[持续对话判定]：完成恢复待机延迟修复，包含本地规则收敛和分类器跳过回归测试

tests/test_continuation.py

@@ -58,6 +58,24 @@ class ContinuationDecisionTests(unittest.TestCase):
         self.assertEqual(decision.action, "standby")
         self.assertEqual(len(llm.calls), 1)
 
+    def test_hybrid_generic_completed_reply_does_not_call_llm_classifier(self) -> None:
+        llm = FakeClassifierLlm('{"action":"continue","confidence":0.99,"reason":"不应调用"}')
+        provider = HybridContinuationDecisionProvider(
+            RuleContinuationDecisionProvider(),
+            LlmContinuationDecisionProvider(llm, threshold=0.65),
+            threshold=0.65,
+        )
+
+        decision = provider.decide(
+            user_text="没有呢",
+            assistant_text="明白了，我先保持待机。有需要再叫我就行。",
+            history=[],
+        )
+
+        self.assertEqual(decision.action, "standby")
+        self.assertEqual(decision.provider, "rule")
+        self.assertEqual(llm.calls, [])
+
     def test_hybrid_high_confidence_llm_can_continue(self) -> None:
         llm = FakeClassifierLlm('{"action":"continue","confidence":0.91,"reason":"等待用户选择"}')
         provider = HybridContinuationDecisionProvider(

tests/test_live_runtime.py

@@ -594,6 +594,38 @@ class LiveRuntimeTests(unittest.TestCase):
         self.assertEqual(event_types[-1], STANDBY_RESUMED)
         self.assertEqual(len(llm.calls), 1)
 
+    def test_completed_reply_returns_to_standby_without_cloud_classifier_delay(self) -> None:
+        frames = [wake_frame(0, 0)]
+        frames.extend(segment_frames(1, 20, partials=["没有呢", "没有呢"]))
+        transport = MemoryAudioTransport(frames, flush_clears_input=False)
+        llm = QueueLlmProvider([["明白了，我先保持待机。有需要再叫我就行。"]])
+        runtime = VoiceAssistantPipeline(
+            config=AppConfig(
+                llm_api_key="secret",
+                speech_provider="cloud",
+                wake_ack_text="",
+                followup_listen_timeout_ms=3000,
+            ),
+            transport=transport,
+            wakeword=KeywordWakeWordProvider(),
+            vad_recorder=VadRecorder(EnergyVadProvider(), min_duration_ms=40, end_silence_ms=40),
+            stt=QueueSttProvider(["没有呢"]),
+            realtime_stt=MetadataSttProvider(),
+            llm=llm,
+            tts=SineTtsProvider(),
+            context=ConversationContext(),
+            reporter=RecordingReporter(),
+            event_bus=PipelineEventBus(),
+        )
+
+        summary = runtime.run(max_turns=1)
+        event_types = [event.type for event in runtime.event_bus.events]
+
+        self.assertEqual(summary.completed_turns, 1)
+        self.assertNotIn(FOLLOWUP_LISTENING, event_types)
+        self.assertEqual(event_types[-1], STANDBY_RESUMED)
+        self.assertEqual(len(llm.calls), 1)
+
     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"]))