[实时字幕端点]：完成无新文字快速结束录音，包含1.5秒停滞配置、Capture端点和回归测试

src/owner_voice_pet/assistant_pipeline.py

@@ -163,6 +163,7 @@ class TurnController:
         self.vad_recorder.provider.reset()
         self.audio_preprocessor.reset()
         realtime_session = self._start_realtime_transcript()
+        last_partial_ms: int | None = None
         self._event(CAPTURE_STARTED, PipelineState.RECORDING, state_message, turn_id=turn_id)
         while True:
             frames = self.transport.read_frames(timeout_ms=100)
@@ -180,7 +181,8 @@ class TurnController:
                 if isinstance(result, ProviderError):
                     return result
                 if self.vad_recorder.started and realtime_session is not None:
-                    self._emit_realtime_transcript(realtime_session, frame, turn_id)
+                    if self._emit_realtime_transcript(realtime_session, frame, turn_id):
+                        last_partial_ms = frame.timestamp_ms
                 if isinstance(result, AudioSegment):
                     if realtime_session is not None:
                         self._finish_realtime_transcript(realtime_session, turn_id)
@@ -192,6 +194,18 @@ class TurnController:
                         payload={"end_reason": result.metadata.get("end_reason", "")},
                     )
                     return result
+                if self._should_end_after_realtime_idle(last_partial_ms, frame.timestamp_ms):
+                    if realtime_session is not None:
+                        self._finish_realtime_transcript(realtime_session, turn_id)
+                    result = self.vad_recorder.finish("partial_transcript_idle")
+                    self._event(
+                        SPEECH_ENDED,
+                        PipelineState.RECORDING,
+                        "用户语音结束",
+                        turn_id=turn_id,
+                        payload={"end_reason": result.metadata.get("end_reason", "")},
+                    )
+                    return result
 
     def _start_realtime_transcript(self) -> RealtimeTranscriptSession | None:
         if not self.config.realtime_transcript_enabled or self.realtime_stt is None:
@@ -203,14 +217,19 @@ class TurnController:
         realtime_session: RealtimeTranscriptSession,
         frame: AudioFrame,
         turn_id: int,
-    ) -> None:
+    ) -> bool:
         transcript = realtime_session.accept_frame(frame)
         if transcript is None:
-            return
+            return False
         text = transcript.normalized_text
         if not is_valid_transcript_text(text):
-            return
+            return False
         self._event(TRANSCRIPT_PARTIAL, PipelineState.RECORDING, "", turn_id=turn_id, payload={"text": text})
+        return True
+
+    def _should_end_after_realtime_idle(self, last_partial_ms: int | None, current_ms: int) -> bool:
+        timeout_ms = self.config.realtime_transcript_idle_timeout_ms
+        return timeout_ms > 0 and last_partial_ms is not None and current_ms - last_partial_ms >= timeout_ms
 
     def _finish_realtime_transcript(
         self,

src/owner_voice_pet/cli.py

@@ -65,6 +65,7 @@ def main(argv: list[str] | None = None) -> int:
                     "llm_api_style": config.llm_api_style,
                     "llm_stream": config.llm_stream,
                     "realtime_transcript_enabled": config.realtime_transcript_enabled,
+                    "realtime_transcript_idle_timeout_ms": config.realtime_transcript_idle_timeout_ms,
                     "llm_api_key_present": bool(config.llm_api_key),
                     "asset_dir": str(config.asset_dir),
                     "wake_provider": config.wake_provider,
@@ -201,6 +202,7 @@ def main(argv: list[str] | None = None) -> int:
                 llm_api_style=config.llm_api_style,
                 llm_stream=False,
                 realtime_transcript_enabled=config.realtime_transcript_enabled,
+                realtime_transcript_idle_timeout_ms=config.realtime_transcript_idle_timeout_ms,
                 audio_input_device=config.audio_input_device,
                 audio_output_device=config.audio_output_device,
                 asset_dir=config.asset_dir,

src/owner_voice_pet/config.py

@@ -17,6 +17,7 @@ class AppConfig:
     llm_api_style: str = "chat_completions"
     llm_stream: bool = True
     realtime_transcript_enabled: bool = True
+    realtime_transcript_idle_timeout_ms: int = 1500
     audio_input_device: str | None = None
     audio_output_device: str | None = None
     asset_dir: Path = Path("assets/pet")
@@ -71,6 +72,9 @@ class AppConfig:
             llm_stream=(get("LLM_STREAM", "1") or "1").lower() not in {"0", "false", "no"},
             realtime_transcript_enabled=(get("REALTIME_TRANSCRIPT_ENABLED", "1") or "1").lower()
             not in {"0", "false", "no"},
+            realtime_transcript_idle_timeout_ms=int(
+                get("REALTIME_TRANSCRIPT_IDLE_TIMEOUT_MS", "1500") or "1500"
+            ),
             audio_input_device=get("AUDIO_INPUT_DEVICE"),
             audio_output_device=get("AUDIO_OUTPUT_DEVICE"),
             asset_dir=Path(get("ASSET_DIR", "assets/pet") or "assets/pet"),
@@ -165,6 +169,16 @@ class AppConfig:
                     "startup",
                 )
             )
+        if self.realtime_transcript_idle_timeout_ms < 0:
+            errors.append(
+                ProviderError(
+                    ErrorCode.CONFIG_MISSING_VALUE,
+                    "OWNER_REALTIME_TRANSCRIPT_IDLE_TIMEOUT_MS must be non-negative",
+                    False,
+                    "config",
+                    "startup",
+                )
+            )
         if self.wake_provider not in {"local_kws"}:
             errors.append(
                 ProviderError(

src/owner_voice_pet/vad.py

@@ -283,6 +283,9 @@ class VadRecorder:
         self.provider.reset()
         return segment
 
+    def finish(self, end_reason: str) -> AudioSegment:
+        return self._build_segment(end_reason)
+
 
 @dataclass(slots=True)
 class PrimarySpeakerVadRecorder(VadRecorder):