[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

src/owner_voice_pet/config.py

@@ -11,7 +11,7 @@ class AppConfig:
     wake_word: str = "小杰小杰"
     sample_rate: int = 16000
     channels: int = 1
-    llm_base_url: str = "https://newapi.mkbk.shop"
+    llm_base_url: str = "https://token-plan-cn.xiaomimimo.com/v1"
     llm_api_key: str | None = None
     llm_model: str = "gpt-5.4-mini"
     llm_api_style: str = "chat_completions"
@@ -20,6 +20,10 @@ class AppConfig:
     audio_output_device: str | None = None
     asset_dir: Path = Path("assets/pet")
     log_dir: Path = Path("logs")
+    speech_provider: str = "cloud"
+    asr_model: str = "mimo-v2.5-asr"
+    tts_model: str = "mimo-v2.5-tts"
+    tts_voice: str = "alloy"
     speech_models_dir: Path = Path("models")
     context_max_messages: int = 12
     context_max_chars: int = 12000
@@ -36,7 +40,7 @@ class AppConfig:
             wake_word=get("WAKE_WORD", "小杰小杰") or "小杰小杰",
             sample_rate=int(get("SAMPLE_RATE", "16000") or "16000"),
             channels=int(get("CHANNELS", "1") or "1"),
-            llm_base_url=(get("LLM_BASE_URL", "https://newapi.mkbk.shop") or "").rstrip("/"),
+            llm_base_url=(get("LLM_BASE_URL", "https://token-plan-cn.xiaomimimo.com/v1") or "").rstrip("/"),
             llm_api_key=get("LLM_API_KEY"),
             llm_model=get("LLM_MODEL", "gpt-5.4-mini") or "gpt-5.4-mini",
             llm_api_style=get("LLM_API_STYLE", "chat_completions") or "chat_completions",
@@ -45,6 +49,10 @@ class AppConfig:
             audio_output_device=get("AUDIO_OUTPUT_DEVICE"),
             asset_dir=Path(get("ASSET_DIR", "assets/pet") or "assets/pet"),
             log_dir=Path(get("LOG_DIR", "logs") or "logs"),
+            speech_provider=(get("SPEECH_PROVIDER", "cloud") or "cloud").lower(),
+            asr_model=get("ASR_MODEL", "mimo-v2.5-asr") or "mimo-v2.5-asr",
+            tts_model=get("TTS_MODEL", "mimo-v2.5-tts") or "mimo-v2.5-tts",
+            tts_voice=get("TTS_VOICE", "alloy") or "alloy",
             speech_models_dir=Path(get("SPEECH_MODELS_DIR", "models") or "models"),
             context_max_messages=int(get("CONTEXT_MAX_MESSAGES", "12") or "12"),
             context_max_chars=int(get("CONTEXT_MAX_CHARS", "12000") or "12000"),
@@ -96,6 +104,16 @@ class AppConfig:
                     "startup",
                 )
             )
+        if self.speech_provider not in {"cloud", "local"}:
+            errors.append(
+                ProviderError(
+                    ErrorCode.CONFIG_MISSING_VALUE,
+                    "OWNER_SPEECH_PROVIDER must be cloud or local",
+                    False,
+                    "config",
+                    "startup",
+                )
+            )
         if not self.llm_base_url.startswith(("http://", "https://")):
             errors.append(
                 ProviderError(
@@ -108,6 +126,13 @@ class AppConfig:
             )
         return errors
 
+    def api_url(self, path: str) -> str:
+        normalized = path if path.startswith("/") else f"/{path}"
+        base = self.llm_base_url.rstrip("/")
+        if base.endswith("/v1") and normalized.startswith("/v1/"):
+            return base + normalized[3:]
+        return base + normalized
+
 
 def parse_dotenv(path: Path) -> dict[str, str]:
     if not path.exists():