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.
This commit is contained in:
nullkey
2026-07-02 15:53:51 +08:00
committed by lyingbug
parent 040a734766
commit d3c03b2f34
95 changed files with 1711 additions and 436 deletions
+22 -8
View File
@@ -16,12 +16,16 @@ import (
// Shallow read only: 1 HTTP call, no failed-doc aggregation.
// For deep verification including failed_count, use `kb check <id>`.
type StatusResult struct {
ID string `json:"id"`
Reachable bool `json:"reachable"`
KnowledgeCount int64 `json:"knowledge_count,omitempty"`
ChunkCount int64 `json:"chunk_count,omitempty"`
IsProcessing bool `json:"is_processing,omitempty"`
ProcessingCount int64 `json:"processing_count,omitempty"`
ID string `json:"id"`
Reachable bool `json:"reachable"`
// RetrievalReady is false when the KB has no embedding model bound — it can
// never index or retrieve until `kb config set` runs. Always emitted (no
// omitempty) so a not-ready KB is visible, not silently green.
RetrievalReady bool `json:"retrieval_ready"`
KnowledgeCount int64 `json:"knowledge_count,omitempty"`
ChunkCount int64 `json:"chunk_count,omitempty"`
IsProcessing bool `json:"is_processing,omitempty"`
ProcessingCount int64 `json:"processing_count,omitempty"`
}
// StatusService is the narrow SDK surface needed for kb status.
@@ -30,7 +34,7 @@ type StatusService interface {
}
var kbStatusFields = []string{
"id", "reachable", "knowledge_count", "chunk_count",
"id", "reachable", "retrieval_ready", "knowledge_count", "chunk_count",
"is_processing", "processing_count",
}
@@ -73,7 +77,7 @@ For full metadata (config / pinned / tenant), use 'weknora kb view <id>'.`,
UsedFor: "shallow health probe of a knowledge base (one HTTP call): reachability, no failed-doc aggregation",
RequiredFlags: []string{"<kb-id> (positional)"},
Examples: []string{"weknora kb status kb_abc"},
Output: "envelope.data is {id, reachable, ...}; use `kb check` for deep failed-doc aggregation",
Output: "envelope.data is {id, reachable, retrieval_ready, ...}; retrieval_ready=false means no embedding model is bound (run `kb config set`), so the KB cannot index/retrieve; use `kb check` for deep failed-doc aggregation",
})
return cmd
}
@@ -89,6 +93,7 @@ func runStatus(ctx context.Context, svc StatusService, id string) (*StatusResult
return &StatusResult{
ID: kb.ID,
Reachable: true,
RetrievalReady: kb.EmbeddingModelID != "",
KnowledgeCount: kb.KnowledgeCount,
ChunkCount: kb.ChunkCount,
IsProcessing: kb.IsProcessing,
@@ -115,11 +120,20 @@ func writeStatusText(w io.Writer, res *StatusResult) error {
if !res.Reachable {
return nil
}
fmt.Fprintf(w, "Retrieval: %v%s\n", res.RetrievalReady, retrievalHint(res.RetrievalReady))
fmt.Fprintf(w, "Knowledge: %d\n", res.KnowledgeCount)
fmt.Fprintf(w, "Chunks: %d\n", res.ChunkCount)
fmt.Fprintf(w, "Processing: %v (%d active)\n", res.IsProcessing, res.ProcessingCount)
return nil
}
// retrievalHint annotates a not-ready KB in text output with the fix.
func retrievalHint(ready bool) string {
if ready {
return ""
}
return " ← no embedding model bound; run `weknora kb config set <id>`"
}
// compile-time check: SDK client satisfies StatusService.
var _ StatusService = (*sdk.Client)(nil)