AIRegulation-DocAnalysis/backend/app/api/main.py

"""FastAPI application entrypoint."""

from contextlib import AsyncExitStack, asynccontextmanager

from fastapi import FastAPI, Request
from fastapi.encoders import jsonable_encoder
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse
from loguru import logger

from app.api.middleware.audit import AuditMiddleware
from app.api.models import ErrorResponse
from app.api.routes import api_router
from app.config.logging import setup_logging
from app.config.settings import settings
from app.mcp.server import build_mcp_asgi_app
from app.shared.bootstrap import cleanup_runtime_dependencies, preload_runtime_dependencies
from app.shared.errors import VectorStoreSchemaError
# Keep module behavior explicit so the backend flow stays easy to audit.


setup_logging(level="INFO" if not settings.debug else "DEBUG")

# Built once at module scope so both lifespan() and app.mount() below reference
# the same instance — mounting a second, separately-built instance would start
# a second, unrelated MCP session manager.
mcp_app = build_mcp_asgi_app()


@asynccontextmanager
async def lifespan(app: FastAPI):
    """Application lifecycle hooks."""
    # FastMCP-style servers own a session manager that only starts via its own
    # lifespan context. app.mount() does NOT propagate nested ASGI lifespans
    # automatically (confirmed Starlette/ASGI limitation) — without this,
    # every search_regulations call would fail because the MCP session
    # manager was never started.
    async with AsyncExitStack() as stack:
        await stack.enter_async_context(mcp_app.router.lifespan_context(mcp_app))

        logger.info(f"启动 {settings.app_name} v{settings.app_version}")
        logger.info(f"调试模式: {settings.debug}")
        logger.info("预加载LLM客户端...")
        preload_runtime_dependencies()

        yield

        logger.info("应用关闭，执行清理...")
        cleanup_runtime_dependencies()


app = FastAPI(
    title=settings.app_name,
    description=(
        "AI+合规智能中枢 - 法律法规文档解析入库功能\n\n"
        "支持PDF/DOCX文档解析、智能分块、向量嵌入、Milvus存储"
    ),
    version=settings.app_version,
    lifespan=lifespan,
    docs_url="/docs",
    redoc_url="/redoc",
)

# Tighten CORS — only allow configured origins.
# Set CORS_ALLOW_ORIGINS in .env to the real frontend URL in production.
_ORIGINS = [o.strip() for o in settings.cors_allow_origins.split(",") if o.strip()]
if not _ORIGINS:
    _ORIGINS = ["http://localhost:5173"]

app.add_middleware(
    CORSMiddleware,
    allow_origins=_ORIGINS,
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Audit middleware logs every authenticated API call for compliance traceability.
app.add_middleware(AuditMiddleware)

app.include_router(api_router, prefix="/api/v1")
app.mount("/mcp", mcp_app)


@app.exception_handler(VectorStoreSchemaError)
async def vector_store_schema_exception_handler(request: Request, exc: VectorStoreSchemaError):
    """Return a stable JSON response for vector store schema/runtime errors."""
    logger.error(f"向量库 schema 异常: {exc}")
    return JSONResponse(
        status_code=500,
        content=jsonable_encoder(
            ErrorResponse(
                error="VectorStoreSchemaError",
                message=str(exc),
            )
        ),
    )


@app.exception_handler(Exception)
async def global_exception_handler(request: Request, exc: Exception):
    """Global exception handler."""
    logger.error(f"未处理的异常: {exc}")
    return JSONResponse(
        status_code=500,
        content=jsonable_encoder(
            ErrorResponse(
                error="InternalServerError",
                message=str(exc),
            )
        ),
    )


@app.get("/health", tags=["health"])
async def health_check():
    """Health check endpoint."""
    return {
        "status": "healthy",
        "app": settings.app_name,
        "version": settings.app_version,
    }


@app.get("/", tags=["root"])
async def root():
    """Root endpoint."""
    return {
        "message": f"Welcome to {settings.app_name}",
        "version": settings.app_version,
        "docs": "/docs",
        "health": "/health",
    }


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(
        "app.api.main:app",
        host=settings.api_host,
        port=settings.api_port,
        reload=settings.debug,
        log_level="info",
    )