Release v2.5.2

[Perf] 优化函数调用的底层逻辑

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,51 @@
+name: 漏洞反馈
+description: 报错或漏洞请使用这个模板创建，不使用此模板创建的异常、漏洞相关issue将被直接关闭
+title: "[Bug]: "
+labels: ["bug?"]
+body:
+  - type: dropdown
+    attributes:
+      label: 部署方式
+      description: "主程序使用的部署方式"
+      options:
+        - 手动部署
+        - 安装器部署
+        - 一键安装包部署
+        - Docker部署
+    validations:
+      required: true
+  - type: dropdown
+    attributes:
+      label: 登录框架
+      description: "连接QQ使用的框架"
+      options:
+        - Mirai
+        - go-cqhttp
+    validations:
+      required: false
+  - type: input
+    attributes:
+      label: 系统环境
+      description: 操作系统、系统架构。
+      placeholder: 例如： CentOS x64、Windows11
+    validations:
+      required: true
+  - type: input
+    attributes:
+      label: Python环境
+      description: 运行程序的Python版本
+      placeholder: 例如： Python 3.10
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: 异常情况
+      description: 完整描述异常情况，什么时候发生的、发生了什么
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: 报错信息
+      description: 请提供完整的**控制台**报错信息（若有）
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,21 @@
+name: 需求建议
+title: "[Feature]: "
+labels: ["enhancement"]
+description: "新功能或现有功能优化请使用这个模板；不符合类别的issue将被直接关闭"
+body:
+  - type: dropdown
+    attributes:
+      label: 这是一个？
+      description: 新功能建议还是现有功能优化
+      options:
+        - 新功能
+        - 现有功能优化
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: 详细描述
+      description: 详细描述，越详细越好
+    validations:
+      required: true
+      

.github/ISSUE_TEMPLATE/漏洞反馈.md

@@ -1,24 +0,0 @@
----
-name: 漏洞反馈
-about: 报错或漏洞请使用这个模板创建
-title: "[BUG]"
-labels: 'bug'
-assignees: ''
-
----
-
-请认真按照实际情况填写以下信息！！！！
-
-**运行环境**
-- 部署方式：
-    手动部署/自动部署/Docker部署
-- 系统环境：
-    例如： Centos x64
-- Python环境（仅手动部署填写）：
-    例如： Python 3.10.9
-
-**描述漏洞**  
-什么时候发生的，mirai还是主程序，越详细越好
-
-**完整报错信息**  
-完整的报错信息

.github/ISSUE_TEMPLATE/需求建议.md

@@ -1,10 +0,0 @@
----
-name: 需求建议
-about: 软件优化建议请使用这个模板创建
-title: "[ENHANCE]"
-labels: 'enhancement'
-assignees: ''
-
----
-
-不是需求建议请勿填写此模板！！！！

.github/pull_request_template.md

@@ -0,0 +1,25 @@
+## 概述
+
+实现/解决/优化的内容: 
+
+### 事务
+
+- [ ] 已阅读仓库[贡献指引](https://github.com/RockChinQ/QChatGPT/blob/master/CONTRIBUTING.md)
+- [ ] 已与维护者在issues或其他平台沟通此PR大致内容
+
+## 以下内容可在起草PR后、合并PR前逐步完成
+
+### 功能
+
+- [ ] 已编写完善的配置文件字段说明（若有新增）
+- [ ] 已编写面向用户的新功能说明（若有必要）
+- [ ] 已测试新功能或更改
+
+### 兼容性
+
+- [ ] 已处理版本兼容性
+- [ ] 已处理插件兼容问题
+
+### 风险
+
+可能导致或已知的问题: 

.github/workflows/sync-wiki.yml

@@ -0,0 +1,45 @@
+name: Update Wiki
+
+on:
+  pull_request:
+    branches:
+      - master
+    paths:
+      - 'res/wiki/**'
+  push:
+    branches:
+      - master
+    paths:
+      - 'res/wiki/**'
+
+jobs:
+  update-wiki:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+    - name: Setup Git
+      run: |
+        git config --global user.name "GitHub Actions"
+        git config --global user.email "github-actions[bot]@users.noreply.github.com"
+    - name: Clone Wiki Repository
+      uses: actions/checkout@v2
+      with:
+        repository: RockChinQ/QChatGPT.wiki
+        path: wiki
+    - name: Copy res/wiki content to wiki
+      run: |
+        cp -r res/wiki/* wiki/
+    - name: Check for changes
+      run: |
+        cd wiki
+        if git diff --quiet; then
+          echo "No changes to commit."
+          exit 0
+        fi
+    - name: Commit and Push Changes
+      run: |
+        cd wiki
+        git add .
+        git commit -m "Update wiki"
+        git push

.github/workflows/update-cmdpriv-template.yml

@@ -0,0 +1,58 @@
+name: Update cmdpriv-template
+
+on:
+  push:
+    paths:
+      - 'pkg/qqbot/cmds/**'
+  pull_request:
+    types: [closed]
+    paths:
+      - 'pkg/qqbot/cmds/**'
+
+jobs:
+  update-cmdpriv-template:
+    if: github.event.pull_request.merged == true || github.event_name == 'push'
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.x
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install --upgrade  yiri-mirai openai colorlog func_timeout dulwich Pillow CallingGPT tiktoken
+
+    - name: Copy Scripts
+      run: |
+        cp res/scripts/generate_cmdpriv_template.py .  
+
+    - name: Generate Files
+      run: |
+        python main.py
+
+    - name: Run generate_cmdpriv_template.py
+      run: python3 generate_cmdpriv_template.py
+
+    - name: Check for changes in cmdpriv-template.json
+      id: check_changes
+      run: |
+        if git diff --name-only | grep -q "res/templates/cmdpriv-template.json"; then
+          echo "::set-output name=changes_detected::true"
+        else
+          echo "::set-output name=changes_detected::false"
+        fi
+
+    - name: Commit changes to cmdpriv-template.json
+      if: steps.check_changes.outputs.changes_detected == 'true'
+      run: |
+        git config --global user.name "GitHub Actions Bot"
+        git config --global user.email "<github-actions@github.com>"
+        git add res/templates/cmdpriv-template.json
+        git commit -m "Update cmdpriv-template.json"
+        git push

.github/workflows/update-override-all.yml

@@ -0,0 +1,53 @@
+name: Check and Update override_all
+
+on:
+  push:
+    paths:
+      - 'config-template.py'
+  pull_request:
+    types:
+      - closed
+    branches:
+      - master
+    paths:
+      - 'config-template.py'
+
+jobs:
+  update-override-all:
+    name: check and update
+    if: github.event.pull_request.merged == true || github.event_name == 'push'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.x
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # 在此处添加您的项目所需的其他依赖
+
+      - name: Copy Scripts
+        run: |
+          cp res/scripts/generate_override_all.py .
+
+      - name: Run generate_override_all.py
+        run: python3 generate_override_all.py
+
+      - name: Check for changes in override-all.json
+        id: check_changes
+        run: |
+          git diff --exit-code override-all.json || echo "::set-output name=changes_detected::true"
+
+      - name: Commit and push changes
+        if: steps.check_changes.outputs.changes_detected == 'true'
+        run: |
+          git config --global user.email "github-actions[bot]@users.noreply.github.com"
+          git config --global user.name "GitHub Actions"
+          git add override-all.json
+          git commit -m "Update override-all.json"
+          git push

.gitignore

@@ -3,10 +3,28 @@ config.py
 __pycache__/
 database.db
 qchatgpt.log
-config.py
 /banlist.py
 plugins/
 !plugins/__init__.py
 /revcfg.py
 prompts/
-logs/
+logs/
+sensitive.json
+temp/
+current_tag
+scenario/
+!scenario/default-template.json
+override.json
+cookies.json
+res/announcement_saved
+res/announcement_saved.json
+cmdpriv.json
+tips.py
+.venv
+bin/
+.vscode
+test_*
+venv/
+hugchat.json
+qcapi
+/*.yaml

CONTRIBUTING.md

@@ -0,0 +1,19 @@
+## 参与项目
+
+欢迎为此项目贡献代码或其他支持，以使您的点子或众人期待的功能成为现实，助力社区成长。  
+
+### 贡献形式
+
+- 提交PR，解决issues中提到的bug或期待的功能
+- 提交PR，实现您设想的功能（请先提出issue与作者沟通）
+- 优化代码架构，使各个模块的组织更加整洁优雅
+- 在issues中提出发现的bug或者期待的功能
+- 为本项目在其他社交平台撰写文章、制作视频等
+- 为本项目的衍生项目作出贡献，或开发插件增加功能
+
+### 如何开始
+
+- 加入本项目交流群，一同探讨项目相关事务
+- 解决本项目或衍生项目的issues中亟待解决的问题
+- 阅读并完善本项目文档
+- 在各个社交媒体撰写本项目教程等

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.9-slim
+WORKDIR /QChatGPT
+
+RUN sed -i "s/deb.debian.org/mirrors.tencent.com/g" /etc/apt/sources.list \
+    && sed -i 's|security.debian.org/debian-security|mirrors.tencent.com/debian-security|g' /etc/apt/sources.list \
+    && apt-get clean \
+    && apt-get update \
+    && apt-get -y upgrade \
+    && apt-get install -y git \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY . /QChatGPT/
+
+RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+CMD [ "python", "main.py" ] 

README.md

@@ -1,25 +1,81 @@
-# QChatGPT🤖
-> 2023/3/3  官方接口疑似被墙，请自行测试，或等待近期敏感时期结束。  
-> 2023/3/3  现已在主线支持官方ChatGPT接口，使用方法查看[#195](https://github.com/RockChinQ/QChatGPT/issues/195)  
-> 2023/3/2  OpenAI已发布ChatGPT官方接口，我们正在全力接入，预计明日前完成，请查看[此PR](https://github.com/RockChinQ/QChatGPT/pull/194)  
-> 2023/2/16 现已支持接入ChatGPT网页版，详情请完成部署并查看底部**插件**小节或[此仓库](https://github.com/RockChinQ/revLibs)
 
-- 到[项目Wiki](https://github.com/RockChinQ/QChatGPT/wiki)可了解项目详细信息
-- 由bilibili TheLazy制作的[视频教程](https://www.bilibili.com/video/BV15v4y1X7aP)
-- 交流、答疑群: ~~204785790~~（已满）、691226829、656285629  
-  - **进群提问前请您`确保`已经找遍文档和issue均无法解决**  
-  - **进群提问前请您`确保`已经找遍文档和issue均无法解决**  
-  - **进群提问前请您`确保`已经找遍文档和issue均无法解决**  
-- QQ频道机器人见[QQChannelChatGPT](https://github.com/Soulter/QQChannelChatGPT)
+<p align="center">
+<img src="res/logo.png" alt="QChatGPT" width="120" />
+</p>
 
-通过调用OpenAI的ChatGPT等语言模型来实现一个更加智能的QQ机器人  
+<div align="center">
+
+# QChatGPT
+
+高稳定性/持续迭代/架构清晰/支持插件/高可自定义的 ChatGPT QQ机器人框架
+
+[English](README_en.md) | 简体中文
+
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
+![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)
+<img src="https://img.shields.io/badge/python-3.9+-blue.svg" alt="python">
+<a href="https://github.com/RockChinQ/QChatGPT/wiki">
+<img alt="Static Badge" src="https://img.shields.io/badge/%E6%9F%A5%E7%9C%8B-%E9%A1%B9%E7%9B%AEWiki-blue">
+</a>
+<a href="https://www.bilibili.com/video/BV1Y14y1Q7kQ">
+<img alt="Static Badge" src="https://img.shields.io/badge/%E8%A7%86%E9%A2%91%E6%95%99%E7%A8%8B-208647">
+</a>
+<a href="https://www.bilibili.com/video/BV11h4y1y74H">
+<img alt="Static Badge" src="https://img.shields.io/badge/Linux%E9%83%A8%E7%BD%B2%E8%A7%86%E9%A2%91-208647">
+</a>
+
+</div>
+
+> 2023/7/29 支持使用GPT的Function Calling功能实现类似ChatGPT Plugin的效果，请见[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)  
+
+<details>
+<summary>
+
+## 🍺模型适配一览
+
+</summary>
+
+### 文字对话
+
+- OpenAI GPT-3.5模型(ChatGPT API), 本项目原生支持, 默认使用
+- OpenAI GPT-3模型, 本项目原生支持, 部署完成后前往`config.py`切换
+- OpenAI GPT-4模型, 本项目原生支持, 目前需要您的账户通过OpenAI的内测申请, 请前往`config.py`切换
+- ChatGPT网页版GPT-3.5模型, 由[插件](https://github.com/RockChinQ/revLibs)接入
+- ChatGPT网页版GPT-4模型, 目前需要ChatGPT Plus订阅, 由[插件](https://github.com/RockChinQ/revLibs)接入
+- New Bing逆向库, 由[插件](https://github.com/RockChinQ/revLibs)接入
+- HuggingChat, 由[插件](https://github.com/RockChinQ/revLibs)接入, 仅支持英文
+
+### 故事续写
+
+- NovelAI API, 由[插件](https://github.com/dominoar/QCPNovelAi)接入
+
+### 图片绘制
+
+- OpenAI DALL·E模型, 本项目原生支持, 使用方法查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
+- NovelAI API, 由[插件](https://github.com/dominoar/QCPNovelAi)接入
+
+### 语音生成
+
+- TTS+VITS, 由[插件](https://github.com/dominoar/QChatPlugins)接入
+- Plachta/VITS-Umamusume-voice-synthesizer, 由[插件](https://github.com/oliverkirk-sudo/chat_voice)接入
+
+
+安装[此插件](https://github.com/RockChinQ/Switcher)，即可在使用中切换文字模型。
+
+</details>
+
+<details>
+<summary>
 
 ## ✅功能
 
+</summary>
+
 <details>
 <summary>✅支持敏感词过滤，避免账号风险</summary>
 
   - 难以监测机器人与用户对话时的内容，故引入此功能以减少机器人风险
+  - 加入了百度云内容审核，在`config.py`中修改`baidu_check`的值，并填写`baidu_api_key`和`baidu_secret_key`以开启此功能
   - 编辑`sensitive.json`，并在`config.py`中修改`sensitive_word_filter`的值以开启此功能
 </details>
 
@@ -63,6 +119,7 @@
 <summary>✅支持插件加载🧩</summary>
 
   - 自行实现插件加载器及相关支持
+  - 支持GPT的Function Calling功能
   - 详细查看[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
 </details>
 <details>
@@ -72,6 +129,12 @@
   - 详见Wiki`加入黑名单`节
 </details>
 <details>
+<summary>✅长消息处理策略</summary>
+
+  - 支持将长消息转换成图片或消息记录组件，避免消息刷屏
+  - 请查看`config.py`中`blob_message_strategy`等字段
+</details>
+<details>
 <summary>✅回复速度限制</summary>
 
   - 支持限制单会话内每分钟可进行的对话次数
@@ -80,24 +143,63 @@
     - “丢弃”策略：此分钟内对话次数达到限制时，丢弃之后的对话
   - 详细请查看config.py中的相关配置
 </details>
+<details>
+<summary>✅支持使用网络代理</summary>
+
+  - 目前已支持正向代理访问接口
+  - 详细请查看config.py中的`openai_config`的说明
+</details>
+<details>
+<summary>✅支持自定义提示内容</summary>
+
+  - 允许用户自定义报错、帮助等提示信息
+  - 请查看`tips.py`
+</details>
+
+### 🏞️截图
+
+<img alt="私聊GPT-3.5" src="res/screenshots/person_gpt3.5.png" width="400"/>
+<br/>
+<img alt="群聊GPT-3.5" src="res/screenshots/group_gpt3.5.png" width="400"/>
+<br/>
+<img alt="New Bing" src="res/screenshots/person_newbing.png" width="400"/>
 
 详情请查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
 
+</details>
+
+<details>
+
+<summary>
+
 ## 🔩部署
 
-**部署过程中遇到任何问题，请先在[QChatGPT](https://github.com/RockChinQ/QChatGPT/issues)或[qcg-installer](https://github.com/RockChinQ/qcg-installer/issues)的issue里进行搜索**
+</summary>
+
+**部署过程中遇到任何问题，请先在[QChatGPT](https://github.com/RockChinQ/QChatGPT/issues)或[qcg-installer](https://github.com/RockChinQ/qcg-installer/issues)的issue里进行搜索**  
+**QChatGPT需要Python版本>=3.9**
+
+- 官方交流、答疑群: 656285629  
+  - **进群提问前请您`确保`已经找遍文档和issue均无法解决**  
+- 社区群（内有一键部署包、图形化界面等资源）: 891448839
 
 ### - 注册OpenAI账号
 
-**可以直接进群找群主购买**  
-或参考以下文章自行注册
+<details>
+<summary>点此查看步骤</summary>
 
-> ~~[只需 1 元搞定 ChatGPT 注册](https://zhuanlan.zhihu.com/p/589470082)~~（已失效）  
+> 若您要直接使用非OpenAI的模型（如New Bing），可跳过此步骤，直接进行之后的部署，完成后按照相关插件的文档进行配置即可
+
+参考以下文章自行注册
+
+> [国内注册ChatGPT的方法(100%可用)](https://www.pythonthree.com/register-openai-chatgpt/)  
 > [手把手教你如何注册ChatGPT，超级详细](https://guxiaobei.com/51461)
 
 注册成功后请前往[个人中心查看](https://beta.openai.com/account/api-keys)api_key  
 完成注册后，使用以下自动化或手动部署步骤
 
+</details>
+
 ### - 自动化部署
 
 <details>
@@ -105,9 +207,13 @@
 
 #### Docker方式
 
-请查看此仓库[mikumifa/QChatGPT-Docker-Installer](https://github.com/mikumifa/QChatGPT-Docker-Installer)
+> docker方式目前仅支持使用mirai登录，若您不**熟悉**docker的操作及相关知识，强烈建议您使用其他方式部署，我们**不会且难以**解决您主机上多个容器的连接问题。
+
+请查看[此文档](res/docs/docker_deploy.md)  
+由[@mikumifa](https://github.com/mikumifa)贡献
 
 #### 安装器方式
+
 使用[此安装器](https://github.com/RockChinQ/qcg-installer)（若无法访问请到[Gitee](https://gitee.com/RockChin/qcg-installer)）进行部署
 
 - 安装器目前仅支持部分平台，请到仓库文档查看，其他平台请手动部署
@@ -118,17 +224,31 @@
 <details>
 <summary>手动部署适用于所有平台</summary>
 
-- 请使用Python 3.9.x以上版本  
-- 请注意OpenAI账号额度消耗  
-  - 每个账户仅有18美元免费额度，如未绑定银行卡，则会在超出时报错  
-  - OpenAI收费标准：默认使用的`text-davinci-003`模型 0.02美元/千字  
+- 请使用Python 3.9.x以上版本   
 
-#### 配置Mirai
+#### ① 配置QQ登录框架
 
-按照[此教程](https://yiri-mirai.wybxc.cc/tutorials/01/configuration)配置Mirai及YiriMirai  
-启动mirai-console后，使用`login`命令登录QQ账号，保持mirai-console运行状态
+目前支持mirai和go-cqhttp，配置任意一个即可
 
-#### 配置主程序
+<details>
+<summary>mirai</summary>
+
+1. 按照[此教程](https://yiri-mirai.wybxc.cc/tutorials/01/configuration)配置Mirai及mirai-api-http  
+2. 启动mirai-console后，使用`login`命令登录QQ账号，保持mirai-console运行状态  
+3. 在下一步配置主程序时请在config.py中将`msg_source_adapter`设为`yirimirai`
+
+</details>
+
+<details>
+<summary>go-cqhttp</summary>
+
+1. 按照[此文档](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE)配置go-cqhttp
+2. 启动go-cqhttp，确保登录成功，保持运行
+3. 在下一步配置主程序时请在config.py中将`msg_source_adapter`设为`nakuru`
+
+</details>
+
+#### ② 配置主程序
 
 1. 克隆此项目
 
@@ -140,8 +260,7 @@ cd QChatGPT
 2. 安装依赖
 
 ```bash
-pip3 install yiri-mirai openai colorlog func_timeout
-pip3 install dulwich
+pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk CallingGPT tiktoken
 ```
 
 3. 运行一次主程序，生成配置文件
@@ -164,49 +283,85 @@ python3 main.py
 
 **常见问题**
 
-- mirai登录提示`QQ版本过低`，见[此issue](https://github.com/RockChinQ/QChatGPT/issues/38)
+- mirai登录提示`QQ版本过低`，见[此issue](https://github.com/RockChinQ/QChatGPT/issues/137)
 - 如提示安装`uvicorn`或`hypercorn`请*不要*安装，这两个不是必需的，目前存在未知原因bug
 - 如报错`TypeError: As of 3.10, the *loop* parameter was removed from Lock() since it is no longer necessary`, 请参考 [此处](https://github.com/RockChinQ/QChatGPT/issues/5)
 
 </details>
 
+</details>
+
+<details>
+
+<summary>
+
 ## 🚀使用
 
-查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E4%BD%BF%E7%94%A8%E6%96%B9%E5%BC%8F)
+</summary>
+
+**部署完成后必看: [指令说明](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)**  
+
+所有功能查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E4%BD%BF%E7%94%A8%E6%96%B9%E5%BC%8F)  
+
+</details>
+
+<details>
+<summary>
 
 ## 🧩插件生态
 
-现已支持自行开发插件对功能进行扩展或自定义程序行为  
-详见[Wiki插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)  
-开发教程见[Wiki插件开发页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91)
+</summary>
 
-### 示例插件
+⭐我们已经支持了[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)，请查看[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)  
 
-在`tests/plugin_examples`目录下，将其整个目录复制到`plugins`目录下即可使用
+> 使用方法见：[Wiki插件使用](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)  
+> 开发教程见：[Wiki插件开发](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91)
 
-- `cmdcn` - 主程序指令中文形式
-- `hello_plugin` - 在收到消息`hello`时回复相应消息
-- `urlikethisijustsix` - 收到冒犯性消息时回复相应消息
 
-### 更多
+[所有插件列表](https://github.com/stars/RockChinQ/lists/qchatgpt-%E6%8F%92%E4%BB%B6)，欢迎提出issue以提交新的插件
 
-欢迎提交新的插件
+### 部分插件
 
-- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目，关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E4%B8%8EChatGPT%E7%BD%91%E9%A1%B5%E7%89%88)
+- [WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin) - 让机器人能联网！！
+- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目，关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E3%80%81ChatGPT%E7%BD%91%E9%A1%B5%E7%89%88%E3%80%81ChatGPT-API%E5%8C%BA%E5%88%AB)
+- [Switcher](https://github.com/RockChinQ/Switcher) - 支持通过指令切换使用的模型
 - [hello_plugin](https://github.com/RockChinQ/hello_plugin) - `hello_plugin` 的储存库形式，插件开发模板
-- [dominoar/QChatPlugins](https://github.com/dominoar/QchatPlugins) - dominoar编写的诸多新功能插件（语言输出、Ranimg、屏蔽词规则等）
+- [dominoar/QChatPlugins](https://github.com/dominoar/QchatPlugins) - dominoar编写的诸多新功能插件（语音输出、Ranimg、屏蔽词规则等）
 - [dominoar/QCP-NovelAi](https://github.com/dominoar/QCP-NovelAi) - NovelAI 故事叙述与绘画
+- [oliverkirk-sudo/chat_voice](https://github.com/oliverkirk-sudo/chat_voice) - 文字转语音输出，使用HuggingFace上的[VITS-Umamusume-voice-synthesizer模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer)
+- [RockChinQ/WaitYiYan](https://github.com/RockChinQ/WaitYiYan) - 实时获取百度`文心一言`等待列表人数
+- [chordfish-k/QChartGPT_Emoticon_Plugin](https://github.com/chordfish-k/QChartGPT_Emoticon_Plugin) - 使机器人根据回复内容发送表情包
+- [oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot) - 接入[Poe](https://poe.com/)上的机器人
+- [lieyanqzu/WeatherPlugin](https://github.com/lieyanqzu/WeatherPlugin) - 天气查询插件
+- [SysStatPlugin](https://github.com/RockChinQ/SysStatPlugin) - 查看系统状态
+</details>
+
+<details>
+
+<summary>
 
 ## 😘致谢
 
-- [@the-lazy-me](https://github.com/the-lazy-me) 为本项目制作[视频教程](https://www.bilibili.com/video/BV15v4y1X7aP)
+</summary>
+
+- [@the-lazy-me](https://github.com/the-lazy-me) 为本项目制作[视频教程](https://www.bilibili.com/video/BV1Y14y1Q7kQ)
 - [@mikumifa](https://github.com/mikumifa) 本项目Docker部署仓库开发者
 - [@dominoar](https://github.com/dominoar) 为本项目开发多种插件
-- [@hissincn](https://github.com/hissincn) 本项目贡献者
-- [@LINSTCL](https://github.com/LINSTCL)   GPT-3.5官方模型适配贡献者
+- [@万神的星空](https://github.com/qq255204159)  整合包发行
+- [@ljcduo](https://github.com/ljcduo)  GPT-4 API内测账号提供
 
-以及其他所有为本项目提供支持的朋友们。
+以及所有[贡献者](https://github.com/RockChinQ/QChatGPT/graphs/contributors)和其他为本项目提供支持的朋友们。
+
+</details>
+
+<details>
+
+<summary>
 
 ## 👍赞赏
 
+</summary>
+
 <img alt="赞赏码" src="res/mm_reward_qrcode_1672840549070.png" width="400" height="400"/>
+
+</details>

README_en.md

@@ -0,0 +1,215 @@
+# QChatGPT🤖
+
+<p align="center">
+<img src="res/social.png" alt="QChatGPT" width="640" />
+</p>
+
+English | [简体中文](README.md)
+
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
+![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)
+
+- Refer to [Wiki](https://github.com/RockChinQ/QChatGPT/wiki) to get further information.  
+- Official QQ group: 656285629  
+- Community QQ group: 362515018
+- QQ channel robot: [QQChannelChatGPT](https://github.com/Soulter/QQChannelChatGPT)
+- Any contribution is welcome, please refer to [CONTRIBUTING.md](CONTRIBUTING.md)
+
+## 🍺List of supported models
+
+<details>
+<summary>Details</summary>
+
+### Chat
+
+- OpenAI GPT-3.5 (ChatGPT API), default model
+- OpenAI GPT-3, supported natively, switch to it in `config.py`
+- OpenAI GPT-4, supported natively, qualification for internal testing required, switch to it in `config.py`
+- ChatGPT website edition (GPT-3.5), see [revLibs plugin](https://github.com/RockChinQ/revLibs)
+- ChatGPT website edition (GPT-4), ChatGPT plus subscription required, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
+- New Bing, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
+- HuggingChat, see [revLibs plugin](https://github.com/RockChinQ/revLibs), English only
+
+### Story
+
+- NovelAI API, see [QCPNovelAi plugin](https://github.com/dominoar/QCPNovelAi)
+
+### Image
+
+- OpenAI DALL·E, supported natively, see [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
+- NovelAI API, see [QCPNovelAi plugin](https://github.com/dominoar/QCPNovelAi)
+
+### Voice
+
+- TTS+VITS, see [QChatPlugins](https://github.com/dominoar/QChatPlugins)
+- Plachta/VITS-Umamusume-voice-synthesizer, see [chat_voice plugin](https://github.com/oliverkirk-sudo/chat_voice)
+
+
+</details>
+
+Install this [plugin](https://github.com/RockChinQ/Switcher) to switch between different models.
+
+## ✅Function Points
+
+<details>
+<summary>Details</summary>
+
+ - ✅Sensitive word filtering, avoid being banned
+ - ✅Multiple responding rules, including regular expression matching
+ - ✅Multiple api-key management, automatic switching when exceeding
+ - ✅Support for customizing the preset prompt text
+ - ✅Chat, story, image, voice, etc. models are supported
+ - ✅Support for hot reloading and hot updating
+ - ✅Support for plugin loading
+ - ✅Blacklist mechanism for private chat and group chat
+ - ✅Excellent long message processing strategy
+ - ✅Reply rate limitation
+ - ✅Support for network proxy
+ - ✅Support for customizing the output format
+</details>
+
+More details, see [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
+
+## 🔩Deployment
+
+**If you encounter any problems during deployment, please search in the issue of [QChatGPT](https://github.com/RockChinQ/QChatGPT/issues) or [qcg-installer](https://github.com/RockChinQ/qcg-installer/issues) first.**
+
+### - Register OpenAI account
+
+> If you want to use a model other than OpenAI (such as New Bing), you can skip this step and directly refer to following steps, and then configure it according to the relevant plugin documentation.
+
+To register OpenAI account, please refer to the following articles(in Chinese):
+
+> [国内注册ChatGPT的方法(100%可用)](https://www.pythonthree.com/register-openai-chatgpt/)  
+> [手把手教你如何注册ChatGPT，超级详细](https://guxiaobei.com/51461)
+
+Check your api-key in [personal center](https://beta.openai.com/account/api-keys) after registration, and then follow the following steps to deploy.
+
+### - Deploy Automatically
+
+<details>
+<summary>Details</summary>
+
+#### Docker
+
+See [this document(cn)](res/docs/docker_deploy.md)  
+Contributed by [@mikumifa](https://github.com/mikumifa)
+
+#### Installer
+
+Use [this installer](https://github.com/RockChinQ/qcg-installer) to deploy.
+
+- The installer currently only supports some platforms, please refer to the repository document for details, and manually deploy for other platforms
+
+</details>
+
+### - Deploy Manually
+<details>
+<summary>Manually deployment supports any platforms</summary>
+
+- Python 3.9.x or higher
+
+#### 配置QQ登录框架
+
+Currently supports mirai and go-cqhttp, configure either one
+
+<details>
+<summary>mirai</summary>
+
+Follow [this tutorial(cn)](https://yiri-mirai.wybxc.cc/tutorials/01/configuration) to configure Mirai and YiriMirai.  
+After starting mirai-console, use the `login` command to log in to the QQ account, and keep the mirai-console running.
+
+</details>
+
+<details>
+<summary>go-cqhttp</summary>
+
+1. Follow [this tutorial(cn)](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE) to configure go-cqhttp.
+2. Start go-cqhttp, make sure it is logged in and running.
+
+</details>
+
+#### Configure QChatGPT
+
+1. Clone the repository
+
+```bash
+git clone https://github.com/RockChinQ/QChatGPT
+cd QChatGPT
+```
+
+2. Install dependencies
+
+```bash
+pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk
+```
+
+3. Generate `config.py`
+
+```bash
+python3 main.py
+```
+
+4. Edit `config.py`
+
+5. Run
+
+```bash
+python3 main.py
+```
+
+Any problems, please refer to the issues page.
+
+</details>
+
+## 🚀Usage
+
+**After deployment, please read: [Commands(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)**  
+
+**For more details, please refer to the [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E4%BD%BF%E7%94%A8%E6%96%B9%E5%BC%8F)**
+
+
+## 🧩Plugin Ecosystem
+
+Plugin [usage](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8) and [development](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91) are supported.
+
+<details>
+<summary>List of plugins (cn)</summary>
+
+### Examples
+
+在`tests/plugin_examples`目录下，将其整个目录复制到`plugins`目录下即可使用
+
+- `cmdcn` - 主程序指令中文形式
+- `hello_plugin` - 在收到消息`hello`时回复相应消息
+- `urlikethisijustsix` - 收到冒犯性消息时回复相应消息
+
+### More Plugins
+
+欢迎提交新的插件
+
+- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目，关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E4%B8%8EChatGPT%E7%BD%91%E9%A1%B5%E7%89%88)
+- [Switcher](https://github.com/RockChinQ/Switcher) - 支持通过指令切换使用的模型
+- [hello_plugin](https://github.com/RockChinQ/hello_plugin) - `hello_plugin` 的储存库形式，插件开发模板
+- [dominoar/QChatPlugins](https://github.com/dominoar/QchatPlugins) - dominoar编写的诸多新功能插件（语音输出、Ranimg、屏蔽词规则等）
+- [dominoar/QCP-NovelAi](https://github.com/dominoar/QCP-NovelAi) - NovelAI 故事叙述与绘画
+- [oliverkirk-sudo/chat_voice](https://github.com/oliverkirk-sudo/chat_voice) - 文字转语音输出，使用HuggingFace上的[VITS-Umamusume-voice-synthesizer模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer)
+- [RockChinQ/WaitYiYan](https://github.com/RockChinQ/WaitYiYan) - 实时获取百度`文心一言`等待列表人数
+- [chordfish-k/QChartGPT_Emoticon_Plugin](https://github.com/chordfish-k/QChartGPT_Emoticon_Plugin) - 使机器人根据回复内容发送表情包
+- [oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot) - 接入[Poe](https://poe.com/)上的机器人
+- [lieyanqzu/WeatherPlugin](https://github.com/lieyanqzu/WeatherPlugin) - 天气查询插件
+</details>
+
+## 😘Thanks
+
+- [@the-lazy-me](https://github.com/the-lazy-me) video tutorial creator
+- [@mikumifa](https://github.com/mikumifa) Docker deployment
+- [@dominoar](https://github.com/dominoar) Plugin development
+- [@万神的星空](https://github.com/qq255204159) Packages publisher
+- [@ljcduo](https://github.com/ljcduo)  GPT-4 API internal test account
+
+And all [contributors](https://github.com/RockChinQ/QChatGPT/graphs/contributors) and other friends who support this project.
+
+<!-- ## 👍赞赏
+
+<img alt="赞赏码" src="res/mm_reward_qrcode_1672840549070.png" width="400" height="400"/> -->

config-template.py

@@ -1,7 +1,13 @@
 # 配置文件: 注释里标[必需]的参数必须修改, 其他参数根据需要修改, 但请勿删除
 import logging
 
-# [必需] Mirai的配置
+# 消息处理协议适配器
+# 目前支持以下适配器:
+# - "yirimirai": mirai的通信框架，YiriMirai框架适配器, 请同时填写下方mirai_http_api_config
+# - "nakuru": go-cqhttp通信框架，请同时填写下方nakuru_config
+msg_source_adapter = "yirimirai"
+
+# [必需(与nakuru二选一，取决于msg_source_adapter)] Mirai的配置
 # 请到配置mirai的步骤中的教程查看每个字段的信息
 # adapter: 选择适配器，目前支持HTTPAdapter和WebSocketAdapter
 # host: 运行mirai的主机地址
@@ -18,6 +24,15 @@ mirai_http_api_config = {
     "qq": 1234567890
 }
 
+# [必需(与mirai二选一，取决于msg_source_adapter)]
+# 使用nakuru-project框架连接go-cqhttp的配置
+nakuru_config = {
+    "host": "localhost",  # go-cqhttp的地址
+    "port": 6700,  # go-cqhttp的正向websocket端口
+    "http_port": 5700,  # go-cqhttp的正向http端口
+    "token": ""  # 若在go-cqhttp的config.yml设置了access_token, 则填写此处
+}
+
 # [必需] OpenAI的配置
 # api_key: OpenAI的API Key
 # http_proxy: 请求OpenAI时使用的代理，None为不使用，https和socks5暂不能使用
@@ -33,13 +48,33 @@ mirai_http_api_config = {
 #     },
 #     "http_proxy": "http://127.0.0.1:12345"
 # }
+# 
+# 现已支持反向代理，可以添加reverse_proxy字段以使用反向代理
+# 使用反向代理可以在国内使用OpenAI的API，反向代理的配置请参考 
+# https://github.com/Ice-Hazymoon/openai-scf-proxy
+#
+# 反向代理填写示例：
+# openai_config = {
+#     "api_key": {
+#         "default": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+#         "key1": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+#         "key2": "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+#     },
+#     "reverse_proxy": "http://example.com:12345/v1"
+# }
 openai_config = {
     "api_key": {
         "default": "openai_api_key"
     },
-    "http_proxy": None
+    "http_proxy": None,
+    "reverse_proxy": None
 }
 
+# api-key切换策略
+# active：每次请求时都会切换api-key
+# passive：仅当api-key超额时才会切换api-key
+switch_strategy = "active"
+
 # [必需] 管理员QQ号，用于接收报错等通知及执行管理员级别指令
 # 支持多个管理员，可以使用list形式设置，例如：
 # admin_qq = [12345678, 87654321]
@@ -79,17 +114,49 @@ default_prompt = {
     "default": "如果我之后想获取帮助，请你说“输入!help获取帮助”",
 }
 
+# 情景预设格式
+# 参考值：默认方式：normal | 完整情景：full_scenario
+# 默认方式 的格式为上述default_prompt中的内容，或prompts目录下的文件名
+# 完整情景方式 的格式为JSON，在scenario目录下的JSON文件中列出对话的每个回合，编写方法见scenario/default-template.json
+#     编写方法请查看：https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E9%A2%84%E8%AE%BE%E6%96%87%E5%AD%97full_scenario%E6%A8%A1%E5%BC%8F
+preset_mode = "normal"
+
 # 群内响应规则
 # 符合此消息的群内消息即使不包含at机器人也会响应
 # 支持消息前缀匹配及正则表达式匹配
+# 支持设置是否响应at消息、随机响应概率
 # 注意：由消息前缀(prefix)匹配的消息中将会删除此前缀，正则表达式(regexp)匹配的消息不会删除匹配的部分
 #      前缀匹配优先级高于正则表达式匹配
 # 正则表达式简明教程：https://www.runoob.com/regexp/regexp-tutorial.html
+# 
+# 支持针对不同群设置不同的响应规则，例如：
+# response_rules = {
+#    "default": {
+#        "at": True,
+#        "prefix": ["/ai", "!ai", "！ai", "ai"],
+#        "regexp": [],
+#        "random_rate": 0.0,
+#    },
+#    "12345678": {
+#        "at": False,
+#        "prefix": ["/ai", "!ai", "！ai", "ai"],
+#        "regexp": [],
+#        "random_rate": 0.0,
+#    },
+# }
+#
+# 以上设置将会在群号为12345678的群中关闭at响应
+# 未单独设置的群将使用default规则
 response_rules = {
-    "prefix": ["/ai", "!ai", "！ai", "ai"],
-    "regexp": []  # "为什么.*", "怎么?样.*", "怎么.*", "如何.*", "[Hh]ow to.*", "[Ww]hy not.*", "[Ww]hat is.*", ".*怎么办", ".*咋办"
+    "default": {
+        "at": True,  # 是否响应at机器人的消息
+        "prefix": ["/ai", "!ai", "！ai", "ai"],
+        "regexp": [],  # "为什么.*", "怎么?样.*", "怎么.*", "如何.*", "[Hh]ow to.*", "[Ww]hy not.*", "[Ww]hat is.*", ".*怎么办", ".*咋办"
+        "random_rate": 0.0,  # 随机响应概率，0.0-1.0，0.0为不随机响应，1.0为响应所有消息, 仅在前几项判断不通过时生效
+    },
 }
 
+
 # 消息忽略规则
 # 适用于私聊及群聊
 # 符合此规则的消息将不会被响应
@@ -102,10 +169,27 @@ ignore_rules = {
     "regexp": []
 }
 
+# 是否检查收到的消息中是否包含敏感词
+# 若收到的消息无法通过下方指定的敏感词检查策略，则发送提示信息
+income_msg_check = False
+
 # 敏感词过滤开关，以同样数量的*代替敏感词回复
 # 请在sensitive.json中添加敏感词
 sensitive_word_filter = True
 
+# 是否启用百度云内容安全审核
+# 注册方式查看 https://cloud.baidu.com/doc/ANTIPORN/s/Wkhu9d5iy
+baidu_check = False
+
+# 百度云API_KEY 24位英文数字字符串
+baidu_api_key = ""
+
+# 百度云SECRET_KEY 32位的英文数字字符串
+baidu_secret_key = ""
+
+# 不合规消息自定义返回
+inappropriate_message_tips = "[百度云]请珍惜机器人，当前返回内容不合规"
+
 # 启动时是否发送赞赏码
 # 仅当使用量已经超过2048字时发送
 encourage_sponsor_at_start = True
@@ -113,14 +197,24 @@ encourage_sponsor_at_start = True
 # 每次向OpenAI接口发送对话记录上下文的字符数
 # 最大不超过(4096 - max_tokens)个字符，max_tokens为下方completion_api_params中的max_tokens
 # 注意：较大的prompt_submit_length会导致OpenAI账户额度消耗更快
-prompt_submit_length = 1024
+prompt_submit_length = 2048
+
+# 是否在token超限报错时自动重置会话
+# 可在tips.py中编辑提示语
+auto_reset = True
 
 # OpenAI补全API的参数
 # 请在下方填写模型，程序自动选择接口
 # 现已支持的模型有：
 # 
+#    'gpt-4'
+#    'gpt-4-0613'
+#    'gpt-4-32k'
+#    'gpt-4-32k-0613'
 #    'gpt-3.5-turbo'
-#    'gpt-3.5-turbo-0301'
+#    'gpt-3.5-turbo-16k'
+#    'gpt-3.5-turbo-0613'
+#    'gpt-3.5-turbo-16k-0613'
 #    'text-davinci-003'
 #    'text-davinci-002'
 #    'code-davinci-002'
@@ -130,10 +224,10 @@ prompt_submit_length = 1024
 #    'text-ada-001'
 #
 # 具体请查看OpenAI的文档: https://beta.openai.com/docs/api-reference/completions/create
+# 请将内容修改到config.py中，请勿修改config-template.py
 completion_api_params = {
     "model": "gpt-3.5-turbo",
     "temperature": 0.9,  # 数值越低得到的回答越理性，取值范围[0, 1]
-    "max_tokens": 512,  # 每次获取OpenAI接口响应的文字量上限, 不高于4096
     "top_p": 1,  # 生成的文本的文本与要求的符合度, 取值范围[0, 1]
     "frequency_penalty": 0.2,
     "presence_penalty": 1.0,
@@ -145,22 +239,55 @@ image_api_params = {
     "size": "256x256",  # 图片尺寸，支持256x256, 512x512, 1024x1024
 }
 
+# 跟踪函数调用
+# 为True时，在每次GPT进行Function Calling时都会输出发送一条回复给用户
+# 同时，一次提问内所有的Function Calling和普通回复消息都会单独发送给用户
+trace_function_calls = False
+
 # 群内回复消息时是否引用原消息
 quote_origin = True
 
+# 群内回复消息时是否at发送者
+at_sender = False
+
 # 回复绘图时是否包含图片描述
 include_image_description = True
 
 # 消息处理的超时时间，单位为秒
 process_message_timeout = 30
 
-# [暂未实现] 群内会话是否启用多对象名称
-# 若不启用，群内会话的prompt只使用user_name和bot_name
-multi_subject = False
-
 # 回复消息时是否显示[GPT]前缀
 show_prefix = False
 
+# 回复前的强制延迟时间，降低机器人被腾讯风控概率
+# *此机制对命令和消息、私聊及群聊均生效
+# 每次处理时从以下的范围取一个随机秒数，
+# 当此次消息处理时间低于此秒数时，将会强制延迟至此秒数
+# 例如：[1.5, 3]，则每次处理时会随机取一个1.5-3秒的随机数，若处理时间低于此随机数，则强制延迟至此随机秒数
+# 若您不需要此功能，请将force_delay_range设置为[0, 0]
+force_delay_range = [1.5, 3]
+
+# 应用长消息处理策略的阈值
+# 当回复消息长度超过此值时，将使用长消息处理策略
+blob_message_threshold = 256
+
+# 长消息处理策略
+# - "image": 将长消息转换为图片发送
+# - "forward": 将长消息转换为转发消息组件发送
+blob_message_strategy = "forward"
+
+# 允许等待
+# 同一会话内，是否等待上一条消息处理完成后再处理下一条消息
+# 若设置为False，若上一条未处理完时收到了新消息，将会丢弃新消息
+# 丢弃消息时的提示信息可以在tips.py中修改
+wait_last_done = True
+
+# 文字转图片时使用的字体文件路径
+# 当策略为"image"时生效
+#   若在Windows系统下，程序会自动使用Windows自带的微软雅黑字体
+#   若未填写或不存在且不是Windows，将禁用文字转图片功能，改为使用转发消息组件
+font_path = ""
+
 # 消息处理超时重试次数
 retry_times = 3
 
@@ -169,30 +296,59 @@ retry_times = 3
 # 设置为False时，向用户及管理员发送错误详细信息
 hide_exce_info_to_user = False
 
-# 消息处理出错时向用户发送的提示信息
-# 仅当hide_exce_info_to_user为True时生效
-# 设置为空字符串时，不发送提示信息
-alter_tip_message = '出错了，请稍后再试'
+# 线程池相关配置
+# 该参数决定机器人可以同时处理几个人的消息，超出线程池数量的请求会被阻塞，不会被丢弃
+# 如果你不清楚该参数的意义，请不要更改
+# 程序运行本身线程池，无代码层面修改请勿更改
+sys_pool_num = 8
+
+# 执行管理员请求和指令的线程池并行线程数量，一般和管理员数量相等
+admin_pool_num = 4
+
+# 执行用户请求和指令的线程池并行线程数量
+# 如需要更高的并发，可以增大该值
+user_pool_num = 8
 
 # 每个会话的过期时间，单位为秒
 # 默认值20分钟
-session_expire_time = 60 * 20
+session_expire_time = 1200
 
 # 会话限速
 # 单会话内每分钟可进行的对话次数
 # 若不需要限速，可以设置为一个很大的值
 # 默认值60次，基本上不会触发限速
-rate_limitation = 60
+#
+# 若要设置针对某特定群的限速，请使用如下格式：
+# {
+#   "group_<群号>": 60,
+#   "default": 60,
+# }
+# 若要设置针对某特定用户私聊的限速，请使用如下格式：
+# {
+#   "person_<用户QQ>": 60,
+#   "default": 60,
+# }
+# 同时设置多个群和私聊的限速，示例：
+# {
+#   "group_12345678": 60,
+#   "group_87654321": 60,
+#   "person_234567890": 60,
+#   "person_345678901": 60,
+#   "default": 60,
+# }
+#
+# 注意: 未指定的都使用default的限速值，default不可删除
+rate_limitation = {
+    "default": 60,
+}
 
 # 会话限速策略
 # - "wait": 每次对话获取到回复时，等待一定时间再发送回复，保证其不会超过限速均值
 # - "drop": 此分钟内，若对话次数超过限速次数，则丢弃之后的对话，每自然分钟重置
-rate_limit_strategy = "wait"
+rate_limit_strategy = "drop"
 
-# drop策略时，超过限速均值时，丢弃的对话的提示信息
-# 仅当rate_limitation_strategy为"drop"时生效
-# 若设置为空字符串，则不发送提示信息
-rate_limit_drop_tip = "本分钟对话次数超过限速次数，此对话被丢弃"
+# 是否在启动时进行依赖库更新
+upgrade_dependencies = True
 
 # 是否上报统计信息
 # 用于统计机器人的使用情况，不会收集任何用户信息
@@ -201,20 +357,3 @@ report_usage = True
 
 # 日志级别
 logging_level = logging.INFO
-
-# 定制帮助消息
-help_message = """此机器人通过调用OpenAI的GPT-3大型语言模型生成回复，不具有情感。
-你可以用自然语言与其交流，回复的消息中[GPT]开头的为模型生成的语言，[bot]开头的为程序提示。
-了解此项目请找QQ 1010553892 联系作者
-请不要用其生成整篇文章或大段代码，因为每次只会向模型提交少部分文字，生成大部分文字会产生偏题、前后矛盾等问题
-每次会话最后一次交互后{}分钟后会自动结束，结束后将开启新会话，如需继续前一次会话请发送 !last 重新开启
-欢迎到github.com/RockChinQ/QChatGPT 给个star
-
-帮助信息：
-!help - 显示帮助
-!reset - 重置会话
-!last - 切换到前一次的对话
-!next - 切换到后一次的对话
-!prompt - 显示当前对话所有内容
-!list - 列出所有历史会话
-!usage - 列出各个api-key的使用量""".format(session_expire_time // 60)

main.py

@@ -1,4 +1,5 @@
 import importlib
+import json
 import os
 import shutil
 import threading
@@ -6,14 +7,20 @@ import time
 
 import logging
 import sys
+import traceback
+
+sys.path.append(".")
+
+from pkg.utils.log import init_runtime_log_file, reset_logging
 
 try:
     import colorlog
 except ImportError:
     # 尝试安装
     import pkg.utils.pkgmgr as pkgmgr
-    pkgmgr.install_requirements("requirements.txt")
     try:
+        pkgmgr.install_requirements("requirements.txt")
+        pkgmgr.install_upgrade("websockets")
         import colorlog
     except ImportError:
         print("依赖不满足,请查看 https://github.com/RockChinQ/qcg-installer/issues/15")
@@ -23,17 +30,12 @@ import colorlog
 import requests
 import websockets.exceptions
 from urllib3.exceptions import InsecureRequestWarning
+import pkg.utils.context
 
 
-sys.path.append(".")
-
-log_colors_config = {
-    'DEBUG': 'green',  # cyan white
-    'INFO': 'white',
-    'WARNING': 'yellow',
-    'ERROR': 'red',
-    'CRITICAL': 'bold_red',
-}
+# 是否使用override.json覆盖配置
+# 仅在启动时提供 --override 或 -r 参数时生效
+use_override = False
 
 
 def init_db():
@@ -43,202 +45,269 @@ def init_db():
     database.initialize_database()
 
 
+def ensure_dependencies():
+    import pkg.utils.pkgmgr as pkgmgr
+    pkgmgr.run_pip(["install", "openai", "Pillow", "nakuru-project-idk", "CallingGPT", "tiktoken", "--upgrade",
+                    "-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
+                    "--trusted-host", "pypi.tuna.tsinghua.edu.cn"])
+
+
 known_exception_caught = False
 
-log_file_name = "qchatgpt.log"
+
+def override_config():
+    import config
+    # 检查override.json覆盖
+    if os.path.exists("override.json") and use_override:
+        override_json = json.load(open("override.json", "r", encoding="utf-8"))
+        overrided = []
+        for key in override_json:
+            if hasattr(config, key):
+                setattr(config, key, override_json[key])
+                # logging.info("覆写配置[{}]为[{}]".format(key, override_json[key]))
+                overrided.append(key)
+            else:
+                logging.error("无法覆写配置[{}]为[{}]，该配置不存在，请检查override.json是否正确".format(key, override_json[key]))
+        if len(overrided) > 0:
+            logging.info("已根据override.json覆写配置项: {}".format(", ".join(overrided)))
 
 
-def init_runtime_log_file():
-    """为此次运行生成日志文件
-    格式: qchatgpt-yyyy-MM-dd-HH-mm-ss.log
-    """
-    global log_file_name
-
-    # 检查logs目录是否存在
-    if not os.path.exists("logs"):
-        os.mkdir("logs")
-
-    # 检查本目录是否有qchatgpt.log，若有，移动到logs目录
-    if os.path.exists("qchatgpt.log"):
-        shutil.move("qchatgpt.log", "logs/qchatgpt.legacy.log")
-
-    log_file_name = "logs/qchatgpt-%s.log" % time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
-    
-
-def reset_logging():
-    global log_file_name
-    assert os.path.exists('config.py')
+# 临时函数，用于加载config和上下文，未来统一放在config类
+def load_config():
+    logging.info("检查config模块完整性.")
+    # 完整性校验
+    non_exist_keys = []
 
+    is_integrity = True
+    config_template = importlib.import_module('config-template')
     config = importlib.import_module('config')
+    for key in dir(config_template):
+        if not key.startswith("__") and not hasattr(config, key):
+            setattr(config, key, getattr(config_template, key))
+            # logging.warning("[{}]不存在".format(key))
+            non_exist_keys.append(key)
+            is_integrity = False
+    
+    if not is_integrity:
+        logging.warning("以下配置字段不存在: {}".format(", ".join(non_exist_keys)))
 
+    # 检查override.json覆盖
+    override_config()
+
+    if not is_integrity:
+        logging.warning("以上不存在的配置已被设为默认值，您可以依据config-template.py检查config.py，将在3秒后继续启动... ")
+        time.sleep(3)
+
+    # 存进上下文
+    pkg.utils.context.set_config(config)
+
+
+def complete_tips():
+    """根据tips-custom-template模块补全tips模块的属性"""
+    non_exist_keys = []
+
+    is_integrity = True
+    logging.info("检查tips模块完整性.")
+    tips_template = importlib.import_module('tips-custom-template')
+    tips = importlib.import_module('tips')
+    for key in dir(tips_template):
+        if not key.startswith("__") and not hasattr(tips, key):
+            setattr(tips, key, getattr(tips_template, key))
+            # logging.warning("[{}]不存在".format(key))
+            non_exist_keys.append(key)
+            is_integrity = False
+
+    if not is_integrity:
+        logging.warning("以下提示语字段不存在: {}".format(", ".join(non_exist_keys)))
+        logging.warning("tips模块不完整，您可以依据tips-custom-template.py检查tips.py")
+        logging.warning("以上配置已被设为默认值，将在3秒后继续启动... ")
+        time.sleep(3)
+
+
+def start(first_time_init=False):
+    """启动流程，reload之后会被执行"""
+
+    global known_exception_caught
     import pkg.utils.context
 
-    if pkg.utils.context.context['logger_handler'] is not None:
-        logging.getLogger().removeHandler(pkg.utils.context.context['logger_handler'])
-
-    for handler in logging.getLogger().handlers:
-        logging.getLogger().removeHandler(handler)
-
-    logging.basicConfig(level=config.logging_level,  # 设置日志输出格式
-                        filename=log_file_name,  # log日志输出的文件位置和文件名
-                        format="[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : %(message)s",
-                        # 日志输出的格式
-                        # -8表示占位符，让输出左对齐，输出长度都为8位
-                        datefmt="%Y-%m-%d %H:%M:%S"  # 时间输出的格式
-                        )
-    sh = logging.StreamHandler()
-    sh.setLevel(config.logging_level)
-    sh.setFormatter(colorlog.ColoredFormatter(
-        fmt="%(log_color)s[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : "
-            "%(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S",
-        log_colors=log_colors_config
-    ))
-    logging.getLogger().addHandler(sh)
-    pkg.utils.context.context['logger_handler'] = sh
-    return sh
-
-
-def main(first_time_init=False):
-    global known_exception_caught
-
-    # 检查并创建plugins、prompts目录
-    check_path = ["plugins", "prompts"]
-    for path in check_path:
-        if not os.path.exists(path):
-            os.mkdir(path)
+    config = pkg.utils.context.get_config()
+    # 更新openai库到最新版本
+    if not hasattr(config, 'upgrade_dependencies') or config.upgrade_dependencies:
+        print("正在更新依赖库，请等待...")
+        if not hasattr(config, 'upgrade_dependencies'):
+            print("这个操作不是必须的,如果不想更新,请在config.py中添加upgrade_dependencies=False")
+        else:
+            print("这个操作不是必须的,如果不想更新,请在config.py中将upgrade_dependencies设置为False")
+        try:
+            ensure_dependencies()
+        except Exception as e:
+            print("更新openai库失败:{}, 请忽略或自行更新".format(e))
 
     known_exception_caught = False
     try:
-        # 导入config.py
-        assert os.path.exists('config.py')
+        try:
 
-        config = importlib.import_module('config')
+            sh = reset_logging()
+            pkg.utils.context.context['logger_handler'] = sh
 
-        import pkg.utils.context
-        pkg.utils.context.set_config(config)
+            # 检查是否设置了管理员
+            if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
+                # logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
+                while True:
+                    try:
+                        config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
+                        # 写入到文件
 
-        init_runtime_log_file()
+                        # 读取文件
+                        config_file_str = ""
+                        with open("config.py", "r", encoding="utf-8") as f:
+                            config_file_str = f.read()
+                        # 替换
+                        config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
+                        # 写入
+                        with open("config.py", "w", encoding="utf-8") as f:
+                            f.write(config_file_str)
 
-        sh = reset_logging()
+                        print("管理员QQ已设置，如需修改请修改config.py中的admin_qq字段")
+                        time.sleep(4)
+                        break
+                    except ValueError:
+                        print("请输入数字")
 
-        # 检查是否设置了管理员
-        if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
-            # logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
-            while True:
-                try:
-                    config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
-                    # 写入到文件
+            import pkg.openai.manager
+            import pkg.database.manager
+            import pkg.openai.session
+            import pkg.qqbot.manager
+            import pkg.openai.dprompt
+            import pkg.qqbot.cmds.aamgr
+            
+            try:
+                pkg.openai.dprompt.register_all()
+                pkg.qqbot.cmds.aamgr.register_all()
+                pkg.qqbot.cmds.aamgr.apply_privileges()
+            except Exception as e:
+                logging.error(e)
+                traceback.print_exc()
 
-                    # 读取文件
-                    config_file_str = ""
-                    with open("config.py", "r", encoding="utf-8") as f:
-                        config_file_str = f.read()
-                    # 替换
-                    config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
-                    # 写入
-                    with open("config.py", "w", encoding="utf-8") as f:
-                        f.write(config_file_str)
+            # 配置OpenAI proxy
+            import openai
+            openai.proxy = None  # 先重置，因为重载后可能需要清除proxy
+            if "http_proxy" in config.openai_config and config.openai_config["http_proxy"] is not None:
+                openai.proxy = config.openai_config["http_proxy"]
 
-                    print("管理员QQ已设置，如需修改请修改config.py中的admin_qq字段")
-                    time.sleep(4)
-                    break
-                except ValueError:
-                    print("请输入数字")
+            # 配置openai api_base
+            if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
+                openai.api_base = config.openai_config["reverse_proxy"]
 
-        import pkg.openai.manager
-        import pkg.database.manager
-        import pkg.openai.session
-        import pkg.qqbot.manager
-        import pkg.openai.dprompt
+            # 主启动流程
+            database = pkg.database.manager.DatabaseManager()
 
-        pkg.openai.dprompt.read_prompt_from_file()
+            database.initialize_database()
 
-        pkg.utils.context.context['logger_handler'] = sh
-        # 主启动流程
-        database = pkg.database.manager.DatabaseManager()
+            openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
 
-        database.initialize_database()
+            # 加载所有未超时的session
+            pkg.openai.session.load_sessions()
 
-        openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
+            # 初始化qq机器人
+            qqbot = pkg.qqbot.manager.QQBotManager(first_time_init=first_time_init)
 
-        # 加载所有未超时的session
-        pkg.openai.session.load_sessions()
+            # 加载插件
+            import pkg.plugin.host
+            pkg.plugin.host.load_plugins()
 
-        # 初始化qq机器人
-        qqbot = pkg.qqbot.manager.QQBotManager(mirai_http_api_config=config.mirai_http_api_config,
-                                               timeout=config.process_message_timeout, retry=config.retry_times,
-                                               first_time_init=first_time_init)
+            pkg.plugin.host.initialize_plugins()
 
-        # 加载插件
-        import pkg.plugin.host
-        pkg.plugin.host.load_plugins()
+            if first_time_init:  # 不是热重载之后的启动,则启动新的bot线程
 
-        pkg.plugin.host.initialize_plugins()
+                import mirai.exceptions
 
-        if first_time_init:  # 不是热重载之后的启动,则不启动新的bot线程
+                def run_bot_wrapper():
+                    global known_exception_caught
+                    try:
+                        logging.debug("使用账号: {}".format(qqbot.bot_account_id))
+                        qqbot.adapter.run_sync()
+                    except TypeError as e:
+                        if str(e).__contains__("argument 'debug'"):
+                            logging.error(
+                                "连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("As of 3.10, the *loop*"):
+                            logging.error(
+                                "Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
+                            known_exception_caught = True
 
-            import mirai.exceptions
-
-            def run_bot_wrapper():
-                global known_exception_caught
-                try:
-                    qqbot.bot.run()
-                except TypeError as e:
-                    if str(e).__contains__("argument 'debug'"):
-                        logging.error(
-                            "连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
-                        known_exception_caught = True
-                    elif str(e).__contains__("As of 3.10, the *loop*"):
-                        logging.error(
-                            "Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
-                        known_exception_caught = True
-
-                except websockets.exceptions.InvalidStatus as e:
-                    logging.error(
-                        "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
-                            e))
-                    known_exception_caught = True
-                except mirai.exceptions.NetworkError as e:
-                    logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
-                    known_exception_caught = True
-                except Exception as e:
-                    if str(e).__contains__("404"):
+                    except websockets.exceptions.InvalidStatus as e:
                         logging.error(
                             "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
                                 e))
                         known_exception_caught = True
-                    elif str(e).__contains__("signal only works in main thread"):
-                        logging.error(
-                            "hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
-                                e))
+                    except mirai.exceptions.NetworkError as e:
+                        logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
                         known_exception_caught = True
-                    elif str(e).__contains__("did not receive a valid HTTP"):
-                        logging.error(
-                            "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
-                                e))
-                    else:
-                        logging.error(
-                            "捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
-                        known_exception_caught = True
-                        raise e
-
-            qq_bot_thread = threading.Thread(target=run_bot_wrapper, args=(), daemon=True)
-            qq_bot_thread.start()
+                    except Exception as e:
+                        if str(e).__contains__("404"):
+                            logging.error(
+                                "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
+                                    e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("signal only works in main thread"):
+                            logging.error(
+                                "hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
+                                    e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("did not receive a valid HTTP"):
+                            logging.error(
+                                "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
+                                    e))
+                        else:
+                            import traceback
+                            traceback.print_exc()
+                            logging.error(
+                                "捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
+                            known_exception_caught = True
+                            raise e
+                    finally:
+                        time.sleep(12)
+                threading.Thread(
+                    target=run_bot_wrapper
+                ).start()
+        except Exception as e:
+            traceback.print_exc()
+            if isinstance(e, KeyboardInterrupt):
+                logging.info("程序被用户中止")
+                sys.exit(0)
+            elif isinstance(e, SyntaxError):
+                logging.error("配置文件存在语法错误，请检查配置文件：\n1. 是否存在中文符号\n2. 是否已按照文件中的说明填写正确")
+                sys.exit(1)
+            else:
+                logging.error("初始化失败:{}".format(e))
+                sys.exit(1)
     finally:
+        # 判断若是Windows，输出选择模式可能会暂停程序的警告
+        if os.name == 'nt':
+            time.sleep(2)
+            logging.info("您正在使用Windows系统，若命令行窗口处于“选择”模式，程序可能会被暂停，此时请右键点击窗口空白区域使其取消选择模式。")
+
         time.sleep(12)
+        
         if first_time_init:
             if not known_exception_caught:
-                logging.info('程序启动完成,如长时间未显示 ”成功登录到账号xxxxx“ ,并且不回复消息,请查看 '
-                             'https://github.com/RockChinQ/QChatGPT/issues/37')
+                import config
+                if config.msg_source_adapter == "yirimirai":
+                    logging.info("QQ: {}, MAH: {}".format(config.mirai_http_api_config['qq'], config.mirai_http_api_config['host']+":"+str(config.mirai_http_api_config['port'])))
+                    logging.critical('程序启动完成,如长时间未显示 "成功登录到账号xxxxx" ,并且不回复消息,解决办法(请勿到群里问): '
+                                'https://github.com/RockChinQ/QChatGPT/issues/37')
+                elif config.msg_source_adapter == 'nakuru':
+                    logging.info("host: {}, port: {}, http_port: {}".format(config.nakuru_config['host'], config.nakuru_config['port'], config.nakuru_config['http_port']))
+                    logging.critical('程序启动完成,如长时间未显示 "Protocol: connected" ,并且不回复消息,请检查config.py中的nakuru_config是否正确')
             else:
                 sys.exit(1)
         else:
             logging.info('热重载完成')
 
     # 发送赞赏码
-    if hasattr(config, 'encourage_sponsor_at_start') \
-        and config.encourage_sponsor_at_start \
+    if config.encourage_sponsor_at_start \
         and pkg.utils.context.get_openai_manager().audit_mgr.get_total_text_length() >= 2048:
 
         logging.info("发送赞赏码")
@@ -258,28 +327,26 @@ def main(first_time_init=False):
     import pkg.utils.updater
     try:
         if pkg.utils.updater.is_new_version_available():
-            pkg.utils.context.get_qqbot_manager().notify_admin("新版本可用，请发送 !update 进行自动更新")
+            logging.info("新版本可用，请发送 !update 进行自动更新\n更新日志:\n{}".format("\n".join(pkg.utils.updater.get_rls_notes())))
         else:
-            logging.info("当前已是最新版本")
+            # logging.info("当前已是最新版本")
+            pass
 
     except Exception as e:
         logging.warning("检查更新失败:{}".format(e))
 
-    while True:
-        try:
-            time.sleep(10)
-            if qqbot != pkg.utils.context.get_qqbot_manager():  # 已经reload了
-                logging.info("以前的main流程由于reload退出")
-                break
-        except KeyboardInterrupt:
-            stop()
-
-            print("程序退出")
-            sys.exit(0)
+    try:
+        import pkg.utils.announcement as announcement
+        new_announcement = announcement.fetch_new()
+        if len(new_announcement) > 0:
+            for announcement in new_announcement:
+                logging.critical("[公告]<{}> {}".format(announcement['time'], announcement['content']))
+    except Exception as e:
+        logging.warning("获取公告失败:{}".format(e))
 
+    return qqbot
 
 def stop():
-    import pkg.utils.context
     import pkg.qqbot.manager
     import pkg.openai.session
     try:
@@ -298,39 +365,108 @@ def stop():
             raise e
 
 
-if __name__ == '__main__':
-    # 检查是否有config.py,如果没有就把config-template.py复制一份,并退出程序
+def check_file():
+    # 检查是否有banlist.py,如果没有就把banlist-template.py复制一份
+    if not os.path.exists('banlist.py'):
+        shutil.copy('res/templates/banlist-template.py', 'banlist.py')
+
+    # 检查是否有sensitive.json
+    if not os.path.exists("sensitive.json"):
+        shutil.copy("res/templates/sensitive-template.json", "sensitive.json")
+
+    # 检查是否有scenario/default.json
+    if not os.path.exists("scenario/default.json"):
+        shutil.copy("scenario/default-template.json", "scenario/default.json")
+
+    # 检查cmdpriv.json
+    if not os.path.exists("cmdpriv.json"):
+        shutil.copy("res/templates/cmdpriv-template.json", "cmdpriv.json")
+
+    # 检查tips_custom
+    if not os.path.exists("tips.py"):
+        shutil.copy("tips-custom-template.py", "tips.py")
+
+    # 检查temp目录
+    if not os.path.exists("temp/"):
+        os.mkdir("temp/")
+
+    # 检查并创建plugins、prompts目录
+    check_path = ["plugins", "prompts"]
+    for path in check_path:
+        if not os.path.exists(path):
+            os.mkdir(path)
+
+    # 配置文件存在性校验
     if not os.path.exists('config.py'):
         shutil.copy('config-template.py', 'config.py')
         print('请先在config.py中填写配置')
         sys.exit(0)
 
-    # 检查是否有banlist.py,如果没有就把banlist-template.py复制一份
-    if not os.path.exists('banlist.py'):
-        shutil.copy('banlist-template.py', 'banlist.py')
 
+def main():
+    global use_override
+    # 检查是否携带了 --override 或 -r 参数
+    if '--override' in sys.argv or '-r' in sys.argv:
+        use_override = True
+
+    # 初始化相关文件
+    check_file()
+
+    # 初始化logging
+    init_runtime_log_file()
+    pkg.utils.context.context['logger_handler'] = reset_logging()
+
+    # 加载配置
+    load_config()
+    config = pkg.utils.context.get_config()
+
+    # 检查tips模块
+    complete_tips()
+
+    # 配置线程池
+    from pkg.utils import ThreadCtl
+    thread_ctl = ThreadCtl(
+        sys_pool_num=config.sys_pool_num,
+        admin_pool_num=config.admin_pool_num,
+        user_pool_num=config.user_pool_num
+    )
+    # 存进上下文
+    pkg.utils.context.set_thread_ctl(thread_ctl)
+
+    # 启动指令处理
     if len(sys.argv) > 1 and sys.argv[1] == 'init_db':
         init_db()
         sys.exit(0)
 
     elif len(sys.argv) > 1 and sys.argv[1] == 'update':
-        try:
-            try:
-                import pkg.utils.pkgmgr
-                pkg.utils.pkgmgr.ensure_dulwich()
-            except:
-                pass
-
-            from dulwich import porcelain
-
-            repo = porcelain.open_repo('.')
-            porcelain.pull(repo)
-        except ModuleNotFoundError:
-            print("dulwich模块未安装,请查看 https://github.com/RockChinQ/QChatGPT/issues/77")
+        print("正在进行程序更新...")
+        import pkg.utils.updater as updater
+        updater.update_all(cli=True)
         sys.exit(0)
 
-    # import pkg.utils.configmgr
-    #
-    # pkg.utils.configmgr.set_config_and_reload("quote_origin", False)
+    # 关闭urllib的http警告
     requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
-    main(True)
+
+    pkg.utils.context.get_thread_ctl().submit_sys_task(
+        start,
+        True
+    )
+
+    # 主线程循环
+    while True:
+        try:
+            time.sleep(0xFF)
+        except:
+            stop()
+            pkg.utils.context.get_thread_ctl().shutdown()
+            import platform
+            if platform.system() == 'Windows':
+                cmd = "taskkill /F /PID {}".format(os.getpid())
+            elif platform.system() in ['Linux', 'Darwin']:
+                cmd = "kill -9 {}".format(os.getpid())
+            os.system(cmd)
+
+
+if __name__ == '__main__':
+    main()
+

override-all.json

@@ -0,0 +1,95 @@
+{
+    "comment": "这是override.json支持的字段全集, 关于override.json机制, 请查看https://github.com/RockChinQ/QChatGPT/pull/271",
+    "msg_source_adapter": "yirimirai",
+    "mirai_http_api_config": {
+        "adapter": "WebSocketAdapter",
+        "host": "localhost",
+        "port": 8080,
+        "verifyKey": "yirimirai",
+        "qq": 1234567890
+    },
+    "nakuru_config": {
+        "host": "localhost",
+        "port": 6700,
+        "http_port": 5700,
+        "token": ""
+    },
+    "openai_config": {
+        "api_key": {
+            "default": "openai_api_key"
+        },
+        "http_proxy": null,
+        "reverse_proxy": null
+    },
+    "switch_strategy": "active",
+    "admin_qq": 0,
+    "default_prompt": {
+        "default": "如果我之后想获取帮助，请你说“输入!help获取帮助”"
+    },
+    "preset_mode": "normal",
+    "response_rules": {
+        "default": {
+            "at": true,
+            "prefix": [
+                "/ai",
+                "!ai",
+                "！ai",
+                "ai"
+            ],
+            "regexp": [],
+            "random_rate": 0.0
+        }
+    },
+    "ignore_rules": {
+        "prefix": [
+            "/"
+        ],
+        "regexp": []
+    },
+    "income_msg_check": false,
+    "sensitive_word_filter": true,
+    "baidu_check": false,
+    "baidu_api_key": "",
+    "baidu_secret_key": "",
+    "inappropriate_message_tips": "[百度云]请珍惜机器人，当前返回内容不合规",
+    "encourage_sponsor_at_start": true,
+    "prompt_submit_length": 2048,
+    "auto_reset": true,
+    "completion_api_params": {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0.9,
+        "top_p": 1,
+        "frequency_penalty": 0.2,
+        "presence_penalty": 1.0
+    },
+    "image_api_params": {
+        "size": "256x256"
+    },
+    "trace_function_calls": false,
+    "quote_origin": true,
+    "at_sender": false,
+    "include_image_description": true,
+    "process_message_timeout": 30,
+    "show_prefix": false,
+    "force_delay_range": [
+        1.5,
+        3
+    ],
+    "blob_message_threshold": 256,
+    "blob_message_strategy": "forward",
+    "wait_last_done": true,
+    "font_path": "",
+    "retry_times": 3,
+    "hide_exce_info_to_user": false,
+    "sys_pool_num": 8,
+    "admin_pool_num": 4,
+    "user_pool_num": 8,
+    "session_expire_time": 1200,
+    "rate_limitation": {
+        "default": 60
+    },
+    "rate_limit_strategy": "drop",
+    "upgrade_dependencies": true,
+    "report_usage": true,
+    "logging_level": 20
+}

pkg/audit/__init__.py

@@ -0,0 +1,3 @@
+"""
+审计相关操作
+"""

pkg/audit/gatherer.py

@@ -1,3 +1,7 @@
+"""
+使用量统计以及数据上报功能实现
+"""
+
 import hashlib
 import json
 import logging
@@ -10,8 +14,11 @@ import pkg.utils.updater
 
 class DataGatherer:
     """数据收集器"""
+
     usage = {}
-    """以key值md5为key,{
+    """各api-key的使用量
+    
+    以key值md5为key,{
         "text": {
             "text-davinci-003": 文字量:int,
         },
@@ -20,21 +27,26 @@ class DataGatherer:
         }
     }为值的字典"""
 
-    version_str = "0.1.0"
+    version_str = "undetermined"
 
     def __init__(self):
         self.load_from_db()
         try:
-            self.version_str = pkg.utils.updater.get_commit_id_and_time_and_msg()[:40 if len(pkg.utils.updater.get_commit_id_and_time_and_msg()) > 40 else len(pkg.utils.updater.get_commit_id_and_time_and_msg())]
+            self.version_str = pkg.utils.updater.get_current_tag()  # 从updater模块获取版本号
         except:
             pass
 
     def report_to_server(self, subservice_name: str, count: int):
+        """向中央服务器报告使用量
+
+        只会报告此次请求的使用量，不会报告总量。
+        不包含除版本号、使用类型、使用量以外的任何信息，仅供开发者分析使用情况。
+        """
         try:
             config = pkg.utils.context.get_config()
-            if hasattr(config, "report_usage") and not config.report_usage:
+            if not config.report_usage:
                 return
-            res = requests.get("http://rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}".format(subservice_name, self.version_str, count))
+            res = requests.get("http://reports.rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}&msg_source={}".format(subservice_name, self.version_str, count, config.msg_source_adapter))
             if res.status_code != 200 or res.text != "ok":
                 logging.warning("report to server failed, status_code: {}, text: {}".format(res.status_code, res.text))
         except:
@@ -44,7 +56,9 @@ class DataGatherer:
         return self.usage[key_md5] if key_md5 in self.usage else {}
 
     def report_text_model_usage(self, model, total_tokens):
-        key_md5 = pkg.utils.context.get_openai_manager().key_mgr.get_using_key_md5()
+        """调用方报告文字模型请求文字使用量"""
+
+        key_md5 = pkg.utils.context.get_openai_manager().key_mgr.get_using_key_md5()  # 以key的md5进行储存
 
         if key_md5 not in self.usage:
             self.usage[key_md5] = {}
@@ -62,6 +76,8 @@ class DataGatherer:
         self.report_to_server("text", length)
 
     def report_image_model_usage(self, size):
+        """调用方报告图片模型请求图片使用量"""
+
         key_md5 = pkg.utils.context.get_openai_manager().key_mgr.get_using_key_md5()
 
         if key_md5 not in self.usage:
@@ -79,6 +95,7 @@ class DataGatherer:
         self.report_to_server("image", 1)
 
     def get_text_length_of_key(self, key):
+        """获取指定api-key (明文) 的文字总使用量(本地记录)"""
         key_md5 = hashlib.md5(key.encode('utf-8')).hexdigest()
         if key_md5 not in self.usage:
             return 0
@@ -88,6 +105,8 @@ class DataGatherer:
         return sum(self.usage[key_md5]["text"].values())
 
     def get_image_count_of_key(self, key):
+        """获取指定api-key (明文) 的图片总使用量(本地记录)"""
+
         key_md5 = hashlib.md5(key.encode('utf-8')).hexdigest()
         if key_md5 not in self.usage:
             return 0
@@ -97,6 +116,7 @@ class DataGatherer:
         return sum(self.usage[key_md5]["image"].values())
 
     def get_total_text_length(self):
+        """获取所有api-key的文字总使用量(本地记录)"""
         total = 0
         for key in self.usage:
             if "text" not in self.usage[key]:

pkg/database/__init__.py

@@ -0,0 +1,3 @@
+"""
+数据库操作封装
+"""

pkg/database/manager.py

@@ -1,3 +1,6 @@
+"""
+数据库管理模块
+"""
 import hashlib
 import json
 import logging
@@ -9,9 +12,9 @@ import sqlite3
 import pkg.utils.context
 
 
-# 数据库管理
-# 为其他模块提供数据库操作接口
 class DatabaseManager:
+    """封装数据库底层操作，并提供方法给上层使用"""
+
     conn = None
     cursor = None
 
@@ -23,21 +26,25 @@ class DatabaseManager:
 
     # 连接到数据库文件
     def reconnect(self):
+        """连接到数据库"""
         self.conn = sqlite3.connect('database.db', check_same_thread=False)
         self.cursor = self.conn.cursor()
 
     def close(self):
         self.conn.close()
 
-    def execute(self, *args, **kwargs) -> Cursor:
+    def __execute__(self, *args, **kwargs) -> Cursor:
         # logging.debug('SQL: {}'.format(sql))
+        logging.debug('SQL: {}'.format(args))
         c = self.cursor.execute(*args, **kwargs)
         self.conn.commit()
         return c
 
     # 初始化数据库的函数
     def initialize_database(self):
-        self.execute("""
+        """创建数据表"""
+
+        self.__execute__("""
         create table if not exists `sessions` (
             `id` INTEGER PRIMARY KEY AUTOINCREMENT,
             `name` varchar(255) not null,
@@ -46,11 +53,31 @@ class DatabaseManager:
             `create_timestamp` bigint not null,
             `last_interact_timestamp` bigint not null,
             `status` varchar(255) not null default 'on_going',
-            `prompt` text not null
+            `default_prompt` text not null default '',
+            `prompt` text not null,
+            `token_counts` text not null default '[]'
         )
         """)
 
-        self.execute("""
+        # 检查sessions表是否存在`default_prompt`字段, 检查是否存在`token_counts`字段
+        self.__execute__("PRAGMA table_info('sessions')")
+        columns = self.cursor.fetchall()
+        has_default_prompt = False
+        has_token_counts = False
+        for field in columns:
+            if field[1] == 'default_prompt':
+                has_default_prompt = True
+            if field[1] == 'token_counts':
+                has_token_counts = True
+            if has_default_prompt and has_token_counts:
+                break
+        if not has_default_prompt:
+            self.__execute__("alter table `sessions` add column `default_prompt` text not null default ''")
+        if not has_token_counts:
+            self.__execute__("alter table `sessions` add column `token_counts` text not null default '[]'")
+
+
+        self.__execute__("""
         create table if not exists `account_fee`(
             `id` INTEGER PRIMARY KEY AUTOINCREMENT,
             `key_md5` varchar(255) not null,
@@ -59,7 +86,7 @@ class DatabaseManager:
         )
         """)
 
-        self.execute("""
+        self.__execute__("""
         create table if not exists `account_usage`(
             `id` INTEGER PRIMARY KEY AUTOINCREMENT,
             `json` text not null
@@ -69,47 +96,49 @@ class DatabaseManager:
 
     # session持久化
     def persistence_session(self, subject_type: str, subject_number: int, create_timestamp: int,
-                            last_interact_timestamp: int, prompt: str):
+                            last_interact_timestamp: int, prompt: str, default_prompt: str = '', token_counts: str = ''):
+        """持久化指定session"""
+
         # 检查是否已经有了此name和create_timestamp的session
         # 如果有，就更新prompt和last_interact_timestamp
         # 如果没有，就插入一条新的记录
-        self.execute("""
+        self.__execute__("""
         select count(*) from `sessions` where `type` = '{}' and `number` = {} and `create_timestamp` = {}
         """.format(subject_type, subject_number, create_timestamp))
         count = self.cursor.fetchone()[0]
         if count == 0:
 
             sql = """
-            insert into `sessions` (`name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`) 
-            values (?, ?, ?, ?, ?, ?)
+            insert into `sessions` (`name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `default_prompt`, `token_counts`) 
+            values (?, ?, ?, ?, ?, ?, ?, ?)
             """
 
-            self.execute(sql,
-                         ("{}_{}".format(subject_type, subject_number), subject_type, subject_number, create_timestamp,
-                          last_interact_timestamp, prompt))
+            self.__execute__(sql,
+                             ("{}_{}".format(subject_type, subject_number), subject_type, subject_number, create_timestamp,
+                          last_interact_timestamp, prompt, default_prompt, token_counts))
         else:
             sql = """
-            update `sessions` set `last_interact_timestamp` = ?, `prompt` = ? 
+            update `sessions` set `last_interact_timestamp` = ?, `prompt` = ?, `token_counts` = ?
             where `type` = ? and `number` = ? and `create_timestamp` = ?
             """
 
-            self.execute(sql, (last_interact_timestamp, prompt, subject_type,
-                               subject_number, create_timestamp))
+            self.__execute__(sql, (last_interact_timestamp, prompt, token_counts, subject_type,
+                                   subject_number, create_timestamp))
 
     # 显式关闭一个session
     def explicit_close_session(self, session_name: str, create_timestamp: int):
-        self.execute("""
+        self.__execute__("""
         update `sessions` set `status` = 'explicitly_closed' where `name` = '{}' and `create_timestamp` = {}
         """.format(session_name, create_timestamp))
 
     def set_session_ongoing(self, session_name: str, create_timestamp: int):
-        self.execute("""
+        self.__execute__("""
         update `sessions` set `status` = 'on_going' where `name` = '{}' and `create_timestamp` = {}
         """.format(session_name, create_timestamp))
 
     # 设置session为过期
     def set_session_expired(self, session_name: str, create_timestamp: int):
-        self.execute("""
+        self.__execute__("""
         update `sessions` set `status` = 'expired' where `name` = '{}' and `create_timestamp` = {}
         """.format(session_name, create_timestamp))
 
@@ -117,8 +146,8 @@ class DatabaseManager:
     def load_valid_sessions(self) -> dict:
         # 从数据库中加载所有还没过期的session
         config = pkg.utils.context.get_config()
-        self.execute("""
-        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`
+        self.__execute__("""
+        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`, `default_prompt`, `token_counts`
         from `sessions` where `last_interact_timestamp` > {}
         """.format(int(time.time()) - config.session_expire_time))
         results = self.cursor.fetchall()
@@ -131,6 +160,8 @@ class DatabaseManager:
             last_interact_timestamp = result[4]
             prompt = result[5]
             status = result[6]
+            default_prompt = result[7]
+            token_counts = result[8]
 
             # 当且仅当最后一个该对象的会话是on_going状态时，才会被加载
             if status == 'on_going':
@@ -139,7 +170,9 @@ class DatabaseManager:
                     'subject_number': subject_number,
                     'create_timestamp': create_timestamp,
                     'last_interact_timestamp': last_interact_timestamp,
-                    'prompt': prompt
+                    'prompt': prompt,
+                    'default_prompt': default_prompt,
+                    'token_counts': token_counts
                 }
             else:
                 if session_name in sessions:
@@ -150,8 +183,8 @@ class DatabaseManager:
     # 获取此session_name前一个session的数据
     def last_session(self, session_name: str, cursor_timestamp: int):
 
-        self.execute("""
-        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`
+        self.__execute__("""
+        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`, `default_prompt`, `token_counts`
         from `sessions` where `name` = '{}' and `last_interact_timestamp` < {} order by `last_interact_timestamp` desc
         limit 1
         """.format(session_name, cursor_timestamp))
@@ -167,20 +200,24 @@ class DatabaseManager:
         last_interact_timestamp = result[4]
         prompt = result[5]
         status = result[6]
+        default_prompt = result[7]
+        token_counts = result[8]
 
         return {
             'subject_type': subject_type,
             'subject_number': subject_number,
             'create_timestamp': create_timestamp,
             'last_interact_timestamp': last_interact_timestamp,
-            'prompt': prompt
+            'prompt': prompt,
+            'default_prompt': default_prompt,
+            'token_counts': token_counts
         }
 
     # 获取此session_name后一个session的数据
     def next_session(self, session_name: str, cursor_timestamp: int):
 
-        self.execute("""
-            select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`
+        self.__execute__("""
+            select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`, `default_prompt`, `token_counts`
             from `sessions` where `name` = '{}' and `last_interact_timestamp` > {} order by `last_interact_timestamp` asc
             limit 1
             """.format(session_name, cursor_timestamp))
@@ -196,19 +233,23 @@ class DatabaseManager:
         last_interact_timestamp = result[4]
         prompt = result[5]
         status = result[6]
+        default_prompt = result[7]
+        token_counts = result[8]
 
         return {
             'subject_type': subject_type,
             'subject_number': subject_number,
             'create_timestamp': create_timestamp,
             'last_interact_timestamp': last_interact_timestamp,
-            'prompt': prompt
+            'prompt': prompt,
+            'default_prompt': default_prompt,
+            'token_counts': token_counts
         }
 
     # 列出与某个对象的所有对话session
     def list_history(self, session_name: str, capacity: int, page: int):
-        self.execute("""
-        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`
+        self.__execute__("""
+        select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`, `default_prompt`, `token_counts`
         from `sessions` where `name` = '{}' order by `last_interact_timestamp` desc limit {} offset {}
         """.format(session_name, capacity, capacity * page))
         results = self.cursor.fetchall()
@@ -221,17 +262,42 @@ class DatabaseManager:
             last_interact_timestamp = result[4]
             prompt = result[5]
             status = result[6]
+            default_prompt = result[7]
+            token_counts = result[8]
 
             sessions.append({
                 'subject_type': subject_type,
                 'subject_number': subject_number,
                 'create_timestamp': create_timestamp,
                 'last_interact_timestamp': last_interact_timestamp,
-                'prompt': prompt
+                'prompt': prompt,
+                'default_prompt': default_prompt,
+                'token_counts': token_counts
             })
 
         return sessions
 
+    def delete_history(self, session_name: str, index: int) -> bool:
+        # 删除倒序第index个session
+        # 查找其id再删除
+        self.__execute__("""
+        delete from `sessions` where `id` in (select `id` from `sessions` where `name` = '{}' order by `last_interact_timestamp` desc limit 1 offset {})
+        """.format(session_name, index))
+
+        return self.cursor.rowcount == 1
+
+    def delete_all_history(self, session_name: str) -> bool:
+        self.__execute__("""
+        delete from `sessions` where `name` = '{}'
+        """.format(session_name))
+        return self.cursor.rowcount > 0
+
+    def delete_all_session_history(self) -> bool:
+        self.__execute__("""
+        delete from `sessions`
+        """)
+        return self.cursor.rowcount > 0
+
     # 将apikey的使用量存进数据库
     def dump_api_key_usage(self, api_keys: dict, usage: dict):
         logging.debug('dumping api key usage...')
@@ -246,22 +312,22 @@ class DatabaseManager:
                 usage_count = usage[key_md5]
             # 将使用量存进数据库
             # 先检查是否已存在
-            self.execute("""
+            self.__execute__("""
             select count(*) from `api_key_usage` where `key_md5` = '{}'""".format(key_md5))
             result = self.cursor.fetchone()
             if result[0] == 0:
                 # 不存在则插入
-                self.execute("""
+                self.__execute__("""
                 insert into `api_key_usage` (`key_md5`, `usage`,`timestamp`) values ('{}', {}, {})
                 """.format(key_md5, usage_count, int(time.time())))
             else:
                 # 存在则更新，timestamp设置为当前
-                self.execute("""
+                self.__execute__("""
                 update `api_key_usage` set `usage` = {}, `timestamp` = {} where `key_md5` = '{}'
                 """.format(usage_count, int(time.time()), key_md5))
 
     def load_api_key_usage(self):
-        self.execute("""
+        self.__execute__("""
         select `key_md5`, `usage` from `api_key_usage`
         """)
         results = self.cursor.fetchall()
@@ -273,23 +339,24 @@ class DatabaseManager:
         return usage
 
     def dump_usage_json(self, usage: dict):
+
         json_str = json.dumps(usage)
-        self.execute("""
+        self.__execute__("""
         select count(*) from `account_usage`""")
         result = self.cursor.fetchone()
         if result[0] == 0:
             # 不存在则插入
-            self.execute("""
+            self.__execute__("""
             insert into `account_usage` (`json`) values ('{}')
             """.format(json_str))
         else:
             # 存在则更新
-            self.execute("""
+            self.__execute__("""
             update `account_usage` set `json` = '{}' where `id` = 1
             """.format(json_str))
 
     def load_usage_json(self):
-        self.execute("""
+        self.__execute__("""
         select `json` from `account_usage` order by id desc limit 1
         """)
         result = self.cursor.fetchone()

pkg/openai/__init__.py

@@ -0,0 +1 @@
+"""OpenAI 接口处理及会话管理相关"""

pkg/openai/api/chat_completion.py

@@ -0,0 +1,204 @@
+import openai
+import json
+import logging
+
+from .model import RequestBase
+
+from ..funcmgr import get_func_schema_list, execute_function, get_func, get_func_schema, ContentFunctionNotFoundError
+
+
+class ChatCompletionRequest(RequestBase):
+    """调用ChatCompletion接口的请求类。
+    
+    此类保证每一次返回的角色为assistant的信息的finish_reason一定为stop。
+    若有函数调用响应，本类的返回瀑布是：函数调用请求->函数调用结果->...->assistant的信息->stop。
+    """
+    model: str
+    messages: list[dict[str, str]]
+    kwargs: dict
+
+    stopped: bool = False
+
+    pending_func_call: dict = None
+
+    pending_msg: str
+
+    def flush_pending_msg(self):
+        self.append_message(
+            role="assistant",
+            content=self.pending_msg
+        )
+        self.pending_msg = ""
+
+    def append_message(self, role: str, content: str, name: str=None, function_call: dict=None):
+        msg = {
+            "role": role,
+            "content": content
+        }
+
+        if name is not None:
+            msg['name'] = name
+
+        if function_call is not None:
+            msg['function_call'] = function_call
+
+        self.messages.append(msg)
+
+    def __init__(
+        self,
+        model: str,
+        messages: list[dict[str, str]],
+        **kwargs
+    ):
+        self.model = model
+        self.messages = messages.copy()
+
+        self.kwargs = kwargs
+
+        self.req_func = openai.ChatCompletion.acreate
+
+        self.pending_func_call = None
+
+        self.stopped = False
+
+        self.pending_msg = ""
+
+    def __iter__(self):
+        return self
+
+    def __next__(self) -> dict:
+        if self.stopped:
+            raise StopIteration()
+
+        if self.pending_func_call is None:  # 没有待处理的函数调用请求
+
+            args = {
+                "model": self.model,
+                "messages": self.messages,
+            }
+
+            funcs = get_func_schema_list()
+
+            if len(funcs) > 0:
+                args['functions'] = funcs
+
+            # 拼接kwargs
+            args = {**args, **self.kwargs}
+
+            resp = self._req(**args)
+
+            choice0 = resp["choices"][0]
+
+            # 如果不是函数调用，且finish_reason为stop，则停止迭代
+            if choice0['finish_reason'] == 'stop':  #  and choice0["finish_reason"] == "stop"
+                self.stopped = True
+            
+            if 'function_call' in choice0['message']:
+                self.pending_func_call = choice0['message']['function_call']
+
+                self.append_message(
+                    role="assistant",
+                    content=choice0['message']['content'],
+                    function_call=choice0['message']['function_call']
+                )
+
+                return {
+                    "id": resp["id"],
+                    "choices": [
+                        {
+                            "index": choice0["index"],
+                            "message": {
+                                "role": "assistant",
+                                "type": "function_call",
+                                "content": choice0['message']['content'],
+                                "function_call": choice0['message']['function_call']
+                            },
+                            "finish_reason": "function_call"
+                        }
+                    ],
+                    "usage": resp["usage"]
+                }
+            else:
+
+                # self.pending_msg += choice0['message']['content']
+                # 普通回复一定处于最后方，故不用再追加进内部messages
+
+                return {
+                    "id": resp["id"],
+                    "choices": [
+                        {
+                            "index": choice0["index"],
+                            "message": {
+                                "role": "assistant",
+                                "type": "text",
+                                "content": choice0['message']['content']
+                            },
+                            "finish_reason": choice0["finish_reason"]
+                        }
+                    ],
+                    "usage": resp["usage"]
+                }
+        else:  # 处理函数调用请求
+
+            cp_pending_func_call = self.pending_func_call.copy()
+            
+            self.pending_func_call = None
+
+            func_name = cp_pending_func_call['name']
+            arguments = {}
+
+            try:
+
+                try:
+                    arguments = json.loads(cp_pending_func_call['arguments'])
+                # 若不是json格式的异常处理
+                except json.decoder.JSONDecodeError:
+                    # 获取函数的参数列表
+                    func_schema = get_func_schema(func_name)
+
+                    arguments = {
+                        func_schema['parameters']['required'][0]: cp_pending_func_call['arguments']
+                    }
+                
+                logging.info("执行函数调用: name={}, arguments={}".format(func_name, arguments))
+
+                # 执行函数调用
+                ret = ""
+                try:
+                    ret = execute_function(func_name, arguments)
+
+                    logging.info("函数执行完成。")
+                except Exception as e:
+                    ret = "error: execute function failed: {}".format(str(e))
+                    logging.error("函数执行失败: {}".format(str(e)))
+
+                self.append_message(
+                    role="function",
+                    content=json.dumps(ret, ensure_ascii=False),
+                    name=func_name
+                )
+
+                return {
+                    "id": -1,
+                    "choices": [
+                        {
+                            "index": -1,
+                            "message": {
+                                "role": "function",
+                                "type": "function_return",
+                                "function_name": func_name,
+                                "content": json.dumps(ret, ensure_ascii=False)
+                            },
+                            "finish_reason": "function_return"
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 0,
+                        "completion_tokens": 0,
+                        "total_tokens": 0
+                    }
+                }
+
+            except ContentFunctionNotFoundError:
+                raise Exception("没有找到函数: {}".format(func_name))
+

pkg/openai/api/completion.py

@@ -0,0 +1,111 @@
+import openai
+
+from .model import RequestBase
+
+
+class CompletionRequest(RequestBase):
+    """调用Completion接口的请求类。
+    
+    调用方可以一直next completion直到finish_reason为stop。
+    """
+
+    model: str
+    prompt: str
+    kwargs: dict
+
+    stopped: bool = False
+
+    def __init__(
+        self,
+        model: str,
+        messages: list[dict[str, str]],
+        **kwargs
+    ):
+        self.model = model
+        self.prompt = ""
+        
+        for message in messages:
+            self.prompt += message["role"] + ": " + message["content"] + "\n"
+        
+        self.prompt += "assistant: "
+
+        self.kwargs = kwargs
+
+        self.req_func = openai.Completion.acreate
+
+    def __iter__(self):
+        return self
+
+    def __next__(self) -> dict:
+        """调用Completion接口，返回生成的文本
+        
+        {
+            "id": "id",
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "type": "text",
+                        "content": "message"
+                    },
+                    "finish_reason": "reason"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": 10,
+                "completion_tokens": 20,
+                "total_tokens": 30
+            }
+        }
+        """
+
+        if self.stopped:
+            raise StopIteration()
+
+        resp = self._req(
+            model=self.model,
+            prompt=self.prompt,
+            **self.kwargs
+        )
+
+        if resp["choices"][0]["finish_reason"] == "stop":
+            self.stopped = True
+
+        choice0 = resp["choices"][0]
+
+        self.prompt += choice0["text"]
+
+        return {
+            "id": resp["id"],
+            "choices": [
+                {
+                    "index": choice0["index"],
+                    "message": {
+                        "role": "assistant",
+                        "type": "text",
+                        "content": choice0["text"]
+                    },
+                    "finish_reason": choice0["finish_reason"]
+                }
+            ],
+            "usage": resp["usage"]
+        }
+        
+if __name__ == "__main__":
+    import os
+
+    openai.api_key = os.environ["OPENAI_API_KEY"]
+
+    for resp in CompletionRequest(
+        model="text-davinci-003",
+        messages=[
+            {
+                "role": "user",
+                "content": "Hello, who are you?"
+            }
+        ]
+    ):
+        print(resp)
+        if resp["choices"][0]["finish_reason"] == "stop":
+            break

pkg/openai/api/model.py

@@ -0,0 +1,62 @@
+# 定义不同接口请求的模型
+import threading
+import asyncio
+import logging
+
+import openai
+
+
+class RequestBase:
+
+    req_func: callable
+
+    def __init__(self, *args, **kwargs):
+        raise NotImplementedError
+
+    def _next_key(self):
+        import pkg.utils.context as context
+        switched, name = context.get_openai_manager().key_mgr.auto_switch()
+        logging.debug("切换api-key: switched={}, name={}".format(switched, name))
+        openai.api_key = context.get_openai_manager().key_mgr.get_using_key()
+
+    def _req(self, **kwargs):
+        """处理代理问题"""
+        import config
+
+        ret: dict = {}
+        exception: Exception = None
+
+        async def awrapper(**kwargs):
+            nonlocal ret, exception
+
+            try:
+                ret = await self.req_func(**kwargs)
+                logging.debug("接口请求返回：%s", str(ret))
+                
+                if config.switch_strategy == 'active':
+                    self._next_key()
+
+                return ret
+            except Exception as e:
+                exception = e
+            
+        loop = asyncio.new_event_loop()
+
+        thr = threading.Thread(
+            target=loop.run_until_complete,
+            args=(awrapper(**kwargs),)
+        )
+
+        thr.start()
+        thr.join()
+
+        if exception is not None:
+            raise exception
+
+        return ret
+
+    def __iter__(self):
+        raise self
+
+    def __next__(self):
+        raise NotImplementedError

pkg/openai/dprompt.py

@@ -1,74 +1,145 @@
 # 多情景预设值管理
+import json
+import logging
+import config
+import os
 
-__current__ = "default"
+# __current__ = "default"
+# """当前默认使用的情景预设的名称
 
-__prompts_from_files__ = {}
+# 由管理员使用`!default <名称>`指令切换
+# """
+
+# __prompts_from_files__ = {}
+# """从文件中读取的情景预设值"""
+
+# __scenario_from_files__ = {}
 
 
-def read_prompt_from_file() -> str:
-    """从文件读取预设值"""
-    # 读取prompts/目录下的所有文件，以文件名为键，文件内容为值
-    # 保存在__prompts_from_files__中
-    global __prompts_from_files__
-    import os
-
-    __prompts_from_files__ = {}
-    for file in os.listdir("prompts"):
-        with open(os.path.join("prompts", file), encoding="utf-8") as f:
-            __prompts_from_files__[file] = f.read()
+__universal_first_reply__ = "ok, I'll follow your commands."
+"""通用首次回复"""
 
 
-def get_prompt_dict() -> dict:
-    """获取预设值字典"""
+class ScenarioMode:
+    """情景预设模式抽象类"""
+
+    using_prompt_name = "default"
+    """新session创建时使用的prompt名称"""
+
+    prompts: dict[str, list] = {}
+
+    def __init__(self):
+        logging.debug("prompts: {}".format(self.prompts))
+
+    def list(self) -> dict[str, list]:
+        """获取所有情景预设的名称及内容"""
+        return self.prompts
+
+    def get_prompt(self, name: str) -> tuple[list, str]:
+        """获取指定情景预设的名称及内容"""
+        for key in self.prompts:
+            if key.startswith(name):
+                return self.prompts[key], key
+        raise Exception("没有找到情景预设: {}".format(name))
+
+    def set_using_name(self, name: str) -> str:
+        """设置默认情景预设"""
+        for key in self.prompts:
+            if key.startswith(name):
+                self.using_prompt_name = key
+                return key
+        raise Exception("没有找到情景预设: {}".format(name))
+    
+    def get_full_name(self, name: str) -> str:
+        """获取完整的情景预设名称"""
+        for key in self.prompts:
+            if key.startswith(name):
+                return key
+        raise Exception("没有找到情景预设: {}".format(name))
+
+    def get_using_name(self) -> str:
+        """获取默认情景预设"""
+        return self.using_prompt_name
+
+
+class NormalScenarioMode(ScenarioMode):
+    """普通情景预设模式"""
+
+    def __init__(self):
+        global __universal_first_reply__
+        # 加载config中的default_prompt值
+        if type(config.default_prompt) == str:
+            self.using_prompt_name = "default"
+            self.prompts = {"default": [
+                {
+                    "role": "user",
+                    "content": config.default_prompt
+                },{
+                    "role": "assistant",
+                    "content": __universal_first_reply__
+                }
+            ]}
+        
+        elif type(config.default_prompt) == dict:
+            for key in config.default_prompt:
+                self.prompts[key] = [
+                    {
+                        "role": "user",
+                        "content": config.default_prompt[key]
+                    },{
+                        "role": "assistant",
+                        "content": __universal_first_reply__
+                    }
+                ]
+
+        # 从prompts/目录下的文件中载入
+        # 遍历文件
+        for file in os.listdir("prompts"):
+            with open(os.path.join("prompts", file), encoding="utf-8") as f:
+                self.prompts[file] = [
+                    {
+                        "role": "user",
+                        "content": f.read()
+                    },{
+                        "role": "assistant",
+                        "content": __universal_first_reply__
+                    }
+                ]
+
+
+class FullScenarioMode(ScenarioMode):
+    """完整情景预设模式"""
+
+    def __init__(self):
+        """从json读取所有"""
+        # 遍历scenario/目录下的所有文件，以文件名为键，文件内容中的prompt为值
+        for file in os.listdir("scenario"):
+            if file == "default-template.json":
+                continue
+            with open(os.path.join("scenario", file), encoding="utf-8") as f:
+                self.prompts[file] = json.load(f)["prompt"]
+
+        super().__init__()
+
+
+scenario_mode_mapping = {}
+"""情景预设模式名称与对象的映射"""
+
+
+def register_all():
+    """注册所有情景预设模式，不使用装饰器，因为装饰器的方式不支持热重载"""
+    global scenario_mode_mapping
+    scenario_mode_mapping = {
+        "normal": NormalScenarioMode(),
+        "full_scenario": FullScenarioMode()
+    }
+
+
+def mode_inst() -> ScenarioMode:
+    """获取指定名称的情景预设模式对象"""
     import config
-    default_prompt = config.default_prompt
-    if type(default_prompt) == str:
-        default_prompt = {"default": default_prompt}
-    elif type(default_prompt) == dict:
-        pass
-    else:
-        raise TypeError("default_prompt must be str or dict")
 
-    # 将文件中的预设值合并到default_prompt中
-    for key in __prompts_from_files__:
-        default_prompt[key] = __prompts_from_files__[key]
+    if config.preset_mode == "default":
+        config.preset_mode = "normal"
 
-    return default_prompt
-
-
-def set_current(name):
-    global __current__
-    for key in get_prompt_dict():
-        if key.lower().startswith(name.lower()):
-            __current__ = key
-            return
-    raise KeyError("未找到情景预设: " + name)
-
-
-def get_current():
-    global __current__
-    return __current__
-
-
-def set_to_default():
-    global __current__
-    default_dict = get_prompt_dict()
-
-    if "default" in default_dict:
-        __current__ = "default"
-    else:
-        __current__ = list(default_dict.keys())[0]
-
-
-def get_prompt(name: str = None) -> str:
-    """获取预设值"""
-    if name is None:
-        name = get_current()
-
-    default_dict = get_prompt_dict()
-
-    for key in default_dict:
-        if key.lower().startswith(name.lower()):
-            return default_dict[key]
-
-    raise KeyError("未找到情景预设: " + name)
+    return scenario_mode_mapping[config.preset_mode]

pkg/openai/funcmgr.py

@@ -0,0 +1,47 @@
+# 封装了function calling的一些支持函数
+import logging
+
+
+from pkg.plugin import host
+
+
+class ContentFunctionNotFoundError(Exception):
+    pass
+
+
+def get_func_schema_list() -> list:
+    """从plugin包中的函数结构中获取并处理成受GPT支持的格式"""
+    if not host.__enable_content_functions__:
+        return []
+
+    schemas = []
+
+    for func in host.__callable_functions__:
+        if func['enabled']:
+            fun_cp = func.copy()
+
+            del fun_cp['enabled']
+
+            schemas.append(fun_cp)
+
+    return schemas
+
+def get_func(name: str) -> callable:
+    if name not in host.__function_inst_map__:
+        raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
+
+    return host.__function_inst_map__[name]
+
+def get_func_schema(name: str) -> dict:
+    for func in host.__callable_functions__:
+        if func['name'] == name:
+            return func
+    raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
+
+def execute_function(name: str, kwargs: dict) -> any:
+    """执行函数调用"""
+
+    logging.debug("executing function: name='{}', kwargs={}".format(name, kwargs))
+
+    func = get_func(name)
+    return func(**kwargs)

pkg/openai/keymgr.py

@@ -5,18 +5,25 @@ import logging
 import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models
 
+
 class KeysManager:
     api_key = {}
+    """所有api-key"""
 
-    # api-key的使用量
-    # 其中键为api-key的md5值，值为使用量
     using_key = ""
+    """当前使用的api-key"""
 
     alerted = []
+    """已提示过超额的key
+    
+    记录在此以避免重复提示
+    """
 
-    # 在此list中的都是经超额报错标记过的api-key
-    # 记录的是key值，仅在运行时有效
     exceeded = []
+    """已超额的key
+    
+    供自动切换功能识别
+    """
 
     def get_using_key(self):
         return self.using_key
@@ -25,8 +32,6 @@ class KeysManager:
         return hashlib.md5(self.using_key.encode('utf-8')).hexdigest()
 
     def __init__(self, api_key):
-        # if hasattr(config, 'api_key_usage_threshold'):
-        #     self.api_key_usage_threshold = config.api_key_usage_threshold
 
         if type(api_key) is dict:
             self.api_key = api_key
@@ -42,10 +47,31 @@ class KeysManager:
 
         self.auto_switch()
 
-    # 根据tested自动切换到可用的api-key
-    # 返回是否切换成功, 切换后的api-key的别名
-    def auto_switch(self) -> (bool, str):
+    def auto_switch(self) -> tuple[bool, str]:
+        """尝试切换api-key
+
+        Returns:
+            是否切换成功, 切换后的api-key的别名
+        """
+
+        index = 0
+
         for key_name in self.api_key:
+            if self.api_key[key_name] == self.using_key:
+                break
+            
+            index += 1
+
+        # 从当前key开始向后轮询
+        start_index = index
+        index += 1
+        if index >= len(self.api_key):
+            index = 0
+
+        while index != start_index:
+            
+            key_name = list(self.api_key.keys())[index]
+
             if self.api_key[key_name] not in self.exceeded:
                 self.using_key = self.api_key[key_name]
 
@@ -60,20 +86,20 @@ class KeysManager:
 
                 return True, key_name
 
-        self.using_key = list(self.api_key.values())[0]
-        logging.info("使用api-key:" + list(self.api_key.keys())[0])
+            index += 1
+            if index >= len(self.api_key):
+                index = 0
 
-        return False, ""
+        self.using_key = list(self.api_key.values())[start_index]
+        logging.debug("使用api-key:" + list(self.api_key.keys())[start_index])
+
+        return False, list(self.api_key.keys())[start_index]
 
     def add(self, key_name, key):
         self.api_key[key_name] = key
 
-    # 设置当前使用的api-key使用量超限
-    # 这是在尝试调用api时发生超限异常时调用的
     def set_current_exceeded(self):
-        # md5 = hashlib.md5(self.using_key.encode('utf-8')).hexdigest()
-        # self.usage[md5] = self.api_key_usage_threshold
-        # self.fee[md5] = self.api_key_fee_threshold
+        """设置当前使用的api-key使用量超限"""
         self.exceeded.append(self.using_key)
 
     def get_key_name(self, api_key):
@@ -81,4 +107,4 @@ class KeysManager:
         for key_name in self.api_key:
             if self.api_key[key_name] == api_key:
                 return key_name
-        return ""
+        return ""

pkg/openai/manager.py

@@ -5,11 +5,16 @@ import openai
 import pkg.openai.keymgr
 import pkg.utils.context
 import pkg.audit.gatherer
-from pkg.openai.modelmgr import ModelRequest, create_openai_model_request
+from pkg.openai.modelmgr import select_request_cls
+
+from pkg.openai.api.model import RequestBase
+
 
-# 为其他模块提供与OpenAI交互的接口
 class OpenAIInteract:
-    api_params = {}
+    """OpenAI 接口封装
+
+    将文字接口和图片接口封装供调用方使用
+    """
 
     key_mgr: pkg.openai.keymgr.KeysManager = None
 
@@ -20,48 +25,53 @@ class OpenAIInteract:
     }
 
     def __init__(self, api_key: str):
-        # self.api_key = api_key
 
         self.key_mgr = pkg.openai.keymgr.KeysManager(api_key)
         self.audit_mgr = pkg.audit.gatherer.DataGatherer()
 
-        logging.info("文字总使用量：%d", self.audit_mgr.get_total_text_length())
+        # logging.info("文字总使用量：%d", self.audit_mgr.get_total_text_length())
 
         openai.api_key = self.key_mgr.get_using_key()
 
         pkg.utils.context.set_openai_manager(self)
 
-    # 请求OpenAI Completion
-    def request_completion(self, prompts):
+    def request_completion(self, messages: list):
+        """请求补全接口回复=
+        """
+        # 选择接口请求类
         config = pkg.utils.context.get_config()
 
-        # 根据模型选择使用的接口
-        ai: ModelRequest = create_openai_model_request(
-            config.completion_api_params['model'], 
-            'user', 
-            config.openai_config["http_proxy"] if "http_proxy" in config.openai_config else None
-        )
-        ai.request(
-            prompts,
-            **config.completion_api_params
-        )
-        response = ai.get_response()
+        request: RequestBase
 
-        logging.debug("OpenAI response: %s", response)
+        model: str = config.completion_api_params['model']
 
-        if 'model' in config.completion_api_params:
-            self.audit_mgr.report_text_model_usage(config.completion_api_params['model'],
-                                                   ai.get_total_tokens())
-        elif 'engine' in config.completion_api_params:
-            self.audit_mgr.report_text_model_usage(config.completion_api_params['engine'],
-                                                   response['usage']['total_tokens'])
+        cp_parmas = config.completion_api_params.copy()
+        del cp_parmas['model']
 
-        return ai.get_message()
+        request = select_request_cls(model, messages, cp_parmas)
 
-    def request_image(self, prompt):
+        # 请求接口
+        for resp in request:
 
+            if resp['usage']['total_tokens'] > 0:
+                self.audit_mgr.report_text_model_usage(
+                    model,
+                    resp['usage']['total_tokens']
+                )
+
+            yield resp
+
+    def request_image(self, prompt) -> dict:
+        """请求图片接口回复
+
+        Parameters:
+            prompt (str): 提示语
+
+        Returns:
+            dict: 响应
+        """
         config = pkg.utils.context.get_config()
-        params = config.image_api_params if hasattr(config, "image_api_params") else self.default_image_api_params
+        params = config.image_api_params
 
         response = openai.Image.create(
             prompt=prompt,

pkg/openai/modelmgr.py

@@ -1,5 +1,17 @@
-# 提供与模型交互的抽象接口
+"""OpenAI 接口底层封装
+
+目前使用的对话接口有：
+ChatCompletion - gpt-3.5-turbo 等模型
+Completion - text-davinci-003 等模型
+此模块封装此两个接口的请求实现，为上层提供统一的调用方式
+"""
 import openai, logging, threading, asyncio
+import openai.error as aiE
+import tiktoken
+
+from pkg.openai.api.model import RequestBase
+from pkg.openai.api.completion import CompletionRequest
+from pkg.openai.api.chat_completion import ChatCompletionRequest
 
 COMPLETION_MODELS = {
     'text-davinci-003',
@@ -13,7 +25,14 @@ COMPLETION_MODELS = {
 
 CHAT_COMPLETION_MODELS = {
     'gpt-3.5-turbo',
-    'gpt-3.5-turbo-0301',
+    'gpt-3.5-turbo-16k',
+    'gpt-3.5-turbo-0613',
+    'gpt-3.5-turbo-16k-0613',
+    # 'gpt-3.5-turbo-0301',
+    'gpt-4',
+    'gpt-4-0613',
+    'gpt-4-32k',
+    'gpt-4-32k-0613'
 }
 
 EDIT_MODELS = {
@@ -25,128 +44,77 @@ IMAGE_MODELS = {
 }
 
 
-class ModelRequest():
-    """GPT父类"""
-    can_chat = False
-    runtime:threading.Thread = None
-    ret = ""
-    proxy:str = None
-
-    def __init__(self, model_name, user_name, request_fun, http_proxy:str = None):
-        self.model_name = model_name
-        self.user_name = user_name
-        self.request_fun = request_fun
-        if http_proxy != None:
-            self.proxy = http_proxy
-            openai.proxy = self.proxy
-
-    async def __a_request__(self, **kwargs):
-        self.ret = await self.request_fun(**kwargs)
-
-    def request(self, **kwargs):
-        if self.proxy != None: #异步请求
-            loop = asyncio.new_event_loop()
-            self.runtime = threading.Thread(
-                target=loop.run_until_complete,
-                args=(self.__a_request__(**kwargs),)
-            )
-            self.runtime.start()
-        else: #同步请求
-            self.ret = self.request_fun(**kwargs)
-
-    def __msg_handle__(self, msg):
-        """将prompt dict转换成接口需要的格式"""
-        return msg
-    
-    def ret_handle(self):
-        '''
-        API消息返回处理函数
-        若重写该方法，应检查异步线程状态，或在需要检查处super该方法
-        '''
-        if self.runtime != None and isinstance(self.runtime, threading.Thread):
-            self.runtime.join()
-        return
-
-    def get_total_tokens(self):
-        try:
-            return self.ret['usage']['total_tokens']
-        except Exception:
-            return 0
-
-    def get_message(self):
-        return self.message
-
-    def get_response(self):
-        return self.ret
-
-class ChatCompletionModel(ModelRequest):
-    """ChatCompletion类模型"""
-    Chat_role = ['system', 'user', 'assistant']
-    def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
-        if http_proxy == None:
-            request_fun = openai.ChatCompletion.create
-        else:
-            request_fun = openai.ChatCompletion.acreate
-        self.can_chat = True
-        super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
-
-    def request(self, prompts, **kwargs):
-        prompts = self.__msg_handle__(prompts)
-        kwargs['messages'] = prompts
-        super().request(**kwargs)
-        self.ret_handle()
-
-    def __msg_handle__(self, msgs):
-        temp_msgs = []
-        # 把msgs拷贝进temp_msgs
-        for msg in msgs:
-            temp_msgs.append(msg.copy())
-        return temp_msgs
-
-    def get_message(self):
-        return self.ret["choices"][0]["message"]['content'] #需要时直接加载加快请求速度，降低内存消耗
-
-
-class CompletionModel(ModelRequest):
-    """Completion类模型"""
-    def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
-        if http_proxy == None:
-            request_fun = openai.Completion.create
-        else:
-            request_fun = openai.Completion.acreate
-        super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
-
-    def request(self, prompts, **kwargs):
-        prompts = self.__msg_handle__(prompts)
-        kwargs['prompt'] = prompts
-        super().request(**kwargs)
-        self.ret_handle()
-
-    def __msg_handle__(self, msgs):
-        prompt = ''
-        for msg in msgs:
-            prompt = prompt + "{}: {}\n".format(msg['role'], msg['content'])
-        # for msg in msgs:
-        #     if msg['role'] == 'assistant':
-        #         prompt = prompt + "{}\n".format(msg['content'])
-        #     else:
-        #         prompt = prompt + "{}:{}\n".format(msg['role'] , msg['content'])
-        prompt = prompt + "assistant: "
-        return prompt
-
-    def get_message(self):
-        return self.ret["choices"][0]["text"]
-
-
-def create_openai_model_request(model_name: str, user_name: str = 'user', http_proxy:str = None) -> ModelRequest:
-    """使用给定的模型名称创建模型请求对象"""
+def select_request_cls(model_name: str, messages: list, args: dict) -> RequestBase:
     if model_name in CHAT_COMPLETION_MODELS:
-        model = ChatCompletionModel(model_name, user_name, http_proxy)
+        return ChatCompletionRequest(model_name, messages, **args)
     elif model_name in COMPLETION_MODELS:
-        model = CompletionModel(model_name, user_name, http_proxy)
-    else :
-        log = "找不到模型[{}]，请检查配置文件".format(model_name)
-        logging.error(log)
-        raise IndexError(log)
-    logging.debug("使用接口[{}]创建模型请求[{}]".format(model.__class__.__name__, model_name))
-    return model
+        return CompletionRequest(model_name, messages, **args)
+    raise ValueError("不支持模型[{}]，请检查配置文件".format(model_name))
+
+
+def count_chat_completion_tokens(messages: list, model: str) -> int:
+    """Return the number of tokens used by a list of messages."""
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+    if model in {
+        "gpt-3.5-turbo-0613",
+        "gpt-3.5-turbo-16k-0613",
+        "gpt-4-0314",
+        "gpt-4-32k-0314",
+        "gpt-4-0613",
+        "gpt-4-32k-0613",
+        }:
+        tokens_per_message = 3
+        tokens_per_name = 1
+    elif model == "gpt-3.5-turbo-0301":
+        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
+        tokens_per_name = -1  # if there's a name, the role is omitted
+    elif "gpt-3.5-turbo" in model:
+        # print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
+        return count_chat_completion_tokens(messages, model="gpt-3.5-turbo-0613")
+    elif "gpt-4" in model:
+        # print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
+        return count_chat_completion_tokens(messages, model="gpt-4-0613")
+    else:
+        raise NotImplementedError(
+            f"""count_chat_completion_tokens() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
+        )
+    num_tokens = 0
+    for message in messages:
+        num_tokens += tokens_per_message
+        for key, value in message.items():
+            num_tokens += len(encoding.encode(value))
+            if key == "name":
+                num_tokens += tokens_per_name
+    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
+    return num_tokens
+
+
+def count_completion_tokens(messages: list, model: str) -> int:
+
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+
+    text = ""
+
+    for message in messages:
+        text += message['role'] + message['content'] + "\n"
+
+    text += "assistant: "
+
+    return len(encoding.encode(text))
+
+
+def count_tokens(messages: list, model: str):
+
+    if model in CHAT_COMPLETION_MODELS:
+        return count_chat_completion_tokens(messages, model)
+    elif model in COMPLETION_MODELS:
+        return count_completion_tokens(messages, model)
+    raise ValueError("不支持模型[{}]，请检查配置文件".format(model))

pkg/openai/pricing.bak.py

@@ -1,28 +0,0 @@
-# 计费模块
-# 已弃用 https://github.com/RockChinQ/QChatGPT/issues/81
-
-import logging
-
-pricing = {
-    "base": {  # 文字模型单位是1000字符
-        "text-davinci-003": 0.02,
-    },
-    "image": {
-        "256x256": 0.016,
-        "512x512": 0.018,
-        "1024x1024": 0.02,
-    }
-}
-
-
-def language_base_price(model, text):
-    salt_rate = 0.93
-    length = ((len(text.encode('utf-8')) - len(text)) / 2 + len(text)) * salt_rate
-    logging.debug("text length: %d" % length)
-
-    return pricing["base"][model] * length / 1000
-
-
-def image_price(size):
-    logging.debug("image size: %s" % size)
-    return pricing["image"][size]

pkg/openai/session.py

@@ -1,3 +1,8 @@
+"""主线使用的会话管理模块
+
+每个人、每个群单独一个session，session内部保留了对话的上下文，
+"""
+
 import logging
 import threading
 import time
@@ -11,6 +16,8 @@ import pkg.utils.context
 import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models
 
+from pkg.openai.modelmgr import count_tokens
+
 # 运行时保存的所有session
 sessions = {}
 
@@ -19,6 +26,7 @@ class SessionOfflineStatus:
     ON_GOING = 'on_going'
     EXPLICITLY_CLOSED = 'explicitly_closed'
 
+
 # 重置session.prompt
 def reset_session_prompt(session_name, prompt):
     # 备份原始数据
@@ -34,7 +42,7 @@ def reset_session_prompt(session_name, prompt):
     prompt = [
         {
             'role': 'system',
-            'content': config.default_prompt['default']
+            'content': config.default_prompt['default'] if type(config.default_prompt) == dict else config.default_prompt
         }
     ]
     # 警告
@@ -43,11 +51,14 @@ def reset_session_prompt(session_name, prompt):
 用户[{}]的数据已被重置，有可能是因为数据版本过旧或存储错误
 原始数据将备份在：
 {}""".format(session_name, bak_path)
-    )
+    )  # 为保证多行文本格式正确故无缩进
     return prompt
 
+
 # 从数据加载session
 def load_sessions():
+    """从数据库加载sessions"""
+
     global sessions
 
     db_inst = pkg.utils.context.get_database_manager()
@@ -55,7 +66,7 @@ def load_sessions():
     session_data = db_inst.load_valid_sessions()
 
     for session_name in session_data:
-        logging.info('加载session: {}'.format(session_name))
+        logging.debug('加载session: {}'.format(session_name))
 
         temp_session = Session(session_name)
         temp_session.name = session_name
@@ -63,15 +74,18 @@ def load_sessions():
         temp_session.last_interact_timestamp = session_data[session_name]['last_interact_timestamp']
         try:
             temp_session.prompt = json.loads(session_data[session_name]['prompt'])
+            temp_session.token_counts = json.loads(session_data[session_name]['token_counts'])
         except Exception:
             temp_session.prompt = reset_session_prompt(session_name, session_data[session_name]['prompt'])
             temp_session.persistence()
+        temp_session.default_prompt = json.loads(session_data[session_name]['default_prompt']) if \
+            session_data[session_name]['default_prompt'] else []
 
         sessions[session_name] = temp_session
 
 
 # 获取指定名称的session，如果不存在则创建一个新的
-def get_session(session_name: str):
+def get_session(session_name: str) -> 'Session':
     global sessions
     if session_name not in sessions:
         sessions[session_name] = Session(session_name)
@@ -93,10 +107,16 @@ class Session:
     name = ''
 
     prompt = []
+    """使用list来保存会话中的回合"""
+
+    default_prompt = []
+    """本session的默认prompt"""
 
     create_timestamp = 0
+    """会话创建时间"""
 
     last_interact_timestamp = 0
+    """上次交互(产生回复)时间"""
 
     just_switched_to_exist_session = False
 
@@ -116,34 +136,27 @@ class Session:
             logging.debug('{},lock release successfully,{}'.format(self.name, self.response_lock))
 
     # 从配置文件获取会话预设信息
-    def get_default_prompt(self, use_default: str=None):
-        config = pkg.utils.context.get_config()
-
+    def get_default_prompt(self, use_default: str = None):
         import pkg.openai.dprompt as dprompt
 
         if use_default is None:
-            current_default_prompt = dprompt.get_prompt(dprompt.get_current())
-        else:
-            current_default_prompt = dprompt.get_prompt(use_default)
+            use_default = dprompt.mode_inst().get_using_name()
 
-        return [
-            {
-                'role': 'user',
-                'content': current_default_prompt
-            },{
-                'role': 'assistant',
-                'content': 'ok'
-            }
-        ]
+        current_default_prompt, _ = dprompt.mode_inst().get_prompt(use_default)
+        return current_default_prompt
 
     def __init__(self, name: str):
         self.name = name
         self.create_timestamp = int(time.time())
         self.last_interact_timestamp = int(time.time())
+        self.prompt = []
+        self.token_counts = []
         self.schedule()
 
         self.response_lock = threading.Lock()
-        self.prompt = self.get_default_prompt()
+
+        self.default_prompt = self.get_default_prompt()
+        logging.debug("prompt is: {}".format(self.default_prompt))
 
     # 设定检查session最后一次对话是否超过过期时间的计时器
     def schedule(self):
@@ -181,89 +194,223 @@ class Session:
 
     # 请求回复
     # 这个函数是阻塞的
-    def append(self, text: str) -> str:
+    def query(self, text: str=None) -> tuple[str, str, list[str]]:
+        """向session中添加一条消息，返回接口回复
+        
+        Args:
+            text (str): 用户消息
+
+        Returns:
+            tuple[str, str]: (接口回复, finish_reason, 已调用的函数列表)
+        """
+
         self.last_interact_timestamp = int(time.time())
 
         # 触发插件事件
-        if self.prompt == self.get_default_prompt():
+        if not self.prompt:
             args = {
                 'session_name': self.name,
                 'session': self,
-                'default_prompt': self.prompt,
+                'default_prompt': self.default_prompt,
             }
 
             event = pkg.plugin.host.emit(plugin_models.SessionFirstMessageReceived, **args)
             if event.is_prevented_default():
-                return None
+                return None, None, None
 
         config = pkg.utils.context.get_config()
-        max_length = config.prompt_submit_length if hasattr(config, "prompt_submit_length") else 1024
+        max_length = config.prompt_submit_length
+
+        local_default_prompt = self.default_prompt.copy()
+        local_prompt = self.prompt.copy()
+
+        # 触发PromptPreProcessing事件
+        args = {
+            'session_name': self.name,
+            'default_prompt': self.default_prompt,
+            'prompt': self.prompt,
+            'text_message': text,
+        }
+
+        event = pkg.plugin.host.emit(plugin_models.PromptPreProcessing, **args)
+        
+        if event.get_return_value('default_prompt') is not None:
+            local_default_prompt = event.get_return_value('default_prompt')
+        
+        if event.get_return_value('prompt') is not None:
+            local_prompt = event.get_return_value('prompt')
+
+        if event.get_return_value('text_message') is not None:
+            text = event.get_return_value('text_message')
+
+        prompts, _ = self.cut_out(text, max_length, local_default_prompt, local_prompt)
+
+        res_text = ""
+
+        pending_msgs = []
+
+        total_tokens = 0
+
+        finish_reason: str = ""
+
+        funcs = []
+
+        trace_func_calls = config.trace_function_calls
+        botmgr = pkg.utils.context.get_qqbot_manager()
+
+        session_name_spt: list[str] = self.name.split("_")
+
+        pending_res_text = ""
+
+        # TODO 对不起，我知道这样非常非常屎山，但我之后会重构的
+        for resp in pkg.utils.context.get_openai_manager().request_completion(prompts):
+
+            if pending_res_text != "":
+                botmgr.adapter.send_message(
+                    session_name_spt[0],
+                    session_name_spt[1],
+                    pending_res_text
+                )
+                pending_res_text = ""
+
+            finish_reason = resp['choices'][0]['finish_reason']
+
+            if resp['choices'][0]['message']['role'] == "assistant" and resp['choices'][0]['message']['content'] != None:  # 包含纯文本响应
+
+                if not trace_func_calls:
+                    res_text += resp['choices'][0]['message']['content'] + "\n"
+                else:
+                    res_text = resp['choices'][0]['message']['content']
+                    pending_res_text = resp['choices'][0]['message']['content']
+
+                total_tokens += resp['usage']['total_tokens']
+
+                msg = {
+                    "role": "assistant",
+                    "content": resp['choices'][0]['message']['content']
+                }
+
+                if 'function_call' in resp['choices'][0]['message']:
+                    msg['function_call'] = json.dumps(resp['choices'][0]['message']['function_call'])
+
+                pending_msgs.append(msg)
+
+            if resp['choices'][0]['message']['type'] == 'function_call':
+                # self.prompt.append(
+                #     {
+                #         "role": "assistant",
+                #         "content": "function call: "+json.dumps(resp['choices'][0]['message']['function_call'])
+                #     }
+                # )
+                if trace_func_calls:
+                    botmgr.adapter.send_message(
+                        session_name_spt[0],
+                        session_name_spt[1],
+                        "调用函数 "+resp['choices'][0]['message']['function_call']['name'] + "..."
+                    )
+
+                total_tokens += resp['usage']['total_tokens']
+            elif resp['choices'][0]['message']['type'] == 'function_return':
+                # self.prompt.append(
+                #     {
+                #         "role": "function",
+                #         "name": resp['choices'][0]['message']['function_name'],
+                #         "content": json.dumps(resp['choices'][0]['message']['content'])
+                #     }
+                # )
+
+                # total_tokens += resp['usage']['total_tokens']
+                funcs.append(
+                    resp['choices'][0]['message']['function_name']
+                )
+                pass
+
 
         # 向API请求补全
-        message = pkg.utils.context.get_openai_manager().request_completion(
-            self.cut_out(text, max_length),
-        )
+        # message, total_token = pkg.utils.context.get_openai_manager().request_completion(
+        #     prompts,
+        # )
 
         # 成功获取，处理回复
-        res_test = message
-        res_ans = res_test
-
-        # 去除开头可能的提示
-        res_ans_spt = res_test.split("\n\n")
-        if len(res_ans_spt) > 1:
-            del (res_ans_spt[0])
-            res_ans = '\n\n'.join(res_ans_spt)
+        # res_test = message
+        res_ans = res_text.strip()
 
         # 将此次对话的双方内容加入到prompt中
-        self.prompt.append({'role':'user', 'content':text})
-        self.prompt.append({'role':'assistant', 'content':res_ans})
+        # self.prompt.append({'role': 'user', 'content': text})
+        # self.prompt.append({'role': 'assistant', 'content': res_ans})
+        if text:
+            self.prompt.append({'role': 'user', 'content': text})
+        # 添加pending_msgs
+        self.prompt += pending_msgs
+
+        # 向token_counts中添加本回合的token数量
+        # self.token_counts.append(total_tokens-total_token_before_query)
+        # logging.debug("本回合使用token: {}, session counts: {}".format(total_tokens-total_token_before_query, self.token_counts))
 
         if self.just_switched_to_exist_session:
             self.just_switched_to_exist_session = False
             self.set_ongoing()
 
-        return res_ans if res_ans[0]!='\n' else res_ans[1:]
+        return res_ans if res_ans[0] != '\n' else res_ans[1:], finish_reason, funcs
 
     # 删除上一回合并返回上一回合的问题
     def undo(self) -> str:
         self.last_interact_timestamp = int(time.time())
 
-        # 删除上一回合
-        if self.prompt[-1]['role'] != 'user':
-            res = self.prompt[-1]['content']
-            self.prompt.remove(self.prompt[-2])
-        else:
-            res = self.prompt[-2]['content']
-        self.prompt.remove(self.prompt[-1])
+        # 删除最后两个消息
+        if len(self.prompt) < 2:
+            raise Exception('之前无对话，无法撤销')
+
+        question = self.prompt[-2]['content']
+        self.prompt = self.prompt[:-2]
+        self.token_counts = self.token_counts[:-1]
 
         # 返回上一回合的问题
-        return res
+        return question
 
     # 构建对话体
-    def cut_out(self, msg: str, max_tokens: int) -> list:
-        """将现有prompt进行切割处理，使得新的prompt长度不超过max_tokens"""
-        # 如果用户消息长度超过max_tokens，直接返回
-        
-        temp_prompt = [
+    def cut_out(self, msg: str, max_tokens: int, default_prompt: list, prompt: list) -> tuple[list, list]:
+        """将现有prompt进行切割处理，使得新的prompt长度不超过max_tokens
+
+        :return: (新的prompt, 新的token_counts)
+        """
+
+        # 最终由三个部分组成
+        # - default_prompt         情景预设固定值
+        # - changable_prompts      可变部分, 此会话中的历史对话回合
+        # - current_question       当前问题
+
+        # 包装目前的对话回合内容
+        changable_prompts = []
+
+        use_model = pkg.utils.context.get_config().completion_api_params['model']
+
+        ptr = len(prompt) - 1
+
+        # 直接从后向前扫描拼接，不管是否是整回合
+        while ptr >= 0:
+            if count_tokens(prompt[ptr:ptr+1]+changable_prompts, use_model) > max_tokens:
+                break
+
+            changable_prompts.insert(0, prompt[ptr])
+
+            ptr -= 1
+
+        # 将default_prompt和changable_prompts合并
+        result_prompt = default_prompt + changable_prompts
+
+        # 添加当前问题
+        if msg:
+            result_prompt.append(
                 {
                     'role': 'user',
                     'content': msg
                 }
-            ]
+            )
 
-        token_count = len(msg)
-        # 倒序遍历prompt
-        for i in range(len(self.prompt) - 1, -1, -1):
-            if token_count >= max_tokens:
-                break
+        logging.debug("cut_out: {}".format(json.dumps(result_prompt, ensure_ascii=False, indent=4)))
 
-            # 将prompt加到temp_prompt头部
-            temp_prompt.insert(0, self.prompt[i])
-            token_count += len(self.prompt[i]['content'])
-
-        logging.debug('cut_out: {}'.format(str(temp_prompt)))
-
-        return temp_prompt
+        return result_prompt, count_tokens(changable_prompts, use_model)
 
     # 持久化session
     def persistence(self):
@@ -278,11 +425,11 @@ class Session:
         subject_number = int(name_spt[1])
 
         db_inst.persistence_session(subject_type, subject_number, self.create_timestamp, self.last_interact_timestamp,
-                                    json.dumps(self.prompt))
+                                    json.dumps(self.prompt), json.dumps(self.default_prompt), json.dumps(self.token_counts))
 
     # 重置session
-    def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None):
-        if self.prompt[-1]['role'] != "system":
+    def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None, persist: bool = False):
+        if self.prompt:
             self.persistence()
             if explicit:
                 # 触发插件事件
@@ -298,7 +445,11 @@ class Session:
 
             if expired:
                 pkg.utils.context.get_database_manager().set_session_expired(self.name, self.create_timestamp)
-        self.prompt = self.get_default_prompt(use_prompt)
+
+        if not persist:  # 不要求保持default prompt
+            self.default_prompt = self.get_default_prompt(use_prompt)
+        self.prompt = []
+        self.token_counts = []
         self.create_timestamp = int(time.time())
         self.last_interact_timestamp = int(time.time())
         self.just_switched_to_exist_session = False
@@ -324,9 +475,11 @@ class Session:
             self.last_interact_timestamp = last_one['last_interact_timestamp']
             try:
                 self.prompt = json.loads(last_one['prompt'])
+                self.token_counts = json.loads(last_one['token_counts'])
             except json.decoder.JSONDecodeError:
                 self.prompt = reset_session_prompt(self.name, last_one['prompt'])
                 self.persistence()
+            self.default_prompt = json.loads(last_one['default_prompt']) if last_one['default_prompt'] else []
 
             self.just_switched_to_exist_session = True
             return self
@@ -343,9 +496,11 @@ class Session:
             self.last_interact_timestamp = next_one['last_interact_timestamp']
             try:
                 self.prompt = json.loads(next_one['prompt'])
+                self.token_counts = json.loads(next_one['token_counts'])
             except json.decoder.JSONDecodeError:
                 self.prompt = reset_session_prompt(self.name, next_one['prompt'])
                 self.persistence()
+            self.default_prompt = json.loads(next_one['default_prompt']) if next_one['default_prompt'] else []
 
             self.just_switched_to_exist_session = True
             return self
@@ -353,5 +508,11 @@ class Session:
     def list_history(self, capacity: int = 10, page: int = 0):
         return pkg.utils.context.get_database_manager().list_history(self.name, capacity, page)
 
+    def delete_history(self, index: int) -> bool:
+        return pkg.utils.context.get_database_manager().delete_history(self.name, index)
+
+    def delete_all_history(self) -> bool:
+        return pkg.utils.context.get_database_manager().delete_all_history(self.name)
+
     def draw_image(self, prompt: str):
         return pkg.utils.context.get_openai_manager().request_image(prompt)

pkg/plugin/__init__.py

@@ -0,0 +1,4 @@
+"""插件支持包
+
+包含插件基类、插件宿主以及部分API接口
+"""

pkg/plugin/host.py

@@ -5,17 +5,21 @@ import importlib
 import os
 import pkgutil
 import sys
+import shutil
 import traceback
 
+import pkg.utils.updater as updater
 import pkg.utils.context as context
 import pkg.plugin.switch as switch
 import pkg.plugin.settings as settings
+import pkg.qqbot.adapter as msadapter
 
 from mirai import Mirai
 
+from CallingGPT.session.session import Session
+
 __plugins__ = {}
-"""
-插件列表
+"""插件列表
 
 示例:
 {
@@ -34,14 +38,24 @@ __plugins__ = {}
         },
         "instance": None
     }
-}"""
+}
+"""
 
 __plugins_order__ = []
 """插件顺序"""
 
+__enable_content_functions__ = True
+"""是否启用内容函数"""
+
+__callable_functions__ = []
+"""供GPT调用的函数结构"""
+
+__function_inst_map__: dict[str, callable] = {}
+"""函数名:实例 映射"""
+
 
 def generate_plugin_order():
-    """ 根据__plugin__生成插件初始顺序，无视是否启用 """
+    """根据__plugin__生成插件初始顺序，无视是否启用"""
     global __plugins_order__
     __plugins_order__ = []
     for plugin_name in __plugins__:
@@ -49,13 +63,13 @@ def generate_plugin_order():
 
 
 def iter_plugins():
-    """ 按照顺序迭代插件 """
+    """按照顺序迭代插件"""
     for plugin_name in __plugins_order__:
         yield __plugins__[plugin_name]
 
 
 def iter_plugins_name():
-    """ 迭代插件名 """
+    """迭代插件名"""
     for plugin_name in __plugins_order__:
         yield plugin_name
 
@@ -77,15 +91,15 @@ def walk_plugin_path(module, prefix='', path_prefix=''):
                 __current_module_path__ = "plugins/"+path_prefix + item.name + '.py'
 
                 importlib.import_module(module.__name__ + '.' + item.name)
-                logging.info('加载模块: plugins/{} 成功'.format(path_prefix + item.name + '.py'))
+                logging.debug('加载模块: plugins/{} 成功'.format(path_prefix + item.name + '.py'))
             except:
                 logging.error('加载模块: plugins/{} 失败: {}'.format(path_prefix + item.name + '.py', sys.exc_info()))
                 traceback.print_exc()
 
 
 def load_plugins():
-    """ 加载插件 """
-    logging.info("加载插件")
+    """加载插件"""
+    logging.debug("加载插件")
     PluginHost()
     walk_plugin_path(__import__('plugins'))
 
@@ -99,24 +113,35 @@ def load_plugins():
     # 加载插件顺序
     settings.load_settings()
 
+    # 输出已注册的内容函数列表
+    logging.debug("registered content functions: {}".format(__callable_functions__))
+    logging.debug("function instance map: {}".format(__function_inst_map__))
+
 
 def initialize_plugins():
-    """ 初始化插件 """
+    """初始化插件"""
     logging.info("初始化插件")
     import pkg.plugin.models as models
+
+    successfully_initialized_plugins = []
+
     for plugin in iter_plugins():
-        if not plugin['enabled']:
-            continue
+        # if not plugin['enabled']:
+        #     continue
         try:
             models.__current_registering_plugin__ = plugin['name']
             plugin['instance'] = plugin["class"](plugin_host=context.get_plugin_host())
-            logging.info("插件 {} 已初始化".format(plugin['name']))
+            # logging.info("插件 {} 已初始化".format(plugin['name']))
+            successfully_initialized_plugins.append(plugin['name'])
         except:
             logging.error("插件{}初始化时发生错误: {}".format(plugin['name'], sys.exc_info()))
+    
+    logging.info("以下插件已初始化: {}".format(", ".join(successfully_initialized_plugins)))
 
 
 def unload_plugins():
-    """ 卸载插件 """
+    """卸载插件"""
+    # 不再显式卸载插件，因为当程序结束时，插件的析构函数会被系统执行
     # for plugin in __plugins__.values():
     #     if plugin['enabled'] and plugin['instance'] is not None:
     #         if not hasattr(plugin['instance'], '__del__'):
@@ -131,7 +156,7 @@ def unload_plugins():
 
 
 def install_plugin(repo_url: str):
-    """ 安装插件，从git储存库获取并解决依赖 """
+    """安装插件，从git储存库获取并解决依赖"""
     try:
         import pkg.utils.pkgmgr
         pkg.utils.pkgmgr.ensure_dulwich()
@@ -154,22 +179,75 @@ def install_plugin(repo_url: str):
         import pkg.utils.pkgmgr
         pkg.utils.pkgmgr.install_requirements("plugins/"+repo_url.split(".git")[0].split("/")[-1]+"/requirements.txt")
 
-        import main
-        main.reset_logging()
+        import pkg.utils.log as log
+        log.reset_logging()
 
 
+def uninstall_plugin(plugin_name: str) -> str:
+    """卸载插件"""
+    if plugin_name not in __plugins__:
+        raise Exception("插件不存在")
+    
+    # 获取文件夹路径
+    plugin_path = __plugins__[plugin_name]['path'].replace("\\", "/")
+
+    # 剪切路径为plugins/插件名
+    plugin_path = plugin_path.split("plugins/")[1].split("/")[0]
+
+    # 删除文件夹
+    shutil.rmtree("plugins/"+plugin_path)
+    return "plugins/"+plugin_path
+
+
+def update_plugin(plugin_name: str):
+    """更新插件"""
+    # 检查是否有远程地址记录
+    target_plugin_dir = "plugins/" + __plugins__[plugin_name]['path'].replace("\\", "/").split("plugins/")[1].split("/")[0]
+
+    remote_url = updater.get_remote_url(target_plugin_dir)
+    if remote_url == "https://github.com/RockChinQ/QChatGPT" or remote_url == "https://gitee.com/RockChin/QChatGPT" \
+        or remote_url == "" or remote_url is None or remote_url == "http://github.com/RockChinQ/QChatGPT" or remote_url == "http://gitee.com/RockChin/QChatGPT":
+        raise Exception("插件没有远程地址记录，无法更新")
+    
+    # 把远程clone到temp/plugins/update/插件名
+    logging.info("克隆插件储存库: {}".format(remote_url))
+
+    from dulwich import porcelain
+    clone_target_dir = "temp/plugins/update/"+target_plugin_dir.split("/")[-1]+"/"
+
+    if os.path.exists(clone_target_dir):
+        shutil.rmtree(clone_target_dir)
+
+    if not os.path.exists(clone_target_dir):
+        os.makedirs(clone_target_dir)
+    repo = porcelain.clone(remote_url, clone_target_dir, checkout=True)
+
+    # 检查此目录是否包含requirements.txt
+    if os.path.exists(clone_target_dir+"requirements.txt"):
+        logging.info("检测到requirements.txt，正在安装依赖")
+        import pkg.utils.pkgmgr
+        pkg.utils.pkgmgr.install_requirements(clone_target_dir+"requirements.txt")
+
+        import pkg.utils.log as log
+        log.reset_logging()
+
+    # 将temp/plugins/update/插件名 覆盖到 plugins/插件名
+    shutil.rmtree(target_plugin_dir)
+
+    shutil.copytree(clone_target_dir, target_plugin_dir)
+
 class EventContext:
-    """ 事件上下文 """
+    """事件上下文"""
     eid = 0
     """事件编号"""
 
     name = ""
 
     __prevent_default__ = False
-    """ 是否阻止默认行为 """
+    """是否阻止默认行为"""
 
     __prevent_postorder__ = False
-    """ 是否阻止后续插件的执行 """
+    """是否阻止后续插件的执行"""
 
     __return_value__ = {}
     """ 返回值 
@@ -194,7 +272,7 @@ class EventContext:
             self.__return_value__[key] = []
         self.__return_value__[key].append(ret)
 
-    def get_return(self, key: str):
+    def get_return(self, key: str) -> list:
         """获取key的所有返回值"""
         if key in self.__return_value__:
             return self.__return_value__[key]
@@ -232,7 +310,7 @@ class EventContext:
 
 
 def emit(event_name: str, **kwargs) -> EventContext:
-    """ 触发事件 """
+    """触发事件"""
     import pkg.utils.context as context
     if context.get_plugin_host() is None:
         return None
@@ -243,7 +321,9 @@ class PluginHost:
     """插件宿主"""
 
     def __init__(self):
+        """初始化插件宿主"""
         context.set_plugin_host(self)
+        self.calling_gpt_session = Session([])
 
     def get_runtime_context(self) -> context:
         """获取运行时上下文（pkg.utils.context模块的对象）
@@ -258,20 +338,24 @@ class PluginHost:
         """获取机器人对象"""
         return context.get_qqbot_manager().bot
 
+    def get_bot_adapter(self) -> msadapter.MessageSourceAdapter:
+        """获取消息源适配器"""
+        return context.get_qqbot_manager().adapter
+
     def send_person_message(self, person, message):
         """发送私聊消息"""
-        asyncio.run(self.get_bot().send_friend_message(person, message))
+        self.get_bot_adapter().send_message("person", person, message)
 
     def send_group_message(self, group, message):
         """发送群消息"""
-        asyncio.run(self.get_bot().send_group_message(group, message))
+        self.get_bot_adapter().send_message("group", group, message)
 
     def notify_admin(self, message):
         """通知管理员"""
         context.get_qqbot_manager().notify_admin(message)
 
     def emit(self, event_name: str, **kwargs) -> EventContext:
-        """ 触发事件 """
+        """触发事件"""
         import json
 
         event_context = EventContext(event_name)
@@ -309,7 +393,7 @@ class PluginHost:
                         logging.debug("插件 {} 已要求阻止事件 {} 的默认行为".format(plugin['name'], event_name))
 
                 except Exception as e:
-                    logging.error("插件{}触发事件{}时发生错误".format(plugin['name'], event_name))
+                    logging.error("插件{}响应事件{}时发生错误".format(plugin['name'], event_name))
                     logging.error(traceback.format_exc())
 
             # print("done:{}".format(plugin['name']))
@@ -321,3 +405,6 @@ class PluginHost:
                                                                 event_context.__return_value__))
 
         return event_context
+
+if __name__ == "__main__":
+    pass

pkg/plugin/models.py

@@ -88,6 +88,8 @@ NormalMessageResponded = "normal_message_responded"
         session: pkg.openai.session.Session 会话对象
         prefix: str 回复文字消息的前缀
         response_text: str 响应文本
+        finish_reason: str 响应结束原因
+        funcs_called: list[str] 此次响应中调用的函数列表
     
     returns (optional):
         prefix: str 修改后的回复文字消息的前缀
@@ -132,19 +134,66 @@ KeySwitched = "key_switched"
         key_list: list[str] api-key列表
 """
 
+PromptPreProcessing = "prompt_pre_processing"
+"""每回合调用接口前对prompt进行预处理时触发，此事件不支持阻止默认行为
+    kwargs:
+        session_name: str 会话名称(<launcher_type>_<launcher_id>)
+        default_prompt: list 此session使用的情景预设内容
+        prompt: list 此session现有的prompt内容
+        text_message: str 用户发送的消息文本
+    
+    returns (optional):
+        default_prompt: list 修改后的情景预设内容
+        prompt: list 修改后的prompt内容
+        text_message: str 修改后的消息文本
+"""
 
-def on(event: str):
+
+def on(*args, **kwargs):
     """注册事件监听器
-    :param
-        event: str 事件名称
     """
-    return Plugin.on(event)
+    return Plugin.on(*args, **kwargs)
+
+def func(*args, **kwargs):
+    """注册内容函数，声明此函数为一个内容函数，在对话中将发送此函数给GPT以供其调用
+    此函数可以具有任意的参数，但必须按照[此文档](https://github.com/RockChinQ/CallingGPT/wiki/1.-Function-Format#function-format)
+    所述的格式编写函数的docstring。
+    此功能仅支持在使用gpt-3.5或gpt-4系列模型时使用。
+    """
+    return Plugin.func(*args, **kwargs)
 
 
 __current_registering_plugin__ = ""
 
 
+def require_ver(ge: str, le: str="v999.9.9") -> bool:
+    """插件版本要求装饰器
+
+    Args:
+        ge (str): 最低版本要求
+        le (str, optional): 最高版本要求
+
+    Returns:
+        bool: 是否满足要求, False时为无法获取版本号，True时为满足要求，报错为不满足要求
+    """
+    qchatgpt_version = ""
+    
+    from pkg.utils.updater import get_current_tag, compare_version_str
+
+    try:
+        qchatgpt_version = get_current_tag()  # 从updater模块获取版本号
+    except:
+        return False
+
+    if compare_version_str(qchatgpt_version, ge) < 0 or \
+        (compare_version_str(qchatgpt_version, le) > 0):
+        raise Exception("QChatGPT 版本不满足要求，某些功能（可能是由插件提供的）无法正常使用。（要求版本：{}-{}，但当前版本：{}）".format(ge, le, qchatgpt_version))
+
+    return True
+
+
 class Plugin:
+    """插件基类"""
 
     host: host.PluginHost
     """插件宿主，提供插件的一些基础功能"""
@@ -175,6 +224,34 @@ class Plugin:
 
         return wrapper
 
+    @classmethod
+    def func(cls, name: str=None):
+        """内容函数装饰器
+        """
+        global __current_registering_plugin__
+        from CallingGPT.entities.namespace import get_func_schema
+
+        def wrapper(func):
+
+            function_schema = get_func_schema(func)
+            function_schema['name'] = __current_registering_plugin__ + '-' + (func.__name__ if name is None else name)
+
+            function_schema['enabled'] = True
+
+            host.__function_inst_map__[function_schema['name']] = function_schema['function']
+
+            del function_schema['function']
+
+            # logging.debug("registering content function: p='{}', f='{}', s={}".format(__current_registering_plugin__, func, function_schema))
+
+            host.__callable_functions__.append(
+                function_schema
+            )
+
+            return func
+
+        return wrapper
+
 
 def register(name: str, description: str, version: str, author: str):
     """注册插件, 此函数作为装饰器使用

pkg/plugin/settings.py

@@ -8,7 +8,10 @@ import logging
 def wrapper_dict_from_runtime_context() -> dict:
     """从变量中包装settings.json的数据字典"""
     settings = {
-        "order": []
+        "order": [],
+        "functions": {
+            "enabled": host.__enable_content_functions__
+        }
     }
 
     for plugin_name in host.__plugins_order__:
@@ -22,6 +25,11 @@ def apply_settings(settings: dict):
     if "order" in settings:
         host.__plugins_order__ = settings["order"]
 
+    if "functions" in settings:
+        if "enabled" in settings["functions"]:
+            host.__enable_content_functions__ = settings["functions"]["enabled"]
+            # logging.debug("set content function enabled: {}".format(host.__enable_content_functions__))
+
 
 def dump_settings():
     """保存settings.json数据"""
@@ -78,6 +86,17 @@ def load_settings():
             settings["order"].append(plugin_name)
             settings_modified = True
 
+    if "functions" not in settings:
+        settings["functions"] = {
+            "enabled": host.__enable_content_functions__
+        }
+        settings_modified = True
+    elif "enabled" not in settings["functions"]:
+        settings["functions"]["enabled"] = host.__enable_content_functions__
+        settings_modified = True
+
+    logging.info("已全局{}内容函数。".format("启用" if settings["functions"]["enabled"] else "禁用"))
+
     apply_settings(settings)
 
     if settings_modified:

pkg/plugin/switch.py

@@ -7,7 +7,7 @@ import pkg.plugin.host as host
 
 
 def wrapper_dict_from_plugin_list() -> dict:
-    """ 将插件列表转换为开关json """
+    """将插件列表转换为开关json"""
     switch = {}
 
     for plugin_name in host.__plugins__:
@@ -28,9 +28,14 @@ def apply_switch(switch: dict):
     for plugin_name in switch:
         host.__plugins__[plugin_name]["enabled"] = switch[plugin_name]["enabled"]
 
+        # 查找此插件的所有内容函数
+        for func in host.__callable_functions__:
+            if func['name'].startswith(plugin_name + '-'):
+                func['enabled'] = switch[plugin_name]["enabled"]
+
 
 def dump_switch():
-    """ 保存开关数据 """
+    """保存开关数据"""
     logging.debug("保存开关数据")
     # 将开关数据写入plugins/switch.json
 
@@ -41,7 +46,7 @@ def dump_switch():
 
 
 def load_switch():
-    """ 加载开关数据 """
+    """加载开关数据"""
     logging.debug("加载开关数据")
     # 读取plugins/switch.json
 

pkg/qqbot/adapter.py

@@ -0,0 +1,136 @@
+# MessageSource的适配器
+import typing
+
+import mirai
+
+
+class MessageSourceAdapter:
+    def __init__(self, config: dict):
+        pass
+
+    def send_message(
+        self,
+        target_type: str,
+        target_id: str,
+        message: mirai.MessageChain
+    ):
+        """发送消息
+        
+        Args:
+            target_type (str): 目标类型，`person`或`group`
+            target_id (str): 目标ID
+            message (mirai.MessageChain): YiriMirai库的消息链
+        """
+        raise NotImplementedError
+
+    def reply_message(
+        self,
+        message_source: mirai.MessageEvent,
+        message: mirai.MessageChain,
+        quote_origin: bool = False
+    ):
+        """回复消息
+
+        Args:
+            message_source (mirai.MessageEvent): YiriMirai消息源事件
+            message (mirai.MessageChain): YiriMirai库的消息链
+            quote_origin (bool, optional): 是否引用原消息. Defaults to False.
+        """
+        raise NotImplementedError
+
+    def is_muted(self, group_id: int) -> bool:
+        """获取账号是否在指定群被禁言"""
+        raise NotImplementedError
+
+    def register_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        """注册事件监听器
+        
+        Args:
+            event_type (typing.Type[mirai.Event]): YiriMirai事件类型
+            callback (typing.Callable[[mirai.Event], None]): 回调函数，接收一个参数，为YiriMirai事件
+        """
+        raise NotImplementedError
+    
+    def unregister_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        """注销事件监听器
+        
+        Args:
+            event_type (typing.Type[mirai.Event]): YiriMirai事件类型
+            callback (typing.Callable[[mirai.Event], None]): 回调函数，接收一个参数，为YiriMirai事件
+        """
+        raise NotImplementedError
+
+    def run_sync(self):
+        """以阻塞的方式运行适配器"""
+        raise NotImplementedError
+
+    def kill(self) -> bool:
+        """关闭适配器
+        
+        Returns:
+            bool: 是否成功关闭，热重载时若此函数返回False则不会重载MessageSource底层
+        """
+        raise NotImplementedError
+
+
+class MessageConverter:
+    """消息链转换器基类"""
+    @staticmethod
+    def yiri2target(message_chain: mirai.MessageChain):
+        """将YiriMirai消息链转换为目标消息链
+
+        Args:
+            message_chain (mirai.MessageChain): YiriMirai消息链
+
+        Returns:
+            typing.Any: 目标消息链
+        """
+        raise NotImplementedError
+
+    @staticmethod
+    def target2yiri(message_chain: typing.Any) -> mirai.MessageChain:
+        """将目标消息链转换为YiriMirai消息链
+
+        Args:
+            message_chain (typing.Any): 目标消息链
+
+        Returns:
+            mirai.MessageChain: YiriMirai消息链
+        """
+        raise NotImplementedError
+
+
+class EventConverter:
+    """事件转换器基类"""
+
+    @staticmethod
+    def yiri2target(event: typing.Type[mirai.Event]):
+        """将YiriMirai事件转换为目标事件
+
+        Args:
+            event (typing.Type[mirai.Event]): YiriMirai事件
+
+        Returns:
+            typing.Any: 目标事件
+        """
+        raise NotImplementedError
+
+    @staticmethod
+    def target2yiri(event: typing.Any) -> mirai.Event:
+        """将目标事件的调用参数转换为YiriMirai的事件参数对象
+
+        Args:
+            event (typing.Any): 目标事件
+
+        Returns:
+            typing.Type[mirai.Event]: YiriMirai事件
+        """
+        raise NotImplementedError

pkg/qqbot/banlist.py

@@ -1,30 +1,34 @@
 import pkg.utils.context
 
 
-def is_banned(launcher_type: str, launcher_id: int) -> bool:
+def is_banned(launcher_type: str, launcher_id: int, sender_id: int) -> bool:
     if not pkg.utils.context.get_qqbot_manager().enable_banlist:
         return False
     
     result = False
     
     if launcher_type == 'group':
-        for group_rule in pkg.utils.context.get_qqbot_manager().ban_group:
-            if type(group_rule) == int:
-                if group_rule == launcher_id: # 此群群号被禁用
-                    result = True
-            elif type(group_rule) == str:
-                if group_rule.startswith('!'):
-                    # 截取!后面的字符串作为表达式，判断是否匹配
-                    reg_str = group_rule[1:]
-                    import re
-                    if re.match(reg_str, str(launcher_id)): # 被豁免，最高级别
-                        result = False
-                        break
-                else:
-                    # 判断是否匹配regexp
-                    import re
-                    if re.match(group_rule, str(launcher_id)): # 此群群号被禁用
+        # 检查是否显式声明发起人QQ要被person忽略
+        if sender_id in pkg.utils.context.get_qqbot_manager().ban_person:
+            result = True
+        else:
+            for group_rule in pkg.utils.context.get_qqbot_manager().ban_group:
+                if type(group_rule) == int:
+                    if group_rule == launcher_id:  # 此群群号被禁用
                         result = True
+                elif type(group_rule) == str:
+                    if group_rule.startswith('!'):
+                        # 截取!后面的字符串作为表达式，判断是否匹配
+                        reg_str = group_rule[1:]
+                        import re
+                        if re.match(reg_str, str(launcher_id)):  # 被豁免，最高级别
+                            result = False
+                            break
+                    else:
+                        # 判断是否匹配regexp
+                        import re
+                        if re.match(group_rule, str(launcher_id)):  # 此群群号被禁用
+                            result = True
                     
     else:
         # ban_person, 与群规则相同

pkg/qqbot/blob.py

@@ -0,0 +1,97 @@
+# 长消息处理相关
+import os
+import time
+import base64
+
+import config
+from mirai.models.message import MessageComponent, MessageChain, Image
+from mirai.models.message import ForwardMessageNode
+from mirai.models.base import MiraiBaseModel
+from typing import List
+import pkg.utils.context as context
+import pkg.utils.text2img as text2img
+
+
+class ForwardMessageDiaplay(MiraiBaseModel):
+    title: str = "群聊的聊天记录"
+    brief: str = "[聊天记录]"
+    source: str = "聊天记录"
+    preview: List[str] = []
+    summary: str = "查看x条转发消息"
+
+
+class Forward(MessageComponent):
+    """合并转发。"""
+    type: str = "Forward"
+    """消息组件类型。"""
+    display: ForwardMessageDiaplay
+    """显示信息"""
+    node_list: List[ForwardMessageNode]
+    """转发消息节点列表。"""
+    def __init__(self, *args, **kwargs):
+        if len(args) == 1:
+            self.node_list = args[0]
+            super().__init__(**kwargs)
+        super().__init__(*args, **kwargs)
+
+    def __str__(self):
+        return '[聊天记录]'
+
+
+def text_to_image(text: str) -> MessageComponent:
+    """将文本转换成图片"""
+    # 检查temp文件夹是否存在
+    if not os.path.exists('temp'):
+        os.mkdir('temp')
+    img_path = text2img.text_to_image(text_str=text, save_as='temp/{}.png'.format(int(time.time())))
+    
+    compressed_path, size = text2img.compress_image(img_path, outfile="temp/{}_compressed.png".format(int(time.time())))
+    # 读取图片，转换成base64
+    with open(compressed_path, 'rb') as f:
+        img = f.read()
+
+    b64 = base64.b64encode(img)
+
+    # 删除图片
+    os.remove(img_path)
+
+    # 判断compressed_path是否存在
+    if os.path.exists(compressed_path):
+        os.remove(compressed_path)
+    # 返回图片
+    return Image(base64=b64.decode('utf-8'))
+
+
+def check_text(text: str) -> list:
+    """检查文本是否为长消息，并转换成该使用的消息链组件"""
+    if len(text) > config.blob_message_threshold:
+
+        # logging.info("长消息: {}".format(text))
+        if config.blob_message_strategy == 'image':
+            # 转换成图片
+            return [text_to_image(text)]
+        elif config.blob_message_strategy == 'forward':
+
+            # 包装转发消息
+            display = ForwardMessageDiaplay(
+                title='群聊的聊天记录',
+                brief='[聊天记录]',
+                source='聊天记录',
+                preview=["bot: "+text],
+                summary="查看1条转发消息"
+            )
+
+            node = ForwardMessageNode(
+                sender_id=config.mirai_http_api_config['qq'],
+                sender_name='bot',
+                message_chain=MessageChain([text])
+            )
+
+            forward = Forward(
+                display=display,
+                node_list=[node]
+            )
+
+            return [forward]
+    else:
+        return [text]

pkg/qqbot/cmds/aamgr.py

@@ -0,0 +1,337 @@
+import importlib
+import inspect
+import logging
+import copy
+import pkgutil
+import traceback
+import types
+import json
+
+
+__command_list__ = {}
+
+import tips as tips_custom
+
+"""命令树
+
+结构：
+{
+    'cmd1': {
+        'description': 'cmd1 description',
+        'usage': 'cmd1 usage',
+        'aliases': ['cmd1 alias1', 'cmd1 alias2'],
+        'privilege': 0,
+        'parent': None,
+        'cls': <class 'pkg.qqbot.cmds.cmd1.CommandCmd1'>,
+        'sub': [
+            'cmd1-1'
+        ]
+    },
+    'cmd1.cmd1-1: {
+        'description': 'cmd1-1 description',
+        'usage': 'cmd1-1 usage',
+        'aliases': ['cmd1-1 alias1', 'cmd1-1 alias2'],
+        'privilege': 0,
+        'parent': 'cmd1',
+        'cls': <class 'pkg.qqbot.cmds.cmd1.CommandCmd1_1'>,
+        'sub': []
+    },
+    'cmd2': {
+        'description': 'cmd2 description',
+        'usage': 'cmd2 usage',
+        'aliases': ['cmd2 alias1', 'cmd2 alias2'],
+        'privilege': 0,
+        'parent': None,
+        'cls': <class 'pkg.qqbot.cmds.cmd2.CommandCmd2'>,
+        'sub': [
+            'cmd2-1'
+        ]
+    },
+    'cmd2.cmd2-1': {
+        'description': 'cmd2-1 description',
+        'usage': 'cmd2-1 usage',
+        'aliases': ['cmd2-1 alias1', 'cmd2-1 alias2'],
+        'privilege': 0,
+        'parent': 'cmd2',
+        'cls': <class 'pkg.qqbot.cmds.cmd2.CommandCmd2_1'>,
+        'sub': [
+            'cmd2-1-1'
+        ]
+    },
+    'cmd2.cmd2-1.cmd2-1-1': {
+        'description': 'cmd2-1-1 description',
+        'usage': 'cmd2-1-1 usage',
+        'aliases': ['cmd2-1-1 alias1', 'cmd2-1-1 alias2'],
+        'privilege': 0,
+        'parent': 'cmd2.cmd2-1',
+        'cls': <class 'pkg.qqbot.cmds.cmd2.CommandCmd2_1_1'>,
+        'sub': []
+    },
+}
+"""
+
+__tree_index__: dict[str, list] = {}
+"""命令树索引
+
+结构：
+{
+    'pkg.qqbot.cmds.cmd1.CommandCmd1': 'cmd1',  # 顶级指令
+    'pkg.qqbot.cmds.cmd1.CommandCmd1_1': 'cmd1.cmd1-1',  # 类名: 节点路径
+    'pkg.qqbot.cmds.cmd2.CommandCmd2': 'cmd2',
+    'pkg.qqbot.cmds.cmd2.CommandCmd2_1': 'cmd2.cmd2-1',
+    'pkg.qqbot.cmds.cmd2.CommandCmd2_1_1': 'cmd2.cmd2-1.cmd2-1-1',
+}
+"""
+
+
+class Context:
+    """命令执行上下文"""
+    command: str
+    """顶级指令文本"""
+
+    crt_command: str
+    """当前子指令文本"""
+
+    params: list
+    """完整参数列表"""
+
+    crt_params: list
+    """当前子指令参数列表"""
+
+    session_name: str
+    """会话名"""
+
+    text_message: str
+    """指令完整文本"""
+
+    launcher_type: str
+    """指令发起者类型"""
+
+    launcher_id: int
+    """指令发起者ID"""
+
+    sender_id: int
+    """指令发送者ID"""
+
+    is_admin: bool
+    """[过时]指令发送者是否为管理员"""
+
+    privilege: int
+    """指令发送者权限等级"""
+
+    def __init__(self, **kwargs):
+        self.__dict__.update(kwargs)
+
+
+class AbstractCommandNode:
+    """指令抽象类"""
+
+    parent: type
+    """父指令类"""
+
+    name: str
+    """指令名"""
+
+    description: str
+    """指令描述"""
+
+    usage: str
+    """指令用法"""
+
+    aliases: list[str]
+    """指令别名"""
+
+    privilege: int
+    """指令权限等级, 权限大于等于此值的用户才能执行指令"""
+
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        """指令处理函数
+        
+        :param ctx: 指令执行上下文
+
+        :return: (是否执行, 回复列表(若执行))
+
+        若未执行，将自动以下一个参数查找并执行子指令
+        """
+        raise NotImplementedError
+    
+    @classmethod
+    def help(cls) -> str:
+        """获取指令帮助信息"""
+        return '指令: {}\n描述: {}\n用法: \n{}\n别名: {}\n权限: {}'.format(
+            cls.name,
+            cls.description,
+            cls.usage,
+            ', '.join(cls.aliases),
+            cls.privilege
+        )
+
+    @staticmethod
+    def register(
+        parent: type = None,
+        name: str = None,
+        description: str = None,
+        usage: str = None,
+        aliases: list[str] = None,
+        privilege: int = 0
+    ):
+        """注册指令
+        
+        :param cls: 指令类
+        :param name: 指令名
+        :param parent: 父指令类
+        """
+        global __command_list__, __tree_index__
+        
+        def wrapper(cls):
+            cls.name = name
+            cls.parent = parent
+            cls.description = description
+            cls.usage = usage
+            cls.aliases = aliases
+            cls.privilege = privilege
+
+            logging.debug("cls: {}, name: {}, parent: {}".format(cls, name, parent))
+
+            if parent is None:
+                # 顶级指令注册
+                __command_list__[name] = {
+                    'description': cls.description,
+                    'usage': cls.usage,
+                    'aliases': cls.aliases,
+                    'privilege': cls.privilege,
+                    'parent': None,
+                    'cls': cls,
+                    'sub': []
+                }
+                # 更新索引
+                __tree_index__[cls.__module__ + '.' + cls.__name__] = name
+            else:
+                # 获取父节点名称
+                path = __tree_index__[parent.__module__ + '.' + parent.__name__]
+                
+                parent_node = __command_list__[path]
+                # 链接父子指令
+                __command_list__[path]['sub'].append(name)
+                # 注册子指令
+                __command_list__[path + '.' + name] = {
+                    'description': cls.description,
+                    'usage': cls.usage,
+                    'aliases': cls.aliases,
+                    'privilege': cls.privilege,
+                    'parent': path,
+                    'cls': cls,
+                    'sub': []
+                }
+                # 更新索引
+                __tree_index__[cls.__module__ + '.' + cls.__name__] = path + '.' + name
+
+            return cls
+        
+        return wrapper
+
+
+class CommandPrivilegeError(Exception):
+    """指令权限不足或不存在异常"""
+    pass
+
+
+# 传入Context对象，广搜命令树，返回执行结果
+# 若命令被处理，返回reply列表
+# 若命令未被处理，继续执行下一级指令
+# 若命令不存在，报异常
+def execute(context: Context) -> list:
+    """执行指令
+    
+    :param ctx: 指令执行上下文
+
+    :return: 回复列表
+    """
+    global __command_list__
+
+    # 拷贝ctx
+    ctx: Context = copy.deepcopy(context)
+
+    # 从树取出顶级指令
+    node = __command_list__
+    
+    path = ctx.command
+
+    while True:
+        try:
+            node = __command_list__[path]
+            logging.debug('执行指令: {}'.format(path))
+
+            # 检查权限
+            if ctx.privilege < node['privilege']:
+                raise CommandPrivilegeError(tips_custom.command_admin_message+"{}".format(path))
+            
+            # 执行
+            execed, reply = node['cls'].process(ctx)
+            if execed:
+                return reply
+            else:
+                # 删除crt_params第一个参数
+                ctx.crt_command = ctx.crt_params.pop(0)
+                # 下一个path
+                path = path + '.' + ctx.crt_command
+        except KeyError:
+            traceback.print_exc()
+            raise CommandPrivilegeError(tips_custom.command_err_message+"{}".format(path))
+
+
+def register_all():
+    """启动时调用此函数注册所有指令
+    
+    递归处理pkg.qqbot.cmds包下及其子包下所有模块的所有继承于AbstractCommand的类
+    """
+    # 模块：遍历其中的继承于AbstractCommand的类，进行注册
+    # 包：递归处理包下的模块
+    # 排除__开头的属性
+    global __command_list__, __tree_index__
+
+    import pkg.qqbot.cmds
+
+    def walk(module, prefix, path_prefix):
+        # 排除不处于pkg.qqbot.cmds中的包
+        if not module.__name__.startswith('pkg.qqbot.cmds'):
+            return
+        
+        logging.debug('walk: {}, path: {}'.format(module.__name__, module.__path__))
+        for item in pkgutil.iter_modules(module.__path__):
+            if item.name.startswith('__'):
+                continue
+
+            if item.ispkg:
+                walk(__import__(module.__name__ + '.' + item.name, fromlist=['']), prefix + item.name + '.', path_prefix + item.name + '/')
+            else:
+                m = __import__(module.__name__ + '.' + item.name, fromlist=[''])
+                # for name, cls in inspect.getmembers(m, inspect.isclass):
+                #     # 检查是否为指令类
+                #     if cls.__module__ == m.__name__ and issubclass(cls, AbstractCommandNode) and cls != AbstractCommandNode:
+                #         cls.register(cls, cls.name, cls.parent)
+
+    walk(pkg.qqbot.cmds, '', '')
+    logging.debug(__command_list__)
+
+
+def apply_privileges():
+    """读取cmdpriv.json并应用指令权限"""
+    # 读取内容
+    json_str = ""
+    with open('cmdpriv.json', 'r', encoding="utf-8") as f:
+        json_str = f.read()
+
+    data = json.loads(json_str)
+    for path, priv in data.items():
+        if path == 'comment':
+            continue
+        
+        if path not in __command_list__:
+            continue
+        
+        if __command_list__[path]['privilege'] != priv:
+            logging.debug('应用权限: {} -> {}(default: {})'.format(path, priv, __command_list__[path]['privilege']))
+
+        __command_list__[path]['privilege'] = priv

pkg/qqbot/cmds/funcs/draw.py

@@ -0,0 +1,36 @@
+from ..aamgr import AbstractCommandNode, Context
+import logging
+
+from mirai import Image
+import config
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="draw",
+    description="使用DALL·E生成图片",
+    usage="!draw <图片提示语>",
+    aliases=[],
+    privilege=1
+)
+class DrawCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+
+        reply = []
+        
+        if len(ctx.params) == 0:
+            reply = ["[bot]err: 未提供图片描述文字"]
+        else:
+            session = pkg.openai.session.get_session(ctx.session_name)
+
+            res = session.draw_image(" ".join(ctx.params))
+
+            logging.debug("draw_image result:{}".format(res))
+            reply = [Image(url=res['data'][0]['url'])]
+            if not (hasattr(config, 'include_image_description')
+                    and not config.include_image_description):
+                reply.append(" ".join(ctx.params))
+
+        return True, reply

pkg/qqbot/cmds/funcs/func.py

@@ -0,0 +1,33 @@
+from ..aamgr import AbstractCommandNode, Context
+import logging
+
+import json
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="func",
+    description="管理内容函数",
+    usage="!func",
+    aliases=[],
+    privilege=1
+)
+class FuncCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        from pkg.plugin.models import host
+
+        reply = []
+
+        reply_str = "当前已加载的内容函数：\n\n"
+
+        logging.debug("host.__callable_functions__: {}".format(json.dumps(host.__callable_functions__, indent=4)))
+
+        index = 1
+        for func in host.__callable_functions__:
+            reply_str += "{}. {}{}:\n{}\n\n".format(index, ("(已禁用) " if not func['enabled'] else ""), func['name'], func['description'])
+            index += 1
+            
+        reply = [reply_str]
+
+        return True, reply

pkg/qqbot/cmds/plugin/plugin.py

@@ -0,0 +1,202 @@
+from ..aamgr import AbstractCommandNode, Context
+
+import os
+
+import pkg.plugin.host as plugin_host
+import pkg.utils.updater as updater
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="plugin",
+    description="插件管理",
+    usage="!plugin\n!plugin get <插件仓库地址>\n!plugin update\n!plugin del <插件名>\n!plugin on <插件名>\n!plugin off <插件名>",
+    aliases=[],
+    privilege=1
+)
+class PluginCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        reply = []
+        plugin_list = plugin_host.__plugins__
+        if len(ctx.params) == 0:
+            # 列出所有插件
+            
+            reply_str = "[bot]所有插件({}):\n".format(len(plugin_host.__plugins__))
+            idx = 0
+            for key in plugin_host.iter_plugins_name():
+                plugin = plugin_list[key]
+                reply_str += "\n#{} {} {}\n{}\nv{}\n作者: {}\n"\
+                    .format((idx+1), plugin['name'],
+                            "[已禁用]" if not plugin['enabled'] else "",
+                            plugin['description'],
+                            plugin['version'], plugin['author'])
+
+                if updater.is_repo("/".join(plugin['path'].split('/')[:-1])):
+                    remote_url = updater.get_remote_url("/".join(plugin['path'].split('/')[:-1]))
+                    if remote_url != "https://github.com/RockChinQ/QChatGPT" and remote_url != "https://gitee.com/RockChin/QChatGPT":
+                        reply_str += "源码: "+remote_url+"\n"
+
+                idx += 1
+
+            reply = [reply_str]
+            return True, reply
+        elif ctx.params[0].startswith("http"):
+            reply = ["[bot]err: 此命令已弃用，请使用 !plugin get <插件仓库地址> 进行安装"]
+            return True, reply
+        else:
+            return False, []
+
+    
+@AbstractCommandNode.register(
+    parent=PluginCommand,
+    name="get",
+    description="安装插件",
+    usage="!plugin get <插件仓库地址>",
+    aliases=[],
+    privilege=2
+)
+class PluginGetCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import threading
+        import logging
+        import pkg.utils.context
+
+        if len(ctx.crt_params) == 0:
+            reply = ["[bot]err: 请提供插件仓库地址"]
+            return True, reply
+        
+        reply = []
+        def closure():
+            try:
+                plugin_host.install_plugin(ctx.crt_params[0])
+                pkg.utils.context.get_qqbot_manager().notify_admin("插件安装成功，请发送 !reload 指令重载插件")
+            except Exception as e:
+                logging.error("插件安装失败:{}".format(e))
+                pkg.utils.context.get_qqbot_manager().notify_admin("插件安装失败:{}".format(e))
+
+        threading.Thread(target=closure, args=()).start()
+        reply = ["[bot]正在安装插件..."]
+        return True, reply
+
+
+@AbstractCommandNode.register(
+    parent=PluginCommand,
+    name="update",
+    description="更新所有插件",
+    usage="!plugin update",
+    aliases=[],
+    privilege=2
+)
+class PluginUpdateCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import threading
+        import logging
+        plugin_list = plugin_host.__plugins__
+
+        reply = []
+
+        if len(ctx.crt_params) > 0:
+            def closure():
+                try:
+                    import pkg.utils.context
+                    
+                    updated = []
+
+                    if ctx.crt_params[0] == 'all':
+                        for key in plugin_list:
+                            plugin_host.update_plugin(key)
+                            updated.append(key)
+                    else:
+                        if ctx.crt_params[0] in plugin_list:
+                            plugin_host.update_plugin(ctx.crt_params[0])
+                            updated.append(ctx.crt_params[0])
+                        else:
+                            raise Exception("未找到插件: {}".format(ctx.crt_params[0]))
+
+                    pkg.utils.context.get_qqbot_manager().notify_admin("已更新插件: {}, 请发送 !reload 重载插件".format(", ".join(updated)))
+                except Exception as e:
+                    logging.error("插件更新失败:{}".format(e))
+                    pkg.utils.context.get_qqbot_manager().notify_admin("插件更新失败:{} 请尝试手动更新插件".format(e))
+
+            reply = ["[bot]正在更新插件，请勿重复发起..."]
+            threading.Thread(target=closure).start()
+        else:
+            reply = ["[bot]请指定要更新的插件, 或使用 !plugin update all 更新所有插件"]
+        return True, reply
+
+
+@AbstractCommandNode.register(
+    parent=PluginCommand,
+    name="del",
+    description="删除插件",
+    usage="!plugin del <插件名>",
+    aliases=[],
+    privilege=2
+)
+class PluginDelCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        plugin_list = plugin_host.__plugins__
+        reply = []
+
+        if len(ctx.crt_params) < 1:
+            reply = ["[bot]err: 未指定插件名"]
+        else:
+            plugin_name = ctx.crt_params[0]
+            if plugin_name in plugin_list:
+                unin_path = plugin_host.uninstall_plugin(plugin_name)
+                reply = ["[bot]已删除插件: {} ({}), 请发送 !reload 重载插件".format(plugin_name, unin_path)]
+            else:
+                reply = ["[bot]err:未找到插件: {}, 请使用!plugin指令查看插件列表".format(plugin_name)]
+        
+        return True, reply
+
+
+@AbstractCommandNode.register(
+    parent=PluginCommand,
+    name="on",
+    description="启用指定插件",
+    usage="!plugin on <插件名>",
+    aliases=[],
+    privilege=2
+)
+@AbstractCommandNode.register(
+    parent=PluginCommand,
+    name="off",
+    description="禁用指定插件",
+    usage="!plugin off <插件名>",
+    aliases=[],
+    privilege=2
+)
+class PluginOnOffCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.plugin.switch as plugin_switch
+
+        plugin_list = plugin_host.__plugins__
+        reply = []
+        
+        print(ctx.params)
+        new_status = ctx.params[0] == 'on'
+
+        if len(ctx.crt_params) < 1:
+            reply = ["[bot]err: 未指定插件名"]
+        else:
+            plugin_name = ctx.crt_params[0]
+            if plugin_name in plugin_list:
+                plugin_list[plugin_name]['enabled'] = new_status
+
+                for func in plugin_host.__callable_functions__:
+                    if func['name'].startswith(plugin_name+"-"):
+                        func['enabled'] = new_status
+
+                plugin_switch.dump_switch()
+                reply = ["[bot]已{}插件: {}".format("启用" if new_status else "禁用", plugin_name)]
+            else:
+                reply = ["[bot]err:未找到插件: {}, 请使用!plugin指令查看插件列表".format(plugin_name)]
+        
+        return True, reply
+

pkg/qqbot/cmds/session/default.py

@@ -0,0 +1,73 @@
+from ..aamgr import AbstractCommandNode, Context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="default",
+    description="操作情景预设",
+    usage="!default\n!default set [指定情景预设为默认]",
+    aliases=[],
+    privilege=1
+)
+class DefaultCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        params = ctx.params
+        reply = []
+        import config
+
+        if len(params) == 0:
+            # 输出目前所有情景预设
+            import pkg.openai.dprompt as dprompt
+            reply_str = "[bot]当前所有情景预设({}模式):\n\n".format(config.preset_mode)
+
+            prompts = dprompt.mode_inst().list()
+
+            for key in prompts:
+                pro = prompts[key]
+                reply_str += "名称: {}".format(key)
+
+                for r in pro:
+                    reply_str += "\n   - [{}]: {}".format(r['role'], r['content'])
+
+                reply_str += "\n\n"
+
+            reply_str += "\n当前默认情景预设:{}\n".format(dprompt.mode_inst().get_using_name())
+            reply_str += "请使用 !default set <情景预设名称> 来设置默认情景预设"
+            reply = [reply_str]
+        elif params[0] != "set":
+            reply = ["[bot]err: 已弃用，请使用!default set <情景预设名称> 来设置默认情景预设"]
+        else:
+            return False, []
+
+        return True, reply
+
+
+@AbstractCommandNode.register(
+    parent=DefaultCommand,
+    name="set",
+    description="设置默认情景预设",
+    usage="!default set <情景预设名称>",
+    aliases=[],
+    privilege=2
+)
+class DefaultSetCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        reply = []
+
+        if len(ctx.crt_params) == 0:
+            reply = ["[bot]err: 请指定情景预设名称"]
+        elif len(ctx.crt_params) > 0:
+            import pkg.openai.dprompt as dprompt
+            try:
+                full_name = dprompt.mode_inst().set_using_name(ctx.crt_params[0])
+                reply = ["[bot]已设置默认情景预设为:{}".format(full_name)]
+            except Exception as e:
+                reply = ["[bot]err: {}".format(e)]
+        else:
+            reply = ["[bot]err: 仅管理员可设置默认情景预设"]
+
+        return True, reply

pkg/qqbot/cmds/session/del.py

@@ -0,0 +1,52 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="del",
+    description="删除当前会话的历史记录",
+    usage="!del <序号>\n!del all",
+    aliases=[],
+    privilege=1
+)
+class DelCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        params = ctx.params
+        reply = []
+        if len(params) == 0:
+            reply = ["[bot]参数不足, 格式: !del <序号>\n可以通过!list查看序号"]
+        else:
+            if params[0] == 'all':
+                return False, []
+            elif params[0].isdigit():
+                if pkg.openai.session.get_session(session_name).delete_history(int(params[0])):
+                    reply = ["[bot]已删除历史会话 #{}".format(params[0])]
+                else:
+                    reply = ["[bot]没有历史会话 #{}".format(params[0])]
+            else:
+                reply = ["[bot]参数错误, 格式: !del <序号>\n可以通过!list查看序号"]
+
+        return True, reply
+
+
+@AbstractCommandNode.register(
+    parent=DelCommand,
+    name="all",
+    description="删除当前会话的全部历史记录",
+    usage="!del all",
+    aliases=[],
+    privilege=1
+)
+class DelAllCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        reply = []
+        pkg.openai.session.get_session(session_name).delete_all_history()
+        reply = ["[bot]已删除所有历史会话"]
+        return True, reply

pkg/qqbot/cmds/session/delhst.py

@@ -0,0 +1,50 @@
+from ..aamgr import AbstractCommandNode, Context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="delhst",
+    description="删除指定会话的所有历史记录",
+    usage="!delhst <会话名称>\n!delhst all",
+    aliases=[],
+    privilege=2
+)
+class DelHistoryCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        import pkg.utils.context
+        params = ctx.params
+        reply = []
+        if len(params) == 0:
+            reply = [
+            "[bot]err:请输入要删除的会话名: group_<群号> 或者 person_<QQ号>, 或使用 !delhst all 删除所有会话的历史记录"]
+        else:
+            if params[0] == 'all':
+                return False, []
+            else:
+                if pkg.utils.context.get_database_manager().delete_all_history(params[0]):
+                    reply = ["[bot]已删除会话 {} 的所有历史记录".format(params[0])]
+                else:
+                    reply = ["[bot]未找到会话 {} 的历史记录".format(params[0])]
+
+        return True, reply
+    
+
+@AbstractCommandNode.register(
+    parent=DelHistoryCommand,
+    name="all",
+    description="删除所有会话的全部历史记录",
+    usage="!delhst all",
+    aliases=[],
+    privilege=2
+)
+class DelAllHistoryCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.utils.context
+        reply = []
+        pkg.utils.context.get_database_manager().delete_all_session_history()
+        reply = ["[bot]已删除所有会话的历史记录"]
+        return True, reply
+    

pkg/qqbot/cmds/session/last.py

@@ -0,0 +1,28 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="last",
+    description="切换前一次对话",
+    usage="!last",
+    aliases=[],
+    privilege=1
+)
+class LastCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+
+        reply = []
+        result = pkg.openai.session.get_session(session_name).last_session()
+        if result is None:
+            reply = ["[bot]没有前一次的对话"]
+        else:
+            datetime_str = datetime.datetime.fromtimestamp(result.create_timestamp).strftime(
+                '%Y-%m-%d %H:%M:%S')
+            reply = ["[bot]已切换到前一次的对话：\n创建时间:{}\n".format(datetime_str)]
+
+        return True, reply

pkg/qqbot/cmds/session/list.py

@@ -0,0 +1,67 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+import json
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name='list',
+    description='列出当前会话的所有历史记录',
+    usage='!list\n!list [页数]',
+    aliases=[],
+    privilege=1
+)
+class ListCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        params = ctx.params
+        reply = []
+
+        pkg.openai.session.get_session(session_name).persistence()
+        page = 0
+
+        if len(params) > 0:
+            try:
+                page = int(params[0])
+            except ValueError:
+                pass
+
+        results = pkg.openai.session.get_session(session_name).list_history(page=page)
+        if len(results) == 0:
+            reply = ["[bot]第{}页没有历史会话".format(page)]
+        else:
+            reply_str = "[bot]历史会话 第{}页：\n".format(page)
+            current = -1
+            for i in range(len(results)):
+                # 时间(使用create_timestamp转换) 序号 部分内容
+                datetime_obj = datetime.datetime.fromtimestamp(results[i]['create_timestamp'])
+                msg = ""
+                try:
+                    msg = json.loads(results[i]['prompt'])
+                except json.decoder.JSONDecodeError:
+                    msg = pkg.openai.session.reset_session_prompt(session_name, results[i]['prompt'])
+                    # 持久化
+                    pkg.openai.session.get_session(session_name).persistence()
+                if len(msg) >= 2:
+                    reply_str += "#{} 创建:{} {}\n".format(i + page * 10,
+                                                        datetime_obj.strftime("%Y-%m-%d %H:%M:%S"),
+                                                        msg[0]['content'])
+                else:
+                    reply_str += "#{} 创建:{} {}\n".format(i + page * 10,
+                                                        datetime_obj.strftime("%Y-%m-%d %H:%M:%S"),
+                                                        "无内容")
+                if results[i]['create_timestamp'] == pkg.openai.session.get_session(
+                        session_name).create_timestamp:
+                    current = i + page * 10
+
+            reply_str += "\n以上信息倒序排列"
+            if current != -1:
+                reply_str += ",当前会话是 #{}\n".format(current)
+            else:
+                reply_str += ",当前处于全新会话或不在此页"
+
+        reply = [reply_str]
+
+        return True, reply

pkg/qqbot/cmds/session/next.py

@@ -0,0 +1,28 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="next",
+    description="切换后一次对话",
+    usage="!next",
+    aliases=[],
+    privilege=1
+)
+class NextCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        reply = []
+
+        result = pkg.openai.session.get_session(session_name).next_session()
+        if result is None:
+            reply = ["[bot]没有后一次的对话"]
+        else:
+            datetime_str = datetime.datetime.fromtimestamp(result.create_timestamp).strftime(
+                '%Y-%m-%d %H:%M:%S')
+            reply = ["[bot]已切换到后一次的对话：\n创建时间:{}\n".format(datetime_str)]
+
+        return True, reply

pkg/qqbot/cmds/session/prompt.py

@@ -0,0 +1,32 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="prompt",
+    description="获取当前会话的前文",
+    usage="!prompt",
+    aliases=[],
+    privilege=1
+)
+class PromptCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        session_name = ctx.session_name
+        params = ctx.params
+        reply = []
+
+        msgs = ""
+        session: list = pkg.openai.session.get_session(session_name).prompt
+        for msg in session:
+            if len(params) != 0 and params[0] in ['-all', '-a']:
+                msgs = msgs + "{}: {}\n\n".format(msg['role'], msg['content'])
+            elif len(msg['content']) > 30:
+                msgs = msgs + "[{}]: {}...\n\n".format(msg['role'], msg['content'][:30])
+            else:
+                msgs = msgs + "[{}]: {}\n\n".format(msg['role'], msg['content'])
+        reply = ["[bot]当前对话所有内容：\n{}".format(msgs)]
+
+        return True, reply

pkg/qqbot/cmds/session/resend.py

@@ -0,0 +1,30 @@
+from ..aamgr import AbstractCommandNode, Context
+import datetime
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="resend",
+    description="重新获取上一次问题的回复",
+    usage="!resend",
+    aliases=[],
+    privilege=1
+)
+class ResendCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        import config
+        session_name = ctx.session_name
+        reply = []
+
+        session = pkg.openai.session.get_session(session_name)
+        to_send = session.undo()
+
+        mgr = pkg.utils.context.get_qqbot_manager()
+
+        reply = pkg.qqbot.message.process_normal_message(to_send, mgr, config,
+                                                        ctx.launcher_type, ctx.launcher_id,
+                                                        ctx.sender_id)
+
+        return True, reply

pkg/qqbot/cmds/session/reset.py

@@ -0,0 +1,35 @@
+from ..aamgr import AbstractCommandNode, Context
+import tips as tips_custom
+
+import pkg.openai.session
+import pkg.utils.context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name='reset',
+    description='重置当前会话',
+    usage='!reset',
+    aliases=[],
+    privilege=1
+)
+class ResetCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        params = ctx.params
+        session_name = ctx.session_name
+        
+        reply = ""
+
+        if len(params) == 0:
+            pkg.openai.session.get_session(session_name).reset(explicit=True)
+            reply = [tips_custom.command_reset_message]
+        else:
+            try:
+                import pkg.openai.dprompt as dprompt
+                pkg.openai.session.get_session(session_name).reset(explicit=True, use_prompt=params[0])
+                reply = [tips_custom.command_reset_name_message+"{}".format(dprompt.mode_inst().get_full_name(params[0]))]
+            except Exception as e:
+                reply = ["[bot]会话重置失败：{}".format(e)]
+        
+        return True, reply

pkg/qqbot/cmds/system/cconfig.py

@@ -0,0 +1,100 @@
+from ..aamgr import AbstractCommandNode, Context
+import json
+
+
+def config_operation(cmd, params):
+    reply = []
+    import pkg.utils.context
+    config = pkg.utils.context.get_config()
+    reply_str = ""
+    if len(params) == 0:
+        reply = ["[bot]err:请输入!cmd cfg查看使用方法"]
+    else:
+        cfg_name = params[0]
+        if cfg_name == 'all':
+            reply_str = "[bot]所有配置项:\n\n"
+            for cfg in dir(config):
+                if not cfg.startswith('__') and not cfg == 'logging':
+                    # 根据配置项类型进行格式化，如果是字典则转换为json并格式化
+                    if isinstance(getattr(config, cfg), str):
+                        reply_str += "{}: \"{}\"\n".format(cfg, getattr(config, cfg))
+                    elif isinstance(getattr(config, cfg), dict):
+                        # 不进行unicode转义，并格式化
+                        reply_str += "{}: {}\n".format(cfg,
+                                                       json.dumps(getattr(config, cfg),
+                                                                  ensure_ascii=False, indent=4))
+                    else:
+                        reply_str += "{}: {}\n".format(cfg, getattr(config, cfg))
+            reply = [reply_str]
+        else:
+            cfg_entry_path = cfg_name.split('.')
+
+            try:
+                if len(params) == 1:
+                    cfg_entry = getattr(config, cfg_entry_path[0])
+                    if len(cfg_entry_path) > 1:
+                        for i in range(1, len(cfg_entry_path)):
+                            cfg_entry = cfg_entry[cfg_entry_path[i]]
+
+                    if isinstance(cfg_entry, str):
+                        reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, cfg_entry)
+                    elif isinstance(cfg_entry, dict):
+                        reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
+                                                                 json.dumps(cfg_entry,
+                                                                            ensure_ascii=False, indent=4))
+                    else:
+                        reply_str = "[bot]配置项{}: {}\n".format(cfg_name, cfg_entry)
+                    reply = [reply_str]
+                else:
+                    cfg_value = " ".join(params[1:])
+                    # 类型转换，如果是json则转换为字典
+                    # if cfg_value == 'true':
+                    #     cfg_value = True
+                    # elif cfg_value == 'false':
+                    #     cfg_value = False
+                    # elif cfg_value.isdigit():
+                    #     cfg_value = int(cfg_value)
+                    # elif cfg_value.startswith('{') and cfg_value.endswith('}'):
+                    #     cfg_value = json.loads(cfg_value)
+                    # else:
+                    #     try:
+                    #         cfg_value = float(cfg_value)
+                    #     except ValueError:
+                    #         pass
+                    cfg_value = eval(cfg_value)
+
+                    cfg_entry = getattr(config, cfg_entry_path[0])
+                    if len(cfg_entry_path) > 1:
+                        for i in range(1, len(cfg_entry_path) - 1):
+                            cfg_entry = cfg_entry[cfg_entry_path[i]]
+                        if isinstance(cfg_entry[cfg_entry_path[-1]], type(cfg_value)):
+                            cfg_entry[cfg_entry_path[-1]] = cfg_value
+                            reply = ["[bot]配置项{}修改成功".format(cfg_name)]
+                        else:
+                            reply = ["[bot]err:配置项{}类型不匹配".format(cfg_name)]
+                    else:
+                        setattr(config, cfg_entry_path[0], cfg_value)
+                        reply = ["[bot]配置项{}修改成功".format(cfg_name)]
+            except AttributeError:
+                reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+            except ValueError:
+                reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+        # else:
+        #     reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+
+    return reply
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="cfg",
+    description="配置项管理",
+    usage="!cfg <配置项> [配置值]\n!cfg all",
+    aliases=[],
+    privilege=2
+)
+class CfgCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        return True, config_operation(ctx.command, ctx.params)
+    

pkg/qqbot/cmds/system/cmd.py

@@ -0,0 +1,39 @@
+from ..aamgr import AbstractCommandNode, Context, __command_list__
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="cmd",
+    description="显示指令列表",
+    usage="!cmd\n!cmd <指令名称>",
+    aliases=[],
+    privilege=1
+)
+class CmdCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        command_list = __command_list__
+
+        reply = []
+
+        if len(ctx.params) == 0:
+            reply_str = "[bot]当前所有指令:\n\n"
+
+            # 遍历顶级指令
+            for key in command_list:
+                command = command_list[key]
+                if command['parent'] is None:
+                    reply_str += "!{} - {}\n".format(key, command['description'])
+
+            reply_str += "\n请使用 !cmd <指令名称> 来查看指令的详细信息"
+
+            reply = [reply_str]
+        else:
+            command_name = ctx.params[0]
+            if command_name in command_list:
+                reply = [command_list[command_name]['cls'].help()]
+            else:
+                reply = ["[bot]指令 {} 不存在".format(command_name)]
+
+        return True, reply
+    

pkg/qqbot/cmds/system/help.py

@@ -0,0 +1,24 @@
+from ..aamgr import AbstractCommandNode, Context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="help",
+    description="显示自定义的帮助信息",
+    usage="!help",
+    aliases=[],
+    privilege=1
+)
+class HelpCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import tips
+        reply = ["[bot] "+tips.help_message + "\n请输入 !cmd 查看指令列表"]
+
+        # 警告config.help_message过时
+        import config
+        if hasattr(config, "help_message"):
+            reply[0] += "\n\n警告：config.py中的help_message已过时，不再生效，请使用tips.py中的help_message替代"
+
+        return True, reply
+    

pkg/qqbot/cmds/system/reload.py

@@ -0,0 +1,23 @@
+from ..aamgr import AbstractCommandNode, Context
+import threading
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="reload",
+    description="执行热重载",
+    usage="!reload",
+    aliases=[],
+    privilege=2
+)
+class ReloadCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        reply = []
+
+        import pkg.utils.reloader
+        def reload_task():
+            pkg.utils.reloader.reload_all()
+
+        threading.Thread(target=reload_task, daemon=True).start()
+
+        return True, reply

pkg/qqbot/cmds/system/update.py

@@ -0,0 +1,38 @@
+from ..aamgr import AbstractCommandNode, Context
+import threading
+import traceback
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="update",
+    description="更新程序",
+    usage="!update",
+    aliases=[],
+    privilege=2
+)
+class UpdateCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        reply = []
+        import pkg.utils.updater
+        import pkg.utils.reloader
+        import pkg.utils.context
+
+        def update_task():
+            try:
+                if pkg.utils.updater.update_all():
+                    pkg.utils.reloader.reload_all(notify=False)
+                    pkg.utils.context.get_qqbot_manager().notify_admin("更新完成")
+                else:
+                    pkg.utils.context.get_qqbot_manager().notify_admin("无新版本")
+            except Exception as e0:
+                traceback.print_exc()
+                pkg.utils.context.get_qqbot_manager().notify_admin("更新失败:{}".format(e0))
+                return
+
+        threading.Thread(target=update_task, daemon=True).start()
+
+        reply = ["[bot]正在更新，请耐心等待，请勿重复发起更新..."]
+
+        return True, reply

pkg/qqbot/cmds/system/usage.py

@@ -0,0 +1,35 @@
+from ..aamgr import AbstractCommandNode, Context
+import logging
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="usage",
+    description="获取使用情况",
+    usage="!usage",
+    aliases=[],
+    privilege=1
+)
+class UsageCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import config
+        import pkg.utils.credit as credit
+        import pkg.utils.context
+
+        reply = []
+
+        reply_str = "[bot]各api-key使用情况:\n\n"
+
+        api_keys = pkg.utils.context.get_openai_manager().key_mgr.api_key
+        for key_name in api_keys:
+            text_length = pkg.utils.context.get_openai_manager().audit_mgr \
+                .get_text_length_of_key(api_keys[key_name])
+            image_count = pkg.utils.context.get_openai_manager().audit_mgr \
+                .get_image_count_of_key(api_keys[key_name])
+            reply_str += "{}:\n - 文本长度:{}\n - 图片数量:{}\n".format(key_name, int(text_length),
+                                                                        int(image_count))
+
+        reply = [reply_str]
+
+        return True, reply

pkg/qqbot/cmds/system/version.py

@@ -0,0 +1,27 @@
+from ..aamgr import AbstractCommandNode, Context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="version",
+    description="查看版本信息",
+    usage="!version",
+    aliases=[],
+    privilege=1
+)
+class VersionCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        reply = []
+        import pkg.utils.updater
+    
+        reply_str = "[bot]当前版本:\n{}\n".format(pkg.utils.updater.get_current_version_info())
+        try:
+            if pkg.utils.updater.is_new_version_available():
+                reply_str += "\n有新版本可用，请使用命令 !update 进行更新"
+        except:
+            pass
+
+        reply = [reply_str]
+
+        return True, reply

pkg/qqbot/command.py

@@ -4,6 +4,7 @@ import json
 import datetime
 import os
 import threading
+import traceback
 
 import pkg.openai.session
 import pkg.openai.manager
@@ -12,151 +13,12 @@ import pkg.utils.updater
 import pkg.utils.context
 import pkg.qqbot.message
 import pkg.utils.credit as credit
+# import pkg.qqbot.cmds.model as cmdmodel
+import pkg.qqbot.cmds.aamgr as cmdmgr
 
 from mirai import Image
 
 
-def config_operation(cmd, params):
-    reply = []
-    config = pkg.utils.context.get_config()
-    reply_str = ""
-    if len(params) == 0:
-        reply = ["[bot]err:请输入配置项"]
-    else:
-        cfg_name = params[0]
-        if cfg_name == 'all':
-            reply_str = "[bot]所有配置项:\n\n"
-            for cfg in dir(config):
-                if not cfg.startswith('__') and not cfg == 'logging':
-                    # 根据配置项类型进行格式化，如果是字典则转换为json并格式化
-                    if isinstance(getattr(config, cfg), str):
-                        reply_str += "{}: \"{}\"\n".format(cfg, getattr(config, cfg))
-                    elif isinstance(getattr(config, cfg), dict):
-                        # 不进行unicode转义，并格式化
-                        reply_str += "{}: {}\n".format(cfg,
-                                                       json.dumps(getattr(config, cfg),
-                                                                  ensure_ascii=False, indent=4))
-                    else:
-                        reply_str += "{}: {}\n".format(cfg, getattr(config, cfg))
-            reply = [reply_str]
-        elif cfg_name in dir(config):
-            if len(params) == 1:
-                # 按照配置项类型进行格式化
-                if isinstance(getattr(config, cfg_name), str):
-                    reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, getattr(config, cfg_name))
-                elif isinstance(getattr(config, cfg_name), dict):
-                    reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
-                                                             json.dumps(getattr(config, cfg_name),
-                                                                        ensure_ascii=False, indent=4))
-                else:
-                    reply_str = "[bot]配置项{}: {}\n".format(cfg_name, getattr(config, cfg_name))
-                reply = [reply_str]
-            else:
-                cfg_value = " ".join(params[1:])
-                # 类型转换，如果是json则转换为字典
-                if cfg_value == 'true':
-                    cfg_value = True
-                elif cfg_value == 'false':
-                    cfg_value = False
-                elif cfg_value.isdigit():
-                    cfg_value = int(cfg_value)
-                elif cfg_value.startswith('{') and cfg_value.endswith('}'):
-                    cfg_value = json.loads(cfg_value)
-                else:
-                    try:
-                        cfg_value = float(cfg_value)
-                    except ValueError:
-                        pass
-
-                # 检查类型是否匹配
-                if isinstance(getattr(config, cfg_name), type(cfg_value)):
-                    setattr(config, cfg_name, cfg_value)
-                    pkg.utils.context.set_config(config)
-                    reply = ["[bot]配置项{}修改成功".format(cfg_name)]
-                else:
-                    reply = ["[bot]err:配置项{}类型不匹配".format(cfg_name)]
-
-        else:
-            reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
-
-    return reply
-
-
-def plugin_operation(cmd, params, is_admin):
-    reply = []
-
-    import pkg.plugin.host as plugin_host
-    import pkg.utils.updater as updater
-
-    plugin_list = plugin_host.__plugins__
-
-    if len(params) == 0:
-        reply_str = "[bot]所有插件({}):\n".format(len(plugin_host.__plugins__))
-        idx = 0
-        for key in plugin_host.iter_plugins_name():
-            plugin = plugin_list[key]
-            reply_str += "\n#{} {} {}\n{}\nv{}\n作者: {}\n"\
-                .format((idx+1), plugin['name'],
-                        "[已禁用]" if not plugin['enabled'] else "",
-                        plugin['description'],
-                        plugin['version'], plugin['author'])
-
-            if updater.is_repo("/".join(plugin['path'].split('/')[:-1])):
-                remote_url = updater.get_remote_url("/".join(plugin['path'].split('/')[:-1]))
-                if remote_url != "https://github.com/RockChinQ/QChatGPT" and remote_url != "https://gitee.com/RockChin/QChatGPT":
-                    reply_str += "源码: "+remote_url+"\n"
-
-            idx += 1
-
-        reply = [reply_str]
-    elif params[0] == 'update':
-        # 更新所有插件
-        if is_admin:
-            def closure():
-                import pkg.utils.context
-                updated = []
-                for key in plugin_list:
-                    plugin = plugin_list[key]
-                    if updater.is_repo("/".join(plugin['path'].split('/')[:-1])):
-                        success = updater.pull_latest("/".join(plugin['path'].split('/')[:-1]))
-                        if success:
-                            updated.append(plugin['name'])
-
-                # 检查是否有requirements.txt
-                pkg.utils.context.get_qqbot_manager().notify_admin("正在安装依赖...")
-                for key in plugin_list:
-                    plugin = plugin_list[key]
-                    if os.path.exists("/".join(plugin['path'].split('/')[:-1])+"/requirements.txt"):
-                        logging.info("{}检测到requirements.txt，安装依赖".format(plugin['name']))
-                        import pkg.utils.pkgmgr
-                        pkg.utils.pkgmgr.install_requirements("/".join(plugin['path'].split('/')[:-1])+"/requirements.txt")
-
-                        import main
-                        main.reset_logging()
-
-                pkg.utils.context.get_qqbot_manager().notify_admin("已更新插件: {}".format(", ".join(updated)))
-
-            threading.Thread(target=closure).start()
-            reply = ["[bot]正在更新所有插件，请勿重复发起..."]
-        else:
-            reply = ["[bot]err:权限不足"]
-    elif params[0].startswith("http"):
-        if is_admin:
-
-            def closure():
-                try:
-                    plugin_host.install_plugin(params[0])
-                    pkg.utils.context.get_qqbot_manager().notify_admin("插件安装成功，请发送 !reload 指令重载插件")
-                except Exception as e:
-                    logging.error("插件安装失败:{}".format(e))
-                    pkg.utils.context.get_qqbot_manager().notify_admin("插件安装失败:{}".format(e))
-
-            threading.Thread(target=closure, args=()).start()
-            reply = ["[bot]正在安装插件..."]
-        else:
-            reply = ["[bot]err:权限不足，请使用管理员账号私聊发起"]
-    return reply
-
 
 def process_command(session_name: str, text_message: str, mgr, config,
                     launcher_type: str, launcher_id: int, sender_id: int, is_admin: bool) -> list:
@@ -169,188 +31,32 @@ def process_command(session_name: str, text_message: str, mgr, config,
         cmd = text_message[1:].strip().split(' ')[0]
 
         params = text_message[1:].strip().split(' ')[1:]
-        if cmd == 'help':
-            reply = ["[bot]" + config.help_message]
-        elif cmd == 'reset':
-            if len(params) == 0:
-                pkg.openai.session.get_session(session_name).reset(explicit=True)
-                reply = ["[bot]会话已重置"]
-            else:
-                pkg.openai.session.get_session(session_name).reset(explicit=True, use_prompt=params[0])
-                reply = ["[bot]会话已重置，使用场景预设:{}".format(params[0])]
-        elif cmd == 'last':
-            result = pkg.openai.session.get_session(session_name).last_session()
-            if result is None:
-                reply = ["[bot]没有前一次的对话"]
-            else:
-                datetime_str = datetime.datetime.fromtimestamp(result.create_timestamp).strftime(
-                    '%Y-%m-%d %H:%M:%S')
-                reply = ["[bot]已切换到前一次的对话：\n创建时间:{}\n".format(datetime_str)]
-        elif cmd == 'next':
-            result = pkg.openai.session.get_session(session_name).next_session()
-            if result is None:
-                reply = ["[bot]没有后一次的对话"]
-            else:
-                datetime_str = datetime.datetime.fromtimestamp(result.create_timestamp).strftime(
-                    '%Y-%m-%d %H:%M:%S')
-                reply = ["[bot]已切换到后一次的对话：\n创建时间:{}\n".format(datetime_str)]
-        elif cmd == 'prompt':
-            msgs = ""
-            session:list = pkg.openai.session.get_session(session_name).prompt
-            for msg in session:
-                if len(params) != 0 and params[0] in ['-all', '-a']:
-                    msgs = msgs + "{}: {}\n\n".format(msg['role'], msg['content'])
-                elif len(msg['content']) > 30:
-                    msgs = msgs + "[{}]: {}...\n\n".format(msg['role'], msg['content'][:30])
-                else:
-                    msgs = msgs + "[{}]: {}\n\n".format(msg['role'], msg['content'])
-            reply = ["[bot]当前对话所有内容：\n{}".format(msgs)]
-        elif cmd == 'list':
-            pkg.openai.session.get_session(session_name).persistence()
-            page = 0
 
-            if len(params) > 0:
-                try:
-                    page = int(params[0])
-                except ValueError:
-                    pass
+        # 把!~开头的转换成!cfg
+        if cmd.startswith('~'):
+            params = [cmd[1:]] + params
+            cmd = 'cfg'
 
-            results = pkg.openai.session.get_session(session_name).list_history(page=page)
-            if len(results) == 0:
-                reply = ["[bot]第{}页没有历史会话".format(page)]
-            else:
-                reply_str = "[bot]历史会话 第{}页：\n".format(page)
-                current = -1
-                for i in range(len(results)):
-                    # 时间(使用create_timestamp转换) 序号 部分内容
-                    datetime_obj = datetime.datetime.fromtimestamp(results[i]['create_timestamp'])
-                    msg = ""
-                    try:
-                        msg = json.loads(results[i]['prompt'])
-                    except json.decoder.JSONDecodeError:
-                        msg = pkg.openai.session.reset_session_prompt(session_name, results[i]['prompt'])
-                        # 持久化
-                        pkg.openai.session.get_session(session_name).persistence()
-                    if len(msg) >= 2:
-                        reply_str += "#{} 创建:{} {}\n".format(i + page * 10,
-                                                               datetime_obj.strftime("%Y-%m-%d %H:%M:%S"),
-                                                               msg[1]['content'])
-                    else:
-                        reply_str += "#{} 创建:{} {}\n".format(i + page * 10,
-                                                               datetime_obj.strftime("%Y-%m-%d %H:%M:%S"),
-                                                               "无内容")
-                    if results[i]['create_timestamp'] == pkg.openai.session.get_session(
-                            session_name).create_timestamp:
-                        current = i + page * 10
+        # 包装参数
+        context = cmdmgr.Context(
+            command=cmd,
+            crt_command=cmd,
+            params=params,
+            crt_params=params[:],
+            session_name=session_name,
+            text_message=text_message,
+            launcher_type=launcher_type,
+            launcher_id=launcher_id,
+            sender_id=sender_id,
+            is_admin=is_admin,
+            privilege=2 if is_admin else 1,  # 普通用户1，管理员2
+        )
+        try:
+            reply = cmdmgr.execute(context)
+        except cmdmgr.CommandPrivilegeError as e:
+            reply = ["{}".format(e)]
 
-                reply_str += "\n以上信息倒序排列"
-                if current != -1:
-                    reply_str += ",当前会话是 #{}\n".format(current)
-                else:
-                    reply_str += ",当前处于全新会话或不在此页"
-
-                reply = [reply_str]
-        elif cmd == 'resend':
-            session = pkg.openai.session.get_session(session_name)
-            to_send = session.undo()
-
-            reply = pkg.qqbot.message.process_normal_message(to_send, mgr, config,
-                                                             launcher_type, launcher_id, sender_id)
-        elif cmd == 'usage':
-            reply_str = "[bot]各api-key使用情况:\n\n"
-
-            api_keys = pkg.utils.context.get_openai_manager().key_mgr.api_key
-            for key_name in api_keys:
-                text_length = pkg.utils.context.get_openai_manager().audit_mgr \
-                    .get_text_length_of_key(api_keys[key_name])
-                image_count = pkg.utils.context.get_openai_manager().audit_mgr \
-                    .get_image_count_of_key(api_keys[key_name])
-                reply_str += "{}:\n - 文本长度:{}\n - 图片数量:{}\n".format(key_name, int(text_length),
-                                                                            int(image_count))
-                # 获取此key的额度
-                try:
-                    credit_data = credit.fetch_credit_data(api_keys[key_name])
-                    reply_str += " - 使用额度:{:.2f}/{:.2f}\n".format(credit_data['total_used'],credit_data['total_granted'])
-                except Exception as e:
-                    logging.warning("获取额度失败:{}".format(e))
-
-            reply = [reply_str]
-        elif cmd == 'draw':
-            if len(params) == 0:
-                reply = ["[bot]err:请输入图片描述文字"]
-            else:
-                session = pkg.openai.session.get_session(session_name)
-
-                res = session.draw_image(" ".join(params))
-
-                logging.debug("draw_image result:{}".format(res))
-                reply = [Image(url=res['data'][0]['url'])]
-                if not (hasattr(config, 'include_image_description')
-                        and not config.include_image_description):
-                    reply.append(" ".join(params))
-        elif cmd == 'version':
-            reply_str = "[bot]当前版本:\n{}\n".format(pkg.utils.updater.get_current_version_info())
-            try:
-                if pkg.utils.updater.is_new_version_available():
-                    reply_str += "\n有新版本可用，请使用命令 !update 进行更新"
-            except:
-                pass
-
-            reply = [reply_str]
-
-        elif cmd == 'plugin':
-            reply = plugin_operation(cmd, params, is_admin)
-
-        elif cmd == 'default':
-            if len(params) == 0:
-                # 输出目前所有情景预设
-                import pkg.openai.dprompt as dprompt
-                reply_str = "[bot]当前所有情景预设:\n\n"
-                for key,value in dprompt.get_prompt_dict().items():
-                    reply_str += "  - {}: {}\n".format(key,value)
-
-                reply_str += "\n当前默认情景预设:{}\n".format(dprompt.get_current())
-                reply_str += "请使用!default <情景预设>来设置默认情景预设"
-                reply = [reply_str]
-            elif len(params) >0  and is_admin:
-                # 设置默认情景
-                import pkg.openai.dprompt as dprompt
-                try:
-                    dprompt.set_current(params[0])
-                    reply = ["[bot]已设置默认情景预设为:{}".format(dprompt.get_current())]
-                except KeyError:
-                    reply = ["[bot]err: 未找到情景预设:{}".format(params[0])]
-            else:
-                reply = ["[bot]err: 仅管理员可设置默认情景预设"]
-        elif cmd == 'reload' and is_admin:
-            def reload_task():
-                pkg.utils.reloader.reload_all()
-
-            threading.Thread(target=reload_task, daemon=True).start()
-        elif cmd == 'update' and is_admin:
-            def update_task():
-                try:
-                    if pkg.utils.updater.update_all():
-                        pkg.utils.reloader.reload_all(notify=False)
-                        pkg.utils.context.get_qqbot_manager().notify_admin("更新完成")
-                    else:
-                        pkg.utils.context.get_qqbot_manager().notify_admin("无新版本")
-                except Exception as e0:
-                    pkg.utils.context.get_qqbot_manager().notify_admin("更新失败:{}".format(e0))
-                    return
-
-            threading.Thread(target=update_task, daemon=True).start()
-
-            reply = ["[bot]正在更新，请耐心等待，请勿重复发起更新..."]
-        elif cmd == 'cfg' and is_admin:
-            reply = config_operation(cmd, params)
-        else:
-            if cmd.startswith("~") and is_admin:
-                config_item = cmd[1:]
-                params = [config_item] + params
-                reply = config_operation("cfg", params)
-            else:
-                reply = ["[bot]err:未知的指令或权限不足: " + cmd]
+        return reply
     except Exception as e:
         mgr.notify_admin("{}指令执行失败:{}".format(session_name, e))
         logging.exception(e)

pkg/qqbot/filter.py

@@ -1,19 +1,84 @@
 # 敏感词过滤模块
 import re
+import requests
+import json
+import logging
 
 
 class ReplyFilter:
-
     sensitive_words = []
+    mask = "*"
+    mask_word = ""
 
-    def __init__(self, sensitive_words: list):
+    # 默认值( 兼容性考虑 )
+    baidu_check = False
+    baidu_api_key = ""
+    baidu_secret_key = ""
+    inappropriate_message_tips = "[百度云]请珍惜机器人，当前返回内容不合规"
+
+    def __init__(self, sensitive_words: list, mask: str = "*", mask_word: str = ""):
         self.sensitive_words = sensitive_words
+        self.mask = mask
+        self.mask_word = mask_word
+        import config
+
+        self.baidu_check = config.baidu_check
+        self.baidu_api_key = config.baidu_api_key
+        self.baidu_secret_key = config.baidu_secret_key
+        self.inappropriate_message_tips = config.inappropriate_message_tips
+
+    def is_illegal(self, message: str) -> bool:
+        processed = self.process(message)
+        if processed != message:
+            return True
+        return False
 
     def process(self, message: str) -> str:
+
+        # 本地关键词屏蔽
         for word in self.sensitive_words:
             match = re.findall(word, message)
             if len(match) > 0:
                 for i in range(len(match)):
-                    message = message.replace(match[i], "*" * len(match[i]))
+                    if self.mask_word == "":
+                        message = message.replace(match[i], self.mask * len(match[i]))
+                    else:
+                        message = message.replace(match[i], self.mask_word)
 
+        # 百度云审核
+        if self.baidu_check:
+
+            # 百度云审核URL
+            baidu_url = "https://aip.baidubce.com/rest/2.0/solution/v1/text_censor/v2/user_defined?access_token=" + \
+                str(requests.post("https://aip.baidubce.com/oauth/2.0/token",
+                      params={"grant_type": "client_credentials",
+                              "client_id": self.baidu_api_key,
+                              "client_secret": self.baidu_secret_key}).json().get("access_token"))
+
+            # 百度云审核
+            payload = "text=" + message
+            logging.info("向百度云发送:" + payload)
+            headers = {'Content-Type': 'application/x-www-form-urlencoded', 'Accept': 'application/json'}
+
+            if isinstance(payload, str):
+                payload = payload.encode('utf-8')
+
+            response = requests.request("POST", baidu_url, headers=headers, data=payload)
+            response_dict = json.loads(response.text)
+
+            if "error_code" in response_dict:
+                error_msg = response_dict.get("error_msg")
+                logging.warning(f"百度云判定出错，错误信息：{error_msg}")
+                conclusion = f"百度云判定出错，错误信息：{error_msg}\n以下是原消息：{message}"
+            else:
+                conclusion = response_dict["conclusion"]
+                if conclusion in ("合规"):
+                    logging.info(f"百度云判定结果：{conclusion}")
+                    return message
+                else:
+                    logging.warning(f"百度云判定结果：{conclusion}")
+                    conclusion = self.inappropriate_message_tips
+            # 返回百度云审核结果
+            return conclusion
+        
         return message

pkg/qqbot/ignore.py

@@ -5,9 +5,6 @@ def ignore(msg: str) -> bool:
     """检查消息是否应该被忽略"""
     import config
     
-    if not hasattr(config, 'ignore_rules'):
-        return False
-    
     if 'prefix' in config.ignore_rules:
         for rule in config.ignore_rules['prefix']:
             if msg.startswith(rule):

pkg/qqbot/manager.py

@@ -3,9 +3,9 @@ import json
 import os
 import threading
 
-import mirai.models.bus
+
 from mirai import At, GroupMessage, MessageEvent, Mirai, StrangerMessage, WebSocketAdapter, HTTPAdapter, \
-    FriendMessage, Image
+    FriendMessage, Image, MessageChain, Plain
 from func_timeout import func_set_timeout
 
 import pkg.openai.session
@@ -19,21 +19,24 @@ import pkg.utils.context
 
 import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models
+import tips as tips_custom
 
-
-# 并行运行
-def go(func, args=()):
-    thread = threading.Thread(target=func, args=args, daemon=True)
-    thread.start()
+import pkg.qqbot.adapter as msadapter
 
 
 # 检查消息是否符合泛响应匹配机制
-def check_response_rule(text: str):
+def check_response_rule(group_id:int, text: str):
     config = pkg.utils.context.get_config()
-    if not hasattr(config, 'response_rules'):
-        return False, ''
 
     rules = config.response_rules
+
+    # 检查是否有特定规则
+    if 'prefix' not in config.response_rules:
+        if str(group_id) in config.response_rules:
+            rules = config.response_rules[str(group_id)]
+        else:
+            rules = config.response_rules['default']
+
     # 检查前缀匹配
     if 'prefix' in rules:
         for rule in rules['prefix']:
@@ -51,57 +54,92 @@ def check_response_rule(text: str):
     return False, ""
 
 
+def response_at(group_id: int):
+    config = pkg.utils.context.get_config()
+
+    use_response_rule = config.response_rules
+
+    # 检查是否有特定规则
+    if 'prefix' not in config.response_rules:
+        if str(group_id) in config.response_rules:
+            use_response_rule = config.response_rules[str(group_id)]
+        else:
+            use_response_rule = config.response_rules['default']
+
+    if 'at' not in use_response_rule:
+        return True
+
+    return use_response_rule['at']
+
+
+def random_responding(group_id):
+    config = pkg.utils.context.get_config()
+
+    use_response_rule = config.response_rules
+
+    # 检查是否有特定规则
+    if 'prefix' not in config.response_rules:
+        if str(group_id) in config.response_rules:
+            use_response_rule = config.response_rules[str(group_id)]
+        else:
+            use_response_rule = config.response_rules['default']
+
+    if 'random_rate' in use_response_rule:
+        import random
+        return random.random() < use_response_rule['random_rate']
+    return False
+
+
 # 控制QQ消息输入输出的类
 class QQBotManager:
     retry = 3
 
-    bot: Mirai = None
+    adapter: msadapter.MessageSourceAdapter = None
+
+    bot_account_id: int = 0
 
     reply_filter = None
 
     enable_banlist = False
 
+    enable_private = True
+    enable_group = True
+
     ban_person = []
     ban_group = []
 
-    def __init__(self, mirai_http_api_config: dict, timeout: int = 60, retry: int = 3, first_time_init=True):
+    def __init__(self, first_time_init=True):
+        import config
 
-        self.timeout = timeout
-        self.retry = retry
-
-        # 加载禁用列表
-        if os.path.exists("banlist.py"):
-            import banlist
-            self.enable_banlist = banlist.enable
-            self.ban_person = banlist.person
-            self.ban_group = banlist.group
-            logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))
-
-        config = pkg.utils.context.get_config()
-        if os.path.exists("sensitive.json") \
-                and config.sensitive_word_filter is not None \
-                and config.sensitive_word_filter:
-            with open("sensitive.json", "r", encoding="utf-8") as f:
-                self.reply_filter = pkg.qqbot.filter.ReplyFilter(json.load(f)['words'])
-        else:
-            self.reply_filter = pkg.qqbot.filter.ReplyFilter([])
+        self.timeout = config.process_message_timeout
+        self.retry = config.retry_times
 
         # 由于YiriMirai的bot对象是单例的，且shutdown方法暂时无法使用
         # 故只在第一次初始化时创建bot对象，重载之后使用原bot对象
         # 因此，bot的配置不支持热重载
         if first_time_init:
-            self.first_time_init(mirai_http_api_config)
+            logging.debug("Use adapter:" + config.msg_source_adapter)
+            if config.msg_source_adapter == 'yirimirai':
+                from pkg.qqbot.sources.yirimirai import YiriMiraiAdapter
+
+                mirai_http_api_config = config.mirai_http_api_config
+                self.bot_account_id = config.mirai_http_api_config['qq']
+                self.adapter = YiriMiraiAdapter(mirai_http_api_config)
+            elif config.msg_source_adapter == 'nakuru':
+                from pkg.qqbot.sources.nakuru import NakuruProjectAdapter
+                self.adapter = NakuruProjectAdapter(config.nakuru_config)
+                self.bot_account_id = self.adapter.bot_account_id
         else:
-            self.bot = pkg.utils.context.get_qqbot_manager().bot
+            self.adapter = pkg.utils.context.get_qqbot_manager().adapter
+            self.bot_account_id = pkg.utils.context.get_qqbot_manager().bot_account_id
 
         pkg.utils.context.set_qqbot_manager(self)
 
+        # 注册诸事件
         # Caution: 注册新的事件处理器之后，请务必在unsubscribe_all中编写相应的取消订阅代码
-        @self.bot.on(FriendMessage)
-        async def on_friend_message(event: FriendMessage):
-
-            def friend_message_handler(event: FriendMessage):
+        def on_friend_message(event: FriendMessage):
 
+            def friend_message_handler():
                 # 触发事件
                 args = {
                     "launcher_type": "person",
@@ -116,12 +154,17 @@ class QQBotManager:
 
                 self.on_person_message(event)
 
-            go(friend_message_handler, (event,))
+            pkg.utils.context.get_thread_ctl().submit_user_task(
+                friend_message_handler,
+            )
+        self.adapter.register_listener(
+            FriendMessage,
+            on_friend_message
+        )
 
-        @self.bot.on(StrangerMessage)
-        async def on_stranger_message(event: StrangerMessage):
+        def on_stranger_message(event: StrangerMessage):
 
-            def stranger_message_handler(event: StrangerMessage):
+            def stranger_message_handler():
                 # 触发事件
                 args = {
                     "launcher_type": "person",
@@ -136,10 +179,17 @@ class QQBotManager:
 
                 self.on_person_message(event)
 
-            go(stranger_message_handler, (event,))
+            pkg.utils.context.get_thread_ctl().submit_user_task(
+                stranger_message_handler,
+            )
+        # nakuru不区分好友和陌生人，故仅为yirimirai注册陌生人事件
+        if config.msg_source_adapter == 'yirimirai':
+            self.adapter.register_listener(
+                StrangerMessage,
+                on_stranger_message
+            )
 
-        @self.bot.on(GroupMessage)
-        async def on_group_message(event: GroupMessage):
+        def on_group_message(event: GroupMessage):
 
             def group_message_handler(event: GroupMessage):
                 # 触发事件
@@ -156,62 +206,96 @@ class QQBotManager:
 
                 self.on_group_message(event)
 
-            go(group_message_handler, (event,))
+            pkg.utils.context.get_thread_ctl().submit_user_task(
+                group_message_handler,
+                event
+            )
+        self.adapter.register_listener(
+            GroupMessage,
+            on_group_message
+        )
 
         def unsubscribe_all():
             """取消所有订阅
 
             用于在热重载流程中卸载所有事件处理器
             """
-            assert isinstance(self.bot, Mirai)
-            bus = self.bot.bus
-            assert isinstance(bus, mirai.models.bus.ModelEventBus)
-
-            bus.unsubscribe(FriendMessage, on_friend_message)
-            bus.unsubscribe(StrangerMessage, on_stranger_message)
-            bus.unsubscribe(GroupMessage, on_group_message)
+            import config
+            self.adapter.unregister_listener(
+                FriendMessage,
+                on_friend_message
+            )
+            if config.msg_source_adapter == 'yirimirai':
+                self.adapter.unregister_listener(
+                    StrangerMessage,
+                    on_stranger_message
+                )
+            self.adapter.unregister_listener(
+                GroupMessage,
+                on_group_message
+            )
 
         self.unsubscribe_all = unsubscribe_all
 
-    def first_time_init(self, mirai_http_api_config: dict):
-        """热重载后不再运行此函数"""
+        # 加载禁用列表
+        if os.path.exists("banlist.py"):
+            import banlist
+            self.enable_banlist = banlist.enable
+            self.ban_person = banlist.person
+            self.ban_group = banlist.group
+            logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))
 
-        if 'adapter' not in mirai_http_api_config or mirai_http_api_config['adapter'] == "WebSocketAdapter":
-            bot = Mirai(
-                qq=mirai_http_api_config['qq'],
-                adapter=WebSocketAdapter(
-                    verify_key=mirai_http_api_config['verifyKey'],
-                    host=mirai_http_api_config['host'],
-                    port=mirai_http_api_config['port']
-                )
-            )
-        elif mirai_http_api_config['adapter'] == "HTTPAdapter":
-            bot = Mirai(
-                qq=mirai_http_api_config['qq'],
-                adapter=HTTPAdapter(
-                    verify_key=mirai_http_api_config['verifyKey'],
-                    host=mirai_http_api_config['host'],
-                    port=mirai_http_api_config['port']
-                )
-            )
+            if hasattr(banlist, "enable_private"):
+                self.enable_private = banlist.enable_private
+            if hasattr(banlist, "enable_group"):
+                self.enable_group = banlist.enable_group
 
-        else:
-            raise Exception("未知的适配器类型")
-
-        self.bot = bot
-
-    def send(self, event, msg, check_quote=True):
         config = pkg.utils.context.get_config()
-        asyncio.run(
-            self.bot.send(event, msg, quote=True if hasattr(config,
-                                                            "quote_origin") and config.quote_origin and check_quote else False))
+        if os.path.exists("sensitive.json") \
+                and config.sensitive_word_filter is not None \
+                and config.sensitive_word_filter:
+            with open("sensitive.json", "r", encoding="utf-8") as f:
+                sensitive_json = json.load(f)
+                self.reply_filter = pkg.qqbot.filter.ReplyFilter(
+                    sensitive_words=sensitive_json['words'],
+                    mask=sensitive_json['mask'] if 'mask' in sensitive_json else '*',
+                    mask_word=sensitive_json['mask_word'] if 'mask_word' in sensitive_json else ''
+                )
+        else:
+            self.reply_filter = pkg.qqbot.filter.ReplyFilter([])
+
+    def send(self, event, msg, check_quote=True, check_at_sender=True):
+        config = pkg.utils.context.get_config()
+        
+        if check_at_sender and config.at_sender:
+            msg.insert(
+                0,
+                Plain(" \n")
+            )
+
+            # 当回复的正文中包含换行时，quote可能会自带at，此时就不再单独添加at，只添加换行
+            if "\n" not in str(msg[1]) or config.msg_source_adapter == 'nakuru':
+                msg.insert(
+                    0,
+                    At(
+                        event.sender.id
+                    )
+                )
+
+        self.adapter.reply_message(
+            event,
+            msg,
+            quote_origin=True if config.quote_origin and check_quote else False
+        )
 
     # 私聊消息处理
     def on_person_message(self, event: MessageEvent):
         import config
         reply = ''
 
-        if event.sender.id == self.bot.qq:
+        if not self.enable_private:
+            logging.debug("已在banlist.py中禁用所有私聊")
+        elif event.sender.id == self.bot_account_id:
             pass
         else:
             if Image in event.message_chain:
@@ -242,20 +326,19 @@ class QQBotManager:
                 if failed == self.retry:
                     pkg.openai.session.get_session('person_{}'.format(event.sender.id)).release_response_lock()
                     self.notify_admin("{} 请求超时".format("person_{}".format(event.sender.id)))
-                    reply = ["[bot]err:请求超时"]
+                    reply = [tips_custom.reply_message]
 
         if reply:
-            return self.send(event, reply, check_quote=False)
+            return self.send(event, reply, check_quote=False, check_at_sender=False)
 
     # 群消息处理
     def on_group_message(self, event: GroupMessage):
         import config
         reply = ''
-
         def process(text=None) -> str:
             replys = ""
-            if At(self.bot.qq) in event.message_chain:
-                event.message_chain.remove(At(self.bot.qq))
+            if At(self.bot_account_id) in event.message_chain:
+                event.message_chain.remove(At(self.bot_account_id))
 
             # 超时则重试，重试超过次数则放弃
             failed = 0
@@ -282,20 +365,27 @@ class QQBotManager:
             if failed == self.retry:
                 pkg.openai.session.get_session('group_{}'.format(event.group.id)).release_response_lock()
                 self.notify_admin("{} 请求超时".format("group_{}".format(event.group.id)))
-                replys = ["[bot]err:请求超时"]
+                replys = [tips_custom.replys_message]
 
             return replys
-
-        if Image in event.message_chain:
+        
+        if not self.enable_group:
+            logging.debug("已在banlist.py中禁用所有群聊")
+        elif Image in event.message_chain:
             pass
-        elif At(self.bot.qq) not in event.message_chain:
-            check, result = check_response_rule(str(event.message_chain).strip())
-
-            if check:
-                reply = process(result.strip())
         else:
-            # 直接调用
-            reply = process()
+            if At(self.bot_account_id) in event.message_chain and response_at(event.group.id):
+                # 直接调用
+                reply = process()
+            else:
+                check, result = check_response_rule(event.group.id, str(event.message_chain).strip())
+
+                if check:
+                    reply = process(result.strip())
+                # 检查是否随机响应
+                elif random_responding(event.group.id):
+                    logging.info("随机响应group_{}消息".format(event.group.id))
+                    reply = process()
 
         if reply:
             return self.send(event, reply)
@@ -303,25 +393,36 @@ class QQBotManager:
     # 通知系统管理员
     def notify_admin(self, message: str):
         config = pkg.utils.context.get_config()
-        if hasattr(config, "admin_qq") and config.admin_qq != 0 and config.admin_qq != []:
+        if config.admin_qq != 0 and config.admin_qq != []:
             logging.info("通知管理员:{}".format(message))
             if type(config.admin_qq) == int:
-                send_task = self.bot.send_friend_message(config.admin_qq, "[bot]{}".format(message))
-                threading.Thread(target=asyncio.run, args=(send_task,)).start()
+                self.adapter.send_message(
+                    "person",
+                    config.admin_qq,
+                    MessageChain([Plain("[bot]{}".format(message))])
+                )
             else:
                 for adm in config.admin_qq:
-                    send_task = self.bot.send_friend_message(adm, "[bot]{}".format(message))
-                    threading.Thread(target=asyncio.run, args=(send_task,)).start()
-
+                    self.adapter.send_message(
+                        "person",
+                        adm,
+                        MessageChain([Plain("[bot]{}".format(message))])
+                    )
 
     def notify_admin_message_chain(self, message):
         config = pkg.utils.context.get_config()
-        if hasattr(config, "admin_qq") and config.admin_qq != 0 and config.admin_qq != []:
+        if config.admin_qq != 0 and config.admin_qq != []:
             logging.info("通知管理员:{}".format(message))
             if type(config.admin_qq) == int:
-                send_task = self.bot.send_friend_message(config.admin_qq, message)
-                threading.Thread(target=asyncio.run, args=(send_task,)).start()
+                self.adapter.send_message(
+                    "person",
+                    config.admin_qq,
+                    message
+                )
             else:
                 for adm in config.admin_qq:
-                    send_task = self.bot.send_friend_message(adm, message)
-                    threading.Thread(target=asyncio.run, args=(send_task,)).start()
+                    self.adapter.send_message(
+                        "person",
+                        adm,
+                        message
+                    )

pkg/qqbot/message.py

@@ -1,23 +1,21 @@
 # 普通消息处理模块
 import logging
-import time
 import openai
 import pkg.utils.context
 import pkg.openai.session
 
 import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models
+import pkg.qqbot.blob as blob
+import tips as tips_custom
 
 
 def handle_exception(notify_admin: str = "", set_reply: str = "") -> list:
     """处理异常，当notify_admin不为空时，会通知管理员，返回通知用户的消息"""
     import config
     pkg.utils.context.get_qqbot_manager().notify_admin(notify_admin)
-    if hasattr(config, 'hide_exce_info_to_user') and config.hide_exce_info_to_user:
-        if hasattr(config, 'alter_tip_message'):
-            return [config.alter_tip_message] if config.alter_tip_message else []
-        else:
-            return ["[bot]出错了，请重试或联系管理员"]
+    if config.hide_exce_info_to_user:
+        return [tips_custom.alter_tip_message] if tips_custom.alter_tip_message else []
     else:
         return [set_reply]
 
@@ -40,9 +38,9 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
             reply = handle_exception(notify_admin=f"{session_name}，多次尝试失败。", set_reply=f"[bot]多次尝试失败，请重试或联系管理员")
             break
         try:
-            prefix = "[GPT]" if hasattr(config, "show_prefix") and config.show_prefix else ""
+            prefix = "[GPT]" if config.show_prefix else ""
 
-            text = session.append(text_message)
+            text, finish_reason, funcs = session.query(text_message)
 
             # 触发插件事件
             args = {
@@ -51,7 +49,9 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
                 "sender_id": sender_id,
                 "session": session,
                 "prefix": prefix,
-                "response_text": text
+                "response_text": text,
+                "finish_reason": finish_reason,
+                "funcs_called": funcs,
             }
 
             event = pkg.plugin.host.emit(plugin_models.NormalMessageResponded, **args)
@@ -64,10 +64,11 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
 
             if not event.is_prevented_default():
                 reply = [prefix + text]
+
         except openai.error.APIConnectionError as e:
             err_msg = str(e)
             if err_msg.__contains__('Error communicating with OpenAI'):
-                reply = handle_exception("{}会话调用API失败:{}\n请尝试关闭网络代理来解决此问题。".format(session_name, e),
+                reply = handle_exception("{}会话调用API失败:{}\n您的网络无法访问OpenAI接口或网络代理不正常".format(session_name, e),
                                          "[bot]err:调用API失败，请重试或联系管理员，或等待修复")
             else:
                 reply = handle_exception("{}会话调用API失败:{}".format(session_name, e), "[bot]err:调用API失败，请重试或联系管理员，或等待修复")
@@ -116,9 +117,12 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
                 reply = handle_exception("{}会话调用API失败:{}".format(session_name, e),
                                          "[bot]err:RateLimitError,请重试或联系作者，或等待修复")
         except openai.error.InvalidRequestError as e:
-            reply = handle_exception("{}API调用参数错误:{}\n\n这可能是由于config.py中的prompt_submit_length参数或"
-                             "completion_api_params中的max_tokens参数数值过大导致的，请尝试将其降低".format(
-                             session_name, e), "[bot]err:API调用参数错误，请联系管理员，或等待修复")
+            if config.auto_reset and "This model's maximum context length is" in str(e):
+                session.reset(persist=True)
+                reply = [tips_custom.session_auto_reset_message]
+            else:
+                reply = handle_exception("{}API调用参数错误:{}\n".format(
+                                session_name, e), "[bot]err:API调用参数错误，请联系管理员，或等待修复")
         except openai.error.ServiceUnavailableError as e:
             reply = handle_exception("{}API调用服务不可用:{}".format(session_name, e), "[bot]err:API调用服务不可用，请重试或联系管理员，或等待修复")
         except Exception as e:

pkg/qqbot/process.py

@@ -26,6 +26,8 @@ import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models
 import pkg.qqbot.ignore as ignore
 import pkg.qqbot.banlist as banlist
+import pkg.qqbot.blob as blob
+import tips as tips_custom
 
 processing = []
 
@@ -49,7 +51,7 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
     session_name = "{}_{}".format(launcher_type, launcher_id)
 
     # 检查发送方是否被禁用
-    if banlist.is_banned(launcher_type, launcher_id):
+    if banlist.is_banned(launcher_type, launcher_id, sender_id):
         logging.info("根据禁用列表忽略{}_{}的消息".format(launcher_type, launcher_id))
         return []
 
@@ -57,24 +59,33 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
         logging.info("根据忽略规则忽略消息: {}".format(text_message))
         return []
 
+    import config
+
+    if not config.wait_last_done and session_name in processing:
+        return MessageChain([Plain(tips_custom.message_drop_tip)])
+
     # 检查是否被禁言
     if launcher_type == 'group':
-        result = mgr.bot.member_info(target=launcher_id, member_id=mgr.bot.qq).get()
-        result = asyncio.run(result)
-        if result.mute_time_remaining > 0:
-            logging.info("机器人被禁言,跳过消息处理(group_{},剩余{}s)".format(launcher_id,
-                                                                                result.mute_time_remaining))
+        is_muted = mgr.adapter.is_muted(launcher_id)
+        if is_muted:
+            logging.info("机器人被禁言,跳过消息处理(group_{})".format(launcher_id))
             return reply
 
+    import config
+    if config.income_msg_check:
+        if mgr.reply_filter.is_illegal(text_message):
+            return MessageChain(Plain("[bot] 消息中存在不合适的内容, 请更换措辞"))
+
     pkg.openai.session.get_session(session_name).acquire_response_lock()
 
     text_message = text_message.strip()
 
+
+    # 为强制消息延迟计时
+    start_time = time.time()
+
     # 处理消息
     try:
-        if session_name in processing:
-            pkg.openai.session.get_session(session_name).release_response_lock()
-            return MessageChain([Plain("[bot]err:正在处理中，请稍后再试")])
 
         config = pkg.utils.context.get_config()
 
@@ -109,10 +120,11 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
             else:  # 消息
                 # 限速丢弃检查
                 # print(ratelimit.__crt_minute_usage__[session_name])
-                if hasattr(config, "rate_limitation") and config.rate_limit_strategy == "drop":
+                if config.rate_limit_strategy == "drop":
                     if ratelimit.is_reach_limit(session_name):
                         logging.info("根据限速策略丢弃[{}]消息: {}".format(session_name, text_message))
-                        return MessageChain(["[bot]"+config.rate_limit_drop_tip]) if hasattr(config, "rate_limit_drop_tip") and config.rate_limit_drop_tip != "" else []
+
+                        return MessageChain(["[bot]"+tips_custom.rate_limit_drop_tip]) if tips_custom.rate_limit_drop_tip != "" else []
 
                 before = time.time()
                 # 触发插件事件
@@ -138,11 +150,10 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
                                                                      mgr, config, launcher_type, launcher_id, sender_id)
 
                 # 限速等待时间
-                if hasattr(config, "rate_limitation") and config.rate_limit_strategy == "wait":
+                if config.rate_limit_strategy == "wait":
                     time.sleep(ratelimit.get_rest_wait_time(session_name, time.time() - before))
                 
-                if hasattr(config, "rate_limitation"):
-                    ratelimit.add_usage(session_name)
+                ratelimit.add_usage(session_name)
 
             if reply is not None and len(reply) > 0 and (type(reply[0]) == str or type(reply[0]) == mirai.Plain):
                 if type(reply[0]) == mirai.Plain:
@@ -152,12 +163,32 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
                                                  reply[0][:min(100, len(reply[0]))] + (
                                                      "..." if len(reply[0]) > 100 else "")))
                 reply = [mgr.reply_filter.process(reply[0])]
+                reply = blob.check_text(reply[0])
             else:
-                logging.info("回复[{}]图片消息:{}".format(session_name, reply))
+                logging.info("回复[{}]消息".format(session_name))
 
         finally:
             processing.remove(session_name)
     finally:
         pkg.openai.session.get_session(session_name).release_response_lock()
 
+    # 检查延迟时间
+    if config.force_delay_range[1] == 0:
+        delay_time = 0
+    else:
+        import random
+
+        # 从延迟范围中随机取一个值(浮点)
+        rdm = random.uniform(config.force_delay_range[0], config.force_delay_range[1])
+
+        spent = time.time() - start_time
+
+        # 如果花费时间小于延迟时间，则延迟
+        delay_time = rdm - spent if rdm - spent > 0 else 0
+
+    # 延迟
+    if delay_time > 0:
+        logging.info("[风控] 强制延迟{:.2f}秒(如需关闭，请到config.py修改force_delay_range字段)".format(delay_time))
+        time.sleep(delay_time)
+
     return MessageChain(reply)

pkg/qqbot/ratelimit.py

@@ -10,6 +10,20 @@ __crt_minute_usage__ = {}
 __timer_thr__: threading.Thread = None
 
 
+def get_limitation(session_name: str) -> int:
+    """获取会话的限制次数"""
+    import config
+
+    if type(config.rate_limitation) == dict:
+        # 如果被指定了
+        if session_name in config.rate_limitation:
+            return config.rate_limitation[session_name]
+        else:
+            return config.rate_limitation["default"]
+    elif type(config.rate_limitation) == int:
+        return config.rate_limitation
+
+
 def add_usage(session_name: str):
     """增加会话的对话次数"""
     global __crt_minute_usage__
@@ -56,12 +70,7 @@ def get_rest_wait_time(session_name: str, spent: float) -> float:
     """获取会话此回合的剩余等待时间"""
     global __crt_minute_usage__
 
-    import config
-
-    if not hasattr(config, 'rate_limitation'):
-        return 0
-
-    min_seconds_per_round = 60.0 / config.rate_limitation
+    min_seconds_per_round = 60.0 / get_limitation(session_name)
 
     if session_name in __crt_minute_usage__:
         return max(0, min_seconds_per_round - spent)
@@ -73,13 +82,8 @@ def is_reach_limit(session_name: str) -> bool:
     """判断会话是否超过限制"""
     global __crt_minute_usage__
 
-    import config
-
-    if not hasattr(config, 'rate_limitation'):
-        return False
-
     if session_name in __crt_minute_usage__:
-        return __crt_minute_usage__[session_name] >= config.rate_limitation
+        return __crt_minute_usage__[session_name] >= get_limitation(session_name)
     else:
         return False
 

pkg/qqbot/sources/nakuru.py

@@ -0,0 +1,321 @@
+import mirai
+
+from ..adapter import MessageSourceAdapter, MessageConverter, EventConverter
+import nakuru
+import nakuru.entities.components as nkc
+
+import asyncio
+import typing
+import traceback
+import logging
+import json
+
+from pkg.qqbot.blob import Forward, ForwardMessageNode, ForwardMessageDiaplay
+
+
+class NakuruProjectMessageConverter(MessageConverter):
+    """消息转换器"""
+    @staticmethod
+    def yiri2target(message_chain: mirai.MessageChain) -> list:
+        msg_list = []
+        if type(message_chain) is mirai.MessageChain:
+            msg_list = message_chain.__root__
+        elif type(message_chain) is list:
+            msg_list = message_chain
+        else:
+            raise Exception("Unknown message type: " + str(message_chain) + str(type(message_chain)))
+        
+        nakuru_msg_list = []
+        
+        # 遍历并转换
+        for component in msg_list:
+            if type(component) is mirai.Plain:
+                nakuru_msg_list.append(nkc.Plain(component.text, False))
+            elif type(component) is mirai.Image:
+                if component.url is not None:
+                    nakuru_msg_list.append(nkc.Image.fromURL(component.url))
+                elif component.base64 is not None:
+                    nakuru_msg_list.append(nkc.Image.fromBase64(component.base64))
+                elif component.path is not None:
+                    nakuru_msg_list.append(nkc.Image.fromFileSystem(component.path))
+            elif type(component) is mirai.Face:
+                nakuru_msg_list.append(nkc.Face(id=component.face_id))
+            elif type(component) is mirai.At:
+                nakuru_msg_list.append(nkc.At(qq=component.target))
+            elif type(component) is mirai.AtAll:
+                nakuru_msg_list.append(nkc.AtAll())
+            elif type(component) is mirai.Voice:
+                if component.url is not None:
+                    nakuru_msg_list.append(nkc.Record.fromURL(component.url))
+                elif component.path is not None:
+                    nakuru_msg_list.append(nkc.Record.fromFileSystem(component.path))
+            elif type(component) is Forward:
+                # 转发消息
+                yiri_forward_node_list = component.node_list
+                nakuru_forward_node_list = []
+
+                # 遍历并转换
+                for yiri_forward_node in yiri_forward_node_list:
+                    try:
+                        content_list = NakuruProjectMessageConverter.yiri2target(yiri_forward_node.message_chain)
+                        nakuru_forward_node = nkc.Node(
+                            name=yiri_forward_node.sender_name,
+                            uin=yiri_forward_node.sender_id,
+                            time=int(yiri_forward_node.time.timestamp()) if yiri_forward_node.time is not None else None,
+                            content=content_list
+                        )
+                        nakuru_forward_node_list.append(nakuru_forward_node)
+                    except Exception as e:
+                        import traceback
+                        traceback.print_exc()
+
+                nakuru_msg_list.append(nakuru_forward_node_list)
+            else:
+                nakuru_msg_list.append(nkc.Plain(str(component)))
+        
+        return nakuru_msg_list
+
+    @staticmethod
+    def target2yiri(message_chain: typing.Any, message_id: int = -1) -> mirai.MessageChain:
+        """将Yiri的消息链转换为YiriMirai的消息链"""
+        assert type(message_chain) is list
+
+        yiri_msg_list = []
+        import datetime
+        # 添加Source组件以标记message_id等信息
+        yiri_msg_list.append(mirai.models.message.Source(id=message_id, time=datetime.datetime.now()))
+        for component in message_chain:
+            if type(component) is nkc.Plain:
+                yiri_msg_list.append(mirai.Plain(text=component.text))
+            elif type(component) is nkc.Image:
+                yiri_msg_list.append(mirai.Image(url=component.url))
+            elif type(component) is nkc.Face:
+                yiri_msg_list.append(mirai.Face(face_id=component.id))
+            elif type(component) is nkc.At:
+                yiri_msg_list.append(mirai.At(target=component.qq))
+            elif type(component) is nkc.AtAll:
+                yiri_msg_list.append(mirai.AtAll())
+            else:
+                pass
+        logging.debug("转换后的消息链: " + str(yiri_msg_list))
+        chain = mirai.MessageChain(yiri_msg_list)
+        return chain
+
+
+class NakuruProjectEventConverter(EventConverter):
+    """事件转换器"""
+    @staticmethod
+    def yiri2target(event: typing.Type[mirai.Event]):
+        if event is mirai.GroupMessage:
+            return nakuru.GroupMessage
+        elif event is mirai.FriendMessage:
+            return nakuru.FriendMessage
+        else:
+            raise Exception("未支持转换的事件类型: " + str(event))
+
+    @staticmethod
+    def target2yiri(event: typing.Any) -> mirai.Event:
+        yiri_chain = NakuruProjectMessageConverter.target2yiri(event.message, event.message_id)
+        if type(event) is nakuru.FriendMessage:  # 私聊消息事件
+            return mirai.FriendMessage(
+                sender=mirai.models.entities.Friend(
+                    id=event.sender.user_id,
+                    nickname=event.sender.nickname,
+                    remark=event.sender.nickname
+                ),
+                message_chain=yiri_chain,
+                time=event.time
+            )
+        elif type(event) is nakuru.GroupMessage:  # 群聊消息事件
+            permission = "MEMBER"
+
+            if event.sender.role == "admin":
+                permission = "ADMINISTRATOR"
+            elif event.sender.role == "owner":
+                permission = "OWNER"
+
+            import mirai.models.entities as entities
+            return mirai.GroupMessage(
+                sender=mirai.models.entities.GroupMember(
+                    id=event.sender.user_id,
+                    member_name=event.sender.nickname,
+                    permission=permission,
+                    group=mirai.models.entities.Group(
+                        id=event.group_id,
+                        name=event.sender.nickname,
+                        permission=entities.Permission.Member
+                    ),
+                    special_title=event.sender.title,
+                    join_timestamp=0,
+                    last_speak_timestamp=0,
+                    mute_time_remaining=0,
+                ),
+                message_chain=yiri_chain,
+                time=event.time
+            )
+        else:
+            raise Exception("未支持转换的事件类型: " + str(event))
+
+
+class NakuruProjectAdapter(MessageSourceAdapter):
+    """nakuru-project适配器"""
+    bot: nakuru.CQHTTP
+    bot_account_id: int
+
+    message_converter: NakuruProjectMessageConverter = NakuruProjectMessageConverter()
+    event_converter: NakuruProjectEventConverter = NakuruProjectEventConverter()
+
+    listener_list: list[dict]
+
+    def __init__(self, cfg: dict):
+        """初始化nakuru-project的对象"""
+        self.bot = nakuru.CQHTTP(**cfg)
+        self.listener_list = []
+        # nakuru库有bug，这个接口没法带access_token，会失败
+        # 所以目前自行发请求
+        import config
+        import requests
+        resp = requests.get(
+            url="http://{}:{}/get_login_info".format(config.nakuru_config['host'], config.nakuru_config['http_port']),
+            headers={
+                'Authorization': "Bearer " + config.nakuru_config['token'] if 'token' in config.nakuru_config else ""
+            },
+            timeout=5
+        )
+        if resp.status_code == 403:
+            logging.error("go-cqhttp拒绝访问，请检查config.py中nakuru_config的token是否与go-cqhttp设置的access-token匹配")
+            raise Exception("go-cqhttp拒绝访问，请检查config.py中nakuru_config的token是否与go-cqhttp设置的access-token匹配")
+        self.bot_account_id = int(resp.json()['data']['user_id'])
+
+    def send_message(
+        self,
+        target_type: str,
+        target_id: str,
+        message: typing.Union[mirai.MessageChain, list],
+        converted: bool = False
+    ):
+        task = None
+
+        converted_msg = self.message_converter.yiri2target(message) if not converted else message
+        
+        # 检查是否有转发消息
+        has_forward = False
+        for msg in converted_msg:
+            if type(msg) is list:  # 转发消息，仅回复此消息组件
+                has_forward = True
+                converted_msg = msg
+                break
+        if has_forward:
+            if target_type == "group":
+                task = self.bot.sendGroupForwardMessage(int(target_id), converted_msg)
+            elif target_type == "person":
+                task = self.bot.sendPrivateForwardMessage(int(target_id), converted_msg)
+            else:
+                raise Exception("Unknown target type: " + target_type)
+        else:
+            if target_type == "group":
+                task = self.bot.sendGroupMessage(int(target_id), converted_msg)
+            elif target_type == "person":
+                task = self.bot.sendFriendMessage(int(target_id), converted_msg)
+            else:
+                raise Exception("Unknown target type: " + target_type)
+
+        asyncio.run(task)
+
+    def reply_message(
+        self,
+        message_source: mirai.MessageEvent,
+        message: mirai.MessageChain,
+        quote_origin: bool = False
+    ):
+        message = self.message_converter.yiri2target(message)
+        if quote_origin:
+            # 在前方添加引用组件
+            message.insert(0, nkc.Reply(
+                    id=message_source.message_chain.message_id,
+                )
+            )
+        if type(message_source) is mirai.GroupMessage:
+            self.send_message(
+                "group",
+                message_source.sender.group.id,
+                message,
+                converted=True
+            )
+        elif type(message_source) is mirai.FriendMessage:
+            self.send_message(
+                "person",
+                message_source.sender.id,
+                message,
+                converted=True
+            )
+        else:
+            raise Exception("Unknown message source type: " + str(type(message_source)))
+
+    def is_muted(self, group_id: int) -> bool:
+        import time
+        # 检查是否被禁言
+        group_member_info = asyncio.run(self.bot.getGroupMemberInfo(group_id, self.bot_account_id))
+        return group_member_info.shut_up_timestamp > int(time.time())
+
+    def register_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        try:
+            logging.debug("注册监听器: " + str(event_type) + " -> " + str(callback))
+
+            # 包装函数
+            async def listener_wrapper(app: nakuru.CQHTTP, source: self.event_converter.yiri2target(event_type)):
+                callback(self.event_converter.target2yiri(source))
+
+            # 将包装函数和原函数的对应关系存入列表
+            self.listener_list.append(
+                {
+                    "event_type": event_type,
+                    "callable": callback,
+                    "wrapper": listener_wrapper,
+                }
+            )
+
+            # 注册监听器
+            self.bot.receiver(self.event_converter.yiri2target(event_type).__name__)(listener_wrapper)
+            logging.debug("注册完成")
+        except Exception as e:
+            traceback.print_exc()
+            raise e
+
+    def unregister_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        nakuru_event_name = self.event_converter.yiri2target(event_type).__name__
+
+        new_event_list = []
+
+        # 从本对象的监听器列表中查找并删除
+        target_wrapper = None
+        for listener in self.listener_list:
+            if listener["event_type"] == event_type and listener["callable"] == callback:
+                target_wrapper = listener["wrapper"]
+                self.listener_list.remove(listener)
+                break
+
+        if target_wrapper is None:
+            raise Exception("未找到对应的监听器")
+
+        for func in self.bot.event[nakuru_event_name]:
+            if func.callable != target_wrapper:
+                new_event_list.append(func)
+
+        self.bot.event[nakuru_event_name] = new_event_list
+
+    def run_sync(self):
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        self.bot.run()
+
+    def kill(self) -> bool:
+        return False

pkg/qqbot/sources/yirimirai.py

@@ -0,0 +1,122 @@
+from ..adapter import MessageSourceAdapter
+import mirai
+import mirai.models.bus
+from mirai.bot import MiraiRunner
+
+import asyncio
+import typing
+
+
+class YiriMiraiAdapter(MessageSourceAdapter):
+    """YiriMirai适配器"""
+    bot: mirai.Mirai
+
+    def __init__(self, config: dict):
+        """初始化YiriMirai的对象"""
+        if 'adapter' not in config or \
+            config['adapter'] == 'WebSocketAdapter':
+            self.bot = mirai.Mirai(
+                qq=config['qq'],
+                adapter=mirai.WebSocketAdapter(
+                    host=config['host'],
+                    port=config['port'],
+                    verify_key=config['verifyKey']
+                )
+            )
+        elif config['adapter'] == 'HTTPAdapter':
+            self.bot = mirai.Mirai(
+                qq=config['qq'],
+                adapter=mirai.HTTPAdapter(
+                    host=config['host'],
+                    port=config['port'],
+                    verify_key=config['verifyKey']
+                )
+            )
+        else:
+            raise Exception('Unknown adapter for YiriMirai: ' + config['adapter'])
+    
+    def send_message(
+        self,
+        target_type: str,
+        target_id: str,
+        message: mirai.MessageChain
+    ):
+        """发送消息
+        
+        Args:
+            target_type (str): 目标类型，`person`或`group`
+            target_id (str): 目标ID
+            message (mirai.MessageChain): YiriMirai库的消息链
+        """
+        task = None
+        if target_type == 'person':
+            task = self.bot.send_friend_message(int(target_id), message)
+        elif target_type == 'group':
+            task = self.bot.send_group_message(int(target_id), message)
+        else:
+            raise Exception('Unknown target type: ' + target_type)
+
+        asyncio.run(task)
+
+    def reply_message(
+        self,
+        message_source: mirai.MessageEvent,
+        message: mirai.MessageChain,
+        quote_origin: bool = False
+    ):
+        """回复消息
+
+        Args:
+            message_source (mirai.MessageEvent): YiriMirai消息源事件
+            message (mirai.MessageChain): YiriMirai库的消息链
+            quote_origin (bool, optional): 是否引用原消息. Defaults to False.
+        """
+        asyncio.run(self.bot.send(message_source, message, quote_origin))
+
+    def is_muted(self, group_id: int) -> bool:
+        result = self.bot.member_info(target=group_id, member_id=self.bot.qq).get()
+        result = asyncio.run(result)
+        if result.mute_time_remaining > 0:
+            return True
+        return False
+
+    def register_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        """注册事件监听器
+        
+        Args:
+            event_type (typing.Type[mirai.Event]): YiriMirai事件类型
+            callback (typing.Callable[[mirai.Event], None]): 回调函数，接收一个参数，为YiriMirai事件
+        """
+        self.bot.on(event_type)(callback)
+
+    def unregister_listener(
+        self,
+        event_type: typing.Type[mirai.Event],
+        callback: typing.Callable[[mirai.Event], None]
+    ):
+        """注销事件监听器
+        
+        Args:
+            event_type (typing.Type[mirai.Event]): YiriMirai事件类型
+            callback (typing.Callable[[mirai.Event], None]): 回调函数，接收一个参数，为YiriMirai事件
+        """
+        assert isinstance(self.bot, mirai.Mirai)
+        bus = self.bot.bus
+        assert isinstance(bus, mirai.models.bus.ModelEventBus)
+        
+        bus.unsubscribe(event_type, callback)
+
+    def run_sync(self):
+        """运行YiriMirai"""
+
+        # 创建新的
+        loop = asyncio.new_event_loop()
+
+        loop.run_until_complete(MiraiRunner(self.bot)._run())
+
+    def kill(self) -> bool:
+        return False

pkg/utils/__init__.py

@@ -0,0 +1 @@
+from .threadctl import ThreadCtl

pkg/utils/announcement.py

@@ -0,0 +1,68 @@
+import base64
+import os
+import json
+
+import requests
+
+
+def read_latest() -> list:
+    import pkg.utils.network as network
+    resp = requests.get(
+        url="https://api.github.com/repos/RockChinQ/QChatGPT/contents/res/announcement.json",
+        proxies=network.wrapper_proxies()
+    )
+    obj_json = resp.json()
+    b64_content = obj_json["content"]
+    # 解码
+    content = base64.b64decode(b64_content).decode("utf-8")
+    return json.loads(content)
+
+
+def read_saved() -> list:
+    # 已保存的在res/announcement_saved
+    # 检查是否存在
+    if not os.path.exists("res/announcement_saved.json"):
+        with open("res/announcement_saved.json", "w", encoding="utf-8") as f:
+            f.write("[]")
+
+    with open("res/announcement_saved.json", "r", encoding="utf-8") as f:
+        content = f.read()
+
+    return json.loads(content)
+
+
+def write_saved(content: list):
+    # 已保存的在res/announcement_saved
+    with open("res/announcement_saved.json", "w", encoding="utf-8") as f:
+        f.write(json.dumps(content, indent=4, ensure_ascii=False))
+
+
+def fetch_new() -> list:
+    latest = read_latest()
+    saved = read_saved()
+
+    to_show: list = []
+
+    for item in latest:
+        # 遍历saved检查是否有相同id的公告
+        for saved_item in saved:
+            if saved_item["id"] == item["id"]:
+                break
+        else:
+            # 没有相同id的公告
+            to_show.append(item)
+
+    write_saved(latest)
+    return to_show
+
+
+if __name__ == '__main__':
+    
+    resp = requests.get(
+        url="https://api.github.com/repos/RockChinQ/QChatGPT/contents/res/announcement.json",
+    )
+    obj_json = resp.json()
+    b64_content = obj_json["content"]
+    # 解码
+    content = base64.b64decode(b64_content).decode("utf-8")
+    print(json.dumps(json.loads(content), indent=4, ensure_ascii=False))

pkg/utils/context.py

@@ -1,50 +1,94 @@
+import threading
+from pkg.utils import ThreadCtl
+
+
 context = {
     'inst': {
         'database.manager.DatabaseManager': None,
         'openai.manager.OpenAIInteract': None,
         'qqbot.manager.QQBotManager': None,
     },
+    'pool_ctl': None,
     'logger_handler': None,
     'config': None,
     'plugin_host': None,
 }
+context_lock = threading.Lock()
 
-
+### context耦合度非常高，需要大改 ###
 def set_config(inst):
+    context_lock.acquire()
     context['config'] = inst
+    context_lock.release()
 
 
 def get_config():
-    return context['config']
+    context_lock.acquire()
+    t = context['config']
+    context_lock.release()
+    return t
 
 
 def set_database_manager(inst):
+    context_lock.acquire()
     context['inst']['database.manager.DatabaseManager'] = inst
+    context_lock.release()
 
 
 def get_database_manager():
-    return context['inst']['database.manager.DatabaseManager']
+    context_lock.acquire()
+    t = context['inst']['database.manager.DatabaseManager']
+    context_lock.release()
+    return t
 
 
 def set_openai_manager(inst):
+    context_lock.acquire()
     context['inst']['openai.manager.OpenAIInteract'] = inst
+    context_lock.release()
 
 
 def get_openai_manager():
-    return context['inst']['openai.manager.OpenAIInteract']
+    context_lock.acquire()
+    t = context['inst']['openai.manager.OpenAIInteract']
+    context_lock.release()
+    return t
 
 
 def set_qqbot_manager(inst):
+    context_lock.acquire()
     context['inst']['qqbot.manager.QQBotManager'] = inst
+    context_lock.release()
 
 
 def get_qqbot_manager():
-    return context['inst']['qqbot.manager.QQBotManager']
+    context_lock.acquire()
+    t = context['inst']['qqbot.manager.QQBotManager']
+    context_lock.release()
+    return t
 
 
 def set_plugin_host(inst):
+    context_lock.acquire()
     context['plugin_host'] = inst
+    context_lock.release()
 
 
 def get_plugin_host():
-    return context['plugin_host']
+    context_lock.acquire()
+    t = context['plugin_host']
+    context_lock.release()
+    return t
+
+
+def set_thread_ctl(inst):
+    context_lock.acquire()
+    context['pool_ctl'] = inst
+    context_lock.release()
+
+
+def get_thread_ctl() -> ThreadCtl:
+    context_lock.acquire()
+    t: ThreadCtl = context['pool_ctl']
+    context_lock.release()
+    return t

pkg/utils/credit.py

@@ -1,13 +1,19 @@
 # OpenAI账号免费额度剩余查询
 import requests
 
-
-def fetch_credit_data(api_key: str) -> dict:
+def fetch_credit_data(api_key: str, http_proxy: str) -> dict:
     """OpenAI账号免费额度剩余查询"""
+    proxies = {
+        "http":http_proxy,
+        "https":http_proxy
+    } if http_proxy is not None else None
+
     resp = requests.get(
         url="https://api.openai.com/dashboard/billing/credit_grants",
         headers={
             "Authorization": "Bearer {}".format(api_key),
-        }
+        },
+        proxies=proxies
     )
+
     return resp.json()

pkg/utils/log.py

@@ -0,0 +1,66 @@
+import os
+import time
+import logging
+import shutil
+
+
+log_file_name = "qchatgpt.log"
+
+
+log_colors_config = {
+    'DEBUG': 'green',  # cyan white
+    'INFO': 'white',
+    'WARNING': 'yellow',
+    'ERROR': 'red',
+    'CRITICAL': 'cyan',
+}
+
+
+def init_runtime_log_file():
+    """为此次运行生成日志文件
+    格式: qchatgpt-yyyy-MM-dd-HH-mm-ss.log
+    """
+    global log_file_name
+
+    # 检查logs目录是否存在
+    if not os.path.exists("logs"):
+        os.mkdir("logs")
+
+    # 检查本目录是否有qchatgpt.log，若有，移动到logs目录
+    if os.path.exists("qchatgpt.log"):
+        shutil.move("qchatgpt.log", "logs/qchatgpt.legacy.log")
+
+    log_file_name = "logs/qchatgpt-%s.log" % time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+    
+
+def reset_logging():
+    global log_file_name
+
+    import config
+    import pkg.utils.context
+    import colorlog
+
+    if pkg.utils.context.context['logger_handler'] is not None:
+        logging.getLogger().removeHandler(pkg.utils.context.context['logger_handler'])
+
+    for handler in logging.getLogger().handlers:
+        logging.getLogger().removeHandler(handler)
+
+    logging.basicConfig(level=config.logging_level,  # 设置日志输出格式
+                        filename=log_file_name,  # log日志输出的文件位置和文件名
+                        format="[%(asctime)s.%(msecs)03d] %(pathname)s (%(lineno)d) - [%(levelname)s] :\n%(message)s",
+                        # 日志输出的格式
+                        # -8表示占位符，让输出左对齐，输出长度都为8位
+                        datefmt="%Y-%m-%d %H:%M:%S"  # 时间输出的格式
+                        )
+    sh = logging.StreamHandler()
+    sh.setLevel(config.logging_level)
+    sh.setFormatter(colorlog.ColoredFormatter(
+        fmt="%(log_color)s[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : "
+            "%(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+        log_colors=log_colors_config
+    ))
+    logging.getLogger().addHandler(sh)
+    pkg.utils.context.context['logger_handler'] = sh
+    return sh

pkg/utils/network.py

@@ -0,0 +1,9 @@
+
+def wrapper_proxies() -> dict:
+    """获取代理"""
+    import config
+
+    return {
+        "http": config.openai_config['proxy'],
+        "https": config.openai_config['proxy']
+    } if 'proxy' in config.openai_config and (config.openai_config['proxy'] is not None) else None

pkg/utils/pkgmgr.py

@@ -1,16 +1,25 @@
 from pip._internal import main as pipmain
 
-import main
+import pkg.utils.log as log
 
 
 def install(package):
     pipmain(['install', package])
-    main.reset_logging()
+    log.reset_logging()
+
+def install_upgrade(package):
+    pipmain(['install', '--upgrade', package])
+    log.reset_logging()
+
+
+def run_pip(params: list):
+    pipmain(params)
+    log.reset_logging()
 
 
 def install_requirements(file):
     pipmain(['install', '-r', file, "--upgrade"])
-    main.reset_logging()
+    log.reset_logging()
 
 
 def ensure_dulwich():

pkg/utils/reloader.py

@@ -3,46 +3,67 @@ import threading
 
 import importlib
 import pkgutil
-import pkg.utils.context
+import pkg.utils.context as context
 import pkg.plugin.host
 
 
-def walk(module, prefix=''):
+def walk(module, prefix='', path_prefix=''):
     """遍历并重载所有模块"""
     for item in pkgutil.iter_modules(module.__path__):
         if item.ispkg:
-            walk(__import__(module.__name__ + '.' + item.name, fromlist=['']), prefix + item.name + '.')
+
+            walk(__import__(module.__name__ + '.' + item.name, fromlist=['']), prefix + item.name + '.', path_prefix + item.name + '/')
         else:
-            logging.info('reload module: {}'.format(prefix + item.name))
+            logging.info('reload module: {}, path: {}'.format(prefix + item.name, path_prefix + item.name + '.py'))
+            pkg.plugin.host.__current_module_path__ = "plugins/" + path_prefix + item.name + '.py'
             importlib.reload(__import__(module.__name__ + '.' + item.name, fromlist=['']))
 
 
 def reload_all(notify=True):
     # 解除bot的事件注册
     import pkg
-    pkg.utils.context.get_qqbot_manager().unsubscribe_all()
+    context.get_qqbot_manager().unsubscribe_all()
     # 执行关闭流程
     logging.info("执行程序关闭流程")
     import main
     main.stop()
 
+    # 删除所有已注册的指令
+    import pkg.qqbot.cmds.aamgr as cmdsmgr
+    cmdsmgr.__command_list__ = {}
+    cmdsmgr.__tree_index__ = {}
+
     # 重载所有模块
-    pkg.utils.context.context['exceeded_keys'] = pkg.utils.context.get_openai_manager().key_mgr.exceeded
-    context = pkg.utils.context.context
+    context.context['exceeded_keys'] = context.get_openai_manager().key_mgr.exceeded
+    this_context = context.context
     walk(pkg)
+    importlib.reload(__import__("config-template"))
     importlib.reload(__import__('config'))
     importlib.reload(__import__('main'))
     importlib.reload(__import__('banlist'))
-    pkg.utils.context.context = context
+    importlib.reload(__import__('tips'))
+    context.context = this_context
 
     # 重载插件
     import plugins
     walk(plugins)
 
+    # 初始化相关文件
+    main.check_file()
+
     # 执行启动流程
     logging.info("执行程序启动流程")
-    threading.Thread(target=main.main, args=(False,), daemon=False).start()
+    main.load_config()
+    main.complete_tips()
+    context.get_thread_ctl().reload(
+        admin_pool_num=context.get_config().admin_pool_num,
+        user_pool_num=context.get_config().user_pool_num
+    )
+    context.get_thread_ctl().submit_sys_task(
+        main.start,
+        False
+    )
 
     logging.info('程序启动完成')
     if notify:
-        pkg.utils.context.get_qqbot_manager().notify_admin("重载完成")
+        context.get_qqbot_manager().notify_admin("重载完成")

pkg/utils/text2img.py

@@ -0,0 +1,193 @@
+import logging
+
+from PIL import Image, ImageDraw, ImageFont
+import re
+import os
+import config
+import traceback
+
+text_render_font: ImageFont = None
+
+if config.blob_message_strategy == "image":  # 仅在启用了image时才加载字体
+    use_font = config.font_path
+    try:
+
+        # 检查是否存在
+        if not os.path.exists(use_font):
+            # 若是windows系统，使用微软雅黑
+            if os.name == "nt":
+                use_font = "C:/Windows/Fonts/msyh.ttc"
+                if not os.path.exists(use_font):
+                    logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
+                    config.blob_message_strategy = "forward"
+                else:
+                    logging.info("使用Windows自带字体：" + use_font)
+                    text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
+            else:
+                logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
+                config.blob_message_strategy = "forward"
+        else:
+            text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
+    except:
+        traceback.print_exc()
+        logging.error("加载字体文件失败({})，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。".format(use_font))
+        config.blob_message_strategy = "forward"
+
+
+def indexNumber(path=''):
+    """
+    查找字符串中数字所在串中的位置
+    :param path:目标字符串
+    :return:<class 'list'>: <class 'list'>: [['1', 16], ['2', 35], ['1', 51]]
+    """
+    kv = []
+    nums = []
+    beforeDatas = re.findall('[\d]+', path)
+    for num in beforeDatas:
+        indexV = []
+        times = path.count(num)
+        if times > 1:
+            if num not in nums:
+                indexs = re.finditer(num, path)
+                for index in indexs:
+                    iV = []
+                    i = index.span()[0]
+                    iV.append(num)
+                    iV.append(i)
+                    kv.append(iV)
+            nums.append(num)
+        else:
+            index = path.find(num)
+            indexV.append(num)
+            indexV.append(index)
+            kv.append(indexV)
+    # 根据数字位置排序
+    indexSort = []
+    resultIndex = []
+    for vi in kv:
+        indexSort.append(vi[1])
+    indexSort.sort()
+    for i in indexSort:
+        for v in kv:
+            if i == v[1]:
+                resultIndex.append(v)
+    return resultIndex
+
+
+def get_size(file):
+    # 获取文件大小:KB
+    size = os.path.getsize(file)
+    return size / 1024
+
+
+def get_outfile(infile, outfile):
+    if outfile:
+        return outfile
+    dir, suffix = os.path.splitext(infile)
+    outfile = '{}-out{}'.format(dir, suffix)
+    return outfile
+
+
+def compress_image(infile, outfile='', kb=100, step=20, quality=90):
+    """不改变图片尺寸压缩到指定大小
+    :param infile: 压缩源文件
+    :param outfile: 压缩文件保存地址
+    :param mb: 压缩目标,KB
+    :param step: 每次调整的压缩比率
+    :param quality: 初始压缩比率
+    :return: 压缩文件地址，压缩文件大小
+    """
+    o_size = get_size(infile)
+    if o_size <= kb:
+        return infile, o_size
+    outfile = get_outfile(infile, outfile)
+    while o_size > kb:
+        im = Image.open(infile)
+        im.save(outfile, quality=quality)
+        if quality - step < 0:
+            break
+        quality -= step
+        o_size = get_size(outfile)
+    return outfile, get_size(outfile)
+
+
+def text_to_image(text_str: str, save_as="temp.png", width=800):
+    global text_render_font
+
+    text_str = text_str.replace("\t", "    ")
+    
+    # 分行
+    lines = text_str.split('\n')
+
+    # 计算并分割
+    final_lines = []
+
+    text_width = width-80
+    for line in lines:
+        # 如果长了就分割
+        line_width = text_render_font.getlength(line)
+        if line_width < text_width:
+            final_lines.append(line)
+            continue
+        else:
+            rest_text = line
+            while True:
+                # 分割最前面的一行
+                point = int(len(rest_text) * (text_width / line_width))
+
+                # 检查断点是否在数字中间
+                numbers = indexNumber(rest_text)
+
+                for number in numbers:
+                    if number[1] < point < number[1] + len(number[0]) and number[1] != 0:
+                        point = number[1]
+                        break
+
+                final_lines.append(rest_text[:point])
+                rest_text = rest_text[point:]
+                line_width = text_render_font.getlength(rest_text)
+                if line_width < text_width:
+                    final_lines.append(rest_text)
+                    break
+                else:
+                    continue
+    # 准备画布
+    img = Image.new('RGBA', (width, max(280, len(final_lines) * 35 + 65)), (255, 255, 255, 255))
+    draw = ImageDraw.Draw(img, mode='RGBA')
+
+    
+    # 绘制正文
+    line_number = 0
+    offset_x = 20
+    offset_y = 30
+    for final_line in final_lines:
+        draw.text((offset_x, offset_y + 35 * line_number), final_line, fill=(0, 0, 0), font=text_render_font)
+        # 遍历此行,检查是否有emoji
+        idx_in_line = 0
+        for ch in final_line:
+            # if self.is_emoji(ch):
+            #     emoji_img_valid = ensure_emoji(hex(ord(ch))[2:])
+            #     if emoji_img_valid:  # emoji图像可用,绘制到指定位置
+            #         emoji_image = Image.open("emojis/{}.png".format(hex(ord(ch))[2:]), mode='r').convert('RGBA')
+            #         emoji_image = emoji_image.resize((32, 32))
+
+            #         x, y = emoji_image.size
+
+            #         final_emoji_img = Image.new('RGBA', emoji_image.size, (255, 255, 255))
+            #         final_emoji_img.paste(emoji_image, (0, 0, x, y), emoji_image)
+
+            #         img.paste(final_emoji_img, box=(int(offset_x + idx_in_line * 32), offset_y + 35 * line_number))
+
+            # 检查字符占位宽
+            char_code = ord(ch)
+            if char_code >= 127:
+                idx_in_line += 1
+            else:
+                idx_in_line += 0.5
+
+        line_number += 1
+
+    
+    img.save(save_as)
+
+    return save_as

pkg/utils/threadctl.py

@@ -0,0 +1,93 @@
+import threading
+import time
+from concurrent.futures import ThreadPoolExecutor
+
+
+class Pool:
+    """线程池结构"""
+    pool_num:int = None
+    ctl:ThreadPoolExecutor = None
+    task_list:list = None
+    task_list_lock:threading.Lock = None
+    monitor_type = True
+
+    def __init__(self, pool_num):
+        self.pool_num = pool_num
+        self.ctl = ThreadPoolExecutor(max_workers = self.pool_num)
+        self.task_list = []
+        self.task_list_lock = threading.Lock()
+    
+    def __thread_monitor__(self):
+        while self.monitor_type:
+            for t in self.task_list:
+                if not t.done():
+                    continue
+                try:
+                    self.task_list.pop(self.task_list.index(t))
+                except:
+                    continue
+            time.sleep(1)
+
+
+class ThreadCtl:
+    def __init__(self, sys_pool_num, admin_pool_num, user_pool_num):
+        """线程池控制类
+        sys_pool_num：分配系统使用的线程池数量(>=8)
+        admin_pool_num：用于处理管理员消息的线程池数量(>=1)
+        user_pool_num：分配用于处理用户消息的线程池的数量(>=1)
+        """
+        if sys_pool_num < 5:
+            raise Exception("Too few system threads(sys_pool_num needs >= 8, but received {})".format(sys_pool_num))
+        if admin_pool_num < 1:
+            raise Exception("Too few admin threads(admin_pool_num needs >= 1, but received {})".format(admin_pool_num))
+        if user_pool_num < 1:
+            raise Exception("Too few user threads(user_pool_num needs >= 1, but received {})".format(admin_pool_num))
+        self.__sys_pool__ = Pool(sys_pool_num)
+        self.__admin_pool__ = Pool(admin_pool_num)
+        self.__user_pool__ = Pool(user_pool_num)
+        self.submit_sys_task(self.__sys_pool__.__thread_monitor__)
+        self.submit_sys_task(self.__admin_pool__.__thread_monitor__)
+        self.submit_sys_task(self.__user_pool__.__thread_monitor__)
+
+    def __submit__(self, pool: Pool, fn, /, *args, **kwargs ):
+        t = pool.ctl.submit(fn, *args, **kwargs)
+        pool.task_list_lock.acquire()
+        pool.task_list.append(t)
+        pool.task_list_lock.release()
+        return t
+
+    def submit_sys_task(self, fn, /, *args, **kwargs):
+        return self.__submit__(
+            self.__sys_pool__,
+            fn, *args, **kwargs
+        )
+
+    def submit_admin_task(self, fn, /, *args, **kwargs):
+        return self.__submit__(
+            self.__admin_pool__,
+            fn, *args, **kwargs
+        )
+
+    def submit_user_task(self, fn, /, *args, **kwargs):
+        return self.__submit__(
+            self.__user_pool__,
+            fn, *args, **kwargs
+        )
+
+    def shutdown(self):
+        self.__user_pool__.ctl.shutdown(cancel_futures=True)
+        self.__user_pool__.monitor_type = False
+        self.__admin_pool__.ctl.shutdown(cancel_futures=True)
+        self.__admin_pool__.monitor_type = False
+        self.__sys_pool__.monitor_type = False
+        self.__sys_pool__.ctl.shutdown(wait=True, cancel_futures=False)
+
+    def reload(self, admin_pool_num, user_pool_num):
+        self.__user_pool__.ctl.shutdown(cancel_futures=True)
+        self.__user_pool__.monitor_type = False
+        self.__admin_pool__.ctl.shutdown(cancel_futures=True)
+        self.__admin_pool__.monitor_type = False
+        self.__admin_pool__ = Pool(admin_pool_num)
+        self.__user_pool__ = Pool(user_pool_num)
+        self.submit_sys_task(self.__admin_pool__.__thread_monitor__)
+        self.submit_sys_task(self.__user_pool__.__thread_monitor__)

pkg/utils/updater.py

@@ -1,6 +1,12 @@
 import datetime
+import logging
+import os.path
 
-import pkg.utils.context
+import requests
+import json
+
+import pkg.utils.constants
+import pkg.utils.network as network
 
 
 def check_dulwich_closure():
@@ -28,34 +34,180 @@ def pull_latest(repo_path: str) -> bool:
     return True
 
 
-def update_all() -> bool:
-    """使用dulwich更新源码"""
-    check_dulwich_closure()
-    import dulwich
-    try:
-        before_commit_id = get_current_commit_id()
-        from dulwich import porcelain
-        repo = porcelain.open_repo('.')
-        porcelain.pull(repo)
+def is_newer(new_tag: str, old_tag: str):
+    """判断版本是否更新，忽略第四位版本和第一位版本"""
+    if new_tag == old_tag:
+        return False
 
-        change_log = ""
+    new_tag = new_tag.split(".")
+    old_tag = old_tag.split(".")
+    
+    # 判断主版本是否相同
+    if new_tag[0] != old_tag[0]:
+        return False
 
-        for entry in repo.get_walker():
-            if str(entry.commit.id)[2:-1] == before_commit_id:
-                break
-            tz = datetime.timezone(datetime.timedelta(hours=entry.commit.commit_timezone // 3600))
-            dt = datetime.datetime.fromtimestamp(entry.commit.commit_time, tz)
-            change_log += dt.strftime('%Y-%m-%d %H:%M:%S') + " [" + str(entry.commit.message, encoding="utf-8").strip()+"]\n"
+    if len(new_tag) < 4:
+        return True
 
-        if change_log != "":
-            pkg.utils.context.get_qqbot_manager().notify_admin("代码拉取完成,更新内容如下:\n"+change_log)
-            return True
-        else:
-            return False
-    except ModuleNotFoundError:
-        raise Exception("dulwich模块未安装,请查看 https://github.com/RockChinQ/QChatGPT/issues/77")
-    except dulwich.porcelain.DivergedBranches:
-        raise Exception("分支不一致,自动更新仅支持master分支,请手动更新(https://github.com/RockChinQ/QChatGPT/issues/76)")
+    # 合成前三段，判断是否相同
+    new_tag = ".".join(new_tag[:3])
+    old_tag = ".".join(old_tag[:3])
+
+    return new_tag != old_tag
+
+
+def get_release_list() -> list:
+    """获取发行列表"""
+    rls_list_resp = requests.get(
+        url="https://api.github.com/repos/RockChinQ/QChatGPT/releases",
+        proxies=network.wrapper_proxies()
+    )
+
+    rls_list = rls_list_resp.json()
+
+    return rls_list
+
+
+def get_current_tag() -> str:
+    """获取当前tag"""
+    current_tag = pkg.utils.constants.semantic_version
+    if os.path.exists("current_tag"):
+        with open("current_tag", "r") as f:
+            current_tag = f.read()
+
+    return current_tag
+
+
+def compare_version_str(v0: str, v1: str) -> int:
+    """比较两个版本号"""
+
+    # 删除版本号前的v
+    if v0.startswith("v"):
+        v0 = v0[1:]
+    if v1.startswith("v"):
+        v1 = v1[1:]
+
+    v0:list = v0.split(".")
+    v1:list = v1.split(".")
+
+    # 如果两个版本号节数不同，把短的后面用0补齐
+    if len(v0) < len(v1):
+        v0.extend(["0"]*(len(v1)-len(v0)))
+    elif len(v0) > len(v1):
+        v1.extend(["0"]*(len(v0)-len(v1)))
+
+    # 从高位向低位比较
+    for i in range(len(v0)):
+        if int(v0[i]) > int(v1[i]):
+            return 1
+        elif int(v0[i]) < int(v1[i]):
+            return -1
+    
+    return 0
+
+
+def update_all(cli: bool = False) -> bool:
+    """检查更新并下载源码"""
+    current_tag = get_current_tag()
+
+    rls_list = get_release_list()
+
+    latest_rls = {}
+    rls_notes = []
+    latest_tag_name = ""
+    for rls in rls_list:
+        rls_notes.append(rls['name'])  # 使用发行名称作为note
+        if latest_tag_name == "":
+            latest_tag_name = rls['tag_name']
+
+        if rls['tag_name'] == current_tag:
+            break
+
+        if latest_rls == {}:
+            latest_rls = rls
+    if not cli:
+        logging.info("更新日志: {}".format(rls_notes))
+    else:
+        print("更新日志: {}".format(rls_notes))
+
+    if latest_rls == {} and not is_newer(latest_tag_name, current_tag):  # 没有新版本
+        return False
+
+    # 下载最新版本的zip到temp目录
+    if not cli:
+        logging.info("开始下载最新版本: {}".format(latest_rls['zipball_url']))
+    else:
+        print("开始下载最新版本: {}".format(latest_rls['zipball_url']))
+    zip_url = latest_rls['zipball_url']
+    zip_resp = requests.get(
+        url=zip_url,
+        proxies=network.wrapper_proxies()
+    )
+    zip_data = zip_resp.content
+
+    # 检查temp/updater目录
+    if not os.path.exists("temp"):
+        os.mkdir("temp")
+    if not os.path.exists("temp/updater"):
+        os.mkdir("temp/updater")
+    with open("temp/updater/{}.zip".format(latest_rls['tag_name']), "wb") as f:
+        f.write(zip_data)
+
+    if not cli:
+        logging.info("下载最新版本完成: {}".format("temp/updater/{}.zip".format(latest_rls['tag_name'])))
+    else:
+        print("下载最新版本完成: {}".format("temp/updater/{}.zip".format(latest_rls['tag_name'])))
+
+    # 解压zip到temp/updater/<tag_name>/
+    import zipfile
+    # 检查目标文件夹
+    if os.path.exists("temp/updater/{}".format(latest_rls['tag_name'])):
+        import shutil
+        shutil.rmtree("temp/updater/{}".format(latest_rls['tag_name']))
+    os.mkdir("temp/updater/{}".format(latest_rls['tag_name']))
+    with zipfile.ZipFile("temp/updater/{}.zip".format(latest_rls['tag_name']), 'r') as zip_ref:
+        zip_ref.extractall("temp/updater/{}".format(latest_rls['tag_name']))
+
+    # 覆盖源码
+    source_root = ""
+    # 找到temp/updater/<tag_name>/中的第一个子目录路径
+    for root, dirs, files in os.walk("temp/updater/{}".format(latest_rls['tag_name'])):
+        if root != "temp/updater/{}".format(latest_rls['tag_name']):
+            source_root = root
+            break
+
+    # 覆盖源码
+    import shutil
+    for root, dirs, files in os.walk(source_root):
+        # 覆盖所有子文件子目录
+        for file in files:
+            src = os.path.join(root, file)
+            dst = src.replace(source_root, ".")
+            if os.path.exists(dst):
+                os.remove(dst)
+
+            # 检查目标文件夹是否存在
+            if not os.path.exists(os.path.dirname(dst)):
+                os.makedirs(os.path.dirname(dst))
+            # 检查目标文件是否存在
+            if not os.path.exists(dst):
+                # 创建目标文件
+                open(dst, "w").close()
+
+            shutil.copy(src, dst)
+
+    # 把current_tag写入文件
+    current_tag = latest_rls['tag_name']
+    with open("current_tag", "w") as f:
+        f.write(current_tag)
+
+    # 通知管理员
+    if not cli:
+        import pkg.utils.context
+        pkg.utils.context.get_qqbot_manager().notify_admin("已更新到最新版本: {}\n更新日志:\n{}\n完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes[:-1])))
+    else:
+        print("已更新到最新版本: {}\n更新日志:\n{}\n完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes[:-1])))
+    return True
 
 
 def is_repo(path: str) -> bool:
@@ -81,24 +233,12 @@ def get_remote_url(repo_path: str) -> str:
 
 def get_current_version_info() -> str:
     """获取当前版本信息"""
-    check_dulwich_closure()
-
-    from dulwich import porcelain
-
-    repo = porcelain.open_repo('.')
-
-    version_str = ""
-
-    for entry in repo.get_walker():
-        version_str += "提交编号: "+str(entry.commit.id)[2:9] + "\n"
-        tz = datetime.timezone(datetime.timedelta(hours=entry.commit.commit_timezone // 3600))
-        dt = datetime.datetime.fromtimestamp(entry.commit.commit_time, tz)
-        version_str += "时间: "+dt.strftime('%m-%d %H:%M:%S') + "\n"
-        version_str += "说明: "+str(entry.commit.message, encoding="utf-8").strip() + "\n"
-        version_str += "提交作者: '" + str(entry.commit.author)[2:-1] + "'"
-        break
-
-    return version_str
+    rls_list = get_release_list()
+    current_tag = get_current_tag()
+    for rls in rls_list:
+        if rls['tag_name'] == current_tag:
+            return rls['name'] + "\n" + rls['body']
+    return "未知版本"
 
 
 def get_commit_id_and_time_and_msg() -> str:
@@ -132,15 +272,44 @@ def get_current_commit_id() -> str:
 
 def is_new_version_available() -> bool:
     """检查是否有新版本"""
-    check_dulwich_closure()
+    # 从github获取release列表
+    rls_list = get_release_list()
+    if rls_list is None:
+        return False
 
-    from dulwich import porcelain
+    # 获取当前版本
+    current_tag = get_current_tag()
 
-    repo = porcelain.open_repo('.')
-    fetch_res = porcelain.ls_remote(porcelain.get_remote_repo(repo, "origin")[1])
+    # 检查是否有新版本
+    latest_tag_name = ""
+    for rls in rls_list:
+        if latest_tag_name == "":
+            latest_tag_name = rls['tag_name']
+            break
 
-    current_commit_id = get_current_commit_id()
+    return is_newer(latest_tag_name, current_tag)
 
-    latest_commit_id = str(fetch_res[b'HEAD'])[2:-1]
 
-    return current_commit_id != latest_commit_id
+def get_rls_notes() -> list:
+    """获取更新日志"""
+    # 从github获取release列表
+    rls_list = get_release_list()
+    if rls_list is None:
+        return None
+
+    # 获取当前版本
+    current_tag = get_current_tag()
+
+    # 检查是否有新版本
+    rls_notes = []
+    for rls in rls_list:
+        if rls['tag_name'] == current_tag:
+            break
+
+        rls_notes.append(rls['name'])
+
+    return rls_notes
+
+
+if __name__ == "__main__":
+    update_all()

requirements.txt

@@ -1,9 +1,12 @@
-requests~=2.28.1
-openai~=0.27.0
-pip~=22.3.1
-dulwich~=0.21.3
+requests~=2.31.0
+openai~=0.27.8
+dulwich~=0.21.5
 colorlog~=6.6.0
-yiri-mirai~=0.2.6.1
-websockets~=10.4
+yiri-mirai
+websockets
 urllib3~=1.26.10
-func_timeout~=4.3.5
+func_timeout~=4.3.5
+Pillow
+nakuru-project-idk
+CallingGPT
+tiktoken

res/announcement

@@ -0,0 +1 @@
+2023/3/31 21:35 【插件兼容性问题】若您使用了revLibs插件，并将主程序升级到了v2.3.0，请立即使用管理员账号向机器人账号发送!plugin update命令更新逆向库插件，以解决由于情景预设重构引起的兼容性问题。

res/announcement.json

@@ -0,0 +1,8 @@
+[
+    {
+        "id": 2,
+        "time": "2023-08-01 10:49:26",
+        "timestamp": 1690858166,
+        "content": "现已支持GPT函数调用功能，欢迎了解：https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0"
+    }
+]

res/docs/docker_deploy.md

@@ -0,0 +1,95 @@
+
+
+## 操作步骤
+
+### 1.安装docker和docker compose
+
+[各种设备的安装Docker方法](https://yeasy.gitbook.io/docker_practice/install)
+
+[安装Compose方法](https://yeasy.gitbook.io/docker_practice/compose)
+
+> `Docker Desktop for Mac/Windows` 自带 `docker-compose` 二进制文件，安装 Docker 之后可以直接使用。
+>
+> 可以选择很多下载方法,反正只要安装了就可以了
+
+### 2. 登录qq(下面所有步骤建议在项目文件夹下操作)
+
+#### 2.1 输入指令
+
+```
+docker run -d -it --name mcl --network host -v ${PWD}/qq/plugins:/app/plugins -v ${PWD}/qq/config:/app/config -v   ${PWD}/qq/data:/app/data -v ${PWD}/qq/bots:/app/bots --restart unless-stopped kagurazakanyaa/mcl:latest
+```
+
+这里使用了[KagurazakaNyaa/mirai-console-loader-docker](https://github.com/KagurazakaNyaa/mirai-console-loader-docker)的镜像
+
+#### 2.2 进入容器
+
+```
+docker ps
+```
+在输出中查看容器的ID，例如：
+```sh
+CONTAINER ID   IMAGE                COMMAND      CREATED          STATUS          PORTS                                       NAMES
+bce1e5568f46   kagurazakanyaa/mcl   "./mcl -u"   10 minutes ago   Up 10 minutes   0.0.0.0:8080->8080/tcp, :::8080->8080/tcp   admiring_mendeleev
+```
+查看`IMAGE`名为`kagurazakanyaa/mcl`的容器的`CONTAINER ID`，在这里是`bce1e5568f46`，于是使用以下命令将其切到前台：
+```
+docker attach bce1e5568f46
+```
+如需将其切到后台运行，请使用组合键`Ctrl+P+Q`
+
+#### 2.3 编写配置文件
+
+- 在` /qq/config/net.mamoe.mirai-api-http` 文件夹中找到`setting.yml`，这是`mirai-api-http`的配置文件
+  - 将这个文件的内容修改为：
+
+```
+adapters:
+  - ws
+debug: true
+enableVerify: true
+verifyKey: yirimirai
+singleMode: false
+cacheSize: 4096
+adapterSettings:
+  ws:
+    host: localhost
+    port: 8080
+    reservedSyncId: -1
+```
+
+`verifyKey`要求与`bot`的`config.py`中的`verifyKey`相同
+
+ `port`: 8080要和2.4 config.py配置里面的端口号相同
+
+#### 2.4 登录
+
+#### 在mirai上登录QQ
+
+```
+login <机器人QQ号> <机器人QQ密码>
+```
+
+> 具体见[此教程](https://yiri-mirai.wybxc.cc/tutorials/01/configuration#4-登录-qq)
+
+#### 配置自动登录(可选)
+
+当机器人账号登录成功以后，执行
+
+```
+autologin add <机器人QQ号> <机器人密码>
+autologin setConfig <机器人QQ号> protocol ANDROID_PAD
+```
+
+> 出现`无法登录`报错时候[无法登录的临时处理方案](https://mirai.mamoe.net/topic/223/无法登录的临时处理方案)
+
+**完成后, `Ctrl+P+Q`退出(不会关掉容器,容器还会运行)**
+
+### 3. 部署QChatGPT
+
+配置好config.py,保存到当前目录下,运行下面的
+
+```
+ docker run  -it -d --name QChatGPT   --network host   -v ${PWD}/config.py:/QChatGPT/config.py  -v ${PWD}/banlist.py:/QChatGPT/banlist.py  -v ${PWD}/sensitive.json:/QChatGPT/sensitive.json  mikumifa/qchatgpt-docker
+```
+

res/scripts/generate_cmdpriv_template.py

@@ -0,0 +1,17 @@
+import pkg.qqbot.cmds.aamgr as cmdsmgr
+import json
+
+# 执行命令模块的注册
+cmdsmgr.register_all()
+
+# 生成限权文件模板
+template: dict[str, int] = {
+    "comment": "以下为命令权限，请设置到cmdpriv.json中。关于此功能的说明，请查看：https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%91%BD%E4%BB%A4%E6%9D%83%E9%99%90%E6%8E%A7%E5%88%B6",
+}
+
+for key in cmdsmgr.__command_list__:
+    template[key] = cmdsmgr.__command_list__[key]['privilege']
+
+# 写入cmdpriv-template.json
+with open('res/templates/cmdpriv-template.json', 'w') as f:
+    f.write(json.dumps(template, indent=4, ensure_ascii=False))

res/scripts/generate_override_all.py

@@ -0,0 +1,23 @@
+# 使用config-template生成override.json的字段全集模板文件override-all.json
+# 关于override.json机制，请参考：https://github.com/RockChinQ/QChatGPT/pull/271
+import json
+import importlib
+
+
+template = importlib.import_module("config-template")
+output_json = {
+    "comment": "这是override.json支持的字段全集, 关于override.json机制, 请查看https://github.com/RockChinQ/QChatGPT/pull/271"
+}
+
+
+for k, v in template.__dict__.items():
+    if k.startswith("__"):
+        continue
+    # 如果是module
+    if type(v) == type(template):
+        continue
+    print(k, v, type(v))
+    output_json[k] = v
+
+with open("override-all.json", "w", encoding="utf-8") as f:
+    json.dump(output_json, f, indent=4, ensure_ascii=False)

res/scripts/publish_announcement.py

@@ -0,0 +1,32 @@
+# 输出工作路径
+import os
+print("工作路径: " + os.getcwd())
+announcement = input("请输入公告内容: ")
+
+import json
+
+# 读取现有的公告文件 res/announcement.json
+with open("res/announcement.json", "r", encoding="utf-8") as f:
+    announcement_json = json.load(f)
+
+# 将公告内容写入公告文件
+
+# 当前自然时间
+import time
+now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+
+# 获取最后一个公告的id
+last_id = announcement_json[-1]["id"] if len(announcement_json) > 0 else -1
+
+announcement = {
+    "id": last_id + 1,
+    "time": now,
+    "timestamp": int(time.time()),
+    "content": announcement
+}
+
+announcement_json.append(announcement)
+
+# 将公告写入公告文件
+with open("res/announcement.json", "w", encoding="utf-8") as f:
+    json.dump(announcement_json, f, indent=4, ensure_ascii=False)