Merge branch 'dev' into fix-kaomoji-missing-bug

.github/workflows/ruff.yml

@@ -12,7 +12,10 @@ jobs:
         with:
           fetch-depth: 0
           ref: ${{ github.head_ref || github.ref_name }}
-      - uses: astral-sh/ruff-action@v3
+      - name: Install the latest version of ruff
+        uses: astral-sh/ruff-action@v3
+        with:
+          version: "latest"
       - run: ruff check --fix
       - run: ruff format
       - name: Commit changes

.gitignore

@@ -29,7 +29,6 @@ config/bot_config_dev.toml
 config/bot_config.toml
 config/bot_config.toml.bak
 src/plugins/remote/client_uuid.json
-run_none.bat
 （测试版）麦麦生成人格.bat
 （临时版）麦麦开始学习.bat
 src/plugins/utils/statistic.py

src/do_tool/tool_use.py

@@ -1,4 +1,4 @@
-from src.plugins.models.utils_model import LLM_request
+from src.plugins.models.utils_model import LLMRequest
 from src.plugins.config.config import global_config
 from src.plugins.chat.chat_stream import ChatStream
 from src.common.database import db
@@ -18,7 +18,7 @@ logger = get_module_logger("tool_use", config=tool_use_config)
 
 class ToolUser:
     def __init__(self):
-        self.llm_model_tool = LLM_request(
+        self.llm_model_tool = LLMRequest(
             model=global_config.llm_tool_use, temperature=0.2, max_tokens=1000, request_type="tool_use"
         )
 
@@ -41,6 +41,12 @@ class ToolUser:
         else:
             mid_memory_info = ""
 
+        stream_id = chat_stream.stream_id
+        chat_talking_prompt = ""
+        if stream_id:
+            chat_talking_prompt = get_recent_group_detailed_plain_text(
+                stream_id, limit=global_config.MAX_CONTEXT_SIZE, combine=True
+            )
         new_messages = list(
             db.messages.find({"chat_id": chat_stream.stream_id, "time": {"$gt": time.time()}}).sort("time", 1).limit(15)
         )
@@ -54,9 +60,10 @@ class ToolUser:
         prompt = ""
         prompt += mid_memory_info
         prompt += "你正在思考如何回复群里的消息。\n"
+        prompt += f"之前群里进行了如下讨论:\n"
+        prompt += chat_talking_prompt
         prompt += f"你注意到{sender_name}刚刚说：{message_txt}\n"
-        prompt += f"注意你就是{bot_name}，{bot_name}指的就是你。"
+        prompt += f"注意你就是{bot_name}，{bot_name}是你的名字。根据之前的聊天记录补充问题信息，搜索时避开你的名字。\n"
-
         prompt += "你现在需要对群里的聊天内容进行回复，现在选择工具来对消息和你的回复进行处理，你是否需要额外的信息，比如回忆或者搜寻已有的知识，改变关系和情感，或者了解你现在正在做什么。"
         return prompt
 
@@ -107,7 +114,7 @@ class ToolUser:
             return None
 
     async def use_tool(
-        self, message_txt: str, sender_name: str, chat_stream: ChatStream, subheartflow: SubHeartflow = None
+        self, message_txt: str, sender_name: str, chat_stream: ChatStream, sub_heartflow: SubHeartflow = None
     ):
         """使用工具辅助思考，判断是否需要额外信息
 
@@ -115,13 +122,14 @@ class ToolUser:
             message_txt: 用户消息文本
             sender_name: 发送者名称
             chat_stream: 聊天流对象
+            sub_heartflow: 子心流对象（可选）
 
         Returns:
             dict: 工具使用结果，包含结构化的信息
         """
         try:
             # 构建提示词
-            prompt = await self._build_tool_prompt(message_txt, sender_name, chat_stream, subheartflow)
+            prompt = await self._build_tool_prompt(message_txt, sender_name, chat_stream, sub_heartflow)
 
             # 定义可用工具
             tools = self._define_tools()

src/heart_flow/heartflow.py

@@ -1,7 +1,7 @@
 from .sub_heartflow import SubHeartflow
 from .observation import ChattingObservation
 from src.plugins.moods.moods import MoodManager
-from src.plugins.models.utils_model import LLM_request
+from src.plugins.models.utils_model import LLMRequest
 from src.plugins.config.config import global_config
 from src.plugins.schedule.schedule_generator import bot_schedule
 from src.plugins.utils.prompt_builder import Prompt, global_prompt_manager
@@ -60,7 +60,7 @@ class Heartflow:
         self.current_mind = "你什么也没想"
         self.past_mind = []
         self.current_state: CurrentState = CurrentState()
-        self.llm_model = LLM_request(
+        self.llm_model = LLMRequest(
             model=global_config.llm_heartflow, temperature=0.6, max_tokens=1000, request_type="heart_flow"
         )
 

src/heart_flow/observation.py

@@ -1,7 +1,7 @@
 # 定义了来自外部世界的信息
 # 外部世界可以是某个聊天 不同平台的聊天 也可以是任意媒体
 from datetime import datetime
-from src.plugins.models.utils_model import LLM_request
+from src.plugins.models.utils_model import LLMRequest
 from src.plugins.config.config import global_config
 from src.common.database import db
 from src.common.logger import get_module_logger
@@ -40,7 +40,7 @@ class ChattingObservation(Observation):
 
         self.updating_old = False
 
-        self.llm_summary = LLM_request(
+        self.llm_summary = LLMRequest(
             model=global_config.llm_observation, temperature=0.7, max_tokens=300, request_type="chat_observation"
         )
 
@@ -57,8 +57,9 @@ class ChattingObservation(Observation):
                             msg_str = ""
                             for msg in mid_memory_by_id["messages"]:
                                 msg_str += f"{msg['detailed_plain_text']}"
-                            time_diff = int((datetime.now().timestamp() - mid_memory_by_id["created_at"]) / 60)
+                            # time_diff = int((datetime.now().timestamp() - mid_memory_by_id["created_at"]) / 60)
-                            mid_memory_str += f"距离现在{time_diff}分钟前：\n{msg_str}\n"
+                            # mid_memory_str += f"距离现在{time_diff}分钟前：\n{msg_str}\n"
+                            mid_memory_str += f"{msg_str}\n"
                 except Exception as e:
                     logger.error(f"获取mid_memory_id失败: {e}")
                     traceback.print_exc()

src/heart_flow/sub_heartflow.py

@@ -1,10 +1,11 @@
 from .observation import Observation, ChattingObservation
 import asyncio
 from src.plugins.moods.moods import MoodManager
-from src.plugins.models.utils_model import LLM_request
+from src.plugins.models.utils_model import LLMRequest
 from src.plugins.config.config import global_config
-import re
 import time
+from src.plugins.chat.message import UserInfo
+from src.plugins.chat.utils import parse_text_timestamps
 
 # from src.plugins.schedule.schedule_generator import bot_schedule
 # from src.plugins.memory_system.Hippocampus import HippocampusManager
@@ -37,11 +38,11 @@ def init_prompt():
     prompt += "{prompt_personality}\n"
     prompt += "刚刚你的想法是{current_thinking_info}。可以适当转换话题\n"
     prompt += "-----------------------------------\n"
-    prompt += "现在你正在上网，和qq群里的网友们聊天，群里正在聊的话题是：{chat_observe_info}\n"
+    prompt += "现在是{time_now}，你正在上网，和qq群里的网友们聊天，群里正在聊的话题是：\n{chat_observe_info}\n"
     prompt += "你现在{mood_info}\n"
     prompt += "你注意到{sender_name}刚刚说：{message_txt}\n"
     prompt += "现在你接下去继续思考，产生新的想法，不要分点输出，输出连贯的内心独白"
-    prompt += "思考时可以想想如何对群聊内容进行回复。回复的要求是：平淡一些，简短一些，说中文，尽量不要说你说过的话\n"
+    prompt += "思考时可以想想如何对群聊内容进行回复。回复的要求是：平淡一些，简短一些，说中文，尽量不要说你说过的话。如果你要回复，最好只回复一个人的一个话题\n"
     prompt += "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)，不要带有括号和动作描写"
     prompt += "记得结合上述的消息，生成内心想法，文字不要浮夸，注意你就是{bot_name}，{bot_name}指的就是你。"
     Prompt(prompt, "sub_heartflow_prompt_before")
@@ -49,7 +50,7 @@ def init_prompt():
     # prompt += f"你现在正在做的事情是：{schedule_info}\n"
     prompt += "{extra_info}\n"
     prompt += "{prompt_personality}\n"
-    prompt += "现在你正在上网，和qq群里的网友们聊天，群里正在聊的话题是：{chat_observe_info}\n"
+    prompt += "现在是{time_now}，你正在上网，和qq群里的网友们聊天，群里正在聊的话题是：\n{chat_observe_info}\n"
     prompt += "刚刚你的想法是{current_thinking_info}。"
     prompt += "你现在看到了网友们发的新消息:{message_new_info}\n"
     prompt += "你刚刚回复了群友们:{reply_info}"
@@ -78,7 +79,7 @@ class SubHeartflow:
         self.current_mind = ""
         self.past_mind = []
         self.current_state: CurrentState = CurrentState()
-        self.llm_model = LLM_request(
+        self.llm_model = LLMRequest(
             model=global_config.llm_sub_heartflow,
             temperature=global_config.llm_sub_heartflow["temp"],
             max_tokens=600,
@@ -154,7 +155,7 @@ class SubHeartflow:
         await observation.observe()
 
     async def do_thinking_before_reply(
-        self, message_txt: str, sender_name: str, chat_stream: ChatStream, extra_info: str, obs_id: int = None
+        self, message_txt: str, sender_info: UserInfo, chat_stream: ChatStream, extra_info: str, obs_id: int = None
     ):
         current_thinking_info = self.current_mind
         mood_info = self.current_state.mood
@@ -207,7 +208,11 @@ class SubHeartflow:
         #     f"根据你和说话者{sender_name}的关系和态度进行回复，明确你的立场和情感。"
         # )
         relation_prompt_all = (await global_prompt_manager.get_prompt_async("relationship_prompt")).format(
-            relation_prompt, sender_name
+            relation_prompt, sender_info.user_nickname
+        )
+
+        sender_name_sign = (
+            f"<{chat_stream.platform}:{sender_info.user_id}:{sender_info.user_nickname}:{sender_info.user_cardname}>"
         )
 
         # prompt = ""
@@ -226,19 +231,25 @@ class SubHeartflow:
         # prompt += "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)，不要带有括号和动作描写"
         # prompt += f"记得结合上述的消息，生成内心想法，文字不要浮夸，注意你就是{self.bot_name}，{self.bot_name}指的就是你。"
 
+        time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+
         prompt = (await global_prompt_manager.get_prompt_async("sub_heartflow_prompt_before")).format(
             extra_info_prompt,
             # prompt_schedule,
             relation_prompt_all,
             prompt_personality,
             current_thinking_info,
+            time_now,
             chat_observe_info,
             mood_info,
-            sender_name,
+            sender_name_sign,
             message_txt,
             self.bot_name,
         )
 
+        prompt = await relationship_manager.convert_all_person_sign_to_person_name(prompt)
+        prompt = parse_text_timestamps(prompt, mode="lite")
+
         try:
             response, reasoning_content = await self.llm_model.generate_response_async(prompt)
         except Exception as e:
@@ -286,9 +297,12 @@ class SubHeartflow:
         message_new_info = chat_talking_prompt
         reply_info = reply_content
 
+        time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+
         prompt = (await global_prompt_manager.get_prompt_async("sub_heartflow_prompt_after")).format(
             extra_info_prompt,
             prompt_personality,
+            time_now,
             chat_observe_info,
             current_thinking_info,
             message_new_info,
@@ -296,6 +310,9 @@ class SubHeartflow:
             mood_info,
         )
 
+        prompt = await relationship_manager.convert_all_person_sign_to_person_name(prompt)
+        prompt = parse_text_timestamps(prompt, mode="lite")
+
         try:
             response, reasoning_content = await self.llm_model.generate_response_async(prompt)
         except Exception as e:
@@ -308,48 +325,6 @@ class SubHeartflow:
 
         self.last_reply_time = time.time()
 
-    async def judge_willing(self):
-        # 开始构建prompt
-        prompt_personality = "你"
-        # 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]}"
-
-        # print("麦麦闹情绪了1")
-        current_thinking_info = self.current_mind
-        mood_info = self.current_state.mood
-        # print("麦麦闹情绪了2")
-        prompt = ""
-        prompt += f"{prompt_personality}\n"
-        prompt += "现在你正在上网，和qq群里的网友们聊天"
-        prompt += f"你现在的想法是{current_thinking_info}。"
-        prompt += f"你现在{mood_info}。"
-        prompt += "现在请你思考，你想不想发言或者回复，请你输出一个数字，1-10，1表示非常不想，10表示非常想。"
-        prompt += "请你用<>包裹你的回复意愿，输出<1>表示不想回复，输出<10>表示非常想回复。请你考虑，你完全可以不回复"
-        try:
-            response, reasoning_content = await self.llm_model.generate_response_async(prompt)
-            # 解析willing值
-            willing_match = re.search(r"<(\d+)>", response)
-        except Exception as e:
-            logger.error(f"意愿判断获取失败: {e}")
-            willing_match = None
-        if willing_match:
-            self.current_state.willing = int(willing_match.group(1))
-        else:
-            self.current_state.willing = 0
-
-        return self.current_state.willing
-
     def update_current_mind(self, response):
         self.past_mind.append(self.current_mind)
         self.current_mind = response

src/individuality/offline_llm.py

@@ -10,7 +10,7 @@ from src.common.logger import get_module_logger
 logger = get_module_logger("offline_llm")
 
 
-class LLM_request_off:
+class LLMRequestOff:
     def __init__(self, model_name="Pro/deepseek-ai/DeepSeek-V3", **kwargs):
         self.model_name = model_name
         self.params = kwargs

src/individuality/per_bf_gen.py

@@ -19,7 +19,7 @@ with open(config_path, "r", encoding="utf-8") as f:
 # 现在可以导入src模块
 from src.individuality.scene import get_scene_by_factor, PERSONALITY_SCENES  # noqa E402
 from src.individuality.questionnaire import FACTOR_DESCRIPTIONS  # noqa E402
-from src.individuality.offline_llm import LLM_request_off  # noqa E402
+from src.individuality.offline_llm import LLMRequestOff  # noqa E402
 
 # 加载环境变量
 env_path = os.path.join(root_path, ".env")
@@ -65,7 +65,7 @@ def adapt_scene(scene: str) -> str:
 现在，请你给出改编后的场景描述
 """
 
-        llm = LLM_request_off(model_name=config["model"]["llm_normal"]["name"])
+        llm = LLMRequestOff(model_name=config["model"]["llm_normal"]["name"])
         adapted_scene, _ = llm.generate_response(prompt)
 
         # 检查返回的场景是否为空或错误信息
@@ -79,7 +79,7 @@ def adapt_scene(scene: str) -> str:
         return scene
 
 
-class PersonalityEvaluator_direct:
+class PersonalityEvaluatorDirect:
     def __init__(self):
         self.personality_traits = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
         self.scenarios = []
@@ -110,7 +110,7 @@ class PersonalityEvaluator_direct:
                     {"场景": scene["scenario"], "评估维度": [trait, secondary_trait], "场景编号": scene_key}
                 )
 
-        self.llm = LLM_request_off()
+        self.llm = LLMRequestOff()
 
     def evaluate_response(self, scenario: str, response: str, dimensions: List[str]) -> Dict[str, float]:
         """
@@ -269,7 +269,7 @@ class PersonalityEvaluator_direct:
 
 
 def main():
-    evaluator = PersonalityEvaluator_direct()
+    evaluator = PersonalityEvaluatorDirect()
     result = evaluator.run_evaluation()
 
     # 准备简化的结果数据

src/main.py

@@ -9,7 +9,7 @@ from .plugins.willing.willing_manager import willing_manager
 from .plugins.chat.chat_stream import chat_manager
 from .heart_flow.heartflow import heartflow
 from .plugins.memory_system.Hippocampus import HippocampusManager
-from .plugins.chat.message_sender import message_manager
+from .plugins.chat.messagesender import message_manager
 from .plugins.storage.storage import MessageStorage
 from .plugins.config.config import global_config
 from .plugins.chat.bot import chat_bot

src/plugins/PFC/action_planner.py

@@ -1,6 +1,6 @@
 from typing import Tuple
 from src.common.logger import get_module_logger
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from .chat_observer import ChatObserver
 from .pfc_utils import get_items_from_json
@@ -23,7 +23,7 @@ class ActionPlanner:
     """行动规划器"""
 
     def __init__(self, stream_id: str):
-        self.llm = LLM_request(
+        self.llm = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.llm_normal["temp"],
             max_tokens=1000,

src/plugins/PFC/message_sender.py

@@ -4,7 +4,7 @@ from ..chat.chat_stream import ChatStream
 from ..chat.message import Message
 from ..message.message_base import Seg
 from src.plugins.chat.message import MessageSending, MessageSet
-from src.plugins.chat.message_sender import message_manager
+from src.plugins.chat.messagesender import message_manager
 
 logger = get_module_logger("message_sender")
 

src/plugins/PFC/message_storage.py

@@ -50,21 +50,18 @@ class MessageStorage(ABC):
 class MongoDBMessageStorage(MessageStorage):
     """MongoDB消息存储实现"""
 
-    def __init__(self):
-        self.db = db
-
     async def get_messages_after(self, chat_id: str, message_time: float) -> List[Dict[str, Any]]:
         query = {"chat_id": chat_id}
         # print(f"storage_check_message: {message_time}")
 
         query["time"] = {"$gt": message_time}
 
-        return list(self.db.messages.find(query).sort("time", 1))
+        return list(db.messages.find(query).sort("time", 1))
 
     async def get_messages_before(self, chat_id: str, time_point: float, limit: int = 5) -> List[Dict[str, Any]]:
         query = {"chat_id": chat_id, "time": {"$lt": time_point}}
 
-        messages = list(self.db.messages.find(query).sort("time", -1).limit(limit))
+        messages = list(db.messages.find(query).sort("time", -1).limit(limit))
 
         # 将消息按时间正序排列
         messages.reverse()
@@ -73,7 +70,7 @@ class MongoDBMessageStorage(MessageStorage):
     async def has_new_messages(self, chat_id: str, after_time: float) -> bool:
         query = {"chat_id": chat_id, "time": {"$gt": after_time}}
 
-        return self.db.messages.find_one(query) is not None
+        return db.messages.find_one(query) is not None
 
 
 # # 创建一个内存消息存储实现，用于测试

src/plugins/PFC/observation_info.py

@@ -120,6 +120,10 @@ class ObservationInfo:
     # #spec
     # meta_plan_trigger: bool = False
 
+    def __init__(self):
+        self.last_message_id = None
+        self.chat_observer = None
+
     def __post_init__(self):
         """初始化后创建handler"""
         self.chat_observer = None
@@ -129,7 +133,7 @@ class ObservationInfo:
         """绑定到指定的chat_observer
 
         Args:
-            stream_id: 聊天流ID
+            chat_observer: 要绑定的ChatObserver实例
         """
         self.chat_observer = chat_observer
         self.chat_observer.notification_manager.register_handler(
@@ -171,7 +175,8 @@ class ObservationInfo:
             self.last_bot_speak_time = message["time"]
         else:
             self.last_user_speak_time = message["time"]
-            self.active_users.add(user_info.user_id)
+            if user_info.user_id is not None:
+                self.active_users.add(str(user_info.user_id))
 
         self.new_messages_count += 1
         self.unprocessed_messages.append(message)
@@ -227,7 +232,7 @@ class ObservationInfo:
         """清空未处理消息列表"""
         # 将未处理消息添加到历史记录中
         for message in self.unprocessed_messages:
-            self.chat_history.append(message)
+            self.chat_history.append(message)  # TODO NEED FIX TYPE???
         # 清空未处理消息列表
         self.has_unread_messages = False
         self.unprocessed_messages.clear()

src/plugins/PFC/pfc.py

@@ -8,7 +8,7 @@ from src.common.logger import get_module_logger
 from ..chat.chat_stream import ChatStream
 from ..message.message_base import UserInfo, Seg
 from ..chat.message import Message
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from src.plugins.chat.message import MessageSending
 from ..message.api import global_api
@@ -30,7 +30,7 @@ class GoalAnalyzer:
     """对话目标分析器"""
 
     def __init__(self, stream_id: str):
-        self.llm = LLM_request(
+        self.llm = LLMRequest(
             model=global_config.llm_normal, temperature=0.7, max_tokens=1000, request_type="conversation_goal"
         )
 
@@ -350,7 +350,7 @@ class DirectMessageSender:
                 # logger.info(f"发送消息到{end_point}")
                 # logger.info(message_json)
                 try:
-                    await global_api.send_message_REST(end_point, message_json)
+                    await global_api.send_message_rest(end_point, message_json)
                 except Exception as e:
                     logger.error(f"REST方式发送失败，出现错误: {str(e)}")
                     logger.info("尝试使用ws发送")

src/plugins/PFC/pfc_KnowledgeFetcher.py

@@ -1,7 +1,7 @@
 from typing import List, Tuple
 from src.common.logger import get_module_logger
 from src.plugins.memory_system.Hippocampus import HippocampusManager
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from ..chat.message import Message
 
@@ -12,7 +12,7 @@ class KnowledgeFetcher:
     """知识调取器"""
 
     def __init__(self):
-        self.llm = LLM_request(
+        self.llm = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.llm_normal["temp"],
             max_tokens=1000,

src/plugins/PFC/reply_checker.py

@@ -2,7 +2,7 @@ import json
 import datetime
 from typing import Tuple
 from src.common.logger import get_module_logger
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from .chat_observer import ChatObserver
 from ..message.message_base import UserInfo
@@ -14,7 +14,7 @@ class ReplyChecker:
     """回复检查器"""
 
     def __init__(self, stream_id: str):
-        self.llm = LLM_request(
+        self.llm = LLMRequest(
             model=global_config.llm_normal, temperature=0.7, max_tokens=1000, request_type="reply_check"
         )
         self.name = global_config.BOT_NICKNAME

src/plugins/PFC/reply_generator.py

@@ -1,6 +1,6 @@
 from typing import Tuple
 from src.common.logger import get_module_logger
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from .chat_observer import ChatObserver
 from .reply_checker import ReplyChecker
@@ -15,7 +15,7 @@ class ReplyGenerator:
     """回复生成器"""
 
     def __init__(self, stream_id: str):
-        self.llm = LLM_request(
+        self.llm = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.llm_normal["temp"],
             max_tokens=300,

src/plugins/chat/__init__.py

@@ -1,7 +1,7 @@
 from .emoji_manager import emoji_manager
 from ..person_info.relationship_manager import relationship_manager
 from .chat_stream import chat_manager
-from .message_sender import message_manager
+from .messagesender import message_manager
 from ..storage.storage import MessageStorage
 
 

src/plugins/chat/bot.py

@@ -42,7 +42,7 @@ class ChatBot:
 
             self._started = True
 
-    async def _create_PFC_chat(self, message: MessageRecv):
+    async def _create_pfc_chat(self, message: MessageRecv):
         try:
             chat_id = str(message.chat_stream.stream_id)
 
@@ -112,7 +112,7 @@ class ChatBot:
                                 )
                                 message.update_chat_stream(chat)
                                 await self.only_process_chat.process_message(message)
-                                await self._create_PFC_chat(message)
+                                await self._create_pfc_chat(message)
                         else:
                             if groupinfo.group_id in global_config.talk_allowed_groups:
                                 # logger.debug(f"开始群聊模式{str(message_data)[:50]}...")

src/plugins/chat/emoji_manager.py

@@ -13,7 +13,7 @@ from ...common.database import db
 from ..config.config import global_config
 from ..chat.utils import get_embedding
 from ..chat.utils_image import ImageManager, image_path_to_base64
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from src.common.logger import get_module_logger
 
 logger = get_module_logger("emoji")
@@ -34,8 +34,8 @@ class EmojiManager:
 
     def __init__(self):
         self._scan_task = None
-        self.vlm = LLM_request(model=global_config.vlm, temperature=0.3, max_tokens=1000, request_type="emoji")
+        self.vlm = LLMRequest(model=global_config.vlm, temperature=0.3, max_tokens=1000, request_type="emoji")
-        self.llm_emotion_judge = LLM_request(
+        self.llm_emotion_judge = LLMRequest(
             model=global_config.llm_emotion_judge, max_tokens=600, temperature=0.8, request_type="emoji"
         )  # 更高的温度，更少的token（后续可以根据情绪来调整温度）
 

src/plugins/chat/message.py

@@ -142,14 +142,16 @@ class MessageRecv(Message):
 
     def _generate_detailed_text(self) -> str:
         """生成详细文本，包含时间和用户信息"""
-        time_str = time.strftime("%m-%d %H:%M:%S", time.localtime(self.message_info.time))
+        # time_str = time.strftime("%m-%d %H:%M:%S", time.localtime(self.message_info.time))
+        time = self.message_info.time
         user_info = self.message_info.user_info
-        name = (
+        # name = (
-            f"{user_info.user_nickname}(ta的昵称:{user_info.user_cardname},ta的id:{user_info.user_id})"
+        #     f"{user_info.user_nickname}(ta的昵称:{user_info.user_cardname},ta的id:{user_info.user_id})"
-            if user_info.user_cardname != None
+        #     if user_info.user_cardname != None
-            else f"{user_info.user_nickname}(ta的id:{user_info.user_id})"
+        #     else f"{user_info.user_nickname}(ta的id:{user_info.user_id})"
-        )
+        # )
-        return f"[{time_str}] {name}: {self.processed_plain_text}\n"
+        name = f"<{self.message_info.platform}:{user_info.user_id}:{user_info.user_nickname}:{user_info.user_cardname}>"
+        return f"[{time}] {name}: {self.processed_plain_text}\n"
 
 
 @dataclass
@@ -239,14 +241,16 @@ class MessageProcessBase(Message):
 
     def _generate_detailed_text(self) -> str:
         """生成详细文本，包含时间和用户信息"""
-        time_str = time.strftime("%m-%d %H:%M:%S", time.localtime(self.message_info.time))
+        # time_str = time.strftime("%m-%d %H:%M:%S", time.localtime(self.message_info.time))
+        time = self.message_info.time
         user_info = self.message_info.user_info
-        name = (
+        # name = (
-            f"{user_info.user_nickname}(ta的昵称:{user_info.user_cardname},ta的id:{user_info.user_id})"
+        #     f"{user_info.user_nickname}(ta的昵称:{user_info.user_cardname},ta的id:{user_info.user_id})"
-            if user_info.user_cardname != None
+        #     if user_info.user_cardname != None
-            else f"{user_info.user_nickname}(ta的id:{user_info.user_id})"
+        #     else f"{user_info.user_nickname}(ta的id:{user_info.user_id})"
-        )
+        # )
-        return f"[{time_str}] {name}: {self.processed_plain_text}\n"
+        name = f"<{self.message_info.platform}:{user_info.user_id}:{user_info.user_nickname}:{user_info.user_cardname}>"
+        return f"[{time}] {name}: {self.processed_plain_text}\n"
 
 
 @dataclass

src/plugins/chat/message_buffer.py

@@ -59,20 +59,20 @@ class MessageBuffer:
                     logger.debug(f"被新消息覆盖信息id: {cache_msg.message.message_info.message_id}")
 
             # 查找最近的处理成功消息(T)
-            recent_F_count = 0
+            recent_f_count = 0
             for msg_id in reversed(self.buffer_pool[person_id_]):
                 msg = self.buffer_pool[person_id_][msg_id]
                 if msg.result == "T":
                     break
                 elif msg.result == "F":
-                    recent_F_count += 1
+                    recent_f_count += 1
 
             # 判断条件：最近T之后有超过3-5条F
-            if recent_F_count >= random.randint(3, 5):
+            if recent_f_count >= random.randint(3, 5):
                 new_msg = CacheMessages(message=message, result="T")
                 new_msg.cache_determination.set()
                 self.buffer_pool[person_id_][message.message_info.message_id] = new_msg
-                logger.debug(f"快速处理消息(已堆积{recent_F_count}条F): {message.message_info.message_id}")
+                logger.debug(f"快速处理消息(已堆积{recent_f_count}条F): {message.message_info.message_id}")
                 return
 
             # 添加新消息
@@ -153,11 +153,11 @@ class MessageBuffer:
                     # 更新当前消息的processed_plain_text
                     if combined_text and combined_text[0] != message.processed_plain_text and is_update:
                         if type == "text":
-                            message.processed_plain_text = "".join(combined_text)
+                            message.processed_plain_text = "，".join(combined_text)
                             logger.debug(f"整合了{len(combined_text) - 1}条F消息的内容到当前消息")
                         elif type == "emoji":
                             combined_text.pop()
-                            message.processed_plain_text = "".join(combined_text)
+                            message.processed_plain_text = "，".join(combined_text)
                             message.is_emoji = False
                             logger.debug(f"整合了{len(combined_text) - 1}条F消息的内容，覆盖当前emoji消息")
 

src/plugins/chat/messagesender.py

@@ -23,7 +23,7 @@ sender_config = LogConfig(
 logger = get_module_logger("msg_sender", config=sender_config)
 
 
-class Message_Sender:
+class MessageSender:
     """发送器"""
 
     def __init__(self):
@@ -83,7 +83,7 @@ class Message_Sender:
                         # logger.info(f"发送消息到{end_point}")
                         # logger.info(message_json)
                         try:
-                            await global_api.send_message_REST(end_point, message_json)
+                            await global_api.send_message_rest(end_point, message_json)
                         except Exception as e:
                             logger.error(f"REST方式发送失败，出现错误: {str(e)}")
                             logger.info("尝试使用ws发送")
@@ -286,4 +286,4 @@ class MessageManager:
 # 创建全局消息管理器实例
 message_manager = MessageManager()
 # 创建全局发送器实例
-message_sender = Message_Sender()
+message_sender = MessageSender()

src/plugins/chat/utils.py

@@ -8,7 +8,7 @@ import jieba
 import numpy as np
 from src.common.logger import get_module_logger
 
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..utils.typo_generator import ChineseTypoGenerator
 from ..config.config import global_config
 from .message import MessageRecv, Message
@@ -38,21 +38,35 @@ def db_message_to_str(message_dict: Dict) -> str:
     return result
 
 
-def is_mentioned_bot_in_message(message: MessageRecv) -> bool:
+def is_mentioned_bot_in_message(message: MessageRecv) -> tuple[bool, float]:
     """检查消息是否提到了机器人"""
     keywords = [global_config.BOT_NICKNAME]
     nicknames = global_config.BOT_ALIAS_NAMES
-    reply_probability = 0
+    reply_probability = 0.0
     is_at = False
     is_mentioned = False
 
+    if (
+        message.message_info.additional_config is not None
+        and message.message_info.additional_config.get("is_mentioned") is not None
+    ):
+        try:
+            reply_probability = float(message.message_info.additional_config.get("is_mentioned"))
+            is_mentioned = True
+            return is_mentioned, reply_probability
+        except Exception as e:
+            logger.warning(e)
+            logger.warning(
+                f"消息中包含不合理的设置 is_mentioned: {message.message_info.additional_config.get('is_mentioned')}"
+            )
+
     # 判断是否被@
     if re.search(f"@[\s\S]*?（id:{global_config.BOT_QQ}）", message.processed_plain_text):
         is_at = True
         is_mentioned = True
 
     if is_at and global_config.at_bot_inevitable_reply:
-        reply_probability = 1
+        reply_probability = 1.0
         logger.info("被@，回复概率设置为100%")
     else:
         if not is_mentioned:
@@ -61,7 +75,7 @@ def is_mentioned_bot_in_message(message: MessageRecv) -> bool:
                 is_mentioned = True
 
             # 判断内容中是否被提及
-            message_content = re.sub(r"\@[\s\S]*?（(\d+)）", "", message.processed_plain_text)
+            message_content = re.sub(r"@[\s\S]*?（(\d+)）", "", message.processed_plain_text)
             message_content = re.sub(r"回复[\s\S]*?\((\d+)\)的消息，说： ", "", message_content)
             for keyword in keywords:
                 if keyword in message_content:
@@ -70,14 +84,14 @@ def is_mentioned_bot_in_message(message: MessageRecv) -> bool:
                 if nickname in message_content:
                     is_mentioned = True
         if is_mentioned and global_config.mentioned_bot_inevitable_reply:
-            reply_probability = 1
+            reply_probability = 1.0
             logger.info("被提及，回复概率设置为100%")
     return is_mentioned, reply_probability
 
 
 async def get_embedding(text, request_type="embedding"):
     """获取文本的embedding向量"""
-    llm = LLM_request(model=global_config.embedding, request_type=request_type)
+    llm = LLMRequest(model=global_config.embedding, request_type=request_type)
     # return llm.get_embedding_sync(text)
     try:
         embedding = await llm.get_embedding(text)
@@ -91,7 +105,7 @@ async def get_recent_group_messages(chat_id: str, limit: int = 12) -> list:
     """从数据库获取群组最近的消息记录
 
     Args:
-        group_id: 群组ID
+        chat_id: 群组ID
         limit: 获取消息数量，默认12条
 
     Returns:
@@ -331,6 +345,7 @@ def process_llm_response(text: str) -> List[str]:
     pattern = re.compile(r"[\(\[].*?[\)\]]")
     # _extracted_contents = pattern.findall(text)
     _extracted_contents = pattern.findall(protected_text) # 在保护后的文本上查找
+
     # 去除 () 和 [] 及其包裹的内容
     # cleaned_text = pattern.sub("", text)
     cleaned_text = pattern.sub("", protected_text)
@@ -493,16 +508,16 @@ def protect_kaomoji(sentence):
     """
     kaomoji_pattern = re.compile(
         r"("
-        r"[\(\[（【]"  # 左括号
+        r"[(\[（【]"  # 左括号
         r"[^()\[\]（）【】]*?"  # 非括号字符（惰性匹配）
-        r"[^\u4e00-\u9fa5a-zA-Z0-9\s]"  # 非中文、非英文、非数字、非空格字符（必须包含至少一个）
+        r"[^一-龥a-zA-Z0-9\s]"  # 非中文、非英文、非数字、非空格字符（必须包含至少一个）
         r"[^()\[\]（）【】]*?"  # 非括号字符（惰性匹配）
-        r"[\)\]）】]"  # 右括号
+        r"[\)\]）】"  # 右括号
+        r"]"
         r")"
         r"|"
-        r"("
+        r"([▼▽・ᴥω･﹏^><≧≦￣｀´∀ヮДд︿﹀へ｡ﾟ╥╯╰︶︹•⁄]{2,15"
-        r"[▼▽・ᴥω･﹏^><≧≦￣｀´∀ヮДд︿﹀へ｡ﾟ╥╯╰︶︹•⁄]{2,15}"
+        r"}"
-        r")"
     )
 
     kaomoji_matches = kaomoji_pattern.findall(sentence)
@@ -636,3 +651,142 @@ def count_messages_between(start_time: float, end_time: float, stream_id: str) -
     except Exception as e:
         logger.error(f"计算消息数量时出错: {str(e)}")
         return 0, 0
+
+
+def translate_timestamp_to_human_readable(timestamp: float, mode: str = "normal") -> str:
+    """将时间戳转换为人类可读的时间格式
+
+    Args:
+        timestamp: 时间戳
+        mode: 转换模式，"normal"为标准格式，"relative"为相对时间格式
+
+    Returns:
+        str: 格式化后的时间字符串
+    """
+    if mode == "normal":
+        return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(timestamp))
+    elif mode == "relative":
+        now = time.time()
+        diff = now - timestamp
+
+        if diff < 20:
+            return "刚刚:"
+        elif diff < 60:
+            return f"{int(diff)}秒前:"
+        elif diff < 1800:
+            return f"{int(diff / 60)}分钟前:"
+        elif diff < 3600:
+            return f"{int(diff / 60)}分钟前:\n"
+        elif diff < 86400:
+            return f"{int(diff / 3600)}小时前:\n"
+        elif diff < 604800:
+            return f"{int(diff / 86400)}天前:\n"
+        else:
+            return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(timestamp)) + ":"
+
+
+def parse_text_timestamps(text: str, mode: str = "normal") -> str:
+    """解析文本中的时间戳并转换为可读时间格式
+
+    Args:
+        text: 包含时间戳的文本，时间戳应以[]包裹
+        mode: 转换模式，传递给translate_timestamp_to_human_readable，"normal"或"relative"
+
+    Returns:
+        str: 替换后的文本
+
+    转换规则:
+    - normal模式: 将文本中所有时间戳转换为可读格式
+    - lite模式:
+        - 第一个和最后一个时间戳必须转换
+        - 以5秒为间隔划分时间段，每段最多转换一个时间戳
+        - 不转换的时间戳替换为空字符串
+    """
+    # 匹配[数字]或[数字.数字]格式的时间戳
+    pattern = r"\[(\d+(?:\.\d+)?)\]"
+
+    # 找出所有匹配的时间戳
+    matches = list(re.finditer(pattern, text))
+
+    if not matches:
+        return text
+
+    # normal模式: 直接转换所有时间戳
+    if mode == "normal":
+        result_text = text
+        for match in matches:
+            timestamp = float(match.group(1))
+            readable_time = translate_timestamp_to_human_readable(timestamp, "normal")
+            # 由于替换会改变文本长度，需要使用正则替换而非直接替换
+            pattern_instance = re.escape(match.group(0))
+            result_text = re.sub(pattern_instance, readable_time, result_text, count=1)
+        return result_text
+    else:
+        # lite模式: 按5秒间隔划分并选择性转换
+        result_text = text
+
+        # 提取所有时间戳及其位置
+        timestamps = [(float(m.group(1)), m) for m in matches]
+        timestamps.sort(key=lambda x: x[0])  # 按时间戳升序排序
+
+        if not timestamps:
+            return text
+
+        # 获取第一个和最后一个时间戳
+        first_timestamp, first_match = timestamps[0]
+        last_timestamp, last_match = timestamps[-1]
+
+        # 将时间范围划分成5秒间隔的时间段
+        time_segments = {}
+
+        # 对所有时间戳按15秒间隔分组
+        for ts, match in timestamps:
+            segment_key = int(ts // 15)  # 将时间戳除以15取整，作为时间段的键
+            if segment_key not in time_segments:
+                time_segments[segment_key] = []
+            time_segments[segment_key].append((ts, match))
+
+        # 记录需要转换的时间戳
+        to_convert = []
+
+        # 从每个时间段中选择一个时间戳进行转换
+        for _, segment_timestamps in time_segments.items():
+            # 选择这个时间段中的第一个时间戳
+            to_convert.append(segment_timestamps[0])
+
+        # 确保第一个和最后一个时间戳在转换列表中
+        first_in_list = False
+        last_in_list = False
+
+        for ts, _ in to_convert:
+            if ts == first_timestamp:
+                first_in_list = True
+            if ts == last_timestamp:
+                last_in_list = True
+
+        if not first_in_list:
+            to_convert.append((first_timestamp, first_match))
+        if not last_in_list:
+            to_convert.append((last_timestamp, last_match))
+
+        # 创建需要转换的时间戳集合，用于快速查找
+        to_convert_set = {match.group(0) for _, match in to_convert}
+
+        # 首先替换所有不需要转换的时间戳为空字符串
+        for _, match in timestamps:
+            if match.group(0) not in to_convert_set:
+                pattern_instance = re.escape(match.group(0))
+                result_text = re.sub(pattern_instance, "", result_text, count=1)
+
+        # 按照时间戳原始顺序排序，避免替换时位置错误
+        to_convert.sort(key=lambda x: x[1].start())
+
+        # 执行替换
+        # 由于替换会改变文本长度，从后向前替换
+        to_convert.reverse()
+        for ts, match in to_convert:
+            readable_time = translate_timestamp_to_human_readable(ts, "relative")
+            pattern_instance = re.escape(match.group(0))
+            result_text = re.sub(pattern_instance, readable_time, result_text, count=1)
+
+        return result_text

src/plugins/chat/utils_image.py

@@ -9,7 +9,7 @@ import io
 
 from ...common.database import db
 from ..config.config import global_config
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 
 from src.common.logger import get_module_logger
 
@@ -32,7 +32,7 @@ class ImageManager:
             self._ensure_description_collection()
             self._ensure_image_dir()
             self._initialized = True
-            self._llm = LLM_request(model=global_config.vlm, temperature=0.4, max_tokens=300, request_type="image")
+            self._llm = LLMRequest(model=global_config.vlm, temperature=0.4, max_tokens=300, request_type="image")
 
     def _ensure_image_dir(self):
         """确保图像存储目录存在"""

src/plugins/chat_module/reasoning_chat/reasoning_chat.py

@@ -8,7 +8,7 @@ from ...config.config import global_config
 from ...chat.emoji_manager import emoji_manager
 from .reasoning_generator import ResponseGenerator
 from ...chat.message import MessageSending, MessageRecv, MessageThinking, MessageSet
-from ...chat.message_sender import message_manager
+from ...chat.messagesender import message_manager
 from ...storage.storage import MessageStorage
 from ...chat.utils import is_mentioned_bot_in_message
 from ...chat.utils_image import image_path_to_base64

src/plugins/chat_module/reasoning_chat/reasoning_generator.py

@@ -1,7 +1,7 @@
 from typing import List, Optional, Tuple, Union
 import random
 
-from ...models.utils_model import LLM_request
+from ...models.utils_model import LLMRequest
 from ...config.config import global_config
 from ...chat.message import MessageThinking
 from .reasoning_prompt_builder import prompt_builder
@@ -22,20 +22,20 @@ logger = get_module_logger("llm_generator", config=llm_config)
 
 class ResponseGenerator:
     def __init__(self):
-        self.model_reasoning = LLM_request(
+        self.model_reasoning = LLMRequest(
             model=global_config.llm_reasoning,
             temperature=0.7,
             max_tokens=3000,
             request_type="response_reasoning",
         )
-        self.model_normal = LLM_request(
+        self.model_normal = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.llm_normal["temp"],
             max_tokens=256,
             request_type="response_reasoning",
         )
 
-        self.model_sum = LLM_request(
+        self.model_sum = LLMRequest(
             model=global_config.llm_summary_by_topic, temperature=0.7, max_tokens=3000, request_type="relation"
         )
         self.current_model_type = "r1"  # 默认使用 R1
@@ -68,7 +68,7 @@ class ResponseGenerator:
             logger.info(f"{self.current_model_type}思考，失败")
             return None
 
-    async def _generate_response_with_model(self, message: MessageThinking, model: LLM_request, thinking_id: str):
+    async def _generate_response_with_model(self, message: MessageThinking, model: LLMRequest, thinking_id: str):
         sender_name = ""
 
         info_catcher = info_catcher_manager.get_info_catcher(thinking_id)

src/plugins/chat_module/think_flow_chat/think_flow_chat.py

@@ -8,7 +8,7 @@ from ...config.config import global_config
 from ...chat.emoji_manager import emoji_manager
 from .think_flow_generator import ResponseGenerator
 from ...chat.message import MessageSending, MessageRecv, MessageThinking, MessageSet
-from ...chat.message_sender import message_manager
+from ...chat.messagesender import message_manager
 from ...storage.storage import MessageStorage
 from ...chat.utils import is_mentioned_bot_in_message, get_recent_group_detailed_plain_text
 from ...chat.utils_image import image_path_to_base64
@@ -258,7 +258,7 @@ class ThinkFlowChat:
                         await heartflow.get_subheartflow(chat.stream_id).do_observe()
                 except Exception as e:
                     logger.error(f"心流观察失败: {e}")
-                    traceback.print_exc()
+                    logger.error(traceback.format_exc())
 
                 info_catcher.catch_after_observe(timing_results["观察"])
 
@@ -329,13 +329,17 @@ class ThinkFlowChat:
                             chat.stream_id
                         ).do_thinking_before_reply(
                             message_txt=message.processed_plain_text,
-                            sender_name=message.message_info.user_info.user_nickname,
+                            sender_info=message.message_info.user_info,
                             chat_stream=chat,
                             obs_id=get_mid_memory_id,
                             extra_info=tool_result_info,
                         )
                 except Exception as e:
                     logger.error(f"心流思考前脑内状态失败: {e}")
+                    logger.error(traceback.format_exc())
+                    # 确保变量被定义，即使在错误情况下
+                    current_mind = ""
+                    past_mind = ""
 
                 info_catcher.catch_afer_shf_step(timing_results["思考前脑内状态"], past_mind, current_mind)
 
@@ -373,6 +377,7 @@ class ThinkFlowChat:
                 except Exception as e:
                     logger.error(f"心流处理表情包失败: {e}")
 
+                # 思考后脑内状态更新
                 try:
                     with Timer("思考后脑内状态更新", timing_results):
                         stream_id = message.chat_stream.stream_id
@@ -387,10 +392,44 @@ class ThinkFlowChat:
                         )
                 except Exception as e:
                     logger.error(f"心流思考后脑内状态更新失败: {e}")
+                    logger.error(traceback.format_exc())
 
                 # 回复后处理
                 await willing_manager.after_generate_reply_handle(message.message_info.message_id)
 
+                # 处理认识关系
+                try:
+                    is_known = await relationship_manager.is_known_some_one(
+                        message.message_info.platform, message.message_info.user_info.user_id
+                    )
+                    if not is_known:
+                        logger.info(f"首次认识用户: {message.message_info.user_info.user_nickname}")
+                        await relationship_manager.first_knowing_some_one(
+                            message.message_info.platform,
+                            message.message_info.user_info.user_id,
+                            message.message_info.user_info.user_nickname,
+                            message.message_info.user_info.user_cardname
+                            or message.message_info.user_info.user_nickname,
+                            "",
+                        )
+                    else:
+                        logger.debug(f"已认识用户: {message.message_info.user_info.user_nickname}")
+                        if not await relationship_manager.is_qved_name(
+                            message.message_info.platform, message.message_info.user_info.user_id
+                        ):
+                            logger.info(f"更新已认识但未取名的用户: {message.message_info.user_info.user_nickname}")
+                            await relationship_manager.first_knowing_some_one(
+                                message.message_info.platform,
+                                message.message_info.user_info.user_id,
+                                message.message_info.user_info.user_nickname,
+                                message.message_info.user_info.user_cardname
+                                or message.message_info.user_info.user_nickname,
+                                "",
+                            )
+                except Exception as e:
+                    logger.error(f"处理认识关系失败: {e}")
+                    logger.error(traceback.format_exc())
+
             except Exception as e:
                 logger.error(f"心流处理消息失败: {e}")
                 logger.error(traceback.format_exc())

src/plugins/chat_module/think_flow_chat/think_flow_generator.py

@@ -2,7 +2,7 @@ from typing import List, Optional
 import random
 
 
-from ...models.utils_model import LLM_request
+from ...models.utils_model import LLMRequest
 from ...config.config import global_config
 from ...chat.message import MessageRecv
 from .think_flow_prompt_builder import prompt_builder
@@ -25,14 +25,14 @@ logger = get_module_logger("llm_generator", config=llm_config)
 
 class ResponseGenerator:
     def __init__(self):
-        self.model_normal = LLM_request(
+        self.model_normal = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.llm_normal["temp"],
             max_tokens=256,
             request_type="response_heartflow",
         )
 
-        self.model_sum = LLM_request(
+        self.model_sum = LLMRequest(
             model=global_config.llm_summary_by_topic, temperature=0.6, max_tokens=2000, request_type="relation"
         )
         self.current_model_type = "r1"  # 默认使用 R1
@@ -94,21 +94,23 @@ class ResponseGenerator:
             return None
 
     async def _generate_response_with_model(
-        self, message: MessageRecv, model: LLM_request, thinking_id: str, mode: str = "normal"
+        self, message: MessageRecv, model: LLMRequest, thinking_id: str, mode: str = "normal"
     ) -> str:
         sender_name = ""
 
         info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
 
-        if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
+        # if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
-            sender_name = (
+        #     sender_name = (
-                f"[({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}]"
+        #         f"[({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}]"
-                f"{message.chat_stream.user_info.user_cardname}"
+        #         f"{message.chat_stream.user_info.user_cardname}"
-            )
+        #     )
-        elif message.chat_stream.user_info.user_nickname:
+        # elif message.chat_stream.user_info.user_nickname:
-            sender_name = f"({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}"
+        #     sender_name = f"({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}"
-        else:
+        # else:
-            sender_name = f"用户({message.chat_stream.user_info.user_id})"
+        #     sender_name = f"用户({message.chat_stream.user_info.user_id})"
+
+        sender_name = f"<{message.chat_stream.user_info.platform}:{message.chat_stream.user_info.user_id}:{message.chat_stream.user_info.user_nickname}:{message.chat_stream.user_info.user_cardname}>"
 
         # 构建prompt
         with Timer() as t_build_prompt:
@@ -119,14 +121,7 @@ class ResponseGenerator:
                     sender_name=sender_name,
                     stream_id=message.chat_stream.stream_id,
                 )
-            elif mode == "simple":
+        logger.info(f"构建prompt时间: {t_build_prompt.human_readable}")
-                prompt = await prompt_builder._build_prompt_simple(
-                    message.chat_stream,
-                    message_txt=message.processed_plain_text,
-                    sender_name=sender_name,
-                    stream_id=message.chat_stream.stream_id,
-                )
-        logger.info(f"构建{mode}prompt时间: {t_build_prompt.human_readable}")
 
         try:
             content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
@@ -141,49 +136,6 @@ class ResponseGenerator:
 
         return content
 
-    async def _check_response_with_model(
-        self, message: MessageRecv, content: str, model: LLM_request, thinking_id: str
-    ) -> str:
-        _info_catcher = info_catcher_manager.get_info_catcher(thinking_id)
-
-        sender_name = ""
-        if message.chat_stream.user_info.user_cardname and message.chat_stream.user_info.user_nickname:
-            sender_name = (
-                f"[({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}]"
-                f"{message.chat_stream.user_info.user_cardname}"
-            )
-        elif message.chat_stream.user_info.user_nickname:
-            sender_name = f"({message.chat_stream.user_info.user_id}){message.chat_stream.user_info.user_nickname}"
-        else:
-            sender_name = f"用户({message.chat_stream.user_info.user_id})"
-
-        # 构建prompt
-        with Timer() as t_build_prompt_check:
-            prompt = await prompt_builder._build_prompt_check_response(
-                message.chat_stream,
-                message_txt=message.processed_plain_text,
-                sender_name=sender_name,
-                stream_id=message.chat_stream.stream_id,
-                content=content,
-            )
-        logger.info(f"构建check_prompt: {prompt}")
-        logger.info(f"构建check_prompt时间: {t_build_prompt_check.human_readable}")
-
-        try:
-            checked_content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
-
-            # info_catcher.catch_after_llm_generated(
-            #     prompt=prompt,
-            #     response=content,
-            #     reasoning_content=reasoning_content,
-            #     model_name=self.current_model_name)
-
-        except Exception:
-            logger.exception("检查回复时出错")
-            return None
-
-        return checked_content
-
     async def _get_emotion_tags(self, content: str, processed_plain_text: str):
         """提取情感标签，结合立场和情绪"""
         try:

src/plugins/chat_module/think_flow_chat/think_flow_prompt_builder.py

@@ -8,6 +8,8 @@ from src.common.logger import get_module_logger
 from ....individuality.individuality import Individuality
 from src.heart_flow.heartflow import heartflow
 from src.plugins.utils.prompt_builder import Prompt, global_prompt_manager
+from src.plugins.person_info.relationship_manager import relationship_manager
+from src.plugins.chat.utils import parse_text_timestamps
 
 logger = get_module_logger("prompt")
 
@@ -161,6 +163,9 @@ class PromptBuilder:
             moderation_prompt=await global_prompt_manager.get_prompt_async("moderation_prompt"),
         )
 
+        prompt = await relationship_manager.convert_all_person_sign_to_person_name(prompt)
+        prompt = parse_text_timestamps(prompt, mode="lite")
+
         return prompt
 
     async def _build_prompt_simple(

src/plugins/config/config.py

@@ -26,9 +26,9 @@ config_config = LogConfig(
 logger = get_module_logger("config", config=config_config)
 
 # 考虑到，实际上配置文件中的mai_version是不会自动更新的,所以采用硬编码
-is_test = False
+is_test = True
-mai_version_main = "0.6.2"
+mai_version_main = "0.6.3"
-mai_version_fix = ""
+mai_version_fix = "snapshot-1"
 
 if mai_version_fix:
     if is_test:
@@ -62,8 +62,7 @@ def update_config():
         shutil.copy2(template_path, old_config_path)
         logger.info(f"已创建新配置文件，请填写后重新运行: {old_config_path}")
         # 如果是新创建的配置文件,直接返回
-        quit()
+        return quit()
-        return
 
     # 读取旧配置文件和模板文件
     with open(old_config_path, "r", encoding="utf-8") as f:

src/plugins/memory_system/Hippocampus.py

@@ -9,7 +9,7 @@ import networkx as nx
 import numpy as np
 from collections import Counter
 from ...common.database import db
-from ...plugins.models.utils_model import LLM_request
+from ...plugins.models.utils_model import LLMRequest
 from src.common.logger import get_module_logger, LogConfig, MEMORY_STYLE_CONFIG
 from src.plugins.memory_system.sample_distribution import MemoryBuildScheduler  # 分布生成器
 from .memory_config import MemoryConfig
@@ -91,7 +91,7 @@ memory_config = LogConfig(
 logger = get_module_logger("memory_system", config=memory_config)
 
 
-class Memory_graph:
+class MemoryGraph:
     def __init__(self):
         self.G = nx.Graph()  # 使用 networkx 的图结构
 
@@ -229,7 +229,7 @@ class Memory_graph:
 # 海马体
 class Hippocampus:
     def __init__(self):
-        self.memory_graph = Memory_graph()
+        self.memory_graph = MemoryGraph()
         self.llm_topic_judge = None
         self.llm_summary_by_topic = None
         self.entorhinal_cortex = None
@@ -243,8 +243,8 @@ class Hippocampus:
         self.parahippocampal_gyrus = ParahippocampalGyrus(self)
         # 从数据库加载记忆图
         self.entorhinal_cortex.sync_memory_from_db()
-        self.llm_topic_judge = LLM_request(self.config.llm_topic_judge, request_type="memory")
+        self.llm_topic_judge = LLMRequest(self.config.llm_topic_judge, request_type="memory")
-        self.llm_summary_by_topic = LLM_request(self.config.llm_summary_by_topic, request_type="memory")
+        self.llm_summary_by_topic = LLMRequest(self.config.llm_summary_by_topic, request_type="memory")
 
     def get_all_node_names(self) -> list:
         """获取记忆图中所有节点的名字列表"""
@@ -346,7 +346,8 @@ class Hippocampus:
 
         Args:
             text (str): 输入文本
-            num (int, optional): 需要返回的记忆数量。默认为5。
+            max_memory_num (int, optional): 记忆数量限制。默认为3。
+            max_memory_length (int, optional): 记忆长度限制。默认为2。
             max_depth (int, optional): 记忆检索深度。默认为2。
             fast_retrieval (bool, optional): 是否使用快速检索。默认为False。
                 如果为True，使用jieba分词和TF-IDF提取关键词，速度更快但可能不够准确。
@@ -540,7 +541,6 @@ class Hippocampus:
 
         Args:
             text (str): 输入文本
-            num (int, optional): 需要返回的记忆数量。默认为5。
             max_depth (int, optional): 记忆检索深度。默认为2。
             fast_retrieval (bool, optional): 是否使用快速检索。默认为False。
                 如果为True，使用jieba分词和TF-IDF提取关键词，速度更快但可能不够准确。
@@ -937,7 +937,7 @@ class EntorhinalCortex:
 # 海马体
 class Hippocampus:
     def __init__(self):
-        self.memory_graph = Memory_graph()
+        self.memory_graph = MemoryGraph()
         self.llm_topic_judge = None
         self.llm_summary_by_topic = None
         self.entorhinal_cortex = None
@@ -951,8 +951,8 @@ class Hippocampus:
         self.parahippocampal_gyrus = ParahippocampalGyrus(self)
         # 从数据库加载记忆图
         self.entorhinal_cortex.sync_memory_from_db()
-        self.llm_topic_judge = LLM_request(self.config.llm_topic_judge, request_type="memory")
+        self.llm_topic_judge = LLMRequest(self.config.llm_topic_judge, request_type="memory")
-        self.llm_summary_by_topic = LLM_request(self.config.llm_summary_by_topic, request_type="memory")
+        self.llm_summary_by_topic = LLMRequest(self.config.llm_summary_by_topic, request_type="memory")
 
     def get_all_node_names(self) -> list:
         """获取记忆图中所有节点的名字列表"""
@@ -1054,8 +1054,9 @@ class Hippocampus:
 
         Args:
             text (str): 输入文本
-            num (int, optional): 需要返回的记忆数量。默认为5。
+            max_memory_num (int, optional): 返回的记忆条目数量上限。默认为3，表示最多返回3条与输入文本相关度最高的记忆。
-            max_depth (int, optional): 记忆检索深度。默认为2。
+            max_memory_length (int, optional): 每个主题最多返回的记忆条目数量。默认为2，表示每个主题最多返回2条相似度最高的记忆。
+            max_depth (int, optional): 记忆检索深度。默认为3。值越大，检索范围越广，可以获取更多间接相关的记忆，但速度会变慢。
             fast_retrieval (bool, optional): 是否使用快速检索。默认为False。
                 如果为True，使用jieba分词和TF-IDF提取关键词，速度更快但可能不够准确。
                 如果为False，使用LLM提取关键词，速度较慢但更准确。
@@ -1248,7 +1249,6 @@ class Hippocampus:
 
         Args:
             text (str): 输入文本
-            num (int, optional): 需要返回的记忆数量。默认为5。
             max_depth (int, optional): 记忆检索深度。默认为2。
             fast_retrieval (bool, optional): 是否使用快速检索。默认为False。
                 如果为True，使用jieba分词和TF-IDF提取关键词，速度更快但可能不够准确。

src/plugins/memory_system/manually_alter_memory.py

@@ -177,7 +177,7 @@ def remove_mem_edge(hippocampus: Hippocampus):
 
 # 修改节点信息
 def alter_mem_node(hippocampus: Hippocampus):
-    batchEnviroment = dict()
+    batch_environment = dict()
     while True:
         concept = input("请输入节点概念名（输入'终止'以结束）:\n")
         if concept.lower() == "终止":
@@ -229,7 +229,7 @@ def alter_mem_node(hippocampus: Hippocampus):
                 break
 
             try:
-                user_exec(command, node_environment, batchEnviroment)
+                user_exec(command, node_environment, batch_environment)
             except Exception as e:
                 console.print(e)
                 console.print(
@@ -239,7 +239,7 @@ def alter_mem_node(hippocampus: Hippocampus):
 
 # 修改边信息
 def alter_mem_edge(hippocampus: Hippocampus):
-    batchEnviroment = dict()
+    batch_enviroment = dict()
     while True:
         source = input("请输入 **第一个节点** 名称（输入'终止'以结束）：\n")
         if source.lower() == "终止":
@@ -262,21 +262,21 @@ def alter_mem_edge(hippocampus: Hippocampus):
         console.print("[yellow]你将获得一个执行任意代码的环境[/yellow]")
         console.print("[red]你已经被警告过了。[/red]\n")
 
-        edgeEnviroment = {"source": "<节点名>", "target": "<节点名>", "strength": "<强度值,装在一个list里>"}
+        edge_environment = {"source": "<节点名>", "target": "<节点名>", "strength": "<强度值,装在一个list里>"}
         console.print(
             "[green]环境变量中会有env与batchEnv两个dict, env在切换节点时会清空, batchEnv在操作终止时才会清空[/green]"
         )
         console.print(
-            f"[green] env 会被初始化为[/green]\n{edgeEnviroment}\n[green]且会在用户代码执行完毕后被提交 [/green]"
+            f"[green] env 会被初始化为[/green]\n{edge_environment}\n[green]且会在用户代码执行完毕后被提交 [/green]"
         )
         console.print(
             "[yellow]为便于书写临时脚本，请手动在输入代码通过Ctrl+C等方式触发KeyboardInterrupt来结束代码执行[/yellow]"
         )
 
         # 拷贝数据以防操作炸了
-        edgeEnviroment["strength"] = [edge["strength"]]
+        edge_environment["strength"] = [edge["strength"]]
-        edgeEnviroment["source"] = source
+        edge_environment["source"] = source
-        edgeEnviroment["target"] = target
+        edge_environment["target"] = target
 
         while True:
 
@@ -288,8 +288,8 @@ def alter_mem_edge(hippocampus: Hippocampus):
             except KeyboardInterrupt:
                 # 稍微防一下小天才
                 try:
-                    if isinstance(edgeEnviroment["strength"][0], int):
+                    if isinstance(edge_environment["strength"][0], int):
-                        edge["strength"] = edgeEnviroment["strength"][0]
+                        edge["strength"] = edge_environment["strength"][0]
                     else:
                         raise Exception
 
@@ -301,7 +301,7 @@ def alter_mem_edge(hippocampus: Hippocampus):
                 break
 
             try:
-                user_exec(command, edgeEnviroment, batchEnviroment)
+                user_exec(command, edge_environment, batch_enviroment)
             except Exception as e:
                 console.print(e)
                 console.print(

src/plugins/memory_system/offline_llm.py

@@ -10,7 +10,7 @@ from src.common.logger import get_module_logger
 logger = get_module_logger("offline_llm")
 
 
-class LLM_request_off:
+class LLMRequestOff:
     def __init__(self, model_name="deepseek-ai/DeepSeek-V3", **kwargs):
         self.model_name = model_name
         self.params = kwargs

src/plugins/message/api.py

@@ -233,7 +233,8 @@ class MessageServer(BaseMessageHandler):
     async def send_message(self, message: MessageBase):
         await self.broadcast_to_platform(message.message_info.platform, message.to_dict())
 
-    async def send_message_REST(self, url: str, data: Dict[str, Any]) -> Dict[str, Any]:
+    @staticmethod
+    async def send_message_rest(url: str, data: Dict[str, Any]) -> Dict[str, Any]:
         """发送消息到指定端点"""
         async with aiohttp.ClientSession() as session:
             try:

src/plugins/models/utils_model.py

@@ -16,7 +16,7 @@ from ..config.config import global_config
 logger = get_module_logger("model_utils")
 
 
-class LLM_request:
+class LLMRequest:
     # 定义需要转换的模型列表，作为类变量避免重复
     MODELS_NEEDING_TRANSFORMATION = [
         "o3-mini",

src/plugins/person_info/person_info.py

@@ -6,6 +6,9 @@ from typing import Any, Callable, Dict
 import datetime
 import asyncio
 import numpy as np
+from src.plugins.models.utils_model import LLMRequest
+from src.plugins.config.config import global_config
+from src.individuality.individuality import Individuality
 
 import matplotlib
 
@@ -13,6 +16,8 @@ matplotlib.use("Agg")
 import matplotlib.pyplot as plt
 from pathlib import Path
 import pandas as pd
+import json
+import re
 
 
 """
@@ -32,6 +37,8 @@ logger = get_module_logger("person_info")
 
 person_info_default = {
     "person_id": None,
+    "person_name": None,
+    "name_reason": None,
     "platform": None,
     "user_id": None,
     "nickname": None,
@@ -48,16 +55,42 @@ person_info_default = {
 
 class PersonInfoManager:
     def __init__(self):
+        self.person_name_list = {}
+        self.qv_name_llm = LLMRequest(
+            model=global_config.llm_normal,
+            max_tokens=256,
+            request_type="qv_name",
+        )
         if "person_info" not in db.list_collection_names():
             db.create_collection("person_info")
             db.person_info.create_index("person_id", unique=True)
 
+        # 初始化时读取所有person_name
+        cursor = db.person_info.find({"person_name": {"$exists": True}}, {"person_id": 1, "person_name": 1, "_id": 0})
+        for doc in cursor:
+            if doc.get("person_name"):
+                self.person_name_list[doc["person_id"]] = doc["person_name"]
+        logger.debug(f"已加载 {len(self.person_name_list)} 个用户名称")
+
     def get_person_id(self, platform: str, user_id: int):
         """获取唯一id"""
+        # 如果platform中存在-，就截取-后面的部分
+        if "-" in platform:
+            platform = platform.split("-")[1]
+
         components = [platform, str(user_id)]
         key = "_".join(components)
         return hashlib.md5(key.encode()).hexdigest()
 
+    def is_person_known(self, platform: str, user_id: int):
+        """判断是否认识某人"""
+        person_id = self.get_person_id(platform, user_id)
+        document = db.person_info.find_one({"person_id": person_id})
+        if document:
+            return True
+        else:
+            return False
+
     async def create_person_info(self, person_id: str, data: dict = None):
         """创建一个项"""
         if not person_id:
@@ -74,7 +107,7 @@ class PersonInfoManager:
 
         db.person_info.insert_one(_person_info_default)
 
-    async def update_one_field(self, person_id: str, field_name: str, value, Data: dict = None):
+    async def update_one_field(self, person_id: str, field_name: str, value, data: dict = None):
         """更新某一个字段，会补全"""
         if field_name not in person_info_default.keys():
             logger.debug(f"更新'{field_name}'失败，未定义的字段")
@@ -85,9 +118,112 @@ class PersonInfoManager:
         if document:
             db.person_info.update_one({"person_id": person_id}, {"$set": {field_name: value}})
         else:
-            Data[field_name] = value
+            data[field_name] = value
             logger.debug(f"更新时{person_id}不存在，已新建")
-            await self.create_person_info(person_id, Data)
+            await self.create_person_info(person_id, data)
+
+    @staticmethod
+    async def has_one_field(person_id: str, field_name: str):
+        """判断是否存在某一个字段"""
+        document = db.person_info.find_one({"person_id": person_id}, {field_name: 1})
+        if document:
+            return True
+        else:
+            return False
+
+    def _extract_json_from_text(self, text: str) -> dict:
+        """从文本中提取JSON数据的高容错方法"""
+        try:
+            # 尝试直接解析
+            return json.loads(text)
+        except json.JSONDecodeError:
+            try:
+                # 尝试找到JSON格式的部分
+                json_pattern = r"\{[^{}]*\}"
+                matches = re.findall(json_pattern, text)
+                if matches:
+                    return json.loads(matches[0])
+
+                # 如果上面都失败了，尝试提取键值对
+                nickname_pattern = r'"nickname"[:\s]+"([^"]+)"'
+                reason_pattern = r'"reason"[:\s]+"([^"]+)"'
+
+                nickname_match = re.search(nickname_pattern, text)
+                reason_match = re.search(reason_pattern, text)
+
+                if nickname_match:
+                    return {
+                        "nickname": nickname_match.group(1),
+                        "reason": reason_match.group(1) if reason_match else "未提供理由",
+                    }
+            except Exception as e:
+                logger.error(f"JSON提取失败: {str(e)}")
+
+            # 如果所有方法都失败了，返回空结果
+            return {"nickname": "", "reason": ""}
+
+    async def qv_person_name(self, person_id: str, user_nickname: str, user_cardname: str, user_avatar: str):
+        """给某个用户取名"""
+        if not person_id:
+            logger.debug("取名失败：person_id不能为空")
+            return
+
+        old_name = await self.get_value(person_id, "person_name")
+        old_reason = await self.get_value(person_id, "name_reason")
+
+        max_retries = 5  # 最大重试次数
+        current_try = 0
+        existing_names = ""
+        while current_try < max_retries:
+            individuality = Individuality.get_instance()
+            prompt_personality = individuality.get_prompt(type="personality", x_person=2, level=1)
+            bot_name = individuality.personality.bot_nickname
+
+            qv_name_prompt = f"你是{bot_name}，你{prompt_personality}"
+            qv_name_prompt += f"现在你想给一个用户取一个昵称，用户是的qq昵称是{user_nickname}，"
+            qv_name_prompt += f"用户的qq群昵称名是{user_cardname}，"
+            if user_avatar:
+                qv_name_prompt += f"用户的qq头像是{user_avatar}，"
+            if old_name:
+                qv_name_prompt += f"你之前叫他{old_name}，是因为{old_reason}，"
+
+            qv_name_prompt += "\n请根据以上用户信息，想想你叫他什么比较好，请最好使用用户的qq昵称，可以稍作修改"
+            if existing_names:
+                qv_name_prompt += f"\n请注意，以下名称已被使用，不要使用以下昵称：{existing_names}。\n"
+            qv_name_prompt += "请用json给出你的想法，并给出理由，示例如下："
+            qv_name_prompt += """{
+                "nickname": "昵称",
+                "reason": "理由"
+            }"""
+            logger.debug(f"取名提示词：{qv_name_prompt}")
+            response = await self.qv_name_llm.generate_response(qv_name_prompt)
+            logger.debug(f"取名回复：{response}")
+            result = self._extract_json_from_text(response[0])
+
+            if not result["nickname"]:
+                logger.error("生成的昵称为空，重试中...")
+                current_try += 1
+                continue
+
+            # 检查生成的昵称是否已存在
+            if result["nickname"] not in self.person_name_list.values():
+                # 更新数据库和内存中的列表
+                await self.update_one_field(person_id, "person_name", result["nickname"])
+                # await self.update_one_field(person_id, "nickname", user_nickname)
+                # await self.update_one_field(person_id, "avatar", user_avatar)
+                await self.update_one_field(person_id, "name_reason", result["reason"])
+
+                self.person_name_list[person_id] = result["nickname"]
+                logger.debug(f"用户 {person_id} 的名称已更新为 {result['nickname']}，原因：{result['reason']}")
+                return result
+            else:
+                existing_names += f"{result['nickname']}、"
+
+            logger.debug(f"生成的昵称 {result['nickname']} 已存在，重试中...")
+            current_try += 1
+
+        logger.error(f"在{max_retries}次尝试后仍未能生成唯一昵称")
+        return None
 
     async def del_one_document(self, person_id: str):
         """删除指定 person_id 的文档"""

src/plugins/person_info/relationship_manager.py

@@ -4,6 +4,8 @@ import math
 from bson.decimal128 import Decimal128
 from .person_info import person_info_manager
 import time
+import re
+import traceback
 
 relationship_config = LogConfig(
     # 使用关系专用样式
@@ -75,6 +77,60 @@ class RelationshipManager:
         else:
             return mood_value / coefficient
 
+    async def is_known_some_one(self, platform, user_id):
+        """判断是否认识某人"""
+        is_known = person_info_manager.is_person_known(platform, user_id)
+        return is_known
+
+    async def is_qved_name(self, platform, user_id):
+        """判断是否认识某人"""
+        person_id = person_info_manager.get_person_id(platform, user_id)
+        is_qved = await person_info_manager.has_one_field(person_id, "person_name")
+        old_name = await person_info_manager.get_value(person_id, "person_name")
+        print(f"old_name: {old_name}")
+        print(f"is_qved: {is_qved}")
+        if is_qved and old_name != None:
+            return True
+        else:
+            return False
+
+    async def first_knowing_some_one(self, platform, user_id, user_nickname, user_cardname, user_avatar):
+        """判断是否认识某人"""
+        person_id = person_info_manager.get_person_id(platform, user_id)
+        await person_info_manager.update_one_field(person_id, "nickname", user_nickname)
+        # await person_info_manager.update_one_field(person_id, "user_cardname", user_cardname)
+        # await person_info_manager.update_one_field(person_id, "user_avatar", user_avatar)
+        await person_info_manager.qv_person_name(person_id, user_nickname, user_cardname, user_avatar)
+
+    async def convert_all_person_sign_to_person_name(self, input_text: str):
+        """将所有人的<platform:user_id:nickname:cardname>格式转换为person_name"""
+        try:
+            # 使用正则表达式匹配<platform:user_id:nickname:cardname>格式
+            all_person = person_info_manager.person_name_list
+
+            pattern = r"<([^:]+):(\d+):([^:]+):([^>]+)>"
+            matches = re.findall(pattern, input_text)
+
+            # 遍历匹配结果，将<platform:user_id:nickname:cardname>替换为person_name
+            result_text = input_text
+            for platform, user_id, nickname, cardname in matches:
+                person_id = person_info_manager.get_person_id(platform, user_id)
+                # 默认使用昵称作为人名
+                person_name = nickname.strip() if nickname.strip() else cardname.strip()
+
+                if person_id in all_person:
+                    if all_person[person_id] != None:
+                        person_name = all_person[person_id]
+
+                    print(f"将<{platform}:{user_id}:{nickname}:{cardname}>替换为{person_name}")
+
+                result_text = result_text.replace(f"<{platform}:{user_id}:{nickname}:{cardname}>", person_name)
+
+            return result_text
+        except Exception:
+            logger.error(traceback.format_exc())
+            return input_text
+
     async def calculate_update_relationship_value(self, chat_stream: ChatStream, label: str, stance: str) -> tuple:
         """计算并变更关系值
         新的关系值变更计算方式：

src/plugins/personality_s/renqingziji.py

@@ -38,7 +38,7 @@ else:
     print("将使用默认配置")
 
 
-class PersonalityEvaluator_direct:
+class PersonalityEvaluatorDirect:
     def __init__(self):
         self.personality_traits = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
         self.scenarios = []
@@ -135,7 +135,7 @@ def main():
     print("\n准备好了吗？按回车键开始...")
     input()
 
-    evaluator = PersonalityEvaluator_direct()
+    evaluator = PersonalityEvaluatorDirect()
     final_scores = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
     dimension_counts = {trait: 0 for trait in final_scores.keys()}
 

src/plugins/remote/remote.py

@@ -125,11 +125,12 @@ def main():
     if global_config.remote_enable:
         """主函数，启动心跳线程"""
         # 配置
-        SERVER_URL = "http://hyybuth.xyz:10058"
+        server_url = "http://hyybuth.xyz:10058"
-        HEARTBEAT_INTERVAL = 300  # 5分钟（秒）
+        # server_url = "http://localhost:10058"
+        heartbeat_interval = 300  # 5分钟（秒）
 
         # 创建并启动心跳线程
-        heartbeat_thread = HeartbeatThread(SERVER_URL, HEARTBEAT_INTERVAL)
+        heartbeat_thread = HeartbeatThread(server_url, heartbeat_interval)
         heartbeat_thread.start()
 
         return heartbeat_thread  # 返回线程对象，便于外部控制

src/plugins/schedule/schedule_generator.py

@@ -11,7 +11,7 @@ sys.path.append(root_path)
 
 from src.common.database import db  # noqa: E402
 from src.common.logger import get_module_logger, SCHEDULE_STYLE_CONFIG, LogConfig  # noqa: E402
-from src.plugins.models.utils_model import LLM_request  # noqa: E402
+from src.plugins.models.utils_model import LLMRequest  # noqa: E402
 from src.plugins.config.config import global_config  # noqa: E402
 
 TIME_ZONE = tz.gettz(global_config.TIME_ZONE)  # 设置时区
@@ -30,13 +30,13 @@ class ScheduleGenerator:
 
     def __init__(self):
         # 使用离线LLM模型
-        self.llm_scheduler_all = LLM_request(
+        self.llm_scheduler_all = LLMRequest(
             model=global_config.llm_reasoning,
             temperature=global_config.SCHEDULE_TEMPERATURE + 0.3,
             max_tokens=7000,
             request_type="schedule",
         )
-        self.llm_scheduler_doing = LLM_request(
+        self.llm_scheduler_doing = LLMRequest(
             model=global_config.llm_normal,
             temperature=global_config.SCHEDULE_TEMPERATURE,
             max_tokens=2048,

src/plugins/topic_identify/topic_identifier.py

@@ -1,7 +1,7 @@
 from typing import List, Optional
 
 
-from ..models.utils_model import LLM_request
+from ..models.utils_model import LLMRequest
 from ..config.config import global_config
 from src.common.logger import get_module_logger, LogConfig, TOPIC_STYLE_CONFIG
 
@@ -17,7 +17,7 @@ logger = get_module_logger("topic_identifier", config=topic_config)
 
 class TopicIdentifier:
     def __init__(self):
-        self.llm_topic_judge = LLM_request(model=global_config.llm_topic_judge, request_type="topic")
+        self.llm_topic_judge = LLMRequest(model=global_config.llm_topic_judge, request_type="topic")
 
     async def identify_topic_llm(self, text: str) -> Optional[List[str]]:
         """识别消息主题，返回主题列表"""

src/plugins/utils/prompt_builder.py

@@ -119,7 +119,7 @@ class Prompt(str):
 
         # 解析模板
         template_args = []
-        result = re.findall(r"\{(.*?)\}", processed_fstr)
+        result = re.findall(r"\{(.*?)}", processed_fstr)
         for expr in result:
             if expr and expr not in template_args:
                 template_args.append(expr)
@@ -164,7 +164,7 @@ class Prompt(str):
         processed_template = cls._process_escaped_braces(template)
 
         template_args = []
-        result = re.findall(r"\{(.*?)\}", processed_template)
+        result = re.findall(r"\{(.*?)}", processed_template)
         for expr in result:
             if expr and expr not in template_args:
                 template_args.append(expr)

src/plugins/utils/statistic.py

@@ -175,13 +175,8 @@ class LLMStatistics:
 
     def _format_stats_section(self, stats: Dict[str, Any], title: str) -> str:
         """格式化统计部分的输出"""
-        output = []
+        output = ["\n" + "-" * 84, f"{title}", "-" * 84, f"总请求数: {stats['total_requests']}"]
 
-        output.append("\n" + "-" * 84)
-        output.append(f"{title}")
-        output.append("-" * 84)
-
-        output.append(f"总请求数: {stats['total_requests']}")
         if stats["total_requests"] > 0:
             output.append(f"总Token数: {stats['total_tokens']}")
             output.append(f"总花费: {stats['total_cost']:.4f}¥")
@@ -238,11 +233,7 @@ class LLMStatistics:
 
     def _format_stats_section_lite(self, stats: Dict[str, Any], title: str) -> str:
         """格式化统计部分的输出"""
-        output = []
+        output = ["\n" + "-" * 84, f"{title}", "-" * 84]
-
-        output.append("\n" + "-" * 84)
-        output.append(f"{title}")
-        output.append("-" * 84)
 
         # output.append(f"总请求数: {stats['total_requests']}")
         if stats["total_requests"] > 0:
@@ -303,8 +294,7 @@ class LLMStatistics:
         """将统计结果保存到文件"""
         current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 
-        output = []
+        output = [f"LLM请求统计报告 (生成时间: {current_time})"]
-        output.append(f"LLM请求统计报告 (生成时间: {current_time})")
 
         # 添加各个时间段的统计
         sections = [