115 lines
3.2 KiB
Go
115 lines
3.2 KiB
Go
|
package eino
|
|||
|
|
|
|||
|
|
import (
|
|||
|
|
"context"
|
|||
|
|
"time"
|
|||
|
|
|
|||
|
|
"github.com/cloudwego/eino/compose"
|
|||
|
|
|
|||
|
|
"github.com/hhs/camtalk/internal/logger"
|
|||
|
|
"github.com/hhs/camtalk/internal/models"
|
|||
|
|
"github.com/hhs/camtalk/internal/session"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
// NewDoneLambda 创建 Done Lambda 节点。
|
|||
|
|
// 输入: struct{}（TTS 完成信号）→ 输出: PipelineOutput
|
|||
|
|
//
|
|||
|
|
// 从 PipelineState 读取完整回复和 token 用量，发送 llm_done 到客户端，
|
|||
|
|
// 追加助手消息到会话历史，返回 PipelineOutput。
|
|||
|
|
func NewDoneLambda(sessionMgr session.Manager, model string) *compose.Lambda {
|
|||
|
|
return compose.InvokableLambda(func(ctx context.Context, _ struct{}) (*PipelineOutput, error) {
|
|||
|
|
log := logger.Log
|
|||
|
|
sender := senderFromCtx(ctx)
|
|||
|
|
requestID := requestIDFromCtx(ctx)
|
|||
|
|
state := stateFromCtx(ctx)
|
|||
|
|
|
|||
|
|
if state == nil {
|
|||
|
|
return &PipelineOutput{}, nil
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
state.mu.Lock()
|
|||
|
|
fullResponse := state.FullResponse.String()
|
|||
|
|
transcribedText := state.TranscribedText
|
|||
|
|
tokenUsage := state.TokenUsage
|
|||
|
|
modelName := model
|
|||
|
|
state.mu.Unlock()
|
|||
|
|
|
|||
|
|
// 追加助手消息到会话历史
|
|||
|
|
sessionID := ""
|
|||
|
|
if state != nil {
|
|||
|
|
// 从 context 获取 sessionID（由适配器注入）
|
|||
|
|
if sid, ok := ctx.Value(ctxKeySessionID{}).(string); ok {
|
|||
|
|
sessionID = sid
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
if sessionID != "" && sessionMgr != nil && fullResponse != "" {
|
|||
|
|
if err := sessionMgr.AppendMessage(ctx, sessionID, models.Message{
|
|||
|
|
Role: "assistant",
|
|||
|
|
Content: fullResponse,
|
|||
|
|
}); err != nil {
|
|||
|
|
log.Errorw("追加助手消息到历史失败", "error", err)
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// 发送 llm_done
|
|||
|
|
if sender != nil && requestID != "" {
|
|||
|
|
done := models.WsLLMDone{
|
|||
|
|
Type: "llm_done",
|
|||
|
|
RequestID: requestID,
|
|||
|
|
FullText: fullResponse,
|
|||
|
|
Model: modelName,
|
|||
|
|
LatencyMs: 0, // 由适配器计算
|
|||
|
|
}
|
|||
|
|
if tokenUsage != nil {
|
|||
|
|
done.TokensUsed = struct {
|
|||
|
|
Prompt int `json:"prompt"`
|
|||
|
|
Completion int `json:"completion"`
|
|||
|
|
Total int `json:"total"`
|
|||
|
|
}{
|
|||
|
|
Prompt: tokenUsage.Prompt,
|
|||
|
|
Completion: tokenUsage.Completion,
|
|||
|
|
Total: tokenUsage.Total,
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
if err := sender.SendLLMDone(done); err != nil {
|
|||
|
|
log.Errorw("发送 llm_done 失败", "error", err)
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
log.Infow("查询处理完成",
|
|||
|
|
"request_id", requestID,
|
|||
|
|
"text_length", len(fullResponse))
|
|||
|
|
|
|||
|
|
return &PipelineOutput{
|
|||
|
|
TranscribedText: transcribedText,
|
|||
|
|
FullResponse: fullResponse,
|
|||
|
|
Model: modelName,
|
|||
|
|
TokenUsage: tokenUsage,
|
|||
|
|
}, nil
|
|||
|
|
})
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// ctxKeySessionID sessionID 的 context key。
|
|||
|
|
type ctxKeySessionID struct{}
|
|||
|
|
|
|||
|
|
// WithSessionID 将 sessionID 注入 context。
|
|||
|
|
func WithSessionID(ctx context.Context, sessionID string) context.Context {
|
|||
|
|
return context.WithValue(ctx, ctxKeySessionID{}, sessionID)
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// latencyFromCtx 从 context 获取开始时间并计算延迟。
|
|||
|
|
func latencyFromCtx(ctx context.Context) int64 {
|
|||
|
|
if startTime, ok := ctx.Value(ctxKeyStartTime{}).(time.Time); ok {
|
|||
|
|
return time.Since(startTime).Milliseconds()
|
|||
|
|
}
|
|||
|
|
return 0
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
// ctxKeyStartTime 请求开始时间的 context key。
|
|||
|
|
type ctxKeyStartTime struct{}
|
|||
|
|
|
|||
|
|
// WithStartTime 将请求开始时间注入 context。
|
|||
|
|
func WithStartTime(ctx context.Context, t time.Time) context.Context {
|
|||
|
|
return context.WithValue(ctx, ctxKeyStartTime{}, t)
|
|||
|
|
}
|