feat: Phase 1+2 — project setup and core infrastructure

- requirements.txt, config.yaml, .env, Dockerfile, docker-compose.yml
- app/core: config (YAML+env override), logging (JSON structured),
  exceptions (typed hierarchy), json_utils (Markdown fence stripping)
- app/clients: LLMClient ABC + ZhipuAIClient (run_in_executor),
  StorageClient ABC + RustFSClient (boto3 head_object for size check)
- app/main.py: FastAPI app with health endpoint and router registration
- app/core/dependencies.py: lru_cache singleton factories
- tests/conftest.py: mock_llm, mock_storage, test_app, client fixtures
- pytest.ini: asyncio_mode=auto
- 11 unit tests passing

app/core/exceptions.py

@@ -0,0 +1,50 @@
+from fastapi import Request
+from fastapi.responses import JSONResponse
+
+
+class AIServiceError(Exception):
+    status_code: int = 500
+    code: str = "INTERNAL_ERROR"
+
+    def __init__(self, message: str) -> None:
+        self.message = message
+        super().__init__(message)
+
+
+class UnsupportedFileTypeError(AIServiceError):
+    status_code = 400
+    code = "UNSUPPORTED_FILE_TYPE"
+
+
+class VideoTooLargeError(AIServiceError):
+    status_code = 400
+    code = "VIDEO_TOO_LARGE"
+
+
+class StorageError(AIServiceError):
+    status_code = 502
+    code = "STORAGE_ERROR"
+
+
+class LLMParseError(AIServiceError):
+    status_code = 502
+    code = "LLM_PARSE_ERROR"
+
+
+class LLMCallError(AIServiceError):
+    status_code = 503
+    code = "LLM_CALL_ERROR"
+
+
+async def ai_service_exception_handler(request: Request, exc: AIServiceError) -> JSONResponse:
+    return JSONResponse(
+        status_code=exc.status_code,
+        content={"code": exc.code, "message": exc.message},
+    )
+
+
+async def unhandled_exception_handler(request: Request, exc: Exception) -> JSONResponse:
+    return JSONResponse(
+        status_code=500,
+        content={"code": "INTERNAL_ERROR", "message": str(exc)},
+    )