mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-10-16 06:59:02 +08:00
lyingbug
6db8fdd601
* feat(artifacts): add an artifacts library with its own message_artifacts table
Skill-generated files were only reachable from inside the conversation that
produced them. This adds a sidebar entry and a page that lists them across
every conversation the user can see.
Storage: artifacts move out of the messages.artifacts JSONB column into a new
message_artifacts table (PostgreSQL 000103, SQLite 000023), backfilled on
upgrade. The table is now the only source of truth; the old column is kept and
the down migration writes the table back into it. The message repository
loads artifacts for every message it returns and writes them on create,
update (when non-nil) and fork, so callers still use Message.Artifacts.
mod_time is stored as RFC 3339 text because the collector matches files on
nanosecond mtimes, which PostgreSQL timestamps would truncate.
API: GET /api/v1/artifacts lists the latest version of each file (grouped by
session + source path, with version_count), scoped like the session list,
with keyword / file type filters and paging. Downloads keep using the
per-session endpoint.
Frontend: "产物/Artifacts" sidebar entry (hidden without sandbox support), a
library page with type tabs, search, date groups, infinite loading, preview
drawer, download and jump-to-conversation; strings in all five locales. The
sidebar's top-menu paths are now one shared list.
* fix(artifacts): keep the restore hash guard and count versions by URL
RecordRestoredArtifactMtime again only stamps rows whose content hash matches
the restored content (and ignores empty hashes), and never rewrites the hash,
matching MessageArtifacts.WithRestoredMtime. Without the guard a restore of
v1's content also moved v2's mtime and relabelled v2 with v1's hash.
The library's version_count now counts distinct URLs per (session, source
path). A later answer that references an earlier file stores another row with
the same URL, which COUNT(*) reported as an extra version.
* fix(artifacts): scope the library to web chats and clear the legacy column
The library used the session list's default scope, which counts sessions
without an owner as legacy tenant-level rows. IM sessions are created without
an owner, so every member saw the file names and titles of every IM chat
(downloads then 404 for non-admins). The library now applies the same "web"
bucket predicate as the home sidebar, extracted from QueryPaged so the two
cannot drift: no IM mapping (including cleared ones), no embed marker, no
API-key owner.
Migrations 000103 / SQLite 000023 now clear messages.artifacts after the
backfill. Message loads still SELECT *, so the stale copy was read on every
history load. Only rows that carried artifacts are rewritten; the column stays
for instances on the old binary during a rolling upgrade, and the down
migration still rebuilds it from the table.
* fix(migrations): keep the 000103 backfill alive on malformed artifact JSON
A single file_size that is not an integer ("12.5", "") or a created_at that
does not parse ("garbage", month 13) raised a cast error and failed the whole
migration, blocking startup. Casts now go through pg_temp helpers that return
NULL on bad input, falling back to 0 and the message's created_at; valid rows
are unchanged. SQLite casts never raise; its migration test now covers the
same malformed values.
* docs(artifacts): describe the web-only library scope and the cleared legacy column
60 lines
2.7 KiB
SQL
60 lines
2.7 KiB
SQL
-- Mirrors versioned migration 000103_message_artifacts_table:
|
|
-- skill-generated files move out of messages.artifacts into their own table,
|
|
-- which becomes the only source of truth. After the backfill the legacy column
|
|
-- is cleared (message loads still SELECT *) but kept; the down migration
|
|
-- rebuilds it from the table.
|
|
|
|
CREATE TABLE IF NOT EXISTS message_artifacts (
|
|
id VARCHAR(36) PRIMARY KEY,
|
|
session_id VARCHAR(36) NOT NULL,
|
|
message_id VARCHAR(36) NOT NULL,
|
|
position INTEGER NOT NULL,
|
|
url TEXT NOT NULL DEFAULT '',
|
|
file_name TEXT NOT NULL DEFAULT '',
|
|
file_type VARCHAR(32) NOT NULL DEFAULT '',
|
|
file_size INTEGER NOT NULL DEFAULT 0,
|
|
content_hash VARCHAR(64) NOT NULL DEFAULT '',
|
|
source_path TEXT NOT NULL DEFAULT '',
|
|
mod_time VARCHAR(64) NOT NULL DEFAULT '',
|
|
created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
|
|
);
|
|
|
|
CREATE UNIQUE INDEX IF NOT EXISTS idx_message_artifacts_message_position
|
|
ON message_artifacts (message_id, position);
|
|
CREATE INDEX IF NOT EXISTS idx_message_artifacts_session_created
|
|
ON message_artifacts (session_id, created_at);
|
|
|
|
-- mod_time is kept as the RFC 3339 text Go wrote (nanosecond precision; the
|
|
-- collector matches files on it). created_at is an ORDER BY key compared as
|
|
-- text, so it is normalised to UTC in the layout the repository writes.
|
|
INSERT OR IGNORE INTO message_artifacts (
|
|
id, session_id, message_id, position, url, file_name, file_type, file_size,
|
|
content_hash, source_path, mod_time, created_at
|
|
)
|
|
SELECT
|
|
lower(hex(randomblob(4)) || '-' || hex(randomblob(2)) || '-' || hex(randomblob(2)) || '-' ||
|
|
hex(randomblob(2)) || '-' || hex(randomblob(6))),
|
|
m.session_id,
|
|
m.id,
|
|
CAST(a.key AS INTEGER),
|
|
COALESCE(json_extract(a.value, '$.url'), ''),
|
|
COALESCE(json_extract(a.value, '$.file_name'), ''),
|
|
substr(COALESCE(json_extract(a.value, '$.file_type'), ''), 1, 32),
|
|
COALESCE(CAST(json_extract(a.value, '$.file_size') AS INTEGER), 0),
|
|
substr(COALESCE(json_extract(a.value, '$.content_hash'), ''), 1, 64),
|
|
COALESCE(json_extract(a.value, '$.source_path'), ''),
|
|
substr(COALESCE(json_extract(a.value, '$.mod_time'), ''), 1, 64),
|
|
COALESCE(
|
|
strftime('%Y-%m-%d %H:%M:%f+00:00', NULLIF(json_extract(a.value, '$.created_at'), '')),
|
|
strftime('%Y-%m-%d %H:%M:%f+00:00', m.created_at),
|
|
strftime('%Y-%m-%d %H:%M:%f+00:00', 'now')
|
|
)
|
|
FROM messages m, json_each(
|
|
CASE WHEN json_valid(m.artifacts) AND json_type(m.artifacts) = 'array' THEN m.artifacts ELSE '[]' END
|
|
) a
|
|
WHERE a.type = 'object';
|
|
|
|
-- Only rows that carried artifacts; '[]' rows are left as they are.
|
|
UPDATE messages SET artifacts = NULL
|
|
WHERE artifacts IS NOT NULL AND artifacts <> '[]';
|