
     HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
 ):
@@ -231,3 +192,21 @@ class SetsMetadata(
     Protocol,
 ):
     ...
+
+
+class Peekable(
+    HasBlurb,
+    HasDataset,
+    HasExtension,
+    HasExtraFilesPath,
+    HasFileName,
+    HasGetSize,
+    HasId,
+    HasInfo,
+    HasMetadata,
+    HasName,
+    HasPeek,
+    HasSetPeek,
+    Protocol,
+):
+    ...
diff --git a/lib/galaxy/datatypes/annotation.py b/lib/galaxy/datatypes/annotation.py
index 14440afd540..8ca1d174214 100644
--- a/lib/galaxy/datatypes/annotation.py
+++ b/lib/galaxy/datatypes/annotation.py
@@ -1,10 +1,7 @@
 import logging
 import tarfile
 
-from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
-)
+from galaxy.datatypes._protocols import Peekable
 from galaxy.datatypes.binary import CompressedArchive
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -24,7 +21,7 @@ class SnapHmm(Text):
     file_ext = "snaphmm"
     edam_data = "data_1364"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "SNAP HMM model"
@@ -32,7 +29,7 @@ class SnapHmm(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -54,7 +51,7 @@ class Augustus(CompressedArchive):
     edam_data = "data_0950"
     compressed = True
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Augustus model"
             dataset.blurb = nice_size(dataset.get_size())
@@ -62,7 +59,7 @@ class Augustus(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 4f3841e57b7..5073a021092 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -9,8 +9,7 @@ from typing import Optional
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
@@ -67,7 +66,7 @@ class AnvioComposite(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Anvio database (multiple files)"
@@ -76,7 +75,7 @@ class AnvioComposite(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index e4de0f5ee03..eec046acd7e 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -38,11 +38,10 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol9,
     DatasetProtocol11,
     DatasetProtocol16,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
     HasFileName,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -116,7 +115,7 @@ class Binary(data.Data):
     def register_unsniffable_binary_ext(ext):
         """Deprecated method."""
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
@@ -137,7 +136,7 @@ class Ab1(Binary):
     edam_format = "format_3000"
     edam_data = "data_0924"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ab1 sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -145,7 +144,7 @@ class Ab1(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -227,7 +226,7 @@ class Cel(Binary):
         elif header_bytes.decode("utf8", errors="ignore").startswith("[CEL]"):
             dataset.metadata.version = "3"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.blurb = f"Cel version: {dataset.metadata.version}"
             dataset.peek = get_file_peek(dataset.file_name)
@@ -261,7 +260,7 @@ class CompressedArchive(Binary):
     compressed = True
     is_binary = "maybe"  # type: ignore[assignment]  # https://github.com/python/mypy/issues/8796
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed binary file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -269,7 +268,7 @@ class CompressedArchive(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -318,7 +317,7 @@ class Bref3(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith_bytes(self._magic)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bref3 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -326,7 +325,7 @@ class Bref3(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -378,7 +377,7 @@ class CompressedZipArchive(CompressedArchive):
 
     file_ext = "zip"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed zip file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -386,7 +385,7 @@ class CompressedZipArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -553,7 +552,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bam alignments file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -561,7 +560,7 @@ class BamNative(CompressedArchive, _BamOrSam):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -992,7 +991,7 @@ class CRAM(Binary):
             log.warning("%s, set_index_file Exception: %s", self, exc)
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CRAM binary alignment file"
             dataset.blurb = "binary data"
@@ -1129,7 +1128,7 @@ class H5(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary HDF5 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1137,7 +1136,7 @@ class H5(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1235,7 +1234,7 @@ class Loom(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary Loom file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1243,7 +1242,7 @@ class Loom(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1500,7 +1499,7 @@ class Anndata(H5):
             if dataset.metadata.shape is None:
                 dataset.metadata.shape = (int(dataset.metadata.obs_size), int(dataset.metadata.var_size))
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             tmp = dataset.metadata
 
@@ -1528,7 +1527,7 @@ class Anndata(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1573,7 +1572,7 @@ class Grib(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary GRIB file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1581,7 +1580,7 @@ class Grib(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1616,7 +1615,7 @@ class GmxBinary(Binary):
         # The first 4 bytes of any GROMACS binary file containing the magic number
         return file_prefix.magic_header(">1i") == self.magic_number
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary GROMACS {self.file_ext} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1624,7 +1623,7 @@ class GmxBinary(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1776,7 +1775,7 @@ class Biom2(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, util.unicodify(e))
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Biom2 (HDF5) file"]
             try:
@@ -1791,7 +1790,7 @@ class Biom2(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1836,7 +1835,7 @@ class Cool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1844,7 +1843,7 @@ class Cool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1896,7 +1895,7 @@ class MCool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Multi-resolution Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1904,7 +1903,7 @@ class MCool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2003,7 +2002,7 @@ class H5MLM(H5):
             log.warning("%s, get model configuration Except: %s", self, e)
             return ""
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             repr = self.get_repr(dataset.file_name)
             dataset.peek = repr[: self.max_peek_size]
@@ -2012,7 +2011,7 @@ class H5MLM(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2149,7 +2148,7 @@ class HexrdMaterials(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Material SpaceGroup Lattice"]
             if dataset.metadata.materials:
@@ -2174,7 +2173,7 @@ class Scf(Binary):
     edam_data = "data_0924"
     file_ext = "scf"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary scf sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2182,7 +2181,7 @@ class Scf(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2202,7 +2201,7 @@ class Sff(Binary):
         # about the format, see http://www.ncbi.nlm.nih.gov/Traces/trace.cgi?cmd=show&f=formats&m=doc&s=format
         return file_prefix.startswith_bytes(b".sff")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sff file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2210,7 +2209,7 @@ class Sff(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2239,7 +2238,7 @@ class BigWig(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.magic_header("I") == self._magic
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary UCSC {self._name} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2247,7 +2246,7 @@ class BigWig(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2280,14 +2279,14 @@ class TwoBit(Binary):
         magic = file_prefix.magic_header(">L")
         return magic == TWOBIT_MAGIC_NUMBER or magic == TWOBIT_MAGIC_NUMBER_SWAP
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary TwoBit format nucleotide file"
             dataset.blurb = nice_size(dataset.get_size())
         else:
             return super().set_peek(dataset)
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2382,7 +2381,7 @@ class SQlite(Binary):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SQLite Database"
             lines = ["SQLite Database"]
@@ -2398,7 +2397,7 @@ class SQlite(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2465,7 +2464,7 @@ class GeminiSQLite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Gemini SQLite Database, version %s" % (dataset.metadata.gemini_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2473,7 +2472,7 @@ class GeminiSQLite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2552,7 +2551,7 @@ class CuffDiffSQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CuffDiff SQLite Database, version %s" % (dataset.metadata.cuffdiff_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2560,7 +2559,7 @@ class CuffDiffSQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2882,7 +2881,7 @@ class IdpDB(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "IDPickerDB SQLite file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2890,7 +2889,7 @@ class IdpDB(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2981,7 +2980,7 @@ class NcbiTaxonomySQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "NCBI Taxonomy SQLite Database, version {} ({} taxons)".format(
                 getattr(dataset.metadata, "ncbitaxonomy_schema_version", "unknown"),
@@ -2992,7 +2991,7 @@ class NcbiTaxonomySQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3028,7 +3027,7 @@ class ExcelXls(Binary):
         """Returns the mime type of the datatype"""
         return "application/vnd.ms-excel"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Microsoft Excel XLS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -3036,7 +3035,7 @@ class ExcelXls(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3055,7 +3054,7 @@ class Sra(Binary):
         """
         return file_prefix.startswith_bytes(b"NCBI.sra")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sra file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3063,7 +3062,7 @@ class Sra(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3452,7 +3451,7 @@ class PostgresqlArchive(CompressedArchive):
                 return "postgresql/db/PG_VERSION" in temptar.getnames()
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"PostgreSQL Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "PostgreSQL version %s" % (dataset.metadata.version or "unknown")
@@ -3460,7 +3459,7 @@ class PostgresqlArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3506,7 +3505,7 @@ class Fast5Archive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"FAST5 Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "%s sequences" % (dataset.metadata.fast5_count or "unknown")
@@ -3514,7 +3513,7 @@ class Fast5Archive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3615,7 +3614,7 @@ class SearchGuiArchive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SearchGUI Archive, version %s" % (dataset.metadata.searchgui_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -3623,7 +3622,7 @@ class SearchGuiArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3638,7 +3637,7 @@ class NetCDF(Binary):
     edam_format = "format_3650"
     edam_data = "data_0943"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary netCDF file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3646,7 +3645,7 @@ class NetCDF(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3694,7 +3693,7 @@ class Dcd(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM/NAMD dcd file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3702,7 +3701,7 @@ class Dcd(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3746,7 +3745,7 @@ class Vel(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM velocity file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3754,7 +3753,7 @@ class Vel(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3843,7 +3842,7 @@ class ICM(Binary):
     file_ext = "icm"
     edam_data = "data_0950"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ICM (interpolated context model) file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3918,7 +3917,7 @@ class BafTar(CompressedArchive):
     def get_type(self) -> str:
         return "Bruker BAF directory archive"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = self.get_type()
             dataset.blurb = nice_size(dataset.get_size())
@@ -3926,7 +3925,7 @@ class BafTar(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4028,7 +4027,7 @@ class Pretext(Binary):
         # file contains binary data.
         return file_prefix.startswith_bytes(b"pstm")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary pretext file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4036,7 +4035,7 @@ class Pretext(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4072,7 +4071,7 @@ class JP2(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary JPEG 2000 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4080,7 +4079,7 @@ class JP2(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4128,7 +4127,7 @@ class Npz(CompressedArchive):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary Numpy npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4136,7 +4135,7 @@ class Npz(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4201,7 +4200,7 @@ class HexrdImagesNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Image npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4213,7 +4212,7 @@ class HexrdImagesNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4263,7 +4262,7 @@ class HexrdEtaOmeNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Eta-Ome npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4275,7 +4274,7 @@ class HexrdEtaOmeNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index 9782b1e3a16..9a7fb50695d 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -41,9 +41,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
+    Peekable,
 )
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -68,7 +67,7 @@ class BlastXml(GenericXml):
     edam_format = "format_3331"
     edam_data = "data_0857"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
@@ -193,7 +192,7 @@ class BlastXml(GenericXml):
 class _BlastDb(Data):
     """Base class for BLAST database datatype."""
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "BLAST database (multiple files)"
@@ -202,7 +201,7 @@ class _BlastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -370,7 +369,7 @@ class LastDb(Data):
     file_ext = "lastdb"
     composite_type = "basic"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "LAST database (multiple files)"
@@ -379,7 +378,7 @@ class LastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index 05ffdd61d17..9638bdbb027 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -15,9 +15,8 @@ from typing import (
 from galaxy import util
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -129,7 +128,7 @@ class Ply:
                             element_tuple = (items[1], int(items[2]))
                             dataset.metadata.other_elements.append(element_tuple)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = f"Faces: {str(dataset.metadata.face)}, Vertices: {str(dataset.metadata.vertex)}"
@@ -137,7 +136,7 @@ class Ply:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -463,7 +462,7 @@ class Vtk:
             blurb += str(dataset.metadata.dataset_type)
         return blurb or "VTK data"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = self.get_blurb(dataset)
@@ -471,7 +470,7 @@ class Vtk:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -572,7 +571,7 @@ class NeperTess(data.Text):
                     if i == 6:
                         dataset.metadata.cells = int(line)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=7)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -659,7 +658,7 @@ class NeperTesr(Binary):
                         dataset.metadata.cells = int(line)
                         break
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=9)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -705,7 +704,7 @@ class NeperPoints(data.Text):
             return None
         return dim
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         data.Text.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -728,7 +727,7 @@ class NeperPointsTabular(NeperPoints, Tabular):
             with open(dataset.file_name, errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         Tabular.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -784,7 +783,7 @@ class GmshMsh(Binary):
                         if len(fields) > 1:
                             dataset.metadata.format = "ASCII" if fields[1] == "0" else "binary"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=3)
             dataset.blurb = f"Gmsh verion: {str(dataset.metadata.version)} {str(dataset.metadata.format)}"
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 2d4c2fb9441..8a36191281d 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -27,15 +27,11 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol0,
     DatasetProtocol1,
     DatasetProtocol2,
-    DatasetProtocol3,
     DatasetProtocol5,
     DatasetProtocol6,
     DatasetProtocol9,
     DatasetProtocol11,
     DatasetProtocol16,
-    DatasetProtocol20,
-    DatasetProtocol21,
-    DatasetProtocol23,
     DatasetProtocol24,
     Displayable,
     HasClearAssociatedFiles,
@@ -45,6 +41,7 @@ from galaxy.datatypes._protocols import (
     HasInfo,
     HasMetadata,
     HasName,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.metadata import (
@@ -303,7 +300,7 @@ class Data(metaclass=DataMeta):
 
     max_optional_metadata_filesize = property(get_max_optional_metadata_filesize, set_max_optional_metadata_filesize)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -314,7 +311,7 @@ class Data(metaclass=DataMeta):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML table, used for displaying peek"""
         out = ['<table cellspacing="0" cellpadding="3">']
         try:
@@ -553,7 +550,7 @@ class Data(metaclass=DataMeta):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: DatasetProtocol20) -> str:
+    def display_as_markdown(self, dataset_instance: Peekable) -> str:
         """Prepare for embedding dataset into a basic Markdown document.
 
         This is a somewhat experimental interface and should not be implemented
@@ -988,7 +985,7 @@ class Text(Data):
         """
         dataset.metadata.data_lines = self.count_data_lines(dataset)
 
-    def estimate_file_lines(self, dataset: DatasetProtocol3) -> Optional[int]:
+    def estimate_file_lines(self, dataset: Peekable) -> Optional[int]:
         """
         Perform a rough estimate by extrapolating number of lines from a small read.
         """
@@ -1023,7 +1020,7 @@ class Text(Data):
                 return None
         return data_lines
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """
         Set the peek.  This method is used by various subclasses of Text.
         """
diff --git a/lib/galaxy/datatypes/flow.py b/lib/galaxy/datatypes/flow.py
index 23ad9c1364a..3f1dd83f65e 100644
--- a/lib/galaxy/datatypes/flow.py
+++ b/lib/galaxy/datatypes/flow.py
@@ -4,10 +4,7 @@ Flow analysis datatypes.
 
 import logging
 
-from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
-)
+from galaxy.datatypes._protocols import Peekable
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -24,7 +21,7 @@ class FCS(Binary):
 
     file_ext = "fcs"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary FCS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -32,7 +29,7 @@ class FCS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 6294827df36..8a8b22dafc8 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -31,11 +31,9 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
     DatasetProtocol11,
-    DatasetProtocol18,
-    DatasetProtocol21,
-    DatasetProtocol23,
     DatasetProtocol24,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -148,7 +146,7 @@ class GenomeGraphs(Tabular):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def make_html_table(self, dataset: DatasetProtocol18, **kwargs) -> str:
+    def make_html_table(self, dataset: Peekable, **kwargs) -> str:
         """
         Create HTML table, used for displaying peek
         """
@@ -243,7 +241,7 @@ class rgTabList(Tabular):
         super().__init__(**kwd)
         self.column_names = []
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -387,7 +385,7 @@ class SNPMatrix(Rgenetics):
 
     file_ext = "snpmatrix"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary RGenetics file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -770,7 +768,7 @@ class RexpBase(Html):
             p = []
         return "\n".join(p)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """
         expects a .pheno file in the extra_files_dir - ugh
         note that R is weird and does not include the row.name in
@@ -916,7 +914,7 @@ class RexpBase(Html):
         except Exception as exc:
             return f"Can't create html table {unicodify(exc)}"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """
         Returns formatted html of peek
         """
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index 62e04356517..d1839b4add2 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -3,8 +3,7 @@ GIS classes
 """
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
 )
 from galaxy.datatypes.binary import Binary
 
@@ -82,7 +81,7 @@ class Shapefile(Binary):
         rval.append("</ul></div></html>\n")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "Shapefile data"
@@ -91,7 +90,7 @@ class Shapefile(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index 105fc8f86da..1651d542adc 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -6,7 +6,7 @@ from typing import List
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol11,
-    DatasetProtocol23,
+    Peekable,
 )
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
@@ -31,7 +31,7 @@ class Xgmml(xml.GenericXml):
 
     file_ext = "xgmml"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -79,7 +79,7 @@ class Sif(tabular.Tabular):
 
     file_ext = "sif"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """
         Set the peek and blurb text
         """
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 06deb2e9252..b568377e13c 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -13,7 +13,7 @@ import tifffile
 from galaxy.datatypes._protocols import (
     DatasetProtocol1,
     DatasetProtocol6,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -55,7 +55,7 @@ class Image(data.Data):
         super().__init__(**kwd)
         self.image_formats = [self.file_ext.upper()]
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Image in {dataset.extension} format"
             dataset.blurb = nice_size(dataset.get_size())
@@ -492,7 +492,7 @@ class Star(data.Text):
 
     file_ext = "star"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 4608154ca09..c60342091f3 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -26,11 +26,11 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol11,
     DatasetProtocol15,
     DatasetProtocol19,
-    DatasetProtocol21,
     DatasetProtocol22,
     DatasetProtocol24,
     HasId,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import DatatypeValidation
@@ -309,7 +309,7 @@ class Interval(Tabular):
                     fh.write("%s\n" % "\t".join(tmp))
             return compression_utils.get_fileobj(fh.name, mode="rb")
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset,
@@ -880,7 +880,7 @@ class Gff(Tabular, _RemoteCallMixin):
                             pass
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -1389,7 +1389,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
@@ -1477,7 +1477,7 @@ class CustomTrack(Tabular):
     def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index b57fff29b49..af6785026f3 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -28,10 +28,9 @@ from markupsafe import escape
 from galaxy import util
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
     HasExtraFilesPath,
+    Peekable,
 )
 from galaxy.datatypes.data import Data
 from galaxy.util.compression_utils import CompressedFile
@@ -163,7 +162,7 @@ class _Isa(Data):
     # Set peek {{{2
     ################################################################
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text. Get first lines of the main file and set it as the peek."""
 
         main_file = self._get_main_file(dataset)
@@ -189,7 +188,7 @@ class _Isa(Data):
     # Display peek {{{2
     ################################################################
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create the HTML table used for displaying peek, from the peek text found by set_peek() method."""
 
         out = ['<table cellspacing="0" cellpadding="3">']
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index 96e038eba18..f89881bb23c 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -2,7 +2,7 @@ import logging
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Cel  # noqa: F401
@@ -80,7 +80,7 @@ class GenericMicroarrayFile(data.Text):
         name="block_type", default=0, desc="Type of block", readonly=True, visible=True, optional=True, no_value=0
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.block_count == 1:
                 dataset.blurb = f"{dataset.metadata.file_type} {dataset.metadata.version_number}: Format {dataset.metadata.file_format}, 1 block, {dataset.metadata.number_of_optional_header_records} headers and {dataset.metadata.number_of_data_columns} columns"
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index 124e082069d..258e81a4a1b 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -9,8 +9,7 @@ from typing import (
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -73,7 +72,7 @@ class GenericMolFile(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -532,7 +531,7 @@ class OBFS(Binary):
         self.add_composite_file("molecule.mol2", optional=True, is_binary=False, description="Molecule File")
         self.add_composite_file("molecule.cml", optional=True, is_binary=False, description="Molecule File")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "OpenBabel Fastsearch Index"
@@ -541,7 +540,7 @@ class OBFS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -582,7 +581,7 @@ class PHAR(GenericMolFile):
 
     file_ext = "phar"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "pharmacophore"
@@ -651,7 +650,7 @@ class PDB(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -704,7 +703,7 @@ class PDBQT(GenericMolFile):
         else:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             root_numbers = count_special_lines("^ROOT", dataset.file_name)
             branch_numbers = count_special_lines("^BRANCH", dataset.file_name)
@@ -808,7 +807,7 @@ class PQR(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -926,7 +925,7 @@ class Cell(GenericMolFile):
                 dataset.metadata.is_periodic = bool(pbc.any())
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1093,7 +1092,7 @@ class CIF(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1291,7 +1290,7 @@ class XYZ(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1446,7 +1445,7 @@ class ExtendedXYZ(XYZ):
             blocks.append({"number_of_atoms": n_atoms, "comment": comment, "atom_data": atoms})
         return blocks
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         super().set_peek(dataset)
         dataset.blurb = "Extended " + dataset.blurb
 
@@ -1454,7 +1453,7 @@ class ExtendedXYZ(XYZ):
 class grd(Text):
     file_ext = "grd"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "grids for docking"
@@ -1466,7 +1465,7 @@ class grd(Text):
 class grdtgz(Binary):
     file_ext = "grd.tgz"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
             dataset.blurb = "compressed grids for docking"
@@ -1504,7 +1503,7 @@ class InChI(Tabular):
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1569,7 +1568,7 @@ class SMILES(Tabular):
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1605,7 +1604,7 @@ class CML(GenericXml):
         """
         dataset.metadata.number_of_molecules = count_special_lines(r"^\s*<molecule", dataset.file_name)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1763,7 +1762,7 @@ class GRO(GenericMolFile):
                 return False
         return True
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             atom_number = int(dataset.peek.split("\n")[1])
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index 814eb5dced6..5605dea13e4 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -9,8 +9,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol18,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import Text
@@ -1073,7 +1073,7 @@ class SffFlow(Tabular):
         except Exception as e:
             log.warning(f"SffFlow set_meta {e}")
 
-    def make_html_table(self, dataset: DatasetProtocol18, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_table(self, dataset: Peekable, skipchars: Optional[List] = None, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 6a51192df29..2a56e9b8d76 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -9,8 +9,7 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -58,7 +57,7 @@ class InfernalCM(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_of_models == 1:
@@ -98,7 +97,7 @@ class Hmmer(Text):
     edam_data = "data_1364"
     edam_format = "format_1370"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "HMMER Database"
@@ -106,7 +105,7 @@ class Hmmer(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -141,7 +140,7 @@ class HmmerPress(Binary):
     file_ext = "hmmpress"
     composite_type = "basic"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "HMMER Binary database"
@@ -150,7 +149,7 @@ class HmmerPress(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -185,7 +184,7 @@ class Stockholm_1_0(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -276,7 +275,7 @@ class MauveXmfa(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index c4696deb5dc..3b681ac9ae8 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -5,8 +5,7 @@ import logging
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
@@ -46,7 +45,7 @@ class Neo4j(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Neo4j database (multiple files)"
@@ -55,7 +54,7 @@ class Neo4j(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index faebf6d1948..8d2a83b3ce0 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -6,8 +6,7 @@ import os
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from .metadata import MetadataElement
@@ -63,7 +62,7 @@ class BowtieIndex(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Bowtie index file ({dataset.metadata.sequence_space})"
             dataset.blurb = f"{dataset.metadata.sequence_space} space"
@@ -71,7 +70,7 @@ class BowtieIndex(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index d160ca93a0b..e7da80b3314 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -11,7 +11,7 @@ from typing import TYPE_CHECKING
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -51,7 +51,7 @@ class Phylip(Text):
         except Exception:
             raise Exception("Header does not correspond to PHYLIP header.")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index 9045e08f4fe..cf93e7b446d 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -2,8 +2,7 @@ import logging
 import re
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -26,13 +25,13 @@ log = logging.getLogger(__name__)
 class Smat(Text):
     file_ext = "smat"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"ESTScan scores matrices ({nice_size(dataset.get_size())})"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "ESTScan scores matrices"
@@ -98,7 +97,7 @@ class PlantTribesKsComponents(Tabular):
         no_value=0,
     )
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -126,7 +125,7 @@ class PlantTribesKsComponents(Tabular):
         if len(significant_components) > 0:
             dataset.metadata.number_comp = max(significant_components)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_comp == 1:
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index ed6706ff203..947442ca595 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -12,8 +12,7 @@ from typing import (
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -105,7 +104,7 @@ class MzTab(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -156,7 +155,7 @@ class MzTab2(MzTab):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -201,7 +200,7 @@ class Kroenik(Tabular):
             "Modifications",
         ]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -240,7 +239,7 @@ class PepList(Tabular):
         super().__init__(**kwd)
         self.column_names = ["m/z", "rt(min)", "snr", "charge", "intensity"]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -277,7 +276,7 @@ class PSMS(Tabular):
         super().__init__(**kwd)
         self.column_names = ["PSMId", "score", "q-value", "posterior_error_prob", "peptide", "proteinIds"]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -337,7 +336,7 @@ class PepXmlReport(Tabular):
             "Interprophet Probability",
         ]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -378,7 +377,7 @@ class ProtXmlReport(Tabular):
             "Is Evidence?",
         ]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -676,7 +675,7 @@ class ProteomicsXml(GenericXml):
         pattern = r"<(\w*:)?%s" % self.root
         return re.search(pattern, line) is not None
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -845,7 +844,7 @@ class Mgf(Text):
     edam_format = "format_3651"
     file_ext = "mgf"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -875,7 +874,7 @@ class MascotDat(Text):
     edam_format = "format_3713"
     file_ext = "mascotdat"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -919,7 +918,7 @@ class ThermoRAW(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Thermo Finnigan RAW file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -927,7 +926,7 @@ class ThermoRAW(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -961,7 +960,7 @@ class SPLibNoIndex(Text):
 
     file_ext = "splib_noindex"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1003,7 +1002,7 @@ class SPLib(Msp):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index 2b162d688ee..20531cd00ee 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -12,9 +12,8 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol21,
-    DatasetProtocol23,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
@@ -43,7 +42,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.metadata.semantic_type_simple = _strip_properties(dataset.metadata.semantic_type)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if dataset.metadata.semantic_type == "Visualization":
             dataset.blurb = "QIIME 2 Visualization"
         else:
@@ -51,7 +50,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.peek = "\n".join(map(": ".join, self._peek(dataset)))
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         def make_row(item):
             return "<tr><th>%s</th><td>%s</td></td>" % tuple(html.escape(x) for x in item)
 
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index 1945b76726d..c312d31cda7 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -26,11 +26,9 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol9,
-    DatasetProtocol18,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
@@ -73,7 +71,7 @@ class SequenceSplitLocations(data.Text):
 
     file_ext = "fqtoc"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             try:
                 parsed_data = json.load(open(dataset.file_name))
@@ -130,7 +128,7 @@ class Sequence(data.Text):
             dataset.metadata.data_lines = data_lines
             dataset.metadata.sequences = sequences
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -668,7 +666,7 @@ class Fastg(Sequence):
             return
         return Sequence.set_meta(self, dataset, overwrite=overwrite, **kwd)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -1051,7 +1049,7 @@ class Maf(Alignment):
         indexes.write(open(index_file.file_name, "wb"))
         dataset.metadata.maf_index = index_file
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1065,11 +1063,11 @@ class Maf(Alignment):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset)
 
-    def make_html_table(self, dataset: DatasetProtocol18, skipchars: Optional[List] = None) -> str:
+    def make_html_table(self, dataset: Peekable, skipchars: Optional[List] = None) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
@@ -1277,7 +1275,7 @@ class RNADotPlotMatrix(data.Data):
     edam_format = "format_3466"
     file_ext = "rna_eps"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "RNA Dot Plot format (Postscript derivative)"
             dataset.blurb = nice_size(dataset.get_size())
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index b459808e7b7..58aa3b4be73 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -13,9 +13,8 @@ from typing import (
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import Data
@@ -100,7 +99,7 @@ class _SpalnDb(Data):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "spaln database (multiple files)"
@@ -109,7 +108,7 @@ class _SpalnDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 2a10c3e408a..67237cec12e 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,18 +30,13 @@ from galaxy.datatypes import (
     metadata,
 )
 from galaxy.datatypes._protocols import (
-    DatasetProtocol7,
     DatasetProtocol9,
     DatasetProtocol11,
-    DatasetProtocol14,
     DatasetProtocol15,
-    DatasetProtocol18,
-    DatasetProtocol20,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
     HasFileName,
     HasMetadata,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -133,7 +128,7 @@ class TabularData(Text):
     def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         kwd.setdefault("line_wrap", False)
         super().set_peek(dataset, **kwd)
         if dataset.metadata.comment_lines:
@@ -233,7 +228,7 @@ class TabularData(Text):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: DatasetProtocol20) -> str:
+    def display_as_markdown(self, dataset_instance: Peekable) -> str:
         with open(dataset_instance.file_name) as f:
             contents = f.read(data.DEFAULT_MAX_PEEK_SIZE)
         markdown = self.make_html_table(dataset_instance, peek=contents)
@@ -241,7 +236,7 @@ class TabularData(Text):
             markdown += indicate_data_truncated()
         return pre_formatted_contents(markdown)
 
-    def make_html_table(self, dataset: DatasetProtocol18, **kwargs) -> str:
+    def make_html_table(self, dataset: Peekable, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         try:
             out = ['<table cellspacing="0" cellpadding="3">']
@@ -254,7 +249,7 @@ class TabularData(Text):
 
     def make_html_peek_header(
         self,
-        dataset: DatasetProtocol7,
+        dataset: Peekable,
         skipchars: Optional[List] = None,
         column_names: Optional[List] = None,
         column_number_format: str = "%s",
@@ -308,7 +303,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek header: {util.unicodify(exc)}")
         return "".join(out)
 
-    def make_html_peek_rows(self, dataset: DatasetProtocol14, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_peek_rows(self, dataset: Peekable, skipchars: Optional[List] = None, **kwargs) -> str:
         if skipchars is None:
             skipchars = []
         out = []
@@ -345,7 +340,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek rows: {util.unicodify(exc)}")
         return "".join(out)
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formatted html of peek"""
         return self.make_html_table(dataset)
 
@@ -641,7 +636,7 @@ class Taxonomy(Tabular):
             "Subspecies",
         ]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -732,7 +727,7 @@ class Sam(Tabular, _BamOrSam):
             "OPT",
         ]
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -948,7 +943,7 @@ class Pileup(Tabular):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset, column_parameter_alias={"chromCol": "Chrom", "startCol": "Start", "baseCol": "Base"}
@@ -1050,7 +1045,7 @@ class BaseVcf(Tabular):
         headers = get_headers(fname_or_file_prefix, "\n", count=1)
         return headers[0][0].startswith("##fileformat=VCF")
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -1238,7 +1233,7 @@ class Eland(Tabular):
         ]
 
     def make_html_table(
-        self, dataset: DatasetProtocol18, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
+        self, dataset: Peekable, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
     ) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index ab367905d11..08278c42bf0 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -18,10 +18,9 @@ import yaml
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
     Displayable,
     HasCreatingJob,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -55,7 +54,7 @@ class Html(Text):
     edam_format = "format_2331"
     file_ext = "html"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "HTML file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -91,7 +90,7 @@ class Json(Text):
     edam_format = "format_3464"
     file_ext = "json"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "JavaScript Object Notation (JSON)"
@@ -128,7 +127,7 @@ class Json(Text):
                 return start.startswith("[") or start.startswith("{")
             return False
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -170,7 +169,7 @@ class ExpressionJson(Json):
 class Ipynb(Json):
     file_ext = "ipynb"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Jupyter Notebook"
@@ -389,7 +388,7 @@ class Biom1(Json):
         no_value=[],
     )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "Biological Observation Matrix v1"
@@ -488,7 +487,7 @@ class ImgtJson(Json):
 
     MetadataElement(name="taxon_names", default=[], desc="taxonID: names", readonly=True, visible=True, no_value=[])
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "IMGT Library"
@@ -554,7 +553,7 @@ class GeoJson(Json):
 
     file_ext = "geojson"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "GeoJSON"
@@ -615,7 +614,7 @@ class Obo(Text):
     edam_format = "format_2549"
     file_ext = "obo"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Open Biomedical Ontology (OBO)"
@@ -657,7 +656,7 @@ class Arff(Text):
     )
     MetadataElement(name="columns", default=0, desc="Number of columns", readonly=True, visible=True, no_value=0)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Attribute-Relation File Format (ARFF)"
@@ -909,7 +908,7 @@ class SnpSiftDbNSFP(Text):
                 unicodify(e),
             )
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"{dataset.metadata.reference_name} :  {','.join(dataset.metadata.annotation)}"
             dataset.blurb = f"{dataset.metadata.reference_name}"
@@ -1152,7 +1151,7 @@ class BCSLts(Json):
             is_bcsl_ts = self._looks_like_bcsl_ts(file_prefix)
         return is_bcsl_ts
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = "States: {}\nTransitions: {}\nUnique agents: {}\nInitial state: {}"
             ts = json.load(open(dataset.file_name, "r"))
@@ -1186,7 +1185,7 @@ class StormSample(Text):
         keywords = ["Storm-pars", "Result (initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Storm-pars sample results."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1211,7 +1210,7 @@ class StormCheck(Text):
         keywords = ["Storm ", "Result (for initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
@@ -1239,7 +1238,7 @@ class CTLresult(Text):
         keywords = ["Result:", "Number of satisfying states:"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index bdab7cb638a..0b15182c456 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -5,8 +5,7 @@ import logging
 
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol21,
-    DatasetProtocol23,
+    Peekable,
 )
 from galaxy.datatypes.text import Html
 from . import binary
@@ -48,14 +47,14 @@ class UCSCTrackHub(Html):
         rval.append("</ul></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Track Hub structure: Visualization in UCSC Track Hub"
         else:
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: DatasetProtocol21) -> str:
+    def display_peek(self, dataset: Peekable) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/triples.py b/lib/galaxy/datatypes/triples.py
index 1a143676730..43070f5cac7 100644
--- a/lib/galaxy/datatypes/triples.py
+++ b/lib/galaxy/datatypes/triples.py
@@ -4,7 +4,7 @@ Triple format classes
 import logging
 import re
 
-from galaxy.datatypes._protocols import DatasetProtocol23
+from galaxy.datatypes._protocols import Peekable
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -37,7 +37,7 @@ class Triples(data.Data):
         """
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -62,7 +62,7 @@ class NTriples(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -86,7 +86,7 @@ class N3(data.Text, Triples):
         """
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -114,7 +114,7 @@ class Turtle(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -143,7 +143,7 @@ class Rdf(xml.GenericXml, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -169,7 +169,7 @@ class Jsonld(text.Json, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -193,7 +193,7 @@ class HDT(binary.Binary, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index 8711751cef2..455a8a108b1 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -8,7 +8,7 @@ from typing import List
 from galaxy import util
 from galaxy.datatypes._protocols import (
     DatasetProtocol11,
-    DatasetProtocol23,
+    Peekable,
     SetsMetadata,
 )
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
@@ -38,7 +38,7 @@ class GenericXml(data.Text):
     edam_format = "format_2332"
     file_ext = "xml"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -91,7 +91,7 @@ class MEMEXml(GenericXml):
 
     file_ext = "memexml"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -107,7 +107,7 @@ class CisML(GenericXml):
 
     file_ext = "cisml"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -168,7 +168,7 @@ class Dzi(GenericXml):
                 dataset.metadata.width = elem.get("Width")
                 dataset.metadata.height = elem.get("Height")
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Deep Zoom Image"
@@ -201,7 +201,7 @@ class Phyloxml(GenericXml):
     edam_format = "format_3159"
     file_ext = "phyloxml"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -236,7 +236,7 @@ class Owl(GenericXml):
     edam_format = "format_3262"
     file_ext = "owl"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Web Ontology Language OWL"
@@ -261,7 +261,7 @@ class Sbml(GenericXml):
     edam_data = "data_2024"
     edam_format = "format_2585"
 
-    def set_peek(self, dataset: DatasetProtocol23, **kwd) -> None:
+    def set_peek(self, dataset: Peekable, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "System Biology Markup Language SBML"

From 893f87622a5b32b166872bd7f4aa25b32bc713d7 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Tue, 20 Dec 2022 16:54:24 -0500
Subject: [PATCH 108/350] Make ProvidesDataSource protocol

---
 lib/galaxy/datatypes/_protocols.py |  9 ++++---
 lib/galaxy/datatypes/binary.py     | 26 +++++++++----------
 lib/galaxy/datatypes/data.py       | 16 ++++++------
 lib/galaxy/datatypes/genetics.py   |  4 +--
 lib/galaxy/datatypes/graph.py      |  6 ++---
 lib/galaxy/datatypes/interval.py   | 28 ++++++++++-----------
 lib/galaxy/datatypes/tabular.py    | 40 +++++++++++++++---------------
 lib/galaxy/datatypes/xml.py        |  4 +--
 8 files changed, 67 insertions(+), 66 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 0c912506053..5f905ebbcc9 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -132,10 +132,6 @@ class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol11(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
-    ...
-
-
 class DatasetProtocol15(HasDataset, HasHasData, HasMetadata, HasState, HasStates, Protocol):
     ...
 
@@ -210,3 +206,8 @@ class Peekable(
     Protocol,
 ):
     ...
+
+
+class ProvidesDataSource(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
+    # passed to the DatasetDataProvider constructor
+    ...
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index eec046acd7e..d4a4bceedaf 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -36,12 +36,12 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
-    DatasetProtocol11,
     DatasetProtocol16,
     Displayable,
     HasFileName,
     HasMetadata,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -807,25 +807,25 @@ class Bam(BamNative):
     # TODO:?? seems like there should be an easier way to do/inherit this - metadata.comment_char?
     # TODO: incorporate samtools options to control output: regions first, then flags, etc.
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> FilteredLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return FilteredLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return ColumnarDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return DictDataProvider(samtools_source, **settings)
@@ -843,20 +843,20 @@ class Bam(BamNative):
     #    return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
         # in this case we can use an option of samtools view to provide just what we need (w/o regex)
         samtools_source = SamtoolsDataProvider(dataset, "-H")
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", DictDataProvider.settings)
-    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         settings["indeces"] = [0, 9, 10]
         settings["column_types"] = ["str", "str", "str"]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", ColumnarDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
         # GenomicRegionDataProvider currently requires a dataset as source - may not be necc.
         # TODO:?? consider (at least) the possible use of a kwarg: metadata_source (def. to source.dataset),
         #   or remove altogether...
@@ -870,14 +870,14 @@ class Bam(BamNative):
         return self.column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", DictDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         settings["indeces"] = [2, 3, 3]
         settings["column_types"] = ["str", "int", "int"]
         settings["column_names"] = ["chrom", "start", "end"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("samtools")
-    def samtools_dataprovider(self, dataset: DatasetProtocol11, **settings) -> SamtoolsDataProvider:
+    def samtools_dataprovider(self, dataset: ProvidesDataSource, **settings) -> SamtoolsDataProvider:
         """Generic samtools interface - all options available through settings."""
         dataset_source = DatasetDataProvider(dataset)
         return SamtoolsDataProvider(dataset_source, **settings)
@@ -2404,17 +2404,17 @@ class SQlite(Binary):
             return f"SQLite Database ({nice_size(dataset.get_size())})"
 
     @dataproviders.decorators.dataprovider_factory("sqlite", SQliteDataProvider.settings)
-    def sqlite_dataprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataProvider:
+    def sqlite_dataprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-table", SQliteDataTableProvider.settings)
-    def sqlite_datatableprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataTableProvider:
+    def sqlite_datatableprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataTableProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataTableProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-dict", SQliteDataDictProvider.settings)
-    def sqlite_datadictprovider(self, dataset: DatasetProtocol11, **settings) -> SQliteDataDictProvider:
+    def sqlite_datadictprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataDictProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataDictProvider(dataset_source, **settings)
 
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 8a36191281d..5986e47999f 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -30,7 +30,6 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol5,
     DatasetProtocol6,
     DatasetProtocol9,
-    DatasetProtocol11,
     DatasetProtocol16,
     DatasetProtocol24,
     Displayable,
@@ -42,6 +41,7 @@ from galaxy.datatypes._protocols import (
     HasMetadata,
     HasName,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.metadata import (
@@ -719,7 +719,7 @@ class Data(metaclass=DataMeta):
         except Exception:
             return "unknown"
 
-    def as_display_type(self, dataset: DatasetProtocol11, type: str, **kwd) -> Union[FileObjType, str]:
+    def as_display_type(self, dataset: ProvidesDataSource, type: str, **kwd) -> Union[FileObjType, str]:
         """Returns modified file contents for a particular display type"""
         try:
             if type in self.get_display_types():
@@ -912,7 +912,7 @@ class Data(metaclass=DataMeta):
         """
         return data_format in self.dataproviders
 
-    def dataprovider(self, dataset: DatasetProtocol11, data_format: str, **settings):
+    def dataprovider(self, dataset: ProvidesDataSource, data_format: str, **settings):
         """
         Base dataprovider factory for all datatypes that returns the proper provider
         for the given `data_format` or raises a `NoProviderAvailable`.
@@ -925,18 +925,18 @@ class Data(metaclass=DataMeta):
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
-    def base_dataprovider(self, dataset: DatasetProtocol11, **settings) -> p_dataproviders.base.DataProvider:
+    def base_dataprovider(self, dataset: ProvidesDataSource, **settings) -> p_dataproviders.base.DataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.base.DataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk", p_dataproviders.chunk.ChunkDataProvider.settings)
-    def chunk_dataprovider(self, dataset: DatasetProtocol11, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
+    def chunk_dataprovider(self, dataset: ProvidesDataSource, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.ChunkDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk64", p_dataproviders.chunk.Base64ChunkDataProvider.settings)
     def chunk64_dataprovider(
-        self, dataset: DatasetProtocol11, **settings
+        self, dataset: ProvidesDataSource, **settings
     ) -> p_dataproviders.chunk.Base64ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.Base64ChunkDataProvider(dataset_source, **settings)
@@ -1134,7 +1134,7 @@ class Text(Data):
     # ------------- Dataproviders
     @p_dataproviders.decorators.dataprovider_factory("line", p_dataproviders.line.FilteredLineDataProvider.settings)
     def line_dataprovider(
-        self, dataset: DatasetProtocol11, **settings
+        self, dataset: ProvidesDataSource, **settings
     ) -> p_dataproviders.line.FilteredLineDataProvider:
         """
         Returns an iterator over the dataset's lines (that have been stripped)
@@ -1145,7 +1145,7 @@ class Text(Data):
 
     @p_dataproviders.decorators.dataprovider_factory("regex-line", p_dataproviders.line.RegexLineDataProvider.settings)
     def regex_line_dataprovider(
-        self, dataset: DatasetProtocol11, **settings
+        self, dataset: ProvidesDataSource, **settings
     ) -> p_dataproviders.line.RegexLineDataProvider:
         """
         Returns an iterator over the dataset's lines
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 8a8b22dafc8..e54a87f1bea 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -30,10 +30,10 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
-    DatasetProtocol11,
     DatasetProtocol24,
     HasMetadata,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -88,7 +88,7 @@ class GenomeGraphs(Tabular):
         t[0] = "string"
         dataset.metadata.column_types = t
 
-    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
         """
         Returns file
         """
diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index 1651d542adc..37c5763e767 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -5,8 +5,8 @@ import logging
 from typing import List
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol11,
     Peekable,
+    ProvidesDataSource,
 )
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
@@ -61,7 +61,7 @@ class Xgmml(xml.GenericXml):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", XMLDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: DatasetProtocol11, **settings) -> "XGMMLGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: ProvidesDataSource, **settings) -> "XGMMLGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return XGMMLGraphDataProvider(dataset_source, **settings)
 
@@ -101,7 +101,7 @@ class Sif(tabular.Tabular):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", ColumnarDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: DatasetProtocol11, **settings) -> "SIFGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: ProvidesDataSource, **settings) -> "SIFGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return SIFGraphDataProvider(dataset_source, **settings)
 
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index c60342091f3..97af9da7f8b 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -23,7 +23,6 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol9,
-    DatasetProtocol11,
     DatasetProtocol15,
     DatasetProtocol19,
     DatasetProtocol22,
@@ -31,6 +30,7 @@ from galaxy.datatypes._protocols import (
     HasId,
     HasMetadata,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.data import DatatypeValidation
@@ -275,7 +275,7 @@ class Interval(Tabular):
             log.exception("Exception caught attempting to generate viewport for dataset '%d'", dataset.id)
         return (None, None, None)
 
-    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data"""
         with tempfile.NamedTemporaryFile(delete=False, mode="w") as fh:
             c, s, e, t, n = (
@@ -411,20 +411,20 @@ class Interval(Tabular):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: DatasetProtocol11, **settings) -> IntervalDataProvider:
+    def interval_dataprovider(self, dataset: ProvidesDataSource, **settings) -> IntervalDataProvider:
         return IntervalDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> IntervalDataProvider:
+    def interval_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> IntervalDataProvider:
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -437,7 +437,7 @@ class BedGraph(Interval):
     track_type = "LineTrack"
     data_sources = {"data": "bigwig", "index": "bigwig"}
 
-    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
         """
         Returns file contents as is with no modifications.
         TODO: this is a functional stub and will need to be enhanced moving forward to provide additional support for bedgraph.
@@ -526,7 +526,7 @@ class Bed(Interval):
                         break
             Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data. If bed 6+, treat as interval."""
         for line in open(dataset.file_name):
             line = line.strip()
@@ -1040,20 +1040,20 @@ class Gff(Tabular, _RemoteCallMixin):
     # ------------- Dataproviders
     # redefine bc super is Tabular
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 3, 4, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: DatasetProtocol11, **settings):
+    def interval_dataprovider(self, dataset: ProvidesDataSource, **settings):
         return IntervalDataProvider(dataset, 0, 3, 4, 6, 2, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: DatasetProtocol11, **settings):
+    def interval_dict_dataprovider(self, dataset: ProvidesDataSource, **settings):
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -1451,12 +1451,12 @@ class Wiggle(Tabular, _RemoteCallMixin):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("wiggle", WiggleDataProvider.settings)
-    def wiggle_dataprovider(self, dataset: DatasetProtocol11, **settings) -> WiggleDataProvider:
+    def wiggle_dataprovider(self, dataset: ProvidesDataSource, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return WiggleDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("wiggle-dict", WiggleDataProvider.settings)
-    def wiggle_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> WiggleDataProvider:
+    def wiggle_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         settings["named_columns"] = True
         return WiggleDataProvider(dataset_source, **settings)
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 67237cec12e..22fe0a14a76 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -31,12 +31,12 @@ from galaxy.datatypes import (
 )
 from galaxy.datatypes._protocols import (
     DatasetProtocol9,
-    DatasetProtocol11,
     DatasetProtocol15,
     Displayable,
     HasFileName,
     HasMetadata,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -376,27 +376,27 @@ class TabularData(Text):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return ColumnarDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetColumnarDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetColumnarDataProvider(dataset, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return DictDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetDictDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetDictDataProvider(dataset, deliminator=delimiter, **settings)
@@ -585,7 +585,7 @@ class Tabular(TabularData):
     def as_gbrowse_display_file(self, dataset: HasFileName, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
-    def as_ucsc_display_file(self, dataset: DatasetProtocol11, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
 
@@ -867,55 +867,55 @@ class Sam(Tabular, _BamOrSam):
     # sam does not use '#' to indicate comments/headers - we need to strip out those headers from the std. providers
     # TODO:?? seems like there should be an easier way to do this - metadata.comment_char?
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> FilteredLineDataProvider:
         settings["comment_char"] = "@"
         return super().line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
         settings["comment_char"] = "@"
         return super().regex_line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         settings["comment_char"] = "@"
         return super().dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetDictDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: DatasetProtocol11, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         headers_source = RegexLineDataProvider(dataset_source, regex_list=["^@"])
         return RegexLineDataProvider(headers_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", dict_dataprovider.settings)
-    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol11, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
         # provided as an example of a specified column dict (w/o metadata)
         settings["indeces"] = [0, 9, 10]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, True, **settings)
 
@@ -996,11 +996,11 @@ class Pileup(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1085,11 +1085,11 @@ class BaseVcf(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 1, 1, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol11, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index 455a8a108b1..73c4e3e3cfc 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -7,8 +7,8 @@ from typing import List
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    DatasetProtocol11,
     Peekable,
+    ProvidesDataSource,
     SetsMetadata,
 )
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
@@ -80,7 +80,7 @@ class GenericXml(data.Text):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("xml", XMLDataProvider.settings)
-    def xml_dataprovider(self, dataset: DatasetProtocol11, **settings) -> XMLDataProvider:
+    def xml_dataprovider(self, dataset: ProvidesDataSource, **settings) -> XMLDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return XMLDataProvider(dataset_source, **settings)
 

From 04ebdceb62704efb35917902ea53e3bbd6d8211a Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 10:42:57 -0500
Subject: [PATCH 109/350] Combine select protocols as ProvidesDisplayLinks

---
 lib/galaxy/datatypes/_protocols.py | 26 ++++++--------------------
 lib/galaxy/datatypes/data.py       |  4 ++--
 lib/galaxy/datatypes/genetics.py   |  4 ++--
 lib/galaxy/datatypes/interval.py   | 29 +++++++++++++----------------
 lib/galaxy/datatypes/tabular.py    |  4 ++--
 5 files changed, 25 insertions(+), 42 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 5f905ebbcc9..b6df215751c 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -132,30 +132,10 @@ class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol15(HasDataset, HasHasData, HasMetadata, HasState, HasStates, Protocol):
-    ...
-
-
 class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol19(HasDataset, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol):
-    ...
-
-
-class DatasetProtocol22(
-    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasState, HasStates, Protocol
-):
-    ...
-
-
-class DatasetProtocol24(
-    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
-):
-    ...
-
-
 class Displayable(
     HasCreatingJob,
     HasDataset,
@@ -211,3 +191,9 @@ class Peekable(
 class ProvidesDataSource(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
     # passed to the DatasetDataProvider constructor
     ...
+
+
+class ProvidesDisplayLinks(
+    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
+):
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 5986e47999f..cee77b4b83f 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -31,7 +31,6 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
     DatasetProtocol16,
-    DatasetProtocol24,
     Displayable,
     HasClearAssociatedFiles,
     HasCreatingJob,
@@ -42,6 +41,7 @@ from galaxy.datatypes._protocols import (
     HasName,
     Peekable,
     ProvidesDataSource,
+    ProvidesDisplayLinks,
     SetsMetadata,
 )
 from galaxy.datatypes.metadata import (
@@ -734,7 +734,7 @@ class Data(metaclass=DataMeta):
         return f"This display type ({type}) is not implemented for this datatype ({dataset.ext})."
 
     def get_display_links(
-        self, dataset: DatasetProtocol24, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
+        self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
     ):
         """
         Returns a list of tuples of (name, link) for a particular display type.  No check on
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index e54a87f1bea..388d11aa333 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -30,10 +30,10 @@ from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
     DatasetProtocol9,
-    DatasetProtocol24,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
+    ProvidesDisplayLinks,
     SetsMetadata,
 )
 from galaxy.datatypes.data import (
@@ -94,7 +94,7 @@ class GenomeGraphs(Tabular):
         """
         return open(dataset.file_name, "rb")
 
-    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         """
         from the ever-helpful angie hinrichs angie@soe.ucsc.edu
         a genome graphs call looks like this
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 97af9da7f8b..eb73b83ba23 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -23,14 +23,11 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol9,
-    DatasetProtocol15,
-    DatasetProtocol19,
-    DatasetProtocol22,
-    DatasetProtocol24,
     HasId,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
+    ProvidesDisplayLinks,
     SetsMetadata,
 )
 from galaxy.datatypes.data import DatatypeValidation
@@ -196,7 +193,7 @@ class Interval(Tabular):
                     else:
                         empty_line_count += 1
 
-    def displayable(self, dataset: DatasetProtocol15) -> bool:
+    def displayable(self, dataset: ProvidesDisplayLinks) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -213,7 +210,7 @@ class Interval(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: DatasetProtocol19,
+        dataset: ProvidesDisplayLinks,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -322,7 +319,7 @@ class Interval(Tabular):
             },
         )
 
-    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         """
         Generate links to UCSC genome browser sites based on the dbkey
         and content of dataset.
@@ -446,7 +443,7 @@ class BedGraph(Interval):
 
     def get_estimated_display_viewport(
         self,
-        dataset: DatasetProtocol19,
+        dataset: ProvidesDisplayLinks,
         chrom_col: Optional[int] = 0,
         start_col: Optional[int] = 1,
         end_col: Optional[int] = 2,
@@ -885,7 +882,7 @@ class Gff(Tabular, _RemoteCallMixin):
         return self.make_html_table(dataset, column_names=self.column_names)
 
     def get_estimated_display_viewport(
-        self, dataset: DatasetProtocol19
+        self, dataset: ProvidesDisplayLinks
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """
         Return a chrom, start, stop tuple for viewing a file.  There are slight differences between gff 2 and gff 3
@@ -961,7 +958,7 @@ class Gff(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -974,7 +971,7 @@ class Gff(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def gbrowse_links(self, dataset: DatasetProtocol22, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -1297,7 +1294,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
     def get_estimated_display_viewport(
-        self, dataset: DatasetProtocol19
+        self, dataset: ProvidesDisplayLinks
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
@@ -1363,7 +1360,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def gbrowse_links(self, dataset: DatasetProtocol22, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1376,7 +1373,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1483,7 +1480,7 @@ class CustomTrack(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: DatasetProtocol19,
+        dataset: ProvidesDisplayLinks,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -1545,7 +1542,7 @@ class CustomTrack(Tabular):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: DatasetProtocol24, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index 22fe0a14a76..f0ca2d387a6 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -31,12 +31,12 @@ from galaxy.datatypes import (
 )
 from galaxy.datatypes._protocols import (
     DatasetProtocol9,
-    DatasetProtocol15,
     Displayable,
     HasFileName,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
+    ProvidesDisplayLinks,
     SetsMetadata,
 )
 from galaxy.datatypes.binary import _BamOrSam
@@ -134,7 +134,7 @@ class TabularData(Text):
         if dataset.metadata.comment_lines:
             dataset.blurb = f"{dataset.blurb}, {util.commaify(str(dataset.metadata.comment_lines))} comments"
 
-    def displayable(self, dataset: DatasetProtocol15) -> bool:
+    def displayable(self, dataset: ProvidesDisplayLinks) -> bool:
         try:
             return (
                 not dataset.dataset.purged

From 2b5e917b8a51ae576d8f39852013724eca11050e Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 11:02:23 -0500
Subject: [PATCH 110/350] Rename protocol as Convertable

---
 lib/galaxy/datatypes/_protocols.py | 11 +++++++----
 lib/galaxy/datatypes/data.py       |  4 ++--
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index b6df215751c..121da7230b7 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -116,10 +116,6 @@ class DatasetProtocol1(HasDataset, HasName, Protocol):
     ...
 
 
-class DatasetProtocol2(HasExt, HasHid, Protocol):
-    ...
-
-
 class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
     ...
 
@@ -197,3 +193,10 @@ class ProvidesDisplayLinks(
     HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
 ):
     ...
+
+
+class Convertable(HasExt, HasHid, Protocol):
+    # TODO: this is passed to convert_dataset, from where it is passed on to
+    # tools.execute(); so this Protocol is only complete in the context of the
+    # datatypes package.
+    ...
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index cee77b4b83f..5a0d4f75f03 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -24,9 +24,9 @@ from typing_extensions import Literal
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
+    Convertable,
     DatasetProtocol0,
     DatasetProtocol1,
-    DatasetProtocol2,
     DatasetProtocol5,
     DatasetProtocol6,
     DatasetProtocol9,
@@ -771,7 +771,7 @@ class Data(metaclass=DataMeta):
     def convert_dataset(
         self,
         trans,
-        original_dataset: DatasetProtocol2,
+        original_dataset: Convertable,
         target_type: str,
         return_output: bool = False,
         visible: bool = True,

From 0478f53f792468fcc7902c1ac59e6f22464adfe0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 11:12:32 -0500
Subject: [PATCH 111/350] Remove Protocol1, replace w/Peekable

---
 lib/galaxy/datatypes/_protocols.py | 4 ----
 lib/galaxy/datatypes/data.py       | 3 +--
 lib/galaxy/datatypes/images.py     | 3 +--
 3 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 121da7230b7..caeeddef98b 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -112,10 +112,6 @@ class DatasetProtocol0(Protocol):
     ...
 
 
-class DatasetProtocol1(HasDataset, HasName, Protocol):
-    ...
-
-
 class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
     ...
 
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 5a0d4f75f03..ffa7729973f 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -26,7 +26,6 @@ from galaxy import util
 from galaxy.datatypes._protocols import (
     Convertable,
     DatasetProtocol0,
-    DatasetProtocol1,
     DatasetProtocol5,
     DatasetProtocol6,
     DatasetProtocol9,
@@ -947,7 +946,7 @@ class Data(metaclass=DataMeta):
                 mime = DEFAULT_MIME_TYPE
         headers["content-type"] = mime
 
-    def handle_dataset_as_image(self, hda: DatasetProtocol1) -> str:
+    def handle_dataset_as_image(self, hda: Peekable) -> str:
         raise Exception("Unimplemented Method")
 
     def __getstate__(self) -> Dict[str, Any]:
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index b568377e13c..b1a366a594f 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -11,7 +11,6 @@ import numpy as np
 import tifffile
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol1,
     DatasetProtocol6,
     Peekable,
     SetsMetadata,
@@ -67,7 +66,7 @@ class Image(data.Data):
         """Determine if the file is in this format"""
         return check_image_type(filename, self.image_formats)
 
-    def handle_dataset_as_image(self, hda: DatasetProtocol1) -> str:
+    def handle_dataset_as_image(self, hda: Peekable) -> str:
         dataset = hda.dataset
         name = hda.name or ""
         with open(dataset.file_name, "rb") as f:

From 6408830f7ae04fc64435cab9f311fd23d89e9d07 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 11:30:55 -0500
Subject: [PATCH 112/350] Remove Protocol9, replace w/Validatable

---
 lib/galaxy/datatypes/_protocols.py | 8 ++++----
 lib/galaxy/datatypes/binary.py     | 4 ++--
 lib/galaxy/datatypes/data.py       | 6 +++---
 lib/galaxy/datatypes/genetics.py   | 4 ++--
 lib/galaxy/datatypes/interval.py   | 4 ++--
 lib/galaxy/datatypes/sequence.py   | 4 ++--
 lib/galaxy/datatypes/tabular.py    | 4 ++--
 7 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index caeeddef98b..0bdaa942ef3 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -120,10 +120,6 @@ class DatasetProtocol6(HasExtraFilesPath, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol9(HasDatatype, HasFileName, HasMetadata, Protocol):
-    ...
-
-
 class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
     ...
 
@@ -196,3 +192,7 @@ class Convertable(HasExt, HasHid, Protocol):
     # tools.execute(); so this Protocol is only complete in the context of the
     # datatypes package.
     ...
+
+
+class Validatable(HasDatatype, HasFileName, HasMetadata, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index d4a4bceedaf..4bcc16de7d2 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -35,7 +35,6 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol9,
     DatasetProtocol16,
     Displayable,
     HasFileName,
@@ -43,6 +42,7 @@ from galaxy.datatypes._protocols import (
     Peekable,
     ProvidesDataSource,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.data import (
     Data,
@@ -685,7 +685,7 @@ class BamNative(CompressedArchive, _BamOrSam):
                 headers,
             )
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         if not BamNative.is_bam(dataset.file_name):
             return DatatypeValidation.invalid("This dataset does not appear to a BAM file.")
         elif self.dataset_content_needs_grooming(dataset.file_name):
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index ffa7729973f..ddcac5cab78 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -28,7 +28,6 @@ from galaxy.datatypes._protocols import (
     DatasetProtocol0,
     DatasetProtocol5,
     DatasetProtocol6,
-    DatasetProtocol9,
     DatasetProtocol16,
     Displayable,
     HasClearAssociatedFiles,
@@ -42,6 +41,7 @@ from galaxy.datatypes._protocols import (
     ProvidesDataSource,
     ProvidesDisplayLinks,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -120,7 +120,7 @@ class DatatypeValidation:
         return f"DatatypeValidation[state={self.state},message={self.message}]"
 
 
-def validate(dataset_instance: DatasetProtocol9) -> DatatypeValidation:
+def validate(dataset_instance: Validatable) -> DatatypeValidation:
     try:
         datatype_validation = dataset_instance.datatype.validate(dataset_instance)
     except Exception as e:
@@ -920,7 +920,7 @@ class Data(metaclass=DataMeta):
             return self.dataproviders[data_format](self, dataset, **settings)
         raise p_dataproviders.exceptions.NoProviderAvailable(self, data_format)
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 388d11aa333..dfd11f8bb7a 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -29,12 +29,12 @@ from markupsafe import escape
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     DatasetProtocol6,
-    DatasetProtocol9,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
     ProvidesDisplayLinks,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -177,7 +177,7 @@ class GenomeGraphs(Tabular):
         except Exception as exc:
             return f"Can't create peek {exc}"
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         """
         Validate a gg file - all numeric after header row
         """
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index eb73b83ba23..2384b849067 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,13 +22,13 @@ from bx.intervals.io import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    DatasetProtocol9,
     HasId,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
     ProvidesDisplayLinks,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
@@ -353,7 +353,7 @@ class Interval(Tabular):
             ret_val.append((site_name, link))
         return ret_val
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         """Validate an interval file using the bx GenomicIntervalReader"""
         c, s, e, t = (
             dataset.metadata.chromCol,
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index c312d31cda7..ef94f2ea49c 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -25,11 +25,11 @@ from markupsafe import escape
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    DatasetProtocol9,
     Displayable,
     HasMetadata,
     Peekable,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import DatatypeValidation
@@ -874,7 +874,7 @@ class BaseFastq(Sequence):
                     return True
         return False
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         headers = iter_headers(dataset.file_name, sep="\n", count=-1)
         # check to see if the base qualities match
         if not self.quality_check(headers):
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index f0ca2d387a6..dcc1e10d428 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,7 +30,6 @@ from galaxy.datatypes import (
     metadata,
 )
 from galaxy.datatypes._protocols import (
-    DatasetProtocol9,
     Displayable,
     HasFileName,
     HasMetadata,
@@ -38,6 +37,7 @@ from galaxy.datatypes._protocols import (
     ProvidesDataSource,
     ProvidesDisplayLinks,
     SetsMetadata,
+    Validatable,
 )
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
@@ -1075,7 +1075,7 @@ class BaseVcf(Tabular):
         if exit_code != 0:
             raise Exception(f"Error merging VCF files: {stderr!r}")
 
-    def validate(self, dataset: DatasetProtocol9, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
         def validate_row(row):
             if len(row) < 8:
                 raise Exception("Not enough columns in row %s" % row.join("\t"))

From 07df3bacab95c96c75c866a23fa14c3c042d2ca8 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 11:34:58 -0500
Subject: [PATCH 113/350] Remove Protocol16, replace w/Archivable

---
 lib/galaxy/datatypes/_protocols.py | 8 ++++----
 lib/galaxy/datatypes/binary.py     | 4 ++--
 lib/galaxy/datatypes/data.py       | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 0bdaa942ef3..296257d6d0e 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -120,10 +120,6 @@ class DatasetProtocol6(HasExtraFilesPath, HasMetadata, Protocol):
     ...
 
 
-class DatasetProtocol16(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
-    ...
-
-
 class Displayable(
     HasCreatingJob,
     HasDataset,
@@ -196,3 +192,7 @@ class Convertable(HasExt, HasHid, Protocol):
 
 class Validatable(HasDatatype, HasFileName, HasMetadata, Protocol):
     ...
+
+
+class Archivable(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
+    ...
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 4bcc16de7d2..c031c8a5afa 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -34,8 +34,8 @@ from bx.seq.twobit import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
+    Archivable,
     DatasetProtocol6,
-    DatasetProtocol16,
     Displayable,
     HasFileName,
     HasMetadata,
@@ -566,7 +566,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return f"Binary bam alignments file ({nice_size(dataset.get_size())})"
 
-    def to_archive(self, dataset: DatasetProtocol16, name: str = "") -> Iterable:
+    def to_archive(self, dataset: Archivable, name: str = "") -> Iterable:
         rel_paths = []
         file_paths = []
         rel_paths.append(f"{name or dataset.file_name}.{dataset.extension}")
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index ddcac5cab78..3722757a13b 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -24,11 +24,11 @@ from typing_extensions import Literal
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
+    Archivable,
     Convertable,
     DatasetProtocol0,
     DatasetProtocol5,
     DatasetProtocol6,
-    DatasetProtocol16,
     Displayable,
     HasClearAssociatedFiles,
     HasCreatingJob,
@@ -411,7 +411,7 @@ class Data(metaclass=DataMeta):
         headers["Content-Disposition"] = f'attachment; filename="{filename}"'
         return open(dataset.file_name, mode="rb"), headers
 
-    def to_archive(self, dataset: DatasetProtocol16, name: str = "") -> Iterable:
+    def to_archive(self, dataset: Archivable, name: str = "") -> Iterable:
         """
         Collect archive paths and file handles that need to be exported when archiving `dataset`.
 

From 399da08bf9b56024a63e3c7c4b804de12688460a Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 11:44:24 -0500
Subject: [PATCH 114/350] Remove Protocol6, replace w/GeneratesPrimaryFile

---
 lib/galaxy/datatypes/_protocols.py | 2 +-
 lib/galaxy/datatypes/anvio.py      | 4 ++--
 lib/galaxy/datatypes/assembly.py   | 4 ++--
 lib/galaxy/datatypes/binary.py     | 4 ++--
 lib/galaxy/datatypes/data.py       | 4 ++--
 lib/galaxy/datatypes/genetics.py   | 8 ++++----
 lib/galaxy/datatypes/gis.py        | 4 ++--
 lib/galaxy/datatypes/hdf5.py       | 4 ++--
 lib/galaxy/datatypes/images.py     | 4 ++--
 lib/galaxy/datatypes/isa.py        | 4 ++--
 lib/galaxy/datatypes/neo4j.py      | 4 ++--
 lib/galaxy/datatypes/ngsindex.py   | 4 ++--
 lib/galaxy/datatypes/proteomics.py | 8 ++++----
 lib/galaxy/datatypes/spaln.py      | 4 ++--
 lib/galaxy/datatypes/text.py       | 4 ++--
 lib/galaxy/datatypes/tracks.py     | 4 ++--
 16 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index 296257d6d0e..da86306d30a 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -116,7 +116,7 @@ class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
     ...
 
 
-class DatasetProtocol6(HasExtraFilesPath, HasMetadata, Protocol):
+class GeneratesPrimaryFile(HasExtraFilesPath, HasMetadata, Protocol):
     ...
 
 
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 5073a021092..57bbca0a0f5 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -8,7 +8,7 @@ import os
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
     SetsMetadata,
 )
@@ -27,7 +27,7 @@ class AnvioComposite(Html):
     file_ext = "anvio_composite"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 58b0da92b12..9d78908eaee 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -13,7 +13,7 @@ from galaxy.datatypes import (
     sequence,
 )
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     SetsMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
@@ -172,7 +172,7 @@ class Velvet(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         log.debug(f"Velvet log info  JJ generate_primary_file {dataset}")
         rval = ["<html><head><title>Velvet Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index c031c8a5afa..99b2635ddb2 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -35,8 +35,8 @@ from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
     Archivable,
-    DatasetProtocol6,
     Displayable,
+    GeneratesPrimaryFile,
     HasFileName,
     HasMetadata,
     Peekable,
@@ -2072,7 +2072,7 @@ class LudwigModel(Html):
             "training_progress.json", description="Training progress", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Ludwig Model Composite Dataset.</title></head><p/>"]
         rval.append("<div>This model dataset is composed of the following items:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 3722757a13b..8c9d36e34d6 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -28,8 +28,8 @@ from galaxy.datatypes._protocols import (
     Convertable,
     DatasetProtocol0,
     DatasetProtocol5,
-    DatasetProtocol6,
     Displayable,
+    GeneratesPrimaryFile,
     HasClearAssociatedFiles,
     HasCreatingJob,
     HasExt,
@@ -874,7 +874,7 @@ class Data(metaclass=DataMeta):
             files[substitute_composite_key(key, value)] = value
         return files
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         raise Exception("generate_primary_file is not implemented for this datatype.")
 
     @property
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index dfd11f8bb7a..92cd7fed064 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -28,7 +28,7 @@ from markupsafe import escape
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     HasMetadata,
     Peekable,
     ProvidesDataSource,
@@ -306,7 +306,7 @@ class Rgenetics(Html):
     composite_type = "auto_primary_file"
     file_ext = "rgenetics"
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Rgenetics Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -594,7 +594,7 @@ class IdeasPre(Html):
                 dataset.metadata.tmp_archive = os.path.join(dataset.extra_files_path, fname)
         self.regenerate_primary_file(dataset)
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
         rval.append("<ul>")
@@ -658,7 +658,7 @@ class RexpBase(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index d1839b4add2..946630b45d1 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -2,7 +2,7 @@
 GIS classes
 """
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
 )
 from galaxy.datatypes.binary import Binary
@@ -64,7 +64,7 @@ class Shapefile(Binary):
             "shapefile.shp.xml", description="Geospatial metadata in XML format (xml)", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Shapefile Galaxy Composite Dataset</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/hdf5.py b/lib/galaxy/datatypes/hdf5.py
index 78dd1b236ed..f9b18747155 100644
--- a/lib/galaxy/datatypes/hdf5.py
+++ b/lib/galaxy/datatypes/hdf5.py
@@ -5,7 +5,7 @@ This datatype was created for use with the iSEE interactive tool.
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     HasMetadata,
 )
 from galaxy.datatypes.data import Data
@@ -55,7 +55,7 @@ class HDF5SummarizedExperiment(Data):
         """Override parent init metadata."""
         Data.init_meta(self, dataset, copy_from=copy_from)
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """Generate primary file to represent dataset."""
         return f"""
               <html>
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index b1a366a594f..7a35f2ea4f1 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -11,7 +11,7 @@ import numpy as np
 import tifffile
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
     SetsMetadata,
 )
@@ -381,7 +381,7 @@ class Analyze75(Binary):
 
         self.add_composite_file("t2m", description="The Analyze75 t2m file.", optional=True, is_binary=True)
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Analyze75 Composite Dataset.</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index af6785026f3..bf1a172ca8e 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -27,8 +27,8 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
     Displayable,
+    GeneratesPrimaryFile,
     HasExtraFilesPath,
     Peekable,
 )
@@ -209,7 +209,7 @@ class _Isa(Data):
     # Generate primary file {{{2
     ################################################################
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """Generate the primary file. It is an HTML file containing description of the composite dataset
         as well as a list of the composite files that it contains."""
 
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index 3b681ac9ae8..24d7c016d43 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -4,7 +4,7 @@ Neo4j Composite Dataset
 import logging
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
 )
 from galaxy.datatypes.data import Data
@@ -22,7 +22,7 @@ class Neo4j(Html):
     stored in extra files path
     """
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index 8d2a83b3ce0..b506b3d7478 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -5,7 +5,7 @@ import logging
 import os
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
     SetsMetadata,
 )
@@ -38,7 +38,7 @@ class BowtieIndex(Html):
 
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 947442ca595..58fe41e1ece 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -11,7 +11,7 @@ from typing import (
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
     SetsMetadata,
 )
@@ -56,7 +56,7 @@ class Wiff(Binary):
             is_binary=True,
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Wiff Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -985,7 +985,7 @@ class SPLib(Msp):
         self.add_composite_file("library.spidx", description="Spectrum index", is_binary=False)
         self.add_composite_file("library.pepidx", description="Peptide index", is_binary=False)
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Spectral Library Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -1074,7 +1074,7 @@ class ImzML(Binary):
 
         self.add_composite_file("ibd", description="The mass spectral data component.", is_binary=True)
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>imzML Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index 58aa3b4be73..de39ae7f159 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -12,8 +12,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
     Displayable,
+    GeneratesPrimaryFile,
     Peekable,
     SetsMetadata,
 )
@@ -64,7 +64,7 @@ class _SpalnDb(Data):
             substitute_name_with_metadata="spalndb_name",
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         rval = ["<html><head><title>Spaln Database</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index 08278c42bf0..c93d7ea18e7 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -17,8 +17,8 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
     Displayable,
+    GeneratesPrimaryFile,
     HasCreatingJob,
     Peekable,
     SetsMetadata,
@@ -863,7 +863,7 @@ class SnpSiftDbNSFP(Text):
             "%s.gz.tbi", description="Tabix Index File", substitute_name_with_metadata="reference_name", is_binary=True
         )
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index 0b15182c456..65e3073ef33 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -4,7 +4,7 @@ Datatype classes for tracks/track views within galaxy.
 import logging
 
 from galaxy.datatypes._protocols import (
-    DatasetProtocol6,
+    GeneratesPrimaryFile,
     Peekable,
 )
 from galaxy.datatypes.text import Html
@@ -29,7 +29,7 @@ class UCSCTrackHub(Html):
     file_ext = "trackhub"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: DatasetProtocol6) -> str:
+    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately

From ade4fe2c9f74cfaf1b912538f809507351c7992b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Wed, 21 Dec 2022 13:16:18 -0500
Subject: [PATCH 115/350] Collapse protocols

---
 lib/galaxy/datatypes/_protocols.py            | 178 +++---------
 lib/galaxy/datatypes/annotation.py            |  10 +-
 lib/galaxy/datatypes/anvio.py                 |  13 +-
 lib/galaxy/datatypes/assembly.py              |  10 +-
 lib/galaxy/datatypes/binary.py                | 270 +++++++++---------
 lib/galaxy/datatypes/blast.py                 |  16 +-
 .../datatypes/constructive_solid_geometry.py  |  41 ++-
 lib/galaxy/datatypes/data.py                  |  74 +++--
 lib/galaxy/datatypes/flow.py                  |   6 +-
 lib/galaxy/datatypes/genetics.py              |  44 ++-
 lib/galaxy/datatypes/gis.py                   |  10 +-
 lib/galaxy/datatypes/goldenpath.py            |   4 +-
 lib/galaxy/datatypes/graph.py                 |  13 +-
 lib/galaxy/datatypes/hdf5.py                  |   4 +-
 lib/galaxy/datatypes/images.py                |  15 +-
 lib/galaxy/datatypes/interval.py              |  84 +++---
 lib/galaxy/datatypes/isa.py                   |  14 +-
 lib/galaxy/datatypes/media.py                 |   8 +-
 lib/galaxy/datatypes/microarrays.py           |  11 +-
 lib/galaxy/datatypes/molecules.py             |  65 ++---
 lib/galaxy/datatypes/mothur.py                |  21 +-
 lib/galaxy/datatypes/msa.py                   |  25 +-
 lib/galaxy/datatypes/neo4j.py                 |  10 +-
 lib/galaxy/datatypes/ngsindex.py              |  13 +-
 lib/galaxy/datatypes/phylip.py                |   9 +-
 lib/galaxy/datatypes/plant_tribes.py          |  15 +-
 lib/galaxy/datatypes/proteomics.py            |  45 ++-
 lib/galaxy/datatypes/qiime2.py                |  11 +-
 lib/galaxy/datatypes/qualityscore.py          |   4 +-
 lib/galaxy/datatypes/registry.py              |   8 +-
 lib/galaxy/datatypes/sequence.py              |  38 ++-
 lib/galaxy/datatypes/spaln.py                 |  19 +-
 lib/galaxy/datatypes/speech.py                |   4 +-
 lib/galaxy/datatypes/tabular.py               |  96 +++----
 lib/galaxy/datatypes/text.py                  |  57 ++--
 lib/galaxy/datatypes/tracks.py                |  10 +-
 lib/galaxy/datatypes/triples.py               |  16 +-
 lib/galaxy/datatypes/xml.py                   |  24 +-
 38 files changed, 580 insertions(+), 735 deletions(-)

diff --git a/lib/galaxy/datatypes/_protocols.py b/lib/galaxy/datatypes/_protocols.py
index da86306d30a..276844d7fc8 100644
--- a/lib/galaxy/datatypes/_protocols.py
+++ b/lib/galaxy/datatypes/_protocols.py
@@ -6,10 +6,6 @@ from typing import Any
 from typing_extensions import Protocol
 
 
-class HasBlurb(Protocol):
-    blurb: str
-
-
 class HasClearAssociatedFiles(Protocol):
     def clear_associated_files(self, metadata_safe: bool = False, purge: bool = False) -> None:
         ...
@@ -21,24 +17,10 @@ class HasCreatingJob(Protocol):
         ...
 
 
-class HasDataset(Protocol):
-    dataset: Any
-
-
-class HasDatatype(Protocol):
-    datatype: Any
-
-
-class HasDbKey(Protocol):
-    dbkey: str
-
-
 class HasExt(Protocol):
-    ext: str
-
-
-class HasExtension(Protocol):
-    extension: str
+    @property
+    def ext(self):
+        ...
 
 
 class HasExtraFilesPath(Protocol):
@@ -51,26 +33,6 @@ class HasFileName(Protocol):
     file_name: Any
 
 
-class HasGetConvertedFilesByType(Protocol):
-    def get_converted_files_by_type(self, file_type):
-        ...
-
-
-class HasGetMime(Protocol):
-    def get_mime(self) -> str:
-        ...
-
-
-class HasGetSize(Protocol):
-    def get_size(self) -> str:
-        ...
-
-
-class HasHasData(Protocol):
-    def has_data(self) -> bool:
-        ...
-
-
 class HasHid(Protocol):
     hid: str
 
@@ -91,108 +53,48 @@ class HasName(Protocol):
     name: str
 
 
-class HasPeek(Protocol):
+class HasExtraFilesAndMetadata(HasExtraFilesPath, HasMetadata, Protocol):
+    ...
+
+
+class DatasetProtocol(
+    HasCreatingJob,
+    HasExt,
+    HasExtraFilesPath,
+    HasFileName,
+    HasId,
+    HasInfo,
+    HasMetadata,
+    HasName,
+    Protocol,
+):
+    blurb: str
+    dataset: Any
+    dbkey: Any
+    extension: str
     peek: Any
+    state: Any
+    states: Any
 
+    @property
+    def datatype(self):
+        ...
+
+    def get_converted_files_by_type(self, file_type):
+        ...
+
+    def get_mime(self) -> str:
+        ...
+
+    def get_size(self) -> str:
+        ...
+
+    def has_data(self) -> bool:
+        ...
 
-class HasSetPeek(Protocol):
     def set_peek(self) -> None:
         ...
 
 
-class HasState(Protocol):
-    state: Any
-
-
-class HasStates(Protocol):
-    states: Any
-
-
-class DatasetProtocol0(Protocol):
-    ...
-
-
-class DatasetProtocol5(HasExt, HasGetConvertedFilesByType, Protocol):
-    ...
-
-
-class GeneratesPrimaryFile(HasExtraFilesPath, HasMetadata, Protocol):
-    ...
-
-
-class Displayable(
-    HasCreatingJob,
-    HasDataset,
-    HasDatatype,
-    HasExtension,
-    HasExtraFilesPath,
-    HasFileName,
-    HasGetMime,
-    HasHid,
-    HasId,
-    HasMetadata,
-    HasName,
-    Protocol,
-):
-    ...
-
-
-class SetsMetadata(
-    HasBlurb,
-    HasDataset,
-    HasExtraFilesPath,
-    HasFileName,
-    HasGetSize,
-    HasHasData,
-    HasId,
-    HasInfo,
-    HasMetadata,
-    HasName,
-    HasPeek,
-    Protocol,
-):
-    ...
-
-
-class Peekable(
-    HasBlurb,
-    HasDataset,
-    HasExtension,
-    HasExtraFilesPath,
-    HasFileName,
-    HasGetSize,
-    HasId,
-    HasInfo,
-    HasMetadata,
-    HasName,
-    HasPeek,
-    HasSetPeek,
-    Protocol,
-):
-    ...
-
-
-class ProvidesDataSource(HasDatatype, HasExt, HasFileName, HasMetadata, Protocol):
-    # passed to the DatasetDataProvider constructor
-    ...
-
-
-class ProvidesDisplayLinks(
-    HasDataset, HasDbKey, HasFileName, HasHasData, HasId, HasMetadata, HasName, HasState, HasStates, Protocol
-):
-    ...
-
-
-class Convertable(HasExt, HasHid, Protocol):
-    # TODO: this is passed to convert_dataset, from where it is passed on to
-    # tools.execute(); so this Protocol is only complete in the context of the
-    # datatypes package.
-    ...
-
-
-class Validatable(HasDatatype, HasFileName, HasMetadata, Protocol):
-    ...
-
-
-class Archivable(HasDatatype, HasExtension, HasExtraFilesPath, HasFileName, HasMetadata, Protocol):
+class DatasetHasHidProtocol(DatasetProtocol, HasHid, Protocol):
     ...
diff --git a/lib/galaxy/datatypes/annotation.py b/lib/galaxy/datatypes/annotation.py
index 8ca1d174214..644983d9da7 100644
--- a/lib/galaxy/datatypes/annotation.py
+++ b/lib/galaxy/datatypes/annotation.py
@@ -1,7 +1,7 @@
 import logging
 import tarfile
 
-from galaxy.datatypes._protocols import Peekable
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import CompressedArchive
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -21,7 +21,7 @@ class SnapHmm(Text):
     file_ext = "snaphmm"
     edam_data = "data_1364"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "SNAP HMM model"
@@ -29,7 +29,7 @@ class SnapHmm(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -51,7 +51,7 @@ class Augustus(CompressedArchive):
     edam_data = "data_0950"
     compressed = True
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Augustus model"
             dataset.blurb = nice_size(dataset.get_size())
@@ -59,7 +59,7 @@ class Augustus(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/anvio.py b/lib/galaxy/datatypes/anvio.py
index 57bbca0a0f5..6da1872b648 100644
--- a/lib/galaxy/datatypes/anvio.py
+++ b/lib/galaxy/datatypes/anvio.py
@@ -8,9 +8,8 @@ import os
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
-    SetsMetadata,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.text import Html
@@ -27,7 +26,7 @@ class AnvioComposite(Html):
     file_ext = "anvio_composite"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -66,7 +65,7 @@ class AnvioComposite(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Anvio database (multiple files)"
@@ -75,7 +74,7 @@ class AnvioComposite(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -95,7 +94,7 @@ class AnvioDB(AnvioComposite):
         if self._anvio_basename is not None:
             self.add_composite_file(self._anvio_basename, is_binary=True, optional=False)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the anvio_basename based upon actual extra_files_path contents.
         """
diff --git a/lib/galaxy/datatypes/assembly.py b/lib/galaxy/datatypes/assembly.py
index 9d78908eaee..a79177eb991 100644
--- a/lib/galaxy/datatypes/assembly.py
+++ b/lib/galaxy/datatypes/assembly.py
@@ -13,8 +13,8 @@ from galaxy.datatypes import (
     sequence,
 )
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    SetsMetadata,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.metadata import MetadataElement
 from galaxy.datatypes.sniff import (
@@ -172,7 +172,7 @@ class Velvet(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         log.debug(f"Velvet log info  JJ generate_primary_file {dataset}")
         rval = ["<html><head><title>Velvet Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
@@ -191,7 +191,7 @@ class Velvet(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -242,6 +242,6 @@ class Velvet(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         Html.set_meta(self, dataset, overwrite=overwrite, **kwd)
         self.regenerate_primary_file(dataset)
diff --git a/lib/galaxy/datatypes/binary.py b/lib/galaxy/datatypes/binary.py
index 99b2635ddb2..706ca2df0f5 100644
--- a/lib/galaxy/datatypes/binary.py
+++ b/lib/galaxy/datatypes/binary.py
@@ -34,15 +34,11 @@ from bx.seq.twobit import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Archivable,
-    Displayable,
-    GeneratesPrimaryFile,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
     HasFileName,
     HasMetadata,
-    Peekable,
-    ProvidesDataSource,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.data import (
     Data,
@@ -115,7 +111,7 @@ class Binary(data.Data):
     def register_unsniffable_binary_ext(ext):
         """Deprecated method."""
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
@@ -136,7 +132,7 @@ class Ab1(Binary):
     edam_format = "format_3000"
     edam_data = "data_0924"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ab1 sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -144,7 +140,7 @@ class Ab1(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -213,7 +209,7 @@ class Cel(Binary):
             found_cel_3 = True
         return found_cel_3 or found_cel_4 or found_cel_agcc
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Cel file.
         """
@@ -226,7 +222,7 @@ class Cel(Binary):
         elif header_bytes.decode("utf8", errors="ignore").startswith("[CEL]"):
             dataset.metadata.version = "3"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.blurb = f"Cel version: {dataset.metadata.version}"
             dataset.peek = get_file_peek(dataset.file_name)
@@ -260,7 +256,7 @@ class CompressedArchive(Binary):
     compressed = True
     is_binary = "maybe"  # type: ignore[assignment]  # https://github.com/python/mypy/issues/8796
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed binary file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -268,7 +264,7 @@ class CompressedArchive(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -317,7 +313,7 @@ class Bref3(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith_bytes(self._magic)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bref3 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -325,7 +321,7 @@ class Bref3(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -377,7 +373,7 @@ class CompressedZipArchive(CompressedArchive):
 
     file_ext = "zip"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Compressed zip file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -385,7 +381,7 @@ class CompressedZipArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -416,7 +412,7 @@ class _BamOrSam:
     Helper class to set the metadata common to sam and bam files
     """
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         try:
             bam_file = pysam.AlignmentFile(dataset.file_name, mode="rb")
             # TODO: Reference names, lengths, read_groups and headers can become very large, truncate when necessary
@@ -521,7 +517,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         no_value={},
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         _BamOrSam().set_meta(dataset, overwrite=overwrite, **kwd)
 
     @staticmethod
@@ -552,7 +548,7 @@ class BamNative(CompressedArchive, _BamOrSam):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary bam alignments file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -560,13 +556,13 @@ class BamNative(CompressedArchive, _BamOrSam):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary bam alignments file ({nice_size(dataset.get_size())})"
 
-    def to_archive(self, dataset: Archivable, name: str = "") -> Iterable:
+    def to_archive(self, dataset: DatasetProtocol, name: str = "") -> Iterable:
         rel_paths = []
         file_paths = []
         rel_paths.append(f"{name or dataset.file_name}.{dataset.extension}")
@@ -649,7 +645,7 @@ class BamNative(CompressedArchive, _BamOrSam):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -685,7 +681,7 @@ class BamNative(CompressedArchive, _BamOrSam):
                 headers,
             )
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         if not BamNative.is_bam(dataset.file_name):
             return DatatypeValidation.invalid("This dataset does not appear to a BAM file.")
         elif self.dataset_content_needs_grooming(dataset.file_name):
@@ -775,7 +771,7 @@ class Bam(BamNative):
         return needs_sorting
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         # These metadata values are not accessible by users, always overwrite
         super().set_meta(dataset=dataset, overwrite=overwrite, **kwd)
@@ -807,25 +803,25 @@ class Bam(BamNative):
     # TODO:?? seems like there should be an easier way to do/inherit this - metadata.comment_char?
     # TODO: incorporate samtools options to control output: regions first, then flags, etc.
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: DatasetProtocol, **settings) -> FilteredLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return FilteredLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: DatasetProtocol, **settings) -> RegexLineDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol, **settings) -> ColumnarDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return ColumnarDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         samtools_source = SamtoolsDataProvider(dataset)
         settings["comment_char"] = "@"
         return DictDataProvider(samtools_source, **settings)
@@ -843,20 +839,20 @@ class Bam(BamNative):
     #    return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: DatasetProtocol, **settings) -> RegexLineDataProvider:
         # in this case we can use an option of samtools view to provide just what we need (w/o regex)
         samtools_source = SamtoolsDataProvider(dataset, "-H")
         return RegexLineDataProvider(samtools_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", DictDataProvider.settings)
-    def id_seq_qual_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         settings["indeces"] = [0, 9, 10]
         settings["column_types"] = ["str", "str", "str"]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", ColumnarDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> ColumnarDataProvider:
         # GenomicRegionDataProvider currently requires a dataset as source - may not be necc.
         # TODO:?? consider (at least) the possible use of a kwarg: metadata_source (def. to source.dataset),
         #   or remove altogether...
@@ -870,14 +866,14 @@ class Bam(BamNative):
         return self.column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", DictDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         settings["indeces"] = [2, 3, 3]
         settings["column_types"] = ["str", "int", "int"]
         settings["column_names"] = ["chrom", "start", "end"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("samtools")
-    def samtools_dataprovider(self, dataset: ProvidesDataSource, **settings) -> SamtoolsDataProvider:
+    def samtools_dataprovider(self, dataset: DatasetProtocol, **settings) -> SamtoolsDataProvider:
         """Generic samtools interface - all options available through settings."""
         dataset_source = DatasetDataProvider(dataset)
         return SamtoolsDataProvider(dataset_source, **settings)
@@ -961,7 +957,7 @@ class CRAM(Binary):
     )
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         major_version, minor_version = self.get_cram_version(dataset.file_name)
         if major_version != -1:
@@ -991,7 +987,7 @@ class CRAM(Binary):
             log.warning("%s, set_index_file Exception: %s", self, exc)
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CRAM binary alignment file"
             dataset.blurb = "binary data"
@@ -1044,7 +1040,7 @@ class Bcf(BaseBcf):
             return False
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """Creates the index for the BCF file."""
         # These metadata values are not accessible by users, always overwrite
@@ -1128,7 +1124,7 @@ class H5(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary HDF5 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1136,7 +1132,7 @@ class H5(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1234,7 +1230,7 @@ class Loom(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary Loom file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1242,13 +1238,13 @@ class Loom(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary Loom file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as loom_file:
@@ -1393,7 +1389,7 @@ class Anndata(H5):
                 return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         with h5py.File(dataset.file_name, "r") as anndata_file:
             dataset.metadata.title = anndata_file.attrs.get("title")
@@ -1499,7 +1495,7 @@ class Anndata(H5):
             if dataset.metadata.shape is None:
                 dataset.metadata.shape = (int(dataset.metadata.obs_size), int(dataset.metadata.var_size))
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             tmp = dataset.metadata
 
@@ -1527,7 +1523,7 @@ class Anndata(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1572,7 +1568,7 @@ class Grib(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary GRIB file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1580,13 +1576,13 @@ class Grib(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Binary GRIB file ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the GRIB edition.
         """
@@ -1615,7 +1611,7 @@ class GmxBinary(Binary):
         # The first 4 bytes of any GROMACS binary file containing the magic number
         return file_prefix.magic_header(">1i") == self.magic_number
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary GROMACS {self.file_ext} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1623,7 +1619,7 @@ class GmxBinary(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1753,7 +1749,7 @@ class Biom2(H5):
                 return required_fields.issubset(f.attrs.keys())
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as f:
@@ -1775,7 +1771,7 @@ class Biom2(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, util.unicodify(e))
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Biom2 (HDF5) file"]
             try:
@@ -1790,7 +1786,7 @@ class Biom2(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1835,7 +1831,7 @@ class Cool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1843,7 +1839,7 @@ class Cool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1895,7 +1891,7 @@ class MCool(H5):
                     return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Multi-resolution Cool (HDF5) file for storing genomic interaction data."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1903,7 +1899,7 @@ class MCool(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -1939,7 +1935,7 @@ class H5MLM(H5):
     )
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         try:
             spec_key = "hyper_params"
@@ -2002,7 +1998,7 @@ class H5MLM(H5):
             log.warning("%s, get model configuration Except: %s", self, e)
             return ""
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             repr = self.get_repr(dataset.file_name)
             dataset.peek = repr[: self.max_peek_size]
@@ -2011,7 +2007,7 @@ class H5MLM(H5):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2020,7 +2016,7 @@ class H5MLM(H5):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -2072,7 +2068,7 @@ class LudwigModel(Html):
             "training_progress.json", description="Training progress", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Ludwig Model Composite Dataset.</title></head><p/>"]
         rval.append("<div>This model dataset is composed of the following items:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -2131,7 +2127,7 @@ class HexrdMaterials(H5):
                         return True
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with h5py.File(dataset.file_name, "r") as mat_file:
@@ -2148,7 +2144,7 @@ class HexrdMaterials(H5):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = ["Material SpaceGroup Lattice"]
             if dataset.metadata.materials:
@@ -2173,7 +2169,7 @@ class Scf(Binary):
     edam_data = "data_0924"
     file_ext = "scf"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary scf sequence file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2181,7 +2177,7 @@ class Scf(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2201,7 +2197,7 @@ class Sff(Binary):
         # about the format, see http://www.ncbi.nlm.nih.gov/Traces/trace.cgi?cmd=show&f=formats&m=doc&s=format
         return file_prefix.startswith_bytes(b".sff")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sff file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2209,7 +2205,7 @@ class Sff(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2238,7 +2234,7 @@ class BigWig(Binary):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.magic_header("I") == self._magic
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary UCSC {self._name} file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2246,7 +2242,7 @@ class BigWig(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2279,14 +2275,14 @@ class TwoBit(Binary):
         magic = file_prefix.magic_header(">L")
         return magic == TWOBIT_MAGIC_NUMBER or magic == TWOBIT_MAGIC_NUMBER_SWAP
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary TwoBit format nucleotide file"
             dataset.blurb = nice_size(dataset.get_size())
         else:
             return super().set_peek(dataset)
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2324,7 +2320,7 @@ class SQlite(Binary):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         Binary.init_meta(self, dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         try:
             tables = []
             columns = dict()
@@ -2381,7 +2377,7 @@ class SQlite(Binary):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SQLite Database"
             lines = ["SQLite Database"]
@@ -2397,24 +2393,24 @@ class SQlite(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"SQLite Database ({nice_size(dataset.get_size())})"
 
     @dataproviders.decorators.dataprovider_factory("sqlite", SQliteDataProvider.settings)
-    def sqlite_dataprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataProvider:
+    def sqlite_dataprovider(self, dataset: DatasetProtocol, **settings) -> SQliteDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-table", SQliteDataTableProvider.settings)
-    def sqlite_datatableprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataTableProvider:
+    def sqlite_datatableprovider(self, dataset: DatasetProtocol, **settings) -> SQliteDataTableProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataTableProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("sqlite-dict", SQliteDataDictProvider.settings)
-    def sqlite_datadictprovider(self, dataset: ProvidesDataSource, **settings) -> SQliteDataDictProvider:
+    def sqlite_datadictprovider(self, dataset: DatasetProtocol, **settings) -> SQliteDataDictProvider:
         dataset_source = DatasetDataProvider(dataset)
         return SQliteDataDictProvider(dataset_source, **settings)
 
@@ -2435,7 +2431,7 @@ class GeminiSQLite(SQlite):
     edam_format = "format_3622"
     edam_data = "data_3498"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2464,7 +2460,7 @@ class GeminiSQLite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Gemini SQLite Database, version %s" % (dataset.metadata.gemini_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2472,7 +2468,7 @@ class GeminiSQLite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2484,7 +2480,7 @@ class ChiraSQLite(SQlite):
 
     file_ext = "chira.sqlite"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2515,7 +2511,7 @@ class CuffDiffSQlite(SQlite):
     # TODO: Update this when/if there is a specific EDAM format for CuffDiff SQLite data.
     edam_format = "format_3621"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             genes = []
@@ -2551,7 +2547,7 @@ class CuffDiffSQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "CuffDiff SQLite Database, version %s" % (dataset.metadata.cuffdiff_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -2559,7 +2555,7 @@ class CuffDiffSQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2571,7 +2567,7 @@ class MzSQlite(SQlite):
 
     file_ext = "mz.sqlite"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2608,7 +2604,7 @@ class PQP(SQlite):
 
     file_ext = "pqp"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2650,7 +2646,7 @@ class OSW(SQlite):
 
     file_ext = "osw"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2693,7 +2689,7 @@ class SQmass(SQlite):
 
     file_ext = "sqmass"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2717,7 +2713,7 @@ class BlibSQlite(SQlite):
     )
     file_ext = "blib"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2770,7 +2766,7 @@ class DlibSQlite(SQlite):
     )
     file_ext = "dlib"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2814,7 +2810,7 @@ class ElibSQlite(SQlite):
     )
     file_ext = "elib"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2865,7 +2861,7 @@ class IdpDB(SQlite):
 
     file_ext = "idpdb"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
     def sniff(self, filename: str) -> bool:
@@ -2881,7 +2877,7 @@ class IdpDB(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "IDPickerDB SQLite file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -2889,7 +2885,7 @@ class IdpDB(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -2910,7 +2906,7 @@ class GAFASQLite(SQlite):
     )
     file_ext = "gafa.sqlite"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2956,7 +2952,7 @@ class NcbiTaxonomySQlite(SQlite):
 
     file_ext = "ncbitaxonomy.sqlite"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             conn = sqlite.connect(dataset.file_name)
@@ -2980,7 +2976,7 @@ class NcbiTaxonomySQlite(SQlite):
             return self.sniff_table_names(filename, table_names)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "NCBI Taxonomy SQLite Database, version {} ({} taxons)".format(
                 getattr(dataset.metadata, "ncbitaxonomy_schema_version", "unknown"),
@@ -2991,7 +2987,7 @@ class NcbiTaxonomySQlite(SQlite):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3027,7 +3023,7 @@ class ExcelXls(Binary):
         """Returns the mime type of the datatype"""
         return "application/vnd.ms-excel"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Microsoft Excel XLS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -3035,7 +3031,7 @@ class ExcelXls(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3054,7 +3050,7 @@ class Sra(Binary):
         """
         return file_prefix.startswith_bytes(b"NCBI.sra")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary sra file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3062,7 +3058,7 @@ class Sra(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3103,7 +3099,7 @@ class RData(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3186,7 +3182,7 @@ class RDS(CompressedArchive):
         optional=False,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         _, fh = compression_utils.get_fileobj_raw(dataset.file_name, "rb")
         try:
@@ -3433,7 +3429,7 @@ class PostgresqlArchive(CompressedArchive):
     )
     file_ext = "postgresql"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3451,7 +3447,7 @@ class PostgresqlArchive(CompressedArchive):
                 return "postgresql/db/PG_VERSION" in temptar.getnames()
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"PostgreSQL Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "PostgreSQL version %s" % (dataset.metadata.version or "unknown")
@@ -3459,7 +3455,7 @@ class PostgresqlArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3481,7 +3477,7 @@ class Fast5Archive(CompressedArchive):
     )
     file_ext = "fast5.tar"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and tarfile.is_tarfile(dataset.file_name):
@@ -3505,7 +3501,7 @@ class Fast5Archive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"FAST5 Archive ({nice_size(dataset.get_size())})"
             dataset.blurb = "%s sequences" % (dataset.metadata.fast5_count or "unknown")
@@ -3513,7 +3509,7 @@ class Fast5Archive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3589,7 +3585,7 @@ class SearchGuiArchive(CompressedArchive):
     )
     file_ext = "searchgui_archive"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             if dataset and zipfile.is_zipfile(dataset.file_name):
@@ -3614,7 +3610,7 @@ class SearchGuiArchive(CompressedArchive):
             log.warning("%s, sniff Exception: %s", self, e)
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "SearchGUI Archive, version %s" % (dataset.metadata.searchgui_version or "unknown")
             dataset.blurb = nice_size(dataset.get_size())
@@ -3622,7 +3618,7 @@ class SearchGuiArchive(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3637,7 +3633,7 @@ class NetCDF(Binary):
     edam_format = "format_3650"
     edam_data = "data_0943"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary netCDF file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3645,7 +3641,7 @@ class NetCDF(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3693,7 +3689,7 @@ class Dcd(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM/NAMD dcd file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3701,7 +3697,7 @@ class Dcd(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3745,7 +3741,7 @@ class Vel(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary CHARMM velocity file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3753,7 +3749,7 @@ class Vel(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -3842,7 +3838,7 @@ class ICM(Binary):
     file_ext = "icm"
     edam_data = "data_0950"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary ICM (interpolated context model) file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -3917,7 +3913,7 @@ class BafTar(CompressedArchive):
     def get_type(self) -> str:
         return "Bruker BAF directory archive"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = self.get_type()
             dataset.blurb = nice_size(dataset.get_size())
@@ -3925,7 +3921,7 @@ class BafTar(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4027,7 +4023,7 @@ class Pretext(Binary):
         # file contains binary data.
         return file_prefix.startswith_bytes(b"pstm")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary pretext file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4035,7 +4031,7 @@ class Pretext(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4071,7 +4067,7 @@ class JP2(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary JPEG 2000 file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4079,7 +4075,7 @@ class JP2(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4119,7 +4115,7 @@ class Npz(CompressedArchive):
             return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         try:
             with np.load(dataset.file_name) as npz:
                 dataset.metadata.nfiles = len(npz.files)
@@ -4127,7 +4123,7 @@ class Npz(CompressedArchive):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Binary Numpy npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})"
             dataset.blurb = nice_size(dataset.get_size())
@@ -4135,7 +4131,7 @@ class Npz(CompressedArchive):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4187,7 +4183,7 @@ class HexrdImagesNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4200,7 +4196,7 @@ class HexrdImagesNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Image npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4212,7 +4208,7 @@ class HexrdImagesNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -4253,7 +4249,7 @@ class HexrdEtaOmeNpz(Npz):
                 return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         try:
             with np.load(dataset.file_name) as npz:
@@ -4262,7 +4258,7 @@ class HexrdEtaOmeNpz(Npz):
         except Exception as e:
             log.warning("%s, set_meta Exception: %s", self, e)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = [
                 f"Binary Hexrd Eta-Ome npz {dataset.metadata.nfiles} files ({nice_size(dataset.get_size())})",
@@ -4274,7 +4270,7 @@ class HexrdEtaOmeNpz(Npz):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
index 9a7fb50695d..0ab11e612c9 100644
--- a/lib/galaxy/datatypes/blast.py
+++ b/lib/galaxy/datatypes/blast.py
@@ -41,8 +41,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Displayable,
-    Peekable,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
 )
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -67,7 +67,7 @@ class BlastXml(GenericXml):
     edam_format = "format_3331"
     edam_data = "data_0857"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
@@ -192,7 +192,7 @@ class BlastXml(GenericXml):
 class _BlastDb(Data):
     """Base class for BLAST database datatype."""
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "BLAST database (multiple files)"
@@ -201,7 +201,7 @@ class _BlastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -211,7 +211,7 @@ class _BlastDb(Data):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -369,7 +369,7 @@ class LastDb(Data):
     file_ext = "lastdb"
     composite_type = "basic"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "LAST database (multiple files)"
@@ -378,7 +378,7 @@ class LastDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/constructive_solid_geometry.py b/lib/galaxy/datatypes/constructive_solid_geometry.py
index 9638bdbb027..3002eeb9cff 100644
--- a/lib/galaxy/datatypes/constructive_solid_geometry.py
+++ b/lib/galaxy/datatypes/constructive_solid_geometry.py
@@ -15,9 +15,8 @@ from typing import (
 from galaxy import util
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
+    DatasetProtocol,
     HasMetadata,
-    Peekable,
-    SetsMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
@@ -105,7 +104,7 @@ class Ply:
                 break
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for line in fh:
@@ -128,7 +127,7 @@ class Ply:
                             element_tuple = (items[1], int(items[2]))
                             dataset.metadata.other_elements.append(element_tuple)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = f"Faces: {str(dataset.metadata.face)}, Vertices: {str(dataset.metadata.vertex)}"
@@ -136,7 +135,7 @@ class Ply:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -285,7 +284,7 @@ class Vtk:
             return check_data_kind(line)
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             dataset.metadata.field_names = []
             dataset.metadata.field_components = {}
@@ -374,7 +373,7 @@ class Vtk:
             if len(field_components) > 0:
                 dataset.metadata.field_components = field_components
 
-    def set_initial_metadata(self, i: int, line: str, dataset: SetsMetadata) -> SetsMetadata:
+    def set_initial_metadata(self, i: int, line: str, dataset: DatasetProtocol) -> DatasetProtocol:
         if i == 0:
             # The first part of legacy VTK files is the file version and
             # identifier. This part contains the single line:
@@ -393,8 +392,8 @@ class Vtk:
         return dataset
 
     def set_structure_metadata(
-        self, line: str, dataset: SetsMetadata, dataset_type: Optional[str]
-    ) -> Tuple[SetsMetadata, Optional[str]]:
+        self, line: str, dataset: DatasetProtocol, dataset_type: Optional[str]
+    ) -> Tuple[DatasetProtocol, Optional[str]]:
         """
         The fourth part of legacy VTK files is the dataset structure. The
         geometry part describes the geometry and topology of the dataset.
@@ -462,7 +461,7 @@ class Vtk:
             blurb += str(dataset.metadata.dataset_type)
         return blurb or "VTK data"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = self.get_blurb(dataset)
@@ -470,7 +469,7 @@ class Vtk:
             dataset.peek = "File does not exist"
             dataset.blurb = "File purged from disc"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -555,7 +554,7 @@ class NeperTess(data.Text):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tess")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -571,7 +570,7 @@ class NeperTess(data.Text):
                     if i == 6:
                         dataset.metadata.cells = int(line)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=7)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -626,7 +625,7 @@ class NeperTesr(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline(10).startswith("***tesr")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 field = ""
@@ -658,7 +657,7 @@ class NeperTesr(Binary):
                         dataset.metadata.cells = int(line)
                         break
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=9)
             dataset.blurb = f"format: {str(dataset.metadata.format)} dim: {str(dataset.metadata.dimension)} cells: {str(dataset.metadata.cells)}"
@@ -679,7 +678,7 @@ class NeperPoints(data.Text):
     def __init__(self, **kwd):
         data.Text.__init__(self, **kwd)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         data.Text.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
@@ -704,7 +703,7 @@ class NeperPoints(data.Text):
             return None
         return dim
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         data.Text.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -721,13 +720,13 @@ class NeperPointsTabular(NeperPoints, Tabular):
     def __init__(self, **kwd):
         Tabular.__init__(self, **kwd)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 dataset.metadata.dimension = self._get_dimension(fh)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         Tabular.set_peek(self, dataset)
         if not dataset.dataset.purged:
             dataset.blurb += f" dim: {str(dataset.metadata.dimension)}"
@@ -767,7 +766,7 @@ class GmshMsh(Binary):
         """
         return file_prefix.text_io(errors="ignore").readline().startswith("$MeshFormat")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if dataset.has_data():
             with open(dataset.file_name, errors="ignore") as fh:
                 for i, line in enumerate(fh):
@@ -783,7 +782,7 @@ class GmshMsh(Binary):
                         if len(fields) > 1:
                             dataset.metadata.format = "ASCII" if fields[1] == "0" else "binary"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name, line_count=3)
             dataset.blurb = f"Gmsh verion: {str(dataset.metadata.version)} {str(dataset.metadata.format)}"
diff --git a/lib/galaxy/datatypes/data.py b/lib/galaxy/datatypes/data.py
index 8c9d36e34d6..067ec0475fe 100644
--- a/lib/galaxy/datatypes/data.py
+++ b/lib/galaxy/datatypes/data.py
@@ -24,24 +24,16 @@ from typing_extensions import Literal
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Archivable,
-    Convertable,
-    DatasetProtocol0,
-    DatasetProtocol5,
-    Displayable,
-    GeneratesPrimaryFile,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
     HasClearAssociatedFiles,
     HasCreatingJob,
     HasExt,
+    HasExtraFilesAndMetadata,
     HasFileName,
     HasInfo,
     HasMetadata,
     HasName,
-    Peekable,
-    ProvidesDataSource,
-    ProvidesDisplayLinks,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.metadata import (
     MetadataElement,  # import directly to maintain ease of use in Datatype class definitions
@@ -120,7 +112,7 @@ class DatatypeValidation:
         return f"DatatypeValidation[state={self.state},message={self.message}]"
 
 
-def validate(dataset_instance: Validatable) -> DatatypeValidation:
+def validate(dataset_instance: DatasetProtocol) -> DatatypeValidation:
     try:
         datatype_validation = dataset_instance.datatype.validate(dataset_instance)
     except Exception as e:
@@ -254,7 +246,7 @@ class Data(metaclass=DataMeta):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, *, overwrite: bool = True, **kwd) -> None:
         """Unimplemented method, allows guessing of metadata from contents of file"""
 
     def missing_meta(self, dataset: HasMetadata, check: Optional[List] = None, skip: Optional[List] = None) -> bool:
@@ -299,7 +291,7 @@ class Data(metaclass=DataMeta):
 
     max_optional_metadata_filesize = property(get_max_optional_metadata_filesize, set_max_optional_metadata_filesize)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -310,7 +302,7 @@ class Data(metaclass=DataMeta):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML table, used for displaying peek"""
         out = ['<table cellspacing="0" cellpadding="3">']
         try:
@@ -351,7 +343,7 @@ class Data(metaclass=DataMeta):
         return error, msg, messagetype
 
     def _archive_composite_dataset(
-        self, trans, data: Displayable, headers: Headers, do_action: str = "zip"
+        self, trans, data: DatasetHasHidProtocol, headers: Headers, do_action: str = "zip"
     ) -> Tuple[Union[ZipstreamWrapper, str], Headers]:
         # save a composite object into a compressed archive for downloading
         outfname = data.name[0:150]
@@ -396,7 +388,9 @@ class Data(metaclass=DataMeta):
                 rpath = os.path.relpath(fpath, extra_files_path)
                 yield fpath, rpath
 
-    def _serve_raw(self, dataset: Displayable, to_ext: Optional[str], headers: Headers, **kwd) -> Tuple[IO, Headers]:
+    def _serve_raw(
+        self, dataset: DatasetHasHidProtocol, to_ext: Optional[str], headers: Headers, **kwd
+    ) -> Tuple[IO, Headers]:
         headers["Content-Length"] = str(os.stat(dataset.file_name).st_size)
         headers[
             "content-type"
@@ -411,7 +405,7 @@ class Data(metaclass=DataMeta):
         headers["Content-Disposition"] = f'attachment; filename="{filename}"'
         return open(dataset.file_name, mode="rb"), headers
 
-    def to_archive(self, dataset: Archivable, name: str = "") -> Iterable:
+    def to_archive(self, dataset: DatasetProtocol, name: str = "") -> Iterable:
         """
         Collect archive paths and file handles that need to be exported when archiving `dataset`.
 
@@ -436,7 +430,7 @@ class Data(metaclass=DataMeta):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -549,7 +543,7 @@ class Data(metaclass=DataMeta):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: Peekable) -> str:
+    def display_as_markdown(self, dataset_instance: DatasetProtocol) -> str:
         """Prepare for embedding dataset into a basic Markdown document.
 
         This is a somewhat experimental interface and should not be implemented
@@ -598,9 +592,9 @@ class Data(metaclass=DataMeta):
 
     def _download_filename(
         self,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         to_ext: Optional[str] = None,
-        hdca: Optional[Displayable] = None,
+        hdca: Optional[DatasetHasHidProtocol] = None,
         element_identifier: Optional[str] = None,
         filename_pattern: Optional[str] = None,
     ) -> str:
@@ -699,7 +693,7 @@ class Data(metaclass=DataMeta):
     def get_display_application(self, key: str, default: Optional["DisplayApplication"] = None) -> "DisplayApplication":
         return self.display_applications.get(key, default)
 
-    def get_display_applications_by_dataset(self, dataset: DatasetProtocol0, trans) -> Dict[str, "DisplayApplication"]:
+    def get_display_applications_by_dataset(self, dataset: DatasetProtocol, trans) -> Dict[str, "DisplayApplication"]:
         rval = {}
         for key, value in self.display_applications.items():
             value = value.filter_by_dataset(dataset, trans)
@@ -718,7 +712,7 @@ class Data(metaclass=DataMeta):
         except Exception:
             return "unknown"
 
-    def as_display_type(self, dataset: ProvidesDataSource, type: str, **kwd) -> Union[FileObjType, str]:
+    def as_display_type(self, dataset: DatasetProtocol, type: str, **kwd) -> Union[FileObjType, str]:
         """Returns modified file contents for a particular display type"""
         try:
             if type in self.get_display_types():
@@ -733,7 +727,7 @@ class Data(metaclass=DataMeta):
         return f"This display type ({type}) is not implemented for this datatype ({dataset.ext})."
 
     def get_display_links(
-        self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
+        self, dataset: DatasetProtocol, type: str, app, base_url: str, target_frame: str = "_blank", **kwd
     ):
         """
         Returns a list of tuples of (name, link) for a particular display type.  No check on
@@ -760,7 +754,7 @@ class Data(metaclass=DataMeta):
         return datatypes_registry.get_converters_by_datatype(original_dataset.ext)
 
     def find_conversion_destination(
-        self, dataset: DatasetProtocol5, accepted_formats: List[str], datatypes_registry, **kwd
+        self, dataset: DatasetProtocol, accepted_formats: List[str], datatypes_registry, **kwd
     ) -> Tuple[bool, Optional[str], Any]:
         """Returns ( direct_match, converted_ext, existing converted dataset )"""
         return datatypes_registry.find_conversion_destination_for_dataset_by_extensions(
@@ -770,7 +764,7 @@ class Data(metaclass=DataMeta):
     def convert_dataset(
         self,
         trans,
-        original_dataset: Convertable,
+        original_dataset: DatasetHasHidProtocol,
         target_type: str,
         return_output: bool = False,
         visible: bool = True,
@@ -874,7 +868,7 @@ class Data(metaclass=DataMeta):
             files[substitute_composite_key(key, value)] = value
         return files
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         raise Exception("generate_primary_file is not implemented for this datatype.")
 
     @property
@@ -911,7 +905,7 @@ class Data(metaclass=DataMeta):
         """
         return data_format in self.dataproviders
 
-    def dataprovider(self, dataset: ProvidesDataSource, data_format: str, **settings):
+    def dataprovider(self, dataset: DatasetProtocol, data_format: str, **settings):
         """
         Base dataprovider factory for all datatypes that returns the proper provider
         for the given `data_format` or raises a `NoProviderAvailable`.
@@ -920,22 +914,22 @@ class Data(metaclass=DataMeta):
             return self.dataproviders[data_format](self, dataset, **settings)
         raise p_dataproviders.exceptions.NoProviderAvailable(self, data_format)
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         return DatatypeValidation.unvalidated()
 
     @p_dataproviders.decorators.dataprovider_factory("base")
-    def base_dataprovider(self, dataset: ProvidesDataSource, **settings) -> p_dataproviders.base.DataProvider:
+    def base_dataprovider(self, dataset: DatasetProtocol, **settings) -> p_dataproviders.base.DataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.base.DataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk", p_dataproviders.chunk.ChunkDataProvider.settings)
-    def chunk_dataprovider(self, dataset: ProvidesDataSource, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
+    def chunk_dataprovider(self, dataset: DatasetProtocol, **settings) -> p_dataproviders.chunk.ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.ChunkDataProvider(dataset_source, **settings)
 
     @p_dataproviders.decorators.dataprovider_factory("chunk64", p_dataproviders.chunk.Base64ChunkDataProvider.settings)
     def chunk64_dataprovider(
-        self, dataset: ProvidesDataSource, **settings
+        self, dataset: DatasetProtocol, **settings
     ) -> p_dataproviders.chunk.Base64ChunkDataProvider:
         dataset_source = p_dataproviders.dataset.DatasetDataProvider(dataset)
         return p_dataproviders.chunk.Base64ChunkDataProvider(dataset_source, **settings)
@@ -946,7 +940,7 @@ class Data(metaclass=DataMeta):
                 mime = DEFAULT_MIME_TYPE
         headers["content-type"] = mime
 
-    def handle_dataset_as_image(self, hda: Peekable) -> str:
+    def handle_dataset_as_image(self, hda: DatasetProtocol) -> str:
         raise Exception("Unimplemented Method")
 
     def __getstate__(self) -> Dict[str, Any]:
@@ -978,13 +972,13 @@ class Text(Data):
         """Returns the mime type of the datatype"""
         return "text/plain"
 
-    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, *, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.data_lines = self.count_data_lines(dataset)
 
-    def estimate_file_lines(self, dataset: Peekable) -> Optional[int]:
+    def estimate_file_lines(self, dataset: DatasetProtocol) -> Optional[int]:
         """
         Perform a rough estimate by extrapolating number of lines from a small read.
         """
@@ -1019,7 +1013,7 @@ class Text(Data):
                 return None
         return data_lines
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """
         Set the peek.  This method is used by various subclasses of Text.
         """
@@ -1132,9 +1126,7 @@ class Text(Data):
 
     # ------------- Dataproviders
     @p_dataproviders.decorators.dataprovider_factory("line", p_dataproviders.line.FilteredLineDataProvider.settings)
-    def line_dataprovider(
-        self, dataset: ProvidesDataSource, **settings
-    ) -> p_dataproviders.line.FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: DatasetProtocol, **settings) -> p_dataproviders.line.FilteredLineDataProvider:
         """
         Returns an iterator over the dataset's lines (that have been stripped)
         optionally excluding blank lines and lines that start with a comment character.
@@ -1144,7 +1136,7 @@ class Text(Data):
 
     @p_dataproviders.decorators.dataprovider_factory("regex-line", p_dataproviders.line.RegexLineDataProvider.settings)
     def regex_line_dataprovider(
-        self, dataset: ProvidesDataSource, **settings
+        self, dataset: DatasetProtocol, **settings
     ) -> p_dataproviders.line.RegexLineDataProvider:
         """
         Returns an iterator over the dataset's lines
diff --git a/lib/galaxy/datatypes/flow.py b/lib/galaxy/datatypes/flow.py
index 3f1dd83f65e..6f43d8316cf 100644
--- a/lib/galaxy/datatypes/flow.py
+++ b/lib/galaxy/datatypes/flow.py
@@ -4,7 +4,7 @@ Flow analysis datatypes.
 
 import logging
 
-from galaxy.datatypes._protocols import Peekable
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
@@ -21,7 +21,7 @@ class FCS(Binary):
 
     file_ext = "fcs"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary FCS file"
             dataset.blurb = data.nice_size(dataset.get_size())
@@ -29,7 +29,7 @@ class FCS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/genetics.py b/lib/galaxy/datatypes/genetics.py
index 92cd7fed064..1cc1b77156a 100644
--- a/lib/galaxy/datatypes/genetics.py
+++ b/lib/galaxy/datatypes/genetics.py
@@ -28,13 +28,9 @@ from markupsafe import escape
 
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
     HasMetadata,
-    Peekable,
-    ProvidesDataSource,
-    ProvidesDisplayLinks,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.data import (
     DatatypeValidation,
@@ -79,7 +75,7 @@ class GenomeGraphs(Tabular):
         super().__init__(**kwd)
         self.add_display_app("ucsc", "Genome Graph", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.markerCol = 1
         header = open(dataset.file_name).readlines()[0].strip().split("\t")
@@ -88,13 +84,13 @@ class GenomeGraphs(Tabular):
         t[0] = "string"
         dataset.metadata.column_types = t
 
-    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObjType, str]:
         """
         Returns file
         """
         return open(dataset.file_name, "rb")
 
-    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         """
         from the ever-helpful angie hinrichs angie@soe.ucsc.edu
         a genome graphs call looks like this
@@ -146,7 +142,7 @@ class GenomeGraphs(Tabular):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def make_html_table(self, dataset: Peekable, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol, **kwargs) -> str:
         """
         Create HTML table, used for displaying peek
         """
@@ -177,7 +173,7 @@ class GenomeGraphs(Tabular):
         except Exception as exc:
             return f"Can't create peek {exc}"
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         """
         Validate a gg file - all numeric after header row
         """
@@ -241,7 +237,7 @@ class rgTabList(Tabular):
         super().__init__(**kwd)
         self.column_names = []
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -306,7 +302,7 @@ class Rgenetics(Html):
     composite_type = "auto_primary_file"
     file_ext = "rgenetics"
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Rgenetics Galaxy Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -323,7 +319,7 @@ class Rgenetics(Html):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -345,7 +341,7 @@ class Rgenetics(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         for lped/pbed eg
 
@@ -385,7 +381,7 @@ class SNPMatrix(Rgenetics):
 
     file_ext = "snpmatrix"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Binary RGenetics file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -581,7 +577,7 @@ class IdeasPre(Html):
         self.add_composite_file("IDEAS_input_config.txt", description="IDEAS input config", is_binary=False)
         self.add_composite_file("tmp.tar.gz", description="Compressed archive of compressed bed files", is_binary=True)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         for fname in os.listdir(dataset.extra_files_path):
             if fname.startswith("chromosomes"):
@@ -594,7 +590,7 @@ class IdeasPre(Html):
                 dataset.metadata.tmp_archive = os.path.join(dataset.extra_files_path, fname)
         self.regenerate_primary_file(dataset)
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
         rval.append("<ul>")
@@ -604,7 +600,7 @@ class IdeasPre(Html):
         rval.append("</ul></body></html>\n")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         # Cannot do this until we are setting metadata.
         rval = ["<html><head></head><body>"]
         rval.append("<h3>Files prepared for IDEAS</h3>")
@@ -658,7 +654,7 @@ class RexpBase(Html):
             is_binary=False,
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -768,7 +764,7 @@ class RexpBase(Html):
             p = []
         return "\n".join(p)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """
         expects a .pheno file in the extra_files_dir - ugh
         note that R is weird and does not include the row.name in
@@ -817,7 +813,7 @@ class RexpBase(Html):
         except Exception:
             return "## rexpression get_file_peek: no file found"
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -838,7 +834,7 @@ class RexpBase(Html):
         if copy_from:
             dataset.metadata = copy_from.metadata
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         NOTE we apply the tabular machinary to the phenodata extracted
         from a BioC eSet or affybatch.
@@ -914,7 +910,7 @@ class RexpBase(Html):
         except Exception as exc:
             return f"Can't create html table {unicodify(exc)}"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """
         Returns formatted html of peek
         """
diff --git a/lib/galaxy/datatypes/gis.py b/lib/galaxy/datatypes/gis.py
index 946630b45d1..b3b37dce200 100644
--- a/lib/galaxy/datatypes/gis.py
+++ b/lib/galaxy/datatypes/gis.py
@@ -2,8 +2,8 @@
 GIS classes
 """
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.binary import Binary
 
@@ -64,7 +64,7 @@ class Shapefile(Binary):
             "shapefile.shp.xml", description="Geospatial metadata in XML format (xml)", is_binary=False, optional=True
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Shapefile Galaxy Composite Dataset</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -81,7 +81,7 @@ class Shapefile(Binary):
         rval.append("</ul></div></html>\n")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "Shapefile data"
@@ -90,7 +90,7 @@ class Shapefile(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/goldenpath.py b/lib/galaxy/datatypes/goldenpath.py
index e67d5fec964..e3204ac3067 100644
--- a/lib/galaxy/datatypes/goldenpath.py
+++ b/lib/galaxy/datatypes/goldenpath.py
@@ -6,7 +6,7 @@ from typing import (
     Union,
 )
 
-from galaxy.datatypes._protocols import SetsMetadata
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -24,7 +24,7 @@ class GoldenPath(Tabular):
     edam_format = "format_3693"
     file_ext = "agp"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         # AGPFile reads and validates entire file.
         AGPFile(dataset.file_name)
         super().set_meta(dataset, overwrite=overwrite, **kwd)
diff --git a/lib/galaxy/datatypes/graph.py b/lib/galaxy/datatypes/graph.py
index 37c5763e767..3ecea4e1ede 100644
--- a/lib/galaxy/datatypes/graph.py
+++ b/lib/galaxy/datatypes/graph.py
@@ -4,10 +4,7 @@ Graph content classes.
 import logging
 from typing import List
 
-from galaxy.datatypes._protocols import (
-    Peekable,
-    ProvidesDataSource,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.dataproviders.column import ColumnarDataProvider
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
@@ -31,7 +28,7 @@ class Xgmml(xml.GenericXml):
 
     file_ext = "xgmml"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -61,7 +58,7 @@ class Xgmml(xml.GenericXml):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", XMLDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: ProvidesDataSource, **settings) -> "XGMMLGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: DatasetProtocol, **settings) -> "XGMMLGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return XGMMLGraphDataProvider(dataset_source, **settings)
 
@@ -79,7 +76,7 @@ class Sif(tabular.Tabular):
 
     file_ext = "sif"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """
         Set the peek and blurb text
         """
@@ -101,7 +98,7 @@ class Sif(tabular.Tabular):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("node-edge", ColumnarDataProvider.settings)
-    def node_edge_dataprovider(self, dataset: ProvidesDataSource, **settings) -> "SIFGraphDataProvider":
+    def node_edge_dataprovider(self, dataset: DatasetProtocol, **settings) -> "SIFGraphDataProvider":
         dataset_source = DatasetDataProvider(dataset)
         return SIFGraphDataProvider(dataset_source, **settings)
 
diff --git a/lib/galaxy/datatypes/hdf5.py b/lib/galaxy/datatypes/hdf5.py
index f9b18747155..2bc15251420 100644
--- a/lib/galaxy/datatypes/hdf5.py
+++ b/lib/galaxy/datatypes/hdf5.py
@@ -5,7 +5,7 @@ This datatype was created for use with the iSEE interactive tool.
 from typing import Optional
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
+    HasExtraFilesAndMetadata,
     HasMetadata,
 )
 from galaxy.datatypes.data import Data
@@ -55,7 +55,7 @@ class HDF5SummarizedExperiment(Data):
         """Override parent init metadata."""
         Data.init_meta(self, dataset, copy_from=copy_from)
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """Generate primary file to represent dataset."""
         return f"""
               <html>
diff --git a/lib/galaxy/datatypes/images.py b/lib/galaxy/datatypes/images.py
index 7a35f2ea4f1..6576b88b871 100644
--- a/lib/galaxy/datatypes/images.py
+++ b/lib/galaxy/datatypes/images.py
@@ -11,9 +11,8 @@ import numpy as np
 import tifffile
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
-    SetsMetadata,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
@@ -54,7 +53,7 @@ class Image(data.Data):
         super().__init__(**kwd)
         self.image_formats = [self.file_ext.upper()]
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Image in {dataset.extension} format"
             dataset.blurb = nice_size(dataset.get_size())
@@ -66,7 +65,7 @@ class Image(data.Data):
         """Determine if the file is in this format"""
         return check_image_type(filename, self.image_formats)
 
-    def handle_dataset_as_image(self, hda: Peekable) -> str:
+    def handle_dataset_as_image(self, hda: DatasetProtocol) -> str:
         dataset = hda.dataset
         name = hda.name or ""
         with open(dataset.file_name, "rb") as f:
@@ -106,7 +105,7 @@ class OMETiff(Tiff):
     )
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         spec_key = "offsets"
         offsets_file = dataset.metadata.offsets
@@ -381,7 +380,7 @@ class Analyze75(Binary):
 
         self.add_composite_file("t2m", description="The Analyze75 t2m file.", optional=True, is_binary=True)
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Analyze75 Composite Dataset.</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -491,7 +490,7 @@ class Star(data.Text):
 
     file_ext = "star"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/interval.py b/lib/galaxy/datatypes/interval.py
index 2384b849067..a21cb2368c4 100644
--- a/lib/galaxy/datatypes/interval.py
+++ b/lib/galaxy/datatypes/interval.py
@@ -22,13 +22,9 @@ from bx.intervals.io import (
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
+    DatasetProtocol,
     HasId,
     HasMetadata,
-    Peekable,
-    ProvidesDataSource,
-    ProvidesDisplayLinks,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.data import DatatypeValidation
 from galaxy.datatypes.dataproviders.dataset import (
@@ -132,7 +128,7 @@ class Interval(Tabular):
         Tabular.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: SetsMetadata, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
+        self, dataset: DatasetProtocol, *, overwrite: bool = True, first_line_is_header: bool = False, **kwd
     ) -> None:
         """Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=0)
@@ -193,7 +189,7 @@ class Interval(Tabular):
                     else:
                         empty_line_count += 1
 
-    def displayable(self, dataset: ProvidesDisplayLinks) -> bool:
+    def displayable(self, dataset: DatasetProtocol) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -210,7 +206,7 @@ class Interval(Tabular):
 
     def get_estimated_display_viewport(
         self,
-        dataset: ProvidesDisplayLinks,
+        dataset: DatasetProtocol,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -272,7 +268,7 @@ class Interval(Tabular):
             log.exception("Exception caught attempting to generate viewport for dataset '%d'", dataset.id)
         return (None, None, None)
 
-    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data"""
         with tempfile.NamedTemporaryFile(delete=False, mode="w") as fh:
             c, s, e, t, n = (
@@ -306,7 +302,7 @@ class Interval(Tabular):
                     fh.write("%s\n" % "\t".join(tmp))
             return compression_utils.get_fileobj(fh.name, mode="rb")
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset,
@@ -319,7 +315,7 @@ class Interval(Tabular):
             },
         )
 
-    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         """
         Generate links to UCSC genome browser sites based on the dbkey
         and content of dataset.
@@ -353,7 +349,7 @@ class Interval(Tabular):
             ret_val.append((site_name, link))
         return ret_val
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         """Validate an interval file using the bx GenomicIntervalReader"""
         c, s, e, t = (
             dataset.metadata.chromCol,
@@ -408,20 +404,20 @@ class Interval(Tabular):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: ProvidesDataSource, **settings) -> IntervalDataProvider:
+    def interval_dataprovider(self, dataset: DatasetProtocol, **settings) -> IntervalDataProvider:
         return IntervalDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> IntervalDataProvider:
+    def interval_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> IntervalDataProvider:
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -434,7 +430,7 @@ class BedGraph(Interval):
     track_type = "LineTrack"
     data_sources = {"data": "bigwig", "index": "bigwig"}
 
-    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObjType, str]:
         """
         Returns file contents as is with no modifications.
         TODO: this is a functional stub and will need to be enhanced moving forward to provide additional support for bedgraph.
@@ -443,7 +439,7 @@ class BedGraph(Interval):
 
     def get_estimated_display_viewport(
         self,
-        dataset: ProvidesDisplayLinks,
+        dataset: DatasetProtocol,
         chrom_col: Optional[int] = 0,
         start_col: Optional[int] = 1,
         end_col: Optional[int] = 2,
@@ -502,7 +498,7 @@ class Bed(Interval):
     )
     # do we need to repeat these? they are the same as should be inherited from interval type
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """Sets the metadata information for datasets previously determined to be in bed format."""
         if dataset.has_data():
             i = 0
@@ -523,7 +519,7 @@ class Bed(Interval):
                         break
             Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObjType, str]:
         """Returns file contents with only the bed data. If bed 6+, treat as interval."""
         for line in open(dataset.file_name):
             line = line.strip()
@@ -735,7 +731,7 @@ class BedStrict(Bed):
         Tabular.__init__(self, **kwd)
         self.clear_display_apps()  # only new style display applications for this datatype
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, **kwd)  # need column count first
         if dataset.metadata.columns >= 4:
             dataset.metadata.nameCol = 4
@@ -819,7 +815,7 @@ class Gff(Tabular, _RemoteCallMixin):
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
-    def set_attribute_metadata(self, dataset: SetsMetadata) -> None:
+    def set_attribute_metadata(self, dataset: DatasetProtocol) -> None:
         """
         Sets metadata elements for dataset's attributes.
         """
@@ -859,7 +855,7 @@ class Gff(Tabular, _RemoteCallMixin):
         dataset.metadata.attribute_types = attribute_types
         dataset.metadata.attributes = len(attribute_types)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
 
         i = 0
@@ -877,12 +873,12 @@ class Gff(Tabular, _RemoteCallMixin):
                             pass
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=i)
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
     def get_estimated_display_viewport(
-        self, dataset: ProvidesDisplayLinks
+        self, dataset: DatasetProtocol
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """
         Return a chrom, start, stop tuple for viewing a file.  There are slight differences between gff 2 and gff 3
@@ -958,7 +954,7 @@ class Gff(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -971,7 +967,7 @@ class Gff(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def gbrowse_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         ret_val = []
         seqid, start, stop = self.get_estimated_display_viewport(dataset)
         if seqid is not None:
@@ -1037,20 +1033,20 @@ class Gff(Tabular, _RemoteCallMixin):
     # ------------- Dataproviders
     # redefine bc super is Tabular
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 3, 4, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval", IntervalDataProvider.settings)
-    def interval_dataprovider(self, dataset: ProvidesDataSource, **settings):
+    def interval_dataprovider(self, dataset: DatasetProtocol, **settings):
         return IntervalDataProvider(dataset, 0, 3, 4, 6, 2, **settings)
 
     @dataproviders.decorators.dataprovider_factory("interval-dict", IntervalDataProvider.settings)
-    def interval_dict_dataprovider(self, dataset: ProvidesDataSource, **settings):
+    def interval_dict_dataprovider(self, dataset: DatasetProtocol, **settings):
         settings["named_columns"] = True
         return self.interval_dataprovider(dataset, **settings)
 
@@ -1078,7 +1074,7 @@ class Gff3(Gff):
         """Initialize datatype, by adding GBrowse display app"""
         Gff.__init__(self, **kwd)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         self.set_attribute_metadata(dataset)
         i = 0
         with compression_utils.get_fileobj(dataset.file_name) as in_fh:
@@ -1294,7 +1290,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
         self.add_display_app("gbrowse", "display in Gbrowse", "as_gbrowse_display_file", "gbrowse_links")
 
     def get_estimated_display_viewport(
-        self, dataset: ProvidesDisplayLinks
+        self, dataset: DatasetProtocol
     ) -> Tuple[Optional[str], Optional[str], Optional[str]]:
         """Return a chrom, start, stop tuple for viewing a file."""
         viewport_feature_count = 100  # viewport should check at least 100 features; excludes comment lines
@@ -1360,7 +1356,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def gbrowse_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def gbrowse_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1373,7 +1369,7 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1386,11 +1382,11 @@ class Wiggle(Tabular, _RemoteCallMixin):
                     ret_val.append((site_name, link))
         return ret_val
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         max_data_lines = None
         i = 0
         for i, line in enumerate(open(dataset.file_name)):  # noqa: B007
@@ -1448,12 +1444,12 @@ class Wiggle(Tabular, _RemoteCallMixin):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("wiggle", WiggleDataProvider.settings)
-    def wiggle_dataprovider(self, dataset: ProvidesDataSource, **settings) -> WiggleDataProvider:
+    def wiggle_dataprovider(self, dataset: DatasetProtocol, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return WiggleDataProvider(dataset_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("wiggle-dict", WiggleDataProvider.settings)
-    def wiggle_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> WiggleDataProvider:
+    def wiggle_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> WiggleDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         settings["named_columns"] = True
         return WiggleDataProvider(dataset_source, **settings)
@@ -1471,16 +1467,16 @@ class CustomTrack(Tabular):
         Tabular.__init__(self, **kwd)
         self.add_display_app("ucsc", "display at UCSC", "as_ucsc_display_file", "ucsc_links")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         Tabular.set_meta(self, dataset, overwrite=overwrite, skip=1)
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, skipchars=["track", "#"])
 
     def get_estimated_display_viewport(
         self,
-        dataset: ProvidesDisplayLinks,
+        dataset: DatasetProtocol,
         chrom_col: Optional[int] = None,
         start_col: Optional[int] = None,
         end_col: Optional[int] = None,
@@ -1542,7 +1538,7 @@ class CustomTrack(Tabular):
                 log.exception("Unexpected error")
         return (None, None, None)  # could not determine viewport
 
-    def ucsc_links(self, dataset: ProvidesDisplayLinks, type: str, app, base_url: str) -> List:
+    def ucsc_links(self, dataset: DatasetProtocol, type: str, app, base_url: str) -> List:
         ret_val = []
         chrom, start, stop = self.get_estimated_display_viewport(dataset)
         if chrom is not None:
@@ -1787,7 +1783,7 @@ class IntervalTabix(Interval):
     # Ideally the tabix_index would be regenerated when the metadataElements are updated
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         first_line_is_header: bool = False,
         metadata_tmp_files_dir: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/isa.py b/lib/galaxy/datatypes/isa.py
index bf1a172ca8e..38edcd22dfd 100644
--- a/lib/galaxy/datatypes/isa.py
+++ b/lib/galaxy/datatypes/isa.py
@@ -27,10 +27,10 @@ from markupsafe import escape
 
 from galaxy import util
 from galaxy.datatypes._protocols import (
-    Displayable,
-    GeneratesPrimaryFile,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
     HasExtraFilesPath,
-    Peekable,
 )
 from galaxy.datatypes.data import Data
 from galaxy.util.compression_utils import CompressedFile
@@ -162,7 +162,7 @@ class _Isa(Data):
     # Set peek {{{2
     ################################################################
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text. Get first lines of the main file and set it as the peek."""
 
         main_file = self._get_main_file(dataset)
@@ -188,7 +188,7 @@ class _Isa(Data):
     # Display peek {{{2
     ################################################################
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create the HTML table used for displaying peek, from the peek text found by set_peek() method."""
 
         out = ['<table cellspacing="0" cellpadding="3">']
@@ -209,7 +209,7 @@ class _Isa(Data):
     # Generate primary file {{{2
     ################################################################
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """Generate the primary file. It is an HTML file containing description of the composite dataset
         as well as a list of the composite files that it contains."""
 
@@ -268,7 +268,7 @@ class _Isa(Data):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
diff --git a/lib/galaxy/datatypes/media.py b/lib/galaxy/datatypes/media.py
index 2ff4e8905a4..1b7baf4ddd7 100644
--- a/lib/galaxy/datatypes/media.py
+++ b/lib/galaxy/datatypes/media.py
@@ -8,7 +8,7 @@ from typing import (
     Tuple,
 )
 
-from galaxy.datatypes._protocols import SetsMetadata
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -72,7 +72,7 @@ class Audio(Binary):
         no_value=0,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
 
@@ -159,7 +159,7 @@ class Video(Binary):
             w = h = fps = 0
         return w, h, fps
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if which("ffprobe"):
             metadata, streams = ffprobe(dataset.file_name)
             (w, h, fps) = self._get_resolution(streams)
@@ -280,7 +280,7 @@ class Wav(Audio):
         with wave.open(filename, "rb"):
             return True
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents."""
         try:
             with wave.open(dataset.dataset.file_name, "rb") as fd:
diff --git a/lib/galaxy/datatypes/microarrays.py b/lib/galaxy/datatypes/microarrays.py
index f89881bb23c..1aeea27a6c5 100644
--- a/lib/galaxy/datatypes/microarrays.py
+++ b/lib/galaxy/datatypes/microarrays.py
@@ -1,10 +1,7 @@
 import logging
 
 from galaxy.datatypes import data
-from galaxy.datatypes._protocols import (
-    Peekable,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import Cel  # noqa: F401
 from galaxy.datatypes.data import get_file_peek
 from galaxy.datatypes.metadata import MetadataElement
@@ -80,7 +77,7 @@ class GenericMicroarrayFile(data.Text):
         name="block_type", default=0, desc="Type of block", readonly=True, visible=True, optional=True, no_value=0
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.block_count == 1:
                 dataset.blurb = f"{dataset.metadata.file_type} {dataset.metadata.version_number}: Format {dataset.metadata.file_format}, 1 block, {dataset.metadata.number_of_optional_header_records} headers and {dataset.metadata.number_of_data_columns} columns"
@@ -120,7 +117,7 @@ class Gal(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix ArrayList" in headers[2][0]
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gal file.
         """
@@ -162,7 +159,7 @@ class Gpr(GenericMicroarrayFile):
         headers = get_headers(file_prefix, sep="\t", count=3)
         return "ATF" in headers[0][0] and "GenePix Results" in headers[2][0]
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Gpr file.
         """
diff --git a/lib/galaxy/datatypes/molecules.py b/lib/galaxy/datatypes/molecules.py
index 258e81a4a1b..69fbc1a4515 100644
--- a/lib/galaxy/datatypes/molecules.py
+++ b/lib/galaxy/datatypes/molecules.py
@@ -8,10 +8,7 @@ from typing import (
 )
 
 from galaxy.datatypes import metadata
-from galaxy.datatypes._protocols import (
-    Peekable,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -72,7 +69,7 @@ class GenericMolFile(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -204,7 +201,7 @@ class GenericMolFile(Text):
 class MOL(GenericMolFile):
     file_ext = "mol"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number molecules, in the case of MOL its always one.
         """
@@ -257,7 +254,7 @@ class SDF(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of molecules in dataset.
         """
@@ -340,7 +337,7 @@ class MOL2(GenericMolFile):
                 break
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -426,7 +423,7 @@ class FPS(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -531,7 +528,7 @@ class OBFS(Binary):
         self.add_composite_file("molecule.mol2", optional=True, is_binary=False, description="Molecule File")
         self.add_composite_file("molecule.cml", optional=True, is_binary=False, description="Molecule File")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "OpenBabel Fastsearch Index"
@@ -540,7 +537,7 @@ class OBFS(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -567,7 +564,7 @@ class OBFS(Binary):
 class DRF(GenericMolFile):
     file_ext = "drf"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
@@ -581,7 +578,7 @@ class PHAR(GenericMolFile):
 
     file_ext = "phar"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "pharmacophore"
@@ -634,7 +631,7 @@ class PDB(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Find Chain_IDs for metadata.
         """
@@ -650,7 +647,7 @@ class PDB(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -703,7 +700,7 @@ class PDBQT(GenericMolFile):
         else:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             root_numbers = count_special_lines("^ROOT", dataset.file_name)
             branch_numbers = count_special_lines("^BRANCH", dataset.file_name)
@@ -788,7 +785,7 @@ class PQR(GenericMolFile):
         else:
             return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Find Optional Chain_IDs for metadata.
         """
@@ -807,7 +804,7 @@ class PQR(GenericMolFile):
             log.error("Error finding chain_ids: %s", unicodify(e))
             raise
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             atom_numbers = count_special_lines("^ATOM", dataset.file_name)
             hetatm_numbers = count_special_lines("^HETATM", dataset.file_name)
@@ -885,7 +882,7 @@ class Cell(GenericMolFile):
                 return True
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -925,7 +922,7 @@ class Cell(GenericMolFile):
                 dataset.metadata.is_periodic = bool(pbc.any())
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1046,7 +1043,7 @@ class CIF(GenericMolFile):
                 return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1092,7 +1089,7 @@ class CIF(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1243,7 +1240,7 @@ class XYZ(GenericMolFile):
                     raise
         return blocks
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Find Atom IDs for metadata.
         """
@@ -1290,7 +1287,7 @@ class XYZ(GenericMolFile):
             dataset.metadata.is_periodic = is_periodic
             dataset.metadata.lattice_parameters = list(lattice_parameters)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.info = self.get_dataset_info(dataset.metadata)
@@ -1445,7 +1442,7 @@ class ExtendedXYZ(XYZ):
             blocks.append({"number_of_atoms": n_atoms, "comment": comment, "atom_data": atoms})
         return blocks
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         super().set_peek(dataset)
         dataset.blurb = "Extended " + dataset.blurb
 
@@ -1453,7 +1450,7 @@ class ExtendedXYZ(XYZ):
 class grd(Text):
     file_ext = "grd"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "grids for docking"
@@ -1465,7 +1462,7 @@ class grd(Text):
 class grdtgz(Binary):
     file_ext = "grd.tgz"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "binary data"
             dataset.blurb = "compressed grids for docking"
@@ -1497,13 +1494,13 @@ class InChI(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1562,13 +1559,13 @@ class SMILES(Tabular):
         no_value=0,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = self.count_data_lines(dataset)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1598,13 +1595,13 @@ class CML(GenericXml):
         no_value=0,
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of lines of data in dataset.
         """
         dataset.metadata.number_of_molecules = count_special_lines(r"^\s*<molecule", dataset.file_name)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_molecules == 1:
                 dataset.blurb = "1 molecule"
@@ -1762,7 +1759,7 @@ class GRO(GenericMolFile):
                 return False
         return True
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             atom_number = int(dataset.peek.split("\n")[1])
diff --git a/lib/galaxy/datatypes/mothur.py b/lib/galaxy/datatypes/mothur.py
index 5605dea13e4..c798e6fd14e 100644
--- a/lib/galaxy/datatypes/mothur.py
+++ b/lib/galaxy/datatypes/mothur.py
@@ -9,9 +9,8 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
+    DatasetProtocol,
     HasMetadata,
-    Peekable,
-    SetsMetadata,
 )
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import MetadataElement
@@ -37,7 +36,7 @@ class Otu(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set metadata for Otu files.
 
@@ -174,7 +173,7 @@ class GroupAbund(Otu):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, skip: Optional[int] = 1, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         # See if file starts with header line
@@ -298,7 +297,7 @@ class AlignCheck(Tabular):
         self.column_types = ["str", "int", "int", "int", "int", "int", "int", "int"]
         self.comment_lines = 1
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
 
         dataset.metadata.column_names = self.column_names
@@ -355,7 +354,7 @@ class DistanceMatrix(Text):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, skip: Optional[int] = 0, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
         headers = iter_headers(dataset.file_name, sep="\t")
@@ -508,7 +507,7 @@ class PairwiseDistanceMatrix(DistanceMatrix, Tabular):
         self.column_names = ["Sequence", "Sequence", "Distance"]
         self.column_types = ["str", "str", "float"]
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, skip: Optional[int] = None, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, skip=skip, **kwd)
 
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
@@ -598,7 +597,7 @@ class Group(Tabular):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = None,
@@ -846,7 +845,7 @@ class CountTable(Tabular):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1058,7 +1057,7 @@ class SffFlow(Tabular):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = 1,
         max_data_lines: Optional[int] = None,
@@ -1073,7 +1072,7 @@ class SffFlow(Tabular):
         except Exception as e:
             log.warning(f"SffFlow set_meta {e}")
 
-    def make_html_table(self, dataset: Peekable, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol, skipchars: Optional[List] = None, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
diff --git a/lib/galaxy/datatypes/msa.py b/lib/galaxy/datatypes/msa.py
index 2a56e9b8d76..901709c0f16 100644
--- a/lib/galaxy/datatypes/msa.py
+++ b/lib/galaxy/datatypes/msa.py
@@ -8,10 +8,7 @@ from typing import (
     List,
 )
 
-from galaxy.datatypes._protocols import (
-    Peekable,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -57,7 +54,7 @@ class InfernalCM(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_of_models == 1:
@@ -81,7 +78,7 @@ class InfernalCM(Text):
         """
         return file_prefix.startswith("INFERNAL")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models and the version of CM file in dataset.
         """
@@ -97,7 +94,7 @@ class Hmmer(Text):
     edam_data = "data_1364"
     edam_format = "format_1370"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "HMMER Database"
@@ -105,7 +102,7 @@ class Hmmer(Text):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disc"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -140,7 +137,7 @@ class HmmerPress(Binary):
     file_ext = "hmmpress"
     composite_type = "basic"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "HMMER Binary database"
@@ -149,7 +146,7 @@ class HmmerPress(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -184,7 +181,7 @@ class Stockholm_1_0(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -198,7 +195,7 @@ class Stockholm_1_0(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.search(STOCKHOLM_SEARCH_PATTERN)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
 
         Set the number of models in dataset.
@@ -275,7 +272,7 @@ class MauveXmfa(Text):
         no_value=0,
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             if dataset.metadata.number_of_models == 1:
                 dataset.blurb = "1 alignment"
@@ -289,7 +286,7 @@ class MauveXmfa(Text):
     def sniff_prefix(self, file_prefix: FilePrefix) -> bool:
         return file_prefix.startswith("#FormatVersion Mauve1")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         dataset.metadata.number_of_models = generic_util.count_special_lines(
             "^#Sequence([[:digit:]]+)Entry", dataset.file_name
         )
diff --git a/lib/galaxy/datatypes/neo4j.py b/lib/galaxy/datatypes/neo4j.py
index 24d7c016d43..27fede42da8 100644
--- a/lib/galaxy/datatypes/neo4j.py
+++ b/lib/galaxy/datatypes/neo4j.py
@@ -4,8 +4,8 @@ Neo4j Composite Dataset
 import logging
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.images import Html
@@ -22,7 +22,7 @@ class Neo4j(Html):
     stored in extra files path
     """
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -45,7 +45,7 @@ class Neo4j(Html):
         """Returns the mime type of the datatype"""
         return "text/html"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = "Neo4j database (multiple files)"
@@ -54,7 +54,7 @@ class Neo4j(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
diff --git a/lib/galaxy/datatypes/ngsindex.py b/lib/galaxy/datatypes/ngsindex.py
index b506b3d7478..2da0df85d96 100644
--- a/lib/galaxy/datatypes/ngsindex.py
+++ b/lib/galaxy/datatypes/ngsindex.py
@@ -5,9 +5,8 @@ import logging
 import os
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
-    SetsMetadata,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from .metadata import MetadataElement
 from .text import Html
@@ -38,14 +37,14 @@ class BowtieIndex(Html):
 
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
         """
         return "<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>"
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -62,7 +61,7 @@ class BowtieIndex(Html):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"Bowtie index file ({dataset.metadata.sequence_space})"
             dataset.blurb = f"{dataset.metadata.sequence_space} space"
@@ -70,7 +69,7 @@ class BowtieIndex(Html):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/phylip.py b/lib/galaxy/datatypes/phylip.py
index e7da80b3314..5c468fe77eb 100644
--- a/lib/galaxy/datatypes/phylip.py
+++ b/lib/galaxy/datatypes/phylip.py
@@ -10,10 +10,7 @@ Phylip datatype sniffer
 from typing import TYPE_CHECKING
 
 from galaxy import util
-from galaxy.datatypes._protocols import (
-    Peekable,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -41,7 +38,7 @@ class Phylip(Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -51,7 +48,7 @@ class Phylip(Text):
         except Exception:
             raise Exception("Header does not correspond to PHYLIP header.")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
diff --git a/lib/galaxy/datatypes/plant_tribes.py b/lib/galaxy/datatypes/plant_tribes.py
index cf93e7b446d..929a648deb5 100644
--- a/lib/galaxy/datatypes/plant_tribes.py
+++ b/lib/galaxy/datatypes/plant_tribes.py
@@ -1,10 +1,7 @@
 import logging
 import re
 
-from galaxy.datatypes._protocols import (
-    Peekable,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.data import (
     get_file_peek,
     Text,
@@ -25,13 +22,13 @@ log = logging.getLogger(__name__)
 class Smat(Text):
     file_ext = "smat"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"ESTScan scores matrices ({nice_size(dataset.get_size())})"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "ESTScan scores matrices"
@@ -97,13 +94,13 @@ class PlantTribesKsComponents(Tabular):
         no_value=0,
     )
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
             return f"Significant components in the Ks distribution ({nice_size(dataset.get_size())})"
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of significant components in the Ks distribution.
         The dataset will always be on the order of less than 10 lines.
@@ -125,7 +122,7 @@ class PlantTribesKsComponents(Tabular):
         if len(significant_components) > 0:
             dataset.metadata.number_comp = max(significant_components)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             if dataset.metadata.number_comp == 1:
diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 58fe41e1ece..8b328580d68 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -11,9 +11,8 @@ from typing import (
 
 from galaxy.datatypes import data
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
-    SetsMetadata,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import Text
@@ -56,7 +55,7 @@ class Wiff(Binary):
             is_binary=True,
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Wiff Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -104,7 +103,7 @@ class MzTab(Text):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -155,7 +154,7 @@ class MzTab2(MzTab):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -200,7 +199,7 @@ class Kroenik(Tabular):
             "Modifications",
         ]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -239,7 +238,7 @@ class PepList(Tabular):
         super().__init__(**kwd)
         self.column_names = ["m/z", "rt(min)", "snr", "charge", "intensity"]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -276,7 +275,7 @@ class PSMS(Tabular):
         super().__init__(**kwd)
         self.column_names = ["PSMId", "score", "q-value", "posterior_error_prob", "peptide", "proteinIds"]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -336,7 +335,7 @@ class PepXmlReport(Tabular):
             "Interprophet Probability",
         ]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -377,7 +376,7 @@ class ProtXmlReport(Tabular):
             "Is Evidence?",
         ]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -392,7 +391,7 @@ class Dta(TabularData):
     file_ext = "dta"
     comment_lines = 0
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         column_types = []
         data_row: List = []
         data_lines = 0
@@ -465,7 +464,7 @@ class Dta2d(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         if dataset.has_data():
@@ -601,7 +600,7 @@ class Edta(TabularData):
                 line[idx] += str(idx // 4)
         return line
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
         delim = None
         tpe = None
@@ -675,7 +674,7 @@ class ProteomicsXml(GenericXml):
         pattern = r"<(\w*:)?%s" % self.root
         return re.search(pattern, line) is not None
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -844,7 +843,7 @@ class Mgf(Text):
     edam_format = "format_3651"
     file_ext = "mgf"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -874,7 +873,7 @@ class MascotDat(Text):
     edam_format = "format_3713"
     file_ext = "mascotdat"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -918,7 +917,7 @@ class ThermoRAW(Binary):
         except Exception:
             return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Thermo Finnigan RAW file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -926,7 +925,7 @@ class ThermoRAW(Binary):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -960,7 +959,7 @@ class SPLibNoIndex(Text):
 
     file_ext = "splib_noindex"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -985,7 +984,7 @@ class SPLib(Msp):
         self.add_composite_file("library.spidx", description="Spectrum index", is_binary=False)
         self.add_composite_file("library.pepidx", description="Peptide index", is_binary=False)
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Spectral Library Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -1002,7 +1001,7 @@ class SPLib(Msp):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1074,7 +1073,7 @@ class ImzML(Binary):
 
         self.add_composite_file("ibd", description="The mass spectral data component.", is_binary=True)
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>imzML Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
diff --git a/lib/galaxy/datatypes/qiime2.py b/lib/galaxy/datatypes/qiime2.py
index 20531cd00ee..987ca9576a6 100644
--- a/lib/galaxy/datatypes/qiime2.py
+++ b/lib/galaxy/datatypes/qiime2.py
@@ -12,9 +12,8 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
+    DatasetProtocol,
     HasMetadata,
-    Peekable,
-    SetsMetadata,
 )
 from galaxy.datatypes.binary import CompressedZipArchive
 from galaxy.datatypes.metadata import MetadataElement
@@ -34,7 +33,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
     MetadataElement(name="format", optional=True, no_value="", readonly=True)
     MetadataElement(name="version", readonly=True)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         metadata = _get_metadata_from_archive(dataset.file_name)
         for key, value in metadata.items():
             if value:
@@ -42,7 +41,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.metadata.semantic_type_simple = _strip_properties(dataset.metadata.semantic_type)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if dataset.metadata.semantic_type == "Visualization":
             dataset.blurb = "QIIME 2 Visualization"
         else:
@@ -50,7 +49,7 @@ class _QIIME2ResultBase(CompressedZipArchive):
 
         dataset.peek = "\n".join(map(": ".join, self._peek(dataset)))
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         def make_row(item):
             return "<tr><th>%s</th><td>%s</td></td>" % tuple(html.escape(x) for x in item)
 
@@ -116,7 +115,7 @@ class QIIME2Metadata(Tabular):
     def get_column_names(self, first_line: str) -> Optional[List[str]]:
         return first_line.strip().split("\t")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Let Galaxy's Tabular format handle most of this. We will just jump
         in at the last minute to (potentially) override some column types.
diff --git a/lib/galaxy/datatypes/qualityscore.py b/lib/galaxy/datatypes/qualityscore.py
index ccb3e3a6980..8349fe9a070 100644
--- a/lib/galaxy/datatypes/qualityscore.py
+++ b/lib/galaxy/datatypes/qualityscore.py
@@ -3,7 +3,7 @@ Qualityscore class
 """
 import logging
 
-from galaxy.datatypes._protocols import SetsMetadata
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -66,7 +66,7 @@ class QualityScoreSOLiD(QualityScore):
                     return False
         return goodblock > 0
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             return
diff --git a/lib/galaxy/datatypes/registry.py b/lib/galaxy/datatypes/registry.py
index fd19d7d33ec..b6bc708cfc2 100644
--- a/lib/galaxy/datatypes/registry.py
+++ b/lib/galaxy/datatypes/registry.py
@@ -20,7 +20,7 @@ from typing import (
 import yaml
 
 import galaxy.util
-from galaxy.datatypes._protocols import DatasetProtocol5
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.tool_util.edam_util import load_edam_tree
 from galaxy.util import RW_R__R__
 from galaxy.util.bunch import Bunch
@@ -831,8 +831,8 @@ class Registry:
         return None
 
     def find_conversion_destination_for_dataset_by_extensions(
-        self, dataset_or_ext: Union[str, DatasetProtocol5], accepted_formats: List[str], converter_safe: bool = True
-    ) -> Tuple[bool, Optional[str], Optional[DatasetProtocol5]]:
+        self, dataset_or_ext: Union[str, DatasetProtocol], accepted_formats: List[str], converter_safe: bool = True
+    ) -> Tuple[bool, Optional[str], Optional[DatasetProtocol]]:
         """
         returns (direct_match, converted_ext, converted_dataset)
         - direct match is True iff no the data set already has an accepted format
@@ -840,7 +840,7 @@ class Registry:
         """
         if hasattr(dataset_or_ext, "ext"):
             ext = dataset_or_ext.ext
-            dataset = cast(DatasetProtocol5, dataset_or_ext)
+            dataset = cast(DatasetProtocol, dataset_or_ext)
         else:
             ext = dataset_or_ext
             dataset = None
diff --git a/lib/galaxy/datatypes/sequence.py b/lib/galaxy/datatypes/sequence.py
index ef94f2ea49c..7eef083dfcb 100644
--- a/lib/galaxy/datatypes/sequence.py
+++ b/lib/galaxy/datatypes/sequence.py
@@ -25,11 +25,9 @@ from markupsafe import escape
 from galaxy import util
 from galaxy.datatypes import metadata
 from galaxy.datatypes._protocols import (
-    Displayable,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
     HasMetadata,
-    Peekable,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.binary import Binary
 from galaxy.datatypes.data import DatatypeValidation
@@ -71,7 +69,7 @@ class SequenceSplitLocations(data.Text):
 
     file_ext = "fqtoc"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             try:
                 parsed_data = json.load(open(dataset.file_name))
@@ -108,7 +106,7 @@ class Sequence(data.Text):
         name="sequences", default=0, desc="Number of sequences", readonly=True, visible=False, optional=True, no_value=0
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines in dataset.
         """
@@ -128,7 +126,7 @@ class Sequence(data.Text):
             dataset.metadata.data_lines = data_lines
             dataset.metadata.sequences = sequences
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -564,7 +562,7 @@ class csFasta(Sequence):
                     return False
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize:
             dataset.metadata.data_lines = None
             dataset.metadata.sequences = None
@@ -641,7 +639,7 @@ class Fastg(Sequence):
                     break  # we found a non-empty line, but it's not a header
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         with open(dataset.file_name) as fh:
             for i, line in enumerate(fh):
                 if not line:
@@ -666,7 +664,7 @@ class Fastg(Sequence):
             return
         return Sequence.set_meta(self, dataset, overwrite=overwrite, **kwd)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             if dataset.metadata.sequences:
@@ -690,7 +688,7 @@ class BaseFastq(Sequence):
     file_ext = "fastq"
     bases_regexp = re.compile(r"^[NGTAC 0123\.]*$", re.IGNORECASE)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
@@ -771,7 +769,7 @@ class BaseFastq(Sequence):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -874,7 +872,7 @@ class BaseFastq(Sequence):
                     return True
         return False
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         headers = iter_headers(dataset.file_name, sep="\n", count=-1)
         # check to see if the base qualities match
         if not self.quality_check(headers):
@@ -1015,7 +1013,7 @@ class Maf(Alignment):
         Alignment.init_meta(self, dataset, copy_from=copy_from)
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         """
         Parses and sets species, chromosomes, index from MAF file.
@@ -1049,7 +1047,7 @@ class Maf(Alignment):
         indexes.write(open(index_file.file_name, "wb"))
         dataset.metadata.maf_index = index_file
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             # The file must exist on disk for the get_file_peek() method
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -1063,11 +1061,11 @@ class Maf(Alignment):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset)
 
-    def make_html_table(self, dataset: Peekable, skipchars: Optional[List] = None) -> str:
+    def make_html_table(self, dataset: DatasetProtocol, skipchars: Optional[List] = None) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
         try:
@@ -1142,7 +1140,7 @@ class MafCustomTrack(data.Text):
         name="vp_end", default="100", desc="Viewport End", readonly=True, optional=True, visible=False, no_value=""
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Parses and sets viewport metadata from MAF file.
         """
@@ -1275,7 +1273,7 @@ class RNADotPlotMatrix(data.Data):
     edam_format = "format_3466"
     file_ext = "rna_eps"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "RNA Dot Plot format (Postscript derivative)"
             dataset.blurb = nice_size(dataset.get_size())
@@ -1313,7 +1311,7 @@ class DotBracket(Sequence):
     sequence_regexp = re.compile(r"^[ACGTURYKMSWBDHVN]+$", re.I)
     structure_regexp = re.compile(r"^[\(\)\.\[\]{}]+$")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of sequences and the number of data lines
         in dataset.
diff --git a/lib/galaxy/datatypes/spaln.py b/lib/galaxy/datatypes/spaln.py
index de39ae7f159..1bc7f0fd950 100644
--- a/lib/galaxy/datatypes/spaln.py
+++ b/lib/galaxy/datatypes/spaln.py
@@ -12,10 +12,9 @@ from typing import (
 )
 
 from galaxy.datatypes._protocols import (
-    Displayable,
-    GeneratesPrimaryFile,
-    Peekable,
-    SetsMetadata,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.data import Data
 from galaxy.datatypes.metadata import MetadataElement
@@ -64,7 +63,7 @@ class _SpalnDb(Data):
             substitute_name_with_metadata="spalndb_name",
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Spaln Database</title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():
@@ -80,7 +79,7 @@ class _SpalnDb(Data):
         rval.append("</ul></div></html>")
         return "\n".join(rval)
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -99,7 +98,7 @@ class _SpalnDb(Data):
             f.write("\n".join(rval))
             f.write("\n")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text."""
         if not dataset.dataset.purged:
             dataset.peek = "spaln database (multiple files)"
@@ -108,7 +107,7 @@ class _SpalnDb(Data):
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Create HTML content, used for displaying peek."""
         try:
             return dataset.peek
@@ -118,7 +117,7 @@ class _SpalnDb(Data):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -179,7 +178,7 @@ class _SpalnDb(Data):
             return None
         raise NotImplementedError("Can't split spaln database")
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         efp = dataset.extra_files_path
         for filename in os.listdir(efp):
diff --git a/lib/galaxy/datatypes/speech.py b/lib/galaxy/datatypes/speech.py
index 6eb0439911f..5f22a4da077 100644
--- a/lib/galaxy/datatypes/speech.py
+++ b/lib/galaxy/datatypes/speech.py
@@ -1,4 +1,4 @@
-from galaxy.datatypes._protocols import SetsMetadata
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.data import Text
 from galaxy.datatypes.metadata import (
     ListParameter,
@@ -98,7 +98,7 @@ class BPF(Text):
         "SAO",
     ]
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """Set the metadata for this dataset from the file contents"""
         types = set()
         with open(dataset.dataset.file_name) as fd:
diff --git a/lib/galaxy/datatypes/tabular.py b/lib/galaxy/datatypes/tabular.py
index dcc1e10d428..f75868f0e34 100644
--- a/lib/galaxy/datatypes/tabular.py
+++ b/lib/galaxy/datatypes/tabular.py
@@ -30,14 +30,10 @@ from galaxy.datatypes import (
     metadata,
 )
 from galaxy.datatypes._protocols import (
-    Displayable,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
     HasFileName,
     HasMetadata,
-    Peekable,
-    ProvidesDataSource,
-    ProvidesDisplayLinks,
-    SetsMetadata,
-    Validatable,
 )
 from galaxy.datatypes.binary import _BamOrSam
 from galaxy.datatypes.data import (
@@ -125,16 +121,16 @@ class TabularData(Text):
     )
 
     @abc.abstractmethod
-    def set_meta(self, dataset: SetsMetadata, *, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, *, overwrite: bool = True, **kwd) -> None:
         raise NotImplementedError
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         kwd.setdefault("line_wrap", False)
         super().set_peek(dataset, **kwd)
         if dataset.metadata.comment_lines:
             dataset.blurb = f"{dataset.blurb}, {util.commaify(str(dataset.metadata.comment_lines))} comments"
 
-    def displayable(self, dataset: ProvidesDisplayLinks) -> bool:
+    def displayable(self, dataset: DatasetProtocol) -> bool:
         try:
             return (
                 not dataset.dataset.purged
@@ -171,7 +167,7 @@ class TabularData(Text):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -228,7 +224,7 @@ class TabularData(Text):
                 headers,
             )
 
-    def display_as_markdown(self, dataset_instance: Peekable) -> str:
+    def display_as_markdown(self, dataset_instance: DatasetProtocol) -> str:
         with open(dataset_instance.file_name) as f:
             contents = f.read(data.DEFAULT_MAX_PEEK_SIZE)
         markdown = self.make_html_table(dataset_instance, peek=contents)
@@ -236,7 +232,7 @@ class TabularData(Text):
             markdown += indicate_data_truncated()
         return pre_formatted_contents(markdown)
 
-    def make_html_table(self, dataset: Peekable, **kwargs) -> str:
+    def make_html_table(self, dataset: DatasetProtocol, **kwargs) -> str:
         """Create HTML table, used for displaying peek"""
         try:
             out = ['<table cellspacing="0" cellpadding="3">']
@@ -249,7 +245,7 @@ class TabularData(Text):
 
     def make_html_peek_header(
         self,
-        dataset: Peekable,
+        dataset: DatasetProtocol,
         skipchars: Optional[List] = None,
         column_names: Optional[List] = None,
         column_number_format: str = "%s",
@@ -303,7 +299,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek header: {util.unicodify(exc)}")
         return "".join(out)
 
-    def make_html_peek_rows(self, dataset: Peekable, skipchars: Optional[List] = None, **kwargs) -> str:
+    def make_html_peek_rows(self, dataset: DatasetProtocol, skipchars: Optional[List] = None, **kwargs) -> str:
         if skipchars is None:
             skipchars = []
         out = []
@@ -340,7 +336,7 @@ class TabularData(Text):
             raise Exception(f"Can't create peek rows: {util.unicodify(exc)}")
         return "".join(out)
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formatted html of peek"""
         return self.make_html_table(dataset)
 
@@ -376,27 +372,27 @@ class TabularData(Text):
 
     # ------------- Dataproviders
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol, **settings) -> ColumnarDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return ColumnarDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: DatasetProtocol, **settings) -> DatasetColumnarDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetColumnarDataProvider(dataset, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         """Uses column settings that are passed in"""
         dataset_source = DatasetDataProvider(dataset)
         delimiter = dataset.metadata.delimiter
         return DictDataProvider(dataset_source, deliminator=delimiter, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DatasetDictDataProvider:
         """Attempts to get column settings from dataset.metadata"""
         delimiter = dataset.metadata.delimiter
         return DatasetDictDataProvider(dataset, deliminator=delimiter, **settings)
@@ -413,7 +409,7 @@ class Tabular(TabularData):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         *,
         overwrite: bool = True,
         skip: Optional[int] = None,
@@ -585,7 +581,7 @@ class Tabular(TabularData):
     def as_gbrowse_display_file(self, dataset: HasFileName, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
-    def as_ucsc_display_file(self, dataset: ProvidesDataSource, **kwd) -> Union[FileObjType, str]:
+    def as_ucsc_display_file(self, dataset: DatasetProtocol, **kwd) -> Union[FileObjType, str]:
         return open(dataset.file_name, "rb")
 
 
@@ -595,7 +591,7 @@ class SraManifest(Tabular):
     file_ext = "sra_manifest.tabular"
     data_line_offset = 1
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         dataset.metadata.comment_lines = 1
 
@@ -636,7 +632,7 @@ class Taxonomy(Tabular):
             "Subspecies",
         ]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -727,7 +723,7 @@ class Sam(Tabular, _BamOrSam):
             "OPT",
         ]
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
@@ -785,7 +781,7 @@ class Sam(Tabular, _BamOrSam):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -867,55 +863,55 @@ class Sam(Tabular, _BamOrSam):
     # sam does not use '#' to indicate comments/headers - we need to strip out those headers from the std. providers
     # TODO:?? seems like there should be an easier way to do this - metadata.comment_char?
     @dataproviders.decorators.dataprovider_factory("line", FilteredLineDataProvider.settings)
-    def line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> FilteredLineDataProvider:
+    def line_dataprovider(self, dataset: DatasetProtocol, **settings) -> FilteredLineDataProvider:
         settings["comment_char"] = "@"
         return super().line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("regex-line", RegexLineDataProvider.settings)
-    def regex_line_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
+    def regex_line_dataprovider(self, dataset: DatasetProtocol, **settings) -> RegexLineDataProvider:
         settings["comment_char"] = "@"
         return super().regex_line_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("column", ColumnarDataProvider.settings)
-    def column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> ColumnarDataProvider:
+    def column_dataprovider(self, dataset: DatasetProtocol, **settings) -> ColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-column", ColumnarDataProvider.settings)
-    def dataset_column_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetColumnarDataProvider:
+    def dataset_column_dataprovider(self, dataset: DatasetProtocol, **settings) -> DatasetColumnarDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_column_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dict", DictDataProvider.settings)
-    def dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         settings["comment_char"] = "@"
         return super().dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("dataset-dict", DictDataProvider.settings)
-    def dataset_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DatasetDictDataProvider:
+    def dataset_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> DatasetDictDataProvider:
         settings["comment_char"] = "@"
         return super().dataset_dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("header", RegexLineDataProvider.settings)
-    def header_dataprovider(self, dataset: ProvidesDataSource, **settings) -> RegexLineDataProvider:
+    def header_dataprovider(self, dataset: DatasetProtocol, **settings) -> RegexLineDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         headers_source = RegexLineDataProvider(dataset_source, regex_list=["^@"])
         return RegexLineDataProvider(headers_source, **settings)
 
     @dataproviders.decorators.dataprovider_factory("id-seq-qual", dict_dataprovider.settings)
-    def id_seq_qual_dataprovider(self, dataset: ProvidesDataSource, **settings) -> DictDataProvider:
+    def id_seq_qual_dataprovider(self, dataset: DatasetProtocol, **settings) -> DictDataProvider:
         # provided as an example of a specified column dict (w/o metadata)
         settings["indeces"] = [0, 9, 10]
         settings["column_names"] = ["id", "seq", "qual"]
         return self.dict_dataprovider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["comment_char"] = "@"
         return GenomicRegionDataProvider(dataset, 2, 3, 3, True, **settings)
 
@@ -943,7 +939,7 @@ class Pileup(Tabular):
     def init_meta(self, dataset: HasMetadata, copy_from: Optional[HasMetadata] = None) -> None:
         super().init_meta(dataset, copy_from=copy_from)
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(
             dataset, column_parameter_alias={"chromCol": "Chrom", "startCol": "Start", "baseCol": "Base"}
@@ -996,11 +992,11 @@ class Pileup(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1045,11 +1041,11 @@ class BaseVcf(Tabular):
         headers = get_headers(fname_or_file_prefix, "\n", count=1)
         return headers[0][0].startswith("##fileformat=VCF")
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         """Returns formated html of peek"""
         return self.make_html_table(dataset, column_names=self.column_names)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         line = None
         with compression_utils.get_fileobj(dataset.file_name) as fh:
@@ -1075,7 +1071,7 @@ class BaseVcf(Tabular):
         if exit_code != 0:
             raise Exception(f"Error merging VCF files: {stderr!r}")
 
-    def validate(self, dataset: Validatable, **kwd) -> DatatypeValidation:
+    def validate(self, dataset: DatasetProtocol, **kwd) -> DatatypeValidation:
         def validate_row(row):
             if len(row) < 8:
                 raise Exception("Not enough columns in row %s" % row.join("\t"))
@@ -1085,11 +1081,11 @@ class BaseVcf(Tabular):
 
     # Dataproviders
     @dataproviders.decorators.dataprovider_factory("genomic-region", GenomicRegionDataProvider.settings)
-    def genomic_region_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         return GenomicRegionDataProvider(dataset, 0, 1, 1, **settings)
 
     @dataproviders.decorators.dataprovider_factory("genomic-region-dict", GenomicRegionDataProvider.settings)
-    def genomic_region_dict_dataprovider(self, dataset: ProvidesDataSource, **settings) -> GenomicRegionDataProvider:
+    def genomic_region_dict_dataprovider(self, dataset: DatasetProtocol, **settings) -> GenomicRegionDataProvider:
         settings["named_columns"] = True
         return self.genomic_region_dataprovider(dataset, **settings)
 
@@ -1130,7 +1126,7 @@ class VcfGz(BaseVcf, binary.Binary):
             return binascii.hexlify(last28) == b"1f8b08040000000000ff0600424302001b0003000000000000000000"
 
     def set_meta(
-        self, dataset: SetsMetadata, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
+        self, dataset: DatasetProtocol, overwrite: bool = True, metadata_tmp_files_dir: Optional[str] = None, **kwd
     ) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         # Creates the index for the VCF file.
@@ -1233,7 +1229,7 @@ class Eland(Tabular):
         ]
 
     def make_html_table(
-        self, dataset: Peekable, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
+        self, dataset: DatasetProtocol, skipchars: Optional[List] = None, peek: Optional[List] = None, **kwargs
     ) -> str:
         """Create HTML table, used for displaying peek"""
         skipchars = skipchars or []
@@ -1294,7 +1290,7 @@ class Eland(Tabular):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1456,7 +1452,7 @@ class BaseCSV(TabularData):
             return False
         return True
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         column_types = []
         header_row = []
         data_row = []
@@ -1538,7 +1534,7 @@ class ConnectivityTable(Tabular):
         self.column_names = ["base_index", "base", "neighbor_left", "neighbor_right", "partner", "natural_numbering"]
         self.column_types = ["int", "str", "int", "int", "int", "int"]
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         data_lines = 0
 
         with open(dataset.file_name) as fh:
@@ -1673,7 +1669,7 @@ class MatrixMarket(TabularData):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 5,
@@ -1801,7 +1797,7 @@ class CMAP(TabularData):
 
     def set_meta(
         self,
-        dataset: SetsMetadata,
+        dataset: DatasetProtocol,
         overwrite: bool = True,
         skip: Optional[int] = None,
         max_data_lines: Optional[int] = 7,
diff --git a/lib/galaxy/datatypes/text.py b/lib/galaxy/datatypes/text.py
index c93d7ea18e7..aacfe0389b6 100644
--- a/lib/galaxy/datatypes/text.py
+++ b/lib/galaxy/datatypes/text.py
@@ -17,11 +17,10 @@ from typing import (
 import yaml
 
 from galaxy.datatypes._protocols import (
-    Displayable,
-    GeneratesPrimaryFile,
+    DatasetHasHidProtocol,
+    DatasetProtocol,
     HasCreatingJob,
-    Peekable,
-    SetsMetadata,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.data import (
     get_file_peek,
@@ -54,7 +53,7 @@ class Html(Text):
     edam_format = "format_2331"
     file_ext = "html"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "HTML file"
             dataset.blurb = nice_size(dataset.get_size())
@@ -90,7 +89,7 @@ class Json(Text):
     edam_format = "format_3464"
     file_ext = "json"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "JavaScript Object Notation (JSON)"
@@ -127,7 +126,7 @@ class Json(Text):
                 return start.startswith("[") or start.startswith("{")
             return False
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
@@ -142,7 +141,7 @@ class ExpressionJson(Json):
         name="json_type", default=None, desc="JavaScript or JSON type of expression", readonly=True, visible=True
     )
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """ """
         if dataset.has_data():
             json_type = "null"
@@ -169,7 +168,7 @@ class ExpressionJson(Json):
 class Ipynb(Json):
     file_ext = "ipynb"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Jupyter Notebook"
@@ -196,7 +195,7 @@ class Ipynb(Json):
     def display_data(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -217,7 +216,7 @@ class Ipynb(Json):
     def _display_data_trusted(
         self,
         trans,
-        dataset: Displayable,
+        dataset: DatasetHasHidProtocol,
         preview: bool = False,
         filename: Optional[str] = None,
         to_ext: Optional[str] = None,
@@ -252,7 +251,7 @@ class Ipynb(Json):
                 )
             return open(ofilename, mode="rb"), headers
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Set the number of models in dataset.
         """
@@ -388,7 +387,7 @@ class Biom1(Json):
         no_value=[],
     )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "Biological Observation Matrix v1"
@@ -425,7 +424,7 @@ class Biom1(Json):
             pass
         return is_biom
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the BIOM file.
         """
@@ -487,7 +486,7 @@ class ImgtJson(Json):
 
     MetadataElement(name="taxon_names", default=[], desc="taxonID: names", readonly=True, visible=True, no_value=[])
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "IMGT Library"
@@ -526,7 +525,7 @@ class ImgtJson(Json):
             pass
         return is_imgt
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Store metadata information from the imgt file.
         """
@@ -553,7 +552,7 @@ class GeoJson(Json):
 
     file_ext = "geojson"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         super().set_peek(dataset)
         if not dataset.dataset.purged:
             dataset.blurb = "GeoJSON"
@@ -614,7 +613,7 @@ class Obo(Text):
     edam_format = "format_2549"
     file_ext = "obo"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Open Biomedical Ontology (OBO)"
@@ -656,7 +655,7 @@ class Arff(Text):
     )
     MetadataElement(name="columns", default=0, desc="Number of columns", readonly=True, visible=True, no_value=0)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = get_file_peek(dataset.file_name)
             dataset.blurb = "Attribute-Relation File Format (ARFF)"
@@ -692,7 +691,7 @@ class Arff(Text):
                     return True
         return False
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         """
         Trying to count the comment lines and the number of columns included.
         A typical ARFF data block looks like this:
@@ -777,7 +776,7 @@ class SnpEffDb(Text):
             pass
         return snpeff_version
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         super().set_meta(dataset, overwrite=overwrite, **kwd)
         data_dir = dataset.extra_files_path
         # search data_dir/genome_version for files
@@ -863,14 +862,14 @@ class SnpSiftDbNSFP(Text):
             "%s.gz.tbi", description="Tabix Index File", substitute_name_with_metadata="reference_name", is_binary=True
         )
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
         """
         return "<html><head><title>SnpSiftDbNSFP Composite Dataset</title></head></html>"
 
-    def regenerate_primary_file(self, dataset: SetsMetadata) -> None:
+    def regenerate_primary_file(self, dataset: DatasetProtocol) -> None:
         """
         cannot do this until we are setting metadata
         """
@@ -882,7 +881,7 @@ class SnpSiftDbNSFP(Text):
                 f.write("\n")
             f.write(annotations)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         try:
             efp = dataset.extra_files_path
             if os.path.exists(efp):
@@ -908,7 +907,7 @@ class SnpSiftDbNSFP(Text):
                 unicodify(e),
             )
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = f"{dataset.metadata.reference_name} :  {','.join(dataset.metadata.annotation)}"
             dataset.blurb = f"{dataset.metadata.reference_name}"
@@ -1151,7 +1150,7 @@ class BCSLts(Json):
             is_bcsl_ts = self._looks_like_bcsl_ts(file_prefix)
         return is_bcsl_ts
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             lines = "States: {}\nTransitions: {}\nUnique agents: {}\nInitial state: {}"
             ts = json.load(open(dataset.file_name, "r"))
@@ -1185,7 +1184,7 @@ class StormSample(Text):
         keywords = ["Storm-pars", "Result (initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Storm-pars sample results."
             dataset.blurb = nice_size(dataset.get_size())
@@ -1210,7 +1209,7 @@ class StormCheck(Text):
         keywords = ["Storm ", "Result (for initial states)"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
@@ -1238,7 +1237,7 @@ class CTLresult(Text):
         keywords = ["Result:", "Number of satisfying states:"]
         return all(keyword in file_prefix.contents_header for keyword in keywords)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             with open(dataset.file_name, "r") as result:
                 answer = ""
diff --git a/lib/galaxy/datatypes/tracks.py b/lib/galaxy/datatypes/tracks.py
index 65e3073ef33..2af7decc628 100644
--- a/lib/galaxy/datatypes/tracks.py
+++ b/lib/galaxy/datatypes/tracks.py
@@ -4,8 +4,8 @@ Datatype classes for tracks/track views within galaxy.
 import logging
 
 from galaxy.datatypes._protocols import (
-    GeneratesPrimaryFile,
-    Peekable,
+    DatasetProtocol,
+    HasExtraFilesAndMetadata,
 )
 from galaxy.datatypes.text import Html
 from . import binary
@@ -29,7 +29,7 @@ class UCSCTrackHub(Html):
     file_ext = "trackhub"
     composite_type = "auto_primary_file"
 
-    def generate_primary_file(self, dataset: GeneratesPrimaryFile) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         """
         This is called only at upload to write the html file
         cannot rename the datasets here - they come with the default unfortunately
@@ -47,14 +47,14 @@ class UCSCTrackHub(Html):
         rval.append("</ul></html>")
         return "\n".join(rval)
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = "Track Hub structure: Visualization in UCSC Track Hub"
         else:
             dataset.peek = "file does not exist"
             dataset.blurb = "file purged from disk"
 
-    def display_peek(self, dataset: Peekable) -> str:
+    def display_peek(self, dataset: DatasetProtocol) -> str:
         try:
             return dataset.peek
         except Exception:
diff --git a/lib/galaxy/datatypes/triples.py b/lib/galaxy/datatypes/triples.py
index 43070f5cac7..d908eae1dd9 100644
--- a/lib/galaxy/datatypes/triples.py
+++ b/lib/galaxy/datatypes/triples.py
@@ -4,7 +4,7 @@ Triple format classes
 import logging
 import re
 
-from galaxy.datatypes._protocols import Peekable
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.sniff import (
     build_sniff_from_prefix,
     FilePrefix,
@@ -37,7 +37,7 @@ class Triples(data.Data):
         """
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -62,7 +62,7 @@ class NTriples(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -86,7 +86,7 @@ class N3(data.Text, Triples):
         """
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -114,7 +114,7 @@ class Turtle(data.Text, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -143,7 +143,7 @@ class Rdf(xml.GenericXml, Triples):
             return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -169,7 +169,7 @@ class Jsonld(text.Json, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -193,7 +193,7 @@ class HDT(binary.Binary, Triples):
                 return True
         return False
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
diff --git a/lib/galaxy/datatypes/xml.py b/lib/galaxy/datatypes/xml.py
index 73c4e3e3cfc..475cc5cd1ff 100644
--- a/lib/galaxy/datatypes/xml.py
+++ b/lib/galaxy/datatypes/xml.py
@@ -6,11 +6,7 @@ import re
 from typing import List
 
 from galaxy import util
-from galaxy.datatypes._protocols import (
-    Peekable,
-    ProvidesDataSource,
-    SetsMetadata,
-)
+from galaxy.datatypes._protocols import DatasetProtocol
 from galaxy.datatypes.dataproviders.dataset import DatasetDataProvider
 from galaxy.datatypes.dataproviders.hierarchy import XMLDataProvider
 from galaxy.datatypes.metadata import MetadataElement
@@ -38,7 +34,7 @@ class GenericXml(data.Text):
     edam_format = "format_2332"
     file_ext = "xml"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -80,7 +76,7 @@ class GenericXml(data.Text):
         data.Text.merge(split_files, output_file)
 
     @dataproviders.decorators.dataprovider_factory("xml", XMLDataProvider.settings)
-    def xml_dataprovider(self, dataset: ProvidesDataSource, **settings) -> XMLDataProvider:
+    def xml_dataprovider(self, dataset: DatasetProtocol, **settings) -> XMLDataProvider:
         dataset_source = DatasetDataProvider(dataset)
         return XMLDataProvider(dataset_source, **settings)
 
@@ -91,7 +87,7 @@ class MEMEXml(GenericXml):
 
     file_ext = "memexml"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -107,7 +103,7 @@ class CisML(GenericXml):
 
     file_ext = "cisml"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -151,7 +147,7 @@ class Dzi(GenericXml):
     def __init__(self, **kwd):
         super().__init__(**kwd)
 
-    def set_meta(self, dataset: SetsMetadata, overwrite: bool = True, **kwd) -> None:
+    def set_meta(self, dataset: DatasetProtocol, overwrite: bool = True, **kwd) -> None:
         tree = util.parse_xml(dataset.file_name)
         root = tree.getroot()
         dataset.metadata.format = root.get("Format")
@@ -168,7 +164,7 @@ class Dzi(GenericXml):
                 dataset.metadata.width = elem.get("Width")
                 dataset.metadata.height = elem.get("Height")
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Deep Zoom Image"
@@ -201,7 +197,7 @@ class Phyloxml(GenericXml):
     edam_format = "format_3159"
     file_ext = "phyloxml"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         """Set the peek and blurb text"""
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
@@ -236,7 +232,7 @@ class Owl(GenericXml):
     edam_format = "format_3262"
     file_ext = "owl"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "Web Ontology Language OWL"
@@ -261,7 +257,7 @@ class Sbml(GenericXml):
     edam_data = "data_2024"
     edam_format = "format_2585"
 
-    def set_peek(self, dataset: Peekable, **kwd) -> None:
+    def set_peek(self, dataset: DatasetProtocol, **kwd) -> None:
         if not dataset.dataset.purged:
             dataset.peek = data.get_file_peek(dataset.file_name)
             dataset.blurb = "System Biology Markup Language SBML"

From 97056c719ccaef32f433c4f382d85ef5a70e3459 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Fri, 13 Jan 2023 12:31:40 +0100
Subject: [PATCH 116/350] Force flush when purging datasets in batch

Required to check hda.dataset.user_can_purge with an updated Dataset.purged_history_associations.
---
 lib/galaxy/webapps/galaxy/services/datasets.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/services/datasets.py b/lib/galaxy/webapps/galaxy/services/datasets.py
index 3da90a7185c..cd8820c76e9 100644
--- a/lib/galaxy/webapps/galaxy/services/datasets.py
+++ b/lib/galaxy/webapps/galaxy/services/datasets.py
@@ -557,7 +557,7 @@ class DatasetsService(ServiceBase, UsesVisualizationMixin):
                 if dataset.src == DatasetSourceType.hda:
                     self.hda_manager.error_if_uploading(dataset_instance)
                 if payload.purge:
-                    manager.purge(dataset_instance, flush=False)
+                    manager.purge(dataset_instance, flush=True)
                 else:
                     manager.delete(dataset_instance, flush=False)
                 success_count += 1

From ab8827d46caa8906547a9565e41ba6235d02b346 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Fri, 13 Jan 2023 12:43:02 +0100
Subject: [PATCH 117/350] Force flush when purging datasets in bulk

Required to check hda.dataset.user_can_purge with an updated Dataset.purged_history_associations.
---
 lib/galaxy/webapps/galaxy/services/history_contents.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/services/history_contents.py b/lib/galaxy/webapps/galaxy/services/history_contents.py
index 2b6754d9368..e087b1687c8 100644
--- a/lib/galaxy/webapps/galaxy/services/history_contents.py
+++ b/lib/galaxy/webapps/galaxy/services/history_contents.py
@@ -1609,7 +1609,7 @@ class HistoryItemOperator:
             return
         if isinstance(item, HistoryDatasetCollectionAssociation):
             return self.dataset_collection_manager.delete(trans, "history", item.id, recursive=True, purge=True)
-        self.hda_manager.purge(item, flush=self.flush)
+        self.hda_manager.purge(item, flush=True)
 
     def _change_datatype(
         self, item: HistoryItemModel, params: ChangeDatatypeOperationParams, trans: ProvidesHistoryContext

From 08acc18311091f0b27ced25cf6e675454e6eb111 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Fri, 13 Jan 2023 15:58:11 +0100
Subject: [PATCH 118/350] Add integration test to ensure files are purged

---
 test/integration/test_purge_datasets.py | 81 +++++++++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 test/integration/test_purge_datasets.py

diff --git a/test/integration/test_purge_datasets.py b/test/integration/test_purge_datasets.py
new file mode 100644
index 00000000000..a5bb44aa8c7
--- /dev/null
+++ b/test/integration/test_purge_datasets.py
@@ -0,0 +1,81 @@
+import os
+from typing import (
+    Callable,
+    Optional,
+)
+
+from galaxy_test.base.populators import DatasetPopulator
+from galaxy_test.driver import integration_util
+
+
+class PurgeDatasetsIntegrationTestCase(integration_util.IntegrationTestCase):
+    def setUp(self):
+        super().setUp()
+        self.dataset_populator = DatasetPopulator(self.galaxy_interactor)
+        self.history_id = self.dataset_populator.new_history()
+
+    @classmethod
+    def handle_galaxy_config_kwds(cls, config):
+        super().handle_galaxy_config_kwds(config)
+        config["allow_user_dataset_purge"] = True
+
+    def test_purge_dataset_batch_removes_underlying_dataset_from_disk(self):
+        self._expect_dataset_purged_on(self._purge_hda_using_batch)
+
+    def test_purge_history_content_bulk_removes_underlying_dataset_from_disk(self):
+        self._expect_dataset_purged_on(self._purge_hda_using_bulk)
+
+    def _expect_dataset_purged_on(self, purge_operation: Callable):
+        hda = self.dataset_populator.new_dataset(self.history_id, wait=True)
+        hda_id = hda["id"]
+
+        # Ensure dataset file exists on disk
+        dataset_file = self._get_underlying_dataset_on_disk(hda_id)
+        assert self._file_exists_on_disk(dataset_file)
+
+        # Purge dataset
+        purge_operation(hda_id)
+
+        # Ensure dataset is purged
+        self.dataset_populator.wait_for_purge(self.history_id, hda_id)
+
+        # Ensure dataset file is removed from disk after purge
+        assert not self._file_exists_on_disk(dataset_file)
+
+    def _purge_hda_using_batch(self, hda_id):
+        payload = {
+            "purge": True,
+            "datasets": [
+                {"id": hda_id, "src": "hda"},
+            ],
+        }
+        purge_response = self._delete("datasets", data=payload, json=True)
+        self._assert_status_code_is_ok(purge_response)
+        purge_result = purge_response.json()
+        assert purge_result["success_count"] == 1
+
+    def _purge_hda_using_bulk(self, hda_id):
+        payload = {
+            "operation": "purge",
+            "items": [
+                {
+                    "id": hda_id,
+                    "history_content_type": "dataset",
+                },
+            ],
+        }
+        purge_response = self._put(
+            f"histories/{self.history_id}/contents/bulk",
+            data=payload,
+            json=True,
+        )
+        self._assert_status_code_is_ok(purge_response)
+        purge_result = purge_response.json()
+        assert purge_result["success_count"] == 1
+
+    def _get_underlying_dataset_on_disk(self, hda_id: str) -> Optional[str]:
+        detailed_response = self._get(f"datasets/{hda_id}", admin=True).json()
+        return detailed_response.get("file_name")
+
+    def _file_exists_on_disk(self, filename: Optional[str]) -> bool:
+        return os.path.isfile(filename) if filename else False

From 543bb90510c6e0fb3e55721dc7d2bf60fea92409 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Fri, 13 Jan 2023 18:15:45 +0100
Subject: [PATCH 119/350] Fix possible flaky test

Ensure the datasets are uploaded before attempting to delete/purge them.
---
 lib/galaxy_test/api/test_datasets.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/galaxy_test/api/test_datasets.py b/lib/galaxy_test/api/test_datasets.py
index c35067c71c2..6f353b66195 100644
--- a/lib/galaxy_test/api/test_datasets.py
+++ b/lib/galaxy_test/api/test_datasets.py
@@ -446,6 +446,8 @@ class DatasetsApiTestCase(ApiTestCase):
             hda = self.dataset_populator.new_dataset(history_id)
             dataset_map[index] = hda["id"]
 
+        self.dataset_populator.wait_for_history(history_id)
+
         expected_deleted_source_ids = [
             {"id": dataset_map[1], "src": "hda"},
             {"id": dataset_map[2], "src": "hda"},

From a3899ff8fb34678081181ee87e401806cba5460f Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Mon, 9 Jan 2023 13:13:37 -0500
Subject: [PATCH 120/350] Prep recursive collection drilldown in details view

---
 .../History/Content/GenericElement.vue        | 41 +++++++++++++------
 .../History/Content/GenericItem.vue           |  4 +-
 2 files changed, 29 insertions(+), 16 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 7b8f4068501..a6796fd1398 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,36 +1,51 @@
 <template>
     <div>
-        <ContentItem
-            :id="item.element_index"
-            :item="item.object"
-            :name="item.element_identifier"
-            :is-dataset="item.element_type == 'hda'"
-            :expand-dataset="expandDataset"
-            @update:expand-dataset="expandDataset = $event"
-            @view-collection="viewCollection = !viewCollection" />
-        <GenericItem v-if="viewCollection" :item-id="item.object.id" :item-src="item.object.history_content_type" />
+        <div v-for="(item, index) in dsc.elements" :key="index">
+            <ContentItem
+                :id="item.element_index"
+                :item="item.object"
+                :name="item.element_identifier"
+                :is-dataset="item.element_type == 'hda'"
+                :expand-dataset="!!expandDatasets[item.id]"
+                @update:expand-dataset="viewDataset(item.id)"
+                @view-collection="viewCollection(item.id)" />
+            <div v-if="!!expandCollections[item.id]">
+                <GenericElementNode :dsc="item.object" />
+            </div>
+        </div>
     </div>
 </template>
 
 <script>
+import Vue from "vue";
 import ContentItem from "./ContentItem";
+import { CollectionElementsProvider } from "components/providers/storeProviders";
 
 export default {
+    name: "GenericElementNode",
     components: {
+        CollectionElementsProvider,
         ContentItem,
-        GenericItem: () => import("components/History/Content/GenericItem"),
     },
     props: {
-        item: {
+        dsc: {
             type: Object,
             required: true,
         },
     },
     data() {
         return {
-            viewCollection: false,
-            expandDataset: false,
+            expandCollections: {},
+            expandDatasets: {},
         };
     },
+    methods: {
+        viewCollection(itemId) {
+            Vue.set(this.expandCollections, itemId, !this.expandCollections[itemId]);
+        },
+        viewDataset(itemId) {
+            Vue.set(this.expandDatasets, itemId, !this.expandDatasets[itemId]);
+        },
+    },
 };
 </script>
diff --git a/client/src/components/History/Content/GenericItem.vue b/client/src/components/History/Content/GenericItem.vue
index 4b93fe579b0..adda51b27de 100644
--- a/client/src/components/History/Content/GenericItem.vue
+++ b/client/src/components/History/Content/GenericItem.vue
@@ -15,9 +15,7 @@
                 @undelete="onUndelete(item)"
                 @unhide="onUnhide(item)" />
             <div v-if="viewCollection">
-                <div v-for="(collectionItem, collectionIndex) in item.elements" :key="collectionIndex">
-                    <GenericElement :item="collectionItem" />
-                </div>
+                <GenericElement :dsc="item" />
             </div>
         </div>
     </component>

From 854177109a2331001c7d948d1a657648d29f57f8 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Sat, 14 Jan 2023 11:57:55 -0500
Subject: [PATCH 121/350] Switch generic element wrapper to composition api

---
 .../History/Content/GenericElement.vue        | 62 ++++++++-----------
 1 file changed, 26 insertions(+), 36 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index a6796fd1398..243dfa919d7 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,3 +1,27 @@
+<script setup>
+import Vue from "vue";
+import ContentItem from "./ContentItem";
+import { ref } from "vue";
+
+const props = defineProps({
+    dsc: {
+        type: Object,
+        required: true,
+    },
+});
+
+const expandCollections = ref({});
+const expandDatasets = ref({});
+
+function viewCollection(itemId) {
+    Vue.set(this.expandCollections, itemId, !this.expandCollections[itemId]);
+}
+
+function viewDataset(itemId) {
+    Vue.set(this.expandDatasets, itemId, !this.expandDatasets[itemId]);
+}
+</script>
+
 <template>
     <div>
         <div v-for="(item, index) in dsc.elements" :key="index">
@@ -9,43 +33,9 @@
                 :expand-dataset="!!expandDatasets[item.id]"
                 @update:expand-dataset="viewDataset(item.id)"
                 @view-collection="viewCollection(item.id)" />
-            <div v-if="!!expandCollections[item.id]">
-                <GenericElementNode :dsc="item.object" />
+            <div v-if="!!expandCollections[item.id]" class="mx-3">
+                <GenericElement :dsc="item.object" />
             </div>
         </div>
     </div>
 </template>
-
-<script>
-import Vue from "vue";
-import ContentItem from "./ContentItem";
-import { CollectionElementsProvider } from "components/providers/storeProviders";
-
-export default {
-    name: "GenericElementNode",
-    components: {
-        CollectionElementsProvider,
-        ContentItem,
-    },
-    props: {
-        dsc: {
-            type: Object,
-            required: true,
-        },
-    },
-    data() {
-        return {
-            expandCollections: {},
-            expandDatasets: {},
-        };
-    },
-    methods: {
-        viewCollection(itemId) {
-            Vue.set(this.expandCollections, itemId, !this.expandCollections[itemId]);
-        },
-        viewDataset(itemId) {
-            Vue.set(this.expandDatasets, itemId, !this.expandDatasets[itemId]);
-        },
-    },
-};
-</script>

From bdb8ca1a968efd28002a4c496f3ec5a76a297d09 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Sat, 14 Jan 2023 12:00:53 -0500
Subject: [PATCH 122/350] Consolidate expansion toggle

---
 .../components/History/Content/GenericElement.vue    | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 243dfa919d7..35f32b50e51 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -13,12 +13,8 @@ const props = defineProps({
 const expandCollections = ref({});
 const expandDatasets = ref({});
 
-function viewCollection(itemId) {
-    Vue.set(this.expandCollections, itemId, !this.expandCollections[itemId]);
-}
-
-function viewDataset(itemId) {
-    Vue.set(this.expandDatasets, itemId, !this.expandDatasets[itemId]);
+function toggle(expansionMap, itemId) {
+    Vue.set(expansionMap, itemId, !expansionMap[itemId]);
 }
 </script>
 
@@ -31,8 +27,8 @@ function viewDataset(itemId) {
                 :name="item.element_identifier"
                 :is-dataset="item.element_type == 'hda'"
                 :expand-dataset="!!expandDatasets[item.id]"
-                @update:expand-dataset="viewDataset(item.id)"
-                @view-collection="viewCollection(item.id)" />
+                @update:expand-dataset="toggle(expandDatasets, item.id)"
+                @view-collection="toggle(expandCollections, item.id)" />
             <div v-if="!!expandCollections[item.id]" class="mx-3">
                 <GenericElement :dsc="item.object" />
             </div>

From 675090553f440a8114d8e6e658d98d08198f0838 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Sat, 14 Jan 2023 17:56:50 -0500
Subject: [PATCH 123/350] Switch to typescript

---
 client/src/components/History/Content/GenericElement.vue | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 35f32b50e51..018d76b30fe 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,9 +1,9 @@
-<script setup>
+<script setup lang="ts">
 import Vue from "vue";
-import ContentItem from "./ContentItem";
+import ContentItem from "./ContentItem.vue";
 import { ref } from "vue";
 
-const props = defineProps({
+defineProps({
     dsc: {
         type: Object,
         required: true,
@@ -13,7 +13,7 @@ const props = defineProps({
 const expandCollections = ref({});
 const expandDatasets = ref({});
 
-function toggle(expansionMap, itemId) {
+function toggle(expansionMap: Record<string, boolean>, itemId: string) {
     Vue.set(expansionMap, itemId, !expansionMap[itemId]);
 }
 </script>

From b5057188dbaf5ce6012b68e58ab668a642b3fcee Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Sat, 14 Jan 2023 19:41:47 -0500
Subject: [PATCH 124/350] Add additional margin

---
 client/src/components/History/Content/GenericElement.vue | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 018d76b30fe..a3f76e84551 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -27,6 +27,7 @@ function toggle(expansionMap: Record<string, boolean>, itemId: string) {
                 :name="item.element_identifier"
                 :is-dataset="item.element_type == 'hda'"
                 :expand-dataset="!!expandDatasets[item.id]"
+                class="mx-3"
                 @update:expand-dataset="toggle(expandDatasets, item.id)"
                 @view-collection="toggle(expandCollections, item.id)" />
             <div v-if="!!expandCollections[item.id]" class="mx-3">

From 0a79d23150a137bf8bbf4068abb0a01c42301015 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Mon, 8 Nov 2021 13:36:15 -0500
Subject: [PATCH 125/350] Implement conditionals via boolean step parameter

For tool steps only right now. This side-steps user-defined javascript
expressions in favor of boolean input parameters.
---
 lib/galaxy/managers/workflows.py      |  6 ++++++
 lib/galaxy/model/__init__.py          |  1 +
 lib/galaxy/tool_util/cwl/parser.py    |  7 ++++--
 lib/galaxy/workflow/modules.py        | 31 ++++++++++++++++++++++++++-
 lib/galaxy/workflow/run.py            | 10 +++++++++
 lib/galaxy_test/api/test_workflows.py | 29 +++++++++++++++++++++++++
 6 files changed, 81 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index f2d88ea5d3f..e793c53ed1d 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -1709,8 +1709,14 @@ class WorkflowContentsManager(UsesAnnotations):
                     step_input.default_value = default
                     step_input.default_value_set = True
 
+        if "when" in step_dict:
+            if isinstance(step_dict["when"], dict) and "source" in step_dict["when"]:
+                step.temp_input_connections["when_source"] = step_dict["when"]["source"]
+            else:
+                step.when_expression = step_dict["when"]
         if dry_run and step in trans.sa_session:
             trans.sa_session.expunge(step)
+
         return module, step
 
     def __load_subworkflow_from_step_dict(
diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index 2d74b52e335..193ae685b59 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -7040,6 +7040,7 @@ class WorkflowStep(Base, RepresentById):
     position = Column(MutableJSONType)
     config = Column(JSONType)
     order_index: int = Column(Integer)
+    when_expression = Column(JSONType)
     uuid = Column(UUIDType)
     label = Column(Unicode(255))
     temp_input_connections: Optional[InputConnDictType]
diff --git a/lib/galaxy/tool_util/cwl/parser.py b/lib/galaxy/tool_util/cwl/parser.py
index 97d79c1fc98..467c6070f66 100644
--- a/lib/galaxy/tool_util/cwl/parser.py
+++ b/lib/galaxy/tool_util/cwl/parser.py
@@ -686,7 +686,6 @@ class WorkflowProxy:
             "input_connections": {},  # Should the Galaxy API really require this? - Seems to.
             "workflow_outputs": self.get_outputs_for_label(label),
         }
-
         if input_type == "File" and "default" not in input:
             input_as_dict["type"] = "data_input"
         elif isinstance(input_type, dict) and input_type.get("type") == "array":
@@ -1057,7 +1056,8 @@ class ToolStepProxy(BaseStepProxy):
             tool_state[input_name] = None
 
         outputs = self.galaxy_workflow_outputs_list()
-        return {
+        when_expression = self._step.tool.get("when")
+        rval = {
             "id": self._index,
             "tool_uuid": self.tool_proxy.uuid,  # TODO: make sure this is respected...
             "label": self.label,
@@ -1068,6 +1068,9 @@ class ToolStepProxy(BaseStepProxy):
             "inputs": self.inputs_to_dicts(),
             "workflow_outputs": outputs,
         }
+        if when_expression:
+            rval["when"] = when_expression
+        return rval
 
 
 class SubworkflowStepProxy(BaseStepProxy):
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 1a7cd41037b..91b980c82b2 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -104,6 +104,10 @@ class NoReplacement:
 NO_REPLACEMENT = NoReplacement()
 
 
+class ConditionalStepWhen(BooleanToolParameter):
+    pass
+
+
 class WorkflowModule:
 
     label: str
@@ -1637,6 +1641,18 @@ class ToolModule(WorkflowModule):
     def get_inputs(self):
         return self.tool.inputs if self.tool else {}
 
+    def get_conditional_param(self, inputs):
+        inputs.append(
+            dict(
+                name="when_source",
+                label="when_source",
+                multiple=False,
+                input_type="parameter",
+                optional=False,
+                type="boolean",
+            )
+        )
+
     def get_all_inputs(self, data_only=False, connectable_only=False):
         if data_only and connectable_only:
             raise Exception("Must specify at most one of data_only and connectable_only as True.")
@@ -1928,6 +1944,10 @@ class ToolModule(WorkflowModule):
             del tool_state.inputs[RUNTIME_STEP_META_STATE_KEY]
 
         all_inputs = self.get_all_inputs()
+        if step.input_connections_by_name.get("when_source"):
+            self.get_conditional_param(all_inputs)
+            tool_inputs = tool.inputs.copy()
+            tool_inputs["when_source"] = ConditionalStepWhen(None, {"name": "when_source", "type": "boolean"})
         all_inputs_by_name = {}
         for input_dict in all_inputs:
             all_inputs_by_name[input_dict["name"]] = input_dict
@@ -1971,12 +1991,16 @@ class ToolModule(WorkflowModule):
                                 replacement = json.load(f)
                     found_replacement_keys.add(prefixed_name)  # noqa: B023
 
+                    if isinstance(input, ConditionalStepWhen) and replacement is False:
+                        outputs = self.get_all_outputs()
+                        raise SkipWorkflowStepEvaluation(outputs)
+
                 return replacement
 
             try:
                 # Replace DummyDatasets with historydatasetassociations
                 visit_input_values(
-                    tool.inputs,
+                    tool_inputs,
                     execution_state.inputs,
                     callback,
                     no_replacement_value=NO_REPLACEMENT,
@@ -2199,6 +2223,11 @@ class CancelWorkflowEvaluation(Exception):
     pass
 
 
+class SkipWorkflowStepEvaluation(Exception):
+    def __init__(self, outputs):
+        self.outputs = outputs
+
+
 class WorkflowModuleInjector:
     """Injects workflow step objects from the ORM with appropriate module and
     module generated/influenced state."""
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index 002b93ee211..deabbb72288 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -209,6 +209,9 @@ class WorkflowInvoker:
                     self.progress.mark_step_outputs_delayed(step, why="Not all jobs scheduled for state.")
                 else:
                     workflow_invocation_step.state = "scheduled"
+            except modules.SkipWorkflowStepEvaluation as we:
+                log.info("Skipping workflow step!")
+                self.progress.mark_step_outputs_skipped(workflow_invocation_step, we.outputs)
             except modules.DelayedWorkflowEvaluation as de:
                 step_delayed = delayed_steps = True
                 self.progress.mark_step_outputs_delayed(step, why=de.why)
@@ -513,6 +516,13 @@ class WorkflowProgress:
     def _record_workflow_output(self, step: "WorkflowStep", workflow_output: "WorkflowOutput", output: Any) -> None:
         self.workflow_invocation.add_output(workflow_output, step, output)
 
+    def mark_step_outputs_skipped(self, invocation_step, outputs):
+        # TODO: Mark the step skipped in the database somehow?
+        null_outputs = {}
+        for output in outputs:
+            null_outputs[output["name"]] = None
+        self.set_step_outputs(invocation_step, null_outputs)
+
     def mark_step_outputs_delayed(self, step: "WorkflowStep", why: Optional[str] = None) -> None:
         if why:
             message = f"Marking step {step.id} outputs of invocation {self.workflow_invocation.id} delayed ({why})"
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 921f4ad3dcc..07ede699ef5 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1930,6 +1930,35 @@ test_data:
                 history_id=history_id,
             )
 
+    def test_run_workflow_simple_conditional(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """class: GalaxyWorkflow
+inputs:
+  should_run:
+    type: boolean
+  some_file:
+    type: data
+steps:
+  cat1:
+    tool_id: cat1
+    in:
+      input1: some_file
+    when:
+      source: should_run
+""",
+                test_data="""
+some_file:
+  value: 1.bed
+  type: File
+should_run:
+  value: false
+  type: raw
+""",
+                history_id=history_id,
+            )
+            assert len(self.dataset_populator.invocation_jobs(summary.invocation_id)) == 0
+
     def test_run_subworkflow_simple(self) -> None:
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(

From 20f9b6feec9fb20ece4bc1ede790ff8973b343f2 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 24 Oct 2022 13:12:55 +0200
Subject: [PATCH 126/350] Attempt to skip mapped-over steps

---
 lib/galaxy/tools/execute.py           |  2 ++
 lib/galaxy/workflow/modules.py        |  8 +++++-
 lib/galaxy_test/api/test_workflows.py | 39 +++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/tools/execute.py b/lib/galaxy/tools/execute.py
index 507b68abaf5..febd7a3b82f 100644
--- a/lib/galaxy/tools/execute.py
+++ b/lib/galaxy/tools/execute.py
@@ -161,6 +161,8 @@ def execute(
             has_remaining_jobs = True
             break
         else:
+            if execution_slice.param_combination.get("when") is False:
+                continue
             execute_single_job(execution_slice, completed_jobs[i])
             history = execution_slice.history or history
             jobs_executed += 1
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 91b980c82b2..5fc820ea738 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -1938,6 +1938,7 @@ class ToolModule(WorkflowModule):
             message = f"Specified tool [{tool.id}] in workflow is not workflow-compatible."
             raise Exception(message)
         tool_state = step.state
+        tool_inputs = tool.inputs.copy()
         # Not strictly needed - but keep Tool state clean by stripping runtime
         # metadata parameters from it.
         if RUNTIME_STEP_META_STATE_KEY in tool_state.inputs:
@@ -1946,7 +1947,6 @@ class ToolModule(WorkflowModule):
         all_inputs = self.get_all_inputs()
         if step.input_connections_by_name.get("when_source"):
             self.get_conditional_param(all_inputs)
-            tool_inputs = tool.inputs.copy()
             tool_inputs["when_source"] = ConditionalStepWhen(None, {"name": "when_source", "type": "boolean"})
         all_inputs_by_name = {}
         for input_dict in all_inputs:
@@ -2006,6 +2006,12 @@ class ToolModule(WorkflowModule):
                     no_replacement_value=NO_REPLACEMENT,
                     replace_optional_connections=True,
                 )
+            except SkipWorkflowStepEvaluation as we:
+                progress.mark_step_outputs_skipped(invocation_step, we.outputs)
+                skip_execution_state = execution_state.inputs
+                skip_execution_state["when"] = False
+                param_combinations.append(execution_state.inputs)
+                continue
             except KeyError as k:
                 message_template = "Error due to input mapping of '%s' in '%s'.  A common cause of this is conditional outputs that cannot be determined until runtime, please review your workflow."
                 message = message_template % (tool.name, unicodify(k))
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 07ede699ef5..2e35999d7e6 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1959,6 +1959,45 @@ should_run:
             )
             assert len(self.dataset_populator.invocation_jobs(summary.invocation_id)) == 0
 
+    def test_run_workflow_conditional_map_over_expression_tool(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """
+class: GalaxyWorkflow
+inputs:
+  boolean_input_files: collection
+steps:
+- label: param_out
+  tool_id: param_value_from_file
+  in:
+     input1: boolean_input_files
+  state:
+    param_type: boolean
+- label: consume_expression_parameter
+  tool_id: cat1
+  in:
+    input1: boolean_input_files
+  when:
+    source: param_out/boolean_param
+test_data:
+  boolean_input_files:
+    collection_type: list
+    elements:
+      - identifier: true
+        content: true
+      - identifier: false
+        content: false
+""",
+                history_id=history_id,
+            )
+            self.workflow_populator.wait_for_invocation_and_jobs(
+                history_id, workflow_id=None, invocation_id=summary.invocation_id
+            )
+            invocation_jobs = self.dataset_populator.invocation_jobs(summary.invocation_id)
+            assert len(invocation_jobs) == 3
+            assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs
+            assert sum(1 for j in invocation_jobs if j["tool_id"] == "cat1") == 1, invocation_jobs
+
     def test_run_subworkflow_simple(self) -> None:
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(

From 1f44e448733230ecdbb17dca9d72e8b28393568c Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 24 Oct 2022 15:56:15 +0200
Subject: [PATCH 127/350] Into map-over

---
 lib/galaxy_test/api/test_workflows.py | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 2e35999d7e6..39557ec34fc 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1990,9 +1990,6 @@ test_data:
 """,
                 history_id=history_id,
             )
-            self.workflow_populator.wait_for_invocation_and_jobs(
-                history_id, workflow_id=None, invocation_id=summary.invocation_id
-            )
             invocation_jobs = self.dataset_populator.invocation_jobs(summary.invocation_id)
             assert len(invocation_jobs) == 3
             assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs

From fbdc45f7f6a7491c9fa399326700856c6b868392 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 24 Oct 2022 16:46:21 +0200
Subject: [PATCH 128/350] Add when_expression migration

---
 ...518c8438a91b_add_when_expression_column.py | 34 +++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py

diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
new file mode 100644
index 00000000000..80c7de30472
--- /dev/null
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
@@ -0,0 +1,34 @@
+"""Add when_expression column
+
+Revision ID: 518c8438a91b
+Revises: e0e3bb173ee6
+Create Date: 2022-10-24 16:43:39.565871
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+from galaxy.model.custom_types import JSONType
+from galaxy.model.migrations.util import (
+    column_exists,
+    drop_column,
+)
+
+# revision identifiers, used by Alembic.
+revision = "518c8438a91b"
+down_revision = "e0e3bb173ee6"
+branch_labels = None
+depends_on = None
+
+# database object names used in this revision
+table_name = "workflow_step"
+column_name = "when_expression"
+
+
+def upgrade():
+    if not column_exists(table_name, column_name):
+        op.add_column(table_name, sa.Column(column_name, JSONType))
+
+
+def downgrade():
+    drop_column(table_name, column_name)

From b06444fb24f7da2ddd2d40bae77b6bf51da00adc Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 24 Oct 2022 17:09:15 +0200
Subject: [PATCH 129/350] WIP: test map over and pick_value

---
 lib/galaxy_test/api/test_workflows.py | 73 +++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 39557ec34fc..5e81fe99d34 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1995,6 +1995,79 @@ test_data:
             assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs
             assert sum(1 for j in invocation_jobs if j["tool_id"] == "cat1") == 1, invocation_jobs
 
+    def test_run_workflow_conditional_map_over_expression_tool_pick_value(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """
+class: GalaxyWorkflow
+inputs:
+  boolean_input_files_1: collection
+  boolean_input_files_2: collection
+steps:
+- label: param_out_1
+  tool_id: param_value_from_file
+  in:
+     input1: boolean_input_files_1
+  state:
+    param_type: boolean
+- label: param_out_2
+  tool_id: param_value_from_file
+  in:
+     input1: boolean_input_files_2
+  state:
+    param_type: boolean
+- label: consume_expression_parameter_1
+  tool_id: cat1
+  in:
+    input1: boolean_input_files_1
+  when:
+    source: param_out_1/boolean_param
+- label: consume_expression_parameter_2
+  tool_id: cat1
+  in:
+    input1: boolean_input_files_2
+  when:
+    source: param_out_2/boolean_param
+- label: pick_value
+  tool_id: pick_value
+  tool_state:
+    style_cond:
+      pick_style: first_or_error
+      type_cond:
+        param_type: data
+        pick_from:
+        - value:
+            __class__: RuntimeValue
+        - value:
+            __class__: RuntimeValue
+  in:
+    style_cond|type_cond|pick_from_0|value:
+      source: consume_expression_parameter_1/out_file1
+    style_cond|type_cond|pick_from_1|value:
+      source: consume_expression_parameter_2/out_file1
+test_data:
+  boolean_input_files_1:
+    collection_type: list
+    elements:
+      - identifier: true
+        content: true
+      - identifier: false
+        content: false
+  boolean_input_files_2:
+    collection_type: list
+    elements:
+      - identifier: false
+        content: false
+      - identifier: true
+        content: true
+""",
+                history_id=history_id,
+            )
+            invocation_jobs = self.dataset_populator.invocation_jobs(summary.invocation_id)
+            assert len(invocation_jobs) == 3
+            assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs
+            assert sum(1 for j in invocation_jobs if j["tool_id"] == "cat1") == 1, invocation_jobs
+
     def test_run_subworkflow_simple(self) -> None:
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(

From a7e392d0da03464110faa42dedf8deff0b6e74f7 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 25 Oct 2022 14:26:08 +0200
Subject: [PATCH 130/350] Fix up migration

---
 .../versions_gxy/518c8438a91b_add_when_expression_column.py     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
index 80c7de30472..ea8fe53d7c8 100644
--- a/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
@@ -5,8 +5,8 @@ Revises: e0e3bb173ee6
 Create Date: 2022-10-24 16:43:39.565871
 
 """
-from alembic import op
 import sqlalchemy as sa
+from alembic import op
 
 from galaxy.model.custom_types import JSONType
 from galaxy.model.migrations.util import (

From b194db6100ba59f6072a08f4e68943621f088d42 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 25 Oct 2022 14:27:26 +0200
Subject: [PATCH 131/350] WIP: Produce json null on skip, load expression.json
 null as null in json_wrap

Should probably avoid the object store assignment here, but I would also
like to avoid the extra pass through the job handler. OTOH a skipped job
might be nice ?
---
 lib/galaxy/tools/__init__.py                |   2 +
 lib/galaxy/tools/actions/__init__.py        | 131 +++++++++++---------
 lib/galaxy/tools/execute.py                 |   8 +-
 lib/galaxy/tools/parameters/wrapped_json.py |  10 ++
 4 files changed, 88 insertions(+), 63 deletions(-)

diff --git a/lib/galaxy/tools/__init__.py b/lib/galaxy/tools/__init__.py
index fba2844f7d0..a569f884a82 100644
--- a/lib/galaxy/tools/__init__.py
+++ b/lib/galaxy/tools/__init__.py
@@ -1899,6 +1899,7 @@ class Tool(Dictifiable):
         collection_info=None,
         job_callback=None,
         flush_job=True,
+        skip=False,
     ):
         """
         Return a pair with whether execution is successful as well as either
@@ -1916,6 +1917,7 @@ class Tool(Dictifiable):
                 collection_info=collection_info,
                 job_callback=job_callback,
                 flush_job=flush_job,
+                skip=skip,
             )
             job = rval[0]
             out_data = rval[1]
diff --git a/lib/galaxy/tools/actions/__init__.py b/lib/galaxy/tools/actions/__init__.py
index c4c77f5648b..f10c787550f 100644
--- a/lib/galaxy/tools/actions/__init__.py
+++ b/lib/galaxy/tools/actions/__init__.py
@@ -23,6 +23,7 @@ from galaxy.model import (
 )
 from galaxy.model.dataset_collections.builder import CollectionBuilder
 from galaxy.model.none_like import NoneDataset
+from galaxy.objectstore import ObjectStorePopulator
 from galaxy.tools.parameters import update_dataset_ids
 from galaxy.tools.parameters.basic import (
     DataCollectionToolParameter,
@@ -367,6 +368,7 @@ class DefaultToolAction(ToolAction):
         collection_info=None,
         job_callback=None,
         flush_job=True,
+        skip=False,
     ):
         """
         Executes a tool, creating job and tool outputs, associating them, and
@@ -506,7 +508,7 @@ class DefaultToolAction(ToolAction):
                     )
             data.copy_tags_to(preserved_tags.values())
 
-            # This may not be neccesary with the new parent/child associations
+            # This may not be necessary with the new parent/child associations
             data.designation = name
             # Copy metadata from one of the inputs if requested.
 
@@ -635,66 +637,77 @@ class DefaultToolAction(ToolAction):
         history.add_pending_items(set_output_hid=set_output_hid)
 
         log.info(add_datasets_timer)
-        job_setup_timer = ExecutionTimer()
-        # Create the job object
-        job, galaxy_session = self._new_job_for_session(trans, tool, history)
-        self._record_inputs(trans, tool, job, incoming, inp_data, inp_dataset_collections)
-        self._record_outputs(job, out_data, output_collections)
-        # execute immediate post job actions and associate post job actions that are to be executed after the job is complete
-        if job_callback:
-            job_callback(job)
-        if job_params:
-            job.params = dumps(job_params)
-        if completed_job:
-            job.set_copied_from_job_id(completed_job.id)
-        trans.sa_session.add(job)
-        # Remap any outputs if this is a rerun and the user chose to continue dependent jobs
-        # This functionality requires tracking jobs in the database.
-        if app.config.track_jobs_in_database and rerun_remap_job_id is not None:
-            # Need to flush here so that referencing outputs by id works
-            session = trans.sa_session()
-            try:
-                session.expire_on_commit = False
-                session.flush()
-            finally:
-                session.expire_on_commit = True
-            self._remap_job_on_rerun(
-                trans=trans,
-                galaxy_session=galaxy_session,
-                rerun_remap_job_id=rerun_remap_job_id,
-                current_job=job,
-                out_data=out_data,
-            )
-        log.info(f"Setup for job {job.log_str()} complete, ready to be enqueued {job_setup_timer}")
-
-        # Some tools are not really executable, but jobs are still created for them ( for record keeping ).
-        # Examples include tools that redirect to other applications ( epigraph ).  These special tools must
-        # include something that can be retrieved from the params ( e.g., REDIRECT_URL ) to keep the job
-        # from being queued.
-        if "REDIRECT_URL" in incoming:
-            # Get the dataset - there should only be 1
-            for name in inp_data.keys():
-                dataset = inp_data[name]
-            redirect_url = tool.parse_redirect_url(dataset, incoming)
-            # GALAXY_URL should be include in the tool params to enable the external application
-            # to send back to the current Galaxy instance
-            GALAXY_URL = incoming.get("GALAXY_URL", None)
-            assert GALAXY_URL is not None, "GALAXY_URL parameter missing in tool config."
-            redirect_url += f"&GALAXY_URL={GALAXY_URL}"
-            # Job should not be queued, so set state to ok
-            job.set_state(app.model.Job.states.OK)
-            job.info = f"Redirected to: {redirect_url}"
-            trans.sa_session.add(job)
-            trans.sa_session.flush()
-            trans.response.send_redirect(redirect_url)
+        job = trans.app.model.Job()
+        job.state = "ok"
+        if skip:
+            object_store_populator = ObjectStorePopulator(trans.app, trans.user)
+            for data in out_data.values():
+                object_store_populator.set_object_store_id(data)
+                data.extension = "expression.json"
+                data.state = "ok"
+                with open(data.dataset.file_name, "w") as out:
+                    out.write(json.dumps(None))
         else:
-            if flush_job:
-                # Set HID and add to history.
-                job_flush_timer = ExecutionTimer()
-                trans.sa_session.flush()
-                log.info(f"Flushed transaction for job {job.log_str()} {job_flush_timer}")
+            job_setup_timer = ExecutionTimer()
+            # Create the job object
+            job, galaxy_session = self._new_job_for_session(trans, tool, history)
+            self._record_inputs(trans, tool, job, incoming, inp_data, inp_dataset_collections)
+            self._record_outputs(job, out_data, output_collections)
+            # execute immediate post job actions and associate post job actions that are to be executed after the job is complete
+            if job_callback:
+                job_callback(job)
+            if job_params:
+                job.params = dumps(job_params)
+            if completed_job:
+                job.set_copied_from_job_id(completed_job.id)
+            trans.sa_session.add(job)
+            # Remap any outputs if this is a rerun and the user chose to continue dependent jobs
+            # This functionality requires tracking jobs in the database.
+            if app.config.track_jobs_in_database and rerun_remap_job_id is not None:
+                # Need to flush here so that referencing outputs by id works
+                session = trans.sa_session()
+                try:
+                    session.expire_on_commit = False
+                    session.flush()
+                finally:
+                    session.expire_on_commit = True
+                self._remap_job_on_rerun(
+                    trans=trans,
+                    galaxy_session=galaxy_session,
+                    rerun_remap_job_id=rerun_remap_job_id,
+                    current_job=job,
+                    out_data=out_data,
+                )
+            log.info(f"Setup for job {job.log_str()} complete, ready to be enqueued {job_setup_timer}")
 
-            return job, out_data, history
+            # Some tools are not really executable, but jobs are still created for them ( for record keeping ).
+            # Examples include tools that redirect to other applications ( epigraph ).  These special tools must
+            # include something that can be retrieved from the params ( e.g., REDIRECT_URL ) to keep the job
+            # from being queued.
+            if "REDIRECT_URL" in incoming:
+                # Get the dataset - there should only be 1
+                for name in inp_data.keys():
+                    dataset = inp_data[name]
+                redirect_url = tool.parse_redirect_url(dataset, incoming)
+                # GALAXY_URL should be include in the tool params to enable the external application
+                # to send back to the current Galaxy instance
+                GALAXY_URL = incoming.get("GALAXY_URL", None)
+                assert GALAXY_URL is not None, "GALAXY_URL parameter missing in tool config."
+                redirect_url += f"&GALAXY_URL={GALAXY_URL}"
+                # Job should not be queued, so set state to ok
+                job.set_state(app.model.Job.states.OK)
+                job.info = f"Redirected to: {redirect_url}"
+                trans.sa_session.add(job)
+                trans.sa_session.flush()
+                trans.response.send_redirect(redirect_url)
+            else:
+                if flush_job:
+                    # Set HID and add to history.
+                    job_flush_timer = ExecutionTimer()
+                    trans.sa_session.flush()
+                    log.info(f"Flushed transaction for job {job.log_str()} {job_flush_timer}")
+
+        return job, out_data, history
 
     def _remap_job_on_rerun(self, trans, galaxy_session, rerun_remap_job_id, current_job, out_data):
         """
diff --git a/lib/galaxy/tools/execute.py b/lib/galaxy/tools/execute.py
index febd7a3b82f..e89de8c1fb6 100644
--- a/lib/galaxy/tools/execute.py
+++ b/lib/galaxy/tools/execute.py
@@ -90,7 +90,7 @@ def execute(
         )
     execution_cache = ToolExecutionCache(trans)
 
-    def execute_single_job(execution_slice, completed_job):
+    def execute_single_job(execution_slice, completed_job, skip=False):
         job_timer = tool.app.execution_timer_factory.get_timer(
             "internals.galaxy.tools.execute.job_single", SINGLE_EXECUTION_SUCCESS_MESSAGE
         )
@@ -121,6 +121,7 @@ def execute(
             collection_info,
             job_callback=job_callback,
             flush_job=False,
+            skip=skip,
         )
         if job:
             log.debug(job_timer.to_str(tool_id=tool.id, job_id=job.id))
@@ -161,9 +162,8 @@ def execute(
             has_remaining_jobs = True
             break
         else:
-            if execution_slice.param_combination.get("when") is False:
-                continue
-            execute_single_job(execution_slice, completed_jobs[i])
+            skip = execution_slice.param_combination.get("when") is False
+            execute_single_job(execution_slice, completed_jobs[i], skip=skip)
             history = execution_slice.history or history
             jobs_executed += 1
 
diff --git a/lib/galaxy/tools/parameters/wrapped_json.py b/lib/galaxy/tools/parameters/wrapped_json.py
index 1cac8c2e2e5..912ea3eb2c7 100644
--- a/lib/galaxy/tools/parameters/wrapped_json.py
+++ b/lib/galaxy/tools/parameters/wrapped_json.py
@@ -1,3 +1,4 @@
+import json
 import logging
 from typing import (
     Any,
@@ -168,6 +169,15 @@ def _json_wrap_input(input, value_wrapper, profile, handle_files="skip"):
 
 
 def _hda_to_object(hda):
+    if hda.extension == "expression.json":
+        # We may have a null data value
+        with open(str(hda)) as inp:
+            try:
+                rval = json.loads(inp.read(5))
+                if rval is None:
+                    return rval
+            except Exception:
+                pass
     hda_dict = hda.to_dict()
     metadata_dict = {}
 

From f087608f6af08370414752835922a2bc053d494a Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 13:08:00 +0200
Subject: [PATCH 132/350] Fix up map_over of conditional output

---
 lib/galaxy/tools/actions/__init__.py  |  1 +
 lib/galaxy/workflow/modules.py        | 11 +++-------
 lib/galaxy_test/api/test_workflows.py | 30 +++++++++++++++++++++------
 3 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/lib/galaxy/tools/actions/__init__.py b/lib/galaxy/tools/actions/__init__.py
index f10c787550f..2c4c74897da 100644
--- a/lib/galaxy/tools/actions/__init__.py
+++ b/lib/galaxy/tools/actions/__init__.py
@@ -640,6 +640,7 @@ class DefaultToolAction(ToolAction):
         job = trans.app.model.Job()
         job.state = "ok"
         if skip:
+            job.state = "skipped"
             object_store_populator = ObjectStorePopulator(trans.app, trans.user)
             for data in out_data.values():
                 object_store_populator.set_object_store_id(data)
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 5fc820ea738..76dc0723b2c 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -1992,8 +1992,7 @@ class ToolModule(WorkflowModule):
                     found_replacement_keys.add(prefixed_name)  # noqa: B023
 
                     if isinstance(input, ConditionalStepWhen) and replacement is False:
-                        outputs = self.get_all_outputs()
-                        raise SkipWorkflowStepEvaluation(outputs)
+                        raise SkipWorkflowStepEvaluation
 
                 return replacement
 
@@ -2006,12 +2005,9 @@ class ToolModule(WorkflowModule):
                     no_replacement_value=NO_REPLACEMENT,
                     replace_optional_connections=True,
                 )
-            except SkipWorkflowStepEvaluation as we:
-                progress.mark_step_outputs_skipped(invocation_step, we.outputs)
+            except SkipWorkflowStepEvaluation:
                 skip_execution_state = execution_state.inputs
                 skip_execution_state["when"] = False
-                param_combinations.append(execution_state.inputs)
-                continue
             except KeyError as k:
                 message_template = "Error due to input mapping of '%s' in '%s'.  A common cause of this is conditional outputs that cannot be determined until runtime, please review your workflow."
                 message = message_template % (tool.name, unicodify(k))
@@ -2230,8 +2226,7 @@ class CancelWorkflowEvaluation(Exception):
 
 
 class SkipWorkflowStepEvaluation(Exception):
-    def __init__(self, outputs):
-        self.outputs = outputs
+    pass
 
 
 class WorkflowModuleInjector:
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 5e81fe99d34..c7a192c6f93 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -2003,6 +2003,9 @@ class: GalaxyWorkflow
 inputs:
   boolean_input_files_1: collection
   boolean_input_files_2: collection
+outputs:
+  my_output:
+    outputSource: pick_value/data_param
 steps:
 - label: param_out_1
   tool_id: param_value_from_file
@@ -2032,13 +2035,17 @@ steps:
   tool_id: pick_value
   tool_state:
     style_cond:
+      __current_case__: 2
       pick_style: first_or_error
       type_cond:
+        __current_case__: 4
         param_type: data
         pick_from:
-        - value:
+        - __index__: 0
+          value:
             __class__: RuntimeValue
-        - value:
+        - __index__: 1
+          value:
             __class__: RuntimeValue
   in:
     style_cond|type_cond|pick_from_0|value:
@@ -2063,10 +2070,21 @@ test_data:
 """,
                 history_id=history_id,
             )
-            invocation_jobs = self.dataset_populator.invocation_jobs(summary.invocation_id)
-            assert len(invocation_jobs) == 3
-            assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs
-            assert sum(1 for j in invocation_jobs if j["tool_id"] == "cat1") == 1, invocation_jobs
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            output_collection_id = invocation_details["output_collections"]["my_output"]["id"]
+            hdca_details = self.dataset_populator.get_history_collection_details(
+                history_id=history_id, content_id=output_collection_id
+            )
+            elements = hdca_details["elements"]
+            assert len(elements) == 2
+            for element in elements:
+                content = self.dataset_populator.get_history_dataset_content(
+                    history_id, content_id=element["object"]["id"]
+                )
+                assert content == "True"
+            consume_expression_parameter_2 = invocation_details["steps"][5]
+            assert consume_expression_parameter_2["workflow_step_label"] == "consume_expression_parameter_2"
+            assert consume_expression_parameter_2["jobs"][0]["state"] == "skipped"
 
     def test_run_subworkflow_simple(self) -> None:
         with self.dataset_populator.test_history() as history_id:

From c146f1771a4b5c1b71850cb35bb8e9d90b0beddd Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 14:03:03 +0200
Subject: [PATCH 133/350] Assert skipped state in tests

---
 lib/galaxy_test/api/test_workflows.py | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index c7a192c6f93..856ff3a19dc 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1957,7 +1957,10 @@ should_run:
 """,
                 history_id=history_id,
             )
-            assert len(self.dataset_populator.invocation_jobs(summary.invocation_id)) == 0
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            conditional_jobs = invocation_details["steps"][2]["jobs"]
+            assert conditional_jobs[0]["state"] == "ok"
+            assert conditional_jobs[1]["state"] == "skipped"
 
     def test_run_workflow_conditional_map_over_expression_tool(self):
         with self.dataset_populator.test_history() as history_id:
@@ -1990,10 +1993,10 @@ test_data:
 """,
                 history_id=history_id,
             )
-            invocation_jobs = self.dataset_populator.invocation_jobs(summary.invocation_id)
-            assert len(invocation_jobs) == 3
-            assert sum(1 for j in invocation_jobs if j["tool_id"] == "param_value_from_file") == 2, invocation_jobs
-            assert sum(1 for j in invocation_jobs if j["tool_id"] == "cat1") == 1, invocation_jobs
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            conditional_jobs = invocation_details["steps"][2]["jobs"]
+            assert conditional_jobs[0]["state"] == "ok"
+            assert conditional_jobs[1]["state"] == "skipped"
 
     def test_run_workflow_conditional_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:

From d39674396a01ff54f85b71cfa48a295072c0be2b Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 14:06:24 +0200
Subject: [PATCH 134/350] Drop unreachable SkipWorkflowStepEvaluation except
 statement

---
 lib/galaxy/workflow/run.py | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index deabbb72288..104ec7e9ec4 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -209,9 +209,6 @@ class WorkflowInvoker:
                     self.progress.mark_step_outputs_delayed(step, why="Not all jobs scheduled for state.")
                 else:
                     workflow_invocation_step.state = "scheduled"
-            except modules.SkipWorkflowStepEvaluation as we:
-                log.info("Skipping workflow step!")
-                self.progress.mark_step_outputs_skipped(workflow_invocation_step, we.outputs)
             except modules.DelayedWorkflowEvaluation as de:
                 step_delayed = delayed_steps = True
                 self.progress.mark_step_outputs_delayed(step, why=de.why)

From 0fb4118faf8562ab296b4ec4863c03da3db536a2 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 14:07:18 +0200
Subject: [PATCH 135/350] Drop unused function

---
 lib/galaxy/workflow/run.py | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index 104ec7e9ec4..002b93ee211 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -513,13 +513,6 @@ class WorkflowProgress:
     def _record_workflow_output(self, step: "WorkflowStep", workflow_output: "WorkflowOutput", output: Any) -> None:
         self.workflow_invocation.add_output(workflow_output, step, output)
 
-    def mark_step_outputs_skipped(self, invocation_step, outputs):
-        # TODO: Mark the step skipped in the database somehow?
-        null_outputs = {}
-        for output in outputs:
-            null_outputs[output["name"]] = None
-        self.set_step_outputs(invocation_step, null_outputs)
-
     def mark_step_outputs_delayed(self, step: "WorkflowStep", why: Optional[str] = None) -> None:
         if why:
             message = f"Marking step {step.id} outputs of invocation {self.workflow_invocation.id} delayed ({why})"

From bfc4801e6d158da73410e7c470880d48183775b6 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 17:05:18 +0200
Subject: [PATCH 136/350] Fix type annotation for temp_input_connections

---
 lib/galaxy/managers/workflows.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index e793c53ed1d..a0801e5c432 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -10,6 +10,7 @@ from typing import (
     NamedTuple,
     Optional,
     Tuple,
+    Union,
 )
 
 from gxformat2 import (
@@ -1668,7 +1669,11 @@ class WorkflowContentsManager(UsesAnnotations):
             self.add_item_annotation(sa_session, trans.get_user(), step, annotation)
 
         # Stick this in the step temporarily
-        step.temp_input_connections = step_dict.get("input_connections", {})
+        DictConnection = Dict[str, Union[int, str]]
+        temp_input_connections: Dict[str, Union[List[DictConnection], DictConnection]] = step_dict.get(
+            "input_connections", {}
+        )
+        step.temp_input_connections = temp_input_connections
 
         # Create the model class for the step
         steps.append(step)

From 20d92ad3ee460d19850e07c1cdee01b6132a9b29 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 17:18:02 +0200
Subject: [PATCH 137/350] Make new tests robust to job and step order

which seems to not be stable?!
---
 lib/galaxy_test/api/test_workflows.py | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 856ff3a19dc..8be1958c68d 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1930,7 +1930,7 @@ test_data:
                 history_id=history_id,
             )
 
-    def test_run_workflow_simple_conditional(self):
+    def test_run_workflow_simple_conditional_step(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
                 """class: GalaxyWorkflow
@@ -1958,11 +1958,11 @@ should_run:
                 history_id=history_id,
             )
             invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
-            conditional_jobs = invocation_details["steps"][2]["jobs"]
-            assert conditional_jobs[0]["state"] == "ok"
-            assert conditional_jobs[1]["state"] == "skipped"
+            for step in invocation_details["steps"]:
+                if step["workflow_step_label"] == "cat1":
+                    assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
 
-    def test_run_workflow_conditional_map_over_expression_tool(self):
+    def test_run_workflow_conditional_step_map_over_expression_tool(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
                 """
@@ -1994,11 +1994,11 @@ test_data:
                 history_id=history_id,
             )
             invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
-            conditional_jobs = invocation_details["steps"][2]["jobs"]
-            assert conditional_jobs[0]["state"] == "ok"
-            assert conditional_jobs[1]["state"] == "skipped"
+            for step in invocation_details["steps"]:
+                if step["workflow_step_label"] == "consume_expression_parameter":
+                    assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
 
-    def test_run_workflow_conditional_map_over_expression_tool_pick_value(self):
+    def test_run_workflow_conditional_step_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
                 """
@@ -2085,9 +2085,9 @@ test_data:
                     history_id, content_id=element["object"]["id"]
                 )
                 assert content == "True"
-            consume_expression_parameter_2 = invocation_details["steps"][5]
-            assert consume_expression_parameter_2["workflow_step_label"] == "consume_expression_parameter_2"
-            assert consume_expression_parameter_2["jobs"][0]["state"] == "skipped"
+            for step in invocation_details["steps"]:
+                if step["workflow_step_label"].startswith("consume_expression_parameter_"):
+                    assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
 
     def test_run_subworkflow_simple(self) -> None:
         with self.dataset_populator.test_history() as history_id:

From a633f1e76cb954b463a461ecbd223b165a7fb957 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 26 Oct 2022 21:22:18 +0200
Subject: [PATCH 138/350] Make sure we're not changing datatypes on skipped
 outputs

---
 lib/galaxy/job_execution/actions/post.py |   3 +
 lib/galaxy/model/__init__.py             |   1 +
 lib/galaxy/tools/actions/__init__.py     | 117 +++++++++++------------
 lib/galaxy_test/api/test_workflows.py    |  13 ++-
 4 files changed, 73 insertions(+), 61 deletions(-)

diff --git a/lib/galaxy/job_execution/actions/post.py b/lib/galaxy/job_execution/actions/post.py
index c377681640a..8b329b48ce1 100644
--- a/lib/galaxy/job_execution/actions/post.py
+++ b/lib/galaxy/job_execution/actions/post.py
@@ -109,6 +109,9 @@ class ChangeDatatypeAction(DefaultJobAction):
 
     @classmethod
     def execute(cls, app, sa_session, action, job, replacement_dict, final_job_state=None):
+        if job.state == job.states.SKIPPED:
+            # Don't change datatype, must remain expression.json
+            return
         for dataset_assoc in job.output_datasets:
             if action.output_name == "" or dataset_assoc.name == action.output_name:
                 app.datatypes_registry.change_datatype(dataset_assoc.dataset, action.action_arguments["newtype"])
diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index 193ae685b59..e5d4ddded3f 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -1072,6 +1072,7 @@ class Job(Base, JobLike, UsesCreateAndUpdateTime, Dictifiable, Serializable):
         DELETED_NEW = "deleted_new"  # now DELETING, remove after 21.0
         STOPPING = "stop"
         STOPPED = "stopped"
+        SKIPPED = "skipped"
 
     terminal_states = [states.OK, states.ERROR, states.DELETED]
     #: job states where the job hasn't finished and the model may still change
diff --git a/lib/galaxy/tools/actions/__init__.py b/lib/galaxy/tools/actions/__init__.py
index 2c4c74897da..7da45dfea24 100644
--- a/lib/galaxy/tools/actions/__init__.py
+++ b/lib/galaxy/tools/actions/__init__.py
@@ -637,10 +637,11 @@ class DefaultToolAction(ToolAction):
         history.add_pending_items(set_output_hid=set_output_hid)
 
         log.info(add_datasets_timer)
-        job = trans.app.model.Job()
-        job.state = "ok"
+        job_setup_timer = ExecutionTimer()
+        # Create the job object
+        job, galaxy_session = self._new_job_for_session(trans, tool, history)
         if skip:
-            job.state = "skipped"
+            job.state = job.states.SKIPPED
             object_store_populator = ObjectStorePopulator(trans.app, trans.user)
             for data in out_data.values():
                 object_store_populator.set_object_store_id(data)
@@ -648,65 +649,61 @@ class DefaultToolAction(ToolAction):
                 data.state = "ok"
                 with open(data.dataset.file_name, "w") as out:
                     out.write(json.dumps(None))
-        else:
-            job_setup_timer = ExecutionTimer()
-            # Create the job object
-            job, galaxy_session = self._new_job_for_session(trans, tool, history)
-            self._record_inputs(trans, tool, job, incoming, inp_data, inp_dataset_collections)
-            self._record_outputs(job, out_data, output_collections)
-            # execute immediate post job actions and associate post job actions that are to be executed after the job is complete
-            if job_callback:
-                job_callback(job)
-            if job_params:
-                job.params = dumps(job_params)
-            if completed_job:
-                job.set_copied_from_job_id(completed_job.id)
-            trans.sa_session.add(job)
-            # Remap any outputs if this is a rerun and the user chose to continue dependent jobs
-            # This functionality requires tracking jobs in the database.
-            if app.config.track_jobs_in_database and rerun_remap_job_id is not None:
-                # Need to flush here so that referencing outputs by id works
-                session = trans.sa_session()
-                try:
-                    session.expire_on_commit = False
-                    session.flush()
-                finally:
-                    session.expire_on_commit = True
-                self._remap_job_on_rerun(
-                    trans=trans,
-                    galaxy_session=galaxy_session,
-                    rerun_remap_job_id=rerun_remap_job_id,
-                    current_job=job,
-                    out_data=out_data,
-                )
-            log.info(f"Setup for job {job.log_str()} complete, ready to be enqueued {job_setup_timer}")
+        self._record_inputs(trans, tool, job, incoming, inp_data, inp_dataset_collections)
+        self._record_outputs(job, out_data, output_collections)
+        # execute immediate post job actions and associate post job actions that are to be executed after the job is complete
+        if job_callback:
+            job_callback(job)
+        if job_params:
+            job.params = dumps(job_params)
+        if completed_job:
+            job.set_copied_from_job_id(completed_job.id)
+        trans.sa_session.add(job)
+        # Remap any outputs if this is a rerun and the user chose to continue dependent jobs
+        # This functionality requires tracking jobs in the database.
+        if app.config.track_jobs_in_database and rerun_remap_job_id is not None:
+            # Need to flush here so that referencing outputs by id works
+            session = trans.sa_session()
+            try:
+                session.expire_on_commit = False
+                session.flush()
+            finally:
+                session.expire_on_commit = True
+            self._remap_job_on_rerun(
+                trans=trans,
+                galaxy_session=galaxy_session,
+                rerun_remap_job_id=rerun_remap_job_id,
+                current_job=job,
+                out_data=out_data,
+            )
+        log.info(f"Setup for job {job.log_str()} complete, ready to be enqueued {job_setup_timer}")
 
-            # Some tools are not really executable, but jobs are still created for them ( for record keeping ).
-            # Examples include tools that redirect to other applications ( epigraph ).  These special tools must
-            # include something that can be retrieved from the params ( e.g., REDIRECT_URL ) to keep the job
-            # from being queued.
-            if "REDIRECT_URL" in incoming:
-                # Get the dataset - there should only be 1
-                for name in inp_data.keys():
-                    dataset = inp_data[name]
-                redirect_url = tool.parse_redirect_url(dataset, incoming)
-                # GALAXY_URL should be include in the tool params to enable the external application
-                # to send back to the current Galaxy instance
-                GALAXY_URL = incoming.get("GALAXY_URL", None)
-                assert GALAXY_URL is not None, "GALAXY_URL parameter missing in tool config."
-                redirect_url += f"&GALAXY_URL={GALAXY_URL}"
-                # Job should not be queued, so set state to ok
-                job.set_state(app.model.Job.states.OK)
-                job.info = f"Redirected to: {redirect_url}"
-                trans.sa_session.add(job)
+        # Some tools are not really executable, but jobs are still created for them ( for record keeping ).
+        # Examples include tools that redirect to other applications ( epigraph ).  These special tools must
+        # include something that can be retrieved from the params ( e.g., REDIRECT_URL ) to keep the job
+        # from being queued.
+        if "REDIRECT_URL" in incoming:
+            # Get the dataset - there should only be 1
+            for name in inp_data.keys():
+                dataset = inp_data[name]
+            redirect_url = tool.parse_redirect_url(dataset, incoming)
+            # GALAXY_URL should be include in the tool params to enable the external application
+            # to send back to the current Galaxy instance
+            GALAXY_URL = incoming.get("GALAXY_URL", None)
+            assert GALAXY_URL is not None, "GALAXY_URL parameter missing in tool config."
+            redirect_url += f"&GALAXY_URL={GALAXY_URL}"
+            # Job should not be queued, so set state to ok
+            job.set_state(app.model.Job.states.OK)
+            job.info = f"Redirected to: {redirect_url}"
+            trans.sa_session.add(job)
+            trans.sa_session.flush()
+            trans.response.send_redirect(redirect_url)
+        else:
+            if flush_job:
+                # Set HID and add to history.
+                job_flush_timer = ExecutionTimer()
                 trans.sa_session.flush()
-                trans.response.send_redirect(redirect_url)
-            else:
-                if flush_job:
-                    # Set HID and add to history.
-                    job_flush_timer = ExecutionTimer()
-                    trans.sa_session.flush()
-                    log.info(f"Flushed transaction for job {job.log_str()} {job_flush_timer}")
+                log.info(f"Flushed transaction for job {job.log_str()} {job_flush_timer}")
 
         return job, out_data, history
 
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 8be1958c68d..a7069013502 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1980,6 +1980,9 @@ steps:
   tool_id: cat1
   in:
     input1: boolean_input_files
+  out:
+    out_file1:
+      change_datatype: txt
   when:
     source: param_out/boolean_param
 test_data:
@@ -1996,7 +1999,15 @@ test_data:
             invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
             for step in invocation_details["steps"]:
                 if step["workflow_step_label"] == "consume_expression_parameter":
-                    assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
+                    skipped_jobs = [j for j in step["jobs"] if j["state"] == "skipped"]
+                    assert len(skipped_jobs) == 1
+                    # also assert that change_datatype was ignored for null output
+                    job_details = self.dataset_populator.get_job_details(skipped_jobs[0]["id"], full=True).json()
+                    skipped_hda_id = job_details["outputs"]["out_file1"]["id"]
+                    dataset_details = self.dataset_populator.get_history_dataset_details(
+                        history_id=history_id, content_id=skipped_hda_id
+                    )
+                    assert dataset_details["file_ext"] == "expression.json", dataset_details
 
     def test_run_workflow_conditional_step_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:

From 4ac429c0dc4423a6f93c0047c550f04418122f7f Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 10 Nov 2022 18:04:40 +0100
Subject: [PATCH 139/350] Add skipped to job state summary

---
 lib/galaxy/model/view/__init__.py | 2 ++
 lib/galaxy/schema/schema.py       | 5 +++++
 2 files changed, 7 insertions(+)

diff --git a/lib/galaxy/model/view/__init__.py b/lib/galaxy/model/view/__init__.py
index 0bb5c2771a1..04fd7d64870 100644
--- a/lib/galaxy/model/view/__init__.py
+++ b/lib/galaxy/model/view/__init__.py
@@ -26,6 +26,7 @@ SELECT
     SUM(CASE WHEN state = 'error' THEN 1 ELSE 0 END) AS error,
     SUM(CASE WHEN state = 'failed' THEN 1 ELSE 0 END) AS failed,
     SUM(CASE WHEN state = 'paused' THEN 1 ELSE 0 END) AS paused,
+    SUM(CASE WHEN state = 'skipped' THEN 1 ELSE 0 END) AS skipped,
     SUM(CASE WHEN state = 'deleted' THEN 1 ELSE 0 END) AS deleted,
     SUM(CASE WHEN state = 'deleted_new' THEN 1 ELSE 0 END) AS deleted_new,
     SUM(CASE WHEN state = 'upload' THEN 1 ELSE 0 END) AS upload,
@@ -61,6 +62,7 @@ GROUP BY jobstates.hdca_id
         column("error", Integer),
         column("failed", Integer),
         column("paused", Integer),
+        column("skipped", Integer),
         column("deleted", Integer),
         column("deleted_new", Integer),
         column("upload", Integer),
diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index 2c81fab87f9..b50faa5feb8 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -733,6 +733,11 @@ class HDCJobStateSummary(Model):
         title="Paused jobs",
         description="Number of jobs in the `paused` state.",
     )
+    skipped: int = Field(
+        0,
+        title="Skipped jobs",
+        description="Number of jobs that were skipped due to conditional workflow step execution.",
+    )
     deleted_new: int = Field(
         0,
         title="Deleted new jobs",

From bbfc689bfe9b66a616ce462a48b46d38e0dffb89 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 10 Nov 2022 16:14:50 +0100
Subject: [PATCH 140/350] Implement conditional subwokflow steps

for mapped over subworkflows and simple subworkflows
---
 lib/galaxy/workflow/modules.py        |  48 +++++++----
 lib/galaxy/workflow/run.py            |  11 ++-
 lib/galaxy_test/api/test_workflows.py | 111 ++++++++++++++++++++++++++
 3 files changed, 152 insertions(+), 18 deletions(-)

diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 76dc0723b2c..037a58b5a06 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -383,6 +383,9 @@ class WorkflowModule:
         collections_to_match = matching.CollectionsToMatch()
         dataset_collection_type_descriptions = self.trans.app.dataset_collection_manager.collection_type_descriptions
 
+        if progress.when:
+            collections_to_match.add("when_source", progress.when)
+
         for input_dict in all_inputs:
             name = input_dict["name"]
             data = progress.replacement_for_input(step, input_dict)
@@ -446,6 +449,17 @@ class WorkflowModule:
 
         return collections_to_match
 
+    @staticmethod
+    def create_when_source_param():
+        return dict(
+            name="when_source",
+            label="when_source",
+            multiple=False,
+            input_type="parameter",
+            optional=False,
+            type="boolean",
+        )
+
 
 class SubWorkflowModule(WorkflowModule):
     # Two step improvements to build runtime inputs for subworkflow modules
@@ -600,10 +614,18 @@ class SubWorkflowModule(WorkflowModule):
         inputs, etc...
         """
         step = invocation_step.workflow_step
-        collection_info = self.compute_collection_info(progress, step, self.get_all_inputs())
+        all_inputs = self.get_all_inputs()
+        if step.input_connections_by_name.get("when_source"):
+            param_dict = self.create_when_source_param()
+            all_inputs.append(param_dict)
+            # Maybe make this lazy with a callback ?
+            when = progress.replacement_for_input(step, param_dict)
+
+        collection_info = self.compute_collection_info(progress, step, all_inputs)
         structure = collection_info.structure if collection_info else None
+
         subworkflow_invoker = progress.subworkflow_invoker(
-            trans, step, use_cached_job=use_cached_job, subworkflow_structure=structure
+            trans, step, use_cached_job=use_cached_job, subworkflow_structure=structure, when=when
         )
         subworkflow_invoker.invoke()
         subworkflow = subworkflow_invoker.workflow
@@ -1641,18 +1663,6 @@ class ToolModule(WorkflowModule):
     def get_inputs(self):
         return self.tool.inputs if self.tool else {}
 
-    def get_conditional_param(self, inputs):
-        inputs.append(
-            dict(
-                name="when_source",
-                label="when_source",
-                multiple=False,
-                input_type="parameter",
-                optional=False,
-                type="boolean",
-            )
-        )
-
     def get_all_inputs(self, data_only=False, connectable_only=False):
         if data_only and connectable_only:
             raise Exception("Must specify at most one of data_only and connectable_only as True.")
@@ -1945,8 +1955,8 @@ class ToolModule(WorkflowModule):
             del tool_state.inputs[RUNTIME_STEP_META_STATE_KEY]
 
         all_inputs = self.get_all_inputs()
-        if step.input_connections_by_name.get("when_source"):
-            self.get_conditional_param(all_inputs)
+        if progress.when is not None or step.input_connections_by_name.get("when_source"):
+            all_inputs.append(self.create_when_source_param())
             tool_inputs["when_source"] = ConditionalStepWhen(None, {"name": "when_source", "type": "boolean"})
         all_inputs_by_name = {}
         for input_dict in all_inputs:
@@ -1975,6 +1985,8 @@ class ToolModule(WorkflowModule):
                 replacement: Union[model.Dataset, NoReplacement] = NO_REPLACEMENT
                 if iteration_elements and prefixed_name in iteration_elements:  # noqa: B023
                     replacement = iteration_elements[prefixed_name]  # noqa: B023
+                elif prefixed_name == "when_source" and progress.when is not None:
+                    replacement = progress.when
                 else:
                     replacement = progress.replacement_for_input(step, input_dict)
 
@@ -1991,7 +2003,9 @@ class ToolModule(WorkflowModule):
                                 replacement = json.load(f)
                     found_replacement_keys.add(prefixed_name)  # noqa: B023
 
-                    if isinstance(input, ConditionalStepWhen) and replacement is False:
+                    # bool cast should be fine, can only have true/false on ConditionalStepWhen
+                    # also terrible of course and it's not needed for API requests
+                    if isinstance(input, ConditionalStepWhen) and bool(replacement) is False:
                         raise SkipWorkflowStepEvaluation
 
                 return replacement
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index 002b93ee211..d860a82482a 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -306,6 +306,7 @@ class WorkflowProgress:
         use_cached_job: bool = False,
         replacement_dict: Optional[Dict[str, str]] = None,
         subworkflow_structure=None,
+        when=None,
     ) -> None:
         self.outputs: Dict[int, Any] = {}
         self.module_injector = module_injector
@@ -318,6 +319,7 @@ class WorkflowProgress:
         self.use_cached_job = use_cached_job
         self.replacement_dict = replacement_dict or {}
         self.subworkflow_structure = subworkflow_structure
+        self.when = when
 
     @property
     def maximum_jobs_to_schedule_or_none(self) -> Optional[int]:
@@ -532,11 +534,16 @@ class WorkflowProgress:
         step: "WorkflowStep",
         use_cached_job: bool = False,
         subworkflow_structure=None,
+        when=None,
     ) -> WorkflowInvoker:
         subworkflow_invocation = self._subworkflow_invocation(step)
         workflow_run_config = workflow_request_to_run_config(subworkflow_invocation, use_cached_job)
         subworkflow_progress = self.subworkflow_progress(
-            subworkflow_invocation, step, workflow_run_config.param_map, subworkflow_structure=subworkflow_structure
+            subworkflow_invocation,
+            step,
+            workflow_run_config.param_map,
+            subworkflow_structure=subworkflow_structure,
+            when=when,
         )
         subworkflow_invocation = subworkflow_progress.workflow_invocation
         return WorkflowInvoker(
@@ -552,6 +559,7 @@ class WorkflowProgress:
         step: "WorkflowStep",
         param_map: Dict,
         subworkflow_structure=None,
+        when=None,
     ) -> "WorkflowProgress":
         subworkflow = subworkflow_invocation.workflow
         subworkflow_inputs = {}
@@ -580,6 +588,7 @@ class WorkflowProgress:
             use_cached_job=self.use_cached_job,
             replacement_dict=self.replacement_dict,
             subworkflow_structure=subworkflow_structure,
+            when=when,
         )
 
     def _recover_mapping(self, step_invocation: WorkflowInvocationStep) -> None:
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index a7069013502..0939c99abd9 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1962,6 +1962,59 @@ should_run:
                 if step["workflow_step_label"] == "cat1":
                     assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
 
+    def test_run_workflow_subworkflow_conditional_step(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """class: GalaxyWorkflow
+inputs:
+  should_run:
+    type: boolean
+  some_file:
+    type: data
+steps:
+  subworkflow:
+    run:
+      class: GalaxyWorkflow
+      inputs:
+        some_file:
+          type: data
+      steps:
+        a_tool_step:
+          tool_id: cat1
+          in:
+            input1: some_file
+    in:
+      some_file: some_file
+    outputs:
+      inner_out: a_tool_step/out_file1
+    when:
+      source: should_run
+outputs:
+  outer_output:
+    outputSource: subworkflow/inner_out
+""",
+                test_data="""
+some_file:
+  value: 1.bed
+  type: File
+should_run:
+  value: false
+  type: raw
+""",
+                history_id=history_id,
+                wait=True,
+                assert_ok=True,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            subworkflow_invocation_id = invocation_details["steps"][-1]["subworkflow_invocation_id"]
+            self.workflow_populator.wait_for_invocation_and_jobs(
+                history_id=history_id, workflow_id="whatever", invocation_id=subworkflow_invocation_id
+            )
+            invocation_details = self.workflow_populator.get_invocation(subworkflow_invocation_id, step_details=True)
+            for step in invocation_details["steps"]:
+                if step["workflow_step_label"] == "a_tool_step":
+                    assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
+
     def test_run_workflow_conditional_step_map_over_expression_tool(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
@@ -2009,6 +2062,64 @@ test_data:
                     )
                     assert dataset_details["file_ext"] == "expression.json", dataset_details
 
+    def test_run_workflow_conditional_subworkflow_step_map_over_expression_tool(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """
+class: GalaxyWorkflow
+inputs:
+  boolean_input_files: collection
+steps:
+  create_list_of_boolean:
+    tool_id: param_value_from_file
+    in:
+       input1: boolean_input_files
+    state:
+      param_type: boolean
+  subworkflow:
+    run:
+      class: GalaxyWorkflow
+      inputs:
+        boolean_input_file: data
+      steps:
+        consume_expression_parameter:
+          tool_id: cat1
+          in:
+            input1: boolean_input_file
+          out:
+            out_file1:
+              change_datatype: txt
+      outputs:
+        inner_output:
+          outputSource: consume_expression_parameter/out_file1
+    in:
+      boolean_input_file: boolean_input_files
+    when:
+      source: create_list_of_boolean/boolean_param
+outputs:
+  outer_output:
+    outputSource: subworkflow/inner_output
+test_data:
+  boolean_input_files:
+    collection_type: list
+    elements:
+      - identifier: true
+        content: true
+      - identifier: false
+        content: false
+""",
+                history_id=history_id,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            assert "outer_output" in invocation_details["output_collections"]
+            outer_output = invocation_details["output_collections"]["outer_output"]
+            outer_hdca = self.dataset_populator.get_history_collection_details(
+                history_id, content_id=outer_output["id"]
+            )
+            assert outer_hdca["job_state_summary"]["all_jobs"] == 2
+            assert outer_hdca["job_state_summary"]["ok"] == 1
+            assert outer_hdca["job_state_summary"]["skipped"] == 1
+
     def test_run_workflow_conditional_step_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(

From 63549fe034fb0ad6d7e96561f5ebd21cae27c083 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 13 Nov 2022 15:25:36 +0100
Subject: [PATCH 141/350] Stick with CWL syntax and CWL tooling to implement
 step skipping

---
 lib/galaxy/managers/workflows.py      |   5 +-
 lib/galaxy/model/__init__.py          |  19 +++
 lib/galaxy/tools/execute.py           |   2 +-
 lib/galaxy/workflow/modules.py        | 215 ++++++++++++++++++++++----
 lib/galaxy_test/api/test_workflows.py |  24 +--
 5 files changed, 214 insertions(+), 51 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index a0801e5c432..e72603aa42e 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -1715,10 +1715,7 @@ class WorkflowContentsManager(UsesAnnotations):
                     step_input.default_value_set = True
 
         if "when" in step_dict:
-            if isinstance(step_dict["when"], dict) and "source" in step_dict["when"]:
-                step.temp_input_connections["when_source"] = step_dict["when"]["source"]
-            else:
-                step.when_expression = step_dict["when"]
+            step.when_expression = step_dict["when"]
         if dry_run and step in trans.sa_session:
             trans.sa_session.expunge(step)
 
diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index e5d4ddded3f..f7f0f98a466 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -7086,10 +7086,12 @@ class WorkflowStep(Base, RepresentById):
     def __init__(self):
         self.uuid = uuid4()
         self._input_connections_by_name = None
+        self._inputs_by_name = None
 
     @reconstructor
     def init_on_load(self):
         self._input_connections_by_name = None
+        self._inputs_by_name = None
 
     @property
     def tool_uuid(self):
@@ -7115,6 +7117,23 @@ class WorkflowStep(Base, RepresentById):
         tool_state = self.tool_inputs
         return tool_state.get("optional") or False
 
+    def setup_inputs_by_name(self):
+        # Ensure input_connections has already been set.
+
+        # Make connection information available on each step by input name.
+        inputs_by_name = {}
+        for step_input in self.inputs:
+            input_name = step_input.name
+            assert input_name not in inputs_by_name
+            inputs_by_name[input_name] = step_input
+        self._inputs_by_name = inputs_by_name
+
+    @property
+    def inputs_by_name(self):
+        if self._inputs_by_name is None:
+            self.setup_inputs_by_name()
+        return self._inputs_by_name
+
     def get_input(self, input_name):
         for step_input in self.inputs:
             if step_input.name == input_name:
diff --git a/lib/galaxy/tools/execute.py b/lib/galaxy/tools/execute.py
index e89de8c1fb6..910a04e497b 100644
--- a/lib/galaxy/tools/execute.py
+++ b/lib/galaxy/tools/execute.py
@@ -162,7 +162,7 @@ def execute(
             has_remaining_jobs = True
             break
         else:
-            skip = execution_slice.param_combination.get("when") is False
+            skip = execution_slice.param_combination.pop("__when_value__", None) is False
             execute_single_job(execution_slice, completed_jobs[i], skip=skip)
             history = execution_slice.history or history
             jobs_executed += 1
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 037a58b5a06..16921476669 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -17,6 +17,7 @@ from typing import (
 )
 
 import packaging.version
+from cwl_utils.expression import do_eval
 from typing_extensions import TypedDict
 
 from galaxy import (
@@ -36,6 +37,7 @@ from galaxy.model import (
     WorkflowStepConnection,
 )
 from galaxy.model.dataset_collections import matching
+from galaxy.tool_util.cwl.util import set_basename_and_derived_properties
 from galaxy.tool_util.parser.output_objects import ToolExpressionOutput
 from galaxy.tools import (
     DatabaseOperationTool,
@@ -108,6 +110,96 @@ class ConditionalStepWhen(BooleanToolParameter):
     pass
 
 
+def evaluate_value_from_expressions(progress, step, execution_state, extra_step_state):
+    when_expression = step.when_expression
+    value_from_expressions = {}
+    replacements = {}
+
+    if execution_state:
+        for key in execution_state.inputs.keys():
+            step_input = step.inputs_by_name.get(key)
+            if step_input and step_input.value_from is not None:
+                value_from_expressions[key] = step_input.value_from
+
+    if not value_from_expressions and when_expression is None:
+        return replacements
+
+    hda_references = []
+
+    def to_cwl(value):
+        element_identifier = None
+        if isinstance(value, model.DatasetCollectionElement) and value.hda:
+            element_identifier = value.element_identifier
+            value = value.hda
+        if isinstance(value, model.HistoryDatasetAssociation):
+            # I think the following two checks are needed but they may
+            # not be needed.
+            if not value.dataset.in_ready_state():
+                why = "dataset [%s] is needed for valueFrom expression and is non-ready" % value.id
+                raise DelayedWorkflowEvaluation(why=why)
+            if not value.is_ok:
+                raise CancelWorkflowEvaluation()
+            if value.ext == "expression.json":
+                with open(value.file_name) as f:
+                    # OUR safe_loads won't work, will not load numbers, etc...
+                    return json.load(f)
+            else:
+                hda_references.append(value)
+                properties = {
+                    "class": "File",
+                    "location": "step_input://%d" % len(hda_references),
+                }
+                set_basename_and_derived_properties(
+                    properties, value.dataset.created_from_basename or element_identifier or value.name
+                )
+                return properties
+        elif hasattr(value, "collection"):
+            collection = value.collection
+            if collection.collection_type == "list":
+                return [to_cwl(dce) for dce in collection.dataset_elements]
+            else:
+                # Could be record or nested lists
+                rval = {}
+                for element in collection.elements:
+                    rval[element.element_identifier] = to_cwl(element.element_object)
+                return rval
+        else:
+            return value
+
+    def from_cwl(value):
+        # TODO: turn actual files into HDAs here ... somehow I suppose. Things with
+        # file:// locations for instance.
+        if isinstance(value, dict) and "class" in value and "location" in value:
+            if value["class"] == "File":
+                # This is going to re-file -> HDA this each iteration I think, not a good
+                # implementation.
+                return progress.raw_to_galaxy(value)
+            assert value["location"].startswith("step_input://"), "Invalid location %s" % value
+            return hda_references[int(value["location"][len("step_input://") :]) - 1]
+        elif isinstance(value, dict):
+            raise NotImplementedError()
+        else:
+            return value
+
+    step_state = {}
+    for key, value in extra_step_state.items():
+        step_state[key] = to_cwl(value)
+    if execution_state:
+        for key, value in execution_state.inputs.items():
+            step_state[key] = to_cwl(value)
+
+    if when_expression is not None:
+        as_cwl_value = do_eval(
+            when_expression,
+            step_state,
+            [{"class": "InlineJavascriptRequirement"}],
+            None,
+            None,
+            {},
+        )
+        return from_cwl(as_cwl_value)
+
+
 class WorkflowModule:
 
     label: str
@@ -365,11 +457,9 @@ class WorkflowModule:
         return []
 
     def compute_collection_info(self, progress, step, all_inputs):
-        """Use get_all_inputs (if implemented) to determine collection mapping for execution.
-
-        Hopefully this can be reused for Tool and Subworkflow modules.
         """
-
+        Use get_all_inputs (if implemented) to determine collection mapping for execution.
+        """
         collections_to_match = self._find_collections_to_match(progress, step, all_inputs)
         # Have implicit collections...
         if collections_to_match.has_collections():
@@ -383,9 +473,6 @@ class WorkflowModule:
         collections_to_match = matching.CollectionsToMatch()
         dataset_collection_type_descriptions = self.trans.app.dataset_collection_manager.collection_type_descriptions
 
-        if progress.when:
-            collections_to_match.add("when_source", progress.when)
-
         for input_dict in all_inputs:
             name = input_dict["name"]
             data = progress.replacement_for_input(step, input_dict)
@@ -447,18 +534,21 @@ class WorkflowModule:
                 collections_to_match.add(name, data)
                 continue
 
-        return collections_to_match
+        known_input_names = {input_dict["name"] for input_dict in all_inputs}
 
-    @staticmethod
-    def create_when_source_param():
-        return dict(
-            name="when_source",
-            label="when_source",
-            multiple=False,
-            input_type="parameter",
-            optional=False,
-            type="boolean",
-        )
+        if step.when_expression:
+            for step_input in step.inputs:
+                step_input_name = step_input.name
+                input_in_execution_state = step_input_name not in known_input_names
+                if input_in_execution_state:
+                    maybe_collection = progress.replacement_for_connection(
+                        step.input_connections_by_name[step_input_name][0]
+                    )
+                    if hasattr(maybe_collection, "collection"):
+                        # Is that always right ?
+                        collections_to_match.add(step_input_name, maybe_collection)
+
+        return collections_to_match
 
 
 class SubWorkflowModule(WorkflowModule):
@@ -615,17 +705,38 @@ class SubWorkflowModule(WorkflowModule):
         """
         step = invocation_step.workflow_step
         all_inputs = self.get_all_inputs()
-        if step.input_connections_by_name.get("when_source"):
-            param_dict = self.create_when_source_param()
-            all_inputs.append(param_dict)
-            # Maybe make this lazy with a callback ?
-            when = progress.replacement_for_input(step, param_dict)
-
         collection_info = self.compute_collection_info(progress, step, all_inputs)
         structure = collection_info.structure if collection_info else None
 
+        if collection_info:
+            iteration_elements_iter = collection_info.slice_collections()
+        else:
+            iteration_elements_iter = [None]
+
+        when_values = []
+        if step.when_expression:
+            for iteration_elements in iteration_elements_iter:
+                extra_step_state = {}
+                for step_input in step.inputs:
+                    step_input_name = step_input.name
+                    if iteration_elements and step_input_name in iteration_elements:  # noqa: B023
+                        value = iteration_elements[step_input_name]  # noqa: B023
+                    else:
+                        value = progress.replacement_for_connection(step_input.connections[0], is_data=True)
+                    extra_step_state[step_input_name] = value
+
+                when_values.append(
+                    evaluate_value_from_expressions(
+                        progress, step, execution_state={}, extra_step_state=extra_step_state
+                    )
+                )
+
         subworkflow_invoker = progress.subworkflow_invoker(
-            trans, step, use_cached_job=use_cached_job, subworkflow_structure=structure, when=when
+            trans,
+            step,
+            use_cached_job=use_cached_job,
+            subworkflow_structure=structure,
+            when=when_values,
         )
         subworkflow_invoker.invoke()
         subworkflow = subworkflow_invoker.workflow
@@ -1955,9 +2066,7 @@ class ToolModule(WorkflowModule):
             del tool_state.inputs[RUNTIME_STEP_META_STATE_KEY]
 
         all_inputs = self.get_all_inputs()
-        if progress.when is not None or step.input_connections_by_name.get("when_source"):
-            all_inputs.append(self.create_when_source_param())
-            tool_inputs["when_source"] = ConditionalStepWhen(None, {"name": "when_source", "type": "boolean"})
+
         all_inputs_by_name = {}
         for input_dict in all_inputs:
             all_inputs_by_name[input_dict["name"]] = input_dict
@@ -1970,7 +2079,7 @@ class ToolModule(WorkflowModule):
             iteration_elements_iter = [None]
 
         resource_parameters = invocation.resource_parameters
-        for iteration_elements in iteration_elements_iter:
+        for iteration_index, iteration_elements in enumerate(iteration_elements_iter):
             execution_state = tool_state.copy()
             # TODO: Move next step into copy()
             execution_state.inputs = make_dict_copy(execution_state.inputs)
@@ -1985,8 +2094,6 @@ class ToolModule(WorkflowModule):
                 replacement: Union[model.Dataset, NoReplacement] = NO_REPLACEMENT
                 if iteration_elements and prefixed_name in iteration_elements:  # noqa: B023
                     replacement = iteration_elements[prefixed_name]  # noqa: B023
-                elif prefixed_name == "when_source" and progress.when is not None:
-                    replacement = progress.when
                 else:
                     replacement = progress.replacement_for_input(step, input_dict)
 
@@ -2019,14 +2126,54 @@ class ToolModule(WorkflowModule):
                     no_replacement_value=NO_REPLACEMENT,
                     replace_optional_connections=True,
                 )
-            except SkipWorkflowStepEvaluation:
-                skip_execution_state = execution_state.inputs
-                skip_execution_state["when"] = False
             except KeyError as k:
                 message_template = "Error due to input mapping of '%s' in '%s'.  A common cause of this is conditional outputs that cannot be determined until runtime, please review your workflow."
                 message = message_template % (tool.name, unicodify(k))
                 raise exceptions.MessageException(message)
 
+            when_value = None
+            if progress.when and progress.when[iteration_index] is False:
+                when_value = False
+            elif step.when_expression:
+                extra_step_state = {}
+                for step_input in step.inputs:
+                    step_input_name = step_input.name
+                    input_in_execution_state = step_input_name not in execution_state.inputs
+                    if input_in_execution_state:
+                        if step_input_name in all_inputs_by_name:
+                            if iteration_elements and step_input_name in iteration_elements:  # noqa: B023
+                                value = iteration_elements[step_input_name]  # noqa: B023
+                            else:
+                                value = progress.replacement_for_input(step, all_inputs_by_name[step_input_name])
+                            # TODO: only do this for values... is everything with a default
+                            # this way a field parameter? I guess not?
+                            extra_step_state[step_input_name] = value
+                        # Might be needed someday...
+                        # elif step_input.default_value_set:
+                        #    extra_step_state[step_input_name] = step_input.default_value
+                        else:
+                            if iteration_elements and step_input_name in iteration_elements:  # noqa: B023
+                                value = iteration_elements[step_input_name]  # noqa: B023
+                            else:
+                                value = progress.replacement_for_connection(step_input.connections[0], is_data=True)
+                            extra_step_state[step_input_name] = value
+
+                when_value = None
+                if progress.when is not None:
+                    if callable(progress.when):
+                        when_value = progress.when()
+                    else:
+                        when_value = progress.when
+
+                if when_value is not False:
+                    when_value = evaluate_value_from_expressions(
+                        progress, step, execution_state=execution_state, extra_step_state=extra_step_state
+                    )
+                    assert isinstance(when_value, bool)
+            if when_value is not None:
+                # Track this more formally ?
+                execution_state.inputs["__when_value__"] = when_value
+
             unmatched_input_connections = expected_replacement_keys - found_replacement_keys
             if unmatched_input_connections:
                 log.warning(f"Failed to use input connections for inputs [{unmatched_input_connections}]")
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 0939c99abd9..5bc48af263b 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1944,8 +1944,8 @@ steps:
     tool_id: cat1
     in:
       input1: some_file
-    when:
-      source: should_run
+      should_run: should_run
+    when: $(inputs.should_run)
 """,
                 test_data="""
 some_file:
@@ -1985,10 +1985,10 @@ steps:
             input1: some_file
     in:
       some_file: some_file
+      should_run: should_run
     outputs:
       inner_out: a_tool_step/out_file1
-    when:
-      source: should_run
+    when: $(inputs.should_run)
 outputs:
   outer_output:
     outputSource: subworkflow/inner_out
@@ -2033,11 +2033,11 @@ steps:
   tool_id: cat1
   in:
     input1: boolean_input_files
+    should_run: param_out/boolean_param
   out:
     out_file1:
       change_datatype: txt
-  when:
-    source: param_out/boolean_param
+  when: $(inputs.should_run)
 test_data:
   boolean_input_files:
     collection_type: list
@@ -2094,8 +2094,8 @@ steps:
           outputSource: consume_expression_parameter/out_file1
     in:
       boolean_input_file: boolean_input_files
-    when:
-      source: create_list_of_boolean/boolean_param
+      should_run: create_list_of_boolean/boolean_param
+    when: $(inputs.should_run)
 outputs:
   outer_output:
     outputSource: subworkflow/inner_output
@@ -2148,14 +2148,14 @@ steps:
   tool_id: cat1
   in:
     input1: boolean_input_files_1
-  when:
-    source: param_out_1/boolean_param
+    should_run: param_out_1/boolean_param
+  when: $(inputs.should_run)
 - label: consume_expression_parameter_2
   tool_id: cat1
   in:
     input1: boolean_input_files_2
-  when:
-    source: param_out_2/boolean_param
+    should_run: param_out_2/boolean_param
+  when: $(inputs.should_run)
 - label: pick_value
   tool_id: pick_value
   tool_state:

From 9cdcde52519202f431d34f75fd6625106b9a116e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 13 Nov 2022 16:22:54 +0100
Subject: [PATCH 142/350] Add subworkflow skip test when tool structure changes

---
 lib/galaxy_test/api/test_workflows.py | 64 +++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 5bc48af263b..af676f8e1d5 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -2120,6 +2120,70 @@ test_data:
             assert outer_hdca["job_state_summary"]["ok"] == 1
             assert outer_hdca["job_state_summary"]["skipped"] == 1
 
+    def test_run_workflow_conditional_subworkflow_step_map_over_expression_tool_with_extra_nesting(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """
+class: GalaxyWorkflow
+inputs:
+  boolean_input_files: collection
+steps:
+  create_list_of_boolean:
+    tool_id: param_value_from_file
+    in:
+       input1: boolean_input_files
+    state:
+      param_type: boolean
+  subworkflow:
+    run:
+      class: GalaxyWorkflow
+      inputs:
+        boolean_input_file: data
+      steps:
+        create_more_inputs:
+          tool_id: collection_creates_dynamic_nested
+        consume_expression_parameter:
+          tool_id: cat1
+          state:
+            input1:
+              $link: create_more_inputs/list_output
+            queries:
+              - input2:
+                $link: boolean_input_file
+          out:
+            out_file1:
+              change_datatype: txt
+      outputs:
+        inner_output:
+          outputSource: consume_expression_parameter/out_file1
+    in:
+      boolean_input_file: boolean_input_files
+      should_run: create_list_of_boolean/boolean_param
+    when: $(inputs.should_run)
+outputs:
+  outer_output:
+    outputSource: subworkflow/inner_output
+test_data:
+  boolean_input_files:
+    collection_type: list
+    elements:
+      - identifier: true
+        content: true
+      - identifier: false
+        content: false
+""",
+                history_id=history_id,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            assert "outer_output" in invocation_details["output_collections"]
+            outer_output = invocation_details["output_collections"]["outer_output"]
+            outer_hdca = self.dataset_populator.get_history_collection_details(
+                history_id, content_id=outer_output["id"]
+            )
+            assert outer_hdca["job_state_summary"]["all_jobs"] == 14  # true/false * (6 inner elements + 1)
+            assert outer_hdca["job_state_summary"]["ok"] == 7
+            assert outer_hdca["job_state_summary"]["skipped"] == 7
+
     def test_run_workflow_conditional_step_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(

From 22a64fa67be9568788ba6d456cc3286185569efa Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 17 Nov 2022 13:56:08 +0100
Subject: [PATCH 143/350] Fix mapping over subworkflow steps without explicit
 connection to outer workflow

---
 lib/galaxy/workflow/modules.py | 11 +++--------
 lib/galaxy/workflow/run.py     | 13 +++++++------
 2 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 16921476669..9d7942d0400 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -462,12 +462,8 @@ class WorkflowModule:
         """
         collections_to_match = self._find_collections_to_match(progress, step, all_inputs)
         # Have implicit collections...
-        if collections_to_match.has_collections():
-            collection_info = self.trans.app.dataset_collection_manager.match_collections(collections_to_match)
-        else:
-            collection_info = None
-
-        return collection_info
+        collection_info = self.trans.app.dataset_collection_manager.match_collections(collections_to_match)
+        return collection_info or progress.subworkflow_collection_info
 
     def _find_collections_to_match(self, progress, step, all_inputs):
         collections_to_match = matching.CollectionsToMatch()
@@ -706,7 +702,6 @@ class SubWorkflowModule(WorkflowModule):
         step = invocation_step.workflow_step
         all_inputs = self.get_all_inputs()
         collection_info = self.compute_collection_info(progress, step, all_inputs)
-        structure = collection_info.structure if collection_info else None
 
         if collection_info:
             iteration_elements_iter = collection_info.slice_collections()
@@ -735,7 +730,7 @@ class SubWorkflowModule(WorkflowModule):
             trans,
             step,
             use_cached_job=use_cached_job,
-            subworkflow_structure=structure,
+            subworkflow_collection_info=collection_info,
             when=when_values,
         )
         subworkflow_invoker.invoke()
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index d860a82482a..bc1c9af27ba 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -305,7 +305,7 @@ class WorkflowProgress:
         copy_inputs_to_history: bool = False,
         use_cached_job: bool = False,
         replacement_dict: Optional[Dict[str, str]] = None,
-        subworkflow_structure=None,
+        subworkflow_collection_info=None,
         when=None,
     ) -> None:
         self.outputs: Dict[int, Any] = {}
@@ -318,7 +318,8 @@ class WorkflowProgress:
         self.copy_inputs_to_history = copy_inputs_to_history
         self.use_cached_job = use_cached_job
         self.replacement_dict = replacement_dict or {}
-        self.subworkflow_structure = subworkflow_structure
+        self.subworkflow_collection_info = subworkflow_collection_info
+        self.subworkflow_structure = subworkflow_collection_info.structure if subworkflow_collection_info else None
         self.when = when
 
     @property
@@ -533,7 +534,7 @@ class WorkflowProgress:
         trans: "WorkRequestContext",
         step: "WorkflowStep",
         use_cached_job: bool = False,
-        subworkflow_structure=None,
+        subworkflow_collection_info=None,
         when=None,
     ) -> WorkflowInvoker:
         subworkflow_invocation = self._subworkflow_invocation(step)
@@ -542,7 +543,7 @@ class WorkflowProgress:
             subworkflow_invocation,
             step,
             workflow_run_config.param_map,
-            subworkflow_structure=subworkflow_structure,
+            subworkflow_collection_info=subworkflow_collection_info,
             when=when,
         )
         subworkflow_invocation = subworkflow_progress.workflow_invocation
@@ -558,7 +559,7 @@ class WorkflowProgress:
         subworkflow_invocation: WorkflowInvocation,
         step: "WorkflowStep",
         param_map: Dict,
-        subworkflow_structure=None,
+        subworkflow_collection_info=None,
         when=None,
     ) -> "WorkflowProgress":
         subworkflow = subworkflow_invocation.workflow
@@ -587,7 +588,7 @@ class WorkflowProgress:
             param_map=param_map,
             use_cached_job=self.use_cached_job,
             replacement_dict=self.replacement_dict,
-            subworkflow_structure=subworkflow_structure,
+            subworkflow_collection_info=subworkflow_collection_info,
             when=when,
         )
 

From ca55ad845dfc484bf00a8f1bf82a3ed644738c33 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 17 Nov 2022 13:56:50 +0100
Subject: [PATCH 144/350] Mark skipped outputs as populated

---
 lib/galaxy/tools/actions/__init__.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/galaxy/tools/actions/__init__.py b/lib/galaxy/tools/actions/__init__.py
index 7da45dfea24..45eba238fd3 100644
--- a/lib/galaxy/tools/actions/__init__.py
+++ b/lib/galaxy/tools/actions/__init__.py
@@ -642,6 +642,8 @@ class DefaultToolAction(ToolAction):
         job, galaxy_session = self._new_job_for_session(trans, tool, history)
         if skip:
             job.state = job.states.SKIPPED
+            for output_collection in output_collections.out_collections.values():
+                output_collection.mark_as_populated()
             object_store_populator = ObjectStorePopulator(trans.app, trans.user)
             for data in out_data.values():
                 object_store_populator.set_object_store_id(data)

From a2c66272a752049737779e290cb0066df35a9d3c Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 17 Nov 2022 20:51:20 +0100
Subject: [PATCH 145/350] Test and fix conditional subworkflow steps where
 subworkflow step produces additional mapping over without being directly
 connected to a workflow input

---
 .../model/dataset_collections/matching.py     |   3 +
 .../model/dataset_collections/structure.py    |   8 +-
 lib/galaxy/tools/execute.py                   |   4 +-
 lib/galaxy/workflow/modules.py                |  38 +++---
 lib/galaxy/workflow/run.py                    |  12 +-
 lib/galaxy_test/api/test_workflows.py         | 119 ++++++++++--------
 lib/galaxy_test/base/workflow_fixtures.py     |  56 +++++++++
 7 files changed, 156 insertions(+), 84 deletions(-)

diff --git a/lib/galaxy/model/dataset_collections/matching.py b/lib/galaxy/model/dataset_collections/matching.py
index 4b1d7efbff6..948e317ec69 100644
--- a/lib/galaxy/model/dataset_collections/matching.py
+++ b/lib/galaxy/model/dataset_collections/matching.py
@@ -48,6 +48,7 @@ class MatchingCollections:
         self.collections = {}
         self.subcollection_types = {}
         self.action_tuples = {}
+        self.when_values = None
 
     def __attempt_add_to_linked_match(self, input_name, hdca, collection_type_description, subcollection_type):
         structure = get_structure(hdca, collection_type_description, leaf_subcollection_type=subcollection_type)
@@ -62,6 +63,7 @@ class MatchingCollections:
             self.subcollection_types[input_name] = subcollection_type
 
     def slice_collections(self):
+        self.linked_structure.when_values = self.when_values
         return self.linked_structure.walk_collections(self.collections)
 
     def subcollection_mapping_type(self, input_name):
@@ -77,6 +79,7 @@ class MatchingCollections:
         if linked_structure is None:
             linked_structure = leaf
         effective_structure = effective_structure.multiply(linked_structure)
+        effective_structure.when_values = self.when_values
         return None if effective_structure.is_leaf else effective_structure
 
     def map_over_action_tuples(self, input_name):
diff --git a/lib/galaxy/model/dataset_collections/structure.py b/lib/galaxy/model/dataset_collections/structure.py
index 79c85b76edd..08d1946bda3 100644
--- a/lib/galaxy/model/dataset_collections/structure.py
+++ b/lib/galaxy/model/dataset_collections/structure.py
@@ -63,9 +63,10 @@ class UninitializedTree(BaseTree):
 class Tree(BaseTree):
     children_known = True
 
-    def __init__(self, children, collection_type_description):
+    def __init__(self, children, collection_type_description, when_values=None):
         super().__init__(collection_type_description)
         self.children = children
+        self.when_values = when_values
 
     @staticmethod
     def for_dataset_collection(dataset_collection, collection_type_description):
@@ -94,10 +95,11 @@ class Tree(BaseTree):
                 return collection[index]  # noqa: B023
 
             if substructure.is_leaf:
-                yield dict_map(get_element, collection_dict)
+                yield dict_map(get_element, collection_dict), self.when_values[index] if self.when_values else None
             else:
                 sub_collections = dict_map(lambda collection: get_element(collection).child_collection, collection_dict)
-                yield from substructure._walk_collections(sub_collections)
+                for element, _when_value in substructure._walk_collections(sub_collections):
+                    yield element, self.when_values[index] if self.when_values else None
 
     @property
     def is_leaf(self):
diff --git a/lib/galaxy/tools/execute.py b/lib/galaxy/tools/execute.py
index 910a04e497b..a325966fb60 100644
--- a/lib/galaxy/tools/execute.py
+++ b/lib/galaxy/tools/execute.py
@@ -528,7 +528,7 @@ class ToolExecutionTracker(ExecutionTracker):
             self.outputs_by_output_name[job_output.name].append(job_output.dataset_collection)
 
     def new_collection_execution_slices(self):
-        for job_index, (param_combination, dataset_collection_elements) in enumerate(
+        for job_index, (param_combination, (dataset_collection_elements, _when_value)) in enumerate(
             zip(self.param_combinations, self.walk_implicit_collections())
         ):
             completed_job = self.completed_jobs and self.completed_jobs[job_index]
@@ -552,7 +552,7 @@ class WorkflowStepExecutionTracker(ExecutionTracker):
             self.invocation_step.job = job
 
     def new_collection_execution_slices(self):
-        for job_index, (param_combination, dataset_collection_elements) in enumerate(
+        for job_index, (param_combination, (dataset_collection_elements, _when_value)) in enumerate(
             zip(self.param_combinations, self.walk_implicit_collections())
         ):
             completed_job = self.completed_jobs and self.completed_jobs[job_index]
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 9d7942d0400..c8a5d00b4ba 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -113,7 +113,6 @@ class ConditionalStepWhen(BooleanToolParameter):
 def evaluate_value_from_expressions(progress, step, execution_state, extra_step_state):
     when_expression = step.when_expression
     value_from_expressions = {}
-    replacements = {}
 
     if execution_state:
         for key in execution_state.inputs.keys():
@@ -122,7 +121,7 @@ def evaluate_value_from_expressions(progress, step, execution_state, extra_step_
                 value_from_expressions[key] = step_input.value_from
 
     if not value_from_expressions and when_expression is None:
-        return replacements
+        return {}
 
     hda_references = []
 
@@ -463,6 +462,8 @@ class WorkflowModule:
         collections_to_match = self._find_collections_to_match(progress, step, all_inputs)
         # Have implicit collections...
         collection_info = self.trans.app.dataset_collection_manager.match_collections(collections_to_match)
+        if collection_info and progress.subworkflow_collection_info:
+            collection_info.when_values = progress.subworkflow_collection_info.when_values
         return collection_info or progress.subworkflow_collection_info
 
     def _find_collections_to_match(self, progress, step, all_inputs):
@@ -706,11 +707,18 @@ class SubWorkflowModule(WorkflowModule):
         if collection_info:
             iteration_elements_iter = collection_info.slice_collections()
         else:
-            iteration_elements_iter = [None]
+            if progress.when_values:
+                # If we have more than one item in when_values it must have come from an expression.json
+                # collection, so we'd have a collection_info instance ... I think.
+                assert len(progress.when_values) == 1, "Got more than 1 when value, this shouldn't be possible"
+            iteration_elements_iter = [(None, progress.when_values[0] if progress.when_values else None)]
 
         when_values = []
         if step.when_expression:
-            for iteration_elements in iteration_elements_iter:
+            for (iteration_elements, when_value) in iteration_elements_iter:
+                if when_value is False:
+                    when_values.append(when_value)
+                    continue
                 extra_step_state = {}
                 for step_input in step.inputs:
                     step_input_name = step_input.name
@@ -725,13 +733,15 @@ class SubWorkflowModule(WorkflowModule):
                         progress, step, execution_state={}, extra_step_state=extra_step_state
                     )
                 )
+            if collection_info:
+                collection_info.when_values = when_values
 
         subworkflow_invoker = progress.subworkflow_invoker(
             trans,
             step,
             use_cached_job=use_cached_job,
             subworkflow_collection_info=collection_info,
-            when=when_values,
+            when_values=when_values,
         )
         subworkflow_invoker.invoke()
         subworkflow = subworkflow_invoker.workflow
@@ -2071,10 +2081,12 @@ class ToolModule(WorkflowModule):
         if collection_info:
             iteration_elements_iter = collection_info.slice_collections()
         else:
-            iteration_elements_iter = [None]
+            if progress.when_values:
+                assert len(progress.when_values) == 1, "Got more than 1 when value, this shouldn't be possible"
+            iteration_elements_iter = [(None, progress.when_values[0] if progress.when_values else None)]
 
         resource_parameters = invocation.resource_parameters
-        for iteration_index, iteration_elements in enumerate(iteration_elements_iter):
+        for (iteration_elements, when_value) in iteration_elements_iter:
             execution_state = tool_state.copy()
             # TODO: Move next step into copy()
             execution_state.inputs = make_dict_copy(execution_state.inputs)
@@ -2126,10 +2138,7 @@ class ToolModule(WorkflowModule):
                 message = message_template % (tool.name, unicodify(k))
                 raise exceptions.MessageException(message)
 
-            when_value = None
-            if progress.when and progress.when[iteration_index] is False:
-                when_value = False
-            elif step.when_expression:
+            if step.when_expression and when_value is not False:
                 extra_step_state = {}
                 for step_input in step.inputs:
                     step_input_name = step_input.name
@@ -2153,13 +2162,6 @@ class ToolModule(WorkflowModule):
                                 value = progress.replacement_for_connection(step_input.connections[0], is_data=True)
                             extra_step_state[step_input_name] = value
 
-                when_value = None
-                if progress.when is not None:
-                    if callable(progress.when):
-                        when_value = progress.when()
-                    else:
-                        when_value = progress.when
-
                 if when_value is not False:
                     when_value = evaluate_value_from_expressions(
                         progress, step, execution_state=execution_state, extra_step_state=extra_step_state
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index bc1c9af27ba..5c0effb8f3a 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -306,7 +306,7 @@ class WorkflowProgress:
         use_cached_job: bool = False,
         replacement_dict: Optional[Dict[str, str]] = None,
         subworkflow_collection_info=None,
-        when=None,
+        when_values=None,
     ) -> None:
         self.outputs: Dict[int, Any] = {}
         self.module_injector = module_injector
@@ -320,7 +320,7 @@ class WorkflowProgress:
         self.replacement_dict = replacement_dict or {}
         self.subworkflow_collection_info = subworkflow_collection_info
         self.subworkflow_structure = subworkflow_collection_info.structure if subworkflow_collection_info else None
-        self.when = when
+        self.when_values = when_values
 
     @property
     def maximum_jobs_to_schedule_or_none(self) -> Optional[int]:
@@ -535,7 +535,7 @@ class WorkflowProgress:
         step: "WorkflowStep",
         use_cached_job: bool = False,
         subworkflow_collection_info=None,
-        when=None,
+        when_values=None,
     ) -> WorkflowInvoker:
         subworkflow_invocation = self._subworkflow_invocation(step)
         workflow_run_config = workflow_request_to_run_config(subworkflow_invocation, use_cached_job)
@@ -544,7 +544,7 @@ class WorkflowProgress:
             step,
             workflow_run_config.param_map,
             subworkflow_collection_info=subworkflow_collection_info,
-            when=when,
+            when_values=when_values,
         )
         subworkflow_invocation = subworkflow_progress.workflow_invocation
         return WorkflowInvoker(
@@ -560,7 +560,7 @@ class WorkflowProgress:
         step: "WorkflowStep",
         param_map: Dict,
         subworkflow_collection_info=None,
-        when=None,
+        when_values=None,
     ) -> "WorkflowProgress":
         subworkflow = subworkflow_invocation.workflow
         subworkflow_inputs = {}
@@ -589,7 +589,7 @@ class WorkflowProgress:
             use_cached_job=self.use_cached_job,
             replacement_dict=self.replacement_dict,
             subworkflow_collection_info=subworkflow_collection_info,
-            when=when,
+            when_values=when_values,
         )
 
     def _recover_mapping(self, step_invocation: WorkflowInvocationStep) -> None:
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index af676f8e1d5..039aa653cd3 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -36,6 +36,7 @@ from galaxy_test.base.populators import (
     WorkflowPopulator,
 )
 from galaxy_test.base.workflow_fixtures import (
+    NESTED_WORKFLOW_WITH_CONDITIONAL_SUBWORKFLOW_AND_DISCONNECTED_MAP_OVER_SOURCE,
     WORKFLOW_INPUTS_AS_OUTPUTS,
     WORKFLOW_NESTED_REPLACEMENT_PARAMETER,
     WORKFLOW_NESTED_RUNTIME_PARAMETER,
@@ -2123,66 +2124,74 @@ test_data:
     def test_run_workflow_conditional_subworkflow_step_map_over_expression_tool_with_extra_nesting(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
-                """
-class: GalaxyWorkflow
-inputs:
-  boolean_input_files: collection
-steps:
-  create_list_of_boolean:
-    tool_id: param_value_from_file
-    in:
-       input1: boolean_input_files
-    state:
-      param_type: boolean
-  subworkflow:
-    run:
-      class: GalaxyWorkflow
-      inputs:
-        boolean_input_file: data
-      steps:
-        create_more_inputs:
-          tool_id: collection_creates_dynamic_nested
-        consume_expression_parameter:
-          tool_id: cat1
-          state:
-            input1:
-              $link: create_more_inputs/list_output
-            queries:
-              - input2:
-                $link: boolean_input_file
-          out:
-            out_file1:
-              change_datatype: txt
-      outputs:
-        inner_output:
-          outputSource: consume_expression_parameter/out_file1
-    in:
-      boolean_input_file: boolean_input_files
-      should_run: create_list_of_boolean/boolean_param
-    when: $(inputs.should_run)
-outputs:
-  outer_output:
-    outputSource: subworkflow/inner_output
-test_data:
-  boolean_input_files:
-    collection_type: list
-    elements:
-      - identifier: true
-        content: true
-      - identifier: false
-        content: false
+                NESTED_WORKFLOW_WITH_CONDITIONAL_SUBWORKFLOW_AND_DISCONNECTED_MAP_OVER_SOURCE,
+                test_data="""boolean_input_files:
+  collection_type: list
+  elements:
+    - identifier: true
+      content: true
+    - identifier: false
+      content: false
 """,
                 history_id=history_id,
             )
             invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
-            assert "outer_output" in invocation_details["output_collections"]
-            outer_output = invocation_details["output_collections"]["outer_output"]
-            outer_hdca = self.dataset_populator.get_history_collection_details(
-                history_id, content_id=outer_output["id"]
+            outer_create_nested_id = invocation_details["output_collections"]["outer_create_nested"]["id"]
+            outer_create_nested = self.dataset_populator.get_history_collection_details(
+                history_id, content_id=outer_create_nested_id
             )
-            assert outer_hdca["job_state_summary"]["all_jobs"] == 14  # true/false * (6 inner elements + 1)
-            assert outer_hdca["job_state_summary"]["ok"] == 7
-            assert outer_hdca["job_state_summary"]["skipped"] == 7
+            assert outer_create_nested["job_state_summary"]["all_jobs"] == 2
+            assert outer_create_nested["job_state_summary"]["ok"] == 1
+            assert outer_create_nested["job_state_summary"]["skipped"] == 1
+
+            for cat1_output in ["outer_output_1", "outer_output_2"]:
+                outer_output = invocation_details["output_collections"][cat1_output]
+                outer_hdca = self.dataset_populator.get_history_collection_details(
+                    history_id, content_id=outer_output["id"]
+                )
+                # You might expect 12 total jobs, 6 ok and 6 skipped,
+                # but because we're not actually running one branch of collection_creates_dynamic_nested
+                # there's no input to consume_expression_parameter.
+                # It's unclear if that's a problem or not ... probably not a major one,
+                # since we keep producing "empty" outer collections, which seems somewhat correct.
+                assert outer_hdca["job_state_summary"]["all_jobs"] == 6
+                assert outer_hdca["job_state_summary"]["ok"] == 6
+                assert outer_hdca["collection_type"] == "list:list:list"
+                elements = outer_hdca["elements"]
+                assert elements[0]["element_identifier"] == "True"
+                assert elements[0]["object"]["element_count"] == 3
+                assert elements[1]["element_identifier"] == "False"
+                assert elements[1]["object"]["element_count"] == 0
+
+    def test_run_workflow_conditional_subworkflow_step_map_over_expression_tool_with_extra_nesting_skip_all(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                NESTED_WORKFLOW_WITH_CONDITIONAL_SUBWORKFLOW_AND_DISCONNECTED_MAP_OVER_SOURCE,
+                test_data="""boolean_input_files:
+  collection_type: list
+  elements:
+    - identifier: false
+      content: false
+    - identifier: also_false
+      content: false
+""",
+                history_id=history_id,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            outer_create_nested_id = invocation_details["output_collections"]["outer_create_nested"]["id"]
+            outer_create_nested = self.dataset_populator.get_history_collection_details(
+                history_id, content_id=outer_create_nested_id
+            )
+            assert outer_create_nested["job_state_summary"]["all_jobs"] == 2
+            assert outer_create_nested["job_state_summary"]["skipped"] == 2
+
+            for cat1_output in ["outer_output_1", "outer_output_2"]:
+                outer_output = invocation_details["output_collections"][cat1_output]
+                outer_hdca = self.dataset_populator.get_history_collection_details(
+                    history_id, content_id=outer_output["id"]
+                )
+                assert outer_hdca["job_state_summary"]["all_jobs"] == 0
+                assert outer_hdca["collection_type"] == "list:list:list"
 
     def test_run_workflow_conditional_step_map_over_expression_tool_pick_value(self):
         with self.dataset_populator.test_history() as history_id:
diff --git a/lib/galaxy_test/base/workflow_fixtures.py b/lib/galaxy_test/base/workflow_fixtures.py
index f01a3c7a13e..0178e935dae 100644
--- a/lib/galaxy_test/base/workflow_fixtures.py
+++ b/lib/galaxy_test/base/workflow_fixtures.py
@@ -994,3 +994,59 @@ bed_input:
   file_type: bed
   type: File
 """
+
+
+NESTED_WORKFLOW_WITH_CONDITIONAL_SUBWORKFLOW_AND_DISCONNECTED_MAP_OVER_SOURCE = """
+class: GalaxyWorkflow
+inputs:
+  boolean_input_files: collection
+steps:
+  create_list_of_boolean:
+    tool_id: param_value_from_file
+    in:
+       input1: boolean_input_files
+    state:
+      param_type: boolean
+  subworkflow:
+    run:
+      class: GalaxyWorkflow
+      inputs:
+        boolean_input_file: data
+      steps:
+        create_more_inputs:
+          tool_id: collection_creates_dynamic_nested
+        consume_expression_parameter:
+          tool_id: cat1
+          state:
+            input1:
+              $link: create_more_inputs/list_output
+            queries:
+              - input2:
+                $link: boolean_input_file
+          out:
+            out_file1:
+              change_datatype: txt
+        consume_expression_parameter_2:
+          tool_id: cat1
+          state:
+            input1:
+              $link: consume_expression_parameter/out_file1
+      outputs:
+        inner_create_nested:
+          outputSource: create_more_inputs/list_output
+        inner_output_1:
+          outputSource: consume_expression_parameter/out_file1
+        inner_output_2:
+          outputSource: consume_expression_parameter_2/out_file1
+    in:
+      boolean_input_file: boolean_input_files
+      should_run: create_list_of_boolean/boolean_param
+    when: $(inputs.should_run)
+outputs:
+  outer_create_nested:
+    outputSource: subworkflow/inner_create_nested
+  outer_output_1:
+    outputSource: subworkflow/inner_output_1
+  outer_output_2:
+    outputSource: subworkflow/inner_output_2
+"""

From f911a5484156713fee1aa12678107cf5fea95e93 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 13 Jan 2023 11:43:40 +0100
Subject: [PATCH 146/350] Fix migration down_revision

---
 .../versions_gxy/518c8438a91b_add_when_expression_column.py   | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
index ea8fe53d7c8..879ec4e35ac 100644
--- a/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/518c8438a91b_add_when_expression_column.py
@@ -1,7 +1,7 @@
 """Add when_expression column
 
 Revision ID: 518c8438a91b
-Revises: e0e3bb173ee6
+Revises: 59e024ceaca1
 Create Date: 2022-10-24 16:43:39.565871
 
 """
@@ -16,7 +16,7 @@ from galaxy.model.migrations.util import (
 
 # revision identifiers, used by Alembic.
 revision = "518c8438a91b"
-down_revision = "e0e3bb173ee6"
+down_revision = "59e024ceaca1"
 branch_labels = None
 depends_on = None
 

From 961d64e68cd3774f195faa51a8fc66ffd97f65f4 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 13 Jan 2023 12:02:34 +0100
Subject: [PATCH 147/350] Update typescript schema

---
 client/src/schema/schema.ts | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/client/src/schema/schema.ts b/client/src/schema/schema.ts
index 29886efe1fb..f4d5523245c 100644
--- a/client/src/schema/schema.ts
+++ b/client/src/schema/schema.ts
@@ -4087,6 +4087,12 @@ export interface components {
              * @default 0
              */
             running?: number;
+            /**
+             * Skipped jobs
+             * @description Number of jobs that were skipped due to conditional workflow step execution.
+             * @default 0
+             */
+            skipped?: number;
             /**
              * Upload jobs
              * @description Number of jobs in the `upload` state.
@@ -7493,7 +7499,8 @@ export interface components {
             | "deleted"
             | "deleted_new"
             | "stop"
-            | "stopped";
+            | "stopped"
+            | "skipped";
         /**
          * populated_states
          * @description An enumeration.

From e59ff1174d262e0082da88a8858a5210ac757645 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 15 Jan 2023 11:31:22 +0100
Subject: [PATCH 148/350] Backend for showing invocation
 failure/cancellation/warning reasons

---
 lib/galaxy/managers/workflows.py              |   6 +-
 lib/galaxy/model/__init__.py                  |  69 ++++++++-
 ...0_add_workflow_invocation_message_table.py |  46 ++++++
 lib/galaxy/schema/schema.py                   | 142 +++++++++++++++++
 lib/galaxy/webapps/galaxy/api/workflows.py    |  14 +-
 .../webapps/galaxy/services/invocations.py    |   5 +-
 lib/galaxy/workflow/modules.py                |  38 ++++-
 lib/galaxy/workflow/run.py                    | 145 ++++++++++++++----
 lib/galaxy_test/api/test_workflows.py         |  81 ++++++++++
 9 files changed, 498 insertions(+), 48 deletions(-)
 create mode 100644 lib/galaxy/model/migrations/alembic/versions_gxy/3100452fa030_add_workflow_invocation_message_table.py

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index e72603aa42e..bee1e4fcf61 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -58,7 +58,10 @@ from galaxy.model.index_filter_util import (
     text_column_filter,
 )
 from galaxy.model.item_attrs import UsesAnnotations
-from galaxy.schema.schema import WorkflowIndexQueryPayload
+from galaxy.schema.schema import (
+    InvocationCancellationUserRequest,
+    WorkflowIndexQueryPayload,
+)
 from galaxy.structured_app import MinimalManagerApp
 from galaxy.tools.parameters import (
     params_to_incoming,
@@ -402,6 +405,7 @@ class WorkflowsManager(sharable.SharableModelManager, deletable.DeletableManager
         cancelled = workflow_invocation.cancel()
 
         if cancelled:
+            workflow_invocation.add_message(InvocationCancellationUserRequest(reason="user_request"))
             trans.sa_session.add(workflow_invocation)
             trans.sa_session.flush()
         else:
diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index f7f0f98a466..35c3cd2bc50 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -152,6 +152,9 @@ from galaxy.util.hash_util import (
 from galaxy.util.json import safe_loads
 from galaxy.util.sanitize_html import sanitize_html
 
+if TYPE_CHECKING:
+    from galaxy.schema.schema import InvocationMessage
+
 log = logging.getLogger(__name__)
 
 _datatypes_registry = None
@@ -7503,9 +7506,26 @@ class WorkflowInvocation(Base, UsesCreateAndUpdateTime, Dictifiable, Serializabl
     )
     output_datasets = relationship("WorkflowInvocationOutputDatasetAssociation", back_populates="workflow_invocation")
     output_values = relationship("WorkflowInvocationOutputValue", back_populates="workflow_invocation")
+    messages = relationship("WorkflowInvocationMessage", back_populates="workflow_invocation")
 
-    dict_collection_visible_keys = ["id", "update_time", "create_time", "workflow_id", "history_id", "uuid", "state"]
-    dict_element_visible_keys = ["id", "update_time", "create_time", "workflow_id", "history_id", "uuid", "state"]
+    dict_collection_visible_keys = [
+        "id",
+        "update_time",
+        "create_time",
+        "workflow_id",
+        "history_id",
+        "uuid",
+        "state",
+    ]
+    dict_element_visible_keys = [
+        "id",
+        "update_time",
+        "create_time",
+        "workflow_id",
+        "history_id",
+        "uuid",
+        "state",
+    ]
 
     class states(str, Enum):
         NEW = "new"  # Brand new workflow invocation... maybe this should be same as READY
@@ -7581,7 +7601,7 @@ class WorkflowInvocation(Base, UsesCreateAndUpdateTime, Dictifiable, Serializabl
             step_invocations[step_id] = invocation_step
         return step_invocations
 
-    def step_invocation_for_step_id(self, step_id):
+    def step_invocation_for_step_id(self, step_id: int) -> Optional["WorkflowInvocationStep"]:
         target_invocation_step = None
         for invocation_step in self.steps:
             if step_id == invocation_step.workflow_step_id:
@@ -7878,6 +7898,19 @@ class WorkflowInvocation(Base, UsesCreateAndUpdateTime, Dictifiable, Serializabl
             attach_step(request_to_content)
             self.input_step_parameters.append(request_to_content)
 
+    def add_message(self, message: "InvocationMessage"):
+        self.messages.append(
+            WorkflowInvocationMessage(
+                workflow_invocation_id=self.id,
+                **message.dict(
+                    exclude_unset=True,
+                    exclude={
+                        "history_id"
+                    },  # history_id comes in through workflow_invocation and isn't persisted in database
+                ),
+            )
+        )
+
     @property
     def resource_parameters(self):
         resource_type = WorkflowRequestInputParameter.types.RESOURCE_PARAMETERS
@@ -7939,6 +7972,36 @@ class WorkflowInvocationToSubworkflowInvocationAssociation(Base, Dictifiable, Re
     dict_element_visible_keys = ["id", "workflow_step_id", "workflow_invocation_id", "subworkflow_invocation_id"]
 
 
+class WorkflowInvocationMessage(Base, Dictifiable, Serializable):
+    __tablename__ = "workflow_invocation_message"
+    id = Column(Integer, primary_key=True)
+    workflow_invocation_id = Column(Integer, ForeignKey("workflow_invocation.id"), index=True, nullable=False)
+    reason = Column(String(32))
+    details = Column(TrimmedString(255), nullable=True)
+    output_name = Column(String(255), nullable=True)
+    workflow_step_id = Column(Integer, ForeignKey("workflow_step.id"), nullable=True)
+    dependent_workflow_step_id = Column(Integer, ForeignKey("workflow_step.id"), nullable=True)
+    job_id = Column(Integer, ForeignKey("job.id"), nullable=True)
+    hda_id = Column(Integer, ForeignKey("history_dataset_association.id"), nullable=True)
+    hdca_id = Column(Integer, ForeignKey("history_dataset_collection_association.id"), nullable=True)
+
+    workflow_invocation = relationship("WorkflowInvocation", back_populates="messages", lazy=True)
+    workflow_step = relationship("WorkflowStep", foreign_keys=workflow_step_id, lazy=True)
+    dependent_workflow_step = relationship("WorkflowStep", foreign_keys=dependent_workflow_step_id, lazy=True)
+
+    @property
+    def workflow_step_index(self):
+        return self.workflow_step and self.workflow_step.order_index
+
+    @property
+    def dependent_workflow_step_index(self):
+        return self.dependent_workflow_step and self.dependent_workflow_step.order_index
+
+    @property
+    def history_id(self):
+        return self.workflow_invocation.history_id
+
+
 class WorkflowInvocationStep(Base, Dictifiable, Serializable):
     __tablename__ = "workflow_invocation_step"
 
diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/3100452fa030_add_workflow_invocation_message_table.py b/lib/galaxy/model/migrations/alembic/versions_gxy/3100452fa030_add_workflow_invocation_message_table.py
new file mode 100644
index 00000000000..263a47110cc
--- /dev/null
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/3100452fa030_add_workflow_invocation_message_table.py
@@ -0,0 +1,46 @@
+"""Add reason column on invocation table
+
+Revision ID: 3100452fa030
+Revises: 518c8438a91b
+Create Date: 2023-01-13 16:13:09.578391
+
+"""
+from alembic import op
+from sqlalchemy import (
+    Column,
+    ForeignKey,
+    Integer,
+    String,
+)
+
+from galaxy.model.custom_types import TrimmedString
+
+# revision identifiers, used by Alembic.
+revision = "3100452fa030"
+down_revision = "518c8438a91b"
+branch_labels = None
+depends_on = None
+
+
+# database object names used in this revision
+table_name = "workflow_invocation_message"
+
+
+def upgrade():
+    op.create_table(
+        table_name,
+        Column("id", Integer, primary_key=True),
+        Column("reason", String(32)),
+        Column("details", TrimmedString(255)),
+        Column("output_name", String(255)),
+        Column("workflow_invocation_id", Integer, ForeignKey("workflow_invocation.id"), index=True, nullable=False),
+        Column("workflow_step_id", Integer, ForeignKey("workflow_step.id"), nullable=True),
+        Column("dependent_workflow_step_id", Integer, ForeignKey("workflow_step.id"), nullable=True),
+        Column("job_id", Integer, ForeignKey("job.id"), nullable=True),
+        Column("hda_id", Integer, ForeignKey("history_dataset_association.id"), nullable=True),
+        Column("hdca_id", Integer, ForeignKey("history_dataset_collection_association.id"), nullable=True),
+    )
+
+
+def downgrade():
+    op.drop_table(table_name)
diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index b50faa5feb8..3ee91e54e0b 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -9,9 +9,11 @@ from enum import Enum
 from typing import (
     Any,
     Dict,
+    Generic,
     List,
     Optional,
     Set,
+    TypeVar,
     Union,
 )
 from uuid import UUID
@@ -26,6 +28,7 @@ from pydantic import (
     Json,
     UUID4,
 )
+from pydantic.generics import GenericModel
 from typing_extensions import (
     Annotated,
     Literal,
@@ -1914,6 +1917,145 @@ class SubworkflowStep(WorkflowStepBase):
     )
 
 
+class WarningReason(str, Enum):
+    workflow_output_not_found = "workflow_output_not_found"
+
+
+class FailureReason(str, Enum):
+    dataset_failed = "dataset_failed"
+    collection_failed = "collection_failed"
+    job_failed = "job_failed"
+    output_not_found = "output_not_found"
+    unexpected_failure = "unexpected_failure"
+
+
+class CancelReason(str, Enum):
+    """Possible reasons for a cancelled workflow."""
+
+    history_deleted = "history_deleted"
+    user_request = "user_request"
+    cancelled_on_review = "cancelled_on_review"
+
+
+DatabaseIdT = TypeVar("DatabaseIdT")
+
+
+class InvocationMessageBase(GenericModel):
+    reason: Union[CancelReason, FailureReason, WarningReason]
+
+    class Config:
+        orm_mode = True
+
+
+class GenericInvocationCancellationReviewFailed(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[CancelReason.cancelled_on_review]
+    workflow_step_id: DatabaseIdT = Field(..., description="Workflow step id of paused step that did not pass review.")
+
+
+class GenericInvocationCancellationHistoryDeleted(InvocationMessageBase, Generic[DatabaseIdT]):
+    # reason: CancelReason.history_deleted
+    reason: Literal[CancelReason.history_deleted]
+    history_id: DatabaseIdT = Field(..., title="History ID", description="History ID of history that was deleted.")
+
+
+class GenericInvocationCancellationUserRequest(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[CancelReason.user_request]
+
+
+class InvocationFailureMessageBase(InvocationMessageBase, Generic[DatabaseIdT]):
+    workflow_step_id: DatabaseIdT = Field(..., description="Workflow step id of step that failed.")
+
+
+class GenericInvocationFailureDatasetFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.dataset_failed]
+    hda_id: DatabaseIdT = Field(
+        ..., title="HistoryDatasetAssociation ID", description="HistoryDatasetAssociation ID that relates to failure."
+    )
+    dependent_workflow_step_id: Optional[DatabaseIdT] = Field(
+        None, description="Workflow step id of step that caused failure."
+    )
+
+
+class GenericInvocationFailureCollectionFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.collection_failed]
+    hdca_id: DatabaseIdT = Field(
+        None,
+        title="HistoryDatasetCollectionAssociation ID",
+        description="HistoryDatasetCollectionAssociation ID that relates to failure.",
+    )
+    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureJobFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.job_failed]
+    job_id: DatabaseIdT = Field(None, title="Job ID", description="Job ID that relates to failure.")
+    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureOutputNotFound(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.output_not_found]
+    output_name: str = Field(..., title="Tool or module output name that was referenced but not produced")
+    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationUnexpectedFailure(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.unexpected_failure]
+    details: Optional[str] = Field(None, description="May contains details to help troubleshoot this problem.")
+
+
+class GenericInvocationWarning(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: WarningReason = Field(..., title="Failure Reason", description="Reason for warning")
+    workflow_step_id: Optional[DatabaseIdT] = Field(None, title="Workflow step id of step that caused a warning.")
+
+
+class GenericInvocationEvaluationWarningWorkflowOutputNotFound(
+    GenericInvocationWarning[DatabaseIdT], Generic[DatabaseIdT]
+):
+    reason: Literal[WarningReason.workflow_output_not_found]
+    output_name: str = Field(
+        ..., description="Output that was designated as workflow output but that has not been found"
+    )
+
+
+InvocationCancellationReviewFailed = GenericInvocationCancellationReviewFailed[int]
+InvocationCancellationHistoryDeleted = GenericInvocationCancellationHistoryDeleted[int]
+InvocationCancellationUserRequest = GenericInvocationCancellationUserRequest[int]
+InvocationFailureDatasetFailed = GenericInvocationFailureDatasetFailed[int]
+InvocationFailureCollectionFailed = GenericInvocationFailureCollectionFailed[int]
+InvocationFailureJobFailed = GenericInvocationFailureJobFailed[int]
+InvocationFailureOutputNotFound = GenericInvocationFailureOutputNotFound[int]
+InvocationUnexpectedFailure = GenericInvocationUnexpectedFailure[int]
+InvocationWarningWorkflowOutputNotFound = GenericInvocationEvaluationWarningWorkflowOutputNotFound[int]
+
+InvocationMessageUnion = Annotated[
+    Union[
+        GenericInvocationCancellationReviewFailed[DatabaseIdT],
+        GenericInvocationCancellationHistoryDeleted[DatabaseIdT],
+        GenericInvocationCancellationUserRequest[DatabaseIdT],
+        GenericInvocationFailureDatasetFailed[DatabaseIdT],
+        GenericInvocationFailureCollectionFailed[DatabaseIdT],
+        GenericInvocationFailureJobFailed[DatabaseIdT],
+        GenericInvocationFailureOutputNotFound[DatabaseIdT],
+        GenericInvocationFailureExpressionEvaluationFailed[DatabaseIdT],
+        GenericInvocationFailureWhenNotBoolean[DatabaseIdT],
+        GenericInvocationUnexpectedFailure[DatabaseIdT],
+        GenericInvocationEvaluationWarningWorkflowOutputNotFound[DatabaseIdT],
+    ],
+    Field(discriminator="reason"),
+]
+
+
+class GenericInvocationMessage(GenericModel, Generic[DatabaseIdT]):
+    __root__: InvocationMessageUnion[DatabaseIdT]
+
+    class Config:
+        orm_mode = True
+
+
+InvocationMessage = InvocationMessageUnion[int]
+InvocationMessageResponseModel = GenericInvocationMessage[EncodedDatabaseIdField]
+
+
 class Creator(Model):
     class_: str = Field(..., alias="class", title="Class", description="The class representing this creator.")
     name: str = Field(..., title="Name", description="The name of the creator.")
diff --git a/lib/galaxy/webapps/galaxy/api/workflows.py b/lib/galaxy/webapps/galaxy/api/workflows.py
index d2e4d0e891d..846f2e34d29 100644
--- a/lib/galaxy/webapps/galaxy/api/workflows.py
+++ b/lib/galaxy/webapps/galaxy/api/workflows.py
@@ -51,6 +51,7 @@ from galaxy.schema.fields import DecodedDatabaseIdField
 from galaxy.schema.schema import (
     AsyncFile,
     AsyncTaskResultSummary,
+    InvocationMessage,
     SetSlugPayload,
     ShareWithPayload,
     ShareWithStatus,
@@ -764,12 +765,19 @@ class WorkflowsAPIController(
             invocations.append(workflow_invocation)
 
         trans.sa_session.flush()
-        invocations = [self.encode_all_ids(trans, invocation.to_dict(), recursive=True) for invocation in invocations]
+        encoded_invocations = []
+        for invocation in invocations:
+            as_dict = workflow_invocation.to_dict()
+            as_dict["messages"] = [
+                InvocationMessage.parse_obj(message).__root__.dict() for message in invocation.messages
+            ]
+            as_dict = self.encode_all_ids(trans, as_dict, recursive=True)
+            encoded_invocations.append(as_dict)
 
         if is_batch:
-            return invocations
+            return encoded_invocations
         else:
-            return invocations[0]
+            return encoded_invocations[0]
 
     @expose_api
     def index_invocations(self, trans: GalaxyWebTransaction, **kwd):
diff --git a/lib/galaxy/webapps/galaxy/services/invocations.py b/lib/galaxy/webapps/galaxy/services/invocations.py
index 82e1bb536d2..a055a4be313 100644
--- a/lib/galaxy/webapps/galaxy/services/invocations.py
+++ b/lib/galaxy/webapps/galaxy/services/invocations.py
@@ -24,6 +24,7 @@ from galaxy.exceptions import (
 )
 from galaxy.managers.histories import HistoryManager
 from galaxy.managers.workflows import WorkflowsManager
+from galaxy.model import WorkflowInvocation
 from galaxy.model.store import (
     BcoExportOptions,
     get_export_store_factory,
@@ -34,6 +35,7 @@ from galaxy.schema.schema import (
     AsyncTaskResultSummary,
     BcoGenerationParametersMixin,
     InvocationIndexQueryPayload,
+    InvocationMessage,
     StoreExportPayload,
     WriteStoreToPayload,
 )
@@ -190,7 +192,7 @@ class InvocationsService(ServiceBase):
 
     def serialize_workflow_invocation(
         self,
-        invocation,
+        invocation: WorkflowInvocation,
         params: InvocationSerializationParams,
         default_view: InvocationSerializationView = InvocationSerializationView.element,
     ):
@@ -198,6 +200,7 @@ class InvocationsService(ServiceBase):
         step_details = params.step_details
         legacy_job_state = params.legacy_job_state
         as_dict = invocation.to_dict(view, step_details=step_details, legacy_job_state=legacy_job_state)
+        as_dict["messages"] = [InvocationMessage.parse_obj(message).__root__.dict() for message in invocation.messages]
         return self.security.encode_all_ids(as_dict, recursive=True)
 
     def serialize_workflow_invocations(
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index c8a5d00b4ba..19e7e0617cb 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -13,6 +13,7 @@ from typing import (
     List,
     Optional,
     Type,
+    TYPE_CHECKING,
     Union,
 )
 
@@ -37,6 +38,12 @@ from galaxy.model import (
     WorkflowStepConnection,
 )
 from galaxy.model.dataset_collections import matching
+from galaxy.schema.schema import (
+    CancelReason,
+    FailureReason,
+    InvocationCancellationReviewFailed,
+    InvocationFailureDatasetFailed,
+)
 from galaxy.tool_util.cwl.util import set_basename_and_derived_properties
 from galaxy.tool_util.parser.output_objects import ToolExpressionOutput
 from galaxy.tools import (
@@ -88,6 +95,9 @@ from galaxy.util.rules_dsl import RuleSet
 from galaxy.util.template import fill_template
 from galaxy.util.tool_shed.common_util import get_tool_shed_url_from_tool_shed_registry
 
+if TYPE_CHECKING:
+    from galaxy.schema.schema import InvocationMessage
+
 log = logging.getLogger(__name__)
 
 # Key into Tool state to describe invocation-specific runtime properties.
@@ -137,7 +147,11 @@ def evaluate_value_from_expressions(progress, step, execution_state, extra_step_
                 why = "dataset [%s] is needed for valueFrom expression and is non-ready" % value.id
                 raise DelayedWorkflowEvaluation(why=why)
             if not value.is_ok:
-                raise CancelWorkflowEvaluation()
+                raise FailWorkflowEvaluation(
+                    why=InvocationFailureDatasetFailed(
+                        reason=FailureReason.dataset_failed, hda_id=value.id, workflow_step_id=step.id
+                    )
+                )
             if value.ext == "expression.json":
                 with open(value.file_name) as f:
                     # OUR safe_loads won't work, will not load numbers, etc...
@@ -1599,7 +1613,11 @@ class PauseModule(WorkflowModule):
                 progress.set_step_outputs(invocation_step, {"output": replacement})
                 return
             elif action is False:
-                raise CancelWorkflowEvaluation()
+                raise CancelWorkflowEvaluation(
+                    why=InvocationCancellationReviewFailed(
+                        reason=CancelReason.cancelled_on_review, workflow_step_id=step.id
+                    )
+                )
         delayed_why = "workflow paused at this step waiting for review"
         raise DelayedWorkflowEvaluation(why=delayed_why)
 
@@ -2061,8 +2079,9 @@ class ToolModule(WorkflowModule):
         step = invocation_step.workflow_step
         tool = trans.app.toolbox.get_tool(step.tool_id, tool_version=step.tool_version, tool_uuid=step.tool_uuid)
         if not tool.is_workflow_compatible:
-            message = f"Specified tool [{tool.id}] in workflow is not workflow-compatible."
-            raise Exception(message)
+            # TODO: why do we even create an invocation, seems like something we could check on submit?
+            message = f"Specified tool [{tool.id}] in step {step.order_index + 1} is not workflow-compatible."
+            raise exceptions.MessageException(message)
         tool_state = step.state
         tool_inputs = tool.inputs.copy()
         # Not strictly needed - but keep Tool state clean by stripping runtime
@@ -2134,8 +2153,7 @@ class ToolModule(WorkflowModule):
                     replace_optional_connections=True,
                 )
             except KeyError as k:
-                message_template = "Error due to input mapping of '%s' in '%s'.  A common cause of this is conditional outputs that cannot be determined until runtime, please review your workflow."
-                message = message_template % (tool.name, unicodify(k))
+                message = f"Error due to input mapping of '{unicodify(k)}' in tool '{tool.id}'.  A common cause of this is conditional outputs that cannot be determined until runtime, please review workflow step {step.order_index + 1}."
                 raise exceptions.MessageException(message)
 
             if step.when_expression and when_value is not False:
@@ -2380,7 +2398,13 @@ class DelayedWorkflowEvaluation(Exception):
 
 
 class CancelWorkflowEvaluation(Exception):
-    pass
+    def __init__(self, why: "InvocationMessage"):
+        self.why = why
+
+
+class FailWorkflowEvaluation(Exception):
+    def __init__(self, why: "InvocationMessage"):
+        self.why = why
 
 
 class SkipWorkflowStepEvaluation(Exception):
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index 5c0effb8f3a..1e2e8490350 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -13,10 +13,22 @@ from typing import (
 from typing_extensions import Protocol
 
 from galaxy import model
+from galaxy.exceptions import MessageException
 from galaxy.model import (
     WorkflowInvocation,
     WorkflowInvocationStep,
 )
+from galaxy.schema.schema import (
+    FailureReason,
+    InvocationCancellationHistoryDeleted,
+    InvocationFailureCollectionFailed,
+    InvocationFailureDatasetFailed,
+    InvocationFailureJobFailed,
+    InvocationFailureOutputNotFound,
+    InvocationUnexpectedFailure,
+    InvocationWarningWorkflowOutputNotFound,
+    WarningReason,
+)
 from galaxy.util import ExecutionTimer
 from galaxy.workflow import modules
 from galaxy.workflow.run_request import (
@@ -73,21 +85,31 @@ def __invoke(
         workflow_invocation=workflow_invocation,
     )
     workflow_invocation = invoker.workflow_invocation
+    outputs = {}
     try:
         outputs = invoker.invoke()
-    except modules.CancelWorkflowEvaluation:
+    except modules.CancelWorkflowEvaluation as e:
         if workflow_invocation.cancel():
-            trans.sa_session.add(workflow_invocation)
-        outputs = {}
+            workflow_invocation.add_message(e.why)
+    except modules.FailWorkflowEvaluation as e:
+        workflow_invocation.fail()
+        workflow_invocation.add_message(e.why)
+    except MessageException as e:
+        # Convention for safe message we can show to users
+        workflow_invocation.fail()
+        failure = InvocationUnexpectedFailure(reason=FailureReason.unexpected_failure, details=str(e))
+        workflow_invocation.add_message(failure)
     except Exception:
+        # Could potentially be large and/or contain raw ids or other secrets, don't add details
         log.exception("Failed to execute scheduled workflow.")
         # Running workflow invocation in background, just mark
         # persistent workflow invocation as failed.
+        failure = InvocationUnexpectedFailure(reason=FailureReason.unexpected_failure)
         workflow_invocation.fail()
-        trans.sa_session.add(workflow_invocation)
-        outputs = {}
+        workflow_invocation.add_message(failure)
 
     # Be sure to update state of workflow_invocation.
+    trans.sa_session.add(workflow_invocation)
     trans.sa_session.flush()
 
     return outputs, workflow_invocation
@@ -176,8 +198,11 @@ class WorkflowInvoker:
             return self.progress.outputs
 
         if workflow_invocation.history.deleted:
-            log.info("Cancelled workflow evaluation due to deleted history")
-            raise modules.CancelWorkflowEvaluation()
+            raise modules.CancelWorkflowEvaluation(
+                why=InvocationCancellationHistoryDeleted(
+                    reason=FailureReason.history_deleted, history_id=workflow_invocation.history_id
+                )
+            )
 
         remaining_steps = self.progress.remaining_steps()
         delayed_steps = False
@@ -244,9 +269,9 @@ class WorkflowInvoker:
         for input_connection in step.input_connections:
             if input_connection.non_data_connection:
                 output_id = input_connection.output_step.id
-                self.__check_implicitly_dependent_step(output_id)
+                self.__check_implicitly_dependent_step(output_id, step.id)
 
-    def __check_implicitly_dependent_step(self, output_id):
+    def __check_implicitly_dependent_step(self, output_id: int, step_id: int):
         step_invocation = self.workflow_invocation.step_invocation_for_step_id(output_id)
 
         # No steps created yet - have to delay evaluation.
@@ -268,7 +293,14 @@ class WorkflowInvoker:
                 raise modules.DelayedWorkflowEvaluation(why=delayed_why)
 
             if job.state != job.states.OK:
-                raise modules.CancelWorkflowEvaluation()
+                raise modules.FailWorkflowEvaluation(
+                    why=InvocationFailureJobFailed(
+                        reason=FailureReason.job_failed,
+                        job_id=job.id,
+                        workflow_step_id=step_id,
+                        dependent_workflow_step_id=step_invocation.id,
+                    )
+                )
 
     def _invoke_step(self, invocation_step: WorkflowInvocationStep) -> Optional[bool]:
         incomplete_or_none = invocation_step.workflow_step.module.execute(
@@ -349,9 +381,10 @@ class WorkflowProgress:
             step_args = self.param_map.get(step_id, {})
             self.module_injector.compute_runtime_state(step, step_args=step_args)
             if step_id not in step_states:
-                raise Exception(
-                    f"Workflow invocation [{self.workflow_invocation.id}] has no step state for step {step.log_str()}. States ids are {list(step_states.keys())}."
-                )
+                # Can this ever happen?
+                public_message = f"Workflow invocation has no step state for step {step.order_index + 1}"
+                log.error(f"{public_message}. State is known for these step ids: {list(step_states.keys())}.")
+                raise MessageException(public_message)
             runtime_state = step_states[step_id].value
             assert step.module
             step.state = step.module.decode_runtime_state(runtime_state)
@@ -393,29 +426,45 @@ class WorkflowProgress:
 
     def replacement_for_connection(self, connection: "WorkflowStepConnection", is_data: bool = True) -> Any:
         output_step_id = connection.output_step.id
+        output_name = connection.output_name
         if output_step_id not in self.outputs:
-            message = f"No outputs found for step id {output_step_id}, outputs are {self.outputs}"
-            raise Exception(message)
+            raise modules.FailWorkflowEvaluation(
+                why=InvocationFailureOutputNotFound(
+                    reason=FailureReason.output_not_found,
+                    workflow_step_id=connection.input_step_id,
+                    output_name=output_name,
+                    dependent_workflow_step_id=output_step_id,
+                )
+            )
         step_outputs = self.outputs[output_step_id]
         if step_outputs is STEP_OUTPUT_DELAYED:
             delayed_why = f"dependent step [{output_step_id}] delayed, so this step must be delayed"
             raise modules.DelayedWorkflowEvaluation(why=delayed_why)
-        output_name = connection.output_name
         try:
             replacement = step_outputs[output_name]
         except KeyError:
-            # Must resolve.
-            template = "Workflow evaluation problem - failed to find output_name %s in step_outputs %s"
-            message = template % (output_name, step_outputs)
-            raise Exception(message)
+            raise modules.FailWorkflowEvaluation(
+                why=InvocationFailureOutputNotFound(
+                    reason=FailureReason.output_not_found,
+                    workflow_step_id=connection.input_step_id,
+                    output_name=output_name,
+                    dependent_workflow_step_id=output_step_id,
+                )
+            )
         if isinstance(replacement, model.HistoryDatasetCollectionAssociation):
             if not replacement.collection.populated:
                 if not replacement.waiting_for_elements:
                     # If we are not waiting for elements, there was some
                     # problem creating the collection. Collection will never
                     # be populated.
-                    # TODO: consider distinguish between cancelled and failed?
-                    raise modules.CancelWorkflowEvaluation()
+                    raise modules.FailWorkflowEvaluation(
+                        why=InvocationFailureCollectionFailed(
+                            reason=FailureReason.collection_failed,
+                            hdca_id=replacement.id,
+                            workflow_step_id=connection.input_step_id,
+                            dependent_workflow_step_id=output_step_id,
+                        )
+                    )
 
                 delayed_why = f"dependent collection [{replacement.id}] not yet populated with datasets"
                 raise modules.DelayedWorkflowEvaluation(why=delayed_why)
@@ -429,7 +478,14 @@ class WorkflowProgress:
                 if replacement.is_pending:
                     raise modules.DelayedWorkflowEvaluation()
                 if not replacement.is_ok:
-                    raise modules.CancelWorkflowEvaluation()
+                    raise modules.FailWorkflowEvaluation(
+                        why=InvocationFailureDatasetFailed(
+                            reason=FailureReason.dataset_failed,
+                            hda_id=replacement.id,
+                            workflow_step_id=connection.input_step_id,
+                            dependent_workflow_step_id=output_step_id,
+                        )
+                    )
             else:
                 if not replacement.collection.populated:
                     raise modules.DelayedWorkflowEvaluation()
@@ -438,7 +494,14 @@ class WorkflowProgress:
                     if dataset_instance.is_pending:
                         pending = True
                     elif not dataset_instance.is_ok:
-                        raise modules.CancelWorkflowEvaluation()
+                        raise modules.FailWorkflowEvaluation(
+                            why=InvocationFailureDatasetFailed(
+                                reason=FailureReason.dataset_failed,
+                                hda_id=replacement.id,
+                                workflow_step_id=connection.input_step_id,
+                                dependent_workflow_step_id=output_step_id,
+                            )
+                        )
                 if pending:
                     raise modules.DelayedWorkflowEvaluation()
 
@@ -469,7 +532,15 @@ class WorkflowProgress:
                 if default_value or step.input_optional:
                     outputs["output"] = default_value
                 else:
-                    raise ValueError(f"{step.log_str()} not found in inputs_step_id {self.inputs_by_step_id}")
+                    log.error(f"{step.log_str()} not found in inputs_step_id {self.inputs_by_step_id}")
+                    raise modules.FailWorkflowEvaluation(
+                        why=InvocationFailureOutputNotFound(
+                            reason=FailureReason.output_not_found,
+                            workflow_step_id=invocation_step.workflow_step_id,
+                            output_name="output",
+                            dependent_workflow_step_id=invocation_step.workflow_step_id,
+                        )
+                    )
             elif step_id in self.inputs_by_step_id:
                 outputs["output"] = self.inputs_by_step_id[step_id]
 
@@ -497,13 +568,14 @@ class WorkflowProgress:
             for workflow_output in step.workflow_outputs:
                 output_name = workflow_output.output_name
                 if output_name not in outputs:
+                    invocation_step.workflow_invocation.add_message(
+                        InvocationWarningWorkflowOutputNotFound(
+                            reason=WarningReason.workflow_output_not_found,
+                            workflow_step_id=step.id,
+                            output_name=output_name,
+                        )
+                    )
                     message = f"Failed to find expected workflow output [{output_name}] in step outputs [{outputs}]"
-                    # raise KeyError(message)
-                    # Pre-18.01 we would have never even detected this output wasn't configured
-                    # and even in 18.01 we don't have a way to tell the user something bad is
-                    # happening so I guess we just log a debug message and continue sadly for now.
-                    # Once https://github.com/galaxyproject/galaxy/issues/5142 is complete we could
-                    # at least tell the user what happened, give them a warning.
                     log.debug(message)
                     continue
                 output = outputs[output_name]
@@ -526,7 +598,7 @@ class WorkflowProgress:
         workflow_invocation = self.workflow_invocation
         subworkflow_invocation = workflow_invocation.get_subworkflow_invocation_for_step(step)
         if subworkflow_invocation is None:
-            raise Exception(f"Failed to find persisted workflow invocation for step [{step.id}]")
+            raise MessageException(f"Failed to find persisted subworkflow invocation for step [{step.order_index + 1}]")
         return subworkflow_invocation
 
     def subworkflow_invoker(
@@ -579,7 +651,14 @@ class WorkflowProgress:
                     break
 
             if not connection_found and not input_subworkflow_step.input_optional:
-                raise Exception("Could not find connections for all subworkflow inputs.")
+                raise modules.FailWorkflowEvaluation(
+                    InvocationFailureOutputNotFound(
+                        reason=FailureReason.output_not_found,
+                        workflow_step_id=step.id,
+                        output_name=input_connection.output_name,
+                        dependent_workflow_step_id=input_connection.output_step.id,
+                    )
+                )
 
         return WorkflowProgress(
             subworkflow_invocation,
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 039aa653cd3..4b143fe5255 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -3450,6 +3450,12 @@ input1:
             self._delete(f"histories/{history_id}")
 
             invocation_cancelled = self._wait_for_invocation_state(uploaded_workflow_id, invocation_id, "cancelled")
+            workflow_details = self._invocation_details(uploaded_workflow_id, invocation_id)
+            assert len(workflow_details["messages"]) == 1
+            message = workflow_details["messages"][0]
+            assert message["history_id"] == history_id
+            assert message["reason"] == "history_deleted"
+
             assert invocation_cancelled, "Workflow state is not cancelled..."
 
     @skip_without_tool("cat")
@@ -3471,6 +3477,11 @@ input1:
 
             invocation_cancelled = self._wait_for_invocation_state(uploaded_workflow_id, invocation_id, "cancelled")
             assert invocation_cancelled, "Workflow state is not cancelled..."
+            workflow_details = self._invocation_details(uploaded_workflow_id, invocation_id)
+            assert len(workflow_details["messages"]) == 1
+            message = workflow_details["messages"][0]
+            assert message["history_id"] == history_id
+            assert message["reason"] == "history_deleted"
 
     @skip_without_tool("cat")
     def test_workflow_pause(self):
@@ -3519,6 +3530,11 @@ input1:
             # Ensure the workflow eventually becomes cancelled.
             invocation_cancelled = self._wait_for_invocation_state(uploaded_workflow_id, invocation_id, "cancelled")
             assert invocation_cancelled, "Workflow state is not cancelled..."
+            workflow_details = self._invocation_details(uploaded_workflow_id, invocation_id)
+            assert len(workflow_details["messages"]) == 1
+            message = workflow_details["messages"][0]
+            assert "workflow_step_id" in message
+            assert message["reason"] == "cancelled_on_review"
 
     @skip_without_tool("head")
     def test_workflow_map_reduce_pause(self):
@@ -3574,6 +3590,71 @@ input1:
 
             invocation = self._invocation_details(uploaded_workflow_id, invocation_id)
             assert invocation["state"] == "cancelled"
+            message = invocation["messages"][0]
+            assert message["reason"] == "user_request"
+
+    def test_workflow_failed_output_not_found(self, history_id):
+        summary = self._run_workflow(
+            """
+class: GalaxyWorkflow
+inputs: []
+steps:
+  create_2:
+    tool_id: create_2
+    state:
+      sleep_time: 0
+    outputs:
+      out_file1:
+        rename: "my new name"
+      out_file2:
+        rename: "my other new name"
+  first_cat1:
+    tool_id: cat
+    in:
+      input1: create_2/does_not_exist
+ """,
+            history_id=history_id,
+            assert_ok=False,
+            wait=True,
+        )
+        invocation = self.workflow_populator.get_invocation(summary.invocation_id)
+        assert invocation["state"] == "failed"
+        assert len(invocation["message"]) == 1
+        message = invocation["message"]
+        assert message["reason"] == "output_not_found"
+        assert "workflow_step_id" in message
+        assert "dependent_workflow_step_id" in message
+
+    def test_workflow_warning_workflow_output_not_found(self, history_id):
+        summary = self._run_workflow(
+            """
+class: GalaxyWorkflow
+inputs: []
+steps:
+  create_2:
+    tool_id: create_2
+    state:
+      sleep_time: 0
+    outputs:
+      out_file1:
+        rename: "my new name"
+      out_file2:
+        rename: "my other new name"
+outputs:
+  main_out:
+    outputSource: create_2/does_not_exist
+ """,
+            history_id=history_id,
+            assert_ok=False,
+            wait=True,
+        )
+        invocation = self.workflow_populator.get_invocation(summary.invocation_id)
+        assert invocation["state"] == "scheduled"
+        assert len(invocation["messages"]) == 1
+        message = invocation["messages"][0]
+        assert message["reason"] == "workflow_output_not_found"
+        assert "workflow_step_id" in message
+        assert message["output_name"] == "does_not_exist"
 
     @skip_without_tool("identifier_multiple")
     def test_invocation_map_over(self, history_id):

From b9b5f52169440df24bc0cd8e4d867a032d005c2e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 15 Jan 2023 11:51:43 +0100
Subject: [PATCH 149/350] Record execution_tracker.execution_errors on
 invocation

---
 lib/galaxy/workflow/modules.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 19e7e0617cb..7c0ee998b42 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -2254,8 +2254,9 @@ class ToolModule(WorkflowModule):
 
             self._handle_mapped_over_post_job_actions(step, step_inputs, step_outputs, progress.replacement_dict)
         if execution_tracker.execution_errors:
-            message = "Failed to create one or more job(s) for workflow step."
-            raise Exception(message)
+            # TODO: formalize into InvocationFailure ?
+            message = f"Failed to create {len(execution_tracker.execution_errors)} job(s) for workflow step {step.order_index + 1}: {str(execution_tracker.execution_errors[0])}"
+            raise exceptions.MessageException(message)
 
         return complete
 

From 7d659bc272f59aa7be546eb47cae3b256bc4fc3e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 15 Jan 2023 17:35:07 +0100
Subject: [PATCH 150/350] Test invalid expressions and expression results

---
 lib/galaxy/schema/schema.py                   | 50 ++++++++---
 lib/galaxy/webapps/galaxy/api/workflows.py    |  8 +-
 .../webapps/galaxy/services/invocations.py    |  9 +-
 lib/galaxy/workflow/modules.py                | 44 +++++++---
 lib/galaxy/workflow/run.py                    |  3 +-
 lib/galaxy_test/api/test_workflows.py         | 82 +++++++++++++++++--
 6 files changed, 162 insertions(+), 34 deletions(-)

diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index 3ee91e54e0b..dcee94891b3 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -29,6 +29,7 @@ from pydantic import (
     UUID4,
 )
 from pydantic.generics import GenericModel
+from pydantic.utils import GetterDict
 from typing_extensions import (
     Annotated,
     Literal,
@@ -1926,6 +1927,8 @@ class FailureReason(str, Enum):
     collection_failed = "collection_failed"
     job_failed = "job_failed"
     output_not_found = "output_not_found"
+    expression_evaluation_failed = "expression_evaluation_failed"
+    when_not_boolean = "when_not_boolean"
     unexpected_failure = "unexpected_failure"
 
 
@@ -1940,20 +1943,33 @@ class CancelReason(str, Enum):
 DatabaseIdT = TypeVar("DatabaseIdT")
 
 
+class StepOrderIndexGetter(GetterDict):
+    def get(self, key: Any, default: Any = None) -> Any:
+
+        # Fetch the order_index when serializing for the API,
+        # which makes much more sense when pointing to steps.
+        if key == "workflow_step_id":
+            return self._obj.workflow_step.order_index
+        elif key == "dependent_workflow_step_id":
+            return self._obj.dependent_workflow_step.order_index
+
+        return super().get(key, default)
+
+
 class InvocationMessageBase(GenericModel):
     reason: Union[CancelReason, FailureReason, WarningReason]
 
     class Config:
         orm_mode = True
+        getter_dict = StepOrderIndexGetter
 
 
 class GenericInvocationCancellationReviewFailed(InvocationMessageBase, Generic[DatabaseIdT]):
     reason: Literal[CancelReason.cancelled_on_review]
-    workflow_step_id: DatabaseIdT = Field(..., description="Workflow step id of paused step that did not pass review.")
+    workflow_step_id: int = Field(..., description="Workflow step id of paused step that did not pass review.")
 
 
 class GenericInvocationCancellationHistoryDeleted(InvocationMessageBase, Generic[DatabaseIdT]):
-    # reason: CancelReason.history_deleted
     reason: Literal[CancelReason.history_deleted]
     history_id: DatabaseIdT = Field(..., title="History ID", description="History ID of history that was deleted.")
 
@@ -1963,7 +1979,7 @@ class GenericInvocationCancellationUserRequest(InvocationMessageBase, Generic[Da
 
 
 class InvocationFailureMessageBase(InvocationMessageBase, Generic[DatabaseIdT]):
-    workflow_step_id: DatabaseIdT = Field(..., description="Workflow step id of step that failed.")
+    workflow_step_id: int = Field(..., description="Workflow step id of step that failed.")
 
 
 class GenericInvocationFailureDatasetFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
@@ -1971,9 +1987,7 @@ class GenericInvocationFailureDatasetFailed(InvocationFailureMessageBase[Databas
     hda_id: DatabaseIdT = Field(
         ..., title="HistoryDatasetAssociation ID", description="HistoryDatasetAssociation ID that relates to failure."
     )
-    dependent_workflow_step_id: Optional[DatabaseIdT] = Field(
-        None, description="Workflow step id of step that caused failure."
-    )
+    dependent_workflow_step_id: Optional[int] = Field(None, description="Workflow step id of step that caused failure.")
 
 
 class GenericInvocationFailureCollectionFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
@@ -1983,29 +1997,41 @@ class GenericInvocationFailureCollectionFailed(InvocationFailureMessageBase[Data
         title="HistoryDatasetCollectionAssociation ID",
         description="HistoryDatasetCollectionAssociation ID that relates to failure.",
     )
-    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
 
 
 class GenericInvocationFailureJobFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
     reason: Literal[FailureReason.job_failed]
     job_id: DatabaseIdT = Field(None, title="Job ID", description="Job ID that relates to failure.")
-    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
 
 
 class GenericInvocationFailureOutputNotFound(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
     reason: Literal[FailureReason.output_not_found]
     output_name: str = Field(..., title="Tool or module output name that was referenced but not produced")
-    dependent_workflow_step_id: DatabaseIdT = Field(None, description="Workflow step id of step that caused failure.")
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
 
 
-class GenericInvocationUnexpectedFailure(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+class GenericInvocationFailureExpressionEvaluationFailed(
+    InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]
+):
+    reason: Literal[FailureReason.expression_evaluation_failed]
+    details: Optional[str] = Field(None, description="May contain details to help troubleshoot this problem.")
+
+
+class GenericInvocationFailureWhenNotBoolean(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.when_not_boolean]
+    details: str = Field(..., description="Contains details to help troubleshoot this problem.")
+
+
+class GenericInvocationUnexpectedFailure(InvocationMessageBase, Generic[DatabaseIdT]):
     reason: Literal[FailureReason.unexpected_failure]
     details: Optional[str] = Field(None, description="May contains details to help troubleshoot this problem.")
 
 
 class GenericInvocationWarning(InvocationMessageBase, Generic[DatabaseIdT]):
     reason: WarningReason = Field(..., title="Failure Reason", description="Reason for warning")
-    workflow_step_id: Optional[DatabaseIdT] = Field(None, title="Workflow step id of step that caused a warning.")
+    workflow_step_id: Optional[int] = Field(None, title="Workflow step id of step that caused a warning.")
 
 
 class GenericInvocationEvaluationWarningWorkflowOutputNotFound(
@@ -2024,6 +2050,8 @@ InvocationFailureDatasetFailed = GenericInvocationFailureDatasetFailed[int]
 InvocationFailureCollectionFailed = GenericInvocationFailureCollectionFailed[int]
 InvocationFailureJobFailed = GenericInvocationFailureJobFailed[int]
 InvocationFailureOutputNotFound = GenericInvocationFailureOutputNotFound[int]
+InvocationFailureExpressionEvaluationFailed = GenericInvocationFailureExpressionEvaluationFailed[int]
+InvocationFailureWhenNotBoolean = GenericInvocationFailureWhenNotBoolean[int]
 InvocationUnexpectedFailure = GenericInvocationUnexpectedFailure[int]
 InvocationWarningWorkflowOutputNotFound = GenericInvocationEvaluationWarningWorkflowOutputNotFound[int]
 
diff --git a/lib/galaxy/webapps/galaxy/api/workflows.py b/lib/galaxy/webapps/galaxy/api/workflows.py
index 846f2e34d29..45a761e7192 100644
--- a/lib/galaxy/webapps/galaxy/api/workflows.py
+++ b/lib/galaxy/webapps/galaxy/api/workflows.py
@@ -51,7 +51,7 @@ from galaxy.schema.fields import DecodedDatabaseIdField
 from galaxy.schema.schema import (
     AsyncFile,
     AsyncTaskResultSummary,
-    InvocationMessage,
+    InvocationMessageResponseModel,
     SetSlugPayload,
     ShareWithPayload,
     ShareWithStatus,
@@ -768,10 +768,10 @@ class WorkflowsAPIController(
         encoded_invocations = []
         for invocation in invocations:
             as_dict = workflow_invocation.to_dict()
-            as_dict["messages"] = [
-                InvocationMessage.parse_obj(message).__root__.dict() for message in invocation.messages
-            ]
             as_dict = self.encode_all_ids(trans, as_dict, recursive=True)
+            as_dict["messages"] = [
+                InvocationMessageResponseModel.parse_obj(message).__root__.dict() for message in invocation.messages
+            ]
             encoded_invocations.append(as_dict)
 
         if is_batch:
diff --git a/lib/galaxy/webapps/galaxy/services/invocations.py b/lib/galaxy/webapps/galaxy/services/invocations.py
index a055a4be313..fd924add80c 100644
--- a/lib/galaxy/webapps/galaxy/services/invocations.py
+++ b/lib/galaxy/webapps/galaxy/services/invocations.py
@@ -35,7 +35,7 @@ from galaxy.schema.schema import (
     AsyncTaskResultSummary,
     BcoGenerationParametersMixin,
     InvocationIndexQueryPayload,
-    InvocationMessage,
+    InvocationMessageResponseModel,
     StoreExportPayload,
     WriteStoreToPayload,
 )
@@ -200,8 +200,11 @@ class InvocationsService(ServiceBase):
         step_details = params.step_details
         legacy_job_state = params.legacy_job_state
         as_dict = invocation.to_dict(view, step_details=step_details, legacy_job_state=legacy_job_state)
-        as_dict["messages"] = [InvocationMessage.parse_obj(message).__root__.dict() for message in invocation.messages]
-        return self.security.encode_all_ids(as_dict, recursive=True)
+        as_dict = self.security.encode_all_ids(as_dict, recursive=True)
+        as_dict["messages"] = [
+            InvocationMessageResponseModel.parse_obj(message).__root__.dict() for message in invocation.messages
+        ]
+        return as_dict
 
     def serialize_workflow_invocations(
         self,
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 7c0ee998b42..c38a7b3d350 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -43,6 +43,8 @@ from galaxy.schema.schema import (
     FailureReason,
     InvocationCancellationReviewFailed,
     InvocationFailureDatasetFailed,
+    InvocationFailureExpressionEvaluationFailed,
+    InvocationFailureWhenNotBoolean,
 )
 from galaxy.tool_util.cwl.util import set_basename_and_derived_properties
 from galaxy.tool_util.parser.output_objects import ToolExpressionOutput
@@ -202,15 +204,38 @@ def evaluate_value_from_expressions(progress, step, execution_state, extra_step_
             step_state[key] = to_cwl(value)
 
     if when_expression is not None:
-        as_cwl_value = do_eval(
-            when_expression,
-            step_state,
-            [{"class": "InlineJavascriptRequirement"}],
-            None,
-            None,
-            {},
-        )
-        return from_cwl(as_cwl_value)
+        try:
+            as_cwl_value = do_eval(
+                when_expression,
+                step_state,
+                [{"class": "InlineJavascriptRequirement"}],
+                None,
+                None,
+                {},
+            )
+        except Exception:
+            # Exception contains script and traceback, which could be helpful for debugging workflows,
+            # but both could conceivably contain secrets.
+            # CWL has a secret hint that should cause values to be sanitized,
+            # but Galaxy does not, so we can't really display anything here at this point.
+            # In any case I believe the CWL secret hint can be bypassed if the value is passed on
+            # to another step input that doesn't have the secret set.
+            # Complicated stuff, ignore for now.
+            raise FailWorkflowEvaluation(
+                InvocationFailureExpressionEvaluationFailed(
+                    reason=FailureReason.expression_evaluation_failed, workflow_step_id=step.id
+                )
+            )
+        when_value = from_cwl(as_cwl_value)
+        if not isinstance(when_value, bool):
+            raise FailWorkflowEvaluation(
+                InvocationFailureWhenNotBoolean(
+                    reason=FailureReason.when_not_boolean,
+                    workflow_step_id=step.id,
+                    details=f"Type is: {when_value.__class__.__name__}",
+                )
+            )
+        return when_value
 
 
 class WorkflowModule:
@@ -2184,7 +2209,6 @@ class ToolModule(WorkflowModule):
                     when_value = evaluate_value_from_expressions(
                         progress, step, execution_state=execution_state, extra_step_state=extra_step_state
                     )
-                    assert isinstance(when_value, bool)
             if when_value is not None:
                 # Track this more formally ?
                 execution_state.inputs["__when_value__"] = when_value
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index 1e2e8490350..f5fa399f052 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -19,6 +19,7 @@ from galaxy.model import (
     WorkflowInvocationStep,
 )
 from galaxy.schema.schema import (
+    CancelReason,
     FailureReason,
     InvocationCancellationHistoryDeleted,
     InvocationFailureCollectionFailed,
@@ -200,7 +201,7 @@ class WorkflowInvoker:
         if workflow_invocation.history.deleted:
             raise modules.CancelWorkflowEvaluation(
                 why=InvocationCancellationHistoryDeleted(
-                    reason=FailureReason.history_deleted, history_id=workflow_invocation.history_id
+                    reason=CancelReason.history_deleted, history_id=workflow_invocation.history_id
                 )
             )
 
diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 4b143fe5255..4f5e1553325 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -1963,6 +1963,78 @@ should_run:
                 if step["workflow_step_label"] == "cat1":
                     assert sum(1 for j in step["jobs"] if j["state"] == "skipped") == 1
 
+    def test_run_workflow_invalid_when_expression(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """class: GalaxyWorkflow
+inputs:
+  should_run:
+    type: boolean
+  some_file:
+    type: data
+steps:
+  cat1:
+    tool_id: cat1
+    in:
+      input1: some_file
+      should_run: should_run
+    when: $(:syntaxError:)
+""",
+                test_data="""
+some_file:
+  value: 1.bed
+  type: File
+should_run:
+  value: false
+  type: raw
+""",
+                history_id=history_id,
+                wait=True,
+                assert_ok=False,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            assert invocation_details["state"] == "failed"
+            assert len(invocation_details["messages"]) == 1
+            message = invocation_details["messages"][0]
+            assert message["reason"] == "expression_evaluation_failed"
+
+    def test_run_workflow_fails_when_expression_not_boolean(self):
+        with self.dataset_populator.test_history() as history_id:
+            summary = self._run_workflow(
+                """class: GalaxyWorkflow
+inputs:
+  should_run:
+    type: boolean
+  some_file:
+    type: data
+steps:
+  cat1:
+    tool_id: cat1
+    in:
+      input1: some_file
+      should_run: should_run
+    when: $("false")
+""",
+                test_data="""
+some_file:
+  value: 1.bed
+  type: File
+should_run:
+  value: false
+  type: raw
+""",
+                history_id=history_id,
+                wait=True,
+                assert_ok=False,
+            )
+            invocation_details = self.workflow_populator.get_invocation(summary.invocation_id, step_details=True)
+            assert invocation_details["state"] == "failed"
+            assert len(invocation_details["messages"]) == 1
+            message = invocation_details["messages"][0]
+            assert message["reason"] == "when_not_boolean"
+            assert message["details"] == "Type is: str"
+            assert message["workflow_step_id"] == 2
+
     def test_run_workflow_subworkflow_conditional_step(self):
         with self.dataset_populator.test_history() as history_id:
             summary = self._run_workflow(
@@ -3529,12 +3601,12 @@ input1:
 
             # Ensure the workflow eventually becomes cancelled.
             invocation_cancelled = self._wait_for_invocation_state(uploaded_workflow_id, invocation_id, "cancelled")
-            assert invocation_cancelled, "Workflow state is not cancelled..."
             workflow_details = self._invocation_details(uploaded_workflow_id, invocation_id)
             assert len(workflow_details["messages"]) == 1
             message = workflow_details["messages"][0]
             assert "workflow_step_id" in message
             assert message["reason"] == "cancelled_on_review"
+            assert invocation_cancelled, "Workflow state is not cancelled..."
 
     @skip_without_tool("head")
     def test_workflow_map_reduce_pause(self):
@@ -3619,11 +3691,11 @@ steps:
         )
         invocation = self.workflow_populator.get_invocation(summary.invocation_id)
         assert invocation["state"] == "failed"
-        assert len(invocation["message"]) == 1
-        message = invocation["message"]
+        assert len(invocation["messages"]) == 1
+        message = invocation["messages"][0]
         assert message["reason"] == "output_not_found"
-        assert "workflow_step_id" in message
-        assert "dependent_workflow_step_id" in message
+        assert message["workflow_step_id"] == 1
+        assert message["dependent_workflow_step_id"] == 0
 
     def test_workflow_warning_workflow_output_not_found(self, history_id):
         summary = self._run_workflow(

From 23cc0c483a7318e9b141f9d64d32827c0d434216 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 15 Jan 2023 22:44:03 +0100
Subject: [PATCH 151/350] Avoid Union of GenericModel

More verbose, but https://github.com/pydantic/pydantic/issues/1194
prevents a more concise setup.
---
 lib/galaxy/model/__init__.py   |  4 +--
 lib/galaxy/schema/schema.py    | 62 ++++++++++++++++++++++++----------
 lib/galaxy/workflow/modules.py |  6 ++--
 3 files changed, 49 insertions(+), 23 deletions(-)

diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index 35c3cd2bc50..f3b4ffd6a6d 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -153,7 +153,7 @@ from galaxy.util.json import safe_loads
 from galaxy.util.sanitize_html import sanitize_html
 
 if TYPE_CHECKING:
-    from galaxy.schema.schema import InvocationMessage
+    from galaxy.schema.schema import InvocationMessageUnion
 
 log = logging.getLogger(__name__)
 
@@ -7898,7 +7898,7 @@ class WorkflowInvocation(Base, UsesCreateAndUpdateTime, Dictifiable, Serializabl
             attach_step(request_to_content)
             self.input_step_parameters.append(request_to_content)
 
-    def add_message(self, message: "InvocationMessage"):
+    def add_message(self, message: "InvocationMessageUnion"):
         self.messages.append(
             WorkflowInvocationMessage(
                 workflow_invocation_id=self.id,
diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index dcee94891b3..ac5380c6c4a 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -2055,35 +2055,61 @@ InvocationFailureWhenNotBoolean = GenericInvocationFailureWhenNotBoolean[int]
 InvocationUnexpectedFailure = GenericInvocationUnexpectedFailure[int]
 InvocationWarningWorkflowOutputNotFound = GenericInvocationEvaluationWarningWorkflowOutputNotFound[int]
 
-InvocationMessageUnion = Annotated[
+InvocationMessageUnion = Union[
+    InvocationCancellationReviewFailed,
+    InvocationCancellationHistoryDeleted,
+    InvocationCancellationUserRequest,
+    InvocationFailureDatasetFailed,
+    InvocationFailureCollectionFailed,
+    InvocationFailureJobFailed,
+    InvocationFailureOutputNotFound,
+    InvocationFailureExpressionEvaluationFailed,
+    InvocationFailureWhenNotBoolean,
+    InvocationUnexpectedFailure,
+    InvocationWarningWorkflowOutputNotFound,
+]
+
+InvocationCancellationReviewFailedResponseModel = GenericInvocationCancellationReviewFailed[EncodedDatabaseIdField]
+InvocationCancellationHistoryDeletedResponseModel = GenericInvocationCancellationHistoryDeleted[EncodedDatabaseIdField]
+InvocationCancellationUserRequestResponseModel = GenericInvocationCancellationUserRequest[EncodedDatabaseIdField]
+InvocationFailureDatasetFailedResponseModel = GenericInvocationFailureDatasetFailed[EncodedDatabaseIdField]
+InvocationFailureCollectionFailedResponseModel = GenericInvocationFailureCollectionFailed[EncodedDatabaseIdField]
+InvocationFailureJobFailedResponseModel = GenericInvocationFailureJobFailed[EncodedDatabaseIdField]
+InvocationFailureOutputNotFoundResponseModel = GenericInvocationFailureOutputNotFound[EncodedDatabaseIdField]
+InvocationFailureExpressionEvaluationFailedResponseModel = GenericInvocationFailureExpressionEvaluationFailed[
+    EncodedDatabaseIdField
+]
+InvocationFailureWhenNotBooleanResponseModel = GenericInvocationFailureWhenNotBoolean[EncodedDatabaseIdField]
+InvocationUnexpectedFailureResponseModel = GenericInvocationUnexpectedFailure[EncodedDatabaseIdField]
+InvocationWarningWorkflowOutputNotFoundResponseModel = GenericInvocationEvaluationWarningWorkflowOutputNotFound[
+    EncodedDatabaseIdField
+]
+
+InvocationMessageResponseUnion = Annotated[
     Union[
-        GenericInvocationCancellationReviewFailed[DatabaseIdT],
-        GenericInvocationCancellationHistoryDeleted[DatabaseIdT],
-        GenericInvocationCancellationUserRequest[DatabaseIdT],
-        GenericInvocationFailureDatasetFailed[DatabaseIdT],
-        GenericInvocationFailureCollectionFailed[DatabaseIdT],
-        GenericInvocationFailureJobFailed[DatabaseIdT],
-        GenericInvocationFailureOutputNotFound[DatabaseIdT],
-        GenericInvocationFailureExpressionEvaluationFailed[DatabaseIdT],
-        GenericInvocationFailureWhenNotBoolean[DatabaseIdT],
-        GenericInvocationUnexpectedFailure[DatabaseIdT],
-        GenericInvocationEvaluationWarningWorkflowOutputNotFound[DatabaseIdT],
+        InvocationCancellationReviewFailedResponseModel,
+        InvocationCancellationHistoryDeletedResponseModel,
+        InvocationCancellationUserRequestResponseModel,
+        InvocationFailureDatasetFailedResponseModel,
+        InvocationFailureCollectionFailedResponseModel,
+        InvocationFailureJobFailedResponseModel,
+        InvocationFailureOutputNotFoundResponseModel,
+        InvocationFailureExpressionEvaluationFailedResponseModel,
+        InvocationFailureWhenNotBooleanResponseModel,
+        InvocationUnexpectedFailureResponseModel,
+        InvocationWarningWorkflowOutputNotFoundResponseModel,
     ],
     Field(discriminator="reason"),
 ]
 
 
-class GenericInvocationMessage(GenericModel, Generic[DatabaseIdT]):
-    __root__: InvocationMessageUnion[DatabaseIdT]
+class InvocationMessageResponseModel(Model):
+    __root__: InvocationMessageResponseUnion
 
     class Config:
         orm_mode = True
 
 
-InvocationMessage = InvocationMessageUnion[int]
-InvocationMessageResponseModel = GenericInvocationMessage[EncodedDatabaseIdField]
-
-
 class Creator(Model):
     class_: str = Field(..., alias="class", title="Class", description="The class representing this creator.")
     name: str = Field(..., title="Name", description="The name of the creator.")
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index c38a7b3d350..bb07e93e763 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -98,7 +98,7 @@ from galaxy.util.template import fill_template
 from galaxy.util.tool_shed.common_util import get_tool_shed_url_from_tool_shed_registry
 
 if TYPE_CHECKING:
-    from galaxy.schema.schema import InvocationMessage
+    from galaxy.schema.schema import InvocationMessageUnion
 
 log = logging.getLogger(__name__)
 
@@ -2423,12 +2423,12 @@ class DelayedWorkflowEvaluation(Exception):
 
 
 class CancelWorkflowEvaluation(Exception):
-    def __init__(self, why: "InvocationMessage"):
+    def __init__(self, why: "InvocationMessageUnion"):
         self.why = why
 
 
 class FailWorkflowEvaluation(Exception):
-    def __init__(self, why: "InvocationMessage"):
+    def __init__(self, why: "InvocationMessageUnion"):
         self.why = why
 
 

From ecb160442add110ba20bd6afd43e673f70509d59 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 12:04:10 +0100
Subject: [PATCH 152/350] Add migration for updated
 HistoryDatasetCollectionJobStateSummary

---
 .../dependencies/pinned-requirements.txt      |  1 +
 ...04_add_skipped_state_to_collection_job_.py | 70 +++++++++++++++++++
 pyproject.toml                                |  1 +
 3 files changed, 72 insertions(+)
 create mode 100644 lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py

diff --git a/lib/galaxy/dependencies/pinned-requirements.txt b/lib/galaxy/dependencies/pinned-requirements.txt
index d369ca9eb30..3bd0f4ea87b 100644
--- a/lib/galaxy/dependencies/pinned-requirements.txt
+++ b/lib/galaxy/dependencies/pinned-requirements.txt
@@ -6,6 +6,7 @@ aiofiles==22.1.0 ; python_version >= "3.7" and python_version < "3.11"
 aiohttp==3.8.3 ; python_version >= "3.7" and python_version < "3.11"
 aiosignal==1.3.1 ; python_version >= "3.7" and python_version < "3.11"
 alembic==1.9.1 ; python_version >= "3.7" and python_version < "3.11"
+alembic_utils==0.7.8 ; python_version >= "3.7" and python_version < "3.11"
 amqp==5.1.1 ; python_version >= "3.7" and python_version < "3.11"
 anyio==3.6.2 ; python_version >= "3.7" and python_version < "3.11"
 apispec==6.0.2 ; python_version >= "3.7" and python_version < "3.11"
diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
new file mode 100644
index 00000000000..86fd5053e49
--- /dev/null
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
@@ -0,0 +1,70 @@
+"""Add skipped state to collection_job_state_summary_view
+
+Revision ID: c39f1de47a04
+Revises: 3100452fa030
+Create Date: 2023-01-16 11:53:59.783836
+
+"""
+from alembic import op
+from alembic_utils.pg_view import PGView
+
+from galaxy.model.view import HistoryDatasetCollectionJobStateSummary
+
+# revision identifiers, used by Alembic.
+revision = "c39f1de47a04"
+down_revision = "3100452fa030"
+branch_labels = None
+depends_on = None
+
+PREVIOUS_AGGREGATE_QUERY = """
+SELECT
+    hdca_id,
+    SUM(CASE WHEN state = 'new' THEN 1 ELSE 0 END) AS new,
+    SUM(CASE WHEN state = 'resubmitted' THEN 1 ELSE 0 END) AS resubmitted,
+    SUM(CASE WHEN state = 'waiting' THEN 1 ELSE 0 END) AS waiting,
+    SUM(CASE WHEN state = 'queued' THEN 1 ELSE 0 END) AS queued,
+    SUM(CASE WHEN state = 'running' THEN 1 ELSE 0 END) AS running,
+    SUM(CASE WHEN state = 'ok' THEN 1 ELSE 0 END) AS ok,
+    SUM(CASE WHEN state = 'error' THEN 1 ELSE 0 END) AS error,
+    SUM(CASE WHEN state = 'failed' THEN 1 ELSE 0 END) AS failed,
+    SUM(CASE WHEN state = 'paused' THEN 1 ELSE 0 END) AS paused,
+    SUM(CASE WHEN state = 'deleted' THEN 1 ELSE 0 END) AS deleted,
+    SUM(CASE WHEN state = 'deleted_new' THEN 1 ELSE 0 END) AS deleted_new,
+    SUM(CASE WHEN state = 'upload' THEN 1 ELSE 0 END) AS upload,
+    SUM(CASE WHEN job_id IS NOT NULL THEN 1 ELSE 0 END) AS all_jobs
+FROM (
+    SELECT hdca.id AS hdca_id, job.id AS job_id, job.state as state
+    FROM history_dataset_collection_association hdca
+    LEFT JOIN implicit_collection_jobs icj
+        ON icj.id = hdca.implicit_collection_jobs_id
+    LEFT JOIN implicit_collection_jobs_job_association icjja
+        ON icj.id = icjja.implicit_collection_jobs_id
+    LEFT JOIN job
+        ON icjja.job_id = job.id
+
+    UNION
+
+    SELECT hdca.id AS hdca_id, job.id AS job_id, job.state AS state
+    FROM history_dataset_collection_association hdca
+    LEFT JOIN job
+        ON hdca.job_id = job.id
+) jobstates
+GROUP BY jobstates.hdca_id
+"""
+
+
+def upgrade():
+    public_collection_job_state_summary_view = PGView(
+        schema="public",
+        signature="collection_job_state_summary_view",
+        definition=HistoryDatasetCollectionJobStateSummary.aggregate_state_query,
+    )
+    # op.replace_entity comes from alembic_utils plugin
+    op.replace_entity(public_collection_job_state_summary_view)  # type: ignore[attr-defined]
+
+
+def downgrade():
+    public_collection_job_state_summary_view = PGView(
+        schema="public", signature="collection_job_state_summary_view", definition=PREVIOUS_AGGREGATE_QUERY
+    )
+    op.replace_entity(public_collection_job_state_summary_view)  # type: ignore[attr-defined]
diff --git a/pyproject.toml b/pyproject.toml
index b1e7c1f6e1a..d8b3484a6e4 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -30,6 +30,7 @@ url = "https://wheels.galaxyproject.org/simple"
 a2wsgi = "*"
 aiofiles = "*"
 alembic = "*"
+alembic_utils = "*"
 apispec = "*"
 Babel = "*"
 bdbag = ">=1.6.3"

From 7705038b6c1e659982126679189be7fe7815fea5 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 12:19:48 +0100
Subject: [PATCH 153/350] Move InvocationMessage models to own file

---
 lib/galaxy/model/__init__.py                  |   2 +-
 lib/galaxy/schema/invocation.py               | 213 ++++++++++++++++++
 lib/galaxy/schema/schema.py                   | 196 ----------------
 lib/galaxy/webapps/galaxy/api/workflows.py    |   2 +-
 .../webapps/galaxy/services/invocations.py    |   2 +-
 lib/galaxy/workflow/modules.py                |   2 +-
 6 files changed, 217 insertions(+), 200 deletions(-)
 create mode 100644 lib/galaxy/schema/invocation.py

diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index f3b4ffd6a6d..29af9c116d7 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -153,7 +153,7 @@ from galaxy.util.json import safe_loads
 from galaxy.util.sanitize_html import sanitize_html
 
 if TYPE_CHECKING:
-    from galaxy.schema.schema import InvocationMessageUnion
+    from galaxy.schema.invocation import InvocationMessageUnion
 
 log = logging.getLogger(__name__)
 
diff --git a/lib/galaxy/schema/invocation.py b/lib/galaxy/schema/invocation.py
new file mode 100644
index 00000000000..d7db228c3a2
--- /dev/null
+++ b/lib/galaxy/schema/invocation.py
@@ -0,0 +1,213 @@
+from enum import Enum
+from typing import (
+    Any,
+    Generic,
+    Optional,
+    TypeVar,
+    Union,
+)
+
+from pydantic import (
+    BaseModel,
+    Field,
+)
+from pydantic.generics import GenericModel
+from pydantic.utils import GetterDict
+from typing_extensions import (
+    Annotated,
+    Literal,
+)
+
+from galaxy.schema.fields import EncodedDatabaseIdField
+
+
+class WarningReason(str, Enum):
+    workflow_output_not_found = "workflow_output_not_found"
+
+
+class FailureReason(str, Enum):
+    dataset_failed = "dataset_failed"
+    collection_failed = "collection_failed"
+    job_failed = "job_failed"
+    output_not_found = "output_not_found"
+    expression_evaluation_failed = "expression_evaluation_failed"
+    when_not_boolean = "when_not_boolean"
+    unexpected_failure = "unexpected_failure"
+
+
+class CancelReason(str, Enum):
+    """Possible reasons for a cancelled workflow."""
+
+    history_deleted = "history_deleted"
+    user_request = "user_request"
+    cancelled_on_review = "cancelled_on_review"
+
+
+DatabaseIdT = TypeVar("DatabaseIdT")
+
+
+class StepOrderIndexGetter(GetterDict):
+    def get(self, key: Any, default: Any = None) -> Any:
+
+        # Fetch the order_index when serializing for the API,
+        # which makes much more sense when pointing to steps.
+        if key == "workflow_step_id":
+            return self._obj.workflow_step.order_index
+        elif key == "dependent_workflow_step_id":
+            return self._obj.dependent_workflow_step.order_index
+
+        return super().get(key, default)
+
+
+class InvocationMessageBase(GenericModel):
+    reason: Union[CancelReason, FailureReason, WarningReason]
+
+    class Config:
+        orm_mode = True
+        getter_dict = StepOrderIndexGetter
+
+
+class GenericInvocationCancellationReviewFailed(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[CancelReason.cancelled_on_review]
+    workflow_step_id: int = Field(..., description="Workflow step id of paused step that did not pass review.")
+
+
+class GenericInvocationCancellationHistoryDeleted(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[CancelReason.history_deleted]
+    history_id: DatabaseIdT = Field(..., title="History ID", description="History ID of history that was deleted.")
+
+
+class GenericInvocationCancellationUserRequest(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[CancelReason.user_request]
+
+
+class InvocationFailureMessageBase(InvocationMessageBase, Generic[DatabaseIdT]):
+    workflow_step_id: int = Field(..., description="Workflow step id of step that failed.")
+
+
+class GenericInvocationFailureDatasetFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.dataset_failed]
+    hda_id: DatabaseIdT = Field(
+        ..., title="HistoryDatasetAssociation ID", description="HistoryDatasetAssociation ID that relates to failure."
+    )
+    dependent_workflow_step_id: Optional[int] = Field(None, description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureCollectionFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.collection_failed]
+    hdca_id: DatabaseIdT = Field(
+        None,
+        title="HistoryDatasetCollectionAssociation ID",
+        description="HistoryDatasetCollectionAssociation ID that relates to failure.",
+    )
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureJobFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.job_failed]
+    job_id: DatabaseIdT = Field(None, title="Job ID", description="Job ID that relates to failure.")
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureOutputNotFound(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.output_not_found]
+    output_name: str = Field(..., title="Tool or module output name that was referenced but not produced")
+    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
+
+
+class GenericInvocationFailureExpressionEvaluationFailed(
+    InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]
+):
+    reason: Literal[FailureReason.expression_evaluation_failed]
+    details: Optional[str] = Field(None, description="May contain details to help troubleshoot this problem.")
+
+
+class GenericInvocationFailureWhenNotBoolean(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.when_not_boolean]
+    details: str = Field(..., description="Contains details to help troubleshoot this problem.")
+
+
+class GenericInvocationUnexpectedFailure(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: Literal[FailureReason.unexpected_failure]
+    details: Optional[str] = Field(None, description="May contains details to help troubleshoot this problem.")
+
+
+class GenericInvocationWarning(InvocationMessageBase, Generic[DatabaseIdT]):
+    reason: WarningReason = Field(..., title="Failure Reason", description="Reason for warning")
+    workflow_step_id: Optional[int] = Field(None, title="Workflow step id of step that caused a warning.")
+
+
+class GenericInvocationEvaluationWarningWorkflowOutputNotFound(
+    GenericInvocationWarning[DatabaseIdT], Generic[DatabaseIdT]
+):
+    reason: Literal[WarningReason.workflow_output_not_found]
+    output_name: str = Field(
+        ..., description="Output that was designated as workflow output but that has not been found"
+    )
+
+
+InvocationCancellationReviewFailed = GenericInvocationCancellationReviewFailed[int]
+InvocationCancellationHistoryDeleted = GenericInvocationCancellationHistoryDeleted[int]
+InvocationCancellationUserRequest = GenericInvocationCancellationUserRequest[int]
+InvocationFailureDatasetFailed = GenericInvocationFailureDatasetFailed[int]
+InvocationFailureCollectionFailed = GenericInvocationFailureCollectionFailed[int]
+InvocationFailureJobFailed = GenericInvocationFailureJobFailed[int]
+InvocationFailureOutputNotFound = GenericInvocationFailureOutputNotFound[int]
+InvocationFailureExpressionEvaluationFailed = GenericInvocationFailureExpressionEvaluationFailed[int]
+InvocationFailureWhenNotBoolean = GenericInvocationFailureWhenNotBoolean[int]
+InvocationUnexpectedFailure = GenericInvocationUnexpectedFailure[int]
+InvocationWarningWorkflowOutputNotFound = GenericInvocationEvaluationWarningWorkflowOutputNotFound[int]
+
+InvocationMessageUnion = Union[
+    InvocationCancellationReviewFailed,
+    InvocationCancellationHistoryDeleted,
+    InvocationCancellationUserRequest,
+    InvocationFailureDatasetFailed,
+    InvocationFailureCollectionFailed,
+    InvocationFailureJobFailed,
+    InvocationFailureOutputNotFound,
+    InvocationFailureExpressionEvaluationFailed,
+    InvocationFailureWhenNotBoolean,
+    InvocationUnexpectedFailure,
+    InvocationWarningWorkflowOutputNotFound,
+]
+
+InvocationCancellationReviewFailedResponseModel = GenericInvocationCancellationReviewFailed[EncodedDatabaseIdField]
+InvocationCancellationHistoryDeletedResponseModel = GenericInvocationCancellationHistoryDeleted[EncodedDatabaseIdField]
+InvocationCancellationUserRequestResponseModel = GenericInvocationCancellationUserRequest[EncodedDatabaseIdField]
+InvocationFailureDatasetFailedResponseModel = GenericInvocationFailureDatasetFailed[EncodedDatabaseIdField]
+InvocationFailureCollectionFailedResponseModel = GenericInvocationFailureCollectionFailed[EncodedDatabaseIdField]
+InvocationFailureJobFailedResponseModel = GenericInvocationFailureJobFailed[EncodedDatabaseIdField]
+InvocationFailureOutputNotFoundResponseModel = GenericInvocationFailureOutputNotFound[EncodedDatabaseIdField]
+InvocationFailureExpressionEvaluationFailedResponseModel = GenericInvocationFailureExpressionEvaluationFailed[
+    EncodedDatabaseIdField
+]
+InvocationFailureWhenNotBooleanResponseModel = GenericInvocationFailureWhenNotBoolean[EncodedDatabaseIdField]
+InvocationUnexpectedFailureResponseModel = GenericInvocationUnexpectedFailure[EncodedDatabaseIdField]
+InvocationWarningWorkflowOutputNotFoundResponseModel = GenericInvocationEvaluationWarningWorkflowOutputNotFound[
+    EncodedDatabaseIdField
+]
+
+InvocationMessageResponseUnion = Annotated[
+    Union[
+        InvocationCancellationReviewFailedResponseModel,
+        InvocationCancellationHistoryDeletedResponseModel,
+        InvocationCancellationUserRequestResponseModel,
+        InvocationFailureDatasetFailedResponseModel,
+        InvocationFailureCollectionFailedResponseModel,
+        InvocationFailureJobFailedResponseModel,
+        InvocationFailureOutputNotFoundResponseModel,
+        InvocationFailureExpressionEvaluationFailedResponseModel,
+        InvocationFailureWhenNotBooleanResponseModel,
+        InvocationUnexpectedFailureResponseModel,
+        InvocationWarningWorkflowOutputNotFoundResponseModel,
+    ],
+    Field(discriminator="reason"),
+]
+
+
+class InvocationMessageResponseModel(BaseModel):
+    __root__: InvocationMessageResponseUnion
+
+    class Config:
+        orm_mode = True
diff --git a/lib/galaxy/schema/schema.py b/lib/galaxy/schema/schema.py
index ac5380c6c4a..b50faa5feb8 100644
--- a/lib/galaxy/schema/schema.py
+++ b/lib/galaxy/schema/schema.py
@@ -9,11 +9,9 @@ from enum import Enum
 from typing import (
     Any,
     Dict,
-    Generic,
     List,
     Optional,
     Set,
-    TypeVar,
     Union,
 )
 from uuid import UUID
@@ -28,8 +26,6 @@ from pydantic import (
     Json,
     UUID4,
 )
-from pydantic.generics import GenericModel
-from pydantic.utils import GetterDict
 from typing_extensions import (
     Annotated,
     Literal,
@@ -1918,198 +1914,6 @@ class SubworkflowStep(WorkflowStepBase):
     )
 
 
-class WarningReason(str, Enum):
-    workflow_output_not_found = "workflow_output_not_found"
-
-
-class FailureReason(str, Enum):
-    dataset_failed = "dataset_failed"
-    collection_failed = "collection_failed"
-    job_failed = "job_failed"
-    output_not_found = "output_not_found"
-    expression_evaluation_failed = "expression_evaluation_failed"
-    when_not_boolean = "when_not_boolean"
-    unexpected_failure = "unexpected_failure"
-
-
-class CancelReason(str, Enum):
-    """Possible reasons for a cancelled workflow."""
-
-    history_deleted = "history_deleted"
-    user_request = "user_request"
-    cancelled_on_review = "cancelled_on_review"
-
-
-DatabaseIdT = TypeVar("DatabaseIdT")
-
-
-class StepOrderIndexGetter(GetterDict):
-    def get(self, key: Any, default: Any = None) -> Any:
-
-        # Fetch the order_index when serializing for the API,
-        # which makes much more sense when pointing to steps.
-        if key == "workflow_step_id":
-            return self._obj.workflow_step.order_index
-        elif key == "dependent_workflow_step_id":
-            return self._obj.dependent_workflow_step.order_index
-
-        return super().get(key, default)
-
-
-class InvocationMessageBase(GenericModel):
-    reason: Union[CancelReason, FailureReason, WarningReason]
-
-    class Config:
-        orm_mode = True
-        getter_dict = StepOrderIndexGetter
-
-
-class GenericInvocationCancellationReviewFailed(InvocationMessageBase, Generic[DatabaseIdT]):
-    reason: Literal[CancelReason.cancelled_on_review]
-    workflow_step_id: int = Field(..., description="Workflow step id of paused step that did not pass review.")
-
-
-class GenericInvocationCancellationHistoryDeleted(InvocationMessageBase, Generic[DatabaseIdT]):
-    reason: Literal[CancelReason.history_deleted]
-    history_id: DatabaseIdT = Field(..., title="History ID", description="History ID of history that was deleted.")
-
-
-class GenericInvocationCancellationUserRequest(InvocationMessageBase, Generic[DatabaseIdT]):
-    reason: Literal[CancelReason.user_request]
-
-
-class InvocationFailureMessageBase(InvocationMessageBase, Generic[DatabaseIdT]):
-    workflow_step_id: int = Field(..., description="Workflow step id of step that failed.")
-
-
-class GenericInvocationFailureDatasetFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.dataset_failed]
-    hda_id: DatabaseIdT = Field(
-        ..., title="HistoryDatasetAssociation ID", description="HistoryDatasetAssociation ID that relates to failure."
-    )
-    dependent_workflow_step_id: Optional[int] = Field(None, description="Workflow step id of step that caused failure.")
-
-
-class GenericInvocationFailureCollectionFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.collection_failed]
-    hdca_id: DatabaseIdT = Field(
-        None,
-        title="HistoryDatasetCollectionAssociation ID",
-        description="HistoryDatasetCollectionAssociation ID that relates to failure.",
-    )
-    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
-
-
-class GenericInvocationFailureJobFailed(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.job_failed]
-    job_id: DatabaseIdT = Field(None, title="Job ID", description="Job ID that relates to failure.")
-    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
-
-
-class GenericInvocationFailureOutputNotFound(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.output_not_found]
-    output_name: str = Field(..., title="Tool or module output name that was referenced but not produced")
-    dependent_workflow_step_id: int = Field(..., description="Workflow step id of step that caused failure.")
-
-
-class GenericInvocationFailureExpressionEvaluationFailed(
-    InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]
-):
-    reason: Literal[FailureReason.expression_evaluation_failed]
-    details: Optional[str] = Field(None, description="May contain details to help troubleshoot this problem.")
-
-
-class GenericInvocationFailureWhenNotBoolean(InvocationFailureMessageBase[DatabaseIdT], Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.when_not_boolean]
-    details: str = Field(..., description="Contains details to help troubleshoot this problem.")
-
-
-class GenericInvocationUnexpectedFailure(InvocationMessageBase, Generic[DatabaseIdT]):
-    reason: Literal[FailureReason.unexpected_failure]
-    details: Optional[str] = Field(None, description="May contains details to help troubleshoot this problem.")
-
-
-class GenericInvocationWarning(InvocationMessageBase, Generic[DatabaseIdT]):
-    reason: WarningReason = Field(..., title="Failure Reason", description="Reason for warning")
-    workflow_step_id: Optional[int] = Field(None, title="Workflow step id of step that caused a warning.")
-
-
-class GenericInvocationEvaluationWarningWorkflowOutputNotFound(
-    GenericInvocationWarning[DatabaseIdT], Generic[DatabaseIdT]
-):
-    reason: Literal[WarningReason.workflow_output_not_found]
-    output_name: str = Field(
-        ..., description="Output that was designated as workflow output but that has not been found"
-    )
-
-
-InvocationCancellationReviewFailed = GenericInvocationCancellationReviewFailed[int]
-InvocationCancellationHistoryDeleted = GenericInvocationCancellationHistoryDeleted[int]
-InvocationCancellationUserRequest = GenericInvocationCancellationUserRequest[int]
-InvocationFailureDatasetFailed = GenericInvocationFailureDatasetFailed[int]
-InvocationFailureCollectionFailed = GenericInvocationFailureCollectionFailed[int]
-InvocationFailureJobFailed = GenericInvocationFailureJobFailed[int]
-InvocationFailureOutputNotFound = GenericInvocationFailureOutputNotFound[int]
-InvocationFailureExpressionEvaluationFailed = GenericInvocationFailureExpressionEvaluationFailed[int]
-InvocationFailureWhenNotBoolean = GenericInvocationFailureWhenNotBoolean[int]
-InvocationUnexpectedFailure = GenericInvocationUnexpectedFailure[int]
-InvocationWarningWorkflowOutputNotFound = GenericInvocationEvaluationWarningWorkflowOutputNotFound[int]
-
-InvocationMessageUnion = Union[
-    InvocationCancellationReviewFailed,
-    InvocationCancellationHistoryDeleted,
-    InvocationCancellationUserRequest,
-    InvocationFailureDatasetFailed,
-    InvocationFailureCollectionFailed,
-    InvocationFailureJobFailed,
-    InvocationFailureOutputNotFound,
-    InvocationFailureExpressionEvaluationFailed,
-    InvocationFailureWhenNotBoolean,
-    InvocationUnexpectedFailure,
-    InvocationWarningWorkflowOutputNotFound,
-]
-
-InvocationCancellationReviewFailedResponseModel = GenericInvocationCancellationReviewFailed[EncodedDatabaseIdField]
-InvocationCancellationHistoryDeletedResponseModel = GenericInvocationCancellationHistoryDeleted[EncodedDatabaseIdField]
-InvocationCancellationUserRequestResponseModel = GenericInvocationCancellationUserRequest[EncodedDatabaseIdField]
-InvocationFailureDatasetFailedResponseModel = GenericInvocationFailureDatasetFailed[EncodedDatabaseIdField]
-InvocationFailureCollectionFailedResponseModel = GenericInvocationFailureCollectionFailed[EncodedDatabaseIdField]
-InvocationFailureJobFailedResponseModel = GenericInvocationFailureJobFailed[EncodedDatabaseIdField]
-InvocationFailureOutputNotFoundResponseModel = GenericInvocationFailureOutputNotFound[EncodedDatabaseIdField]
-InvocationFailureExpressionEvaluationFailedResponseModel = GenericInvocationFailureExpressionEvaluationFailed[
-    EncodedDatabaseIdField
-]
-InvocationFailureWhenNotBooleanResponseModel = GenericInvocationFailureWhenNotBoolean[EncodedDatabaseIdField]
-InvocationUnexpectedFailureResponseModel = GenericInvocationUnexpectedFailure[EncodedDatabaseIdField]
-InvocationWarningWorkflowOutputNotFoundResponseModel = GenericInvocationEvaluationWarningWorkflowOutputNotFound[
-    EncodedDatabaseIdField
-]
-
-InvocationMessageResponseUnion = Annotated[
-    Union[
-        InvocationCancellationReviewFailedResponseModel,
-        InvocationCancellationHistoryDeletedResponseModel,
-        InvocationCancellationUserRequestResponseModel,
-        InvocationFailureDatasetFailedResponseModel,
-        InvocationFailureCollectionFailedResponseModel,
-        InvocationFailureJobFailedResponseModel,
-        InvocationFailureOutputNotFoundResponseModel,
-        InvocationFailureExpressionEvaluationFailedResponseModel,
-        InvocationFailureWhenNotBooleanResponseModel,
-        InvocationUnexpectedFailureResponseModel,
-        InvocationWarningWorkflowOutputNotFoundResponseModel,
-    ],
-    Field(discriminator="reason"),
-]
-
-
-class InvocationMessageResponseModel(Model):
-    __root__: InvocationMessageResponseUnion
-
-    class Config:
-        orm_mode = True
-
-
 class Creator(Model):
     class_: str = Field(..., alias="class", title="Class", description="The class representing this creator.")
     name: str = Field(..., title="Name", description="The name of the creator.")
diff --git a/lib/galaxy/webapps/galaxy/api/workflows.py b/lib/galaxy/webapps/galaxy/api/workflows.py
index 45a761e7192..48b0f9f3108 100644
--- a/lib/galaxy/webapps/galaxy/api/workflows.py
+++ b/lib/galaxy/webapps/galaxy/api/workflows.py
@@ -48,10 +48,10 @@ from galaxy.managers.workflows import (
 from galaxy.model.item_attrs import UsesAnnotations
 from galaxy.model.store import BcoExportOptions
 from galaxy.schema.fields import DecodedDatabaseIdField
+from galaxy.schema.invocation import InvocationMessageResponseModel
 from galaxy.schema.schema import (
     AsyncFile,
     AsyncTaskResultSummary,
-    InvocationMessageResponseModel,
     SetSlugPayload,
     ShareWithPayload,
     ShareWithStatus,
diff --git a/lib/galaxy/webapps/galaxy/services/invocations.py b/lib/galaxy/webapps/galaxy/services/invocations.py
index fd924add80c..44d0655a3fe 100644
--- a/lib/galaxy/webapps/galaxy/services/invocations.py
+++ b/lib/galaxy/webapps/galaxy/services/invocations.py
@@ -30,12 +30,12 @@ from galaxy.model.store import (
     get_export_store_factory,
 )
 from galaxy.schema.fields import DecodedDatabaseIdField
+from galaxy.schema.invocation import InvocationMessageResponseModel
 from galaxy.schema.schema import (
     AsyncFile,
     AsyncTaskResultSummary,
     BcoGenerationParametersMixin,
     InvocationIndexQueryPayload,
-    InvocationMessageResponseModel,
     StoreExportPayload,
     WriteStoreToPayload,
 )
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index bb07e93e763..15855c94566 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -98,7 +98,7 @@ from galaxy.util.template import fill_template
 from galaxy.util.tool_shed.common_util import get_tool_shed_url_from_tool_shed_registry
 
 if TYPE_CHECKING:
-    from galaxy.schema.schema import InvocationMessageUnion
+    from galaxy.schema.invocation import InvocationMessageUnion
 
 log = logging.getLogger(__name__)
 

From bc337ce37cf693856a1b5da91d6310246f93cdfa Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 21:55:17 +0100
Subject: [PATCH 154/350] Invocation schema import fixes

---
 lib/galaxy/managers/workflows.py | 6 ++----
 lib/galaxy/workflow/modules.py   | 2 +-
 lib/galaxy/workflow/run.py       | 2 +-
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index bee1e4fcf61..19b6a5c5bdb 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -58,10 +58,8 @@ from galaxy.model.index_filter_util import (
     text_column_filter,
 )
 from galaxy.model.item_attrs import UsesAnnotations
-from galaxy.schema.schema import (
-    InvocationCancellationUserRequest,
-    WorkflowIndexQueryPayload,
-)
+from galaxy.schema.invocation import InvocationCancellationUserRequest
+from galaxy.schema.schema import WorkflowIndexQueryPayload
 from galaxy.structured_app import MinimalManagerApp
 from galaxy.tools.parameters import (
     params_to_incoming,
diff --git a/lib/galaxy/workflow/modules.py b/lib/galaxy/workflow/modules.py
index 15855c94566..ce0445dd17b 100644
--- a/lib/galaxy/workflow/modules.py
+++ b/lib/galaxy/workflow/modules.py
@@ -38,7 +38,7 @@ from galaxy.model import (
     WorkflowStepConnection,
 )
 from galaxy.model.dataset_collections import matching
-from galaxy.schema.schema import (
+from galaxy.schema.invocation import (
     CancelReason,
     FailureReason,
     InvocationCancellationReviewFailed,
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index f5fa399f052..bccae86d7a6 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -18,7 +18,7 @@ from galaxy.model import (
     WorkflowInvocation,
     WorkflowInvocationStep,
 )
-from galaxy.schema.schema import (
+from galaxy.schema.invocation import (
     CancelReason,
     FailureReason,
     InvocationCancellationHistoryDeleted,

From 7dc0bf4b99d7b74270899daf37281f607980b064 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 21:56:17 +0100
Subject: [PATCH 155/350] Fix dependent workflow step id

---
 lib/galaxy/managers/workflows.py | 6 +++---
 lib/galaxy/workflow/run.py       | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index 19b6a5c5bdb..8604cc8dc31 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -361,11 +361,11 @@ class WorkflowsManager(sharable.SharableModelManager, deletable.DeletableManager
 
         return True
 
-    def get_invocation(self, trans, decoded_invocation_id, eager=False):
-        q = trans.sa_session.query(self.app.model.WorkflowInvocation)
+    def get_invocation(self, trans, decoded_invocation_id, eager=False) -> model.WorkflowInvocation:
+        q = trans.sa_session.query(model.WorkflowInvocation)
         if eager:
             q = q.options(
-                subqueryload(self.app.model.WorkflowInvocation.steps)
+                subqueryload(model.WorkflowInvocation.steps)
                 .joinedload("implicit_collection_jobs")
                 .joinedload("jobs")
                 .joinedload("job")
diff --git a/lib/galaxy/workflow/run.py b/lib/galaxy/workflow/run.py
index bccae86d7a6..ef447aaabb0 100644
--- a/lib/galaxy/workflow/run.py
+++ b/lib/galaxy/workflow/run.py
@@ -299,7 +299,7 @@ class WorkflowInvoker:
                         reason=FailureReason.job_failed,
                         job_id=job.id,
                         workflow_step_id=step_id,
-                        dependent_workflow_step_id=step_invocation.id,
+                        dependent_workflow_step_id=output_id,
                     )
                 )
 

From acf7a18e3ecbb18b4308c0208f172e83ddcfd2b0 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 21:59:14 +0100
Subject: [PATCH 156/350] Make workflow_step_id required for
 workflow_output_not_found warning

---
 lib/galaxy/schema/invocation.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/galaxy/schema/invocation.py b/lib/galaxy/schema/invocation.py
index d7db228c3a2..6803d2183e9 100644
--- a/lib/galaxy/schema/invocation.py
+++ b/lib/galaxy/schema/invocation.py
@@ -141,6 +141,7 @@ class GenericInvocationEvaluationWarningWorkflowOutputNotFound(
     GenericInvocationWarning[DatabaseIdT], Generic[DatabaseIdT]
 ):
     reason: Literal[WarningReason.workflow_output_not_found]
+    workflow_step_id: int = Field(..., title="Workflow step id of step that caused a warning.")
     output_name: str = Field(
         ..., description="Output that was designated as workflow output but that has not been found"
     )

From d40cd7b6aed125ae55858f210952332da100d6d7 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 12:28:34 +0100
Subject: [PATCH 157/350] Generate model for InvocationMessage

---
 .../invocationMessageModel.ts                 | 242 ++++++++++++++++++
 1 file changed, 242 insertions(+)
 create mode 100644 client/src/components/WorkflowInvocationState/invocationMessageModel.ts

diff --git a/client/src/components/WorkflowInvocationState/invocationMessageModel.ts b/client/src/components/WorkflowInvocationState/invocationMessageModel.ts
new file mode 100644
index 00000000000..7c86d43ad17
--- /dev/null
+++ b/client/src/components/WorkflowInvocationState/invocationMessageModel.ts
@@ -0,0 +1,242 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+/* This file was automatically generated from pydantic models by running pydantic2ts.
+/* Do not modify it by hand - just update the pydantic models and then re-run the script
+*/
+
+export type InvocationMessageResponseModel =
+    | GenericInvocationCancellationReviewFailedEncodedDatabaseIdField
+    | GenericInvocationCancellationHistoryDeletedEncodedDatabaseIdField
+    | GenericInvocationCancellationUserRequestEncodedDatabaseIdField
+    | GenericInvocationFailureDatasetFailedEncodedDatabaseIdField
+    | GenericInvocationFailureCollectionFailedEncodedDatabaseIdField
+    | GenericInvocationFailureJobFailedEncodedDatabaseIdField
+    | GenericInvocationFailureOutputNotFoundEncodedDatabaseIdField
+    | GenericInvocationFailureExpressionEvaluationFailedEncodedDatabaseIdField
+    | GenericInvocationFailureWhenNotBooleanEncodedDatabaseIdField
+    | GenericInvocationUnexpectedFailureEncodedDatabaseIdField
+    | GenericInvocationEvaluationWarningWorkflowOutputNotFoundEncodedDatabaseIdField;
+
+export interface GenericInvocationCancellationHistoryDeletedEncodedDatabaseIdField {
+    reason: "history_deleted";
+    /**
+     * History ID of history that was deleted.
+     */
+    history_id: string;
+}
+export interface GenericInvocationCancellationHistoryDeletedInt {
+    reason: "history_deleted";
+    /**
+     * History ID of history that was deleted.
+     */
+    history_id: number;
+}
+export interface GenericInvocationCancellationReviewFailedEncodedDatabaseIdField {
+    reason: "cancelled_on_review";
+    /**
+     * Workflow step id of paused step that did not pass review.
+     */
+    workflow_step_id: number;
+}
+export interface GenericInvocationCancellationReviewFailedInt {
+    reason: "cancelled_on_review";
+    /**
+     * Workflow step id of paused step that did not pass review.
+     */
+    workflow_step_id: number;
+}
+export interface GenericInvocationCancellationUserRequestEncodedDatabaseIdField {
+    reason: "user_request";
+}
+export interface GenericInvocationCancellationUserRequestInt {
+    reason: "user_request";
+}
+export interface GenericInvocationEvaluationWarningWorkflowOutputNotFoundEncodedDatabaseIdField {
+    reason: "workflow_output_not_found";
+    workflow_step_id: number;
+    /**
+     * Output that was designated as workflow output but that has not been found
+     */
+    output_name: string;
+}
+export interface GenericInvocationEvaluationWarningWorkflowOutputNotFoundInt {
+    reason: "workflow_output_not_found";
+    workflow_step_id: number;
+    /**
+     * Output that was designated as workflow output but that has not been found
+     */
+    output_name: string;
+}
+export interface GenericInvocationFailureCollectionFailedEncodedDatabaseIdField {
+    reason: "collection_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * HistoryDatasetCollectionAssociation ID that relates to failure.
+     */
+    hdca_id?: string;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureCollectionFailedInt {
+    reason: "collection_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * HistoryDatasetCollectionAssociation ID that relates to failure.
+     */
+    hdca_id?: number;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureDatasetFailedEncodedDatabaseIdField {
+    reason: "dataset_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * HistoryDatasetAssociation ID that relates to failure.
+     */
+    hda_id: string;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id?: number;
+}
+export interface GenericInvocationFailureDatasetFailedInt {
+    reason: "dataset_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * HistoryDatasetAssociation ID that relates to failure.
+     */
+    hda_id: number;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id?: number;
+}
+export interface GenericInvocationFailureExpressionEvaluationFailedEncodedDatabaseIdField {
+    reason: "expression_evaluation_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * May contain details to help troubleshoot this problem.
+     */
+    details?: string;
+}
+export interface GenericInvocationFailureExpressionEvaluationFailedInt {
+    reason: "expression_evaluation_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * May contain details to help troubleshoot this problem.
+     */
+    details?: string;
+}
+export interface GenericInvocationFailureJobFailedEncodedDatabaseIdField {
+    reason: "job_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * Job ID that relates to failure.
+     */
+    job_id?: string;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureJobFailedInt {
+    reason: "job_failed";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * Job ID that relates to failure.
+     */
+    job_id?: number;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureOutputNotFoundEncodedDatabaseIdField {
+    reason: "output_not_found";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    output_name: string;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureOutputNotFoundInt {
+    reason: "output_not_found";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    output_name: string;
+    /**
+     * Workflow step id of step that caused failure.
+     */
+    dependent_workflow_step_id: number;
+}
+export interface GenericInvocationFailureWhenNotBooleanEncodedDatabaseIdField {
+    reason: "when_not_boolean";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * Contains details to help troubleshoot this problem.
+     */
+    details: string;
+}
+export interface GenericInvocationFailureWhenNotBooleanInt {
+    reason: "when_not_boolean";
+    /**
+     * Workflow step id of step that failed.
+     */
+    workflow_step_id: number;
+    /**
+     * Contains details to help troubleshoot this problem.
+     */
+    details: string;
+}
+export interface GenericInvocationUnexpectedFailureEncodedDatabaseIdField {
+    reason: "unexpected_failure";
+    /**
+     * May contains details to help troubleshoot this problem.
+     */
+    details?: string;
+}
+export interface GenericInvocationUnexpectedFailureInt {
+    reason: "unexpected_failure";
+    /**
+     * May contains details to help troubleshoot this problem.
+     */
+    details?: string;
+}

From 4fe58744a43ff0d8ef89d8a44bce828e473dbb5e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 21:56:56 +0100
Subject: [PATCH 158/350] Create and use useWorkflowInstance composable

---
 .../WorkflowInvocationDetails.vue             | 17 ++------------
 client/src/composables/useWorkflowInstance.ts | 23 +++++++++++++++++++
 .../{workflowStore.js => workflowStore.ts}    | 21 ++++++++++-------
 3 files changed, 38 insertions(+), 23 deletions(-)
 create mode 100644 client/src/composables/useWorkflowInstance.ts
 rename client/src/stores/{workflowStore.js => workflowStore.ts} (65%)

diff --git a/client/src/components/WorkflowInvocationState/WorkflowInvocationDetails.vue b/client/src/components/WorkflowInvocationState/WorkflowInvocationDetails.vue
index fcf9af8baba..c8977d2b5c0 100644
--- a/client/src/components/WorkflowInvocationState/WorkflowInvocationDetails.vue
+++ b/client/src/components/WorkflowInvocationState/WorkflowInvocationDetails.vue
@@ -1,8 +1,5 @@
 <script setup>
-import { computed, onMounted } from "vue";
-
-import { useWorkflowStore } from "stores/workflowStore";
-
+import { useWorkflowInstance } from "@/composables/useWorkflowInstance";
 import ParameterStep from "./ParameterStep";
 import GenericHistoryItem from "components/History/Content/GenericItem";
 import WorkflowInvocationStep from "./WorkflowInvocationStep";
@@ -14,11 +11,7 @@ const props = defineProps({
     },
 });
 
-const workflowStore = useWorkflowStore();
-
-const workflow = computed(() => {
-    return workflowStore.workflowsByInstanceId[props.invocation.workflow_id];
-});
+const { workflow } = useWorkflowInstance(props.invocation.workflow_id);
 
 function dataInputStepLabel(key, input) {
     const invocationStep = props.invocation.steps[key];
@@ -32,12 +25,6 @@ function dataInputStepLabel(key, input) {
     }
     return label;
 }
-
-onMounted(async () => {
-    if (!workflowStore.workflowsByInstanceId[props.invocation.workflow_id]) {
-        workflowStore.fetchWorkflowForInstanceId(props.invocation.workflow_id);
-    }
-});
 </script>
 <template>
     <div v-if="invocation">
diff --git a/client/src/composables/useWorkflowInstance.ts b/client/src/composables/useWorkflowInstance.ts
new file mode 100644
index 00000000000..4e1a376397b
--- /dev/null
+++ b/client/src/composables/useWorkflowInstance.ts
@@ -0,0 +1,23 @@
+import { useWorkflowStore } from "@/stores/workflowStore";
+import { ref } from "vue";
+
+export function useWorkflowInstance(workflowId: string) {
+    const workflowStore = useWorkflowStore();
+    const workflow = ref(workflowStore.getWorkflowByInstanceId(workflowId));
+    const loading = ref(false);
+
+    async function getWorkflowInstance() {
+        if (!workflow.value) {
+            loading.value = true;
+            try {
+                await workflowStore.fetchWorkflowForInstanceId(workflowId);
+            } catch (e) {
+                loading.value = false;
+                console.error("unable to fetch workflow \n", e);
+            }
+        }
+    }
+    getWorkflowInstance();
+
+    return { workflow, loading };
+}
diff --git a/client/src/stores/workflowStore.js b/client/src/stores/workflowStore.ts
similarity index 65%
rename from client/src/stores/workflowStore.js
rename to client/src/stores/workflowStore.ts
index 5ba6400e1fe..5cf2b8b8d9d 100644
--- a/client/src/stores/workflowStore.js
+++ b/client/src/stores/workflowStore.ts
@@ -1,20 +1,25 @@
 import { defineStore } from "pinia";
 import axios from "axios";
+import type { Steps } from "@/stores/workflowStepStore";
+import { getAppRoot } from "@/onload/loadConfig";
 
-import { getAppRoot } from "onload/loadConfig";
+interface Workflow {
+    [index: string]: any;
+    steps: Steps;
+}
 
 export const useWorkflowStore = defineStore("workflowStore", {
     state: () => ({
-        workflowsByInstanceId: {},
+        workflowsByInstanceId: {} as { [index: string]: Workflow },
     }),
     getters: {
         getWorkflowByInstanceId: (state) => {
-            return (workflowId) => {
-                state.workflowsByInstanceId[workflowId];
+            return (workflowId: string) => {
+                return state.workflowsByInstanceId[workflowId];
             };
         },
         getWorkflowNameByInstanceId: (state) => {
-            return (workflowId) => {
+            return (workflowId: string) => {
                 const details = state.workflowsByInstanceId[workflowId];
                 if (details && details.name) {
                     return details.name;
@@ -24,19 +29,19 @@ export const useWorkflowStore = defineStore("workflowStore", {
             };
         },
         getStoredWorkflowIdByInstanceId: (state) => {
-            return (workflowId) => {
+            return (workflowId: string) => {
                 const storedWorkflow = state.workflowsByInstanceId[workflowId];
                 return storedWorkflow?.id;
             };
         },
     },
     actions: {
-        async fetchWorkflowForInstanceId(workflowId) {
+        async fetchWorkflowForInstanceId(workflowId: string) {
             console.debug("Fetching workflow details for", workflowId);
             const params = { instance: "true" };
             const { data } = await axios.get(`${getAppRoot()}api/workflows/${workflowId}`, { params });
             this.$patch((state) => {
-                state.workflowsByInstanceId[workflowId] = data;
+                state.workflowsByInstanceId[workflowId] = data as Workflow;
             });
         },
     },

From b10cd454a17a5f35e5c8160631b72a6ebb9d2a82 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 22:01:21 +0100
Subject: [PATCH 159/350] Fix regular workflow file upload in UI

---
 lib/galaxy/webapps/galaxy/api/workflows.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/api/workflows.py b/lib/galaxy/webapps/galaxy/api/workflows.py
index 48b0f9f3108..c4f3b0c97c0 100644
--- a/lib/galaxy/webapps/galaxy/api/workflows.py
+++ b/lib/galaxy/webapps/galaxy/api/workflows.py
@@ -237,6 +237,7 @@ class WorkflowsAPIController(
 
         """
         ways_to_create = {
+            "archive_file",
             "archive_source",
             "from_history_id",
             "from_path",
@@ -255,8 +256,8 @@ class WorkflowsAPIController(
             message = f"Only one parameter among - {', '.join(ways_to_create)} - must be specified"
             raise exceptions.RequestParameterInvalidException(message)
 
-        if "archive_source" in payload:
-            archive_source = payload["archive_source"]
+        if "archive_source" in payload or "archive_file" in payload:
+            archive_source = payload.get("archive_source")
             archive_file = payload.get("archive_file")
             archive_data = None
             if archive_source:

From 9a47b5ed26be0e7ee4ca7983bf3d1e3a5d7bdea5 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 16 Jan 2023 22:02:54 +0100
Subject: [PATCH 160/350] Add InvocationMessage component and mount in
 invocation summary tab

---
 .../InvocationMessage.vue                     | 192 ++++++++++++++++++
 .../WorkflowInvocationSummary.vue             |  14 +-
 2 files changed, 204 insertions(+), 2 deletions(-)
 create mode 100644 client/src/components/WorkflowInvocationState/InvocationMessage.vue

diff --git a/client/src/components/WorkflowInvocationState/InvocationMessage.vue b/client/src/components/WorkflowInvocationState/InvocationMessage.vue
new file mode 100644
index 00000000000..3d3efe121ca
--- /dev/null
+++ b/client/src/components/WorkflowInvocationState/InvocationMessage.vue
@@ -0,0 +1,192 @@
+<script setup lang="ts">
+import { computed } from "vue";
+import { useWorkflowInstance } from "@/composables/useWorkflowInstance";
+import type { InvocationMessageResponseModel } from "./invocationMessageModel";
+import GenericHistoryItem from "@/components/History/Content/GenericItem.vue";
+import WorkflowInvocationStep from "@/components/WorkflowInvocationState/WorkflowInvocationStep.vue";
+import JobInformation from "@/components/JobInformation/JobInformation.vue";
+
+type ReasonToLevel = {
+    history_deleted: "cancel";
+    user_request: "cancel";
+    cancelled_on_review: "cancel";
+    dataset_failed: "error";
+    collection_failed: "error";
+    job_failed: "error";
+    output_not_found: "error";
+    expression_evaluation_failed: "error";
+    when_not_boolean: "error";
+    unexpected_failure: "error";
+    workflow_output_not_found: "warning";
+};
+
+const level: ReasonToLevel = {
+    history_deleted: "cancel",
+    user_request: "cancel",
+    cancelled_on_review: "cancel",
+    dataset_failed: "error",
+    collection_failed: "error",
+    job_failed: "error",
+    output_not_found: "error",
+    expression_evaluation_failed: "error",
+    when_not_boolean: "error",
+    unexpected_failure: "error",
+    workflow_output_not_found: "warning",
+};
+
+const levelClasses = {
+    warning: "warningmessage",
+    cancel: "infomessage",
+    error: "errormessage",
+};
+
+interface Invocation {
+    workflow_id: string;
+    state: string;
+}
+
+interface InvocationMessageProps {
+    invocationMessage: InvocationMessageResponseModel;
+    invocation: Invocation;
+}
+
+const props = defineProps<InvocationMessageProps>();
+const levelClass = computed(() => levelClasses[level[props.invocationMessage.reason]]);
+
+const workflow = computed(() => {
+    if ("workflow_step_id" in props.invocationMessage) {
+        const { workflow } = useWorkflowInstance(props.invocation.workflow_id);
+        return workflow.value;
+    }
+    return undefined;
+});
+
+const workflowStep = computed(() => {
+    if ("workflow_step_id" in props.invocationMessage && workflow.value) {
+        return workflow.value.steps[props.invocationMessage.workflow_step_id];
+    }
+    return undefined;
+});
+
+const dependentWorkflowStep = computed(() => {
+    if ("dependent_workflow_step_id" in props.invocationMessage && workflow.value) {
+        const stepId = props.invocationMessage["dependent_workflow_step_id"];
+        if (stepId !== undefined) {
+            return workflow.value.steps[stepId];
+        }
+    }
+    return undefined;
+});
+
+const jobId = computed(() => "job_id" in props.invocationMessage && props.invocationMessage.job_id);
+const HdaId = computed(() => "hda_id" in props.invocationMessage && props.invocationMessage.hda_id);
+const HdcaId = computed(() => "hdca_id" in props.invocationMessage && props.invocationMessage.hdca_id);
+
+const cancelFragment = "Invocation scheduling cancelled because";
+const failFragment = "Invocation scheduling failed because ";
+const stepDescription = computed(() => {
+    const messageLevel = level[props.invocationMessage.reason];
+    if (messageLevel === "warning") {
+        return "This step caused a warning";
+    } else if (messageLevel === "cancel") {
+        return "This step canceled the invocation";
+    } else if (messageLevel === "error") {
+        return "This step failed the invocation";
+    } else {
+        throw "Unknown message level";
+    }
+});
+
+const infoString = computed(() => {
+    const invocationMessage = props.invocationMessage;
+    const reason = invocationMessage.reason;
+    if (reason === "user_request") {
+        return `${cancelFragment} user requested cancellation.`;
+    } else if (reason === "history_deleted") {
+        return `${cancelFragment} the history of the invocation was deleted.`;
+    } else if (reason === "cancelled_on_review") {
+        return `${cancelFragment} the invocation was paused at step ${
+            invocationMessage.workflow_step_id + 1
+        } and not approved.`;
+    } else if (reason === "collection_failed") {
+        return `${failFragment} step ${
+            invocationMessage.workflow_step_id + 1
+        } requires a dataset collection created by step ${
+            invocationMessage.dependent_workflow_step_id + 1
+        }, but dataset collection entered a failed state.`;
+    } else if (reason === "dataset_failed") {
+        if (
+            invocationMessage.dependent_workflow_step_id !== null &&
+            invocationMessage.dependent_workflow_step_id !== undefined
+        ) {
+            return `${failFragment} step ${invocationMessage.workflow_step_id + 1} requires a dataset created by step ${
+                invocationMessage.dependent_workflow_step_id + 1
+            }, but dataset entered a failed state.`;
+        } else {
+            return `${failFragment} step ${
+                invocationMessage.workflow_step_id + 1
+            } requires a dataset, but dataset entered a failed state.`;
+        }
+    } else if (reason === "job_failed") {
+        return `${failFragment} step ${invocationMessage.workflow_step_id + 1} depends on job(s) created in step ${
+            invocationMessage.dependent_workflow_step_id + 1
+        }, but a job for that step failed.`;
+    } else if (reason === "output_not_found") {
+        return `${failFragment} step ${invocationMessage.workflow_step_id + 1} depends on output '${
+            invocationMessage.output_name
+        }' of step ${
+            invocationMessage.dependent_workflow_step_id + 1
+        }, but this step did not produce an output of that name.`;
+    } else if (reason === "expression_evaluation_failed") {
+        return `${failFragment} step ${
+            invocationMessage.workflow_step_id + 1
+        } contains an expression that could not be evaluated.`;
+    } else if (reason === "when_not_boolean") {
+        return `${failFragment} step ${
+            invocationMessage.workflow_step_id + 1
+        } is a conditional step and the result of the when expression is not a boolean type.`;
+    } else if (reason === "unexpected_failure") {
+        return `${failFragment} an unexpected failure occurred.`;
+    } else if (reason === "workflow_output_not_found") {
+        return `Defined workflow output '${invocationMessage.output_name}' was not found in step ${
+            invocationMessage.workflow_step_id + 1
+        }.`;
+    } else {
+        return reason;
+    }
+});
+</script>
+
+<template>
+    <div>
+        <div :class="levelClass" style="text-align: center">
+            {{ infoString }}
+        </div>
+        <div v-if="dependentWorkflowStep">
+            Problem occurred at this step:
+            <workflow-invocation-step
+                :invocation="invocation"
+                :workflow="workflow"
+                :workflow-step="dependentWorkflowStep"></workflow-invocation-step>
+        </div>
+        <div v-if="workflowStep">
+            {{ stepDescription }}
+            <workflow-invocation-step
+                :invocation="invocation"
+                :workflow="workflow"
+                :workflow-step="workflowStep"></workflow-invocation-step>
+        </div>
+        <div v-if="HdaId">
+            This dataset failed:
+            <generic-history-item :item-id="HdaId" item-src="hda" />
+        </div>
+        <div v-if="HdcaId">
+            This dataset collection failed:
+            <generic-history-item :item-id="HdcaId" item-src="hdca" />
+        </div>
+        <div v-if="jobId">
+            This job failed:
+            <job-information :job_id="jobId" />
+        </div>
+    </div>
+</template>
diff --git a/client/src/components/WorkflowInvocationState/WorkflowInvocationSummary.vue b/client/src/components/WorkflowInvocationState/WorkflowInvocationSummary.vue
index 1949dc2661b..5853c90edd1 100644
--- a/client/src/components/WorkflowInvocationState/WorkflowInvocationSummary.vue
+++ b/client/src/components/WorkflowInvocationState/WorkflowInvocationSummary.vue
@@ -12,18 +12,26 @@
                     title="Download PDF" />
             </span>
         </div>
-        <div v-else>
+        <div v-else-if="!invocationSchedulingTerminal">
             <b-alert variant="info" show>
                 <LoadingSpan :message="`Waiting to complete invocation ${indexStr}`" />
             </b-alert>
             <span
-                v-if="!invocationSchedulingTerminal"
                 v-b-tooltip.hover
                 class="fa fa-times cancel-workflow-scheduling"
                 title="Cancel scheduling of workflow invocation"
                 @click="onCancel"></span>
         </div>
         <progress-bar v-if="!stepCount" note="Loading step state summary..." :loading="true" class="steps-progress" />
+        <template v-if="invocation.messages?.length">
+            <invocation-message
+                v-for="message in invocation.messages"
+                :key="message.reason"
+                class="steps-progress my-1"
+                :invocation-message="message"
+                :invocation="invocation">
+            </invocation-message>
+        </template>
         <progress-bar
             v-else-if="invocationState == 'cancelled'"
             note="Invocation scheduling cancelled - expected jobs and outputs may not be generated."
@@ -57,6 +65,7 @@ import { getRootFromIndexLink } from "onload";
 import mixin from "components/JobStates/mixin";
 import ProgressBar from "components/ProgressBar";
 import LoadingSpan from "components/LoadingSpan";
+import InvocationMessage from "@/components/WorkflowInvocationState/InvocationMessage.vue";
 
 import { mapGetters } from "vuex";
 
@@ -64,6 +73,7 @@ const getUrl = (path) => getRootFromIndexLink() + path;
 
 export default {
     components: {
+        InvocationMessage,
         ProgressBar,
         LoadingSpan,
     },

From 9ddea9237596a532a487398406b4fe38b8276e55 Mon Sep 17 00:00:00 2001
From: Nicola Soranzo <nicola.soranzo@earlham.ac.uk>
Date: Tue, 17 Jan 2023 17:40:05 +0000
Subject: [PATCH 161/350] Update lists of non-passing CWL conformance tests

for the cwl-1.0 branch.

- `dynamic_initial_workdir` and `dynamic_resreq_filesizes` now pass.
- 7 non-passing tests have been given a label upstream.
---
 scripts/cwl_conformance_to_test_cases.py | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/scripts/cwl_conformance_to_test_cases.py b/scripts/cwl_conformance_to_test_cases.py
index 44e6bb79b1e..ad63d88fbd4 100644
--- a/scripts/cwl_conformance_to_test_cases.py
+++ b/scripts/cwl_conformance_to_test_cases.py
@@ -44,8 +44,6 @@ RED_TESTS = {
         "directory_secondaryfiles",
         "docker_entrypoint",
         "dockeroutputdir",
-        "dynamic_initial_workdir",
-        "dynamic_resreq_filesizes",
         "dynamic_resreq_wf_optional_file_default",
         "dynamic_resreq_wf_optional_file_wf_default",
         "env_home_tmpdir",
@@ -102,7 +100,6 @@ RED_TESTS = {
         "directory_secondaryfiles",
         "docker_entrypoint",
         "dockeroutputdir",
-        "dynamic_resreq_filesizes",
         "dynamic_resreq_wf_optional_file_default",
         "dynamic_resreq_wf_optional_file_wf_default",
         "embedded_subworkflow",
@@ -174,13 +171,13 @@ RED_TESTS = {
         "step_input_default_value_overriden_2nd_step_noexp",
         "step_input_default_value_overriden_noexp",
         # not required
-        "225",
-        "226",
-        "233",
-        "235",
-        "236",
-        "306",
-        "307",
+        "initial_work_dir_for_null_and_arrays",
+        "initial_work_dir_for_array_dirs",
+        "illegal_symlink",
+        "modify_file_content",
+        "modify_directory_content",
+        "cond-with-defaults-1",
+        "cond-with-defaults-2",
         "all_non_null_all_null",
         "all_non_null_all_null_nojs",
         "all_non_null_multi_non_null",
@@ -209,7 +206,6 @@ RED_TESTS = {
         "directory_secondaryfiles",
         "docker_entrypoint",
         "dockeroutputdir",
-        "dynamic_resreq_filesizes",
         "dynamic_resreq_wf_optional_file_default",
         "dynamic_resreq_wf_optional_file_wf_default",
         "embedded_subworkflow",

From cd1a866714c105197f1eb4f6dc786205fb328a18 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Tue, 17 Jan 2023 13:05:58 -0500
Subject: [PATCH 162/350] Add basic test to generic element component

---
 .../History/Content/GenericElement.test.js    | 70 +++++++++++++++++++
 1 file changed, 70 insertions(+)
 create mode 100644 client/src/components/History/Content/GenericElement.test.js

diff --git a/client/src/components/History/Content/GenericElement.test.js b/client/src/components/History/Content/GenericElement.test.js
new file mode 100644
index 00000000000..99916da9e18
--- /dev/null
+++ b/client/src/components/History/Content/GenericElement.test.js
@@ -0,0 +1,70 @@
+import { mount } from "@vue/test-utils";
+import { getLocalVue } from "tests/jest/helpers";
+import GenericElement from "./GenericElement";
+
+const localVue = getLocalVue();
+
+describe("GenericElement", () => {
+    let wrapper;
+
+    beforeEach(() => {
+        wrapper = mount(GenericElement, {
+            propsData: {
+                dsc: {
+                    elements: [
+                        {
+                            element_index: 1,
+                            element_identifier: "element-1",
+                            element_type: "hda",
+                            object: {
+                                id: "item-1",
+                            },
+                        },
+                        {
+                            element_index: 2,
+                            element_identifier: "element-2",
+                            element_type: "hdca",
+                            object: {
+                                id: "item-2",
+                                collection_type: "list",
+                                element_count: 2,
+                                elements_datatypes: ["txt"],
+                                elements: [
+                                    {
+                                        element_index: 3,
+                                        element_identifier: "element-3",
+                                        element_type: "hda",
+                                        object: {
+                                            id: "item_3",
+                                        },
+                                    },
+                                    {
+                                        element_index: 4,
+                                        element_identifier: "element-4",
+                                        element_type: "hda",
+                                        object: {
+                                            id: "item_4",
+                                        },
+                                    },
+                                ],
+                            },
+                        },
+                    ],
+                },
+            },
+            localVue,
+        });
+    });
+
+    it("check basics", async () => {
+        const contentItems = wrapper.findAll(".content-item");
+        expect(contentItems.length).toBe(2);
+        expect(contentItems.at(0).attributes("data-hid")).toBe("1");
+        expect(contentItems.at(1).attributes("data-hid")).toBe("2");
+        await contentItems.at(1).find(".cursor-pointer").trigger("click");
+        const contentExpanded = wrapper.findAll(".content-item");
+        expect(contentExpanded.length).toBe(4);
+        expect(contentExpanded.at(2).attributes("data-hid")).toBe("3");
+        expect(contentExpanded.at(3).attributes("data-hid")).toBe("4");
+    });
+});

From b944bfc786b1958fc55c3220ac7307ec8c28d5ca Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 17 Jan 2023 19:18:00 +0100
Subject: [PATCH 163/350] remove the use of deprecated `root` object

---
 .../components/User/UserBeaconSettings.vue    | 25 ++++++++-----------
 .../src/components/User/UserPreferences.vue   |  1 -
 2 files changed, 11 insertions(+), 15 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index 8c024f7bc11..a6878d6d135 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -7,9 +7,9 @@
       >
       <div v-localize class="form-text text-muted">Contribute variants to Beacon</div>
       <b-modal
-          size="xl"
           id="modal-beacon"
           ref="modal"
+          size="xl"
           ok-only
           title="Manage Beacon"
           title-tag="h1"
@@ -43,7 +43,7 @@
             </div>
             <div class="fill"></div>
             <div class="no-shrink">
-              <b-button @click="optOut" variant="danger">Disable</b-button>
+              <b-button variant="danger" @click="optOut">Disable</b-button>
             </div>
           </div>
         </b-alert>
@@ -57,7 +57,7 @@
             </div>
             <div class="fill"></div>
             <div>
-              <b-button @click="optIn" variant="success">Enable</b-button>
+              <b-button variant="success" @click="optIn">Enable</b-button>
             </div>
           </div>
         </b-alert>
@@ -90,7 +90,7 @@
           <!-- Case: History exists -->
           <div v-for="beaconHistory in beaconHistories" :key="beaconHistory.id" class="flex-row history-entry"
                :class="{'gray-border-bottom': beaconHistory.id !== beaconHistories[beaconHistories.length-1].id}">
-            <div class="no-shrink" v-if="beaconHistory.contents">
+            <div v-if="beaconHistory.contents" class="no-shrink">
               History with {{ beaconHistory.contents.length }} datasets
             </div>
             <div class="fill"></div>
@@ -123,15 +123,12 @@ import store from "store"
 import axios from "axios";
 import Vue from "vue";
 import BootstrapVue from "bootstrap-vue";
+import { withPrefix } from "utils/redirect";
 
 Vue.use(BootstrapVue);
 
 export default {
   props: {
-    root: {
-      type: String,
-      required: true,
-    },
     userId: {
       type: String,
       required: true,
@@ -150,7 +147,7 @@ export default {
     },
     getBeaconHistories: function () {
       axios
-          .get(this.root + "api/histories?&keys=id,contents&q=name&qv=" + encodeURI(this.beaconHistoryName))
+          .get(withPrefix("api/histories?&keys=id,contents&q=name&qv=" + encodeURI(this.beaconHistoryName)))
           .then((response) => {
             this.beaconHistories = this.removeDeletedContents(response.data)
           })
@@ -173,9 +170,9 @@ export default {
     createBeaconHistory: function () {
       const annotation = "Variants will be collected from VCF datasets in this history if beacon sharing is activated"
       axios
-          .post(this.root + "api/histories", {name: this.beaconHistoryName})
+          .post(withPrefix("api/histories"), {name: this.beaconHistoryName})
           .then((response) => {
-            axios.put(`${this.root}api/histories/${response.data.id}`, {"annotation": annotation}).then(
+            axios.put(withPrefix(`api/histories/${response.data.id}`), {"annotation": annotation}).then(
                 () => {
                   this.getBeaconHistories()
                 }
@@ -187,7 +184,7 @@ export default {
     },
     optIn() {
       try {
-        axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": true}).then(
+        axios.post(withPrefix(`api/users/${this.userId}/beacon`), {"enabled": true}).then(
             response => {
               // TODO check response
               this.loadSettings();
@@ -203,7 +200,7 @@ export default {
     },
     optOut() {
       try {
-        axios.post(`${this.root}api/users/${this.userId}/beacon`, {"enabled": false}).then(
+        axios.post(withPrefix(`api/users/${this.userId}/beacon`), {"enabled": false}).then(
             response => {
               // TODO check response
               this.loadSettings();
@@ -219,7 +216,7 @@ export default {
     },
     async loadSettings() {
       try {
-        await axios.get(`${this.root}api/users/${this.userId}/beacon`).then(
+        await axios.get(withPrefix(`api/users/${this.userId}/beacon`)).then(
             response => {
               this.enabled = response.data.enabled;
             }
diff --git a/client/src/components/User/UserPreferences.vue b/client/src/components/User/UserPreferences.vue
index fd88bb519e1..de2a753f9d3 100644
--- a/client/src/components/User/UserPreferences.vue
+++ b/client/src/components/User/UserPreferences.vue
@@ -85,7 +85,6 @@
         <ConfigProvider v-slot="{ config }">
         <UserBeaconSettings
             v-if="config && config.enable_beacon_integration"
-            :root="root"
             :user-id="userId">>
         </UserBeaconSettings>
       </ConfigProvider>

From 02360453086d333c41b53e5d32fe087b943a760e Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 17 Jan 2023 20:17:39 +0100
Subject: [PATCH 164/350] clean up import and lint

---
 .../components/User/UserBeaconSettings.vue    | 440 +++++++++---------
 .../src/components/User/UserPreferences.vue   |  11 +-
 2 files changed, 220 insertions(+), 231 deletions(-)

diff --git a/client/src/components/User/UserBeaconSettings.vue b/client/src/components/User/UserBeaconSettings.vue
index a6878d6d135..afc1befa05e 100644
--- a/client/src/components/User/UserBeaconSettings.vue
+++ b/client/src/components/User/UserBeaconSettings.vue
@@ -1,282 +1,272 @@
 <template>
-  <b-row class="ml-3 mb-1">
-    <i class="pref-icon pt-1 fa fa-lg fa-broadcast-tower"/>
-    <div class="pref-content pr-1">
-      <a id="beacon-settings" href="javascript:void(0)"
-      ><b v-b-modal.modal-beacon v-localize>Manage Beacon</b></a
-      >
-      <div v-localize class="form-text text-muted">Contribute variants to Beacon</div>
-      <b-modal
-          id="modal-beacon"
-          ref="modal"
-          size="xl"
-          ok-only
-          title="Manage Beacon"
-          title-tag="h1"
-          @show="onOpenModal">
+    <b-row class="ml-3 mb-1">
+        <i class="pref-icon pt-1 fa fa-lg fa-broadcast-tower" />
+        <div class="pref-content pr-1">
+            <a id="beacon-settings" href="javascript:void(0)"><b v-b-modal.modal-beacon v-localize>Manage Beacon</b></a>
+            <div v-localize class="form-text text-muted">Contribute variants to Beacon</div>
+            <b-modal
+                id="modal-beacon"
+                ref="modal"
+                size="xl"
+                ok-only
+                title="Manage Beacon"
+                title-tag="h1"
+                @show="onOpenModal">
+                <!-- Explanation text-->
+                <p>
+                    The
+                    <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables
+                    safe sharing of human genetic variants.<br />
+                    <br />
+                    Galaxy lets you use the Beacon protocol to share genetic variants directly from your analysis with
+                    the scientific community in the following anonymous way:<br />
+                    <br />
+                    For participating users, we will merge variant lists to be shared into a single Beacon dataset per
+                    reference genome and make that dataset accessible through a Beacon server.<br />
+                    If someone queries the server for a specific variant that is in our Beacon dataset, the server will
+                    reply with
+                    <span class="cursive">“Yes, we have seen such a variant”</span>.<br />
+                    <br />
+                    The user that issued the query then has the possibility to contact a Galaxy server admin who can
+                    link the variant call in question to particular Galaxy users. If you are among the users that shared
+                    the variant, the admin will, in turn, contact you and ask if you want to contact the user that
+                    initiated the query to negotiate further information exchange or data access.
+                </p>
 
+                <b-alert v-if="enabled" show>
+                    <div class="flex-row space-between">
+                        <div class="no-shrink">
+                            Beacon sharing is <span class="bold">enabled</span> for your profile
+                        </div>
+                        <div class="fill"></div>
+                        <div class="no-shrink">
+                            <b-button variant="danger" @click="optOut">Disable</b-button>
+                        </div>
+                    </div>
+                </b-alert>
 
-        <!-- Explanation text-->
-        <p>
-          The <a href="https://beacon-project.io">Global Alliance for Genomics & Health Beacon Project</a> enables safe
-          sharing of human genetic variants.<br>
-          <br>
-          Galaxy lets you use the Beacon protocol to share genetic variants directly from your analysis with the
-          scientific
-          community in the following anonymous way:<br>
-          <br>
-          For participating users, we will merge variant lists to be shared into a single Beacon dataset per reference
-          genome and make that dataset accessible through a Beacon server.<br>
-          If someone queries the server for a specific variant that is in our Beacon dataset, the server will reply with
-          <span class="cursive">“Yes, we have seen such a variant”</span>.<br>
-          <br>
-          The user that issued the query then has the possibility to contact a Galaxy server admin who can link the
-          variant call in question to particular Galaxy users. If you are among the users that shared the variant, the
-          admin will, in turn, contact you and ask if you want to contact the user that initiated the query to negotiate
-          further information exchange or data access.
-        </p>
+                <!-- Setting to show when beacon is disabled -->
+                <b-alert v-if="!enabled" show>
+                    <div class="flex-row space-between">
+                        <div class="no-shrink">
+                            Beacon sharing is currently <span class="bold">disabled</span> - no data will be shared
+                        </div>
+                        <div class="fill"></div>
+                        <div>
+                            <b-button variant="success" @click="optIn">Enable</b-button>
+                        </div>
+                    </div>
+                </b-alert>
 
-        <b-alert v-if="enabled" show>
-          <div class="flex-row space-between">
-            <div class="no-shrink">
-              Beacon sharing is <span class="bold">enabled</span> for your profile
-            </div>
-            <div class="fill"></div>
-            <div class="no-shrink">
-              <b-button variant="danger" @click="optOut">Disable</b-button>
-            </div>
-          </div>
-        </b-alert>
+                <div v-if="enabled">
+                    <p>
+                        You can share data by copying VCF or VCF.bgzip files to a history called
+                        <span class="cursive gray-background">{{ beaconHistoryName }}</span
+                        >. <br />
+                        <br />
+                        The Beacon database is rebuilt periodically. Therefore, changes do not go into effect
+                        immediately. If you disable beacon sharing or remove a dataset from the beacon history, the
+                        corresponding variants will disappear from the beacon dataset during the next rebuild.
+                    </p>
+                </div>
 
+                <!-- Detailed information about the beacon history -->
+                <div v-if="enabled" class="gray-box">
+                    <!-- Case: History does not exist-->
+                    <div v-if="beaconHistories.length < 1" class="flex-row history-entry">
+                        <div class="no-shrink">No beacon history found</div>
+                        <div class="fill"></div>
+                        <div class="no-shrink">
+                            <b-button @click="createBeaconHistory">Create Beacon History</b-button>
+                        </div>
+                    </div>
 
-        <!-- Setting to show when beacon is disabled -->
-        <b-alert v-if="!enabled" show>
-          <div class="flex-row space-between">
-            <div class="no-shrink">
-              Beacon sharing is currently <span class="bold">disabled</span> - no data will be shared
-            </div>
-            <div class="fill"></div>
-            <div>
-              <b-button variant="success" @click="optIn">Enable</b-button>
-            </div>
-          </div>
-        </b-alert>
+                    <!-- Case: History exists -->
+                    <div
+                        v-for="beaconHistory in beaconHistories"
+                        :key="beaconHistory.id"
+                        class="flex-row history-entry"
+                        :class="{
+                            'gray-border-bottom': beaconHistory.id !== beaconHistories[beaconHistories.length - 1].id,
+                        }">
+                        <div v-if="beaconHistory.contents" class="no-shrink">
+                            History with {{ beaconHistory.contents.length }} datasets
+                        </div>
+                        <div class="fill"></div>
+                        <div class="no-shrink">
+                            <b-button @click="switchHistory(beaconHistory.id)">Switch to History</b-button>
+                        </div>
+                    </div>
+                </div>
 
-        <div v-if="enabled">
-          <p>
-            You can share data by copying VCF or VCF.bgzip files to a history called
-            <span class="cursive gray-background">{{ beaconHistoryName }}</span>. <br>
-            <br>
-            The Beacon database is rebuilt periodically. Therefore, changes do not go into effect immediately.
-            If you disable beacon sharing or remove a dataset from the beacon history, the corresponding variants will
-            disappear from the beacon dataset during the next rebuild.
-          </p>
+                <div v-if="enabled">
+                    <p>Datasets must fulfill the following conditions in order to be processed</p>
+                    <ul>
+                        <li>must be VCF or VCF.bgzip format</li>
+                        <li>must have a human reference assigned to it (e.g. hg19)</li>
+                        <li>must define at least one sample in a dedicated genotype column</li>
+                        <li>
+                            must contain the info field <span class="cursive">AC</span>, with the total number of
+                            alternate alleles in called genotypes
+                        </li>
+                    </ul>
+                </div>
+            </b-modal>
         </div>
-
-
-        <!-- Detailed information about the beacon history -->
-        <div v-if="enabled" class="gray-box">
-          <!-- Case: History does not exist-->
-          <div v-if="beaconHistories.length < 1" class="flex-row history-entry">
-            <div class="no-shrink">
-              No beacon history found
-            </div>
-            <div class="fill"></div>
-            <div class="no-shrink">
-              <b-button @click="createBeaconHistory">Create Beacon History</b-button>
-            </div>
-          </div>
-
-          <!-- Case: History exists -->
-          <div v-for="beaconHistory in beaconHistories" :key="beaconHistory.id" class="flex-row history-entry"
-               :class="{'gray-border-bottom': beaconHistory.id !== beaconHistories[beaconHistories.length-1].id}">
-            <div v-if="beaconHistory.contents" class="no-shrink">
-              History with {{ beaconHistory.contents.length }} datasets
-            </div>
-            <div class="fill"></div>
-            <div class="no-shrink">
-              <b-button @click="switchHistory(beaconHistory.id)">Switch to History</b-button>
-            </div>
-          </div>
-        </div>
-
-        <div v-if="enabled">
-          <p>
-            Datasets must fulfill the following conditions in order to be processed
-          </p>
-          <ul>
-            <li>must be VCF or VCF.bgzip format</li>
-            <li>must have a human reference assigned to it (e.g. hg19)</li>
-            <li>must define at least one sample in a dedicated genotype column</li>
-            <li>must contain the info field <span class="cursive">AC</span>, with the total
-              number of alternate alleles in called genotypes
-            </li>
-          </ul>
-        </div>
-      </b-modal>
-    </div>
-  </b-row>
+    </b-row>
 </template>
 
 <script>
-import store from "store"
+import store from "store";
 import axios from "axios";
-import Vue from "vue";
-import BootstrapVue from "bootstrap-vue";
-import { withPrefix } from "utils/redirect";
 
-Vue.use(BootstrapVue);
+import { withPrefix } from "utils/redirect";
+import { BAlert, BButton, BModal, BRow } from "bootstrap-vue";
 
 export default {
-  props: {
-    userId: {
-      type: String,
-      required: true,
+    components: { BButton, BModal, BRow, BAlert },
+    props: {
+        userId: {
+            type: String,
+            required: true,
+        },
     },
-  },
-  data() {
-    return {
-      enabled: false,
-      beaconHistoryName: "Beacon Export 📡",
-      beaconHistories: [{}]
-    };
-  },
-  methods: {
-    switchHistory: async function (historyId) {
-      await store.dispatch("history/setCurrentHistory", historyId);
+    data() {
+        return {
+            enabled: false,
+            beaconHistoryName: "Beacon Export 📡",
+            beaconHistories: [{}],
+        };
     },
-    getBeaconHistories: function () {
-      axios
-          .get(withPrefix("api/histories?&keys=id,contents&q=name&qv=" + encodeURI(this.beaconHistoryName)))
-          .then((response) => {
-            this.beaconHistories = this.removeDeletedContents(response.data)
-          })
-          .catch((error) => {
-            console.log(error.response)
-          });
-    },
-    removeDeletedContents: function (beaconHistories) {
-      beaconHistories.forEach(
-          beaconHistory => {
-            beaconHistory.contents.splice(0, beaconHistory.contents.length, ...beaconHistory.contents.filter(
-                dataset => {
-                  return !dataset.deleted
-                }
-            ))
-          }
-      )
-      return beaconHistories
-    },
-    createBeaconHistory: function () {
-      const annotation = "Variants will be collected from VCF datasets in this history if beacon sharing is activated"
-      axios
-          .post(withPrefix("api/histories"), {name: this.beaconHistoryName})
-          .then((response) => {
-            axios.put(withPrefix(`api/histories/${response.data.id}`), {"annotation": annotation}).then(
-                () => {
-                  this.getBeaconHistories()
-                }
-            );
-          })
-          .catch((error) => {
-            this.errorMessages.push(error.response.data.err_msg), console.log(error.response)
-          });
-    },
-    optIn() {
-      try {
-        axios.post(withPrefix(`api/users/${this.userId}/beacon`), {"enabled": true}).then(
-            response => {
-              // TODO check response
-              this.loadSettings();
-              if (this.beaconHistories.length < 1) {
-                this.createBeaconHistory()
-                this.getBeaconHistories()
-              }
+    methods: {
+        switchHistory: async function (historyId) {
+            await store.dispatch("history/setCurrentHistory", historyId);
+        },
+        getBeaconHistories: function () {
+            axios
+                .get(withPrefix("api/histories?&keys=id,contents&q=name&qv=" + encodeURI(this.beaconHistoryName)))
+                .then((response) => {
+                    this.beaconHistories = this.removeDeletedContents(response.data);
+                })
+                .catch((error) => {
+                    console.log(error.response);
+                });
+        },
+        removeDeletedContents: function (beaconHistories) {
+            beaconHistories.forEach((beaconHistory) => {
+                beaconHistory.contents.splice(
+                    0,
+                    beaconHistory.contents.length,
+                    ...beaconHistory.contents.filter((dataset) => {
+                        return !dataset.deleted;
+                    })
+                );
+            });
+            return beaconHistories;
+        },
+        createBeaconHistory: function () {
+            const annotation =
+                "Variants will be collected from VCF datasets in this history if beacon sharing is activated";
+            axios
+                .post(withPrefix("api/histories"), { name: this.beaconHistoryName })
+                .then((response) => {
+                    axios.put(withPrefix(`api/histories/${response.data.id}`), { annotation: annotation }).then(() => {
+                        this.getBeaconHistories();
+                    });
+                })
+                .catch((error) => {
+                    this.errorMessages.push(error.response.data.err_msg), console.log(error.response);
+                });
+        },
+        optIn() {
+            try {
+                axios.post(withPrefix(`api/users/${this.userId}/beacon`), { enabled: true }).then((response) => {
+                    // TODO check response
+                    this.loadSettings();
+                    if (this.beaconHistories.length < 1) {
+                        this.createBeaconHistory();
+                        this.getBeaconHistories();
+                    }
+                });
+            } catch (e) {
+                console.log(e);
             }
-        );
-      } catch (e) {
-        console.log(e);
-      }
-    },
-    optOut() {
-      try {
-        axios.post(withPrefix(`api/users/${this.userId}/beacon`), {"enabled": false}).then(
-            response => {
-              // TODO check response
-              this.loadSettings();
+        },
+        optOut() {
+            try {
+                axios.post(withPrefix(`api/users/${this.userId}/beacon`), { enabled: false }).then((response) => {
+                    // TODO check response
+                    this.loadSettings();
+                });
+            } catch (e) {
+                console.log(e);
             }
-        );
-      } catch (e) {
-        console.log(e);
-      }
-    },
-    onOpenModal() {
-      this.loadSettings();
-      this.getBeaconHistories();
-    },
-    async loadSettings() {
-      try {
-        await axios.get(withPrefix(`api/users/${this.userId}/beacon`)).then(
-            response => {
-              this.enabled = response.data.enabled;
+        },
+        onOpenModal() {
+            this.loadSettings();
+            this.getBeaconHistories();
+        },
+        async loadSettings() {
+            try {
+                await axios.get(withPrefix(`api/users/${this.userId}/beacon`)).then((response) => {
+                    this.enabled = response.data.enabled;
+                });
+            } catch (e) {
+                console.log(e);
             }
-        );
-      } catch (e) {
-        console.log(e);
-      }
+        },
     },
-  },
 };
 </script>
 
 <style scoped>
 span.bold {
-  font-weight: bold;
+    font-weight: bold;
 }
 
 .pref-icon {
-  width: 3rem;
+    width: 3rem;
 }
 
 .gray-box {
-  margin-top: 32px;
-  margin-bottom: 32px;
-  border: 1px solid #bdc6d0;
-  border-radius: 5px;
-  background-color: rgba(0, 0, 0, 0.04);
+    margin-top: 32px;
+    margin-bottom: 32px;
+    border: 1px solid #bdc6d0;
+    border-radius: 5px;
+    background-color: rgba(0, 0, 0, 0.04);
 }
 
 .flex-row {
-  display: flex;
-  flex-flow: row;
+    display: flex;
+    flex-flow: row;
 }
 
 .history-entry {
-  padding: 8px;
+    padding: 8px;
 }
 
 .gray-border-bottom {
-  border-bottom: 1px solid #bdc6d0;
+    border-bottom: 1px solid #bdc6d0;
 }
 
 .space-between {
-  justify-content: space-between;
-  align-items: center;
+    justify-content: space-between;
+    align-items: center;
 }
 
 .cursive {
-  font-style: italic;
+    font-style: italic;
 }
 
 .bold {
-  font-weight: bolder;
+    font-weight: bolder;
 }
 
 .fill {
-  width: 100%;
+    width: 100%;
 }
 
 .no-shrink {
-  flex-shrink: 0;
+    flex-shrink: 0;
 }
-</style>
\ No newline at end of file
+</style>
diff --git a/client/src/components/User/UserPreferences.vue b/client/src/components/User/UserPreferences.vue
index de2a753f9d3..09afa1e0532 100644
--- a/client/src/components/User/UserPreferences.vue
+++ b/client/src/components/User/UserPreferences.vue
@@ -83,11 +83,10 @@
                 @click="makeDataPrivate" />
         </ConfigProvider>
         <ConfigProvider v-slot="{ config }">
-        <UserBeaconSettings
-            v-if="config && config.enable_beacon_integration"
-            :user-id="userId">>
-        </UserBeaconSettings>
-      </ConfigProvider>
+            <UserBeaconSettings v-if="config && config.enable_beacon_integration" :user-id="userId"
+                >>
+            </UserBeaconSettings>
+        </ConfigProvider>
         <ConfigProvider v-slot="{ config }">
             <UserDeletion
                 v-if="config && !config.single_user && config.enable_account_interface"
@@ -131,7 +130,7 @@ export default {
         UserDeletion,
         UserPreferencesElement,
         ThemeSelector,
-        UserBeaconSettings
+        UserBeaconSettings,
     },
     props: {
         userId: {

From 83982797bc9483af789a0ead28d28479f18da79b Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 17 Jan 2023 20:23:25 +0100
Subject: [PATCH 165/350] remove unused import

---
 lib/galaxy/webapps/galaxy/api/users.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index ece8b5b9706..c65ac5bf0ad 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -5,7 +5,6 @@ import copy
 import json
 import logging
 import re
-from typing import Any
 
 from fastapi import (
     Body,

From 6723161fbf56a69e91725e261cb3128caa7bbace Mon Sep 17 00:00:00 2001
From: Benno Weiss <benno.weiss@gmail.com>
Date: Tue, 17 Jan 2023 20:30:07 +0100
Subject: [PATCH 166/350] adding api documentation

---
 client/src/schema/schema.ts            | 88 ++++++++++++++++++++++++++
 lib/galaxy/webapps/galaxy/api/users.py |  6 ++
 2 files changed, 94 insertions(+)

diff --git a/client/src/schema/schema.ts b/client/src/schema/schema.ts
index 29886efe1fb..31af5eed2a8 100644
--- a/client/src/schema/schema.ts
+++ b/client/src/schema/schema.ts
@@ -1169,6 +1169,18 @@ export interface paths {
         /** Return the user's API key with extra information. */
         get: operations["get_api_key_detailed_api_users__user_id__api_key_detailed_get"];
     };
+    "/api/users/{user_id}/beacon": {
+        /**
+         * Returns information about beacon share settings
+         * @description **Warning**: This endpoint is experimental and might change or disappear in future versions.
+         */
+        get: operations["get_beacon_api_users__user_id__beacon_get"];
+        /**
+         * Changes beacon setting
+         * @description **Warning**: This endpoint is experimental and might change or disappear in future versions.
+         */
+        post: operations["set_beacon_api_users__user_id__beacon_post"];
+    };
     "/api/version": {
         /**
          * Return Galaxy version information: major/minor version, optional extra info
@@ -7188,6 +7200,17 @@ export interface components {
              */
             url: string;
         };
+        /**
+         * UserBeaconSetting
+         * @description Base model definition with common configuration used by all derived models.
+         */
+        UserBeaconSetting: {
+            /**
+             * Enabled
+             * @description True if beacon sharing is enabled
+             */
+            enabled: boolean;
+        };
         /**
          * UserEmail
          * @description Base model definition with common configuration used by all derived models.
@@ -13916,6 +13939,71 @@ export interface operations {
             };
         };
     };
+    get_beacon_api_users__user_id__beacon_get: {
+        /**
+         * Returns information about beacon share settings
+         * @description **Warning**: This endpoint is experimental and might change or disappear in future versions.
+         */
+        parameters: {
+            /** @description The user ID that will be used to effectively make this API call. Only admins and designated users can make API calls on behalf of other users. */
+            header?: {
+                "run-as"?: string;
+            };
+            /** @description The ID of the user to get. */
+            path: {
+                user_id: string;
+            };
+        };
+        responses: {
+            /** @description Successful Response */
+            200: {
+                content: {
+                    "application/json": components["schemas"]["UserBeaconSetting"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
+    set_beacon_api_users__user_id__beacon_post: {
+        /**
+         * Changes beacon setting
+         * @description **Warning**: This endpoint is experimental and might change or disappear in future versions.
+         */
+        parameters: {
+            /** @description The user ID that will be used to effectively make this API call. Only admins and designated users can make API calls on behalf of other users. */
+            header?: {
+                "run-as"?: string;
+            };
+            /** @description The ID of the user to get. */
+            path: {
+                user_id: string;
+            };
+        };
+        requestBody: {
+            content: {
+                "application/json": components["schemas"]["UserBeaconSetting"];
+            };
+        };
+        responses: {
+            /** @description Successful Response */
+            200: {
+                content: {
+                    "application/json": components["schemas"]["UserBeaconSetting"];
+                };
+            };
+            /** @description Validation Error */
+            422: {
+                content: {
+                    "application/json": components["schemas"]["HTTPValidationError"];
+                };
+            };
+        };
+    };
     version_api_version_get: {
         /**
          * Return Galaxy version information: major/minor version, optional extra info
diff --git a/lib/galaxy/webapps/galaxy/api/users.py b/lib/galaxy/webapps/galaxy/api/users.py
index c65ac5bf0ad..8eb658c81bf 100644
--- a/lib/galaxy/webapps/galaxy/api/users.py
+++ b/lib/galaxy/webapps/galaxy/api/users.py
@@ -149,6 +149,9 @@ class FastAPIHistories:
         trans: ProvidesUserContext = DependsOnTrans,
         user_id: DecodedDatabaseIdField = UserIdPathParam,
     ) -> UserBeaconSetting:
+        """
+        **Warning**: This endpoint is experimental and might change or disappear in future versions.
+        """
         user = self.service._get_user(trans, user_id)
 
         enabled = user.preferences["beacon_enabled"] if "beacon_enabled" in user.preferences else False
@@ -165,6 +168,9 @@ class FastAPIHistories:
         user_id: DecodedDatabaseIdField = UserIdPathParam,
         payload: UserBeaconSetting = Body(...),
     ) -> UserBeaconSetting:
+        """
+        **Warning**: This endpoint is experimental and might change or disappear in future versions.
+        """
         user = self.service._get_user(trans, user_id)
 
         user.preferences["beacon_enabled"] = payload.enabled

From 1a2f45c64360cb891fd6fce3764860d920ed31b1 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Tue, 17 Jan 2023 17:10:32 -0500
Subject: [PATCH 167/350] Ensure that tool form is initialized before
 attempting updates triggered by history change emission

---
 client/src/components/Tool/ToolForm.vue | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/client/src/components/Tool/ToolForm.vue b/client/src/components/Tool/ToolForm.vue
index 2dc15868beb..ebb30af69bb 100644
--- a/client/src/components/Tool/ToolForm.vue
+++ b/client/src/components/Tool/ToolForm.vue
@@ -163,6 +163,7 @@ export default {
     data() {
         return {
             disabled: false,
+            initialized: false,
             showLoading: true,
             showForm: false,
             showEntryPoints: false,
@@ -225,7 +226,7 @@ export default {
     watch: {
         getLatestCreateTime() {
             const Galaxy = getGalaxyInstance();
-            if (Galaxy && Galaxy.currHistoryPanel) {
+            if (this.initialized && Galaxy && Galaxy.currHistoryPanel) {
                 console.debug("History change watcher detected a change.");
                 this.onHistoryChange();
             }
@@ -233,6 +234,7 @@ export default {
     },
     created() {
         this.requestTool().then(() => {
+            this.initialized = true;
             console.debug(`ToolForm::created - Started listening to history changes. [${this.id}]`);
         });
     },

From 4879cd160ac1d01c6c17e7f1c3b70f37ff78aee8 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Tue, 17 Jan 2023 17:58:11 -0500
Subject: [PATCH 168/350] Add additional typing to generic element component

---
 .../History/Content/GenericElement.vue        | 22 ++++++++++++++-----
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index a3f76e84551..7020054f170 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,14 +1,24 @@
 <script setup lang="ts">
 import Vue from "vue";
+import type { PropType } from "vue";
 import ContentItem from "./ContentItem.vue";
 import { ref } from "vue";
 
-defineProps({
-    dsc: {
-        type: Object,
-        required: true,
-    },
-});
+interface DatasetCollectionElement {
+    id: string;
+    element_index: number;
+    element_identifier: string;
+    element_type: string;
+    object: Record<string, any>;
+}
+
+interface DatasetCollection {
+    elements: DatasetCollectionElement[];
+}
+
+defineProps<{
+    dsc: DatasetCollection;
+}>();
 
 const expandCollections = ref({});
 const expandDatasets = ref({});

From 1ff68f7a296d5b79a195df3c546ed4c0e0b3a039 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Tue, 17 Jan 2023 18:04:00 -0500
Subject: [PATCH 169/350] Remove unused import, using inline instead

---
 client/src/components/History/Content/GenericElement.vue | 1 -
 1 file changed, 1 deletion(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 7020054f170..37400e30758 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,6 +1,5 @@
 <script setup lang="ts">
 import Vue from "vue";
-import type { PropType } from "vue";
 import ContentItem from "./ContentItem.vue";
 import { ref } from "vue";
 

From 45c7f2019a2187c20f595a0cae317d510a7fe403 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Wed, 18 Jan 2023 08:25:44 -0500
Subject: [PATCH 170/350] Import interface from schema as type?

---
 .../components/History/Content/GenericElement.vue | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 37400e30758..1ffa14b0e8e 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -2,21 +2,10 @@
 import Vue from "vue";
 import ContentItem from "./ContentItem.vue";
 import { ref } from "vue";
-
-interface DatasetCollectionElement {
-    id: string;
-    element_index: number;
-    element_identifier: string;
-    element_type: string;
-    object: Record<string, any>;
-}
-
-interface DatasetCollection {
-    elements: DatasetCollectionElement[];
-}
+import type { components } from "@/schema";
 
 defineProps<{
-    dsc: DatasetCollection;
+    dsc: components.DCObject;
 }>();
 
 const expandCollections = ref({});

From 897fafa85eb264d446c7d858b6da4c90892e53f0 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Wed, 18 Jan 2023 08:41:34 -0500
Subject: [PATCH 171/350] Use proptype to assign schema type for dataset
 collection object

---
 .../components/History/Content/GenericElement.vue  | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/client/src/components/History/Content/GenericElement.vue b/client/src/components/History/Content/GenericElement.vue
index 1ffa14b0e8e..d12d9f1de86 100644
--- a/client/src/components/History/Content/GenericElement.vue
+++ b/client/src/components/History/Content/GenericElement.vue
@@ -1,12 +1,16 @@
 <script setup lang="ts">
 import Vue from "vue";
-import ContentItem from "./ContentItem.vue";
-import { ref } from "vue";
+import type { PropType } from "vue";
 import type { components } from "@/schema";
+import { ref } from "vue";
+import ContentItem from "./ContentItem.vue";
 
-defineProps<{
-    dsc: components.DCObject;
-}>();
+defineProps({
+    dsc: {
+        type: Object as PropType<components["schemas"]["DCObject"]>,
+        required: true,
+    },
+});
 
 const expandCollections = ref({});
 const expandDatasets = ref({});

From af01645748e0e999bd8e5fbb7d3a77b145019998 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 18 Jan 2023 16:15:35 +0100
Subject: [PATCH 172/350] add wait utility

---
 client/src/utils/wait.ts | 5 +++++
 1 file changed, 5 insertions(+)
 create mode 100644 client/src/utils/wait.ts

diff --git a/client/src/utils/wait.ts b/client/src/utils/wait.ts
new file mode 100644
index 00000000000..9c9930b5488
--- /dev/null
+++ b/client/src/utils/wait.ts
@@ -0,0 +1,5 @@
+export function wait(milliseconds: number) {
+    return new Promise<void>((resolve) => {
+        setTimeout(() => resolve(), milliseconds);
+    });
+}

From b94a5a777c0c2b192b81ce13eb98acb7c4064bba Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 18 Jan 2023 16:16:19 +0100
Subject: [PATCH 173/350] convert fileDrop to ts and fix dragleave

---
 .../composables/{fileDrop.js => fileDrop.ts}  | 65 +++++++++++++------
 1 file changed, 45 insertions(+), 20 deletions(-)
 rename client/src/composables/{fileDrop.js => fileDrop.ts} (55%)

diff --git a/client/src/composables/fileDrop.js b/client/src/composables/fileDrop.ts
similarity index 55%
rename from client/src/composables/fileDrop.js
rename to client/src/composables/fileDrop.ts
index 76e8ed1609f..78856250aa1 100644
--- a/client/src/composables/fileDrop.js
+++ b/client/src/composables/fileDrop.ts
@@ -1,5 +1,6 @@
 import { ref, unref } from "vue";
-import { useEventListener } from "@vueuse/core";
+import { useEventListener, type MaybeComputedRef } from "@vueuse/core";
+import { wait } from "@/utils/wait";
 
 /**
  * Custom File-Drop composable
@@ -7,18 +8,26 @@ import { useEventListener } from "@vueuse/core";
  * @param onDrop callback function called when drop occurs
  * @param solo when true, only reacts if no modal is open
  */
-export function useFileDrop(dropZone, onDrop, solo) {
+export function useFileDrop(
+    dropZone: MaybeComputedRef<EventTarget | null | undefined>,
+    onDrop: (event: DragEvent) => void,
+    solo: MaybeComputedRef<boolean>
+) {
     const isFileOverDocument = ref(false);
     const isFileOverDropZone = ref(false);
 
-    const dragBlocked = ref(false);
+    // blocks drag events in this composable, to avoid drag events in unwanted situations
+    let dragBlocked = false;
+
+    // keeps track if the drag has exited, to avoid premature drag canceling
+    let hasExited = true;
 
     // Don't react to page-internal drag events
     useEventListener(
         document.body,
         "dragstart",
         () => {
-            dragBlocked.value = true;
+            dragBlocked = true;
         },
         true
     );
@@ -27,9 +36,10 @@ export function useFileDrop(dropZone, onDrop, solo) {
         document.body,
         "dragover",
         (event) => {
-            if (!dragBlocked.value) {
+            if (!dragBlocked) {
                 // prevent the browser from opening the file
                 event.preventDefault();
+                hasExited = false;
             }
         },
         true
@@ -39,40 +49,53 @@ export function useFileDrop(dropZone, onDrop, solo) {
         document.body,
         "drop",
         (event) => {
-            if (!dragBlocked.value) {
+            if (!dragBlocked) {
                 // prevent the browser from opening the file
                 event.preventDefault();
 
                 if (isFileOverDropZone.value && isFileOverDocument.value) {
-                    unref(onDrop)(event);
+                    unref(onDrop)(event as DragEvent);
                 }
             }
             isFileOverDocument.value = false;
-            dragBlocked.value = false;
+            dragBlocked = false;
+            hasExited = true;
         },
         true
     );
 
-    useEventListener(
-        document.body,
-        "dragend",
-        () => {
-            // reset on drag end
-            isFileOverDocument.value = false;
-            isFileOverDropZone.value = false;
-            dragBlocked.value = false;
-        },
-        true
-    );
+    /** Reset all variables */
+    const reset = () => {
+        isFileOverDocument.value = false;
+        isFileOverDropZone.value = false;
+        dragBlocked = false;
+        hasExited = true;
+    };
+
+    useEventListener(document.body, "dragend", reset, true);
+
+    useEventListener(document.body, "dragleave", async () => {
+        hasExited = true;
+
+        // This event may have been triggered by components
+        // which have not been properly childed to the body yet.
+        // Wait a bit, and check if hasExited is still true.
+        await wait(100);
+
+        if (hasExited) {
+            reset();
+        }
+    });
 
     useEventListener(
         document.body,
         "dragenter",
         (event) => {
             // init values if drag is possible
-            if (!dragBlocked.value && !(unref(solo) && isAnyModalOpen())) {
+            if (!dragBlocked && !(unref(solo) && isAnyModalOpen())) {
                 isFileOverDocument.value = true;
                 isFileOverDropZone.value = false;
+                hasExited = false;
 
                 event.preventDefault();
             }
@@ -90,6 +113,7 @@ export function useFileDrop(dropZone, onDrop, solo) {
         "dragenter",
         () => {
             isFileOverDropZone.value = true;
+            hasExited = false;
         },
         true
     );
@@ -99,6 +123,7 @@ export function useFileDrop(dropZone, onDrop, solo) {
         "dragleave",
         () => {
             isFileOverDropZone.value = false;
+            hasExited = false;
         },
         true
     );

From 7f4e721bde44f7582611ca65e7a13154aa4a01cd Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 18 Jan 2023 16:16:49 +0100
Subject: [PATCH 174/350] replace wait function with util

---
 client/src/components/Upload/UploadModal.vue | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/client/src/components/Upload/UploadModal.vue b/client/src/components/Upload/UploadModal.vue
index eb11bab2507..20dd79ce8ef 100644
--- a/client/src/components/Upload/UploadModal.vue
+++ b/client/src/components/Upload/UploadModal.vue
@@ -7,6 +7,7 @@ import { getAppRoot } from "onload";
 import { useCurrentUser } from "composables/user";
 import { useUserHistories } from "composables/userHistories";
 import { useConfig } from "composables/config";
+import { wait } from "@/utils/wait";
 
 const { currentUser } = useCurrentUser();
 const { currentHistoryId } = useUserHistories(currentUser);
@@ -51,12 +52,6 @@ function dismiss(result) {
     showModal.value = false;
 }
 
-function wait(milliseconds) {
-    return new Promise((resolve) => {
-        setTimeout(() => resolve(), milliseconds);
-    });
-}
-
 async function open(overrideOptions) {
     const newOptions = overrideOptions ?? {};
 

From b69cfcf343d437202fb45d4219f1e3f3a912e2c7 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 18 Jan 2023 16:17:07 +0100
Subject: [PATCH 175/350] wait for upload confirmation

---
 client/src/components/Upload/UploadModalContent.vue | 1 -
 1 file changed, 1 deletion(-)

diff --git a/client/src/components/Upload/UploadModalContent.vue b/client/src/components/Upload/UploadModalContent.vue
index e3ddd0fb8a6..188a21eea22 100644
--- a/client/src/components/Upload/UploadModalContent.vue
+++ b/client/src/components/Upload/UploadModalContent.vue
@@ -218,7 +218,6 @@ export default {
         },
         immediateUpload: function (files) {
             this.$refs.regular?.addFiles(files);
-            this.$refs.regular?._eventStart();
         },
     },
 };

From 00337ec433b460563fe22f85ecb16ff0a2be8f71 Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Wed, 18 Jan 2023 17:03:50 +0100
Subject: [PATCH 176/350] add slots and tmpdir to `samtools sort`

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 lib/galaxy/datatypes/converters/cram_to_bam_converter.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
index dd5dc11d5c3..62bc6e3b845 100644
--- a/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
+++ b/lib/galaxy/datatypes/converters/cram_to_bam_converter.xml
@@ -3,7 +3,7 @@
         <requirement type="package" version="1.16.1">samtools</requirement>
     </requirements>
     <command><![CDATA[
-        samtools sort '$input' -o '$output' --output-fmt BAM
+        samtools sort -@\${GALAXY_SLOTS:-1} -T "\${TMPDIR:-.}" -o '$output' --output-fmt BAM '$input'
     ]]></command>
     <inputs>
         <param format="cram" name="input" type="data" label="Choose CRAM file"/>

From 6808cbde43c22e57662decd10c14d2d62e1d3cbb Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 09:33:40 +0100
Subject: [PATCH 177/350] Bump requirements

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 .../datatypes/converters/interval_to_bgzip_converter.xml      | 4 ++--
 .../datatypes/converters/interval_to_tabix_converter.xml      | 2 +-
 lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml         | 2 +-
 .../datatypes/converters/vcf_bgzip_to_tabix_converter.xml     | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 67578c4fb8c..28687352445 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -8,8 +8,8 @@
         </xml>
     </macros>
     <requirements>
-        <requirement type="package" version="9.0">coreutils</requirement>
-        <requirement type="package" version="1.14">htslib</requirement>
+        <requirement type="package" version="9.1">coreutils</requirement>
+        <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
         grep -e '^"#"' -e '^track' -v '$input1' 
diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index d1a0fc41021..e22afd37aaf 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -1,7 +1,7 @@
 <tool id="CONVERTER_interval_to_tabix_0" name="Convert Interval to tabix" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="1.14">htslib</requirement>
+        <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
         ln -s '$bgzip' input.bgz &&
diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
index 7ece375289f..ed04d61b485 100644
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
+++ b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
@@ -1,7 +1,7 @@
 <tool id="tabular_to_dbnsfp" name="Convert tabular to dbnsfp" version="1.0.2" profile="16.04">
     <description></description>
     <requirements>
-        <requirement type="package" version="1.14">htslib</requirement>
+        <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
         mkdir '$dbnsfp.extra_files_path' &&
diff --git a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
index edd858cb8ef..b6bdcd0c53a 100644
--- a/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/vcf_bgzip_to_tabix_converter.xml
@@ -1,7 +1,7 @@
 <tool id="CONVERTER_vcf_bgzip_to_tabix_0" name="Convert BGZ VCF to tabix" version="1.0.2" hidden="true" profile="16.04">
     <!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
     <requirements>
-        <requirement type="package" version="1.14">htslib</requirement>
+        <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
         cp '$input1.metadata.tabix_index' '$output1' &&

From e7f82cbdb9782d9791bcb6fe6aa41372b3eabf7f Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 09:34:51 +0100
Subject: [PATCH 178/350] Fix grep for comment lines

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 .../datatypes/converters/interval_to_bgzip_converter.xml      | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 28687352445..6aa607a0dae 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -12,7 +12,8 @@
         <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
-        grep -e '^"#"' -e '^track' -v '$input1' 
+        ## Skip any lines starting with '#' and 'track'
+        grep -e '^#' -e '^track' -v '$input1' 
         |
         sort 
         #if $input1.is_of_type('vcf')
@@ -80,6 +81,7 @@
             </output>
             <assert_command>
                 <has_text text="-k1,1 -k2,2n"/>
+                <has_text_matching expression="^#" negate="true"/>
             </assert_command>
         </test>
         <test>

From c4a7d7106d69ece2031c959bb37fd8d155225104 Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 09:46:36 +0100
Subject: [PATCH 179/350] Use mkdir -p

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
index ed04d61b485..7727d107dc7 100644
--- a/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
+++ b/lib/galaxy/datatypes/converters/tabular_to_dbnsfp.xml
@@ -4,7 +4,7 @@
         <requirement type="package" version="1.16">htslib</requirement>
     </requirements>
     <command><![CDATA[
-        mkdir '$dbnsfp.extra_files_path' &&
+        mkdir -p '$dbnsfp.extra_files_path' &&
         bgzip -c '$input' > '$dbnsfp.extra_files_path/dbNSFP.gz' &&
         tabix -s 1 -b 2 -e 2 '$dbnsfp.extra_files_path/dbNSFP.gz'
     ]]></command>

From a02514598f5d88098e83be09fc9a9c8d73ba9e28 Mon Sep 17 00:00:00 2001
From: M Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 09:47:54 +0100
Subject: [PATCH 180/350] Get output from workdir

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 .../datatypes/converters/interval_to_tabix_converter.xml       | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index e22afd37aaf..b8e29495d3c 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -25,7 +25,6 @@
             exit 1;
         fi 
         &&
-        cp input.bgz.tbi '$output1' &&
         tabix -l input.bgz
     ]]></command>
     <inputs>
@@ -37,7 +36,7 @@
         <param format="bgzip" name="bgzip" type="data" label="BGZIP file"/>
     </inputs>
     <outputs>
-        <data format="tabix" name="output1"/>
+        <data format="tabix" name="output1" from_work_dir="input.bgz.tbi"/>
     </outputs>
     <tests>
         <test>

From 89b14289f6e9565b0ccd4b9bf59130f0c0fa18c0 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Thu, 19 Jan 2023 09:58:56 +0100
Subject: [PATCH 181/350] improve types

---
 client/src/composables/fileDrop.ts | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/client/src/composables/fileDrop.ts b/client/src/composables/fileDrop.ts
index 78856250aa1..0d71b92425b 100644
--- a/client/src/composables/fileDrop.ts
+++ b/client/src/composables/fileDrop.ts
@@ -1,7 +1,9 @@
-import { ref, unref } from "vue";
+import { ref, unref, type Ref } from "vue";
 import { useEventListener, type MaybeComputedRef } from "@vueuse/core";
 import { wait } from "@/utils/wait";
 
+export type FileDropHandler = (event: DragEvent) => void;
+
 /**
  * Custom File-Drop composable
  * @param dropZone Element which files should be dropped on
@@ -10,7 +12,7 @@ import { wait } from "@/utils/wait";
  */
 export function useFileDrop(
     dropZone: MaybeComputedRef<EventTarget | null | undefined>,
-    onDrop: (event: DragEvent) => void,
+    onDrop: Ref<FileDropHandler> | FileDropHandler,
     solo: MaybeComputedRef<boolean>
 ) {
     const isFileOverDocument = ref(false);
@@ -54,7 +56,8 @@ export function useFileDrop(
                 event.preventDefault();
 
                 if (isFileOverDropZone.value && isFileOverDocument.value) {
-                    unref(onDrop)(event as DragEvent);
+                    const dropHandler = unref(onDrop);
+                    dropHandler(event as DragEvent);
                 }
             }
             isFileOverDocument.value = false;

From e35b92ea10c99fa90634d49a02b682bf9b585f27 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Thu, 19 Jan 2023 10:37:33 +0100
Subject: [PATCH 182/350] increase available memory to 4gb

---
 client/package.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/package.json b/client/package.json
index 777badca0eb..1116a20ed0e 100644
--- a/client/package.json
+++ b/client/package.json
@@ -111,7 +111,7 @@
   },
   "scripts": {
     "watch": "gulp && yarn run save-build-hash && yarn run webpack-watch",
-    "serve": "NODE_ENV=development gulp && webpack serve",
+    "serve": "NODE_OPTIONS=--max-old-space-size=4096 && NODE_ENV=development gulp && webpack serve",
     "build": "NODE_ENV=development gulp && webpack && yarn run save-build-hash",
     "build-production": "NODE_ENV=production gulp && yarn run webpack-production && yarn run save-build-hash",
     "build-production-maps": "NODE_ENV=production gulp && yarn run webpack-production-maps && yarn run save-build-hash",

From 658bc49bcb47d6d54fb2bef08fc04ba05aee3fb7 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Mon, 16 Jan 2023 12:54:54 +0100
Subject: [PATCH 183/350] update prettier

---
 client/package.json | 2 +-
 client/yarn.lock    | 7 ++++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/client/package.json b/client/package.json
index 777badca0eb..2b7c854824f 100644
--- a/client/package.json
+++ b/client/package.json
@@ -173,7 +173,7 @@
     "karma-webpack": "^5.0.0",
     "mini-css-extract-plugin": "^2.5.3",
     "postcss-loader": "^7.0.1",
-    "prettier": "^2.7.1",
+    "prettier": "^2.8.3",
     "process": "^0.11.10",
     "qunit": "^2.17.2",
     "raw-loader": "^4.0.2",
diff --git a/client/yarn.lock b/client/yarn.lock
index f8301aad7da..ecccf5a872b 100644
--- a/client/yarn.lock
+++ b/client/yarn.lock
@@ -8972,11 +8972,16 @@ prelude-ls@~1.1.2:
   resolved "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.1.2.tgz"
   integrity sha512-ESF23V4SKG6lVSGZgYNpbsiaAkdab6ZgOxe52p7+Kid3W3u3bxR4Vfd/o21dmN7jSt0IwgZ4v5MUd26FEtXE9w==
 
-"prettier@^1.18.2 || ^2.0.0", prettier@^2.7.1:
+"prettier@^1.18.2 || ^2.0.0":
   version "2.7.1"
   resolved "https://registry.npmjs.org/prettier/-/prettier-2.7.1.tgz"
   integrity sha512-ujppO+MkdPqoVINuDFDRLClm7D78qbDt0/NR+wp5FqEZOoTNAjPHWj17QRhu7geIHJfcNhRk1XVQmF8Bp3ye+g==
 
+prettier@^2.8.3:
+  version "2.8.3"
+  resolved "https://registry.yarnpkg.com/prettier/-/prettier-2.8.3.tgz#ab697b1d3dd46fb4626fbe2f543afe0cc98d8632"
+  integrity sha512-tJ/oJ4amDihPoufT5sM0Z1SKEuKay8LfVAMlbbhnnkvt6BUserZylqo2PN+p9KeljLr0OHa2rXHU1T8reeoTrw==
+
 pretty-bytes@^6.0.0:
   version "6.0.0"
   resolved "https://registry.npmjs.org/pretty-bytes/-/pretty-bytes-6.0.0.tgz"

From c3233c33a5e8c5ae22c83cadb14fe64a66170053 Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Mon, 16 Jan 2023 14:13:06 +0100
Subject: [PATCH 184/350] run prettier update pre-commit hook

---
 .pre-commit-config.yaml.sample | 4 +++-
 client/src/mvc/ui/ui-modal.js  | 5 +----
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/.pre-commit-config.yaml.sample b/.pre-commit-config.yaml.sample
index 0523e68b212..8de06e00314 100644
--- a/.pre-commit-config.yaml.sample
+++ b/.pre-commit-config.yaml.sample
@@ -8,11 +8,13 @@ repos:
     hooks:
     - id: flake8
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v2.6.0 # Use the sha or tag you want to point at
+    rev: v2.7.1 # Use the sha or tag you want to point at
     hooks:
       - id: prettier
         types: [file]
         types_or: [javascript, jsx, ts, tsx, vue]
+        additional_dependencies:
+          - prettier@2.8.3 # Workaround. See https://github.com/pre-commit/mirrors-prettier/issues/29
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.3.0  # Use the ref you want to point at
     hooks:
diff --git a/client/src/mvc/ui/ui-modal.js b/client/src/mvc/ui/ui-modal.js
index e36f52e199d..cae8e5eb341 100644
--- a/client/src/mvc/ui/ui-modal.js
+++ b/client/src/mvc/ui/ui-modal.js
@@ -108,10 +108,7 @@ export var View = Backbone.View.extend({
         if (this.options.buttons) {
             var counter = 0;
             $.each(this.options.buttons, (name, callback) => {
-                var $button = $("<button/>")
-                    .attr("id", `button-${counter++}`)
-                    .text(name)
-                    .click(callback);
+                var $button = $("<button/>").attr("id", `button-${counter++}`).text(name).click(callback);
                 self.$buttons.append($button).append("&nbsp;");
                 self.buttonList[name] = $button;
             });

From 8d3beb3757821295cd7e996b69d7751d783b010a Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 11:36:12 +0100
Subject: [PATCH 185/350] cnt

---
 lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
index b8e29495d3c..2f94c32737c 100644
--- a/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_tabix_converter.xml
@@ -99,7 +99,7 @@
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="tabix">
                 <assert_contents>
-                    <has_size value="148"/>
+                    <has_size value="143"/>
                 </assert_contents>
             </output>
             <assert_command>

From 553e7a051dcb8fe389ccf6db8236a006cf491049 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 11:37:36 +0100
Subject: [PATCH 186/350] fix test

---
 .../converters/interval_to_bgzip_converter.xml         | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 6aa607a0dae..f3de9ec5035 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -4,6 +4,7 @@
         <xml name="assert_size" tokens="value" token_delta="10">
             <assert_contents>
                 <has_size value="@VALUE@" delta="@DELTA@"/>
+                <yield/>
             </assert_contents>
         </xml>
     </macros>
@@ -49,7 +50,9 @@
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
             <output name="output1" ftype="bgzip">
-                <expand macro="assert_size" value="299"/>
+                <expand macro="assert_size" value="143">
+                    <has_text_matching expression="^#" negate="true"/>
+                </expand>
             </output>
             <assert_command>
                 <has_text text="-k1,1 -k2,2n -k3,3n"/>
@@ -77,11 +80,12 @@
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
-                <expand macro="assert_size" value="707"/>
+                <expand macro="assert_size" value="322">
+                    <has_text_matching expression="^#" negate="true"/>
+                </expand>
             </output>
             <assert_command>
                 <has_text text="-k1,1 -k2,2n"/>
-                <has_text_matching expression="^#" negate="true"/>
             </assert_command>
         </test>
         <test>

From 47687c773fb78474e7fc8b27cb813b60494ae173 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 13:15:57 +0100
Subject: [PATCH 187/350] update test sizes

---
 .../datatypes/converters/interval_to_bgzip_converter.xml      | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index f3de9ec5035..335da146ae4 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -50,7 +50,7 @@
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
             <output name="output1" ftype="bgzip">
-                <expand macro="assert_size" value="143">
+                <expand macro="assert_size" value="299">
                     <has_text_matching expression="^#" negate="true"/>
                 </expand>
             </output>
@@ -80,7 +80,7 @@
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
-                <expand macro="assert_size" value="322">
+                <expand macro="assert_size" value="707">
                     <has_text_matching expression="^#" negate="true"/>
                 </expand>
             </output>

From 9e97b40c77264b56177d314d48bfbac7be4629b6 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 15:32:46 +0100
Subject: [PATCH 188/350] Revert "update test sizes"

This reverts commit 47687c773fb78474e7fc8b27cb813b60494ae173.
---
 .../datatypes/converters/interval_to_bgzip_converter.xml      | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 335da146ae4..f3de9ec5035 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -50,7 +50,7 @@
         <test>
             <param name="input1" ftype="encodepeak" value="encode.broad.peak"/>
             <output name="output1" ftype="bgzip">
-                <expand macro="assert_size" value="299">
+                <expand macro="assert_size" value="143">
                     <has_text_matching expression="^#" negate="true"/>
                 </expand>
             </output>
@@ -80,7 +80,7 @@
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
-                <expand macro="assert_size" value="707">
+                <expand macro="assert_size" value="322">
                     <has_text_matching expression="^#" negate="true"/>
                 </expand>
             </output>

From ddbd29c71536f192d04df99edf264433cf168236 Mon Sep 17 00:00:00 2001
From: Yvan Le Bras <yvan.le-bras@mnhn.fr>
Date: Thu, 19 Jan 2023 16:45:13 +0100
Subject: [PATCH 189/350] Add ecology type section + hdr and bil datatypes

---
 lib/galaxy/config/sample/datatypes_conf.xml.sample | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/config/sample/datatypes_conf.xml.sample b/lib/galaxy/config/sample/datatypes_conf.xml.sample
index 7392118b503..0fda080f64a 100644
--- a/lib/galaxy/config/sample/datatypes_conf.xml.sample
+++ b/lib/galaxy/config/sample/datatypes_conf.xml.sample
@@ -414,7 +414,6 @@
     </datatype>
     <datatype extension="scf" type="galaxy.datatypes.binary:Scf" mimetype="application/octet-stream" display_in_upload="true" description="A binary sequence file in 'scf' format with a '.scf' file extension.  You must manually select this 'File Format' when uploading the file." description_url="https://wiki.galaxyproject.org/Learn/Datatypes#Scf"/>
     <datatype extension="sequences" type="galaxy.datatypes.assembly:Sequences" display_in_upload="false"/>
-    <datatype extension="shp" type="galaxy.datatypes.gis:Shapefile" mimetype="application/octet-stream" display_in_upload="true"/>
     <datatype extension="snpeffdb" type="galaxy.datatypes.text:SnpEffDb" display_in_upload="true"/>
     <datatype extension="snpsiftdbnsfp" type="galaxy.datatypes.text:SnpSiftDbNSFP" display_in_upload="true"/>
     <datatype extension="dbnsfp.tabular" type="galaxy.datatypes.tabular:Tabular" subclass="true" display_in_upload="true">
@@ -933,6 +932,10 @@
     <datatype extension="castep" type="galaxy.datatypes.text:Castep" display_in_upload="true"/>
     <datatype extension="param" type="galaxy.datatypes.text:Param" display_in_upload="true"/>
     <datatype extension="den_fmt" type="galaxy.datatypes.text:FormattedDensity" display_in_upload="true"/>
+    <!-- ECOLOGY types -->
+    <datatype extension="bil" type="galaxy.datatypes.binary:Binary" mimetype="application/octet-stream" display_in_upload="true" subclass="true"/>
+    <datatype extension="hdr" type="galaxy.datatypes.data:Text" mimetype="text/html" display_in_upload="true" subclass="true"/>
+    <datatype extension="shp" type="galaxy.datatypes.gis:Shapefile" mimetype="application/octet-stream" display_in_upload="true"/>
   </registration>
   <sniffers>
     <!--

From 2b9292d243ab90f7b32a5e9598efb57e248a842e Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 17:02:52 +0100
Subject: [PATCH 190/350] remove one output diff comparison

and add n lines in addition
---
 .../datatypes/converters/interval_to_bgzip_converter.xml       | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index f3de9ec5035..75a48c574f2 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -79,8 +79,9 @@
         </test>
         <test>
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
-            <output name="output1" ftype="bgzip" value="bgzip_to_maf_in.bgzip" decompress="true">
+            <output name="output1" ftype="bgzip" decompress="true">
                 <expand macro="assert_size" value="322">
+                    <has_n_lines n="3"/>
                     <has_text_matching expression="^#" negate="true"/>
                 </expand>
             </output>

From 8fd4cc7d3eabd62c1c7e867f81f27db28c8f84cd Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Thu, 19 Jan 2023 17:04:29 +0100
Subject: [PATCH 191/350] doc accept_default as deprecated

when `default_value` was deprecated this rendered the semantics
of this attribute pretty nonsensical. So I'm documenting it and
marking it as deprecated (i.e. do not use it anymore).

- before it might have been: take `default_value` if no `value` is given
  and 1 if no `default_value` is set
- now it is take `value` if no `value` is given and 1 if no `value` is set
  which is equiv to take 1 of no `value` is given. There are better ways
  to do this, e.g. just set a default of 1 for the `value` also the
  implicit default of 1 is also intransparent to the user...
---
 lib/galaxy/tool_util/xsd/galaxy.xsd | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/tool_util/xsd/galaxy.xsd b/lib/galaxy/tool_util/xsd/galaxy.xsd
index 0a64ccde38c..4a65271cf75 100644
--- a/lib/galaxy/tool_util/xsd/galaxy.xsd
+++ b/lib/galaxy/tool_util/xsd/galaxy.xsd
@@ -3459,7 +3459,11 @@ or ``select``.
         </xs:attribute>
         <xs:attribute name="accept_default" type="PermissiveBoolean">
           <xs:annotation>
-            <xs:documentation xml:lang="en"></xs:documentation>
+            <xs:documentation xml:lang="en"><![CDATA[
+Deprecated. Take the value given by ``default_value`` (or ``value``) and ``1``
+if no ``value`` is given. Applies to ``data_column`` and ``group_tag``
+parameters.
+            ]]></xs:documentation>
           </xs:annotation>
         </xs:attribute>
         <xs:attribute name="refresh_on_change" type="PermissiveBoolean">

From 43866420b231dd42f731f9ef9326f7c9363d3565 Mon Sep 17 00:00:00 2001
From: Yvan Le Bras <yvan.le-bras@mnhn.fr>
Date: Thu, 19 Jan 2023 17:05:41 +0100
Subject: [PATCH 192/350] texct/html => text/plain

---
 lib/galaxy/config/sample/datatypes_conf.xml.sample | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/config/sample/datatypes_conf.xml.sample b/lib/galaxy/config/sample/datatypes_conf.xml.sample
index 0fda080f64a..f5fa6d505ae 100644
--- a/lib/galaxy/config/sample/datatypes_conf.xml.sample
+++ b/lib/galaxy/config/sample/datatypes_conf.xml.sample
@@ -934,7 +934,7 @@
     <datatype extension="den_fmt" type="galaxy.datatypes.text:FormattedDensity" display_in_upload="true"/>
     <!-- ECOLOGY types -->
     <datatype extension="bil" type="galaxy.datatypes.binary:Binary" mimetype="application/octet-stream" display_in_upload="true" subclass="true"/>
-    <datatype extension="hdr" type="galaxy.datatypes.data:Text" mimetype="text/html" display_in_upload="true" subclass="true"/>
+    <datatype extension="hdr" type="galaxy.datatypes.data:Text" mimetype="text/plain" display_in_upload="true" subclass="true"/>
     <datatype extension="shp" type="galaxy.datatypes.gis:Shapefile" mimetype="application/octet-stream" display_in_upload="true"/>
   </registration>
   <sniffers>

From 875f605fd3b18671c581c052eb8d44d90b8981c1 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 14:25:33 -0500
Subject: [PATCH 193/350] Fix appendVueComponent to just use plain Elements, no
 more jquery

---
 client/src/mvc/visualization/chart/views/groups.js   | 2 +-
 client/src/mvc/visualization/chart/views/settings.js | 2 +-
 client/src/utils/mountVueComponent.js                | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/client/src/mvc/visualization/chart/views/groups.js b/client/src/mvc/visualization/chart/views/groups.js
index 8fdaafdaa9c..750bf677d76 100644
--- a/client/src/mvc/visualization/chart/views/groups.js
+++ b/client/src/mvc/visualization/chart/views/groups.js
@@ -75,7 +75,7 @@ var GroupView = Backbone.View.extend({
                             params[name] = input.value;
                         });
                         self.redraw(params);
-                        const instance = appendVueComponent(self.$el, FormDisplay, {
+                        const instance = appendVueComponent(self.el, FormDisplay, {
                             inputs: inputs,
                         });
                         instance.$on("onChange", (data) => {
diff --git a/client/src/mvc/visualization/chart/views/settings.js b/client/src/mvc/visualization/chart/views/settings.js
index db0475bebdc..d7ef7a4be37 100644
--- a/client/src/mvc/visualization/chart/views/settings.js
+++ b/client/src/mvc/visualization/chart/views/settings.js
@@ -27,7 +27,7 @@ export default Backbone.View.extend({
                     self.chart.settings.set(name, input.value);
                 }
             });
-            const instance = appendVueComponent(this.$el, FormDisplay, {
+            const instance = appendVueComponent(this.el, FormDisplay, {
                 inputs: inputs,
             });
             instance.$on("onChange", (data) => {
diff --git a/client/src/utils/mountVueComponent.js b/client/src/utils/mountVueComponent.js
index 02efe8e2e5b..bee021432a5 100644
--- a/client/src/utils/mountVueComponent.js
+++ b/client/src/utils/mountVueComponent.js
@@ -32,10 +32,10 @@ export const mountVueComponent = (ComponentDefinition) => {
     return (propsData, el) => new component({ store, propsData, el });
 };
 
-export const appendVueComponent = ($el, ComponentDefinition, propsData = {}) => {
+export const appendVueComponent = (el, ComponentDefinition, propsData = {}) => {
     // TODO:  this doesn't append, it wipes out the element and replaces contents?
     const container = document.createElement("div");
-    $el.replaceChildren(container);
+    el.replaceChildren(container);
     const component = Vue.extend(ComponentDefinition);
     const mountFn = (propsData, el) => new component({ propsData, el });
     return mountFn(propsData, container);

From c979e21167d3864abcc87e9279d35219984e1e69 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 14:27:03 -0500
Subject: [PATCH 194/350] Rename appendVueComponent to be more accurate

---
 client/src/mvc/dataset/data.js                       | 4 ++--
 client/src/mvc/visualization/chart/views/groups.js   | 4 ++--
 client/src/mvc/visualization/chart/views/settings.js | 4 ++--
 client/src/utils/mountVueComponent.js                | 3 +--
 4 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/client/src/mvc/dataset/data.js b/client/src/mvc/dataset/data.js
index 2705f3a6960..78cadb2c434 100644
--- a/client/src/mvc/dataset/data.js
+++ b/client/src/mvc/dataset/data.js
@@ -3,7 +3,7 @@ import Backbone from "backbone";
 import { getAppRoot } from "onload/loadConfig";
 
 //temporary
-import { appendVueComponent } from "utils/mountVueComponent";
+import { replaceChildrenWithComponent } from "utils/mountVueComponent";
 import TabularChunkedView from "components/Visualizations/Tabular/TabularChunkedView.vue";
 
 /**
@@ -72,5 +72,5 @@ export var DatasetCollection = Backbone.Collection.extend({
 
 export const createTabularDatasetChunkedView = (options) => {
     // We'll always have a parent_elt in options, so create a div and insert it into that.
-    return appendVueComponent(options.parent_elt, TabularChunkedView, { options });
+    return replaceChildrenWithComponent(options.parent_elt, TabularChunkedView, { options });
 };
diff --git a/client/src/mvc/visualization/chart/views/groups.js b/client/src/mvc/visualization/chart/views/groups.js
index 750bf677d76..150e13ea2b5 100644
--- a/client/src/mvc/visualization/chart/views/groups.js
+++ b/client/src/mvc/visualization/chart/views/groups.js
@@ -8,7 +8,7 @@ import Utils from "utils/utils";
 import Repeat from "./repeat";
 import { visitInputs } from "components/Form/utilities";
 import FormDisplay from "components/Form/FormDisplay";
-import { appendVueComponent } from "utils/mountVueComponent";
+import { replaceChildrenWithComponent } from "utils/mountVueComponent";
 
 var GroupView = Backbone.View.extend({
     initialize: function (app, options) {
@@ -75,7 +75,7 @@ var GroupView = Backbone.View.extend({
                             params[name] = input.value;
                         });
                         self.redraw(params);
-                        const instance = appendVueComponent(self.el, FormDisplay, {
+                        const instance = replaceChildrenWithComponent(self.el, FormDisplay, {
                             inputs: inputs,
                         });
                         instance.$on("onChange", (data) => {
diff --git a/client/src/mvc/visualization/chart/views/settings.js b/client/src/mvc/visualization/chart/views/settings.js
index d7ef7a4be37..80f6e03e042 100644
--- a/client/src/mvc/visualization/chart/views/settings.js
+++ b/client/src/mvc/visualization/chart/views/settings.js
@@ -3,7 +3,7 @@ import Backbone from "backbone";
 import Utils from "utils/utils";
 import { visitInputs } from "components/Form/utilities";
 import FormDisplay from "components/Form/FormDisplay";
-import { appendVueComponent } from "utils/mountVueComponent";
+import { replaceChildrenWithComponent } from "utils/mountVueComponent";
 
 export default Backbone.View.extend({
     initialize: function (app) {
@@ -27,7 +27,7 @@ export default Backbone.View.extend({
                     self.chart.settings.set(name, input.value);
                 }
             });
-            const instance = appendVueComponent(this.el, FormDisplay, {
+            const instance = replaceChildrenWithComponent(this.el, FormDisplay, {
                 inputs: inputs,
             });
             instance.$on("onChange", (data) => {
diff --git a/client/src/utils/mountVueComponent.js b/client/src/utils/mountVueComponent.js
index bee021432a5..c7b1f240f07 100644
--- a/client/src/utils/mountVueComponent.js
+++ b/client/src/utils/mountVueComponent.js
@@ -32,8 +32,7 @@ export const mountVueComponent = (ComponentDefinition) => {
     return (propsData, el) => new component({ store, propsData, el });
 };
 
-export const appendVueComponent = (el, ComponentDefinition, propsData = {}) => {
-    // TODO:  this doesn't append, it wipes out the element and replaces contents?
+export const replaceChildrenWithComponent = (el, ComponentDefinition, propsData = {}) => {
     const container = document.createElement("div");
     el.replaceChildren(container);
     const component = Vue.extend(ComponentDefinition);

From 30b3fa5b7031d6ad7bd0a7d86c09b18993c21f7c Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 15:50:34 -0500
Subject: [PATCH 195/350] Drop unused ui-thumbnail class from tour list

---
 client/src/components/Tour/TourList.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Tour/TourList.vue b/client/src/components/Tour/TourList.vue
index 39d20bcdb80..cf572dabdaf 100644
--- a/client/src/components/Tour/TourList.vue
+++ b/client/src/components/Tour/TourList.vue
@@ -1,5 +1,5 @@
 <template>
-    <div class="ui-thumbnails">
+    <div>
         <h1 class="h-lg">Galaxy Tours</h1>
         <p>
             This page presents a list of interactive tours available on this Galaxy server. Select any tour to get

From 8d723ec29a1c1cab7cf8df582aac1134ce37a906 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 15:55:59 -0500
Subject: [PATCH 196/350] Move pluginlist style to component, rename classes

---
 .../components/Visualizations/PluginList.vue  | 51 +++++++++++++++----
 client/src/style/scss/ui.scss                 | 31 -----------
 2 files changed, 41 insertions(+), 41 deletions(-)

diff --git a/client/src/components/Visualizations/PluginList.vue b/client/src/components/Visualizations/PluginList.vue
index 54013e4d541..5fd6579f0a5 100644
--- a/client/src/components/Visualizations/PluginList.vue
+++ b/client/src/components/Visualizations/PluginList.vue
@@ -1,5 +1,5 @@
 <template>
-    <div class="ui-thumbnails">
+    <div class="plugin-list">
         <div v-if="error" class="alert alert-danger">{{ error }}</div>
         <div v-else>
             <DelayedInput
@@ -10,18 +10,14 @@
                 @change="onSearch" />
             <div v-for="plugin in plugins" :key="plugin.name">
                 <table v-if="match(plugin)">
-                    <tr class="ui-thumbnails-item" @click="select(plugin)">
+                    <tr class="plugin-list-item" @click="select(plugin)">
                         <td>
-                            <img
-                                v-if="plugin.logo"
-                                alt="ui thumbnails"
-                                class="ui-thumbnails-image"
-                                :src="plugin.logo" />
-                            <div v-else class="ui-thumbnails-icon fa fa-eye" />
+                            <img v-if="plugin.logo" alt="ui thumbnails" class="plugin-list-image" :src="plugin.logo" />
+                            <div v-else class="plugin-list-icon fa fa-eye" />
                         </td>
                         <td>
-                            <div class="ui-thumbnails-title font-weight-bold">{{ plugin.html }}</div>
-                            <div class="ui-thumbnails-text">{{ plugin.description }}</div>
+                            <div class="plugin-list-title font-weight-bold">{{ plugin.html }}</div>
+                            <div class="plugin-list-text">{{ plugin.description }}</div>
                         </td>
                     </tr>
                     <tr v-if="!fixed">
@@ -155,3 +151,38 @@ export default {
     },
 };
 </script>
+
+<style lang="scss" scoped>
+@import "theme/blue.scss";
+@import "~scss/mixins.scss";
+
+.plugin-list {
+    .plugin-list-item {
+        cursor: pointer;
+        .plugin-list-image {
+            padding: 1rem;
+            width: 5rem;
+            height: 4.3rem;
+        }
+        .plugin-list-icon {
+            padding: 1rem;
+            width: 5rem;
+            height: 4.3rem;
+            font-size: 2em;
+            text-align: center;
+            color: $text-color;
+        }
+        .plugin-list-text {
+            word-wrap: break-word;
+        }
+    }
+    .plugin-list-item:hover {
+        .plugin-list-title {
+            text-decoration: underline;
+        }
+        .plugin-list-text {
+            text-decoration: underline;
+        }
+    }
+}
+</style>
diff --git a/client/src/style/scss/ui.scss b/client/src/style/scss/ui.scss
index 9726e862dfa..8f2e316092d 100644
--- a/client/src/style/scss/ui.scss
+++ b/client/src/style/scss/ui.scss
@@ -102,37 +102,6 @@ $ui-margin-horizontal-large: $margin-v * 2;
     cursor: pointer;
 }
 
-// thumbnails
-.ui-thumbnails {
-    .ui-thumbnails-item {
-        cursor: pointer;
-        .ui-thumbnails-image {
-            padding: 1rem;
-            width: 5rem;
-            height: 4.3rem;
-        }
-        .ui-thumbnails-icon {
-            padding: 1rem;
-            width: 5rem;
-            height: 4.3rem;
-            font-size: 2em;
-            text-align: center;
-            color: $text-color;
-        }
-        .ui-thumbnails-text {
-            word-wrap: break-word;
-        }
-    }
-    .ui-thumbnails-item:hover {
-        .ui-thumbnails-title {
-            text-decoration: underline;
-        }
-        .ui-thumbnails-text {
-            text-decoration: underline;
-        }
-    }
-}
-
 .ui-form-composite {
     height: 100%;
     flex-direction: column;

From 5d1dc25bac72524fb902514a83ced8e2f09dac53 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 16:02:50 -0500
Subject: [PATCH 197/350] Annotate visualize button class like other action
 buttons are

---
 .../src/components/History/Content/Dataset/DatasetActions.vue   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/History/Content/Dataset/DatasetActions.vue b/client/src/components/History/Content/Dataset/DatasetActions.vue
index 46fce47e359..118010babe4 100644
--- a/client/src/components/History/Content/Dataset/DatasetActions.vue
+++ b/client/src/components/History/Content/Dataset/DatasetActions.vue
@@ -44,7 +44,7 @@
                 </b-button>
                 <b-button
                     v-if="showVisualizations"
-                    class="px-1"
+                    class="visualize-btn px-1"
                     title="Visualize"
                     size="sm"
                     variant="link"

From 66166128e5f01c1e80399f4723f2c0b75e3d4c0a Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 16:43:39 -0500
Subject: [PATCH 198/350] Add plugin name as a data element in plugin list
 display

---
 client/src/components/Visualizations/PluginList.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Visualizations/PluginList.vue b/client/src/components/Visualizations/PluginList.vue
index 5fd6579f0a5..81e469f040e 100644
--- a/client/src/components/Visualizations/PluginList.vue
+++ b/client/src/components/Visualizations/PluginList.vue
@@ -10,7 +10,7 @@
                 @change="onSearch" />
             <div v-for="plugin in plugins" :key="plugin.name">
                 <table v-if="match(plugin)">
-                    <tr class="plugin-list-item" @click="select(plugin)">
+                    <tr class="plugin-list-item" :data-plugin-name="plugin.name" @click="select(plugin)">
                         <td>
                             <img v-if="plugin.logo" alt="ui thumbnails" class="plugin-list-image" :src="plugin.logo" />
                             <div v-else class="plugin-list-icon fa fa-eye" />

From 7f0684c02bffed7d046e30b139698f98f3f977e2 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 16:44:42 -0500
Subject: [PATCH 199/350] Add basic visualization test exercising nvd3_bar.  It
 exercises most of the basic parts of the chart entrypoint and rendering.

---
 client/src/utils/navigation/navigation.yml     |  6 ++++++
 .../selenium/test_visualizations.py            | 18 ++++++++++++++++++
 2 files changed, 24 insertions(+)
 create mode 100644 lib/galaxy_test/selenium/test_visualizations.py

diff --git a/client/src/utils/navigation/navigation.yml b/client/src/utils/navigation/navigation.yml
index 5b8a7a8120c..d223bf078f8 100644
--- a/client/src/utils/navigation/navigation.yml
+++ b/client/src/utils/navigation/navigation.yml
@@ -183,6 +183,7 @@ history_panel:
       edit_button: '${_} .edit-btn'
       delete_button: '${_} .delete-btn'
       rerun_button: '${_} .rerun-btn'
+      visualize_button: '${_} .visualize-btn'
       collection_job_details_button: '${_} .collection-job-details-btn'
 
       # Action buttons...
@@ -523,6 +524,11 @@ workflows:
       annotation: '#workflow_annotation'
       submit: '#submit'
 
+visualization:
+  selectors:
+    _: '#center div.plugin-list'
+    plugin_item: '[data-plugin-name*="${id}"]'
+
 trs_search:
   selectors:
     search: "#trs-search-query"
diff --git a/lib/galaxy_test/selenium/test_visualizations.py b/lib/galaxy_test/selenium/test_visualizations.py
new file mode 100644
index 00000000000..ef4fa8f23c0
--- /dev/null
+++ b/lib/galaxy_test/selenium/test_visualizations.py
@@ -0,0 +1,18 @@
+from .framework import (
+    selenium_test,
+    SeleniumTestCase,
+)
+
+
+class TestVisualizations(SeleniumTestCase):
+    @selenium_test
+    def test_charts_framework(self):
+        self.register()
+        self.perform_upload(self.get_filename("1.sam"))
+        self.history_panel_wait_for_hid_ok(1)
+        dataset_component = self.history_panel_click_item_title(1, wait=True)
+        dataset_component.visualize_button.wait_for_and_click()
+
+        self.components.visualization.plugin_item(id="nvd3_bar").wait_for_and_click()
+
+        # wait for the chart to render and look for something.
\ No newline at end of file

From 3dba0c964003d56735cd27e891272e5e813d91ef Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 17:25:35 -0500
Subject: [PATCH 200/350] Look in main panel and ensure there's an nvd3
 *something*

---
 lib/galaxy_test/selenium/test_visualizations.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy_test/selenium/test_visualizations.py b/lib/galaxy_test/selenium/test_visualizations.py
index ef4fa8f23c0..93908594523 100644
--- a/lib/galaxy_test/selenium/test_visualizations.py
+++ b/lib/galaxy_test/selenium/test_visualizations.py
@@ -15,4 +15,6 @@ class TestVisualizations(SeleniumTestCase):
 
         self.components.visualization.plugin_item(id="nvd3_bar").wait_for_and_click()
 
-        # wait for the chart to render and look for something.
\ No newline at end of file
+        with self.main_panel():
+            self.wait_for_selector("g.nvd3")
+            self.screenshot("test_charts_framework -- nvd3_bar")
\ No newline at end of file

From 0e4c21ec79b6d9980ccdfe67a599cb1afbdb528e Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 18 Jan 2023 17:28:55 -0500
Subject: [PATCH 201/350] EOF

---
 lib/galaxy_test/selenium/test_visualizations.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy_test/selenium/test_visualizations.py b/lib/galaxy_test/selenium/test_visualizations.py
index 93908594523..ca662748a64 100644
--- a/lib/galaxy_test/selenium/test_visualizations.py
+++ b/lib/galaxy_test/selenium/test_visualizations.py
@@ -17,4 +17,4 @@ class TestVisualizations(SeleniumTestCase):
 
         with self.main_panel():
             self.wait_for_selector("g.nvd3")
-            self.screenshot("test_charts_framework -- nvd3_bar")
\ No newline at end of file
+            self.screenshot("test_charts_framework -- nvd3_bar")

From 89f8aa0b7d9fd62e6dadb73bcbd617fa37840285 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Fri, 9 Dec 2022 19:23:38 -0500
Subject: [PATCH 202/350] Visualization specs are optional

---
 client/src/mvc/visualization/chart/chart-client.js | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/client/src/mvc/visualization/chart/chart-client.js b/client/src/mvc/visualization/chart/chart-client.js
index 3b94a33dda4..4a030f5c10b 100644
--- a/client/src/mvc/visualization/chart/chart-client.js
+++ b/client/src/mvc/visualization/chart/chart-client.js
@@ -31,12 +31,7 @@ export default Backbone.View.extend({
         this.$buttons = this.$(".charts-buttons");
         this.chart = new Chart({}, options);
         this.chart.plugin = options.visualization_plugin;
-        this.chart.plugin.specs = this.chart.plugin.specs || {};
-        if (Object.keys(this.chart.plugin.specs).length === 0) {
-            this.chart.requiresConfirmation = false;
-        } else {
-            this.chart.requiresConfirmation = asBoolean(this.chart.plugin.specs.confirm);
-        }
+        this.chart.requiresConfirmation = asBoolean(this.chart.plugin.specs?.confirm);
         this.chart_load = options.chart_load;
         this.message = new Ui.Message();
         this.deferred = new Deferred();

From c03b2946e886a905590770b78bfed8ba875f794e Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 21:03:58 -0500
Subject: [PATCH 203/350] Fix dataset download_url access for pv viewer

---
 config/plugins/visualizations/pv/src/pv.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/config/plugins/visualizations/pv/src/pv.js b/config/plugins/visualizations/pv/src/pv.js
index 14a9bdf7db3..da0260ac21b 100644
--- a/config/plugins/visualizations/pv/src/pv.js
+++ b/config/plugins/visualizations/pv/src/pv.js
@@ -10,7 +10,7 @@ window.bundleEntries.load = function (options) {
         antialias: true,
         outline: true,
     });
-    const safe_download_url = `${options.root}${dataset.download_url}`;
+    const safe_download_url = `${options.root}${options.dataset.download_url}`;
     var xhr = new XMLHttpRequest();
     xhr.open("GET", safe_download_url);
     xhr.onload = function () {

From cb6df67bfa4a8c123c9644b63f790b5feedc8bd6 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 21:35:43 -0500
Subject: [PATCH 204/350] Fix redundant paths when not using prefix, causes
 lookup failure

---
 config/plugins/visualizations/pv/src/pv.js | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/config/plugins/visualizations/pv/src/pv.js b/config/plugins/visualizations/pv/src/pv.js
index da0260ac21b..529554a9142 100644
--- a/config/plugins/visualizations/pv/src/pv.js
+++ b/config/plugins/visualizations/pv/src/pv.js
@@ -1,5 +1,11 @@
 import * as pv from "bio-pv";
 
+/* This should be part of the charts/viz standard lib */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 window.bundleEntries = window.bundleEntries || {};
 window.bundleEntries.load = function (options) {
     var settings = options.chart.settings;
@@ -10,9 +16,8 @@ window.bundleEntries.load = function (options) {
         antialias: true,
         outline: true,
     });
-    const safe_download_url = `${options.root}${options.dataset.download_url}`;
     var xhr = new XMLHttpRequest();
-    xhr.open("GET", safe_download_url);
+    xhr.open("GET", prefixedDownloadUrl(options.root, options.dataset.download_url));
     xhr.onload = function () {
         if (xhr.status === 200) {
             var structure = pv.io.pdb(xhr.response);

From dfb87ef9f979ef35527770e6dbb7ff1c765ea3a0 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 22:07:12 -0500
Subject: [PATCH 205/350] Update, fix ngl visualization

---
 config/plugins/visualizations/ngl/src/ngl.js | 34 ++++++++++++--------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/config/plugins/visualizations/ngl/src/ngl.js b/config/plugins/visualizations/ngl/src/ngl.js
index b9d92f73bec..65dc0c67038 100644
--- a/config/plugins/visualizations/ngl/src/ngl.js
+++ b/config/plugins/visualizations/ngl/src/ngl.js
@@ -1,31 +1,37 @@
 import * as ngl from "./viewer";
 
 /** Get boolean as string */
-function asBoolean (value) {
+function asBoolean(value) {
     return String(value).toLowerCase() == "true";
 }
 
+/* This should be part of the charts/viz standard lib */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 window.bundleEntries = window.bundleEntries || {};
 window.bundleEntries.load = function (options) {
-    var dataset = options.dataset,
-        settings = options.chart.settings,
-        stage = new ngl.Stage(options.target, { backgroundColor: settings.get("backcolor") }),
-        representation_parameters = {},
-        stage_parameters = {};
-    representation_parameters = {
+    const dataset = options.dataset;
+    const settings = options.chart.settings;
+    const stage = new ngl.Stage(options.target, { backgroundColor: settings.get("backcolor") });
+    const representationParameters = {
         radius: settings.get("radius"),
         assembly: settings.get("assembly"),
         color: settings.get("colorscheme"),
         opacity: settings.get("opacity"),
     };
-    stage_parameters = { ext: dataset.extension, defaultRepresentation: true };
-    const safe_download_url = `${options.root}${dataset.download_url}`;
+    const stageParameters = { ext: dataset.extension, defaultRepresentation: true };
+
     try {
-        stage.loadFile(safe_download_url, stage_parameters).then(function (component) {
-            component.addRepresentation(settings.get("mode"), representation_parameters);
-            options.chart.state("ok", "Chart drawn.");
-            options.process.resolve();
-        });
+        stage
+            .loadFile(prefixedDownloadUrl(options.root, dataset.download_url), stageParameters)
+            .then(function (component) {
+                component.addRepresentation(settings.get("mode"), representationParameters);
+                options.chart.state("ok", "Chart drawn.");
+                options.process.resolve();
+            });
     } catch (e) {
         options.chart.state("failed", "Could not load PDB file.");
         options.process.resolve();

From aa7cc1bd8be59677a8986b56aaa2ac9d379d2fdf Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 22:08:26 -0500
Subject: [PATCH 206/350] Specs can be null or undefined (yet another usecase
 for converting this over to ts...)

---
 client/src/mvc/visualization/chart/views/menu.js | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/client/src/mvc/visualization/chart/views/menu.js b/client/src/mvc/visualization/chart/views/menu.js
index e1f259704cb..283c329767f 100644
--- a/client/src/mvc/visualization/chart/views/menu.js
+++ b/client/src/mvc/visualization/chart/views/menu.js
@@ -134,14 +134,14 @@ export default Backbone.View.extend({
     },
 
     render: function () {
-        var visible = this.model.get("visible");
+        const visible = this.model.get("visible");
         this.app.$el[visible ? "removeClass" : "addClass"]("charts-fullscreen");
-        this.execute_button.model.set("visible", visible && !!this.app.chart.plugin.specs.confirm);
+        this.execute_button.model.set("visible", visible && !!this.app.chart.plugin.specs?.confirm);
         this.save_button.model.set("visible", visible);
         this.export_button.model.set("visible", visible);
         this.right_button.model.set("visible", visible);
         this.left_button.model.set("visible", !visible);
-        var exports = this.app.chart.plugin.specs.exports || [];
+        const exports = this.app.chart.plugin.specs?.exports ?? [];
         this.export_button.collection.each((model) => {
             model.set("visible", exports.indexOf(model.get("key")) !== -1);
         });

From b83a64bb2260c895e38a8341663d194339e32f09 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Fri, 20 Jan 2023 09:54:33 +0100
Subject: [PATCH 207/350] drop assertion

---
 .../datatypes/converters/interval_to_bgzip_converter.xml     | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
index 75a48c574f2..52e1e8d7b98 100644
--- a/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
+++ b/lib/galaxy/datatypes/converters/interval_to_bgzip_converter.xml
@@ -81,8 +81,9 @@
             <param name="input1" ftype="vcf" value="vcf_to_maf_in.vcf"/>
             <output name="output1" ftype="bgzip" decompress="true">
                 <expand macro="assert_size" value="322">
-                    <has_n_lines n="3"/>
-                    <has_text_matching expression="^#" negate="true"/>
+                    <!-- will only work with https://github.com/galaxyproject/galaxy/pull/15085
+                        <has_n_lines n="3"/>
+                        <has_text_matching expression="^#" negate="true"/> -->
                 </expand>
             </output>
             <assert_command>

From c15f9efc66d34d8d2d05a0901bade2e8da09592c Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 17 Jan 2023 17:04:29 +0100
Subject: [PATCH 208/350] Track and display invalid connections

---
 .../Workflow/Editor/ConnectionMenu.vue        |   8 +-
 .../components/Workflow/Editor/Connector.vue  |  13 +-
 .../src/components/Workflow/Editor/Index.vue  |   9 +-
 .../src/components/Workflow/Editor/Node.vue   |  30 ++-
 .../components/Workflow/Editor/NodeInput.vue  |  47 ++--
 .../components/Workflow/Editor/NodeOutput.vue |  10 +-
 .../components/Workflow/Editor/Options.vue    |  37 ++--
 .../Workflow/Editor/TerminalConnector.vue     |  12 +-
 .../Editor/composables/useTerminal.ts         |   2 +-
 .../Workflow/Editor/modules/terminals.test.ts |   9 +
 .../Workflow/Editor/modules/terminals.ts      | 204 ++++++++++++++----
 client/src/stores/workflowConnectionStore.ts  |  14 ++
 client/src/stores/workflowStepStore.ts        |   4 +-
 13 files changed, 312 insertions(+), 87 deletions(-)

diff --git a/client/src/components/Workflow/Editor/ConnectionMenu.vue b/client/src/components/Workflow/Editor/ConnectionMenu.vue
index ec214414ab9..098a9e4c694 100644
--- a/client/src/components/Workflow/Editor/ConnectionMenu.vue
+++ b/client/src/components/Workflow/Editor/ConnectionMenu.vue
@@ -24,7 +24,7 @@
 <script lang="ts" setup>
 import { useWorkflowStepStore } from "@/stores/workflowStepStore";
 import { computed, onMounted, ref, watch, type ComputedRef } from "vue";
-import { type OutputTerminals, type InputTerminals, terminalFactory } from "./modules/terminals";
+import { type OutputTerminals, type InputTerminalsAndInvalid, terminalFactory } from "./modules/terminals";
 import { useFocusWithin } from "@/composables/useActiveElement";
 
 const props = defineProps<{
@@ -78,13 +78,15 @@ function decrement() {
     }
 }
 
-function terminalToInputObject(terminal: InputTerminals, connected: boolean): InputObject {
+function terminalToInputObject(terminal: InputTerminalsAndInvalid, connected: boolean): InputObject {
     const step = stepStore.getStep(terminal.stepId);
     const inputLabel = `${terminal.name} in step ${step.id + 1}: ${step.label}`;
     return { stepId: step.id, inputName: terminal.name, inputLabel, connected };
 }
 
-function inputObjectToTerminal(inputObject: InputObject): InputTerminals {
+function inputObjectToTerminal(inputObject: InputObject): InputTerminalsAndInvalid {
+    // TODO: this isn't ideal, we may not actually have a step .. except we do.
+    // Generalize connection.<input | output> to terminalSource ?
     const inputSource = stepStore
         .getStep(inputObject.stepId)
         .inputs.find((input) => input.name == inputObject.inputName)!;
diff --git a/client/src/components/Workflow/Editor/Connector.vue b/client/src/components/Workflow/Editor/Connector.vue
index e78e13a3028..c42b833d062 100644
--- a/client/src/components/Workflow/Editor/Connector.vue
+++ b/client/src/components/Workflow/Editor/Connector.vue
@@ -1,8 +1,13 @@
 <template>
     <g :id="id" class="ribbon">
         <g v-for="svgLine in paths" :key="svgLine">
-            <path class="ribbon-outer" :d="svgLine" :stroke-width="stroke.outerStroke" fill="none"></path>
-            <path class="ribbon-inner" :d="svgLine" :stroke-width="stroke.innerStroke" fill="none"></path>
+            <path
+                v-b-tooltip:hover="`my message`"
+                class="ribbon-outer"
+                :d="svgLine"
+                :stroke-width="stroke.outerStroke"
+                fill="none"></path>
+            <path :class="innerClass" :d="svgLine" :stroke-width="stroke.innerStroke" fill="none"></path>
         </g>
     </g>
 </template>
@@ -17,11 +22,13 @@ const props = withDefaults(
         position: TerminalPosition;
         inputIsMappedOver: boolean;
         outputIsMappedOver: boolean;
+        connectionIsValid?: boolean;
     }>(),
     {
         id: undefined,
         inputIsMappedOver: false,
         outputIsMappedOver: false,
+        connectionIsValid: true,
     }
 );
 
@@ -40,6 +47,8 @@ const stroke = computed(() => {
     return { innerStroke, outerStroke };
 });
 
+const innerClass = computed(() => (props.connectionIsValid ? "ribbon-inner" : "ribbon-inner ribbon-inner-invalid"));
+
 const offsets = computed(() => {
     const _offsets = [-2 * ribbonMargin, -ribbonMargin, 0, ribbonMargin, 2 * ribbonMargin];
     let startOffsets = [0];
diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index 872af56a6de..6e55f451e03 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -91,6 +91,7 @@
                             <div class="unified-panel-header-inner">
                                 <WorkflowOptions
                                     :has-changes="hasChanges"
+                                    :has-invalid-connections="hasInvalidConnections"
                                     @onSave="onSave"
                                     @onSaveAs="onSaveAs"
                                     @onRun="onRun"
@@ -185,7 +186,7 @@ import WorkflowGraph from "./WorkflowGraph.vue";
 import { defaultPosition } from "./composables/useDefaultStepPosition";
 import { useConnectionStore } from "@/stores/workflowConnectionStore";
 
-import Vue, { onUnmounted, computed } from "vue";
+import Vue, { onUnmounted, computed, ref } from "vue";
 import { ConfirmDialog } from "@/composables/confirmDialog";
 import { useWorkflowStepStore } from "@/stores/workflowStepStore";
 import { useWorkflowStateStore } from "@/stores/workflowEditorStateStore";
@@ -247,6 +248,9 @@ export default {
             return null;
         });
 
+        const hasChanges = ref(false);
+        const hasInvalidConnections = computed(() => Object.keys(connectionsStore.invalidConnections).length > 0);
+
         function resetStores() {
             connectionsStore.$reset();
             stepStore.$reset();
@@ -257,6 +261,8 @@ export default {
         });
         return {
             connectionsStore,
+            hasChanges,
+            hasInvalidConnections,
             stepStore,
             steps,
             nodeIndex: getStepIndex,
@@ -276,7 +282,6 @@ export default {
             markdownText: null,
             versions: [],
             parameters: null,
-            hasChanges: false,
             report: {},
             labels: {},
             license: null,
diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index 377791425c0..4e5b6f0fbaf 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -118,6 +118,7 @@ import { useWorkflowStateStore, type XYPosition } from "@/stores/workflowEditorS
 import type { Step } from "@/stores/workflowStepStore";
 import { DatatypesMapperModel } from "@/components/Datatypes/model";
 import type { UseElementBoundingReturn, UseScrollReturn } from "@vueuse/core";
+import { useConnectionStore } from "@/stores/workflowConnectionStore";
 
 Vue.use(BootstrapVue);
 
@@ -161,6 +162,7 @@ function remove() {
 const el: Ref<HTMLElement | null> = ref(null);
 const postJobActions = computed(() => props.step.post_job_actions || {});
 const workflowOutputs = computed(() => props.step.workflow_outputs || []);
+const connectionStore = useConnectionStore();
 const stateStore = useWorkflowStateStore();
 const isLoading = computed(() => Boolean(stateStore.getStepLoadingState(props.id)?.loading));
 useNodePosition(el, props.id, stateStore);
@@ -184,8 +186,32 @@ const style = computed(() => {
     return { top: props.step.position!.top + "px", left: props.step.position!.left + "px" };
 });
 const errors = computed(() => props.step.errors || stateStore.getStepLoadingState(props.id)?.error);
-const inputs = computed(() => props.step.inputs);
-const outputs = computed(() => props.step.outputs);
+const invalidInputs = computed(() => {
+    const connections = connectionStore.getConnectionsForStep(props.id);
+    const invalidConnections = connections.filter(
+        (connection) =>
+            connection.input.stepId == props.id &&
+            !props.step.inputs.find((input) => input.name === connection.input.name)
+    );
+    const invalidInputNames = [...new Set(invalidConnections.map((connection) => connection.input.name))];
+    return invalidInputNames.map((name) => {
+        return { name, optional: false, extensions: [], valid: false, input_type: "dataset" };
+    });
+});
+const inputs = computed(() => [...props.step.inputs, ...invalidInputs.value]);
+const invalidOutputs = computed(() => {
+    const connections = connectionStore.getConnectionsForStep(props.id);
+    const invalidConnections = connections.filter(
+        (connection) =>
+            connection.output.stepId == props.id &&
+            !props.step.outputs.find((output) => output.name === connection.output.name)
+    );
+    const invalidOutputNames = [...new Set(invalidConnections.map((connection) => connection.output.name))];
+    return invalidOutputNames.map((name) => {
+        return { name, optional: false, datatypes: [], valid: false };
+    });
+});
+const outputs = computed(() => [...props.step.outputs, ...invalidOutputs.value]);
 
 function onMoveTo(position: XYPosition) {
     emit("onUpdateStepPosition", props.id, {
diff --git a/client/src/components/Workflow/Editor/NodeInput.vue b/client/src/components/Workflow/Editor/NodeInput.vue
index 28b9e76faa5..a75ef9242ec 100644
--- a/client/src/components/Workflow/Editor/NodeInput.vue
+++ b/client/src/components/Workflow/Editor/NodeInput.vue
@@ -1,10 +1,5 @@
 <template>
-    <div
-        class="form-row dataRow input-data-row"
-        @mouseleave="leave"
-        @mouseenter="enter"
-        @focusin="enter"
-        @focusout="leave">
+    <div :class="rowClass" @mouseleave="leave" @mouseenter="enter" @focusin="enter" @focusout="leave">
         <div
             :id="id"
             :input-name="input.name"
@@ -75,8 +70,34 @@ export default {
         watchEffect(() => {
             hasTerminals.value = connectionStore.getOutputTerminalsForInputTerminal(id.value).length > 0;
         });
+
+        const rowClass = computed(() => {
+            const classes = ["form-row", "dataRow", "input-data-row"];
+            if (props.input?.valid === false) {
+                classes.push("form-row-error");
+            }
+            return classes;
+        });
+
         const stateStore = useWorkflowStateStore();
         const { draggingTerminal } = storeToRefs(stateStore);
+
+        const terminalIsHovered = ref(false);
+        const connections = computed(() => {
+            return connectionStore.getConnectionsForTerminal(id.value);
+        });
+        const invalidConnections = computed(() =>
+            connections.value.filter((connection) => connectionStore.invalidConnections[connection.id])
+        );
+
+        const showRemove = computed(() => {
+            if (invalidConnections.value.length > 0) {
+                return true;
+            } else {
+                return terminalIsHovered.value && connections.value.length > 0;
+            }
+        });
+
         return {
             el,
             position,
@@ -85,15 +106,13 @@ export default {
             connectionStore,
             id,
             iconId,
+            rowClass,
             hasTerminals,
             terminal,
             stateStore,
             isMultiple,
-        };
-    },
-    data() {
-        return {
-            showRemove: false,
+            showRemove,
+            terminalIsHovered,
         };
     },
     computed: {
@@ -165,13 +184,13 @@ export default {
         onRemove() {
             const connections = this.connectionStore.getConnectionsForTerminal(this.id);
             connections.forEach((connection) => this.terminal.disconnect(connection));
-            this.showRemove = false;
+            this.terminalIsHovered = false;
         },
         enter() {
-            this.showRemove = this.hasTerminals;
+            this.terminalIsHovered = true;
         },
         leave() {
-            this.showRemove = false;
+            this.terminalIsHovered = false;
         },
         onDrop(e) {
             const stepOut = JSON.parse(e.dataTransfer.getData("text/plain"));
diff --git a/client/src/components/Workflow/Editor/NodeOutput.vue b/client/src/components/Workflow/Editor/NodeOutput.vue
index 6500330a335..b7109d645e9 100644
--- a/client/src/components/Workflow/Editor/NodeOutput.vue
+++ b/client/src/components/Workflow/Editor/NodeOutput.vue
@@ -1,5 +1,5 @@
 <template>
-    <div class="form-row dataRow output-data-row">
+    <div :class="rowClass">
         <div
             v-if="showCalloutActiveOutput"
             v-b-tooltip
@@ -154,6 +154,13 @@ export default {
             const activeLabel = workflowOutput.value?.label || props.output.name;
             return `${activeLabel} (${extensions.value.join(", ")})`;
         });
+        const rowClass = computed(() => {
+            const classes = ["form-row", "dataRow", "output-data-row"];
+            if (props.output?.valid === false) {
+                classes.push("form-row-error");
+            }
+            return classes;
+        });
 
         const menu = ref(null);
         const icon = ref(null);
@@ -212,6 +219,7 @@ export default {
             activeClass,
             visibleClass,
             visibleHint,
+            rowClass,
             isVisible,
             terminal,
             isMultiple,
diff --git a/client/src/components/Workflow/Editor/Options.vue b/client/src/components/Workflow/Editor/Options.vue
index 4a5d26f8226..e5e342930dc 100644
--- a/client/src/components/Workflow/Editor/Options.vue
+++ b/client/src/components/Workflow/Editor/Options.vue
@@ -11,14 +11,14 @@
             @click="$emit('onAttributes')">
             <span class="fa fa-pencil-alt" />
         </b-button>
-        <b-button-group v-b-tooltip class="editor-button-save-group" title="Save Workflow">
+        <b-button-group v-b-tooltip class="editor-button-save-group" :title="saveHover">
             <b-button
                 id="workflow-save-button"
                 role="button"
                 variant="link"
                 aria-label="Save Workflow"
                 class="editor-button-save"
-                :disabled="!hasChanges"
+                :disabled="!hasChanges || hasInvalidConnections"
                 @click="$emit('onSave')">
                 <span class="fa fa-floppy-o" />
             </b-button>
@@ -77,22 +77,23 @@
     </div>
 </template>
 
-<script>
+<script setup lang="ts">
+import { computed } from "vue";
 import { BDropdown, BDropdownItem, BButton } from "bootstrap-vue";
 
-export default {
-    components: {
-        BDropdown,
-        BDropdownItem,
-        BButton,
-    },
-    props: {
-        hasChanges: {
-            type: Boolean,
-        },
-        requiredReindex: {
-            type: Boolean,
-        },
-    },
-};
+const props = defineProps<{
+    hasChanges?: boolean;
+    hasInvalidConnections?: boolean;
+    requiredReindex?: boolean;
+}>();
+
+const saveHover = computed(() => {
+    if (!props.hasChanges) {
+        return "Workflow has no changes";
+    } else if (props.hasInvalidConnections) {
+        return "Workflow has invalid connections, review and remove invalid connections";
+    } else {
+        return "Save Workflow";
+    }
+});
 </script>
diff --git a/client/src/components/Workflow/Editor/TerminalConnector.vue b/client/src/components/Workflow/Editor/TerminalConnector.vue
index 20dfc4a2540..eb3006f44b4 100644
--- a/client/src/components/Workflow/Editor/TerminalConnector.vue
+++ b/client/src/components/Workflow/Editor/TerminalConnector.vue
@@ -4,14 +4,15 @@
         :id="connectionId"
         :position="position"
         :output-is-mapped-over="outputIsMappedOver"
-        :input-is-mapped-over="inputIsMappedOver"></raw-connector>
+        :input-is-mapped-over="inputIsMappedOver"
+        :connection-is-valid="connectionIsValid"></raw-connector>
 </template>
 
 <script lang="ts" setup>
 import RawConnector from "@/components/Workflow/Editor/Connector.vue";
 import { useWorkflowStateStore } from "@/stores/workflowEditorStateStore";
 import { useWorkflowStepStore } from "@/stores/workflowStepStore";
-import type { Connection } from "@/stores/workflowConnectionStore";
+import { useConnectionStore, type Connection } from "@/stores/workflowConnectionStore";
 import { computed } from "vue";
 
 const props = defineProps<{
@@ -19,9 +20,16 @@ const props = defineProps<{
 }>();
 
 const stepStore = useWorkflowStepStore();
+const connectionStore = useConnectionStore();
 const outputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.output.stepId]?.isCollection);
 const inputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.input.stepId]?.isCollection);
 
+// move into connection store ?
+// move all of terminal logic into connection store ?
+const connectionIsValid = computed(() => {
+    return !Boolean(connectionStore.invalidConnections[props.connection.id]);
+});
+
 const stateStore = useWorkflowStateStore();
 const connectionId = computed(() => {
     return `connection-node-${props.connection.input.stepId}-input-${props.connection.input.name}-node-${props.connection.output.stepId}-output-${props.connection.output.name}`;
diff --git a/client/src/components/Workflow/Editor/composables/useTerminal.ts b/client/src/components/Workflow/Editor/composables/useTerminal.ts
index 15e66ce4531..1290cef3f9b 100644
--- a/client/src/components/Workflow/Editor/composables/useTerminal.ts
+++ b/client/src/components/Workflow/Editor/composables/useTerminal.ts
@@ -13,7 +13,7 @@ export function useTerminal(
     watchEffect(() => {
         // rebuild terminal if any of the tracked dependencies change
         const newTerminal = terminalFactory(stepId.value, terminalSource.value, datatypesMapper.value);
-        newTerminal.destroyInvalidConnections();
+        newTerminal.getInvalidConnectedTerminals();
         terminal.value = newTerminal;
         isMappedOver.value = newTerminal.isMappedOver();
     });
diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index ded5054db32..738232bc50d 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -10,6 +10,7 @@ import {
     OutputTerminal,
     OutputParameterTerminal,
     producesAcceptableDatatype,
+    InvalidOutputTerminal,
 } from "./terminals";
 import { testDatatypesMapper } from "@/components/Datatypes/test_fixtures";
 import { useConnectionStore } from "@/stores/workflowConnectionStore";
@@ -473,6 +474,14 @@ describe("Input terminal", () => {
         connectionStore.addConnection(connection);
         expect(firstInputTerminal.canAccept(dataInputOutputTerminal).canAccept).toBe(false);
     });
+    it("will maintain invalid connections", () => {
+        const connection = connectionStore.connections[0];
+        connection.output.name = "I don't exist";
+        const firstInputTerminal = terminals[1]["input"] as InputTerminal;
+        const invalidTerminals = firstInputTerminal.getConnectedTerminals();
+        expect(invalidTerminals.length).toBe(1);
+        expect(invalidTerminals[0]).toBeInstanceOf(InvalidOutputTerminal);
+    });
 });
 
 describe("producesAcceptableDatatype", () => {
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index fdcebf890ce..536554ecfa6 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -42,6 +42,7 @@ interface InputTerminalInputs {
 
 interface InputTerminalArgs extends BaseTerminalArgs {
     input: InputTerminalInputs;
+    input_type: "dataset" | "dataset_collection" | "parameter";
 }
 
 class Terminal extends EventEmitter {
@@ -295,14 +296,26 @@ class BaseInputTerminal extends Terminal {
     getConnectedTerminals() {
         return this.connections.map((connection) => {
             const outputStep = this.stepStore.getStep(connection.output.stepId);
+            if (!outputStep) {
+                return new InvalidOutputTerminal({
+                    stepId: -1,
+                    optional: false,
+                    datatypes: [],
+                    name: connection.output.name,
+                    valid: false,
+                    datatypesMapper: this.datatypesMapper,
+                });
+            }
             let terminalSource = outputStep.outputs.find((output) => output.name === connection.output.name);
             if (!terminalSource) {
-                /*
-                / This can't happen, I think, because we'd drop the connection.
-                / We (probably) want to eventually display invalid connections,
-                / so maybe generate a NullTerminal when there is no terminalSource ?
-                */
-                throw `Could not find output ${connection.output.name} on step ${connection.output.stepId}`;
+                return new InvalidOutputTerminal({
+                    stepId: -1,
+                    optional: false,
+                    datatypes: [],
+                    name: connection.output.name,
+                    valid: false,
+                    datatypesMapper: this.datatypesMapper,
+                });
             }
             const postJobActionKey = `ChangeDatatypeAction${connection.output.name}`;
             if (
@@ -318,13 +331,39 @@ class BaseInputTerminal extends Terminal {
             return terminalFactory(outputStep.id, terminalSource, this.datatypesMapper);
         });
     }
-    destroyInvalidConnections() {
-        this.getConnectedTerminals().forEach((terminal) => {
-            if (!this.attachable(terminal).canAccept) {
-                this.disconnect(terminal);
+
+    getInvalidConnectedTerminals() {
+        return this.getConnectedTerminals().filter((terminal) => {
+            const canAccept = this.attachable(terminal);
+            if (!canAccept.canAccept) {
+                const connectionId = `${this.stepId}-${this.name}-${terminal.stepId}-${terminal.name}`;
+                this.connectionStore.addInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
+                return true;
             }
+            return false;
         });
     }
+
+    destroyInvalidConnections() {
+        this.getInvalidConnectedTerminals().forEach((terminal) => this.disconnect(terminal));
+    }
+}
+
+interface InvalidInputTerminalArgs extends InputTerminalArgs {
+    valid: false;
+}
+
+export class InvalidInputTerminal extends BaseInputTerminal {
+    valid: false;
+
+    constructor(attr: InvalidInputTerminalArgs) {
+        super(attr);
+        this.valid = false;
+    }
+
+    attachable(terminal: BaseOutputTerminal) {
+        return new ConnectionAcceptable(false, "Cannot attach to invalid input.");
+    }
 }
 
 // TODO: turn into InputTerminalAttachableMixin ?
@@ -519,6 +558,8 @@ interface BaseOutputTerminalArgs extends BaseTerminalArgs {
     optional: boolean;
 }
 
+export type InputTerminalsAndInvalid = InputTerminals | InvalidInputTerminal;
+
 class BaseOutputTerminal extends Terminal {
     datatypes: BaseOutputTerminalArgs["datatypes"];
     optional: BaseOutputTerminalArgs["optional"];
@@ -532,16 +573,40 @@ class BaseOutputTerminal extends Terminal {
         this.optional = attr.optional;
         this.terminalType = "output";
     }
-    getConnectedTerminals() {
+    getConnectedTerminals(): InputTerminalsAndInvalid[] {
         return this.connections.map((connection) => {
             const inputStep = this.stepStore.getStep(connection.input.stepId);
             const terminalSource = inputStep.inputs.find((input) => input.name === connection.input.name);
             if (!terminalSource) {
-                throw `Could not find input ${connection.input.name} on step ${connection.input.stepId}`;
+                return new InvalidInputTerminal({
+                    valid: false,
+                    name: connection.input.name,
+                    stepId: connection.input.stepId,
+                    datatypesMapper: this.datatypesMapper,
+                    input_type: "dataset",
+                    input: {
+                        datatypes: [],
+                        optional: false,
+                        multiple: false,
+                    },
+                });
             }
             return terminalFactory(inputStep.id, terminalSource, this.datatypesMapper);
         });
     }
+
+    getInvalidConnectedTerminals() {
+        return this.getConnectedTerminals().filter((terminal: any) => {
+            const canAccept = terminal.attachable(this);
+            if (!canAccept.canAccept) {
+                const connectionId = `${terminal.stepId}-${terminal.name}-${this.stepId}-${this.name}`;
+                this.connectionStore.addInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
+                return true;
+            }
+            return false;
+        });
+    }
+
     destroyInvalidConnections() {
         this.getConnectedTerminals().forEach((terminal) => {
             if (!terminal.attachable(this).canAccept) {
@@ -597,6 +662,27 @@ export class OutputParameterTerminal extends BaseOutputTerminal {
     }
 }
 
+interface InvalidOutputTerminalArgs extends BaseOutputTerminalArgs {
+    valid: false;
+}
+
+export class InvalidOutputTerminal extends BaseOutputTerminal {
+    valid: false;
+
+    constructor(attr: InvalidOutputTerminalArgs) {
+        super(attr);
+        this.valid = false;
+    }
+
+    validInputTerminals() {
+        return [];
+    }
+
+    canAccept() {
+        return new ConnectionAcceptable(false, "Can't connect to invalid terminal.");
+    }
+}
+
 export type OutputTerminals = OutputTerminal | OutputCollectionTerminal | OutputParameterTerminal;
 export type InputTerminals = InputTerminal | InputCollectionTerminal | InputParameterTerminal;
 
@@ -639,7 +725,27 @@ export function producesAcceptableDatatype(
     );
 }
 
-type TerminalOf<T extends TerminalSource> = T extends DataStepInput
+type TerminalSourceAndInvalid = TerminalSource | InvalidOutputTerminalArgs | InvalidInputTerminalArgs;
+
+function isInvalidOutputArg(arg: TerminalSourceAndInvalid): arg is InvalidOutputTerminalArgs {
+    return "name" in arg && "valid" in arg && arg.valid === false;
+}
+
+function isOutputParameterArg(arg: TerminalSourceAndInvalid): arg is ParameterOutput {
+    return "name" in arg && "parameter" in arg && arg.parameter === true;
+}
+
+function isOutputCollectionArg(arg: TerminalSourceAndInvalid): arg is CollectionOutput {
+    return "name" in arg && "collection" in arg && arg.collection;
+}
+
+function isOutputArg(arg: TerminalSourceAndInvalid): arg is DataOutput {
+    return "name" in arg && "extensions" in arg;
+}
+
+type TerminalOf<T extends TerminalSourceAndInvalid> = T extends InvalidInputTerminalArgs
+    ? InvalidInputTerminal
+    : T extends DataStepInput
     ? InputTerminal
     : T extends DataCollectionStepInput
     ? InputCollectionTerminal
@@ -651,9 +757,11 @@ type TerminalOf<T extends TerminalSource> = T extends DataStepInput
     ? OutputCollectionTerminal
     : T extends ParameterOutput
     ? OutputParameterTerminal
+    : T extends BaseOutputTerminalArgs
+    ? InvalidOutputTerminal
     : never;
 
-export function terminalFactory<T extends TerminalSource>(
+export function terminalFactory<T extends TerminalSourceAndInvalid>(
     stepId: number,
     terminalSource: T,
     datatypesMapper: DatatypesMapperModel
@@ -661,36 +769,49 @@ export function terminalFactory<T extends TerminalSource>(
     if ("input_type" in terminalSource) {
         const terminalArgs = {
             datatypesMapper: datatypesMapper,
+            input_type: terminalSource.input_type,
             name: terminalSource.name,
             stepId: stepId,
         };
-        const inputArgs = {
-            datatypes: terminalSource.extensions,
-            multiple: terminalSource.multiple,
-            optional: terminalSource.optional,
-        };
-        if (terminalSource.input_type == "dataset") {
-            // type cast appears to be necessary: https://github.com/Microsoft/TypeScript/issues/13995
-            return new InputTerminal({
+        if ("valid" in terminalSource) {
+            return new InvalidInputTerminal({
                 ...terminalArgs,
-                input: inputArgs,
-            }) as TerminalOf<T>;
-        } else if (terminalSource.input_type === "dataset_collection") {
-            return new InputCollectionTerminal({
-                ...terminalArgs,
-                collection_types: terminalSource.collection_types,
                 input: {
-                    ...inputArgs,
-                },
-            }) as TerminalOf<T>;
-        } else if (terminalSource.input_type === "parameter") {
-            return new InputParameterTerminal({
-                ...terminalArgs,
-                type: terminalSource.type,
-                input: {
-                    ...inputArgs,
+                    datatypes: [],
+                    multiple: false,
+                    optional: false,
                 },
+                valid: terminalSource.valid,
             }) as TerminalOf<T>;
+        } else {
+            const inputArgs = {
+                datatypes: terminalSource.extensions,
+                multiple: terminalSource.multiple,
+                optional: terminalSource.optional,
+            };
+            if (terminalSource.input_type == "dataset") {
+                // type cast appears to be necessary: https://github.com/Microsoft/TypeScript/issues/13995
+                return new InputTerminal({
+                    ...terminalArgs,
+                    input: inputArgs,
+                }) as TerminalOf<T>;
+            } else if (terminalSource.input_type === "dataset_collection") {
+                return new InputCollectionTerminal({
+                    ...terminalArgs,
+                    collection_types: terminalSource.collection_types,
+                    input: {
+                        ...inputArgs,
+                    },
+                }) as TerminalOf<T>;
+            } else if (terminalSource.input_type === "parameter") {
+                return new InputParameterTerminal({
+                    ...terminalArgs,
+                    type: terminalSource.type,
+                    input: {
+                        ...inputArgs,
+                    },
+                }) as TerminalOf<T>;
+            }
         }
     } else if (terminalSource.name) {
         const outputArgs = {
@@ -699,24 +820,27 @@ export function terminalFactory<T extends TerminalSource>(
             stepId: stepId,
             datatypesMapper: datatypesMapper,
         };
-        if ("parameter" in terminalSource) {
+        if (isOutputParameterArg(terminalSource)) {
             return new OutputParameterTerminal({
                 ...outputArgs,
                 type: terminalSource.type,
             }) as TerminalOf<T>;
-        } else if ("collection" in terminalSource && terminalSource.collection) {
+        } else if (isOutputCollectionArg(terminalSource)) {
             return new OutputCollectionTerminal({
                 ...outputArgs,
                 datatypes: terminalSource.extensions,
                 collection_type: terminalSource.collection_type,
                 collection_type_source: terminalSource.collection_type_source,
             }) as TerminalOf<T>;
-        } else {
+        } else if (isOutputArg(terminalSource)) {
             return new OutputTerminal({
                 ...outputArgs,
                 datatypes: terminalSource.extensions,
             }) as TerminalOf<T>;
         }
     }
+    if (isInvalidOutputArg(terminalSource)) {
+        return new InvalidOutputTerminal(terminalSource) as TerminalOf<T>;
+    }
     throw `Could not build terminal for ${terminalSource}`;
 }
diff --git a/client/src/stores/workflowConnectionStore.ts b/client/src/stores/workflowConnectionStore.ts
index 45f08a05653..b28b28854f9 100644
--- a/client/src/stores/workflowConnectionStore.ts
+++ b/client/src/stores/workflowConnectionStore.ts
@@ -1,8 +1,15 @@
 import { defineStore } from "pinia";
 import { useWorkflowStepStore } from "@/stores/workflowStepStore";
+import { state } from "@/store/tagStore";
+import Vue from "vue";
+
+interface InvalidConnections {
+    [index: string]: string;
+}
 
 export interface State {
     connections: Connection[];
+    invalidConnections: InvalidConnections;
 }
 
 export class Connection {
@@ -44,6 +51,7 @@ interface TerminalToInputTerminals {
 export const useConnectionStore = defineStore("workflowConnectionStore", {
     state: (): State => ({
         connections: [] as Connection[],
+        invalidConnections: {} as InvalidConnections,
     }),
     getters: {
         getOutputTerminalsForInputTerminal(state: State) {
@@ -112,12 +120,16 @@ export const useConnectionStore = defineStore("workflowConnectionStore", {
             const stepStore = useWorkflowStepStore();
             stepStore.addConnection(connection);
         },
+        addInvalidConnection(this: State, connectionId: string, reason: string) {
+            Vue.set(this.invalidConnections, connectionId, reason);
+        },
         removeConnection(this: State, terminal: InputTerminal | OutputTerminal | Connection["id"]) {
             const stepStore = useWorkflowStepStore();
             this.connections = this.connections.filter((connection) => {
                 if (typeof terminal === "string") {
                     if (connection.id == terminal) {
                         stepStore.removeConnection(connection);
+                        Vue.delete(this.invalidConnections, connection.id);
                         return false;
                     } else {
                         return true;
@@ -125,6 +137,7 @@ export const useConnectionStore = defineStore("workflowConnectionStore", {
                 } else if (terminal.connectorType === "input") {
                     if (connection.input.stepId == terminal.stepId && connection.input.name == terminal.name) {
                         stepStore.removeConnection(connection);
+                        Vue.delete(this.invalidConnections, connection.id);
                         return false;
                     } else {
                         return true;
@@ -132,6 +145,7 @@ export const useConnectionStore = defineStore("workflowConnectionStore", {
                 } else {
                     if (connection.output.stepId == terminal.stepId && connection.output.name == terminal.name) {
                         stepStore.removeConnection(connection);
+                        Vue.delete(this.invalidConnections, connection.id);
                         return false;
                     } else {
                         return true;
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index f183bd9606e..32b043304dc 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -78,8 +78,8 @@ export interface ParameterStepInput extends Omit<BaseStepInput, "input_type"> {
     type: typeof ParameterTypes;
 }
 
-type InputTerminalSource = DataStepInput | DataCollectionStepInput | ParameterStepInput;
-type OutputTerminalSource = DataOutput | CollectionOutput | ParameterOutput;
+export type InputTerminalSource = DataStepInput | DataCollectionStepInput | ParameterStepInput;
+export type OutputTerminalSource = DataOutput | CollectionOutput | ParameterOutput;
 export type TerminalSource = InputTerminalSource | OutputTerminalSource;
 
 interface WorkflowOutput {

From ce70d5e080e5253b280d6bade4c835d1ee2bc11a Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 19 Jan 2023 21:40:39 +0100
Subject: [PATCH 209/350] Display optional output connections as dashed lines

---
 client/src/components/Workflow/Editor/Connector.vue  | 12 +++++-------
 .../components/Workflow/Editor/TerminalConnector.vue | 11 ++++++++++-
 .../src/components/Workflow/Editor/WorkflowEdges.vue |  7 ++++++-
 client/src/stores/workflowStepStore.ts               |  1 +
 client/src/style/scss/workflow.scss                  |  3 +++
 5 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Connector.vue b/client/src/components/Workflow/Editor/Connector.vue
index c42b833d062..863a130a799 100644
--- a/client/src/components/Workflow/Editor/Connector.vue
+++ b/client/src/components/Workflow/Editor/Connector.vue
@@ -1,12 +1,7 @@
 <template>
-    <g :id="id" class="ribbon">
+    <g :id="id" :class="ribbonClasses">
         <g v-for="svgLine in paths" :key="svgLine">
-            <path
-                v-b-tooltip:hover="`my message`"
-                class="ribbon-outer"
-                :d="svgLine"
-                :stroke-width="stroke.outerStroke"
-                fill="none"></path>
+            <path class="ribbon-outer" :d="svgLine" :stroke-width="stroke.outerStroke" fill="none"></path>
             <path :class="innerClass" :d="svgLine" :stroke-width="stroke.innerStroke" fill="none"></path>
         </g>
     </g>
@@ -23,12 +18,14 @@ const props = withDefaults(
         inputIsMappedOver: boolean;
         outputIsMappedOver: boolean;
         connectionIsValid?: boolean;
+        nullable?: boolean;
     }>(),
     {
         id: undefined,
         inputIsMappedOver: false,
         outputIsMappedOver: false,
         connectionIsValid: true,
+        nullable: false,
     }
 );
 
@@ -47,6 +44,7 @@ const stroke = computed(() => {
     return { innerStroke, outerStroke };
 });
 
+const ribbonClasses = computed(() => (props.nullable ? "ribbon dashed" : "ribbon"));
 const innerClass = computed(() => (props.connectionIsValid ? "ribbon-inner" : "ribbon-inner ribbon-inner-invalid"));
 
 const offsets = computed(() => {
diff --git a/client/src/components/Workflow/Editor/TerminalConnector.vue b/client/src/components/Workflow/Editor/TerminalConnector.vue
index eb3006f44b4..1b0d12bd214 100644
--- a/client/src/components/Workflow/Editor/TerminalConnector.vue
+++ b/client/src/components/Workflow/Editor/TerminalConnector.vue
@@ -5,7 +5,8 @@
         :position="position"
         :output-is-mapped-over="outputIsMappedOver"
         :input-is-mapped-over="inputIsMappedOver"
-        :connection-is-valid="connectionIsValid"></raw-connector>
+        :connection-is-valid="connectionIsValid"
+        :nullable="outputIsOptional"></raw-connector>
 </template>
 
 <script lang="ts" setup>
@@ -23,6 +24,14 @@ const stepStore = useWorkflowStepStore();
 const connectionStore = useConnectionStore();
 const outputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.output.stepId]?.isCollection);
 const inputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.input.stepId]?.isCollection);
+const outputIsOptional = computed(() => {
+    return Boolean(
+        stepStore.getStep(props.connection.output.stepId)?.when ||
+            stepStore
+                .getStep(props.connection.output.stepId)
+                ?.outputs.find((output) => output.name === props.connection.output.name && output.optional)
+    );
+});
 
 // move into connection store ?
 // move all of terminal logic into connection store ?
diff --git a/client/src/components/Workflow/Editor/WorkflowEdges.vue b/client/src/components/Workflow/Editor/WorkflowEdges.vue
index b481c7fc5e3..36809805069 100644
--- a/client/src/components/Workflow/Editor/WorkflowEdges.vue
+++ b/client/src/components/Workflow/Editor/WorkflowEdges.vue
@@ -26,6 +26,10 @@ const dragStyle = computed(() => {
     }
     return dragStyle;
 });
+
+const dragIsOptional = computed(() => {
+    return props.draggingTerminal?.optional;
+});
 </script>
 <template>
     <div>
@@ -35,7 +39,8 @@ const dragStyle = computed(() => {
                 v-if="draggingTerminal && draggingConnection"
                 :position="draggingConnection"
                 :input-is-mapped-over="false"
-                :output-is-mapped-over="draggingTerminal.mapOver.isCollection"></raw-connector>
+                :output-is-mapped-over="draggingTerminal.mapOver.isCollection"
+                :nullable="dragIsOptional"></raw-connector>
             <terminal-connector
                 v-for="connection in connections"
                 :key="connection.id"
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 32b043304dc..5955056672f 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -105,6 +105,7 @@ export interface NewStep {
     tooltip?: string;
     type: "tool" | "data_input" | "data_collection_input" | "subworkflow" | "parameter_input" | "pause";
     uuid?: string;
+    when?: string;
     workflow_outputs?: WorkflowOutput[];
 }
 
diff --git a/client/src/style/scss/workflow.scss b/client/src/style/scss/workflow.scss
index eb94d9c3dfa..a3ca99cf01d 100644
--- a/client/src/style/scss/workflow.scss
+++ b/client/src/style/scss/workflow.scss
@@ -117,6 +117,9 @@
                 .ribbon-inner-invalid {
                     stroke: $brand-warning;
                 }
+                &.dashed {
+                    stroke-dasharray: 5, 3;
+                }
                 &:hover .ribbon-outer {
                     stroke: $brand-success;
                 }

From f0149e0fe41877e05abb444c3f938e8099cc43f6 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 19 Jan 2023 21:45:04 +0100
Subject: [PATCH 210/350] Add code-branch icon to conditional step header

---
 client/src/components/Workflow/Editor/Node.vue | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index 4e5b6f0fbaf..e51ef1ce727 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -57,6 +57,9 @@
                 </b-popover>
             </b-button-group>
             <i :class="iconClass" />
+            <span v-if="step.when" v-b-tooltip.hover title="This step is conditionally executed.">
+                <font-awesome-icon icon="fa-code-branch" />
+            </span>
             <span
                 v-b-tooltip.hover
                 title="Index of the step in the workflow run form. Steps are ordered by distance to the upper-left corner of the window; inputs are listed first."
@@ -119,9 +122,15 @@ import type { Step } from "@/stores/workflowStepStore";
 import { DatatypesMapperModel } from "@/components/Datatypes/model";
 import type { UseElementBoundingReturn, UseScrollReturn } from "@vueuse/core";
 import { useConnectionStore } from "@/stores/workflowConnectionStore";
+import { faCodeBranch } from "@fortawesome/free-solid-svg-icons";
+import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
+import { library } from "@fortawesome/fontawesome-svg-core";
 
 Vue.use(BootstrapVue);
 
+// @ts-ignore
+library.add(faCodeBranch);
+
 const props = defineProps({
     id: { type: Number, required: true },
     contentId: { type: String as PropType<string | null>, default: null },

From 43c4c6188db057ee2e46ed625a762058076b512a Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 19 Jan 2023 21:46:58 +0100
Subject: [PATCH 211/350] Serialize workflow when attribute

---
 lib/galaxy/managers/workflows.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index 8604cc8dc31..f5cf64d45f7 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -937,6 +937,7 @@ class WorkflowContentsManager(UsesAnnotations):
             else:
                 inputs = step.module.get_runtime_inputs(connections=step.output_connections)
                 step_model = {"inputs": [input.to_dict(trans) for input in inputs.values()]}
+            step_model["when"] = step.when_expression
             step_model["replacement_parameters"] = step.module.get_replacement_parameters(step)
             step_model["step_type"] = step.type
             step_model["step_label"] = step.label
@@ -1131,6 +1132,7 @@ class WorkflowContentsManager(UsesAnnotations):
                 "annotation": annotation_str,
                 "post_job_actions": module.get_post_job_actions({}),
                 "uuid": str(step.uuid) if step.uuid else None,
+                "when": step.when_expression,
                 "workflow_outputs": [],
             }
             if tooltip:
@@ -1363,6 +1365,7 @@ class WorkflowContentsManager(UsesAnnotations):
                 "uuid": str(step.uuid),
                 "label": step.label or None,
                 "annotation": annotation_str,
+                "when": step.when_expression,
             }
             if step.type == "tool":
                 step_dict["tool_id"] = content_id if allow_upgrade else step.tool_id
@@ -1550,6 +1553,7 @@ class WorkflowContentsManager(UsesAnnotations):
                 "annotation": self.get_item_annotation_str(sa_session, stored.user, step),
                 "tool_inputs": step.tool_inputs,
                 "input_steps": {},
+                "when": step.when_expression,
             }
 
             if step_type == "subworkflow":

From b4c7f3dd2d37e494c9d56c4c83a5485d571ca3c1 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 19 Jan 2023 22:34:31 +0100
Subject: [PATCH 212/350] Add UI for conditional steps

---
 .../Workflow/Editor/Forms/FormConditional.vue | 52 +++++++++++++++++++
 .../Workflow/Editor/Forms/FormDefault.test.js |  2 +-
 .../Workflow/Editor/Forms/FormDefault.vue     |  2 +
 .../Workflow/Editor/Forms/FormTool.vue        | 34 ++++++++----
 .../src/components/Workflow/Editor/Index.vue  |  3 ++
 .../src/components/Workflow/Editor/Node.vue   | 33 ++++++++----
 .../components/Workflow/Editor/NodeOutput.vue |  1 -
 .../Workflow/Editor/TerminalConnector.vue     |  2 +-
 .../Workflow/Editor/modules/model.ts          | 20 ++++---
 .../Workflow/Editor/modules/terminals.ts      |  5 +-
 client/src/stores/workflowStepStore.ts        | 31 ++++++++++-
 11 files changed, 152 insertions(+), 33 deletions(-)
 create mode 100644 client/src/components/Workflow/Editor/Forms/FormConditional.vue

diff --git a/client/src/components/Workflow/Editor/Forms/FormConditional.vue b/client/src/components/Workflow/Editor/Forms/FormConditional.vue
new file mode 100644
index 00000000000..77934844c7e
--- /dev/null
+++ b/client/src/components/Workflow/Editor/Forms/FormConditional.vue
@@ -0,0 +1,52 @@
+<script setup lang="ts">
+
+import FormElement from "@/components/Form/FormElement.vue";
+import { computed } from 'vue';
+import type { Step } from '@/stores/workflowStepStore';
+
+const emit = defineEmits<{
+    (e: "onUpdateStep", value: Step): void;
+}>();
+const props = defineProps<{
+    step: Step
+}>();
+
+const conditionalDefined = computed(() => {
+    return Boolean(props.step.when);
+});
+
+function onSkipBoolean(value: boolean) {
+    if (props.step.when && value === false) {
+        emit("onUpdateStep", { ...props.step, when: undefined });
+    } else if (value === true && !props.step.when) {
+        const when = "${inputs.when}";
+        const newStep = {
+            ...props.step,
+            when,
+            input_connections: { ...props.step.input_connections, when: undefined },
+        };
+        emit("onUpdateStep", newStep);
+    }
+}
+
+</script>
+
+<template>
+    <FormElement
+    id="__conditional"
+    :value="conditionalDefined"
+    title="Conditionally skip step?"
+    help="Set to true and connect a boolean parameter that determines whether step will be skipped"
+    type="boolean"
+    @input="onSkipBoolean"></FormElement>
+    <!-- We don't seem to have a disabled text field
+        <FormElement
+            v-if="setConditional"
+            id="__when"
+            :value="step.when"
+            type="text"
+            help="Step will be executed if javascript expression below evaluates to true."
+            >
+        </FormElement>
+    -->
+</template>
\ No newline at end of file
diff --git a/client/src/components/Workflow/Editor/Forms/FormDefault.test.js b/client/src/components/Workflow/Editor/Forms/FormDefault.test.js
index 7ab61f364dd..c5e10e5a3bd 100644
--- a/client/src/components/Workflow/Editor/Forms/FormDefault.test.js
+++ b/client/src/components/Workflow/Editor/Forms/FormDefault.test.js
@@ -40,7 +40,7 @@ describe("FormDefault", () => {
         const title = wrapper.find(".portlet-title-text").text();
         expect(title).toBe("label");
         const inputCount = wrapper.findAll("input").length;
-        expect(inputCount).toBe(3);
+        expect(inputCount).toBe(4);
         const outputLabelCount = wrapper.findAll("#__label__output-name").length;
         expect(outputLabelCount).toBe(1);
         const otherLabelCount = wrapper.findAll("#__label__other-name").length;
diff --git a/client/src/components/Workflow/Editor/Forms/FormDefault.vue b/client/src/components/Workflow/Editor/Forms/FormDefault.vue
index 9f3f77f78c4..90a195bf7c4 100644
--- a/client/src/components/Workflow/Editor/Forms/FormDefault.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormDefault.vue
@@ -39,6 +39,7 @@
                 :area="true"
                 help="Add an annotation or notes to this step. Annotations are available when a workflow is viewed."
                 @input="onAnnotation" />
+            <FormConditional v-if="isSubworkflow" :step="step" v-on="$listeners"/>
             <FormDisplay
                 v-if="configForm?.inputs"
                 :id="formDisplayId"
@@ -61,6 +62,7 @@ import FormDisplay from "@/components/Form/FormDisplay.vue";
 import FormCard from "@/components/Form/FormCard.vue";
 import FormElement from "@/components/Form/FormElement.vue";
 import FormOutputLabel from "@/components/Workflow/Editor/Forms/FormOutputLabel.vue";
+import FormConditional from "./FormConditional.vue"
 import WorkflowIcons from "@/components/Workflow/icons";
 import { useWorkflowStepStore, type Step } from "@/stores/workflowStepStore";
 import { useUniqueLabelError } from "../composables/useUniqueLabelError";
diff --git a/client/src/components/Workflow/Editor/Forms/FormTool.vue b/client/src/components/Workflow/Editor/Forms/FormTool.vue
index 160613d9904..5d6e34023d4 100644
--- a/client/src/components/Workflow/Editor/Forms/FormTool.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormTool.vue
@@ -27,6 +27,7 @@
                     :area="true"
                     help="Add an annotation or notes to this step. Annotations are available when a workflow is viewed."
                     @input="onAnnotation" />
+                <FormConditional :step="step" v-on="$listeners"/>
                 <div class="mt-2 mb-4">
                     <Heading h2 separator bold size="sm"> Tool Parameters </Heading>
                     <FormDisplay
@@ -55,14 +56,15 @@
 </template>
 
 <script>
-import CurrentUser from "components/providers/CurrentUser";
-import FormDisplay from "components/Form/FormDisplay";
-import ToolCard from "components/Tool/ToolCard";
-import FormSection from "./FormSection";
-import FormElement from "components/Form/FormElement";
+import CurrentUser from "@/components/providers/CurrentUser";
+import FormDisplay from "@/components/Form/FormDisplay.vue";
+import ToolCard from "@/components/Tool/ToolCard.vue";
+import FormSection from "./FormSection.vue";
+import FormElement from "@/components/Form/FormElement.vue";
+import FormConditional from "./FormConditional.vue"
 import Utils from "utils/utils";
-import Heading from "components/Common/Heading";
-import { useWorkflowStepStore, Step } from "@/stores/workflowStepStore";
+import Heading from "@/components/Common/Heading.vue";
+import { useWorkflowStepStore,} from "@/stores/workflowStepStore";
 import { useUniqueLabelError } from "../composables/useUniqueLabelError";
 import { useStepProps } from "../composables/useStepProps";
 import { toRef } from "vue";
@@ -73,12 +75,13 @@ export default {
         FormDisplay,
         ToolCard,
         FormElement,
+        FormConditional,
         FormSection,
         Heading,
     },
     props: {
         step: {
-            type: Step,
+            type: Object,
             required: true,
         },
         datatypes: {
@@ -86,13 +89,24 @@ export default {
             required: true,
         },
     },
-    setup(props) {
+    emits: ["onSetData", "onUpdateStep", "onChangePostJobActions", "onAnnotation", "onLabel"],
+    setup(props, { emit }) {
         const { stepId, annotation, label, stepInputs, stepOutputs, configForm, postJobActions } = useStepProps(
             toRef(props, "step")
         );
         const stepStore = useWorkflowStepStore();
         const uniqueErrorLabel = useUniqueLabelError(stepStore, label);
-        return { stepId, annotation, label, stepInputs, stepOutputs, configForm, postJobActions, uniqueErrorLabel };
+
+        return {
+            stepId,
+            annotation,
+            label,
+            stepInputs,
+            stepOutputs,
+            configForm,
+            postJobActions,
+            uniqueErrorLabel,
+        };
     },
     data() {
         return {
diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index 6e55f451e03..a682769f5ec 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -113,6 +113,7 @@
                                     @onChangePostJobActions="onChangePostJobActions"
                                     @onAnnotation="onAnnotation"
                                     @onLabel="onLabel"
+                                    @onUpdateStep="onUpdateStep"
                                     @onSetData="onSetData" />
                                 <FormDefault
                                     v-else-if="hasActiveNodeDefault"
@@ -122,6 +123,7 @@
                                     @onLabel="onLabel"
                                     @onEditSubworkflow="onEditSubworkflow"
                                     @onAttemptRefactor="onAttemptRefactor"
+                                    @onUpdateStep="onUpdateStep"
                                     @onSetData="onSetData" />
                                 <WorkflowAttributes
                                     v-else-if="showAttributes"
@@ -642,6 +644,7 @@ export default {
                 name: name,
                 content_id: contentId,
                 type: type,
+                outputs: [],
                 position: defaultPosition(this.graphOffset, this.transform),
                 post_job_actions: {},
             };
diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index e51ef1ce727..ee5e33c3efb 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -122,6 +122,7 @@ import type { Step } from "@/stores/workflowStepStore";
 import { DatatypesMapperModel } from "@/components/Datatypes/model";
 import type { UseElementBoundingReturn, UseScrollReturn } from "@vueuse/core";
 import { useConnectionStore } from "@/stores/workflowConnectionStore";
+import { useWorkflowStepStore } from "@/stores/workflowStepStore";
 import { faCodeBranch } from "@fortawesome/free-solid-svg-icons";
 import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
 import { library } from "@fortawesome/fontawesome-svg-core";
@@ -173,6 +174,7 @@ const postJobActions = computed(() => props.step.post_job_actions || {});
 const workflowOutputs = computed(() => props.step.workflow_outputs || []);
 const connectionStore = useConnectionStore();
 const stateStore = useWorkflowStateStore();
+const stepStore = useWorkflowStepStore();
 const isLoading = computed(() => Boolean(stateStore.getStepLoadingState(props.id)?.loading));
 useNodePosition(el, props.id, stateStore);
 const title = computed(() => props.step.label || props.step.name);
@@ -195,19 +197,22 @@ const style = computed(() => {
     return { top: props.step.position!.top + "px", left: props.step.position!.left + "px" };
 });
 const errors = computed(() => props.step.errors || stateStore.getStepLoadingState(props.id)?.error);
-const invalidInputs = computed(() => {
+const inputs = computed(() => {
     const connections = connectionStore.getConnectionsForStep(props.id);
-    const invalidConnections = connections.filter(
-        (connection) =>
-            connection.input.stepId == props.id &&
-            !props.step.inputs.find((input) => input.name === connection.input.name)
-    );
-    const invalidInputNames = [...new Set(invalidConnections.map((connection) => connection.input.name))];
-    return invalidInputNames.map((name) => {
+    const extraStepInputs = stepStore.getStepExtraInputs(props.id);
+    const stepInputs = [...extraStepInputs, ...(props.step.inputs || [])];
+    const unknownInputs: string[] = [];
+    connections.forEach((connection) => {
+        if (connection.input.stepId == props.id && !stepInputs.find((input) => input.name === connection.input.name)) {
+            unknownInputs.push(connection.input.name);
+        }
+    });
+    const invalidInputNames = [...new Set(unknownInputs)];
+    const invalidInputTerminalSource = invalidInputNames.map((name) => {
         return { name, optional: false, extensions: [], valid: false, input_type: "dataset" };
     });
+    return [...stepInputs, ...invalidInputTerminalSource];
 });
-const inputs = computed(() => [...props.step.inputs, ...invalidInputs.value]);
 const invalidOutputs = computed(() => {
     const connections = connectionStore.getConnectionsForStep(props.id);
     const invalidConnections = connections.filter(
@@ -220,7 +225,15 @@ const invalidOutputs = computed(() => {
         return { name, optional: false, datatypes: [], valid: false };
     });
 });
-const outputs = computed(() => [...props.step.outputs, ...invalidOutputs.value]);
+const outputs = computed(() => {
+    let stepOutputs = props.step.outputs;
+    if (props.step.when) {
+        stepOutputs = stepOutputs.map((output) => {
+            return { ...output, optional: true };
+        });
+    }
+    return [...stepOutputs, ...invalidOutputs.value];
+});
 
 function onMoveTo(position: XYPosition) {
     emit("onUpdateStepPosition", props.id, {
diff --git a/client/src/components/Workflow/Editor/NodeOutput.vue b/client/src/components/Workflow/Editor/NodeOutput.vue
index b7109d645e9..34b7301f66b 100644
--- a/client/src/components/Workflow/Editor/NodeOutput.vue
+++ b/client/src/components/Workflow/Editor/NodeOutput.vue
@@ -183,7 +183,6 @@ export default {
         function onToggleActive() {
             const step = stepStore.getStep(stepId.value);
             if (workflowOutput.value) {
-                console.log("wfo", workflowOutput.value);
                 step.workflow_outputs = step.workflow_outputs.filter(
                     (workflowOutput) => workflowOutput.output_name !== output.value.name
                 );
diff --git a/client/src/components/Workflow/Editor/TerminalConnector.vue b/client/src/components/Workflow/Editor/TerminalConnector.vue
index 1b0d12bd214..9700c452dd3 100644
--- a/client/src/components/Workflow/Editor/TerminalConnector.vue
+++ b/client/src/components/Workflow/Editor/TerminalConnector.vue
@@ -36,7 +36,7 @@ const outputIsOptional = computed(() => {
 // move into connection store ?
 // move all of terminal logic into connection store ?
 const connectionIsValid = computed(() => {
-    return !Boolean(connectionStore.invalidConnections[props.connection.id]);
+    return !connectionStore.invalidConnections[props.connection.id];
 });
 
 const stateStore = useWorkflowStateStore();
diff --git a/client/src/components/Workflow/Editor/modules/model.ts b/client/src/components/Workflow/Editor/modules/model.ts
index 03c9b6982c7..086c6d2fdbc 100644
--- a/client/src/components/Workflow/Editor/modules/model.ts
+++ b/client/src/components/Workflow/Editor/modules/model.ts
@@ -27,16 +27,20 @@ export async function fromSimple(data: Workflow, appendData = false, defaultPosi
             step.position.left += defaultPosition.left;
             step.position.top += defaultPosition.top;
             Object.values(step.input_connections).forEach((link) => {
-                let linkArray: ConnectionOutputLink[];
-                if (!Array.isArray(link)) {
-                    linkArray = [link];
+                if (link === undefined) {
+                    console.error("input connections invalid", step.input_connections)
                 } else {
-                    linkArray = link;
+                    let linkArray: ConnectionOutputLink[];
+                    if (!Array.isArray(link)) {
+                        linkArray = [link];
+                    } else {
+                        linkArray = link;
+                    }
+                    linkArray.forEach((link) => {
+                        link.id += stepIdOffset;
+                    });
                 }
-                linkArray.forEach((link) => {
-                    link.id += stepIdOffset;
-                });
-            });
+           });
         }
     });
     Object.values(data.steps).map((step) => {
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 536554ecfa6..29e5231199e 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -576,7 +576,10 @@ class BaseOutputTerminal extends Terminal {
     getConnectedTerminals(): InputTerminalsAndInvalid[] {
         return this.connections.map((connection) => {
             const inputStep = this.stepStore.getStep(connection.input.stepId);
-            const terminalSource = inputStep.inputs.find((input) => input.name === connection.input.name);
+            const extraStepInput = this.stepStore.getStepExtraInputs(inputStep.id);
+            const terminalSource = [...extraStepInput, ...inputStep.inputs].find(
+                (input) => input.name === connection.input.name
+            );
             if (!terminalSource) {
                 return new InvalidInputTerminal({
                     valid: false,
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 5955056672f..61c0ee0735c 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -118,7 +118,7 @@ export interface Steps {
 }
 
 export interface StepInputConnection {
-    [index: string]: ConnectionOutputLink | ConnectionOutputLink[];
+    [index: string]: ConnectionOutputLink | ConnectionOutputLink[] | undefined;
 }
 
 export interface ConnectionOutputLink {
@@ -145,6 +145,32 @@ export const useWorkflowStepStore = defineStore("workflowStepStore", {
                 return state.steps[stepId.toString()];
             };
         },
+        getStepExtraInputs(state: State) {
+            const extraInputs: { [index: number]: InputTerminalSource[] } = {};
+            Object.values(state.steps).forEach((step) => {
+                if (step?.when !== undefined) {
+                    Object.keys(step.input_connections).forEach((inputName) => {
+                        if (!step.inputs.find((input) => input.name === inputName) && step.when?.includes(inputName)) {
+                            const terminalSource = {
+                                name: inputName,
+                                optional: false,
+                                input_type: "parameter" as const,
+                                type: "boolean" as const,
+                                multiple: false,
+                                label: inputName,
+                                extensions: [],
+                            };
+                            if (extraInputs[step.id]) {
+                                extraInputs[step.id].push(terminalSource);
+                            } else {
+                                extraInputs[step.id] = [terminalSource];
+                            }
+                        }
+                    });
+                }
+            });
+            return (stepId: number) => extraInputs[stepId] || [];
+        },
         getStepIndex(state: State) {
             return Math.max(...Object.values(state.steps).map((step) => step.id), state.stepIndex);
         },
@@ -217,6 +243,9 @@ export function stepToConnections(step: Step): Connection[] {
     const connections: Connection[] = [];
     if (step.input_connections) {
         Object.entries(step?.input_connections).forEach(([input_name, outputArray]) => {
+            if (outputArray === undefined) {
+                return
+            }
             if (!Array.isArray(outputArray)) {
                 outputArray = [outputArray];
             }

From 0780f24f82ac4b93f9fcbd4342eaabf156387fbc Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 19 Jan 2023 23:07:57 +0100
Subject: [PATCH 213/350] Fix subworkflow title in sidepanel

---
 .../Workflow/Editor/Forms/FormConditional.vue | 22 +++++++++----------
 .../Workflow/Editor/Forms/FormDefault.vue     | 15 ++++++++++---
 .../Workflow/Editor/Forms/FormTool.vue        |  6 ++---
 .../Workflow/Editor/modules/model.ts          |  4 ++--
 client/src/stores/workflowStepStore.ts        |  2 +-
 5 files changed, 28 insertions(+), 21 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Forms/FormConditional.vue b/client/src/components/Workflow/Editor/Forms/FormConditional.vue
index 77934844c7e..b3dd431b481 100644
--- a/client/src/components/Workflow/Editor/Forms/FormConditional.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormConditional.vue
@@ -1,14 +1,13 @@
 <script setup lang="ts">
-
 import FormElement from "@/components/Form/FormElement.vue";
-import { computed } from 'vue';
-import type { Step } from '@/stores/workflowStepStore';
+import { computed } from "vue";
+import type { Step } from "@/stores/workflowStepStore";
 
 const emit = defineEmits<{
     (e: "onUpdateStep", value: Step): void;
 }>();
 const props = defineProps<{
-    step: Step
+    step: Step;
 }>();
 
 const conditionalDefined = computed(() => {
@@ -28,17 +27,16 @@ function onSkipBoolean(value: boolean) {
         emit("onUpdateStep", newStep);
     }
 }
-
 </script>
 
 <template>
     <FormElement
-    id="__conditional"
-    :value="conditionalDefined"
-    title="Conditionally skip step?"
-    help="Set to true and connect a boolean parameter that determines whether step will be skipped"
-    type="boolean"
-    @input="onSkipBoolean"></FormElement>
+        id="__conditional"
+        :value="conditionalDefined"
+        title="Conditionally skip step?"
+        help="Set to true and connect a boolean parameter that determines whether step will be skipped"
+        type="boolean"
+        @input="onSkipBoolean"></FormElement>
     <!-- We don't seem to have a disabled text field
         <FormElement
             v-if="setConditional"
@@ -49,4 +47,4 @@ function onSkipBoolean(value: boolean) {
             >
         </FormElement>
     -->
-</template>
\ No newline at end of file
+</template>
diff --git a/client/src/components/Workflow/Editor/Forms/FormDefault.vue b/client/src/components/Workflow/Editor/Forms/FormDefault.vue
index 90a195bf7c4..6e2a47cbd0d 100644
--- a/client/src/components/Workflow/Editor/Forms/FormDefault.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormDefault.vue
@@ -39,7 +39,7 @@
                 :area="true"
                 help="Add an annotation or notes to this step. Annotations are available when a workflow is viewed."
                 @input="onAnnotation" />
-            <FormConditional v-if="isSubworkflow" :step="step" v-on="$listeners"/>
+            <FormConditional v-if="isSubworkflow" :step="step" v-on="$listeners" />
             <FormDisplay
                 v-if="configForm?.inputs"
                 :id="formDisplayId"
@@ -62,7 +62,7 @@ import FormDisplay from "@/components/Form/FormDisplay.vue";
 import FormCard from "@/components/Form/FormCard.vue";
 import FormElement from "@/components/Form/FormElement.vue";
 import FormOutputLabel from "@/components/Workflow/Editor/Forms/FormOutputLabel.vue";
-import FormConditional from "./FormConditional.vue"
+import FormConditional from "./FormConditional.vue";
 import WorkflowIcons from "@/components/Workflow/icons";
 import { useWorkflowStepStore, type Step } from "@/stores/workflowStepStore";
 import { useUniqueLabelError } from "../composables/useUniqueLabelError";
@@ -79,7 +79,16 @@ const stepRef = toRef(props, "step");
 const { stepId, contentId, annotation, label, name, type, configForm } = useStepProps(stepRef);
 const stepStore = useWorkflowStepStore();
 const uniqueErrorLabel = useUniqueLabelError(stepStore, label?.value);
-const stepTitle = computed(() => (label?.value || contentId?.value || name.value)!);
+const stepTitle = computed(() => {
+    if (label?.value) {
+        return label.value;
+    }
+    if (isSubworkflow.value) {
+        return name.value;
+    } else {
+        return contentId?.value || name.value;
+    }
+});
 const nodeIcon = computed(() => WorkflowIcons[type.value]);
 const formDisplayId = computed(() => stepId.value.toString());
 const isSubworkflow = computed(() => type.value === "subworkflow");
diff --git a/client/src/components/Workflow/Editor/Forms/FormTool.vue b/client/src/components/Workflow/Editor/Forms/FormTool.vue
index 5d6e34023d4..609447c15a9 100644
--- a/client/src/components/Workflow/Editor/Forms/FormTool.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormTool.vue
@@ -27,7 +27,7 @@
                     :area="true"
                     help="Add an annotation or notes to this step. Annotations are available when a workflow is viewed."
                     @input="onAnnotation" />
-                <FormConditional :step="step" v-on="$listeners"/>
+                <FormConditional :step="step" v-on="$listeners" />
                 <div class="mt-2 mb-4">
                     <Heading h2 separator bold size="sm"> Tool Parameters </Heading>
                     <FormDisplay
@@ -61,10 +61,10 @@ import FormDisplay from "@/components/Form/FormDisplay.vue";
 import ToolCard from "@/components/Tool/ToolCard.vue";
 import FormSection from "./FormSection.vue";
 import FormElement from "@/components/Form/FormElement.vue";
-import FormConditional from "./FormConditional.vue"
+import FormConditional from "./FormConditional.vue";
 import Utils from "utils/utils";
 import Heading from "@/components/Common/Heading.vue";
-import { useWorkflowStepStore,} from "@/stores/workflowStepStore";
+import { useWorkflowStepStore } from "@/stores/workflowStepStore";
 import { useUniqueLabelError } from "../composables/useUniqueLabelError";
 import { useStepProps } from "../composables/useStepProps";
 import { toRef } from "vue";
diff --git a/client/src/components/Workflow/Editor/modules/model.ts b/client/src/components/Workflow/Editor/modules/model.ts
index 086c6d2fdbc..b36c494a6b3 100644
--- a/client/src/components/Workflow/Editor/modules/model.ts
+++ b/client/src/components/Workflow/Editor/modules/model.ts
@@ -28,7 +28,7 @@ export async function fromSimple(data: Workflow, appendData = false, defaultPosi
             step.position.top += defaultPosition.top;
             Object.values(step.input_connections).forEach((link) => {
                 if (link === undefined) {
-                    console.error("input connections invalid", step.input_connections)
+                    console.error("input connections invalid", step.input_connections);
                 } else {
                     let linkArray: ConnectionOutputLink[];
                     if (!Array.isArray(link)) {
@@ -40,7 +40,7 @@ export async function fromSimple(data: Workflow, appendData = false, defaultPosi
                         link.id += stepIdOffset;
                     });
                 }
-           });
+            });
         }
     });
     Object.values(data.steps).map((step) => {
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 61c0ee0735c..95e4fbe687c 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -244,7 +244,7 @@ export function stepToConnections(step: Step): Connection[] {
     if (step.input_connections) {
         Object.entries(step?.input_connections).forEach(([input_name, outputArray]) => {
             if (outputArray === undefined) {
-                return
+                return;
             }
             if (!Array.isArray(outputArray)) {
                 outputArray = [outputArray];

From c8b0dae33402b8d2b961f80f4ad6de25c0b4db61 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 13:36:08 +0100
Subject: [PATCH 214/350] Fix view migration for sqlite

---
 ...04_add_skipped_state_to_collection_job_.py | 51 +++++++++++++++----
 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
index 86fd5053e49..f05d819e50f 100644
--- a/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
@@ -5,8 +5,16 @@ Revises: 3100452fa030
 Create Date: 2023-01-16 11:53:59.783836
 
 """
-from alembic import op
+from typing import Generator
+
+from alembic import (
+    context,
+    op,
+)
 from alembic_utils.pg_view import PGView
+from sqlalchemy import text as sql_text
+from sqlalchemy.engine.url import make_url
+from sqlalchemy.sql.elements import TextClause
 
 from galaxy.model.view import HistoryDatasetCollectionJobStateSummary
 
@@ -53,18 +61,39 @@ GROUP BY jobstates.hdca_id
 """
 
 
+class SqlitePGView(PGView):
+    def to_sql_statement_create_or_replace(self) -> Generator[TextClause, None, None]:
+        """Generates a SQL "create or replace view" statement"""
+
+        yield sql_text(f"""DROP VIEW IF EXISTS {self.literal_schema}."{self.signature}";""")
+        yield sql_text(f"""CREATE VIEW {self.literal_schema}."{self.signature}" AS {self.definition};""")
+
+
+def get_view_instance(definition: str):
+
+    try:
+        url = make_url(context.config.get_main_option("sqlalchemy.url"))
+        dialect = url.get_dialect().name
+    except Exception:
+        # If someone's doing offline migrations they're probably using postgrea
+        dialect = "postgresql"
+    if dialect == "postgresql":
+        ViewClass = PGView
+        schema = "public"
+    elif dialect == "sqlite":
+        ViewClass = SqlitePGView
+        schema = "main"
+    else:
+        raise Exception(f"Don't know how to generate view for dialect '{dialect}'")
+    return ViewClass(schema=schema, signature="collection_job_state_summary_view", definition=definition)
+
+
 def upgrade():
-    public_collection_job_state_summary_view = PGView(
-        schema="public",
-        signature="collection_job_state_summary_view",
-        definition=HistoryDatasetCollectionJobStateSummary.aggregate_state_query,
-    )
+    view = get_view_instance(HistoryDatasetCollectionJobStateSummary.aggregate_state_query)
     # op.replace_entity comes from alembic_utils plugin
-    op.replace_entity(public_collection_job_state_summary_view)  # type: ignore[attr-defined]
+    op.replace_entity(view)  # type: ignore[attr-defined]
 
 
 def downgrade():
-    public_collection_job_state_summary_view = PGView(
-        schema="public", signature="collection_job_state_summary_view", definition=PREVIOUS_AGGREGATE_QUERY
-    )
-    op.replace_entity(public_collection_job_state_summary_view)  # type: ignore[attr-defined]
+    view = get_view_instance(PREVIOUS_AGGREGATE_QUERY)
+    op.replace_entity(view)  # type: ignore[attr-defined]

From 6f65a2675c10b1df100ef3c490ed494fce08488f Mon Sep 17 00:00:00 2001
From: Marius van den Beek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 14:15:34 +0100
Subject: [PATCH 215/350] Fix postgres typo

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 .../c39f1de47a04_add_skipped_state_to_collection_job_.py        | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
index f05d819e50f..8474c471106 100644
--- a/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
+++ b/lib/galaxy/model/migrations/alembic/versions_gxy/c39f1de47a04_add_skipped_state_to_collection_job_.py
@@ -75,7 +75,7 @@ def get_view_instance(definition: str):
         url = make_url(context.config.get_main_option("sqlalchemy.url"))
         dialect = url.get_dialect().name
     except Exception:
-        # If someone's doing offline migrations they're probably using postgrea
+        # If someone's doing offline migrations they're probably using PostgreSQL
         dialect = "postgresql"
     if dialect == "postgresql":
         ViewClass = PGView

From f7dece8af37f199c0c494e88391ef5cb2e27ac6e Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 08:59:48 -0500
Subject: [PATCH 216/350] Fix prefix handling in annotate_image

---
 .../visualizations/annotate_image/src/script.js      | 12 +++++++++---
 config/plugins/visualizations/ngl/src/ngl.js         |  2 +-
 config/plugins/visualizations/pv/src/pv.js           |  2 +-
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/config/plugins/visualizations/annotate_image/src/script.js b/config/plugins/visualizations/annotate_image/src/script.js
index e8167257e4f..c9eaaf692fe 100644
--- a/config/plugins/visualizations/annotate_image/src/script.js
+++ b/config/plugins/visualizations/annotate_image/src/script.js
@@ -5,6 +5,12 @@ import _ from "underscore";
 // Use lighter weight 'core' version of paper since we don't need paperscript
 import paper from "../node_modules/paper/dist/paper-core.js";
 
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 const CommandManager = (function() {
     function CommandManager() {}
 
@@ -437,12 +443,12 @@ window.bundleEntries.load = function (opt) {
         });
     };
 
-    const safe_download_url = `${options.root}${dataset.download_url}`;
+    const downloadUrl = prefixedDownloadUrl(options.root, dataset.download_url);
     $.ajax({
-        url: safe_download_url,
+        url: downloadUrl,
         success: function(content) {
             const $chartViewer = $("#" + opt.target);
-            $chartViewer.html("<img id='image-annotate' src='" + safe_download_url + "' />");
+            $chartViewer.html("<img id='image-annotate' src='" + downloadUrl + "' />");
             $chartViewer.css("overflow", "auto");
             $chartViewer.css("position", "relative");
             const $image = $chartViewer.find("img");
diff --git a/config/plugins/visualizations/ngl/src/ngl.js b/config/plugins/visualizations/ngl/src/ngl.js
index 65dc0c67038..5d9ee9cfd6f 100644
--- a/config/plugins/visualizations/ngl/src/ngl.js
+++ b/config/plugins/visualizations/ngl/src/ngl.js
@@ -5,7 +5,7 @@ function asBoolean(value) {
     return String(value).toLowerCase() == "true";
 }
 
-/* This should be part of the charts/viz standard lib */
+/* This will be part of the charts/viz standard lib in 23.1 */
 const slashCleanup = /(\/)+/g;
 function prefixedDownloadUrl(root, path) {
     return `${root}/${path}`.replace(slashCleanup, "/");
diff --git a/config/plugins/visualizations/pv/src/pv.js b/config/plugins/visualizations/pv/src/pv.js
index 529554a9142..6dc41a292a5 100644
--- a/config/plugins/visualizations/pv/src/pv.js
+++ b/config/plugins/visualizations/pv/src/pv.js
@@ -1,6 +1,6 @@
 import * as pv from "bio-pv";
 
-/* This should be part of the charts/viz standard lib */
+/* This will be part of the charts/viz standard lib in 23.1 */
 const slashCleanup = /(\/)+/g;
 function prefixedDownloadUrl(root, path) {
     return `${root}/${path}`.replace(slashCleanup, "/");

From 2e222b5b21d4e1b037f85bc7e1fef0947244d3d6 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 11:26:02 +0100
Subject: [PATCH 217/350] Fix node input and output positions when inputs
 change

---
 client/src/components/Workflow/Editor/Node.vue | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index ee5e33c3efb..3a475c5ceb2 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -72,8 +72,8 @@
         </b-alert>
         <div v-else class="node-body" @click="makeActive" @keyup.enter="makeActive">
             <node-input
-                v-for="input in inputs"
-                :key="input.name"
+                v-for="(input, index) in inputs"
+                :key="`${index}-${input.name}`"
                 :input="input"
                 :step-id="id"
                 :datatypes-mapper="datatypesMapper"
@@ -85,8 +85,8 @@
                 @onChange="onChange" />
             <div v-if="showRule" class="rule" />
             <node-output
-                v-for="output in outputs"
-                :key="output.name"
+                v-for="(output, index) in outputs"
+                :key="`${index + inputs.length}-${output.name}`"
                 :output="output"
                 :workflow-outputs="workflowOutputs"
                 :post-job-actions="postJobActions"

From 117f10a812d041129a919d34db59752082a68c20 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 12:36:03 +0100
Subject: [PATCH 218/350] Show reason if hover over invalid terminal disconnect
 button

---
 .../components/Workflow/Editor/NodeInput.vue  | 35 ++++++++++++-------
 .../Workflow/Editor/modules/terminals.test.ts |  2 +-
 .../Workflow/Editor/modules/terminals.ts      |  4 +--
 3 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/client/src/components/Workflow/Editor/NodeInput.vue b/client/src/components/Workflow/Editor/NodeInput.vue
index a75ef9242ec..c0f89069fd2 100644
--- a/client/src/components/Workflow/Editor/NodeInput.vue
+++ b/client/src/components/Workflow/Editor/NodeInput.vue
@@ -9,7 +9,13 @@
             @dragleave.prevent="dragLeave">
             <div :id="iconId" ref="el" v-b-tooltip.manual class="icon" :title="reason" />
         </div>
-        <div v-if="showRemove" class="delete-terminal" @click="onRemove" @keyup.delete="onRemove" />
+        <div
+            v-if="showRemove"
+            v-b-tooltip.hover
+            :title="reason"
+            class="delete-terminal"
+            @click="onRemove"
+            @keyup.delete="onRemove" />
         {{ label }}
     </div>
 </template>
@@ -24,7 +30,7 @@ import { storeToRefs } from "pinia";
 import { useTerminal } from "./composables/useTerminal";
 import { DatatypesMapperModel } from "@/components/Datatypes/model";
 import { useWorkflowStateStore } from "@/stores/workflowEditorStateStore";
-import { terminalFactory } from "@/components/Workflow/Editor/modules/terminals";
+import { terminalFactory, ConnectionAcceptable } from "@/components/Workflow/Editor/modules/terminals";
 
 export default {
     props: {
@@ -86,12 +92,23 @@ export default {
         const connections = computed(() => {
             return connectionStore.getConnectionsForTerminal(id.value);
         });
-        const invalidConnections = computed(() =>
-            connections.value.filter((connection) => connectionStore.invalidConnections[connection.id])
+        const invalidConnectionReasons = computed(() =>
+            connections.value
+                .map((connection) => connectionStore.invalidConnections[connection.id])
+                .filter((reason) => reason)
         );
 
+        const canAccept = computed(() => {
+            if (draggingTerminal.value) {
+                return terminal.value.canAccept(draggingTerminal.value);
+            } else if (invalidConnectionReasons.value.length) {
+                return new ConnectionAcceptable(false, invalidConnectionReasons.value[0]);
+            }
+            return null;
+        });
+
         const showRemove = computed(() => {
-            if (invalidConnections.value.length > 0) {
+            if (invalidConnectionReasons.value.length > 0) {
                 return true;
             } else {
                 return terminalIsHovered.value && connections.value.length > 0;
@@ -102,11 +119,11 @@ export default {
             el,
             position,
             isDragging,
-            draggingTerminal,
             connectionStore,
             id,
             iconId,
             rowClass,
+            canAccept,
             hasTerminals,
             terminal,
             stateStore,
@@ -131,12 +148,6 @@ export default {
         label() {
             return this.input.label || this.input.name;
         },
-        canAccept() {
-            if (this.draggingTerminal) {
-                return this.terminal.canAccept(this.draggingTerminal);
-            }
-            return null;
-        },
         reason() {
             const reason = this.canAccept?.reason;
             return reason;
diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 738232bc50d..4d41492bc86 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -143,7 +143,7 @@ describe("canAccept", () => {
         const dataOut = terminals["simple data"]["out_file1"] as OutputTerminal;
         const dataIn = terminals["simple data"]["input"] as InputTerminal;
         expect(dataIn.canAccept(dataOut).canAccept).toBe(false);
-        expect(dataIn.canAccept(dataOut).reason).toBe("Cannot connection output to input of same step.");
+        expect(dataIn.canAccept(dataOut).reason).toBe("Cannot connect output to input of same step.");
     });
     it("rejects paired input on multi-data input", () => {
         const multiDataIn = terminals["multi data"]["f1"] as InputTerminal;
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 29e5231199e..dbdfa175c2b 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -19,7 +19,7 @@ import type {
 } from "@/stores/workflowStepStore";
 import type { DatatypesMapperModel } from "@/components/Datatypes/model";
 
-class ConnectionAcceptable {
+export class ConnectionAcceptable {
     reason: string | null;
     canAccept: boolean;
     constructor(canAccept: boolean, reason: string | null) {
@@ -179,7 +179,7 @@ class BaseInputTerminal extends Terminal {
     }
     canAccept(outputTerminal: BaseOutputTerminal) {
         if (this.stepId == outputTerminal.stepId) {
-            return new ConnectionAcceptable(false, "Cannot connection output to input of same step.");
+            return new ConnectionAcceptable(false, "Cannot connect output to input of same step.");
         }
         if (this._inputFilled()) {
             return new ConnectionAcceptable(

From 5c5dced6be6818ca1e5d2786906e686185273a48 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 12:40:23 +0100
Subject: [PATCH 219/350] Validate/invalidate when toggling step's conditional
 state

---
 .../Workflow/Editor/modules/terminals.ts          | 15 +++++++++++----
 client/src/stores/workflowConnectionStore.ts      |  7 +++++--
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index dbdfa175c2b..4efe198c526 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -318,6 +318,9 @@ class BaseInputTerminal extends Terminal {
                 });
             }
             const postJobActionKey = `ChangeDatatypeAction${connection.output.name}`;
+            if (outputStep.when) {
+                terminalSource = { ...terminalSource, optional: true };
+            }
             if (
                 "extensions" in terminalSource &&
                 outputStep.post_job_actions &&
@@ -335,10 +338,12 @@ class BaseInputTerminal extends Terminal {
     getInvalidConnectedTerminals() {
         return this.getConnectedTerminals().filter((terminal) => {
             const canAccept = this.attachable(terminal);
+            const connectionId = `${this.stepId}-${this.name}-${terminal.stepId}-${terminal.name}`;
             if (!canAccept.canAccept) {
-                const connectionId = `${this.stepId}-${this.name}-${terminal.stepId}-${terminal.name}`;
-                this.connectionStore.addInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
+                this.connectionStore.markInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
                 return true;
+            } else if (this.connectionStore.invalidConnections[connectionId]) {
+                this.connectionStore.dropFromInvalidConnections(connectionId);
             }
             return false;
         });
@@ -601,10 +606,12 @@ class BaseOutputTerminal extends Terminal {
     getInvalidConnectedTerminals() {
         return this.getConnectedTerminals().filter((terminal: any) => {
             const canAccept = terminal.attachable(this);
+            const connectionId = `${terminal.stepId}-${terminal.name}-${this.stepId}-${this.name}`;
             if (!canAccept.canAccept) {
-                const connectionId = `${terminal.stepId}-${terminal.name}-${this.stepId}-${this.name}`;
-                this.connectionStore.addInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
+                this.connectionStore.markInvalidConnection(connectionId, canAccept.reason ?? "Unknown");
                 return true;
+            } else if (this.connectionStore.invalidConnections[connectionId]) {
+                this.connectionStore.dropFromInvalidConnections(connectionId);
             }
             return false;
         });
diff --git a/client/src/stores/workflowConnectionStore.ts b/client/src/stores/workflowConnectionStore.ts
index b28b28854f9..627f5df5525 100644
--- a/client/src/stores/workflowConnectionStore.ts
+++ b/client/src/stores/workflowConnectionStore.ts
@@ -4,7 +4,7 @@ import { state } from "@/store/tagStore";
 import Vue from "vue";
 
 interface InvalidConnections {
-    [index: string]: string;
+    [index: string]: string | undefined;
 }
 
 export interface State {
@@ -120,9 +120,12 @@ export const useConnectionStore = defineStore("workflowConnectionStore", {
             const stepStore = useWorkflowStepStore();
             stepStore.addConnection(connection);
         },
-        addInvalidConnection(this: State, connectionId: string, reason: string) {
+        markInvalidConnection(this: State, connectionId: string, reason: string) {
             Vue.set(this.invalidConnections, connectionId, reason);
         },
+        dropFromInvalidConnections(this: State, connectionId: string) {
+            this.invalidConnections[connectionId] = undefined;
+        },
         removeConnection(this: State, terminal: InputTerminal | OutputTerminal | Connection["id"]) {
             const stepStore = useWorkflowStepStore();
             this.connections = this.connections.filter((connection) => {

From d3f55406473459bcc93239bdec92adae232dbafa Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 14:57:39 +0100
Subject: [PATCH 220/350] Assert that connections are invalid, instead of
 auto-destroyed

---
 client/src/utils/navigation/navigation.yml       | 1 +
 lib/galaxy_test/selenium/test_workflow_editor.py | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/client/src/utils/navigation/navigation.yml b/client/src/utils/navigation/navigation.yml
index 5b8a7a8120c..416d3b7644b 100644
--- a/client/src/utils/navigation/navigation.yml
+++ b/client/src/utils/navigation/navigation.yml
@@ -643,6 +643,7 @@ workflow_editor:
         //div[@data-label='Remove Tags']//input
     tool_version_button: ".tool-versions"
     connector_for: "#connection-${sink_id}-${source_id}"
+    connector_invalid_for: "#connection-${sink_id}-${source_id} .ribbon-inner-invalid"
     connector_destroy_callout: '.delete-terminal'
     save_button: '.editor-button-save'
     state_modal_body: '.state-upgrade-modal'
diff --git a/lib/galaxy_test/selenium/test_workflow_editor.py b/lib/galaxy_test/selenium/test_workflow_editor.py
index f58142eef8b..f907926eb07 100644
--- a/lib/galaxy_test/selenium/test_workflow_editor.py
+++ b/lib/galaxy_test/selenium/test_workflow_editor.py
@@ -557,7 +557,7 @@ steps:
         editor.select_datatype_text_search.wait_for_and_send_keys("bam")
         editor.select_datatype(datatype="bam").wait_for_and_click()
         editor.node.output_data_row(output_name="out_file1", extension="bam").wait_for_visible()
-        self.assert_not_connected("create_2#out_file1", "checksum#input")
+        self.assert_connection_invalid("create_2#out_file1", "checksum#input")
 
     @selenium_test
     def test_change_datatype_post_job_action_lost_regression(self):
@@ -862,6 +862,10 @@ steps:
         source_id, sink_id = self.workflow_editor_source_sink_terminal_ids(source, sink)
         self.components.workflow_editor.connector_for(source_id=source_id, sink_id=sink_id).wait_for_visible()
 
+    def assert_connection_invalid(self, source, sink):
+        source_id, sink_id = self.workflow_editor_source_sink_terminal_ids(source, sink)
+        self.components.workflow_editor.connector_invalid_for(source_id=source_id, sink_id=sink_id).wait_for_present()
+
     def assert_not_connected(self, source, sink):
         source_id, sink_id = self.workflow_editor_source_sink_terminal_ids(source, sink)
         self.components.workflow_editor.connector_for(source_id=source_id, sink_id=sink_id).wait_for_absent()

From 192586a5f2cc6d13a025c608adfa3790c6cad675 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 09:02:50 -0500
Subject: [PATCH 221/350] Bug in annotate_image options handling

---
 config/plugins/visualizations/annotate_image/src/script.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/config/plugins/visualizations/annotate_image/src/script.js b/config/plugins/visualizations/annotate_image/src/script.js
index c9eaaf692fe..d97fe758420 100644
--- a/config/plugins/visualizations/annotate_image/src/script.js
+++ b/config/plugins/visualizations/annotate_image/src/script.js
@@ -443,7 +443,7 @@ window.bundleEntries.load = function (opt) {
         });
     };
 
-    const downloadUrl = prefixedDownloadUrl(options.root, dataset.download_url);
+    const downloadUrl = prefixedDownloadUrl(opt.root, dataset.download_url);
     $.ajax({
         url: downloadUrl,
         success: function(content) {

From 96d0b0585c983d26e6254856d628d403732a0eea Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 09:24:12 -0500
Subject: [PATCH 222/350] Fix prefix handling in cytoscape

---
 config/plugins/visualizations/cytoscape/src/script.js | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/config/plugins/visualizations/cytoscape/src/script.js b/config/plugins/visualizations/cytoscape/src/script.js
index fbcb9510c7d..a2d0fdd2d01 100644
--- a/config/plugins/visualizations/cytoscape/src/script.js
+++ b/config/plugins/visualizations/cytoscape/src/script.js
@@ -1,5 +1,11 @@
 import Cytoscape from 'cytoscape';
 
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 // Public method. Return graph data as JSON
 var parse_sif = function( text ) {
     // Private variables and methods
@@ -166,9 +172,8 @@ window.bundleEntries.load = function (options) {
     cytoscape = null,
     sif_file_ext = "sif",
     highlighted_color = settings.get( 'color_picker_highlighted' );
-    const safe_download_url = `${options.root}${dataset.download_url}`;
     $.ajax({
-        url     : safe_download_url,
+        url     : prefixedDownloadUrl(options.root, dataset.download_url),
         success : function( content ) {
             // Select data for the graph
             if( dataset.file_ext === sif_file_ext ) {

From 86420066d90c57971deb324202642fbc8cec10dd Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 09:26:43 -0500
Subject: [PATCH 223/350] Fix prefix handling in drawrna

---
 config/plugins/visualizations/drawrna/src/script.js | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/config/plugins/visualizations/drawrna/src/script.js b/config/plugins/visualizations/drawrna/src/script.js
index 2b0ac8faf20..ce081c07266 100644
--- a/config/plugins/visualizations/drawrna/src/script.js
+++ b/config/plugins/visualizations/drawrna/src/script.js
@@ -1,11 +1,17 @@
 import DrawRNA from "./drawrnajs/drawrna";
 window.bundleEntries = window.bundleEntries || {};
+
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 window.bundleEntries.load = function (options) {
     var chart = options.chart;
     var dataset = options.dataset;
-    const safe_download_url = `${options.root}${dataset.download_url}`;
     $.ajax({
-        url: safe_download_url,
+        url: prefixedDownloadUrl(options.root, dataset.download_url),
         success: function(response) {
             var input = response.split('\n');
             var app = new DrawRNA({

From 27340fe18b0ba9b2aa52e7000a17a75b369018b7 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 09:31:52 -0500
Subject: [PATCH 224/350] Fix prefix handling in msa

---
 config/plugins/visualizations/msa/src/script.js | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/config/plugins/visualizations/msa/src/script.js b/config/plugins/visualizations/msa/src/script.js
index a89020f424b..72dabe78577 100755
--- a/config/plugins/visualizations/msa/src/script.js
+++ b/config/plugins/visualizations/msa/src/script.js
@@ -1,5 +1,11 @@
 import "./msa.min.js";
 
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 Object.assign(window.bundleEntries || {}, {
     load: function (options) {
         const chart = options.chart;
@@ -14,8 +20,7 @@ Object.assign(window.bundleEntries || {}, {
             menu: "small",
             bootstrapMenu: "true" == settings.get("menu"),
         });
-        const safe_download_url = `${options.root}${dataset.download_url}`;
-        msaViz.u.file.importURL(safe_download_url, () => {
+        msaViz.u.file.importURL(prefixedDownloadUrl(options.root, dataset.download_url), () => {
             msaViz.render();
             chart.state("ok", "Chart drawn.");
             options.process.resolve();

From 1b6fd884e9a893cf75beb7e88e1a6f889c85731b Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 20 Jan 2023 15:37:30 +0100
Subject: [PATCH 225/350] Make workflow mako more lenient

Probably fixes https://github.com/galaxyproject/galaxy/issues/15327
---
 lib/galaxy/managers/workflows.py | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index b81445e026b..e87ab370ab8 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -990,13 +990,16 @@ class WorkflowContentsManager(UsesAnnotations):
                             nested_input_dict = {}
                             index = repeat_values[i]["__index__"]
                             nested_input_dict["title"] = "%i. %s" % (i + 1, input.title)
-                            nested_input_dict["inputs"] = do_inputs(
-                                input.inputs,
-                                repeat_values[i],
-                                f"{prefix + input.name}_{str(index)}|",
-                                step,
-                                other_values,
-                            )
+                            try:
+                                nested_input_dict["inputs"] = do_inputs(
+                                    input.inputs,
+                                    repeat_values[i],
+                                    f"{prefix + input.name}_{str(index)}|",
+                                    step,
+                                    other_values,
+                                )
+                            except KeyError:
+                                continue
                             nested_input_dicts.append(nested_input_dict)
                         input_dict["inputs"] = nested_input_dicts
                 elif input.type == "conditional":
@@ -1006,14 +1009,20 @@ class WorkflowContentsManager(UsesAnnotations):
                     row_for_param(
                         input_dict, input.test_param, group_values[input.test_param.name], other_values, prefix, step
                     )
-                    input_dict["inputs"] = do_inputs(
-                        input.cases[current_case].inputs, group_values, new_prefix, step, other_values
-                    )
+                    try:
+                        input_dict["inputs"] = do_inputs(
+                            input.cases[current_case].inputs, group_values, new_prefix, step, other_values
+                        )
+                    except KeyError:
+                        continue
                 elif input.type == "section":
                     new_prefix = f"{prefix + input.name}|"
                     group_values = values[input.name]
                     input_dict["title"] = input.title
-                    input_dict["inputs"] = do_inputs(input.inputs, group_values, new_prefix, step, other_values)
+                    try:
+                        input_dict["inputs"] = do_inputs(input.inputs, group_values, new_prefix, step, other_values)
+                    except KeyError:
+                        continue
                 else:
                     row_for_param(input_dict, input, values[input.name], other_values, prefix, step)
                 input_dicts.append(input_dict)

From ee677ce5c84c3b80f446237fc886c5d373cc3859 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 09:43:32 -0500
Subject: [PATCH 226/350] Fix openlayers prefix handling

---
 .../plugins/visualizations/openlayers/src/script.js  | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/config/plugins/visualizations/openlayers/src/script.js b/config/plugins/visualizations/openlayers/src/script.js
index b4ca4af179f..90922403fa7 100644
--- a/config/plugins/visualizations/openlayers/src/script.js
+++ b/config/plugins/visualizations/openlayers/src/script.js
@@ -13,6 +13,12 @@ import { saveAs } from "file-saver";
 import shp from "shpjs";
 import axios from "axios";
 
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 var MapViewer = (function(mv) {
     mv.gMap = null;
 
@@ -240,11 +246,11 @@ window.bundleEntries = window.bundleEntries || {};
 window.bundleEntries.load = function (options) {
     const chart = options.chart;
     const dataset = options.dataset;
-    const safe_download_url = `${options.root}${dataset.download_url}`;
+    const downloadUrl = prefixedDownloadUrl(options.root, dataset.download_url);
     $.ajax({
-        url: safe_download_url,
+        url: downloadUrl,
         success: () => {
-            MapViewer.loadFile(safe_download_url, dataset.extension, options, chart);
+            MapViewer.loadFile(downloadUrl, dataset.extension, options, chart);
         },
         error: () => {
             chart.state("failed", "Failed to access dataset.");

From af632a6b618dae52e75ce7ed3f5d1e6b419d3fc9 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 10:04:03 -0500
Subject: [PATCH 227/350] Fix prefix handling in phylocanvas

---
 .../plugins/visualizations/phylocanvas/src/script.js   | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/config/plugins/visualizations/phylocanvas/src/script.js b/config/plugins/visualizations/phylocanvas/src/script.js
index d437bfe6942..f2b3c6a60e3 100644
--- a/config/plugins/visualizations/phylocanvas/src/script.js
+++ b/config/plugins/visualizations/phylocanvas/src/script.js
@@ -1,12 +1,18 @@
 import * as Phylocanvas from "phylocanvas";
+
+/* This will be part of the charts/viz standard lib in 23.1 */
+const slashCleanup = /(\/)+/g;
+function prefixedDownloadUrl(root, path) {
+    return `${root}/${path}`.replace(slashCleanup, "/");
+}
+
 _.extend(window.bundleEntries || {}, {
     load: function(options) {
         var chart = options.chart;
         var dataset = options.dataset;
         var settings = options.chart.settings;
-        const safe_download_url = `${options.root}${dataset.download_url}`;
         $.ajax( {
-            url     : safe_download_url,
+            url     : prefixedDownloadUrl(options.root, dataset.download_url),
             success : function( content ) {
                 try {
                     var tree = Phylocanvas.default.createTree( options.target ),

From 527736280dd28afcb48350d6d74dadd2ceff2ae8 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 15 Dec 2022 10:36:08 -0500
Subject: [PATCH 228/350] Build to dist, then we stage, to separate the
 process.

---
 client/webpack.config.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 9a892104993..11eefa22b48 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -40,7 +40,7 @@ module.exports = (env = {}, argv = {}) => {
             toolshed: ["polyfills", "bundleToolshed", "entry/generic"],
         },
         output: {
-            path: path.join(__dirname, "../", "/static/dist"),
+            path: path.join(__dirname, "dist"),
             filename: "[name].bundled.js",
         },
         resolve: {

From 73ec1f63819a9dfa2686b77677292b52fb69280d Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 16 Dec 2022 09:21:01 -0500
Subject: [PATCH 229/350] Publish to @galaxyproject namespace

---
 client/package.json | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/client/package.json b/client/package.json
index dbcf569c61f..74fc22f242e 100644
--- a/client/package.json
+++ b/client/package.json
@@ -1,5 +1,5 @@
 {
-  "name": "galaxy-client",
+  "name": "@galaxyproject/galaxy-client",
   "version": "0.1.0",
   "description": "Galaxy client application build system",
   "keywords": [
@@ -9,7 +9,10 @@
     "type": "git",
     "url": "https://github.com/galaxyproject/galaxy.git"
   },
-  "license": "AFL-3.0",
+  "license": "MIT",
+  "files": [
+    "dist"
+  ],
   "browserslist": [
     "defaults",
     "not ie <= 11",
@@ -110,14 +113,12 @@
     "xml-beautifier": "^0.5.0"
   },
   "scripts": {
-    "watch": "gulp && yarn run save-build-hash && yarn run webpack-watch",
-    "serve": "NODE_OPTIONS=--max-old-space-size=4096 && NODE_ENV=development gulp && webpack serve",
+    "develop": "NODE_OPTIONS=--max-old-space-size=4096 NODE_ENV=development gulp && webpack-dev-server",
     "build": "NODE_ENV=development gulp && webpack && yarn run save-build-hash",
     "build-production": "NODE_ENV=production gulp && yarn run webpack-production && yarn run save-build-hash",
     "build-production-maps": "NODE_ENV=production gulp && yarn run webpack-production-maps && yarn run save-build-hash",
     "build-stats": "NODE_ENV=production webpack --profile --json=webpack-stats.json",
     "view-stats": "webpack-bundle-analyzer webpack-stats.json ../static/dist/",
-    "webpack-watch": "webpack --watch",
     "webpack-production": "NODE_ENV=production webpack",
     "webpack-production-maps": "GXY_BUILD_SOURCEMAPS=1 NODE_ENV=production webpack",
     "gulp": "gulp",

From 891cdb659b241b8a72f4945769be632bd19cc6b8 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 16 Dec 2022 09:25:16 -0500
Subject: [PATCH 230/350] Ensure webpack cleans between builds

---
 client/webpack.config.js | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 11eefa22b48..06f773f8f3a 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -42,6 +42,7 @@ module.exports = (env = {}, argv = {}) => {
         output: {
             path: path.join(__dirname, "dist"),
             filename: "[name].bundled.js",
+            clean: true,
         },
         resolve: {
             plugins: [new TsconfigPathsPlugin({ extensions: [".ts", ".js", ".json", ".vue", ".scss"] })],

From d974287400355eac5e8318d0605380e50df372cd Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 16 Dec 2022 09:55:45 -0500
Subject: [PATCH 231/350] Basic staging of built dependencies

---
 package.json | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 package.json

diff --git a/package.json b/package.json
new file mode 100644
index 00000000000..05aabcb42eb
--- /dev/null
+++ b/package.json
@@ -0,0 +1,24 @@
+{
+  "name": "@galaxyproject/galaxy",
+  "version": "1.0.0",
+  "description": ".. figure:: https://galaxyproject.org/images/galaxy-logos/galaxy_project_logo.jpg    :alt: Galaxy Logo",
+  "main": "index.js",
+  "devDependencies": {},
+  "scripts": {
+    "stage": "cpy './node_modules/@galaxyproject/galaxy-client/dist/*' './static/dist'"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/galaxyproject/galaxy.git"
+  },
+  "author": "Galaxy Contributors",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/galaxyproject/galaxy/issues"
+  },
+  "homepage": "https://github.com/galaxyproject/galaxy#readme",
+  "dependencies": {
+    "@galaxyproject/galaxy-client": "^0.1.0",
+    "cpy-cli": "^4.2.0"
+  }
+}

From 9b6dd967c2beddba71f183ad6385917b99d03d9e Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 11:23:20 -0500
Subject: [PATCH 232/350] Basic client installation command added

---
 Makefile                  | 33 ++++++++++++++++++++++-----------
 scripts/common_startup.sh | 33 +++++++++++++++++++++++++--------
 2 files changed, 47 insertions(+), 19 deletions(-)

diff --git a/Makefile b/Makefile
index d2748e0ff5d..87d71d98613 100644
--- a/Makefile
+++ b/Makefile
@@ -162,6 +162,14 @@ skip-client: ## Run only the server, skipping the client build.
 	GALAXY_SKIP_CLIENT_BUILD=1 sh run.sh
 
 node-deps: ## Install NodeJS dependencies.
+ifndef YARN
+	@echo "Could not find yarn, which is required to install the Galaxy client.\nTo install yarn, please visit \033[0;34mhttps://yarnpkg.com/en/docs/install\033[0m for instructions, and package information for all platforms.\n"
+	false;
+else
+	yarn install $(YARN_INSTALL_OPTS)
+endif
+
+client-node-deps: ## Install NodeJS dependencies for the client.
 ifndef YARN
 	@echo "Could not find yarn, which is required to build the Galaxy client.\nTo install yarn, please visit \033[0;34mhttps://yarnpkg.com/en/docs/install\033[0m for instructions, and package information for all platforms.\n"
 	false;
@@ -176,7 +184,7 @@ build-api-schema:
 remove-api-schema:
 	rm _schema.yaml
 
-update-client-api-schema: node-deps build-api-schema
+update-client-api-schema: client-node-deps build-api-schema
 	$(IN_VENV) cd client && node openapi_to_schema.mjs ../_schema.yaml > src/schema/schema.ts && npx prettier --write src/schema/schema.ts
 	$(MAKE) remove-api-schema
 
@@ -185,34 +193,37 @@ lint-api-schema: build-api-schema
 	$(IN_VENV) codespell -I .ci/ignore-spelling.txt _schema.yaml
 	$(MAKE) remove-api-schema
 
-client: node-deps ## Rebuild client-side artifacts for local development.
+installed-client: node-deps ## Install prebuilt client as defined in root package.json
+	yarn install && yarn run stage
+
+client: client-node-deps ## Rebuild client-side artifacts for local development.
 	cd client && yarn run build
 
-client-production: node-deps ## Rebuild client-side artifacts for a production deployment without sourcemaps.
+client-production: client-node-deps ## Rebuild client-side artifacts for a production deployment without sourcemaps.
 	cd client && yarn run build-production
 
-client-production-maps: node-deps ## Rebuild client-side artifacts for a production deployment with sourcemaps.
+client-production-maps: client-node-deps ## Rebuild client-side artifacts for a production deployment with sourcemaps.
 	cd client && yarn run build-production-maps
 
-client-format: node-deps ## Reformat client code
+client-format: client-node-deps ## Reformat client code
 	cd client && yarn run format
 
-client-watch: node-deps ## A useful target for parallel development building.  See also client-dev-server.
+client-watch: client-node-deps ## A useful target for parallel development building.  See also client-dev-server.
 	cd client && yarn run watch
 
-client-dev-server: node-deps ## Starts a webpack dev server for client development (HMR enabled)
+client-dev-server: client-node-deps ## Starts a webpack dev server for client development (HMR enabled)
 	cd client && yarn run serve
 
-client-test: node-deps  ## Run JS unit tests
+client-test: client-node-deps  ## Run JS unit tests
 	cd client && yarn run test
 
-client-eslint-precommit: node-deps # Client linting for pre-commit hook; skips glob input and takes specific paths
+client-eslint-precommit: client-node-deps # Client linting for pre-commit hook; skips glob input and takes specific paths
 	cd client && yarn run eslint-precommit
 
-client-eslint: node-deps # Run client linting
+client-eslint: client-node-deps # Run client linting
 	cd client && yarn run eslint
 
-client-format-check: node-deps # Run client formatting check
+client-format-check: client-node-deps # Run client formatting check
 	cd client && yarn run format-check
 
 client-lint: client-eslint client-format-check ## ES lint and check format of client
diff --git a/scripts/common_startup.sh b/scripts/common_startup.sh
index a2716829aa3..48f1f936ec2 100755
--- a/scripts/common_startup.sh
+++ b/scripts/common_startup.sh
@@ -17,6 +17,7 @@ FETCH_WHEELS=1
 CREATE_VENV=1
 COPY_SAMPLE_FILES=1
 SKIP_CLIENT_BUILD=${GALAXY_SKIP_CLIENT_BUILD:-0}
+INSTALL_PREBUILT_CLIENT=${GALAXY_INSTALL_PREBUILT_CLIENT:-0}
 NODE_VERSION=${GALAXY_NODE_VERSION:-"$(cat client/.node_version)"}
 YARN_INSTALL_OPTS=${YARN_INSTALL_OPTS:-"--network-timeout 300000 --check-files"}
 
@@ -257,16 +258,32 @@ if [ $SKIP_CLIENT_BUILD -eq 0 ]; then
     set_galaxy_config_file_var
     # Set plugin path
     GALAXY_PLUGIN_PATH=$(python scripts/config_parse.py --setting=plugin_path --config-file="$GALAXY_CONFIG_FILE")
-    # Build client
-    cd client
-    if yarn install $YARN_INSTALL_OPTS; then
-        if ! (export GALAXY_PLUGIN_PATH="$GALAXY_PLUGIN_PATH"; yarn run build-production-maps;) then
-            echo "ERROR: Galaxy client build failed. See ./client/README.md for more information, including how to get help."
+
+    if [ $INSTALL_PREBUILT_CLIENT -eq 0 ]; then
+        # If we have not opted to use a prebuilt client, then build client.
+        cd client
+        if yarn install $YARN_INSTALL_OPTS; then
+            if ! (export GALAXY_PLUGIN_PATH="$GALAXY_PLUGIN_PATH"; yarn run build-production-maps;) then
+                echo "ERROR: Galaxy client build failed. See ./client/README.md for more information, including how to get help."
+                exit 1
+            fi
+        else
+            echo "ERROR: Galaxy client dependency installation failed. See ./client/README.md for more information, including how to get help."
             exit 1
         fi
+        cd -
     else
-        echo "ERROR: Galaxy client dependency installation failed. See ./client/README.md for more information, including how to get help."
-        exit 1
+        # Install prebuilt client
+        if yarn install $YARN_INSTALL_OPTS; then
+            if ! (yarn run stage) then
+                echo "ERROR: Galaxy prebuilt client install failed. See ./client/README.md for more information, including how to get help."
+                exit 1
+            fi
+        else
+            echo "ERROR: Galaxy prebuilt client dependency installation failed. See ./client/README.md for more information, including how to get help."
+            exit 1
+        fi
+
     fi
-    cd -
+
 fi

From 8b699b8705e8eedfd0eaf6bbb972cecb72a0f11e Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 12:51:09 -0500
Subject: [PATCH 233/350] Ignore dist in .eslintrc

---
 client/.eslintrc.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/.eslintrc.json b/client/.eslintrc.json
index f13b7808484..a02efdbb365 100644
--- a/client/.eslintrc.json
+++ b/client/.eslintrc.json
@@ -59,7 +59,7 @@
         "vuejs-accessibility/no-autofocus": "error",
         "vuejs-accessibility/tabindex-no-positive": "error"
     },
-    "ignorePatterns": ["src/qunit", "src/mocha", "src/libs", "src/nls", "src/legacy"],
+    "ignorePatterns": ["dist", "src/qunit", "src/mocha", "src/libs", "src/nls", "src/legacy"],
     "overrides": [
         {
             "files": ["**/*.vue"],

From a972ba14cef1c6f60b113696b1936c71664116d7 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 13:08:07 -0500
Subject: [PATCH 234/350] Rename make target to "install-client" instead of
 "installed-client"

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 87d71d98613..7833421fcab 100644
--- a/Makefile
+++ b/Makefile
@@ -193,7 +193,7 @@ lint-api-schema: build-api-schema
 	$(IN_VENV) codespell -I .ci/ignore-spelling.txt _schema.yaml
 	$(MAKE) remove-api-schema
 
-installed-client: node-deps ## Install prebuilt client as defined in root package.json
+install-client: node-deps ## Install prebuilt client as defined in root package.json
 	yarn install && yarn run stage
 
 client: client-node-deps ## Rebuild client-side artifacts for local development.

From d9e09ab9f2db6be77a9028d99923fb2287fcc092 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 19 Jan 2023 13:42:27 -0500
Subject: [PATCH 235/350] Separate build staging process, use client/dist. 
 Include toplevel yarn.lock.

---
 client/package.json |   9 +-
 client/yarn.lock    | 291 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 290 insertions(+), 10 deletions(-)

diff --git a/client/package.json b/client/package.json
index 74fc22f242e..ca7c9ee3630 100644
--- a/client/package.json
+++ b/client/package.json
@@ -114,15 +114,15 @@
   },
   "scripts": {
     "develop": "NODE_OPTIONS=--max-old-space-size=4096 NODE_ENV=development gulp && webpack-dev-server",
-    "build": "NODE_ENV=development gulp && webpack && yarn run save-build-hash",
-    "build-production": "NODE_ENV=production gulp && yarn run webpack-production && yarn run save-build-hash",
-    "build-production-maps": "NODE_ENV=production gulp && yarn run webpack-production-maps && yarn run save-build-hash",
+    "build": "NODE_ENV=development gulp && webpack && yarn run stage-build",
+    "build-production": "NODE_ENV=production gulp && yarn run webpack-production && yarn run stage-build",
+    "build-production-maps": "NODE_ENV=production gulp && yarn run webpack-production-maps && yarn run stage-build",
     "build-stats": "NODE_ENV=production webpack --profile --json=webpack-stats.json",
     "view-stats": "webpack-bundle-analyzer webpack-stats.json ../static/dist/",
     "webpack-production": "NODE_ENV=production webpack",
     "webpack-production-maps": "GXY_BUILD_SOURCEMAPS=1 NODE_ENV=production webpack",
     "gulp": "gulp",
-    "save-build-hash": "(git rev-parse HEAD 2>/dev/null || echo '') >../static/client_build_hash.txt",
+    "stage-build": "cpy 'dist/*' '../static/dist' && (git rev-parse HEAD 2>/dev/null || echo '') >../static/client_build_hash.txt",
     "format": "prettier --write 'src/style/scss/**/*.scss' 'src/**/{*.ts,*.js,*.vue}' 'tests/jest/standalone/{*.ts,*.js}' '!src/libs/**'",
     "format-check": "prettier --check 'src/style/scss/**/*.scss' 'src/**/{*.js,*.vue}' 'tests/jest/standalone/{*.ts,*.js}' '!src/libs/**'",
     "prettier": "yarn run format",
@@ -152,6 +152,7 @@
     "axios-mock-adapter": "^1.20.0",
     "babel-jest": "^29.3.1",
     "buffer": "^6.0.3",
+    "cpy-cli": "^4.2.0",
     "css-loader": "^6.7.1",
     "css-minimizer-webpack-plugin": "^4.0.0",
     "del": "^6.0.0",
diff --git a/client/yarn.lock b/client/yarn.lock
index ecccf5a872b..effa8a67e86 100644
--- a/client/yarn.lock
+++ b/client/yarn.lock
@@ -2295,11 +2295,21 @@
   resolved "https://registry.npmjs.org/@types/mime/-/mime-3.0.1.tgz"
   integrity sha512-Y4XFY5VJAuw0FgAqPNd6NNoV44jbq9Bz2L7Rh/J6jLTiHBSBJa9fxqQIvkIld4GsoDOcCbvzOUAbLPsSKKg+uA==
 
+"@types/minimist@^1.2.2":
+  version "1.2.2"
+  resolved "https://registry.yarnpkg.com/@types/minimist/-/minimist-1.2.2.tgz#ee771e2ba4b3dc5b372935d549fd9617bf345b8c"
+  integrity sha512-jhuKLIRrhvCPLqwPcx6INqmKeiA5EWrsCOPhrlFSrbrmU4ZMPjj5Ul/oLCMDO98XRUIwVm78xICz4EPCektzeQ==
+
 "@types/node@*", "@types/node@>=10.0.0":
   version "18.6.5"
   resolved "https://registry.npmjs.org/@types/node/-/node-18.6.5.tgz"
   integrity sha512-Xjt5ZGUa5WusGZJ4WJPbOT8QOqp6nDynVFRKcUt32bOgvXEoc6o085WNkYTMO7ifAj2isEfQQ2cseE+wT6jsRw==
 
+"@types/normalize-package-data@^2.4.0":
+  version "2.4.1"
+  resolved "https://registry.yarnpkg.com/@types/normalize-package-data/-/normalize-package-data-2.4.1.tgz#d3357479a0fdfdd5907fe67e17e0a85c906e1301"
+  integrity sha512-Gj7cI7z+98M282Tqmp2K5EIsoouUEzbBJhQQzDE3jSIRk6r9gsz0oUokqIUR4u1R3dMHo0pDHM7sNOHyhulypw==
+
 "@types/parse-json@^4.0.0":
   version "4.0.0"
   resolved "https://registry.npmjs.org/@types/parse-json/-/parse-json-4.0.0.tgz"
@@ -2788,6 +2798,14 @@ aggregate-error@^3.0.0:
     clean-stack "^2.0.0"
     indent-string "^4.0.0"
 
+aggregate-error@^4.0.0:
+  version "4.0.1"
+  resolved "https://registry.yarnpkg.com/aggregate-error/-/aggregate-error-4.0.1.tgz#25091fe1573b9e0be892aeda15c7c66a545f758e"
+  integrity sha512-0poP0T7el6Vq3rstR8Mn4V/IQrpBLO6POkUSrN7RhyY+GF/InCFShQzsQ39T25gkHhLgSLByyAz+Kjb+c2L98w==
+  dependencies:
+    clean-stack "^4.0.0"
+    indent-string "^5.0.0"
+
 ajv-formats@^2.1.1:
   version "2.1.1"
   resolved "https://registry.npmjs.org/ajv-formats/-/ajv-formats-2.1.1.tgz"
@@ -3035,6 +3053,16 @@ array-unique@^0.3.2:
   resolved "https://registry.npmjs.org/array-unique/-/array-unique-0.3.2.tgz"
   integrity sha512-SleRWjh9JUud2wH1hPs9rZBZ33H6T9HOiL0uwGnGx9FpE6wKGyfWugmbkEOIs6qWrZhg0LWeLziLrEwQJhs5mQ==
 
+arrify@^1.0.1:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/arrify/-/arrify-1.0.1.tgz#898508da2226f380df904728456849c1501a4b0d"
+  integrity sha512-3CYzex9M9FGQjCGMGyi6/31c8GJbgb0qGyrx5HWxPd0aCwh4cB2YjMb2Xf9UuoogrMrlO9cTqnB5rI5GHZTcUA==
+
+arrify@^3.0.0:
+  version "3.0.0"
+  resolved "https://registry.yarnpkg.com/arrify/-/arrify-3.0.0.tgz#ccdefb8eaf2a1d2ab0da1ca2ce53118759fd46bc"
+  integrity sha512-tLkvA81vQG/XqE2mjDkGQHoOINtMHtysSnemrmoGe6PydDPMRbVugqyk4A6V/WDWEfm3l+0d8anA9r8cv/5Jaw==
+
 assert@^2.0.0:
   version "2.0.0"
   resolved "https://registry.npmjs.org/assert/-/assert-2.0.0.tgz"
@@ -3506,6 +3534,16 @@ callsites@^3.0.0:
   resolved "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz"
   integrity sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ==
 
+camelcase-keys@^7.0.0:
+  version "7.0.2"
+  resolved "https://registry.yarnpkg.com/camelcase-keys/-/camelcase-keys-7.0.2.tgz#d048d8c69448745bb0de6fc4c1c52a30dfbe7252"
+  integrity sha512-Rjs1H+A9R+Ig+4E/9oyB66UC5Mj9Xq3N//vcLf2WzgdTi/3gUu3Z9KoqmlrEG4VuuLK8wJHofxzdQXz/knhiYg==
+  dependencies:
+    camelcase "^6.3.0"
+    map-obj "^4.1.0"
+    quick-lru "^5.1.1"
+    type-fest "^1.2.1"
+
 camelcase@^3.0.0:
   version "3.0.0"
   resolved "https://registry.npmjs.org/camelcase/-/camelcase-3.0.0.tgz"
@@ -3516,7 +3554,7 @@ camelcase@^5.3.1:
   resolved "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz"
   integrity sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==
 
-camelcase@^6.2.0:
+camelcase@^6.2.0, camelcase@^6.3.0:
   version "6.3.0"
   resolved "https://registry.npmjs.org/camelcase/-/camelcase-6.3.0.tgz"
   integrity sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA==
@@ -3662,6 +3700,13 @@ clean-stack@^2.0.0:
   resolved "https://registry.npmjs.org/clean-stack/-/clean-stack-2.2.0.tgz"
   integrity sha512-4diC9HaTE+KRAMWhDhrGOECgWZxoevMc5TlkObMqNSsVU62PYzXZ/SMTjzyGAFF1YusgxGcSWTEXBhp0CPwQ1A==
 
+clean-stack@^4.0.0:
+  version "4.2.0"
+  resolved "https://registry.yarnpkg.com/clean-stack/-/clean-stack-4.2.0.tgz#c464e4cde4ac789f4e0735c5d75beb49d7b30b31"
+  integrity sha512-LYv6XPxoyODi36Dp976riBtSY27VmFo+MKqEU9QCCWyTrdEPDog+RWA7xQWHi6Vbp61j5c4cdzzX1NidnwtUWg==
+  dependencies:
+    escape-string-regexp "5.0.0"
+
 cliui@^3.2.0:
   version "3.2.0"
   resolved "https://registry.npmjs.org/cliui/-/cliui-3.2.0.tgz"
@@ -4012,6 +4057,38 @@ cosmiconfig@^7.0.0:
     path-type "^4.0.0"
     yaml "^1.10.0"
 
+cp-file@^9.1.0:
+  version "9.1.0"
+  resolved "https://registry.yarnpkg.com/cp-file/-/cp-file-9.1.0.tgz#e98e30db72d57d47b5b1d444deb70d05e5684921"
+  integrity sha512-3scnzFj/94eb7y4wyXRWwvzLFaQp87yyfTnChIjlfYrVqp5lVO3E2hIJMeQIltUT0K2ZAB3An1qXcBmwGyvuwA==
+  dependencies:
+    graceful-fs "^4.1.2"
+    make-dir "^3.0.0"
+    nested-error-stacks "^2.0.0"
+    p-event "^4.1.0"
+
+cpy-cli@^4.2.0:
+  version "4.2.0"
+  resolved "https://registry.yarnpkg.com/cpy-cli/-/cpy-cli-4.2.0.tgz#d60bf9ac776486af20aac2fa4fb95f8f10b35ce8"
+  integrity sha512-b04b+cbdr29CdpREPKw/itrfjO43Ty0Aj7wRM6M6LoE4GJxZJCk9Xp+Eu1IqztkKh3LxIBt1tDplENsa6KYprg==
+  dependencies:
+    cpy "^9.0.0"
+    meow "^10.1.2"
+
+cpy@^9.0.0:
+  version "9.0.1"
+  resolved "https://registry.yarnpkg.com/cpy/-/cpy-9.0.1.tgz#7f3ad0ad5bafe0bc70645c4bb567969927cadb9f"
+  integrity sha512-D9U0DR5FjTCN3oMTcFGktanHnAG5l020yvOCR1zKILmAyPP7I/9pl6NFgRbDcmSENtbK1sQLBz1p9HIOlroiNg==
+  dependencies:
+    arrify "^3.0.0"
+    cp-file "^9.1.0"
+    globby "^13.1.1"
+    junk "^4.0.0"
+    micromatch "^4.0.4"
+    nested-error-stacks "^2.1.0"
+    p-filter "^3.0.0"
+    p-map "^5.3.0"
+
 cross-spawn@^7.0.2, cross-spawn@^7.0.3:
   version "7.0.3"
   resolved "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.3.tgz"
@@ -4489,11 +4566,24 @@ debug@4, debug@^4.1.0, debug@^4.1.1, debug@^4.3.2, debug@^4.3.4, debug@~4.3.1, d
   dependencies:
     ms "2.1.2"
 
-decamelize@^1.1.1:
+decamelize-keys@^1.1.0:
+  version "1.1.1"
+  resolved "https://registry.yarnpkg.com/decamelize-keys/-/decamelize-keys-1.1.1.tgz#04a2d523b2f18d80d0158a43b895d56dff8d19d8"
+  integrity sha512-WiPxgEirIV0/eIOMcnFBA3/IJZAZqKnwAwWyvvdi4lsr1WCN22nhdf/3db3DoZcUjTV2SqfzIwNyp6y2xs3nmg==
+  dependencies:
+    decamelize "^1.1.0"
+    map-obj "^1.0.0"
+
+decamelize@^1.1.0, decamelize@^1.1.1:
   version "1.2.0"
   resolved "https://registry.npmjs.org/decamelize/-/decamelize-1.2.0.tgz"
   integrity sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==
 
+decamelize@^5.0.0:
+  version "5.0.1"
+  resolved "https://registry.yarnpkg.com/decamelize/-/decamelize-5.0.1.tgz#db11a92e58c741ef339fb0a2868d8a06a9a7b1e9"
+  integrity sha512-VfxadyCECXgQlkoEAjeghAr5gY3Hf+IKjKb+X8tGVDtveCjN+USwprd2q3QXBR9T1+x2DG0XZF5/w+7HAtSaXA==
+
 decimal.js@^10.4.2:
   version "10.4.3"
   resolved "https://registry.yarnpkg.com/decimal.js/-/decimal.js-10.4.3.tgz#1044092884d245d1b7f65725fa4ad4c6f781cc23"
@@ -5052,6 +5142,11 @@ escape-html@~1.0.3:
   resolved "https://registry.npmjs.org/escape-html/-/escape-html-1.0.3.tgz"
   integrity sha512-NiSupZ4OeuGwr68lGIeym/ksIZMJodUGOSCZ/FSnTxcrekbvqrgdUxlJOMpijaKZVjAJrWrGs/6Jy8OMuyj9ow==
 
+escape-string-regexp@5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/escape-string-regexp/-/escape-string-regexp-5.0.0.tgz#4683126b500b61762f2dbebace1806e8be31b1c8"
+  integrity sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw==
+
 escape-string-regexp@^1.0.5:
   version "1.0.5"
   resolved "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz"
@@ -5409,7 +5504,7 @@ fast-deep-equal@^3.1.1, fast-deep-equal@^3.1.3:
   resolved "https://registry.npmjs.org/fast-deep-equal/-/fast-deep-equal-3.1.3.tgz"
   integrity sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==
 
-fast-glob@^3.2.12:
+fast-glob@^3.2.11, fast-glob@^3.2.12:
   version "3.2.12"
   resolved "https://registry.yarnpkg.com/fast-glob/-/fast-glob-3.2.12.tgz#7f39ec99c2e6ab030337142da9e0c18f37afae80"
   integrity sha512-DVj4CQIYYow0BlaelwK1pHl5n5cRSJfM60UA0zK891sVInoPri2Ekj7+e1CT3/3qxXenpI+nBBmQAcJPJgaj4w==
@@ -5926,6 +6021,17 @@ globby@^11.0.1, globby@^11.1.0:
     merge2 "^1.4.1"
     slash "^3.0.0"
 
+globby@^13.1.1:
+  version "13.1.3"
+  resolved "https://registry.yarnpkg.com/globby/-/globby-13.1.3.tgz#f62baf5720bcb2c1330c8d4ef222ee12318563ff"
+  integrity sha512-8krCNHXvlCgHDpegPzleMq07yMYTO2sXKASmZmquEYWEmCx6J5UTRbp5RwMJkTJGtcQ44YpiUYUiN0b9mzy8Bw==
+  dependencies:
+    dir-glob "^3.0.1"
+    fast-glob "^3.2.11"
+    ignore "^5.2.0"
+    merge2 "^1.4.1"
+    slash "^4.0.0"
+
 globrex@^0.1.2:
   version "0.1.2"
   resolved "https://registry.npmjs.org/globrex/-/globrex-0.1.2.tgz"
@@ -6010,6 +6116,11 @@ handsontable@^4.0.0:
     numbro "^2.0.6"
     pikaday "1.5.1"
 
+hard-rejection@^2.1.0:
+  version "2.1.0"
+  resolved "https://registry.yarnpkg.com/hard-rejection/-/hard-rejection-2.1.0.tgz#1c6eda5c1685c63942766d79bb40ae773cecd883"
+  integrity sha512-VIZB+ibDhx7ObhAe7OVtoEbuP4h/MuOTHJ+J8h/eBXotJYl0fBgR72xDFCKgIh22OJZIOVNxBMWuhAr10r8HdA==
+
 has-bigints@^1.0.1, has-bigints@^1.0.2:
   version "1.0.2"
   resolved "https://registry.npmjs.org/has-bigints/-/has-bigints-1.0.2.tgz"
@@ -6104,6 +6215,13 @@ hosted-git-info@^2.1.4:
   resolved "https://registry.npmjs.org/hosted-git-info/-/hosted-git-info-2.8.9.tgz"
   integrity sha512-mxIDAb9Lsm6DoOJ7xH+5+X4y1LU/4Hi50L9C5sIswK3JzULS4bwk1FvjdBgvYR4bzT4tuUQiC15FE2f5HbLvYw==
 
+hosted-git-info@^4.0.1:
+  version "4.1.0"
+  resolved "https://registry.yarnpkg.com/hosted-git-info/-/hosted-git-info-4.1.0.tgz#827b82867e9ff1c8d0c4d9d53880397d2c86d224"
+  integrity sha512-kyCuEOWjJqZuDbRHzL8V93NzQhwIB71oFWSyzVo+KPZI+pnQPPxucdkrOZvkLRnrf5URsQM+IJ09Dw29cRALIA==
+  dependencies:
+    lru-cache "^6.0.0"
+
 hpack.js@^2.1.6:
   version "2.1.6"
   resolved "https://registry.npmjs.org/hpack.js/-/hpack.js-2.1.6.tgz"
@@ -6300,6 +6418,11 @@ indent-string@^4.0.0:
   resolved "https://registry.npmjs.org/indent-string/-/indent-string-4.0.0.tgz"
   integrity sha512-EdDDZu4A2OyIK7Lr/2zG+w5jmbuk1DVBnEwREQvBzspBJkCEbRa8GxU1lghYcaGJCnRWibjDXlq779X1/y5xwg==
 
+indent-string@^5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/indent-string/-/indent-string-5.0.0.tgz#4fd2980fccaf8622d14c64d694f4cf33c81951a5"
+  integrity sha512-m6FAo/spmsW2Ab2fU35JTYwtOKa2yAwXSwgjSv1TJzh4Mh7mC3lzAOVLBprb72XsTrgkEIsl7YrFNAiDiRhIGg==
+
 inflight@^1.0.4:
   version "1.0.6"
   resolved "https://registry.npmjs.org/inflight/-/inflight-1.0.6.tgz"
@@ -6434,6 +6557,13 @@ is-callable@^1.1.3, is-callable@^1.1.4, is-callable@^1.2.4:
   resolved "https://registry.npmjs.org/is-callable/-/is-callable-1.2.4.tgz"
   integrity sha512-nsuwtxZfMX67Oryl9LCQ+upnC0Z0BgpwntpS89m1H/TLF0zNfzfLMV/9Wa/6MZsj0acpEjAO0KF1xT6ZdLl95w==
 
+is-core-module@^2.5.0:
+  version "2.11.0"
+  resolved "https://registry.yarnpkg.com/is-core-module/-/is-core-module-2.11.0.tgz#ad4cb3e3863e814523c96f3f58d26cc570ff0144"
+  integrity sha512-RRjxlvLDkD1YJwDbroBHMb+cukurkDWNyHx7D3oNB5x9rb5ogcksMC5wHCadcXoo67gVr/+3GFySh3134zi6rw==
+  dependencies:
+    has "^1.0.3"
+
 is-core-module@^2.9.0:
   version "2.10.0"
   resolved "https://registry.npmjs.org/is-core-module/-/is-core-module-2.10.0.tgz"
@@ -6597,6 +6727,11 @@ is-path-inside@^3.0.2, is-path-inside@^3.0.3:
   resolved "https://registry.npmjs.org/is-path-inside/-/is-path-inside-3.0.3.tgz"
   integrity sha512-Fd4gABb+ycGAmKou8eMftCupSir5lRxqf4aD/vd0cD2qc4HL07OjCeuHMr8Ro4CoMaeCKDB0/ECBOVWjTwUvPQ==
 
+is-plain-obj@^1.1.0:
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/is-plain-obj/-/is-plain-obj-1.1.0.tgz#71a50c8429dfca773c92a390a4a03b39fcd51d3e"
+  integrity sha512-yvkRyxmFKEOQ4pNXCmJG5AEQNlXJS5LaONXo5/cLdTZdWvsZ1ioJEonLGAosKlMWE8lwUy/bJzMjcw8az73+Fg==
+
 is-plain-obj@^3.0.0:
   version "3.0.0"
   resolved "https://registry.npmjs.org/is-plain-obj/-/is-plain-obj-3.0.0.tgz"
@@ -7425,6 +7560,11 @@ jspdf@^2.5.1:
     dompurify "^2.2.0"
     html2canvas "^1.0.0-rc.5"
 
+junk@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/junk/-/junk-4.0.0.tgz#9b1104ddf5281cd24ffa3c8a7443d19ce192b37f"
+  integrity sha512-ojtSU++zLJ3jQG9bAYjg94w+/DOJtRyD7nPaerMFrBhmdVmiV5/exYH5t4uHga4G/95nT6hr1OJoKIFbYbrW5w==
+
 just-debounce@^1.0.0:
   version "1.1.0"
   resolved "https://registry.npmjs.org/just-debounce/-/just-debounce-1.1.0.tgz"
@@ -7510,7 +7650,7 @@ kind-of@^5.0.0, kind-of@^5.0.2:
   resolved "https://registry.npmjs.org/kind-of/-/kind-of-5.1.0.tgz"
   integrity sha512-NGEErnH6F2vUuXDh+OlbcKW7/wOcfdRHaZ7VWtqCztfHri/++YKmP51OdWeGPuqCOba6kk2OTe5d02VmTB80Pw==
 
-kind-of@^6.0.0, kind-of@^6.0.2:
+kind-of@^6.0.0, kind-of@^6.0.2, kind-of@^6.0.3:
   version "6.0.3"
   resolved "https://registry.npmjs.org/kind-of/-/kind-of-6.0.3.tgz"
   integrity sha512-dcS1ul+9tmeD95T+x28/ehLgd9mENa3LsvDTtzm3vyBEO7RPptvAD+t44WVXaUjTBRcrpFeFlC8WCruUR456hw==
@@ -7832,6 +7972,16 @@ map-cache@^0.2.0, map-cache@^0.2.2:
   resolved "https://registry.npmjs.org/map-cache/-/map-cache-0.2.2.tgz"
   integrity sha512-8y/eV9QQZCiyn1SprXSrCmqJN0yNRATe+PO8ztwqrvrbdRLA3eYJF0yaR0YayLWkMbsQSKWS9N2gPcGEc4UsZg==
 
+map-obj@^1.0.0:
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/map-obj/-/map-obj-1.0.1.tgz#d933ceb9205d82bdcf4886f6742bdc2b4dea146d"
+  integrity sha512-7N/q3lyZ+LVCp7PzuxrJr4KMbBE2hW7BT7YNia330OFxIf4d3r5zVpicP2650l7CPN6RM9zOJRl3NGpqSiw3Eg==
+
+map-obj@^4.1.0:
+  version "4.3.0"
+  resolved "https://registry.yarnpkg.com/map-obj/-/map-obj-4.3.0.tgz#9304f906e93faae70880da102a9f1df0ea8bb05a"
+  integrity sha512-hdN1wVrZbb29eBGiGjJbeP8JbKjq1urkHJ/LIP/NY48MZ1QVXUsQBV1G1zvYFHn1XE06cwjBsOI2K3Ulnj1YXQ==
+
 map-visit@^1.0.0:
   version "1.0.0"
   resolved "https://registry.npmjs.org/map-visit/-/map-visit-1.0.0.tgz"
@@ -7892,6 +8042,24 @@ memfs@^3.4.3:
   dependencies:
     fs-monkey "^1.0.3"
 
+meow@^10.1.2:
+  version "10.1.5"
+  resolved "https://registry.yarnpkg.com/meow/-/meow-10.1.5.tgz#be52a1d87b5f5698602b0f32875ee5940904aa7f"
+  integrity sha512-/d+PQ4GKmGvM9Bee/DPa8z3mXs/pkvJE2KEThngVNOqtmljC6K7NMPxtc2JeZYTmpWb9k/TmxjeL18ez3h7vCw==
+  dependencies:
+    "@types/minimist" "^1.2.2"
+    camelcase-keys "^7.0.0"
+    decamelize "^5.0.0"
+    decamelize-keys "^1.1.0"
+    hard-rejection "^2.1.0"
+    minimist-options "4.1.0"
+    normalize-package-data "^3.0.2"
+    read-pkg-up "^8.0.0"
+    redent "^4.0.0"
+    trim-newlines "^4.0.2"
+    type-fest "^1.2.2"
+    yargs-parser "^20.2.9"
+
 merge-descriptors@1.0.1:
   version "1.0.1"
   resolved "https://registry.npmjs.org/merge-descriptors/-/merge-descriptors-1.0.1.tgz"
@@ -7973,7 +8141,7 @@ mimic-fn@^2.1.0:
   resolved "https://registry.npmjs.org/mimic-fn/-/mimic-fn-2.1.0.tgz"
   integrity sha512-OqbOk5oEQeAZ8WXWydlu9HJjz9WVdEIvamMCcXmuqUYjTknH/sqsWvhQ3vgwKFRR1HpjvNBKQ37nbJgYzGqGcg==
 
-min-indent@^1.0.0:
+min-indent@^1.0.0, min-indent@^1.0.1:
   version "1.0.1"
   resolved "https://registry.npmjs.org/min-indent/-/min-indent-1.0.1.tgz"
   integrity sha512-I9jwMn07Sy/IwOj3zVkVik2JTvgpaykDZEigL6Rx6N9LbMywwUSMtxET+7lVoDLLd3O3IXwJwvuuns8UB/HeAg==
@@ -8004,6 +8172,15 @@ minimatch@^5.0.1:
   dependencies:
     brace-expansion "^2.0.1"
 
+minimist-options@4.1.0:
+  version "4.1.0"
+  resolved "https://registry.yarnpkg.com/minimist-options/-/minimist-options-4.1.0.tgz#c0655713c53a8a2ebd77ffa247d342c40f010619"
+  integrity sha512-Q4r8ghd80yhO/0j1O3B2BjweX3fiHg9cdOwjJd2J76Q135c+NDxGCqdYKQ1SKBuFfgWbAUzBfvYjPUEeNgqN1A==
+  dependencies:
+    arrify "^1.0.1"
+    is-plain-obj "^1.1.0"
+    kind-of "^6.0.3"
+
 minimist@^1.2.0, minimist@^1.2.6:
   version "1.2.6"
   resolved "https://registry.npmjs.org/minimist/-/minimist-1.2.6.tgz"
@@ -8109,6 +8286,11 @@ neo-async@^2.6.2:
   resolved "https://registry.npmjs.org/neo-async/-/neo-async-2.6.2.tgz"
   integrity sha512-Yd3UES5mWCSqR+qNT93S3UoYUkqAZ9lLg8a7g9rimsWmYGK8cVToA4/sF3RrshdyV3sAGMXVUmpMYOw+dLpOuw==
 
+nested-error-stacks@^2.0.0, nested-error-stacks@^2.1.0:
+  version "2.1.1"
+  resolved "https://registry.yarnpkg.com/nested-error-stacks/-/nested-error-stacks-2.1.1.tgz#26c8a3cee6cc05fbcf1e333cd2fc3e003326c0b5"
+  integrity sha512-9iN1ka/9zmX1ZvLV9ewJYEk9h7RyRRtqdK0woXcqohu8EWIerfPUjYJPg0ULy0UqP7cslmdGc8xKDJcojlKiaw==
+
 next-tick@^1.1.0:
   version "1.1.0"
   resolved "https://registry.npmjs.org/next-tick/-/next-tick-1.1.0.tgz"
@@ -8177,6 +8359,16 @@ normalize-package-data@^2.3.2:
     semver "2 || 3 || 4 || 5"
     validate-npm-package-license "^3.0.1"
 
+normalize-package-data@^3.0.2:
+  version "3.0.3"
+  resolved "https://registry.yarnpkg.com/normalize-package-data/-/normalize-package-data-3.0.3.tgz#dbcc3e2da59509a0983422884cd172eefdfa525e"
+  integrity sha512-p2W1sgqij3zMMyRC067Dg16bfzVH+w7hyegmpIvZ4JNjqtGOVAIvLmjBx3yP7YTe9vKJgkoNOPjwQGogDoMXFA==
+  dependencies:
+    hosted-git-info "^4.0.1"
+    is-core-module "^2.5.0"
+    semver "^7.3.4"
+    validate-npm-package-license "^3.0.1"
+
 normalize-path@^2.1.1:
   version "2.1.1"
   resolved "https://registry.npmjs.org/normalize-path/-/normalize-path-2.1.1.tgz"
@@ -8436,6 +8628,25 @@ os-locale@^1.4.0:
   dependencies:
     lcid "^1.0.0"
 
+p-event@^4.1.0:
+  version "4.2.0"
+  resolved "https://registry.yarnpkg.com/p-event/-/p-event-4.2.0.tgz#af4b049c8acd91ae81083ebd1e6f5cae2044c1b5"
+  integrity sha512-KXatOjCRXXkSePPb1Nbi0p0m+gQAwdlbhi4wQKJPI1HsMQS9g+Sqp2o+QHziPr7eYJyOZet836KoHEVM1mwOrQ==
+  dependencies:
+    p-timeout "^3.1.0"
+
+p-filter@^3.0.0:
+  version "3.0.0"
+  resolved "https://registry.yarnpkg.com/p-filter/-/p-filter-3.0.0.tgz#ce50e03b24b23930e11679ab8694bd09a2d7ed35"
+  integrity sha512-QtoWLjXAW++uTX67HZQz1dbTpqBfiidsB6VtQUC9iR85S120+s0T5sO6s+B5MLzFcZkrEd/DGMmCjR+f2Qpxwg==
+  dependencies:
+    p-map "^5.1.0"
+
+p-finally@^1.0.0:
+  version "1.0.0"
+  resolved "https://registry.yarnpkg.com/p-finally/-/p-finally-1.0.0.tgz#3fbcfb15b899a44123b34b6dcc18b724336a2cae"
+  integrity sha512-LICb2p9CB7FS+0eR1oqWnHhp0FljGLZCWBE9aix0Uye9W8LTQPwMTYVGWQWIw9RdQiDg4+epXQODwIYJtSJaow==
+
 p-limit@^2.2.0:
   version "2.3.0"
   resolved "https://registry.npmjs.org/p-limit/-/p-limit-2.3.0.tgz"
@@ -8471,6 +8682,13 @@ p-map@^4.0.0:
   dependencies:
     aggregate-error "^3.0.0"
 
+p-map@^5.1.0, p-map@^5.3.0:
+  version "5.5.0"
+  resolved "https://registry.yarnpkg.com/p-map/-/p-map-5.5.0.tgz#054ca8ca778dfa4cf3f8db6638ccb5b937266715"
+  integrity sha512-VFqfGDHlx87K66yZrNdI4YGtD70IRyd+zSvgks6mzHPRNkoKy+9EKP4SFC77/vTTQYmRmti7dvqC+m5jBrBAcg==
+  dependencies:
+    aggregate-error "^4.0.0"
+
 p-retry@^4.5.0:
   version "4.6.2"
   resolved "https://registry.npmjs.org/p-retry/-/p-retry-4.6.2.tgz"
@@ -8479,6 +8697,13 @@ p-retry@^4.5.0:
     "@types/retry" "0.12.0"
     retry "^0.13.1"
 
+p-timeout@^3.1.0:
+  version "3.2.0"
+  resolved "https://registry.yarnpkg.com/p-timeout/-/p-timeout-3.2.0.tgz#c7e17abc971d2a7962ef83626b35d635acf23dfe"
+  integrity sha512-rhIwUycgwwKcP9yTOOFK/AKsAopjjCakVqLHePO3CC6Mir1Z99xT+R63jZxAT5lFZLa2inS5h+ZS2GvR99/FBg==
+  dependencies:
+    p-finally "^1.0.0"
+
 p-try@^2.0.0:
   version "2.2.0"
   resolved "https://registry.npmjs.org/p-try/-/p-try-2.2.0.tgz"
@@ -9137,6 +9362,11 @@ queue-microtask@^1.2.2:
   resolved "https://registry.npmjs.org/queue-microtask/-/queue-microtask-1.2.3.tgz"
   integrity sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==
 
+quick-lru@^5.1.1:
+  version "5.1.1"
+  resolved "https://registry.yarnpkg.com/quick-lru/-/quick-lru-5.1.1.tgz#366493e6b3e42a3a6885e2e99d18f80fb7a8c932"
+  integrity sha512-WuyALRjWPDGtt/wzJiadO5AXY+8hZ80hVpe6MyivgraREW751X3SbhRvG3eLKOYN+8VEvqLcf3wdnt44Z4S4SA==
+
 qunit@^2.17.2:
   version "2.19.1"
   resolved "https://registry.npmjs.org/qunit/-/qunit-2.19.1.tgz"
@@ -9201,6 +9431,15 @@ read-pkg-up@^1.0.1:
     find-up "^1.0.0"
     read-pkg "^1.0.0"
 
+read-pkg-up@^8.0.0:
+  version "8.0.0"
+  resolved "https://registry.yarnpkg.com/read-pkg-up/-/read-pkg-up-8.0.0.tgz#72f595b65e66110f43b052dd9af4de6b10534670"
+  integrity sha512-snVCqPczksT0HS2EC+SxUndvSzn6LRCwpfSvLrIfR5BKDQQZMaI6jPRC9dYvYFDRAuFEAnkwww8kBBNE/3VvzQ==
+  dependencies:
+    find-up "^5.0.0"
+    read-pkg "^6.0.0"
+    type-fest "^1.0.1"
+
 read-pkg@^1.0.0:
   version "1.1.0"
   resolved "https://registry.npmjs.org/read-pkg/-/read-pkg-1.1.0.tgz"
@@ -9210,6 +9449,16 @@ read-pkg@^1.0.0:
     normalize-package-data "^2.3.2"
     path-type "^1.0.0"
 
+read-pkg@^6.0.0:
+  version "6.0.0"
+  resolved "https://registry.yarnpkg.com/read-pkg/-/read-pkg-6.0.0.tgz#a67a7d6a1c2b0c3cd6aa2ea521f40c458a4a504c"
+  integrity sha512-X1Fu3dPuk/8ZLsMhEj5f4wFAF0DWoK7qhGJvgaijocXxBmSToKfbFtqbxMO7bVjNA1dmE5huAzjXj/ey86iw9Q==
+  dependencies:
+    "@types/normalize-package-data" "^2.4.0"
+    normalize-package-data "^3.0.2"
+    parse-json "^5.2.0"
+    type-fest "^1.0.1"
+
 readable-stream@^2.0.0, readable-stream@^2.0.1, readable-stream@^2.0.5, readable-stream@^2.1.5, readable-stream@^2.2.2, readable-stream@^2.3.3, readable-stream@^2.3.5, readable-stream@^2.3.6, readable-stream@~2.3.6:
   version "2.3.7"
   resolved "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.7.tgz"
@@ -9261,6 +9510,14 @@ redent@^3.0.0:
     indent-string "^4.0.0"
     strip-indent "^3.0.0"
 
+redent@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/redent/-/redent-4.0.0.tgz#0c0ba7caabb24257ab3bb7a4fd95dd1d5c5681f9"
+  integrity sha512-tYkDkVVtYkSVhuQ4zBgfvciymHaeuel+zFKXShfDnFP5SyVEP7qo70Rf1jTOTCx3vGNAbnEi/xFkcfQVMIBWag==
+  dependencies:
+    indent-string "^5.0.0"
+    strip-indent "^4.0.0"
+
 regenerate-unicode-properties@^10.0.1:
   version "10.0.1"
   resolved "https://registry.npmjs.org/regenerate-unicode-properties/-/regenerate-unicode-properties-10.0.1.tgz"
@@ -9856,6 +10113,11 @@ slash@^3.0.0:
   resolved "https://registry.npmjs.org/slash/-/slash-3.0.0.tgz"
   integrity sha512-g9Q1haeby36OSStwb4ntCGGGaKsaVSjQ68fBxoQcutl5fS1vuY18H3wSt3jFyFtrkx+Kz0V1G85A4MyAdDMi2Q==
 
+slash@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/slash/-/slash-4.0.0.tgz#2422372176c4c6c5addb5e2ada885af984b396a7"
+  integrity sha512-3dOsAHXXUkQTpOYcoAxLIorMTp4gIQr5IW3iVb7A7lFIp0VHhnynm9izx6TssdrIcVIESAlVjtnO2K8bg+Coew==
+
 slugify@^1.6.5:
   version "1.6.5"
   resolved "https://registry.npmjs.org/slugify/-/slugify-1.6.5.tgz"
@@ -10258,6 +10520,13 @@ strip-indent@^3.0.0:
   dependencies:
     min-indent "^1.0.0"
 
+strip-indent@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/strip-indent/-/strip-indent-4.0.0.tgz#b41379433dd06f5eae805e21d631e07ee670d853"
+  integrity sha512-mnVSV2l+Zv6BLpSD/8V87CW/y9EmmbYzGCIavsnsI6/nwn26DwffM/yztm30Z/I2DY9wdS3vXVCMnHDgZaVNoA==
+  dependencies:
+    min-indent "^1.0.1"
+
 strip-json-comments@^2.0.0:
   version "2.0.1"
   resolved "https://registry.yarnpkg.com/strip-json-comments/-/strip-json-comments-2.0.1.tgz#3c531942e908c2697c0ec344858c286c7ca0a60a"
@@ -10537,6 +10806,11 @@ tr46@~0.0.3:
   resolved "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz"
   integrity sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==
 
+trim-newlines@^4.0.2:
+  version "4.0.2"
+  resolved "https://registry.yarnpkg.com/trim-newlines/-/trim-newlines-4.0.2.tgz#d6aaaf6a0df1b4b536d183879a6b939489808c7c"
+  integrity sha512-GJtWyq9InR/2HRiLZgpIKv+ufIKrVrvjQWEj7PxAXNc5dwbNJkqhAUoAGgzRmULAnoOM5EIpveYd3J2VeSAIew==
+
 ts-jest@^29.0.3:
   version "29.0.3"
   resolved "https://registry.yarnpkg.com/ts-jest/-/ts-jest-29.0.3.tgz#63ea93c5401ab73595440733cefdba31fcf9cb77"
@@ -10648,6 +10922,11 @@ type-fest@^0.21.3:
   resolved "https://registry.npmjs.org/type-fest/-/type-fest-0.21.3.tgz"
   integrity sha512-t0rzBq87m3fVcduHDUFhKmyyX+9eo6WQjZvf51Ea/M0Q7+T374Jp1aUiyUl0GKxp8M/OETVHSDvmkyPgvX+X2w==
 
+type-fest@^1.0.1, type-fest@^1.2.1, type-fest@^1.2.2:
+  version "1.4.0"
+  resolved "https://registry.yarnpkg.com/type-fest/-/type-fest-1.4.0.tgz#e9fb813fe3bf1744ec359d55d1affefa76f14be1"
+  integrity sha512-yGSza74xk0UG8k+pLh5oeoYirvIiWo5t0/o3zHHAO2tRDiZcxWP7fywNlXhqb6/r6sWvwi+RsyQMWhVLe4BVuA==
+
 type-is@~1.6.18:
   version "1.6.18"
   resolved "https://registry.npmjs.org/type-is/-/type-is-1.6.18.tgz"
@@ -11499,7 +11778,7 @@ yaml@^2.0.0:
   resolved "https://registry.npmjs.org/yaml/-/yaml-2.1.1.tgz"
   integrity sha512-o96x3OPo8GjWeSLF+wOAbrPfhFOGY0W00GNaxCDv+9hkcDJEnev1yh8S7pgHF0ik6zc8sQLuL8hjHjJULZp8bw==
 
-yargs-parser@^20.2.2:
+yargs-parser@^20.2.2, yargs-parser@^20.2.9:
   version "20.2.9"
   resolved "https://registry.npmjs.org/yargs-parser/-/yargs-parser-20.2.9.tgz"
   integrity sha512-y11nGElTIV+CT3Zv9t7VKl+Q3hTQoT9a1Qzezhhl6Rp21gJ/IVTW7Z3y9EWXhuUBC2Shnf+DX0antecpAwSP8w==

From 02e35b4720c0268ae053f2db2eda7338e670cd44 Mon Sep 17 00:00:00 2001
From: Matthias Bernt <m.bernt@ufz.de>
Date: Fri, 20 Jan 2023 16:26:12 +0100
Subject: [PATCH 236/350] add xsd datatype

---
 lib/galaxy/config/sample/datatypes_conf.xml.sample | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/galaxy/config/sample/datatypes_conf.xml.sample b/lib/galaxy/config/sample/datatypes_conf.xml.sample
index 7392118b503..cb077806490 100644
--- a/lib/galaxy/config/sample/datatypes_conf.xml.sample
+++ b/lib/galaxy/config/sample/datatypes_conf.xml.sample
@@ -441,6 +441,7 @@
     <datatype extension="memexml" type="galaxy.datatypes.xml:MEMEXml" mimetype="application/xml" display_in_upload="true"/>
     <datatype extension="cisml" type="galaxy.datatypes.xml:CisML" mimetype="application/xml" display_in_upload="true"/>
     <datatype extension="xml" type="galaxy.datatypes.xml:GenericXml" mimetype="application/xml" display_in_upload="true"/>
+    <datatype extension="xsd" type="galaxy.datatypes.xml:GenericXml" mimetype="application/xml" display_in_upload="true"/>
     <datatype extension="dzi" type="galaxy.datatypes.xml:Dzi" mimetype="application/xml" display_in_upload="true"/>
     <datatype extension="vcf" type="galaxy.datatypes.tabular:Vcf" display_in_upload="true">
       <converter file="interval_to_bgzip_converter.xml" target_datatype="bgzip"/>

From bc929353bd6f6ebe578a28bffb9e222806b1ea89 Mon Sep 17 00:00:00 2001
From: Yvan Le Bras <yvan.le-bras@mnhn.fr>
Date: Fri, 20 Jan 2023 17:17:50 +0100
Subject: [PATCH 237/350] add descriptions

---
 lib/galaxy/config/sample/datatypes_conf.xml.sample | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/galaxy/config/sample/datatypes_conf.xml.sample b/lib/galaxy/config/sample/datatypes_conf.xml.sample
index f5fa6d505ae..0bb39a5e45d 100644
--- a/lib/galaxy/config/sample/datatypes_conf.xml.sample
+++ b/lib/galaxy/config/sample/datatypes_conf.xml.sample
@@ -933,9 +933,9 @@
     <datatype extension="param" type="galaxy.datatypes.text:Param" display_in_upload="true"/>
     <datatype extension="den_fmt" type="galaxy.datatypes.text:FormattedDensity" display_in_upload="true"/>
     <!-- ECOLOGY types -->
-    <datatype extension="bil" type="galaxy.datatypes.binary:Binary" mimetype="application/octet-stream" display_in_upload="true" subclass="true"/>
-    <datatype extension="hdr" type="galaxy.datatypes.data:Text" mimetype="text/plain" display_in_upload="true" subclass="true"/>
-    <datatype extension="shp" type="galaxy.datatypes.gis:Shapefile" mimetype="application/octet-stream" display_in_upload="true"/>
+    <datatype extension="bil" type="galaxy.datatypes.binary:Binary" mimetype="application/octet-stream" display_in_upload="true" subclass="true" description="ENVI file with band interleave by line (BIL) format"/>
+    <datatype extension="hdr" type="galaxy.datatypes.data:Text" mimetype="text/plain" display_in_upload="true" subclass="true" description="ENVI metadata header file"/>
+    <datatype extension="shp" type="galaxy.datatypes.gis:Shapefile" mimetype="application/octet-stream" display_in_upload="true" description="geospatial vector data format for geographic information system"/>
   </registration>
   <sniffers>
     <!--

From e94eeda4294f9689439b32940443d7458206381f Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Fri, 20 Jan 2023 13:10:17 -0500
Subject: [PATCH 238/350] Drop client-watch, update 'serve' target in makefile

---
 Makefile | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/Makefile b/Makefile
index 7833421fcab..b609f14f411 100644
--- a/Makefile
+++ b/Makefile
@@ -208,11 +208,8 @@ client-production-maps: client-node-deps ## Rebuild client-side artifacts for a
 client-format: client-node-deps ## Reformat client code
 	cd client && yarn run format
 
-client-watch: client-node-deps ## A useful target for parallel development building.  See also client-dev-server.
-	cd client && yarn run watch
-
 client-dev-server: client-node-deps ## Starts a webpack dev server for client development (HMR enabled)
-	cd client && yarn run serve
+	cd client && yarn run develop
 
 client-test: client-node-deps  ## Run JS unit tests
 	cd client && yarn run test

From d09bd9350265c096ec91b71a41952faeecc03687 Mon Sep 17 00:00:00 2001
From: galaxybot <galaxybot@users.noreply.github.com>
Date: Sat, 21 Jan 2023 03:10:19 +0000
Subject: [PATCH 239/350] Update Python dependencies

---
 lib/galaxy/dependencies/dev-requirements.txt  | 14 +++++-----
 .../dependencies/pinned-lint-requirements.txt |  4 +--
 .../dependencies/pinned-requirements.txt      | 27 ++++++++++---------
 .../pinned-typecheck-requirements.txt         | 14 +++++-----
 4 files changed, 31 insertions(+), 28 deletions(-)

diff --git a/lib/galaxy/dependencies/dev-requirements.txt b/lib/galaxy/dependencies/dev-requirements.txt
index 2d83fdd2c9f..afb44df79cc 100644
--- a/lib/galaxy/dependencies/dev-requirements.txt
+++ b/lib/galaxy/dependencies/dev-requirements.txt
@@ -53,7 +53,7 @@ lockfile==0.12.2 ; python_version >= "3.7" and python_version < "3.11"
 lxml==4.9.2 ; python_version >= "3.7" and python_version < "3.11"
 markdown-it-reporter==0.0.2 ; python_version >= "3.7" and python_version < "3.11"
 markdown==3.4.1 ; python_version >= "3.7" and python_version < "3.11"
-markupsafe==2.1.1 ; python_version >= "3.7" and python_version < "3.11"
+markupsafe==2.1.2 ; python_version >= "3.7" and python_version < "3.11"
 matplotlib==3.5.3 ; python_version >= "3.7" and python_version < "3.11"
 mirakuru==2.4.2 ; python_version >= "3.7" and python_version < "3.11"
 mistune==2.0.4 ; python_version >= "3.7" and python_version < "3.11"
@@ -89,10 +89,10 @@ pytest-metadata==2.0.4 ; python_version >= "3.7" and python_version < "3.11"
 pytest-mock==3.10.0 ; python_version >= "3.7" and python_version < "3.11"
 pytest-postgresql==4.1.1 ; python_version >= "3.7" and python_version < "3.11"
 pytest-shard==0.1.2 ; python_version >= "3.7" and python_version < "3.11"
-pytest==7.2.0 ; python_version >= "3.7" and python_version < "3.11"
+pytest==7.2.1 ; python_version >= "3.7" and python_version < "3.11"
 python-dateutil==2.8.2 ; python_version >= "3.7" and python_version < "3.11"
-python-irodsclient==1.1.5 ; python_version >= "3.7" and python_version < "3.11"
-pytz==2022.7 ; python_version >= "3.7" and python_version < "3.11"
+python-irodsclient==1.1.6 ; python_version >= "3.7" and python_version < "3.11"
+pytz==2022.7.1 ; python_version >= "3.7" and python_version < "3.11"
 rdflib==6.2.0 ; python_version >= "3.7" and python_version < "3.11"
 recommonmark==0.7.1 ; python_version >= "3.7" and python_version < "3.11"
 requests==2.28.2 ; python_version >= "3.7" and python_version < "3.11"
@@ -104,7 +104,7 @@ schema-salad==8.3.20230109181936 ; python_version >= "3.7" and python_version <
 scipy==1.7.3 ; python_version >= "3.7" and python_version < "3.11"
 selenium==4.7.2 ; python_version >= "3.7" and python_version < "3.11"
 seletools==1.3.0 ; python_version >= "3.7" and python_version < "3.11"
-setuptools==65.7.0 ; python_version >= "3.7" and python_version < "3.11"
+setuptools==66.1.1 ; python_version >= "3.7" and python_version < "3.11"
 six==1.16.0 ; python_version >= "3.7" and python_version < "3.11"
 sniffio==1.3.0 ; python_version >= "3.7" and python_version < "3.11"
 snowballstemmer==2.2.0 ; python_version >= "3.7" and python_version < "3.11"
@@ -120,7 +120,7 @@ sphinxcontrib-qthelp==1.0.3 ; python_version >= "3.7" and python_version < "3.11
 sphinxcontrib-serializinghtml==1.1.5 ; python_version >= "3.7" and python_version < "3.11"
 statsd==4.0.1 ; python_version >= "3.7" and python_version < "3.11"
 testfixtures==7.0.4 ; python_version >= "3.7" and python_version < "3.11"
-tinydb==4.7.0 ; python_version >= "3.7" and python_version < "3.11"
+tinydb==4.7.1 ; python_version >= "3.7" and python_version < "3.11"
 toml==0.10.2 ; python_version >= "3.7" and python_version < "3.11"
 tomli==2.0.1 ; python_version >= "3.7" and python_version < "3.11"
 trio-websocket==0.9.2 ; python_version >= "3.7" and python_version < "3.11"
@@ -134,7 +134,7 @@ urllib3==1.26.14 ; python_version >= "3.7" and python_version < "3.11"
 urllib3[socks]==1.26.14 ; python_version >= "3.7" and python_version < "3.11"
 vine==5.0.0 ; python_version >= "3.7" and python_version < "3.11"
 watchdog==2.2.1 ; python_version >= "3.7" and python_version < "3.11"
-wcwidth==0.2.5 ; python_version >= "3.7" and python_version < "3.11"
+wcwidth==0.2.6 ; python_version >= "3.7" and python_version < "3.11"
 wrapt==1.14.1 ; python_version >= "3.7" and python_version < "3.11"
 wsproto==1.2.0 ; python_version >= "3.7" and python_version < "3.11"
 yarl==1.8.2 ; python_version >= "3.7" and python_version < "3.11"
diff --git a/lib/galaxy/dependencies/pinned-lint-requirements.txt b/lib/galaxy/dependencies/pinned-lint-requirements.txt
index 4cf3961e3dd..e5ca6fafb5d 100644
--- a/lib/galaxy/dependencies/pinned-lint-requirements.txt
+++ b/lib/galaxy/dependencies/pinned-lint-requirements.txt
@@ -1,10 +1,10 @@
 attrs==22.2.0
 flake8==5.0.4
-flake8-bugbear==22.12.6
+flake8-bugbear==23.1.20
 importlib-metadata==4.2.0
 mccabe==0.7.0
 pycodestyle==2.9.1
 pyflakes==2.5.0
-ruff==0.0.223
+ruff==0.0.228
 typing_extensions==4.4.0
 zipp==3.11.0
diff --git a/lib/galaxy/dependencies/pinned-requirements.txt b/lib/galaxy/dependencies/pinned-requirements.txt
index 3bd0f4ea87b..3cf5b20fd73 100644
--- a/lib/galaxy/dependencies/pinned-requirements.txt
+++ b/lib/galaxy/dependencies/pinned-requirements.txt
@@ -5,8 +5,8 @@ adal==1.2.7 ; python_version >= "3.7" and python_version < "3.11"
 aiofiles==22.1.0 ; python_version >= "3.7" and python_version < "3.11"
 aiohttp==3.8.3 ; python_version >= "3.7" and python_version < "3.11"
 aiosignal==1.3.1 ; python_version >= "3.7" and python_version < "3.11"
-alembic==1.9.1 ; python_version >= "3.7" and python_version < "3.11"
-alembic_utils==0.7.8 ; python_version >= "3.7" and python_version < "3.11"
+alembic-utils==0.7.8 ; python_version >= "3.7" and python_version < "3.11"
+alembic==1.9.2 ; python_version >= "3.7" and python_version < "3.11"
 amqp==5.1.1 ; python_version >= "3.7" and python_version < "3.11"
 anyio==3.6.2 ; python_version >= "3.7" and python_version < "3.11"
 apispec==6.0.2 ; python_version >= "3.7" and python_version < "3.11"
@@ -46,7 +46,6 @@ cloudauthz==0.6.0 ; python_version >= "3.7" and python_version < "3.11"
 cloudbridge==3.1.0 ; python_version >= "3.7" and python_version < "3.11"
 colorama==0.4.6 ; python_version >= "3.7" and python_version < "3.11" and platform_system == "Windows"
 coloredlogs==15.0.1 ; python_version >= "3.7" and python_version < "3.11"
-commonmark==0.9.1 ; python_version >= "3.7" and python_version < "3.11"
 cryptography==39.0.0 ; python_version >= "3.7" and python_version < "3.11"
 cwl-upgrader==1.2.4 ; python_version >= "3.7" and python_version < "3.11"
 cwl-utils==0.21 ; python_version >= "3.7" and python_version < "3.11"
@@ -55,7 +54,7 @@ decorator==5.1.1 ; python_version >= "3.7" and python_version < "3.11"
 defusedxml==0.7.1 ; python_version >= "3.7" and python_version < "3.11"
 deprecation==2.1.0 ; python_version >= "3.7" and python_version < "3.11"
 dictobj==0.4 ; python_version >= "3.7" and python_version < "3.11"
-dnspython==2.2.1 ; python_version >= "3.7" and python_version < "3.11"
+dnspython==2.3.0 ; python_version >= "3.7" and python_version < "3.11"
 docopt==0.6.2 ; python_version >= "3.7" and python_version < "3.11"
 docutils==0.16 ; python_version >= "3.7" and python_version < "3.11"
 ecdsa==0.18.0 ; python_version >= "3.7" and python_version < "3.11"
@@ -63,6 +62,7 @@ edam-ontology==1.25.2 ; python_version >= "3.7" and python_version < "3.11"
 email-validator==1.3.0 ; python_version >= "3.7" and python_version < "3.11"
 fastapi-utils==0.2.1 ; python_version >= "3.7" and python_version < "3.11"
 fastapi==0.89.1 ; python_version >= "3.7" and python_version < "3.11"
+flupy==1.2.0 ; python_version >= "3.7" and python_version < "3.11"
 frozenlist==1.3.3 ; python_version >= "3.7" and python_version < "3.11"
 fs==2.4.16 ; python_version >= "3.7" and python_version < "3.11"
 funcsigs==1.0.2 ; python_version >= "3.7" and python_version < "3.11"
@@ -82,15 +82,17 @@ importlib-resources==5.10.2 ; python_version >= "3.7" and python_version < "3.11
 isa-rwval==0.10.10 ; python_version >= "3.7" and python_version < "3.11"
 isodate==0.6.1 ; python_version >= "3.7" and python_version < "3.11"
 jinja2==3.1.2 ; python_version >= "3.7" and python_version < "3.11"
-jsonref==1.0.1 ; python_version >= "3.7" and python_version < "3.11"
+jsonref==1.1.0 ; python_version >= "3.7" and python_version < "3.11"
 jsonschema==4.17.3 ; python_version >= "3.7" and python_version < "3.11"
 kombu==5.2.4 ; python_version >= "3.7" and python_version < "3.11"
 lagom==2.2.0 ; python_version >= "3.7" and python_version < "3.11"
 lockfile==0.12.2 ; python_version >= "3.7" and python_version < "3.11"
 lxml==4.9.2 ; python_version >= "3.7" and python_version < "3.11"
 mako==1.2.4 ; python_version >= "3.7" and python_version < "3.11"
+markdown-it-py==2.1.0 ; python_version >= "3.7" and python_version < "3.11"
 markdown==3.4.1 ; python_version >= "3.7" and python_version < "3.11"
-markupsafe==2.1.1 ; python_version >= "3.7" and python_version < "3.11"
+markupsafe==2.1.2 ; python_version >= "3.7" and python_version < "3.11"
+mdurl==0.1.2 ; python_version >= "3.7" and python_version < "3.11"
 mercurial==6.3.2 ; python_version >= "3.7" and python_version < "3.11"
 mistune==2.0.4 ; python_version >= "3.7" and python_version < "3.11"
 mrcfile==1.4.3 ; python_version >= "3.7" and python_version < "3.11"
@@ -103,7 +105,8 @@ numpy==1.21.6 ; python_version >= "3.7" and python_version < "3.11"
 oauthlib==3.2.2 ; python_version >= "3.7" and python_version < "3.11"
 oyaml==1.0 ; python_version >= "3.7" and python_version < "3.11"
 packaging==21.3 ; python_version >= "3.7" and python_version < "3.11"
-paramiko==2.12.0 ; python_version >= "3.7" and python_version < "3.11"
+paramiko==3.0.0 ; python_version >= "3.7" and python_version < "3.11"
+parse==1.19.0 ; python_version >= "3.7" and python_version < "3.11"
 parsley==1.3 ; python_version >= "3.7" and python_version < "3.11"
 paste==3.5.2 ; python_version >= "3.7" and python_version < "3.11"
 pastedeploy==3.0.1 ; python_version >= "3.7" and python_version < "3.11"
@@ -138,7 +141,7 @@ python-jose==3.3.0 ; python_version >= "3.7" and python_version < "3.11"
 python-magic==0.4.27 ; python_version >= "3.7" and python_version < "3.11"
 python-multipart==0.0.5 ; python_version >= "3.7" and python_version < "3.11"
 python3-openid==3.2.0 ; python_version >= "3.7" and python_version < "3.11"
-pytz==2022.7 ; python_version >= "3.7" and python_version < "3.11"
+pytz==2022.7.1 ; python_version >= "3.7" and python_version < "3.11"
 pyyaml==6.0 ; python_version >= "3.7" and python_version < "3.11"
 pyzmq==25.0.0 ; python_version >= "3.7" and python_version < "3.11"
 rdflib==6.2.0 ; python_version >= "3.7" and python_version < "3.11"
@@ -148,7 +151,7 @@ requests-oauthlib==1.3.1 ; python_version >= "3.7" and python_version < "3.11"
 requests-toolbelt==0.10.1 ; python_version >= "3.7" and python_version < "3.11"
 requests-unixsocket==0.3.0 ; python_version >= "3.7" and python_version < "3.11"
 requests==2.28.2 ; python_version >= "3.7" and python_version < "3.11"
-rich==13.0.1 ; python_version >= "3.7" and python_version < "3.11"
+rich==13.2.0 ; python_version >= "3.7" and python_version < "3.11"
 rocrate==0.7.0 ; python_version >= "3.7" and python_version < "3.11"
 routes==2.5.1 ; python_version >= "3.7" and python_version < "3.11"
 rsa==4.9 ; python_version >= "3.7" and python_version < "3.11"
@@ -156,7 +159,7 @@ ruamel-yaml-clib==0.2.7 ; platform_python_implementation == "CPython" and python
 ruamel-yaml==0.17.21 ; python_version < "3.11" and python_version >= "3.7"
 schema-salad==8.3.20230109181936 ; python_version >= "3.7" and python_version < "3.11"
 setuptools-scm==5.0.2 ; python_version >= "3.7" and python_version < "3.11"
-setuptools==65.7.0 ; python_version >= "3.7" and python_version < "3.11"
+setuptools==66.1.1 ; python_version >= "3.7" and python_version < "3.11"
 shellescape==3.8.1 ; python_version >= "3.7" and python_version < "3.11"
 six==1.16.0 ; python_version >= "3.7" and python_version < "3.11"
 sniffio==1.3.0 ; python_version >= "3.7" and python_version < "3.11"
@@ -173,7 +176,7 @@ svgwrite==1.4.3 ; python_version >= "3.7" and python_version < "3.11"
 tempita==0.5.2 ; python_version >= "3.7" and python_version < "3.11"
 tenacity==8.1.0 ; python_version >= "3.7" and python_version < "3.11"
 tifffile==2021.11.2 ; python_version >= "3.7" and python_version < "3.11"
-tinydb==4.7.0 ; python_version >= "3.7" and python_version < "3.11"
+tinydb==4.7.1 ; python_version >= "3.7" and python_version < "3.11"
 tornado==6.2 ; python_version >= "3.7" and python_version < "3.11"
 tqdm==4.64.1 ; python_version >= "3.7" and python_version < "3.11"
 tuspy==1.0.0 ; python_version >= "3.7" and python_version < "3.11"
@@ -185,7 +188,7 @@ urllib3==1.26.14 ; python_version >= "3.7" and python_version < "3.11"
 uvicorn==0.20.0 ; python_version >= "3.7" and python_version < "3.11"
 uvloop==0.17.0 ; python_version >= "3.7" and python_version < "3.11"
 vine==5.0.0 ; python_version >= "3.7" and python_version < "3.11"
-wcwidth==0.2.5 ; python_version >= "3.7" and python_version < "3.11"
+wcwidth==0.2.6 ; python_version >= "3.7" and python_version < "3.11"
 webencodings==0.5.1 ; python_version >= "3.7" and python_version < "3.11"
 webob==1.8.7 ; python_version >= "3.7" and python_version < "3.11"
 whoosh==2.7.4 ; python_version >= "3.7" and python_version < "3.11"
diff --git a/lib/galaxy/dependencies/pinned-typecheck-requirements.txt b/lib/galaxy/dependencies/pinned-typecheck-requirements.txt
index f1e1c5305b3..5b68529c79c 100644
--- a/lib/galaxy/dependencies/pinned-typecheck-requirements.txt
+++ b/lib/galaxy/dependencies/pinned-typecheck-requirements.txt
@@ -6,16 +6,16 @@ pycparser==2.21
 tomli==2.0.1
 typed-ast==1.5.4
 types-bleach==5.0.3.1
-types-boto==2.49.18.4
+types-boto==2.49.18.5
 types-contextvars==2.4.7
 types-dataclasses==0.6.6
-types-docutils==0.19.1.1
-types-Markdown==3.4.2.1
-types-paramiko==2.12.0.2
+types-docutils==0.19.1.2
+types-Markdown==3.4.2.2
+types-paramiko==2.12.0.3
 types-pkg-resources==0.1.3
-types-python-dateutil==2.8.19.5
-types-PyYAML==6.0.12.2
-types-requests==2.28.11.7
+types-python-dateutil==2.8.19.6
+types-PyYAML==6.0.12.3
+types-requests==2.28.11.8
 types-six==1.16.21.4
 types-urllib3==1.26.25.4
 typing_extensions==4.4.0

From a79c3619f08db1875413d4e72c1efb4b949c094e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sat, 21 Jan 2023 12:26:10 +0100
Subject: [PATCH 240/350] More f-strings for ruff

---
 lib/galaxy/job_execution/actions/post.py          | 2 +-
 lib/galaxy/model/dataset_collections/structure.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/job_execution/actions/post.py b/lib/galaxy/job_execution/actions/post.py
index 8b329b48ce1..47b466110cb 100644
--- a/lib/galaxy/job_execution/actions/post.py
+++ b/lib/galaxy/job_execution/actions/post.py
@@ -333,7 +333,7 @@ class ColumnSetAction(DefaultJobAction):
 
     @classmethod
     def get_short_str(cls, pja):
-        return f"Set the following metadata values:<br/>{'<br/>'.join('{} : {}'.format(escape(k), escape(v)) for k, v in pja.action_arguments.items())}"
+        return f"Set the following metadata values:<br/>{'<br/>'.join(f'{escape(k)} : {escape(v)}' for k, v in pja.action_arguments.items())}"
 
 
 class SetMetadataAction(DefaultJobAction):
diff --git a/lib/galaxy/model/dataset_collections/structure.py b/lib/galaxy/model/dataset_collections/structure.py
index 08d1946bda3..159f5ad5562 100644
--- a/lib/galaxy/model/dataset_collections/structure.py
+++ b/lib/galaxy/model/dataset_collections/structure.py
@@ -141,7 +141,7 @@ class Tree(BaseTree):
         return Tree(cloned_children, self.collection_type_description)
 
     def __str__(self):
-        return f"Tree[collection_type={self.collection_type_description},children={','.join(map(lambda identifier_and_element: '{}={}'.format(identifier_and_element[0], identifier_and_element[1]), self.children))}]"
+        return f"Tree[collection_type={self.collection_type_description},children={','.join(map(lambda identifier_and_element: f'{identifier_and_element[0]}={identifier_and_element[1]}', self.children))}]"
 
 
 def tool_output_to_structure(get_sliced_input_collection_structure, tool_output, collections_manager):

From b38c0c910e2faef09ebcdcecfa190a1ca685ceaa Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sat, 21 Jan 2023 12:36:51 +0100
Subject: [PATCH 241/350] Stabilize mulled integration tests

The extended timeout waiting for the HDA doesn't really make sense if we
fail before that because the history doesn't finish.
---
 test/integration/test_containerized_jobs.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/test/integration/test_containerized_jobs.py b/test/integration/test_containerized_jobs.py
index a10bc084986..68178fbf053 100644
--- a/test/integration/test_containerized_jobs.py
+++ b/test/integration/test_containerized_jobs.py
@@ -24,20 +24,20 @@ class MulledJobTestCases:
 
     def test_explicit(self, history_id: str) -> None:
         self.dataset_populator.run_tool("mulled_example_explicit", {}, history_id)
-        self.dataset_populator.wait_for_history(history_id, assert_ok=True)
-        output = self.dataset_populator.get_history_dataset_content(history_id, timeout=EXTENDED_TIMEOUT)
+        self.dataset_populator.wait_for_history(history_id, assert_ok=True, timeout=EXTENDED_TIMEOUT)
+        output = self.dataset_populator.get_history_dataset_content(history_id)
         assert "0.7.15-r1140" in output
 
     def test_mulled_simple(self, history_id: str) -> None:
         self.dataset_populator.run_tool("mulled_example_simple", {}, history_id)
-        self.dataset_populator.wait_for_history(history_id, assert_ok=True)
-        output = self.dataset_populator.get_history_dataset_content(history_id, timeout=EXTENDED_TIMEOUT)
+        self.dataset_populator.wait_for_history(history_id, assert_ok=True, timeout=EXTENDED_TIMEOUT)
+        output = self.dataset_populator.get_history_dataset_content(history_id)
         assert "0.7.15-r1140" in output
 
     def test_mulled_explicit_invalid_case(self, history_id: str) -> None:
         self.dataset_populator.run_tool("mulled_example_invalid_case", {}, history_id)
-        self.dataset_populator.wait_for_history(history_id, assert_ok=True)
-        output = self.dataset_populator.get_history_dataset_content(history_id, timeout=EXTENDED_TIMEOUT)
+        self.dataset_populator.wait_for_history(history_id, assert_ok=True, timeout=EXTENDED_TIMEOUT)
+        output = self.dataset_populator.get_history_dataset_content(history_id)
         assert "0.7.15-r1140" in output
 
 

From c431c6f0fc9ec9be996ac77500d2bfbe3ec38cfc Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sat, 21 Jan 2023 12:47:09 +0100
Subject: [PATCH 242/350] Tighten pytest raises assertions

---
 test/unit/util/test_bool_expressions.py |  3 ++-
 test/unit/util/test_sqlite_utils.py     | 14 ++++++++------
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/test/unit/util/test_bool_expressions.py b/test/unit/util/test_bool_expressions.py
index 58e9766a679..1c8596ca528 100644
--- a/test/unit/util/test_bool_expressions.py
+++ b/test/unit/util/test_bool_expressions.py
@@ -1,4 +1,5 @@
 import pytest
+from pyparsing.exceptions import ParseException
 
 from galaxy.util.bool_expressions import (
     BooleanExpressionEvaluator,
@@ -61,7 +62,7 @@ def test_expression_evaluates_as_expected(expr: str, expected: bool, contained_e
 
 @pytest.mark.parametrize("expr", INVALID_EXPRESSIONS_TESTS)
 def test_invalid_expression_raises_exception(expr: str, contained_evaluator: BooleanExpressionEvaluator):
-    with pytest.raises(Exception):
+    with pytest.raises(ParseException):
         contained_evaluator.evaluate_expression(expr)
 
 
diff --git a/test/unit/util/test_sqlite_utils.py b/test/unit/util/test_sqlite_utils.py
index 8e627614316..758733579c5 100644
--- a/test/unit/util/test_sqlite_utils.py
+++ b/test/unit/util/test_sqlite_utils.py
@@ -21,17 +21,19 @@ def test_sqlite_exploits():
     connection = sqlite.connect(":memory:")
     connection.execute("create TABLE FOO (foo1 text)")
     __assert_has_n_rows(connection, "select * from FOO", 0)
-    __assert_query_errors(connection, "select * from FOOX")
+    __assert_query_errors(connection, "select * from FOOX", "no such table")
 
     # Make sure sqlite query cannot execute multiple statements
-    __assert_query_errors(connection, "select * from FOO; select * from FOO")
+    __assert_query_errors(
+        connection, "select * from FOO; select * from FOO", "You can only execute one statement at a time."
+    )
 
     # Make sure sqlite cannot select on PRAGMA results
-    __assert_query_errors(connection, "select * from (PRAGMA database_list)")
+    __assert_query_errors(connection, "select * from (PRAGMA database_list)", "no such table: PRAGMA")
 
     __assert_has_n_rows(connection, "select * from FOO where foo1 in (SELECT foo1 from FOO)", 0)
     # Ensure nested queries cannot modify database.
-    __assert_query_errors(connection, "select * from FOO where foo1 in (INSERT INTO FOO VALUES ('bar')")
+    __assert_query_errors(connection, "select * from FOO where foo1 in (INSERT INTO FOO VALUES ('bar')", "syntax error")
 
     # Should access to the schema be disallowed?
     # __assert_has_n_rows(connection, "select * from SQLITE_MASTER", 0)
@@ -44,8 +46,8 @@ def __assert_has_n_rows(connection, query, n):
     assert count == n
 
 
-def __assert_query_errors(connection, query):
-    with pytest.raises(Exception):
+def __assert_query_errors(connection, query, match):
+    with pytest.raises(Exception, match=match):
         connection.cursor().execute(query)
 
 

From 6d27f6fcf969cd68350305d422a375d3cb064a9d Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sat, 21 Jan 2023 13:28:13 +0100
Subject: [PATCH 243/350] Update purge dataset for new testcase-less testing

---
 test/integration/test_purge_datasets.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/test/integration/test_purge_datasets.py b/test/integration/test_purge_datasets.py
index a5bb44aa8c7..726f698fd3d 100644
--- a/test/integration/test_purge_datasets.py
+++ b/test/integration/test_purge_datasets.py
@@ -8,7 +8,10 @@ from galaxy_test.base.populators import DatasetPopulator
 from galaxy_test.driver import integration_util
 
 
-class PurgeDatasetsIntegrationTestCase(integration_util.IntegrationTestCase):
+class TestPurgeDatasetsIntegration(integration_util.IntegrationTestCase):
+
+    dataset_populator: DatasetPopulator
+
     def setUp(self):
         super().setUp()
         self.dataset_populator = DatasetPopulator(self.galaxy_interactor)

From 6d3ade93dd210a6d137e00609773b5a8807e8d24 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 15:48:26 -0500
Subject: [PATCH 244/350] Join/load: replace strings with attrs; use chaining
 (model)

---
 lib/galaxy/model/__init__.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index 29af9c116d7..f53a3febb67 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -2962,10 +2962,10 @@ class History(Base, HasTags, Dictifiable, UsesAnnotations, HasName, Serializable
             .filter(not_(HistoryDatasetAssociation.deleted))
             .order_by(HistoryDatasetAssociation.table.c.hid.asc())
             .options(
-                joinedload("dataset"),
-                joinedload("dataset.actions"),
-                joinedload("dataset.actions.role"),
-                joinedload("tags"),
+                joinedload(HistoryDatasetAssociation.dataset)
+                .joinedload(Dataset.actions)
+                .joinedload(DatasetPermissions.role),
+                joinedload(HistoryDatasetAssociation.tags),
             )
         )
 

From aa24b9560fa717269ce5250e46f8f46e902be9c2 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 18:01:38 -0500
Subject: [PATCH 245/350] Join/load: replace strings with attrs (model)

---
 lib/galaxy/model/__init__.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index f53a3febb67..bda53e4dc96 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -2993,7 +2993,10 @@ class History(Base, HasTags, Dictifiable, UsesAnnotations, HasName, Serializable
                 .filter(not_(HistoryDatasetCollectionAssociation.deleted))
                 .filter(HistoryDatasetCollectionAssociation.visible)
                 .order_by(HistoryDatasetCollectionAssociation.table.c.hid.asc())
-                .options(joinedload("collection"), joinedload("tags"))
+                .options(
+                    joinedload(HistoryDatasetCollectionAssociation.collection),
+                    joinedload(HistoryDatasetCollectionAssociation.tags),
+                )
             )
             self._active_visible_dataset_collections = query.all()
         return self._active_visible_dataset_collections

From da9b431d5c030f3d4ecbd217e835a45405871984 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 20:21:22 -0500
Subject: [PATCH 246/350] Join/load: replace strings with attrs
 (model.security)

---
 lib/galaxy/model/security.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/model/security.py b/lib/galaxy/model/security.py
index 29159b70d0e..881e3276bf4 100644
--- a/lib/galaxy/model/security.py
+++ b/lib/galaxy/model/security.py
@@ -1507,12 +1507,15 @@ class GalaxyRBACAgent(RBACAgent):
             return True, ""
         action = self.permitted_actions.DATASET_ACCESS
 
+        raise
         lddas = (
             self.sa_session.query(self.model.LibraryDatasetDatasetAssociation)
             .join("library_dataset")
             .filter(self.model.LibraryDataset.folder == folder)
             .join("dataset")
-            .options(joinedload("dataset").joinedload("actions"))
+            .options(
+                joinedload(self.model.LibraryDatasetDatasetAssociation.dataset).joinedload(self.model.Dataset.actions)
+            )
             .all()
         )
 

From 6b063c396433f301445f94e15c297ba3b42f9404 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 21:02:25 -0500
Subject: [PATCH 247/350] Join/load: replace strings with attrs
 (managers.history_contents)

---
 lib/galaxy/managers/history_contents.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/managers/history_contents.py b/lib/galaxy/managers/history_contents.py
index 055a8b94687..077b8fff1fd 100644
--- a/lib/galaxy/managers/history_contents.py
+++ b/lib/galaxy/managers/history_contents.py
@@ -438,7 +438,7 @@ class HistoryContentsManager(base.SortableManager):
             .query(component_class)
             .filter(component_class.id.in_(id_list))
             .options(undefer(component_class._metadata))
-            .options(joinedload("dataset.actions"))  # TODO: use class attr after moving Dataset to declarative mapping.
+            .options(joinedload(component_class.dataset).joinedload(model.Dataset.actions))
             .options(joinedload(component_class.tags))
             .options(joinedload(component_class.annotations))  # type: ignore[attr-defined]
         )

From e07d390db939c14b65fba9563fb29b50b8ae7805 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 21:05:29 -0500
Subject: [PATCH 248/350] Join/load: replace strings with attrs
 (tools.actions.upload_common)

---
 lib/galaxy/tools/actions/upload_common.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/tools/actions/upload_common.py b/lib/galaxy/tools/actions/upload_common.py
index 94f752c8faf..412e83d0b54 100644
--- a/lib/galaxy/tools/actions/upload_common.py
+++ b/lib/galaxy/tools/actions/upload_common.py
@@ -422,10 +422,11 @@ def active_folders(trans, folder):
     # Stolen from galaxy.web.controllers.library_common (importing from which causes a circular issues).
     # Much faster way of retrieving all active sub-folders within a given folder than the
     # performance of the mapper.  This query also eagerloads the permissions on each folder.
+    raise
     return (
         trans.sa_session.query(LibraryFolder)
         .filter_by(parent=folder, deleted=False)
-        .options(joinedload("actions"))
+        .options(joinedload(LibraryFolder.actions))
         .order_by(LibraryFolder.table.c.name)
         .all()
     )

From a1fa4ee817adb96ebb76e1d6c3d0da6fa33fe028 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 21:11:45 -0500
Subject: [PATCH 249/350] Join/load: replace strings with attrs
 (managers.session)

---
 lib/galaxy/managers/session.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/managers/session.py b/lib/galaxy/managers/session.py
index 5d9fc238af8..4f6ca157f0e 100644
--- a/lib/galaxy/managers/session.py
+++ b/lib/galaxy/managers/session.py
@@ -30,7 +30,7 @@ class GalaxySessionManager:
                     self.model.GalaxySession.table.c.is_valid == true(),
                 )
             )
-            .options(joinedload("user"))
+            .options(joinedload(self.model.GalaxySession.user))
             .first()
         )
         return galaxy_session

From bacd49f26ecadc6663bcae90056698c33fa4edf1 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 21:13:31 -0500
Subject: [PATCH 250/350] Join/load: replace strings with attrs
 (webapps.reports...)

---
 lib/galaxy/webapps/reports/controllers/system.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/reports/controllers/system.py b/lib/galaxy/webapps/reports/controllers/system.py
index 0c8bfbe63ee..e26446c75d2 100644
--- a/lib/galaxy/webapps/reports/controllers/system.py
+++ b/lib/galaxy/webapps/reports/controllers/system.py
@@ -115,7 +115,7 @@ class System(BaseUIController):
                         model.History.update_time < cutoff_time,
                     )
                 )
-                .options(joinedload("datasets"))
+                .options(joinedload(model.History.datasets))
             )
 
             for history in histories:

From dcb481eeb0e531e65cd5b28523ceef1bdb1388bb Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Thu, 19 Jan 2023 22:02:04 -0500
Subject: [PATCH 251/350] Join/load: replace strings with attrs
 (webapps...controllers.workflow)

---
 lib/galaxy/webapps/galaxy/controllers/workflow.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/workflow.py b/lib/galaxy/webapps/galaxy/controllers/workflow.py
index 3e51a7d8308..8c8038c6384 100644
--- a/lib/galaxy/webapps/galaxy/controllers/workflow.py
+++ b/lib/galaxy/webapps/galaxy/controllers/workflow.py
@@ -163,12 +163,12 @@ class StoredWorkflowAllPublishedGrid(grids.Grid):
         # of its steps to be eagerly loaded.
         return (
             trans.sa_session.query(self.model_class)
-            .join("user")
+            .join(self.model_class.user)
             .options(
-                lazyload("latest_workflow"),
-                joinedload("user").load_only("username"),
-                joinedload("annotations"),
-                undefer("average_rating"),
+                lazyload(self.model_class.latest_workflow),
+                joinedload(self.model_class.user).load_only(model.User.username),
+                joinedload(self.model_class.annotations),
+                undefer(self.model_class.average_rating),
             )
         )
 
@@ -487,7 +487,7 @@ class WorkflowController(BaseUIController, SharableMixin, UsesStoredWorkflowMixi
             trans.sa_session.query(model.StoredWorkflow)
             .filter_by(user=trans.user, deleted=False, hidden=False)
             .order_by(desc(model.StoredWorkflow.table.c.update_time))
-            .options(joinedload("latest_workflow").joinedload("steps"))
+            .options(joinedload(model.StoredWorkflow.latest_workflow).joinedload(model.Workflow.steps))
             .all()
         )
         if version is None:

From f8567642ee8d4cf934bf488c79d466789fd33e7c Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:04:44 -0500
Subject: [PATCH 252/350] Join/load: replace strings with attrs
 (managers.workflows)

---
 lib/galaxy/managers/workflows.py | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/lib/galaxy/managers/workflows.py b/lib/galaxy/managers/workflows.py
index b1fd01a565a..9e2e011bf77 100644
--- a/lib/galaxy/managers/workflows.py
+++ b/lib/galaxy/managers/workflows.py
@@ -163,10 +163,10 @@ class WorkflowsManager(sharable.SharableModelManager, deletable.DeletableManager
             query = query.outerjoin(model.StoredWorkflow.users_shared_with)
         query = query.outerjoin(model.StoredWorkflow.tags)
 
-        latest_workflow_load = joinedload("latest_workflow")
+        latest_workflow_load = joinedload(model.StoredWorkflow.latest_workflow)
         if not payload.skip_step_counts:
             latest_workflow_load = latest_workflow_load.undefer("step_count")
-        latest_workflow_load = latest_workflow_load.lazyload("steps")
+        latest_workflow_load = latest_workflow_load.lazyload(model.Workflow.steps)
 
         query = query.options(joinedload(model.StoredWorkflow.annotations))
         query = query.options(latest_workflow_load)
@@ -268,9 +268,11 @@ class WorkflowsManager(sharable.SharableModelManager, deletable.DeletableManager
                     )
                 )
         stored_workflow = workflow_query.options(
-            joinedload("annotations"),
-            joinedload("tags"),
-            subqueryload("latest_workflow").joinedload("steps").joinedload("*"),
+            joinedload(trans.app.model.StoredWorkflow.annotations),
+            joinedload(trans.app.model.StoredWorkflow.tags),
+            subqueryload(trans.app.model.StoredWorkflow.latest_workflow)
+            .joinedload(trans.app.model.Workflow.steps)
+            .joinedload("*"),
         ).first()
         if stored_workflow is None:
             if not by_stored_id:
@@ -366,10 +368,10 @@ class WorkflowsManager(sharable.SharableModelManager, deletable.DeletableManager
         if eager:
             q = q.options(
                 subqueryload(model.WorkflowInvocation.steps)
-                .joinedload("implicit_collection_jobs")
-                .joinedload("jobs")
-                .joinedload("job")
-                .joinedload("input_datasets")
+                .joinedload(model.WorkflowInvocationStep.implicit_collection_jobs)
+                .joinedload(model.ImplicitCollectionJobs.jobs)
+                .joinedload(model.ImplicitCollectionJobsJobAssociation.job)
+                .joinedload(model.Job.input_datasets)
             )
         workflow_invocation = q.get(decoded_invocation_id)
         if not workflow_invocation:

From 7358b4421642e3c5749a13c6589dcbf2a1a6cb30 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:20:25 -0500
Subject: [PATCH 253/350] Join/load: replace strings with attrs
 (managers.collections)

---
 lib/galaxy/managers/collections.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/managers/collections.py b/lib/galaxy/managers/collections.py
index 70370edd452..1cd673b50c0 100644
--- a/lib/galaxy/managers/collections.py
+++ b/lib/galaxy/managers/collections.py
@@ -829,7 +829,9 @@ class DatasetCollectionManager:
         DCE = model.DatasetCollectionElement
         qry = Query(DCE).filter(DCE.dataset_collection_id == parent_id)
         qry = qry.order_by(DCE.element_index)
-        qry = qry.options(joinedload("child_collection"), joinedload("hda"))
+        qry = qry.options(
+            joinedload(model.DatasetCollectionElement.child_collection), joinedload(model.DatasetCollectionElement.hda)
+        )
         if limit is not None:
             qry = qry.limit(int(limit))
         if offset is not None:

From 84c017c5d6c5cc186488baf3f89879d6d6f9cedd Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:22:13 -0500
Subject: [PATCH 254/350] Join/load: replace strings with attrs
 (webapps...controllers.page)

---
 lib/galaxy/webapps/galaxy/controllers/page.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/page.py b/lib/galaxy/webapps/galaxy/controllers/page.py
index 180d782dea9..b753e1a0786 100644
--- a/lib/galaxy/webapps/galaxy/controllers/page.py
+++ b/lib/galaxy/webapps/galaxy/controllers/page.py
@@ -161,7 +161,11 @@ class PageAllPublishedGrid(grids.Grid):
             trans.sa_session.query(self.model_class)
             .join("user")
             .filter(model.User.deleted == false())
-            .options(joinedload("user").load_only("username"), joinedload("annotations"), undefer("average_rating"))
+            .options(
+                joinedload(self.model_class.user).load_only("username"),
+                joinedload(self.model_class.annotations),
+                undefer("average_rating"),
+            )
         )
 
     def apply_query_filter(self, trans, query, **kwargs):

From 69e91d339f7ae904aa30c13d80562402fb01cfc0 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:24:01 -0500
Subject: [PATCH 255/350] Join/load: replace strings with attrs
 (webapps...controllers.visualization)

---
 lib/galaxy/webapps/galaxy/controllers/visualization.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/visualization.py b/lib/galaxy/webapps/galaxy/controllers/visualization.py
index e56b249d8a6..248b777ef90 100644
--- a/lib/galaxy/webapps/galaxy/controllers/visualization.py
+++ b/lib/galaxy/webapps/galaxy/controllers/visualization.py
@@ -287,8 +287,12 @@ class VisualizationAllPublishedGrid(grids.Grid):
         # See optimization description comments and TODO for tags in matching public histories query.
         return (
             trans.sa_session.query(self.model_class)
-            .join("user")
-            .options(joinedload("user").load_only("username"), joinedload("annotations"), undefer("average_rating"))
+            .join(self.model_class.user)
+            .options(
+                joinedload(self.model_class.user).load_only("username"),
+                joinedload(self.model_class.annotations),
+                undefer("average_rating"),
+            )
         )
 
     def apply_query_filter(self, trans, query, **kwargs):

From fe7bf276583231098247914aed936433b276fa92 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:36:08 -0500
Subject: [PATCH 256/350] Join/load: replace strings with attrs
 (toolshed-related)

---
 lib/tool_shed/webapp/api/repositories.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/lib/tool_shed/webapp/api/repositories.py b/lib/tool_shed/webapp/api/repositories.py
index 5dfc86d2ecf..6ce3d482a35 100644
--- a/lib/tool_shed/webapp/api/repositories.py
+++ b/lib/tool_shed/webapp/api/repositories.py
@@ -38,6 +38,7 @@ from galaxy.webapps.base.controller import (
     BaseAPIController,
     HTTPBadRequest,
 )
+from tool_shed.webapp import model
 from tool_shed.dependencies import attribute_handlers
 from tool_shed.metadata import repository_metadata_manager
 from tool_shed.repository_types import util as rt_util
@@ -118,7 +119,7 @@ class RepositoriesController(BaseAPIController):
         if owner is None:
             owner = kwd.get("owner", None)
         tsr_id = kwd.get("tsr_id", None)
-        eagerload_columns = ["downloadable_revisions"]
+        eagerload_columns = [model.Repository.downloadable_revisions]
         if None not in [name, owner]:
             # Get the repository information.
             repository = repository_util.get_repository_by_name_and_owner(
@@ -217,7 +218,7 @@ class RepositoriesController(BaseAPIController):
         if name and owner and changeset_revision:
             # Get the repository information.
             repository = repository_util.get_repository_by_name_and_owner(
-                self.app, name, owner, eagerload_columns=["downloadable_revisions"]
+                self.app, name, owner, eagerload_columns=[model.Repository.downloadable_revisions]
             )
             if repository is None:
                 log.debug(f"Cannot locate repository {name} owned by {owner}")
@@ -284,7 +285,7 @@ class RepositoriesController(BaseAPIController):
         tsr_id = kwd.get("tsr_id", None)
         if tsr_id is not None:
             repository = repository_util.get_repository_in_tool_shed(
-                self.app, tsr_id, eagerload_columns=["downloadable_revisions"]
+                self.app, tsr_id, eagerload_columns=[model.Repository.downloadable_revisions]
             )
         else:
             error_message = "Error in the Tool Shed repositories API in get_ordered_installable_revisions: "
@@ -737,7 +738,7 @@ class RepositoriesController(BaseAPIController):
         changeset_revision = kwd.get("changeset_revision", None)
         hexlify_this = util.asbool(kwd.get("hexlify", True))
         repository = repository_util.get_repository_by_name_and_owner(
-            trans.app, name, owner, eagerload_columns=["downloadable_revisions"]
+            trans.app, name, owner, eagerload_columns=[model.Repository.downloadable_revisions]
         )
         if repository and repository.downloadable_revisions:
             repository_metadata = metadata_util.get_repository_metadata_by_changeset_revision(
@@ -837,7 +838,7 @@ class RepositoriesController(BaseAPIController):
         downloadable_only = util.asbool(kwd.get("downloadable_only", "True"))
         all_metadata = {}
         repository = repository_util.get_repository_in_tool_shed(
-            self.app, id, eagerload_columns=["downloadable_revisions"]
+            self.app, id, eagerload_columns=[model.Repository.downloadable_revisions]
         )
         for changeset, changehash in metadata_util.get_metadata_revisions(
             self.app, repository, sort_revisions=True, downloadable=downloadable_only

From 1d6dfb585bd150ade2800ba0d187b8a33982847b Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:48:33 -0500
Subject: [PATCH 257/350] Join/load: replace strings with attrs
 (webapps...controllers.history)

---
 lib/galaxy/webapps/galaxy/controllers/history.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/history.py b/lib/galaxy/webapps/galaxy/controllers/history.py
index 73d9717e7e0..6411a3a158b 100644
--- a/lib/galaxy/webapps/galaxy/controllers/history.py
+++ b/lib/galaxy/webapps/galaxy/controllers/history.py
@@ -208,7 +208,7 @@ class SharedHistoryListGrid(grids.Grid):
     ]
 
     def build_initial_query(self, trans, **kwargs):
-        return trans.sa_session.query(self.model_class).join("users_shared_with")
+        return trans.sa_session.query(self.model_class).join(self.model_class.users_shared_with)
 
     def apply_query_filter(self, trans, query, **kwargs):
         return query.filter(model.HistoryUserShareAssociation.user == trans.user)

From 4725e06d4e0fd551b64a1c7b0c7b5f425fdabca3 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Fri, 20 Jan 2023 18:49:54 -0500
Subject: [PATCH 258/350] Join/load: replace strings with attrs
 (managers.sharable)

---
 lib/galaxy/managers/sharable.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/managers/sharable.py b/lib/galaxy/managers/sharable.py
index aebef5bb039..20eb3442f72 100644
--- a/lib/galaxy/managers/sharable.py
+++ b/lib/galaxy/managers/sharable.py
@@ -222,7 +222,7 @@ class SharableModelManager(
         Return a query for this model already filtered to models shared
         with a particular user.
         """
-        query = self.session().query(self.model_class).join("users_shared_with")
+        query = self.session().query(self.model_class).join(self.model_class.users_shared_with)
         if eagerloads is False:
             query = query.enable_eagerloads(False)
         # TODO: as filter in FilterParser also

From 38afccd78022f81ecc0e075f7c6829c6d4dc09d3 Mon Sep 17 00:00:00 2001
From: John Davis <jdavcs@gmail.com>
Date: Sat, 21 Jan 2023 11:13:36 -0500
Subject: [PATCH 259/350] Fix linting

---
 lib/tool_shed/webapp/api/repositories.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/tool_shed/webapp/api/repositories.py b/lib/tool_shed/webapp/api/repositories.py
index 6ce3d482a35..86f6a9f859e 100644
--- a/lib/tool_shed/webapp/api/repositories.py
+++ b/lib/tool_shed/webapp/api/repositories.py
@@ -38,7 +38,6 @@ from galaxy.webapps.base.controller import (
     BaseAPIController,
     HTTPBadRequest,
 )
-from tool_shed.webapp import model
 from tool_shed.dependencies import attribute_handlers
 from tool_shed.metadata import repository_metadata_manager
 from tool_shed.repository_types import util as rt_util
@@ -51,6 +50,7 @@ from tool_shed.util import (
     repository_util,
     tool_util,
 )
+from tool_shed.webapp import model
 from tool_shed.webapp.search.repo_search import RepoSearch
 
 log = logging.getLogger(__name__)

From dde16032028f831197712a836bb5a9409aa005b3 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 22 Jan 2023 12:32:00 +0100
Subject: [PATCH 260/350] Fix re-enabling save button when invalid connections
 are resolved

---
 client/src/stores/workflowConnectionStore.ts     |  2 +-
 lib/galaxy_test/selenium/test_workflow_editor.py | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/client/src/stores/workflowConnectionStore.ts b/client/src/stores/workflowConnectionStore.ts
index 627f5df5525..7748a417e77 100644
--- a/client/src/stores/workflowConnectionStore.ts
+++ b/client/src/stores/workflowConnectionStore.ts
@@ -124,7 +124,7 @@ export const useConnectionStore = defineStore("workflowConnectionStore", {
             Vue.set(this.invalidConnections, connectionId, reason);
         },
         dropFromInvalidConnections(this: State, connectionId: string) {
-            this.invalidConnections[connectionId] = undefined;
+            Vue.delete(this.invalidConnections, connectionId);
         },
         removeConnection(this: State, terminal: InputTerminal | OutputTerminal | Connection["id"]) {
             const stepStore = useWorkflowStepStore();
diff --git a/lib/galaxy_test/selenium/test_workflow_editor.py b/lib/galaxy_test/selenium/test_workflow_editor.py
index f907926eb07..9be68ab210c 100644
--- a/lib/galaxy_test/selenium/test_workflow_editor.py
+++ b/lib/galaxy_test/selenium/test_workflow_editor.py
@@ -558,6 +558,17 @@ steps:
         editor.select_datatype(datatype="bam").wait_for_and_click()
         editor.node.output_data_row(output_name="out_file1", extension="bam").wait_for_visible()
         self.assert_connection_invalid("create_2#out_file1", "checksum#input")
+        save_button = self.components.workflow_editor.save_button
+        # Assert save button is disabled
+        assert save_button.has_class("disabled")
+        # Make connection valid again
+        editor.change_datatype.wait_for_and_click()
+        editor.select_datatype_text_search.wait_for_and_send_keys("tabular")
+        editor.select_datatype(datatype="tabular").wait_for_and_click()
+        # Assert connection is valid
+        self.assert_connected("create_2#out_file1", "checksum#input")
+        # Assert save button is enabled
+        assert not save_button.has_class("disabled")
 
     @selenium_test
     def test_change_datatype_post_job_action_lost_regression(self):

From 04fdc8b3321d5be472d0898e239648f394af830f Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Sun, 22 Jan 2023 20:57:48 -0500
Subject: [PATCH 261/350] Update version to .dev0

---
 Makefile              | 2 +-
 lib/galaxy/version.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index b609f14f411..2f79fecc927 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VENV?=.venv
 # Source virtualenv to execute command (darker, sphinx, twine, etc...)
 IN_VENV=if [ -f "$(VENV)/bin/activate" ]; then . "$(VENV)/bin/activate"; fi;
-RELEASE_CURR:=23.0
+RELEASE_CURR:=
 RELEASE_UPSTREAM:=upstream
 CONFIG_MANAGE=$(IN_VENV) python lib/galaxy/config/config_manage.py
 PROJECT_URL?=https://github.com/galaxyproject/galaxy
diff --git a/lib/galaxy/version.py b/lib/galaxy/version.py
index db94f44b5b7..0325c387cee 100644
--- a/lib/galaxy/version.py
+++ b/lib/galaxy/version.py
@@ -1,3 +1,3 @@
-VERSION_MAJOR = "23.0"
+VERSION_MAJOR = ""
 VERSION_MINOR = "dev0"
 VERSION = VERSION_MAJOR + (f".{VERSION_MINOR}" if VERSION_MINOR else "")

From fd03e5ab77bddff0674a9f0bc2eafe09fb3be62c Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Sun, 22 Jan 2023 20:57:48 -0500
Subject: [PATCH 262/350] Update version to 23.0.rc1

---
 lib/galaxy/version.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/version.py b/lib/galaxy/version.py
index db94f44b5b7..a922ca03f42 100644
--- a/lib/galaxy/version.py
+++ b/lib/galaxy/version.py
@@ -1,3 +1,3 @@
 VERSION_MAJOR = "23.0"
-VERSION_MINOR = "dev0"
+VERSION_MINOR = "rc1"
 VERSION = VERSION_MAJOR + (f".{VERSION_MINOR}" if VERSION_MINOR else "")

From 1be4c3fbed5b9fb451806278e7ac691104fc7cc3 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Sun, 22 Jan 2023 21:03:28 -0500
Subject: [PATCH 263/350] Fix @next version numbers

---
 Makefile              | 2 +-
 lib/galaxy/version.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 2f79fecc927..8821c7445e1 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VENV?=.venv
 # Source virtualenv to execute command (darker, sphinx, twine, etc...)
 IN_VENV=if [ -f "$(VENV)/bin/activate" ]; then . "$(VENV)/bin/activate"; fi;
-RELEASE_CURR:=
+RELEASE_CURR:=23.1
 RELEASE_UPSTREAM:=upstream
 CONFIG_MANAGE=$(IN_VENV) python lib/galaxy/config/config_manage.py
 PROJECT_URL?=https://github.com/galaxyproject/galaxy
diff --git a/lib/galaxy/version.py b/lib/galaxy/version.py
index 0325c387cee..3ffcc1d351b 100644
--- a/lib/galaxy/version.py
+++ b/lib/galaxy/version.py
@@ -1,3 +1,3 @@
-VERSION_MAJOR = ""
+VERSION_MAJOR = "23.1"
 VERSION_MINOR = "dev0"
 VERSION = VERSION_MAJOR + (f".{VERSION_MINOR}" if VERSION_MINOR else "")

From 1ee7b96a67bef47a0b595db69bb5cabf24a886d6 Mon Sep 17 00:00:00 2001
From: Dannon <dannon.baker@gmail.com>
Date: Sun, 22 Jan 2023 21:09:31 -0500
Subject: [PATCH 264/350] Update maintenance_bot.yaml

---
 .github/workflows/maintenance_bot.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/maintenance_bot.yaml b/.github/workflows/maintenance_bot.yaml
index e8e78c8d60d..aca4415ff55 100644
--- a/.github/workflows/maintenance_bot.yaml
+++ b/.github/workflows/maintenance_bot.yaml
@@ -8,7 +8,7 @@ jobs:
     if: github.repository_owner == 'galaxyproject'
     runs-on: ubuntu-latest
     env:
-      MILESTONE_NUMBER: 23
+      MILESTONE_NUMBER: 24
     steps:
       - name: Get latest pull request labels
         id: get_pr_labels

From e7443bbb01ce6c4c49141bcb8e298b36e93ef9a2 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 23 Jan 2023 16:06:28 +0100
Subject: [PATCH 265/350] Use built-in download_to_file instead of relying on
 curl/wget for conda/involucro installs

Fixes https://github.com/galaxyproject/galaxy/issues/15355
---
 lib/galaxy/tool_util/deps/conda_util.py          |  6 ++----
 lib/galaxy/tool_util/deps/mulled/mulled_build.py | 11 +++++++----
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/lib/galaxy/tool_util/deps/conda_util.py b/lib/galaxy/tool_util/deps/conda_util.py
index b5bdfd72473..bc91af0c433 100644
--- a/lib/galaxy/tool_util/deps/conda_util.py
+++ b/lib/galaxy/tool_util/deps/conda_util.py
@@ -24,6 +24,7 @@ import packaging.version
 
 from galaxy.util import (
     commands,
+    download_to_file,
     listify,
     shlex_join,
     smart_str,
@@ -483,16 +484,13 @@ def hash_conda_packages(conda_packages: Iterable[CondaTarget]) -> str:
 def install_conda(conda_context: CondaContext, force_conda_build: bool = False) -> int:
     with tempfile.NamedTemporaryFile(suffix=".sh", prefix="conda_install", delete=False) as temp:
         script_path = temp.name
-    download_cmd = commands.download_command(conda_link(), to=script_path)
     install_cmd = ["bash", script_path, "-b", "-p", conda_context.conda_prefix]
     package_targets = list(CONDA_PACKAGE_SPECS)
     if force_conda_build or conda_context.use_local:
         package_targets.extend(CONDA_BUILD_SPECS)
     log.info("Installing conda, this may take several minutes.")
     try:
-        exit_code = conda_context.shell_exec(download_cmd)
-        if exit_code:
-            return exit_code
+        download_to_file(conda_link(), script_path)
         exit_code = conda_context.shell_exec(install_cmd)
     except Exception:
         log.exception("Failed to install conda")
diff --git a/lib/galaxy/tool_util/deps/mulled/mulled_build.py b/lib/galaxy/tool_util/deps/mulled/mulled_build.py
index 7f99a829b3f..82ca88e156e 100644
--- a/lib/galaxy/tool_util/deps/mulled/mulled_build.py
+++ b/lib/galaxy/tool_util/deps/mulled/mulled_build.py
@@ -29,6 +29,7 @@ from galaxy.tool_util.deps.conda_util import (
 from galaxy.tool_util.deps.docker_util import command_list as docker_command_list
 from galaxy.util import (
     commands,
+    download_to_file,
     safe_makedirs,
     shlex_join,
     unicodify,
@@ -428,10 +429,12 @@ def ensure_installed(involucro_context, auto_init):
 def install_involucro(involucro_context):
     install_path = os.path.abspath(involucro_context.involucro_bin)
     involucro_context.involucro_bin = install_path
-    download_cmd = commands.download_command(involucro_link(), to=install_path)
-    exit_code = involucro_context.shell_exec(download_cmd)
-    if exit_code:
-        return exit_code
+
+    try:
+        download_to_file(involucro_link(), install_path)
+    except Exception:
+        log.exception(f"Failed to download involucro from url '{involucro_link()}'")
+        return 1
     try:
         os.chmod(install_path, os.stat(install_path).st_mode | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH)
         return 0

From ce93b01b116660760109e698072d083413b084e2 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Mon, 23 Jan 2023 15:08:32 -0500
Subject: [PATCH 266/350] Add metadata generation failed dataset details, when
 metadata fails

---
 client/src/components/History/Content/model/states.js | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/src/components/History/Content/model/states.js b/client/src/components/History/Content/model/states.js
index 150d990b228..2ddfcecbf9e 100644
--- a/client/src/components/History/Content/model/states.js
+++ b/client/src/components/History/Content/model/states.js
@@ -33,6 +33,7 @@ export const STATES = {
     /** metadata discovery/setting failed or errored (but otherwise ok) */
     failed_metadata: {
         status: "danger",
+        text: "Metadata generation failed.",
         icon: "exclamation-triangle",
     },
     /** was created without a tool */

From f2926ad41f28d569c1c7ae44c79d78c51737483e Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Tue, 24 Jan 2023 10:48:06 +0100
Subject: [PATCH 267/350] Fix reference to sample_tool_conf.xml

---
 .vscode/.test.env          | 2 +-
 .vscode/launch_gitpod.json | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.vscode/.test.env b/.vscode/.test.env
index 0fd4d77f2ed..8321bcadf92 100644
--- a/.vscode/.test.env
+++ b/.vscode/.test.env
@@ -1 +1 @@
-GALAXY_TEST_TOOL_CONF="lib/galaxy/config/sample/tool_conf.xml.sample,test/functional/tools/samples_tool_conf.xml"
\ No newline at end of file
+GALAXY_TEST_TOOL_CONF="lib/galaxy/config/sample/tool_conf.xml.sample,test/functional/tools/sample_tool_conf.xml"
diff --git a/.vscode/launch_gitpod.json b/.vscode/launch_gitpod.json
index c9bee582dcd..ebab8a9437a 100644
--- a/.vscode/launch_gitpod.json
+++ b/.vscode/launch_gitpod.json
@@ -10,7 +10,7 @@
             "env": {
                 "GALAXY_CONFIG_FILE": "${workspaceFolder}/config/galaxy.yml",
                 "GALAXY_CONDA_AUTO_INIT": "false",
-                "GALAXY_CONFIG_TOOL_CONFIG_FILE": "lib/galaxy/config/sample/tool_conf.xml.sample,test/functional/tools/samples_tool_conf.xml",
+                "GALAXY_CONFIG_TOOL_CONFIG_FILE": "lib/galaxy/config/sample/tool_conf.xml.sample,test/functional/tools/sample_tool_conf.xml",
                 "GALAXY_CONFIG_DATABASE_CONNECTION": "postgresql://localhost/galaxy"
             }
         },

From bb5ecb72a24b8b82753b093eaec6b13988ad2c8f Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 24 Jan 2023 13:32:28 +0100
Subject: [PATCH 268/350] Reset confirmation state then unmounting workflow
 editor

Should fix https://github.com/galaxyproject/galaxy/issues/15366
---
 client/src/components/Workflow/Editor/Index.vue | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index a682769f5ec..92ee4af0680 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -236,7 +236,7 @@ export default {
             required: true,
         },
     },
-    setup() {
+    setup(props, { emit }) {
         const { datatypes, datatypesMapper, datatypesMapperLoading } = useDatatypesMapper();
         const connectionsStore = useConnectionStore();
         const stepStore = useWorkflowStepStore();
@@ -260,6 +260,7 @@ export default {
         }
         onUnmounted(() => {
             resetStores();
+            emit("update:confirmation", false);
         });
         return {
             connectionsStore,

From e9cd987e90ec4400b0578d732fc5b203472a8728 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 24 Jan 2023 14:27:10 +0100
Subject: [PATCH 269/350] Allow configuring webpack devserver port

Should be useful when you're debugging against a live server and a local
instance.
---
 client/webpack.config.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 06f773f8f3a..795db78e6f1 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -252,7 +252,7 @@ module.exports = (env = {}, argv = {}) => {
                 publicPath: "/static/dist",
             },
             hot: true,
-            port: 8081,
+            port: process.env.WEBPACK_PORT || 8081,
             host: "0.0.0.0",
             // proxy *everything* to the galaxy server.
             // someday, when we have a fully API-driven independent client, this

From 31d31cb74f3e1a4bfabd772458c4a551c801a264 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Tue, 24 Jan 2023 12:44:10 +0100
Subject: [PATCH 270/350] Extend terminal test

---
 client/src/components/Workflow/Editor/modules/terminals.test.ts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 4d41492bc86..00cdd99954c 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -102,6 +102,7 @@ describe("canAccept", () => {
         dataIn.connect(collectionOut);
         expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         expect(dataIn.canAccept(collectionOut).canAccept).toBe(false);
+        expect(dataIn.canAccept(collectionOut).reason).toBe("Input already filled with another connection, delete it before connecting another output.");
         dataIn.disconnect(collectionOut);
         expect(dataIn.canAccept(collectionOut).canAccept).toBe(true);
         expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);

From c6e700b7c5d7ec3cfa548984406bf4341ce4619c Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Tue, 24 Jan 2023 14:35:25 +0100
Subject: [PATCH 271/350] Disable add button when nothing is selected

---
 client/src/components/History/Modals/SelectorModal.vue | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/client/src/components/History/Modals/SelectorModal.vue b/client/src/components/History/Modals/SelectorModal.vue
index 76dded0a196..60771b6d37a 100644
--- a/client/src/components/History/Modals/SelectorModal.vue
+++ b/client/src/components/History/Modals/SelectorModal.vue
@@ -31,7 +31,9 @@
         </b-table>
         <template v-slot:modal-footer>
             <b-pagination v-model="currentPage" :total-rows="totalRows" :per-page="perPage" />
-            <b-button v-if="multiple" variant="primary" @click="addSelected">Add Selected</b-button>
+            <b-button v-if="multiple" :disabled="isEmptySelection" variant="primary" @click="addSelected">
+                Add Selected
+            </b-button>
         </template>
     </b-modal>
 </template>
@@ -77,6 +79,9 @@ export default {
                 return item;
             });
         },
+        isEmptySelection() {
+            return this.selectedHistories.length === 0;
+        },
     },
     watch: {
         histories(newVal) {

From a30beb4da541d6160037ad67855961d5a999bdc9 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Tue, 24 Jan 2023 14:43:52 +0100
Subject: [PATCH 272/350] Update row variant conditionally

The current history will be still highlighted differently when is not explicitly selected.
---
 client/src/components/History/Modals/SelectorModal.vue | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/client/src/components/History/Modals/SelectorModal.vue b/client/src/components/History/Modals/SelectorModal.vue
index 60771b6d37a..4776ed30dd5 100644
--- a/client/src/components/History/Modals/SelectorModal.vue
+++ b/client/src/components/History/Modals/SelectorModal.vue
@@ -74,7 +74,10 @@ export default {
         formattedItems() {
             return this.histories.map((item) => {
                 if (item.id === this.currentHistoryId) {
-                    item._rowVariant = "info";
+                    const isCurrentSelected = this.selectedHistories.some(
+                        (history) => history.id === this.currentHistoryId
+                    );
+                    item._rowVariant = isCurrentSelected ? "success" : "info";
                 }
                 return item;
             });

From bd25f11a5d8a638355a984e00a7a5c43813cb51c Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Tue, 24 Jan 2023 08:55:22 -0500
Subject: [PATCH 273/350] Have webpack dev server write files to disk by
 default -- this should be equivalent to the old watch mode

---
 client/webpack.config.js | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 795db78e6f1..aa12a065163 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -250,6 +250,7 @@ module.exports = (env = {}, argv = {}) => {
             allowedHosts: process.env.GITPOD_WORKSPACE_ID ? "all" : "auto",
             devMiddleware: {
                 publicPath: "/static/dist",
+                writeToDisk: true,
             },
             hot: true,
             port: process.env.WEBPACK_PORT || 8081,

From 6c99486d8f2096a6c34bf8c4f0be6302ca06a527 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Tue, 24 Jan 2023 09:04:53 -0500
Subject: [PATCH 274/350] Client README updates

---
 client/README.md | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/client/README.md b/client/README.md
index 15fad423884..9b23e47280c 100644
--- a/client/README.md
+++ b/client/README.md
@@ -53,24 +53,12 @@ and these should not be committed.
 When you're actively developing, it is convenient to have the client
 automatically rebuild every time you save a file. You can do this using:
 
-    make client-watch
-
-This will first stage client dependencies, initiate a build, and then will
-watch for changes in any of the galaxy client source files.  When a file is
-changed, the client will automatically rebuild, after which you can refresh
-your browser to see changes.
-
-For even more rapid development you can use the webpack development server,
-which takes advantage of hot module replacement (HMR). This technique allows
-swapping out of javascript modules while the application is running without
-requiring a full page reload most of the time, at least in the more modern
-parts of the application.
-
-The command below starts a special webpack dev server after a client
-build.
-
     make client-dev-server
 
+Or, with the package scripts from this `client` directory:
+    
+    yarn run develop
+
 This will start up an extra client development server running on port 8081.
 Open your browser to http://localhost:8081 (instead of the default 8080 that
 Galaxy would run on), and you should see Galaxy like normal.  Except now, when
@@ -86,6 +74,10 @@ Sometimes you want to run your local UI against a remote Galaxy server. This is
 
     CHANGE_ORIGIN=true GALAXY_URL="https://usegalaxy.org/" make client-dev-server
 
+You can also specify a particular port to bind the dev server to:
+
+    WEBPACK_PORT=8083 yarn run develop
+
 ## Running a Separate Server
 
 When developing the client it can be helpful to run a local server for the
@@ -94,6 +86,11 @@ commands. This command will run galaxy without building the client:
 
     make skip-client
 
+Or by setting the following environment variable and running Galaxy however you
+prefer:
+
+    GALAXY_SKIP_CLIENT_BUILD=1 ./run.sh
+
 ## Changing Styles/CSS
 
 Galaxy uses Sass for its styling, which is a superset of CSS that compiles down

From 67a5e81d51fcf2e04207733bf6e6c328b1b123cc Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Tue, 24 Jan 2023 15:16:55 +0100
Subject: [PATCH 275/350] Add jest test for current history highlight

---
 .../History/Modals/SelectorModal.test.js      | 62 +++++++++++++------
 1 file changed, 44 insertions(+), 18 deletions(-)

diff --git a/client/src/components/History/Modals/SelectorModal.test.js b/client/src/components/History/Modals/SelectorModal.test.js
index bc026247c84..8aa8b281aed 100644
--- a/client/src/components/History/Modals/SelectorModal.test.js
+++ b/client/src/components/History/Modals/SelectorModal.test.js
@@ -5,7 +5,7 @@ import SelectorModal from "./SelectorModal";
 
 const localVue = getLocalVue();
 
-const SELECTED_HISTORY_ID = "COOL_ID";
+const CURRENT_HISTORY_ID = "COOL_ID";
 const getFakeHistorySummaries = (num, selectedIndex = 0) => {
     const result = Array.from({ length: num }, (_, index) => ({
         id: `ID-${index}`,
@@ -13,11 +13,11 @@ const getFakeHistorySummaries = (num, selectedIndex = 0) => {
         tags: [],
         update_time: new Date().toISOString(),
     }));
-    result[selectedIndex].id = SELECTED_HISTORY_ID;
+    result[selectedIndex].id = CURRENT_HISTORY_ID;
     return result;
 };
 const PROPS_WITH_10_HISTORIES = {
-    currentHistoryId: SELECTED_HISTORY_ID,
+    currentHistoryId: CURRENT_HISTORY_ID,
     histories: getFakeHistorySummaries(10),
     perPage: 3,
     static: true, // Force the modal visible for testing
@@ -27,6 +27,9 @@ const PROPS_WITH_10_HISTORY_MULTIPLE_SELECT = {
     multiple: true,
 };
 
+const CURRENT_HISTORY_HIGHLIGHT_CLASS = ".table-info";
+const SELECTED_HISTORY_HIGHLIGHT_CLASS = ".table-success";
+
 describe("History SelectorModal.vue", () => {
     let wrapper;
 
@@ -41,9 +44,9 @@ describe("History SelectorModal.vue", () => {
     it("should highlight the currently selected history", async () => {
         await mountWith(PROPS_WITH_10_HISTORIES);
 
-        const selectedRows = wrapper.findAll(".table-info");
+        const selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
         expect(selectedRows.length).toBe(1);
-        expect(selectedRows.at(0).attributes("data-pk")).toBe(SELECTED_HISTORY_ID);
+        expect(selectedRows.at(0).attributes("data-pk")).toBe(CURRENT_HISTORY_ID);
     });
 
     it("paginates the histories", async () => {
@@ -67,25 +70,48 @@ describe("History SelectorModal.vue", () => {
         expect(wrapper.emitted()["selectHistory"][0][0].id).toBe(targetHistoryId);
     });
 
-    it("select multiple histories", async () => {
-        await mountWith(PROPS_WITH_10_HISTORY_MULTIPLE_SELECT);
+    describe("Multi-selection Mode", () => {
+        it("should select multiple histories", async () => {
+            await mountWith(PROPS_WITH_10_HISTORY_MULTIPLE_SELECT);
 
-        expect(wrapper.emitted()["selectHistories"]).toBeUndefined();
+            expect(wrapper.emitted()["selectHistories"]).toBeUndefined();
 
-        const targetHistoryId1 = "ID-1";
-        const targetRow1 = wrapper.find(`[data-pk="${targetHistoryId1}"]`);
-        await targetRow1.trigger("click");
+            const targetHistoryId1 = "ID-1";
+            const targetRow1 = wrapper.find(`[data-pk="${targetHistoryId1}"]`);
+            await targetRow1.trigger("click");
 
-        const targetHistoryId2 = "ID-2";
-        const targetRow2 = wrapper.find(`[data-pk="${targetHistoryId2}"]`);
-        await targetRow2.trigger("click");
+            const targetHistoryId2 = "ID-2";
+            const targetRow2 = wrapper.find(`[data-pk="${targetHistoryId2}"]`);
+            await targetRow2.trigger("click");
 
-        expect(wrapper.vm.selectedHistories.length).toBe(2);
+            expect(wrapper.vm.selectedHistories.length).toBe(2);
 
-        const button = wrapper.find(".btn-primary");
+            const button = wrapper.find(".btn-primary");
 
-        await button.trigger("click");
+            await button.trigger("click");
 
-        expect(wrapper.emitted()["selectHistories"][0][0][0].id).toBe(targetHistoryId1);
+            expect(wrapper.emitted()["selectHistories"][0][0][0].id).toBe(targetHistoryId1);
+
+            console.debug(wrapper.html());
+        });
+
+        it("should highlight the current history differently by default but equally when selected", async () => {
+            await mountWith(PROPS_WITH_10_HISTORY_MULTIPLE_SELECT);
+
+            let selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
+            expect(selectedRows.length).toBe(1);
+            expect(selectedRows.at(0).attributes("data-pk")).toBe(CURRENT_HISTORY_ID);
+
+            const targetRow = wrapper.find(`[data-pk="${CURRENT_HISTORY_ID}"]`);
+            await targetRow.trigger("click");
+
+            // No longer highlighted as current
+            selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
+            expect(selectedRows.length).toBe(0);
+
+            // Highlighted as normal selection
+            selectedRows = wrapper.findAll(SELECTED_HISTORY_HIGHLIGHT_CLASS);
+            expect(selectedRows.length).toBe(1);
+        });
     });
 });

From 56a2ace72d2218d086129b3222878329f7f783ee Mon Sep 17 00:00:00 2001
From: Anup Kumar <kumara@informatik.uni-freiburg.de>
Date: Thu, 12 Jan 2023 11:49:08 +0100
Subject: [PATCH 276/350] Update interactivetool_ml_jupyter_notebook.xml

Add changes to GPU Jupyterlab tool based on Jupytool
---
 .../interactivetool_ml_jupyter_notebook.xml   | 245 ++++++++++++++----
 1 file changed, 197 insertions(+), 48 deletions(-)

diff --git a/tools/interactive/interactivetool_ml_jupyter_notebook.xml b/tools/interactive/interactivetool_ml_jupyter_notebook.xml
index f11cec41589..5d19185d4ef 100644
--- a/tools/interactive/interactivetool_ml_jupyter_notebook.xml
+++ b/tools/interactive/interactivetool_ml_jupyter_notebook.xml
@@ -1,6 +1,6 @@
 <tool id="interactive_tool_ml_jupyter_notebook" tool_type="interactive" name="GPU enabled Interactive Jupyter Notebook for Machine Learning" version="@VERSION@" profile="22.01">
     <macros>
-        <token name="@VERSION@">0.1</token>
+        <token name="@VERSION@">0.2</token>
     </macros>
     <requirements>
         <container type="docker">docker.io/anupkumar/docker-ml-jupyterlab:galaxy-integration-@VERSION@</container>
@@ -19,71 +19,221 @@
         <environment_variable name="DISABLE_AUTH">true</environment_variable>
         <environment_variable name="API_KEY" inject="api_key" />
     </environment_variables>
-    <command detect_errors="aggressive"><![CDATA[
-        #import re
+    <configfiles>
+        <inputs name="inputs" filename="galaxy_inputs.json" data_style="staging_path_and_source_path"/>
+        <configfile name="staging_script" filename="staging_script.py"><![CDATA[
+import json, os, shutil
+import os.path
+galaxy_inputs = "galaxy_inputs.json"
+galaxy_inputs_raw = "galaxy_inputs_raw.json"
+base_staging_path = "jupyter"
+base_data_staging_path = "galaxy_inputs"
+data_staging_path = os.path.join(base_staging_path, base_data_staging_path)
+os.makedirs(data_staging_path, exist_ok=True)
+shutil.copyfile(galaxy_inputs, os.path.join(data_staging_path, galaxy_inputs_raw))
+galaxy_input_dict = {}
+for user_input in json.load(open(galaxy_inputs, "r")).get("user_inputs", []):
+    input_values = user_input['input_type']['input_value']
+    input_name = user_input["input_name"]
+    assert input_name not in galaxy_input_dict, ValueError("Each name can only be used once, but a duplicate was found: %s" % (input_name))
+    if 'dataset' in user_input['input_type']['input_type_selector']:
+        input_values2 = []
+        if not isinstance(input_values, list):
+            input_values = [input_values]
+        for input_value_dict in input_values:
+            path, filename = os.path.split(input_value_dict['staging_path'])
+            input_value_dict2 = {"path": os.path.join(base_data_staging_path, input_name, path, filename), "metadata_files": []}
+            path = os.path.join(data_staging_path, input_name, path)
+            os.makedirs(path, exist_ok=True)
+            try:
+                os.symlink(input_value_dict['source_path'], os.path.join(path, filename))
+            except FileExistsError:
+                pass
+            for metadata_value_dict in input_value_dict['metadata_files']:
+                path, filename = os.path.split(metadata_value_dict['staging_path'])
+                input_value_dict2["metadata_files"].append(os.path.join(base_data_staging_path, input_name, path, filename))
+                path = os.path.join(data_staging_path, input_name, path)
+                os.makedirs(path, exist_ok=True)
+                try:
+                    os.symlink(metadata_value_dict['source_path'], os.path.join(path, filename))
+                except FileExistsError:
+                    pass
+            input_values2.append(input_value_dict2)
+        input_values = input_values2
+    galaxy_input_dict[input_name] = input_values
+with open(os.path.join(data_staging_path, galaxy_inputs), "w") as fh:
+    json.dump(galaxy_input_dict, fh)
+]]>
+        </configfile>
+        <configfile name="galaxy_input_startup_script"><![CDATA[
+import json, os
+from galaxy_ie_helpers import get
+from galaxy_ie_helpers import put
+from galaxy_ie_helpers import get_galaxy_connection
+HISTORY_ID = os.environ.get('HISTORY_ID', None)
+try:
+    GALAXY_INPUTS = json.load(open(os.path.join(os.environ.get("GALAXY_WORKING_DIR", ""), "jupyter", "galaxy_inputs", "galaxy_inputs.json")))
+except FileNotFoundError:
+    GALAXY_INPUTS = {}
+        ]]>
+    </configfile>
+    </configfiles>
+    
+    <command><![CDATA[
+        python staging_script.py &&
         export GALAXY_WORKING_DIR=`pwd` &&
-        mkdir -p ./jupyter/outputs/ &&
-        mkdir -p ./jupyter/data &&
-        mkdir -p ./jupyter/notebooks &&
-        mkdir -p ./jupyter/elyra &&
-
-        #set $cleaned_name = re.sub('[^\w\-\.]', '_', str($input.element_identifier))
-        ln -sf '$input' './jupyter/data/${cleaned_name}' &&
-
-        ## change into the directory where the notebooks are located
+        mkdir -p ./jupyter/outputs &&
+        mkdir -p ./jupyter/galaxy_inputs &&
         cd ./jupyter/ &&
         export HOME=/home/\$NB_USER/ &&
         export PATH=/home/\$NB_USER/.local/bin:\$PATH &&
+        cp '${galaxy_input_startup_script}' /home/\$NB_USER/.ipython/profile_default/startup/02-load.py &&
+        #set $output_notebook_name = 'jupyterlab_notebook.ipynb'
         #if $mode.mode_select == 'scratch':
-            ## copy all notebooks, workflows and data
-            cp /home/\$NB_USER/home_page.ipynb ./ &&
-            cp /home/\$NB_USER/notebooks/*.ipynb ./notebooks/ &&
-            cp /home/\$NB_USER/elyra/*.* ./elyra/ &&
-            cp /home/\$NB_USER/data/*.tsv ./data/ &&
-            ## provide all rights to copied files
-            chown -R \$NB_USER:users `pwd` &&
-            chown \$NB_USER ./home_page.ipynb &&
-            chown \$NB_USER ./notebooks/ &&
-            chown \$NB_USER ./notebooks/*.ipynb &&
-            chown \$NB_USER ./elyra/ &&
-            chown \$NB_USER ./elyra/*.* &&
-            jupyter trust ./home_page.ipynb &&
-            jupyter trust ./notebooks/*.ipynb &&
-            jupyter trust ./elyra/*.ipynb &&
-            jupyter lab --allow-root --no-browser --NotebookApp.shutdown_button=True
+            cp -r /home/\$NB_USER/data ./ &&
+            cp -r /home/\$NB_USER/elyra ./ &&
+            cp -r /home/\$NB_USER/notebooks ./ &&
+            cp -r /home/\$NB_USER/usecases ./ &&
+            cp -r /home/\$NB_USER/home_page.ipynb ./ &&
+            jupyter lab --no-browser --NotebookApp.shutdown_button=True
         #else:
-            #set $noteboook_name = re.sub('[^\w\-\.\s]', '_', str($mode.ipynb.element_identifier))
-            cp '$mode.ipynb' './${noteboook_name}.ipynb' &&
-            jupyter trust './${noteboook_name}.ipynb' &&
+            #import re
+            #set $cleaned_name = re.sub('[^\w\-\.]', '_', str($mode.ipynb.element_identifier))
+            #if not $cleaned_name.endswith(".ipynb"'$jupyter_notebook'):
+                #set $cleaned_name = "%s.ipynb" % $cleaned_name
+            #end if
+            cp '$mode.ipynb' '${cleaned_name}' &&
+            jupyter trust '${cleaned_name}' &&
+
             #if $mode.run_it:
-                jupyter nbconvert --to notebook --execute --output ./ipython_galaxy_notebook.ipynb --allow-errors  ./*.ipynb &&
-                #set $noteboook_name = 'ipython_galaxy_notebook'
+                jupyter nbconvert --to notebook --execute --output '${output_notebook_name}' --allow-errors '${cleaned_name}' &&
+                cp '${output_notebook_name}' '$jupyter_notebook'
             #else:
-                jupyter lab --allow-root --no-browser --NotebookApp.shutdown_button=True &&
+                #set $output_notebook_name = $cleaned_name
+                jupyter lab --no-browser --NotebookApp.shutdown_button=True
             #end if
-            cp './${noteboook_name}.ipynb' '$jupyter_notebook'
         #end if
     ]]>
     </command>
     <inputs>
-
         <conditional name="mode">
-            <param name="mode_select" type="select" label="Do you already have a notebook?" help="If not, no problem we will provide you with a default one.">
-                <option value="scratch">Start with a fresh notebook</option>
-                <option value="previous">Load a previous notebook</option>
+            <param name="mode_select" type="select" label="Do you already have a notebook?" help="Select a set of default notebooks or load an existing one.">
+                <option value="scratch">Start with default notebooks</option>
+                <option value="previous">Load an existing notebook</option>
             </param>
             <when value="scratch"/>
             <when value="previous">
-                <param name="ipynb" type="data" format="ipynb" label="IPython Notebook"/>
-                <param name="run_it" type="boolean" truevalue="true" falsevalue="false" label="Execute notebook and return a new one."
-                    help="This option is useful in workflows when you just want to execute a notebook and not dive into the webfrontend."/>
+                <param name="ipynb" type="data" format="ipynb" label="IPython Notebook" required="true"/>
+                <param name="run_it" type="boolean" truevalue="true" falsevalue="false" label="Execute notebook and return a new one." help="This option is useful in workflows when you just want to execute a notebook and not dive into the webfrontend."/>
             </when>
         </conditional>
-        <param name="input" type="data" optional="true" label="Include data into the environment"/>
-
+        <repeat name="user_inputs" title="User inputs">
+            <param name="input_name" type="text" value="" label="Name for parameter" optional="False" help="Required. ASCII letters and numbers only.">
+                <validator type="empty_field" message="Name is required"/>
+                <sanitizer>
+                    <valid initial="string.ascii_letters,string.digits"/>
+                </sanitizer>
+            </param>
+            <param name="description" type="text" label="Additional optional description" optional="true"/>
+            <conditional name="input_type">
+                <param name="input_type_selector" type="select" label="Choose the input type">
+                    <option value="dataset" selected="true">Dataset</option>
+                    <option value="dataset_multiple">Multiple datasets</option>
+                    <option value="dataset_collection">Dataset collection</option>
+                    <option value="dataset_collection_list">Dataset collection (list)</option>
+                    <option value="dataset_collection_paired">Dataset collection (paired)</option>
+                    <option value="dataset_collection_list_paired">Dataset collection (list:paired)</option>
+                    <option value="text">Text</option>
+                    <option value="integer">Integer</option>
+                    <option value="float">Floating point</option>
+                    <option value="boolean">Boolean</option>
+                    <option value="color">Color selector</option>
+                    <option value="dataset_optional" selected="true">Optional Dataset</option>
+                    <option value="dataset_multiple_optional">Optional Multiple datasets</option>
+                    <option value="dataset_collection_optional">Optional Dataset collection</option>
+                    <option value="dataset_collection_list_optional">Optional Dataset collection (list)</option>
+                    <option value="dataset_collection_paired_optional">Optional Dataset collection (paired)</option>
+                    <option value="dataset_collection_list_paired_optional">Optional Dataset collection (list:paired)</option>
+                    <option value="text_optional">Optional Text</option>
+                    <option value="integer_optional">Optional Integer</option>
+                    <option value="float_optional">Optional Floating point</option>
+                    <option value="boolean_optional">Optional Boolean</option>
+                    <option value="color_optional">Optional Color selector</option>
+                </param>
+                <when value="dataset">
+                    <param name="input_value" type="data" format="data" label="Select value" multiple="false" optional="false"/>
+                </when>
+                <when value="dataset_multiple">
+                    <param name="input_value" type="data" format="data" label="Select value" multiple="true" optional="false"/>
+                </when>
+                <when value="dataset_collection">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" optional="false"/>
+                </when>
+                <when value="dataset_collection_list">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="list" optional="false"/>
+                </when>
+                <when value="dataset_collection_paired">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="paired" optional="false"/>
+                </when>
+                <when value="dataset_collection_list_paired">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="list:paired" optional="false"/>
+                </when>
+                <when value="text">
+                    <param name="input_value" type="text" value="" label="Select value" optional="false"/>
+                </when>
+                <when value="integer">
+                    <param name="input_value" type="integer" value="" label="Select value" optional="false"/>
+                </when>
+                <when value="float">
+                    <param name="input_value" type="float" value="" label="Select value" optional="false"/>
+                </when>
+                <when value="boolean">
+                    <param name="input_value" type="boolean" truevalue="true" falsevalue="false" label="Select value" optional="false"/>
+                </when>
+                <when value="color">
+                    <param name="input_value" type="color" label="Select value" optional="false"/>
+                </when>
+                <when value="dataset_optional">
+                    <param name="input_value" type="data" format="data" label="Select value" multiple="false" optional="true"/>
+                </when>
+                <when value="dataset_multiple_optional">
+                    <param name="input_value" type="data" format="data" label="Select value" multiple="true" optional="true"/>
+                </when>
+                <when value="dataset_collection_optional">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" optional="true"/>
+                </when>
+                <when value="dataset_collection_list_optional">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="list" optional="true"/>
+                </when>
+                <when value="dataset_collection_paired_optional">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="paired" optional="true"/>
+                </when>
+                <when value="dataset_collection_list_paired_optional">
+                    <param name="input_value" type="data_collection" format="data" label="Select value" collection_type="list:paired" optional="true"/>
+                </when>
+                <when value="text_optional">
+                    <param name="input_value" type="text" value="" label="Select value" optional="true"/>
+                </when>
+                <when value="integer_optional">
+                    <param name="input_value" type="integer" value="" label="Select value" optional="true"/>
+                </when>
+                <when value="float_optional">
+                    <param name="input_value" type="float" value="" label="Select value" optional="true"/>
+                </when>
+                <when value="boolean_optional">
+                    <param name="input_value" type="boolean" truevalue="true" falsevalue="false" label="Select value" optional="true"/>
+                </when>
+                <when value="color_optional">
+                    <param name="input_value" type="color" label="Select value" optional="true"/>
+                </when>
+            </conditional>
+        </repeat>
     </inputs>
     <outputs>
-        <data name="jupyter_notebook" format="ipynb" label="Executed Notebook" />
+        <data name="jupyter_notebook" format="ipynb" label="Executed GPU JupyterLab Notebook"/>
+        <collection name="output_collection" type="list" label="GPU JupyterLab notebook output collection">
+            <discover_datasets pattern="__designation_and_ext__" directory="jupyter/outputs" visible="false"/>
+        </collection>
     </outputs>
     <tests>
         <test expect_num_outputs="1">
@@ -97,10 +247,9 @@
         JupyterLab is a next-generation web-based user interface for Project Jupyter. JupyterLab enables you to work with documents and activities such as Jupyter notebooks, text editors,
         terminals, and custom components in a flexible, integrated, and extensible manner.
 
-        Galaxy offers you to use Jupyter Lab directly in Galaxy accessing and interacting with Galaxy datasets as you like. A very common use-case is to
+        Galaxy offers you to use JupyterLab directly in Galaxy accessing and interacting with Galaxy datasets as you like. A very common use-case is to
         do the heavy lifting such as performing computation on GPUs and data reduction steps in Galaxy and the plotting and more `interactive` part on smaller datasets in Jupyter Lab.
 
-        You can start with a new Jupyter Lab notebook from scratch and wait until the job starts running. Running job will provide you a link which can be opened in the same or another
-        browser tab. This link opens Jupyter Lab notebook which can be used to prototype machine learning solutions.
+        You can start with a new JupyterLab notebook from scratch and wait until the job starts running. Running job will provide you a link which can be opened in the same or another browser tab. This link opens JupyterLab notebook which can be used to prototype machine learning solutions.
     ]]></help>
 </tool>

From 6f99f8aa281c6f2caf6002c4597030e7b6ee9936 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Tue, 24 Jan 2023 19:12:25 +0100
Subject: [PATCH 277/350] Indicate current history without color highlight

---
 .../History/Modals/SelectorModal.test.js      | 29 +++----------------
 .../History/Modals/SelectorModal.vue          | 16 +++-------
 2 files changed, 8 insertions(+), 37 deletions(-)

diff --git a/client/src/components/History/Modals/SelectorModal.test.js b/client/src/components/History/Modals/SelectorModal.test.js
index 8aa8b281aed..121e911f63b 100644
--- a/client/src/components/History/Modals/SelectorModal.test.js
+++ b/client/src/components/History/Modals/SelectorModal.test.js
@@ -27,8 +27,7 @@ const PROPS_WITH_10_HISTORY_MULTIPLE_SELECT = {
     multiple: true,
 };
 
-const CURRENT_HISTORY_HIGHLIGHT_CLASS = ".table-info";
-const SELECTED_HISTORY_HIGHLIGHT_CLASS = ".table-success";
+const CURRENT_HISTORY_INDICATION_TEXT = "(Current)";
 
 describe("History SelectorModal.vue", () => {
     let wrapper;
@@ -41,12 +40,11 @@ describe("History SelectorModal.vue", () => {
         await flushPromises();
     }
 
-    it("should highlight the currently selected history", async () => {
+    it("should indicate the currently selected history", async () => {
         await mountWith(PROPS_WITH_10_HISTORIES);
 
-        const selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
-        expect(selectedRows.length).toBe(1);
-        expect(selectedRows.at(0).attributes("data-pk")).toBe(CURRENT_HISTORY_ID);
+        const currentHistoryRow = wrapper.find(`[data-pk="${CURRENT_HISTORY_ID}"]`);
+        expect(currentHistoryRow.html()).toContain(CURRENT_HISTORY_INDICATION_TEXT);
     });
 
     it("paginates the histories", async () => {
@@ -94,24 +92,5 @@ describe("History SelectorModal.vue", () => {
 
             console.debug(wrapper.html());
         });
-
-        it("should highlight the current history differently by default but equally when selected", async () => {
-            await mountWith(PROPS_WITH_10_HISTORY_MULTIPLE_SELECT);
-
-            let selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
-            expect(selectedRows.length).toBe(1);
-            expect(selectedRows.at(0).attributes("data-pk")).toBe(CURRENT_HISTORY_ID);
-
-            const targetRow = wrapper.find(`[data-pk="${CURRENT_HISTORY_ID}"]`);
-            await targetRow.trigger("click");
-
-            // No longer highlighted as current
-            selectedRows = wrapper.findAll(CURRENT_HISTORY_HIGHLIGHT_CLASS);
-            expect(selectedRows.length).toBe(0);
-
-            // Highlighted as normal selection
-            selectedRows = wrapper.findAll(SELECTED_HISTORY_HIGHLIGHT_CLASS);
-            expect(selectedRows.length).toBe(1);
-        });
     });
 });
diff --git a/client/src/components/History/Modals/SelectorModal.vue b/client/src/components/History/Modals/SelectorModal.vue
index 4776ed30dd5..5fdd0440798 100644
--- a/client/src/components/History/Modals/SelectorModal.vue
+++ b/client/src/components/History/Modals/SelectorModal.vue
@@ -11,7 +11,7 @@
             primary-key="id"
             :fields="fields"
             :filter="filter"
-            :items="formattedItems"
+            :items="histories"
             :per-page="perPage"
             :current-page="currentPage"
             :selectable="true"
@@ -22,6 +22,9 @@
             selected-variant="success"
             @row-selected="rowSelected"
             @filtered="onFiltered">
+            <template v-slot:cell(name)="row">
+                {{ row.item.name }} <i v-if="row.item.id === currentHistoryId"><b>(Current)</b></i>
+            </template>
             <template v-slot:cell(tags)="row">
                 <stateless-tags :value="row.item.tags" :disabled="true" />
             </template>
@@ -71,17 +74,6 @@ export default {
         };
     },
     computed: {
-        formattedItems() {
-            return this.histories.map((item) => {
-                if (item.id === this.currentHistoryId) {
-                    const isCurrentSelected = this.selectedHistories.some(
-                        (history) => history.id === this.currentHistoryId
-                    );
-                    item._rowVariant = isCurrentSelected ? "success" : "info";
-                }
-                return item;
-            });
-        },
         isEmptySelection() {
             return this.selectedHistories.length === 0;
         },

From 5af728c4cb5ef37bd30ac2b88fab02e81dd25fd7 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Tue, 24 Jan 2023 13:28:31 -0500
Subject: [PATCH 278/350] Fix bag auto-merge of dev.

---
 lib/galaxy/datatypes/proteomics.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/datatypes/proteomics.py b/lib/galaxy/datatypes/proteomics.py
index 082bad8c2dd..dae3f7c5f81 100644
--- a/lib/galaxy/datatypes/proteomics.py
+++ b/lib/galaxy/datatypes/proteomics.py
@@ -97,7 +97,7 @@ class Wiff2(Binary):
             is_binary=True,
         )
 
-    def generate_primary_file(self, dataset: GeneratePrimaryFileDataset) -> str:
+    def generate_primary_file(self, dataset: HasExtraFilesAndMetadata) -> str:
         rval = ["<html><head><title>Wiff2 Composite Dataset </title></head><p/>"]
         rval.append("<div>This composite dataset is composed of the following files:<p/><ul>")
         for composite_name, composite_file in self.get_composite_files(dataset=dataset).items():

From 1fd4ce8ab0d0fd215fb66494057aa9c82c77d17e Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Tue, 24 Jan 2023 13:54:22 -0500
Subject: [PATCH 279/350] Fix for bleach 6.0 that dropped today.

https://pypi.org/project/bleach/
---
 lib/galaxy/util/sanitize_html.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/util/sanitize_html.py b/lib/galaxy/util/sanitize_html.py
index cdfe5229168..d915a80a7a1 100644
--- a/lib/galaxy/util/sanitize_html.py
+++ b/lib/galaxy/util/sanitize_html.py
@@ -252,5 +252,5 @@ _acceptable_attributes = [
 def sanitize_html(htmlSource, allow_data_urls=False):
     kwd = dict(tags=_acceptable_elements, attributes=_acceptable_attributes, strip=True)
     if allow_data_urls:
-        kwd["protocols"] = bleach.ALLOWED_PROTOCOLS + ["data"]
+        kwd["protocols"] = list(bleach.ALLOWED_PROTOCOLS) + ["data"]
     return bleach.clean(unicodify(htmlSource), **kwd)

From 5ab06841dab4bfcb46fd8cdeab266b0f0d82380b Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Tue, 24 Jan 2023 16:23:39 -0500
Subject: [PATCH 280/350] Attempt to force result order?

---
 client/webpack.config.js | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 795db78e6f1..3389ffb1529 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -28,6 +28,9 @@ const modulesExcludedFromLibs = [
 
 const buildDate = new Date();
 
+const dns = require('node:dns');
+dns.setDefaultResultOrder('ipv4first');
+
 module.exports = (env = {}, argv = {}) => {
     // environment name based on -d, -p, webpack flag
     const targetEnv = process.env.NODE_ENV == "production" || argv.mode == "production" ? "production" : "development";

From 7674416df0c1cb0c6e73bc3d881aab904b090329 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Tue, 24 Jan 2023 16:38:00 -0500
Subject: [PATCH 281/350] Swap default binding from localhost to explicit ipv4
 loopback

---
 client/webpack.config.js | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/client/webpack.config.js b/client/webpack.config.js
index 3389ffb1529..e4729ccc555 100644
--- a/client/webpack.config.js
+++ b/client/webpack.config.js
@@ -28,9 +28,6 @@ const modulesExcludedFromLibs = [
 
 const buildDate = new Date();
 
-const dns = require('node:dns');
-dns.setDefaultResultOrder('ipv4first');
-
 module.exports = (env = {}, argv = {}) => {
     // environment name based on -d, -p, webpack flag
     const targetEnv = process.env.NODE_ENV == "production" || argv.mode == "production" ? "production" : "development";
@@ -262,7 +259,10 @@ module.exports = (env = {}, argv = {}) => {
             // can be a more limited set -- e.g. `/api`, `/auth`
             proxy: {
                 "**": {
-                    target: process.env.GALAXY_URL || "http://localhost:8080",
+                    // We explicitly use ipv4 loopback instead of localhost to
+                    // avoid ipv6/ipv4 resolution order issues; this should
+                    // align with Galaxy's default.
+                    target: process.env.GALAXY_URL || "http://127.0.0.1:8080",
                     secure: process.env.CHANGE_ORIGIN ? !process.env.CHANGE_ORIGIN : true,
                     changeOrigin: !!process.env.CHANGE_ORIGIN,
                     logLevel: "debug",

From 9a6ee51d28fc278b241efbbd7790efe5439439b4 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Tue, 24 Jan 2023 12:25:28 -0500
Subject: [PATCH 282/350] Fix workflow editing route for workflows created from
 history

---
 lib/galaxy/webapps/galaxy/controllers/workflow.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/workflow.py b/lib/galaxy/webapps/galaxy/controllers/workflow.py
index 8c8038c6384..b5e8861a911 100644
--- a/lib/galaxy/webapps/galaxy/controllers/workflow.py
+++ b/lib/galaxy/webapps/galaxy/controllers/workflow.py
@@ -711,8 +711,8 @@ class WorkflowController(BaseUIController, SharableMixin, UsesStoredWorkflowMixi
                 'You can <a href="%s" target="_parent">edit</a> or <a href="%s" target="_parent">run</a> the workflow.'
                 % (
                     escape(workflow_name),
-                    url_for(controller="workflow", action="editor", id=workflow_id),
-                    url_for(controller="workflows", action="run", id=workflow_id),
+                    url_for("/workflows/edit?id=%s" % workflow_id),
+                    url_for("/workflows/run?id=%s" % workflow_id),
                 )
             )
 

From 71fbbfe0d232ccd77bd58f98f53398d330dbf987 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Tue, 24 Jan 2023 20:35:54 -0500
Subject: [PATCH 283/350] Use fstrings instead of % style composition

---
 lib/galaxy/webapps/galaxy/controllers/workflow.py | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/workflow.py b/lib/galaxy/webapps/galaxy/controllers/workflow.py
index b5e8861a911..88fae496993 100644
--- a/lib/galaxy/webapps/galaxy/controllers/workflow.py
+++ b/lib/galaxy/webapps/galaxy/controllers/workflow.py
@@ -706,14 +706,11 @@ class WorkflowController(BaseUIController, SharableMixin, UsesStoredWorkflowMixi
             )
             # Index page with message
             workflow_id = trans.security.encode_id(stored_workflow.id)
+            edit_url = url_for(f"/workflows/edit?id={workflow_id}")
+            run_url = url_for(f"/workflows/run?id={workflow_id}")
             return trans.show_message(
-                'Workflow "%s" created from current history. '
-                'You can <a href="%s" target="_parent">edit</a> or <a href="%s" target="_parent">run</a> the workflow.'
-                % (
-                    escape(workflow_name),
-                    url_for("/workflows/edit?id=%s" % workflow_id),
-                    url_for("/workflows/run?id=%s" % workflow_id),
-                )
+                f'Workflow "{escape(workflow_name)}" created from current history. '
+                f'You can <a href="{edit_url}" target="_parent">edit</a> or <a href="{run_url}" target="_parent">run</a> the workflow.'
             )
 
     def get_item(self, trans, id):

From c72af2b045b837cf231a7989d09451ae5992582d Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 25 Jan 2023 10:35:03 +0100
Subject: [PATCH 284/350] fix broken fetch

---
 client/src/composables/datatypes.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/composables/datatypes.ts b/client/src/composables/datatypes.ts
index 88a38f045f4..cb29633e4ec 100644
--- a/client/src/composables/datatypes.ts
+++ b/client/src/composables/datatypes.ts
@@ -29,7 +29,7 @@ export function useDetailedDatatypes() {
 
     async function getDatatypes() {
         try {
-            const datatypesPromise = datatypesFetcher({ extension_only: true });
+            const datatypesPromise = datatypesFetcher({ extension_only: false });
             const datatypeEDAMFormatsPromise = edamFormatsFetcher({});
             const datatypeEDAMDataPromise = edamDataFetcher({});
 

From 32961aca6bf68e877dd427c9855509aedb7b414b Mon Sep 17 00:00:00 2001
From: Laila Los <44241786+ElectronicBlueberry@users.noreply.github.com>
Date: Wed, 25 Jan 2023 12:58:27 +0100
Subject: [PATCH 285/350] fix zoom and refactor

---
 .../Workflow/Editor/WorkflowGraph.vue         |  5 +-
 .../Workflow/Editor/ZoomControl.vue           | 85 +++++++------------
 .../composables/{useZoom.ts => d3Zoom.ts}     | 18 +---
 .../Workflow/Editor/modules/zoomLevels.ts     | 59 +++++++++++++
 4 files changed, 97 insertions(+), 70 deletions(-)
 rename client/src/components/Workflow/Editor/composables/{useZoom.ts => d3Zoom.ts} (76%)
 create mode 100644 client/src/components/Workflow/Editor/modules/zoomLevels.ts

diff --git a/client/src/components/Workflow/Editor/WorkflowGraph.vue b/client/src/components/Workflow/Editor/WorkflowGraph.vue
index 2dfdb7841bc..3dc2aa26b14 100644
--- a/client/src/components/Workflow/Editor/WorkflowGraph.vue
+++ b/client/src/components/Workflow/Editor/WorkflowGraph.vue
@@ -48,9 +48,10 @@ import { useWorkflowStateStore } from "@/stores/workflowEditorStateStore";
 import type { TerminalPosition } from "@/stores/workflowEditorStateStore";
 import { DatatypesMapperModel } from "@/components/Datatypes/model";
 import { useWorkflowStepStore, type Step } from "@/stores/workflowStepStore";
-import { useZoom } from "./composables/useZoom";
+import { useD3Zoom } from "./composables/d3Zoom";
 import type { XYPosition } from "@/stores/workflowEditorStateStore";
 import type { OutputTerminals } from "./modules/terminals";
+import { minZoom, maxZoom } from "./modules/zoomLevels";
 
 const emit = defineEmits(["transform", "graph-offset", "onRemove", "scrollTo"]);
 const props = defineProps({
@@ -67,7 +68,7 @@ const canvas: Ref<HTMLElement | null> = ref(null);
 
 const elementBounding = useElementBounding(canvas, { windowResize: false, windowScroll: false });
 const scroll = useScroll(canvas);
-const { transform, panBy, setZoom, moveTo } = useZoom(1, 0.2, 5, canvas, scroll);
+const { transform, panBy, setZoom, moveTo } = useD3Zoom(1, minZoom, maxZoom, canvas, scroll);
 
 const isDragging = ref(false);
 provide("isDragging", isDragging);
diff --git a/client/src/components/Workflow/Editor/ZoomControl.vue b/client/src/components/Workflow/Editor/ZoomControl.vue
index 755d89343e4..081ec21fa7a 100644
--- a/client/src/components/Workflow/Editor/ZoomControl.vue
+++ b/client/src/components/Workflow/Editor/ZoomControl.vue
@@ -1,8 +1,38 @@
+<script lang="ts" setup>
+import Vue, { computed } from "vue";
+import BootstrapVue from "bootstrap-vue";
+import { getZoomInLevel, getZoomOutLevel, isMinZoom, isMaxZoom } from "./modules/zoomLevels";
+
+Vue.use(BootstrapVue);
+
+const props = defineProps({
+    zoomLevel: { type: Number, default: 1 },
+});
+
+const emit = defineEmits<{
+    (e: "onZoom", zoom: number): void;
+}>();
+
+const zoomDefault = 1;
+const zoomPercentage = computed(() => Math.round(props.zoomLevel * 100));
+
+function onZoomIn() {
+    emit("onZoom", getZoomInLevel(props.zoomLevel));
+}
+
+function onZoomOut() {
+    emit("onZoom", getZoomOutLevel(props.zoomLevel));
+}
+
+function onZoomReset() {
+    emit("onZoom", zoomDefault);
+}
+</script>
+
 <template>
     <span class="zoom-control float-right btn-group-horizontal">
         <b-button
-            v-b-tooltip.hover
-            :disabled="isMin"
+            :disabled="isMinZoom(props.zoomLevel)"
             role="button"
             class="fa fa-minus"
             title="Zoom Out"
@@ -21,8 +51,7 @@
             {{ zoomPercentage }}%
         </b-button>
         <b-button
-            v-b-tooltip.hover
-            :disabled="isMax"
+            :disabled="isMaxZoom(props.zoomLevel)"
             role="button"
             class="fa fa-plus"
             title="Zoom In"
@@ -32,54 +61,6 @@
     </span>
 </template>
 
-<script lang="ts" setup>
-import Vue, { computed } from "vue";
-import BootstrapVue from "bootstrap-vue";
-
-Vue.use(BootstrapVue);
-
-const props = withDefaults(
-    defineProps<{
-        zoomLevel: number;
-    }>(),
-    {
-        zoomLevel: 1,
-    }
-);
-const emit = defineEmits(["onZoom"]);
-
-const zoomDefault = 1;
-const zoomLevels = [0.1, 0.2, 0.25, 0.33, 0.5, 0.67, 0.75, 0.8, 0.9, 1, 1.1, 1.25, 1.33, 1.5, 2, 2.5, 3, 4, 5];
-const isMin = computed(() => Math.round(props.zoomLevel * 100) == Math.round(zoomLevels[0] * 100));
-const isMax = computed(() => Math.round(props.zoomLevel * 100) == Math.round(zoomLevels.at(-1)! * 100));
-const zoomPercentage = computed(() => Math.round(props.zoomLevel * 100));
-const index = computed(() => {
-    let index = zoomLevels.indexOf(props.zoomLevel);
-    if (index < 0) {
-        const closest = zoomLevels.reduce((prev, curr) => {
-            return Math.abs(curr - props.zoomLevel) < Math.abs(prev - props.zoomLevel) ? curr : prev;
-        });
-        index = zoomLevels.indexOf(closest);
-    }
-    return index;
-});
-function onZoomIn() {
-    const zoomLevel = zoomLevels[index.value + 1];
-    if (zoomLevel) {
-        emit("onZoom", zoomLevel);
-    }
-}
-function onZoomOut() {
-    const zoomLevel = zoomLevels[index.value - 1];
-    if (zoomLevel) {
-        emit("onZoom", zoomLevel);
-    }
-}
-function onZoomReset() {
-    emit("onZoom", zoomDefault);
-}
-</script>
-
 <style scoped>
 .zoom-reset {
     width: 4rem;
diff --git a/client/src/components/Workflow/Editor/composables/useZoom.ts b/client/src/components/Workflow/Editor/composables/d3Zoom.ts
similarity index 76%
rename from client/src/components/Workflow/Editor/composables/useZoom.ts
rename to client/src/components/Workflow/Editor/composables/d3Zoom.ts
index 76beceb2e4b..17df1fc74dd 100644
--- a/client/src/components/Workflow/Editor/composables/useZoom.ts
+++ b/client/src/components/Workflow/Editor/composables/d3Zoom.ts
@@ -1,6 +1,6 @@
 import { zoom, zoomIdentity, type D3ZoomEvent } from "d3-zoom";
 import { ref, watch } from "vue";
-import { pointer, select } from "d3-selection";
+import { select } from "d3-selection";
 import type { Ref } from "vue";
 import type { XYPosition } from "@/stores/workflowEditorStateStore";
 import type { UseScrollReturn } from "@vueuse/core";
@@ -12,7 +12,7 @@ const filter = (event: any) => {
     return !preventZoom;
 };
 
-export function useZoom(
+export function useD3Zoom(
     k: number,
     minZoom: number,
     maxZoom: number,
@@ -29,20 +29,6 @@ export function useZoom(
                 .translate(transform.value.x, transform.value.y)
                 .scale(transform.value.k);
             d3Zoom.transform(d3Selection, updatedTransform);
-
-            d3Selection
-                .on("wheel", (event) => {
-                    const currentZoom = d3Selection.property("__zoom").k || 1;
-
-                    const pinchDelta =
-                        -event.deltaY * (event.deltaMode === 1 ? 0.05 : event.deltaMode ? 1 : 0.002) * 10;
-                    const point = pointer(event);
-                    point[0] += scroll.x.value;
-                    point[1] += scroll.y.value;
-                    const zoom = currentZoom * 2 ** pinchDelta;
-                    d3Zoom.scaleTo(d3Selection, zoom, point);
-                })
-                .on("wheel.zoom", null);
         }
 
         d3Zoom.on("zoom", (event: D3ZoomEvent<HTMLElement, unknown>) => {
diff --git a/client/src/components/Workflow/Editor/modules/zoomLevels.ts b/client/src/components/Workflow/Editor/modules/zoomLevels.ts
new file mode 100644
index 00000000000..79048cfe720
--- /dev/null
+++ b/client/src/components/Workflow/Editor/modules/zoomLevels.ts
@@ -0,0 +1,59 @@
+export const zoomLevels = [
+    0.1, 0.2, 0.25, 0.33, 0.5, 0.67, 0.75, 0.8, 0.9, 1, 1.1, 1.25, 1.33, 1.5, 2, 2.5, 3, 4, 5,
+] as const;
+
+export type ZoomLevel = (typeof zoomLevels)[number];
+
+export const minZoom = zoomLevels[0];
+export const maxZoom = zoomLevels[zoomLevels.length - 1];
+
+/**
+ * Finds the closest snapped zoom level
+ * @param zoom decimal number indicating current zoom multiplier
+ * @returns snapped zoom level
+ */
+export function getSnappedZoom(zoom: number): ZoomLevel {
+    return zoomLevels.reduce((a, b) => {
+        return Math.abs(b - zoom) < Math.abs(a - zoom) ? b : a;
+    });
+}
+
+/**
+ * Gets the next largest zoom level
+ * @param zoom decimal number indicating current zoom multiplier
+ * @returns snapped zoom level
+ */
+export function getZoomInLevel(zoom: number): ZoomLevel {
+    const snapped = getSnappedZoom(zoom);
+    const index = zoomLevels.indexOf(snapped);
+
+    if (index === zoomLevels.length - 1) {
+        return snapped;
+    } else {
+        return zoomLevels[index + 1];
+    }
+}
+
+/**
+ * Get the next smaller zoom level
+ * @param zoom decimal number indicating current zoom multiplier
+ * @returns snapped zoom level
+ */
+export function getZoomOutLevel(zoom: number): ZoomLevel {
+    const snapped = getSnappedZoom(zoom);
+    const index = zoomLevels.indexOf(snapped);
+
+    if (index === 0) {
+        return snapped;
+    } else {
+        return zoomLevels[index - 1];
+    }
+}
+
+export function isMinZoom(zoom: number): boolean {
+    return zoom === minZoom;
+}
+
+export function isMaxZoom(zoom: number): boolean {
+    return zoom === maxZoom;
+}

From b413bfa189e57ab8cb96f47b7f76b402983cc212 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Wed, 25 Jan 2023 13:24:20 +0100
Subject: [PATCH 286/350] Redirect anonymous users on histories/list

---
 client/src/components/Grid/GridHistory.vue | 10 +---------
 client/src/components/Grid/history-list.js |  9 ++-------
 client/src/entry/analysis/router.js        | 11 ++++++-----
 3 files changed, 9 insertions(+), 21 deletions(-)

diff --git a/client/src/components/Grid/GridHistory.vue b/client/src/components/Grid/GridHistory.vue
index 8f91a6af438..c00cf5641ae 100644
--- a/client/src/components/Grid/GridHistory.vue
+++ b/client/src/components/Grid/GridHistory.vue
@@ -5,16 +5,8 @@
 <script>
 import HistoryList from "./history-list";
 export default {
-    props: {
-        actionId: {
-            type: String,
-            default: null,
-        },
-    },
     mounted() {
-        new HistoryList.View({
-            action_id: this.actionId,
-        }).$el.appendTo(this.$refs.target);
+        new HistoryList.View().$el.appendTo(this.$refs.target);
     },
 };
 </script>
diff --git a/client/src/components/Grid/history-list.js b/client/src/components/Grid/history-list.js
index e8a768413af..42b8c21ff2c 100644
--- a/client/src/components/Grid/history-list.js
+++ b/client/src/components/Grid/history-list.js
@@ -62,15 +62,10 @@ var View = Backbone.View.extend({
     initialize: function (options) {
         const Galaxy = getGalaxyInstance();
         LoadingIndicator.markViewAsLoading(this);
-
-        if (options.action_id == "list_published") {
-            this.active_tab = "shared";
-        } else if (options.action_id == "list") {
-            this.active_tab = "user";
-        }
+        this.active_tab = "user";
         this.model = new Backbone.Model();
         Utils.get({
-            url: `${getAppRoot()}history/${options.action_id}?${$.param(Galaxy.params)}`,
+            url: `${getAppRoot()}history/list?${$.param(Galaxy.params)}`,
             success: (response) => {
                 this.model.set(response);
                 this.render();
diff --git a/client/src/entry/analysis/router.js b/client/src/entry/analysis/router.js
index 56e2bdac7e9..558e962322f 100644
--- a/client/src/entry/analysis/router.js
+++ b/client/src/entry/analysis/router.js
@@ -235,6 +235,12 @@ export function getRouter(Galaxy) {
                         component: HistoryPublishedList,
                         props: true,
                     },
+                    {
+                        path: "histories/list",
+                        component: GridHistory,
+                        props: true,
+                        redirect: redirectAnon(),
+                    },
                     {
                         path: "histories/:historyId/export",
                         get component() {
@@ -242,11 +248,6 @@ export function getRouter(Galaxy) {
                         },
                         props: true,
                     },
-                    {
-                        path: "histories/:actionId",
-                        component: GridHistory,
-                        props: true,
-                    },
                     {
                         path: "interactivetool_entry_points/list",
                         component: InteractiveTools,

From e192896011172272749b10feddc6d213193c09e8 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 25 Jan 2023 09:06:24 -0500
Subject: [PATCH 287/350] Content updates to client readme, some grammatical
 and other changes.

---
 client/README.md | 64 ++++++++++++++++++++++++------------------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/client/README.md b/client/README.md
index 9b23e47280c..c3dde023c79 100644
--- a/client/README.md
+++ b/client/README.md
@@ -1,19 +1,19 @@
 # Client Build System
 
 Installs, stages, and builds the client-side scripts necessary for running the
-Galaxy webapp. When started through `run.sh` or any other method that utilizes
-`scripts/common_startup.sh`, Galaxy will (since 18.09) _automatically_ build
-the client as a part of server startup, when it detects changes, unless that
+Galaxy web client. When started through `run.sh` or any other method that
+utilizes `scripts/common_startup.sh`, Galaxy will (since 18.09) _automatically_
+build the client as a part of server startup when it detects changes unless that
 functionality is explicitly disabled.
 
-The base dependencies used are Node.js and Yarn. Galaxy now includes these in
-the virtual environment, and they can be accessed by activating that with `.
-.venv/bin/activate` from the Galaxy root directory.
+The base dependencies used are Node.js and Yarn. Galaxy includes appropriate
+versions of these in the virtual environment, and they can be accessed by
+activating that with `. .venv/bin/activate` from the Galaxy root directory.
 
-If you'd like to install your own dependencies, on OSX the easiest way to get
-set up is using `homebrew` and the command `brew install nodejs yarn`. More
-information, including instructions for other platforms, is available at
-[https://nodejs.org](https://nodejs.org) and
+If you'd like to install your dependencies external to Galaxy, on OSX the
+easiest way to get set up is using `homebrew` and the command `brew install
+nodejs yarn`. More information, including instructions for other platforms, is
+available at [https://nodejs.org](https://nodejs.org) and
 [https://yarnpkg.com/](https://yarnpkg.com).
 
 The Galaxy client build has necessarily grown more complex in the past several
@@ -27,11 +27,11 @@ directly on Gitter at
 
 There are many moving parts to the client build system, but the entry point for
 most people is the 'client' rule in the Makefile at the root of the Galaxy
-repository. Execute the following to perform a complete build suitable for
-local development, including dependency staging, style building, script
-processing, and bundling. This is a development-specific build which includes
-extra debugging features, and excludes several production optimizations made
-during the build process.
+repository. Execute the following to perform a complete build suitable for local
+development, including dependency staging, style building, script processing,
+and bundling. This is a development-specific build that includes extra debugging
+features and excludes several production optimizations made during the build
+process.
 
     make client
 
@@ -56,21 +56,21 @@ automatically rebuild every time you save a file. You can do this using:
     make client-dev-server
 
 Or, with the package scripts from this `client` directory:
-    
+
     yarn run develop
 
-This will start up an extra client development server running on port 8081.
-Open your browser to http://localhost:8081 (instead of the default 8080 that
-Galaxy would run on), and you should see Galaxy like normal.  Except now, when
-you change client code it'll automatically rebuild *and* reload the relevant
-portion of the application for you. Lastly, if you
-are running Galaxy at a location other than the default, you can specify a
-different proxy target (in this example, port 8000) using the GALAXY_URL
-environment variable:
+This will start up an extra client development server running on port 8081. Open
+your browser to `http://localhost:8081` (instead of the default 8080 that Galaxy
+would run on), and you should see Galaxy like normal.  Except now, when you
+change client code it'll automatically rebuild _and_ reload the relevant portion
+of the application for you. Lastly, if you are running Galaxy at a location
+other than the default, you can specify a different proxy target (in this
+example, port 8000) using the GALAXY_URL environment variable:
 
     GALAXY_URL="http://localhost:8000" make client-dev-server
 
-Sometimes you want to run your local UI against a remote Galaxy server. This is also possible, if you enable `CHANGE_ORIGIN` flag 
+Sometimes you want to run your local UI against a remote Galaxy server. This is
+also possible if you enable `CHANGE_ORIGIN` flag:
 
     CHANGE_ORIGIN=true GALAXY_URL="https://usegalaxy.org/" make client-dev-server
 
@@ -93,11 +93,11 @@ prefer:
 
 ## Changing Styles/CSS
 
-Galaxy uses Sass for its styling, which is a superset of CSS that compiles down
+Galaxy uses Sass for globally applied styling, which is a superset of CSS that compiles down
 to regular CSS. Most Galaxy styling source (.scss) files are kept in
-`client/src/style/scss`. There are additionally style blocks alongside some Vue
-components -- styles that are particular to that individual component and do
-not apply site-wide.
+`client/src/style/scss`. There are additionaly style blocks alongside some Vue
+components -- styles that are particular to that individual component and do not
+apply site-wide.
 
 On build, the compiled css bundle is served at `/static/style/base.css`.
 
@@ -139,8 +139,8 @@ directory. This is what happens during a complete client build.
 
 During client-side development, it is more convenient to have granular testing
 options. The various testing scripts are defined inside package.json within the
-client folder, and are called with `yarn` as demonstrated in the
-following commands.
+client folder, and are called with `yarn` as demonstrated in the following
+commands.
 
 This is what CI is going to run, and also what 'make client-test' invokes,
 executing all the client tests:
@@ -151,7 +151,7 @@ You can also bypass qunit and single-run all of the jest tests like so:
 
      yarn run jest
 
-Or, if you really want to run just the qunit tests:
+Or, if you want to run just the qunit tests:
 
     yarn run qunit
 

From 2c69c96dfd441678714b433477807aa3f29968af Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Wed, 25 Jan 2023 09:13:35 -0500
Subject: [PATCH 288/350] Update run_tests_help w/ client targets

---
 doc/source/dev/run_tests_help.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/doc/source/dev/run_tests_help.txt b/doc/source/dev/run_tests_help.txt
index 4e002913339..5e646326027 100644
--- a/doc/source/dev/run_tests_help.txt
+++ b/doc/source/dev/run_tests_help.txt
@@ -75,8 +75,8 @@ Run a specific selenium test (under Linux or Mac OS X after installing geckodriv
 
 Run a selenium test against a running server while watching client (fastest iterating on client tests):
     ./run.sh & # run Galaxy on 8080
-    make client-watch & # watch for client changes
-    export GALAXY_TEST_EXTERNAL=http://localhost:8080/  # Target tests at server.
+    make client-dev-server & # watch for client changes
+    export GALAXY_TEST_EXTERNAL=http://localhost:8081/  # Target tests at server.
     . .venv/bin/activate # source the virtualenv so can skip run_tests.sh.
     pytest lib/galaxy_test/selenium/test_workflow_editor.py::TestWorkflowEditor::test_data_input
 

From 741aec7aa90eef081b5a04578c4d0447d383e6ea Mon Sep 17 00:00:00 2001
From: Dannon <dannon.baker@gmail.com>
Date: Wed, 25 Jan 2023 09:22:27 -0500
Subject: [PATCH 289/350] Apply suggestions from code review

Thanks @nsoranzo!

Co-authored-by: Nicola Soranzo <nicola.soranzo@gmail.com>
---
 client/README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/client/README.md b/client/README.md
index c3dde023c79..3045a31b16a 100644
--- a/client/README.md
+++ b/client/README.md
@@ -70,7 +70,7 @@ example, port 8000) using the GALAXY_URL environment variable:
     GALAXY_URL="http://localhost:8000" make client-dev-server
 
 Sometimes you want to run your local UI against a remote Galaxy server. This is
-also possible if you enable `CHANGE_ORIGIN` flag:
+also possible if you set the `CHANGE_ORIGIN` environment variable:
 
     CHANGE_ORIGIN=true GALAXY_URL="https://usegalaxy.org/" make client-dev-server
 
@@ -95,7 +95,7 @@ prefer:
 
 Galaxy uses Sass for globally applied styling, which is a superset of CSS that compiles down
 to regular CSS. Most Galaxy styling source (.scss) files are kept in
-`client/src/style/scss`. There are additionaly style blocks alongside some Vue
+`client/src/style/scss`. There are additional style blocks alongside some Vue
 components -- styles that are particular to that individual component and do not
 apply site-wide.
 

From a8e5702e3cb01e07a55886c1e32f1cb465c6167f Mon Sep 17 00:00:00 2001
From: Assunta DeSanto <assuntad23@gmail.com>
Date: Wed, 25 Jan 2023 12:53:06 -0500
Subject: [PATCH 290/350] Adding more directive to the tooltip

---
 client/src/components/Workflow/Editor/modules/terminals.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 4efe198c526..cdb3538e69c 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -367,7 +367,7 @@ export class InvalidInputTerminal extends BaseInputTerminal {
     }
 
     attachable(terminal: BaseOutputTerminal) {
-        return new ConnectionAcceptable(false, "Cannot attach to invalid input.");
+        return new ConnectionAcceptable(false, "Cannot attach to invalid input. Disconnect this input.");
     }
 }
 

From d683d1a50a82da2a545856b988f2dbc72f13a928 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Wed, 25 Jan 2023 16:50:38 -0500
Subject: [PATCH 291/350] Add hint to indicate that retrying to auto-detect the
 metadata might succeed

---
 client/src/components/History/Content/model/states.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/History/Content/model/states.js b/client/src/components/History/Content/model/states.js
index 2ddfcecbf9e..f37800d8282 100644
--- a/client/src/components/History/Content/model/states.js
+++ b/client/src/components/History/Content/model/states.js
@@ -33,7 +33,7 @@ export const STATES = {
     /** metadata discovery/setting failed or errored (but otherwise ok) */
     failed_metadata: {
         status: "danger",
-        text: "Metadata generation failed.",
+        text: "Metadata generation failed. Please retry.",
         icon: "exclamation-triangle",
     },
     /** was created without a tool */

From b48f4dcdca2d6ad1e92f8ad9a29d4d1f34be3347 Mon Sep 17 00:00:00 2001
From: Assunta DeSanto <assuntad23@gmail.com>
Date: Wed, 25 Jan 2023 22:43:21 -0500
Subject: [PATCH 292/350] vueify formUpload with composition API

---
 .../components/Form/Elements/FormUpload.vue   | 41 +++++++++++++++++++
 client/src/components/Form/FormElement.vue    |  2 +
 2 files changed, 43 insertions(+)
 create mode 100644 client/src/components/Form/Elements/FormUpload.vue

diff --git a/client/src/components/Form/Elements/FormUpload.vue b/client/src/components/Form/Elements/FormUpload.vue
new file mode 100644
index 00000000000..de43d4b55f3
--- /dev/null
+++ b/client/src/components/Form/Elements/FormUpload.vue
@@ -0,0 +1,41 @@
+<script setup>
+import { ref, defineEmits, computed } from "vue";
+import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
+const props = defineProps({
+    value: ""
+});
+const file = ref(null);
+const emit = defineEmits(["input"]);
+const currentValue = computed({
+    get() {
+        return props.value;
+    },
+    set(newValue) {
+        emit("input", newValue);
+    },
+});
+const waiting = ref(false);
+function readFile() {
+    const fileContent = file.value && file.value.files[0];
+    var reader = new FileReader();
+    if (fileContent) {
+        waiting.value = true;
+        reader.onload = () => {
+            currentValue.value = reader.result;
+            waiting.value = false;
+        };
+        reader.readAsText(fileContent);
+    }
+}
+</script>
+
+<template>
+    <div>
+        <input ref="file" type="file" class="mb-1" @change="readFile" />
+        <div v-if="waiting">
+            <font-awesome-icon icon="spinner" spin />
+            Uploading File...
+        </div>
+        <textarea v-show="currentValue" v-model="currentValue" class="ui-textarea" disabled></textarea>
+    </div>
+</template>
\ No newline at end of file
diff --git a/client/src/components/Form/FormElement.vue b/client/src/components/Form/FormElement.vue
index 9e74614f742..ecc6fa340a7 100644
--- a/client/src/components/Form/FormElement.vue
+++ b/client/src/components/Form/FormElement.vue
@@ -10,6 +10,7 @@ import FormNumber from "./Elements/FormNumber.vue";
 import FormText from "./Elements/FormText.vue";
 import FormOptionalText from "./Elements/FormOptionalText.vue";
 import FormRulesEdit from "./Elements/FormRulesEdit.vue";
+import FormUpload from "./Elements/FormUpload.vue";
 import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
 import { ref, computed, useAttrs } from "vue";
 import { library } from "@fortawesome/fontawesome-svg-core";
@@ -265,6 +266,7 @@ const isOptional = computed(() => !isRequired.value && attrs.value["optional"] !
                 :multiple="attrs.multiple" />
             <FormColor v-else-if="props.type === 'color'" :id="props.id" v-model="currentValue" />
             <FormDirectory v-else-if="props.type === 'directory_uri'" v-model="currentValue" />
+            <FormUpload v-else-if="props.type === 'upload'" v-model="currentValue" />
             <FormRulesEdit v-else-if="props.type == 'rules'" v-model="currentValue" :target="attrs.target" />
             <FormParameter
                 v-else-if="backbonejs"

From 9a0bb385b8876ac0914d5a803cf1f13ffb9a1083 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Thu, 26 Jan 2023 11:33:43 +0100
Subject: [PATCH 293/350] Fix dataset options text

On show, explicitly state that we will be switching to the history to avoid confusion.

On copy, explicitly state that it will be copied to the current history.
---
 client/src/components/Dataset/DatasetName.vue | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/client/src/components/Dataset/DatasetName.vue b/client/src/components/Dataset/DatasetName.vue
index 1625cd497ac..9751155ea3d 100644
--- a/client/src/components/Dataset/DatasetName.vue
+++ b/client/src/components/Dataset/DatasetName.vue
@@ -22,11 +22,11 @@
         <div class="dropdown-menu" aria-labelledby="dataset-dropdown">
             <a class="dropdown-item" href="#" @click.prevent="showDataset">
                 <span class="fa fa-eye fa-fw mr-1" />
-                <span>Show in History</span>
+                <span>Switch to History containing dataset</span>
             </a>
             <a class="dropdown-item" href="#" @click.prevent="copyDataset">
                 <span class="fa fa-copy fa-fw mr-1" />
-                <span>Copy to History</span>
+                <span>Copy to current History</span>
             </a>
         </div>
     </div>

From 005fdafc23de3abf4b0e7761ca14d8789079dc35 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Wed, 25 Jan 2023 22:29:14 +0100
Subject: [PATCH 294/350] Split up node map over into input map over

Fixes https://github.com/galaxyproject/galaxy/issues/15369 ...
this was a real pain, and it definitely needs more tests.
---
 .../Workflow/Editor/TerminalConnector.vue     |  6 ++-
 .../Workflow/Editor/modules/terminals.test.ts |  8 ++-
 .../Workflow/Editor/modules/terminals.ts      | 53 ++++++++++++++-----
 client/src/stores/workflowStepStore.ts        | 18 ++++++-
 4 files changed, 67 insertions(+), 18 deletions(-)

diff --git a/client/src/components/Workflow/Editor/TerminalConnector.vue b/client/src/components/Workflow/Editor/TerminalConnector.vue
index 9700c452dd3..5830982e5d0 100644
--- a/client/src/components/Workflow/Editor/TerminalConnector.vue
+++ b/client/src/components/Workflow/Editor/TerminalConnector.vue
@@ -23,7 +23,11 @@ const props = defineProps<{
 const stepStore = useWorkflowStepStore();
 const connectionStore = useConnectionStore();
 const outputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.output.stepId]?.isCollection);
-const inputIsMappedOver = computed(() => stepStore.stepMapOver[props.connection.input.stepId]?.isCollection);
+const inputIsMappedOver = computed(
+    () =>
+        stepStore.stepInputMapOver[props.connection.input.stepId] &&
+        stepStore.stepInputMapOver[props.connection.input.stepId][props.connection.input.name]?.isCollection
+);
 const outputIsOptional = computed(() => {
     return Boolean(
         stepStore.getStep(props.connection.output.stepId)?.when ||
diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 00cdd99954c..dd46474b686 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -102,7 +102,9 @@ describe("canAccept", () => {
         dataIn.connect(collectionOut);
         expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         expect(dataIn.canAccept(collectionOut).canAccept).toBe(false);
-        expect(dataIn.canAccept(collectionOut).reason).toBe("Input already filled with another connection, delete it before connecting another output.");
+        expect(dataIn.canAccept(collectionOut).reason).toBe(
+            "Input already filled with another connection, delete it before connecting another output."
+        );
         dataIn.disconnect(collectionOut);
         expect(dataIn.canAccept(collectionOut).canAccept).toBe(true);
         expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);
@@ -262,14 +264,16 @@ describe("canAccept", () => {
         dataIn.connect(collectionOut);
         dataInTwo.connect(dataOut);
         expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+        expect(dataIn.localMapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         //
         dataIn.disconnect(collectionOut);
         // this is weird and not particularly robust, if you save and reload this will most likely not be constrained
         // TODO: avoid this if possible ...
         expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+        expect(dataIn.localMapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         expect(dataIn.canAccept(simpleDataOut).canAccept).toBe(false);
         expect(dataIn.canAccept(simpleDataOut).reason).toBe(
-            "Cannot attach non-collection outputs to mapped over inputs, consider disconnecting inputs and outputs to reset this input's mapping."
+            "Cannot attach non-collection output to mapped over input, consider disconnecting inputs and outputs to reset this input's mapping."
         );
     });
     // TODO: test mapOver reset when constraint removed
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 4efe198c526..249bd89fe55 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -18,6 +18,7 @@ import type {
     TerminalSource,
 } from "@/stores/workflowStepStore";
 import type { DatatypesMapperModel } from "@/components/Datatypes/model";
+import Vue from "vue";
 
 export class ConnectionAcceptable {
     reason: string | null;
@@ -53,6 +54,7 @@ class Terminal extends EventEmitter {
     stepId: number;
     terminalType: "input" | "output";
     datatypesMapper: DatatypesMapperModel;
+    localMapOver: CollectionTypeDescriptor;
 
     constructor(attr: BaseTerminalArgs) {
         super();
@@ -63,6 +65,7 @@ class Terminal extends EventEmitter {
         this.multiple = false;
         this.terminalType = "input";
         this.datatypesMapper = attr.datatypesMapper;
+        this.localMapOver = NULL_COLLECTION_TYPE_DESCRIPTION;
     }
     public get id() {
         return `node-${this.stepId}-${this.terminalType}-${this.name}`;
@@ -105,10 +108,12 @@ class Terminal extends EventEmitter {
             outputVal = val.effectiveMapOver(description);
         }
         const effectiveMapOver = this._effectiveMapOver(outputVal);
+        if (!this.localMapOver.equal(effectiveMapOver)) {
+            this.stepStore.changeStepInputMapOver(this.stepId, this.name, effectiveMapOver);
+            this.localMapOver = effectiveMapOver;
+        }
         if (!this.mapOver.equal(effectiveMapOver)) {
             this.stepStore.changeStepMapOver(this.stepId, effectiveMapOver);
-            // TODO: do we even need to listen for this?
-            this.emit("changeMapOver", outputVal);
         }
     }
     _effectiveMapOver(otherCollectionType: CollectionTypeDescriptor) {
@@ -119,8 +124,7 @@ class Terminal extends EventEmitter {
     }
     resetMapping(connection?: Connection) {
         this.stepStore.changeStepMapOver(this.stepId, NULL_COLLECTION_TYPE_DESCRIPTION);
-        // necessary ?
-        this.emit("changeMapOver", this.mapOver);
+        this.stepStore.resetStepInputMapOver(this.stepId);
     }
     hasConnectedMappedInputTerminals() {
         // check if step has connected and mapped input terminals ... should maybe be on step/node ?
@@ -150,7 +154,7 @@ class Terminal extends EventEmitter {
         // No output terminals are counting on this being mapped
         // over if connected inputs are still mapped over or if none
         // of the outputs are connected...
-        const reset = this.hasConnectedMappedInputTerminals() || !this.hasConnectedOutputTerminals();
+        const reset = !this.hasConnectedOutputTerminals();
         if (reset) {
             this.resetMapping(connection);
         }
@@ -160,12 +164,18 @@ class Terminal extends EventEmitter {
 class BaseInputTerminal extends Terminal {
     datatypes: InputTerminalInputs["datatypes"];
     optional: InputTerminalInputs["optional"];
+    localMapOver: CollectionTypeDescriptor;
 
     constructor(attr: InputTerminalArgs) {
         super(attr);
         this.datatypes = attr.input.datatypes;
         this.multiple = attr.input.multiple;
         this.optional = attr.input.optional;
+        if (this.stepStore.stepInputMapOver[this.stepId] && this.stepStore.stepInputMapOver[this.stepId][this.name]) {
+            this.localMapOver = this.stepStore.stepInputMapOver[this.stepId][this.name];
+        } else {
+            this.localMapOver = NULL_COLLECTION_TYPE_DESCRIPTION;
+        }
     }
     connect(other: BaseOutputTerminal): void {
         super.connect(other);
@@ -174,9 +184,15 @@ class BaseInputTerminal extends Terminal {
     setDefaultMapOver(other: BaseOutputTerminal) {
         const otherCollectionType = this._otherCollectionType(other);
         if (otherCollectionType.isCollection) {
-            this.setMapOver(otherCollectionType);
+            return this.setMapOver(otherCollectionType);
         }
     }
+    getStepMapOver() {
+        this.getConnectedTerminals().forEach((other) => {
+            this.setDefaultMapOver(other);
+        });
+    }
+
     canAccept(outputTerminal: BaseOutputTerminal) {
         if (this.stepId == outputTerminal.stepId) {
             return new ConnectionAcceptable(false, "Cannot connect output to input of same step.");
@@ -201,6 +217,7 @@ class BaseInputTerminal extends Terminal {
     }
     resetMapping(connection?: Connection) {
         super.resetMapping(connection);
+        this.stepStore.changeStepInputMapOver(this.stepId, this.name, NULL_COLLECTION_TYPE_DESCRIPTION);
         const outputStepIds = this._getOutputTerminals().map((outputTerminal) => outputTerminal.stepId);
         if (connection) {
             outputStepIds.push(connection.output.stepId);
@@ -360,10 +377,12 @@ interface InvalidInputTerminalArgs extends InputTerminalArgs {
 
 export class InvalidInputTerminal extends BaseInputTerminal {
     valid: false;
+    localMapOver: CollectionTypeDescriptor;
 
     constructor(attr: InvalidInputTerminalArgs) {
         super(attr);
         this.valid = false;
+        this.localMapOver = NULL_COLLECTION_TYPE_DESCRIPTION;
     }
 
     attachable(terminal: BaseOutputTerminal) {
@@ -378,7 +397,11 @@ export class InputTerminal extends BaseInputTerminal {
     constructor(attr: InputTerminalArgs) {
         super(attr);
         this.collection = false;
-        this.getConnectedTerminals().map((other) => this.setDefaultMapOver(other));
+        this.getStepMapOver();
+    }
+
+    isMappedOver(): boolean {
+        return Boolean(this.localMapOver.isCollection);
     }
 
     attachable(other: BaseOutputTerminal) {
@@ -435,11 +458,13 @@ export class InputTerminal extends BaseInputTerminal {
                     }
                 }
             }
-        } else if (mapOver.isCollection) {
-            return new ConnectionAcceptable(
-                false,
-                "Cannot attach non-collection outputs to mapped over inputs, consider disconnecting inputs and outputs to reset this input's mapping."
-            );
+        } else {
+            if (this.localMapOver.isCollection) {
+                return new ConnectionAcceptable(
+                    false,
+                    "Cannot attach non-collection output to mapped over input, consider disconnecting inputs and outputs to reset this input's mapping."
+                );
+            }
         }
         return this._producesAcceptableDatatypeAndOptionalness(other);
     }
@@ -455,7 +480,7 @@ export class InputParameterTerminal extends BaseInputTerminal {
     constructor(attr: InputParameterTerminalArgs) {
         super(attr);
         this.type = attr.type;
-        this.getConnectedTerminals().map((other) => this.setDefaultMapOver(other));
+        this.getStepMapOver();
     }
 
     effectiveType(parameterType: string) {
@@ -490,7 +515,7 @@ export class InputCollectionTerminal extends BaseInputTerminal {
         if (!this.collectionTypes.length) {
             this.collectionTypes.push(ANY_COLLECTION_TYPE_DESCRIPTION);
         }
-        this.getConnectedTerminals().map((other) => this.setDefaultMapOver(other));
+        this.getStepMapOver();
     }
     _effectiveMapOver(otherCollectionType: CollectionTypeDescriptor) {
         const collectionTypes = this.collectionTypes;
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 95e4fbe687c..655f6735c7d 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -8,6 +8,7 @@ interface State {
     steps: { [index: string]: Step };
     stepIndex: number;
     stepMapOver: { [index: number]: CollectionTypeDescriptor };
+    stepInputMapOver: StepInputMapOver;
 }
 
 interface StepPosition {
@@ -133,10 +134,15 @@ interface WorkflowOutputs {
     };
 }
 
+interface StepInputMapOver {
+    [index: number]: { [index: string]: CollectionTypeDescriptor };
+}
+
 export const useWorkflowStepStore = defineStore("workflowStepStore", {
     state: (): State => ({
         steps: {} as Steps,
         stepMapOver: {} as { [index: number]: CollectionTypeDescriptor },
+        stepInputMapOver: {} as StepInputMapOver,
         stepIndex: -1,
     }),
     getters: {
@@ -211,7 +217,17 @@ export const useWorkflowStepStore = defineStore("workflowStepStore", {
             this.steps[step.id.toString()] = step;
         },
         changeStepMapOver(stepId: number, mapOver: CollectionTypeDescriptor) {
-            this.stepMapOver[stepId] = mapOver;
+            Vue.set(this.stepMapOver, stepId, mapOver);
+        },
+        resetStepInputMapOver(stepId: number) {
+            Vue.set(this.stepInputMapOver, stepId, {});
+        },
+        changeStepInputMapOver(stepId: number, inputName: string, mapOver: CollectionTypeDescriptor) {
+            if (this.stepInputMapOver[stepId]) {
+                Vue.set(this.stepInputMapOver[stepId], inputName, mapOver);
+            } else {
+                Vue.set(this.stepInputMapOver, stepId, { [inputName]: mapOver });
+            }
         },
         addConnection(connection: Connection) {
             const inputStep = this.getStep(connection.input.stepId);

From a6456b4c3b766587063e1044eef594f6732930f1 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 26 Jan 2023 13:30:04 +0100
Subject: [PATCH 295/350] Add test for connecting to non-mapped over input

---
 .../Workflow/Editor/modules/terminals.test.ts | 71 ++++++++++++++-----
 1 file changed, 55 insertions(+), 16 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index dd46474b686..3c18f160e8d 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -271,28 +271,67 @@ describe("canAccept", () => {
         // TODO: avoid this if possible ...
         expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         expect(dataIn.localMapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+        expect(dataIn.localMapOver.isCollection).toBe(true);
         expect(dataIn.canAccept(simpleDataOut).canAccept).toBe(false);
         expect(dataIn.canAccept(simpleDataOut).reason).toBe(
             "Cannot attach non-collection output to mapped over input, consider disconnecting inputs and outputs to reset this input's mapping."
         );
-    });
-    // TODO: test mapOver reset when constraint removed
-    it("resets mapOver when constraint is lifted", () => {
-        const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
-        const dataIn = terminals["simple data"]["input"] as InputTerminal;
-        const dataOut = terminals["simple data"]["out_file1"] as OutputTerminal;
-        const dataInTwo = terminals["simple data 2"]["input"] as InputTerminal;
-        dataIn.connect(collectionOut);
-        dataInTwo.connect(dataOut);
-        expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
-        //
-        dataIn.disconnect(collectionOut);
-        // this is weird and not particularly robust, if you save and reload this will most likely not be constrained
-        // TODO: avoid this if possible ...
-        expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         dataInTwo.disconnect(dataOut);
-        expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);
+        // terminal isn't a reactive class in any way (worth a thought doing, but difficult!), the following happens when a new terminal is built
+        // in useTerminal.ts
+        const rebuiltDataIn = terminalFactory(
+            dataIn.stepId,
+            advancedSteps[dataIn.stepId].inputs[0],
+            testDatatypesMapper
+        );
+        expect(rebuiltDataIn.localMapOver.isCollection).toBe(false);
+        expect(rebuiltDataIn.canAccept(simpleDataOut).canAccept).toBe(true);
     });
+    it("accepts attaching dataset to non-mapped over input for a mapped over step", () => {
+        const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
+        const simpleDataOut = terminals["data input"]["output"] as OutputTerminal;
+        const otherDataIn = terminals["simple data"]["input"] as InputTerminal;
+        const multiSimpleInputOne = terminals["multiple simple data"]["input1"] as InputTerminal;
+        const multiSimpleInputTwo = terminals["multiple simple data"]["queries_0|input2"] as InputTerminal;
+        const multiSimpleOut = terminals["multiple simple data"]["out_file1"] as OutputTerminal;
+        // map over simple input
+        multiSimpleInputOne.connect(collectionOut);
+        // constrain input by connecting an output to same step
+        otherDataIn.connect(multiSimpleOut);
+        // can connect a simple input to the non mapped-over input of the mapped-over step
+        expect(multiSimpleInputTwo.canAccept(simpleDataOut).canAccept).toBe(true);
+        // can also connect a connection of the same map over state
+        expect(multiSimpleInputTwo.canAccept(collectionOut).canAccept).toBe(true);
+        // cannot connect connection of deeper nesting
+        const listListOut = terminals["list:list input"]["output"] as OutputCollectionTerminal;
+        expect(multiSimpleInputTwo.canAccept(listListOut).canAccept).toBe(false);
+        expect(multiSimpleInputTwo.canAccept(listListOut).reason).toBe(
+            "Can't map over this input with output collection type - other inputs have an incompatible map over collection type. Disconnect inputs (and potentially outputs) and retry."
+        );
+        // disconnect, map over should be maintained
+        multiSimpleInputOne.disconnect(collectionOut);
+        expect(multiSimpleInputOne.localMapOver.isCollection).toBe(true);
+        expect(multiSimpleInputOne.canAccept(simpleDataOut).canAccept).toBe(false);
+        expect(multiSimpleInputOne.canAccept(simpleDataOut).reason).toBe(
+            "Cannot attach non-collection output to mapped over input, consider disconnecting inputs and outputs to reset this input's mapping."
+        );
+    }),
+        it("resets mapOver when constraint is lifted", () => {
+            const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
+            const dataIn = terminals["simple data"]["input"] as InputTerminal;
+            const dataOut = terminals["simple data"]["out_file1"] as OutputTerminal;
+            const dataInTwo = terminals["simple data 2"]["input"] as InputTerminal;
+            dataIn.connect(collectionOut);
+            dataInTwo.connect(dataOut);
+            expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+            //
+            dataIn.disconnect(collectionOut);
+            // this is weird and not particularly robust, if you save and reload this will most likely not be constrained
+            // TODO: avoid this if possible ...
+            expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+            dataInTwo.disconnect(dataOut);
+            expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);
+        });
     it("rejects connecting incompatible connection types", () => {
         const pairedOut = terminals["paired input"]["output"] as OutputCollectionTerminal;
         const collectionIn = terminals["list collection input"]["input1"] as InputCollectionTerminal;

From 83f6463e46a0d2c6d88e02ca01af6a81994e2953 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 26 Jan 2023 09:04:45 -0500
Subject: [PATCH 296/350] Minor touchups to client readme

---
 client/README.md | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/client/README.md b/client/README.md
index 3045a31b16a..8b015c9ce7e 100644
--- a/client/README.md
+++ b/client/README.md
@@ -93,16 +93,16 @@ prefer:
 
 ## Changing Styles/CSS
 
-Galaxy uses Sass for globally applied styling, which is a superset of CSS that compiles down
-to regular CSS. Most Galaxy styling source (.scss) files are kept in
-`client/src/style/scss`. There are additional style blocks alongside some Vue
-components -- styles that are particular to that individual component and do not
+Galaxy uses Sass for globally applied styling, which is a superset of CSS that
+compiles down to regular CSS. Most Galaxy styling source (.scss) files are kept
+in `client/src/style/scss`. Many components will also have local style blocks
+containing styles that are particular to that individual component and do not
 apply site-wide.
 
 On build, the compiled css bundle is served at `/static/style/base.css`.
 
-As mentioned above, `make client` will rebuild styles, as a part of the webpack
-build. For iterative development, "Watch Mode" rebuilds as described above do
+As mentioned above, `make client` will rebuild styles as a part of the webpack
+build. For iterative development "Watch Mode" rebuilds as described above do
 include style changes.
 
 ## Client-Side Unit Testing

From becd483b5062470d06598558208e337d396f0815 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 26 Jan 2023 09:38:51 -0500
Subject: [PATCH 297/350] Fix test definition

---
 .../Workflow/Editor/modules/terminals.test.ts | 34 +++++++++----------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 3c18f160e8d..1ab09b97a25 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -315,23 +315,23 @@ describe("canAccept", () => {
         expect(multiSimpleInputOne.canAccept(simpleDataOut).reason).toBe(
             "Cannot attach non-collection output to mapped over input, consider disconnecting inputs and outputs to reset this input's mapping."
         );
-    }),
-        it("resets mapOver when constraint is lifted", () => {
-            const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
-            const dataIn = terminals["simple data"]["input"] as InputTerminal;
-            const dataOut = terminals["simple data"]["out_file1"] as OutputTerminal;
-            const dataInTwo = terminals["simple data 2"]["input"] as InputTerminal;
-            dataIn.connect(collectionOut);
-            dataInTwo.connect(dataOut);
-            expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
-            //
-            dataIn.disconnect(collectionOut);
-            // this is weird and not particularly robust, if you save and reload this will most likely not be constrained
-            // TODO: avoid this if possible ...
-            expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
-            dataInTwo.disconnect(dataOut);
-            expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);
-        });
+    });
+    it("resets mapOver when constraint is lifted", () => {
+        const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
+        const dataIn = terminals["simple data"]["input"] as InputTerminal;
+        const dataOut = terminals["simple data"]["out_file1"] as OutputTerminal;
+        const dataInTwo = terminals["simple data 2"]["input"] as InputTerminal;
+        dataIn.connect(collectionOut);
+        dataInTwo.connect(dataOut);
+        expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+        //
+        dataIn.disconnect(collectionOut);
+        // this is weird and not particularly robust, if you save and reload this will most likely not be constrained
+        // TODO: avoid this if possible ...
+        expect(dataIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
+        dataInTwo.disconnect(dataOut);
+        expect(dataIn.mapOver).toEqual(NULL_COLLECTION_TYPE_DESCRIPTION);
+    });
     it("rejects connecting incompatible connection types", () => {
         const pairedOut = terminals["paired input"]["output"] as OutputCollectionTerminal;
         const collectionIn = terminals["list collection input"]["input1"] as InputCollectionTerminal;

From 8118c1906e9f86a1e00e921ff25bda0304c200e0 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Thu, 26 Jan 2023 15:54:11 +0100
Subject: [PATCH 298/350] Don't display tooltip of connection is acceptable

---
 .../src/components/Workflow/Editor/modules/terminals.test.ts | 2 ++
 client/src/components/Workflow/Editor/modules/terminals.ts   | 5 +++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 4d41492bc86..5abb667c019 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -205,6 +205,8 @@ describe("canAccept", () => {
         const integerInputParam = terminals["multi data"]["advanced|advanced_threshold"] as InputParameterTerminal;
         const integerOutputParam = terminals["integer parameter input"]["output"] as OutputParameterTerminal;
         expect(integerInputParam.canAccept(integerOutputParam).canAccept).toBe(true);
+        // regression test for https://github.com/galaxyproject/galaxy/issues/15417
+        expect(integerInputParam.canAccept(integerOutputParam).reason).toBe(null);
     });
     it("rejects text to integer parameter connection", () => {
         const integerInputParam = terminals["multi data"]["advanced|advanced_threshold"] as InputParameterTerminal;
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 4efe198c526..eff12488333 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -465,9 +465,10 @@ export class InputParameterTerminal extends BaseInputTerminal {
         const effectiveThisType = this.effectiveType(this.type);
         const otherType = ("type" in other && other.type) || "data";
         const effectiveOtherType = this.effectiveType(otherType);
+        const canAccept = effectiveThisType === effectiveOtherType
         return new ConnectionAcceptable(
-            effectiveThisType == effectiveOtherType,
-            `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
+            canAccept,
+            canAccept ? null: `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
         );
     }
 }

From addc0159f043d92fcb7952ea66f076b084d5a44d Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 26 Jan 2023 09:56:11 -0500
Subject: [PATCH 299/350] Commas are confusing

---
 client/README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/client/README.md b/client/README.md
index 8b015c9ce7e..aec3f0f8622 100644
--- a/client/README.md
+++ b/client/README.md
@@ -102,7 +102,7 @@ apply site-wide.
 On build, the compiled css bundle is served at `/static/style/base.css`.
 
 As mentioned above, `make client` will rebuild styles as a part of the webpack
-build. For iterative development "Watch Mode" rebuilds as described above do
+build. For iterative development, "Watch Mode" rebuilds as described above do
 include style changes.
 
 ## Client-Side Unit Testing
@@ -139,7 +139,7 @@ directory. This is what happens during a complete client build.
 
 During client-side development, it is more convenient to have granular testing
 options. The various testing scripts are defined inside package.json within the
-client folder, and are called with `yarn` as demonstrated in the following
+client folder and are called with `yarn` as demonstrated in the following
 commands.
 
 This is what CI is going to run, and also what 'make client-test' invokes,

From f4cebe9a66227fe45d8ebc171def5e57d8766ac8 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Thu, 26 Jan 2023 10:28:36 -0500
Subject: [PATCH 300/350] Sort tool sections in a way that works for both
 Chrome and Firefox. We should refactor this whole thing and pull the state
 into a separate store.

---
 .../src/components/Panels/Common/ToolSection.vue | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/client/src/components/Panels/Common/ToolSection.vue b/client/src/components/Panels/Common/ToolSection.vue
index f02fc438f18..c57738e49e3 100644
--- a/client/src/components/Panels/Common/ToolSection.vue
+++ b/client/src/components/Panels/Common/ToolSection.vue
@@ -137,9 +137,19 @@ export default {
                 this.config.toolbox_auto_sort === true &&
                 !this.category.elems.some((el) => el.text !== undefined && el.text !== "")
             ) {
-                return Object.entries(
-                    [...this.category.elems].sort((a, b) => a.name.toLowerCase() > b.name.toLowerCase())
-                );
+                const elements = [...this.category.elems];
+                const sorted = elements.sort((a, b) => {
+                    const aNameLower = a.name.toLowerCase();
+                    const bNameLower = b.name.toLowerCase();
+                    if (aNameLower > bNameLower) {
+                        return 1;
+                    } else if (aNameLower < bNameLower) {
+                        return -1;
+                    } else {
+                        return 0;
+                    }
+                });
+                return Object.entries(sorted);
             } else {
                 return Object.entries(this.category.elems);
             }

From c3cbb6fdf77d4b79469715a2e9397143aab056ae Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Thu, 26 Jan 2023 10:26:10 -0500
Subject: [PATCH 301/350] Bug fixes for URL handling in test_drs...

---
 lib/galaxy_test/api/test_drs.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/lib/galaxy_test/api/test_drs.py b/lib/galaxy_test/api/test_drs.py
index 81d77dee25b..f942c7761e2 100644
--- a/lib/galaxy_test/api/test_drs.py
+++ b/lib/galaxy_test/api/test_drs.py
@@ -4,7 +4,10 @@ from typing import (
     List,
 )
 from unittest import SkipTest
-from urllib.parse import urlparse
+from urllib.parse import (
+    urljoin,
+    urlparse,
+)
 
 import requests
 
@@ -31,18 +34,18 @@ class TestDrsApi(ApiTestCase):
         self.dataset_populator = DatasetPopulator(self.galaxy_interactor)
 
     def test_service_info(self):
-        api_url = f"{self.url}ga4gh/drs/v1/service-info"
+        api_url = self._url_join("ga4gh/drs/v1/service-info")
         info_response = requests.get(api_url)
         info_response.raise_for_status()
 
-    def test_404_on_private_datsets(self):
+    def test_404_on_private_datasets(self):
         history_id = self.dataset_populator.new_history()
         hda = self.dataset_populator.new_dataset(history_id, content=CONTENT, wait=True)
         dataset_id = hda["id"]
         drs_id = hda["drs_id"]
         self.dataset_populator.make_private(history_id=history_id, dataset_id=dataset_id)
         for method in HTTP_METHODS:
-            api_url = f"{self.url}ga4gh/drs/v1/objects/{drs_id}"
+            api_url = self._url_join(f"ga4gh/drs/v1/objects/{drs_id}")
             show_response = method(api_url)
             assert show_response.status_code == 403
 
@@ -52,7 +55,7 @@ class TestDrsApi(ApiTestCase):
         drs_id = hda["drs_id"]
         for method in HTTP_METHODS:
             for _ in range(10):
-                api_url = f"{self.url}ga4gh/drs/v1/objects/{drs_id}"
+                api_url = self._url_join(f"ga4gh/drs/v1/objects/{drs_id}")
                 show_response = method(api_url)
                 show_response.raise_for_status()
                 if show_response.status_code != 202:
@@ -102,10 +105,13 @@ class TestDrsApi(ApiTestCase):
         drs_id = hda["drs_id"]
 
         for method in HTTP_METHODS:
-            api_url = f"{self.url}ga4gh/drs/v1/objects/{drs_id}/access/fakeid"
+            api_url = self._url_join(f"ga4gh/drs/v1/objects/{drs_id}/access/fakeid")
             error_response = method(api_url)
             assert type(error_response.status_code) == int
             assert error_response.status_code == 404
             error_as_dict = error_response.json()
             assert "status_code" in error_as_dict
             assert "msg" in error_as_dict
+
+    def _url_join(self, suffix):
+        return urljoin(self.url, suffix)

From 9ed8bc717b14091ba48931d3440925751a7a5813 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Wed, 25 Jan 2023 10:02:39 -0500
Subject: [PATCH 302/350] Decorate API user tests properly.

---
 lib/galaxy_test/api/test_authenticate.py      |  2 ++
 .../api/test_dataset_collections.py           |  3 +++
 lib/galaxy_test/api/test_histories.py         | 11 ++++++++++
 lib/galaxy_test/api/test_history_contents.py  | 15 +++++++++++++
 lib/galaxy_test/api/test_users.py             | 22 +++++++++++++++++++
 lib/galaxy_test/base/decorators.py            |  6 +++++
 lib/galaxy_test/selenium/test_anon_history.py |  3 +++
 7 files changed, 62 insertions(+)

diff --git a/lib/galaxy_test/api/test_authenticate.py b/lib/galaxy_test/api/test_authenticate.py
index a63ae40bed6..41f437d4913 100644
--- a/lib/galaxy_test/api/test_authenticate.py
+++ b/lib/galaxy_test/api/test_authenticate.py
@@ -4,6 +4,7 @@ from requests import get
 
 from galaxy_test.base.api_util import baseauth_headers
 from galaxy_test.base.decorators import requires_new_user
+from galaxy_test.base.populators import skip_without_tool
 from ._framework import ApiTestCase
 
 TEST_USER_EMAIL = "auth_user_test@bx.psu.edu"
@@ -26,6 +27,7 @@ class TestAuthenticateApi(ApiTestCase):
         random_api_response = get(random_api_url, params=dict(key=auth_dict["api_key"]))
         self._assert_status_code_is(random_api_response, 200)
 
+    @skip_without_tool("test_data_source")
     def test_tool_runner_session_cookie_handling(self):
         response = get(self.url)
         tool_runner_session_cookie = response.cookies["galaxytoolrunnersession"]
diff --git a/lib/galaxy_test/api/test_dataset_collections.py b/lib/galaxy_test/api/test_dataset_collections.py
index 0798c809da8..af218d8a096 100644
--- a/lib/galaxy_test/api/test_dataset_collections.py
+++ b/lib/galaxy_test/api/test_dataset_collections.py
@@ -4,6 +4,7 @@ from typing import List
 
 from galaxy.util.unittest_utils import skip_if_github_down
 from galaxy_test.base.api_asserts import assert_object_id_error
+from galaxy_test.base.decorators import requires_new_user
 from galaxy_test.base.populators import (
     DatasetCollectionPopulator,
     DatasetPopulator,
@@ -181,6 +182,7 @@ class TestDatasetCollectionsApi(ApiTestCase):
             namelist = archive.namelist()
             assert len(namelist) == 3, f"Expected 3 elements in [{namelist}]"
 
+    @requires_new_user
     def test_hda_security(self):
         with self.dataset_populator.test_history(require_new=False) as history_id:
             element_identifiers = self.dataset_collection_populator.pair_identifiers(history_id)
@@ -374,6 +376,7 @@ class TestDatasetCollectionsApi(ApiTestCase):
     def _download_dataset_collection(self, history_id: str, hdca_id: str):
         return self._get(f"histories/{history_id}/contents/dataset_collections/{hdca_id}/download")
 
+    @requires_new_user
     def test_collection_contents_security(self, history_id):
         # request contents on an hdca that doesn't belong to user
         hdca, contents_url = self._create_collection_contents_pair(history_id)
diff --git a/lib/galaxy_test/api/test_histories.py b/lib/galaxy_test/api/test_histories.py
index b4ab38be3ff..3e0ffae41dc 100644
--- a/lib/galaxy_test/api/test_histories.py
+++ b/lib/galaxy_test/api/test_histories.py
@@ -11,6 +11,10 @@ from galaxy.model.unittest_utils.store_fixtures import (
 )
 from galaxy_test.api.sharable import SharingApiTests
 from galaxy_test.base.api_asserts import assert_has_keys
+from galaxy_test.base.decorators import (
+    requires_admin,
+    requires_new_user,
+)
 from galaxy_test.base.populators import (
     DatasetCollectionPopulator,
     DatasetPopulator,
@@ -249,6 +253,7 @@ class TestHistoriesApi(ApiTestCase, BaseHistories):
         create_response = self._post("histories", data=post_data, anon=True)
         self._assert_status_code_is(create_response, 403)
 
+    @requires_admin
     def test_create_without_session_fails(self):
         post_data = dict(name="SessionNeeded")
         # Using admin=True will boostrap an Admin user without session
@@ -581,6 +586,7 @@ class TestSharingHistory(ApiTestCase, BaseHistories, SharingApiTests):
         super().setUp()
         self.dataset_populator = DatasetPopulator(self.galaxy_interactor)
 
+    @requires_new_user
     def test_sharing_with_private_datasets(self):
         history_id = self.dataset_populator.new_history()
         hda = self.dataset_populator.new_dataset(history_id)
@@ -607,6 +613,8 @@ class TestSharingHistory(ApiTestCase, BaseHistories, SharingApiTests):
         assert sharing_response["users_shared_with"]
         assert sharing_response["users_shared_with"][0]["id"] == target_user_id
 
+    @requires_admin
+    @requires_new_user
     def test_sharing_without_manage_permissions(self):
         history_id = self.dataset_populator.new_history()
         hda = self.dataset_populator.new_dataset(history_id)
@@ -649,6 +657,7 @@ class TestSharingHistory(ApiTestCase, BaseHistories, SharingApiTests):
         assert sharing_response["users_shared_with"]
         assert sharing_response["users_shared_with"][0]["id"] == target_user_id
 
+    @requires_new_user
     def test_sharing_empty_not_allowed(self):
         history_id = self.dataset_populator.new_history()
 
@@ -661,6 +670,7 @@ class TestSharingHistory(ApiTestCase, BaseHistories, SharingApiTests):
         assert sharing_response["errors"]
         assert "empty" in sharing_response["errors"][0]
 
+    @requires_new_user
     def test_sharing_with_duplicated_users(self):
         history_id = self.create("HistoryToShareWithDuplicatedUser")
 
@@ -674,6 +684,7 @@ class TestSharingHistory(ApiTestCase, BaseHistories, SharingApiTests):
         assert len(sharing_response["users_shared_with"]) == 1
         assert sharing_response["users_shared_with"][0]["id"] == target_user_id
 
+    @requires_new_user
     def test_sharing_private_history_makes_datasets_public(self):
         history_id = self.dataset_populator.new_history()
         hda = self.dataset_populator.new_dataset(history_id)
diff --git a/lib/galaxy_test/api/test_history_contents.py b/lib/galaxy_test/api/test_history_contents.py
index a51528d96fe..de9267a9a10 100644
--- a/lib/galaxy_test/api/test_history_contents.py
+++ b/lib/galaxy_test/api/test_history_contents.py
@@ -7,6 +7,12 @@ from typing import (
 )
 
 from galaxy_test.api._framework import ApiTestCase
+from galaxy_test.base.decorators import (
+    requires_admin,
+    requires_celery,
+    requires_new_library,
+    requires_new_user,
+)
 from galaxy_test.base.populators import (
     DatasetCollectionPopulator,
     DatasetPopulator,
@@ -35,6 +41,7 @@ class TestHistoryContentsApi(ApiTestCase):
         hda_summary = self.__check_for_hda(contents_response, hda1)
         assert "display_types" not in hda_summary  # Quick summary, not full details
 
+    @requires_admin
     def test_make_private_and_public(self, history_id):
         hda1 = self._wait_for_new_hda(history_id)
         update_url = f"histories/{history_id}/contents/{hda1['id']}/permissions"
@@ -64,9 +71,11 @@ class TestHistoryContentsApi(ApiTestCase):
         self._assert_status_code_is(update_response, 200)
         self._assert_other_user_can_access(history_id, hda1["id"])
 
+    @requires_new_user
     def test_set_permissions_add_admin_history_contents(self, history_id):
         self._verify_dataset_permissions(history_id, "history_contents")
 
+    @requires_new_user
     def test_set_permissions_add_admin_datasets(self, history_id):
         self._verify_dataset_permissions(history_id, "dataset")
 
@@ -204,6 +213,7 @@ class TestHistoryContentsApi(ApiTestCase):
         inheritance_chain = inheritance_chain_response.json()
         assert len(inheritance_chain) == 1
 
+    @requires_new_library
     def test_library_copy(self, history_id):
         ld = self.library_populator.new_library_dataset("lda_test_library")
         create_data = dict(
@@ -591,6 +601,7 @@ class TestHistoryContentsApi(ApiTestCase):
 
         return element0["object"], element1["object"]
 
+    @requires_new_library
     def test_hdca_from_library_datasets(self, history_id):
         ld = self.library_populator.new_library_dataset("el1")
         ldda_id = ld["ldda_id"]
@@ -612,6 +623,7 @@ class TestHistoryContentsApi(ApiTestCase):
         assert hda["copied_from_ldda_id"] == ldda_id
         assert hda["history_id"] == history_id
 
+    @requires_new_library
     def test_hdca_from_inaccessible_library_datasets(self, history_id):
         library, library_dataset = self.library_populator.new_library_dataset_in_private_library(
             "HDCACreateInaccesibleLibrary"
@@ -943,6 +955,7 @@ class TestHistoryContentsApiBulkOperation(ApiTestCase):
                 if item["history_content_type"] == "dataset":
                     self.dataset_populator.wait_for_purge(history_id=history_id, content_id=item["id"])
 
+    @requires_new_user
     def test_only_owner_can_apply_bulk_operations(self):
         with self.dataset_populator.test_history() as history_id:
             self._create_test_history_contents(history_id)
@@ -993,6 +1006,7 @@ class TestHistoryContentsApiBulkOperation(ApiTestCase):
                     for expected_tag in expected_tags:
                         assert expected_tag in item["tags"]
 
+    @requires_celery
     def test_bulk_dbkey_change(self):
         with self.dataset_populator.test_history() as history_id:
             _, _, history_contents = self._create_test_history_contents(history_id)
@@ -1015,6 +1029,7 @@ class TestHistoryContentsApiBulkOperation(ApiTestCase):
                 if item["history_content_type"] == "dataset":
                     assert item["dbkey"] == expected_dbkey
 
+    @requires_celery
     def test_bulk_dbkey_change_dataset_collection(self):
         with self.dataset_populator.test_history() as history_id:
             _, collection_ids, history_contents = self._create_test_history_contents(history_id)
diff --git a/lib/galaxy_test/api/test_users.py b/lib/galaxy_test/api/test_users.py
index fc17dea745a..186bd039a77 100644
--- a/lib/galaxy_test/api/test_users.py
+++ b/lib/galaxy_test/api/test_users.py
@@ -8,6 +8,10 @@ from requests import (
 
 from galaxy_test.api._framework import ApiTestCase
 from galaxy_test.base.api_asserts import assert_object_id_error
+from galaxy_test.base.decorators import (
+    requires_admin,
+    requires_new_user,
+)
 from galaxy_test.base.populators import skip_without_tool
 
 TEST_USER_EMAIL = "user_for_users_index_test@bx.psu.edu"
@@ -17,6 +21,8 @@ TEST_USER_EMAIL_UNDELETE = "user_for_undelete_test@bx.psu.edu"
 
 
 class TestUsersApi(ApiTestCase):
+    @requires_admin
+    @requires_new_user
     def test_index(self):
         self._setup_user(TEST_USER_EMAIL)
         all_users_response = self._get("users", admin=True)
@@ -28,6 +34,7 @@ class TestUsersApi(ApiTestCase):
         # new user.
         assert len(all_users) > 1
 
+    @requires_new_user
     def test_index_only_self_for_nonadmins(self):
         self._setup_user(TEST_USER_EMAIL)
         with self._different_user():
@@ -35,6 +42,7 @@ class TestUsersApi(ApiTestCase):
             # Non admin users can only see themselves
             assert len(all_users_response.json()) == 1
 
+    @requires_new_user
     def test_show(self):
         user = self._setup_user(TEST_USER_EMAIL)
         with self._different_user(email=TEST_USER_EMAIL):
@@ -42,6 +50,7 @@ class TestUsersApi(ApiTestCase):
             self._assert_status_code_is(show_response, 200)
             self.__assert_matches_user(user, show_response.json())
 
+    @requires_new_user
     def test_update(self):
         new_name = "linnaeus"
         user = self._setup_user(TEST_USER_EMAIL)
@@ -68,6 +77,8 @@ class TestUsersApi(ApiTestCase):
             update_response = put(update_url, data=json.dumps(dict(username=new_name)))
             assert_object_id_error(update_response)
 
+    @requires_admin
+    @requires_new_user
     def test_admin_update(self):
         new_name = "flexo"
         user = self._setup_user(TEST_USER_EMAIL)
@@ -77,12 +88,16 @@ class TestUsersApi(ApiTestCase):
         update_json = update_response.json()
         assert update_json["username"] == new_name
 
+    @requires_admin
+    @requires_new_user
     def test_delete_user(self):
         user = self._setup_user(TEST_USER_EMAIL_DELETE)
         self._delete(f"users/{user['id']}", admin=True)
         updated_user = self._get(f"users/deleted/{user['id']}", admin=True).json()
         assert updated_user["deleted"] is True, updated_user
 
+    @requires_admin
+    @requires_new_user
     def test_purge_user(self):
         """Delete user and then purge them."""
         user = self._setup_user(TEST_USER_EMAIL_PURGE)
@@ -96,6 +111,8 @@ class TestUsersApi(ApiTestCase):
         assert purged_user["deleted"] is True, purged_user
         assert purged_user["purged"] is True, purged_user
 
+    @requires_admin
+    @requires_new_user
     def test_undelete_user(self):
         """Delete user and then undelete them."""
         user = self._setup_user(TEST_USER_EMAIL_UNDELETE)
@@ -107,6 +124,7 @@ class TestUsersApi(ApiTestCase):
         undeleted_user = self._get(f"users/{user['id']}", admin=True).json()
         assert undeleted_user["deleted"] is False, undeleted_user
 
+    @requires_new_user
     def test_information(self):
         user = self._setup_user(TEST_USER_EMAIL)
         url = self.__url("information/inputs", user)
@@ -126,6 +144,7 @@ class TestUsersApi(ApiTestCase):
         assert len(response["addresses"]) == 1
         assert response["addresses"][0]["desc"] == "_desc"
 
+    @requires_new_user
     def test_manage_api_key(self):
         with self._different_user("manage-api-key-test@user.com"):
             user_id = self._get_current_user_id()
@@ -150,6 +169,7 @@ class TestUsersApi(ApiTestCase):
             assert new_api_key
             assert new_api_key != user_api_key
 
+    @requires_new_user
     def test_only_admin_can_manage_other_users_api_key(self):
         with self._different_user():
             other_user_id = self._get_current_user_id()
@@ -171,6 +191,8 @@ class TestUsersApi(ApiTestCase):
         response = self._delete(f"users/{other_user_id}/api_key", admin=True)
         self._assert_status_code_is_ok(response)
 
+    @requires_admin
+    @requires_new_user
     @skip_without_tool("cat1")
     def test_favorites(self):
         user = self._setup_user(TEST_USER_EMAIL)
diff --git a/lib/galaxy_test/base/decorators.py b/lib/galaxy_test/base/decorators.py
index 8e8be0b6c05..91613faa439 100644
--- a/lib/galaxy_test/base/decorators.py
+++ b/lib/galaxy_test/base/decorators.py
@@ -18,6 +18,7 @@ from typing_extensions import Literal
 
 KnownRequirementT = Union[
     Literal["admin"],
+    Literal["celery"],
     Literal["new_history"],
     Literal["new_library"],
     Literal["new_published_objects"],
@@ -92,9 +93,14 @@ def requires_admin(method):
     return _wrap_method_with_galaxy_requirement(method, "admin")
 
 
+def requires_celery(method):
+    return _wrap_method_with_galaxy_requirement(method, "celery")
+
+
 __all__ = (
     "has_requirement",
     "requires_admin",
+    "requires_celery",
     "requires_new_history",
     "requires_new_library",
     "requires_new_published_objects",
diff --git a/lib/galaxy_test/selenium/test_anon_history.py b/lib/galaxy_test/selenium/test_anon_history.py
index d8f7ab1329a..ab1ea2289c4 100644
--- a/lib/galaxy_test/selenium/test_anon_history.py
+++ b/lib/galaxy_test/selenium/test_anon_history.py
@@ -1,3 +1,4 @@
+from galaxy_test.base.decorators import requires_new_user
 from .framework import (
     selenium_test,
     SeleniumTestCase,
@@ -25,12 +26,14 @@ class TestAnonymousHistories(SeleniumTestCase):
         self.components.history_panel.empty_message.assert_absent_or_hidden()
 
     @selenium_test
+    @requires_new_user
     def test_anon_history_after_registration(self):
         self._upload_file_anonymous_then_register_user()
         self.home()
         self.history_panel_wait_for_hid_state(1, "ok")
 
     @selenium_test
+    @requires_new_user
     def test_clean_anon_history_after_logout(self):
         self._upload_file_anonymous_then_register_user()
         self.logout_if_needed()

From ab27741959a8ef08cf1bb9314959db8d1f3329b2 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Thu, 26 Jan 2023 10:33:28 -0500
Subject: [PATCH 303/350] Decorate more UI tests that require fresh histories.

Based on tests against usegalaxy.org.
---
 lib/galaxy_test/selenium/test_collection_builders.py       | 7 +++++++
 lib/galaxy_test/selenium/test_collection_edit.py           | 3 +++
 lib/galaxy_test/selenium/test_dataset_metadata_download.py | 2 ++
 lib/galaxy_test/selenium/test_history_dataset_state.py     | 5 +++++
 lib/galaxy_test/selenium/test_history_multi_view.py        | 2 ++
 5 files changed, 19 insertions(+)

diff --git a/lib/galaxy_test/selenium/test_collection_builders.py b/lib/galaxy_test/selenium/test_collection_builders.py
index 21f3c492d37..25b6d0afa0f 100644
--- a/lib/galaxy_test/selenium/test_collection_builders.py
+++ b/lib/galaxy_test/selenium/test_collection_builders.py
@@ -1,4 +1,5 @@
 from .framework import (
+    managed_history,
     selenium_test,
     SeleniumTestCase,
 )
@@ -9,6 +10,7 @@ class TestCollectionBuilders(SeleniumTestCase):
     ensure_registered = True
 
     @selenium_test
+    @managed_history
     def test_build_list_simple_hidden(self):
         self.perform_upload(self.get_filename("1.fasta"))
         self._wait_for_and_select([1])
@@ -19,6 +21,7 @@ class TestCollectionBuilders(SeleniumTestCase):
         self._wait_for_hid_visible(2)
 
     @selenium_test
+    @managed_history
     def test_build_list_and_show_items(self):
         self.perform_upload(self.get_filename("1.fasta"))
         self._wait_for_and_select([1])
@@ -32,6 +35,7 @@ class TestCollectionBuilders(SeleniumTestCase):
         self._wait_for_hid_visible(3)
 
     @selenium_test
+    @managed_history
     def test_build_pair_simple_hidden(self):
         self.perform_upload(self.get_filename("1.tabular"))
         self.perform_upload(self.get_filename("2.tabular"))
@@ -43,6 +47,7 @@ class TestCollectionBuilders(SeleniumTestCase):
         self._wait_for_hid_visible(3)
 
     @selenium_test
+    @managed_history
     def test_build_paired_list_simple(self):
         self.perform_upload(self.get_filename("1.tabular"))
         self.perform_upload(self.get_filename("2.tabular"))
@@ -61,6 +66,7 @@ class TestCollectionBuilders(SeleniumTestCase):
         self._wait_for_hid_visible(2)
 
     @selenium_test
+    @managed_history
     def test_build_paired_list_show_original(self):
         self.perform_upload(self.get_filename("1.tabular"))
         self.perform_upload(self.get_filename("2.tabular"))
@@ -85,6 +91,7 @@ class TestCollectionBuilders(SeleniumTestCase):
         self._wait_for_hid_visible(4)
 
     @selenium_test
+    @managed_history
     def test_build_simple_list_via_rules_hidden(self):
         self.perform_upload(self.get_filename("1.fasta"))
         self._wait_for_and_select([1])
diff --git a/lib/galaxy_test/selenium/test_collection_edit.py b/lib/galaxy_test/selenium/test_collection_edit.py
index 279724d97b9..73148a36816 100644
--- a/lib/galaxy_test/selenium/test_collection_edit.py
+++ b/lib/galaxy_test/selenium/test_collection_edit.py
@@ -1,4 +1,5 @@
 from .framework import (
+    managed_history,
     selenium_test,
     SeleniumTestCase,
 )
@@ -9,6 +10,7 @@ class TestCollectionEdit(SeleniumTestCase):
     ensure_registered = True
 
     @selenium_test
+    @managed_history
     def test_change_dbkey_simple_list(self):
         self.create_simple_list_collection()
         self.open_collection_edit_view()
@@ -23,6 +25,7 @@ class TestCollectionEdit(SeleniumTestCase):
         self.check_current_data_value(dataNew)
 
     @selenium_test
+    @managed_history
     def test_change_datatype_simple_list(self):
         self.create_simple_list_collection_txt()
         self.open_collection_edit_view()
diff --git a/lib/galaxy_test/selenium/test_dataset_metadata_download.py b/lib/galaxy_test/selenium/test_dataset_metadata_download.py
index 3df1e638dce..0a36a93078f 100644
--- a/lib/galaxy_test/selenium/test_dataset_metadata_download.py
+++ b/lib/galaxy_test/selenium/test_dataset_metadata_download.py
@@ -1,4 +1,5 @@
 from .framework import (
+    managed_history,
     selenium_test,
     SeleniumTestCase,
     UsesHistoryItemAssertions,
@@ -11,6 +12,7 @@ class TestHistoryDatasetState(SeleniumTestCase, UsesHistoryItemAssertions):
     ensure_registered = True
 
     @selenium_test
+    @managed_history
     def test_dataset_metadata_download(self):
         self._prepare_dataset()
         item = self.history_panel_item_component(hid=FIRST_HID)
diff --git a/lib/galaxy_test/selenium/test_history_dataset_state.py b/lib/galaxy_test/selenium/test_history_dataset_state.py
index e4b059ecff5..eae0342fc4f 100644
--- a/lib/galaxy_test/selenium/test_history_dataset_state.py
+++ b/lib/galaxy_test/selenium/test_history_dataset_state.py
@@ -4,6 +4,7 @@ from galaxy.model.unittest_utils.store_fixtures import (
     TEST_SOURCE_URI,
 )
 from .framework import (
+    managed_history,
     selenium_test,
     SeleniumTestCase,
     UsesHistoryItemAssertions,
@@ -26,6 +27,7 @@ class TestHistoryDatasetState(SeleniumTestCase, UsesHistoryItemAssertions):
     ensure_registered = True
 
     @selenium_test
+    @managed_history
     def test_dataset_state(self):
         self._prepare_dataset()
         self.history_panel_item_body_component(FIRST_HID, wait=True)
@@ -40,6 +42,7 @@ class TestHistoryDatasetState(SeleniumTestCase, UsesHistoryItemAssertions):
         self.screenshot("dataset_details_ok")
 
     @selenium_test
+    @managed_history
     def test_dataset_change_dbkey(self):
         item = self._prepare_dataset()
         self.assert_item_dbkey_displayed_as(FIRST_HID, "?")
@@ -57,6 +60,7 @@ class TestHistoryDatasetState(SeleniumTestCase, UsesHistoryItemAssertions):
         self.assert_item_dbkey_displayed_as(FIRST_HID, "apiMel3")
 
     @selenium_test
+    @managed_history
     def test_dataset_state_discarded(self):
         self.history_panel_create_new()
         history_id = self.current_history_id()
@@ -77,6 +81,7 @@ class TestHistoryDatasetState(SeleniumTestCase, UsesHistoryItemAssertions):
         self.screenshot("dataset_details_discarded")
 
     @selenium_test
+    @managed_history
     def test_dataset_state_deferred(self):
         self.history_panel_create_new()
         history_id = self.current_history_id()
diff --git a/lib/galaxy_test/selenium/test_history_multi_view.py b/lib/galaxy_test/selenium/test_history_multi_view.py
index 785c2c84f28..03db2c2c418 100644
--- a/lib/galaxy_test/selenium/test_history_multi_view.py
+++ b/lib/galaxy_test/selenium/test_history_multi_view.py
@@ -1,4 +1,5 @@
 from .framework import (
+    managed_history,
     selenium_test,
     SeleniumTestCase,
 )
@@ -22,6 +23,7 @@ class TestHistoryMultiView(SeleniumTestCase):
         self.screenshot("multi_history_collection")
 
     @selenium_test
+    @managed_history
     def test_list_list_display(self):
         history_id = self.current_history_id()
         method = self.dataset_collection_populator.create_list_of_list_in_history(history_id, wait=True).json

From 235ef39f16971e21f87ac327648b1873dc1f2a48 Mon Sep 17 00:00:00 2001
From: John Chilton <jmchilton@gmail.com>
Date: Tue, 24 Jan 2023 12:11:05 -0500
Subject: [PATCH 304/350] deployment testing

---
 .github/workflows/deployment.yaml  |  71 +++++++++++++++++++
 scripts/common_startup.sh          |  28 ++++----
 test/deployment/usegalaxystar.bash | 110 +++++++++++++++++++++++++++++
 3 files changed, 197 insertions(+), 12 deletions(-)
 create mode 100644 .github/workflows/deployment.yaml
 create mode 100644 test/deployment/usegalaxystar.bash

diff --git a/.github/workflows/deployment.yaml b/.github/workflows/deployment.yaml
new file mode 100644
index 00000000000..441f35e7167
--- /dev/null
+++ b/.github/workflows/deployment.yaml
@@ -0,0 +1,71 @@
+name: Deployment Tests
+on:
+  workflow_dispatch:
+    inputs:
+      target:
+        description: 'Galaxy Deployment to target'
+        required: true
+        default: 'usegalaxymain'
+        type: choice
+        options:
+        - usegalaxytest
+        - usegalaxymain
+        - usegalaxyeu
+      type:
+        description: 'Test type'
+        required: true
+        default: 'all'
+        type: choice
+        options:
+        - all
+        - api
+        - selenium
+      branch:
+        description: 'Branch of code to run from'
+        default: 'dev'
+        type: string        
+      debug:
+        required: true
+        description: 'Run deployment tests with debug mode on'
+        type: boolean
+jobs:
+  testdeployment:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.7']
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ inputs.branch }}
+          fetch-depth: 0
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Cache pip dir
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: pip-cache-${{ matrix.python-version }}-${{ hashFiles('requirements.txt') }}
+      - uses: nanasess/setup-chromedriver@v1
+      - name: Run tests
+        run: bash ./test/deployment/usegalaxystar.bash
+        env:
+          GALAXY_TEST_DEPLOYMENT_TARGET: ${{ inputs.target }}
+          GALAXY_TEST_DEPLOYMENT_DEBUG: ${{ inputs.debug }}
+          GALAXY_TEST_DEPLOYMENT_TEST_TYPE: ${{ inputs.type }}
+          GALAXY_TEST_USEGALAXYMAIN_USER_EMAIL: "jmchilton+test@gmail.com"
+          GALAXY_TEST_USEGALAXYMAIN_USER_PASSWORD: ${{ secrets.USEGALAXYMAIN_USER_PASSWORD }}
+          GALAXY_TEST_USEGALAXYMAIN_USER_KEY: ${{ secrets.USEGALAXYMAIN_USER_KEY }}
+          GALAXY_TEST_USEGALAXYTEST_USER_EMAIL: "jmchilton+test@gmail.com"
+          GALAXY_TEST_USEGALAXYTEST_USER_PASSWORD: ${{ secrets.USEGALAXYTEST_USER_PASSWORD }}
+          GALAXY_TEST_USEGALAXYTEST_USER_KEY: ${{ secrets.USEGALAXYTEST_USER_KEY }}
+          GALAXY_TEST_USEGALAXYEU_USER_EMAIL: "jmchilton+test@gmail.com"
+          GALAXY_TEST_USEGALAXYEU_USER_PASSWORD: ${{ secrets.USEGALAXYEU_USER_PASSWORD }}
+          GALAXY_TEST_USEGALAXYEU_USER_KEY: ${{ secrets.USEGALAXYEU_USER_KEY }}
+          GALAXY_TEST_TIMEOUT_MULTIPLIER: 10
+      - uses: actions/upload-artifact@v2
+        if: always()
+        with:
+          name: Deployment test results (${{ inputs.target }}, ${{ inputs.type }})
+          path: 'deployment_tests.html'
diff --git a/scripts/common_startup.sh b/scripts/common_startup.sh
index 48f1f936ec2..245421136da 100755
--- a/scripts/common_startup.sh
+++ b/scripts/common_startup.sh
@@ -17,6 +17,7 @@ FETCH_WHEELS=1
 CREATE_VENV=1
 COPY_SAMPLE_FILES=1
 SKIP_CLIENT_BUILD=${GALAXY_SKIP_CLIENT_BUILD:-0}
+SKIP_NODE=${GALAXY_SKIP_NODE:-0}
 INSTALL_PREBUILT_CLIENT=${GALAXY_INSTALL_PREBUILT_CLIENT:-0}
 NODE_VERSION=${GALAXY_NODE_VERSION:-"$(cat client/.node_version)"}
 YARN_INSTALL_OPTS=${YARN_INSTALL_OPTS:-"--network-timeout 300000 --check-files"}
@@ -29,6 +30,7 @@ for arg in "$@"; do
     [ "$arg" = "--stop-daemon" ] && FETCH_WHEELS=0
     [ "$arg" = "--skip-samples" ] && COPY_SAMPLE_FILES=0
     [ "$arg" = "--skip-client-build" ] && SKIP_CLIENT_BUILD=1
+    [ "$arg" = "--skip-node" ] && SKIP_NODE=1
 done
 
 SAMPLES="
@@ -198,19 +200,21 @@ if [ $FETCH_WHEELS -eq 1 ]; then
 fi
 
 # Install node if not installed
-if [ -n "$VIRTUAL_ENV" ]; then
-    if ! in_venv "$(command -v node)" || [ "$(node --version)" != "v${NODE_VERSION}" ]; then
-        echo "Installing node into $VIRTUAL_ENV with nodeenv."
-        if [ -d "${VIRTUAL_ENV}/lib/node_modules" ]; then
-            echo "Removing old ${VIRTUAL_ENV}/lib/node_modules directory."
-            rm -rf "${VIRTUAL_ENV}/lib/node_modules"
+if [ $SKIP_NODE -eq 0 ]; then
+    if [ -n "$VIRTUAL_ENV" ]; then
+        if ! in_venv "$(command -v node)" || [ "$(node --version)" != "v${NODE_VERSION}" ]; then
+            echo "Installing node into $VIRTUAL_ENV with nodeenv."
+            if [ -d "${VIRTUAL_ENV}/lib/node_modules" ]; then
+                echo "Removing old ${VIRTUAL_ENV}/lib/node_modules directory."
+                rm -rf "${VIRTUAL_ENV}/lib/node_modules"
+            fi
+            nodeenv -n "$NODE_VERSION" -p
+        fi
+    elif [ -n "$CONDA_DEFAULT_ENV" ] && [ -n "$CONDA_EXE" ]; then
+        if ! in_conda_env "$(command -v node)"; then
+            echo "Installing node into '$CONDA_DEFAULT_ENV' Conda environment with conda."
+            $CONDA_EXE install --yes --override-channels --channel conda-forge --name "$CONDA_DEFAULT_ENV" nodejs="$NODE_VERSION"
         fi
-        nodeenv -n "$NODE_VERSION" -p
-    fi
-elif [ -n "$CONDA_DEFAULT_ENV" ] && [ -n "$CONDA_EXE" ]; then
-    if ! in_conda_env "$(command -v node)"; then
-        echo "Installing node into '$CONDA_DEFAULT_ENV' Conda environment with conda."
-        $CONDA_EXE install --yes --override-channels --channel conda-forge --name "$CONDA_DEFAULT_ENV" nodejs="$NODE_VERSION"
     fi
 fi
 
diff --git a/test/deployment/usegalaxystar.bash b/test/deployment/usegalaxystar.bash
new file mode 100644
index 00000000000..7d7711c8657
--- /dev/null
+++ b/test/deployment/usegalaxystar.bash
@@ -0,0 +1,110 @@
+#!/bin/bash
+
+# Once-a-release deployment tests for usegalaxy*
+# This script is designed for use with .github/workflows/deployment.yaml,
+# a manually triggered GitHub Actions workflow.
+# The variables this script consumes include:
+# - GALAXY_TEST_DEPLOYMENT_TARGET
+#    target Galaxy deployment to test against - this should be
+#    usegalaxymain or usegalaxytest currently.
+# - GALAXY_TEST_DEPLOYMENT_DEBUG
+#    should be the string "true" to enable additional debugging
+# - GALAXY_TEST_USEGALAXYMAIN_USER_KEY
+#   GALAXY_TEST_USEGALAXYTEST_USER_KEY
+#    API key to select for given target.
+
+set -e
+
+echo "Deployment target is $GALAXY_TEST_DEPLOYMENT_TARGET"
+
+# Setup dependencies and activate resulting Python environment.
+./scripts/common_startup.sh --skip-client-build --skip-node
+. .venv/bin/activate
+
+if [ $GALAXY_TEST_DEPLOYMENT_DEBUG = "true" ];
+then
+    PYTEST_DEBUG_ARGS="-s -v"
+else
+    PYTEST_DEBUG_ARGS=""
+fi
+
+if [ "$GALAXY_TEST_DEPLOYMENT_TARGET" = "usegalaxymain" ];
+then
+    GALAXY_TEST_EXTERNAL="https://usegalaxy.org"
+    GALAXY_TEST_USER_API_KEY="$GALAXY_TEST_USEGALAXYMAIN_USER_KEY"
+    GALAXY_TEST_USER_EMAIL="$GALAXY_TEST_USEGALAXYMAIN_USER_EMAIL"
+    GALAXY_TEST_SELENIUM_USER_PASSWORD="$GALAXY_TEST_USEGALAXYMAIN_USER_PASSWORD"
+elif [ "$GALAXY_TEST_DEPLOYMENT_TARGET" = "usegalaxytest" ];
+then
+    GALAXY_TEST_EXTERNAL="https://test.galaxyproject.org"
+    GALAXY_TEST_USER_API_KEY="$GALAXY_TEST_USEGALAXYTEST_USER_KEY"
+    GALAXY_TEST_USER_EMAIL="$GALAXY_TEST_USEGALAXYTEST_USER_EMAIL"
+    GALAXY_TEST_SELENIUM_USER_PASSWORD="$GALAXY_TEST_USEGALAXYTEST_USER_PASSWORD"
+elif [ "$GALAXY_TEST_DEPLOYMENT_TARGET" = "usegalaxyeu" ];
+then
+    GALAXY_TEST_EXTERNAL="https://usegalaxy.eu"
+    GALAXY_TEST_USER_API_KEY="$GALAXY_TEST_USEGALAXYEU_USER_KEY"
+    GALAXY_TEST_USER_EMAIL="$GALAXY_TEST_USEGALAXYEU_USER_EMAIL"
+    GALAXY_TEST_SELENIUM_USER_PASSWORD="$GALAXY_TEST_USEGALAXYEU_USER_PASSWORD"
+else
+    echo "ERROR: Unknown deployment test target ${GALAXY_TEST_DEPLOYMENT_TARGET}"
+    exit 1
+fi
+export GALAXY_TEST_EXTERNAL
+export GALAXY_TEST_USER_API_KEY
+export GALAXY_TEST_USER_EMAIL
+GALAXY_TEST_SELENIUM_USER_EMAIL="$GALAXY_TEST_USER_EMAIL"
+export GALAXY_TEST_SELENIUM_USER_EMAIL
+export GALAXY_TEST_SELENIUM_USER_PASSWORD
+
+api_tests=(
+    lib/galaxy_test/api/test_datatypes.py
+    lib/galaxy_test/api/test_workflow_extraction.py
+    lib/galaxy_test/api/test_users.py
+    lib/galaxy_test/api/test_roles.py
+    lib/galaxy_test/api/test_authenticate.py
+    lib/galaxy_test/api/test_configuration.py
+    lib/galaxy_test/api/test_dataset_collections.py
+    lib/galaxy_test/api/test_display_applications.py
+    lib/galaxy_test/api/test_drs.py
+    lib/galaxy_test/api/test_folders.py
+    lib/galaxy_test/api/test_folder_contents.py
+    lib/galaxy_test/api/test_framework.py
+    lib/galaxy_test/api/test_histories.py
+    lib/galaxy_test/api/test_history_contents.py
+)
+selenium_tests=(
+    lib/galaxy_test/selenium/test_anon_history.py
+    lib/galaxy_test/selenium/test_collection_builders.py
+    lib/galaxy_test/selenium/test_dataset_metadata_download.py
+    lib/galaxy_test/selenium/test_collection_edit.py
+    lib/galaxy_test/selenium/test_history_copy_elements.py
+    lib/galaxy_test/selenium/test_history_dataset_state.py
+    lib/galaxy_test/selenium/test_history_multi_view.py
+)
+if [ "$GALAXY_TEST_DEPLOYMENT_TEST_TYPE" = "all" ];
+then
+    tests=("${api_tests[@]}" "${selenium_tests[@]}")
+elif [ "$GALAXY_TEST_DEPLOYMENT_TEST_TYPE" = "api" ];
+then
+    tests=("${api_tests[@]}")
+elif [ "$GALAXY_TEST_DEPLOYMENT_TEST_TYPE" = "selenium" ];
+then
+    tests=("${selenium_tests[@]}")
+else
+    echo "Unknown GALAXY_TEST_DEPLOYMENT_TEST_TYPE encountered ${GALAXY_TEST_DEPLOYMENT_TEST_TYPE}"
+    exit 1
+fi
+
+echo "Running tests: ${tests[@]}"
+# pytest markers to select against. In order to not cause an explosion of
+# semi-permanent artifacts that are difficult to manage tests which require
+# new libraries or users are disabled. Tests which require admin keys are
+# also disabled for security/simplicity reasons.
+PYTEST_MARKER_EXPRESSION="not requires_admin and not requires_new_library and not requires_new_user and not requires_celery"
+PYTEST_HTML_REPORT="deployment_tests.html"
+pytest \
+    $PYTEST_DEBUG_ARGS \
+    --html "$PYTEST_HTML_REPORT" \
+    -m "${PYTEST_MARKER_EXPRESSION}" \
+    "${tests[@]}"

From bf1938b1075633b2827aded350a5199a621a0289 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 15:03:07 -0500
Subject: [PATCH 305/350] Hide metadata auto-detection option if dataset is in
 improper state

---
 .../src/components/DatasetInformation/DatasetAttributes.vue   | 4 ++--
 lib/galaxy/webapps/galaxy/controllers/dataset.py              | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/client/src/components/DatasetInformation/DatasetAttributes.vue b/client/src/components/DatasetInformation/DatasetAttributes.vue
index dd942966dd0..fbb1aa44e52 100644
--- a/client/src/components/DatasetInformation/DatasetAttributes.vue
+++ b/client/src/components/DatasetInformation/DatasetAttributes.vue
@@ -20,12 +20,12 @@
                                 @click="submit('attribute', 'attributes')">
                                 <font-awesome-icon icon="save" class="mr-1" />{{ "Save" | l }}
                             </b-button>
-                            <b-button @click="submit('attribute', 'autodetect')">
+                            <b-button v-if="!result['metadata_disable']" @click="submit('attribute', 'autodetect')">
                                 <font-awesome-icon icon="redo" class="mr-1" />{{ "Auto-detect" | l }}
                             </b-button>
                         </div>
                     </b-tab>
-                    <b-tab v-if="!result['conversion_disable'] || !result['datatype_disable']">
+                    <b-tab v-if="(!result['conversion_disable'] || !result['datatype_disable']) && !result['metadata_disable']">
                         <template v-slot:title>
                             <span v-if="!result['conversion_disable']">
                                 <font-awesome-icon icon="cog" class="mr-1" />{{ "Convert" | l }}
diff --git a/lib/galaxy/webapps/galaxy/controllers/dataset.py b/lib/galaxy/webapps/galaxy/controllers/dataset.py
index 0473f7d2a1f..c496a8aedeb 100644
--- a/lib/galaxy/webapps/galaxy/controllers/dataset.py
+++ b/lib/galaxy/webapps/galaxy/controllers/dataset.py
@@ -291,6 +291,7 @@ class DatasetInterface(BaseUIController, UsesAnnotations, UsesItemRatings, UsesE
             if data.missing_meta():
                 message = 'Required metadata values are missing. Some of these values may not be editable by the user. Selecting "Auto-detect" will attempt to fix these values.'
                 status = "warning"
+            metadata_disable = data.state not in [trans.model.Dataset.states.OK, trans.model.Dataset.states.FAILED_METADATA]
             # datatype conversion
             conversion_options = [
                 (f"{convert_id} (using '{convert_name}')", convert_id)
@@ -369,6 +370,7 @@ class DatasetInterface(BaseUIController, UsesAnnotations, UsesItemRatings, UsesE
                 "message": message,
                 "status": status,
                 "dataset_id": dataset_id,
+                "metadata_disable": metadata_disable,
                 "attribute_inputs": attribute_inputs,
                 "conversion_inputs": conversion_inputs,
                 "conversion_disable": conversion_disable,

From ec7b8b01401e2eb3b4cfb74d4120e95efca8ddbd Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 15:09:09 -0500
Subject: [PATCH 306/350] Fix linting

---
 .../src/components/DatasetInformation/DatasetAttributes.vue | 6 +++++-
 client/src/components/Workflow/Editor/modules/terminals.ts  | 4 ++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/client/src/components/DatasetInformation/DatasetAttributes.vue b/client/src/components/DatasetInformation/DatasetAttributes.vue
index fbb1aa44e52..73874c5f601 100644
--- a/client/src/components/DatasetInformation/DatasetAttributes.vue
+++ b/client/src/components/DatasetInformation/DatasetAttributes.vue
@@ -25,7 +25,11 @@
                             </b-button>
                         </div>
                     </b-tab>
-                    <b-tab v-if="(!result['conversion_disable'] || !result['datatype_disable']) && !result['metadata_disable']">
+                    <b-tab
+                        v-if="
+                            (!result['conversion_disable'] || !result['datatype_disable']) &&
+                            !result['metadata_disable']
+                        ">
                         <template v-slot:title>
                             <span v-if="!result['conversion_disable']">
                                 <font-awesome-icon icon="cog" class="mr-1" />{{ "Convert" | l }}
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 1e354149ffa..9b145699bed 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -490,10 +490,10 @@ export class InputParameterTerminal extends BaseInputTerminal {
         const effectiveThisType = this.effectiveType(this.type);
         const otherType = ("type" in other && other.type) || "data";
         const effectiveOtherType = this.effectiveType(otherType);
-        const canAccept = effectiveThisType === effectiveOtherType
+        const canAccept = effectiveThisType === effectiveOtherType;
         return new ConnectionAcceptable(
             canAccept,
-            canAccept ? null: `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
+            canAccept ? null : `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
         );
     }
 }

From bf754bac2050fda3797a4c8aac43de9757d475d8 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 15:43:46 -0500
Subject: [PATCH 307/350] Use b-form-file, fix value prop declaration

---
 .../components/Form/Elements/FormUpload.vue   | 20 +++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/client/src/components/Form/Elements/FormUpload.vue b/client/src/components/Form/Elements/FormUpload.vue
index de43d4b55f3..a9cb3da4cfa 100644
--- a/client/src/components/Form/Elements/FormUpload.vue
+++ b/client/src/components/Form/Elements/FormUpload.vue
@@ -2,10 +2,15 @@
 import { ref, defineEmits, computed } from "vue";
 import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
 const props = defineProps({
-    value: ""
+    value: {
+        required: true,
+    },
 });
 const file = ref(null);
+const waiting = ref(false);
+
 const emit = defineEmits(["input"]);
+
 const currentValue = computed({
     get() {
         return props.value;
@@ -14,28 +19,27 @@ const currentValue = computed({
         emit("input", newValue);
     },
 });
-const waiting = ref(false);
+
 function readFile() {
-    const fileContent = file.value && file.value.files[0];
     var reader = new FileReader();
-    if (fileContent) {
+    if (file.value) {
         waiting.value = true;
         reader.onload = () => {
             currentValue.value = reader.result;
             waiting.value = false;
         };
-        reader.readAsText(fileContent);
+        reader.readAsText(file.value);
     }
 }
 </script>
 
 <template>
     <div>
-        <input ref="file" type="file" class="mb-1" @change="readFile" />
+        <b-form-file v-model="file" class="mb-1" @input="readFile" />
         <div v-if="waiting">
             <font-awesome-icon icon="spinner" spin />
             Uploading File...
         </div>
-        <textarea v-show="currentValue" v-model="currentValue" class="ui-textarea" disabled></textarea>
+        <textarea v-show="currentValue" v-model="currentValue" class="ui-textarea" disabled />
     </div>
-</template>
\ No newline at end of file
+</template>

From d71472f07143b712c85ca1005c129ebca4007b55 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 15:49:27 -0500
Subject: [PATCH 308/350] Fix python linting

---
 lib/galaxy/webapps/galaxy/controllers/dataset.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lib/galaxy/webapps/galaxy/controllers/dataset.py b/lib/galaxy/webapps/galaxy/controllers/dataset.py
index c496a8aedeb..95bdbb1632d 100644
--- a/lib/galaxy/webapps/galaxy/controllers/dataset.py
+++ b/lib/galaxy/webapps/galaxy/controllers/dataset.py
@@ -291,6 +291,10 @@ class DatasetInterface(BaseUIController, UsesAnnotations, UsesItemRatings, UsesE
             if data.missing_meta():
                 message = 'Required metadata values are missing. Some of these values may not be editable by the user. Selecting "Auto-detect" will attempt to fix these values.'
                 status = "warning"
+            metadata_disable = data.state not in [
+                trans.model.Dataset.states.OK,
+                trans.model.Dataset.states.FAILED_METADATA,
+            ]
             metadata_disable = data.state not in [trans.model.Dataset.states.OK, trans.model.Dataset.states.FAILED_METADATA]
             # datatype conversion
             conversion_options = [

From 4ed173a0fc38675c916166a4eeafb2dd76121d13 Mon Sep 17 00:00:00 2001
From: Martin Cech <marten@bx.psu.edu>
Date: Thu, 26 Jan 2023 15:34:24 -0800
Subject: [PATCH 309/350] move loading indicator and supress it for non-initial
 load

---
 client/src/components/LoadingSpan.vue          | 9 +++++++--
 client/src/components/Workflow/Editor/Node.vue | 6 ++++--
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/client/src/components/LoadingSpan.vue b/client/src/components/LoadingSpan.vue
index 85e79a25c7e..c4c3b9d26b5 100644
--- a/client/src/components/LoadingSpan.vue
+++ b/client/src/components/LoadingSpan.vue
@@ -1,7 +1,7 @@
 <template>
     <span>
-        <span :class="spinnerClasses"></span>
-        <span class="loading-message">{{ message }}.<span class="blinking">..</span></span>
+        <span :class="spinnerClasses" title="loading"></span>
+        <span v-if="!spinnerOnly" class="loading-message">{{ message }}.<span class="blinking">..</span></span>
     </span>
 </template>
 <script>
@@ -16,6 +16,11 @@ export default {
             type: String,
             default: "Loading",
         },
+        spinnerOnly: {
+            type: Boolean,
+            required: false,
+            default: false,
+        },
     },
     computed: {
         spinnerClasses() {
diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index 3a475c5ceb2..af5fec39f87 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -11,8 +11,8 @@
         @move="onMoveTo"
         @pan-by="onPanBy">
         <div class="node-header unselectable clearfix" @click="makeActive" @keyup.enter="makeActive">
-            <loading-span v-if="isLoading" message="Loading details" />
             <b-button-group class="float-right">
+                <loading-span v-if="isLoading" spinner-only />
                 <b-button
                     v-if="canClone"
                     v-b-tooltip.hover
@@ -175,7 +175,9 @@ const workflowOutputs = computed(() => props.step.workflow_outputs || []);
 const connectionStore = useConnectionStore();
 const stateStore = useWorkflowStateStore();
 const stepStore = useWorkflowStepStore();
-const isLoading = computed(() => Boolean(stateStore.getStepLoadingState(props.id)?.loading));
+const isLoading = computed(() =>
+    Boolean(stateStore.getStepLoadingState(props.id)?.loading && props.step.outputs.length === 0)
+);
 useNodePosition(el, props.id, stateStore);
 const title = computed(() => props.step.label || props.step.name);
 const idString = computed(() => `wf-node-step-${props.id}`);

From b0187d6670659b5e82aa808d04bc5e6e536dd2fa Mon Sep 17 00:00:00 2001
From: Martin Cech <emulatorer@gmail.com>
Date: Fri, 27 Jan 2023 00:47:51 +0100
Subject: [PATCH 310/350] drop duplicated statement

---
 lib/galaxy/webapps/galaxy/controllers/dataset.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/lib/galaxy/webapps/galaxy/controllers/dataset.py b/lib/galaxy/webapps/galaxy/controllers/dataset.py
index 95bdbb1632d..fe1578907b9 100644
--- a/lib/galaxy/webapps/galaxy/controllers/dataset.py
+++ b/lib/galaxy/webapps/galaxy/controllers/dataset.py
@@ -295,7 +295,6 @@ class DatasetInterface(BaseUIController, UsesAnnotations, UsesItemRatings, UsesE
                 trans.model.Dataset.states.OK,
                 trans.model.Dataset.states.FAILED_METADATA,
             ]
-            metadata_disable = data.state not in [trans.model.Dataset.states.OK, trans.model.Dataset.states.FAILED_METADATA]
             # datatype conversion
             conversion_options = [
                 (f"{convert_id} (using '{convert_name}')", convert_id)

From dce33f8f3cd2f052ffd90ff29aa971b229d05c30 Mon Sep 17 00:00:00 2001
From: Assunta DeSanto <assuntad23@gmail.com>
Date: Thu, 26 Jan 2023 22:15:36 -0500
Subject: [PATCH 311/350] adding client test cases

---
 .../Form/Elements/FormUpload.test.js          | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 client/src/components/Form/Elements/FormUpload.test.js

diff --git a/client/src/components/Form/Elements/FormUpload.test.js b/client/src/components/Form/Elements/FormUpload.test.js
new file mode 100644
index 00000000000..e642a327a9c
--- /dev/null
+++ b/client/src/components/Form/Elements/FormUpload.test.js
@@ -0,0 +1,30 @@
+import { mount } from "@vue/test-utils";
+import { getLocalVue } from "tests/jest/helpers";
+import FormUpload from "./FormUpload";
+
+const localVue = getLocalVue();
+
+describe("FormUpload", () => {
+    const mountFormUpload = async (props) =>
+        await mount(FormUpload, {
+            propsData: props,
+            localVue,
+        });
+
+    it("should display selected file in disabled textarea", async () => {
+        const v = "H1, H2, H3\nv1, v2, v3";
+        const wrapper = await mountFormUpload({ value: v });
+        const el = wrapper.find("textarea");
+        expect(el.element.value).toEqual(v);
+        const isDisabled = el.element.disabled === true;
+        expect(isDisabled).toBe(true);
+
+    });
+
+    it("should not display text box if file has not been selected", async () => {
+        const v = "";
+        const wrapper = await mountFormUpload({ value: v });
+        const el = wrapper.find("textarea");
+        expect(el.isVisible()).toBe(false);
+    });
+});

From b25198cd79d8d6fa6bf32b44d8309e3ac2b72d4e Mon Sep 17 00:00:00 2001
From: Assunta DeSanto <assuntad23@gmail.com>
Date: Thu, 26 Jan 2023 22:18:38 -0500
Subject: [PATCH 312/350] running prettier

---
 client/src/components/Form/Elements/FormUpload.test.js | 1 -
 1 file changed, 1 deletion(-)

diff --git a/client/src/components/Form/Elements/FormUpload.test.js b/client/src/components/Form/Elements/FormUpload.test.js
index e642a327a9c..94c68f5b6e9 100644
--- a/client/src/components/Form/Elements/FormUpload.test.js
+++ b/client/src/components/Form/Elements/FormUpload.test.js
@@ -18,7 +18,6 @@ describe("FormUpload", () => {
         expect(el.element.value).toEqual(v);
         const isDisabled = el.element.disabled === true;
         expect(isDisabled).toBe(true);
-
     });
 
     it("should not display text box if file has not been selected", async () => {

From df1e40229a41fe052d370c58a31ce7063a61b9c3 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 22:43:03 -0500
Subject: [PATCH 313/350] Remove unused awaits, check label

---
 .../components/Form/Elements/FormUpload.test.js   | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/client/src/components/Form/Elements/FormUpload.test.js b/client/src/components/Form/Elements/FormUpload.test.js
index 94c68f5b6e9..b140b31d0e5 100644
--- a/client/src/components/Form/Elements/FormUpload.test.js
+++ b/client/src/components/Form/Elements/FormUpload.test.js
@@ -5,25 +5,26 @@ import FormUpload from "./FormUpload";
 const localVue = getLocalVue();
 
 describe("FormUpload", () => {
-    const mountFormUpload = async (props) =>
-        await mount(FormUpload, {
+    const mountFormUpload = (props) =>
+        mount(FormUpload, {
             propsData: props,
             localVue,
         });
 
     it("should display selected file in disabled textarea", async () => {
         const v = "H1, H2, H3\nv1, v2, v3";
-        const wrapper = await mountFormUpload({ value: v });
+        const wrapper = mountFormUpload({ value: v });
         const el = wrapper.find("textarea");
         expect(el.element.value).toEqual(v);
-        const isDisabled = el.element.disabled === true;
-        expect(isDisabled).toBe(true);
+        expect(el.element.disabled).toBe(true);
     });
 
     it("should not display text box if file has not been selected", async () => {
-        const v = "";
-        const wrapper = await mountFormUpload({ value: v });
+        const wrapper = mountFormUpload({ value: null });
         const el = wrapper.find("textarea");
         expect(el.isVisible()).toBe(false);
+        expect(el.text()).toBe("");
+        const noInput = wrapper.find("label");
+        expect(noInput.text()).toBe("No file chosen");
     });
 });

From c3ae63d538186d31b5615567fe134c9fe44b9dbb Mon Sep 17 00:00:00 2001
From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com>
Date: Fri, 27 Jan 2023 10:19:43 +0000
Subject: [PATCH 314/350] Bump ua-parser-js from 0.7.31 to 0.7.33 in /client

Bumps [ua-parser-js](https://github.com/faisalman/ua-parser-js) from 0.7.31 to 0.7.33.
- [Release notes](https://github.com/faisalman/ua-parser-js/releases)
- [Changelog](https://github.com/faisalman/ua-parser-js/blob/master/changelog.md)
- [Commits](https://github.com/faisalman/ua-parser-js/compare/0.7.31...0.7.33)

---
updated-dependencies:
- dependency-name: ua-parser-js
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
---
 client/yarn.lock | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/client/yarn.lock b/client/yarn.lock
index effa8a67e86..d7f18e64d3a 100644
--- a/client/yarn.lock
+++ b/client/yarn.lock
@@ -10961,9 +10961,9 @@ typescript@^4.9.3:
   integrity sha512-CIfGzTelbKNEnLpLdGFgdyKhG23CKdKgQPOBc+OUNrkJ2vr+KSzsSV5kq5iWhEQbok+quxgGzrAtGWCyU7tHnA==
 
 ua-parser-js@^0.7.30:
-  version "0.7.31"
-  resolved "https://registry.npmjs.org/ua-parser-js/-/ua-parser-js-0.7.31.tgz"
-  integrity sha512-qLK/Xe9E2uzmYI3qLeOmI0tEOt+TBBQyUIAh4aAgU05FVYzeZrKUdkAZfBNVGRaHVgV0TDkdEngJSw/SyQchkQ==
+  version "0.7.33"
+  resolved "https://registry.yarnpkg.com/ua-parser-js/-/ua-parser-js-0.7.33.tgz#1d04acb4ccef9293df6f70f2c3d22f3030d8b532"
+  integrity sha512-s8ax/CeZdK9R/56Sui0WM6y9OFREJarMRHqLB2EwkovemBxNQ+Bqu8GAsUnVcXKgphb++ghr/B2BZx4mahujPw==
 
 uc.micro@^1.0.1, uc.micro@^1.0.5:
   version "1.0.6"

From 93c2835aeffa034e0eda30c21327da2fcebf29c7 Mon Sep 17 00:00:00 2001
From: Martin Cech <cech.marten@gmail.com>
Date: Fri, 27 Jan 2023 18:46:02 +0100
Subject: [PATCH 315/350] do no t limit loading indicator to initial load

Co-authored-by: Marius van den Beek <m.vandenbeek@gmail.com>
---
 client/src/components/Workflow/Editor/Node.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index af5fec39f87..d6a11e5a1e2 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -176,7 +176,7 @@ const connectionStore = useConnectionStore();
 const stateStore = useWorkflowStateStore();
 const stepStore = useWorkflowStepStore();
 const isLoading = computed(() =>
-    Boolean(stateStore.getStepLoadingState(props.id)?.loading && props.step.outputs.length === 0)
+    Boolean(stateStore.getStepLoadingState(props.id)?.loading)
 );
 useNodePosition(el, props.id, stateStore);
 const title = computed(() => props.step.label || props.step.name);

From 0375df7c70a343f2eb4d5ea8ccb778dc52cc1602 Mon Sep 17 00:00:00 2001
From: Martin Cech <marten@bx.psu.edu>
Date: Fri, 27 Jan 2023 10:00:20 -0800
Subject: [PATCH 316/350] pretify

---
 client/src/components/Workflow/Editor/Node.vue | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Node.vue b/client/src/components/Workflow/Editor/Node.vue
index d6a11e5a1e2..0d7abe9abd6 100644
--- a/client/src/components/Workflow/Editor/Node.vue
+++ b/client/src/components/Workflow/Editor/Node.vue
@@ -175,9 +175,7 @@ const workflowOutputs = computed(() => props.step.workflow_outputs || []);
 const connectionStore = useConnectionStore();
 const stateStore = useWorkflowStateStore();
 const stepStore = useWorkflowStepStore();
-const isLoading = computed(() =>
-    Boolean(stateStore.getStepLoadingState(props.id)?.loading)
-);
+const isLoading = computed(() => Boolean(stateStore.getStepLoadingState(props.id)?.loading));
 useNodePosition(el, props.id, stateStore);
 const title = computed(() => props.step.label || props.step.name);
 const idString = computed(() => `wf-node-step-${props.id}`);

From b33b48561785cebbe4c62f6378f286251295646a Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Thu, 26 Jan 2023 13:30:44 -0500
Subject: [PATCH 317/350] Prevent posting changes when initializing tool forms
 in workflow editor

---
 client/src/components/Workflow/Editor/Forms/FormTool.vue | 9 ++++++++-
 client/src/components/Workflow/Editor/Index.vue          | 1 +
 .../src/components/Workflow/Editor/modules/terminals.ts  | 4 ++--
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Forms/FormTool.vue b/client/src/components/Workflow/Editor/Forms/FormTool.vue
index 609447c15a9..2d8e70e2972 100644
--- a/client/src/components/Workflow/Editor/Forms/FormTool.vue
+++ b/client/src/components/Workflow/Editor/Forms/FormTool.vue
@@ -163,9 +163,16 @@ export default {
         onLabel(newLabel) {
             this.$emit("onLabel", this.stepId, newLabel);
         },
+        /**
+         * Change event is triggered on component creation and input changes.
+         * @param { Object } values contains flat key-value pairs `prefixed-name=value`
+         */
         onChange(values) {
+            const initialRequest = Object.keys(this.mainValues).length === 0;
             this.mainValues = values;
-            this.postChanges();
+            if (!initialRequest) {
+                this.postChanges();
+            }
         },
         onChangePostJobActions(postJobActions) {
             this.$emit("onChangePostJobActions", this.stepId, postJobActions);
diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index 92ee4af0680..3f5f8e3fd41 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -108,6 +108,7 @@
                             <div>
                                 <FormTool
                                     v-if="hasActiveNodeTool"
+                                    :key="activeStep.id"
                                     :step="activeStep"
                                     :datatypes="datatypes"
                                     @onChangePostJobActions="onChangePostJobActions"
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 1e354149ffa..9b145699bed 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -490,10 +490,10 @@ export class InputParameterTerminal extends BaseInputTerminal {
         const effectiveThisType = this.effectiveType(this.type);
         const otherType = ("type" in other && other.type) || "data";
         const effectiveOtherType = this.effectiveType(otherType);
-        const canAccept = effectiveThisType === effectiveOtherType
+        const canAccept = effectiveThisType === effectiveOtherType;
         return new ConnectionAcceptable(
             canAccept,
-            canAccept ? null: `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
+            canAccept ? null : `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
         );
     }
 }

From f0e09031f4a194f0d1f9c1656eb53d1f1681e9a9 Mon Sep 17 00:00:00 2001
From: guerler <aysam.guerler@gmail.com>
Date: Fri, 27 Jan 2023 19:30:44 -0500
Subject: [PATCH 318/350] Adjust test to ensure that onSetData is not fired on
 initialization

---
 .../Workflow/Editor/Forms/FormTool.test.js          | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Forms/FormTool.test.js b/client/src/components/Workflow/Editor/Forms/FormTool.test.js
index 2db5af07c0e..01bdcfb973c 100644
--- a/client/src/components/Workflow/Editor/Forms/FormTool.test.js
+++ b/client/src/components/Workflow/Editor/Forms/FormTool.test.js
@@ -11,9 +11,7 @@ import { createTestingPinia } from "@pinia/testing";
 const localVue = getLocalVue();
 
 describe("FormTool", () => {
-    let wrapper;
-
-    beforeEach(() => {
+    function mountTarget() {
         const store = new Vuex.Store({
             modules: {
                 user: mockModule(userStore),
@@ -21,7 +19,7 @@ describe("FormTool", () => {
             },
         });
 
-        wrapper = mount(FormTool, {
+        return mount(FormTool, {
             propsData: {
                 id: "input",
                 datatypes: [],
@@ -32,7 +30,7 @@ describe("FormTool", () => {
                         name: "tool_name",
                         version: "1.0",
                         description: "description",
-                        inputs: [],
+                        inputs: [{ name: "input", label: "input", type: "text", value: "value" }],
                         help: "help_text",
                         versions: ["1.0", "2.0", "3.0"],
                         citations: false,
@@ -46,15 +44,16 @@ describe("FormTool", () => {
             stubs: {
                 CurrentUser: MockCurrentUser({ id: "fakeuser" }),
                 ConfigProvider: MockConfigProvider({ id: "fakeconfig" }),
-                FormElement: { template: "<div>form-element</div>" },
                 ToolFooter: { template: "<div>tool-footer</div>" },
             },
             pinia: createTestingPinia(),
             provide: { store },
         });
-    });
+    }
 
     it("changes between different versions", async () => {
+        const wrapper = mountTarget();
+
         const dropdowns = wrapper.findAll(".tool-versions .dropdown-item");
         let version = dropdowns.at(1);
         expect(version.text()).toBe("Switch to 2.0");

From 63d0e5c14984265eb78db36b8635c84dccd7f8b0 Mon Sep 17 00:00:00 2001
From: Ahmed Awan <qe66653@umbc.edu>
Date: Sat, 28 Jan 2023 23:26:48 +0500
Subject: [PATCH 319/350] Add name+description ToolSearch

---
 client/src/components/Panels/Common/ToolSearch.vue | 2 +-
 client/src/components/Panels/utilities.js          | 7 ++++++-
 client/src/components/Panels/utilities.test.js     | 6 ++++++
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/client/src/components/Panels/Common/ToolSearch.vue b/client/src/components/Panels/Common/ToolSearch.vue
index dd2a5303020..167659c2870 100644
--- a/client/src/components/Panels/Common/ToolSearch.vue
+++ b/client/src/components/Panels/Common/ToolSearch.vue
@@ -109,7 +109,7 @@ export default {
                     this.$emit("onResults", this.favoritesResults);
                 } else {
                     // keys with sorting order
-                    const keys = { exact: 2, name: 1, description: 0 };
+                    const keys = { exact: 3, name: 2, description: 1, combined: 0 };
                     this.$emit("onResults", searchToolsByKeys(this.toolsList, keys, q));
                 }
             } else {
diff --git a/client/src/components/Panels/utilities.js b/client/src/components/Panels/utilities.js
index 8431e0828c1..900e32079ba 100644
--- a/client/src/components/Panels/utilities.js
+++ b/client/src/components/Panels/utilities.js
@@ -89,7 +89,12 @@ export function searchToolsByKeys(tools, keys, query) {
     const returnedTools = [];
     for (const tool of tools) {
         for (const key of Object.keys(keys)) {
-            const actualValue = tool[key] ? tool[key].toLowerCase() : "";
+            let actualValue = "";
+            if (key === "combined") {
+                actualValue = tool.name.toLowerCase() + " " + tool.description.toLowerCase();
+            } else {
+                actualValue = tool[key] ? tool[key].toLowerCase() : "";
+            }
             const queryLowerCase = query.toLowerCase();
             if (actualValue.match(queryLowerCase)) {
                 // do we care for exact matches && is it an exact match ?
diff --git a/client/src/components/Panels/utilities.test.js b/client/src/components/Panels/utilities.test.js
index eb6fdadad6f..976c43e1a47 100644
--- a/client/src/components/Panels/utilities.test.js
+++ b/client/src/components/Panels/utilities.test.js
@@ -37,6 +37,12 @@ describe("test helpers in tool searching utilities", () => {
         keys = { description: 0, name: 1 };
         results = searchToolsByKeys(normalizeTools(toolsList), keys, q);
         expect(results).toEqual(expectedResults);
+
+        q = "filter empty datasets";
+        expectedResults = ["__FILTER_EMPTY_DATASETS__"];
+        keys = { description: 1, name: 2, combined: 0 };
+        results = searchToolsByKeys(normalizeTools(toolsList), keys, q);
+        expect(results).toEqual(expectedResults);
     });
 
     it("test tool filtering helpers on toolsList given list of ids", async () => {

From e14d68bfda5888819a41201b4e07e5a3db9632f2 Mon Sep 17 00:00:00 2001
From: Ahmed Awan <qe66653@umbc.edu>
Date: Sat, 28 Jan 2023 23:31:52 +0500
Subject: [PATCH 320/350] name+description ToolSearch: change constant to let

---
 client/src/components/Panels/utilities.test.js | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Panels/utilities.test.js b/client/src/components/Panels/utilities.test.js
index 976c43e1a47..05697266a11 100644
--- a/client/src/components/Panels/utilities.test.js
+++ b/client/src/components/Panels/utilities.test.js
@@ -17,7 +17,7 @@ describe("test helpers in tool searching utilities", () => {
     });
 
     it("test tool search helper that searches for tools given keys", async () => {
-        const q = "collection";
+        let q = "collection";
         let expectedResults = [
             "__FILTER_FAILED_DATASETS__",
             "__FILTER_EMPTY_DATASETS__",

From adc425c6569ff5b5d839db3f2e9db9128897fccd Mon Sep 17 00:00:00 2001
From: Ahmed Awan <qe66653@umbc.edu>
Date: Sun, 29 Jan 2023 00:45:32 +0500
Subject: [PATCH 321/350] ToolBoxWorkflow only include and search for
 compatible tools

---
 client/src/components/Panels/Common/Tool.vue     |  4 ++--
 client/src/components/Panels/ToolBoxWorkflow.vue | 10 +++++++---
 client/src/components/Panels/utilities.js        | 16 ++++++++++++++++
 3 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/client/src/components/Panels/Common/Tool.vue b/client/src/components/Panels/Common/Tool.vue
index be926ec04ed..7da41962ca2 100644
--- a/client/src/components/Panels/Common/Tool.vue
+++ b/client/src/components/Panels/Common/Tool.vue
@@ -59,9 +59,9 @@ export default {
     computed: {
         targetClass() {
             if (this.toolKey) {
-                return `tool-menu-item-${this.tool[this.toolKey]} title-link`;
+                return `tool-menu-item-${this.tool[this.toolKey]} title-link cursor-pointer`;
             } else {
-                return `title-link`;
+                return `title-link cursor-pointer`;
             }
         },
     },
diff --git a/client/src/components/Panels/ToolBoxWorkflow.vue b/client/src/components/Panels/ToolBoxWorkflow.vue
index 95e2dab6d48..bcb26c53f60 100644
--- a/client/src/components/Panels/ToolBoxWorkflow.vue
+++ b/client/src/components/Panels/ToolBoxWorkflow.vue
@@ -18,7 +18,7 @@
             <tool-search
                 :current-panel-view="currentPanelView"
                 placeholder="search tools"
-                :toolbox="toolbox"
+                :toolbox="workflowTools"
                 :query="query"
                 @onQuery="onQuery"
                 @onResults="onResults" />
@@ -74,7 +74,7 @@
 import _l from "utils/localization";
 import ToolSection from "./Common/ToolSection";
 import ToolSearch from "./Common/ToolSearch";
-import { filterToolSections } from "./utilities";
+import { filterToolSections, removeDisabledTools } from "./utilities";
 import PanelViewButton from "./Buttons/PanelViewButton";
 
 export default {
@@ -140,12 +140,13 @@ export default {
             };
         },
         sections() {
-            return filterToolSections(this.toolsLayout, this.results);
+            return filterToolSections(this.workflowTools, this.results);
         },
         toolsLayout() {
             return this.toolbox.map((section) => {
                 return {
                     ...section,
+                    disabled: !section.elems && !section.is_workflow_compatible,
                     elems:
                         section.elems &&
                         section.elems.map((el) => {
@@ -155,6 +156,9 @@ export default {
                 };
             });
         },
+        workflowTools() {
+            return removeDisabledTools(this.toolsLayout);
+        },
     },
     methods: {
         onQuery(query) {
diff --git a/client/src/components/Panels/utilities.js b/client/src/components/Panels/utilities.js
index 8431e0828c1..434f1005d81 100644
--- a/client/src/components/Panels/utilities.js
+++ b/client/src/components/Panels/utilities.js
@@ -109,6 +109,22 @@ export function normalizeTools(tools) {
     return tools;
 }
 
+export function removeDisabledTools(tools) {
+    return tools.filter((section) => {
+        if (section.model_class === "ToolSectionLabel") {
+            return true;
+        } else if (!section.elems && section.disabled) {
+            return false;
+        } else if (section.elems) {
+            section.elems = section.elems.filter((el) => !el.disabled);
+            if (!section.elems.length) {
+                return false;
+            }
+        }
+        return true;
+    });
+}
+
 function flattenToolsSection(section) {
     const flattenTools = [];
     if (section.elems) {

From c2bd9df6218a6e7fe45a9b11cd3d4d0570854192 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Wed, 25 Jan 2023 14:43:01 +0100
Subject: [PATCH 322/350] Disable Switch histories for anonymous users

---
 .../components/History/CurrentHistory/HistoryNavigation.vue    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/client/src/components/History/CurrentHistory/HistoryNavigation.vue b/client/src/components/History/CurrentHistory/HistoryNavigation.vue
index 9d73f41cf6a..1e4cfba5873 100644
--- a/client/src/components/History/CurrentHistory/HistoryNavigation.vue
+++ b/client/src/components/History/CurrentHistory/HistoryNavigation.vue
@@ -23,7 +23,8 @@
                     data-description="switch to another history"
                     size="sm"
                     variant="link"
-                    title="Switch to history">
+                    :disabled="currentUser.isAnonymous"
+                    :title="userTitle('Switch to history')">
                     <Icon fixed-width icon="exchange-alt" />
                 </b-button>
 

From ba4907cb897530c2629c3862fd46ae0db4ce9761 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Wed, 25 Jan 2023 14:43:31 +0100
Subject: [PATCH 323/350] Disable creating histories for anonymous users

---
 .../components/History/CurrentHistory/HistoryNavigation.vue    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/client/src/components/History/CurrentHistory/HistoryNavigation.vue b/client/src/components/History/CurrentHistory/HistoryNavigation.vue
index 1e4cfba5873..adc4d45a35e 100644
--- a/client/src/components/History/CurrentHistory/HistoryNavigation.vue
+++ b/client/src/components/History/CurrentHistory/HistoryNavigation.vue
@@ -12,7 +12,8 @@
                     data-description="create new history"
                     size="sm"
                     variant="link"
-                    title="Create new history"
+                    :disabled="currentUser.isAnonymous"
+                    :title="userTitle('Create new history')"
                     @click="$emit('createNewHistory')">
                     <Icon fixed-width icon="plus" />
                 </b-button>

From 66464d201c9454db75821f500d007d8bd1bb7ce1 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Wed, 25 Jan 2023 17:06:55 +0100
Subject: [PATCH 324/350] Add tests for buttons availability

---
 .../History/CurrentHistory/HistoryNavigation.test.js  | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/client/src/components/History/CurrentHistory/HistoryNavigation.test.js b/client/src/components/History/CurrentHistory/HistoryNavigation.test.js
index e0486579328..3fffa8e50ec 100644
--- a/client/src/components/History/CurrentHistory/HistoryNavigation.test.js
+++ b/client/src/components/History/CurrentHistory/HistoryNavigation.test.js
@@ -56,6 +56,11 @@ describe("History Navigation", () => {
             provide: { store },
         });
 
+        const createButton = wrapper.find("*[data-description='create new history']");
+        expect(createButton.attributes().disabled).toBeFalsy();
+        const switchButton = wrapper.find("*[data-description='switch to another history']");
+        expect(switchButton.attributes().disabled).toBeFalsy();
+
         const dropDown = wrapper.find("*[data-description='history options']");
         const optionElements = dropDown.findAll("b-dropdown-item-stub");
         const optionTexts = optionElements.wrappers.map((el) => el.text());
@@ -76,8 +81,12 @@ describe("History Navigation", () => {
             provide: { store },
         });
 
-        const dropDown = wrapper.find("*[data-description='history options']");
+        const createButton = wrapper.find("*[data-description='create new history']");
+        expect(createButton.attributes().disabled).toBeTruthy();
+        const switchButton = wrapper.find("*[data-description='switch to another history']");
+        expect(switchButton.attributes().disabled).toBeTruthy();
 
+        const dropDown = wrapper.find("*[data-description='history options']");
         const enabledOptionElements = dropDown.findAll("b-dropdown-item-stub:not([disabled])");
         const enabledOptionTexts = enabledOptionElements.wrappers.map((el) => el.text());
         expect(enabledOptionTexts).toStrictEqual(anonymousOptions);

From 4d57cd820bbd99ccb32deeebc6f7db589fd750c2 Mon Sep 17 00:00:00 2001
From: davelopez <46503462+davelopez@users.noreply.github.com>
Date: Thu, 26 Jan 2023 16:18:03 +0100
Subject: [PATCH 325/350] Adapt Window Manager tour

Instead of auto-creating a new history, make it a requirement.
---
 config/plugins/tours/core.windows.yaml | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/config/plugins/tours/core.windows.yaml b/config/plugins/tours/core.windows.yaml
index 226150dadf6..d2318ce3c5d 100644
--- a/config/plugins/tours/core.windows.yaml
+++ b/config/plugins/tours/core.windows.yaml
@@ -6,15 +6,14 @@ tags:
   - "UI"
   - "visualization"
 
+requirements:
+  - new_history
+
 steps:
     - content: "This short tour will walk you through <b>Galaxy's Window Manager</b> feature"
 
-    - element: "#current-history-panel .create-hist-btn"
-      intro: "Before using the Window Manager, we will create a new history for this tour."
-      postclick: true
-
     - element: "#tool-panel-upload-button"
-      intro: "Now, we will upload some tabular data into our new history."
+      intro: "First, we will upload some tabular data into our new history."
       postclick: true
 
     - element: "#btn-new"
@@ -78,7 +77,7 @@ steps:
 
     - element: "#right"
       intro: "This is your history. It contains our two tables being uploaded."
-    
+
     - component: history_panel.item(hid=1,state=ok).display_button
       intro: "Clicking the eye-icon usually displays a dataset in the center panel."
       postclick: true

From 1997c7d8abc74b3b0c9527cf5efb2e46e5153eb1 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 30 Jan 2023 11:18:01 +0100
Subject: [PATCH 326/350] Adjust to bleach.ALLOWED_PROTOCOLS being frozenset

---
 lib/galaxy/util/sanitize_html.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/galaxy/util/sanitize_html.py b/lib/galaxy/util/sanitize_html.py
index cdfe5229168..d915a80a7a1 100644
--- a/lib/galaxy/util/sanitize_html.py
+++ b/lib/galaxy/util/sanitize_html.py
@@ -252,5 +252,5 @@ _acceptable_attributes = [
 def sanitize_html(htmlSource, allow_data_urls=False):
     kwd = dict(tags=_acceptable_elements, attributes=_acceptable_attributes, strip=True)
     if allow_data_urls:
-        kwd["protocols"] = bleach.ALLOWED_PROTOCOLS + ["data"]
+        kwd["protocols"] = list(bleach.ALLOWED_PROTOCOLS) + ["data"]
     return bleach.clean(unicodify(htmlSource), **kwd)

From 911bf26078fb0f004704f527447c4fd9257fdf2c Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 27 Jan 2023 11:24:07 +0100
Subject: [PATCH 327/350] Determine collection type when collection_type_source
 is given

And make sure mapOver doesn't "flicker" when combining different
effective mapOver types.
---
 .../Editor/composables/useUniqueLabelError.ts |  2 +-
 .../Workflow/Editor/modules/terminals.test.ts | 41 ++++++--
 .../Workflow/Editor/modules/terminals.ts      | 51 +++++++++-
 .../Editor/test-data/parameter_steps.json     | 94 +++++++++++++++++++
 client/src/stores/workflowStepStore.ts        |  8 +-
 5 files changed, 180 insertions(+), 16 deletions(-)

diff --git a/client/src/components/Workflow/Editor/composables/useUniqueLabelError.ts b/client/src/components/Workflow/Editor/composables/useUniqueLabelError.ts
index db69f9e509e..50916494f52 100644
--- a/client/src/components/Workflow/Editor/composables/useUniqueLabelError.ts
+++ b/client/src/components/Workflow/Editor/composables/useUniqueLabelError.ts
@@ -3,7 +3,7 @@ import { ref } from "vue";
 
 export function useUniqueLabelError(
     workflowStateStore: ReturnType<typeof useWorkflowStepStore>,
-    label: string | undefined
+    label: string | null | undefined
 ) {
     const error = ref("");
     if (label && workflowStateStore.workflowOutputs[label]) {
diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index f71de5dabbf..16bd273d6d6 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -1,6 +1,6 @@
 import { setActivePinia, createPinia } from "pinia";
 
-import { useWorkflowStepStore } from "@/stores/workflowStepStore";
+import { useWorkflowStepStore, type TerminalSource } from "@/stores/workflowStepStore";
 import {
     terminalFactory,
     InputCollectionTerminal,
@@ -15,7 +15,11 @@ import {
 import { testDatatypesMapper } from "@/components/Datatypes/test_fixtures";
 import { useConnectionStore } from "@/stores/workflowConnectionStore";
 import type { DataOutput, Steps } from "@/stores/workflowStepStore";
-import { NULL_COLLECTION_TYPE_DESCRIPTION } from "./collectionTypeDescription";
+import {
+    ANY_COLLECTION_TYPE_DESCRIPTION,
+    CollectionTypeDescription,
+    NULL_COLLECTION_TYPE_DESCRIPTION,
+} from "./collectionTypeDescription";
 import { simpleSteps, advancedSteps } from "../test_fixtures";
 
 function setupAdvanced() {
@@ -35,6 +39,17 @@ function setupAdvanced() {
     return terminals;
 }
 
+function rebuildTerminal<T extends ReturnType<typeof terminalFactory>>(terminal: T): T {
+    let terminalSource: TerminalSource;
+    const step = terminal.stepStore.getStep(terminal.stepId);
+    if (terminal.terminalType === "input") {
+        terminalSource = step.inputs.find((input) => input.name == terminal.name)!;
+    } else {
+        terminalSource = step.outputs.find((output) => output.name == terminal.name)!;
+    }
+    return terminalFactory(terminal.stepId, terminalSource, testDatatypesMapper) as T;
+}
+
 describe("terminalFactory", () => {
     let terminals: { [index: string]: { [index: string]: ReturnType<typeof terminalFactory> } } = {};
     beforeEach(() => {
@@ -64,6 +79,8 @@ describe("terminalFactory", () => {
         expect(terminals["any collection"]["output"]).toBeInstanceOf(OutputCollectionTerminal);
         expect(terminals["multi data"]["advanced|advanced_threshold"]).toBeInstanceOf(InputParameterTerminal);
         expect(terminals["list collection input"]["input1"]).toBeInstanceOf(InputCollectionTerminal);
+        expect(terminals["filter_failed"]["input"]).toBeInstanceOf(InputCollectionTerminal);
+        expect(terminals["filter_failed"]["output"]).toBeInstanceOf(OutputCollectionTerminal);
     });
     it("throws error on invalid terminalSource", () => {
         const invalidFactory = () => terminalFactory(1, {} as any, testDatatypesMapper);
@@ -281,11 +298,7 @@ describe("canAccept", () => {
         dataInTwo.disconnect(dataOut);
         // terminal isn't a reactive class in any way (worth a thought doing, but difficult!), the following happens when a new terminal is built
         // in useTerminal.ts
-        const rebuiltDataIn = terminalFactory(
-            dataIn.stepId,
-            advancedSteps[dataIn.stepId].inputs[0],
-            testDatatypesMapper
-        );
+        const rebuiltDataIn = rebuildTerminal(dataIn);
         expect(rebuiltDataIn.localMapOver.isCollection).toBe(false);
         expect(rebuiltDataIn.canAccept(simpleDataOut).canAccept).toBe(true);
     });
@@ -459,6 +472,20 @@ describe("canAccept", () => {
             "Effective output data type(s) [tabular] do not appear to match input type(s) [ab1]."
         );
     });
+    it("resolves collection type source", () => {
+        const filterFailedInput = terminals["filter_failed"]["input"] as InputCollectionTerminal;
+        const filterFailedOutput = terminals["filter_failed"]["output"] as OutputCollectionTerminal;
+        expect(filterFailedOutput.collectionType).toBe(ANY_COLLECTION_TYPE_DESCRIPTION);
+        const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
+        filterFailedInput.connect(collectionOut);
+        expect(rebuildTerminal(filterFailedOutput).collectionType).toStrictEqual(new CollectionTypeDescription("list"));
+        filterFailedInput.disconnect(collectionOut);
+        const listPairedOutput = terminals["list:paired input"]["output"] as OutputCollectionTerminal;
+        filterFailedInput.connect(listPairedOutput);
+        expect(rebuildTerminal(filterFailedOutput).collectionType).toStrictEqual(
+            new CollectionTypeDescription("list:paired")
+        );
+    });
 });
 
 describe("Input terminal", () => {
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 9b145699bed..2e3eb87d539 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -97,6 +97,7 @@ class Terminal extends EventEmitter {
         this.resetMappingIfNeeded(connection);
     }
     setMapOver(val: CollectionTypeDescriptor) {
+        // we use this method to determine the map over status based on all terminals connected to this step
         let outputVal = val;
         if (this.multiple) {
             // emulate list input
@@ -112,7 +113,12 @@ class Terminal extends EventEmitter {
             this.stepStore.changeStepInputMapOver(this.stepId, this.name, effectiveMapOver);
             this.localMapOver = effectiveMapOver;
         }
-        if (!this.mapOver.equal(effectiveMapOver)) {
+        if (
+            !this.mapOver.equal(effectiveMapOver) &&
+            Object.values(this.stepStore.stepInputMapOver[this.stepId]).some((mapOver) =>
+                mapOver.equal(effectiveMapOver)
+            )
+        ) {
             this.stepStore.changeStepMapOver(this.stepId, effectiveMapOver);
         }
     }
@@ -672,19 +678,56 @@ interface OutputCollectionTerminalArgs extends BaseOutputTerminalArgs {
 }
 
 export class OutputCollectionTerminal extends BaseOutputTerminal {
+    collectionTypeSource: string | null;
+
     constructor(attr: OutputCollectionTerminalArgs) {
         super(attr);
+        this.collectionTypeSource = null;
         if (attr.collection_type) {
             this.collectionType = new CollectionTypeDescription(attr.collection_type);
         } else {
-            const collectionTypeSource = attr.collection_type_source;
-            if (!collectionTypeSource) {
+            this.collectionTypeSource = attr.collection_type_source;
+            if (!this.collectionTypeSource) {
                 console.log("Warning: No collection type or collection type source defined.");
             }
-            this.collectionType = ANY_COLLECTION_TYPE_DESCRIPTION;
+            this.collectionType = this.getCollectionTypeFromInput() || ANY_COLLECTION_TYPE_DESCRIPTION;
         }
         this.isCollection = true;
     }
+
+    getCollectionTypeFromInput() {
+        const connection = this.connectionStore.connections.find(
+            (connection) =>
+                connection.input.name === this.collectionTypeSource && connection.input.stepId === this.stepId
+        );
+        if (connection) {
+            const outputStep = this.stepStore.getStep(connection.output.stepId);
+            const inputStep = this.stepStore.getStep(this.stepId);
+            if (outputStep) {
+                const stepOutput = outputStep.outputs.find((output) => output.name == connection.output.name);
+                const stepInput = inputStep.inputs.find((input) => input.name === this.collectionTypeSource);
+                if (stepInput && stepOutput) {
+                    const outputTerminal = terminalFactory(connection.output.stepId, stepOutput, this.datatypesMapper);
+                    const inputTerminal = terminalFactory(connection.output.stepId, stepInput, this.datatypesMapper);
+                    // otherCollectionType is the mapped over output collection as it would appear at the input terminal
+                    const otherCollectionType = inputTerminal._otherCollectionType(outputTerminal);
+                    // we need to find which of the possible input collection types is connected
+                    if ("collectionTypes" in inputTerminal) {
+                        // collection_type_source must point at input collection terminal
+                        const connectedCollectionType = inputTerminal.collectionTypes.find(
+                            (collectionType) =>
+                                otherCollectionType.canMatch(collectionType) ||
+                                otherCollectionType.canMapOver(collectionType)
+                        );
+                        if (connectedCollectionType) {
+                            return connectedCollectionType;
+                        }
+                    }
+                }
+            }
+        }
+        return ANY_COLLECTION_TYPE_DESCRIPTION;
+    }
 }
 
 interface OutputParameterTerminalArgs extends Omit<BaseOutputTerminalArgs, "datatypes"> {
diff --git a/client/src/components/Workflow/Editor/test-data/parameter_steps.json b/client/src/components/Workflow/Editor/test-data/parameter_steps.json
index fb9a9ed0f02..d3cff2cf8d9 100644
--- a/client/src/components/Workflow/Editor/test-data/parameter_steps.json
+++ b/client/src/components/Workflow/Editor/test-data/parameter_steps.json
@@ -812,5 +812,99 @@
       "left": 70.45245361328125,
       "top": 316.3525695800781
     }
+  },
+  "17": {
+    "id": 17,
+    "type": "tool",
+    "label": "filter_failed",
+    "content_id": "__FILTER_FAILED_DATASETS__",
+    "name": "Filter failed datasets",
+    "tool_state": {
+      "input": "{\"__class__\": \"RuntimeValue\"}",
+      "__page__": null,
+      "__rerun_remap_job_id__": null
+    },
+    "errors": null,
+    "inputs": [
+      {
+        "name": "input",
+        "label": "Input Collection",
+        "multiple": false,
+        "input_type": "dataset_collection",
+        "collection_types": [
+          "list",
+          "list:paired"
+        ],
+        "optional": false,
+        "extensions": [
+          "data"
+        ]
+      }
+    ],
+    "outputs": [
+      {
+        "name": "output",
+        "extensions": [
+          "input"
+        ],
+        "type": "collection",
+        "optional": false,
+        "collection": true,
+        "collection_type": null,
+        "collection_type_source": "input",
+        "label": "input dataset(s) (filtered failed datasets)"
+      }
+    ],
+    "annotation": "",
+    "post_job_actions": {},
+    "uuid": "f5de18b9-b08e-4160-b71b-54768a4e5208",
+    "when": null,
+    "workflow_outputs": [
+      {
+        "output_name": "output",
+        "uuid": "3774e554-b7d1-41ba-9acd-ee82ba9fbf54",
+        "label": null
+      }
+    ],
+    "input_connections": {},
+    "position": {
+      "left": 0,
+      "top": 0
+    }
+  },
+  "18": {
+    "id": 18,
+    "type": "data_collection_input",
+    "label": "list:paired input",
+    "content_id": null,
+    "name": "Input dataset collection",
+    "tool_state": {
+      "collection_type": "\"list:paired\"",
+      "optional": "\"false\"",
+      "tag": "\"\"",
+      "__page__": null,
+      "__rerun_remap_job_id__": null
+    },
+    "errors": null,
+    "inputs": [],
+    "outputs": [
+      {
+        "name": "output",
+        "extensions": [
+          "input"
+        ],
+        "collection": true,
+        "collection_type": "list:paired",
+        "optional": false
+      }
+    ],
+    "annotation": "",
+    "post_job_actions": {},
+    "workflow_outputs": [],
+    "input_connections": {},
+    "position": {
+      "left": 12.8729248046875,
+      "top": 501.7839660644531
+    }
   }
 }
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 655f6735c7d..113f8f8ba01 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -85,8 +85,8 @@ export type TerminalSource = InputTerminalSource | OutputTerminalSource;
 
 interface WorkflowOutput {
     output_name: string;
-    label?: string;
-    uuid?: string;
+    label?: string | null;
+    uuid?: string | null;
 }
 
 export interface NewStep {
@@ -97,7 +97,7 @@ export interface NewStep {
     errors?: string[] | null;
     input_connections: StepInputConnection;
     inputs: Array<InputTerminalSource>;
-    label?: string;
+    label?: string | null;
     name: string;
     outputs: Array<OutputTerminalSource>;
     position?: StepPosition;
@@ -106,7 +106,7 @@ export interface NewStep {
     tooltip?: string;
     type: "tool" | "data_input" | "data_collection_input" | "subworkflow" | "parameter_input" | "pause";
     uuid?: string;
-    when?: string;
+    when?: string | null;
     workflow_outputs?: WorkflowOutput[];
 }
 

From 85ee4c3c1fde08d0bc004491614881749ad9b62a Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Fri, 27 Jan 2023 14:48:03 +0100
Subject: [PATCH 328/350] Fix isMappedOver for all types of input terminals

It previously only worked for non-collection, non-parameter inputs.
---
 .../components/Workflow/Editor/modules/terminals.test.ts | 2 ++
 .../src/components/Workflow/Editor/modules/terminals.ts  | 9 +++++----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index 16bd273d6d6..e3f6bcd5cc2 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -402,7 +402,9 @@ describe("canAccept", () => {
         const collectionOut = terminals["list:list input"]["output"] as OutputCollectionTerminal;
         const collectionIn = terminals["list collection input"]["input1"] as InputCollectionTerminal;
         expect(collectionIn.canAccept(collectionOut).canAccept).toBe(true);
+        expect(collectionIn.isMappedOver()).toBe(false);
         collectionIn.connect(collectionOut);
+        expect(collectionIn.isMappedOver()).toBe(true);
         expect(collectionIn.mapOver).toEqual({ collectionType: "list", isCollection: true, rank: 1 });
         const intermediateOut = terminals["list collection input"]["out_file1"] as OutputCollectionTerminal;
         const otherListIn = terminals["list collection input 2"]["input1"] as InputCollectionTerminal;
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 2e3eb87d539..f1b4b1ec474 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -248,6 +248,11 @@ class BaseInputTerminal extends Terminal {
         }
         return null;
     }
+
+    isMappedOver(): boolean {
+        return Boolean(this.localMapOver.isCollection);
+    }
+
     connected() {
         return Boolean(this._getFirstOutputTerminal());
     }
@@ -406,10 +411,6 @@ export class InputTerminal extends BaseInputTerminal {
         this.getStepMapOver();
     }
 
-    isMappedOver(): boolean {
-        return Boolean(this.localMapOver.isCollection);
-    }
-
     attachable(other: BaseOutputTerminal) {
         const otherCollectionType = this._otherCollectionType(other);
         const mapOver = this.mapOver;

From a78ca90b7187e2eec4a0830614a30a8cca7f8b97 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 29 Jan 2023 11:01:25 +0100
Subject: [PATCH 329/350] Infer subworkflow input step if index is not given
 explicitly Seems to be used at least by the refactor action.

---
 lib/galaxy/model/__init__.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy/model/__init__.py b/lib/galaxy/model/__init__.py
index bda53e4dc96..6063ad4ad17 100644
--- a/lib/galaxy/model/__init__.py
+++ b/lib/galaxy/model/__init__.py
@@ -7163,8 +7163,20 @@ class WorkflowStep(Base, RepresentById):
         conn.output_name = output_name
         add_object_to_object_session(conn, output_step)
         conn.output_step = output_step
-        if input_subworkflow_step_index is not None:
-            input_subworkflow_step = self.subworkflow.step_by_index(input_subworkflow_step_index)
+        if self.subworkflow:
+            if input_subworkflow_step_index is not None:
+                input_subworkflow_step = self.subworkflow.step_by_index(input_subworkflow_step_index)
+            else:
+                input_subworkflow_steps = [step for step in self.subworkflow.input_steps if step.label == input_name]
+                if not input_subworkflow_steps:
+                    inferred_order_index = input_name.split(":", 1)[0]
+                    if inferred_order_index.isdigit():
+                        input_subworkflow_steps = [self.subworkflow.step_by_index(int(inferred_order_index))]
+                if len(input_subworkflow_steps) != 1:
+                    raise galaxy.exceptions.MessageException(
+                        f"Invalid subworkflow connection at step index {self.order_index + 1}"
+                    )
+                input_subworkflow_step = input_subworkflow_steps[0]
             conn.input_subworkflow_step = input_subworkflow_step
         return conn
 

From 62715c998de64113c139292f2052a3aa6be97715 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 29 Jan 2023 15:35:26 +0100
Subject: [PATCH 330/350] Fix test description typo

---
 client/src/components/Workflow/Editor/modules/terminals.test.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.test.ts b/client/src/components/Workflow/Editor/modules/terminals.test.ts
index e3f6bcd5cc2..154477afb7f 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.test.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.test.ts
@@ -274,7 +274,7 @@ describe("canAccept", () => {
             "Can't map over this input with output collection type - this step has outputs defined constraining the mapping of this tool. Disconnect outputs and retry."
         );
     });
-    it("rejects attaching non-collection outputs to mapper over inputs", () => {
+    it("rejects attaching non-collection outputs to mapped-over inputs", () => {
         const collectionOut = terminals["list input"]["output"] as OutputCollectionTerminal;
         const simpleDataOut = terminals["data input"]["output"] as OutputTerminal;
         const dataIn = terminals["simple data"]["input"] as InputTerminal;

From 6847a94b35f8dae54a5304363edfaeb95d20f4ce Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 29 Jan 2023 15:38:42 +0100
Subject: [PATCH 331/350] Fix resetting mapOver

Reset to null only if no input terminal is mapped over.
If a terminal is mapped over and another is not this
could lead to an infinite update cycle.
---
 client/src/components/Workflow/Editor/modules/terminals.ts | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index f1b4b1ec474..f6f4cc149cb 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -115,9 +115,8 @@ class Terminal extends EventEmitter {
         }
         if (
             !this.mapOver.equal(effectiveMapOver) &&
-            Object.values(this.stepStore.stepInputMapOver[this.stepId]).some((mapOver) =>
-                mapOver.equal(effectiveMapOver)
-            )
+            (effectiveMapOver.isCollection ||
+                !Object.values(this.stepStore.stepInputMapOver[this.stepId]).find((mapOver) => mapOver.isCollection))
         ) {
             this.stepStore.changeStepMapOver(this.stepId, effectiveMapOver);
         }

From fbebbb13c44ed917b79c81dee302fcc4b750bc2f Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 29 Jan 2023 15:49:31 +0100
Subject: [PATCH 332/350] Reset stores when receiving refactor action response

---
 client/src/components/Workflow/Editor/Index.vue | 1 +
 1 file changed, 1 insertion(+)

diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index 3f5f8e3fd41..a4be41fab7b 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -409,6 +409,7 @@ export default {
             hide_modal(); // hide other modals created in utilities also...
         },
         async onRefactor(response) {
+            this.resetStores();
             await fromSimple(response.workflow);
             this._loadEditorData(response.workflow);
         },

From 63b59f26cc0a0bb168b97ade5dcffdf3a3ef2df3 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Sun, 29 Jan 2023 15:51:53 +0100
Subject: [PATCH 333/350] Track input subworkflow step id

---
 client/src/stores/workflowConnectionStore.ts |  1 +
 client/src/stores/workflowStepStore.ts       | 20 +++++++++++++++++---
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/client/src/stores/workflowConnectionStore.ts b/client/src/stores/workflowConnectionStore.ts
index 7748a417e77..cacd54e14f6 100644
--- a/client/src/stores/workflowConnectionStore.ts
+++ b/client/src/stores/workflowConnectionStore.ts
@@ -34,6 +34,7 @@ export interface BaseTerminal {
 
 export interface InputTerminal extends BaseTerminal {
     connectorType: "input";
+    input_subworkflow_step_id?: number;
 }
 
 export interface OutputTerminal extends BaseTerminal {
diff --git a/client/src/stores/workflowStepStore.ts b/client/src/stores/workflowStepStore.ts
index 113f8f8ba01..20057d984f1 100644
--- a/client/src/stores/workflowStepStore.ts
+++ b/client/src/stores/workflowStepStore.ts
@@ -63,6 +63,7 @@ interface BaseStepInput {
     extensions: string[];
     optional: boolean;
     input_type: string;
+    input_subworkflow_step_id?: number;
 }
 
 export interface DataStepInput extends BaseStepInput {
@@ -125,6 +126,7 @@ export interface StepInputConnection {
 export interface ConnectionOutputLink {
     output_name: string;
     id: number;
+    input_subworkflow_step_id?: number;
 }
 
 interface WorkflowOutputs {
@@ -231,11 +233,19 @@ export const useWorkflowStepStore = defineStore("workflowStepStore", {
         },
         addConnection(connection: Connection) {
             const inputStep = this.getStep(connection.input.stepId);
+            const input = inputStep.inputs.find((input) => input.name === connection.input.name);
+            const connectionLink: ConnectionOutputLink = {
+                output_name: connection.output.name,
+                id: connection.output.stepId,
+            };
+            if (input && "input_subworkflow_step_id" in input && input.input_subworkflow_step_id !== undefined) {
+                connectionLink["input_subworkflow_step_id"] = input.input_subworkflow_step_id;
+            }
             const updatedStep = {
                 ...inputStep,
                 input_connections: {
                     ...inputStep.input_connections,
-                    [connection.input.name]: { output_name: connection.output.name, id: connection.output.stepId },
+                    [connection.input.name]: connectionLink,
                 },
             };
             this.updateStep(updatedStep);
@@ -258,7 +268,7 @@ export const useWorkflowStepStore = defineStore("workflowStepStore", {
 export function stepToConnections(step: Step): Connection[] {
     const connections: Connection[] = [];
     if (step.input_connections) {
-        Object.entries(step?.input_connections).forEach(([input_name, outputArray]) => {
+        Object.entries(step?.input_connections).forEach(([inputName, outputArray]) => {
             if (outputArray === undefined) {
                 return;
             }
@@ -269,7 +279,7 @@ export function stepToConnections(step: Step): Connection[] {
                 const connection = new Connection(
                     {
                         stepId: step.id,
-                        name: input_name,
+                        name: inputName,
                         connectorType: "input",
                     },
                     {
@@ -278,6 +288,10 @@ export function stepToConnections(step: Step): Connection[] {
                         connectorType: "output",
                     }
                 );
+                const connectionInput = step.inputs.find((input) => input.name == inputName);
+                if (connectionInput && "input_subworkflow_step_id" in connectionInput) {
+                    connection.input.input_subworkflow_step_id = connectionInput.input_subworkflow_step_id;
+                }
                 connections.push(connection);
             });
         });

From 1edefe8b3db3b34811d26f27d221b16a955bdd4b Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 30 Jan 2023 10:39:41 +0100
Subject: [PATCH 334/350] Fix test workflow input definitions

---
 lib/galaxy_test/api/test_workflows.py     | 3 +++
 lib/galaxy_test/base/workflow_fixtures.py | 1 +
 2 files changed, 4 insertions(+)

diff --git a/lib/galaxy_test/api/test_workflows.py b/lib/galaxy_test/api/test_workflows.py
index 4f5e1553325..92bbd17a2aa 100644
--- a/lib/galaxy_test/api/test_workflows.py
+++ b/lib/galaxy_test/api/test_workflows.py
@@ -2051,6 +2051,8 @@ steps:
       inputs:
         some_file:
           type: data
+        should_run:
+          type: boolean
       steps:
         a_tool_step:
           tool_id: cat1
@@ -2154,6 +2156,7 @@ steps:
       class: GalaxyWorkflow
       inputs:
         boolean_input_file: data
+        should_run: boolean
       steps:
         consume_expression_parameter:
           tool_id: cat1
diff --git a/lib/galaxy_test/base/workflow_fixtures.py b/lib/galaxy_test/base/workflow_fixtures.py
index 0178e935dae..0f164c087b0 100644
--- a/lib/galaxy_test/base/workflow_fixtures.py
+++ b/lib/galaxy_test/base/workflow_fixtures.py
@@ -1012,6 +1012,7 @@ steps:
       class: GalaxyWorkflow
       inputs:
         boolean_input_file: data
+        should_run: boolean
       steps:
         create_more_inputs:
           tool_id: collection_creates_dynamic_nested

From f624f188cbcb91f63b5a2f36038ffdf93b94820f Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 30 Jan 2023 12:44:05 +0100
Subject: [PATCH 335/350] Replace manual step watcher with step store
 subscription

---
 client/src/components/Workflow/Editor/Index.vue | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/client/src/components/Workflow/Editor/Index.vue b/client/src/components/Workflow/Editor/Index.vue
index a4be41fab7b..34362b5f2ff 100644
--- a/client/src/components/Workflow/Editor/Index.vue
+++ b/client/src/components/Workflow/Editor/Index.vue
@@ -254,6 +254,10 @@ export default {
         const hasChanges = ref(false);
         const hasInvalidConnections = computed(() => Object.keys(connectionsStore.invalidConnections).length > 0);
 
+        stepStore.$subscribe((mutation, state) => {
+            hasChanges.value = true;
+        });
+
         function resetStores() {
             connectionsStore.$reset();
             stepStore.$reset();
@@ -342,9 +346,6 @@ export default {
                 this.hasChanges = true;
             }
         },
-        steps(newSteps, oldSteps) {
-            this.hasChanges = true;
-        },
         hasChanges() {
             this.$emit("update:confirmation", this.hasChanges);
         },
@@ -357,7 +358,6 @@ export default {
     methods: {
         onUpdateStep(step) {
             this.stepStore.updateStep(step);
-            this.hasChanges = true;
         },
         onUpdateStepPosition(stepId, position) {
             const step = { ...this.steps[stepId], position };

From 4cac7c216ead1e3131a887416713a08b7a0ea522 Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 30 Jan 2023 12:59:19 +0100
Subject: [PATCH 336/350] Extend selenium tests and make sure
 input_subworkflow_step_id is passed

---
 lib/galaxy_test/selenium/test_workflow_editor.py | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/lib/galaxy_test/selenium/test_workflow_editor.py b/lib/galaxy_test/selenium/test_workflow_editor.py
index 9be68ab210c..eb40f60ff96 100644
--- a/lib/galaxy_test/selenium/test_workflow_editor.py
+++ b/lib/galaxy_test/selenium/test_workflow_editor.py
@@ -697,7 +697,10 @@ steps:
         workflow_populator.upload_yaml_workflow(WORKFLOW_OPTIONAL_TRUE_INPUT_COLLECTION, name=child_workflow_name)
         parent_workflow_id = workflow_populator.upload_yaml_workflow(
             """class: GalaxyWorkflow
-inputs: []
+inputs:
+  input_collection:
+    type: collection
+    collection_type: "list"
 steps:
   - tool_id: multiple_versions
     tool_version: 0.1
@@ -716,10 +719,16 @@ steps:
         self.sleep_for(self.wait_types.UX_RENDER)
         self.assert_workflow_has_changes_and_save()
         workflow = self.workflow_populator.download_workflow(parent_workflow_id)
-        subworkflow_step = workflow["steps"]["1"]
+        subworkflow_step = workflow["steps"]["2"]
         assert subworkflow_step["name"] == child_workflow_name
         assert subworkflow_step["type"] == "subworkflow"
         assert subworkflow_step["subworkflow"]["a_galaxy_workflow"] == "true"
+        self.workflow_editor_connect("input_collection#output", f"{child_workflow_name}#input1")
+        self.assert_connected("input_collection#output", f"{child_workflow_name}#input1")
+        self.assert_workflow_has_changes_and_save()
+        workflow = self.workflow_populator.download_workflow(parent_workflow_id)
+        subworkflow_step = workflow["steps"]["2"]
+        assert subworkflow_step["input_connections"]["input1"]["input_subworkflow_step_id"] == 0
 
     @selenium_test
     def test_editor_insert_steps(self):

From 32fc3b4b8bf63b6263bb2af8081a4df2749accab Mon Sep 17 00:00:00 2001
From: Oleg Zharkov <oleg.zharkov22@gmail.com>
Date: Mon, 30 Jan 2023 14:10:21 +0100
Subject: [PATCH 337/350] Import old screenshot generator

---
 .github/workflows/screenshot-producer.yml | 40 +++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 .github/workflows/screenshot-producer.yml

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
new file mode 100644
index 00000000000..5f572473803
--- /dev/null
+++ b/.github/workflows/screenshot-producer.yml
@@ -0,0 +1,40 @@
+on: [push, pull_request]
+name: tests
+jobs:
+  screenshooter:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        galaxy_version: [release_21.01]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.6
+
+      - name: create screenshots from ${{ matrix.galaxy_version }}
+        run: |
+          wget https://github.com/galaxyproject/galaxy/archive/${{ matrix.galaxy_version }}.tar.gz
+          tar xvzf ${{ matrix.galaxy_version }}.tar.gz | tail
+          cd galaxy-${{ matrix.galaxy_version }}
+          SCREENSHOTS_DIR=${{ github.workspace }}/screenshots
+          mkdir -p "$SCREENSHOTS_DIR"
+          GALAXY_TEST_SCREENSHOTS_DIRECTORY=$SCREENSHOTS_DIR ./run_tests.sh -selenium lib/galaxy_test/selenium -- -m gtn_screenshot -m local
+          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
+
+      - name: Upload screenshots to S3
+        run: |
+          echo $SCREENSHOTS_DIR
+          aws configure set aws_access_key_id ${{ secrets.TESTS_AWS_ACCESS_KEY_ID }}
+          aws configure set aws_secret_access_key ${{ secrets.TESTS_AWS_SECRET_KEY_ID }}
+          aws configure set default.region us-east-2
+          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/local --acl public-read
+          aws s3 ls s3://galaxy-tests
+
+      - name: Cache pip dir
+        uses: actions/cache@v2
+        with:
+          path: ${{ github.workspace }}/galaxy-${{ matrix.galaxy_version }}/.venv
+          key: pip-cache-${{ matrix.galaxy_version }}
\ No newline at end of file

From 58b1927b31408438d96c532119988eafa7e713e9 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:17:43 +0100
Subject: [PATCH 338/350] Update to take current version of Galaxy

---
 .github/workflows/screenshot-producer.yml | 28 ++++++++---------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index 5f572473803..def301c5ee3 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -3,26 +3,24 @@ name: tests
 jobs:
   screenshooter:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        galaxy_version: [release_21.01]
-
     steps:
       - uses: actions/checkout@v2
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
-          python-version: 3.6
+          python-version: 3.10
 
-      - name: create screenshots from ${{ matrix.galaxy_version }}
+      - name: create screenshots from current version
         run: |
-          wget https://github.com/galaxyproject/galaxy/archive/${{ matrix.galaxy_version }}.tar.gz
-          tar xvzf ${{ matrix.galaxy_version }}.tar.gz | tail
-          cd galaxy-${{ matrix.galaxy_version }}
-          SCREENSHOTS_DIR=${{ github.workspace }}/screenshots
+          # Setup environment
+          export GALAXY_VERSION=$(cat lib/galaxy/version.py | grep '^VERSION_MAJOR' | cut -d'"' -f 2)
+          export SCREENSHOTS_DIR=/tmp/screenshots
+          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
+          echo "GALAXY_VERSION=$GALAXY_VERSION" >> $GITHUB_ENV
+
+          # Take our screenshots
           mkdir -p "$SCREENSHOTS_DIR"
           GALAXY_TEST_SCREENSHOTS_DIRECTORY=$SCREENSHOTS_DIR ./run_tests.sh -selenium lib/galaxy_test/selenium -- -m gtn_screenshot -m local
-          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
 
       - name: Upload screenshots to S3
         run: |
@@ -30,11 +28,5 @@ jobs:
           aws configure set aws_access_key_id ${{ secrets.TESTS_AWS_ACCESS_KEY_ID }}
           aws configure set aws_secret_access_key ${{ secrets.TESTS_AWS_SECRET_KEY_ID }}
           aws configure set default.region us-east-2
-          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/local --acl public-read
+          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/${GALAXY_VERSION}/ --acl public-read
           aws s3 ls s3://galaxy-tests
-
-      - name: Cache pip dir
-        uses: actions/cache@v2
-        with:
-          path: ${{ github.workspace }}/galaxy-${{ matrix.galaxy_version }}/.venv
-          key: pip-cache-${{ matrix.galaxy_version }}
\ No newline at end of file

From f28063c6fe0b1ab8c255d7b4734268189d448127 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:19:39 +0100
Subject: [PATCH 339/350] Swap to cron, dispatch

---
 .github/workflows/screenshot-producer.yml | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index def301c5ee3..672654887ac 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -1,10 +1,21 @@
-on: [push, pull_request]
-name: tests
+name: Autogenerate UI screenshots for GTN Tutorials
+
+on:
+  schedule:
+    # Run mondays at noon.
+    - cron:  '0 12 * * 1'
+  workflow_dispatch:
+
 jobs:
   screenshooter:
+    if: github.repository_owner == 'galaxyproject'
     runs-on: ubuntu-latest
     steps:
+      # Shallow should be fine here.
       - uses: actions/checkout@v2
+        with:
+          fetch-depth: 500
+
       - name: Set up Python
         uses: actions/setup-python@v2
         with:

From cba9140534ea684c10108201c788a114a028563b Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:21:46 +0100
Subject: [PATCH 340/350] Only run on modern branches

---
 .github/workflows/screenshot-producer.yml | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index 672654887ac..37acd48ab8b 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -1,10 +1,12 @@
 name: Autogenerate UI screenshots for GTN Tutorials
 
 on:
-  schedule:
-    # Run mondays at noon.
-    - cron:  '0 12 * * 1'
   workflow_dispatch:
+  # Generate screenshots per release branch whenever they're updated
+  push:
+    branches:
+      - dev
+      - 'release_2*'
 
 jobs:
   screenshooter:

From 232a52e96c60410d045da873a1ae067997d42a66 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:25:02 +0100
Subject: [PATCH 341/350] Revert "Only run on modern branches"

This reverts commit cba9140534ea684c10108201c788a114a028563b.
---
 .github/workflows/screenshot-producer.yml | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index 37acd48ab8b..672654887ac 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -1,12 +1,10 @@
 name: Autogenerate UI screenshots for GTN Tutorials
 
 on:
+  schedule:
+    # Run mondays at noon.
+    - cron:  '0 12 * * 1'
   workflow_dispatch:
-  # Generate screenshots per release branch whenever they're updated
-  push:
-    branches:
-      - dev
-      - 'release_2*'
 
 jobs:
   screenshooter:

From 3edf6335137cd976557007471c47d86356c4db71 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:25:42 +0100
Subject: [PATCH 342/350] Revert "Swap to cron, dispatch"

This reverts commit f28063c6fe0b1ab8c255d7b4734268189d448127.
---
 .github/workflows/screenshot-producer.yml | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index 672654887ac..def301c5ee3 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -1,21 +1,10 @@
-name: Autogenerate UI screenshots for GTN Tutorials
-
-on:
-  schedule:
-    # Run mondays at noon.
-    - cron:  '0 12 * * 1'
-  workflow_dispatch:
-
+on: [push, pull_request]
+name: tests
 jobs:
   screenshooter:
-    if: github.repository_owner == 'galaxyproject'
     runs-on: ubuntu-latest
     steps:
-      # Shallow should be fine here.
       - uses: actions/checkout@v2
-        with:
-          fetch-depth: 500
-
       - name: Set up Python
         uses: actions/setup-python@v2
         with:

From 14a30b3d014a0ef262d5f3c6c43cf0e58cacc8e1 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:25:51 +0100
Subject: [PATCH 343/350] Revert "Update to take current version of Galaxy"

This reverts commit 58b1927b31408438d96c532119988eafa7e713e9.
---
 .github/workflows/screenshot-producer.yml | 28 +++++++++++++++--------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
index def301c5ee3..5f572473803 100644
--- a/.github/workflows/screenshot-producer.yml
+++ b/.github/workflows/screenshot-producer.yml
@@ -3,24 +3,26 @@ name: tests
 jobs:
   screenshooter:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        galaxy_version: [release_21.01]
+
     steps:
       - uses: actions/checkout@v2
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
-          python-version: 3.10
+          python-version: 3.6
 
-      - name: create screenshots from current version
+      - name: create screenshots from ${{ matrix.galaxy_version }}
         run: |
-          # Setup environment
-          export GALAXY_VERSION=$(cat lib/galaxy/version.py | grep '^VERSION_MAJOR' | cut -d'"' -f 2)
-          export SCREENSHOTS_DIR=/tmp/screenshots
-          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
-          echo "GALAXY_VERSION=$GALAXY_VERSION" >> $GITHUB_ENV
-
-          # Take our screenshots
+          wget https://github.com/galaxyproject/galaxy/archive/${{ matrix.galaxy_version }}.tar.gz
+          tar xvzf ${{ matrix.galaxy_version }}.tar.gz | tail
+          cd galaxy-${{ matrix.galaxy_version }}
+          SCREENSHOTS_DIR=${{ github.workspace }}/screenshots
           mkdir -p "$SCREENSHOTS_DIR"
           GALAXY_TEST_SCREENSHOTS_DIRECTORY=$SCREENSHOTS_DIR ./run_tests.sh -selenium lib/galaxy_test/selenium -- -m gtn_screenshot -m local
+          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
 
       - name: Upload screenshots to S3
         run: |
@@ -28,5 +30,11 @@ jobs:
           aws configure set aws_access_key_id ${{ secrets.TESTS_AWS_ACCESS_KEY_ID }}
           aws configure set aws_secret_access_key ${{ secrets.TESTS_AWS_SECRET_KEY_ID }}
           aws configure set default.region us-east-2
-          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/${GALAXY_VERSION}/ --acl public-read
+          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/local --acl public-read
           aws s3 ls s3://galaxy-tests
+
+      - name: Cache pip dir
+        uses: actions/cache@v2
+        with:
+          path: ${{ github.workspace }}/galaxy-${{ matrix.galaxy_version }}/.venv
+          key: pip-cache-${{ matrix.galaxy_version }}
\ No newline at end of file

From 32fa9d50278b888889a862ce119bdf745bd18131 Mon Sep 17 00:00:00 2001
From: Helena Rasche <hexylena@galaxians.org>
Date: Mon, 30 Jan 2023 14:26:01 +0100
Subject: [PATCH 344/350] Revert "Import old screenshot generator"

This reverts commit 32fc3b4b8bf63b6263bb2af8081a4df2749accab.
---
 .github/workflows/screenshot-producer.yml | 40 -----------------------
 1 file changed, 40 deletions(-)
 delete mode 100644 .github/workflows/screenshot-producer.yml

diff --git a/.github/workflows/screenshot-producer.yml b/.github/workflows/screenshot-producer.yml
deleted file mode 100644
index 5f572473803..00000000000
--- a/.github/workflows/screenshot-producer.yml
+++ /dev/null
@@ -1,40 +0,0 @@
-on: [push, pull_request]
-name: tests
-jobs:
-  screenshooter:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        galaxy_version: [release_21.01]
-
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.6
-
-      - name: create screenshots from ${{ matrix.galaxy_version }}
-        run: |
-          wget https://github.com/galaxyproject/galaxy/archive/${{ matrix.galaxy_version }}.tar.gz
-          tar xvzf ${{ matrix.galaxy_version }}.tar.gz | tail
-          cd galaxy-${{ matrix.galaxy_version }}
-          SCREENSHOTS_DIR=${{ github.workspace }}/screenshots
-          mkdir -p "$SCREENSHOTS_DIR"
-          GALAXY_TEST_SCREENSHOTS_DIRECTORY=$SCREENSHOTS_DIR ./run_tests.sh -selenium lib/galaxy_test/selenium -- -m gtn_screenshot -m local
-          echo "SCREENSHOTS_DIR=$SCREENSHOTS_DIR" >> $GITHUB_ENV
-
-      - name: Upload screenshots to S3
-        run: |
-          echo $SCREENSHOTS_DIR
-          aws configure set aws_access_key_id ${{ secrets.TESTS_AWS_ACCESS_KEY_ID }}
-          aws configure set aws_secret_access_key ${{ secrets.TESTS_AWS_SECRET_KEY_ID }}
-          aws configure set default.region us-east-2
-          aws s3 cp --recursive $SCREENSHOTS_DIR s3://galaxy-tests/galaxy-gtn-screenshots/local --acl public-read
-          aws s3 ls s3://galaxy-tests
-
-      - name: Cache pip dir
-        uses: actions/cache@v2
-        with:
-          path: ${{ github.workspace }}/galaxy-${{ matrix.galaxy_version }}/.venv
-          key: pip-cache-${{ matrix.galaxy_version }}
\ No newline at end of file

From 118855d5705d79fa3b1b4d972772a663c1a8161e Mon Sep 17 00:00:00 2001
From: mvdbeek <m.vandenbeek@gmail.com>
Date: Mon, 6 Dec 2021 15:59:03 +0100
Subject: [PATCH 345/350] Serialize tools via json, not pickle

I assume we don't need to maintain comments for this kind of
serialization.
---
 lib/galaxy/tool_util/cwl/parser.py | 67 +++++++++---------------------
 1 file changed, 20 insertions(+), 47 deletions(-)

diff --git a/lib/galaxy/tool_util/cwl/parser.py b/lib/galaxy/tool_util/cwl/parser.py
index 467c6070f66..5f0bd18563c 100644
--- a/lib/galaxy/tool_util/cwl/parser.py
+++ b/lib/galaxy/tool_util/cwl/parser.py
@@ -4,12 +4,10 @@ adapt cwltool to Galaxy features and abstract the library away from the rest
 of the framework.
 """
 
-import base64
 import copy
 import json
 import logging
 import os
-import pickle
 from abc import (
     ABCMeta,
     abstractmethod,
@@ -31,7 +29,6 @@ from galaxy.exceptions import MessageException
 from galaxy.util import (
     listify,
     safe_makedirs,
-    unicodify,
 )
 from galaxy.util.bunch import Bunch
 from .cwltool_deps import (
@@ -86,8 +83,6 @@ SUPPORTED_TOOL_REQUIREMENTS = [
 
 SUPPORTED_WORKFLOW_REQUIREMENTS = SUPPORTED_TOOL_REQUIREMENTS + []
 
-PERSISTED_REPRESENTATION = "cwl_tool_object"
-
 ToolStateType = Dict[str, Union[None, str, bool, Dict[str, str]]]
 
 
@@ -173,29 +168,29 @@ class ToolProxy(metaclass=ABCMeta):
     def to_persistent_representation(self):
         """Return a JSON representation of this tool. Not for serialization
         over the wire, but serialization in a database."""
-        # TODO: Replace this with some more readable serialization,
-        # I really don't like using pickle here.
-        if PERSISTED_REPRESENTATION == "cwl_tool_object":
-            persisted_obj = remove_pickle_problems(self._tool)
-        else:
-            persisted_obj = self._raw_process_reference
+        persisted_obj = self._tool.tool
+        persisted_obj["requirements"] = self.requirements
+        if not persisted_obj.get("cwlVersion"):
+            # This happens for any inline process, but getting it from metadata is correct for inline processes at least
+            persisted_obj["cwlVersion"] = self._tool.metadata["cwlVersion"]
         return {
             "class": self._class,
-            "pickle": unicodify(base64.b64encode(pickle.dumps(persisted_obj, pickle.HIGHEST_PROTOCOL))),
+            # Should maybe be yaml instead
+            "raw_process_reference": persisted_obj,
             "uuid": self.uuid,
         }
 
     @staticmethod
-    def from_persistent_representation(as_object) -> "ToolProxy":
+    def from_persistent_representation(as_object, strict_cwl_validation=True, tool_directory=None) -> "ToolProxy":
         """Recover an object serialized with to_persistent_representation."""
         if "class" not in as_object:
             raise Exception("Failed to deserialize tool proxy from JSON object - no class found.")
-        if "pickle" not in as_object:
-            raise Exception("Failed to deserialize tool proxy from JSON object - no pickle representation found.")
-        if "uuid" not in as_object:
-            raise Exception("Failed to deserialize tool proxy from JSON object - no uuid found.")
-        to_unpickle = base64.b64decode(as_object["pickle"])
-        loaded_object = pickle.loads(to_unpickle)
+        loaded_object = tool_proxy(
+            tool_object=as_object["raw_process_reference"],
+            strict_cwl_validation=strict_cwl_validation,
+            tool_directory=tool_directory,
+            uuid=as_object.get("uuid"),
+        )
         return loaded_object
 
     @property
@@ -743,14 +738,8 @@ def tool_proxy_from_persistent_representation(
 ) -> ToolProxy:
     """Load a ToolProxy from a previously persisted representation."""
     ensure_cwltool_available()
-    if PERSISTED_REPRESENTATION == "cwl_tool_object":
-        kwds = {"cwl_tool_object": ToolProxy.from_persistent_representation(persisted_tool)}
-    else:
-        raw_process_reference = persisted_tool  # ???
-        kwds = {"raw_process_reference": ToolProxy.from_persistent_representation(raw_process_reference)}
-    uuid = persisted_tool["uuid"]
-    return _to_cwl_tool_object(
-        uuid=uuid, strict_cwl_validation=strict_cwl_validation, tool_directory=tool_directory, **kwds
+    return ToolProxy.from_persistent_representation(
+        persisted_tool, strict_cwl_validation=strict_cwl_validation, tool_directory=tool_directory
     )
 
 
@@ -765,15 +754,10 @@ def load_job_proxy(job_directory, strict_cwl_validation=True) -> JobProxy:
     job_objects = json.load(open(job_objects_path))
     job_inputs = job_objects["job_inputs"]
     output_dict = job_objects["output_dict"]
-    # Any reason to retain older tool_path variant of this? Probably not?
-    if "tool_path" in job_objects:
-        tool_path = job_objects["tool_path"]
-        cwl_tool = tool_proxy(tool_path, strict_cwl_validation=strict_cwl_validation)
-    else:
-        persisted_tool = job_objects["tool_representation"]
-        cwl_tool = tool_proxy_from_persistent_representation(
-            persisted_tool=persisted_tool, strict_cwl_validation=strict_cwl_validation
-        )
+    persisted_tool = job_objects["tool_representation"]
+    cwl_tool = tool_proxy_from_persistent_representation(
+        persisted_tool=persisted_tool, strict_cwl_validation=strict_cwl_validation
+    )
     return cwl_tool.job_proxy(job_inputs, output_dict, job_directory=job_directory)
 
 
@@ -1107,17 +1091,6 @@ class SubworkflowStepProxy(BaseStepProxy):
         return self._subworkflow_proxy
 
 
-def remove_pickle_problems(obj):
-    """doc_loader does not pickle correctly"""
-    if hasattr(obj, "doc_loader"):
-        obj.doc_loader = None
-    if hasattr(obj, "embedded_tool"):
-        obj.embedded_tool = remove_pickle_problems(obj.embedded_tool)
-    if hasattr(obj, "steps"):
-        obj.steps = [remove_pickle_problems(s) for s in obj.steps]
-    return obj
-
-
 def _outer_field_to_input_instance(field):
     field_type = field_to_field_type(field)  # Must be a list if in here?
     if not isinstance(field_type, list):

From cf36e5d4462234b0bf95eaf3958b3bbf75dc28c6 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Mon, 30 Jan 2023 11:49:32 -0500
Subject: [PATCH 346/350] Add .prettierignore and swap to excludes instead of
 includes mechanism

---
 client/.prettierignore | 16 ++++++++++++++++
 client/package.json    |  4 ++--
 2 files changed, 18 insertions(+), 2 deletions(-)
 create mode 100644 client/.prettierignore

diff --git a/client/.prettierignore b/client/.prettierignore
new file mode 100644
index 00000000000..95fb6f29303
--- /dev/null
+++ b/client/.prettierignore
@@ -0,0 +1,16 @@
+# Standard ignores
+**/.git
+**/.svn
+**/.hg
+**/node_modules
+# Ignore the dist folder
+**/dist
+# We will always defer to package manager for formatting of package.json files.
+**/package.json
+# Skip formatting of explicitly included libs (to stay in sync with upstream, and they should go away eventually)
+src/libs
+# Don't reformat .json or .yml files included in the project
+*.json
+*.yml
+# Might be nice to add markdown formatting eventually?
+*.md
\ No newline at end of file
diff --git a/client/package.json b/client/package.json
index ca7c9ee3630..6e3f76bfc7e 100644
--- a/client/package.json
+++ b/client/package.json
@@ -123,8 +123,8 @@
     "webpack-production-maps": "GXY_BUILD_SOURCEMAPS=1 NODE_ENV=production webpack",
     "gulp": "gulp",
     "stage-build": "cpy 'dist/*' '../static/dist' && (git rev-parse HEAD 2>/dev/null || echo '') >../static/client_build_hash.txt",
-    "format": "prettier --write 'src/style/scss/**/*.scss' 'src/**/{*.ts,*.js,*.vue}' 'tests/jest/standalone/{*.ts,*.js}' '!src/libs/**'",
-    "format-check": "prettier --check 'src/style/scss/**/*.scss' 'src/**/{*.js,*.vue}' 'tests/jest/standalone/{*.ts,*.js}' '!src/libs/**'",
+    "format": "prettier --write .",
+    "format-check": "prettier --check .",
     "prettier": "yarn run format",
     "test": "yarn run qunit && yarn run jest",
     "jest": "jest --config tests/jest/jest.config.js",

From ef49ada44b217d081e791a055d1dfe28a235f0b8 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Mon, 30 Jan 2023 11:49:51 -0500
Subject: [PATCH 347/350] Rerun prettier

---
 client/prettier.config.js                     |  2 +-
 .../LibraryFolder/library-folder-table.css    |  9 ++++-----
 client/tests/jest/__mocks__/config.js         |  6 +++---
 client/tests/jest/__mocks__/trackster.js      |  2 +-
 client/tests/jest/jest-raw-loader.js          |  4 +++-
 client/tests/jest/jest.setup.js               |  2 +-
 client/tests/jest/yaml-jest.js                | 20 +++++++++----------
 .../paired-collection-creator.data.js         | 18 ++++++++---------
 client/types/globals.d.ts                     |  4 ++--
 client/types/shim-vue.d.ts                    |  4 ++--
 client/types/types.d.ts                       |  6 +++---
 11 files changed, 39 insertions(+), 38 deletions(-)

diff --git a/client/prettier.config.js b/client/prettier.config.js
index df792433737..d9cc69f4d8c 100644
--- a/client/prettier.config.js
+++ b/client/prettier.config.js
@@ -1,5 +1,5 @@
 module.exports = {
     tabWidth: 4,
     printWidth: 120,
-    bracketSameLine: true
+    bracketSameLine: true,
 };
diff --git a/client/src/components/Libraries/LibraryFolder/library-folder-table.css b/client/src/components/Libraries/LibraryFolder/library-folder-table.css
index ec0b864166e..ba412838b8e 100644
--- a/client/src/components/Libraries/LibraryFolder/library-folder-table.css
+++ b/client/src/components/Libraries/LibraryFolder/library-folder-table.css
@@ -3,15 +3,15 @@ th:focus {
 }
 
 .pagination-input-field {
-    max-width: 60px
+    max-width: 60px;
 }
 
 .pagination-total-pages-text {
-    margin-left: .25rem;
+    margin-left: 0.25rem;
 }
 
 .more-text-btn {
-    margin-left: .25rem;
+    margin-left: 0.25rem;
     font-size: 60%;
     color: grey;
 }
@@ -20,7 +20,6 @@ th:focus {
     width: 40rem;
 }
 
-
 .empty-folder-message {
     text-align: center;
 }
@@ -34,5 +33,5 @@ th:focus {
 }
 
 .lib-btn {
-    margin-bottom: 2%
+    margin-bottom: 2%;
 }
diff --git a/client/tests/jest/__mocks__/config.js b/client/tests/jest/__mocks__/config.js
index 0aaa35c1744..61763815697 100644
--- a/client/tests/jest/__mocks__/config.js
+++ b/client/tests/jest/__mocks__/config.js
@@ -5,6 +5,6 @@ export default {
     caching: {
         adapter: "memory",
         revs_limit: 1,
-        pageSize: 50
-    }
-}
+        pageSize: 50,
+    },
+};
diff --git a/client/tests/jest/__mocks__/trackster.js b/client/tests/jest/__mocks__/trackster.js
index 34f0f96bfab..ce75d703b2b 100644
--- a/client/tests/jest/__mocks__/trackster.js
+++ b/client/tests/jest/__mocks__/trackster.js
@@ -8,4 +8,4 @@ export class TracksterUI extends Backbone.Model {
     initialize(baseURL) {
         this.baseURL = baseURL;
     }
-}
\ No newline at end of file
+}
diff --git a/client/tests/jest/jest-raw-loader.js b/client/tests/jest/jest-raw-loader.js
index 3ef7c744106..087224e0497 100644
--- a/client/tests/jest/jest-raw-loader.js
+++ b/client/tests/jest/jest-raw-loader.js
@@ -1,3 +1,5 @@
 module.exports = {
-  process: content => { return { code: "module.exports = " + JSON.stringify(content)}}
+    process: (content) => {
+        return { code: "module.exports = " + JSON.stringify(content) };
+    },
 };
diff --git a/client/tests/jest/jest.setup.js b/client/tests/jest/jest.setup.js
index 474a5845a15..3dda52917b4 100644
--- a/client/tests/jest/jest.setup.js
+++ b/client/tests/jest/jest.setup.js
@@ -1,5 +1,5 @@
 import "@testing-library/jest-dom";
-import Vue from 'vue';
+import Vue from "vue";
 
 // Set Vue to suppress production / devtools / etc. warnings
 Vue.config.productionTip = false;
diff --git a/client/tests/jest/yaml-jest.js b/client/tests/jest/yaml-jest.js
index 8e84063fe5b..2034043ff0e 100644
--- a/client/tests/jest/yaml-jest.js
+++ b/client/tests/jest/yaml-jest.js
@@ -1,13 +1,13 @@
-const transformer = require("yaml-jest").default
+const transformer = require("yaml-jest").default;
 
 const newTransformer = {
-  ...transformer,
-  process: function (...params) {
-    return {
-      code: transformer?.process(...params),
-      map: null,
-    }
-  },
-}
+    ...transformer,
+    process: function (...params) {
+        return {
+            code: transformer?.process(...params),
+            map: null,
+        };
+    },
+};
 
-module.exports = newTransformer
+module.exports = newTransformer;
diff --git a/client/tests/qunit/test-data/paired-collection-creator.data.js b/client/tests/qunit/test-data/paired-collection-creator.data.js
index a6c3c954568..1e2638c8a75 100644
--- a/client/tests/qunit/test-data/paired-collection-creator.data.js
+++ b/client/tests/qunit/test-data/paired-collection-creator.data.js
@@ -19,23 +19,23 @@ var datasets1 = [
 ];
 
 var datasets2 = [
-    { name: "DP134_1_FS_PSII_FSB_42C_A10.1.fastq", state: STATES.OK},
-    { name: "DP134_1_FS_PSII_FSB_42C_A10.2.fastq", state: STATES.OK}
-]
+    { name: "DP134_1_FS_PSII_FSB_42C_A10.1.fastq", state: STATES.OK },
+    { name: "DP134_1_FS_PSII_FSB_42C_A10.2.fastq", state: STATES.OK },
+];
 
 var datasets3 = [
-    {name: "UII_moo_1.1.fastq", state: STATES.OK},
-    {name: "UII_moo_1.2.fastq", state: STATES.OK}
-]
+    { name: "UII_moo_1.1.fastq", state: STATES.OK },
+    { name: "UII_moo_1.2.fastq", state: STATES.OK },
+];
 
-var datasets4= [
+var datasets4 = [
     { name: "SET1-01_R1.fastq", state: STATES.OK },
     { name: "SET1-01_R2.fastq", state: STATES.OK },
     { name: "SET1-02_R1.fastq", state: STATES.OK },
     { name: "SET1-02_R2.fastq", state: STATES.OK },
     { name: "SET1-03_R1.fastq", state: STATES.OK },
     { name: "SET1-03_R2.fastq", state: STATES.OK },
-]
+];
 
 var datasets1CreateRequestJSON = {
     type: "dataset_collection",
@@ -171,5 +171,5 @@ export default {
     _1requestJSON: datasets1CreateRequestJSON,
     _2: datasets2,
     _3: datasets3,
-    _4: datasets4
+    _4: datasets4,
 };
diff --git a/client/types/globals.d.ts b/client/types/globals.d.ts
index abf750be2e1..97ec1d6ccf9 100644
--- a/client/types/globals.d.ts
+++ b/client/types/globals.d.ts
@@ -1,4 +1,4 @@
 // Webpack-injected globals.
-declare const __webpack_public_path__:string;
+declare const __webpack_public_path__: string;
 declare const __buildTimestamp__: string;
-declare const __license__: string;
\ No newline at end of file
+declare const __license__: string;
diff --git a/client/types/shim-vue.d.ts b/client/types/shim-vue.d.ts
index 0660bd67a54..d6e6b864e50 100644
--- a/client/types/shim-vue.d.ts
+++ b/client/types/shim-vue.d.ts
@@ -1,4 +1,4 @@
 declare module "*.vue" {
-  import Vue from "vue";
-  export default Vue;
+    import Vue from "vue";
+    export default Vue;
 }
diff --git a/client/types/types.d.ts b/client/types/types.d.ts
index efe9231ef21..423222e511c 100644
--- a/client/types/types.d.ts
+++ b/client/types/types.d.ts
@@ -1,4 +1,4 @@
-declare module '*.yml' {
-    const data: any
-    export default data
+declare module "*.yml" {
+    const data: any;
+    export default data;
 }

From 45d71eb01b102c10477fb0c9de828713240ceeb6 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Mon, 30 Jan 2023 11:50:12 -0500
Subject: [PATCH 348/350] Test including markdown in formatting

---
 client/.prettierignore                        |  4 +-
 client/README.md                              |  4 +-
 client/docs/avoid-using-global-Galaxy.md      | 19 ++++-----
 client/docs/composables.md                    | 18 ++++----
 client/docs/headings.md                       | 28 ++++++-------
 client/docs/never-use-jquery.md               |  7 ++--
 client/docs/providers-and-renderers.md        | 41 ++++++++-----------
 client/docs/readme.md                         | 17 ++++----
 client/docs/styleguide.md                     | 22 ++++------
 .../docs/unit-testing/debugging-unit-tests.md | 15 +++----
 client/docs/unit-testing/readme.md            | 20 ++++-----
 client/docs/unit-testing/strategies.md        |  6 +--
 client/docs/unit-testing/writing-tests.md     | 16 +++-----
 client/src/components/Alert.md                |  2 +-
 client/src/components/History/README.md       |  9 ++--
 .../Workflow/Editor/modules/terminals.ts      |  4 +-
 16 files changed, 100 insertions(+), 132 deletions(-)

diff --git a/client/.prettierignore b/client/.prettierignore
index 95fb6f29303..bc99ee79eab 100644
--- a/client/.prettierignore
+++ b/client/.prettierignore
@@ -11,6 +11,4 @@
 src/libs
 # Don't reformat .json or .yml files included in the project
 *.json
-*.yml
-# Might be nice to add markdown formatting eventually?
-*.md
\ No newline at end of file
+*.yml
\ No newline at end of file
diff --git a/client/README.md b/client/README.md
index aec3f0f8622..abb2741ce1b 100644
--- a/client/README.md
+++ b/client/README.md
@@ -61,7 +61,7 @@ Or, with the package scripts from this `client` directory:
 
 This will start up an extra client development server running on port 8081. Open
 your browser to `http://localhost:8081` (instead of the default 8080 that Galaxy
-would run on), and you should see Galaxy like normal.  Except now, when you
+would run on), and you should see Galaxy like normal. Except now, when you
 change client code it'll automatically rebuild _and_ reload the relevant portion
 of the application for you. Lastly, if you are running Galaxy at a location
 other than the default, you can specify a different proxy target (in this
@@ -119,7 +119,7 @@ framework.
 
 For testing Vue components, we use the [Vue testing
 utils](https://vue-test-utils.vuejs.org/) to mount individual components in a
-test bed and check them for rendered features.  Please use jest-based mocking
+test bed and check them for rendered features. Please use jest-based mocking
 for isolating test functionality.
 
 A set of older qUnit tests also exist which will be phased-out as the code they
diff --git a/client/docs/avoid-using-global-Galaxy.md b/client/docs/avoid-using-global-Galaxy.md
index 2a19a2597c7..3092190ce58 100644
--- a/client/docs/avoid-using-global-Galaxy.md
+++ b/client/docs/avoid-using-global-Galaxy.md
@@ -9,17 +9,17 @@ you access to the Galaxy.config, current user, and current user histories. Pleas
 retrieve your values, and bypass importing Galaxy altogether.
 
 #### Sometimes you still need to update Vue from backbone as the legacy environment changes
+
 There are definitely use-cases where the Backbone models update over time and we need to update some
 value inside Vue. Instead of importing backbone models directly into Vue components, try building a
 backbone event listener that updates some relevant Vuex store.
 
-* [Keeping Vuex in Sync with
-  Galaxy](https://github.com/galaxyproject/galaxy/blob/dev/client/src/store/syncVuexToGalaxy.js)
+-   [Keeping Vuex in Sync with
+    Galaxy](https://github.com/galaxyproject/galaxy/blob/dev/client/src/store/syncVuexToGalaxy.js)
 
 These issues should disappear over time as the all of the old client is rebuilt in the new
 ecosystem.
 
-
 ## Mount Functions
 
 In what most people think of as a "standard" Vue application there would be only one place that Vue
@@ -30,7 +30,6 @@ However, we are incrementally replacing old Backbone views, so in its current st
 several mounting functions for various components depending on where that component is intended to
 fit into the existing Backbone layouts.
 
-
 ### Using the standard mount to pass in Galaxy variables as props
 
 A standard mount function has been provided in src/utils. This mount function accepts a component
@@ -46,28 +45,26 @@ import MyComponent from "components/MyComponent";
 import { mountVueComponent } from "utils/mountVueComponent";
 
 const OldBackboneView = {
-
     someInitMethodYouMake() {
         const Galaxy = getGalaxyInstance();
         const mounter = mountVueComponent(MyComponent);
 
         // pass in required props
-        const props = { 
-
+        const props = {
             // Something peeled off the global galaxy
-            somePropVal: Galaxy.someDealie, 
+            somePropVal: Galaxy.someDealie,
 
             // ...or the current history
             name: Galaxy.currentHistory.name,
 
             // or maybe from the backbone model for this view
-            shoeSize: this.model.shoeSize
+            shoeSize: this.model.shoeSize,
         };
 
         // VM is a Vue instance.
         // this.$el is some jquery selection, first item is the actual DOM object
         const container = this.$el[0];
         const vm = mounter(props, container);
-    }
-}
+    },
+};
 ```
diff --git a/client/docs/composables.md b/client/docs/composables.md
index a7a22b5c6d3..248e30f5575 100644
--- a/client/docs/composables.md
+++ b/client/docs/composables.md
@@ -6,9 +6,9 @@ Using them effectively can make your code more reusable, decoupled, and easier t
 
 **More about Composables:**
 
-* [Composables Overview](https://vuejs.org/guide/reusability/composables.html)
-* [Composition API](https://vuejs.org/api/composition-api-setup.html)
-* [\<script setup\>](https://vuejs.org/api/sfc-script-setup.html)
+-   [Composables Overview](https://vuejs.org/guide/reusability/composables.html)
+-   [Composition API](https://vuejs.org/api/composition-api-setup.html)
+-   [\<script setup\>](https://vuejs.org/api/sfc-script-setup.html)
 
 ## Using Composables in the Composition API
 
@@ -36,8 +36,8 @@ export default {
     setup() {
         const { currentUser } = useCurrentUser();
         return { currentUser };
-    }
-}
+    },
+};
 </script>
 ```
 
@@ -79,7 +79,7 @@ import { useCurrentUser } from "composables/user";
 
 jest.mock("composables/user");
 useCurrentUser.mockReturnValue({
-    currentUser: {}
+    currentUser: {},
 });
 ```
 
@@ -95,11 +95,7 @@ Usage:
 <script setup>
 import { useFilterObjectArray } from "composables/utils/filter";
 
-const filteredArray = useFilterObjectArray(
-    someReactiveArray,
-    searchValue,
-    ["name", "description"]
-);
+const filteredArray = useFilterObjectArray(someReactiveArray, searchValue, ["name", "description"]);
 </script>
 ```
 
diff --git a/client/docs/headings.md b/client/docs/headings.md
index a7cf82bfb14..87538b3d8a6 100644
--- a/client/docs/headings.md
+++ b/client/docs/headings.md
@@ -6,23 +6,23 @@ Heading Levels are used by screen readers, and other software, to get a rough id
 
 ## Heading Level best practices
 
- - Make sure every route has exactly one `<h1>` element, which best describes the content of the current page.
+-   Make sure every route has exactly one `<h1>` element, which best describes the content of the current page.
 
- - When increasing a heading level, do not skip Levels.
+-   When increasing a heading level, do not skip Levels.
 
- - Do not use a headings level to determine it's size. Use one of the heading utility classes (e.g. `h-lg`) instead.
+-   Do not use a headings level to determine it's size. Use one of the heading utility classes (e.g. `h-lg`) instead.
 
- - Do not use a heading tag to make a non-heading text large. Use a heading utility class on a `<span>` instead.
+-   Do not use a heading tag to make a non-heading text large. Use a heading utility class on a `<span>` instead.
 
 ## Sizing Headings
 
 There are several utility classes which size headings:
 
- - `h-xl` - Extra large headings
- - `h-lg` - Large headings (most main headings should have this size)
- - `h-md` - Medium headings
- - `h-sm` - Small headings (many sub-headings have this size)
- - `h-text` - Text sized headings
+-   `h-xl` - Extra large headings
+-   `h-lg` - Large headings (most main headings should have this size)
+-   `h-md` - Medium headings
+-   `h-sm` - Small headings (many sub-headings have this size)
+-   `h-text` - Text sized headings
 
 Galaxy uses `h-lg` for most top-level (`<h1>`) headings.
 
@@ -45,8 +45,8 @@ Set the headings level, by setting aa `h1 ... h6` prop:
 
 Following properties allow for further styling the component:
 
- - `size=["xl", "lg", "md", "sm", "text"]` - sets the headings size class
- - `bold` - makes a heading bold
- - `inline` - displays the heading inline
- - `separator` - draws a separating line, to better distinguish sections
- - `icon="..."` - adds a font-awesome icon decoration to the left of the heading. Make sure to also load the icon with `library.add(...)`.
+-   `size=["xl", "lg", "md", "sm", "text"]` - sets the headings size class
+-   `bold` - makes a heading bold
+-   `inline` - displays the heading inline
+-   `separator` - draws a separating line, to better distinguish sections
+-   `icon="..."` - adds a font-awesome icon decoration to the left of the heading. Make sure to also load the icon with `library.add(...)`.
diff --git a/client/docs/never-use-jquery.md b/client/docs/never-use-jquery.md
index c1e07181928..df7a5370da5 100644
--- a/client/docs/never-use-jquery.md
+++ b/client/docs/never-use-jquery.md
@@ -1,6 +1,6 @@
 Did you know, jQuery is old enough to drive? It's old enough to get a driver's license. jQuery is a
 tool that was built to deal with inconsistencies in browsers that NO LONGER EXIST. In a couple
-years, jQuery will be voting, drinking, and capable of being tried as an adult. 
+years, jQuery will be voting, drinking, and capable of being tried as an adult.
 
 If you think you need jQuery, you are mistaken. Please seek help from somebody in the wg-ui-ux
 workgroup. There is nothing jQuery can provide you that isn't already part of vanilla javascript or
@@ -14,5 +14,6 @@ One of our most important goals in redesigning Galaxy is the complete eliminatio
 from our source, along with all its invasive plugins.
 
 ### References
-* [You Don't Need jQuery](https://github.com/nefe/You-Dont-Need-jQuery)
-* [document.querySelector](https://developer.mozilla.org/en-US/docs/Web/API/Document/querySelector)
\ No newline at end of file
+
+-   [You Don't Need jQuery](https://github.com/nefe/You-Dont-Need-jQuery)
+-   [document.querySelector](https://developer.mozilla.org/en-US/docs/Web/API/Document/querySelector)
diff --git a/client/docs/providers-and-renderers.md b/client/docs/providers-and-renderers.md
index 1eca93b3e13..2637fcbf9f9 100644
--- a/client/docs/providers-and-renderers.md
+++ b/client/docs/providers-and-renderers.md
@@ -22,34 +22,27 @@ component we previously made, but you are free to putput whatever you want in th
 doodad and saveDoddad properties as desired, as well as any other local data with the only
 restriction that Vue needs a single root element in which to render.
 
-
 ## The Renderer
 
 ```html static
 <!-- DoodadEditor.vue, a simple "rendering" component -->
 
 <template>
-    <AutoComplete
-        :options="options"
-        :value="doodad.category"
-        @select="saveCategory"
-    />
+    <AutoComplete :options="options" :value="doodad.category" @select="saveCategory" />
 </template>
 
 <script>
-
-export default {
-    props: {
-        doodad: { type: Object, required: true },
-        options: { type: Array, required: true },
-    },
-    methods: {
-        saveCategory(newCategory) {
-            this.$emit('update:doodad', { ...this.doodad, category: newCategory });
-        }
-    }
-}
-
+    export default {
+        props: {
+            doodad: { type: Object, required: true },
+            options: { type: Array, required: true },
+        },
+        methods: {
+            saveCategory(newCategory) {
+                this.$emit("update:doodad", { ...this.doodad, category: newCategory });
+            },
+        },
+    };
 </script>
 ```
 
@@ -66,7 +59,6 @@ binds](https://vuejs.org/v2/guide/components-custom-events.html#sync-Modifier)).
 Whatever happens to that new object is somebody else's job. As soon as you tie the data management
 to the rendering, the re-usability of your components craters.
 
-
 ## The Provider
 
 As the opposite of the rendering component, a provider or renderless component, is pure logic. It
@@ -76,7 +68,6 @@ functionality available in Vue. Some others are [Mixins](https://vuejs.org/v2/gu
 [Provide/Inject](https://v3.vuejs.org/guide/component-provide-inject.html) and (in Vue3) [the
 composition API](https://v3.vuejs.org/guide/composition-api-introduction.html).
 
-
 ```js static
 // DoodadProvider.js
 
@@ -134,7 +125,7 @@ mandatory markup, just one big empty slot.
 // Testing a renderless component
 
 import { shallowMount } from "@vue/test-utils";
-import { getLocalVue, waitForLifecyleEvent } from "tests/jest/helpers"
+import { getLocalVue, waitForLifecyleEvent } from "tests/jest/helpers";
 import DoodadProvider from "./DoodadProvider";
 
 describe("A renderless component", () => {
@@ -157,12 +148,12 @@ describe("A renderless component", () => {
         // component. This is often good enough for waiting for
         // an initial ajax load to finish, for example
         await waitForLifecyleEvent(wrapper.vm, "updated");
-    })
+    });
 
     test("someProp", () => {
         const { someProp } = slotProps;
         expect(someProp).toExist();
         // ...more tests
-    })
-})
+    });
+});
 ```
diff --git a/client/docs/readme.md b/client/docs/readme.md
index dba0f97c1e1..e7442b5637b 100644
--- a/client/docs/readme.md
+++ b/client/docs/readme.md
@@ -5,7 +5,7 @@ I'm not talking about how webpack turns it into a rendering function. That's obv
 I mean conceptually, props come in (like arguments) and events go out (like the return statements).
 A component is a fancy kind of function that can keep emitting results and accept changing inputs
 over time. In truth it more closely resembles an Observable, but an observable is ALSO a slightly
-fancier kind of function. 
+fancier kind of function.
 
 If you just think of a component as thing that takes input props and emits output events you're well
 on your way to using them well.
@@ -19,22 +19,22 @@ problems of the old imperative class-based legacy code.
 New vue programmers are ok at handing props to components, but they rarely use events effectively
 (at first). As a result they end up using a lot of global state, a million little data props and
 relying on imperfect globalized tools like Vuex or other imported dependencies for every little
-variable. 
+variable.
 
 Vuex definitely has its uses, but not as many as you might expect given the way it is
 overly-emphasized in common tutorials. It's easy to walk away from an "Intro to Vue" video with the
-idea that all data must live in Vuex all the time. That's a really undesirable situation. 
+idea that all data must live in Vuex all the time. That's a really undesirable situation.
 
 Although vuex is a well-organized (many would say over-organized) state machine, it is important
 to remember that it is still a kind of global injection and deserves to be considered as such.
 
-* [Should I Store This Data in
-  Vuex](https://markus.oberlehner.net/blog/should-i-store-this-data-in-vuex/)
-* [Vuex getters are great, but don’t overuse
-  them](https://codeburst.io/vuex-getters-are-great-but-dont-overuse-them-9c946689b414)
+-   [Should I Store This Data in
+    Vuex](https://markus.oberlehner.net/blog/should-i-store-this-data-in-vuex/)
+-   [Vuex getters are great, but don’t overuse
+    them](https://codeburst.io/vuex-getters-are-great-but-dont-overuse-them-9c946689b414)
 
 Data persistence should be something that happens near the top of your component tree, not down in
-the guts. 
+the guts.
 
 Your first thought with a component should be: "How can I offload the handling of the results of
 this component to my caller?" The answer is usually going to be events. A component that simply
@@ -46,7 +46,6 @@ global state to operate.
 They're just fancy shorthands for a prop / event handler combination. They are fundamentally no
 different from props and events, but the syntax is important to understand.
 
-
 ### Think carefully about what should really be in "data".
 
 Most of good component design boils down to answering the following question: What do I want to put
diff --git a/client/docs/styleguide.md b/client/docs/styleguide.md
index 938ed22fc23..d158fd0a3a3 100644
--- a/client/docs/styleguide.md
+++ b/client/docs/styleguide.md
@@ -44,7 +44,7 @@ const myFunction = (param) => {
 };
 
 // anonymous functions
-const myFunction = function(param) {
+const myFunction = function (param) {
     //do stuff
 };
 ```
@@ -84,10 +84,9 @@ When possible, use arrow functions instead.
 > export function myFunction(parameter) {
 >     const addOne = (value) => {
 >         return value + 1;
->     }
+>     };
 >     // do more stuff...
 > }
->
 > ```
 >
 > **Don't**
@@ -96,12 +95,11 @@ When possible, use arrow functions instead.
 > // in myModules.js
 >
 > export const myFunction = (parameter) => {
->     const addOne = function(value) {
+>     const addOne = function (value) {
 >         return value + 1;
->     }
+>     };
 >     // do more stuff...
-> }
->
+> };
 > ```
 
 ## HTML Multi-Line Layout
@@ -115,9 +113,7 @@ Prettier tries to respect whitespace when formatting your HTML templates, even w
 Might get turned into:
 
 ```vue
-<b-button class="danger-button mb-4" variant="danger" @click="onDangerButtonClick"
-    >A very Long Button Text</b-button
->
+<b-button class="danger-button mb-4" variant="danger" @click="onDangerButtonClick">A very Long Button Text</b-button>
 ```
 
 Notice the strange positioning of the `>` brackets.
@@ -277,7 +273,7 @@ Do not add space between elements connected by conditionals.
 >     <span v-if="conditional">
 >         condition met
 >     </span>
->
+> 
 >     <span v-else>
 >         condition not met
 >     </span>
@@ -293,7 +289,7 @@ Add space between non-connected elements.
 >     <span>
 >         First span.
 >     </span>
->
+> 
 >     <span>
 >         Second span.
 >     </span>
@@ -325,7 +321,7 @@ Add space between logical blocks of elements.
 >     <span v-else>
 >         condition 1 not met
 >     </span>
->
+> 
 >     <span v-if="otherConditional">
 >         condition 2 met
 >     </span>
diff --git a/client/docs/unit-testing/debugging-unit-tests.md b/client/docs/unit-testing/debugging-unit-tests.md
index d7916cf6fa5..74097ef365b 100644
--- a/client/docs/unit-testing/debugging-unit-tests.md
+++ b/client/docs/unit-testing/debugging-unit-tests.md
@@ -9,7 +9,7 @@ code updates its test extensions again.
 
 #### To debug a single Jest test:
 
-1. Open a jest test (a file that ends with *.test.js)
+1. Open a jest test (a file that ends with \*.test.js)
 
 1. Make sure the test file is selected, especially if you have multiple files open. This process
    will fail confusingly and without obvious error if you have not launched the debugger with the
@@ -34,8 +34,6 @@ code updates its test extensions again.
    variables near your breakpoint and see their values in the "Variables" section of the Run and
    Debug pane.
 
-
-
 ```json
 // sample launch.json
 {
@@ -45,16 +43,16 @@ code updates its test extensions again.
             "type": "node",
             "name": "debug selected jest test",
             "request": "launch",
-            
+
             // launches version of jest from inside the node_modules
             // this means you need to have run yarn first
             "program": "${workspaceFolder}/client/node_modules/jest/bin/jest",
             "args": [
-                // Alias -i. 
+                // Alias -i.
                 // Normally jest opens up a bunch of workers to run all your tests faster
                 // but we don't want that right now.
                 "--runInBand",
-                
+
                 // finds jest config
                 "--config",
                 "${workspaceFolder}/client/tests/jest/jest.config.js",
@@ -68,9 +66,8 @@ code updates its test extensions again.
             "console": "integratedTerminal",
 
             // allows you to place breakpoints right in vscode's gutter
-            "disableOptimisticBPs": true,
-        },
-        
+            "disableOptimisticBPs": true
+        }
     ]
 }
 ```
diff --git a/client/docs/unit-testing/readme.md b/client/docs/unit-testing/readme.md
index 393c1a0c117..72c3ef2e582 100644
--- a/client/docs/unit-testing/readme.md
+++ b/client/docs/unit-testing/readme.md
@@ -1,20 +1,18 @@
-
 [Galaxy uses Jest](https://jestjs.io/) for its client-side unit testing
 framework.
 
 For testing Vue components, we use the [Vue testing
 utils](https://vue-test-utils.vuejs.org/) to mount individual components in a
-test bed and check them for rendered features.  Please use jest-based mocking
+test bed and check them for rendered features. Please use jest-based mocking
 for isolating test functionality.
 
-
 ### Specific test scenarios & examples
 
-* [Mocking an imported
-dependency](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/tagService.test.js)
-* [Testing async
-operations](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/tagService.test.js)
-* [Testing a Vue component for expected rendering
-output](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/StatelessTags.test.js)
-* [Firing an event against a shallow mounted vue
-component](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/StatelessTags.test.js)
+-   [Mocking an imported
+    dependency](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/tagService.test.js)
+-   [Testing async
+    operations](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/tagService.test.js)
+-   [Testing a Vue component for expected rendering
+    output](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/StatelessTags.test.js)
+-   [Firing an event against a shallow mounted vue
+    component](https://github.com/galaxyproject/galaxy/blob/dev/client/src/components/Tags/StatelessTags.test.js)
diff --git a/client/docs/unit-testing/strategies.md b/client/docs/unit-testing/strategies.md
index 64c343cc850..d06353193c3 100644
--- a/client/docs/unit-testing/strategies.md
+++ b/client/docs/unit-testing/strategies.md
@@ -1,4 +1,4 @@
-Part of making good code is making that code easy to test. 
+Part of making good code is making that code easy to test.
 
 ### Implement logic in pure functions when possible
 
@@ -10,14 +10,13 @@ There is almost definitely no such thing as a well-written 1000 line function.
 Most of whatever happened in that thing was probably deterministic and can be
 broken up into easily testable chunks.
 
-
 ### Wrap native browser resources in a function so they can be easily mocked
 
 If your javascript needs to talk to the window object, or navigator, etc. wrap
 that in a function call so that it can be easily mocked during testing.
 
-
 #### Your Module
+
 ```js static
 // myModule.js
 
@@ -35,6 +34,7 @@ export function theThingYouReallyCareAbout() {
 ```
 
 #### Your test file
+
 ```js static
 // myModule.test.js
 import { theThingYouReallyCareAbout, redirectTo } from "./myModule";
diff --git a/client/docs/unit-testing/writing-tests.md b/client/docs/unit-testing/writing-tests.md
index 8951b5797de..9a49db6c510 100644
--- a/client/docs/unit-testing/writing-tests.md
+++ b/client/docs/unit-testing/writing-tests.md
@@ -2,14 +2,13 @@
 
 Please remember that these tests are not _for_ you. They're for the people who
 come after you. It will be a lot easier to modify, repair and upgrade your code
-if they can figure out what you were originally hoping to accomplish.  Try to
+if they can figure out what you were originally hoping to accomplish. Try to
 use as detailed 'expect' statements as possible -- overuse of 'toBeTruthy()'
 for example, can hide the intent of your test.
 
-Add a couple of comments. Use variable names that mean something.  Nobody's
+Add a couple of comments. Use variable names that mean something. Nobody's
 code is as self-documenting as they believe it to be.
 
-
 ### Only test the public API that you define
 
 Internal implementations come and go with library upgrades and new tech. But
@@ -20,17 +19,16 @@ Separate your concerns and identify the developer-facing methods and functions
 you expect them to use. Test THOSE. Everything else should probably be
 considered an implementation detail.
 
-The other side of the same coin is to test *only* the unit in question.  If your
+The other side of the same coin is to test _only_ the unit in question. If your
 component has a model that uses a service that touches Vuex, which then uses
-Axios to fetch some data -- don't test all that at once.  Break things apart and
-mock functionality to isolate testing to units.  End to end testing is a
+Axios to fetch some data -- don't test all that at once. Break things apart and
+mock functionality to isolate testing to units. End to end testing is a
 separate thing that shouldn't be attempted using spec tests in Jest.
 
 Assume nobody cares _how_ your code works, we just need to know that the public
 API you designed _does_ work. If performance problems or new tech necessitate a
 re-write, these tests become a guide for the next implementation.
 
-
 ### Writing a test file
 
 Jest will try to test any file ending in "\*.test.js". Please place your test
@@ -65,9 +63,7 @@ describe("some module you wrote", () => {
 });
 ```
 
-
 ### Check out the Jest helper functions
 
 We have created some [common helpers for common testing
-scenarios](https://github.com/galaxyproject/galaxy/blob/dev/client/tests/jest/helpers.js). 
-
+scenarios](https://github.com/galaxyproject/galaxy/blob/dev/client/tests/jest/helpers.js).
diff --git a/client/src/components/Alert.md b/client/src/components/Alert.md
index 021efd67e56..61038ebc71a 100644
--- a/client/src/components/Alert.md
+++ b/client/src/components/Alert.md
@@ -8,7 +8,7 @@
 
 ```js
 <div v-for="variant in [ 'success', 'info', 'warning', 'error' ]">
-	<Alert v-bind:variant="variant">A {{variant}} message</Alert>
+    <Alert v-bind:variant="variant">A {{ variant }} message</Alert>
 </div>
 ```
 
diff --git a/client/src/components/History/README.md b/client/src/components/History/README.md
index 3bf90443ce9..9388c5b3f6e 100644
--- a/client/src/components/History/README.md
+++ b/client/src/components/History/README.md
@@ -1,13 +1,12 @@
 ### History Panel Component Tree
+
 This is not intended to be a complete listing, but a general idea of how the components are intended
 to interact with each other.
 
 ```html static
 <Index :history="history">
-
     <!-- if main history selected -->
     <CurrentHistory :history="history">
-
         <!-- Data providers do the heavy-lifting of mixing params, history, and 
         scroll position to deliver the content for the scroller -->
         <StoreProvider>
@@ -18,7 +17,7 @@ to interact with each other.
 
             <!-- Uses a virtual scroller plugin to render all ContentItems and throttles the scrolling pace by limiting
             the frequency and magnitude of offset changes. -->
-            <Listing>
+            <listing>
 
                 <!-- The ContentItem renders a row in the list, showing the title, some attributes,
                 and basic operation buttons such as display and edit for either a dataset or a collection.
@@ -40,11 +39,11 @@ to interact with each other.
             <CollectionOperations />
 
             <!-- As above, the same virtual scroller and ContentItem component is being used to render the elements. -->
-            <Listing>
+            <listing>
                 (<ContentItem />)
                     <DatasetDetails />
             </Listing>
         </StoreProvider>
     </CurrentCollection>
 </Index>
-```
\ No newline at end of file
+```
diff --git a/client/src/components/Workflow/Editor/modules/terminals.ts b/client/src/components/Workflow/Editor/modules/terminals.ts
index 1e354149ffa..9b145699bed 100644
--- a/client/src/components/Workflow/Editor/modules/terminals.ts
+++ b/client/src/components/Workflow/Editor/modules/terminals.ts
@@ -490,10 +490,10 @@ export class InputParameterTerminal extends BaseInputTerminal {
         const effectiveThisType = this.effectiveType(this.type);
         const otherType = ("type" in other && other.type) || "data";
         const effectiveOtherType = this.effectiveType(otherType);
-        const canAccept = effectiveThisType === effectiveOtherType
+        const canAccept = effectiveThisType === effectiveOtherType;
         return new ConnectionAcceptable(
             canAccept,
-            canAccept ? null: `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
+            canAccept ? null : `Cannot attach a ${effectiveOtherType} parameter to a ${effectiveThisType} input`
         );
     }
 }

From 4a9dcd618f3ca0e23a055ffdf376d05844717368 Mon Sep 17 00:00:00 2001
From: Dannon Baker <dannon.baker@gmail.com>
Date: Mon, 30 Jan 2023 12:27:07 -0500
Subject: [PATCH 349/350] Drop defineEmits import from FormUpload

---
 client/src/components/Form/Elements/FormUpload.vue | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/src/components/Form/Elements/FormUpload.vue b/client/src/components/Form/Elements/FormUpload.vue
index a9cb3da4cfa..bd1d46d820c 100644
--- a/client/src/components/Form/Elements/FormUpload.vue
+++ b/client/src/components/Form/Elements/FormUpload.vue
@@ -1,5 +1,5 @@
 <script setup>
-import { ref, defineEmits, computed } from "vue";
+import { ref, computed } from "vue";
 import { FontAwesomeIcon } from "@fortawesome/vue-fontawesome";
 const props = defineProps({
     value: {

From 4638d857c428c8a23c326b6ccd0ac11523f0a1b5 Mon Sep 17 00:00:00 2001
From: Dannon <dannon.baker@gmail.com>
Date: Tue, 31 Jan 2023 07:46:34 -0500
Subject: [PATCH 350/350] Update client/.prettierignore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: David López <46503462+davelopez@users.noreply.github.com>
---
 client/.prettierignore | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/client/.prettierignore b/client/.prettierignore
index bc99ee79eab..143859dcc25 100644
--- a/client/.prettierignore
+++ b/client/.prettierignore
@@ -11,4 +11,4 @@
 src/libs
 # Don't reformat .json or .yml files included in the project
 *.json
-*.yml
\ No newline at end of file
+*.yml