feat(model,capacity,vision,io): per-persona 路由 + 本地三级(默认关) + L3 分类 + OCR 独立模型 + image-crop 工具(裁决 03.4.1/03.4.3/14.4.1/14.4.4/14.4.5)
- 03.4.1:per-persona 路由载体选 models.json(组内新增 personaModels/personaProviders + 校验 + PersonaRoute()), Router/RuntimeLLM 快照绑定、loop 流式路径按该 turn 的 persona 路由;主步用路由结果、降级步钉自己的模型 - 03.4.3:本地第三级降级链(LLM_LOCAL_*,Configured() 含 Enabled ⇒ **默认关**),warn 标注来源 - 14.4.4:capacity 接入 L3(分类器接口 + TTL 缓存 + 严格 JSON 解析),CAPACITY_L3_ENABLED **默认 false** - 14.4.1:语义修正 —— group.multimodal 才是「主模型能否收图」(env 路径不再臆断),LLM_VISION_MODEL 只配视觉工具; vision/OCR 可各用不同模型;runtime 不再因有图抢路由(vision.Router 是唯一分层权威) - 14.4.5:新增 image-crop 工具(工具数 5→6,策略默认 owner-only),schema 支持按区域裁切 - 组合根:wire_runtime 读 group.Multimodal;capacity 装配拆出 wire_capacity.go(守 500 行) - 复核:`go build`/`go vet`/各包 `go test -count=1` 全绿;**6 条变异反证**先红后还原(含作者自查出的 2 条假阳性变异) - 未落:按 provider 的 thinking 开关(需 openai_encode.go/openai.go 文件面)、persona awakening(需 loader 文件面)
This commit is contained in:
1 parent
63e5b70e3d
commit
fa33c79e11
24 files changed
+1941
-122
No files matched your search
@@ -125,6 +125,17 @@ func (m *RuntimeLLM) RouteRequest(req Request) (string, bool) {
|
||||
return r.RouteRequest(req)
|
||||
}
|
||||
|
||||
// RouteRequestForPersona implements PersonaRouter (裁决 03.4.1): the loop routes
|
||||
// a turn as the persona it answers as, and a per-persona binding in the active
|
||||
// models.json group reaches the request through here.
|
||||
func (m *RuntimeLLM) RouteRequestForPersona(personaID string, req Request) (string, bool) {
|
||||
r := m.load().router
|
||||
if r == nil {
|
||||
return "", false
|
||||
}
|
||||
return r.RouteRequestForPersona(personaID, req)
|
||||
}
|
||||
|
||||
// loadInitial builds the first snapshot; a build failure leaves a nil chain so
|
||||
// calls report a clear no-model error instead of panicking.
|
||||
func (m *RuntimeLLM) loadInitial() {
|
||||
@@ -160,11 +171,20 @@ func (m *RuntimeLLM) load() *runtimeChainSnapshot {
|
||||
|
||||
// buildSnapshot turns the active group (index 0) into a chain+router. A group
|
||||
// without a base URL/model yields a nil chain (no model configured), surfaced as
|
||||
// ErrNoModel by the adapter methods. The Router keeps the env vision model so a
|
||||
// dedicated vision model survives a reload that only changes the vendor group.
|
||||
// ErrNoModel by the adapter methods.
|
||||
//
|
||||
// The env-local rung is copied onto the group's flat config because a models.json
|
||||
// group does not carry it: without that copy the third degradation level
|
||||
// (裁决 03.4.3) would silently disappear as soon as models.json exists.
|
||||
//
|
||||
// The router is seeded with the active group's per-persona bindings
|
||||
// (裁决 03.4.1). It is deliberately NOT given the env vision model: image routing
|
||||
// is owned by vision.Router, and a "has image → switch model" rule here bypassed
|
||||
// that decision (裁决 14.4.1/14.4.5).
|
||||
func buildSnapshot(groups []runtimeconfig.Group, env config.LLMConfig, log *slog.Logger) (*runtimeChainSnapshot, error) {
|
||||
active := groups[0]
|
||||
cfg := active.ToLLMConfig()
|
||||
cfg.Local = env.Local
|
||||
chain, err := NewChatChainWithLog(cfg, log)
|
||||
if err != nil && !errors.Is(err, ErrNoModel) {
|
||||
return nil, err
|
||||
@@ -175,9 +195,20 @@ func buildSnapshot(groups []runtimeconfig.Group, env config.LLMConfig, log *slog
|
||||
// last step of a chain that really has a fallback (design/04 §3.1).
|
||||
chain = chain.WithTokenBudget(active.MaxTokens, env.FallbackMaxTokens)
|
||||
}
|
||||
router := NewRouter(DefaultModelForProvider(cfg),
|
||||
WithVisionModel(env.VisionModel),
|
||||
WithDefaultProvider(cfg.Provider),
|
||||
)
|
||||
router := NewRouter(DefaultModelForProvider(cfg), personaRouterOptions(active, cfg)...)
|
||||
return &runtimeChainSnapshot{chain: chain, router: router, group: active, groups: groups}, nil
|
||||
}
|
||||
|
||||
// personaRouterOptions turns the active group's per-persona model/provider
|
||||
// bindings into router options (裁决 03.4.1). It is a helper so buildSnapshot
|
||||
// stays inside the 80-line function budget.
|
||||
func personaRouterOptions(active runtimeconfig.Group, cfg config.LLMConfig) []RouterOption {
|
||||
opts := []RouterOption{WithDefaultProvider(cfg.Provider)}
|
||||
for persona, model := range active.PersonaModels {
|
||||
opts = append(opts, WithPersonaModel(persona, model))
|
||||
}
|
||||
for persona, provider := range active.PersonaProviders {
|
||||
opts = append(opts, WithPersonaProvider(persona, provider))
|
||||
}
|
||||
return opts
|
||||
}
|
||||
Reference in new issue
Block a user