Files
Enterprise-Knowledge-Base/cli/cmd/kb/config_set_test.go
T
nullkey d3c03b2f34 feat(cli)!: v0.10 reliability, agent-UX, and command-surface hardening
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.
2026-07-06 22:53:01 +08:00

139 lines
4.9 KiB
Go

package kb
import (
"context"
"encoding/json"
"errors"
"testing"
"github.com/spf13/cobra"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
"github.com/Tencent/WeKnora/cli/internal/iostreams"
"github.com/Tencent/WeKnora/cli/internal/prompt"
sdk "github.com/Tencent/WeKnora/client"
)
type fakeInitSvc struct {
gotKB string
gotCfg *sdk.KBModelConfig
result *sdk.KBModelConfigView
setErr error
}
func (f *fakeInitSvc) SetKBModelConfig(_ context.Context, kbID string, cfg *sdk.KBModelConfig) error {
f.gotKB = kbID
f.gotCfg = cfg
return f.setErr
}
func (f *fakeInitSvc) GetInitializationConfig(_ context.Context, _ string) (*sdk.KBModelConfigView, error) {
if f.result != nil {
return f.result, nil
}
if f.gotCfg == nil {
return &sdk.KBModelConfigView{}, nil
}
return &sdk.KBModelConfigView{
RetrievalReady: f.gotCfg.EmbeddingModelID != "",
Embedding: sdk.ModelSlotView{Configured: f.gotCfg.EmbeddingModelID != "", ModelName: f.gotCfg.EmbeddingModelID},
LLM: sdk.ModelSlotView{Configured: f.gotCfg.LLMModelID != "", ModelName: f.gotCfg.LLMModelID},
}, nil
}
func TestKBConfigSet_AppliesAndEmitsResult(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeInitSvc{}
opts := &ConfigSetOptions{ChatModel: "model_llm", EmbeddingModel: "model_emb"}
require.NoError(t, runConfigSet(context.Background(), opts, &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}, svc, "kb_abc"))
assert.Equal(t, "kb_abc", svc.gotKB)
require.NotNil(t, svc.gotCfg)
assert.Equal(t, "model_llm", svc.gotCfg.LLMModelID)
assert.Equal(t, "model_emb", svc.gotCfg.EmbeddingModelID)
var env struct {
OK bool `json:"ok"`
Data sdk.KBModelConfigView `json:"data"`
}
require.NoError(t, json.Unmarshal(out.Bytes(), &env))
assert.True(t, env.OK)
assert.Equal(t, "model_emb", env.Data.Embedding.ModelName)
assert.Equal(t, "model_llm", env.Data.LLM.ModelName)
assert.True(t, env.Data.RetrievalReady)
}
func TestKBConfigSet_RequiresBothModels(t *testing.T) {
_, _ = iostreams.SetForTest(t)
svc := &fakeInitSvc{}
// Missing both.
err := runConfigSet(context.Background(), &ConfigSetOptions{}, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc, "kb_abc")
var ce *cmdutil.Error
require.ErrorAs(t, err, &ce)
assert.Equal(t, cmdutil.CodeInputMissingFlag, ce.Code)
assert.Equal(t, "", svc.gotKB, "must not call SetKBModelConfig when flags are missing")
// Missing just embedding.
err = runConfigSet(context.Background(), &ConfigSetOptions{ChatModel: "m"}, &cmdutil.FormatOptions{Mode: cmdutil.FormatText}, svc, "kb_abc")
require.ErrorAs(t, err, &ce)
assert.Contains(t, ce.Message, "--embedding-model")
}
func TestKBConfigSet_WriteSucceedsReadbackFails(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc2 := &readbackErrSvc{fakeInitSvc: &fakeInitSvc{}}
opts := &ConfigSetOptions{ChatModel: "model_llm", EmbeddingModel: "model_emb"}
require.NoError(t, runConfigSet(context.Background(), opts, &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}, svc2, "kb_abc"))
var env struct {
Data sdk.KBModelConfigView `json:"data"`
}
require.NoError(t, json.Unmarshal(out.Bytes(), &env))
assert.Equal(t, "model_emb", env.Data.Embedding.ModelName, "falls back to applied config when read-back fails")
}
type readbackErrSvc struct{ *fakeInitSvc }
func (s *readbackErrSvc) GetInitializationConfig(_ context.Context, _ string) (*sdk.KBModelConfigView, error) {
return nil, errors.New("read-back boom")
}
// withRootKB wraps a kb subcommand under a synthetic root with global flags,
// keyed off the sub's own name (unlike withRootHarnessKB which is hardcoded to
// `update`).
func withRootKB(sub *cobra.Command, args ...string) *cobra.Command {
root := &cobra.Command{Use: "weknora"}
pf := root.PersistentFlags()
pf.BoolP("yes", "y", false, "")
pf.String("format", "", "")
pf.StringP("jq", "q", "", "")
kb := &cobra.Command{Use: "kb"}
kb.AddCommand(sub)
root.AddCommand(kb)
root.SetArgs(append([]string{"kb", sub.Name()}, args...))
root.SetContext(context.Background())
root.SilenceErrors = true
root.SilenceUsage = true
return root
}
func TestKBConfigSet_RequiresConfirmation(t *testing.T) {
iostreams.SetForTest(t)
f := &cmdutil.Factory{
Client: func() (*sdk.Client, error) { return nil, nil },
Prompter: func() prompt.Prompter { return prompt.AgentPrompter{} },
}
// Drive `kb config set` (the config parent routes to its `set` subcommand).
root := withRootKB(NewCmdConfig(f), "set", "kb_abc", "--chat-model", "model_llm", "--embedding-model", "model_emb", "--format", "json")
err := root.Execute()
require.Error(t, err)
var ce *cmdutil.Error
require.ErrorAs(t, err, &ce)
assert.Equal(t, cmdutil.CodeInputConfirmationRequired, ce.Code)
assert.Equal(t, 10, cmdutil.ExitCode(err))
assert.Contains(t, ce.RetryArgv, "-y")
assert.Contains(t, ce.RetryArgv, "model_emb")
assert.Contains(t, ce.RetryArgv, "set", "retry_argv should target `kb config set`")
}