追加了数据保存的方式

utils/output_handler.py

@@ -91,9 +91,40 @@ class FileSystemOutputHandler(OutputHandler):
         """Saves content JSON and prompt for a specific variant."""
         variant_dir = self._get_variant_dir(run_id, topic_index, variant_index)
         
+        # 检查内容是否经过审核
+        if content_data.get("judged", False):
+            # 保存原始内容到raw_data.json
+            raw_content = {
+                "title": content_data.get("original_title", content_data.get("title", "")),
+                "content": content_data.get("original_content", content_data.get("content", "")),
+                "tag": content_data.get("tag", ""),  # 确保保留tag字段
+                "error": content_data.get("error", False)
+            }
+            
+            # 如果内容里没有original_字段，则认为当前内容就是原始内容
+            if "original_title" not in content_data and "original_content" not in content_data:
+                # 先深拷贝当前内容数据以避免修改原数据
+                import copy
+                raw_content = copy.deepcopy(content_data)
+                # 移除审核相关字段
+                raw_content.pop("judged", None)
+                raw_content.pop("judge_analysis", None)
+            
+            raw_data_path = os.path.join(variant_dir, "raw_data.json")
+            try:
+                with open(raw_data_path, "w", encoding="utf-8") as f:
+                    json.dump(raw_content, f, ensure_ascii=False, indent=4)
+                logging.info(f"原始内容保存到: {raw_data_path}")
+            except Exception as e:
+                logging.exception(f"保存原始内容到 {raw_data_path} 失败: {e}")
+        
         # Save content JSON
         content_path = os.path.join(variant_dir, "article.json")
         try:
+            # 确保tag字段存在
+            if "tag" not in content_data and content_data.get("tags"):
+                content_data["tag"] = content_data["tags"]
+                
             with open(content_path, "w", encoding="utf-8") as f:
                 json.dump(content_data, f, ensure_ascii=False, indent=4)
             logging.info(f"Content JSON saved to: {content_path}")

utils/prompt_manager.py

@@ -23,11 +23,13 @@ class PromptManager:
                  prompts_config: list = None,  # 新的配置方式 
                  resource_dir_config: list = None,
                  topic_gen_num: int = 1, # Default values if needed
-                 topic_gen_date: str = "" 
+                 topic_gen_date: str = "",
+                 content_judger_system_prompt_path: str = None # 添加内容审核系统提示词路径参数
                  ):
         self.topic_system_prompt_path = topic_system_prompt_path
         self.topic_user_prompt_path = topic_user_prompt_path
         self.content_system_prompt_path = content_system_prompt_path
+        self.content_judger_system_prompt_path = content_judger_system_prompt_path # 添加成员变量
         self.prompts_dir = prompts_dir  # 保留兼容旧配置
         self.prompts_config = prompts_config or []  # 新的配置方式
         self.resource_dir_config = resource_dir_config or []
@@ -67,6 +69,13 @@ class PromptManager:
                 self._system_prompt_cache["content"] = content
                 logging.info(f"预加载内容系统提示词: {self.content_system_prompt_path}")
         
+        # 预加载内容审核系统提示词
+        if self.content_judger_system_prompt_path and os.path.exists(self.content_judger_system_prompt_path):
+            content = ResourceLoader.load_file_content(self.content_judger_system_prompt_path)
+            if content:
+                self._system_prompt_cache["judger_system_prompt"] = content
+                logging.info(f"预加载内容审核系统提示词: {self.content_judger_system_prompt_path}")
+        
         # 预加载日期线文件
         if self.topic_user_prompt_path:
             user_prompt_dir = os.path.dirname(self.topic_user_prompt_path)

utils/tweet_generator.py

@@ -512,6 +512,10 @@ content: {content_json.get('content', '')}
                             if "title" in judged_result and "content" in judged_result:
                                 # 使用审核后的内容替换原内容
                                 logging.info(f"  内容审核成功，使用审核后的内容替换原内容")
+                                # 保存原始标题和内容
+                                content_json["original_title"] = content_json.get("title", "")
+                                content_json["original_content"] = content_json.get("content", "")
+                                # 更新为审核后的内容
                                 content_json["title"] = judged_result["title"]
                                 content_json["content"] = judged_result["content"]
                                 # 添加审核标记