[Wake/VAD/STT 与 Live runtime]：完成真实重复语音运行，包含云端ASR/TTS开关、run-live和临时上下文测试

tests/test_wake_vad_stt.py

@@ -1,10 +1,12 @@
 from __future__ import annotations
 
+import json
 import tempfile
 import unittest
 
 from owner_voice_pet.models import AudioFrame, AudioSegment, ErrorCode, ProviderError
-from owner_voice_pet.stt import MetadataSttProvider, SherpaOnnxSttProvider, is_valid_transcript_text
+from owner_voice_pet.config import AppConfig
+from owner_voice_pet.stt import CloudAsrSttProvider, MetadataSttProvider, SherpaOnnxSttProvider, is_valid_transcript_text
 from owner_voice_pet.vad import EnergyVadProvider, VadRecorder
 from owner_voice_pet.wakeword import KeywordWakeWordProvider, MissingWakeWordModelProvider
 
@@ -102,6 +104,34 @@ class WakeVadSttTests(unittest.TestCase):
                 provider.load()
         self.assertEqual(raised.exception.code, ErrorCode.STT_MODEL_MISSING)
 
+    def test_cloud_asr_posts_audio_transcription_request(self) -> None:
+        class FakeResponse:
+            def __enter__(self):
+                return self
+
+            def __exit__(self, *args) -> None:
+                return None
+
+            def read(self) -> bytes:
+                return json.dumps({"text": "你好小杰", "language": "zh"}, ensure_ascii=False).encode()
+
+        requests = []
+
+        def fake_urlopen(request, timeout):
+            requests.append(request)
+            return FakeResponse()
+
+        provider = CloudAsrSttProvider(
+            AppConfig(llm_api_key="secret", asr_model="mimo-v2.5-asr"),
+            urlopen=fake_urlopen,
+        )
+        provider.load()
+        transcript = provider.transcribe(AudioSegment(b"\x00\x00\x01\x00", 16000, 1, 0, 100))
+
+        self.assertEqual(transcript.text, "你好小杰")
+        self.assertIn("/v1/audio/transcriptions", requests[0].full_url)
+        self.assertIn(b'mimo-v2.5-asr', requests[0].data)
+
 
 if __name__ == "__main__":
     unittest.main()