feat：统一normal和focus的动作调整,emoji统一可选随机激活或llm激活

changelogs/changelog.md

@@ -10,6 +10,8 @@
 - 优化计时信息和Log
 - 添加回复超时检查
 - normal的插件允许llm激活
+- 合并action激活器
+- emoji统一可选随机激活或llm激活
 
 ## [0.8.1] - 2025-7-5
 

src/chat/focus_chat/heartFC_chat.py

@@ -21,9 +21,9 @@ from src.chat.heart_flow.observation.actions_observation import ActionObservatio
 
 from src.chat.focus_chat.memory_activator import MemoryActivator
 from src.chat.focus_chat.info_processors.base_processor import BaseProcessor
-from src.chat.focus_chat.planners.planner_simple import ActionPlanner
-from src.chat.focus_chat.planners.modify_actions import ActionModifier
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.planner_focus import ActionPlanner
+from src.chat.planner_actions.action_modifier import ActionModifier
+from src.chat.planner_actions.action_manager import ActionManager
 from src.config.config import global_config
 from src.chat.focus_chat.hfc_performance_logger import HFCPerformanceLogger
 from src.chat.focus_chat.hfc_version_manager import get_hfc_version
@@ -50,24 +50,6 @@ PROCESSOR_CLASSES = {
 logger = get_logger("hfc")  # Logger Name Changed
 
 
-async def _handle_cycle_delay(action_taken_this_cycle: bool, cycle_start_time: float, log_prefix: str):
-    """处理循环延迟"""
-    cycle_duration = time.monotonic() - cycle_start_time
-
-    try:
-        sleep_duration = 0.0
-        if not action_taken_this_cycle and cycle_duration < 1:
-            sleep_duration = 1 - cycle_duration
-        elif cycle_duration < 0.2:
-            sleep_duration = 0.2
-
-        if sleep_duration > 0:
-            await asyncio.sleep(sleep_duration)
-
-    except asyncio.CancelledError:
-        logger.info(f"{log_prefix} Sleep interrupted, loop likely cancelling.")
-        raise
-
 
 class HeartFChatting:
     """
@@ -80,7 +62,6 @@ class HeartFChatting:
         self,
         chat_id: str,
         on_stop_focus_chat: Optional[Callable[[], Awaitable[None]]] = None,
-        performance_version: str = None,
     ):
         """
         HeartFChatting 初始化函数
@@ -122,7 +103,7 @@ class HeartFChatting:
         self.action_planner = ActionPlanner(
             log_prefix=self.log_prefix, action_manager=self.action_manager
         )
-        self.action_modifier = ActionModifier(action_manager=self.action_manager)
+        self.action_modifier = ActionModifier(action_manager=self.action_manager, chat_id=self.stream_id)
         self.action_observation = ActionObservation(observe_id=self.stream_id)
         self.action_observation.set_action_manager(self.action_manager)
 
@@ -146,7 +127,7 @@ class HeartFChatting:
 
         # 初始化性能记录器
         # 如果没有指定版本号，则使用全局版本管理器的版本号
-        actual_version = performance_version or get_hfc_version()
+        actual_version = get_hfc_version()
         self.performance_logger = HFCPerformanceLogger(chat_id, actual_version)
 
         logger.info(
@@ -287,7 +268,6 @@ class HeartFChatting:
 
                 # 初始化周期状态
                 cycle_timers = {}
-                loop_cycle_start_time = time.monotonic()
 
                 # 执行规划和处理阶段
                 try:
@@ -370,11 +350,6 @@ class HeartFChatting:
 
                         self._current_cycle_detail.timers = cycle_timers
 
-                        # 防止循环过快消耗资源
-                        await _handle_cycle_delay(
-                            loop_info["loop_action_info"]["action_taken"], loop_cycle_start_time, self.log_prefix
-                        )
-
                     # 完成当前循环并保存历史
                     self._current_cycle_detail.complete_cycle()
                     self._cycle_history.append(self._current_cycle_detail)
@@ -407,7 +382,7 @@ class HeartFChatting:
                         self.performance_logger.record_cycle(cycle_performance_data)
                     except Exception as perf_e:
                         logger.warning(f"{self.log_prefix} 记录性能数据失败: {perf_e}")
-
+                    
                     await asyncio.sleep(global_config.focus_chat.think_interval)
 
                 except asyncio.CancelledError:
@@ -543,6 +518,7 @@ class HeartFChatting:
                     # 调用完整的动作修改流程
                     await self.action_modifier.modify_actions(
                         observations=self.observations,
+                        mode="focus",
                     )
 
                     await self.action_observation.observe()
@@ -567,7 +543,7 @@ class HeartFChatting:
             logger.debug(f"{self.log_prefix} 并行阶段完成，准备进入规划器，plan_info数量: {len(all_plan_info)}")
 
             with Timer("规划器", cycle_timers):
-                plan_result = await self.action_planner.plan(all_plan_info, self.observations, loop_start_time)
+                plan_result = await self.action_planner.plan(all_plan_info, loop_start_time)
 
                 loop_plan_info = {
                     "action_result": plan_result.get("action_result", {}),

src/chat/focus_chat/planners/base_planner.py

@@ -1,28 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List, Dict, Any
-from src.chat.focus_chat.planners.action_manager import ActionManager
-from src.chat.focus_chat.info.info_base import InfoBase
-
-
-class BasePlanner(ABC):
-    """规划器基类"""
-
-    def __init__(self, log_prefix: str, action_manager: ActionManager):
-        self.log_prefix = log_prefix
-        self.action_manager = action_manager
-
-    @abstractmethod
-    async def plan(
-        self, all_plan_info: List[InfoBase], running_memorys: List[Dict[str, Any]], loop_start_time: float
-    ) -> Dict[str, Any]:
-        """
-        规划下一步行动
-
-        Args:
-            all_plan_info: 所有计划信息
-            running_memorys: 回忆信息
-            loop_start_time: 循环开始时间
-        Returns:
-            Dict[str, Any]: 规划结果
-        """
-        pass

src/chat/heart_flow/observation/actions_observation.py

@@ -2,7 +2,7 @@
 # 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.common.logger import get_logger
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.action_manager import ActionManager
 
 logger = get_logger("observation")
 

src/chat/normal_chat/normal_chat.py

@@ -9,18 +9,17 @@ from src.plugin_system.apis import generator_api
 from maim_message import UserInfo, Seg
 from src.chat.message_receive.chat_stream import ChatStream, get_chat_manager
 from src.chat.utils.timer_calculator import Timer
-
+from src.common.message_repository import count_messages
 from src.chat.utils.prompt_builder import global_prompt_manager
 from ..message_receive.message import MessageSending, MessageRecv, MessageThinking, MessageSet
 from src.chat.message_receive.message_sender import message_manager
 from src.chat.normal_chat.willing.willing_manager import get_willing_manager
-from src.chat.normal_chat.normal_chat_utils import get_recent_message_stats
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.action_manager import ActionManager
 from src.person_info.relationship_builder_manager import relationship_builder_manager
 from .priority_manager import PriorityManager
 import traceback
-from src.chat.normal_chat.normal_chat_planner import NormalChatPlanner
-from src.chat.normal_chat.normal_chat_action_modifier import NormalChatActionModifier
+from src.chat.planner_actions.planner_normal import NormalChatPlanner
+from src.chat.planner_actions.action_modifier import ActionModifier
 
 from src.chat.heart_flow.utils_chat import get_chat_type_and_target_info
 from src.manager.mood_manager import mood_manager
@@ -71,7 +70,7 @@ class NormalChat:
         # Planner相关初始化
         self.action_manager = ActionManager()
         self.planner = NormalChatPlanner(self.stream_name, self.action_manager)
-        self.action_modifier = NormalChatActionModifier(self.action_manager, self.stream_id, self.stream_name)
+        self.action_modifier = ActionModifier(self.action_manager, self.stream_id)
         self.enable_planner = global_config.normal_chat.enable_planner  # 从配置中读取是否启用planner
 
         # 记录最近的回复内容，每项包含: {time, user_message, response, is_mentioned, is_reference_reply}
@@ -569,8 +568,8 @@ class NormalChat:
         available_actions = None
         if self.enable_planner:
             try:
-                await self.action_modifier.modify_actions_for_normal_chat(
-                    self.chat_stream, self.recent_replies, message.processed_plain_text
+                await self.action_modifier.modify_actions(
+                    mode="normal", message_content=message.processed_plain_text
                 )
                 available_actions = self.action_manager.get_using_actions_for_mode("normal")
             except Exception as e:
@@ -1003,3 +1002,29 @@ class NormalChat:
         except Exception as e:
             logger.error(f"[{self.stream_name}] 清理思考消息 {thinking_id} 时出错: {e}")
 
+
+def get_recent_message_stats(minutes: int = 30, chat_id: str = None) -> dict:
+    """
+    Args:
+        minutes (int): 检索的分钟数，默认30分钟
+        chat_id (str, optional): 指定的chat_id，仅统计该chat下的消息。为None时统计全部。
+    Returns:
+        dict: {"bot_reply_count": int, "total_message_count": int}
+    """
+
+    now = time.time()
+    start_time = now - minutes * 60
+    bot_id = global_config.bot.qq_account
+
+    filter_base = {"time": {"$gte": start_time}}
+    if chat_id is not None:
+        filter_base["chat_id"] = chat_id
+
+    # 总消息数
+    total_message_count = count_messages(filter_base)
+    # bot自身回复数
+    bot_filter = filter_base.copy()
+    bot_filter["user_id"] = bot_id
+    bot_reply_count = count_messages(bot_filter)
+
+    return {"bot_reply_count": bot_reply_count, "total_message_count": total_message_count}

src/chat/normal_chat/normal_chat_action_modifier.py

@@ -1,403 +0,0 @@
-from typing import List, Any, Dict
-from src.common.logger import get_logger
-from src.chat.focus_chat.planners.action_manager import ActionManager
-from src.chat.utils.chat_message_builder import build_readable_messages, get_raw_msg_before_timestamp_with_chat
-from src.config.config import global_config
-import random
-import time
-import asyncio
-
-logger = get_logger("normal_chat_action_modifier")
-
-
-class NormalChatActionModifier:
-    """Normal Chat动作修改器
-
-    负责根据Normal Chat的上下文和状态动态调整可用的动作集合
-    实现与Focus Chat类似的动作激活策略，但将LLM_JUDGE转换为概率激活以提升性能
-    """
-
-    def __init__(self, action_manager: ActionManager, stream_id: str, stream_name: str):
-        """初始化动作修改器"""
-        self.action_manager = action_manager
-        self.stream_id = stream_id
-        self.stream_name = stream_name
-        self.log_prefix = f"[{stream_name}]动作修改器"
-
-        # 缓存所有注册的动作
-        self.all_actions = self.action_manager.get_registered_actions()
-
-    async def modify_actions_for_normal_chat(
-        self,
-        chat_stream,
-        recent_replies: List[dict],
-        message_content: str,
-        **kwargs: Any,
-    ):
-        """为Normal Chat修改可用动作集合
-
-        实现动作激活策略：
-        1. 基于关联类型的动态过滤
-        2. 基于激活类型的智能判定（LLM_JUDGE转为概率激活）
-
-        Args:
-            chat_stream: 聊天流对象
-            recent_replies: 最近的回复记录
-            message_content: 当前消息内容
-            **kwargs: 其他参数
-        """
-
-        reasons = []
-        merged_action_changes = {"add": [], "remove": []}
-        type_mismatched_actions = []  # 在外层定义避免作用域问题
-
-        self.action_manager.restore_default_actions()
-
-        # 第一阶段：基于关联类型的动态过滤
-        if chat_stream:
-            chat_context = chat_stream.context if hasattr(chat_stream, "context") else None
-            if chat_context:
-                # 获取Normal模式下的可用动作（已经过滤了mode_enable）
-                current_using_actions = self.action_manager.get_using_actions_for_mode("normal")
-                # print(f"current_using_actions: {current_using_actions}")
-                for action_name in current_using_actions.keys():
-                    if action_name in self.all_actions:
-                        data = self.all_actions[action_name]
-                        if data.get("associated_types"):
-                            if not chat_context.check_types(data["associated_types"]):
-                                type_mismatched_actions.append(action_name)
-                                logger.debug(f"{self.log_prefix} 动作 {action_name} 关联类型不匹配，移除该动作")
-
-                if type_mismatched_actions:
-                    merged_action_changes["remove"].extend(type_mismatched_actions)
-                    reasons.append(f"移除{type_mismatched_actions}(关联类型不匹配)")
-
-        # 第二阶段：应用激活类型判定
-        # 构建聊天内容 - 使用与planner一致的方式
-        chat_content = ""
-        if chat_stream and hasattr(chat_stream, "stream_id"):
-            try:
-                # 获取消息历史，使用与normal_chat_planner相同的方法
-                message_list_before_now = get_raw_msg_before_timestamp_with_chat(
-                    chat_id=chat_stream.stream_id,
-                    timestamp=time.time(),
-                    limit=global_config.chat.max_context_size,  # 使用相同的配置
-                )
-
-                # 构建可读的聊天上下文
-                chat_content = build_readable_messages(
-                    message_list_before_now,
-                    replace_bot_name=True,
-                    merge_messages=False,
-                    timestamp_mode="relative",
-                    read_mark=0.0,
-                    show_actions=True,
-                )
-
-                logger.debug(f"{self.log_prefix} 成功构建聊天内容，长度: {len(chat_content)}")
-
-            except Exception as e:
-                logger.warning(f"{self.log_prefix} 构建聊天内容失败: {e}")
-                chat_content = ""
-
-        # 获取当前Normal模式下的动作集进行激活判定
-        current_actions = self.action_manager.get_using_actions_for_mode("normal")
-
-        # print(f"current_actions: {current_actions}")
-        # print(f"chat_content: {chat_content}")
-        final_activated_actions = await self._apply_normal_activation_filtering(
-            current_actions, chat_content, message_content, recent_replies
-        )
-        # print(f"final_activated_actions: {final_activated_actions}")
-
-        # 统一处理所有需要移除的动作，避免重复移除
-        all_actions_to_remove = set()  # 使用set避免重复
-
-        # 添加关联类型不匹配的动作
-        if type_mismatched_actions:
-            all_actions_to_remove.update(type_mismatched_actions)
-
-        # 添加激活类型判定未通过的动作
-        for action_name in current_actions.keys():
-            if action_name not in final_activated_actions:
-                all_actions_to_remove.add(action_name)
-
-        # 统计移除原因（避免重复）
-        activation_failed_actions = [
-            name
-            for name in current_actions.keys()
-            if name not in final_activated_actions and name not in type_mismatched_actions
-        ]
-        if activation_failed_actions:
-            reasons.append(f"移除{activation_failed_actions}(激活类型判定未通过)")
-
-        # 统一执行移除操作
-        for action_name in all_actions_to_remove:
-            success = self.action_manager.remove_action_from_using(action_name)
-            if success:
-                logger.debug(f"{self.log_prefix} 移除动作: {action_name}")
-            else:
-                logger.debug(f"{self.log_prefix} 动作 {action_name} 已经不在使用集中，跳过移除")
-
-        # 应用动作添加（如果有的话）
-        for action_name in merged_action_changes["add"]:
-            if action_name in self.all_actions:
-                success = self.action_manager.add_action_to_using(action_name)
-                if success:
-                    logger.debug(f"{self.log_prefix} 添加动作: {action_name}")
-
-        # 记录变更原因
-        if reasons:
-            logger.info(f"{self.log_prefix} 动作调整完成: {' | '.join(reasons)}")
-
-        # 获取最终的Normal模式可用动作并记录
-        final_actions = self.action_manager.get_using_actions_for_mode("normal")
-        logger.debug(f"{self.log_prefix} 当前Normal模式可用动作: {list(final_actions.keys())}")
-
-    async def _apply_normal_activation_filtering(
-        self,
-        actions_with_info: Dict[str, Any],
-        chat_content: str = "",
-        message_content: str = "",
-        recent_replies: List[dict] = None,
-    ) -> Dict[str, Any]:
-        """
-        应用Normal模式的激活类型过滤逻辑
-
-        与Focus模式的区别：
-        1. LLM_JUDGE类型转换为概率激活（避免LLM调用）
-        2. RANDOM类型保持概率激活
-        3. KEYWORD类型保持关键词匹配
-        4. ALWAYS类型直接激活
-
-        Args:
-            actions_with_info: 带完整信息的动作字典
-            chat_content: 聊天内容
-            message_content: 当前消息内容
-            recent_replies: 最近的回复记录列表
-
-        Returns:
-            Dict[str, Any]: 过滤后激活的actions字典
-        """
-        activated_actions = {}
-
-        # 分类处理不同激活类型的actions
-        always_actions = {}
-        random_actions = {}
-        keyword_actions = {}
-        llm_judge_actions = {}
-
-        for action_name, action_info in actions_with_info.items():
-            # 使用normal_activation_type
-            activation_type = action_info.get("normal_activation_type", "always")
-
-            # 现在统一是字符串格式的激活类型值
-            if activation_type == "always":
-                always_actions[action_name] = action_info
-            elif activation_type == "random":
-                random_actions[action_name] = action_info
-            elif activation_type == "llm_judge":
-                llm_judge_actions[action_name] = action_info
-            elif activation_type == "keyword":
-                keyword_actions[action_name] = action_info
-            else:
-                logger.warning(f"{self.log_prefix}未知的激活类型: {activation_type}，跳过处理")
-
-        # 1. 处理ALWAYS类型（直接激活）
-        for action_name, action_info in always_actions.items():
-            activated_actions[action_name] = action_info
-            logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: ALWAYS类型直接激活")
-
-        # 2. 处理RANDOM类型（概率激活）
-        for action_name, action_info in random_actions.items():
-            probability = action_info.get("random_activation_probability", ActionManager.DEFAULT_RANDOM_PROBABILITY)
-            should_activate = random.random() < probability
-            if should_activate:
-                activated_actions[action_name] = action_info
-                logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: RANDOM类型触发（概率{probability}）")
-            else:
-                logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: RANDOM类型未触发（概率{probability}）")
-
-        # 3. 处理KEYWORD类型（关键词匹配）
-        for action_name, action_info in keyword_actions.items():
-            should_activate = self._check_keyword_activation(action_name, action_info, chat_content, message_content)
-            if should_activate:
-                activated_actions[action_name] = action_info
-                keywords = action_info.get("activation_keywords", [])
-                logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: KEYWORD类型匹配关键词（{keywords}）")
-            else:
-                keywords = action_info.get("activation_keywords", [])
-                logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: KEYWORD类型未匹配关键词（{keywords}）")
-
-        # 4. 处理LLM_JUDGE类型（并行判定）
-        if llm_judge_actions:
-            # 直接并行处理所有LLM判定actions
-            llm_results = await self._process_llm_judge_actions_parallel(
-                llm_judge_actions,
-                chat_content,
-            )
-
-            # 添加激活的LLM判定actions
-            for action_name, should_activate in llm_results.items():
-                if should_activate:
-                    activated_actions[action_name] = llm_judge_actions[action_name]
-                    logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: LLM_JUDGE类型判定通过")
-                else:
-                    logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: LLM_JUDGE类型判定未通过")
-
-
-
-        logger.debug(f"{self.log_prefix}Normal模式激活类型过滤完成: {list(activated_actions.keys())}")
-        return activated_actions
-
-    def _check_keyword_activation(
-        self,
-        action_name: str,
-        action_info: Dict[str, Any],
-        chat_content: str = "",
-        message_content: str = "",
-    ) -> bool:
-        """
-        检查是否匹配关键词触发条件
-
-        Args:
-            action_name: 动作名称
-            action_info: 动作信息
-            chat_content: 聊天内容（已经是格式化后的可读消息）
-
-        Returns:
-            bool: 是否应该激活此action
-        """
-
-        activation_keywords = action_info.get("activation_keywords", [])
-        case_sensitive = action_info.get("keyword_case_sensitive", False)
-
-        if not activation_keywords:
-            logger.warning(f"{self.log_prefix}动作 {action_name} 设置为关键词触发但未配置关键词")
-            return False
-
-        # 使用构建好的聊天内容作为检索文本
-        search_text = chat_content + message_content
-
-        # 如果不区分大小写，转换为小写
-        if not case_sensitive:
-            search_text = search_text.lower()
-
-        # 检查每个关键词
-        matched_keywords = []
-        for keyword in activation_keywords:
-            check_keyword = keyword if case_sensitive else keyword.lower()
-            if check_keyword in search_text:
-                matched_keywords.append(keyword)
-
-        # print(f"search_text: {search_text}")
-        # print(f"activation_keywords: {activation_keywords}")
-
-        if matched_keywords:
-            logger.debug(f"{self.log_prefix}动作 {action_name} 匹配到关键词: {matched_keywords}")
-            return True
-        else:
-            logger.debug(f"{self.log_prefix}动作 {action_name} 未匹配到任何关键词: {activation_keywords}")
-            return False
-        
-        
-    async def _process_llm_judge_actions_parallel(
-        self,
-        llm_judge_actions: Dict[str, Any],
-        chat_content: str = "",
-    ) -> Dict[str, bool]:
-        """
-        并行处理LLM判定actions，支持智能缓存
-
-        Args:
-            llm_judge_actions: 需要LLM判定的actions
-            chat_content: 聊天内容
-
-        Returns:
-            Dict[str, bool]: action名称到激活结果的映射
-        """
-
-        # 生成当前上下文的哈希值
-        current_context_hash = self._generate_context_hash(chat_content)
-        current_time = time.time()
-
-        results = {}
-        tasks_to_run = {}
-
-        # 检查缓存
-        for action_name, action_info in llm_judge_actions.items():
-            cache_key = f"{action_name}_{current_context_hash}"
-
-            # 检查是否有有效的缓存
-            if (
-                cache_key in self._llm_judge_cache
-                and current_time - self._llm_judge_cache[cache_key]["timestamp"] < self._cache_expiry_time
-            ):
-                results[action_name] = self._llm_judge_cache[cache_key]["result"]
-                logger.debug(
-                    f"{self.log_prefix}使用缓存结果 {action_name}: {'激活' if results[action_name] else '未激活'}"
-                )
-            else:
-                # 需要进行LLM判定
-                tasks_to_run[action_name] = action_info
-
-        # 如果有需要运行的任务，并行执行
-        if tasks_to_run:
-            logger.debug(f"{self.log_prefix}并行执行LLM判定，任务数: {len(tasks_to_run)}")
-
-            # 创建并行任务
-            tasks = []
-            task_names = []
-
-            for action_name, action_info in tasks_to_run.items():
-                task = self._llm_judge_action(
-                    action_name,
-                    action_info,
-                    chat_content,
-                )
-                tasks.append(task)
-                task_names.append(action_name)
-
-            # 并行执行所有任务
-            try:
-                task_results = await asyncio.gather(*tasks, return_exceptions=True)
-
-                # 处理结果并更新缓存
-                for _, (action_name, result) in enumerate(zip(task_names, task_results)):
-                    if isinstance(result, Exception):
-                        logger.error(f"{self.log_prefix}LLM判定action {action_name} 时出错: {result}")
-                        results[action_name] = False
-                    else:
-                        results[action_name] = result
-
-                        # 更新缓存
-                        cache_key = f"{action_name}_{current_context_hash}"
-                        self._llm_judge_cache[cache_key] = {"result": result, "timestamp": current_time}
-
-                logger.debug(f"{self.log_prefix}并行LLM判定完成，耗时: {time.time() - current_time:.2f}s")
-
-            except Exception as e:
-                logger.error(f"{self.log_prefix}并行LLM判定失败: {e}")
-                # 如果并行执行失败，为所有任务返回False
-                for action_name in tasks_to_run.keys():
-                    results[action_name] = False
-
-        # 清理过期缓存
-        self._cleanup_expired_cache(current_time)
-
-        return results
-
-    def get_available_actions_count(self) -> int:
-        """获取当前可用动作数量（排除默认的no_action）"""
-        current_actions = self.action_manager.get_using_actions_for_mode("normal")
-        # 排除no_action（如果存在）
-        filtered_actions = {k: v for k, v in current_actions.items() if k != "no_action"}
-        return len(filtered_actions)
-
-    def should_skip_planning(self) -> bool:
-        """判断是否应该跳过规划过程"""
-        available_count = self.get_available_actions_count()
-        if available_count == 0:
-            logger.debug(f"{self.log_prefix} 没有可用动作，跳过规划")
-            return True
-        return False

src/chat/normal_chat/normal_chat_utils.py

@@ -1,30 +0,0 @@
-import time
-from src.config.config import global_config
-from src.common.message_repository import count_messages
-
-
-def get_recent_message_stats(minutes: int = 30, chat_id: str = None) -> dict:
-    """
-    Args:
-        minutes (int): 检索的分钟数，默认30分钟
-        chat_id (str, optional): 指定的chat_id，仅统计该chat下的消息。为None时统计全部。
-    Returns:
-        dict: {"bot_reply_count": int, "total_message_count": int}
-    """
-
-    now = time.time()
-    start_time = now - minutes * 60
-    bot_id = global_config.bot.qq_account
-
-    filter_base = {"time": {"$gte": start_time}}
-    if chat_id is not None:
-        filter_base["chat_id"] = chat_id
-
-    # 总消息数
-    total_message_count = count_messages(filter_base)
-    # bot自身回复数
-    bot_filter = filter_base.copy()
-    bot_filter["user_id"] = bot_id
-    bot_reply_count = count_messages(bot_filter)
-
-    return {"bot_reply_count": bot_reply_count, "total_message_count": total_message_count}

src/chat/planner_actions/action_manager.py

@@ -292,10 +292,6 @@ class ActionManager:
         )
         self._using_actions = self._default_actions.copy()
 
-    def restore_default_actions(self) -> None:
-        """恢复默认动作集到使用集"""
-        self._using_actions = self._default_actions.copy()
-
     def add_system_action_if_needed(self, action_name: str) -> bool:
         """
         根据需要添加系统动作到使用集

src/chat/planner_actions/action_modifier.py

@@ -10,7 +10,8 @@ import random
 import asyncio
 import hashlib
 import time
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.action_manager import ActionManager
+from src.chat.utils.chat_message_builder import get_raw_msg_before_timestamp_with_chat, build_readable_messages
 
 logger = get_logger("action_manager")
 
@@ -23,12 +24,13 @@ class ActionModifier:
     支持并行判定和智能缓存优化。
     """
 
-    log_prefix = "动作处理"
-
-    def __init__(self, action_manager: ActionManager):
+    def __init__(self, action_manager: ActionManager, chat_id: str):
         """初始化动作处理器"""
+        self.chat_id = chat_id
+        self.chat_stream = get_chat_manager().get_stream(self.chat_id)
+        self.log_prefix = f"[{get_chat_manager().get_stream_name(self.chat_id) or self.chat_id}]"
+
         self.action_manager = action_manager
-        self.all_actions = self.action_manager.get_using_actions_for_mode("focus")
 
         # 用于LLM判定的小模型
         self.llm_judge = LLMRequest(
@@ -43,11 +45,12 @@ class ActionModifier:
 
     async def modify_actions(
         self,
+        mode: str = "focus",
         observations: Optional[List[Observation]] = None,
-        **kwargs: Any,
+        message_content: str = "",
     ):
         """
-        完整的动作修改流程，整合传统观察处理和新的激活类型判定
+        动作修改流程，整合传统观察处理和新的激活类型判定
 
         这个方法处理完整的动作管理流程：
         1. 基于观察的传统动作修改（循环历史分析、类型匹配等）
@@ -57,230 +60,156 @@ class ActionModifier:
         """
         logger.debug(f"{self.log_prefix}开始完整动作修改流程")
 
+        removals_s1 = []
+        removals_s2 = []
+        
+        self.action_manager.restore_actions()
+        all_actions = self.action_manager.get_using_actions_for_mode(mode)
+        
+        message_list_before_now_half = get_raw_msg_before_timestamp_with_chat(
+            chat_id=self.chat_stream.stream_id,
+            timestamp=time.time(),
+            limit=int(global_config.chat.max_context_size * 0.5),
+        )
+        chat_content = build_readable_messages(
+            message_list_before_now_half,
+            replace_bot_name=True,
+            merge_messages=False,
+            timestamp_mode="relative",
+            read_mark=0.0,
+            show_actions=True,
+        )
+        
+        if message_content:
+            chat_content = chat_content + "\n" + f"现在，最新的消息是：{message_content}"
+
         # === 第一阶段：传统观察处理 ===
-        chat_content = None
-
         if observations:
-            hfc_obs = None
-            chat_obs = None
-
-            # 收集所有观察对象
             for obs in observations:
                 if isinstance(obs, HFCloopObservation):
-                    hfc_obs = obs
-                if isinstance(obs, ChattingObservation):
-                    chat_obs = obs
-                    chat_content = obs.talking_message_str_truncate_short
+                    # 获取适用于FOCUS模式的动作
+                    removals_from_loop = await self.analyze_loop_actions(obs)
+                    if removals_from_loop:
+                        removals_s1.extend(removals_from_loop)
 
-            # 合并所有动作变更
-            merged_action_changes = {"add": [], "remove": []}
-            reasons = []
+        # 检查动作的关联类型
+        chat_context = self.chat_stream.context
+        type_mismatched_actions = self._check_action_associated_types(all_actions, chat_context)
 
-            # 处理HFCloopObservation - 传统的循环历史分析
-            if hfc_obs:
-                obs = hfc_obs
-                # 获取适用于FOCUS模式的动作
-                all_actions = self.all_actions
-                action_changes = await self.analyze_loop_actions(obs)
-                if action_changes["add"] or action_changes["remove"]:
-                    # 合并动作变更
-                    merged_action_changes["add"].extend(action_changes["add"])
-                    merged_action_changes["remove"].extend(action_changes["remove"])
-                    reasons.append("基于循环历史分析")
+        if type_mismatched_actions:
+            removals_s1.extend(type_mismatched_actions)
 
-                    # 详细记录循环历史分析的变更原因
-                    for action_name in action_changes["add"]:
-                        logger.info(f"{self.log_prefix}添加动作: {action_name}，原因: 循环历史分析建议添加")
-                    for action_name in action_changes["remove"]:
-                        logger.info(f"{self.log_prefix}移除动作: {action_name}，原因: 循环历史分析建议移除")
+        # 应用第一阶段的移除
+        for action_name, reason in removals_s1:
+            self.action_manager.remove_action_from_using(action_name)
+            logger.debug(f"{self.log_prefix}阶段一移除动作: {action_name}，原因: {reason}")
 
-            # 处理ChattingObservation - 传统的类型匹配检查
-            if chat_obs:
-                # 检查动作的关联类型
-                chat_context = get_chat_manager().get_stream(chat_obs.chat_id).context
-                type_mismatched_actions = []
-
-                for action_name in all_actions.keys():
-                    data = all_actions[action_name]
-                    if data.get("associated_types"):
-                        if not chat_context.check_types(data["associated_types"]):
-                            type_mismatched_actions.append(action_name)
-                            associated_types_str = ", ".join(data["associated_types"])
-                            logger.info(
-                                f"{self.log_prefix}移除动作: {action_name}，原因: 关联类型不匹配（需要: {associated_types_str}）"
-                            )
-
-                if type_mismatched_actions:
-                    # 合并到移除列表中
-                    merged_action_changes["remove"].extend(type_mismatched_actions)
-                    reasons.append("基于关联类型检查")
-
-            # 应用传统的动作变更到ActionManager
-            for action_name in merged_action_changes["add"]:
-                if action_name in self.action_manager.get_registered_actions():
-                    self.action_manager.add_action_to_using(action_name)
-                    logger.debug(f"{self.log_prefix}应用添加动作: {action_name}，原因集合: {reasons}")
-
-            for action_name in merged_action_changes["remove"]:
-                self.action_manager.remove_action_from_using(action_name)
-                logger.debug(f"{self.log_prefix}应用移除动作: {action_name}，原因集合: {reasons}")
-
-            logger.info(
-                f"{self.log_prefix}传统动作修改完成，当前使用动作: {list(self.action_manager.get_using_actions().keys())}"
-            )
-
-        # 注释：已移除exit_focus_chat动作，现在由no_reply动作处理频率检测退出专注模式
 
         # === 第二阶段：激活类型判定 ===
-        # 如果提供了聊天上下文，则进行激活类型判定
         if chat_content is not None:
             logger.debug(f"{self.log_prefix}开始激活类型判定阶段")
 
-            # 获取当前使用的动作集（经过第一阶段处理，且适用于FOCUS模式）
-            current_using_actions = self.action_manager.get_using_actions()
-            all_registered_actions = self.action_manager.get_registered_actions()
-
-            # 构建完整的动作信息
-            current_actions_with_info = {}
-            for action_name in current_using_actions.keys():
-                if action_name in all_registered_actions:
-                    current_actions_with_info[action_name] = all_registered_actions[action_name]
-                else:
-                    logger.warning(f"{self.log_prefix}使用中的动作 {action_name} 未在已注册动作中找到")
-
-            # 应用激活类型判定
-            final_activated_actions = await self._apply_activation_type_filtering(
-                current_actions_with_info,
+            # 获取当前使用的动作集（经过第一阶段处理）
+            current_using_actions = self.action_manager.get_using_actions_for_mode(mode)
+            
+            # 获取因激活类型判定而需要移除的动作
+            removals_s2 = await self._get_deactivated_actions_by_type(
+                current_using_actions,
+                mode,
                 chat_content,
             )
 
-            # 更新ActionManager，移除未激活的动作
-            actions_to_remove = []
-            removal_reasons = {}
-
-            for action_name in current_using_actions.keys():
-                if action_name not in final_activated_actions:
-                    actions_to_remove.append(action_name)
-                    # 确定移除原因
-                    if action_name in all_registered_actions:
-                        action_info = all_registered_actions[action_name]
-                        activation_type = action_info.get("focus_activation_type", "always")
-
-                        # 处理字符串格式的激活类型值
-                        if activation_type == "random":
-                            probability = action_info.get("random_probability", 0.3)
-                            removal_reasons[action_name] = f"RANDOM类型未触发（概率{probability}）"
-                        elif activation_type == "llm_judge":
-                            removal_reasons[action_name] = "LLM判定未激活"
-                        elif activation_type == "keyword":
-                            keywords = action_info.get("activation_keywords", [])
-                            removal_reasons[action_name] = f"关键词未匹配（关键词: {keywords}）"
-                        else:
-                            removal_reasons[action_name] = "激活判定未通过"
-                    else:
-                        removal_reasons[action_name] = "动作信息不完整"
-
-            for action_name in actions_to_remove:
+            # 应用第二阶段的移除
+            for action_name, reason in removals_s2:
                 self.action_manager.remove_action_from_using(action_name)
-                reason = removal_reasons.get(action_name, "未知原因")
-                logger.info(f"{self.log_prefix}移除动作: {action_name}，原因: {reason}")
-
-            # 注释：已完全移除exit_focus_chat动作
-
-            logger.info(f"{self.log_prefix}激活类型判定完成，最终可用动作: {list(final_activated_actions.keys())}")
+                logger.debug(f"{self.log_prefix}阶段二移除动作: {action_name}，原因: {reason}")
+        
+        # === 统一日志记录 ===
+        all_removals = removals_s1 + removals_s2
+        if all_removals:
+            removals_summary = " | ".join([f"{name}({reason})" for name, reason in all_removals])
 
         logger.info(
-            f"{self.log_prefix}完整动作修改流程结束，最终动作集: {list(self.action_manager.get_using_actions().keys())}"
+            f"{self.log_prefix}{mode}模式动作修改流程结束，最终可用动作: {list(self.action_manager.get_using_actions_for_mode(mode).keys())}||移除记录: {removals_summary}"
         )
 
-    async def _apply_activation_type_filtering(
+    def _check_action_associated_types(self, all_actions, chat_context):
+        type_mismatched_actions = []
+        for action_name, data in all_actions.items():
+            if data.get("associated_types"):
+                if not chat_context.check_types(data["associated_types"]):
+                    associated_types_str = ", ".join(data["associated_types"])
+                    reason = f"适配器不支持（需要: {associated_types_str}）"
+                    type_mismatched_actions.append((action_name, reason))
+                    logger.debug(
+                        f"{self.log_prefix}决定移除动作: {action_name}，原因: {reason}"
+                    )
+        return type_mismatched_actions
+    
+    async def _get_deactivated_actions_by_type(
         self,
         actions_with_info: Dict[str, Any],
+        mode: str = "focus",
         chat_content: str = "",
-    ) -> Dict[str, Any]:
+    ) -> List[tuple[str, str]]:
         """
-        应用激活类型过滤逻辑，支持四种激活类型的并行处理
+        根据激活类型过滤，返回需要停用的动作列表及原因
 
         Args:
             actions_with_info: 带完整信息的动作字典
             chat_content: 聊天内容
 
         Returns:
-            Dict[str, Any]: 过滤后激活的actions字典
+            List[Tuple[str, str]]: 需要停用的 (action_name, reason) 元组列表
         """
-        activated_actions = {}
+        deactivated_actions = []
 
         # 分类处理不同激活类型的actions
-        always_actions = {}
-        random_actions = {}
         llm_judge_actions = {}
-        keyword_actions = {}
+        
+        actions_to_check = list(actions_with_info.items())
+        random.shuffle(actions_to_check)
 
-        for action_name, action_info in actions_with_info.items():
-            activation_type = action_info.get("focus_activation_type", "always")
+        for action_name, action_info in actions_to_check:
+            activation_type = f"{mode}_activation_type"
+            activation_type = action_info.get(activation_type, "always")
 
-            # print(f"action_name: {action_name}, activation_type: {activation_type}")
-
-            # 现在统一是字符串格式的激活类型值
             if activation_type == "always":
-                always_actions[action_name] = action_info
+                continue  # 总是激活，无需处理
+
             elif activation_type == "random":
-                random_actions[action_name] = action_info
+                probability = action_info.get("random_activation_probability", ActionManager.DEFAULT_RANDOM_PROBABILITY)
+                if not (random.random() < probability):
+                    reason = f"RANDOM类型未触发（概率{probability}）"
+                    deactivated_actions.append((action_name, reason))
+                    logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: {reason}")
+
+            elif activation_type == "keyword":
+                if not self._check_keyword_activation(action_name, action_info, chat_content):
+                    keywords = action_info.get("activation_keywords", [])
+                    reason = f"关键词未匹配（关键词: {keywords}）"
+                    deactivated_actions.append((action_name, reason))
+                    logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: {reason}")
+
             elif activation_type == "llm_judge":
                 llm_judge_actions[action_name] = action_info
-            elif activation_type == "keyword":
-                keyword_actions[action_name] = action_info
+            
             else:
                 logger.warning(f"{self.log_prefix}未知的激活类型: {activation_type}，跳过处理")
 
-        # 1. 处理ALWAYS类型（直接激活）
-        for action_name, action_info in always_actions.items():
-            activated_actions[action_name] = action_info
-            logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: ALWAYS类型直接激活")
-
-        # 2. 处理RANDOM类型
-        for action_name, action_info in random_actions.items():
-            probability = action_info.get("random_activation_probability", ActionManager.DEFAULT_RANDOM_PROBABILITY)
-            should_activate = random.random() < probability
-            if should_activate:
-                activated_actions[action_name] = action_info
-                logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: RANDOM类型触发（概率{probability}）")
-            else:
-                logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: RANDOM类型未触发（概率{probability}）")
-
-        # 3. 处理KEYWORD类型（快速判定）
-        for action_name, action_info in keyword_actions.items():
-            should_activate = self._check_keyword_activation(
-                action_name,
-                action_info,
-                chat_content,
-            )
-            if should_activate:
-                activated_actions[action_name] = action_info
-                keywords = action_info.get("activation_keywords", [])
-                logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: KEYWORD类型匹配关键词（{keywords}）")
-            else:
-                keywords = action_info.get("activation_keywords", [])
-                logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: KEYWORD类型未匹配关键词（{keywords}）")
-
-        # 4. 处理LLM_JUDGE类型（并行判定）
+        # 并行处理LLM_JUDGE类型
         if llm_judge_actions:
-            # 直接并行处理所有LLM判定actions
             llm_results = await self._process_llm_judge_actions_parallel(
                 llm_judge_actions,
                 chat_content,
             )
-
-            # 添加激活的LLM判定actions
             for action_name, should_activate in llm_results.items():
-                if should_activate:
-                    activated_actions[action_name] = llm_judge_actions[action_name]
-                    logger.debug(f"{self.log_prefix}激活动作: {action_name}，原因: LLM_JUDGE类型判定通过")
-                else:
-                    logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: LLM_JUDGE类型判定未通过")
+                if not should_activate:
+                    reason = "LLM判定未激活"
+                    deactivated_actions.append((action_name, reason))
+                    logger.debug(f"{self.log_prefix}未激活动作: {action_name}，原因: {reason}")
 
-        logger.debug(f"{self.log_prefix}激活类型过滤完成: {list(activated_actions.keys())}")
-        return activated_actions
+        return deactivated_actions
 
     async def process_actions_for_planner(
         self, observed_messages_str: str = "", chat_context: Optional[str] = None, extra_context: Optional[str] = None
@@ -538,22 +467,19 @@ class ActionModifier:
             logger.debug(f"{self.log_prefix}动作 {action_name} 未匹配到任何关键词: {activation_keywords}")
             return False
 
-    async def analyze_loop_actions(self, obs: HFCloopObservation) -> Dict[str, List[str]]:
-        """分析最近的循环内容并决定动作的增减
+    async def analyze_loop_actions(self, obs: HFCloopObservation) -> List[tuple[str, str]]:
+        """分析最近的循环内容并决定动作的移除
 
         Returns:
-            Dict[str, List[str]]: 包含要增加和删除的动作
-                {
-                    "add": ["action1", "action2"],
-                    "remove": ["action3"]
-                }
+            List[Tuple[str, str]]: 包含要删除的动作及原因的元组列表
+                [("action3", "some reason")]
         """
-        result = {"add": [], "remove": []}
+        removals = []
 
         # 获取最近10次循环
         recent_cycles = obs.history_loop[-10:] if len(obs.history_loop) > 10 else obs.history_loop
         if not recent_cycles:
-            return result
+            return removals
 
         reply_sequence = []  # 记录最近的动作序列
 
@@ -584,36 +510,39 @@ class ActionModifier:
         # 根据最近的reply情况决定是否移除reply动作
         if len(last_max_reply_num) >= max_reply_num and all(last_max_reply_num):
             # 如果最近max_reply_num次都是reply，直接移除
-            result["remove"].append("reply")
+            reason = f"连续回复过多（最近{len(last_max_reply_num)}次全是reply，超过阈值{max_reply_num}）"
+            removals.append(("reply", reason))
             # reply_count = len(last_max_reply_num) - no_reply_count
-            logger.info(
-                f"{self.log_prefix}移除reply动作，原因: 连续回复过多（最近{len(last_max_reply_num)}次全是reply，超过阈值{max_reply_num}）"
-            )
         elif len(last_max_reply_num) >= sec_thres_reply_num and all(last_max_reply_num[-sec_thres_reply_num:]):
             # 如果最近sec_thres_reply_num次都是reply，40%概率移除
             removal_probability = 0.4 / global_config.focus_chat.consecutive_replies
             if random.random() < removal_probability:
-                result["remove"].append("reply")
-                logger.info(
-                    f"{self.log_prefix}移除reply动作，原因: 连续回复较多（最近{sec_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，触发移除）"
-                )
-            else:
-                logger.debug(
-                    f"{self.log_prefix}连续回复检测：最近{sec_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，未触发"
-                )
+                reason = f"连续回复较多（最近{sec_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，触发移除）"
+                removals.append(("reply", reason))
         elif len(last_max_reply_num) >= one_thres_reply_num and all(last_max_reply_num[-one_thres_reply_num:]):
             # 如果最近one_thres_reply_num次都是reply，20%概率移除
             removal_probability = 0.2 / global_config.focus_chat.consecutive_replies
             if random.random() < removal_probability:
-                result["remove"].append("reply")
-                logger.info(
-                    f"{self.log_prefix}移除reply动作，原因: 连续回复检测（最近{one_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，触发移除）"
-                )
-            else:
-                logger.debug(
-                    f"{self.log_prefix}连续回复检测：最近{one_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，未触发"
-                )
+                reason = f"连续回复检测（最近{one_thres_reply_num}次全是reply，{removal_probability:.2f}概率移除，触发移除）"
+                removals.append(("reply", reason))
         else:
             logger.debug(f"{self.log_prefix}连续回复检测：无需移除reply动作，最近回复模式正常")
 
-        return result
+        return removals
+
+
+
+    def get_available_actions_count(self) -> int:
+        """获取当前可用动作数量（排除默认的no_action）"""
+        current_actions = self.action_manager.get_using_actions_for_mode("normal")
+        # 排除no_action（如果存在）
+        filtered_actions = {k: v for k, v in current_actions.items() if k != "no_action"}
+        return len(filtered_actions)
+
+    def should_skip_planning(self) -> bool:
+        """判断是否应该跳过规划过程"""
+        available_count = self.get_available_actions_count()
+        if available_count == 0:
+            logger.debug(f"{self.log_prefix} 没有可用动作，跳过规划")
+            return True
+        return False

src/chat/planner_actions/planner_focus.py

@@ -9,9 +9,8 @@ from src.chat.focus_chat.info.obs_info import ObsInfo
 from src.chat.focus_chat.info.action_info import ActionInfo
 from src.common.logger import get_logger
 from src.chat.utils.prompt_builder import Prompt, global_prompt_manager
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.action_manager import ActionManager
 from json_repair import repair_json
-from src.chat.focus_chat.planners.base_planner import BasePlanner
 from src.chat.heart_flow.utils_chat import get_chat_type_and_target_info
 from datetime import datetime
 
@@ -69,9 +68,10 @@ def init_prompt():
     )
 
 
-class ActionPlanner(BasePlanner):
+class ActionPlanner:
     def __init__(self, log_prefix: str, action_manager: ActionManager):
-        super().__init__(log_prefix, action_manager)
+        self.log_prefix = log_prefix
+        self.action_manager = action_manager
         # LLM规划器配置
         self.planner_llm = LLMRequest(
             model=global_config.model.planner,
@@ -84,7 +84,7 @@ class ActionPlanner(BasePlanner):
         )
 
     async def plan(
-        self, all_plan_info: List[InfoBase], running_memorys: List[Dict[str, Any]], loop_start_time: float
+        self, all_plan_info: List[InfoBase],loop_start_time: float
     ) -> Dict[str, Any]:
         """
         规划器 (Planner): 使用LLM根据上下文决定做出什么动作。

src/chat/planner_actions/planner_normal.py

@@ -6,7 +6,7 @@ from src.config.config import global_config
 from src.common.logger import get_logger
 from src.chat.utils.prompt_builder import Prompt, global_prompt_manager
 from src.individuality.individuality import get_individuality
-from src.chat.focus_chat.planners.action_manager import ActionManager
+from src.chat.planner_actions.action_manager import ActionManager
 from src.chat.message_receive.message import MessageThinking
 from json_repair import repair_json
 from src.chat.utils.chat_message_builder import build_readable_messages, get_raw_msg_before_timestamp_with_chat

src/common/logger.py

@@ -340,7 +340,7 @@ MODULE_COLORS = {
     "memory": "\033[34m",
     "hfc": "\033[96m",
     "base_action": "\033[96m",
-    "action_manager": "\033[34m",
+    "action_manager": "\033[32m",
     # 关系系统
     "relation": "\033[38;5;201m",  # 深粉色
     # 聊天相关模块
@@ -414,7 +414,7 @@ MODULE_COLORS = {
     "confirm": "\033[1;93m",  # 黄色+粗体
     # 模型相关
     "model_utils": "\033[38;5;164m",  # 紫红色
-    
+    "relationship_fetcher": "\033[38;5;170m",  # 浅紫色
     "relationship_builder": "\033[38;5;117m",  # 浅蓝色
 }
 

src/config/official_configs.py

@@ -273,12 +273,6 @@ class MessageReceiveConfig(ConfigBase):
 class NormalChatConfig(ConfigBase):
     """普通聊天配置类"""
 
-    message_buffer: bool = False
-    """消息缓冲器"""
-
-    emoji_chance: float = 0.2
-    """发送表情包的基础概率"""
-
 
     willing_mode: str = "classical"
     """意愿模式"""
@@ -295,14 +289,6 @@ class NormalChatConfig(ConfigBase):
     enable_planner: bool = False
     """是否启用动作规划器"""
 
-    gather_timeout: int = 110  # planner和generator的并行执行超时时间
-    """planner和generator的并行执行超时时间"""
-
-    auto_focus_threshold: float = 1.0  # 自动切换到专注模式的阈值，值越大越难触发
-    """自动切换到专注模式的阈值，值越大越难触发"""
-
-    fatigue_talk_frequency: float = 0.2  # 疲劳模式下的基础对话频率 (条/分钟)
-    """疲劳模式下的基础对话频率 (条/分钟)"""
 
 
 @dataclass
@@ -362,6 +348,12 @@ class ToolConfig(ConfigBase):
 @dataclass
 class EmojiConfig(ConfigBase):
     """表情包配置类"""
+    
+    emoji_chance: float = 0.6
+    """发送表情包的基础概率"""
+
+    emoji_activate_type: str = "random"
+    """表情包激活类型，可选：random，llm，random下，表情包动作随机启用，llm下，表情包动作根据llm判断是否启用"""
 
     max_reg_num: int = 200
     """表情包最大注册数量"""

src/person_info/relationship_fetcher.py

@@ -142,7 +142,7 @@ class RelationshipFetcher:
 
                 # 检查是否返回了不需要查询的标志
                 if "none" in content_json:
-                    logger.info(f"{self.log_prefix} LLM判断当前不需要查询任何信息：{content_json.get('none', '')}")
+                    logger.debug(f"{self.log_prefix} LLM判断当前不需要查询任何信息：{content_json.get('none', '')}")
                     return None
 
                 info_type = content_json.get("info_type")

src/plugin_system/apis/emoji_api.py

@@ -31,7 +31,7 @@ async def get_by_description(description: str) -> Optional[Tuple[str, str, str]]
         Optional[Tuple[str, str, str]]: (base64编码, 表情包描述, 匹配的情感标签) 或 None
     """
     try:
-        logger.info(f"[EmojiAPI] 根据描述获取表情包: {description}")
+        logger.debug(f"[EmojiAPI] 根据描述获取表情包: {description}")
 
         emoji_manager = get_emoji_manager()
         emoji_result = await emoji_manager.get_emoji_for_text(description)
@@ -47,7 +47,7 @@ async def get_by_description(description: str) -> Optional[Tuple[str, str, str]]
             logger.error(f"[EmojiAPI] 无法将表情包文件转换为base64: {emoji_path}")
             return None
 
-        logger.info(f"[EmojiAPI] 成功获取表情包: {emoji_description}, 匹配情感: {matched_emotion}")
+        logger.debug(f"[EmojiAPI] 成功获取表情包: {emoji_description}, 匹配情感: {matched_emotion}")
         return emoji_base64, emoji_description, matched_emotion
 
     except Exception as e:

src/plugin_system/apis/send_api.py

@@ -116,7 +116,7 @@ async def _send_to_target(
         )
 
         if sent_msg:
-            logger.info(f"[SendAPI] 成功发送消息到 {stream_id}")
+            logger.debug(f"[SendAPI] 成功发送消息到 {stream_id}")
             return True
         else:
             logger.error("[SendAPI] 发送消息失败")

src/plugins/built_in/core_actions/emoji.py

@@ -18,7 +18,7 @@ class EmojiAction(BaseAction):
     """表情动作 - 发送表情包"""
 
     # 激活设置
-    focus_activation_type = ActionActivationType.LLM_JUDGE
+    focus_activation_type = ActionActivationType.RANDOM
     normal_activation_type = ActionActivationType.RANDOM
     mode_enable = ChatMode.ALL
     parallel_action = True

src/plugins/built_in/core_actions/plugin.py

@@ -180,8 +180,15 @@ class CoreActionsPlugin(BasePlugin):
         """返回插件包含的组件列表"""
 
         # --- 从配置动态设置Action/Command ---
-        emoji_chance = global_config.normal_chat.emoji_chance
-        EmojiAction.random_activation_probability = emoji_chance
+        emoji_chance = global_config.emoji.emoji_chance
+        if global_config.emoji.emoji_activate_type == "random":
+            EmojiAction.random_activation_probability = emoji_chance
+            EmojiAction.focus_activation_type = ActionActivationType.RANDOM
+            EmojiAction.normal_activation_type = ActionActivationType.RANDOM
+        elif global_config.emoji.emoji_activate_type == "llm":
+            EmojiAction.random_activation_probability = 0.0
+            EmojiAction.focus_activation_type = ActionActivationType.LLM_JUDGE
+            EmojiAction.normal_activation_type = ActionActivationType.LLM_JUDGE
 
         no_reply_probability = self.get_config("no_reply.random_probability", 0.8)
         NoReplyAction.random_activation_probability = no_reply_probability

src/tools/tool_executor.py

@@ -128,7 +128,8 @@ class ToolExecutor:
         if tool_results:
             self._set_cache(cache_key, tool_results)
 
-        logger.info(f"{self.log_prefix}工具执行完成，共执行{len(used_tools)}个工具: {used_tools}")
+        if used_tools:
+            logger.info(f"{self.log_prefix}工具执行完成，共执行{len(used_tools)}个工具: {used_tools}")
 
         if return_details:
             return tool_results, used_tools, prompt

template/bot_config_template.toml

@@ -1,5 +1,5 @@
 [inner]
-version = "3.3.0"
+version = "3.4.0"
 
 #----以下是给开发人员阅读的，如果你只是部署了麦麦，不需要阅读----
 #如果你想要修改配置文件，请在修改后将version的值进行变更
@@ -118,7 +118,6 @@ ban_msgs_regex = [
 
 [normal_chat] #普通聊天
 #一般回复参数
-emoji_chance = 0.2 # 麦麦一般回复时使用表情包的概率
 willing_mode = "classical" # 回复意愿模式 —— 经典模式：classical，mxp模式：mxp，自定义模式：custom（需要你自己实现）
 response_interested_rate_amplifier = 1 # 麦麦回复兴趣度放大系数
 mentioned_bot_inevitable_reply = true # 提及 bot 必然回复
@@ -137,6 +136,9 @@ enable_in_normal_chat = false # 是否在普通聊天中启用工具
 enable_in_focus_chat = true # 是否在专注聊天中启用工具
 
 [emoji]
+emoji_chance = 0.6 # 麦麦激活表情包动作的概率
+emoji_activate_type = "random" # 表情包激活类型，可选：random，llm ; random下，表情包动作随机启用，llm下，表情包动作根据llm判断是否启用
+
 max_reg_num = 60 # 表情包最大注册数量
 do_replace = true # 开启则在达到最大数量时删除（替换）表情包，关闭则达到最大数量时不会继续收集表情包
 check_interval = 10 # 检查表情包（注册，破损，删除）的时间间隔(分钟)