feat: admin 端点补齐 + 视觉真推理 + 语音链路 + wire.go 收口(A+B+第3步)
CI / Backend (build / vet / test / cross-compile) (push) Has been cancelled
CI / Frontend (tsc + vite build) (push) Has been cancelled

批次A admin 端点(原本 404 变 200 真实数据):
- GET /admin/llm:读 s.cfg.LLM 组 openai+anthropic 两 provider(enabled=当前 Provider、multimodal=配 VisionModel),APIKey 不进 wire 零泄露。
- GET /admin/automations:*automations.Service.List()(reminders+event rules+cron schedules,cron 加只读登记)。
- GET /admin/users:cfg.AdminUser + *auth.APIKey.List()(密钥掩码);无用户存储,恒先返回当前 admin 账号。
- GET /admin/backthink:*backthink.Backthink.List(ctx,50)。均只读、owner/admin RBAC、{data} 信封。

批次B 视觉真推理 + 语音:
- rest.go chatRequest 加 Image?;流式 publishChatStream 带 image;userChatMessages 构造 ImageMessage(model.go:71)。
- loop/vision.go:ImageResolver 可注入(MVP 先看图再对话);run.go Run 开头 resolveImages,无 resolver 透传直交主模型。
- vision/resolver.go:MessageResolver 调 vision.Router.Route——KindMain 保留图片交主模型多模态、KindVisionTool/OCRTool 经 dispatcher.Invoke 折叠成 [图片内容] 文本、KindUnsupported 记日志保留原图不崩。
- gateway/voice.go:VoiceService 接口 + SetVoice 注入点 + handleVoiceInput(未注入回 error 不崩)+ runVoiceTurn 异步 STT→loop chat→TTS→定向 voice_output 帧。
- ws_hub/ws_route:voice_input 接 handleVoiceInput;前端 ws.ts decodeBase64/playVoiceAudio/case voice_output。

第3步 wire.go 收口(唯一碰 wire.go 的一步):
- Deps 补传 Automations:a.automation / Backthink:a.backthink / Users:auth.NewAPIKey(a.cfg.Auth)(*auth.APIKey 原生满足 UserStore,避免 admin 重复的复合类型)。
- gw.SetVoice(a.voice);loop.Options.Vision = vision.NewMessageResolver(router, info, dispatcher.Invoke)(router=NewRouter(WithVisionTool/WithOCRTool)、info=cfg.LLM.VisionModel)。

实机验证:四 admin 端点 200 真实数据(llm 双 provider 脱敏、users=admin,yeij0942,owner);WS 握手正常。go build/vet/test 全绿 + 前端 tsc。wire.go 557 行。
This commit is contained in:
Aska committed 2026-09-06 18:54:05 +08:00
1 parent 648292d035
commit 518bd0a230
21 files changed
+976 -38

No files matched your search

+8 -4
View File
@@ -28,6 +28,7 @@ const (
wsChatSubject = "ws.chat"
wsStreamSubject = "ws.stream"
wsVoiceInput = "ws.voice_input"
wsVoiceOutput = "voice_output"
wsReadLimit = 4096
wsWriteWait = 10 * time.Second
wsPongWait = 60 * time.Second
@@ -72,6 +73,7 @@ type hub struct {
runner Chatter
auditor SubagentAuditor
taskOutputs TaskOutputStore
voice VoiceService
streaming bool
log *slog.Logger
upgrader websocket.Upgrader
@@ -90,6 +92,7 @@ func newHub(s *Server) *hub {
runner: s.runner,
auditor: s.auditor,
taskOutputs: s.taskOutputs,
voice: s.voice,
streaming: s.streaming,
log: s.log,
origins: origins,
@@ -213,14 +216,14 @@ func (h *hub) streamChat(ctx context.Context, payload any) {
_ = json.Unmarshal(b, &req)
}
turnID := newTurnID()
if h.runner == nil || strings.TrimSpace(req.Text) == "" {
if h.runner == nil || (strings.TrimSpace(req.Text) == "" && strings.TrimSpace(req.Image) == "") {
h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": "idle"}})
return
}
if req.SessionID == "" {
req.SessionID = "web"
}
res, err := h.runner.Run(ctx, req.SessionID, []model.Message{model.TextMessage(model.RoleUser, req.Text)})
res, err := h.runner.Run(ctx, req.SessionID, userChatMessages(req.Text, req.Image))
if err != nil {
h.log.Error("ws chat run", "err", err, "session", req.SessionID)
h.broadcast(wsEvent{Type: "stream_end", TurnID: turnID, Seq: int(h.streamSeq.Add(1)), Data: map[string]any{"stopReason": "error", "error": err.Error()}})
@@ -256,6 +259,7 @@ func (h *hub) broadcastStream(payload any) {
type chatStreamRequest struct {
SessionID string `json:"sessionId"`
Text string `json:"text"`
Image string `json:"image,omitempty"`
}
// handleWS upgrades /ws/chat after authenticating the JWT from the query token or
@@ -382,11 +386,11 @@ func (c *wsConn) enqueueJSON(ev wsEvent) {
}
// publishChatStream publishes a ws.chat streaming trigger (REST stream mode).
func (s *Server) publishChatStream(ctx context.Context, sessionID, text string) {
func (s *Server) publishChatStream(ctx context.Context, sessionID, text, image string) {
if s.bus == nil {
return
}
_ = s.bus.Publish(ctx, wsChatSubject, map[string]any{"sessionId": sessionID, "text": text})
_ = s.bus.Publish(ctx, wsChatSubject, map[string]any{"sessionId": sessionID, "text": text, "image": image})
}
// wsToken extracts the JWT from the ?token= query or the Authorization header.