ruff reformatted

src/plugins/chat_module/only_process/only_message_process.py

@@ -7,12 +7,13 @@ from datetime import datetime
 
 logger = get_module_logger("pfc_message_processor")
 
+
 class MessageProcessor:
     """消息处理器，负责处理接收到的消息并存储"""
-    
+
     def __init__(self):
         self.storage = MessageStorage()
-        
+
     def _check_ban_words(self, text: str, chat, userinfo) -> bool:
         """检查消息中是否包含过滤词"""
         for word in global_config.ban_words:
@@ -34,10 +35,10 @@ class MessageProcessor:
                 logger.info(f"[正则表达式过滤]消息匹配到{pattern}，filtered")
                 return True
         return False
-        
+
     async def process_message(self, message: MessageRecv) -> None:
         """处理消息并存储
-        
+
         Args:
             message: 消息对象
         """
@@ -55,12 +56,9 @@ class MessageProcessor:
 
         # 存储消息
         await self.storage.store_message(message, chat)
-        
+
         # 打印消息信息
         mes_name = chat.group_info.group_name if chat.group_info else "私聊"
         # 将时间戳转换为datetime对象
         current_time = datetime.fromtimestamp(message.message_info.time).strftime("%H:%M:%S")
-        logger.info(
-            f"[{current_time}][{mes_name}]"
-            f"{chat.user_info.user_nickname}: {message.processed_plain_text}"
-        )
+        logger.info(f"[{current_time}][{mes_name}]{chat.user_info.user_nickname}: {message.processed_plain_text}")

src/plugins/chat_module/reasoning_chat/reasoning_chat.py

@@ -27,6 +27,7 @@ chat_config = LogConfig(
 
 logger = get_module_logger("reasoning_chat", config=chat_config)
 
+
 class ReasoningChat:
     def __init__(self):
         self.storage = MessageStorage()
@@ -224,13 +225,13 @@ class ReasoningChat:
         do_reply = False
         if random() < reply_probability:
             do_reply = True
-            
+
             # 创建思考消息
             timer1 = time.time()
             thinking_id = await self._create_thinking_message(message, chat, userinfo, messageinfo)
             timer2 = time.time()
             timing_results["创建思考消息"] = timer2 - timer1
-            
+
             # 生成回复
             timer1 = time.time()
             response_set = await self.gpt.generate_response(message)

src/plugins/chat_module/reasoning_chat/reasoning_generator.py

@@ -40,7 +40,7 @@ class ResponseGenerator:
 
     async def generate_response(self, message: MessageThinking) -> Optional[Union[str, List[str]]]:
         """根据当前模型类型选择对应的生成函数"""
-        #从global_config中获取模型概率值并选择模型
+        # 从global_config中获取模型概率值并选择模型
         if random.random() < global_config.MODEL_R1_PROBABILITY:
             self.current_model_type = "深深地"
             current_model = self.model_reasoning
@@ -51,7 +51,6 @@ class ResponseGenerator:
         logger.info(
             f"{self.current_model_type}思考:{message.processed_plain_text[:30] + '...' if len(message.processed_plain_text) > 30 else message.processed_plain_text}"
         )  # noqa: E501
-        
 
         model_response = await self._generate_response_with_model(message, current_model)
 
@@ -189,4 +188,4 @@ class ResponseGenerator:
 
         # print(f"得到了处理后的llm返回{processed_response}")
 
-        return processed_response
+        return processed_response

src/plugins/chat_module/reasoning_chat/reasoning_prompt_builder.py

@@ -24,35 +24,32 @@ class PromptBuilder:
     async def _build_prompt(
         self, chat_stream, message_txt: str, sender_name: str = "某人", stream_id: Optional[int] = None
     ) -> tuple[str, str]:
-    
         # 开始构建prompt
         prompt_personality = "你"
-        #person
+        # person
         individuality = Individuality.get_instance()
-        
+
         personality_core = individuality.personality.personality_core
         prompt_personality += personality_core
-        
+
         personality_sides = individuality.personality.personality_sides
         random.shuffle(personality_sides)
         prompt_personality += f",{personality_sides[0]}"
-        
+
         identity_detail = individuality.identity.identity_detail
         random.shuffle(identity_detail)
         prompt_personality += f",{identity_detail[0]}"
-        
-        
-            
+
         # 关系
-        who_chat_in_group = [(chat_stream.user_info.platform, 
-                              chat_stream.user_info.user_id, 
-                              chat_stream.user_info.user_nickname)]
+        who_chat_in_group = [
+            (chat_stream.user_info.platform, chat_stream.user_info.user_id, chat_stream.user_info.user_nickname)
+        ]
         who_chat_in_group += get_recent_group_speaker(
             stream_id,
             (chat_stream.user_info.platform, chat_stream.user_info.user_id),
             limit=global_config.MAX_CONTEXT_SIZE,
         )
-        
+
         relation_prompt = ""
         for person in who_chat_in_group:
             relation_prompt += await relationship_manager.build_relationship_info(person)
@@ -67,7 +64,7 @@ class PromptBuilder:
         mood_prompt = mood_manager.get_prompt()
 
         # logger.info(f"心情prompt: {mood_prompt}")
-        
+
         # 调取记忆
         memory_prompt = ""
         related_memory = await HippocampusManager.get_instance().get_memory_from_text(
@@ -84,7 +81,7 @@ class PromptBuilder:
         # print(f"相关记忆：{related_memory_info}")
 
         # 日程构建
-        schedule_prompt = f'''你现在正在做的事情是：{bot_schedule.get_current_num_task(num = 1,time_info = False)}'''
+        schedule_prompt = f"""你现在正在做的事情是：{bot_schedule.get_current_num_task(num=1, time_info=False)}"""
 
         # 获取聊天上下文
         chat_in_group = True
@@ -143,7 +140,7 @@ class PromptBuilder:
 涉及政治敏感以及违法违规的内容请规避。"""
 
         logger.info("开始构建prompt")
-        
+
         prompt = f"""
 {relation_prompt_all}
 {memory_prompt}
@@ -165,7 +162,7 @@ class PromptBuilder:
         start_time = time.time()
         related_info = ""
         logger.debug(f"获取知识库内容，元消息：{message[:30]}...，消息长度: {len(message)}")
-        
+
         # 1. 先从LLM获取主题，类似于记忆系统的做法
         topics = []
         # try:
@@ -173,7 +170,7 @@ class PromptBuilder:
         #     hippocampus = HippocampusManager.get_instance()._hippocampus
         #     topic_num = min(5, max(1, int(len(message) * 0.1)))
         #     topics_response = await hippocampus.llm_topic_judge.generate_response(hippocampus.find_topic_llm(message, topic_num))
-            
+
         #     # 提取关键词
         #     topics = re.findall(r"<([^>]+)>", topics_response[0])
         #     if not topics:
@@ -184,7 +181,7 @@ class PromptBuilder:
         #             for topic in ",".join(topics).replace("，", ",").replace("、", ",").replace(" ", ",").split(",")
         #             if topic.strip()
         #         ]
-            
+
         #     logger.info(f"从LLM提取的主题: {', '.join(topics)}")
         # except Exception as e:
         #     logger.error(f"从LLM提取主题失败: {str(e)}")
@@ -192,7 +189,7 @@ class PromptBuilder:
         #     words = jieba.cut(message)
         #     topics = [word for word in words if len(word) > 1][:5]
         #     logger.info(f"使用jieba提取的主题: {', '.join(topics)}")
-        
+
         # 如果无法提取到主题，直接使用整个消息
         if not topics:
             logger.info("未能提取到任何主题，使用整个消息进行查询")
@@ -200,26 +197,26 @@ class PromptBuilder:
             if not embedding:
                 logger.error("获取消息嵌入向量失败")
                 return ""
-                
+
             related_info = self.get_info_from_db(embedding, limit=3, threshold=threshold)
             logger.info(f"知识库检索完成，总耗时: {time.time() - start_time:.3f}秒")
             return related_info
-        
+
         # 2. 对每个主题进行知识库查询
         logger.info(f"开始处理{len(topics)}个主题的知识库查询")
-        
+
         # 优化：批量获取嵌入向量，减少API调用
         embeddings = {}
         topics_batch = [topic for topic in topics if len(topic) > 0]
         if message:  # 确保消息非空
             topics_batch.append(message)
-        
+
         # 批量获取嵌入向量
         embed_start_time = time.time()
         for text in topics_batch:
             if not text or len(text.strip()) == 0:
                 continue
-                
+
             try:
                 embedding = await get_embedding(text, request_type="prompt_build")
                 if embedding:
@@ -228,17 +225,17 @@ class PromptBuilder:
                     logger.warning(f"获取'{text}'的嵌入向量失败")
             except Exception as e:
                 logger.error(f"获取'{text}'的嵌入向量时发生错误: {str(e)}")
-        
+
         logger.info(f"批量获取嵌入向量完成，耗时: {time.time() - embed_start_time:.3f}秒")
-        
+
         if not embeddings:
             logger.error("所有嵌入向量获取失败")
             return ""
-        
+
         # 3. 对每个主题进行知识库查询
         all_results = []
         query_start_time = time.time()
-        
+
         # 首先添加原始消息的查询结果
         if message in embeddings:
             original_results = self.get_info_from_db(embeddings[message], limit=3, threshold=threshold, return_raw=True)
@@ -247,12 +244,12 @@ class PromptBuilder:
                     result["topic"] = "原始消息"
                 all_results.extend(original_results)
                 logger.info(f"原始消息查询到{len(original_results)}条结果")
-        
+
         # 然后添加每个主题的查询结果
         for topic in topics:
             if not topic or topic not in embeddings:
                 continue
-                
+
             try:
                 topic_results = self.get_info_from_db(embeddings[topic], limit=3, threshold=threshold, return_raw=True)
                 if topic_results:
@@ -263,9 +260,9 @@ class PromptBuilder:
                     logger.info(f"主题'{topic}'查询到{len(topic_results)}条结果")
             except Exception as e:
                 logger.error(f"查询主题'{topic}'时发生错误: {str(e)}")
-        
+
         logger.info(f"知识库查询完成，耗时: {time.time() - query_start_time:.3f}秒，共获取{len(all_results)}条结果")
-        
+
         # 4. 去重和过滤
         process_start_time = time.time()
         unique_contents = set()
@@ -275,14 +272,16 @@ class PromptBuilder:
             if content not in unique_contents:
                 unique_contents.add(content)
                 filtered_results.append(result)
-        
+
         # 5. 按相似度排序
         filtered_results.sort(key=lambda x: x["similarity"], reverse=True)
-        
+
         # 6. 限制总数量（最多10条）
         filtered_results = filtered_results[:10]
-        logger.info(f"结果处理完成，耗时: {time.time() - process_start_time:.3f}秒，过滤后剩余{len(filtered_results)}条结果")
-        
+        logger.info(
+            f"结果处理完成，耗时: {time.time() - process_start_time:.3f}秒，过滤后剩余{len(filtered_results)}条结果"
+        )
+
         # 7. 格式化输出
         if filtered_results:
             format_start_time = time.time()
@@ -292,7 +291,7 @@ class PromptBuilder:
                 if topic not in grouped_results:
                     grouped_results[topic] = []
                 grouped_results[topic].append(result)
-            
+
             # 按主题组织输出
             for topic, results in grouped_results.items():
                 related_info += f"【主题: {topic}】\n"
@@ -303,13 +302,15 @@ class PromptBuilder:
                     # related_info += f"{i}. [{similarity:.2f}] {content}\n"
                     related_info += f"{content}\n"
                 related_info += "\n"
-            
+
             logger.info(f"格式化输出完成，耗时: {time.time() - format_start_time:.3f}秒")
-        
+
         logger.info(f"知识库检索总耗时: {time.time() - start_time:.3f}秒")
         return related_info
 
-    def get_info_from_db(self, query_embedding: list, limit: int = 1, threshold: float = 0.5, return_raw: bool = False) -> Union[str, list]:
+    def get_info_from_db(
+        self, query_embedding: list, limit: int = 1, threshold: float = 0.5, return_raw: bool = False
+    ) -> Union[str, list]:
         if not query_embedding:
             return "" if not return_raw else []
         # 使用余弦相似度计算

src/plugins/chat_module/think_flow_chat/think_flow_chat.py

@@ -28,6 +28,7 @@ chat_config = LogConfig(
 
 logger = get_module_logger("think_flow_chat", config=chat_config)
 
+
 class ThinkFlowChat:
     def __init__(self):
         self.storage = MessageStorage()
@@ -96,7 +97,7 @@ class ThinkFlowChat:
             )
             if not mark_head:
                 mark_head = True
-                
+
             # print(f"thinking_start_time:{bot_message.thinking_start_time}")
             message_set.add_message(bot_message)
         message_manager.add_message(message_set)
@@ -110,7 +111,7 @@ class ThinkFlowChat:
             if emoji_raw:
                 emoji_path, description = emoji_raw
                 emoji_cq = image_path_to_base64(emoji_path)
-                
+
                 # logger.info(emoji_cq)
 
                 thinking_time_point = round(message.message_info.time, 2)
@@ -130,7 +131,7 @@ class ThinkFlowChat:
                     is_head=False,
                     is_emoji=True,
                 )
-                
+
                 # logger.info("22222222222222")
                 message_manager.add_message(bot_message)
 
@@ -180,7 +181,7 @@ class ThinkFlowChat:
 
         await message.process()
         logger.debug(f"消息处理成功{message.processed_plain_text}")
-        
+
         # 过滤词/正则表达式过滤
         if self._check_ban_words(message.processed_plain_text, chat, userinfo) or self._check_ban_regex(
             message.raw_message, chat, userinfo
@@ -190,7 +191,7 @@ class ThinkFlowChat:
 
         await self.storage.store_message(message, chat)
         logger.debug(f"存储成功{message.processed_plain_text}")
-        
+
         # 记忆激活
         timer1 = time.time()
         interested_rate = await HippocampusManager.get_instance().get_activate_from_text(
@@ -214,15 +215,13 @@ class ThinkFlowChat:
         # 处理提及
         is_mentioned, reply_probability = is_mentioned_bot_in_message(message)
 
-
         # 计算回复意愿
         current_willing_old = willing_manager.get_willing(chat_stream=chat)
         # current_willing_new = (heartflow.get_subheartflow(chat.stream_id).current_state.willing - 5) / 4
-        # current_willing = (current_willing_old + current_willing_new) / 2 
+        # current_willing = (current_willing_old + current_willing_new) / 2
         # 有点bug
         current_willing = current_willing_old
 
-
         willing_manager.set_willing(chat.stream_id, current_willing)
 
         # 意愿激活
@@ -258,7 +257,7 @@ class ThinkFlowChat:
         if random() < reply_probability:
             try:
                 do_reply = True
-                
+
                 # 创建思考消息
                 try:
                     timer1 = time.time()
@@ -267,9 +266,9 @@ class ThinkFlowChat:
                     timing_results["创建思考消息"] = timer2 - timer1
                 except Exception as e:
                     logger.error(f"心流创建思考消息失败: {e}")
-                
+
                 try:
-                # 观察
+                    # 观察
                     timer1 = time.time()
                     await heartflow.get_subheartflow(chat.stream_id).do_observe()
                     timer2 = time.time()
@@ -280,12 +279,14 @@ class ThinkFlowChat:
                 # 思考前脑内状态
                 try:
                     timer1 = time.time()
-                    await heartflow.get_subheartflow(chat.stream_id).do_thinking_before_reply(message.processed_plain_text)
+                    await heartflow.get_subheartflow(chat.stream_id).do_thinking_before_reply(
+                        message.processed_plain_text
+                    )
                     timer2 = time.time()
                     timing_results["思考前脑内状态"] = timer2 - timer1
                 except Exception as e:
                     logger.error(f"心流思考前脑内状态失败: {e}")
-                
+
                 # 生成回复
                 timer1 = time.time()
                 response_set = await self.gpt.generate_response(message)

src/plugins/chat_module/think_flow_chat/think_flow_generator.py

@@ -35,7 +35,6 @@ class ResponseGenerator:
     async def generate_response(self, message: MessageThinking) -> Optional[Union[str, List[str]]]:
         """根据当前模型类型选择对应的生成函数"""
 
-        
         logger.info(
             f"思考:{message.processed_plain_text[:30] + '...' if len(message.processed_plain_text) > 30 else message.processed_plain_text}"
         )
@@ -178,4 +177,3 @@ class ResponseGenerator:
         # print(f"得到了处理后的llm返回{processed_response}")
 
         return processed_response
-

src/plugins/chat_module/think_flow_chat/think_flow_prompt_builder.py

@@ -21,22 +21,21 @@ class PromptBuilder:
     async def _build_prompt(
         self, chat_stream, message_txt: str, sender_name: str = "某人", stream_id: Optional[int] = None
     ) -> tuple[str, str]:
-        
         current_mind_info = heartflow.get_subheartflow(stream_id).current_mind
-        
+
         individuality = Individuality.get_instance()
-        prompt_personality = individuality.get_prompt(type = "personality",x_person = 2,level = 1)
-        prompt_identity = individuality.get_prompt(type = "identity",x_person = 2,level = 1)
+        prompt_personality = individuality.get_prompt(type="personality", x_person=2, level=1)
+        prompt_identity = individuality.get_prompt(type="identity", x_person=2, level=1)
         # 关系
-        who_chat_in_group = [(chat_stream.user_info.platform, 
-                              chat_stream.user_info.user_id, 
-                              chat_stream.user_info.user_nickname)]
+        who_chat_in_group = [
+            (chat_stream.user_info.platform, chat_stream.user_info.user_id, chat_stream.user_info.user_nickname)
+        ]
         who_chat_in_group += get_recent_group_speaker(
             stream_id,
             (chat_stream.user_info.platform, chat_stream.user_info.user_id),
             limit=global_config.MAX_CONTEXT_SIZE,
         )
-        
+
         relation_prompt = ""
         for person in who_chat_in_group:
             relation_prompt += await relationship_manager.build_relationship_info(person)
@@ -100,7 +99,7 @@ class PromptBuilder:
 涉及政治敏感以及违法违规的内容请规避。"""
 
         logger.info("开始构建prompt")
-        
+
         prompt = f"""
         {relation_prompt_all}\n
 {chat_target}
@@ -114,7 +113,7 @@ class PromptBuilder:
 请回复的平淡一些，简短一些，说中文，不要刻意突出自身学科背景，尽量不要说你说过的话 
 请注意不要输出多余内容(包括前后缀，冒号和引号，括号，表情等)，只输出回复内容。
 {moderation_prompt}不要输出多余内容(包括前后缀，冒号和引号，括号，表情包，at或 @等 )。"""
-        
+
         return prompt