random qa

src/chat/actions/base_action.py

@@ -73,7 +73,6 @@ class BaseAction(ABC):
         """初始化动作
 
         Args:
-            action_name: 动作名称
             action_data: 动作数据
             reasoning: 执行该动作的理由
             cycle_timers: 计时器字典

src/chat/actions/default_actions/reply_action.py

@@ -118,13 +118,10 @@ class ReplyAction(BaseAction):
 
         reply_to = reply_data.get("reply_to", "none")
 
-        # sender = ""
-        target = ""
         if ":" in reply_to or "：" in reply_to:
             # 使用正则表达式匹配中文或英文冒号
             parts = re.split(pattern=r"[:：]", string=reply_to, maxsplit=1)
             if len(parts) == 2:
-                # sender = parts[0].strip()
                 target = parts[1].strip()
                 anchor_message = chatting_observation.search_message_by_text(target)
         else:

src/chat/command/command_handler.py

@@ -32,10 +32,7 @@ class BaseCommand(ABC):
         """
         self.message = message
         self.matched_groups: Dict[str, str] = {}  # 存储正则表达式匹配的命名组
-        self._services = {}  # 存储内部服务
-
-        # 设置服务
-        self._services["chat_stream"] = message.chat_stream
+        self._services = {"chat_stream": message.chat_stream}  # 存储内部服务
 
         # 日志前缀
         self.log_prefix = f"[Command:{self.command_name}]"

src/chat/focus_chat/expressors/default_expressor.py

@@ -181,11 +181,6 @@ class DefaultExpressor:
         (已整合原 HeartFCGenerator 的功能)
         """
         try:
-            # 1. 获取情绪影响因子并调整模型温度
-            # arousal_multiplier = mood_manager.get_arousal_multiplier()
-            # current_temp = float(global_config.model.normal["temp"]) * arousal_multiplier
-            # self.express_model.params["temperature"] = current_temp  # 动态调整温度
-
             # --- Determine sender_name for private chat ---
             sender_name_for_prompt = "某人"  # Default for group or if info unavailable
             if not self.is_group_chat and self.chat_target_info:

src/chat/focus_chat/info_processors/tool_processor.py

@@ -48,11 +48,13 @@ class ToolProcessor(BaseProcessor):
         self.structured_info = []
 
     async def process_info(
-        self, observations: Optional[List[Observation]] = None, running_memorys: Optional[List[Dict]] = None, *infos
-    ) -> List[dict]:
+        self, observations: Optional[List[Observation]] = None, running_memories: Optional[List[Dict]] = None, *infos
+    ) -> List[StructuredInfo]:
         """处理信息对象
 
         Args:
+            observations: 可选的观察列表，包含ChattingObservation和StructureObservation类型
+            running_memories: 可选的运行时记忆列表，包含字典类型的记忆信息
             *infos: 可变数量的InfoBase类型的信息对象
 
         Returns:
@@ -60,15 +62,15 @@ class ToolProcessor(BaseProcessor):
         """
 
         working_infos = []
+        result = []
 
         if observations:
             for observation in observations:
                 if isinstance(observation, ChattingObservation):
-                    result, used_tools, prompt = await self.execute_tools(observation, running_memorys)
+                    result, used_tools, prompt = await self.execute_tools(observation, running_memories)
 
-            # 更新WorkingObservation中的结构化信息
             logger.debug(f"工具调用结果: {result}")
-
+            # 更新WorkingObservation中的结构化信息
             for observation in observations:
                 if isinstance(observation, StructureObservation):
                     for structured_info in result:
@@ -81,12 +83,7 @@ class ToolProcessor(BaseProcessor):
         structured_info = StructuredInfo()
         if working_infos:
             for working_info in working_infos:
-                # print(f"working_info: {working_info}")
-                # print(f"working_info.get('type'): {working_info.get('type')}")
-                # print(f"working_info.get('content'): {working_info.get('content')}")
                 structured_info.set_info(key=working_info.get("type"), value=working_info.get("content"))
-                # info = structured_info.get_processed_info()
-                # print(f"info: {info}")
 
         return [structured_info]
 

src/chat/focus_chat/planners/modify_actions.py

@@ -198,9 +198,7 @@ class ActionModifier:
 
         Args:
             actions_with_info: 带完整信息的动作字典
-            observed_messages_str: 观察到的聊天消息
-            chat_context: 聊天上下文信息
-            extra_context: 额外的上下文信息
+            chat_content: 聊天内容
 
         Returns:
             Dict[str, Any]: 过滤后激活的actions字典
@@ -320,9 +318,7 @@ class ActionModifier:
 
         Args:
             llm_judge_actions: 需要LLM判定的actions
-            observed_messages_str: 观察到的聊天消息
-            chat_context: 聊天上下文
-            extra_context: 额外上下文
+            chat_content: 聊天内容
 
         Returns:
             Dict[str, bool]: action名称到激活结果的映射

src/chat/focus_chat/planners/planner_simple.py

@@ -217,7 +217,6 @@ class ActionPlanner(BasePlanner):
 
                     # 提取决策，提供默认值
                     extracted_action = parsed_json.get("action", "no_reply")
-                    # extracted_reasoning = parsed_json.get("reasoning", "LLM未提供理由")
                     extracted_reasoning = ""
 
                     # 将所有其他属性添加到action_data

src/chat/knowledge/lpmmconfig.py

@@ -132,9 +132,6 @@ global_config = dict(
     }
 )
 
-# _load_config(global_config, parser.parse_args().config_path)
-# file_path = os.path.abspath(__file__)
-# dir_path = os.path.dirname(file_path)
 ROOT_PATH = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", ".."))
 config_path = os.path.join(ROOT_PATH, "config", "lpmm_config.toml")
 _load_config(global_config, config_path)

src/chat/knowledge/raw_processing.py

@@ -25,10 +25,10 @@ def load_raw_data(path: str = None) -> tuple[list[str], list[str]]:
             import_json = json.loads(f.read())
     else:
         raise Exception(f"原始数据文件读取失败: {json_path}")
-    # import_json内容示例：
-    # import_json = [
-    #       "The capital of China is Beijing. The capital of France is Paris.",
-    # ]
+    """
+    import_json 内容示例：
+    import_json = ["The capital of China is Beijing. The capital of France is Paris.",]
+    """
     raw_data = []
     sha256_list = []
     sha256_set = set()

src/chat/message_receive/message.py

@@ -112,7 +112,7 @@ class MessageRecv(Message):
         self.detailed_plain_text = message_dict.get("detailed_plain_text", "")  # 初始化为空字符串
         self.is_emoji = False
 
-    def update_chat_stream(self, chat_stream: "ChatStream"):
+    def update_chat_stream(self, chat_stream: ChatStream):
         self.chat_stream = chat_stream
 
     async def process(self) -> None:

src/chat/utils/chat_message_builder.py

@@ -585,14 +585,9 @@ async def build_anonymous_messages(messages: List[Dict[str, Any]]) -> str:
 
     for msg in messages:
         try:
-            # user_info = msg.get("user_info", {})
             platform = msg.get("chat_info_platform")
             user_id = msg.get("user_id")
             _timestamp = msg.get("time")
-            # print(f"msg:{msg}")
-            # print(f"platform:{platform}")
-            # print(f"user_id:{user_id}")
-            # print(f"timestamp:{timestamp}")
             if msg.get("display_message"):
                 content = msg.get("display_message")
             else:

src/chat/utils/utils.py

@@ -247,8 +247,6 @@ def split_into_sentences_w_remove_punctuation(text: str) -> list[str]:
 
     # 如果分割后为空（例如，输入全是分隔符且不满足保留条件），恢复颜文字并返回
     if not segments:
-        # recovered_text = recover_kaomoji([text], mapping) # 恢复原文本中的颜文字 - 已移至上层处理
-        # return [s for s in recovered_text if s] # 返回非空结果
         return [text] if text else []  # 如果原始文本非空，则返回原始文本（可能只包含未被分割的字符或颜文字占位符）
 
     # 2. 概率合并
@@ -336,7 +334,6 @@ def process_llm_response(text: str) -> list[str]:
         kaomoji_mapping = {}
     # 提取被 () 或 [] 或 （）包裹且包含中文的内容
     pattern = re.compile(r"[(\[（](?=.*[一-鿿]).*?[)\]）]")
-    # _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("", protected_text)