[播报文本净化]：完成TTS表情包过滤，包含emoji清理、上下文净化和回归测试

src/owner_voice_pet/runtime.py

@@ -33,7 +33,7 @@ from .models import AudioSegment, ErrorCode, PipelineState, ProviderError
 from .protocols import AudioTransport, LlmProvider, RealtimeSttProvider, SttProvider, TtsProvider, WakeWordProvider
 from .stt import CloudAsrSttProvider, SherpaOnnxSttProvider, is_valid_transcript_text
 from .transport import SoundDeviceAudioTransport
-from .tts import CloudTtsProvider, MacSayTtsProvider, SentenceBuffer
+from .tts import CloudTtsProvider, MacSayTtsProvider, SentenceBuffer, sanitize_tts_text
 from .vad import EnergyVadProvider, HybridVadProvider, PrimarySpeakerVadRecorder, SherpaOnnxVadProvider, VadRecorder
 from .wakeword import SherpaOnnxKeywordWakeWordProvider
 
@@ -267,13 +267,18 @@ class LiveVoiceRuntime:
         self.context.append_user(user_text)
         self._event(LLM_STARTED, PipelineState.THINKING, "思考中：正在生成回复", turn_id=turn_id)
         assistant_text = ""
+        spoken_parts: list[str] = []
         try:
             for delta in self.llm.stream_reply(self.context.build_llm_messages()):
                 assistant_text += delta.text_delta
                 for sentence in self.sentence_buffer.feed(delta.text_delta, bool(delta.finish_reason)):
-                    self._speak(sentence, turn_id)
+                    spoken = self._speak(sentence, turn_id)
+                    if spoken:
+                        spoken_parts.append(spoken)
             for sentence in self.sentence_buffer.flush():
-                self._speak(sentence, turn_id)
+                spoken = self._speak(sentence, turn_id)
+                if spoken:
+                    spoken_parts.append(spoken)
         except ProviderError as exc:
             return self._recover(exc, turn_id)
         if not assistant_text.strip():
@@ -287,18 +292,34 @@ class LiveVoiceRuntime:
                 ),
                 turn_id,
             )
-        self.context.append_assistant(assistant_text)
+        spoken_text = "".join(spoken_parts)
+        if not spoken_text.strip():
+            return self._recover(
+                ProviderError(
+                    ErrorCode.TTS_EMPTY_AUDIO,
+                    "LLM reply contained no speakable text after TTS sanitization",
+                    True,
+                    "live-runtime",
+                    "tts",
+                ),
+                turn_id,
+            )
+        self.context.append_assistant(spoken_text)
         self._event(STANDBY_RESUMED, PipelineState.WAKE_LISTENING, "恢复待机：可继续唤醒", turn_id=turn_id)
-        return TurnResult(True, user_text, assistant_text, states=list(self._states))
+        return TurnResult(True, user_text, spoken_text, states=list(self._states))
 
-    def _speak(self, sentence: str, turn_id: int) -> None:
+    def _speak(self, sentence: str, turn_id: int) -> str:
+        spoken_sentence = sanitize_tts_text(sentence)
+        if not spoken_sentence:
+            return ""
         self._event(TTS_STARTED, PipelineState.SPEAKING, "播放中：正在播报回复", turn_id=turn_id)
-        segment = self.tts.synthesize(sentence)
+        segment = self.tts.synthesize(spoken_sentence)
         playback = self.transport.play_pcm(segment)
         if playback.error:
             raise playback.error
         self._event(PLAYBACK_FINISHED, PipelineState.SPEAKING, "播放完成", turn_id=turn_id)
         self._drain_input_after_playback()
+        return spoken_sentence
 
     def _recover(self, error: ProviderError, turn_id: int) -> TurnResult:
         self._event(STAGE_ERROR, PipelineState.ERROR_RECOVERING, error.message, turn_id=turn_id, payload={"error": error})