mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-08-31 00:50:02 +08:00
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.
347 lines
12 KiB
Go
347 lines
12 KiB
Go
package client
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"time"
|
|
)
|
|
|
|
// 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"`
|
|
RerankModelID string `json:"rerank_model_id,omitempty"`
|
|
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"`
|
|
Size int64 `json:"size"`
|
|
ModifiedAt string `json:"modified_at"`
|
|
}
|
|
|
|
// DownloadTask represents an Ollama model download task
|
|
type DownloadTask struct {
|
|
ID string `json:"id"`
|
|
ModelName string `json:"modelName"`
|
|
Status string `json:"status"`
|
|
Progress float64 `json:"progress"`
|
|
Message string `json:"message"`
|
|
StartTime time.Time `json:"startTime"`
|
|
EndTime *time.Time `json:"endTime,omitempty"`
|
|
}
|
|
|
|
// ModelCheckResult represents the result of checking a remote model
|
|
type ModelCheckResult struct {
|
|
Success bool `json:"success"`
|
|
Message string `json:"message,omitempty"`
|
|
}
|
|
|
|
// 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 {
|
|
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
|
|
}
|
|
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
|
|
func (c *Client) InitializeByKB(ctx context.Context, kbID string, config *InitializationConfig) error {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, fmt.Sprintf("/api/v1/initialization/initialize/%s", kbID), config, nil)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return parseResponse(resp, nil)
|
|
}
|
|
|
|
// UpdateKBConfig updates the model configuration for a knowledge base.
|
|
//
|
|
// Deprecated: the PUT /initialization/config endpoint binds KBModelConfigRequest
|
|
// (fields llmModelId / embeddingModelId), not InitializationConfig, so this
|
|
// method sends a shape the server rejects. Use SetKBModelConfig instead.
|
|
func (c *Client) UpdateKBConfig(ctx context.Context, kbID string, config *InitializationConfig) error {
|
|
resp, err := c.doRequest(ctx, http.MethodPut, fmt.Sprintf("/api/v1/initialization/config/%s", kbID), config, nil)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return parseResponse(resp, nil)
|
|
}
|
|
|
|
// KBModelConfig points a knowledge base at already-registered models. Field
|
|
// names match the server's KBModelConfigRequest (PUT
|
|
// /initialization/config/:kbId). LLMModelID is required server-side;
|
|
// EmbeddingModelID is optional (omitted when RAG indexing is disabled).
|
|
type KBModelConfig struct {
|
|
LLMModelID string `json:"llmModelId"`
|
|
EmbeddingModelID string `json:"embeddingModelId,omitempty"`
|
|
}
|
|
|
|
// SetKBModelConfig binds a knowledge base to already-registered models via PUT
|
|
// /initialization/config/:kbId. Register models first with CreateModel; the
|
|
// server rejects unknown model ids and refuses to change the embedding model of
|
|
// a KB that already has documents.
|
|
func (c *Client) SetKBModelConfig(ctx context.Context, kbID string, cfg *KBModelConfig) error {
|
|
resp, err := c.doRequest(ctx, http.MethodPut, fmt.Sprintf("/api/v1/initialization/config/%s", kbID), cfg, nil)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return parseResponse(resp, nil)
|
|
}
|
|
|
|
// CheckOllamaStatus checks if Ollama is running and accessible
|
|
func (c *Client) CheckOllamaStatus(ctx context.Context) (bool, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodGet, "/api/v1/initialization/ollama/status", nil, nil)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data struct {
|
|
Available bool `json:"available"`
|
|
} `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return false, err
|
|
}
|
|
return result.Data.Available, nil
|
|
}
|
|
|
|
// ListOllamaModels lists all locally available Ollama models
|
|
func (c *Client) ListOllamaModels(ctx context.Context) ([]OllamaModelInfo, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodGet, "/api/v1/initialization/ollama/models", nil, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data []OllamaModelInfo `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// CheckOllamaModels checks if specific Ollama models are available
|
|
func (c *Client) CheckOllamaModels(ctx context.Context, models []string) (map[string]bool, error) {
|
|
req := map[string][]string{"models": models}
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/ollama/models/check", req, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data map[string]bool `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// DownloadOllamaModel starts downloading an Ollama model
|
|
func (c *Client) DownloadOllamaModel(ctx context.Context, modelName string) (*DownloadTask, error) {
|
|
req := map[string]string{"model": modelName}
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/ollama/models/download", req, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *DownloadTask `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// GetOllamaDownloadProgress gets the download progress of an Ollama model
|
|
func (c *Client) GetOllamaDownloadProgress(ctx context.Context, taskID string) (*DownloadTask, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodGet, fmt.Sprintf("/api/v1/initialization/ollama/download/progress/%s", taskID), nil, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *DownloadTask `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// ListOllamaDownloadTasks lists all Ollama download tasks
|
|
func (c *Client) ListOllamaDownloadTasks(ctx context.Context) ([]*DownloadTask, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodGet, "/api/v1/initialization/ollama/download/tasks", nil, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data []*DownloadTask `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// CheckRemoteModel checks if a remote model API is accessible
|
|
func (c *Client) CheckRemoteModel(ctx context.Context, params map[string]string) (*ModelCheckResult, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/remote/check", params, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *ModelCheckResult `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// TestEmbeddingModel tests an embedding model
|
|
func (c *Client) TestEmbeddingModel(ctx context.Context, params map[string]string) (*ModelCheckResult, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/embedding/test", params, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *ModelCheckResult `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// CheckRerankModel checks if a rerank model is accessible
|
|
func (c *Client) CheckRerankModel(ctx context.Context, params map[string]string) (*ModelCheckResult, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/rerank/check", params, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *ModelCheckResult `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// TestMultimodalFunction tests multimodal model functionality
|
|
func (c *Client) TestMultimodalFunction(ctx context.Context, params map[string]string) (*ModelCheckResult, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/multimodal/test", params, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data *ModelCheckResult `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|
|
|
|
// ExtractTextRelations extracts text relations for knowledge graph
|
|
func (c *Client) ExtractTextRelations(ctx context.Context, params any) (json.RawMessage, error) {
|
|
resp, err := c.doRequest(ctx, http.MethodPost, "/api/v1/initialization/extract/text-relation", params, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
var result struct {
|
|
Success bool `json:"success"`
|
|
Data json.RawMessage `json:"data"`
|
|
}
|
|
if err := parseResponse(resp, &result); err != nil {
|
|
return nil, err
|
|
}
|
|
return result.Data, nil
|
|
}
|