d3c03b2f34
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.
171 lines
6.2 KiB
Go
171 lines
6.2 KiB
Go
package modelcmd
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
type fakeListSvc struct {
|
|
models []sdk.Model
|
|
err error
|
|
}
|
|
|
|
func (f *fakeListSvc) ListModels(_ context.Context) ([]sdk.Model, error) {
|
|
return f.models, f.err
|
|
}
|
|
|
|
func TestModelList_Text(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{
|
|
{ID: "m1", DisplayName: "GPT-X", Type: sdk.ModelTypeKnowledgeQA, Source: sdk.ModelSourceOpenAI, IsDefault: true},
|
|
{ID: "m2", Name: "bge", Type: sdk.ModelTypeEmbedding, Source: sdk.ModelSourceLocal},
|
|
}}
|
|
if err := runList(context.Background(), &ListOptions{Limit: 30}, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
got := out.String()
|
|
for _, want := range []string{"ID", "NAME", "TYPE", "SOURCE", "m1", "GPT-X", "KnowledgeQA", "m2", "bge", "Embedding", "default"} {
|
|
if !strings.Contains(got, want) {
|
|
t.Errorf("missing %q in:\n%s", want, got)
|
|
}
|
|
}
|
|
}
|
|
|
|
// TestModelList_TypeFilter: --type narrows the set case-insensitively, and the
|
|
// JSON envelope's meta.count reflects the filtered total.
|
|
func TestModelList_TypeFilter(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{
|
|
{ID: "m1", Type: sdk.ModelTypeKnowledgeQA},
|
|
{ID: "m2", Type: sdk.ModelTypeEmbedding},
|
|
}}
|
|
if err := runList(context.Background(), &ListOptions{Type: "embedding", Limit: 30}, &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
var env struct {
|
|
Data []sdk.Model `json:"data"`
|
|
Meta struct {
|
|
Count int `json:"count"`
|
|
} `json:"meta"`
|
|
}
|
|
if err := json.Unmarshal(out.Bytes(), &env); err != nil {
|
|
t.Fatalf("parse: %v\n%s", err, out.String())
|
|
}
|
|
if len(env.Data) != 1 || env.Data[0].ID != "m2" {
|
|
t.Errorf("expected only m2 (Embedding), got %+v", env.Data)
|
|
}
|
|
if env.Meta.Count != 1 {
|
|
t.Errorf("meta.count = %d, want 1", env.Meta.Count)
|
|
}
|
|
}
|
|
|
|
func TestModelList_Empty(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: nil}
|
|
if err := runList(context.Background(), &ListOptions{Limit: 30}, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
if !strings.Contains(out.String(), "(no models)") {
|
|
t.Errorf("expected empty marker, got %q", out.String())
|
|
}
|
|
}
|
|
|
|
func TestModelList_EmptyAfterFilter(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{{ID: "m1", Type: sdk.ModelTypeEmbedding}}}
|
|
if err := runList(context.Background(), &ListOptions{Type: "Rerank", Limit: 30}, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
if !strings.Contains(out.String(), "(no models match the filter)") {
|
|
t.Errorf("expected filter empty marker, got %q", out.String())
|
|
}
|
|
}
|
|
|
|
// TestModelList_SourceFilter: --source narrows by provider, case-insensitively.
|
|
func TestModelList_SourceFilter(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{
|
|
{ID: "m1", Type: sdk.ModelTypeEmbedding, Source: sdk.ModelSourceLocal},
|
|
{ID: "m2", Type: sdk.ModelTypeKnowledgeQA, Source: sdk.ModelSourceOpenAI},
|
|
}}
|
|
if err := runList(context.Background(), &ListOptions{Source: "OpenAI", Limit: 30}, &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
var env struct {
|
|
Data []sdk.Model `json:"data"`
|
|
}
|
|
if err := json.Unmarshal(out.Bytes(), &env); err != nil {
|
|
t.Fatalf("parse: %v\n%s", err, out.String())
|
|
}
|
|
if len(env.Data) != 1 || env.Data[0].ID != "m2" {
|
|
t.Errorf("expected only m2 (openai), got %+v", env.Data)
|
|
}
|
|
}
|
|
|
|
// TestModelList_InvalidEnum: a typo'd --type / --source is rejected up front
|
|
// (input.invalid_argument) instead of silently returning an empty set.
|
|
func TestModelList_InvalidEnum(t *testing.T) {
|
|
for _, tc := range []struct{ name string; opts ListOptions }{
|
|
{"type", ListOptions{Type: "bogus", Limit: 30}},
|
|
{"source", ListOptions{Source: "bogus", Limit: 30}},
|
|
} {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
_, _ = iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{{ID: "m1", Type: sdk.ModelTypeEmbedding, Source: sdk.ModelSourceLocal}}}
|
|
err := runList(context.Background(), &tc.opts, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc)
|
|
var typed *cmdutil.Error
|
|
if !errors.As(err, &typed) || typed.Code != cmdutil.CodeInputInvalidArgument {
|
|
t.Errorf("expected input.invalid_argument, got %v", err)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
// TestModelList_Limit_TruncatesAndSignals verifies --limit caps model list
|
|
// output and reports meta.total_count/has_more like every other list command.
|
|
// Regression: model list had no --limit, so an agent could not cap output or
|
|
// tell whether it saw the full set.
|
|
func TestModelList_Limit_TruncatesAndSignals(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeListSvc{models: []sdk.Model{
|
|
{ID: "m1", Type: sdk.ModelTypeKnowledgeQA},
|
|
{ID: "m2", Type: sdk.ModelTypeKnowledgeQA},
|
|
{ID: "m3", Type: sdk.ModelTypeKnowledgeQA},
|
|
}}
|
|
fopts := &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}
|
|
if err := runList(context.Background(), &ListOptions{Limit: 2}, fopts, svc); err != nil {
|
|
t.Fatalf("runList: %v", err)
|
|
}
|
|
got := out.String()
|
|
if n := strings.Count(got, `"id":"m`); n != 2 {
|
|
t.Errorf("--limit 2 should slice to 2 models, got %d in:\n%s", n, got)
|
|
}
|
|
if !strings.Contains(got, `"has_more":true`) {
|
|
t.Errorf("truncated model list must set has_more:true; got:\n%s", got)
|
|
}
|
|
if !strings.Contains(got, `"total_count":3`) {
|
|
t.Errorf("truncated model list must report total_count:3; got:\n%s", got)
|
|
}
|
|
}
|
|
|
|
// TestModelList_BadLimit_Rejected verifies an out-of-range --limit is exit-5
|
|
// typed validation, consistent with kb/session list.
|
|
func TestModelList_BadLimit_Rejected(t *testing.T) {
|
|
_, _ = iostreams.SetForTest(t)
|
|
err := runList(context.Background(), &ListOptions{Limit: 99999}, &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}, &fakeListSvc{})
|
|
if err == nil {
|
|
t.Fatal("--limit 99999 must be rejected")
|
|
}
|
|
var e *cmdutil.Error
|
|
if !errors.As(err, &e) || e.Code != cmdutil.CodeInputInvalidArgument {
|
|
t.Errorf("want input.invalid_argument, got %v", err)
|
|
}
|
|
}
|