v3接口restful风格，规范化接口；添加mcp服务器；新增log模块

backend/core/config.py

@@ -1,5 +1,9 @@
 from pydantic_settings import BaseSettings, SettingsConfigDict
+import logging
 
+# 获取当前模块的专用 Logger
+# __name__ 会自动识别为 "backend.services.crawler_service" 这样的路径
+logger = logging.getLogger(__name__)
 class Settings(BaseSettings):
     """
     系统配置类

backend/core/database.py

@@ -1,7 +1,11 @@
 from sqlalchemy import create_engine, MetaData, Table
 from pgvector.sqlalchemy import Vector
 from .config import settings
+import logging
 
+# 获取当前模块的专用 Logger
+# __name__ 会自动识别为 "backend.services.crawler_service" 这样的路径
+logger = logging.getLogger(__name__)
 class Database:
     """
     数据库单例类
@@ -30,9 +34,9 @@ class Database:
             self.tasks = Table('crawl_tasks', self.metadata, autoload_with=self.engine)
             self.queue = Table('crawl_queue', self.metadata, autoload_with=self.engine)
             self.chunks = Table('knowledge_chunks', self.metadata, autoload_with=self.engine)
-            print("[INFO] Database tables reflected successfully.")
+            logger.info("Database tables reflected successfully.")
         except Exception as e:
-            print(f"[ERROR] Failed to reflect tables: {e}")
+            logger.error(f"Failed to reflect tables: {e}")
 
 # 全局数据库实例
 db = Database()

backend/core/logger.py

@@ -0,0 +1,24 @@
+# backend/core/logger.py
+import logging
+import sys
+
+def setup_logging(level=logging.INFO):
+    """
+    全局日志配置
+    关键点：强制将日志输出到 sys.stderr，防止污染 sys.stdout 导致 MCP 协议崩溃。
+    """
+    # 定义日志格式：时间 - 模块名 - 级别 - 内容
+    log_format = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+    
+    # 配置根记录器
+    logging.basicConfig(
+        level=level,
+        format=log_format,
+        handlers=[
+            # 【绝对关键】使用 StreamHandler(sys.stderr)
+            # 这样日志会走标准错误通道，不会干扰 MCP 的标准输出通信
+            logging.StreamHandler(sys.stderr)
+        ],
+        # 强制重新配置，防止被第三方库覆盖
+        force=True
+    )