[低延迟端点]：完成首句保留和快速结束修正，包含ACK缓冲策略、批量读帧和主说话人端点回归测试

src/owner_voice_pet/cli.py

@@ -62,6 +62,7 @@ def main(argv: list[str] | None = None) -> int:
                     "pipeline_mode": config.pipeline_mode,
                     "endpoint_mode": config.endpoint_mode,
                     "speaker_profile_ms": config.speaker_profile_ms,
+                    "speaker_profile_min_ms": config.speaker_profile_min_ms,
                     "speaker_absent_ms": config.speaker_absent_ms,
                     "speaker_similarity_threshold": config.speaker_similarity_threshold,
                     "speaker_min_rms": config.speaker_min_rms,
@@ -164,6 +165,7 @@ def main(argv: list[str] | None = None) -> int:
                 pipeline_mode=config.pipeline_mode,
                 endpoint_mode=config.endpoint_mode,
                 speaker_profile_ms=config.speaker_profile_ms,
+                speaker_profile_min_ms=config.speaker_profile_min_ms,
                 speaker_absent_ms=config.speaker_absent_ms,
                 speaker_similarity_threshold=config.speaker_similarity_threshold,
                 speaker_min_rms=config.speaker_min_rms,

src/owner_voice_pet/config.py

@@ -25,10 +25,11 @@ class AppConfig:
     wake_kws_threshold: float = 0.15
     wake_kws_score: float = 1.0
     wake_ack_text: str = "我在"
-    post_playback_drain_ms: int = 50
+    post_playback_drain_ms: int = 0
     pipeline_mode: str = "live_turn_based"
     endpoint_mode: str = "primary_speaker"
     speaker_profile_ms: int = 600
+    speaker_profile_min_ms: int = 120
     speaker_absent_ms: int = 300
     speaker_similarity_threshold: float = 0.70
     speaker_min_rms: float = 0.012
@@ -73,10 +74,11 @@ class AppConfig:
             wake_kws_threshold=float(get("WAKE_KWS_THRESHOLD", "0.15") or "0.15"),
             wake_kws_score=float(get("WAKE_KWS_SCORE", "1.0") or "1.0"),
             wake_ack_text=get("WAKE_ACK_TEXT", "我在") or "我在",
-            post_playback_drain_ms=int(get("POST_PLAYBACK_DRAIN_MS", "50") or "50"),
+            post_playback_drain_ms=int(get("POST_PLAYBACK_DRAIN_MS", "0") or "0"),
             pipeline_mode=(get("PIPELINE_MODE", "live_turn_based") or "live_turn_based").lower(),
             endpoint_mode=(get("ENDPOINT_MODE", "primary_speaker") or "primary_speaker").lower(),
             speaker_profile_ms=int(get("SPEAKER_PROFILE_MS", "600") or "600"),
+            speaker_profile_min_ms=int(get("SPEAKER_PROFILE_MIN_MS", "120") or "120"),
             speaker_absent_ms=int(get("SPEAKER_ABSENT_MS", "300") or "300"),
             speaker_similarity_threshold=float(
                 get("SPEAKER_SIMILARITY_THRESHOLD", "0.70") or "0.70"
@@ -216,6 +218,7 @@ class AppConfig:
             )
         for name, value in {
             "OWNER_SPEAKER_PROFILE_MS": self.speaker_profile_ms,
+            "OWNER_SPEAKER_PROFILE_MIN_MS": self.speaker_profile_min_ms,
             "OWNER_SPEAKER_ABSENT_MS": self.speaker_absent_ms,
         }.items():
             if value <= 0:

src/owner_voice_pet/runtime.py

@@ -357,6 +357,7 @@ def build_live_runtime(config: AppConfig, reporter: RuntimeReporter | None = Non
         recorder_kwargs.update(
             {
                 "speaker_profile_ms": config.speaker_profile_ms,
+                "speaker_profile_min_ms": config.speaker_profile_min_ms,
                 "speaker_absent_ms": config.speaker_absent_ms,
                 "similarity_threshold": config.speaker_similarity_threshold,
                 "min_rms": config.speaker_min_rms,

src/owner_voice_pet/transport.py

@@ -223,9 +223,15 @@ class SoundDeviceAudioTransport:
             return []
         timeout_s = max(0, timeout_ms) / 1000
         try:
-            return [self._queue.get(timeout=timeout_s)]
+            frames = [self._queue.get(timeout=timeout_s)]
         except queue.Empty:
             return []
+        while True:
+            try:
+                frames.append(self._queue.get_nowait())
+            except queue.Empty:
+                break
+        return frames
 
     def play_pcm(self, segment: AudioSegment, interrupt: bool = False) -> PlaybackResult:
         if self._sd is None:

src/owner_voice_pet/vad.py

@@ -287,6 +287,7 @@ class VadRecorder:
 @dataclass(slots=True)
 class PrimarySpeakerVadRecorder(VadRecorder):
     speaker_profile_ms: int = 600
+    speaker_profile_min_ms: int = 120
     speaker_absent_ms: int = 300
     similarity_threshold: float = 0.70
     min_rms: float = 0.012
@@ -336,7 +337,7 @@ class PrimarySpeakerVadRecorder(VadRecorder):
                 self.primary_absent_ms = 0
             else:
                 self.primary_absent_ms += frame_ms
-            if self.primary_absent_ms >= self.speaker_absent_ms and duration >= self.min_duration_ms:
+            if self.primary_absent_ms >= self.speaker_absent_ms:
                 return self._build_segment("primary_speaker_absent")
         if result.silence_ms >= self.end_silence_ms and duration >= self.min_duration_ms:
             return self._build_segment("silence")
@@ -365,7 +366,7 @@ class PrimarySpeakerVadRecorder(VadRecorder):
             self.profile.vector = tuple(averaged)
 
     def _profile_ready(self) -> bool:
-        minimum_ms = min(self.speaker_profile_ms, max(120, self.min_duration_ms))
+        minimum_ms = min(self.speaker_profile_ms, self.speaker_profile_min_ms)
         return self.profile.speech_ms >= minimum_ms and (
             self.profile.speaker_id is not None or self.profile.vector is not None
         )