feat: refactor summarizer and PDF extraction pipeline

- Split summarizer into summary_generator and summary_persister modules
- Refactor pdf_image_extractor to two-phase pipeline with PicoDet layout detection
- Add layout_detector service for PicoDet-S_layout_3cls integration
- Add exceptions module with ConflictError and NotFoundError
- Improve admin dashboard with better statistics and task management
- Add design review document with system optimization suggestions
- Add new tests for crawler, pdf_downloader, pipeline, and summary_utils
- Update dependencies and configuration
- Clean up dead code and improve error handling

app/main.py

@@ -5,10 +5,12 @@ import os
 from contextlib import asynccontextmanager
 
 from fastapi import FastAPI
+from fastapi.responses import JSONResponse
 from fastapi.staticfiles import StaticFiles
 from starlette.middleware.sessions import SessionMiddleware
 
 from app.config import settings
+from app.exceptions import AppError, ConflictError, ExternalAPIError, NotFoundError, PdfProcessError, ValidationError
 from app.database import engine, init_db
 from app.routes.admin import router as admin_router
 from app.routes.compare import router as compare_router
@@ -38,8 +40,10 @@ async def lifespan(app: FastAPI):
 
     # ── shutdown ──
     from app.services.scheduler import stop_scheduler
+    from app.services.pdf_downloader import close_http_session
 
     stop_scheduler()
+    close_http_session()
 
 
 def create_app() -> FastAPI:
@@ -60,15 +64,38 @@ def create_app() -> FastAPI:
     # Session 中间件
     app.add_middleware(SessionMiddleware, secret_key=settings.SECRET_KEY)
 
+    # ── 统一业务异常处理 ──
+    @app.exception_handler(NotFoundError)
+    async def _not_found_handler(request, exc):
+        return JSONResponse(status_code=404, content={"error": exc.message})
+
+    @app.exception_handler(ValidationError)
+    async def _validation_handler(request, exc):
+        return JSONResponse(status_code=400, content={"error": exc.message})
+
+    @app.exception_handler(ExternalAPIError)
+    async def _external_api_handler(request, exc):
+        return JSONResponse(status_code=502, content={"error": exc.message})
+
+    @app.exception_handler(PdfProcessError)
+    async def _pdf_process_handler(request, exc):
+        return JSONResponse(status_code=500, content={"error": exc.message})
+
+    @app.exception_handler(ConflictError)
+    async def _conflict_handler(request, exc):
+        return JSONResponse(status_code=409, content={"error": exc.message})
+
+    @app.exception_handler(AppError)
+    async def _app_error_handler(request, exc):
+        return JSONResponse(status_code=500, content={"error": exc.message})
+
     # 安全警告
     if settings.SECRET_KEY == "change-me":
         logger.warning(
             "⚠️  SECRET_KEY is the default value 'change-me'. Please change it in .env!"
         )
     if not settings.ADMIN_PASSWORD:
-        logger.warning(
-            "⚠️  ADMIN_PASSWORD is empty. Please set it in .env!"
-        )
+        logger.warning("⚠️  ADMIN_PASSWORD is empty. Please set it in .env!")
 
     # 静态文件
     app.mount("/static", StaticFiles(directory="app/static"), name="static")