mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-11-03 14:33:31 +08:00
A hardening + finalization pass over the agent-first CLI: correctness fixes,
richer machine-readable signals, flag/naming consistency, and a symmetric
config surface. Pre-1.0, so it includes breaking renames.
Correctness:
- agent update: resolve/validate --model/--rerank-model (was storing a bogus
name verbatim, corrupting config.model_id).
- doctor: honor WEKNORA_HOST / WEKNORA_API_KEY (headless path no longer reports
"no host configured").
- session ask / MCP session_ask: text answer was empty on non-TTY — the agent
stream sets Done=true on an intermediate agent_query frame before the answer,
and AgentAccumulator treated the first Done as terminal. Terminate on the
`complete` event (new sdk.AgentResponseTypeComplete), not a per-frame Done.
- batch exit codes: any per-item failure collapses to operation.failed (exit 1),
including `doc upload --recursive` partial failures — a permanent per-file
failure (e.g. a duplicate) no longer surfaces as a retryable exit 7 an agent
would loop on; per-item typed errors stay in the envelope.
Agent-first signals & discovery:
- error.exit_code in the envelope (type + exit_code disambiguate the
input.invalid_argument exit-2-vs-5 split in one JSON read).
- meta.hint on empty content search and on draft doc create; doc wait fails fast
on a never-parsing draft instead of hanging to --timeout.
- retrieval-readiness is visible in the natural flow: kb status / kb check emit
retrieval_ready, and kb create hints the fix when no embedding model is bound
— an unconfigured KB no longer looks silently healthy.
- schema contract completeness: every leaf declares output + >=1 example
(drift-guarded); output strings match the meta actually emitted; chunk list
and search docs now emit meta.total_count (both previously dropped it).
- schema tolerates a quoted multi-word command label; zero-state auth — and
`link` with no profile — point at profile setup / the headless WEKNORA_KB_ID
path instead of looping on `auth login`.
- id-addressed reads tolerate a redundant --kb (doc view/wait, chunk list/view
accept and ignore it, declared in schema) so a carried-over --kb doesn't
exit 2; streaming commands warn that --jq does not apply to an NDJSON stream.
- keep JSON-always as the default; --jq hints spell out the .data path.
Consistency & gating:
- doc create: drop the deprecated --name alias (--title only; pre-1.0 break).
- chunk list --limit aligned to 1..10000; model list --limit/-L with
has_more/total_count; api write-gates -X PUT/PATCH (exit 10); skills install
expands a leading ~.
- docs corrected: search docs / doc list --keyword help is case-insensitive
(server does LOWER LIKE); AGENTS.md risk-action list (no phantom kb.init; add
model.update / kb.config.set) and batch example (failed item carries `error`);
session resume --message id comes from `message list`, not the stream.
- auth/profile ergonomics: env credentials are now first-class — `auth token`
prints the active WEKNORA_API_KEY / WEKNORA_TOKEN, and auth login/logout/refresh
give an env-aware message instead of looping on "run auth login". `auth logout`
clears credentials but keeps the profile registered (host preserved for
re-login); deleting a profile is `profile remove`'s job (clean logout/remove
separation, matching gh / lark).
Config surface (symmetric read/write, in-place model edits):
- kb config now returns a secret-free KBModelConfigView (was {}); `kb config`
reads, new `kb config set` writes; `kb init` removed (misnomer).
- kb create --chat-model: retrieval-ready in one step.
- model update: edit a model in place (id preserved, references survive) —
rotate --api-key-stdin, change base-url / display-name / etc.
- session continue-stream renamed to session resume.
Docs: AGENTS.md is the single wire-contract source; CHANGELOG slimmed; stale
kb-init / continue-stream references removed; skill wire-vocab guard extended.
AGENTS.md / weknora-shared SKILL document retrieval_ready (a KB needs an
embedding model to be searchable), that --jq does not apply to NDJSON
streams, and the env-credential-first auth path; the KB quickstart example
now creates a retrieval-ready KB.
186 lines
6.5 KiB
Go
186 lines
6.5 KiB
Go
package modelcmd
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"sort"
|
|
"strings"
|
|
"text/tabwriter"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
"github.com/Tencent/WeKnora/cli/internal/output"
|
|
"github.com/Tencent/WeKnora/cli/internal/text"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
// modelListFields enumerates the fields surfaced for `--format json` discovery
|
|
// on `model list`. The nested `parameters` object is omitted — use `--jq` for
|
|
// it (and `model view` renders the full record).
|
|
var modelListFields = []string{
|
|
"id", "name", "display_name", "type", "source",
|
|
"description", "is_default", "created_at", "updated_at",
|
|
}
|
|
|
|
// modelTypeValues / modelSourceValues are the closed server enums the
|
|
// corresponding filter flags accept, sourced from the SDK's enumerators so the
|
|
// CLI can't drift from the SDK/server. A typo is rejected up front rather than
|
|
// silently returning an empty set (which an agent cannot distinguish from a
|
|
// genuine no-match).
|
|
var modelTypeValues = cmdutil.EnumStrings(sdk.AllModelTypes())
|
|
|
|
var modelSourceValues = cmdutil.EnumStrings(sdk.AllModelSources())
|
|
|
|
// ListOptions captures `model list` filter flag state.
|
|
type ListOptions struct {
|
|
// Type / Source, when set, restrict output to models of that type
|
|
// (Embedding, Rerank, KnowledgeQA, VLLM, ASR) or provider (local, openai,
|
|
// …), matched case-insensitively. Empty shows everything.
|
|
Type string
|
|
Source string
|
|
// Limit caps the returned slice client-side (applied after --type/--source
|
|
// filtering and sort). The ListModels SDK is unpaginated, so the CLI holds
|
|
// the true total and reports meta.total_count/has_more when --limit drops any.
|
|
Limit int
|
|
}
|
|
|
|
// ListService is the narrow SDK surface this command depends on.
|
|
type ListService interface {
|
|
ListModels(ctx context.Context) ([]sdk.Model, error)
|
|
}
|
|
|
|
// NewCmdList builds `weknora model list`.
|
|
func NewCmdList(f *cmdutil.Factory) *cobra.Command {
|
|
opts := &ListOptions{}
|
|
cmd := &cobra.Command{
|
|
Use: "list",
|
|
Short: "List models configured on the server",
|
|
Long: `List the models configured on the server, sorted by type then name. Pass
|
|
--type to restrict to one model type (Embedding, Rerank, KnowledgeQA, VLLM, ASR).`,
|
|
Args: cobra.NoArgs,
|
|
RunE: func(c *cobra.Command, _ []string) error {
|
|
fopts, err := cmdutil.CheckFormatFlag(c)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
fopts.ResolveDefault(iostreams.IO.IsStdoutTTY())
|
|
// Validate static input before building the client so a bad --limit
|
|
// returns input.invalid_argument (exit 5), not an auth error (exit 3).
|
|
if err := validateListOpts(opts); err != nil {
|
|
return err
|
|
}
|
|
cli, err := f.Client()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return runList(c.Context(), opts, fopts, cli)
|
|
},
|
|
}
|
|
cmd.Flags().StringVar(&opts.Type, "type", "", "Only show models of this type (Embedding, Rerank, KnowledgeQA, VLLM, ASR)")
|
|
cmd.Flags().StringVar(&opts.Source, "source", "", "Only show models from this provider (local, remote, openai, aliyun, …)")
|
|
cmd.Flags().IntVarP(&opts.Limit, "limit", "L", 30, "Maximum results to return — client-side cap; meta.has_more/total_count report the full size (1..10000)")
|
|
cmdutil.AddFormatFlag(cmd, modelListFields...)
|
|
cmdutil.SetAgentHelp(cmd, cmdutil.AgentHelp{
|
|
UsedFor: "discover model ids for `agent create --model` and a KB's embedding/summary model",
|
|
Examples: []string{
|
|
"weknora model list",
|
|
"weknora model list --type KnowledgeQA --format json",
|
|
"weknora model list --source local",
|
|
},
|
|
Output: "envelope.data is an array of Model objects (id, name, display_name, type, source, is_default); narrow it with --type / --source; meta.count is the returned count, meta.total_count is the full set and meta.has_more=true means --limit truncated it",
|
|
})
|
|
return cmd
|
|
}
|
|
|
|
// validateListOpts checks --limit. Called from RunE before the client is built
|
|
// (so a bad value surfaces as exit 5, not an auth error) and at runList's top
|
|
// for direct callers; idempotent.
|
|
func validateListOpts(opts *ListOptions) error {
|
|
if opts.Limit < 1 || opts.Limit > 10000 {
|
|
return &cmdutil.Error{
|
|
Code: cmdutil.CodeInputInvalidArgument,
|
|
Message: fmt.Sprintf("--limit must be in 1..10000, got %d", opts.Limit),
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func runList(ctx context.Context, opts *ListOptions, fopts *cmdutil.FormatOptions, svc ListService) error {
|
|
if err := validateListOpts(opts); err != nil {
|
|
return err
|
|
}
|
|
if _, err := cmdutil.ValidateEnum("type", opts.Type, modelTypeValues); err != nil {
|
|
return err
|
|
}
|
|
if _, err := cmdutil.ValidateEnum("source", opts.Source, modelSourceValues); err != nil {
|
|
return err
|
|
}
|
|
items, err := svc.ListModels(ctx)
|
|
if err != nil {
|
|
return cmdutil.WrapHTTP(err, "list models")
|
|
}
|
|
if items == nil {
|
|
items = []sdk.Model{} // ensure JSON [] not null
|
|
}
|
|
hasFilter := opts.Type != "" || opts.Source != ""
|
|
if hasFilter {
|
|
filtered := items[:0]
|
|
for _, m := range items {
|
|
if opts.Type != "" && !strings.EqualFold(string(m.Type), opts.Type) {
|
|
continue
|
|
}
|
|
if opts.Source != "" && !strings.EqualFold(string(m.Source), opts.Source) {
|
|
continue
|
|
}
|
|
filtered = append(filtered, m)
|
|
}
|
|
items = filtered
|
|
}
|
|
// Deterministic order: by type, then label. Server return order is not
|
|
// guaranteed, so a client-side sort keeps output stable.
|
|
sort.Slice(items, func(i, j int) bool {
|
|
if items[i].Type != items[j].Type {
|
|
return items[i].Type < items[j].Type
|
|
}
|
|
return modelLabel(items[i]) < modelLabel(items[j])
|
|
})
|
|
|
|
// Client-side --limit cap. The ListModels SDK is unpaginated, so the CLI
|
|
// holds the true total and can tell the caller whether --limit dropped any:
|
|
// total_count is the full (post-filter) count, has_more flags truncation.
|
|
total := len(items)
|
|
truncated := false
|
|
if opts.Limit > 0 && len(items) > opts.Limit {
|
|
items = items[:opts.Limit]
|
|
truncated = true
|
|
}
|
|
|
|
if fopts.WantsJSON() {
|
|
meta := &output.Meta{Count: output.IntPtr(len(items)), HasMore: truncated, TotalCount: output.IntPtr(total)}
|
|
return fopts.Emit(iostreams.IO.Out, items, meta)
|
|
}
|
|
|
|
if len(items) == 0 {
|
|
if hasFilter {
|
|
fmt.Fprintln(iostreams.IO.Out, "(no models match the filter)")
|
|
return nil
|
|
}
|
|
fmt.Fprintln(iostreams.IO.Out, "(no models)")
|
|
return nil
|
|
}
|
|
|
|
tw := tabwriter.NewWriter(iostreams.IO.Out, 0, 0, 2, ' ', 0)
|
|
fmt.Fprintln(tw, "ID\tNAME\tTYPE\tSOURCE\tDEFAULT")
|
|
for _, m := range items {
|
|
def := ""
|
|
if m.IsDefault {
|
|
def = "default"
|
|
}
|
|
fmt.Fprintf(tw, "%s\t%s\t%s\t%s\t%s\n",
|
|
m.ID, text.Truncate(40, modelLabel(m)), m.Type, m.Source, def)
|
|
}
|
|
return tw.Flush()
|
|
}
|