feat(affinity-flow): 通过标签扩展与提及分类增强兴趣匹配
- 实施扩展标签描述以实现更精确的语义匹配 - 增加强/弱提及分类,并附带独立的兴趣评分 - 重构机器人兴趣管理器,采用动态嵌入生成与缓存机制 - 通过增强的@提及处理功能优化消息处理 - 更新配置以支持回帖提升机制 - 将亲和力流量聊天重新组织为模块化结构,包含核心、规划器、主动响应和工具子模块 - 移除已弃用的规划器组件并整合功能 - 为napcat适配器插件添加数据库表初始化功能 - 修复元事件处理器中的心跳监控
This commit is contained in:
654
docs/affinity_flow_chatter_optimization_summary.md
Normal file
654
docs/affinity_flow_chatter_optimization_summary.md
Normal file
@@ -0,0 +1,654 @@
|
||||
# Affinity Flow Chatter 插件优化总结
|
||||
|
||||
## 更新日期
|
||||
2025年11月3日
|
||||
|
||||
## 优化概述
|
||||
|
||||
本次对 Affinity Flow Chatter 插件进行了全面的重构和优化,主要包括目录结构优化、性能改进、bug修复和新功能添加。
|
||||
|
||||
## <20> 任务-1: 细化提及分数机制(强提及 vs 弱提及)
|
||||
|
||||
### 变更内容
|
||||
将原有的统一提及分数细化为**强提及**和**弱提及**两种类型,使用不同的分值。
|
||||
|
||||
### 原设计问题
|
||||
**旧逻辑**:
|
||||
- ❌ 所有提及方式使用同一个分值(`mention_bot_interest_score`)
|
||||
- ❌ 被@、私聊、文本提到名字都是相同的重要性
|
||||
- ❌ 无法区分用户的真实意图
|
||||
|
||||
### 新设计
|
||||
|
||||
#### 强提及(Strong Mention)
|
||||
**定义**:用户**明确**想与bot交互
|
||||
- ✅ 被 @ 提及
|
||||
- ✅ 被回复
|
||||
- ✅ 私聊消息
|
||||
|
||||
**分值**:`strong_mention_interest_score = 2.5`(默认)
|
||||
|
||||
#### 弱提及(Weak Mention)
|
||||
**定义**:在讨论中**顺带**提到bot
|
||||
- ✅ 消息中包含bot名字
|
||||
- ✅ 消息中包含bot别名
|
||||
|
||||
**分值**:`weak_mention_interest_score = 1.5`(默认)
|
||||
|
||||
### 检测逻辑
|
||||
|
||||
```python
|
||||
def is_mentioned_bot_in_message(message) -> tuple[bool, float]:
|
||||
"""
|
||||
Returns:
|
||||
tuple[bool, float]: (是否提及, 提及类型)
|
||||
提及类型: 0=未提及, 1=弱提及, 2=强提及
|
||||
"""
|
||||
# 1. 检查私聊 → 强提及
|
||||
if is_private_chat:
|
||||
return True, 2.0
|
||||
|
||||
# 2. 检查 @ → 强提及
|
||||
if is_at:
|
||||
return True, 2.0
|
||||
|
||||
# 3. 检查回复 → 强提及
|
||||
if is_replied:
|
||||
return True, 2.0
|
||||
|
||||
# 4. 检查文本匹配 → 弱提及
|
||||
if text_contains_bot_name_or_alias:
|
||||
return True, 1.0
|
||||
|
||||
return False, 0.0
|
||||
```
|
||||
|
||||
### 配置参数
|
||||
|
||||
**config/bot_config.toml**:
|
||||
```toml
|
||||
[affinity_flow]
|
||||
# 提及bot相关参数
|
||||
strong_mention_interest_score = 2.5 # 强提及(@/回复/私聊)
|
||||
weak_mention_interest_score = 1.5 # 弱提及(文本匹配)
|
||||
```
|
||||
|
||||
### 实际效果对比
|
||||
|
||||
**场景1:被@**
|
||||
```
|
||||
用户: "@小狐 你好呀"
|
||||
旧逻辑: 提及分 = 2.5
|
||||
新逻辑: 提及分 = 2.5 (强提及) ✅ 保持不变
|
||||
```
|
||||
|
||||
**场景2:回复bot**
|
||||
```
|
||||
用户: [回复 小狐:...] "是的"
|
||||
旧逻辑: 提及分 = 2.5
|
||||
新逻辑: 提及分 = 2.5 (强提及) ✅ 保持不变
|
||||
```
|
||||
|
||||
**场景3:私聊**
|
||||
```
|
||||
用户: "在吗"
|
||||
旧逻辑: 提及分 = 2.5
|
||||
新逻辑: 提及分 = 2.5 (强提及) ✅ 保持不变
|
||||
```
|
||||
|
||||
**场景4:文本提及**
|
||||
```
|
||||
用户: "小狐今天没来吗"
|
||||
旧逻辑: 提及分 = 2.5 (可能过高)
|
||||
新逻辑: 提及分 = 1.5 (弱提及) ✅ 更合理
|
||||
```
|
||||
|
||||
**场景5:讨论bot**
|
||||
```
|
||||
用户A: "小狐这个bot挺有意思的"
|
||||
旧逻辑: 提及分 = 2.5 (bot可能会插话)
|
||||
新逻辑: 提及分 = 1.5 (弱提及,降低打断概率) ✅ 更自然
|
||||
```
|
||||
|
||||
### 优势
|
||||
|
||||
- ✅ **意图识别**:区分"想对话"和"在讨论"
|
||||
- ✅ **减少误判**:降低在他人讨论中插话的概率
|
||||
- ✅ **灵活调节**:可以独立调整强弱提及的权重
|
||||
- ✅ **向后兼容**:保持原有强提及的行为不变
|
||||
|
||||
### 影响文件
|
||||
|
||||
- `config/bot_config.toml`:添加 `strong/weak_mention_interest_score` 配置
|
||||
- `template/bot_config_template.toml`:同步模板配置
|
||||
- `src/config/official_configs.py`:添加配置字段定义
|
||||
- `src/chat/utils/utils.py`:修改 `is_mentioned_bot_in_message()` 函数
|
||||
- `src/plugins/built_in/affinity_flow_chatter/core/affinity_interest_calculator.py`:使用新的强弱提及逻辑
|
||||
- `docs/affinity_flow_guide.md`:更新文档说明
|
||||
|
||||
---
|
||||
|
||||
## <20>🆔 任务0: 修改 Personality ID 生成逻辑
|
||||
|
||||
### 变更内容
|
||||
将 `bot_person_id` 从固定值改为基于人设文本的 hash 生成,实现人设变化时自动触发兴趣标签重新生成。
|
||||
|
||||
### 原设计问题
|
||||
**旧逻辑**:
|
||||
```python
|
||||
self.bot_person_id = person_info_manager.get_person_id("system", "bot_id")
|
||||
# 结果:md5("system_bot_id") = 固定值
|
||||
```
|
||||
- ❌ personality_id 固定不变
|
||||
- ❌ 人设修改后不会重新生成兴趣标签
|
||||
- ❌ 需要手动清空数据库才能触发重新生成
|
||||
|
||||
### 新设计
|
||||
**新逻辑**:
|
||||
```python
|
||||
personality_hash, _ = self._get_config_hash(bot_nickname, personality_core, personality_side, identity)
|
||||
self.bot_person_id = personality_hash
|
||||
# 结果:md5(人设配置的JSON) = 动态值
|
||||
```
|
||||
|
||||
### Hash 生成规则
|
||||
```python
|
||||
personality_config = {
|
||||
"nickname": bot_nickname,
|
||||
"personality_core": personality_core,
|
||||
"personality_side": personality_side,
|
||||
"compress_personality": global_config.personality.compress_personality,
|
||||
}
|
||||
personality_hash = md5(json_dumps(personality_config, sorted=True))
|
||||
```
|
||||
|
||||
### 工作原理
|
||||
1. **初始化时**:根据当前人设配置计算 hash 作为 personality_id
|
||||
2. **配置变化检测**:
|
||||
- 计算当前人设的 hash
|
||||
- 与上次保存的 hash 对比
|
||||
- 如果不同,触发重新生成
|
||||
3. **兴趣标签生成**:
|
||||
- `bot_interest_manager` 根据 personality_id 查询数据库
|
||||
- 如果 personality_id 不存在(人设变化了),自动生成新的兴趣标签
|
||||
- 保存时使用新的 personality_id
|
||||
|
||||
### 优势
|
||||
- ✅ **自动检测**:人设改变后无需手动操作
|
||||
- ✅ **数据隔离**:不同人设的兴趣标签分开存储
|
||||
- ✅ **版本管理**:可以保留历史人设的兴趣标签(如果需要)
|
||||
- ✅ **逻辑清晰**:personality_id 直接反映人设内容
|
||||
|
||||
### 示例
|
||||
```
|
||||
人设 A:
|
||||
nickname: "小狐"
|
||||
personality_core: "活泼开朗"
|
||||
personality_side: "喜欢编程"
|
||||
→ personality_id: a1b2c3d4e5f6...
|
||||
|
||||
人设 B (修改后):
|
||||
nickname: "小狐"
|
||||
personality_core: "冷静理性" ← 改变
|
||||
personality_side: "喜欢编程"
|
||||
→ personality_id: f6e5d4c3b2a1... ← 自动生成新ID
|
||||
|
||||
结果:
|
||||
- 数据库查询时找不到 f6e5d4c3b2a1 的兴趣标签
|
||||
- 自动触发重新生成
|
||||
- 新兴趣标签保存在 f6e5d4c3b2a1 下
|
||||
```
|
||||
|
||||
### 影响范围
|
||||
- `src/individuality/individuality.py`:personality_id 生成逻辑
|
||||
- `src/chat/interest_system/bot_interest_manager.py`:兴趣标签加载/保存(已支持)
|
||||
- 数据库:`bot_personality_interests` 表通过 personality_id 字段关联
|
||||
|
||||
---
|
||||
|
||||
## 📁 任务1: 优化插件目录结构
|
||||
|
||||
### 变更内容
|
||||
将原本扁平的文件结构重组为分层目录,提高代码可维护性:
|
||||
|
||||
```
|
||||
affinity_flow_chatter/
|
||||
├── core/ # 核心模块
|
||||
│ ├── __init__.py
|
||||
│ ├── affinity_chatter.py # 主聊天处理器
|
||||
│ └── affinity_interest_calculator.py # 兴趣度计算器
|
||||
│
|
||||
├── planner/ # 规划器模块
|
||||
│ ├── __init__.py
|
||||
│ ├── planner.py # 动作规划器
|
||||
│ ├── planner_prompts.py # 提示词模板
|
||||
│ ├── plan_generator.py # 计划生成器
|
||||
│ ├── plan_filter.py # 计划过滤器
|
||||
│ └── plan_executor.py # 计划执行器
|
||||
│
|
||||
├── proactive/ # 主动思考模块
|
||||
│ ├── __init__.py
|
||||
│ ├── proactive_thinking_scheduler.py # 主动思考调度器
|
||||
│ ├── proactive_thinking_executor.py # 主动思考执行器
|
||||
│ └── proactive_thinking_event.py # 主动思考事件
|
||||
│
|
||||
├── tools/ # 工具模块
|
||||
│ ├── __init__.py
|
||||
│ ├── chat_stream_impression_tool.py # 聊天印象工具
|
||||
│ └── user_profile_tool.py # 用户档案工具
|
||||
│
|
||||
├── plugin.py # 插件注册
|
||||
├── __init__.py # 插件元数据
|
||||
└── README.md # 文档
|
||||
```
|
||||
|
||||
### 优势
|
||||
- ✅ **逻辑清晰**:相关功能集中在同一目录
|
||||
- ✅ **易于维护**:模块职责明确,便于定位和修改
|
||||
- ✅ **可扩展性**:新功能可以轻松添加到对应目录
|
||||
- ✅ **团队协作**:多人开发时减少文件冲突
|
||||
|
||||
---
|
||||
|
||||
## 💾 任务2: 修改 Embedding 存储策略
|
||||
|
||||
### 问题分析
|
||||
**原设计**:兴趣标签的 embedding 向量(2560维度浮点数组)直接存储在数据库中
|
||||
- ❌ 数据库存储过长,可能导致写入失败
|
||||
- ❌ 每次加载需要反序列化大量数据
|
||||
- ❌ 数据库体积膨胀
|
||||
|
||||
### 解决方案
|
||||
**新设计**:Embedding 改为启动时动态生成并缓存在内存中
|
||||
|
||||
#### 实现细节
|
||||
|
||||
**1. 数据库存储**(不再包含 embedding):
|
||||
```python
|
||||
# 保存时
|
||||
tag_dict = {
|
||||
"tag_name": tag.tag_name,
|
||||
"weight": tag.weight,
|
||||
"expanded": tag.expanded, # 扩展描述
|
||||
"created_at": tag.created_at.isoformat(),
|
||||
"updated_at": tag.updated_at.isoformat(),
|
||||
"is_active": tag.is_active,
|
||||
# embedding 不再存储
|
||||
}
|
||||
```
|
||||
|
||||
**2. 启动时动态生成**:
|
||||
```python
|
||||
async def _generate_embeddings_for_tags(self, interests: BotPersonalityInterests):
|
||||
"""为所有兴趣标签生成embedding(仅缓存在内存中)"""
|
||||
for tag in interests.interest_tags:
|
||||
if tag.tag_name in self.embedding_cache:
|
||||
# 使用内存缓存
|
||||
tag.embedding = self.embedding_cache[tag.tag_name]
|
||||
else:
|
||||
# 动态生成新的embedding
|
||||
embedding = await self._get_embedding(tag.tag_name)
|
||||
tag.embedding = embedding # 设置到内存对象
|
||||
self.embedding_cache[tag.tag_name] = embedding # 缓存
|
||||
```
|
||||
|
||||
**3. 加载时处理**:
|
||||
```python
|
||||
tag = BotInterestTag(
|
||||
tag_name=tag_data.get("tag_name", ""),
|
||||
weight=tag_data.get("weight", 0.5),
|
||||
expanded=tag_data.get("expanded"),
|
||||
embedding=None, # 不从数据库加载,改为动态生成
|
||||
# ...
|
||||
)
|
||||
```
|
||||
|
||||
### 优势
|
||||
- ✅ **数据库轻量化**:数据库只存储标签名和权重等元数据
|
||||
- ✅ **避免写入失败**:不再因为数据过长导致数据库操作失败
|
||||
- ✅ **灵活性**:可以随时切换 embedding 模型而无需迁移数据
|
||||
- ✅ **性能**:内存缓存访问速度快
|
||||
|
||||
### 权衡
|
||||
- ⚠️ 启动时需要生成 embedding(首次启动稍慢,约10-20秒)
|
||||
- ✅ 后续运行时使用内存缓存,性能与原来相当
|
||||
|
||||
---
|
||||
|
||||
## 🔧 任务3: 修复连续不回复阈值调整问题
|
||||
|
||||
### 问题描述
|
||||
原实现中,连续不回复调整只提升了分数,但阈值保持不变:
|
||||
```python
|
||||
# ❌ 错误的实现
|
||||
adjusted_score = self._apply_no_reply_boost(total_score) # 只提升分数
|
||||
should_reply = adjusted_score >= self.reply_threshold # 阈值不变
|
||||
```
|
||||
|
||||
**问题**:动作阈值(`non_reply_action_interest_threshold`)没有被调整,导致即使回复阈值满足,动作阈值可能仍然不满足。
|
||||
|
||||
### 解决方案
|
||||
改为**同时降低回复阈值和动作阈值**:
|
||||
|
||||
```python
|
||||
def _apply_no_reply_threshold_adjustment(self) -> tuple[float, float]:
|
||||
"""应用阈值调整(包括连续不回复和回复后降低机制)"""
|
||||
base_reply_threshold = self.reply_threshold
|
||||
base_action_threshold = global_config.affinity_flow.non_reply_action_interest_threshold
|
||||
|
||||
total_reduction = 0.0
|
||||
|
||||
# 连续不回复的阈值降低
|
||||
if self.no_reply_count > 0:
|
||||
no_reply_reduction = self.no_reply_count * self.probability_boost_per_no_reply
|
||||
total_reduction += no_reply_reduction
|
||||
|
||||
# 应用到两个阈值
|
||||
adjusted_reply_threshold = max(0.0, base_reply_threshold - total_reduction)
|
||||
adjusted_action_threshold = max(0.0, base_action_threshold - total_reduction)
|
||||
|
||||
return adjusted_reply_threshold, adjusted_action_threshold
|
||||
```
|
||||
|
||||
**使用**:
|
||||
```python
|
||||
# ✅ 正确的实现
|
||||
adjusted_reply_threshold, adjusted_action_threshold = self._apply_no_reply_threshold_adjustment()
|
||||
should_reply = adjusted_score >= adjusted_reply_threshold
|
||||
should_take_action = adjusted_score >= adjusted_action_threshold
|
||||
```
|
||||
|
||||
### 优势
|
||||
- ✅ **逻辑一致**:回复阈值和动作阈值同步调整
|
||||
- ✅ **避免矛盾**:不会出现"满足回复但不满足动作"的情况
|
||||
- ✅ **更合理**:连续不回复时,bot更容易采取任何行动
|
||||
|
||||
---
|
||||
|
||||
## ⏱️ 任务4: 添加兴趣度计算超时机制
|
||||
|
||||
### 问题描述
|
||||
兴趣匹配计算调用 embedding API,可能因为网络问题或模型响应慢导致:
|
||||
- ❌ 长时间等待(>5秒)
|
||||
- ❌ 整体超时导致强制使用默认分值
|
||||
- ❌ **丢失了提及分和关系分**(因为整个计算被中断)
|
||||
|
||||
### 解决方案
|
||||
为兴趣匹配计算添加**1.5秒超时保护**,超时时返回默认分值:
|
||||
|
||||
```python
|
||||
async def _calculate_interest_match_score(self, content: str, keywords: list[str] | None = None) -> float:
|
||||
"""计算兴趣匹配度(带超时保护)"""
|
||||
try:
|
||||
# 使用 asyncio.wait_for 添加1.5秒超时
|
||||
match_result = await asyncio.wait_for(
|
||||
bot_interest_manager.calculate_interest_match(content, keywords or []),
|
||||
timeout=1.5
|
||||
)
|
||||
|
||||
if match_result:
|
||||
# 正常计算分数
|
||||
final_score = match_result.overall_score * 1.15 * match_result.confidence + match_count_bonus
|
||||
return final_score
|
||||
else:
|
||||
return 0.0
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
# 超时时返回默认分值 0.5
|
||||
logger.warning("⏱️ 兴趣匹配计算超时(>1.5秒),返回默认分值0.5以保留其他分数")
|
||||
return 0.5 # 避免丢失提及分和关系分
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"智能兴趣匹配失败: {e}")
|
||||
return 0.0
|
||||
```
|
||||
|
||||
### 工作流程
|
||||
```
|
||||
正常情况(<1.5秒):
|
||||
兴趣匹配分: 0.8 + 关系分: 0.3 + 提及分: 2.5 = 3.6 ✅
|
||||
|
||||
超时情况(>1.5秒):
|
||||
兴趣匹配分: 0.5(默认)+ 关系分: 0.3 + 提及分: 2.5 = 3.3 ✅
|
||||
(保留了关系分和提及分)
|
||||
|
||||
强制中断(无超时保护):
|
||||
整体计算失败 = 0.0(默认) ❌
|
||||
(丢失了所有分数)
|
||||
```
|
||||
|
||||
### 优势
|
||||
- ✅ **防止阻塞**:不会因为一个API调用卡住整个流程
|
||||
- ✅ **保留分数**:即使兴趣匹配超时,提及分和关系分依然有效
|
||||
- ✅ **用户体验**:响应更快,不会长时间无反应
|
||||
- ✅ **降级优雅**:超时时仍能给出合理的默认值
|
||||
|
||||
---
|
||||
|
||||
## 🔄 任务5: 实现回复后阈值降低机制
|
||||
|
||||
### 需求背景
|
||||
**目标**:让bot在回复后更容易进行连续对话,提升对话的连贯性和自然性。
|
||||
|
||||
**场景示例**:
|
||||
```
|
||||
用户: "你好呀"
|
||||
Bot: "你好!今天过得怎么样?" ← 此时激活连续对话模式
|
||||
|
||||
用户: "还不错"
|
||||
Bot: "那就好~有什么有趣的事情吗?" ← 阈值降低,更容易回复
|
||||
|
||||
用户: "没什么"
|
||||
Bot: "嗯嗯,那要不要聊聊别的?" ← 仍然更容易回复
|
||||
|
||||
用户: "..."
|
||||
(如果一直不回复,降低效果会逐渐衰减)
|
||||
```
|
||||
|
||||
### 配置项
|
||||
在 `bot_config.toml` 中添加:
|
||||
|
||||
```toml
|
||||
# 回复后连续对话机制参数
|
||||
enable_post_reply_boost = true # 是否启用回复后阈值降低机制
|
||||
post_reply_threshold_reduction = 0.15 # 回复后初始阈值降低值
|
||||
post_reply_boost_max_count = 3 # 回复后阈值降低的最大持续次数
|
||||
post_reply_boost_decay_rate = 0.5 # 每次回复后阈值降低衰减率(0-1)
|
||||
```
|
||||
|
||||
### 实现细节
|
||||
|
||||
**1. 初始化计数器**:
|
||||
```python
|
||||
def __init__(self):
|
||||
# 回复后阈值降低机制
|
||||
self.enable_post_reply_boost = affinity_config.enable_post_reply_boost
|
||||
self.post_reply_boost_remaining = 0 # 剩余的回复后降低次数
|
||||
self.post_reply_threshold_reduction = affinity_config.post_reply_threshold_reduction
|
||||
self.post_reply_boost_max_count = affinity_config.post_reply_boost_max_count
|
||||
self.post_reply_boost_decay_rate = affinity_config.post_reply_boost_decay_rate
|
||||
```
|
||||
|
||||
**2. 阈值调整**:
|
||||
```python
|
||||
def _apply_no_reply_threshold_adjustment(self) -> tuple[float, float]:
|
||||
"""应用阈值调整"""
|
||||
total_reduction = 0.0
|
||||
|
||||
# 1. 连续不回复的降低
|
||||
if self.no_reply_count > 0:
|
||||
no_reply_reduction = self.no_reply_count * self.probability_boost_per_no_reply
|
||||
total_reduction += no_reply_reduction
|
||||
|
||||
# 2. 回复后的降低(带衰减)
|
||||
if self.enable_post_reply_boost and self.post_reply_boost_remaining > 0:
|
||||
# 计算衰减因子
|
||||
decay_factor = self.post_reply_boost_decay_rate ** (
|
||||
self.post_reply_boost_max_count - self.post_reply_boost_remaining
|
||||
)
|
||||
post_reply_reduction = self.post_reply_threshold_reduction * decay_factor
|
||||
total_reduction += post_reply_reduction
|
||||
|
||||
# 应用总降低量
|
||||
adjusted_reply_threshold = max(0.0, base_reply_threshold - total_reduction)
|
||||
adjusted_action_threshold = max(0.0, base_action_threshold - total_reduction)
|
||||
|
||||
return adjusted_reply_threshold, adjusted_action_threshold
|
||||
```
|
||||
|
||||
**3. 状态更新**:
|
||||
```python
|
||||
def on_reply_sent(self):
|
||||
"""当机器人发送回复后调用"""
|
||||
if self.enable_post_reply_boost:
|
||||
# 重置回复后降低计数器
|
||||
self.post_reply_boost_remaining = self.post_reply_boost_max_count
|
||||
# 同时重置不回复计数
|
||||
self.no_reply_count = 0
|
||||
|
||||
def on_message_processed(self, replied: bool):
|
||||
"""消息处理完成后调用"""
|
||||
# 更新不回复计数
|
||||
self.update_no_reply_count(replied)
|
||||
|
||||
# 如果已回复,激活回复后降低机制
|
||||
if replied:
|
||||
self.on_reply_sent()
|
||||
else:
|
||||
# 如果没有回复,减少回复后降低剩余次数
|
||||
if self.post_reply_boost_remaining > 0:
|
||||
self.post_reply_boost_remaining -= 1
|
||||
```
|
||||
|
||||
### 衰减机制说明
|
||||
|
||||
**衰减公式**:
|
||||
```
|
||||
decay_factor = decay_rate ^ (max_count - remaining_count)
|
||||
actual_reduction = base_reduction * decay_factor
|
||||
```
|
||||
|
||||
**示例**(`base_reduction=0.15`, `decay_rate=0.5`, `max_count=3`):
|
||||
```
|
||||
第1次回复后: decay_factor = 0.5^0 = 1.00, reduction = 0.15 * 1.00 = 0.15
|
||||
第2次回复后: decay_factor = 0.5^1 = 0.50, reduction = 0.15 * 0.50 = 0.075
|
||||
第3次回复后: decay_factor = 0.5^2 = 0.25, reduction = 0.15 * 0.25 = 0.0375
|
||||
```
|
||||
|
||||
### 实际效果
|
||||
|
||||
**配置示例**:
|
||||
- 回复阈值: 0.7
|
||||
- 初始降低值: 0.15
|
||||
- 最大次数: 3
|
||||
- 衰减率: 0.5
|
||||
|
||||
**对话流程**:
|
||||
```
|
||||
初始状态:
|
||||
回复阈值: 0.7
|
||||
|
||||
Bot发送回复 → 激活连续对话模式:
|
||||
剩余次数: 3
|
||||
|
||||
第1条消息:
|
||||
阈值降低: 0.15
|
||||
实际阈值: 0.7 - 0.15 = 0.55 ✅ 更容易回复
|
||||
|
||||
第2条消息:
|
||||
阈值降低: 0.075 (衰减)
|
||||
实际阈值: 0.7 - 0.075 = 0.625
|
||||
|
||||
第3条消息:
|
||||
阈值降低: 0.0375 (继续衰减)
|
||||
实际阈值: 0.7 - 0.0375 = 0.6625
|
||||
|
||||
第4条消息:
|
||||
降低结束,恢复正常阈值: 0.7
|
||||
```
|
||||
|
||||
### 优势
|
||||
- ✅ **连贯对话**:bot回复后更容易继续对话
|
||||
- ✅ **自然衰减**:避免无限连续回复,逐渐恢复正常
|
||||
- ✅ **可配置**:可以根据需求调整降低值、次数和衰减率
|
||||
- ✅ **灵活控制**:可以随时启用/禁用此功能
|
||||
|
||||
---
|
||||
|
||||
## 📊 整体影响
|
||||
|
||||
### 性能优化
|
||||
- ✅ **内存优化**:不再在数据库中存储大量 embedding 数据
|
||||
- ✅ **响应速度**:超时保护避免长时间等待
|
||||
- ✅ **启动速度**:首次启动需要生成 embedding(10-20秒),后续运行使用缓存
|
||||
|
||||
### 功能增强
|
||||
- ✅ **阈值调整**:修复了回复和动作阈值不一致的问题
|
||||
- ✅ **连续对话**:新增回复后阈值降低机制,提升对话连贯性
|
||||
- ✅ **容错能力**:超时保护确保即使API失败也能保留其他分数
|
||||
|
||||
### 代码质量
|
||||
- ✅ **目录结构**:清晰的模块划分,易于维护
|
||||
- ✅ **可扩展性**:新功能可以轻松添加到对应目录
|
||||
- ✅ **可配置性**:关键参数可通过配置文件调整
|
||||
|
||||
---
|
||||
|
||||
## 🔧 使用说明
|
||||
|
||||
### 配置调整
|
||||
|
||||
在 `config/bot_config.toml` 中调整回复后连续对话参数:
|
||||
|
||||
```toml
|
||||
[affinity_flow]
|
||||
# 回复后连续对话机制
|
||||
enable_post_reply_boost = true # 启用/禁用
|
||||
post_reply_threshold_reduction = 0.15 # 初始降低值(建议0.1-0.2)
|
||||
post_reply_boost_max_count = 3 # 持续次数(建议2-5)
|
||||
post_reply_boost_decay_rate = 0.5 # 衰减率(建议0.3-0.7)
|
||||
```
|
||||
|
||||
### 调用方式
|
||||
|
||||
在 planner 或其他需要的地方调用:
|
||||
|
||||
```python
|
||||
# 计算兴趣值
|
||||
result = await interest_calculator.execute(message)
|
||||
|
||||
# 消息处理完成后更新状态
|
||||
interest_calculator.on_message_processed(replied=result.should_reply)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🐛 已知问题
|
||||
|
||||
暂无
|
||||
|
||||
---
|
||||
|
||||
## 📝 后续优化建议
|
||||
|
||||
1. **监控日志**:观察实际使用中的阈值调整效果
|
||||
2. **A/B测试**:对比启用/禁用回复后降低机制的对话质量
|
||||
3. **参数调优**:根据实际使用情况调整默认配置值
|
||||
4. **性能监控**:监控 embedding 生成的时间和缓存命中率
|
||||
|
||||
---
|
||||
|
||||
## 👥 贡献者
|
||||
|
||||
- GitHub Copilot - 代码实现和文档编写
|
||||
|
||||
---
|
||||
|
||||
## 📅 更新历史
|
||||
|
||||
- 2025-11-03: 完成所有5个任务的实现
|
||||
- ✅ 优化插件目录结构
|
||||
- ✅ 修改 embedding 存储策略
|
||||
- ✅ 修复连续不回复阈值调整
|
||||
- ✅ 添加超时保护机制
|
||||
- ✅ 实现回复后阈值降低
|
||||
@@ -70,6 +70,11 @@
|
||||
- `mention_bot_adjustment_threshold`
|
||||
提及 Bot 后的调整阈值。当bot被提及后,回复阈值会改变为这个值。
|
||||
|
||||
- `strong_mention_interest_score`
|
||||
强提及的兴趣分。强提及包括:被@、被回复、私聊消息。这类提及表示用户明确想与bot交互。
|
||||
|
||||
- `weak_mention_interest_score`
|
||||
弱提及的兴趣分。弱提及包括:消息中包含bot的名字或别名(文本匹配)。这类提及可能只是在讨论中提到bot。
|
||||
|
||||
- `base_relationship_score`
|
||||
---
|
||||
@@ -80,13 +85,16 @@
|
||||
2. **Bot 太热情/回复太多**
|
||||
- 提高 `reply_action_interest_threshold`,或降低关键词相关倍率。
|
||||
|
||||
3. **希望 Bot 更关注被 @ 的消息**
|
||||
- 提高 `mention_bot_interest_score` 或 `mention_bot_weight`。
|
||||
3. **希望 Bot 更关注被 @ 或回复的消息**
|
||||
- 提高 `strong_mention_interest_score` 或 `mention_bot_weight`。
|
||||
|
||||
4. **希望 Bot 更看重关系好的用户**
|
||||
4. **希望 Bot 对文本提及也积极回应**
|
||||
- 提高 `weak_mention_interest_score`。
|
||||
|
||||
5. **希望 Bot 更看重关系好的用户**
|
||||
- 提高 `relationship_weight` 或 `base_relationship_score`。
|
||||
|
||||
5. **表情包行为过于频繁/稀少**
|
||||
6. **表情包行为过于频繁/稀少**
|
||||
- 调整 `non_reply_action_interest_threshold`。
|
||||
|
||||
---
|
||||
@@ -121,7 +129,8 @@ keyword_match_weight = 0.4
|
||||
mention_bot_weight = 0.3
|
||||
relationship_weight = 0.3
|
||||
mention_bot_adjustment_threshold = 0.5
|
||||
mention_bot_interest_score = 2.5
|
||||
strong_mention_interest_score = 2.5 # 强提及(@/回复/私聊)
|
||||
weak_mention_interest_score = 1.5 # 弱提及(文本匹配)
|
||||
base_relationship_score = 0.3
|
||||
```
|
||||
|
||||
@@ -134,7 +143,10 @@ MoFox-Bot 在收到每条消息时,会通过一套“兴趣度评分(afc)
|
||||
- 不同匹配度的关键词会乘以对应的倍率(high/medium/low_match_keyword_multiplier),并根据匹配数量叠加加成(match_count_bonus,max_match_bonus)。
|
||||
|
||||
### 2. 提及与关系加分
|
||||
- 如果消息中提及了 Bot(如被@),会直接获得一部分兴趣分(mention_bot_interest_score),并按权重(mention_bot_weight)计入总分。
|
||||
- 如果消息中提及了 Bot,会根据提及类型获得不同的兴趣分:
|
||||
* **强提及**(被@、被回复、私聊): 获得 `strong_mention_interest_score` 分值,表示用户明确想与bot交互
|
||||
* **弱提及**(文本中包含bot名字或别名): 获得 `weak_mention_interest_score` 分值,表示在讨论中提到bot
|
||||
* 提及分按权重(`mention_bot_weight`)计入总分
|
||||
- 与用户的关系分(base_relationship_score 及动态关系分)也会按 relationship_weight 计入总分。
|
||||
|
||||
### 3. 综合评分计算
|
||||
|
||||
@@ -26,6 +26,8 @@ class BotInterestManager:
|
||||
def __init__(self):
|
||||
self.current_interests: BotPersonalityInterests | None = None
|
||||
self.embedding_cache: dict[str, list[float]] = {} # embedding缓存
|
||||
self.expanded_tag_cache: dict[str, str] = {} # 扩展标签缓存
|
||||
self.expanded_embedding_cache: dict[str, list[float]] = {} # 扩展标签的embedding缓存
|
||||
self._initialized = False
|
||||
|
||||
# Embedding客户端配置
|
||||
@@ -169,22 +171,47 @@ class BotInterestManager:
|
||||
1. 标签应该符合人设特点和性格
|
||||
2. 每个标签都有权重(0.1-1.0),表示对该兴趣的喜好程度
|
||||
3. 生成15-25个不等的标签
|
||||
4. 标签应该是具体的关键词,而不是抽象概念
|
||||
5. 每个标签的长度不超过10个字符
|
||||
4. 每个标签包含两个部分:
|
||||
- name: 简短的标签名(2-6个字符),用于显示和管理,如"Python"、"追番"、"撸猫"
|
||||
- expanded: 完整的描述性文本(20-50个字符),用于语义匹配,描述这个兴趣的具体内容和场景
|
||||
5. expanded 扩展描述要求:
|
||||
- 必须是完整的句子或短语,包含丰富的语义信息
|
||||
- 描述具体的对话场景、活动内容、相关话题
|
||||
- 避免过于抽象,要有明确的语境
|
||||
- 示例:
|
||||
* "Python" -> "讨论Python编程语言、写Python代码、Python脚本开发、Python技术问题"
|
||||
* "追番" -> "讨论正在播出的动漫番剧、追番进度、动漫剧情、番剧推荐、动漫角色"
|
||||
* "撸猫" -> "讨论猫咪宠物、晒猫分享、萌宠日常、可爱猫猫、养猫心得"
|
||||
* "社恐" -> "表达社交焦虑、不想见人、想躲起来、害怕社交的心情"
|
||||
* "深夜码代码" -> "深夜写代码、熬夜编程、夜猫子程序员、深夜调试bug"
|
||||
|
||||
请以JSON格式返回,格式如下:
|
||||
{{
|
||||
"interests": [
|
||||
{{"name": "标签名", "weight": 0.8}},
|
||||
{{"name": "标签名", "weight": 0.6}},
|
||||
{{"name": "标签名", "weight": 0.9}}
|
||||
{{
|
||||
"name": "Python",
|
||||
"expanded": "讨论Python编程语言、写Python代码、Python脚本开发、Python技术问题",
|
||||
"weight": 0.9
|
||||
}},
|
||||
{{
|
||||
"name": "追番",
|
||||
"expanded": "讨论正在播出的动漫番剧、追番进度、动漫剧情、番剧推荐、动漫角色",
|
||||
"weight": 0.85
|
||||
}},
|
||||
{{
|
||||
"name": "撸猫",
|
||||
"expanded": "讨论猫咪宠物、晒猫分享、萌宠日常、可爱猫猫、养猫心得",
|
||||
"weight": 0.95
|
||||
}}
|
||||
]
|
||||
}}
|
||||
|
||||
注意:
|
||||
- 权重范围0.1-1.0,权重越高表示越感兴趣
|
||||
- 标签要具体,如"编程"、"游戏"、"旅行"等
|
||||
- 根据人设生成个性化的标签
|
||||
- name: 简短标签名,2-6个字符,方便显示
|
||||
- expanded: 完整描述,20-50个字符,用于精准的语义匹配
|
||||
- weight: 权重范围0.1-1.0,权重越高表示越感兴趣
|
||||
- 根据人设生成个性化、具体的标签和描述
|
||||
- expanded 描述要有具体场景,避免泛化
|
||||
"""
|
||||
|
||||
# 调用LLM生成兴趣标签
|
||||
@@ -211,16 +238,22 @@ class BotInterestManager:
|
||||
for i, tag_data in enumerate(interests_list):
|
||||
tag_name = tag_data.get("name", f"标签_{i}")
|
||||
weight = tag_data.get("weight", 0.5)
|
||||
expanded = tag_data.get("expanded") # 获取扩展描述
|
||||
|
||||
# 检查标签长度,如果过长则截断
|
||||
if len(tag_name) > 10:
|
||||
logger.warning(f"⚠️ 标签 '{tag_name}' 过长,将截断为10个字符")
|
||||
tag_name = tag_name[:10]
|
||||
|
||||
tag = BotInterestTag(tag_name=tag_name, weight=weight)
|
||||
bot_interests.interest_tags.append(tag)
|
||||
# 验证扩展描述
|
||||
if expanded:
|
||||
logger.debug(f" 🏷️ {tag_name} (权重: {weight:.2f})")
|
||||
logger.debug(f" 📝 扩展: {expanded}")
|
||||
else:
|
||||
logger.warning(f" ⚠️ 标签 '{tag_name}' 缺少扩展描述,将使用回退方案")
|
||||
|
||||
logger.debug(f" 🏷️ {tag_name} (权重: {weight:.2f})")
|
||||
tag = BotInterestTag(tag_name=tag_name, weight=weight, expanded=expanded)
|
||||
bot_interests.interest_tags.append(tag)
|
||||
|
||||
# 为所有标签生成embedding
|
||||
logger.info("🧠 开始为兴趣标签生成embedding向量...")
|
||||
@@ -284,12 +317,12 @@ class BotInterestManager:
|
||||
return None
|
||||
|
||||
async def _generate_embeddings_for_tags(self, interests: BotPersonalityInterests):
|
||||
"""为所有兴趣标签生成embedding"""
|
||||
"""为所有兴趣标签生成embedding(仅缓存在内存中)"""
|
||||
if not hasattr(self, "embedding_request"):
|
||||
raise RuntimeError("❌ Embedding客户端未初始化,无法生成embedding")
|
||||
|
||||
total_tags = len(interests.interest_tags)
|
||||
logger.info(f"🧠 开始为 {total_tags} 个兴趣标签生成embedding向量...")
|
||||
logger.info(f"🧠 开始为 {total_tags} 个兴趣标签生成embedding向量(动态生成,仅内存缓存)...")
|
||||
|
||||
cached_count = 0
|
||||
generated_count = 0
|
||||
@@ -297,22 +330,22 @@ class BotInterestManager:
|
||||
|
||||
for i, tag in enumerate(interests.interest_tags, 1):
|
||||
if tag.tag_name in self.embedding_cache:
|
||||
# 使用缓存的embedding
|
||||
# 使用内存缓存的embedding
|
||||
tag.embedding = self.embedding_cache[tag.tag_name]
|
||||
cached_count += 1
|
||||
logger.debug(f" [{i}/{total_tags}] 🏷️ '{tag.tag_name}' - 使用缓存")
|
||||
logger.debug(f" [{i}/{total_tags}] 🏷️ '{tag.tag_name}' - 使用内存缓存")
|
||||
else:
|
||||
# 生成新的embedding
|
||||
# 动态生成新的embedding
|
||||
embedding_text = tag.tag_name
|
||||
|
||||
logger.debug(f" [{i}/{total_tags}] 🔄 正在为 '{tag.tag_name}' 生成embedding...")
|
||||
logger.debug(f" [{i}/{total_tags}] 🔄 正在为 '{tag.tag_name}' 动态生成embedding...")
|
||||
embedding = await self._get_embedding(embedding_text)
|
||||
|
||||
if embedding:
|
||||
tag.embedding = embedding
|
||||
self.embedding_cache[tag.tag_name] = embedding
|
||||
tag.embedding = embedding # 设置到 tag 对象(内存中)
|
||||
self.embedding_cache[tag.tag_name] = embedding # 同时缓存
|
||||
generated_count += 1
|
||||
logger.debug(f" ✅ '{tag.tag_name}' embedding生成成功")
|
||||
logger.debug(f" ✅ '{tag.tag_name}' embedding动态生成成功并缓存到内存")
|
||||
else:
|
||||
failed_count += 1
|
||||
logger.warning(f" ❌ '{tag.tag_name}' embedding生成失败")
|
||||
@@ -322,12 +355,12 @@ class BotInterestManager:
|
||||
|
||||
interests.last_updated = datetime.now()
|
||||
logger.info("=" * 50)
|
||||
logger.info("✅ Embedding生成完成!")
|
||||
logger.info("✅ Embedding动态生成完成(仅存储在内存中)!")
|
||||
logger.info(f"📊 总标签数: {total_tags}")
|
||||
logger.info(f"💾 缓存命中: {cached_count}")
|
||||
logger.info(f"💾 内存缓存命中: {cached_count}")
|
||||
logger.info(f"🆕 新生成: {generated_count}")
|
||||
logger.info(f"❌ 失败: {failed_count}")
|
||||
logger.info(f"🗃️ 总缓存大小: {len(self.embedding_cache)}")
|
||||
logger.info(f"🗃️ 内存缓存总大小: {len(self.embedding_cache)}")
|
||||
logger.info("=" * 50)
|
||||
|
||||
async def _get_embedding(self, text: str) -> list[float]:
|
||||
@@ -421,7 +454,19 @@ class BotInterestManager:
|
||||
async def calculate_interest_match(
|
||||
self, message_text: str, keywords: list[str] | None = None
|
||||
) -> InterestMatchResult:
|
||||
"""计算消息与机器人兴趣的匹配度"""
|
||||
"""计算消息与机器人兴趣的匹配度(优化版 - 标签扩展策略)
|
||||
|
||||
核心优化:将短标签扩展为完整的描述性句子,解决语义粒度不匹配问题
|
||||
|
||||
原问题:
|
||||
- 消息: "今天天气不错" (完整句子)
|
||||
- 标签: "蹭人治愈" (2-4字短语)
|
||||
- 结果: 误匹配,因为短标签的 embedding 过于抽象
|
||||
|
||||
解决方案:
|
||||
- 标签扩展: "蹭人治愈" -> "表达亲近、寻求安慰、撒娇的内容"
|
||||
- 现在是: 句子 vs 句子,匹配更准确
|
||||
"""
|
||||
if not self.current_interests or not self._initialized:
|
||||
raise RuntimeError("❌ 兴趣标签系统未初始化")
|
||||
|
||||
@@ -442,13 +487,13 @@ class BotInterestManager:
|
||||
message_embedding = await self._get_embedding(message_text)
|
||||
logger.debug(f"消息 embedding 生成成功, 维度: {len(message_embedding)}")
|
||||
|
||||
# 计算与每个兴趣标签的相似度
|
||||
# 计算与每个兴趣标签的相似度(使用扩展标签)
|
||||
match_count = 0
|
||||
high_similarity_count = 0
|
||||
medium_similarity_count = 0
|
||||
low_similarity_count = 0
|
||||
|
||||
# 分级相似度阈值
|
||||
# 分级相似度阈值 - 优化后可以提高阈值,因为匹配更准确了
|
||||
affinity_config = global_config.affinity_flow
|
||||
high_threshold = affinity_config.high_match_interest_threshold
|
||||
medium_threshold = affinity_config.medium_match_interest_threshold
|
||||
@@ -458,27 +503,45 @@ class BotInterestManager:
|
||||
|
||||
for tag in active_tags:
|
||||
if tag.embedding:
|
||||
similarity = self._calculate_cosine_similarity(message_embedding, tag.embedding)
|
||||
# 🔧 优化:获取扩展标签的 embedding(带缓存)
|
||||
expanded_embedding = await self._get_expanded_tag_embedding(tag.tag_name)
|
||||
|
||||
if expanded_embedding:
|
||||
# 使用扩展标签的 embedding 进行匹配
|
||||
similarity = self._calculate_cosine_similarity(message_embedding, expanded_embedding)
|
||||
|
||||
# 同时计算原始标签的相似度作为参考
|
||||
original_similarity = self._calculate_cosine_similarity(message_embedding, tag.embedding)
|
||||
|
||||
# 混合策略:扩展标签权重更高(70%),原始标签作为补充(30%)
|
||||
# 这样可以兼顾准确性(扩展)和灵活性(原始)
|
||||
final_similarity = similarity * 0.7 + original_similarity * 0.3
|
||||
|
||||
logger.debug(f"标签'{tag.tag_name}': 原始={original_similarity:.3f}, 扩展={similarity:.3f}, 最终={final_similarity:.3f}")
|
||||
else:
|
||||
# 如果扩展 embedding 获取失败,使用原始 embedding
|
||||
final_similarity = self._calculate_cosine_similarity(message_embedding, tag.embedding)
|
||||
logger.debug(f"标签'{tag.tag_name}': 使用原始相似度={final_similarity:.3f}")
|
||||
|
||||
# 基础加权分数
|
||||
weighted_score = similarity * tag.weight
|
||||
weighted_score = final_similarity * tag.weight
|
||||
|
||||
# 根据相似度等级应用不同的加成
|
||||
if similarity > high_threshold:
|
||||
if final_similarity > high_threshold:
|
||||
# 高相似度:强加成
|
||||
enhanced_score = weighted_score * affinity_config.high_match_keyword_multiplier
|
||||
match_count += 1
|
||||
high_similarity_count += 1
|
||||
result.add_match(tag.tag_name, enhanced_score, [tag.tag_name])
|
||||
|
||||
elif similarity > medium_threshold:
|
||||
elif final_similarity > medium_threshold:
|
||||
# 中相似度:中等加成
|
||||
enhanced_score = weighted_score * affinity_config.medium_match_keyword_multiplier
|
||||
match_count += 1
|
||||
medium_similarity_count += 1
|
||||
result.add_match(tag.tag_name, enhanced_score, [tag.tag_name])
|
||||
|
||||
elif similarity > low_threshold:
|
||||
elif final_similarity > low_threshold:
|
||||
# 低相似度:轻微加成
|
||||
enhanced_score = weighted_score * affinity_config.low_match_keyword_multiplier
|
||||
match_count += 1
|
||||
@@ -520,6 +583,121 @@ class BotInterestManager:
|
||||
)
|
||||
return result
|
||||
|
||||
async def _get_expanded_tag_embedding(self, tag_name: str) -> list[float] | None:
|
||||
"""获取扩展标签的 embedding(带缓存)
|
||||
|
||||
优先使用缓存,如果没有则生成并缓存
|
||||
"""
|
||||
# 检查缓存
|
||||
if tag_name in self.expanded_embedding_cache:
|
||||
return self.expanded_embedding_cache[tag_name]
|
||||
|
||||
# 扩展标签
|
||||
expanded_tag = self._expand_tag_for_matching(tag_name)
|
||||
|
||||
# 生成 embedding
|
||||
try:
|
||||
embedding = await self._get_embedding(expanded_tag)
|
||||
if embedding:
|
||||
# 缓存结果
|
||||
self.expanded_tag_cache[tag_name] = expanded_tag
|
||||
self.expanded_embedding_cache[tag_name] = embedding
|
||||
logger.debug(f"✅ 为标签'{tag_name}'生成并缓存扩展embedding: {expanded_tag[:50]}...")
|
||||
return embedding
|
||||
except Exception as e:
|
||||
logger.warning(f"为标签'{tag_name}'生成扩展embedding失败: {e}")
|
||||
|
||||
return None
|
||||
|
||||
def _expand_tag_for_matching(self, tag_name: str) -> str:
|
||||
"""将短标签扩展为完整的描述性句子
|
||||
|
||||
这是解决"标签太短导致误匹配"的核心方法
|
||||
|
||||
策略:
|
||||
1. 优先使用 LLM 生成的 expanded 字段(最准确)
|
||||
2. 如果没有,使用基于规则的回退方案
|
||||
3. 最后使用通用模板
|
||||
|
||||
示例:
|
||||
- "Python" + expanded -> "讨论Python编程语言、写Python代码、Python脚本开发、Python技术问题"
|
||||
- "蹭人治愈" + expanded -> "想要获得安慰、寻求温暖关怀、撒娇卖萌、表达亲昵、求抱抱求陪伴的对话"
|
||||
"""
|
||||
# 使用缓存
|
||||
if tag_name in self.expanded_tag_cache:
|
||||
return self.expanded_tag_cache[tag_name]
|
||||
|
||||
# 🎯 优先策略:使用 LLM 生成的 expanded 字段
|
||||
if self.current_interests:
|
||||
for tag in self.current_interests.interest_tags:
|
||||
if tag.tag_name == tag_name and tag.expanded:
|
||||
logger.debug(f"✅ 使用LLM生成的扩展描述: {tag_name} -> {tag.expanded[:50]}...")
|
||||
self.expanded_tag_cache[tag_name] = tag.expanded
|
||||
return tag.expanded
|
||||
|
||||
# 🔧 回退策略:基于规则的扩展(用于兼容旧数据或LLM未生成扩展的情况)
|
||||
logger.debug(f"⚠️ 标签'{tag_name}'没有LLM扩展描述,使用规则回退方案")
|
||||
tag_lower = tag_name.lower()
|
||||
|
||||
# 技术编程类标签(具体化描述)
|
||||
if any(word in tag_lower for word in ['python', 'java', 'code', '代码', '编程', '脚本', '算法', '开发']):
|
||||
if 'python' in tag_lower:
|
||||
return f"讨论Python编程语言、写Python代码、Python脚本开发、Python技术问题"
|
||||
elif '算法' in tag_lower:
|
||||
return f"讨论算法题目、数据结构、编程竞赛、刷LeetCode题目、代码优化"
|
||||
elif '代码' in tag_lower or '被窝' in tag_lower:
|
||||
return f"讨论写代码、编程开发、代码实现、技术方案、编程技巧"
|
||||
else:
|
||||
return f"讨论编程开发、软件技术、代码编写、技术实现"
|
||||
|
||||
# 情感表达类标签(具体化为真实对话场景)
|
||||
elif any(word in tag_lower for word in ['治愈', '撒娇', '安慰', '呼噜', '蹭', '卖萌']):
|
||||
return f"想要获得安慰、寻求温暖关怀、撒娇卖萌、表达亲昵、求抱抱求陪伴的对话"
|
||||
|
||||
# 游戏娱乐类标签(具体游戏场景)
|
||||
elif any(word in tag_lower for word in ['游戏', '网游', 'mmo', '游', '玩']):
|
||||
return f"讨论网络游戏、MMO游戏、游戏玩法、组队打副本、游戏攻略心得"
|
||||
|
||||
# 动漫影视类标签(具体观看行为)
|
||||
elif any(word in tag_lower for word in ['番', '动漫', '视频', 'b站', '弹幕', '追番', '云新番']):
|
||||
# 特别处理"云新番" - 它的意思是在网上看新动漫,不是泛泛的"新东西"
|
||||
if '云' in tag_lower or '新番' in tag_lower:
|
||||
return f"讨论正在播出的新动漫、新番剧集、动漫剧情、追番心得、动漫角色"
|
||||
else:
|
||||
return f"讨论动漫番剧内容、B站视频、弹幕文化、追番体验"
|
||||
|
||||
# 社交平台类标签(具体平台行为)
|
||||
elif any(word in tag_lower for word in ['小红书', '贴吧', '论坛', '社区', '吃瓜', '八卦']):
|
||||
if '吃瓜' in tag_lower:
|
||||
return f"聊八卦爆料、吃瓜看热闹、网络热点事件、社交平台热议话题"
|
||||
else:
|
||||
return f"讨论社交平台内容、网络社区话题、论坛讨论、分享生活"
|
||||
|
||||
# 生活日常类标签(具体萌宠场景)
|
||||
elif any(word in tag_lower for word in ['猫', '宠物', '尾巴', '耳朵', '毛绒']):
|
||||
return f"讨论猫咪宠物、晒猫分享、萌宠日常、可爱猫猫、养猫心得"
|
||||
|
||||
# 状态心情类标签(具体情绪状态)
|
||||
elif any(word in tag_lower for word in ['社恐', '隐身', '流浪', '深夜', '被窝']):
|
||||
if '社恐' in tag_lower:
|
||||
return f"表达社交焦虑、不想见人、想躲起来、害怕社交的心情"
|
||||
elif '深夜' in tag_lower:
|
||||
return f"深夜睡不着、熬夜、夜猫子、深夜思考人生的对话"
|
||||
else:
|
||||
return f"表达当前心情状态、个人感受、生活状态"
|
||||
|
||||
# 物品装备类标签(具体使用场景)
|
||||
elif any(word in tag_lower for word in ['键盘', '耳机', '装备', '设备']):
|
||||
return f"讨论键盘耳机装备、数码产品、使用体验、装备推荐评测"
|
||||
|
||||
# 互动关系类标签
|
||||
elif any(word in tag_lower for word in ['拾风', '互怼', '互动']):
|
||||
return f"聊天互动、开玩笑、友好互怼、日常对话交流"
|
||||
|
||||
# 默认:尽量具体化
|
||||
else:
|
||||
return f"明确讨论{tag_name}这个特定主题的具体内容和相关话题"
|
||||
|
||||
def _calculate_keyword_match_bonus(self, keywords: list[str], matched_tags: list[str]) -> dict[str, float]:
|
||||
"""计算关键词直接匹配奖励"""
|
||||
if not keywords or not matched_tags:
|
||||
@@ -668,11 +846,12 @@ class BotInterestManager:
|
||||
last_updated=db_interests.last_updated,
|
||||
)
|
||||
|
||||
# 解析兴趣标签
|
||||
# 解析兴趣标签(embedding 从数据库加载后会被忽略,因为我们不再存储它)
|
||||
for tag_data in tags_data:
|
||||
tag = BotInterestTag(
|
||||
tag_name=tag_data.get("tag_name", ""),
|
||||
weight=tag_data.get("weight", 0.5),
|
||||
expanded=tag_data.get("expanded"), # 加载扩展描述
|
||||
created_at=datetime.fromisoformat(
|
||||
tag_data.get("created_at", datetime.now().isoformat())
|
||||
),
|
||||
@@ -680,11 +859,11 @@ class BotInterestManager:
|
||||
tag_data.get("updated_at", datetime.now().isoformat())
|
||||
),
|
||||
is_active=tag_data.get("is_active", True),
|
||||
embedding=tag_data.get("embedding"),
|
||||
embedding=None, # 不再从数据库加载 embedding,改为动态生成
|
||||
)
|
||||
interests.interest_tags.append(tag)
|
||||
|
||||
logger.debug(f"成功解析 {len(interests.interest_tags)} 个兴趣标签")
|
||||
logger.debug(f"成功解析 {len(interests.interest_tags)} 个兴趣标签(embedding 将在初始化时动态生成)")
|
||||
return interests
|
||||
|
||||
except (orjson.JSONDecodeError, Exception) as e:
|
||||
@@ -715,16 +894,17 @@ class BotInterestManager:
|
||||
from src.common.database.compatibility import get_db_session
|
||||
from src.common.database.core.models import BotPersonalityInterests as DBBotPersonalityInterests
|
||||
|
||||
# 将兴趣标签转换为JSON格式
|
||||
# 将兴趣标签转换为JSON格式(不再保存embedding,启动时动态生成)
|
||||
tags_data = []
|
||||
for tag in interests.interest_tags:
|
||||
tag_dict = {
|
||||
"tag_name": tag.tag_name,
|
||||
"weight": tag.weight,
|
||||
"expanded": tag.expanded, # 保存扩展描述
|
||||
"created_at": tag.created_at.isoformat(),
|
||||
"updated_at": tag.updated_at.isoformat(),
|
||||
"is_active": tag.is_active,
|
||||
"embedding": tag.embedding,
|
||||
# embedding 不再存储到数据库,改为内存缓存
|
||||
}
|
||||
tags_data.append(tag_dict)
|
||||
|
||||
|
||||
@@ -196,10 +196,18 @@ async def _process_single_segment(segment: Seg, state: dict, message_info: BaseM
|
||||
state["is_emoji"] = False
|
||||
state["is_video"] = False
|
||||
state["is_at"] = True
|
||||
# 处理at消息,格式为"昵称:QQ号"
|
||||
if isinstance(segment.data, str) and ":" in segment.data:
|
||||
nickname, qq_id = segment.data.split(":", 1)
|
||||
return f"@{nickname}"
|
||||
# 处理at消息,格式为"@<昵称:QQ号>"
|
||||
if isinstance(segment.data, str):
|
||||
if ":" in segment.data:
|
||||
# 标准格式: "昵称:QQ号"
|
||||
nickname, qq_id = segment.data.split(":", 1)
|
||||
result = f"@<{nickname}:{qq_id}>"
|
||||
logger.info(f"[at处理] 标准格式 -> {result}")
|
||||
return result
|
||||
else:
|
||||
logger.warning(f"[at处理] 无法解析格式: '{segment.data}'")
|
||||
return f"@{segment.data}"
|
||||
logger.warning(f"[at处理] 数据类型异常: {type(segment.data)}")
|
||||
return f"@{segment.data}" if isinstance(segment.data, str) else "@未知用户"
|
||||
|
||||
elif segment.type == "image":
|
||||
|
||||
@@ -49,23 +49,22 @@ def is_mentioned_bot_in_message(message) -> tuple[bool, float]:
|
||||
message: DatabaseMessages 消息对象
|
||||
|
||||
Returns:
|
||||
tuple[bool, float]: (是否提及, 提及概率)
|
||||
tuple[bool, float]: (是否提及, 提及类型)
|
||||
提及类型: 0=未提及, 1=弱提及(文本匹配), 2=强提及(@/回复/私聊)
|
||||
"""
|
||||
keywords = [global_config.bot.nickname]
|
||||
nicknames = global_config.bot.alias_names
|
||||
reply_probability = 0.0
|
||||
is_at = False
|
||||
is_mentioned = False
|
||||
mention_type = 0 # 0=未提及, 1=弱提及, 2=强提及
|
||||
|
||||
# 检查 is_mentioned 属性
|
||||
# 检查 is_mentioned 属性(保持向后兼容)
|
||||
mentioned_attr = getattr(message, "is_mentioned", None)
|
||||
if mentioned_attr is not None:
|
||||
try:
|
||||
return bool(mentioned_attr), float(mentioned_attr)
|
||||
# 如果已有 is_mentioned,直接返回(假设是强提及)
|
||||
return bool(mentioned_attr), 2.0 if mentioned_attr else 0.0
|
||||
except (ValueError, TypeError):
|
||||
pass
|
||||
|
||||
# 检查 additional_config
|
||||
# 检查 additional_config(保持向后兼容)
|
||||
additional_config = None
|
||||
|
||||
# DatabaseMessages: additional_config 是 JSON 字符串
|
||||
@@ -78,62 +77,66 @@ def is_mentioned_bot_in_message(message) -> tuple[bool, float]:
|
||||
|
||||
if additional_config and additional_config.get("is_mentioned") is not None:
|
||||
try:
|
||||
reply_probability = float(additional_config.get("is_mentioned")) # type: ignore
|
||||
is_mentioned = True
|
||||
return is_mentioned, reply_probability
|
||||
mentioned_value = float(additional_config.get("is_mentioned")) # type: ignore
|
||||
# 如果配置中有提及值,假设是强提及
|
||||
return True, 2.0 if mentioned_value > 0 else 0.0
|
||||
except Exception as e:
|
||||
logger.warning(str(e))
|
||||
logger.warning(
|
||||
f"消息中包含不合理的设置 is_mentioned: {additional_config.get('is_mentioned')}"
|
||||
)
|
||||
|
||||
# 检查消息文本内容
|
||||
processed_text = message.processed_plain_text or ""
|
||||
if global_config.bot.nickname in processed_text:
|
||||
is_mentioned = True
|
||||
|
||||
for alias_name in global_config.bot.alias_names:
|
||||
if alias_name in processed_text:
|
||||
is_mentioned = True
|
||||
# 1. 判断是否为私聊(强提及)
|
||||
group_info = getattr(message, "group_info", None)
|
||||
if not group_info or not getattr(group_info, "group_id", None):
|
||||
is_private = True
|
||||
mention_type = 2
|
||||
logger.debug("检测到私聊消息 - 强提及")
|
||||
|
||||
# 判断是否被@
|
||||
if re.search(rf"@<(.+?):{global_config.bot.qq_account}>", message.processed_plain_text):
|
||||
# 2. 判断是否被@(强提及)
|
||||
if re.search(rf"@<(.+?):{global_config.bot.qq_account}>", processed_text):
|
||||
is_at = True
|
||||
is_mentioned = True
|
||||
mention_type = 2
|
||||
logger.debug("检测到@提及 - 强提及")
|
||||
|
||||
# print(f"message.processed_plain_text: {message.processed_plain_text}")
|
||||
# print(f"is_mentioned: {is_mentioned}")
|
||||
# print(f"is_at: {is_at}")
|
||||
# 3. 判断是否被回复(强提及)
|
||||
if re.match(
|
||||
rf"\[回复 (.+?)\({global_config.bot.qq_account!s}\):(.+?)\],说:", processed_text
|
||||
) or re.match(
|
||||
rf"\[回复<(.+?)(?=:{global_config.bot.qq_account!s}>)\:{global_config.bot.qq_account!s}>:(.+?)\],说:",
|
||||
processed_text,
|
||||
):
|
||||
is_replied = True
|
||||
mention_type = 2
|
||||
logger.debug("检测到回复消息 - 强提及")
|
||||
|
||||
if is_at and global_config.chat.at_bot_inevitable_reply:
|
||||
reply_probability = 1.0
|
||||
logger.debug("被@,回复概率设置为100%")
|
||||
else:
|
||||
if not is_mentioned:
|
||||
# 判断是否被回复
|
||||
if re.match(
|
||||
rf"\[回复 (.+?)\({global_config.bot.qq_account!s}\):(.+?)\],说:", message.processed_plain_text
|
||||
) or re.match(
|
||||
rf"\[回复<(.+?)(?=:{global_config.bot.qq_account!s}>)\:{global_config.bot.qq_account!s}>:(.+?)\],说:",
|
||||
message.processed_plain_text,
|
||||
):
|
||||
is_mentioned = True
|
||||
else:
|
||||
# 判断内容中是否被提及
|
||||
message_content = re.sub(r"@(.+?)((\d+))", "", message.processed_plain_text)
|
||||
message_content = re.sub(r"@<(.+?)(?=:(\d+))\:(\d+)>", "", message_content)
|
||||
message_content = re.sub(r"\[回复 (.+?)\(((\d+)|未知id)\):(.+?)\],说:", "", message_content)
|
||||
message_content = re.sub(r"\[回复<(.+?)(?=:(\d+))\:(\d+)>:(.+?)\],说:", "", message_content)
|
||||
for keyword in keywords:
|
||||
if keyword in message_content:
|
||||
is_mentioned = True
|
||||
for nickname in nicknames:
|
||||
if nickname in message_content:
|
||||
is_mentioned = True
|
||||
if is_mentioned and global_config.chat.mentioned_bot_inevitable_reply:
|
||||
reply_probability = 1.0
|
||||
logger.debug("被提及,回复概率设置为100%")
|
||||
return is_mentioned, reply_probability
|
||||
# 4. 判断文本中是否提及bot名字或别名(弱提及)
|
||||
if mention_type == 0: # 只有在没有强提及时才检查弱提及
|
||||
# 移除@和回复标记后再检查
|
||||
message_content = re.sub(r"@(.+?)((\d+))", "", processed_text)
|
||||
message_content = re.sub(r"@<(.+?)(?=:(\d+))\:(\d+)>", "", message_content)
|
||||
message_content = re.sub(r"\[回复 (.+?)\(((\d+)|未知id)\):(.+?)\],说:", "", message_content)
|
||||
message_content = re.sub(r"\[回复<(.+?)(?=:(\d+))\:(\d+)>:(.+?)\],说:", "", message_content)
|
||||
|
||||
# 检查bot主名字
|
||||
if global_config.bot.nickname in message_content:
|
||||
is_text_mentioned = True
|
||||
mention_type = 1
|
||||
logger.debug(f"检测到文本提及bot主名字 '{global_config.bot.nickname}' - 弱提及")
|
||||
# 如果主名字没匹配,再检查别名
|
||||
elif nicknames:
|
||||
for alias_name in nicknames:
|
||||
if alias_name in message_content:
|
||||
is_text_mentioned = True
|
||||
mention_type = 1
|
||||
logger.debug(f"检测到文本提及bot别名 '{alias_name}' - 弱提及")
|
||||
break
|
||||
|
||||
# 返回结果
|
||||
is_mentioned = mention_type > 0
|
||||
return is_mentioned, float(mention_type)
|
||||
|
||||
async def get_embedding(text, request_type="embedding") -> list[float] | None:
|
||||
"""获取文本的embedding向量"""
|
||||
|
||||
@@ -16,6 +16,7 @@ class BotInterestTag(BaseDataModel):
|
||||
|
||||
tag_name: str
|
||||
weight: float = 1.0 # 权重,表示对这个兴趣的喜好程度 (0.0-1.0)
|
||||
expanded: str | None = None # 标签的扩展描述,用于更精准的语义匹配
|
||||
embedding: list[float] | None = None # 标签的embedding向量
|
||||
created_at: datetime = field(default_factory=datetime.now)
|
||||
updated_at: datetime = field(default_factory=datetime.now)
|
||||
@@ -26,6 +27,7 @@ class BotInterestTag(BaseDataModel):
|
||||
return {
|
||||
"tag_name": self.tag_name,
|
||||
"weight": self.weight,
|
||||
"expanded": self.expanded,
|
||||
"embedding": self.embedding,
|
||||
"created_at": self.created_at.isoformat(),
|
||||
"updated_at": self.updated_at.isoformat(),
|
||||
@@ -38,6 +40,7 @@ class BotInterestTag(BaseDataModel):
|
||||
return cls(
|
||||
tag_name=data["tag_name"],
|
||||
weight=data.get("weight", 1.0),
|
||||
expanded=data.get("expanded"),
|
||||
embedding=data.get("embedding"),
|
||||
created_at=datetime.fromisoformat(data["created_at"]) if data.get("created_at") else datetime.now(),
|
||||
updated_at=datetime.fromisoformat(data["updated_at"]) if data.get("updated_at") else datetime.now(),
|
||||
|
||||
@@ -703,6 +703,12 @@ class AffinityFlowConfig(ValidatedConfigBase):
|
||||
reply_cooldown_reduction: int = Field(default=2, description="回复后减少的不回复计数")
|
||||
max_no_reply_count: int = Field(default=5, description="最大不回复计数次数")
|
||||
|
||||
# 回复后连续对话机制参数
|
||||
enable_post_reply_boost: bool = Field(default=True, description="是否启用回复后阈值降低机制,使bot在回复后更容易进行连续对话")
|
||||
post_reply_threshold_reduction: float = Field(default=0.15, description="回复后初始阈值降低值(建议0.1-0.2)")
|
||||
post_reply_boost_max_count: int = Field(default=3, description="回复后阈值降低的最大持续次数(建议2-5)")
|
||||
post_reply_boost_decay_rate: float = Field(default=0.5, description="每次回复后阈值降低衰减率(0-1,建议0.3-0.7)")
|
||||
|
||||
# 综合评分权重
|
||||
keyword_match_weight: float = Field(default=0.4, description="兴趣关键词匹配度权重")
|
||||
mention_bot_weight: float = Field(default=0.3, description="提及bot分数权重")
|
||||
@@ -710,7 +716,9 @@ class AffinityFlowConfig(ValidatedConfigBase):
|
||||
|
||||
# 提及bot相关参数
|
||||
mention_bot_adjustment_threshold: float = Field(default=0.3, description="提及bot后的调整阈值")
|
||||
mention_bot_interest_score: float = Field(default=0.6, description="提及bot的兴趣分")
|
||||
mention_bot_interest_score: float = Field(default=0.6, description="提及bot的兴趣分(已弃用,改用strong/weak_mention)")
|
||||
strong_mention_interest_score: float = Field(default=2.5, description="强提及的兴趣分(被@、被回复、私聊)")
|
||||
weak_mention_interest_score: float = Field(default=1.5, description="弱提及的兴趣分(文本匹配bot名字或别名)")
|
||||
base_relationship_score: float = Field(default=0.5, description="基础人物关系分")
|
||||
|
||||
# 关系追踪系统参数
|
||||
|
||||
@@ -33,9 +33,14 @@ class Individuality:
|
||||
personality_side = global_config.personality.personality_side
|
||||
identity = global_config.personality.identity
|
||||
|
||||
person_info_manager = get_person_info_manager()
|
||||
self.bot_person_id = person_info_manager.get_person_id("system", "bot_id")
|
||||
# 基于人设文本生成 personality_id(使用 MD5 hash)
|
||||
# 这样当人设发生变化时会自动生成新的 ID,触发重新生成兴趣标签
|
||||
personality_hash, _ = self._get_config_hash(bot_nickname, personality_core, personality_side, identity)
|
||||
self.bot_person_id = personality_hash
|
||||
self.name = bot_nickname
|
||||
logger.info(f"生成的 personality_id: {self.bot_person_id[:16]}... (基于人设文本 hash)")
|
||||
|
||||
person_info_manager = get_person_info_manager()
|
||||
|
||||
# 检查配置变化,如果变化则清空
|
||||
personality_changed, identity_changed = await self._check_config_and_clear_if_changed(
|
||||
@@ -72,8 +77,8 @@ class Individuality:
|
||||
if personality_changed or identity_changed:
|
||||
logger.info("将清空数据库中原有的关键词缓存")
|
||||
update_data = {
|
||||
"platform": "system",
|
||||
"user_id": "bot_id",
|
||||
"platform": "personality",
|
||||
"user_id": self.bot_person_id, # 使用基于人设生成的 ID
|
||||
"person_name": self.name,
|
||||
"nickname": self.name,
|
||||
}
|
||||
@@ -171,8 +176,8 @@ class Individuality:
|
||||
if personality_changed or identity_changed:
|
||||
logger.info("将清空原有的关键词缓存")
|
||||
update_data = {
|
||||
"platform": "system",
|
||||
"user_id": "bot_id",
|
||||
"platform": "personality",
|
||||
"user_id": current_personality_hash, # 使用 personality hash 作为 user_id
|
||||
"person_name": self.name,
|
||||
"nickname": self.name,
|
||||
}
|
||||
|
||||
10
src/plugins/built_in/affinity_flow_chatter/core/__init__.py
Normal file
10
src/plugins/built_in/affinity_flow_chatter/core/__init__.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""
|
||||
AffinityFlow Chatter 核心模块
|
||||
|
||||
包含兴趣度计算器和核心对话处理逻辑
|
||||
"""
|
||||
|
||||
from .affinity_chatter import AffinityChatter
|
||||
from .affinity_interest_calculator import AffinityInterestCalculator
|
||||
|
||||
__all__ = ["AffinityChatter", "AffinityInterestCalculator"]
|
||||
@@ -15,7 +15,7 @@ from src.common.data_models.message_manager_data_model import StreamContext
|
||||
from src.common.logger import get_logger
|
||||
from src.plugin_system.base.base_chatter import BaseChatter
|
||||
from src.plugin_system.base.component_types import ChatType
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner import ChatterActionPlanner
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner.planner import ChatterActionPlanner
|
||||
|
||||
logger = get_logger("affinity_chatter")
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
基于原有的 AffinityFlow 兴趣度评分系统,提供标准化的兴趣值计算功能
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import time
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
@@ -60,10 +61,18 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
# 用户关系数据缓存
|
||||
self.user_relationships: dict[str, float] = {} # user_id -> relationship_score
|
||||
|
||||
# 回复后阈值降低机制
|
||||
self.enable_post_reply_boost = affinity_config.enable_post_reply_boost
|
||||
self.post_reply_boost_remaining = 0 # 剩余的回复后降低次数
|
||||
self.post_reply_threshold_reduction = affinity_config.post_reply_threshold_reduction
|
||||
self.post_reply_boost_max_count = affinity_config.post_reply_boost_max_count
|
||||
self.post_reply_boost_decay_rate = affinity_config.post_reply_boost_decay_rate
|
||||
|
||||
logger.info("[Affinity兴趣计算器] 初始化完成:")
|
||||
logger.info(f" - 权重配置: {self.score_weights}")
|
||||
logger.info(f" - 回复阈值: {self.reply_threshold}")
|
||||
logger.info(f" - 智能匹配: {self.use_smart_matching}")
|
||||
logger.info(f" - 回复后连续对话: {self.enable_post_reply_boost}")
|
||||
|
||||
# 检查 bot_interest_manager 状态
|
||||
try:
|
||||
@@ -120,22 +129,23 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
f"{mentioned_score:.3f}*{self.score_weights['mentioned']} = {total_score:.3f}"
|
||||
)
|
||||
|
||||
# 5. 考虑连续不回复的概率提升
|
||||
adjusted_score = self._apply_no_reply_boost(total_score)
|
||||
logger.debug(f"[Affinity兴趣计算] 应用不回复提升后: {total_score:.3f} → {adjusted_score:.3f}")
|
||||
# 5. 考虑连续不回复的阈值调整
|
||||
adjusted_score = total_score
|
||||
adjusted_reply_threshold, adjusted_action_threshold = self._apply_no_reply_threshold_adjustment()
|
||||
logger.debug(
|
||||
f"[Affinity兴趣计算] 连续不回复调整: 回复阈值 {self.reply_threshold:.3f} → {adjusted_reply_threshold:.3f}, "
|
||||
f"动作阈值 {global_config.affinity_flow.non_reply_action_interest_threshold:.3f} → {adjusted_action_threshold:.3f}"
|
||||
)
|
||||
|
||||
# 6. 决定是否回复和执行动作
|
||||
reply_threshold = self.reply_threshold
|
||||
action_threshold = global_config.affinity_flow.non_reply_action_interest_threshold
|
||||
|
||||
should_reply = adjusted_score >= reply_threshold
|
||||
should_take_action = adjusted_score >= action_threshold
|
||||
should_reply = adjusted_score >= adjusted_reply_threshold
|
||||
should_take_action = adjusted_score >= adjusted_action_threshold
|
||||
|
||||
logger.debug(
|
||||
f"[Affinity兴趣计算] 阈值判断: {adjusted_score:.3f} >= 回复阈值:{reply_threshold:.3f}? = {should_reply}"
|
||||
f"[Affinity兴趣计算] 阈值判断: {adjusted_score:.3f} >= 回复阈值:{adjusted_reply_threshold:.3f}? = {should_reply}"
|
||||
)
|
||||
logger.debug(
|
||||
f"[Affinity兴趣计算] 阈值判断: {adjusted_score:.3f} >= 动作阈值:{action_threshold:.3f}? = {should_take_action}"
|
||||
f"[Affinity兴趣计算] 阈值判断: {adjusted_score:.3f} >= 动作阈值:{adjusted_action_threshold:.3f}? = {should_take_action}"
|
||||
)
|
||||
|
||||
calculation_time = time.time() - start_time
|
||||
@@ -162,7 +172,7 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
)
|
||||
|
||||
async def _calculate_interest_match_score(self, content: str, keywords: list[str] | None = None) -> float:
|
||||
"""计算兴趣匹配度(使用智能兴趣匹配系统)"""
|
||||
"""计算兴趣匹配度(使用智能兴趣匹配系统,带超时保护)"""
|
||||
|
||||
# 调试日志:检查各个条件
|
||||
if not content:
|
||||
@@ -178,8 +188,11 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
logger.debug(f"开始兴趣匹配计算,内容: {content[:50]}...")
|
||||
|
||||
try:
|
||||
# 使用机器人的兴趣标签系统进行智能匹配
|
||||
match_result = await bot_interest_manager.calculate_interest_match(content, keywords or [])
|
||||
# 使用机器人的兴趣标签系统进行智能匹配(1.5秒超时保护)
|
||||
match_result = await asyncio.wait_for(
|
||||
bot_interest_manager.calculate_interest_match(content, keywords or []),
|
||||
timeout=1.5
|
||||
)
|
||||
logger.debug(f"兴趣匹配结果: {match_result}")
|
||||
|
||||
if match_result:
|
||||
@@ -195,6 +208,9 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
logger.debug("兴趣匹配返回0.0: match_result为None")
|
||||
return 0.0
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
logger.warning(f"⏱️ 兴趣匹配计算超时(>1.5秒),返回默认分值0.5以保留其他分数")
|
||||
return 0.5 # 超时时返回默认分值,避免丢失提及分和关系分
|
||||
except Exception as e:
|
||||
logger.warning(f"智能兴趣匹配失败: {e}")
|
||||
return 0.0
|
||||
@@ -226,29 +242,78 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
return global_config.affinity_flow.base_relationship_score
|
||||
|
||||
def _calculate_mentioned_score(self, message: "DatabaseMessages", bot_nickname: str) -> float:
|
||||
"""计算提及分 - 统一使用配置值,不区分提及方式"""
|
||||
is_mentioned = getattr(message, "is_mentioned", False)
|
||||
processed_plain_text = getattr(message, "processed_plain_text", "")
|
||||
"""计算提及分 - 区分强提及和弱提及
|
||||
|
||||
# 判断是否为私聊 - 通过 group_info 对象判断
|
||||
is_private_chat = not message.group_info # 如果没有group_info则是私聊
|
||||
强提及(被@、被回复、私聊): 使用 strong_mention_interest_score
|
||||
弱提及(文本匹配名字/别名): 使用 weak_mention_interest_score
|
||||
"""
|
||||
from src.chat.utils.utils import is_mentioned_bot_in_message
|
||||
|
||||
logger.debug(f"[提及分计算] is_mentioned={is_mentioned}, is_private_chat={is_private_chat}, group_info={message.group_info}")
|
||||
# 使用统一的提及检测函数
|
||||
is_mentioned, mention_type = is_mentioned_bot_in_message(message)
|
||||
|
||||
# 检查是否被提及(包括文本匹配)
|
||||
bot_aliases = [bot_nickname, *global_config.bot.alias_names]
|
||||
is_text_mentioned = any(alias in processed_plain_text for alias in bot_aliases if alias)
|
||||
if not is_mentioned:
|
||||
logger.debug("[提及分计算] 未提及机器人,返回0.0")
|
||||
return 0.0
|
||||
|
||||
# 统一判断:只要提及了机器人(包括@、文本提及、私聊)都返回配置的分值
|
||||
if is_mentioned or is_text_mentioned or is_private_chat:
|
||||
logger.debug("[提及分计算] 检测到机器人提及,返回配置分值")
|
||||
return global_config.affinity_flow.mention_bot_interest_score
|
||||
# mention_type: 0=未提及, 1=弱提及, 2=强提及
|
||||
if mention_type >= 2:
|
||||
# 强提及:被@、被回复、私聊
|
||||
score = global_config.affinity_flow.strong_mention_interest_score
|
||||
logger.debug(f"[提及分计算] 检测到强提及(@/回复/私聊),返回分值: {score}")
|
||||
return score
|
||||
elif mention_type >= 1:
|
||||
# 弱提及:文本匹配bot名字或别名
|
||||
score = global_config.affinity_flow.weak_mention_interest_score
|
||||
logger.debug(f"[提及分计算] 检测到弱提及(文本匹配),返回分值: {score}")
|
||||
return score
|
||||
else:
|
||||
logger.debug("[提及分计算] 未提及机器人,返回0.0")
|
||||
return 0.0 # 未提及机器人
|
||||
return 0.0
|
||||
|
||||
def _apply_no_reply_threshold_adjustment(self) -> tuple[float, float]:
|
||||
"""应用阈值调整(包括连续不回复和回复后降低机制)
|
||||
|
||||
Returns:
|
||||
tuple[float, float]: (调整后的回复阈值, 调整后的动作阈值)
|
||||
"""
|
||||
# 基础阈值
|
||||
base_reply_threshold = self.reply_threshold
|
||||
base_action_threshold = global_config.affinity_flow.non_reply_action_interest_threshold
|
||||
|
||||
total_reduction = 0.0
|
||||
|
||||
# 1. 连续不回复的阈值降低
|
||||
if self.no_reply_count > 0 and self.no_reply_count < self.max_no_reply_count:
|
||||
no_reply_reduction = self.no_reply_count * self.probability_boost_per_no_reply
|
||||
total_reduction += no_reply_reduction
|
||||
logger.debug(f"[阈值调整] 连续不回复降低: {no_reply_reduction:.3f} (计数: {self.no_reply_count})")
|
||||
|
||||
# 2. 回复后的阈值降低(使bot更容易连续对话)
|
||||
if self.enable_post_reply_boost and self.post_reply_boost_remaining > 0:
|
||||
# 计算衰减后的降低值
|
||||
decay_factor = self.post_reply_boost_decay_rate ** (
|
||||
self.post_reply_boost_max_count - self.post_reply_boost_remaining
|
||||
)
|
||||
post_reply_reduction = self.post_reply_threshold_reduction * decay_factor
|
||||
total_reduction += post_reply_reduction
|
||||
logger.debug(
|
||||
f"[阈值调整] 回复后降低: {post_reply_reduction:.3f} "
|
||||
f"(剩余次数: {self.post_reply_boost_remaining}, 衰减: {decay_factor:.2f})"
|
||||
)
|
||||
|
||||
# 应用总降低量
|
||||
adjusted_reply_threshold = max(0.0, base_reply_threshold - total_reduction)
|
||||
adjusted_action_threshold = max(0.0, base_action_threshold - total_reduction)
|
||||
|
||||
return adjusted_reply_threshold, adjusted_action_threshold
|
||||
|
||||
def _apply_no_reply_boost(self, base_score: float) -> float:
|
||||
"""应用连续不回复的概率提升"""
|
||||
"""【已弃用】应用连续不回复的概率提升
|
||||
|
||||
注意:此方法已被 _apply_no_reply_threshold_adjustment 替代
|
||||
保留用于向后兼容
|
||||
"""
|
||||
if self.no_reply_count > 0 and self.no_reply_count < self.max_no_reply_count:
|
||||
boost = self.no_reply_count * self.probability_boost_per_no_reply
|
||||
return min(1.0, base_score + boost)
|
||||
@@ -315,3 +380,34 @@ class AffinityInterestCalculator(BaseInterestCalculator):
|
||||
self.no_reply_count = 0
|
||||
else:
|
||||
self.no_reply_count = min(self.no_reply_count + 1, self.max_no_reply_count)
|
||||
|
||||
def on_reply_sent(self):
|
||||
"""当机器人发送回复后调用,激活回复后阈值降低机制"""
|
||||
if self.enable_post_reply_boost:
|
||||
# 重置回复后降低计数器
|
||||
self.post_reply_boost_remaining = self.post_reply_boost_max_count
|
||||
logger.debug(
|
||||
f"[回复后机制] 激活连续对话模式,阈值将在接下来 {self.post_reply_boost_max_count} 条消息中降低"
|
||||
)
|
||||
# 同时重置不回复计数
|
||||
self.no_reply_count = 0
|
||||
|
||||
def on_message_processed(self, replied: bool):
|
||||
"""消息处理完成后调用,更新各种计数器
|
||||
|
||||
Args:
|
||||
replied: 是否回复了此消息
|
||||
"""
|
||||
# 更新不回复计数
|
||||
self.update_no_reply_count(replied)
|
||||
|
||||
# 如果已回复,激活回复后降低机制
|
||||
if replied:
|
||||
self.on_reply_sent()
|
||||
else:
|
||||
# 如果没有回复,减少回复后降低剩余次数
|
||||
if self.post_reply_boost_remaining > 0:
|
||||
self.post_reply_boost_remaining -= 1
|
||||
logger.debug(
|
||||
f"[回复后机制] 未回复消息,剩余降低次数: {self.post_reply_boost_remaining}"
|
||||
)
|
||||
@@ -0,0 +1,13 @@
|
||||
"""
|
||||
AffinityFlow Chatter 规划器模块
|
||||
|
||||
包含计划生成、过滤、执行等规划相关功能
|
||||
"""
|
||||
|
||||
from .plan_executor import ChatterPlanExecutor
|
||||
from .plan_filter import ChatterPlanFilter
|
||||
from .plan_generator import ChatterPlanGenerator
|
||||
from .planner import ChatterActionPlanner
|
||||
from . import planner_prompts
|
||||
|
||||
__all__ = ["ChatterActionPlanner", "planner_prompts", "ChatterPlanGenerator", "ChatterPlanFilter", "ChatterPlanExecutor"]
|
||||
@@ -11,9 +11,9 @@ from src.common.logger import get_logger
|
||||
from src.config.config import global_config
|
||||
from src.mood.mood_manager import mood_manager
|
||||
from src.plugin_system.base.component_types import ChatMode
|
||||
from src.plugins.built_in.affinity_flow_chatter.plan_executor import ChatterPlanExecutor
|
||||
from src.plugins.built_in.affinity_flow_chatter.plan_filter import ChatterPlanFilter
|
||||
from src.plugins.built_in.affinity_flow_chatter.plan_generator import ChatterPlanGenerator
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner.plan_executor import ChatterPlanExecutor
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner.plan_filter import ChatterPlanFilter
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner.plan_generator import ChatterPlanGenerator
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from src.chat.planner_actions.action_manager import ChatterActionManager
|
||||
@@ -21,7 +21,7 @@ if TYPE_CHECKING:
|
||||
from src.common.data_models.message_manager_data_model import StreamContext
|
||||
|
||||
# 导入提示词模块以确保其被初始化
|
||||
from src.plugins.built_in.affinity_flow_chatter import planner_prompts # noqa
|
||||
from src.plugins.built_in.affinity_flow_chatter.planner import planner_prompts
|
||||
|
||||
logger = get_logger("planner")
|
||||
|
||||
@@ -39,48 +39,48 @@ class AffinityChatterPlugin(BasePlugin):
|
||||
components: ClassVar = []
|
||||
|
||||
try:
|
||||
# 延迟导入 AffinityChatter
|
||||
from .affinity_chatter import AffinityChatter
|
||||
# 延迟导入 AffinityChatter(从 core 子模块)
|
||||
from .core.affinity_chatter import AffinityChatter
|
||||
|
||||
components.append((AffinityChatter.get_chatter_info(), AffinityChatter))
|
||||
except Exception as e:
|
||||
logger.error(f"加载 AffinityChatter 时出错: {e}")
|
||||
|
||||
try:
|
||||
# 延迟导入 AffinityInterestCalculator
|
||||
from .affinity_interest_calculator import AffinityInterestCalculator
|
||||
# 延迟导入 AffinityInterestCalculator(从 core 子模块)
|
||||
from .core.affinity_interest_calculator import AffinityInterestCalculator
|
||||
|
||||
components.append((AffinityInterestCalculator.get_interest_calculator_info(), AffinityInterestCalculator))
|
||||
except Exception as e:
|
||||
logger.error(f"加载 AffinityInterestCalculator 时出错: {e}")
|
||||
|
||||
try:
|
||||
# 延迟导入 UserProfileTool
|
||||
from .user_profile_tool import UserProfileTool
|
||||
# 延迟导入 UserProfileTool(从 tools 子模块)
|
||||
from .tools.user_profile_tool import UserProfileTool
|
||||
|
||||
components.append((UserProfileTool.get_tool_info(), UserProfileTool))
|
||||
except Exception as e:
|
||||
logger.error(f"加载 UserProfileTool 时出错: {e}")
|
||||
|
||||
try:
|
||||
# 延迟导入 ChatStreamImpressionTool
|
||||
from .chat_stream_impression_tool import ChatStreamImpressionTool
|
||||
# 延迟导入 ChatStreamImpressionTool(从 tools 子模块)
|
||||
from .tools.chat_stream_impression_tool import ChatStreamImpressionTool
|
||||
|
||||
components.append((ChatStreamImpressionTool.get_tool_info(), ChatStreamImpressionTool))
|
||||
except Exception as e:
|
||||
logger.error(f"加载 ChatStreamImpressionTool 时出错: {e}")
|
||||
|
||||
try:
|
||||
# 延迟导入 ProactiveThinkingReplyHandler
|
||||
from .proactive_thinking_event import ProactiveThinkingReplyHandler
|
||||
# 延迟导入 ProactiveThinkingReplyHandler(从 proactive 子模块)
|
||||
from .proactive.proactive_thinking_event import ProactiveThinkingReplyHandler
|
||||
|
||||
components.append((ProactiveThinkingReplyHandler.get_handler_info(), ProactiveThinkingReplyHandler))
|
||||
except Exception as e:
|
||||
logger.error(f"加载 ProactiveThinkingReplyHandler 时出错: {e}")
|
||||
|
||||
try:
|
||||
# 延迟导入 ProactiveThinkingMessageHandler
|
||||
from .proactive_thinking_event import ProactiveThinkingMessageHandler
|
||||
# 延迟导入 ProactiveThinkingMessageHandler(从 proactive 子模块)
|
||||
from .proactive.proactive_thinking_event import ProactiveThinkingMessageHandler
|
||||
|
||||
components.append((ProactiveThinkingMessageHandler.get_handler_info(), ProactiveThinkingMessageHandler))
|
||||
except Exception as e:
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
"""
|
||||
AffinityFlow Chatter 主动思考模块
|
||||
|
||||
包含主动思考调度器、执行器和事件处理
|
||||
"""
|
||||
|
||||
from .proactive_thinking_event import ProactiveThinkingMessageHandler, ProactiveThinkingReplyHandler
|
||||
from .proactive_thinking_executor import execute_proactive_thinking
|
||||
from .proactive_thinking_scheduler import ProactiveThinkingScheduler, proactive_thinking_scheduler
|
||||
|
||||
__all__ = [
|
||||
"ProactiveThinkingReplyHandler",
|
||||
"ProactiveThinkingMessageHandler",
|
||||
"execute_proactive_thinking",
|
||||
"ProactiveThinkingScheduler",
|
||||
"proactive_thinking_scheduler",
|
||||
]
|
||||
@@ -9,7 +9,7 @@ from typing import ClassVar
|
||||
from src.common.logger import get_logger
|
||||
from src.plugin_system import BaseEventHandler, EventType
|
||||
from src.plugin_system.base.base_event import HandlerResult
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive_thinking_scheduler import (
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive.proactive_thinking_scheduler import (
|
||||
proactive_thinking_scheduler,
|
||||
)
|
||||
|
||||
@@ -226,7 +226,7 @@ class ProactiveThinkingPlanner:
|
||||
# 5. 获取上次决策
|
||||
last_decision = None
|
||||
try:
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive_thinking_scheduler import (
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive.proactive_thinking_scheduler import (
|
||||
proactive_thinking_scheduler,
|
||||
)
|
||||
|
||||
@@ -520,7 +520,7 @@ async def execute_proactive_thinking(stream_id: str):
|
||||
stream_id: 聊天流ID
|
||||
"""
|
||||
from src.config.config import global_config
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive_thinking_scheduler import (
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive.proactive_thinking_scheduler import (
|
||||
proactive_thinking_scheduler,
|
||||
)
|
||||
|
||||
@@ -256,7 +256,7 @@ class ProactiveThinkingScheduler:
|
||||
logger.debug(f"[调度器] 触发间隔={interval_seconds}秒 ({interval_seconds / 60:.1f}分钟)")
|
||||
|
||||
# 导入回调函数(延迟导入避免循环依赖)
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive_thinking_executor import (
|
||||
from src.plugins.built_in.affinity_flow_chatter.proactive.proactive_thinking_executor import (
|
||||
execute_proactive_thinking,
|
||||
)
|
||||
|
||||
10
src/plugins/built_in/affinity_flow_chatter/tools/__init__.py
Normal file
10
src/plugins/built_in/affinity_flow_chatter/tools/__init__.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""
|
||||
AffinityFlow Chatter 工具模块
|
||||
|
||||
包含各种辅助工具类
|
||||
"""
|
||||
|
||||
from .chat_stream_impression_tool import ChatStreamImpressionTool
|
||||
from .user_profile_tool import UserProfileTool
|
||||
|
||||
__all__ = ["ChatStreamImpressionTool", "UserProfileTool"]
|
||||
@@ -386,6 +386,9 @@ class NapcatAdapterPlugin(BasePlugin):
|
||||
return components
|
||||
|
||||
async def on_plugin_loaded(self):
|
||||
# 初始化数据库表
|
||||
await self._init_database_tables()
|
||||
|
||||
# 设置插件配置
|
||||
message_send_instance.set_plugin_config(self.config)
|
||||
# 设置chunker的插件配置
|
||||
@@ -410,3 +413,18 @@ class NapcatAdapterPlugin(BasePlugin):
|
||||
stream_router.cleanup_interval = config_api.get_plugin_config(self.config, "stream_router.cleanup_interval", 60)
|
||||
|
||||
# 设置其他handler的插件配置(现在由component_registry在注册时自动设置)
|
||||
|
||||
async def _init_database_tables(self):
|
||||
"""初始化插件所需的数据库表"""
|
||||
try:
|
||||
from src.common.database.core.engine import get_engine
|
||||
from .src.database import NapcatBanRecord
|
||||
|
||||
engine = await get_engine()
|
||||
async with engine.begin() as conn:
|
||||
# 创建 napcat_ban_records 表
|
||||
await conn.run_sync(NapcatBanRecord.metadata.create_all)
|
||||
|
||||
logger.info("Napcat 插件数据库表初始化成功")
|
||||
except Exception as e:
|
||||
logger.error(f"Napcat 插件数据库表初始化失败: {e}", exc_info=True)
|
||||
|
||||
@@ -35,13 +35,17 @@ class MetaEventHandler:
|
||||
self_id = message.get("self_id")
|
||||
self.last_heart_beat = time.time()
|
||||
logger.info(f"Bot {self_id} 连接成功")
|
||||
asyncio.create_task(self.check_heartbeat(self_id))
|
||||
# 不在连接时立即启动心跳检查,等第一个心跳包到达后再启动
|
||||
elif event_type == MetaEventType.heartbeat:
|
||||
if message["status"].get("online") and message["status"].get("good"):
|
||||
if not self._interval_checking:
|
||||
asyncio.create_task(self.check_heartbeat())
|
||||
self_id = message.get("self_id")
|
||||
if not self._interval_checking and self_id:
|
||||
# 第一次收到心跳包时才启动心跳检查
|
||||
asyncio.create_task(self.check_heartbeat(self_id))
|
||||
self.last_heart_beat = time.time()
|
||||
self.interval = message.get("interval") / 1000
|
||||
interval = message.get("interval")
|
||||
if interval:
|
||||
self.interval = interval / 1000
|
||||
else:
|
||||
self_id = message.get("self_id")
|
||||
logger.warning(f"Bot {self_id} Napcat 端异常!")
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[inner]
|
||||
version = "7.5.6"
|
||||
version = "7.5.7"
|
||||
|
||||
#----以下是给开发人员阅读的,如果你只是部署了MoFox-Bot,不需要阅读----
|
||||
#如果你想要修改配置文件,请递增version的值
|
||||
@@ -558,6 +558,12 @@ no_reply_threshold_adjustment = 0.01 # 不回复兴趣阈值调整值
|
||||
reply_cooldown_reduction = 5 # 回复后减少的不回复计数
|
||||
max_no_reply_count = 20 # 最大不回复计数次数
|
||||
|
||||
# 回复后连续对话机制参数
|
||||
enable_post_reply_boost = true # 是否启用回复后阈值降低机制,使bot在回复后更容易进行连续对话
|
||||
post_reply_threshold_reduction = 0.15 # 回复后初始阈值降低值(建议0.1-0.2)
|
||||
post_reply_boost_max_count = 3 # 回复后阈值降低的最大持续次数(建议2-5)
|
||||
post_reply_boost_decay_rate = 0.5 # 每次回复后阈值降低衰减率(0-1,建议0.3-0.7)
|
||||
|
||||
# 综合评分权重
|
||||
keyword_match_weight = 0.4 # 兴趣关键词匹配度权重
|
||||
mention_bot_weight = 0.3 # 提及bot分数权重
|
||||
@@ -565,7 +571,9 @@ relationship_weight = 0.3 # 人物关系分数权重
|
||||
|
||||
# 提及bot相关参数
|
||||
mention_bot_adjustment_threshold = 0.5 # 提及bot后的调整阈值
|
||||
mention_bot_interest_score = 2.5 # 提及bot的兴趣分
|
||||
# 强提及(被@、被回复、私聊)和弱提及(文本匹配名字/别名)使用不同分值
|
||||
strong_mention_interest_score = 2.5 # 强提及的兴趣分(被@、被回复、私聊)
|
||||
weak_mention_interest_score = 1.5 # 弱提及的兴趣分(文本匹配bot名字或别名)
|
||||
base_relationship_score = 0.3 # 基础人物关系分
|
||||
|
||||
# 关系追踪系统参数
|
||||
|
||||
Reference in New Issue
Block a user