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.
111 lines
3.1 KiB
Go
111 lines
3.1 KiB
Go
package kb
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
type fakeStatusSvc struct {
|
|
kb *sdk.KnowledgeBase
|
|
getErr error
|
|
}
|
|
|
|
func (f *fakeStatusSvc) GetKnowledgeBase(_ context.Context, id string) (*sdk.KnowledgeBase, error) {
|
|
if f.getErr != nil {
|
|
return nil, f.getErr
|
|
}
|
|
return f.kb, nil
|
|
}
|
|
|
|
func TestRunStatus_ShallowFields(t *testing.T) {
|
|
svc := &fakeStatusSvc{kb: &sdk.KnowledgeBase{
|
|
ID: "kb_x",
|
|
KnowledgeCount: 42,
|
|
ChunkCount: 100,
|
|
IsProcessing: true,
|
|
ProcessingCount: 3,
|
|
EmbeddingModelID: "emb_1",
|
|
}}
|
|
res, err := runStatus(context.Background(), svc, "kb_x")
|
|
if err != nil {
|
|
t.Fatalf("runStatus: %v", err)
|
|
}
|
|
if !res.Reachable {
|
|
t.Error("Reachable=false, want true")
|
|
}
|
|
if res.KnowledgeCount != 42 || res.ChunkCount != 100 || res.ProcessingCount != 3 || !res.IsProcessing {
|
|
t.Errorf("got %+v", res)
|
|
}
|
|
if !res.RetrievalReady {
|
|
t.Error("RetrievalReady=false, want true when an embedding model is bound")
|
|
}
|
|
}
|
|
|
|
// A KB with no embedding model can never retrieve — the health probe must say
|
|
// so (retrieval_ready=false), not report a silent all-green status.
|
|
func TestRunStatus_RetrievalNotReadyWithoutEmbeddingModel(t *testing.T) {
|
|
svc := &fakeStatusSvc{kb: &sdk.KnowledgeBase{ID: "kb_x", KnowledgeCount: 1}}
|
|
res, err := runStatus(context.Background(), svc, "kb_x")
|
|
if err != nil {
|
|
t.Fatalf("runStatus: %v", err)
|
|
}
|
|
if res.RetrievalReady {
|
|
t.Error("RetrievalReady=true, want false when no embedding model is bound")
|
|
}
|
|
}
|
|
|
|
func TestRunStatus_Unreachable(t *testing.T) {
|
|
svc := &fakeStatusSvc{getErr: fmt.Errorf("404 not found")}
|
|
res, err := runStatus(context.Background(), svc, "kb_x")
|
|
if err != nil {
|
|
t.Fatalf("runStatus should not return err on unreachable; got %v", err)
|
|
}
|
|
if res.Reachable {
|
|
t.Error("Reachable=true, want false")
|
|
}
|
|
if res.ID != "kb_x" {
|
|
t.Errorf("ID=%q, want kb_x (echoed even when unreachable)", res.ID)
|
|
}
|
|
}
|
|
|
|
func TestEmitStatus_JSON(t *testing.T) {
|
|
var buf bytes.Buffer
|
|
res := &StatusResult{ID: "kb_x", Reachable: true, KnowledgeCount: 5}
|
|
fopts := &cmdutil.FormatOptions{Mode: cmdutil.FormatJSON}
|
|
if err := emitStatus(res, fopts, &buf); err != nil {
|
|
t.Fatalf("emitStatus: %v", err)
|
|
}
|
|
var env struct {
|
|
OK bool `json:"ok"`
|
|
Data StatusResult `json:"data"`
|
|
}
|
|
if err := json.Unmarshal(buf.Bytes(), &env); err != nil {
|
|
t.Fatalf("not JSON: %v\n%s", err, buf.String())
|
|
}
|
|
got := env.Data
|
|
if got.ID != "kb_x" || got.KnowledgeCount != 5 {
|
|
t.Errorf("got %+v", got)
|
|
}
|
|
}
|
|
|
|
func TestEmitStatus_Text(t *testing.T) {
|
|
var buf bytes.Buffer
|
|
res := &StatusResult{ID: "kb_x", Reachable: true, KnowledgeCount: 5, ChunkCount: 20, IsProcessing: true, ProcessingCount: 1}
|
|
fopts := &cmdutil.FormatOptions{Mode: cmdutil.FormatText}
|
|
if err := emitStatus(res, fopts, &buf); err != nil {
|
|
t.Fatalf("emitStatus: %v", err)
|
|
}
|
|
for _, want := range []string{"kb_x", "5", "20", "true"} {
|
|
if !strings.Contains(buf.String(), want) {
|
|
t.Errorf("output missing %q:\n%s", want, buf.String())
|
|
}
|
|
}
|
|
}
|