[文档、验收与归档]：完成真实运行说明和OpenSpec归档，包含README、最终门禁和主规范更新

tests/test_models_config.py

@@ -72,7 +72,7 @@ class ModelsConfigTests(unittest.TestCase):
             self.assertEqual(config.speech_provider, "cloud")
             self.assertEqual(config.asr_model, "mimo-v2.5-asr")
             self.assertEqual(config.tts_model, "mimo-v2.5-tts")
-            self.assertEqual(config.tts_voice, "alloy")
+            self.assertEqual(config.tts_voice, "mimo_default")
             self.assertEqual(str(config.speech_models_dir), "models")
             self.assertTrue(config.llm_stream)
             self.assertEqual(config.validate_basic(), [])

tests/test_pipeline_llm_tts.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import io
+import base64
 import json
 import unittest
 
@@ -75,7 +76,17 @@ class PipelineLlmTtsTests(unittest.TestCase):
                 return None
 
             def read(self) -> bytes:
-                return b"fake-mp3"
+                return json.dumps(
+                    {
+                        "choices": [
+                            {
+                                "message": {
+                                    "audio": {"data": base64.b64encode(b"fake-wav").decode("ascii")}
+                                }
+                            }
+                        ]
+                    }
+                ).encode()
 
         requests = []
 
@@ -90,11 +101,14 @@ class PipelineLlmTtsTests(unittest.TestCase):
         provider.load()
         segment = provider.synthesize("你好")
 
-        self.assertEqual(segment.metadata["format"], "mp3")
-        self.assertEqual(segment.pcm, b"fake-mp3")
+        self.assertEqual(segment.metadata["format"], "wav")
+        self.assertEqual(segment.pcm, b"fake-wav")
         body = json.loads(requests[0].data.decode())
         self.assertEqual(body["model"], "mimo-v2.5-tts")
-        self.assertIn("/v1/audio/speech", requests[0].full_url)
+        self.assertEqual(body["messages"][0]["role"], "assistant")
+        self.assertEqual(body["messages"][0]["content"], "你好")
+        self.assertEqual(body["audio"]["format"], "wav")
+        self.assertIn("/v1/chat/completions", requests[0].full_url)
 
     def test_pipeline_runs_from_wake_to_playback(self) -> None:
         frames = [

tests/test_wake_vad_stt.py

@@ -113,7 +113,10 @@ class WakeVadSttTests(unittest.TestCase):
                 return None
 
             def read(self) -> bytes:
-                return json.dumps({"text": "你好小杰", "language": "zh"}, ensure_ascii=False).encode()
+                return json.dumps(
+                    {"choices": [{"message": {"content": "你好小杰"}}]},
+                    ensure_ascii=False,
+                ).encode()
 
         requests = []
 
@@ -129,8 +132,12 @@ class WakeVadSttTests(unittest.TestCase):
         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)
+        self.assertIn("/v1/chat/completions", requests[0].full_url)
+        body = json.loads(requests[0].data.decode())
+        self.assertEqual(body["model"], "mimo-v2.5-asr")
+        content = body["messages"][0]["content"][0]
+        self.assertEqual(content["type"], "input_audio")
+        self.assertTrue(content["input_audio"]["data"].startswith("data:audio/wav;base64,"))
 
 
 if __name__ == "__main__":