[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

src/owner_voice_pet/stt.py

@@ -1,12 +1,12 @@
 from __future__ import annotations
 
 import io
+import base64
 import json
 import re
 import socket
 import urllib.error
 import urllib.request
-import uuid
 import wave
 from collections.abc import Callable
 from pathlib import Path
@@ -84,19 +84,28 @@ class CloudAsrSttProvider:
                 "newapi-asr",
                 "stt",
             )
-        wav_bytes = _segment_to_wav_bytes(segment)
-        boundary = "owner-voice-pet-" + uuid.uuid4().hex
-        body = _multipart_form_data(
-            boundary,
-            fields={"model": self.config.asr_model, "response_format": "json"},
-            files={"file": ("utterance.wav", "audio/wav", wav_bytes)},
-        )
+        audio_data = base64.b64encode(_segment_to_wav_bytes(segment)).decode("ascii")
+        payload = {
+            "model": self.config.asr_model,
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "input_audio",
+                            "input_audio": {"data": f"data:audio/wav;base64,{audio_data}"},
+                        }
+                    ],
+                }
+            ],
+            "asr_options": {"language": "auto"},
+        }
         request = urllib.request.Request(
-            self.config.api_url("/v1/audio/transcriptions"),
-            data=body,
+            self.config.api_url("/v1/chat/completions"),
+            data=json.dumps(payload).encode("utf-8"),
             headers={
                 "Authorization": f"Bearer {self.config.llm_api_key}",
-                "Content-Type": f"multipart/form-data; boundary={boundary}",
+                "Content-Type": "application/json",
             },
             method="POST",
         )
@@ -119,7 +128,9 @@ class CloudAsrSttProvider:
                 "newapi-asr",
                 "stt",
             ) from exc
-        text = str(payload.get("text") or "").strip()
+        choices = payload.get("choices") or []
+        message = (choices[0].get("message") if choices else {}) or {}
+        text = str(message.get("content") or payload.get("text") or "").strip()
         if not is_valid_transcript_text(text):
             raise ProviderError(
                 ErrorCode.STT_EMPTY_TRANSCRIPT,
@@ -261,27 +272,3 @@ def _segment_to_wav_bytes(segment: AudioSegment) -> bytes:
         wav.setframerate(segment.sample_rate)
         wav.writeframes(segment.pcm)
     return buffer.getvalue()
-
-
-def _multipart_form_data(
-    boundary: str,
-    *,
-    fields: dict[str, str],
-    files: dict[str, tuple[str, str, bytes]],
-) -> bytes:
-    body = bytearray()
-    for name, value in fields.items():
-        body.extend(f"--{boundary}\r\n".encode())
-        body.extend(f'Content-Disposition: form-data; name="{name}"\r\n\r\n'.encode())
-        body.extend(value.encode("utf-8"))
-        body.extend(b"\r\n")
-    for name, (filename, content_type, data) in files.items():
-        body.extend(f"--{boundary}\r\n".encode())
-        body.extend(
-            f'Content-Disposition: form-data; name="{name}"; filename="{filename}"\r\n'.encode()
-        )
-        body.extend(f"Content-Type: {content_type}\r\n\r\n".encode())
-        body.extend(data)
-        body.extend(b"\r\n")
-    body.extend(f"--{boundary}--\r\n".encode())
-    return bytes(body)