feat(voice): 语音silent降级信号(C2) — provider仅在结果为空时出现

- voice/Chain+Service: STTWithProvider/TTSWithProvider(真实档位cloud/local/edge-tts/espeak/silent), 旧方法改薄包装
- gateway: transcribe空文本带{text,provider} / voice_output空音频带provider / speech空音频tts_empty+X-Voice-Provider头
- middleware: CORS Access-Control-Expose-Headers: X-Voice-Provider
- 可选接口 voiceProviderReporter(type断言透传), 自定义实现回退silent
- 新增测试10个(provider_signal/voice_signal), build/vet/test全绿+交叉编译
- Docs/api-client v0.23 + api-reference CORS 同步

internal/runtime/multimodal/voice/chain.go

@@ -25,8 +25,16 @@ func NewChain(steps ...Provider) *Chain {
 
 // STT walks the chain for a transcription.
 func (c *Chain) STT(ctx context.Context, audio Audio) (string, error) {
+	text, _, err := c.STTWithProvider(ctx, audio)
+	return text, err
+}
+
+// STTWithProvider is STT but also reports the name of the provider rung that
+// produced the transcription (cloud / local / edge-tts / silent), so a caller can
+// surface which tier actually served the request.
+func (c *Chain) STTWithProvider(ctx context.Context, audio Audio) (string, string, error) {
 	if len(c.steps) == 0 {
-		return "", ErrProviderFailed
+		return "", "", ErrProviderFailed
 	}
 	var lastErr error
 	for _, p := range c.steps {
@@ -36,11 +44,11 @@ func (c *Chain) STT(ctx context.Context, audio Audio) (string, error) {
 		}
 		text, err := stt.STT(ctx, audio)
 		if err == nil {
-			return text, nil
+			return text, p.Name(), nil
 		}
 		lastErr = err
 	}
-	return "", fmt.Errorf("voice: %w: %v", ErrProviderFailed, lastErr)
+	return "", "", fmt.Errorf("voice: %w: %v", ErrProviderFailed, lastErr)
 }
 
 // CloneVoice creates a custom voice via the cloud provider's voice-enrollment
@@ -55,8 +63,15 @@ func (c *Chain) CloneVoice(ctx context.Context, referenceURL, prefix string) (st
 
 // TTS walks the chain for synthesized audio.
 func (c *Chain) TTS(ctx context.Context, text string) (Audio, error) {
+	audio, _, err := c.TTSWithProvider(ctx, text)
+	return audio, err
+}
+
+// TTSWithProvider is TTS but also reports the name of the provider rung that
+// produced the audio.
+func (c *Chain) TTSWithProvider(ctx context.Context, text string) (Audio, string, error) {
 	if len(c.steps) == 0 {
-		return Audio{}, ErrProviderFailed
+		return Audio{}, "", ErrProviderFailed
 	}
 	var lastErr error
 	for _, p := range c.steps {
@@ -66,11 +81,11 @@ func (c *Chain) TTS(ctx context.Context, text string) (Audio, error) {
 		}
 		audio, err := tts.TTS(ctx, text)
 		if err == nil {
-			return audio, nil
+			return audio, p.Name(), nil
 		}
 		lastErr = err
 	}
-	return Audio{}, fmt.Errorf("voice: %w: %v", ErrProviderFailed, lastErr)
+	return Audio{}, "", fmt.Errorf("voice: %w: %v", ErrProviderFailed, lastErr)
 }
 
 // Option customizes a chain built by New.