[播报文本净化]：完成TTS表情包过滤，包含emoji清理、上下文净化和回归测试

tests/test_pipeline_llm_tts.py

@@ -12,7 +12,7 @@ from owner_voice_pet.models import AudioFrame, ErrorCode, Message, PipelineState
 from owner_voice_pet.pipeline import VoicePipeline
 from owner_voice_pet.stt import MetadataSttProvider
 from owner_voice_pet.transport import MemoryAudioTransport
-from owner_voice_pet.tts import CloudTtsProvider, SentenceBuffer, SineTtsProvider
+from owner_voice_pet.tts import CloudTtsProvider, SentenceBuffer, SineTtsProvider, sanitize_tts_text
 from owner_voice_pet.vad import EnergyVadProvider, VadRecorder
 from owner_voice_pet.wakeword import KeywordWakeWordProvider
 
@@ -60,6 +60,12 @@ class PipelineLlmTtsTests(unittest.TestCase):
         self.assertEqual(buffer.feed("剩余").copy(), [])
         self.assertEqual(buffer.flush(), ["剩余"])
 
+    def test_sanitize_tts_text_removes_unspeakable_expression_tokens(self) -> None:
+        self.assertEqual(sanitize_tts_text("你好 😊"), "你好")
+        self.assertEqual(sanitize_tts_text("好的![开心](x.png)"), "好的")
+        self.assertEqual(sanitize_tts_text("没问题[捂脸]，我来帮你。"), "没问题，我来帮你。")
+        self.assertEqual(sanitize_tts_text("😂😂"), "")
+
     def test_sine_tts_generates_non_empty_audio(self) -> None:
         provider = SineTtsProvider()
         provider.load()
@@ -126,6 +132,22 @@ class PipelineLlmTtsTests(unittest.TestCase):
         self.assertEqual(len(transport.played_segments), 1)
         self.assertEqual(pipeline.context.messages()[-1].role, "assistant")
 
+    def test_pipeline_sanitizes_tts_text_and_assistant_context(self) -> None:
+        frames = [
+            frame(0, 0, {"wake_word": "小杰小杰", "wake_confidence": 0.95}),
+            frame(1, 20, {"speech": True, "transcript": "你好"}),
+            frame(2, 40, {"speech": True}),
+            frame(3, 60, {"speech": False}),
+            frame(4, 80, {"speech": False}),
+        ]
+        pipeline, transport = make_pipeline(frames, MockLlmProvider(["你好 😊。没问题[捂脸]，我来帮你。"]))
+        result = pipeline.run_once()
+
+        self.assertTrue(result.success)
+        self.assertEqual(result.assistant_text, "你好。没问题，我来帮你。")
+        self.assertEqual(transport.played_segments[0].metadata["text"], "你好。没问题，我来帮你。")
+        self.assertEqual(pipeline.context.messages()[-1].content, "你好。没问题，我来帮你。")
+
     def test_pipeline_skips_llm_on_empty_transcript(self) -> None:
         llm = MockLlmProvider(["不应调用"])
         frames = [