refactor: streamline data serialization in tool implementations

- Replaced model_dump and to_dict methods with direct calls to dict for improved consistency and performance in JSON serialization across multiple tools.
- Updated ConversationMemoryManager, GetRecommendationsTool, QueryDownloadsTool, and QueryMediaLibraryTool to enhance data handling.

app/agent/tools/impl/query_media_library.py

@@ -26,7 +26,7 @@ class QueryMediaLibraryTool(MoviePilotTool):
                     continue
                 filtered_medias.append(media)
             if filtered_medias:
-                return json.dumps([m.to_dict() if hasattr(m, 'to_dict') else m.dict() if hasattr(m, 'dict') else m.model_dump() if hasattr(m, 'model_dump') else m for m in filtered_medias], ensure_ascii=False, indent=2)
+                return json.dumps([m.to_dict() for m in filtered_medias])
             return "媒体库中未找到相关媒体。"
         except Exception as e:
             logger.error(f"查询媒体库失败: {e}", exc_info=True)