[异步播报打断]：完成播放中麦克风监听和音色隔离，包含后台监听、助手回放抑制和用户音色打断测试

tests/test_live_runtime.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import time
 import unittest
 
 from owner_voice_pet.config import AppConfig
@@ -238,6 +239,7 @@ class PlaybackInjectedTransport(MemoryAudioTransport):
         if self.play_count == self.inject_after_play_count:
             for frame in self.injected_frames:
                 self.inject(frame)
+        time.sleep(0.002)
         return result
 
     def health(self) -> TransportHealth:
@@ -649,15 +651,41 @@ class LiveRuntimeTests(unittest.TestCase):
 
     def test_barge_in_interrupts_playback_and_keeps_only_spoken_context(self) -> None:
         first_question_frames = [wake_frame(0, 0)]
-        first_question_frames.extend(segment_frames(1, 20, partials=["第一问", "第一问"]))
+        first_question_frames.extend(
+            [
+                AudioFrame(
+                    frame.pcm,
+                    frame.sample_rate,
+                    frame.channels,
+                    frame.timestamp_ms,
+                    frame.frame_id,
+                    {**dict(frame.metadata), "speaker_id": "owner"},
+                )
+                for frame in segment_frames(1, 20, partials=["第一问", "第一问"])
+            ]
+        )
         barge_frames = [
-            AudioFrame(b"\xff\x7f", 16000, 1, 600, 20, {"duration_ms": 20, "speech": True, "partial_transcript": "等一下"}),
-            AudioFrame(b"\xff\x7f", 16000, 1, 620, 21, {"duration_ms": 20, "speech": True, "partial_transcript": "等一下"}),
+            AudioFrame(
+                b"\xff\x7f",
+                16000,
+                1,
+                600,
+                20,
+                {"duration_ms": 20, "speech": True, "partial_transcript": "等一下", "speaker_id": "owner"},
+            ),
+            AudioFrame(
+                b"\xff\x7f",
+                16000,
+                1,
+                620,
+                21,
+                {"duration_ms": 20, "speech": True, "partial_transcript": "等一下", "speaker_id": "owner"},
+            ),
             *silence_frames(22, 640, 3),
         ]
         transport = PlaybackInjectedTransport(
             first_question_frames,
-            inject_after_play_count=8,
+            inject_after_play_count=18,
             injected_frames=barge_frames,
         )
         stt = QueueSttProvider(["第一问", "打断问题"])
@@ -677,8 +705,10 @@ class LiveRuntimeTests(unittest.TestCase):
                 speech_provider="cloud",
                 wake_ack_text="",
                 barge_in_enabled=True,
-                barge_in_echo_guard_ms=500,
+                barge_in_echo_guard_ms=0,
                 barge_in_min_speech_ms=40,
+                barge_in_listen_interval_ms=1,
+                barge_in_chunk_ms=20,
                 followup_listen_timeout_ms=3000,
             ),
             transport=transport,