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
+72 -6
View File
@@ -8,7 +8,9 @@ import (
"time"
)
// InitializationConfig represents the initialization configuration for a knowledge base
// InitializationConfig is the WRITE payload for InitializeByKB / UpdateKBConfig
// (the server's write endpoint accepts these flat model ids). It is NOT the
// shape the read endpoint returns — see KBModelConfigView / GetInitializationConfig.
type InitializationConfig struct {
ChatModelID string `json:"chat_model_id,omitempty"`
EmbeddingModelID string `json:"embedding_model_id,omitempty"`
@@ -16,6 +18,40 @@ type InitializationConfig struct {
MultimodalID string `json:"multimodal_id,omitempty"`
}
// KBModelConfigView is the secret-free, read-only model configuration of a
// knowledge base, returned by GetInitializationConfig. The server's read
// response nests config under embedding/llm/rerank/multimodal and INCLUDES
// provider apiKey/baseUrl (for the web config form); this view intentionally
// parses only the non-secret fields, so credentials can never leak through the
// CLI. Field tags are snake_case (the CLI envelope convention), remapped from
// the server's camelCase.
type KBModelConfigView struct {
RetrievalReady bool `json:"retrieval_ready"` // embedding model bound → KB can embed/retrieve
Embedding ModelSlotView `json:"embedding"`
LLM ModelSlotView `json:"llm"`
Rerank RerankSlotView `json:"rerank"`
Multimodal MultimodalSlotView `json:"multimodal"`
}
// ModelSlotView is one non-secret model slot (embedding / llm).
type ModelSlotView struct {
Configured bool `json:"configured"`
ModelName string `json:"model_name,omitempty"`
Source string `json:"source,omitempty"`
Dimension int `json:"dimension,omitempty"`
}
// RerankSlotView is the rerank slot (may be disabled).
type RerankSlotView struct {
Enabled bool `json:"enabled"`
ModelName string `json:"model_name,omitempty"`
}
// MultimodalSlotView reports whether multimodal processing is enabled.
type MultimodalSlotView struct {
Enabled bool `json:"enabled"`
}
// OllamaModelInfo represents info about an Ollama model
type OllamaModelInfo struct {
Name string `json:"name"`
@@ -40,20 +76,50 @@ type ModelCheckResult struct {
Message string `json:"message,omitempty"`
}
// GetInitializationConfig gets the current initialization config for a knowledge base
func (c *Client) GetInitializationConfig(ctx context.Context, kbID string) (*InitializationConfig, error) {
// GetInitializationConfig returns a knowledge base's model configuration as a
// secret-free KBModelConfigView. The server response nests config under
// embedding/llm/rerank/multimodal and includes provider apiKey/baseUrl; this
// parses ONLY the non-secret fields (apiKey/baseUrl are never read into the
// struct, so they cannot leak through the CLI) and remaps to snake_case.
func (c *Client) GetInitializationConfig(ctx context.Context, kbID string) (*KBModelConfigView, error) {
resp, err := c.doRequest(ctx, http.MethodGet, fmt.Sprintf("/api/v1/initialization/config/%s", kbID), nil, nil)
if err != nil {
return nil, err
}
// Deliberately model only non-secret fields; apiKey / baseUrl in the server
// payload are ignored by omission.
var result struct {
Success bool `json:"success"`
Data *InitializationConfig `json:"data"`
Data struct {
Embedding struct {
Source string `json:"source"`
ModelName string `json:"modelName"`
Dimension int `json:"dimension"`
} `json:"embedding"`
LLM struct {
Source string `json:"source"`
ModelName string `json:"modelName"`
} `json:"llm"`
Rerank struct {
Enabled bool `json:"enabled"`
ModelName string `json:"modelName"`
} `json:"rerank"`
Multimodal struct {
Enabled bool `json:"enabled"`
} `json:"multimodal"`
} `json:"data"`
}
if err := parseResponse(resp, &result); err != nil {
return nil, err
}
return result.Data, nil
d := result.Data
view := &KBModelConfigView{
RetrievalReady: d.Embedding.ModelName != "",
Embedding: ModelSlotView{Configured: d.Embedding.ModelName != "", ModelName: d.Embedding.ModelName, Source: d.Embedding.Source, Dimension: d.Embedding.Dimension},
LLM: ModelSlotView{Configured: d.LLM.ModelName != "", ModelName: d.LLM.ModelName, Source: d.LLM.Source},
Rerank: RerankSlotView{Enabled: d.Rerank.Enabled, ModelName: d.Rerank.ModelName},
Multimodal: MultimodalSlotView{Enabled: d.Multimodal.Enabled},
}
return view, nil
}
// InitializeByKB initializes a knowledge base with model configuration