[真实链路自测]：完成完整流程自测和ACK缓冲修正，包含真实Provider验收、播放回声清理和回归测试

src/owner_voice_pet/assistant_pipeline.py

@@ -227,7 +227,6 @@ class TurnController:
     def _acknowledge_wake(self, turn_id: int) -> ProviderError | None:
         text = self.config.wake_ack_text.strip()
         if not text:
-            self._drain_input_after_playback()
             return None
         try:
             self._event(ACK_STARTED, PipelineState.SPEAKING, f"应答中：{text}", turn_id=turn_id)
@@ -278,9 +277,9 @@ class TurnController:
         self._drain_input_after_playback()
 
     def _drain_input_after_playback(self) -> None:
+        self.transport.flush_input()
         if self.config.post_playback_drain_ms <= 0:
             return
-        self.transport.flush_input()
         remaining_ms = self.config.post_playback_drain_ms
         while remaining_ms > 0:
             timeout_ms = min(50, remaining_ms)

src/owner_voice_pet/runtime.py

@@ -240,7 +240,6 @@ class LiveVoiceRuntime:
     def _acknowledge_wake(self, turn_id: int) -> ProviderError | None:
         text = self.config.wake_ack_text.strip()
         if not text:
-            self._drain_input_after_playback()
             return None
         try:
             self._event(ACK_STARTED, PipelineState.SPEAKING, f"应答中：{text}", turn_id=turn_id)
@@ -254,9 +253,9 @@ class LiveVoiceRuntime:
             return exc
 
     def _drain_input_after_playback(self) -> None:
+        self.transport.flush_input()
         if self.config.post_playback_drain_ms <= 0:
             return
-        self.transport.flush_input()
         remaining_ms = self.config.post_playback_drain_ms
         while remaining_ms > 0:
             timeout_ms = min(50, remaining_ms)

src/owner_voice_pet/simulation.py

@@ -55,7 +55,7 @@ class SimulationReporter:
 
 class BoundedMemoryAudioTransport(MemoryAudioTransport):
     def __init__(self, frames: list[AudioFrame], *, max_empty_reads: int = 5) -> None:
-        super().__init__(frames)
+        super().__init__(frames, flush_clears_input=False)
         self.max_empty_reads = max_empty_reads
         self.empty_reads = 0
 

src/owner_voice_pet/transport.py

@@ -58,12 +58,15 @@ class MemoryAudioTransport:
         frames: list[AudioFrame] | None = None,
         input_available: bool = True,
         output_available: bool = True,
+        flush_clears_input: bool = True,
     ) -> None:
         self._frames: deque[AudioFrame] = deque(frames or [])
         self.played_segments: list[AudioSegment] = []
+        self.flush_count = 0
         self.started = False
         self._input_available = input_available
         self._output_available = output_available
+        self._flush_clears_input = flush_clears_input
 
     def start_input(
         self, device_id: str | None = None, sample_rate: int = 16000, channels: int = 1
@@ -104,6 +107,9 @@ class MemoryAudioTransport:
         return PlaybackResult(True, segment.duration_ms)
 
     def flush_input(self) -> int:
+        self.flush_count += 1
+        if not self._flush_clears_input:
+            return 0
         count = len(self._frames)
         self._frames.clear()
         return count