[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,