[依赖、模型和配置]：完成本地语音模型准备，包含.env配置、模型下载脚本和model-check

src/owner_voice_pet/cli.py

@@ -12,6 +12,7 @@ from .conversation import ConversationContext
 from .llm import MockLlmProvider, OpenAICompatibleLlmProvider
 from .models import AudioFrame, ProviderError
 from .pipeline import VoicePipeline
+from .speech_models import check_speech_models, model_status_errors
 from .stt import MetadataSttProvider
 from .transport import MemoryAudioTransport
 from .tts import SineTtsProvider
@@ -27,6 +28,8 @@ def main(argv: list[str] | None = None) -> int:
     subparsers.add_parser("acceptance", help="Run deterministic end-to-end pipeline acceptance")
     subparsers.add_parser("validate-assets", help="Validate project pet assets")
     subparsers.add_parser("security-check", help="Scan tracked files for leaked API keys")
+    model_check = subparsers.add_parser("model-check", help="Validate local speech model files")
+    model_check.add_argument("--models-dir", default=None, help="Speech models directory. Defaults to .env or models")
     smoke = subparsers.add_parser("llm-smoke", help="Call configured OpenAI/NewAPI endpoint")
     smoke.add_argument("--message", default="用一句中文回复：小杰在线。")
     smoke.add_argument("--no-stream", action="store_true")
@@ -46,6 +49,7 @@ def main(argv: list[str] | None = None) -> int:
                     "llm_stream": config.llm_stream,
                     "llm_api_key_present": bool(config.llm_api_key),
                     "asset_dir": str(config.asset_dir),
+                    "speech_models_dir": str(config.speech_models_dir),
                 },
                 ensure_ascii=False,
                 sort_keys=True,
@@ -63,6 +67,16 @@ def main(argv: list[str] | None = None) -> int:
         print(json.dumps({"secret_leaks": leaks, "valid": not leaks}, ensure_ascii=False, sort_keys=True))
         return 1 if leaks else 0
 
+    if args.command == "model-check":
+        config = AppConfig.from_dotenv(args.env_file)
+        models_dir = Path(args.models_dir) if args.models_dir else config.speech_models_dir
+        status = check_speech_models(models_dir, require_sherpa=True)
+        errors = model_status_errors(status)
+        data = status.to_json()
+        data["errors"] = [str(error) for error in errors]
+        print(json.dumps(data, ensure_ascii=False, sort_keys=True))
+        return 1 if errors else 0
+
     if args.command == "acceptance":
         result = run_acceptance()
         print(json.dumps(result, ensure_ascii=False, sort_keys=True))
@@ -84,6 +98,7 @@ def main(argv: list[str] | None = None) -> int:
                 audio_output_device=config.audio_output_device,
                 asset_dir=config.asset_dir,
                 log_dir=config.log_dir,
+                speech_models_dir=config.speech_models_dir,
                 context_max_messages=config.context_max_messages,
                 context_max_chars=config.context_max_chars,
             )