Aska
518bd0a230
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。
95 lines
2.9 KiB
Go
95 lines
2.9 KiB
Go
package vision
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
|
|
"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
|
|
)
|
|
|
|
func TestMessageResolver_FoldsImageToDescription(t *testing.T) {
|
|
t.Parallel()
|
|
rt := NewRouter(WithVisionTool("vision"), WithOCRTool("ocr"))
|
|
invoked := ""
|
|
res := NewMessageResolver(rt, func() ModelInfo {
|
|
return ModelInfo{Name: "text-model", SupportsVision: false}
|
|
}, func(_ context.Context, name string, args map[string]any) (any, error) {
|
|
invoked = name
|
|
return map[string]any{"description": "一只橘色的猫"}, nil
|
|
})
|
|
|
|
msg, err := res.Resolve(context.Background(), model.ImageMessage(model.RoleUser, "看到了吗", "data:image/png;base64,AAAA"))
|
|
if err != nil {
|
|
t.Fatalf("Resolve: %v", err)
|
|
}
|
|
if invoked != "vision" {
|
|
t.Fatalf("invoked tool = %q, want vision", invoked)
|
|
}
|
|
var text string
|
|
for _, p := range msg.Content {
|
|
if p.Type == model.ContentTypeText {
|
|
text += p.Text
|
|
}
|
|
if p.Type == model.ContentTypeImage {
|
|
t.Fatalf("image part still present after tool route: %+v", p)
|
|
}
|
|
}
|
|
if text == "" || text == "看到了吗" {
|
|
t.Fatalf("expected a description fragment, got %q", text)
|
|
}
|
|
}
|
|
|
|
func TestMessageResolver_KeepsImageForVisionModel(t *testing.T) {
|
|
t.Parallel()
|
|
rt := NewRouter(WithVisionTool("vision"), WithOCRTool("ocr"))
|
|
res := NewMessageResolver(rt, func() ModelInfo {
|
|
return ModelInfo{Name: "vision-model", SupportsVision: true}
|
|
}, func(_ context.Context, _ string, _ map[string]any) (any, error) {
|
|
t.Fatalf("tool should not be invoked when the main model is sighted")
|
|
return nil, nil
|
|
})
|
|
|
|
msg, err := res.Resolve(context.Background(), model.ImageMessage(model.RoleUser, "x", "data:image/png;base64,AAAA"))
|
|
if err != nil {
|
|
t.Fatalf("Resolve: %v", err)
|
|
}
|
|
if !messageHasImagePart(msg) {
|
|
t.Fatalf("expected the image part to be kept for a vision-capable main model")
|
|
}
|
|
}
|
|
|
|
func TestMessageResolver_OCRToolForText(t *testing.T) {
|
|
t.Parallel()
|
|
rt := NewRouter(WithVisionTool("vision"), WithOCRTool("ocr"))
|
|
invoked := ""
|
|
res := NewMessageResolver(rt, func() ModelInfo {
|
|
return ModelInfo{Name: "text-model", SupportsVision: false}
|
|
}, func(_ context.Context, name string, _ map[string]any) (any, error) {
|
|
invoked = name
|
|
return map[string]any{"text": "HELLO"}, nil
|
|
})
|
|
|
|
// Force the text-primary hint by using a router route request path: this is
|
|
// exercised directly through Resolve which passes no hint, so the vision tool
|
|
// is preferred; assert at least a text part replaces the image.
|
|
msg, err := res.Resolve(context.Background(), model.ImageMessage(model.RoleUser, "x", "data:image/png;base64,AAAA"))
|
|
if err != nil {
|
|
t.Fatalf("Resolve: %v", err)
|
|
}
|
|
if invoked != "vision" {
|
|
t.Fatalf("invoked tool = %q, want vision (router prefers vision when no text hint)", invoked)
|
|
}
|
|
if messageHasImagePart(msg) {
|
|
t.Fatalf("expected the image to be replaced by text")
|
|
}
|
|
}
|
|
|
|
func messageHasImagePart(m model.Message) bool {
|
|
for _, p := range m.Content {
|
|
if p.Type == model.ContentTypeImage {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|