chore: bump version 4.3.0b4

fix: tool call params in localagent
fix: minor bugs
2025-11-25 19:37:36 +08:00 · 2025-08-28 14:43:45 +08:00 · 2025-08-28 14:38:10 +08:00 · 2025-08-28 14:02:56 +08:00 · 2025-08-26 22:40:32 +08:00 · 2025-08-25 23:22:36 +08:00
244 changed files with 12209 additions and 1496 deletions
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@@ -9,7 +9,7 @@

 *请在方括号间写`x`以打勾 / Please tick the box with `x`*

- [ ] 阅读仓库[贡献指引](https://github.com/RockChinQ/LangBot/blob/master/CONTRIBUTING.md)了吗？ / Have you read the [contribution guide](https://github.com/RockChinQ/LangBot/blob/master/CONTRIBUTING.md)?
+- [ ] 阅读仓库[贡献指引](https://github.com/langbot-app/LangBot/blob/master/CONTRIBUTING.md)了吗？ / Have you read the [contribution guide](https://github.com/langbot-app/LangBot/blob/master/CONTRIBUTING.md)?
 - [ ] 与项目所有者沟通过了吗？ / Have you communicated with the project maintainer?
 - [ ] 我确定已自行测试所作的更改，确保功能符合预期。 / I have tested the changes and ensured they work as expected.

--- a/.gitignore
+++ b/.gitignore
@@ -42,4 +42,5 @@ botpy.log*
 test.py
 /web_ui
 .venv/
-uv.lock
+uv.lock
+/test
--- a/README.md
+++ b/README.md
@@ -1,50 +1,40 @@

 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+[English](README_EN.md) / 简体中文 / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)

 <a href="https://langbot.app">项目主页</a> ｜
 <a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a> ｜
 <a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">插件介绍</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>

-<div align="center">
-😎高稳定、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台🤖  
-</div>
-
-<br/>
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
-
-简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)

 </div>

 </p>

-## ✨ 特性
-
- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态能力，并深度适配 [Dify](https://dify.ai)。目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
- 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
- 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
- 😻 Web 管理面板：支持通过浏览器管理 LangBot 实例，不再需要手动编写配置文件。
+LangBot 是一个开源的大语言模型原生即时通信机器人开发平台，旨在提供开箱即用的 IM 机器人开发体验，具有 Agent、RAG、MCP 等多种 LLM 应用功能，适配全球主流即时通信平台，并提供丰富的 API 接口，支持自定义开发。

 ## 📦 开始使用

 #### Docker Compose 部署

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -71,23 +61,25 @@ docker compose up -d

 直接使用发行版运行，查看文档[手动部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。

-## 📸 效果展示
+## 😎 保持更新

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="450px"/>
+点击仓库右上角 Star 和 Watch 按钮，获取最新动态。

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="450px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="450px"/>
+## ✨ 特性

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="450px"/>
+- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态、流式输出能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
+- 🤖 多平台支持：目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
+- 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
+- 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
+- 😻 Web 管理面板：支持通过浏览器管理 LangBot 实例，不再需要手动编写配置文件。

-<img alt="回复效果（带有联网插件）" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+详细规格特性请访问[文档](https://docs.langbot.app/zh/insight/features.html)。

- WebUI Demo: https://demo.langbot.dev/
-    - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
-    - 注意：仅展示webui效果，公开环境，请不要在其中填入您的任何敏感信息。
-
-## 🔌 组件兼容性
+或访问 demo 环境：https://demo.langbot.dev/  
+  - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
+  - 注意：仅展示 WebUI 效果，公开环境，请不要在其中填入您的任何敏感信息。

 ### 消息平台

@@ -104,10 +96,6 @@ docker compose up -d
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: 正在开发中

 ### 大模型能力

@@ -119,8 +107,10 @@ docker compose up -d
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [智谱AI](https://open.bigmodel.cn/) | ✅ |  |
+| [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 资源平台 |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 资源平台 |
-| [302 AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
+| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 资源平台 |
+| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
 | [Ollama](https://ollama.com/) | ✅ | 本地大模型运行平台 |
@@ -148,14 +138,8 @@ docker compose up -d

 ## 😘 社区贡献

-感谢以下[代码贡献者](https://github.com/RockChinQ/LangBot/graphs/contributors)和社区里其他成员对 LangBot 的贡献：
+感谢以下[代码贡献者](https://github.com/langbot-app/LangBot/graphs/contributors)和社区里其他成员对 LangBot 的贡献：

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 保持更新
-
-点击仓库右上角 Star 和 Watch 按钮，获取最新动态。
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/README_EN.md
+++ b/README_EN.md
@@ -1,48 +1,34 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+English / [简体中文](README.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">

 <a href="https://langbot.app">Home</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Deployment</a> ｜
 <a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>
-
-<div align="center">
-😎High Stability, 🧩Extension Supported, 🦄Multi-modal - LLM Native Instant Messaging Bot Platform🤖  
-</div>
-
-<br/>
-
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-
-[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>

 </div>

 </p>

-## ✨ Features
-
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Deeply integrates with [Dify](https://dify.ai). Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
- 😻 [New] Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
+LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.

 ## 📦 Getting Started

 #### Docker Compose Deployment

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -69,23 +55,25 @@ Community contributed Zeabur template.

 Directly use the released version to run, see the [Manual Deployment](https://docs.langbot.app/en/deploy/langbot/manual.html) documentation.

-## 📸 Demo
+## 😎 Stay Ahead

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
+Click the Star and Watch button in the upper right corner of the repository to get the latest updates.

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
+## ✨ Features

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
+- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
+- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
+- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
+- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
+- 😻 Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.

-<img alt="Reply Effect (with Internet Plugin)" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+For more detailed specifications, please refer to the [documentation](https://docs.langbot.app/en/insight/features.html).

- WebUI Demo: https://demo.langbot.dev/
-    - Login information: Email: `demo@langbot.app` Password: `langbot123456`
-    - Note: Only the WebUI effect is shown, please do not fill in any sensitive information in the public environment.
-
-## 🔌 Component Compatibility
+Or visit the demo environment: https://demo.langbot.dev/
+  - Login information: Email: `demo@langbot.app` Password: `langbot123456`
+  - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.

 ### Message Platform

@@ -101,10 +89,6 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: In development

 ### LLMs

@@ -116,9 +100,11 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | LLM and GPU resource platform |
 | [Dify](https://dify.ai) | ✅ | LLMOps platform |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
-| [302 AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM and GPU resource platform |
+| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |
 | [LMStudio](https://lmstudio.ai/) | ✅ | Local LLM running platform |
@@ -131,14 +117,8 @@ Directly use the released version to run, see the [Manual Deployment](https://do

 ## 🤝 Community Contribution

-Thank you for the following [code contributors](https://github.com/RockChinQ/LangBot/graphs/contributors) and other members in the community for their contributions to LangBot:
+Thank you for the following [code contributors](https://github.com/langbot-app/LangBot/graphs/contributors) and other members in the community for their contributions to LangBot:

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 Stay Ahead
-
-Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/README_JP.md
+++ b/README_JP.md
@@ -1,47 +1,34 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social.png" alt="LangBot"/>
+<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
 </a>

 <div align="center">

-<a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+[English](README_EN.md) / [简体中文](README.md) / [繁體中文](README_TW.md) / 日本語 / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">

 <a href="https://langbot.app">ホーム</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">デプロイ</a> ｜
 <a href="https://docs.langbot.app/en/plugin/plugin-intro.html">プラグイン</a> ｜
-<a href="https://github.com/RockChinQ/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>
-
-<div align="center">
-😎高い安定性、🧩拡張サポート、🦄マルチモーダル - LLMネイティブインスタントメッセージングボットプラットフォーム🤖  
-</div>
-
-<br/>
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/RockChinQ/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/LangBot)](https://github.com/RockChinQ/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-
-[简体中文](README_CN.md) / [English](README.md) / [日本語](README_JP.md) / (PR for your language)
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>

 </div>

 </p>

-## ✨ 機能
-
- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート。 [Dify](https://dify.ai) と深く統合。現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。
+LangBot は、エージェント、RAG、MCP などの LLM アプリケーション機能を備えた、オープンソースの LLM ネイティブのインスタントメッセージングロボット開発プラットフォームです。世界中のインスタントメッセージングプラットフォームに適応し、豊富な API インターフェースを提供し、カスタム開発をサポートします。

 ## 📦 始め方

 #### Docker Compose デプロイ

 ```bash
-git clone https://github.com/RockChinQ/LangBot
+git clone https://github.com/langbot-app/LangBot
 cd LangBot
 docker compose up -d
 ```
@@ -50,7 +37,7 @@ http://localhost:5300 にアクセスして使用を開始します。

 詳細なドキュメントは[Dockerデプロイ](https://docs.langbot.app/en/deploy/langbot/docker.html)を参照してください。

-#### BTPanelでのワンクリックデプロイ
+#### Panelでのワンクリックデプロイ

 LangBotはBTPanelにリストされています。BTPanelをインストールしている場合は、[ドキュメント](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html)を使用して使用できます。

@@ -68,23 +55,25 @@ LangBotはBTPanelにリストされています。BTPanelをインストール

 リリースバージョンを直接使用して実行します。[手動デプロイ](https://docs.langbot.app/en/deploy/langbot/manual.html)のドキュメントを参照してください。

-## 📸 デモ
+## 😎 最新情報を入手

-<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
+リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。

-<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
+![star gif](https://docs.langbot.app/star.gif)

-<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
+## ✨ 機能

-<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
+- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル、ストリーミング出力機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
+- 🤖 多プラットフォーム対応: 現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
+- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
+- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
+- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。

-<img alt="返信効果（インターネットプラグイン付き）" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
+詳細な仕様については、[ドキュメント](https://docs.langbot.app/en/insight/features.html)を参照してください。

- WebUIデモ: https://demo.langbot.dev/
-    - ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
-    - 注意: WebUIの効果のみを示しています。公開環境では、機密情報を入力しないでください。
-
-## 🔌 コンポーネントの互換性
+または、デモ環境にアクセスしてください: https://demo.langbot.dev/
+  - ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
+  - 注意: WebUI のデモンストレーションのみの場合、公開環境では機密情報を入力しないでください。

 ### メッセージプラットフォーム

@@ -100,10 +89,6 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: 開発中

 ### LLMs

@@ -115,8 +100,10 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
-| [302 AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLMとGPUリソースプラットフォーム |
+| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |
 | [Ollama](https://ollama.com/) | ✅ | ローカルLLM実行プラットフォーム |
@@ -130,14 +117,8 @@ LangBotはBTPanelにリストされています。BTPanelをインストール

 ## 🤝 コミュニティ貢献

-LangBot への貢献に対して、以下の [コード貢献者](https://github.com/RockChinQ/LangBot/graphs/contributors) とコミュニティの他のメンバーに感謝します。
+LangBot への貢献に対して、以下の [コード貢献者](https://github.com/langbot-app/LangBot/graphs/contributors) とコミュニティの他のメンバーに感謝します。

-<a href="https://github.com/RockChinQ/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=RockChinQ/LangBot" />
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-## 😎 最新情報を入手
-
-リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。
-
-![star gif](https://docs.langbot.app/star.gif)
--- a/README_TW.md
+++ b/README_TW.md
@@ -0,0 +1,140 @@
+<p align="center">
+<a href="https://langbot.app">
+<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
+</a>
+
+<div align="center"><a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+[English](README_EN.md) / [简体中文](README.md) / 繁體中文 / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
+
+<a href="https://langbot.app">主頁</a> ｜
+<a href="https://docs.langbot.app/zh/insight/guide.html">部署文件</a> ｜
+<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">外掛介紹</a> ｜
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交外掛</a>
+
+</div>
+
+</p>
+
+LangBot 是一個開源的大語言模型原生即時通訊機器人開發平台，旨在提供開箱即用的 IM 機器人開發體驗，具有 Agent、RAG、MCP 等多種 LLM 應用功能，適配全球主流即時通訊平台，並提供豐富的 API 介面，支援自定義開發。
+
+## 📦 開始使用
+
+#### Docker Compose 部署
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot
+docker compose up -d
+```
+
+訪問 http://localhost:5300 即可開始使用。
+
+詳細文件[Docker 部署](https://docs.langbot.app/zh/deploy/langbot/docker.html)。
+
+#### 寶塔面板部署
+
+已上架寶塔面板，若您已安裝寶塔面板，可以根據[文件](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html)使用。
+
+#### Zeabur 雲端部署
+
+社群貢獻的 Zeabur 模板。
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
+
+#### Railway 雲端部署
+
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+#### 手動部署
+
+直接使用發行版運行，查看文件[手動部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。
+
+## 😎 保持更新
+
+點擊倉庫右上角 Star 和 Watch 按鈕，獲取最新動態。
+
+![star gif](https://docs.langbot.app/star.gif)
+
+## ✨ 特性
+
+- 💬 大模型對話、Agent：支援多種大模型，適配群聊和私聊；具有多輪對話、工具調用、多模態、流式輸出能力，自帶 RAG（知識庫）實現，並深度適配 [Dify](https://dify.ai)。
+- 🤖 多平台支援：目前支援 QQ、QQ頻道、企業微信、個人微信、飛書、Discord、Telegram 等平台。
+- 🛠️ 高穩定性、功能完備：原生支援訪問控制、限速、敏感詞過濾等機制；配置簡單，支援多種部署方式。支援多流水線配置，不同機器人用於不同應用場景。
+- 🧩 外掛擴展、活躍社群：支援事件驅動、組件擴展等外掛機制；適配 Anthropic [MCP 協議](https://modelcontextprotocol.io/)；目前已有數百個外掛。
+- 😻 Web 管理面板：支援通過瀏覽器管理 LangBot 實例，不再需要手動編寫配置文件。
+
+詳細規格特性請訪問[文件](https://docs.langbot.app/zh/insight/features.html)。
+
+或訪問 demo 環境：https://demo.langbot.dev/  
+  - 登入資訊：郵箱：`demo@langbot.app` 密碼：`langbot123456`
+  - 注意：僅展示 WebUI 效果，公開環境，請不要在其中填入您的任何敏感資訊。
+
+### 訊息平台
+
+| 平台 | 狀態 | 備註 |
+| --- | --- | --- |
+| QQ 個人號 | ✅ | QQ 個人號私聊、群聊 |
+| QQ 官方機器人 | ✅ | QQ 官方機器人，支援頻道、私聊、群聊 |
+| 微信 | ✅ |  |
+| 企微對外客服 | ✅ |  |
+| 微信公眾號 | ✅ |  |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+
+### 大模型能力
+
+| 模型 | 狀態 | 備註 |
+| --- | --- | --- |
+| [OpenAI](https://platform.openai.com/) | ✅ | 可接入任何 OpenAI 介面格式模型 |
+| [DeepSeek](https://www.deepseek.com/) | ✅ |  |
+| [Moonshot](https://www.moonshot.cn/) | ✅ |  |
+| [Anthropic](https://www.anthropic.com/) | ✅ |  |
+| [xAI](https://x.ai/) | ✅ |  |
+| [智譜AI](https://open.bigmodel.cn/) | ✅ |  |
+| [勝算雲](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 資源平台 |
+| [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 資源平台 |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 資源平台 |
+| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
+| [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
+| [Ollama](https://ollama.com/) | ✅ | 本地大模型運行平台 |
+| [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型運行平台 |
+| [GiteeAI](https://ai.gitee.com/) | ✅ | 大模型介面聚合平台 |
+| [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
+| [阿里雲百煉](https://bailian.console.aliyun.com/) | ✅ | 大模型聚合平台, LLMOps 平台 |
+| [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | 大模型聚合平台, LLMOps 平台 |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | 大模型聚合平台 |
+| [MCP](https://modelcontextprotocol.io/) | ✅ | 支援通過 MCP 協議獲取工具 |
+
+### TTS
+
+| 平台/模型 | 備註 |
+| --- | --- |
+| [FishAudio](https://fish.audio/zh-CN/discovery/) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
+| [海豚 AI](https://www.ttson.cn/?source=thelazy) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
+| [AzureTTS](https://portal.azure.com/) | [外掛](https://github.com/Ingnaryk/LangBot_AzureTTS) |
+
+### 文生圖
+
+| 平台/模型 | 備註 |
+| --- | --- |
+| 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
+
+## 😘 社群貢獻
+
+感謝以下[程式碼貢獻者](https://github.com/langbot-app/LangBot/graphs/contributors)和社群裡其他成員對 LangBot 的貢獻：
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a> 
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -1,6 +1,21 @@
 version: "3"

 services:
+
+  langbot_plugin_runtime:
+    image: rockchin/langbot:latest
+    container_name: langbot_plugin_runtime
+    volumes:
+      - ./data/plugins:/app/data/plugins
+    ports:
+      - 5401:5401
+    restart: on-failure
+    environment:
+      - TZ=Asia/Shanghai
+    command: ["uv", "run", "-m", "langbot_plugin.cli.__init__", "rt"]
+    networks:
+      - langbot_network
+
  langbot:
    image: rockchin/langbot:latest
    container_name: langbot
@@ -11,6 +26,11 @@ services:
    environment:
      - TZ=Asia/Shanghai
    ports:
-      - 5300:5300  # 供 WebUI 使用
-      - 2280-2290:2280-2290  # 供消息平台适配器方向连接
-    # 根据具体环境配置网络
+      - 5300:5300  # For web ui
+      - 2280-2290:2280-2290  # For platform webhook
+    networks:
+      - langbot_network
+
+networks:
+  langbot_network:
+    driver: bridge
--- a/libs/dingtalk_api/api.py
+++ b/libs/dingtalk_api/api.py
@@ -253,6 +253,43 @@ class DingTalkClient:
            await self.logger.error(f'failed to send proactive massage to group: {traceback.format_exc()}')
            raise Exception(f'failed to send proactive massage to group: {traceback.format_exc()}')

+    async def create_and_card(
+        self, temp_card_id: str, incoming_message: dingtalk_stream.ChatbotMessage, quote_origin: bool = False
+    ):
+        content_key = 'content'
+        card_data = {content_key: ''}
+
+        card_instance = dingtalk_stream.AICardReplier(self.client, incoming_message)
+        # print(card_instance)
+        # 先投放卡片: https://open.dingtalk.com/document/orgapp/create-and-deliver-cards
+        card_instance_id = await card_instance.async_create_and_deliver_card(
+            temp_card_id,
+            card_data,
+        )
+        return card_instance, card_instance_id
+
+    async def send_card_message(self, card_instance, card_instance_id: str, content: str, is_final: bool):
+        content_key = 'content'
+        try:
+            await card_instance.async_streaming(
+                card_instance_id,
+                content_key=content_key,
+                content_value=content,
+                append=False,
+                finished=is_final,
+                failed=False,
+            )
+        except Exception as e:
+            self.logger.exception(e)
+            await card_instance.async_streaming(
+                card_instance_id,
+                content_key=content_key,
+                content_value='',
+                append=False,
+                finished=is_final,
+                failed=True,
+            )
+
    async def start(self):
        """启动 WebSocket 连接，监听消息"""
        await self.client.start()
--- a/libs/wechatpad_api/init.py
+++ b/libs/wechatpad_api/init.py
@@ -1,4 +1 @@
-from .client import WeChatPadClient
-
-
-__all__ = ['WeChatPadClient']
+from .client import WeChatPadClient as WeChatPadClient
--- a/main.py
+++ b/main.py
@@ -11,7 +11,7 @@ asciiart = r"""
 |____\__,_|_||_\__, |___/\___/\__|
               |___/              

-⭐️ Open Source 开源地址: https://github.com/RockChinQ/LangBot
+⭐️ Open Source 开源地址: https://github.com/langbot-app/LangBot
 📖 Documentation 文档地址: https://docs.langbot.app
 """

@@ -19,8 +19,14 @@ asciiart = r"""
 async def main_entry(loop: asyncio.AbstractEventLoop):
    parser = argparse.ArgumentParser(description='LangBot')
    parser.add_argument('--skip-plugin-deps-check', action='store_true', help='跳过插件依赖项检查', default=False)
+    parser.add_argument('--standalone-runtime', action='store_true', help='使用独立插件运行时', default=False)
    args = parser.parse_args()

+    if args.standalone_runtime:
+        from pkg.utils import platform
+
+        platform.standalone_runtime = True
+
    print(asciiart)

    import sys
--- a/pkg/api/http/controller/group.py
+++ b/pkg/api/http/controller/group.py
@@ -11,10 +11,10 @@ from ....core import app


 preregistered_groups: list[type[RouterGroup]] = []
-"""RouterGroup 的预注册列表"""
+"""Pre-registered list of RouterGroup"""


-def group_class(name: str, path: str) -> None:
+def group_class(name: str, path: str) -> typing.Callable[[typing.Type[RouterGroup]], typing.Type[RouterGroup]]:
    """注册一个 RouterGroup"""

    def decorator(cls: typing.Type[RouterGroup]) -> typing.Type[RouterGroup]:
@@ -27,7 +27,7 @@ def group_class(name: str, path: str) -> None:


 class AuthType(enum.Enum):
-    """认证类型"""
+    """Authentication type"""

    NONE = 'none'
    USER_TOKEN = 'user-token'
@@ -56,7 +56,7 @@ class RouterGroup(abc.ABC):
        auth_type: AuthType = AuthType.USER_TOKEN,
        **options: typing.Any,
    ) -> typing.Callable[[RouteCallable], RouteCallable]:  # decorator
-        """注册一个路由"""
+        """Register a route"""

        def decorator(f: RouteCallable) -> RouteCallable:
            nonlocal rule
@@ -64,11 +64,11 @@ class RouterGroup(abc.ABC):

            async def handler_error(*args, **kwargs):
                if auth_type == AuthType.USER_TOKEN:
-                    # 从Authorization头中获取token
+                    # get token from Authorization header
                    token = quart.request.headers.get('Authorization', '').replace('Bearer ', '')

                    if not token:
-                        return self.http_status(401, -1, '未提供有效的用户令牌')
+                        return self.http_status(401, -1, 'No valid user token provided')

                    try:
                        user_email = await self.ap.user_service.verify_jwt_token(token)
@@ -76,9 +76,9 @@ class RouterGroup(abc.ABC):
                        # check if this account exists
                        user = await self.ap.user_service.get_user_by_email(user_email)
                        if not user:
-                            return self.http_status(401, -1, '用户不存在')
+                            return self.http_status(401, -1, 'User not found')

-                        # 检查f是否接受user_email参数
+                        # check if f accepts user_email parameter
                        if 'user_email' in f.__code__.co_varnames:
                            kwargs['user_email'] = user_email
                    except Exception as e:
@@ -86,10 +86,11 @@ class RouterGroup(abc.ABC):

                try:
                    return await f(*args, **kwargs)
-                except Exception:  # 自动 500
+
+                except Exception as e:  # 自动 500
                    traceback.print_exc()
                    # return self.http_status(500, -2, str(e))
-                    return self.http_status(500, -2, 'internal server error')
+                    return self.http_status(500, -2, str(e))

            new_f = handler_error
            new_f.__name__ = (self.name + rule).replace('/', '__')
@@ -101,7 +102,7 @@ class RouterGroup(abc.ABC):
        return decorator

    def success(self, data: typing.Any = None) -> quart.Response:
-        """返回一个 200 响应"""
+        """Return a 200 response"""
        return quart.jsonify(
            {
                'code': 0,
@@ -111,7 +112,7 @@ class RouterGroup(abc.ABC):
        )

    def fail(self, code: int, msg: str) -> quart.Response:
-        """返回一个异常响应"""
+        """Return an error response"""

        return quart.jsonify(
            {
@@ -120,6 +121,6 @@ class RouterGroup(abc.ABC):
            }
        )

-    def http_status(self, status: int, code: int, msg: str) -> quart.Response:
+    def http_status(self, status: int, code: int, msg: str) -> typing.Tuple[quart.Response, int]:
        """返回一个指定状态码的响应"""
-        return self.fail(code, msg), status
+        return (self.fail(code, msg), status)
--- a/pkg/api/http/controller/groups/files.py
+++ b/pkg/api/http/controller/groups/files.py
@@ -2,6 +2,10 @@ from __future__ import annotations

 import quart
 import mimetypes
+import uuid
+import asyncio
+
+import quart.datastructures

 from .. import group

@@ -20,3 +24,23 @@ class FilesRouterGroup(group.RouterGroup):
                mime_type = 'image/jpeg'

            return quart.Response(image_bytes, mimetype=mime_type)
+
+        @self.route('/documents', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> quart.Response:
+            request = quart.request
+            # get file bytes from 'file'
+            file = (await request.files)['file']
+            assert isinstance(file, quart.datastructures.FileStorage)
+
+            file_bytes = await asyncio.to_thread(file.stream.read)
+            extension = file.filename.split('.')[-1]
+            file_name = file.filename.split('.')[0]
+
+            file_key = file_name + '_' + str(uuid.uuid4())[:8] + '.' + extension
+            # save file to storage
+            await self.ap.storage_mgr.storage_provider.save(file_key, file_bytes)
+            return self.success(
+                data={
+                    'file_id': file_key,
+                }
+            )
--- a/pkg/api/http/controller/groups/knowledge/init.py
+++ b/pkg/api/http/controller/groups/knowledge/init.py
--- a/pkg/api/http/controller/groups/knowledge/base.py
+++ b/pkg/api/http/controller/groups/knowledge/base.py
@@ -0,0 +1,90 @@
+import quart
+from ... import group
+
+
+@group.group_class('knowledge_base', '/api/v1/knowledge/bases')
+class KnowledgeBaseRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['POST', 'GET'])
+        async def handle_knowledge_bases() -> quart.Response:
+            if quart.request.method == 'GET':
+                knowledge_bases = await self.ap.knowledge_service.get_knowledge_bases()
+                return self.success(data={'bases': knowledge_bases})
+
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                knowledge_base_uuid = await self.ap.knowledge_service.create_knowledge_base(json_data)
+                return self.success(data={'uuid': knowledge_base_uuid})
+
+            return self.http_status(405, -1, 'Method not allowed')
+
+        @self.route(
+            '/<knowledge_base_uuid>',
+            methods=['GET', 'DELETE', 'PUT'],
+        )
+        async def handle_specific_knowledge_base(knowledge_base_uuid: str) -> quart.Response:
+            if quart.request.method == 'GET':
+                knowledge_base = await self.ap.knowledge_service.get_knowledge_base(knowledge_base_uuid)
+
+                if knowledge_base is None:
+                    return self.http_status(404, -1, 'knowledge base not found')
+
+                return self.success(
+                    data={
+                        'base': knowledge_base,
+                    }
+                )
+
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                await self.ap.knowledge_service.update_knowledge_base(knowledge_base_uuid, json_data)
+                return self.success({})
+
+            elif quart.request.method == 'DELETE':
+                await self.ap.knowledge_service.delete_knowledge_base(knowledge_base_uuid)
+                return self.success({})
+
+        @self.route(
+            '/<knowledge_base_uuid>/files',
+            methods=['GET', 'POST'],
+        )
+        async def get_knowledge_base_files(knowledge_base_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                files = await self.ap.knowledge_service.get_files_by_knowledge_base(knowledge_base_uuid)
+                return self.success(
+                    data={
+                        'files': files,
+                    }
+                )
+
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                file_id = json_data.get('file_id')
+                if not file_id:
+                    return self.http_status(400, -1, 'File ID is required')
+
+                # 调用服务层方法将文件与知识库关联
+                task_id = await self.ap.knowledge_service.store_file(knowledge_base_uuid, file_id)
+                return self.success(
+                    {
+                        'task_id': task_id,
+                    }
+                )
+
+        @self.route(
+            '/<knowledge_base_uuid>/files/<file_id>',
+            methods=['DELETE'],
+        )
+        async def delete_specific_file_in_kb(file_id: str, knowledge_base_uuid: str) -> str:
+            await self.ap.knowledge_service.delete_file(knowledge_base_uuid, file_id)
+            return self.success({})
+
+        @self.route(
+            '/<knowledge_base_uuid>/retrieve',
+            methods=['POST'],
+        )
+        async def retrieve_knowledge_base(knowledge_base_uuid: str) -> str:
+            json_data = await quart.request.json
+            query = json_data.get('query')
+            results = await self.ap.knowledge_service.retrieve_knowledge_base(knowledge_base_uuid, query)
+            return self.success(data={'results': results})
--- a/pkg/api/http/controller/groups/pipelines/pipelines.py
+++ b/pkg/api/http/controller/groups/pipelines/pipelines.py
@@ -11,7 +11,11 @@ class PipelinesRouterGroup(group.RouterGroup):
        @self.route('', methods=['GET', 'POST'])
        async def _() -> str:
            if quart.request.method == 'GET':
-                return self.success(data={'pipelines': await self.ap.pipeline_service.get_pipelines()})
+                sort_by = quart.request.args.get('sort_by', 'created_at')
+                sort_order = quart.request.args.get('sort_order', 'DESC')
+                return self.success(
+                    data={'pipelines': await self.ap.pipeline_service.get_pipelines(sort_by, sort_order)}
+                )
            elif quart.request.method == 'POST':
                json_data = await quart.request.json

--- a/pkg/api/http/controller/groups/pipelines/webchat.py
+++ b/pkg/api/http/controller/groups/pipelines/webchat.py
@@ -1,3 +1,5 @@
+import json
+
 import quart

 from ... import group
@@ -8,11 +10,19 @@ class WebChatDebugRouterGroup(group.RouterGroup):
    async def initialize(self) -> None:
        @self.route('/send', methods=['POST'])
        async def send_message(pipeline_uuid: str) -> str:
-            """发送调试消息到流水线"""
+            """Send a message to the pipeline for debugging"""
+
+            async def stream_generator(generator):
+                yield 'data: {"type": "start"}\n\n'
+                async for message in generator:
+                    yield f'data: {json.dumps({"message": message})}\n\n'
+                yield 'data: {"type": "end"}\n\n'
+
            try:
                data = await quart.request.get_json()
                session_type = data.get('session_type', 'person')
                message_chain_obj = data.get('message', [])
+                is_stream = data.get('is_stream', False)

                if not message_chain_obj:
                    return self.http_status(400, -1, 'message is required')
@@ -25,20 +35,40 @@ class WebChatDebugRouterGroup(group.RouterGroup):
                if not webchat_adapter:
                    return self.http_status(404, -1, 'WebChat adapter not found')

-                result = await webchat_adapter.send_webchat_message(pipeline_uuid, session_type, message_chain_obj)
-
-                return self.success(
-                    data={
-                        'message': result,
+                if is_stream:
+                    generator = webchat_adapter.send_webchat_message(
+                        pipeline_uuid, session_type, message_chain_obj, is_stream
+                    )
+                    # 设置正确的响应头
+                    headers = {
+                        'Content-Type': 'text/event-stream',
+                        'Transfer-Encoding': 'chunked',
+                        'Cache-Control': 'no-cache',
+                        'Connection': 'keep-alive',
                    }
-                )
+                    return quart.Response(stream_generator(generator), mimetype='text/event-stream', headers=headers)
+
+                else:  # non-stream
+                    result = None
+                    async for message in webchat_adapter.send_webchat_message(
+                        pipeline_uuid, session_type, message_chain_obj
+                    ):
+                        result = message
+                    if result is not None:
+                        return self.success(
+                            data={
+                                'message': result,
+                            }
+                        )
+                    else:
+                        return self.http_status(400, -1, 'message is required')

            except Exception as e:
                return self.http_status(500, -1, f'Internal server error: {str(e)}')

        @self.route('/messages/<session_type>', methods=['GET'])
        async def get_messages(pipeline_uuid: str, session_type: str) -> str:
-            """获取调试消息历史"""
+            """Get the message history of the pipeline for debugging"""
            try:
                if session_type not in ['person', 'group']:
                    return self.http_status(400, -1, 'session_type must be person or group')
@@ -57,7 +87,7 @@ class WebChatDebugRouterGroup(group.RouterGroup):

        @self.route('/reset/<session_type>', methods=['POST'])
        async def reset_session(session_type: str) -> str:
-            """重置调试会话"""
+            """Reset the debug session"""
            try:
                if session_type not in ['person', 'group']:
                    return self.http_status(400, -1, 'session_type must be person or group')
--- a/pkg/api/http/controller/groups/provider/models.py
+++ b/pkg/api/http/controller/groups/provider/models.py
@@ -9,18 +9,18 @@ class LLMModelsRouterGroup(group.RouterGroup):
        @self.route('', methods=['GET', 'POST'])
        async def _() -> str:
            if quart.request.method == 'GET':
-                return self.success(data={'models': await self.ap.model_service.get_llm_models()})
+                return self.success(data={'models': await self.ap.llm_model_service.get_llm_models()})
            elif quart.request.method == 'POST':
                json_data = await quart.request.json

-                model_uuid = await self.ap.model_service.create_llm_model(json_data)
+                model_uuid = await self.ap.llm_model_service.create_llm_model(json_data)

                return self.success(data={'uuid': model_uuid})

        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
        async def _(model_uuid: str) -> str:
            if quart.request.method == 'GET':
-                model = await self.ap.model_service.get_llm_model(model_uuid)
+                model = await self.ap.llm_model_service.get_llm_model(model_uuid)

                if model is None:
                    return self.http_status(404, -1, 'model not found')
@@ -29,11 +29,11 @@ class LLMModelsRouterGroup(group.RouterGroup):
            elif quart.request.method == 'PUT':
                json_data = await quart.request.json

-                await self.ap.model_service.update_llm_model(model_uuid, json_data)
+                await self.ap.llm_model_service.update_llm_model(model_uuid, json_data)

                return self.success()
            elif quart.request.method == 'DELETE':
-                await self.ap.model_service.delete_llm_model(model_uuid)
+                await self.ap.llm_model_service.delete_llm_model(model_uuid)

                return self.success()

@@ -41,6 +41,49 @@ class LLMModelsRouterGroup(group.RouterGroup):
        async def _(model_uuid: str) -> str:
            json_data = await quart.request.json

-            await self.ap.model_service.test_llm_model(model_uuid, json_data)
+            await self.ap.llm_model_service.test_llm_model(model_uuid, json_data)
+
+            return self.success()
+
+
+@group.group_class('models/embedding', '/api/v1/provider/models/embedding')
+class EmbeddingModelsRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'])
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                return self.success(data={'models': await self.ap.embedding_models_service.get_embedding_models()})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+
+                model_uuid = await self.ap.embedding_models_service.create_embedding_model(json_data)
+
+                return self.success(data={'uuid': model_uuid})
+
+        @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
+        async def _(model_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                model = await self.ap.embedding_models_service.get_embedding_model(model_uuid)
+
+                if model is None:
+                    return self.http_status(404, -1, 'model not found')
+
+                return self.success(data={'model': model})
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+
+                await self.ap.embedding_models_service.update_embedding_model(model_uuid, json_data)
+
+                return self.success()
+            elif quart.request.method == 'DELETE':
+                await self.ap.embedding_models_service.delete_embedding_model(model_uuid)
+
+                return self.success()
+
+        @self.route('/<model_uuid>/test', methods=['POST'])
+        async def _(model_uuid: str) -> str:
+            json_data = await quart.request.json
+
+            await self.ap.embedding_models_service.test_embedding_model(model_uuid, json_data)

            return self.success()
--- a/pkg/api/http/controller/groups/provider/requesters.py
+++ b/pkg/api/http/controller/groups/provider/requesters.py
@@ -8,7 +8,8 @@ class RequestersRouterGroup(group.RouterGroup):
    async def initialize(self) -> None:
        @self.route('', methods=['GET'])
        async def _() -> quart.Response:
-            return self.success(data={'requesters': self.ap.model_mgr.get_available_requesters_info()})
+            model_type = quart.request.args.get('type', '')
+            return self.success(data={'requesters': self.ap.model_mgr.get_available_requesters_info(model_type)})

        @self.route('/<requester_name>', methods=['GET'])
        async def _(requester_name: str) -> quart.Response:
--- a/pkg/api/http/controller/groups/user.py
+++ b/pkg/api/http/controller/groups/user.py
@@ -1,5 +1,6 @@
 import quart
 import argon2
+import asyncio

 from .. import group

@@ -13,7 +14,7 @@ class UserRouterGroup(group.RouterGroup):
                return self.success(data={'initialized': await self.ap.user_service.is_initialized()})

            if await self.ap.user_service.is_initialized():
-                return self.fail(1, '系统已初始化')
+                return self.fail(1, 'System already initialized')

            json_data = await quart.request.json

@@ -31,7 +32,7 @@ class UserRouterGroup(group.RouterGroup):
            try:
                token = await self.ap.user_service.authenticate(json_data['user'], json_data['password'])
            except argon2.exceptions.VerifyMismatchError:
-                return self.fail(1, '用户名或密码错误')
+                return self.fail(1, 'Invalid username or password')

            return self.success(data={'token': token})

@@ -40,3 +41,45 @@ class UserRouterGroup(group.RouterGroup):
            token = await self.ap.user_service.generate_jwt_token(user_email)

            return self.success(data={'token': token})
+
+        @self.route('/reset-password', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def _() -> str:
+            json_data = await quart.request.json
+
+            user_email = json_data['user']
+            recovery_key = json_data['recovery_key']
+            new_password = json_data['new_password']
+
+            # hard sleep 3s for security
+            await asyncio.sleep(3)
+
+            if not await self.ap.user_service.is_initialized():
+                return self.http_status(400, -1, 'System not initialized')
+
+            user_obj = await self.ap.user_service.get_user_by_email(user_email)
+
+            if user_obj is None:
+                return self.http_status(400, -1, 'User not found')
+
+            if recovery_key != self.ap.instance_config.data['system']['recovery_key']:
+                return self.http_status(403, -1, 'Invalid recovery key')
+
+            await self.ap.user_service.reset_password(user_email, new_password)
+
+            return self.success(data={'user': user_email})
+
+        @self.route('/change-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(user_email: str) -> str:
+            json_data = await quart.request.json
+
+            current_password = json_data['current_password']
+            new_password = json_data['new_password']
+
+            try:
+                await self.ap.user_service.change_password(user_email, current_password, new_password)
+            except argon2.exceptions.VerifyMismatchError:
+                return self.http_status(400, -1, 'Current password is incorrect')
+            except ValueError as e:
+                return self.http_status(400, -1, str(e))
+
+            return self.success(data={'user': user_email})
--- a/pkg/api/http/controller/main.py
+++ b/pkg/api/http/controller/main.py
@@ -14,11 +14,13 @@ from . import group
 from .groups import provider as groups_provider
 from .groups import platform as groups_platform
 from .groups import pipelines as groups_pipelines
+from .groups import knowledge as groups_knowledge

 importutil.import_modules_in_pkg(groups)
 importutil.import_modules_in_pkg(groups_provider)
 importutil.import_modules_in_pkg(groups_platform)
 importutil.import_modules_in_pkg(groups_pipelines)
+importutil.import_modules_in_pkg(groups_knowledge)


 class HTTPController:
@@ -45,7 +47,7 @@ class HTTPController:
                try:
                    await self.quart_app.run_task(*args, **kwargs)
                except Exception as e:
-                    self.ap.logger.error(f'启动 HTTP 服务失败： {e}')
+                    self.ap.logger.error(f'Failed to start HTTP service: {e}')

            self.ap.task_mgr.create_task(
                exception_handler(
--- a/pkg/api/http/service/bot.py
+++ b/pkg/api/http/service/bot.py
@@ -10,7 +10,7 @@ from ....entity.persistence import pipeline as persistence_pipeline


 class BotService:
-    """机器人服务"""
+    """Bot service"""

    ap: app.Application

@@ -63,7 +63,7 @@ class BotService:
        return persistence_bot

    async def create_bot(self, bot_data: dict) -> str:
-        """创建机器人"""
+        """Create bot"""
        # TODO: 检查配置信息格式
        bot_data['uuid'] = str(uuid.uuid4())

@@ -87,7 +87,7 @@ class BotService:
        return bot_data['uuid']

    async def update_bot(self, bot_uuid: str, bot_data: dict) -> None:
-        """更新机器人"""
+        """Update bot"""
        if 'uuid' in bot_data:
            del bot_data['uuid']

@@ -123,7 +123,7 @@ class BotService:
                session.using_conversation = None

    async def delete_bot(self, bot_uuid: str) -> None:
-        """删除机器人"""
+        """Delete bot"""
        await self.ap.platform_mgr.remove_bot(bot_uuid)
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.delete(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_uuid)
--- a/pkg/api/http/service/knowledge.py
+++ b/pkg/api/http/service/knowledge.py
@@ -0,0 +1,120 @@
+from __future__ import annotations
+
+import uuid
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import rag as persistence_rag
+
+
+class KnowledgeService:
+    """知识库服务"""
+
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_knowledge_bases(self) -> list[dict]:
+        """获取所有知识库"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_rag.KnowledgeBase))
+        knowledge_bases = result.all()
+        return [
+            self.ap.persistence_mgr.serialize_model(persistence_rag.KnowledgeBase, knowledge_base)
+            for knowledge_base in knowledge_bases
+        ]
+
+    async def get_knowledge_base(self, kb_uuid: str) -> dict | None:
+        """获取知识库"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
+        )
+        knowledge_base = result.first()
+        if knowledge_base is None:
+            return None
+        return self.ap.persistence_mgr.serialize_model(persistence_rag.KnowledgeBase, knowledge_base)
+
+    async def create_knowledge_base(self, kb_data: dict) -> str:
+        """创建知识库"""
+        kb_data['uuid'] = str(uuid.uuid4())
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.KnowledgeBase).values(kb_data))
+
+        kb = await self.get_knowledge_base(kb_data['uuid'])
+
+        await self.ap.rag_mgr.load_knowledge_base(kb)
+
+        return kb_data['uuid']
+
+    async def update_knowledge_base(self, kb_uuid: str, kb_data: dict) -> None:
+        """更新知识库"""
+        if 'uuid' in kb_data:
+            del kb_data['uuid']
+
+        if 'embedding_model_uuid' in kb_data:
+            del kb_data['embedding_model_uuid']
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_rag.KnowledgeBase)
+            .values(kb_data)
+            .where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
+        )
+        await self.ap.rag_mgr.remove_knowledge_base_from_runtime(kb_uuid)
+
+        kb = await self.get_knowledge_base(kb_uuid)
+
+        await self.ap.rag_mgr.load_knowledge_base(kb)
+
+    async def store_file(self, kb_uuid: str, file_id: str) -> int:
+        """存储文件"""
+        # await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.File).values(kb_id=kb_uuid, file_id=file_id))
+        # await self.ap.rag_mgr.store_file(file_id)
+        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+        if runtime_kb is None:
+            raise Exception('Knowledge base not found')
+        return await runtime_kb.store_file(file_id)
+
+    async def retrieve_knowledge_base(self, kb_uuid: str, query: str) -> list[dict]:
+        """检索知识库"""
+        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+        if runtime_kb is None:
+            raise Exception('Knowledge base not found')
+        return [
+            result.model_dump() for result in await runtime_kb.retrieve(query, runtime_kb.knowledge_base_entity.top_k)
+        ]
+
+    async def get_files_by_knowledge_base(self, kb_uuid: str) -> list[dict]:
+        """获取知识库文件"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
+        )
+        files = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_rag.File, file) for file in files]
+
+    async def delete_file(self, kb_uuid: str, file_id: str) -> None:
+        """删除文件"""
+        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+        if runtime_kb is None:
+            raise Exception('Knowledge base not found')
+        await runtime_kb.delete_file(file_id)
+
+    async def delete_knowledge_base(self, kb_uuid: str) -> None:
+        """删除知识库"""
+        await self.ap.rag_mgr.delete_knowledge_base(kb_uuid)
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
+        )
+
+        # delete files
+        files = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
+        )
+        for file in files:
+            # delete chunks
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(persistence_rag.Chunk).where(persistence_rag.Chunk.file_id == file.uuid)
+            )
+            # delete file
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file.uuid)
+            )
--- a/pkg/api/http/service/model.py
+++ b/pkg/api/http/service/model.py
@@ -10,7 +10,7 @@ from ....provider.modelmgr import requester as model_requester
 from langbot_plugin.api.entities.builtin.provider import message as provider_message


-class ModelsService:
+class LLMModelsService:
    ap: app.Application

    def __init__(self, ap: app.Application) -> None:
@@ -109,5 +109,91 @@ class ModelsService:
            model=runtime_llm_model,
            messages=[provider_message.Message(role='user', content='Hello, world!')],
            funcs=[],
+            extra_args=model_data.get('extra_args', {}),
+        )
+
+
+class EmbeddingModelsService:
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_embedding_models(self) -> list[dict]:
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
+
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model) for model in models]
+
+    async def create_embedding_model(self, model_data: dict) -> str:
+        model_data['uuid'] = str(uuid.uuid4())
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_model.EmbeddingModel).values(**model_data)
+        )
+
+        embedding_model = await self.get_embedding_model(model_data['uuid'])
+
+        await self.ap.model_mgr.load_embedding_model(embedding_model)
+
+        return model_data['uuid']
+
+    async def get_embedding_model(self, model_uuid: str) -> dict | None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.EmbeddingModel).where(
+                persistence_model.EmbeddingModel.uuid == model_uuid
+            )
+        )
+
+        model = result.first()
+
+        if model is None:
+            return None
+
+        return self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+
+    async def update_embedding_model(self, model_uuid: str, model_data: dict) -> None:
+        if 'uuid' in model_data:
+            del model_data['uuid']
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_model.EmbeddingModel)
+            .where(persistence_model.EmbeddingModel.uuid == model_uuid)
+            .values(**model_data)
+        )
+
+        await self.ap.model_mgr.remove_embedding_model(model_uuid)
+
+        embedding_model = await self.get_embedding_model(model_uuid)
+
+        await self.ap.model_mgr.load_embedding_model(embedding_model)
+
+    async def delete_embedding_model(self, model_uuid: str) -> None:
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_model.EmbeddingModel).where(
+                persistence_model.EmbeddingModel.uuid == model_uuid
+            )
+        )
+
+        await self.ap.model_mgr.remove_embedding_model(model_uuid)
+
+    async def test_embedding_model(self, model_uuid: str, model_data: dict) -> None:
+        runtime_embedding_model: model_requester.RuntimeEmbeddingModel | None = None
+
+        if model_uuid != '_':
+            for model in self.ap.model_mgr.embedding_models:
+                if model.model_entity.uuid == model_uuid:
+                    runtime_embedding_model = model
+                    break
+
+            if runtime_embedding_model is None:
+                raise Exception('model not found')
+
+        else:
+            runtime_embedding_model = await self.ap.model_mgr.init_runtime_embedding_model(model_data)
+
+        await runtime_embedding_model.requester.invoke_embedding(
+            model=runtime_embedding_model,
+            input_text=['Hello, world!'],
            extra_args={},
        )
--- a/pkg/api/http/service/pipeline.py
+++ b/pkg/api/http/service/pipeline.py
@@ -38,9 +38,21 @@ class PipelineService:
            self.ap.pipeline_config_meta_output.data,
        ]

-    async def get_pipelines(self) -> list[dict]:
-        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+    async def get_pipelines(self, sort_by: str = 'created_at', sort_order: str = 'DESC') -> list[dict]:
+        query = sqlalchemy.select(persistence_pipeline.LegacyPipeline)

+        if sort_by == 'created_at':
+            if sort_order == 'DESC':
+                query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.desc())
+            else:
+                query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.asc())
+        elif sort_by == 'updated_at':
+            if sort_order == 'DESC':
+                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.desc())
+            else:
+                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.asc())
+
+        result = await self.ap.persistence_mgr.execute_async(query)
        pipelines = result.all()
        return [
            self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
--- a/pkg/api/http/service/user.py
+++ b/pkg/api/http/service/user.py
@@ -73,3 +73,27 @@ class UserService:
        jwt_secret = self.ap.instance_config.data['system']['jwt']['secret']

        return jwt.decode(token, jwt_secret, algorithms=['HS256'])['user']
+
+    async def reset_password(self, user_email: str, new_password: str) -> None:
+        ph = argon2.PasswordHasher()
+
+        hashed_password = ph.hash(new_password)
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
+        )
+
+    async def change_password(self, user_email: str, current_password: str, new_password: str) -> None:
+        ph = argon2.PasswordHasher()
+
+        user_obj = await self.get_user_by_email(user_email)
+        if user_obj is None:
+            raise ValueError('User not found')
+
+        ph.verify(user_obj.password, current_password)
+
+        hashed_password = ph.hash(new_password)
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
+        )
--- a/pkg/config/impls/json.py
+++ b/pkg/config/impls/json.py
@@ -6,7 +6,7 @@ from .. import model as file_model


 class JSONConfigFile(file_model.ConfigFile):
-    """JSON配置文件"""
+    """JSON config file"""

    def __init__(
        self,
@@ -42,7 +42,7 @@ class JSONConfigFile(file_model.ConfigFile):
            try:
                cfg = json.load(f)
            except json.JSONDecodeError as e:
-                raise Exception(f'配置文件 {self.config_file_name} 语法错误: {e}')
+                raise Exception(f'Syntax error in config file {self.config_file_name}: {e}')

        if completion:
            for key in self.template_data:
--- a/pkg/config/impls/pymodule.py
+++ b/pkg/config/impls/pymodule.py
@@ -7,13 +7,13 @@ from .. import model as file_model


 class PythonModuleConfigFile(file_model.ConfigFile):
-    """Python模块配置文件"""
+    """Python module config file"""

    config_file_name: str = None
-    """配置文件名"""
+    """Config file name"""

    template_file_name: str = None
-    """模板文件名"""
+    """Template file name"""

    def __init__(self, config_file_name: str, template_file_name: str) -> None:
        self.config_file_name = config_file_name
@@ -42,7 +42,7 @@ class PythonModuleConfigFile(file_model.ConfigFile):

            cfg[key] = getattr(module, key)

-        # 从模板模块文件中进行补全
+        # complete from template module file
        if completion:
            module_name = os.path.splitext(os.path.basename(self.template_file_name))[0]
            module = importlib.import_module(module_name)
@@ -60,7 +60,7 @@ class PythonModuleConfigFile(file_model.ConfigFile):
        return cfg

    async def save(self, data: dict):
-        logging.warning('Python模块配置文件不支持保存')
+        logging.warning('Python module config file does not support saving')

    def save_sync(self, data: dict):
-        logging.warning('Python模块配置文件不支持保存')
+        logging.warning('Python module config file does not support saving')
--- a/pkg/config/impls/yaml.py
+++ b/pkg/config/impls/yaml.py
@@ -6,7 +6,7 @@ from .. import model as file_model


 class YAMLConfigFile(file_model.ConfigFile):
-    """YAML配置文件"""
+    """YAML config file"""

    def __init__(
        self,
@@ -42,7 +42,7 @@ class YAMLConfigFile(file_model.ConfigFile):
            try:
                cfg = yaml.load(f, Loader=yaml.FullLoader)
            except yaml.YAMLError as e:
-                raise Exception(f'配置文件 {self.config_file_name} 语法错误: {e}')
+                raise Exception(f'Syntax error in config file {self.config_file_name}: {e}')

        if completion:
            for key in self.template_data:
--- a/pkg/config/manager.py
+++ b/pkg/config/manager.py
@@ -5,27 +5,27 @@ from .impls import pymodule, json as json_file, yaml as yaml_file


 class ConfigManager:
-    """配置文件管理器"""
+    """Config file manager"""

    name: str = None
-    """配置管理器名"""
+    """Config manager name"""

    description: str = None
-    """配置管理器描述"""
+    """Config manager description"""

    schema: dict = None
-    """配置文件 schema
-    需要符合 JSON Schema Draft 7 规范
+    """Config file schema
+    Must conform to JSON Schema Draft 7 specification
    """

    file: file_model.ConfigFile = None
-    """配置文件实例"""
+    """Config file instance"""

    data: dict = None
-    """配置数据"""
+    """Config data"""

    doc_link: str = None
-    """配置文件文档链接"""
+    """Config file documentation link"""

    def __init__(self, cfg_file: file_model.ConfigFile) -> None:
        self.file = cfg_file
@@ -42,15 +42,15 @@ class ConfigManager:


 async def load_python_module_config(config_name: str, template_name: str, completion: bool = True) -> ConfigManager:
-    """加载Python模块配置文件
+    """Load Python module config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        completion (bool): Whether to automatically complete the config file in memory

    Returns:
-        ConfigManager: 配置文件管理器
+        ConfigManager: Config file manager
    """
    cfg_inst = pymodule.PythonModuleConfigFile(config_name, template_name)

@@ -66,13 +66,13 @@ async def load_json_config(
    template_data: dict = None,
    completion: bool = True,
 ) -> ConfigManager:
-    """加载JSON配置文件
+    """Load JSON config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        template_data (dict): 模板数据
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        template_data (dict): Template data
+        completion (bool): Whether to automatically complete the config file in memory
    """
    cfg_inst = json_file.JSONConfigFile(config_name, template_name, template_data)

@@ -88,16 +88,16 @@ async def load_yaml_config(
    template_data: dict = None,
    completion: bool = True,
 ) -> ConfigManager:
-    """加载YAML配置文件
+    """Load YAML config file

    Args:
-        config_name (str): 配置文件名
-        template_name (str): 模板文件名
-        template_data (dict): 模板数据
-        completion (bool): 是否自动补全内存中的配置文件
+        config_name (str): Config file name
+        template_name (str): Template file name
+        template_data (dict): Template data
+        completion (bool): Whether to automatically complete the config file in memory

    Returns:
-        ConfigManager: 配置文件管理器
+        ConfigManager: Config file manager
    """
    cfg_inst = yaml_file.YAMLConfigFile(config_name, template_name, template_data)

--- a/pkg/config/model.py
+++ b/pkg/config/model.py
@@ -2,16 +2,16 @@ import abc


 class ConfigFile(metaclass=abc.ABCMeta):
-    """配置文件抽象类"""
+    """Config file abstract class"""

    config_file_name: str = None
-    """配置文件名"""
+    """Config file name"""

    template_file_name: str = None
-    """模板文件名"""
+    """Template file name"""

    template_data: dict = None
-    """模板数据"""
+    """Template data"""

    @abc.abstractmethod
    def exists(self) -> bool:
--- a/pkg/core/app.py
+++ b/pkg/core/app.py
@@ -21,15 +21,18 @@ from ..api.http.service import user as user_service
 from ..api.http.service import model as model_service
 from ..api.http.service import pipeline as pipeline_service
 from ..api.http.service import bot as bot_service
+from ..api.http.service import knowledge as knowledge_service
 from ..discover import engine as discover_engine
 from ..storage import mgr as storagemgr
 from ..utils import logcache
 from . import taskmgr
 from . import entities as core_entities
+from ..rag.knowledge import kbmgr as rag_mgr
+from ..vector import mgr as vectordb_mgr


 class Application:
-    """运行时应用对象和上下文"""
+    """Runtime application object and context"""

    event_loop: asyncio.AbstractEventLoop = None

@@ -46,10 +49,12 @@ class Application:

    model_mgr: llm_model_mgr.ModelManager = None

-    # TODO 移动到 pipeline 里
+    rag_mgr: rag_mgr.RAGManager = None
+
+    # TODO move to pipeline
    tool_mgr: llm_tool_mgr.ToolManager = None

-    # ======= 配置管理器 =======
+    # ======= Config manager =======

    command_cfg: config_mgr.ConfigManager = None  # deprecated

@@ -63,7 +68,7 @@ class Application:

    instance_config: config_mgr.ConfigManager = None

-    # ======= 元数据配置管理器 =======
+    # ======= Metadata config manager =======

    sensitive_meta: config_mgr.ConfigManager = None

@@ -92,6 +97,8 @@ class Application:

    persistence_mgr: persistencemgr.PersistenceManager = None

+    vector_db_mgr: vectordb_mgr.VectorDBManager = None
+
    http_ctrl: http_controller.HTTPController = None

    log_cache: logcache.LogCache = None
@@ -102,12 +109,16 @@ class Application:

    user_service: user_service.UserService = None

-    model_service: model_service.ModelsService = None
+    llm_model_service: model_service.LLMModelsService = None
+
+    embedding_models_service: model_service.EmbeddingModelsService = None

    pipeline_service: pipeline_service.PipelineService = None

    bot_service: bot_service.BotService = None

+    knowledge_service: knowledge_service.KnowledgeService = None
+
    def __init__(self):
        pass

@@ -142,6 +153,7 @@ class Application:
                name='http-api-controller',
                scopes=[core_entities.LifecycleControlScope.APPLICATION],
            )
+
            self.task_mgr.create_task(
                never_ending(),
                name='never-ending-task',
@@ -153,14 +165,14 @@ class Application:
        except asyncio.CancelledError:
            pass
        except Exception as e:
-            self.logger.error(f'应用运行致命异常: {e}')
+            self.logger.error(f'Application runtime fatal exception: {e}')
            self.logger.debug(f'Traceback: {traceback.format_exc()}')

    def dispose(self):
        self.plugin_connector.dispose()

    async def print_web_access_info(self):
-        """打印访问 webui 的提示"""
+        """Print access webui tips"""

        if not os.path.exists(os.path.join('.', 'web/out')):
            self.logger.warning('WebUI 文件缺失，请根据文档部署：https://docs.langbot.app/zh')
--- a/pkg/core/boot.py
+++ b/pkg/core/boot.py
@@ -8,7 +8,7 @@ from . import app
 from . import stage
 from ..utils import constants, importutil

-# 引入启动阶段实现以便注册
+# Import startup stage implementation to register
 from . import stages

 importutil.import_modules_in_pkg(stages)
@@ -25,7 +25,7 @@ stage_order = [


 async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:
-    # 确定是否为调试模式
+    # Determine if it is debug mode
    if 'DEBUG' in os.environ and os.environ['DEBUG'] in ['true', '1']:
        constants.debug_mode = True

@@ -33,7 +33,7 @@ async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:

    ap.event_loop = loop

-    # 执行启动阶段
+    # Execute startup stage
    for stage_name in stage_order:
        stage_cls = stage.preregistered_stages[stage_name]
        stage_inst = stage_cls()
@@ -47,12 +47,12 @@ async def make_app(loop: asyncio.AbstractEventLoop) -> app.Application:

 async def main(loop: asyncio.AbstractEventLoop):
    try:
-        # 挂系统信号处理
+        # Hang system signal processing
        import signal

        def signal_handler(sig, frame):
            app_inst.dispose()
-            print('[Signal] 程序退出.')
+            print('[Signal] Program exit.')
            os._exit(0)

        signal.signal(signal.SIGINT, signal_handler)
--- a/pkg/core/bootutils/deps.py
+++ b/pkg/core/bootutils/deps.py
@@ -2,8 +2,8 @@ import pip
 import os
 from ...utils import pkgmgr

-# 检查依赖，防止用户未安装
-# 左边为引入名称，右边为依赖名称
+# Check dependencies to prevent users from not installing
+# Left is the import name, right is the dependency name
 required_deps = {
    'requests': 'requests',
    'openai': 'openai',
@@ -65,7 +65,7 @@ async def install_deps(deps: list[str]):
 async def precheck_plugin_deps():
    print('[Startup] Prechecking plugin dependencies...')

-    # 只有在plugins目录存在时才执行插件依赖安装
+    # Only execute plugin dependency installation when the plugins directory exists
    if os.path.exists('plugins'):
        for dir in os.listdir('plugins'):
            subdir = os.path.join('plugins', dir)
--- a/pkg/core/bootutils/log.py
+++ b/pkg/core/bootutils/log.py
@@ -17,7 +17,7 @@ log_colors_config = {


 async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.Logger:
-    # 删除所有现有的logger
+    # Remove all existing loggers
    for handler in logging.root.handlers[:]:
        logging.root.removeHandler(handler)

@@ -54,13 +54,13 @@ async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.
        handler.setFormatter(color_formatter)
        qcg_logger.addHandler(handler)

-    qcg_logger.debug('日志初始化完成，日志级别：%s' % level)
+    qcg_logger.debug('Logging initialized, log level: %s' % level)
    logging.basicConfig(
-        level=logging.CRITICAL,  # 设置日志输出格式
+        level=logging.CRITICAL,  # Set log output format
        format='[DEPR][%(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
+        # Log output format
+        # -8 is a placeholder, left-align the output, and output length is 8
+        datefmt='%Y-%m-%d %H:%M:%S',  # Time output format
        handlers=[logging.NullHandler()],
    )

--- a/pkg/core/migration.py
+++ b/pkg/core/migration.py
@@ -7,11 +7,11 @@ from . import app


 preregistered_migrations: list[typing.Type[Migration]] = []
-"""当前阶段暂不支持扩展"""
+"""Currently not supported for extension"""


 def migration_class(name: str, number: int):
-    """注册一个迁移"""
+    """Register a migration"""

    def decorator(cls: typing.Type[Migration]) -> typing.Type[Migration]:
        cls.name = name
@@ -23,7 +23,7 @@ def migration_class(name: str, number: int):


 class Migration(abc.ABC):
-    """一个版本的迁移"""
+    """A version migration"""

    name: str

@@ -36,10 +36,10 @@ class Migration(abc.ABC):

    @abc.abstractmethod
    async def need_migrate(self) -> bool:
-        """判断当前环境是否需要运行此迁移"""
+        """Determine if the current environment needs to run this migration"""
        pass

    @abc.abstractmethod
    async def run(self):
-        """执行迁移"""
+        """Run migration"""
        pass
--- a/pkg/core/note.py
+++ b/pkg/core/note.py
@@ -9,7 +9,7 @@ preregistered_notes: list[typing.Type[LaunchNote]] = []


 def note_class(name: str, number: int):
-    """注册一个启动信息"""
+    """Register a launch information"""

    def decorator(cls: typing.Type[LaunchNote]) -> typing.Type[LaunchNote]:
        cls.name = name
@@ -21,7 +21,7 @@ def note_class(name: str, number: int):


 class LaunchNote(abc.ABC):
-    """启动信息"""
+    """Launch information"""

    name: str

@@ -34,10 +34,10 @@ class LaunchNote(abc.ABC):

    @abc.abstractmethod
    async def need_show(self) -> bool:
-        """判断当前环境是否需要显示此启动信息"""
+        """Determine if the current environment needs to display this launch information"""
        pass

    @abc.abstractmethod
    async def yield_note(self) -> typing.AsyncGenerator[typing.Tuple[str, int], None]:
-        """生成启动信息"""
+        """Generate launch information"""
        pass
--- a/pkg/core/notes/n001_classic_msgs.py
+++ b/pkg/core/notes/n001_classic_msgs.py
@@ -7,7 +7,7 @@ from .. import note

@note.note_class('ClassicNotes', 1)
 class ClassicNotes(note.LaunchNote):
-    """经典启动信息"""
+    """Classic launch information"""

    async def need_show(self) -> bool:
        return True
--- a/pkg/core/notes/n002_selection_mode_on_windows.py
+++ b/pkg/core/notes/n002_selection_mode_on_windows.py
@@ -9,7 +9,7 @@ from .. import note

@note.note_class('SelectionModeOnWindows', 2)
 class SelectionModeOnWindows(note.LaunchNote):
-    """Windows 上的选择模式提示信息"""
+    """Selection mode prompt information on Windows"""

    async def need_show(self) -> bool:
        return os.name == 'nt'
@@ -19,3 +19,8 @@ class SelectionModeOnWindows(note.LaunchNote):
            """您正在使用 Windows 系统，若窗口左上角显示处于”选择“模式，程序将被暂停运行，此时请右键窗口中空白区域退出选择模式。""",
            logging.INFO,
        )
+
+        yield (
+            """You are using Windows system, if the top left corner of the window displays "Selection" mode, the program will be paused running, please right-click on the blank area in the window to exit the selection mode.""",
+            logging.INFO,
+        )
--- a/pkg/core/stage.py
+++ b/pkg/core/stage.py
@@ -7,9 +7,9 @@ from . import app


 preregistered_stages: dict[str, typing.Type[BootingStage]] = {}
-"""预注册的请求处理阶段。在初始化时，所有请求处理阶段类会被注册到此字典中。
+"""Pre-registered request processing stages. All request processing stage classes are registered in this dictionary during initialization.

-当前阶段暂不支持扩展
+Currently not supported for extension
 """


@@ -22,11 +22,11 @@ def stage_class(name: str):


 class BootingStage(abc.ABC):
-    """启动阶段"""
+    """Booting stage"""

    name: str = None

    @abc.abstractmethod
    async def run(self, ap: app.Application):
-        """启动"""
+        """Run"""
        pass
--- a/pkg/core/stages/build_app.py
+++ b/pkg/core/stages/build_app.py
@@ -10,6 +10,7 @@ from ...command import cmdmgr
 from ...provider.session import sessionmgr as llm_session_mgr
 from ...provider.modelmgr import modelmgr as llm_model_mgr
 from ...provider.tools import toolmgr as llm_tool_mgr
+from ...rag.knowledge import kbmgr as rag_mgr
 from ...platform import botmgr as im_mgr
 from ...persistence import mgr as persistencemgr
 from ...api.http.controller import main as http_controller
@@ -17,18 +18,20 @@ from ...api.http.service import user as user_service
 from ...api.http.service import model as model_service
 from ...api.http.service import pipeline as pipeline_service
 from ...api.http.service import bot as bot_service
+from ...api.http.service import knowledge as knowledge_service
 from ...discover import engine as discover_engine
 from ...storage import mgr as storagemgr
 from ...utils import logcache
+from ...vector import mgr as vectordb_mgr
 from .. import taskmgr


@stage.stage_class('BuildAppStage')
 class BuildAppStage(stage.BootingStage):
-    """构建应用阶段"""
+    """Build LangBot application"""

    async def run(self, ap: app.Application):
-        """构建app对象的各个组件对象并初始化"""
+        """Build LangBot application"""
        ap.task_mgr = taskmgr.AsyncTaskManager(ap)

        discover = discover_engine.ComponentDiscoveryEngine(ap)
@@ -43,7 +46,7 @@ class BuildAppStage(stage.BootingStage):
        await ver_mgr.initialize()
        ap.ver_mgr = ver_mgr

-        # 发送公告
+        # Send announcement
        ann_mgr = announce.AnnouncementManager(ap)
        ap.ann_mgr = ann_mgr

@@ -92,6 +95,15 @@ class BuildAppStage(stage.BootingStage):
        await pipeline_mgr.initialize()
        ap.pipeline_mgr = pipeline_mgr

+        rag_mgr_inst = rag_mgr.RAGManager(ap)
+        await rag_mgr_inst.initialize()
+        ap.rag_mgr = rag_mgr_inst
+
+        # 初始化向量数据库管理器
+        vectordb_mgr_inst = vectordb_mgr.VectorDBManager(ap)
+        await vectordb_mgr_inst.initialize()
+        ap.vector_db_mgr = vectordb_mgr_inst
+
        http_ctrl = http_controller.HTTPController(ap)
        await http_ctrl.initialize()
        ap.http_ctrl = http_ctrl
@@ -99,8 +111,11 @@ class BuildAppStage(stage.BootingStage):
        user_service_inst = user_service.UserService(ap)
        ap.user_service = user_service_inst

-        model_service_inst = model_service.ModelsService(ap)
-        ap.model_service = model_service_inst
+        llm_model_service_inst = model_service.LLMModelsService(ap)
+        ap.llm_model_service = llm_model_service_inst
+
+        embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
+        ap.embedding_models_service = embedding_models_service_inst

        pipeline_service_inst = pipeline_service.PipelineService(ap)
        ap.pipeline_service = pipeline_service_inst
@@ -108,5 +123,8 @@ class BuildAppStage(stage.BootingStage):
        bot_service_inst = bot_service.BotService(ap)
        ap.bot_service = bot_service_inst

+        knowledge_service_inst = knowledge_service.KnowledgeService(ap)
+        ap.knowledge_service = knowledge_service_inst
+
        ctrl = controller.Controller(ap)
        ap.ctrl = ctrl
--- a/pkg/core/stages/genkeys.py
+++ b/pkg/core/stages/genkeys.py
@@ -7,11 +7,18 @@ from .. import stage, app

@stage.stage_class('GenKeysStage')
 class GenKeysStage(stage.BootingStage):
-    """生成密钥阶段"""
+    """Generate keys stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Generate keys"""

        if not ap.instance_config.data['system']['jwt']['secret']:
            ap.instance_config.data['system']['jwt']['secret'] = secrets.token_hex(16)
            await ap.instance_config.dump_config()
+
+        if 'recovery_key' not in ap.instance_config.data['system']:
+            ap.instance_config.data['system']['recovery_key'] = ''
+
+        if not ap.instance_config.data['system']['recovery_key']:
+            ap.instance_config.data['system']['recovery_key'] = secrets.token_hex(3).upper()
+            await ap.instance_config.dump_config()
--- a/pkg/core/stages/load_config.py
+++ b/pkg/core/stages/load_config.py
@@ -8,10 +8,10 @@ from ..bootutils import config

@stage.stage_class('LoadConfigStage')
 class LoadConfigStage(stage.BootingStage):
-    """加载配置文件阶段"""
+    """Load config file stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Load config file"""

        # ======= deprecated =======
        if os.path.exists('data/config/command.json'):
--- a/pkg/core/stages/migrate.py
+++ b/pkg/core/stages/migrate.py
@@ -11,10 +11,13 @@ importutil.import_modules_in_pkg(migrations)

@stage.stage_class('MigrationStage')
 class MigrationStage(stage.BootingStage):
-    """迁移阶段"""
+    """Migration stage
+
+    These migrations are legacy, only performed in version 3.x
+    """

    async def run(self, ap: app.Application):
-        """启动"""
+        """Run migration"""

        if any(
            [
@@ -29,7 +32,7 @@ class MigrationStage(stage.BootingStage):

        migrations = migration.preregistered_migrations

-        # 按照迁移号排序
+        # Sort by migration number
        migrations.sort(key=lambda x: x.number)

        for migration_cls in migrations:
@@ -37,4 +40,4 @@ class MigrationStage(stage.BootingStage):

            if await migration_instance.need_migrate():
                await migration_instance.run()
-                print(f'已执行迁移 {migration_instance.name}')
+                print(f'Migration {migration_instance.name} executed')
--- a/pkg/core/stages/setup_logger.py
+++ b/pkg/core/stages/setup_logger.py
@@ -8,7 +8,7 @@ from ..bootutils import log

 class PersistenceHandler(logging.Handler, object):
    """
-    保存日志到数据库
+    Save logs to database
    """

    ap: app.Application
@@ -19,9 +19,9 @@ class PersistenceHandler(logging.Handler, object):

    def emit(self, record):
        """
-        emit函数为自定义handler类时必重写的函数，这里可以根据需要对日志消息做一些处理，比如发送日志到服务器
+        emit function is a required function for custom handler classes, here you can process the log messages as needed, such as sending logs to the server

-        发出记录(Emit a record)
+        Emit a record
        """
        try:
            msg = self.format(record)
@@ -34,10 +34,10 @@ class PersistenceHandler(logging.Handler, object):

@stage.stage_class('SetupLoggerStage')
 class SetupLoggerStage(stage.BootingStage):
-    """设置日志器阶段"""
+    """Setup logger stage"""

    async def run(self, ap: app.Application):
-        """启动"""
+        """Setup logger"""
        persistence_handler = PersistenceHandler('LoggerHandler', ap)

        extra_handlers = []
--- a/pkg/core/stages/show_notes.py
+++ b/pkg/core/stages/show_notes.py
@@ -12,10 +12,10 @@ importutil.import_modules_in_pkg(notes)

@stage.stage_class('ShowNotesStage')
 class ShowNotesStage(stage.BootingStage):
-    """显示启动信息阶段"""
+    """Show notes stage"""

    async def run(self, ap: app.Application):
-        # 排序
+        # Sort
        note.preregistered_notes.sort(key=lambda x: x.number)

        for note_cls in note.preregistered_notes:
--- a/pkg/core/taskmgr.py
+++ b/pkg/core/taskmgr.py
@@ -9,13 +9,13 @@ from . import entities as core_entities


 class TaskContext:
-    """任务跟踪上下文"""
+    """Task tracking context"""

    current_action: str
-    """当前正在执行的动作"""
+    """Current action being executed"""

    log: str
-    """记录日志"""
+    """Log"""

    def __init__(self):
        self.current_action = 'default'
@@ -58,40 +58,40 @@ placeholder_context: TaskContext | None = None


 class TaskWrapper:
-    """任务包装器"""
+    """Task wrapper"""

    _id_index: int = 0
-    """任务ID索引"""
+    """Task ID index"""

    id: int
-    """任务ID"""
+    """Task ID"""

-    task_type: str = 'system'  # 任务类型: system 或 user
-    """任务类型"""
+    task_type: str = 'system'  # Task type: system or user
+    """Task type"""

-    kind: str = 'system_task'  # 由发起者确定任务种类，通常同质化的任务种类相同
-    """任务种类"""
+    kind: str = 'system_task'  # Task type determined by the initiator, usually the same task type
+    """Task type"""

    name: str = ''
-    """任务唯一名称"""
+    """Task unique name"""

    label: str = ''
-    """任务显示名称"""
+    """Task display name"""

    task_context: TaskContext
-    """任务上下文"""
+    """Task context"""

    task: asyncio.Task
-    """任务"""
+    """Task"""

    task_stack: list = None
-    """任务堆栈"""
+    """Task stack"""

    ap: app.Application
-    """应用实例"""
+    """Application instance"""

    scopes: list[core_entities.LifecycleControlScope]
-    """任务所属生命周期控制范围"""
+    """Task scope"""

    def __init__(
        self,
@@ -165,13 +165,13 @@ class TaskWrapper:


 class AsyncTaskManager:
-    """保存app中的所有异步任务
-    包含系统级的和用户级（插件安装、更新等由用户直接发起的）的"""
+    """Save all asynchronous tasks in the app
+    Include system-level and user-level (plugin installation, update, etc. initiated by users directly)"""

    ap: app.Application

    tasks: list[TaskWrapper]
-    """所有任务"""
+    """All tasks"""

    def __init__(self, ap: app.Application):
        self.ap = ap
--- a/pkg/entity/persistence/bot.py
+++ b/pkg/entity/persistence/bot.py
@@ -4,7 +4,7 @@ from .base import Base


 class Bot(Base):
-    """机器人"""
+    """Bot"""

    __tablename__ = 'bots'

--- a/pkg/entity/persistence/metadata.py
+++ b/pkg/entity/persistence/metadata.py
@@ -12,7 +12,7 @@ initial_metadata = [


 class Metadata(Base):
-    """数据库元数据"""
+    """Database metadata"""

    __tablename__ = 'metadata'

--- a/pkg/entity/persistence/model.py
+++ b/pkg/entity/persistence/model.py
@@ -4,7 +4,7 @@ from .base import Base


 class LLMModel(Base):
-    """LLM 模型"""
+    """LLM model"""

    __tablename__ = 'llm_models'

@@ -23,3 +23,24 @@ class LLMModel(Base):
        server_default=sqlalchemy.func.now(),
        onupdate=sqlalchemy.func.now(),
    )
+
+
+class EmbeddingModel(Base):
+    """Embedding 模型"""
+
+    __tablename__ = 'embedding_models'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    description = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    requester = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    requester_config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    api_keys = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
+    extra_args = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
+    updated_at = sqlalchemy.Column(
+        sqlalchemy.DateTime,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )
--- a/pkg/entity/persistence/pipeline.py
+++ b/pkg/entity/persistence/pipeline.py
@@ -4,7 +4,7 @@ from .base import Base


 class LegacyPipeline(Base):
-    """旧版流水线"""
+    """Legacy pipeline"""

    __tablename__ = 'legacy_pipelines'

@@ -20,13 +20,12 @@ class LegacyPipeline(Base):
    )
    for_version = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
    is_default = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
-
    stages = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
    config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)


 class PipelineRunRecord(Base):
-    """流水线运行记录"""
+    """Pipeline run record"""

    __tablename__ = 'pipeline_run_records'

@@ -43,3 +42,4 @@ class PipelineRunRecord(Base):
    started_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
    finished_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
    result = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
+    knowledge_base_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
--- a/pkg/entity/persistence/plugin.py
+++ b/pkg/entity/persistence/plugin.py
@@ -4,7 +4,7 @@ from .base import Base


 class PluginSetting(Base):
-    """插件配置"""
+    """Plugin setting"""

    __tablename__ = 'plugin_settings'

--- a/pkg/entity/persistence/rag.py
+++ b/pkg/entity/persistence/rag.py
@@ -0,0 +1,50 @@
+import sqlalchemy
+from .base import Base
+
+# Base = declarative_base()
+# DATABASE_URL = os.getenv('DATABASE_URL', 'sqlite:///./rag_knowledge.db')
+# print("Using database URL:", DATABASE_URL)
+
+
+# engine = create_engine(DATABASE_URL, connect_args={'check_same_thread': False})
+
+# SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+# def create_db_and_tables():
+#     """Creates all database tables defined in the Base."""
+#     Base.metadata.create_all(bind=engine)
+#     print('Database tables created or already exist.')
+
+
+class KnowledgeBase(Base):
+    __tablename__ = 'knowledge_bases'
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String, index=True)
+    description = sqlalchemy.Column(sqlalchemy.Text)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())
+    embedding_model_uuid = sqlalchemy.Column(sqlalchemy.String, default='')
+    top_k = sqlalchemy.Column(sqlalchemy.Integer, default=5)
+
+
+class File(Base):
+    __tablename__ = 'knowledge_base_files'
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    kb_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    file_name = sqlalchemy.Column(sqlalchemy.String)
+    extension = sqlalchemy.Column(sqlalchemy.String)
+    created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())
+    status = sqlalchemy.Column(sqlalchemy.String, default='pending')  # pending, processing, completed, failed
+
+
+class Chunk(Base):
+    __tablename__ = 'knowledge_base_chunks'
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    file_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    text = sqlalchemy.Column(sqlalchemy.Text)
+
+
+# class Vector(Base):
+#     __tablename__ = 'knowledge_base_vectors'
+#     uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+#     chunk_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
+#     embedding = sqlalchemy.Column(sqlalchemy.LargeBinary)
--- a/pkg/entity/persistence/vector.py
+++ b/pkg/entity/persistence/vector.py
@@ -0,0 +1,13 @@
+from sqlalchemy import Column, Integer, ForeignKey, LargeBinary
+from sqlalchemy.orm import declarative_base, relationship
+
+Base = declarative_base()
+
+
+class Vector(Base):
+    __tablename__ = 'vectors'
+    id = Column(Integer, primary_key=True, index=True)
+    chunk_id = Column(Integer, ForeignKey('chunks.id'), unique=True)
+    embedding = Column(LargeBinary)  # Store embeddings as binary
+
+    chunk = relationship('Chunk', back_populates='vector')
--- a/pkg/entity/rag/init.py
+++ b/pkg/entity/rag/init.py
--- a/pkg/entity/rag/retriever.py
+++ b/pkg/entity/rag/retriever.py
@@ -0,0 +1,13 @@
+from __future__ import annotations
+
+import pydantic
+
+from typing import Any
+
+
+class RetrieveResultEntry(pydantic.BaseModel):
+    id: str
+
+    metadata: dict[str, Any]
+
+    distance: float
--- a/pkg/persistence/database.py
+++ b/pkg/persistence/database.py
@@ -11,7 +11,7 @@ preregistered_managers: list[type[BaseDatabaseManager]] = []


 def manager_class(name: str) -> None:
-    """注册一个数据库管理类"""
+    """Register a database manager class"""

    def decorator(cls: type[BaseDatabaseManager]) -> type[BaseDatabaseManager]:
        cls.name = name
@@ -22,7 +22,7 @@ def manager_class(name: str) -> None:


 class BaseDatabaseManager(abc.ABC):
-    """基础数据库管理类"""
+    """Base database manager class"""

    name: str

--- a/pkg/persistence/databases/sqlite.py
+++ b/pkg/persistence/databases/sqlite.py
@@ -7,7 +7,7 @@ from .. import database

@database.manager_class('sqlite')
 class SQLiteDatabaseManager(database.BaseDatabaseManager):
-    """SQLite 数据库管理类"""
+    """SQLite database manager"""

    async def initialize(self) -> None:
        sqlite_path = 'data/langbot.db'
--- a/pkg/persistence/mgr.py
+++ b/pkg/persistence/mgr.py
@@ -22,12 +22,12 @@ importutil.import_modules_in_pkg(persistence)


 class PersistenceManager:
-    """持久化模块管理器"""
+    """Persistence module manager"""

    ap: app.Application

    db: database.BaseDatabaseManager
-    """数据库管理器"""
+    """Database manager"""

    meta: sqlalchemy.MetaData

@@ -111,7 +111,7 @@ class PersistenceManager:
                'stages': pipeline_service.default_stage_order,
                'is_default': True,
                'name': 'ChatPipeline',
-                'description': '默认提供的流水线，您配置的机器人、第一个模型将自动绑定到此流水线',
+                'description': 'Default pipeline, new bots will be bound to this pipeline | 默认提供的流水线，您配置的机器人将自动绑定到此流水线',
                'config': pipeline_config,
            }

--- a/pkg/persistence/migration.py
+++ b/pkg/persistence/migration.py
@@ -10,7 +10,7 @@ preregistered_db_migrations: list[typing.Type[DBMigration]] = []


 def migration_class(number: int):
-    """迁移类装饰器"""
+    """Migration class decorator"""

    def wrapper(cls: typing.Type[DBMigration]) -> typing.Type[DBMigration]:
        cls.number = number
@@ -21,20 +21,20 @@ def migration_class(number: int):


 class DBMigration(abc.ABC):
-    """数据库迁移"""
+    """Database migration"""

    number: int
-    """迁移号"""
+    """Migration number"""

    def __init__(self, ap: app.Application):
        self.ap = ap

    @abc.abstractmethod
    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        pass

    @abc.abstractmethod
    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm001_migrate_v3_config.py
+++ b/pkg/persistence/migrations/dbm001_migrate_v3_config.py
@@ -15,21 +15,21 @@ from ...entity.persistence import (

@migration.migration_class(1)
 class DBMigrateV3Config(migration.DBMigration):
-    """从 v3 的配置迁移到 v4 的数据库"""
+    """Migrate v3 config to v4 database"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        """
-        将 data/config 下的所有配置文件进行迁移。
-        迁移后，之前的配置文件都保存到 data/legacy/config 下。
-        迁移后，data/metadata/ 下的所有配置文件都保存到 data/legacy/metadata 下。
+        Migrate all config files under data/config.
+        After migration, all previous config files are saved under data/legacy/config.
+        After migration, all config files under data/metadata/ are saved under data/legacy/metadata.
        """

        if self.ap.provider_cfg is None:
            return

-        # ======= 迁移模型 =======
-        # 只迁移当前选中的模型
+        # ======= Migrate model =======
+        # Only migrate the currently selected model
        model_name = self.ap.provider_cfg.data.get('model', 'gpt-4o')

        model_requester = 'openai-chat-completions'
@@ -91,8 +91,8 @@ class DBMigrateV3Config(migration.DBMigration):
            sqlalchemy.insert(persistence_model.LLMModel).values(**llm_model_data)
        )

-        # ======= 迁移流水线配置 =======
-        # 修改到默认流水线
+        # ======= Migrate pipeline config =======
+        # Modify to default pipeline
        default_pipeline = [
            self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
            for pipeline in (
@@ -184,8 +184,8 @@ class DBMigrateV3Config(migration.DBMigration):
                .where(persistence_pipeline.LegacyPipeline.uuid == default_pipeline['uuid'])
            )

-        # ======= 迁移机器人 =======
-        # 只迁移启用的机器人
+        # ======= Migrate bot =======
+        # Only migrate enabled bots
        for adapter in self.ap.platform_cfg.data.get('platform-adapters', []):
            if not adapter.get('enable'):
                continue
@@ -207,7 +207,7 @@ class DBMigrateV3Config(migration.DBMigration):

            await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_bot.Bot).values(**bot_data))

-        # ======= 迁移系统设置 =======
+        # ======= Migrate system settings =======
        self.ap.instance_config.data['admins'] = self.ap.system_cfg.data['admin-sessions']
        self.ap.instance_config.data['api']['port'] = self.ap.system_cfg.data['http-api']['port']
        self.ap.instance_config.data['command'] = {
@@ -223,7 +223,7 @@ class DBMigrateV3Config(migration.DBMigration):
        await self.ap.instance_config.dump_config()

        # ======= move files =======
-        # 迁移 data/config 下的所有配置文件
+        # Migrate all config files under data/config
        all_legacy_dir_name = [
            'config',
            # 'metadata',
@@ -246,4 +246,4 @@ class DBMigrateV3Config(migration.DBMigration):
            move_legacy_files(dir_name)

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
--- a/pkg/persistence/migrations/dbm002_combine_quote_msg_config.py
+++ b/pkg/persistence/migrations/dbm002_combine_quote_msg_config.py
@@ -7,10 +7,10 @@ from ...entity.persistence import pipeline as persistence_pipeline

@migration.migration_class(2)
 class DBMigrateCombineQuoteMsgConfig(migration.DBMigration):
-    """引用消息合并配置"""
+    """Combine quote message config"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        # read all pipelines
        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))

@@ -37,5 +37,5 @@ class DBMigrateCombineQuoteMsgConfig(migration.DBMigration):
            )

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm003_n8n_config.py
+++ b/pkg/persistence/migrations/dbm003_n8n_config.py
@@ -7,10 +7,10 @@ from ...entity.persistence import pipeline as persistence_pipeline

@migration.migration_class(3)
 class DBMigrateN8nConfig(migration.DBMigration):
-    """N8n配置"""
+    """N8n config"""

    async def upgrade(self):
-        """升级"""
+        """Upgrade"""
        # read all pipelines
        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))

@@ -45,5 +45,5 @@ class DBMigrateN8nConfig(migration.DBMigration):
            )

    async def downgrade(self):
-        """降级"""
+        """Downgrade"""
        pass
--- a/pkg/persistence/migrations/dbm004_rag_kb_uuid.py
+++ b/pkg/persistence/migrations/dbm004_rag_kb_uuid.py
@@ -0,0 +1,38 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(4)
+class DBMigrateRAGKBUUID(migration.DBMigration):
+    """RAG知识库UUID"""
+
+    async def upgrade(self):
+        """升级"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            if 'knowledge-base' not in config['ai']['local-agent']:
+                config['ai']['local-agent']['knowledge-base'] = ''
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """降级"""
+        pass
--- a/pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py
+++ b/pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py
@@ -0,0 +1,38 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(5)
+class DBMigratePipelineRemoveCotConfig(migration.DBMigration):
+    """Pipeline remove cot config"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            if 'remove-think' not in config['output']['misc']:
+                config['output']['misc']['remove-think'] = False
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass
--- a/pkg/persistence/migrations/dbm006_plugin_install_source.py
+++ b/pkg/persistence/migrations/dbm006_plugin_install_source.py
@@ -2,7 +2,7 @@ import sqlalchemy
 from .. import migration


-@migration.migration_class(5)
+@migration.migration_class(6)
 class DBMigratePluginInstallSource(migration.DBMigration):
    """插件安装来源"""

--- a/pkg/pipeline/bansess/bansess.py
+++ b/pkg/pipeline/bansess/bansess.py
@@ -6,9 +6,9 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query

@stage.stage_class('BanSessionCheckStage')
 class BanSessionCheckStage(stage.PipelineStage):
-    """访问控制处理阶段
+    """Access control processing stage

-    仅检查query中群号或个人号是否在访问控制列表中。
+    Only check if the group or personal number in the query is in the access control list.
    """

    async def initialize(self, pipeline_config: dict):
@@ -41,5 +41,7 @@ class BanSessionCheckStage(stage.PipelineStage):
        return entities.StageProcessResult(
            result_type=entities.ResultType.CONTINUE if ctn else entities.ResultType.INTERRUPT,
            new_query=query,
-            console_notice=f'根据访问控制忽略消息: {query.launcher_type.value}_{query.launcher_id}' if not ctn else '',
+            console_notice=f'Ignore message according to access control: {query.launcher_type.value}_{query.launcher_id}'
+            if not ctn
+            else '',
        )
--- a/pkg/pipeline/cntfilter/filter.py
+++ b/pkg/pipeline/cntfilter/filter.py
@@ -13,13 +13,13 @@ preregistered_filters: list[typing.Type[ContentFilter]] = []
 def filter_class(
    name: str,
 ) -> typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]:
-    """内容过滤器类装饰器
+    """Content filter class decorator

    Args:
-        name (str): 过滤器名称
+        name (str): Filter name

    Returns:
-        typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]: 装饰器
+        typing.Callable[[typing.Type[ContentFilter]], typing.Type[ContentFilter]]: Decorator
    """

    def decorator(cls: typing.Type[ContentFilter]) -> typing.Type[ContentFilter]:
@@ -35,7 +35,7 @@ def filter_class(


 class ContentFilter(metaclass=abc.ABCMeta):
-    """内容过滤器抽象类"""
+    """Content filter abstract class"""

    name: str

@@ -46,31 +46,31 @@ class ContentFilter(metaclass=abc.ABCMeta):

    @property
    def enable_stages(self):
-        """启用的阶段
+        """Enabled stages

-        默认为消息请求AI前后的两个阶段。
+        Default is the two stages before and after the message request to AI.

-        entity.EnableStage.PRE: 消息请求AI前，此时需要检查的内容是用户的输入消息。
-        entity.EnableStage.POST: 消息请求AI后，此时需要检查的内容是AI的回复消息。
+        entity.EnableStage.PRE: Before message request to AI, the content to check is the user's input message.
+        entity.EnableStage.POST: After message request to AI, the content to check is the AI's reply message.
        """
        return [entities.EnableStage.PRE, entities.EnableStage.POST]

    async def initialize(self):
-        """初始化过滤器"""
+        """Initialize filter"""
        pass

    @abc.abstractmethod
    async def process(self, query: pipeline_query.Query, message: str = None, image_url=None) -> entities.FilterResult:
        """处理消息

-        分为前后阶段，具体取决于 enable_stages 的值。
-        对于内容过滤器来说，不需要考虑消息所处的阶段，只需要检查消息内容即可。
+        It is divided into two stages, depending on the value of enable_stages.
+        For content filters, you do not need to consider the stage of the message, you only need to check the message content.

        Args:
-            message (str): 需要检查的内容
-            image_url (str): 要检查的图片的 URL
+            message (str): Content to check
+            image_url (str): URL of the image to check

        Returns:
-            entities.FilterResult: 过滤结果，具体内容请查看 entities.FilterResult 类的文档
+            entities.FilterResult: Filter result, please refer to the documentation of entities.FilterResult class
        """
        raise NotImplementedError
--- a/pkg/pipeline/cntfilter/filters/banwords.py
+++ b/pkg/pipeline/cntfilter/filters/banwords.py
@@ -8,7 +8,7 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query

@filter_model.filter_class('ban-word-filter')
 class BanWordFilter(filter_model.ContentFilter):
-    """根据内容过滤"""
+    """Filter content"""

    async def initialize(self):
        pass
--- a/pkg/pipeline/cntfilter/filters/cntignore.py
+++ b/pkg/pipeline/cntfilter/filters/cntignore.py
@@ -8,7 +8,7 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query

@filter_model.filter_class('content-ignore')
 class ContentIgnore(filter_model.ContentFilter):
-    """根据内容忽略消息"""
+    """Ignore message according to content"""

    @property
    def enable_stages(self):
@@ -24,7 +24,7 @@ class ContentIgnore(filter_model.ContentFilter):
                        level=entities.ResultLevel.BLOCK,
                        replacement='',
                        user_notice='',
-                        console_notice='根据 ignore_rules 中的 prefix 规则，忽略消息',
+                        console_notice='Ignore message according to prefix rule in ignore_rules',
                    )

        if 'regexp' in query.pipeline_config['trigger']['ignore-rules']:
@@ -34,7 +34,7 @@ class ContentIgnore(filter_model.ContentFilter):
                        level=entities.ResultLevel.BLOCK,
                        replacement='',
                        user_notice='',
-                        console_notice='根据 ignore_rules 中的 regexp 规则，忽略消息',
+                        console_notice='Ignore message according to regexp rule in ignore_rules',
                    )

        return entities.FilterResult(
--- a/pkg/pipeline/longtext/longtext.py
+++ b/pkg/pipeline/longtext/longtext.py
@@ -15,9 +15,9 @@ importutil.import_modules_in_pkg(strategies)

@stage.stage_class('LongTextProcessStage')
 class LongTextProcessStage(stage.PipelineStage):
-    """长消息处理阶段
+    """Long message processing stage

-    改写：
+    Rewrite:
        - resp_message_chain
    """

@@ -35,22 +35,22 @@ class LongTextProcessStage(stage.PipelineStage):
                        use_font = 'C:/Windows/Fonts/msyh.ttc'
                        if not os.path.exists(use_font):
                            self.ap.logger.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，您可以在配置文件中调整相关设置。'
+                                'Font file not found, and Windows system font cannot be used, switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'
                            )
                            config['blob_message_strategy'] = 'forward'
                        else:
-                            self.ap.logger.info('使用Windows自带字体：' + use_font)
+                            self.ap.logger.info('Using Windows system font: ' + use_font)
                            config['font-path'] = use_font
                    else:
                        self.ap.logger.warn(
-                            '未找到字体文件，且无法使用系统自带字体，更换为转发消息组件以发送长消息，您可以在配置文件中调整相关设置。'
+                            'Font file not found, and system font cannot be used, switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'
                        )

                        pipeline_config['output']['long-text-processing']['strategy'] = 'forward'
            except Exception:
                traceback.print_exc()
                self.ap.logger.error(
-                    '加载字体文件失败({})，更换为转发消息组件以发送长消息，您可以在配置文件中调整相关设置。'.format(
+                    'Failed to load font file ({}), switch to forward message component to send long messages, you can adjust the related settings in the configuration file.'.format(
                        use_font
                    )
                )
@@ -62,7 +62,7 @@ class LongTextProcessStage(stage.PipelineStage):
                self.strategy_impl = strategy_cls(self.ap)
                break
        else:
-            raise ValueError(f'未找到名为 {config["strategy"]} 的长消息处理策略')
+            raise ValueError(f'Long message processing strategy not found: {config["strategy"]}')

        await self.strategy_impl.initialize()

@@ -76,7 +76,7 @@ class LongTextProcessStage(stage.PipelineStage):
                break

        if contains_non_plain:
-            self.ap.logger.debug('消息中包含非 Plain 组件，跳过长消息处理。')
+            self.ap.logger.debug('Message contains non-Plain components, skip long message processing.')
        elif (
            len(str(query.resp_message_chain[-1]))
            > query.pipeline_config['output']['long-text-processing']['threshold']
--- a/pkg/pipeline/longtext/strategies/forward.py
+++ b/pkg/pipeline/longtext/strategies/forward.py
@@ -15,17 +15,17 @@ Forward = platform_message.Forward
 class ForwardComponentStrategy(strategy_model.LongTextStrategy):
    async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
        display = ForwardMessageDiaplay(
-            title='群聊的聊天记录',
-            brief='[聊天记录]',
-            source='聊天记录',
-            preview=['QQ用户: ' + message],
-            summary='查看1条转发消息',
+            title='Group chat history',
+            brief='[Chat history]',
+            source='Chat history',
+            preview=['User: ' + message],
+            summary='View 1 forwarded message',
        )

        node_list = [
            platform_message.ForwardMessageNode(
                sender_id=query.adapter.bot_account_id,
-                sender_name='QQ用户',
+                sender_name='User',
                message_chain=platform_message.MessageChain([message]),
            )
        ]
--- a/pkg/pipeline/longtext/strategy.py
+++ b/pkg/pipeline/longtext/strategy.py
@@ -15,13 +15,13 @@ preregistered_strategies: list[typing.Type[LongTextStrategy]] = []
 def strategy_class(
    name: str,
 ) -> typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]:
-    """长文本处理策略类装饰器
+    """Long text processing strategy class decorator

    Args:
-        name (str): 策略名称
+        name (str): Strategy name

    Returns:
-        typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]: 装饰器
+        typing.Callable[[typing.Type[LongTextStrategy]], typing.Type[LongTextStrategy]]: Decorator
    """

    def decorator(cls: typing.Type[LongTextStrategy]) -> typing.Type[LongTextStrategy]:
@@ -37,7 +37,7 @@ def strategy_class(


 class LongTextStrategy(metaclass=abc.ABCMeta):
-    """长文本处理策略抽象类"""
+    """Long text processing strategy abstract class"""

    name: str

@@ -53,13 +53,13 @@ class LongTextStrategy(metaclass=abc.ABCMeta):
    async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
        """处理长文本

-        在 platform.json 中配置 long-text-process 字段，只要 文本长度超过了 threshold 就会调用此方法
+        If the text length exceeds the threshold, this method will be called.

        Args:
-            message (str): 消息
-            query (core_entities.Query): 此次请求的上下文对象
+            message (str): Message
+            query (core_entities.Query): Query object

        Returns:
-            list[platform_message.MessageComponent]: 转换后的 平台 消息组件列表
+            list[platform_message.MessageComponent]: Converted platform message components
        """
        return []
--- a/pkg/pipeline/msgtrun/msgtrun.py
+++ b/pkg/pipeline/msgtrun/msgtrun.py
@@ -11,9 +11,9 @@ importutil.import_modules_in_pkg(truncators)

@stage.stage_class('ConversationMessageTruncator')
 class ConversationMessageTruncator(stage.PipelineStage):
-    """会话消息截断器
+    """Conversation message truncator

-    用于截断会话消息链，以适应平台消息长度限制。
+    Used to truncate the conversation message chain to adapt to the LLM message length limit.
    """

    trun: truncator.Truncator
@@ -26,7 +26,7 @@ class ConversationMessageTruncator(stage.PipelineStage):
                self.trun = trun(self.ap)
                break
        else:
-            raise ValueError(f'未知的截断器: {use_method}')
+            raise ValueError(f'Unknown truncator: {use_method}')

    async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
        """处理"""
--- a/pkg/pipeline/msgtrun/truncators/round.py
+++ b/pkg/pipeline/msgtrun/truncators/round.py
@@ -6,7 +6,7 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query

@truncator.truncator_class('round')
 class RoundTruncator(truncator.Truncator):
-    """前文回合数阶段器"""
+    """Truncate the conversation message chain to adapt to the LLM message length limit."""

    async def truncate(self, query: pipeline_query.Query) -> pipeline_query.Query:
        """截断"""
@@ -16,7 +16,7 @@ class RoundTruncator(truncator.Truncator):

        current_round = 0

-        # 从后往前遍历
+        # Traverse from back to front
        for msg in query.messages[::-1]:
            if current_round < max_round:
                temp_messages.append(msg)
--- a/pkg/pipeline/pipelinemgr.py
+++ b/pkg/pipeline/pipelinemgr.py
@@ -97,12 +97,20 @@ class RuntimePipeline:
                query.message_event, platform_events.GroupMessage
            ):
                result.user_notice.insert(0, platform_message.At(query.message_event.sender.id))
-
-            await query.adapter.reply_message(
-                message_source=query.message_event,
-                message=result.user_notice,
-                quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
-            )
+            if await query.adapter.is_stream_output_supported():
+                await query.adapter.reply_message_chunk(
+                    message_source=query.message_event,
+                    bot_message=query.resp_messages[-1],
+                    message=result.user_notice,
+                    quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
+                    is_final=[msg.is_final for msg in query.resp_messages][0],
+                )
+            else:
+                await query.adapter.reply_message(
+                    message_source=query.message_event,
+                    message=result.user_notice,
+                    quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
+                )
        if result.debug_notice:
            self.ap.logger.debug(result.debug_notice)
        if result.console_notice:
@@ -148,23 +156,27 @@ class RuntimePipeline:
                result = await result

            if isinstance(result, pipeline_entities.StageProcessResult):  # 直接返回结果
-                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {result}')
+                self.ap.logger.debug(
+                    f'Stage {stage_container.inst_name} processed query {query.query_id} res {result.result_type}'
+                )
                await self._check_output(query, result)

                if result.result_type == pipeline_entities.ResultType.INTERRUPT:
-                    self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
+                    self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
                    break
                elif result.result_type == pipeline_entities.ResultType.CONTINUE:
                    query = result.new_query
            elif isinstance(result, typing.AsyncGenerator):  # 生成器
-                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} gen')
+                self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query.query_id} gen')

                async for sub_result in result:
-                    self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {sub_result}')
+                    self.ap.logger.debug(
+                        f'Stage {stage_container.inst_name} processed query {query.query_id} res {sub_result.result_type}'
+                    )
                    await self._check_output(query, sub_result)

                    if sub_result.result_type == pipeline_entities.ResultType.INTERRUPT:
-                        self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
+                        self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
                        break
                    elif sub_result.result_type == pipeline_entities.ResultType.CONTINUE:
                        query = sub_result.new_query
@@ -196,7 +208,7 @@ class RuntimePipeline:
            if event_ctx.is_prevented_default():
                return

-            self.ap.logger.debug(f'Processing query {query}')
+            self.ap.logger.debug(f'Processing query {query.query_id}')

            await self._execute_from_stage(0, query)
        except Exception as e:
@@ -204,7 +216,7 @@ class RuntimePipeline:
            self.ap.logger.error(f'处理请求时出错 query_id={query.query_id} stage={inst_name} : {e}')
            self.ap.logger.error(f'Traceback: {traceback.format_exc()}')
        finally:
-            self.ap.logger.debug(f'Query {query} processed')
+            self.ap.logger.debug(f'Query {query.query_id} processed')
            del self.ap.query_pool.cached_queries[query.query_id]


--- a/pkg/pipeline/preproc/preproc.py
+++ b/pkg/pipeline/preproc/preproc.py
@@ -11,11 +11,11 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query

@stage.stage_class('PreProcessor')
 class PreProcessor(stage.PipelineStage):
-    """请求预处理阶段
+    """Request pre-processing stage

-    签出会话、prompt、上文、模型、内容函数。
+    Check out session, prompt, context, model, and content functions.

-    改写：
+    Rewrite:
        - session
        - prompt
        - messages
@@ -29,12 +29,12 @@ class PreProcessor(stage.PipelineStage):
        query: pipeline_query.Query,
        stage_inst_name: str,
    ) -> entities.StageProcessResult:
-        """处理"""
+        """Process"""
        selected_runner = query.pipeline_config['ai']['runner']['runner']

        session = await self.ap.sess_mgr.get_session(query)

-        # 非 local-agent 时，llm_model 为 None
+        # When not local-agent, llm_model is None
        llm_model = (
            await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
            if selected_runner == 'local-agent'
@@ -80,7 +80,7 @@ class PreProcessor(stage.PipelineStage):
                        if me.type == 'image_url':
                            msg.content.remove(me)

-        content_list = []
+        content_list: list[provider_message.ContentElement] = []

        plain_text = ''
        qoute_msg = query.pipeline_config['trigger'].get('misc', '').get('combine-quote-message')
--- a/pkg/pipeline/process/handler.py
+++ b/pkg/pipeline/process/handler.py
@@ -25,7 +25,7 @@ class MessageHandler(metaclass=abc.ABCMeta):

    def cut_str(self, s: str) -> str:
        """
-        取字符串第一行，最多20个字符，若有多行，或超过20个字符，则加省略号
+        Take the first line of the string, up to 20 characters, if there are multiple lines, or more than 20 characters, add an ellipsis
        """
        s0 = s.split('\n')[0]
        if len(s0) > 20 or '\n' in s:
--- a/pkg/pipeline/process/handlers/chat.py
+++ b/pkg/pipeline/process/handlers/chat.py
@@ -1,5 +1,6 @@
 from __future__ import annotations

+import uuid
 import typing
 import traceback

@@ -48,7 +49,6 @@ class ChatMessageHandler(handler.MessageHandler):
        if event_ctx.is_prevented_default():
            if event_ctx.event.reply is not None:
                mc = platform_message.MessageChain(event_ctx.event.reply)
-
                query.resp_messages.append(mc)

                yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
@@ -60,6 +60,10 @@ class ChatMessageHandler(handler.MessageHandler):
                query.user_message.content = event_ctx.event.alter

            text_length = 0
+            try:
+                is_stream = await query.adapter.is_stream_output_supported()
+            except AttributeError:
+                is_stream = False

            try:
                for r in runner_module.preregistered_runners:
@@ -68,21 +72,41 @@ class ChatMessageHandler(handler.MessageHandler):
                        break
                else:
                    raise ValueError(f'未找到请求运行器: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                if is_stream:
+                    resp_message_id = uuid.uuid4()
+                    await query.adapter.create_message_card(str(resp_message_id), query.message_event)
+                    async for result in runner.run(query):
+                        result.resp_message_id = str(resp_message_id)
+                        if query.resp_messages:
+                            query.resp_messages.pop()
+                        if query.resp_message_chain:
+                            query.resp_message_chain.pop()

-                async for result in runner.run(query):
-                    query.resp_messages.append(result)
+                        query.resp_messages.append(result)
+                        self.ap.logger.info(f'对话({query.query_id})流式响应: {self.cut_str(result.readable_str())}')

-                    self.ap.logger.info(f'对话({query.query_id})响应: {self.cut_str(result.readable_str())}')
+                        if result.content is not None:
+                            text_length += len(result.content)

-                    if result.content is not None:
-                        text_length += len(result.content)
+                        yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

-                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
+                else:
+                    async for result in runner.run(query):
+                        query.resp_messages.append(result)
+
+                        self.ap.logger.info(f'对话({query.query_id})响应: {self.cut_str(result.readable_str())}')
+
+                        if result.content is not None:
+                            text_length += len(result.content)
+
+                        yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

                query.session.using_conversation.messages.append(query.user_message)
+
                query.session.using_conversation.messages.extend(query.resp_messages)
            except Exception as e:
                self.ap.logger.error(f'对话({query.query_id})请求失败: {type(e).__name__} {str(e)}')
+                traceback.print_exc()

                hide_exception_info = query.pipeline_config['output']['misc']['hide-exception']

--- a/pkg/pipeline/process/handlers/command.py
+++ b/pkg/pipeline/process/handlers/command.py
@@ -16,7 +16,7 @@ class CommandHandler(handler.MessageHandler):
        self,
        query: pipeline_query.Query,
    ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
-        """处理"""
+        """Process"""

        command_text = str(query.message_chain).strip()[1:]

@@ -71,7 +71,7 @@ class CommandHandler(handler.MessageHandler):
                        )
                    )

-                    self.ap.logger.info(f'命令({query.query_id})报错: {self.cut_str(str(ret.error))}')
+                    self.ap.logger.info(f'Command({query.query_id}) error: {self.cut_str(str(ret.error))}')

                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
                elif ret.text is not None or ret.image_url is not None:
@@ -90,7 +90,7 @@ class CommandHandler(handler.MessageHandler):
                        )
                    )

-                    self.ap.logger.info(f'命令返回: {self.cut_str(str(content[0]))}')
+                    self.ap.logger.info(f'Command returned: {self.cut_str(str(content[0]))}')

                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
                else:
--- a/pkg/pipeline/process/process.py
+++ b/pkg/pipeline/process/process.py
@@ -33,11 +33,11 @@ class Processor(stage.PipelineStage):
        query: pipeline_query.Query,
        stage_inst_name: str,
    ) -> entities.StageProcessResult:
-        """处理"""
+        """Process"""
        message_text = str(query.message_chain).strip()

        self.ap.logger.info(
-            f'处理 {query.launcher_type.value}_{query.launcher_id} 的请求({query.query_id}): {message_text}'
+            f'Processing request from {query.launcher_type.value}_{query.launcher_id} ({query.query_id}): {message_text}'
        )

        async def generator():
--- a/pkg/pipeline/respback/respback.py
+++ b/pkg/pipeline/respback/respback.py
@@ -6,6 +6,7 @@ import asyncio

 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
+import langbot_plugin.api.entities.builtin.provider.message as provider_message

 from .. import stage, entities
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -36,10 +37,22 @@ class SendResponseBackStage(stage.PipelineStage):

        quote_origin = query.pipeline_config['output']['misc']['quote-origin']

-        await query.adapter.reply_message(
-            message_source=query.message_event,
-            message=query.resp_message_chain[-1],
-            quote_origin=quote_origin,
-        )
+        has_chunks = any(isinstance(msg, provider_message.MessageChunk) for msg in query.resp_messages)
+        # TODO 命令与流式的兼容性问题
+        if await query.adapter.is_stream_output_supported() and has_chunks:
+            is_final = [msg.is_final for msg in query.resp_messages][0]
+            await query.adapter.reply_message_chunk(
+                message_source=query.message_event,
+                bot_message=query.resp_messages[-1],
+                message=query.resp_message_chain[-1],
+                quote_origin=quote_origin,
+                is_final=is_final,
+            )
+        else:
+            await query.adapter.reply_message(
+                message_source=query.message_event,
+                message=query.resp_message_chain[-1],
+                quote_origin=quote_origin,
+            )

        return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
--- a/pkg/pipeline/resprule/rules/atbot.py
+++ b/pkg/pipeline/resprule/rules/atbot.py
@@ -16,17 +16,26 @@ class AtBotRule(rule_model.GroupRespondRule):
        rule_dict: dict,
        query: pipeline_query.Query,
    ) -> entities.RuleJudgeResult:
-        if message_chain.has(platform_message.At(query.adapter.bot_account_id)) and rule_dict['at']:
-            message_chain.remove(platform_message.At(query.adapter.bot_account_id))
+        def remove_at(message_chain: platform_message.MessageChain):
+            for component in message_chain.root:
+                if isinstance(component, platform_message.At) and component.target == query.adapter.bot_account_id:
+                    message_chain.remove(component)
+                    break

-            if message_chain.has(
-                platform_message.At(query.adapter.bot_account_id)
-            ):  # 回复消息时会at两次，检查并删除重复的
-                message_chain.remove(platform_message.At(query.adapter.bot_account_id))
+        remove_at(message_chain)
+        remove_at(message_chain)  # 回复消息时会at两次，检查并删除重复的

-            return entities.RuleJudgeResult(
-                matching=True,
-                replacement=message_chain,
-            )
+        # if message_chain.has(platform_message.At(query.adapter.bot_account_id)) and rule_dict['at']:
+        #     message_chain.remove(platform_message.At(query.adapter.bot_account_id))
+
+        #     if message_chain.has(
+        #         platform_message.At(query.adapter.bot_account_id)
+        #     ):  # 回复消息时会at两次，检查并删除重复的
+        #         message_chain.remove(platform_message.At(query.adapter.bot_account_id))
+
+        #     return entities.RuleJudgeResult(
+        #         matching=True,
+        #         replacement=message_chain,
+        #     )

        return entities.RuleJudgeResult(matching=False, replacement=message_chain)
--- a/pkg/platform/botmgr.py
+++ b/pkg/platform/botmgr.py
@@ -115,8 +115,10 @@ class RuntimeBot:
                if isinstance(e, asyncio.CancelledError):
                    self.task_context.set_current_action('Exited.')
                    return
+
+                traceback_str = traceback.format_exc()
                self.task_context.set_current_action('Exited with error.')
-                await self.logger.error(f'平台适配器运行出错:\n{e}\n{traceback.format_exc()}')
+                await self.logger.error(f'平台适配器运行出错:\n{e}\n{traceback_str}')

        self.task_wrapper = self.ap.task_mgr.create_task(
            exception_wrapper(),
@@ -169,8 +171,8 @@ class PlatformManager:
            {},
            webchat_logger,
            ap=self.ap,
+            is_stream=False,
        )
-        webchat_adapter_inst.ap = self.ap

        self.webchat_proxy_bot = RuntimeBot(
            ap=self.ap,
--- a/pkg/platform/logger.py
+++ b/pkg/platform/logger.py
@@ -120,7 +120,7 @@ class EventLogger(abstract_platform_event_logger.AbstractEventLogger):
    async def _truncate_logs(self):
        if len(self.logs) > MAX_LOG_COUNT:
            for i in range(DELETE_COUNT_PER_TIME):
-                for image_key in self.logs[i].images:
+                for image_key in self.logs[i].images:  # type: ignore
                    await self.ap.storage_mgr.storage_provider.delete(image_key)
            self.logs = self.logs[DELETE_COUNT_PER_TIME:]

--- a/pkg/platform/sources/aiocqhttp.py
+++ b/pkg/platform/sources/aiocqhttp.py
@@ -61,13 +61,13 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
                for node in msg.node_list:
                    msg_list.extend((await AiocqhttpMessageConverter.yiri2target(node.message_chain))[0])
            elif isinstance(msg, platform_message.File):
-                msg_list.append({"type":"file", "data":{'file': msg.url, "name": msg.name}})
+                msg_list.append({'type': 'file', 'data': {'file': msg.url, 'name': msg.name}})
            elif isinstance(msg, platform_message.Face):
-                if msg.face_type=='face':
+                if msg.face_type == 'face':
                    msg_list.append(aiocqhttp.MessageSegment.face(msg.face_id))
-                elif msg.face_type=='rps':
+                elif msg.face_type == 'rps':
                    msg_list.append(aiocqhttp.MessageSegment.rps())
-                elif msg.face_type=='dice':
+                elif msg.face_type == 'dice':
                    msg_list.append(aiocqhttp.MessageSegment.dice())

            else:
@@ -76,44 +76,130 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
        return msg_list, msg_id, msg_time

    @staticmethod
-    async def target2yiri(message: str, message_id: int = -1, bot=None):
+    async def target2yiri(message: str, message_id: int = -1, bot: aiocqhttp.CQHttp = None):
        message = aiocqhttp.Message(message)

        def get_face_name(face_id):
            face_code_dict = {
-                "2": '好色',
-                "4": "得意", "5": "流泪", "8": "睡", "9": "大哭", "10": "尴尬", "12": "调皮", "14": "微笑", "16": "酷",
-                "21": "可爱",
-                "23": "傲慢", "24": "饥饿", "25": "困", "26": "惊恐", "27": "流汗", "28": "憨笑", "29": "悠闲",
-                "30": "奋斗",
-                "32": "疑问", "33": "嘘", "34": "晕", "38": "敲打", "39": "再见", "41": "发抖", "42": "爱情",
-                "43": "跳跳",
-                "49": "拥抱", "53": "蛋糕", "60": "咖啡", "63": "玫瑰", "66": "爱心", "74": "太阳", "75": "月亮",
-                "76": "赞",
-                "78": "握手", "79": "胜利", "85": "飞吻", "89": "西瓜", "96": "冷汗", "97": "擦汗", "98": "抠鼻",
-                "99": "鼓掌",
-                "100": "糗大了", "101": "坏笑", "102": "左哼哼", "103": "右哼哼", "104": "哈欠", "106": "委屈",
-                "109": "左亲亲",
-                "111": "可怜", "116": "示爱", "118": "抱拳", "120": "拳头", "122": "爱你", "123": "NO", "124": "OK",
-                "125": "转圈",
-                "129": "挥手", "144": "喝彩", "147": "棒棒糖", "171": "茶", "173": "泪奔", "174": "无奈", "175": "卖萌",
-                "176": "小纠结", "179": "doge", "180": "惊喜", "181": "骚扰", "182": "笑哭", "183": "我最美",
-                "201": "点赞",
-                "203": "托脸", "212": "托腮", "214": "啵啵", "219": "蹭一蹭", "222": "抱抱", "227": "拍手",
-                "232": "佛系",
-                "240": "喷脸", "243": "甩头", "246": "加油抱抱", "262": "脑阔疼", "264": "捂脸", "265": "辣眼睛",
-                "266": "哦哟",
-                "267": "头秃", "268": "问号脸", "269": "暗中观察", "270": "emm", "271": "吃瓜", "272": "呵呵哒",
-                "273": "我酸了",
-                "277": "汪汪", "278": "汗", "281": "无眼笑", "282": "敬礼", "284": "面无表情", "285": "摸鱼",
-                "287": "哦",
-                "289": "睁眼", "290": "敲开心", "293": "摸锦鲤", "294": "期待", "297": "拜谢", "298": "元宝",
-                "299": "牛啊",
-                "305": "右亲亲", "306": "牛气冲天", "307": "喵喵", "314": "仔细分析", "315": "加油", "318": "崇拜",
-                "319": "比心",
-                "320": "庆祝", "322": "拒绝", "324": "吃糖", "326": "生气"
+                '2': '好色',
+                '4': '得意',
+                '5': '流泪',
+                '8': '睡',
+                '9': '大哭',
+                '10': '尴尬',
+                '12': '调皮',
+                '14': '微笑',
+                '16': '酷',
+                '21': '可爱',
+                '23': '傲慢',
+                '24': '饥饿',
+                '25': '困',
+                '26': '惊恐',
+                '27': '流汗',
+                '28': '憨笑',
+                '29': '悠闲',
+                '30': '奋斗',
+                '32': '疑问',
+                '33': '嘘',
+                '34': '晕',
+                '38': '敲打',
+                '39': '再见',
+                '41': '发抖',
+                '42': '爱情',
+                '43': '跳跳',
+                '49': '拥抱',
+                '53': '蛋糕',
+                '60': '咖啡',
+                '63': '玫瑰',
+                '66': '爱心',
+                '74': '太阳',
+                '75': '月亮',
+                '76': '赞',
+                '78': '握手',
+                '79': '胜利',
+                '85': '飞吻',
+                '89': '西瓜',
+                '96': '冷汗',
+                '97': '擦汗',
+                '98': '抠鼻',
+                '99': '鼓掌',
+                '100': '糗大了',
+                '101': '坏笑',
+                '102': '左哼哼',
+                '103': '右哼哼',
+                '104': '哈欠',
+                '106': '委屈',
+                '109': '左亲亲',
+                '111': '可怜',
+                '116': '示爱',
+                '118': '抱拳',
+                '120': '拳头',
+                '122': '爱你',
+                '123': 'NO',
+                '124': 'OK',
+                '125': '转圈',
+                '129': '挥手',
+                '144': '喝彩',
+                '147': '棒棒糖',
+                '171': '茶',
+                '173': '泪奔',
+                '174': '无奈',
+                '175': '卖萌',
+                '176': '小纠结',
+                '179': 'doge',
+                '180': '惊喜',
+                '181': '骚扰',
+                '182': '笑哭',
+                '183': '我最美',
+                '201': '点赞',
+                '203': '托脸',
+                '212': '托腮',
+                '214': '啵啵',
+                '219': '蹭一蹭',
+                '222': '抱抱',
+                '227': '拍手',
+                '232': '佛系',
+                '240': '喷脸',
+                '243': '甩头',
+                '246': '加油抱抱',
+                '262': '脑阔疼',
+                '264': '捂脸',
+                '265': '辣眼睛',
+                '266': '哦哟',
+                '267': '头秃',
+                '268': '问号脸',
+                '269': '暗中观察',
+                '270': 'emm',
+                '271': '吃瓜',
+                '272': '呵呵哒',
+                '273': '我酸了',
+                '277': '汪汪',
+                '278': '汗',
+                '281': '无眼笑',
+                '282': '敬礼',
+                '284': '面无表情',
+                '285': '摸鱼',
+                '287': '哦',
+                '289': '睁眼',
+                '290': '敲开心',
+                '293': '摸锦鲤',
+                '294': '期待',
+                '297': '拜谢',
+                '298': '元宝',
+                '299': '牛啊',
+                '305': '右亲亲',
+                '306': '牛气冲天',
+                '307': '喵喵',
+                '314': '仔细分析',
+                '315': '加油',
+                '318': '崇拜',
+                '319': '比心',
+                '320': '庆祝',
+                '322': '拒绝',
+                '324': '吃糖',
+                '326': '生气',
            }
-            return face_code_dict.get(face_id,'')
+            return face_code_dict.get(face_id, '')

        async def process_message_data(msg_data, reply_list):
            if msg_data['type'] == 'image':
@@ -156,10 +242,10 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
            elif msg.type == 'text':
                yiri_msg_list.append(platform_message.Plain(text=msg.data['text']))
            elif msg.type == 'image':
-                emoji_id = msg.data.get("emoji_package_id", None)
+                emoji_id = msg.data.get('emoji_package_id', None)
                if emoji_id:
                    face_id = emoji_id
-                    face_name = msg.data.get("summary", '')
+                    face_name = msg.data.get('summary', '')
                    image_msg = platform_message.Face(face_id=face_id, face_name=face_name)
                else:
                    image_base64, image_format = await image.qq_image_url_to_base64(msg.data['url'])
@@ -185,27 +271,28 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
                yiri_msg_list.append(reply_msg)

            elif msg.type == 'file':
+                pass
                # file_name = msg.data['file']
-                file_id = msg.data['file_id']
-                file_data = await bot.get_file(file_id=file_id)
-                file_name = file_data.get('file_name')
-                file_path = file_data.get('file')
-                _ = file_path
-                file_url = file_data.get('file_url')
-                file_size = file_data.get('file_size')
-                yiri_msg_list.append(platform_message.File(id=file_id, name=file_name,url=file_url,size=file_size))
+                # file_id = msg.data['file_id']
+                # file_data = await bot.get_file(file_id=file_id)
+                # file_name = file_data.get('file_name')
+                # file_path = file_data.get('file')
+                # _ = file_path
+                # file_url = file_data.get('file_url')
+                # file_size = file_data.get('file_size')
+                # yiri_msg_list.append(platform_message.File(id=file_id, name=file_name,url=file_url,size=file_size))
            elif msg.type == 'face':
                face_id = msg.data['id']
                face_name = msg.data['raw']['faceText']
                if not face_name:
                    face_name = get_face_name(face_id)
-                yiri_msg_list.append(platform_message.Face(face_id=int(face_id),face_name=face_name.replace('/','')))
+                yiri_msg_list.append(platform_message.Face(face_id=int(face_id), face_name=face_name.replace('/', '')))
            elif msg.type == 'rps':
                face_id = msg.data['result']
-                yiri_msg_list.append(platform_message.Face(face_type="rps",face_id=int(face_id),face_name='猜拳'))
+                yiri_msg_list.append(platform_message.Face(face_type='rps', face_id=int(face_id), face_name='猜拳'))
            elif msg.type == 'dice':
                face_id = msg.data['result']
-                yiri_msg_list.append(platform_message.Face(face_type='dice',face_id=int(face_id),face_name='骰子'))
+                yiri_msg_list.append(platform_message.Face(face_type='dice', face_id=int(face_id), face_name='骰子'))

        chain = platform_message.MessageChain(yiri_msg_list)

@@ -221,7 +308,6 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
    async def target2yiri(event: aiocqhttp.Event, bot=None):
        yiri_chain = await AiocqhttpMessageConverter.target2yiri(event.message, event.message_id, bot)

-
        if event.message_type == 'group':
            permission = 'MEMBER'

--- a/pkg/platform/sources/dingtalk.py
+++ b/pkg/platform/sources/dingtalk.py
@@ -96,10 +96,16 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
    message_converter: DingTalkMessageConverter = DingTalkMessageConverter()
    event_converter: DingTalkEventConverter = DingTalkEventConverter()
    config: dict
+    card_instance_id_dict: (
+        dict  # 回复卡片消息字典，key为消息id，value为回复卡片实例id，用于在流式消息时判断是否发送到指定卡片
+    )
+    seq: int  # 消息顺序，直接以seq作为标识

    def __init__(self, config: dict, logger: EventLogger):
        self.config = config
        self.logger = logger
+        self.card_instance_id_dict = {}
+        # self.seq = 1
        required_keys = [
            'client_id',
            'client_secret',
@@ -112,6 +118,15 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

        self.bot_account_id = self.config['robot_name']

+        self.bot = DingTalkClient(
+            client_id=config['client_id'],
+            client_secret=config['client_secret'],
+            robot_name=config['robot_name'],
+            robot_code=config['robot_code'],
+            markdown_card=config['markdown_card'],
+            logger=self.logger,
+        )
+
    async def reply_message(
        self,
        message_source: platform_events.MessageEvent,
@@ -126,6 +141,33 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        content, at = await DingTalkMessageConverter.yiri2target(message)
        await self.bot.send_message(content, incoming_message, at)

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        # event = await DingTalkEventConverter.yiri2target(
+        #     message_source,
+        # )
+        # incoming_message = event.incoming_message
+
+        # msg_id = incoming_message.message_id
+        message_id = bot_message.resp_message_id
+        msg_seq = bot_message.msg_sequence
+
+        if (msg_seq - 1) % 8 == 0 or is_final:
+            content, at = await DingTalkMessageConverter.yiri2target(message)
+
+            card_instance, card_instance_id = self.card_instance_id_dict[message_id]
+            # print(card_instance_id)
+            await self.bot.send_card_message(card_instance, card_instance_id, content, is_final)
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.card_instance_id_dict.pop(message_id)  # 消息回复结束之后删除卡片实例id
+
    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
        content = await DingTalkMessageConverter.yiri2target(message)
        if target_type == 'person':
@@ -133,6 +175,20 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        if target_type == 'group':
            await self.bot.send_proactive_message_to_group(target_id, content)

+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
+    async def create_message_card(self, message_id, event):
+        card_template_id = self.config['card_template_id']
+        incoming_message = event.source_platform_object.incoming_message
+        # message_id = incoming_message.message_id
+        card_instance, card_instance_id = await self.bot.create_and_card(card_template_id, incoming_message)
+        self.card_instance_id_dict[message_id] = (card_instance, card_instance_id)
+        return True
+
    def register_listener(
        self,
        event_type: typing.Type[platform_events.Event],
@@ -155,15 +211,6 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
            self.bot.on_message('GroupMessage')(on_message)

    async def run_async(self):
-        config = self.config
-        self.bot = DingTalkClient(
-            client_id=config['client_id'],
-            client_secret=config['client_secret'],
-            robot_name=config['robot_name'],
-            robot_code=config['robot_code'],
-            markdown_card=config['markdown_card'],
-            logger=self.logger,
-        )
        await self.bot.start()

    async def kill(self) -> bool:
--- a/pkg/platform/sources/dingtalk.yaml
+++ b/pkg/platform/sources/dingtalk.yaml
@@ -46,6 +46,23 @@ spec:
      type: boolean
      required: false
      default: true
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用钉钉卡片流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of lark reply mode
+        zh_Hans: 如果启用，将使用钉钉卡片流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
+    - name: card_template_id
+      label:
+        en_US: card template id
+        zh_Hans: 卡片模板ID
+      type: string
+      required: true
+      default: "填写你的卡片template_id"
 execution:
  python:
    path: ./dingtalk.py
--- a/pkg/platform/sources/discord.py
+++ b/pkg/platform/sources/discord.py
@@ -8,6 +8,8 @@ import base64
 import uuid
 import os
 import datetime
+import asyncio
+from enum import Enum

 import aiohttp
 import pydantic
@@ -17,6 +19,568 @@ import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
 import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_platform_logger
+from ..logger import EventLogger
+
+
+# 语音功能相关异常定义
+class VoiceConnectionError(Exception):
+    """语音连接基础异常"""
+
+    def __init__(self, message: str, error_code: str = None, guild_id: int = None):
+        super().__init__(message)
+        self.error_code = error_code
+        self.guild_id = guild_id
+        self.timestamp = datetime.datetime.now()
+
+
+class VoicePermissionError(VoiceConnectionError):
+    """语音权限异常"""
+
+    def __init__(self, message: str, missing_permissions: list = None, user_id: int = None, channel_id: int = None):
+        super().__init__(message, 'PERMISSION_ERROR')
+        self.missing_permissions = missing_permissions or []
+        self.user_id = user_id
+        self.channel_id = channel_id
+
+
+class VoiceNetworkError(VoiceConnectionError):
+    """语音网络异常"""
+
+    def __init__(self, message: str, retry_count: int = 0):
+        super().__init__(message, 'NETWORK_ERROR')
+        self.retry_count = retry_count
+        self.last_attempt = datetime.datetime.now()
+
+
+class VoiceConnectionStatus(Enum):
+    """语音连接状态枚举"""
+
+    IDLE = 'idle'
+    CONNECTING = 'connecting'
+    CONNECTED = 'connected'
+    PLAYING = 'playing'
+    RECONNECTING = 'reconnecting'
+    FAILED = 'failed'
+
+
+class VoiceConnectionInfo:
+    """
+    语音连接信息类
+
+    用于存储和管理单个语音连接的详细信息，包括连接状态、时间戳、
+    频道信息等。提供连接信息的标准化数据结构。
+
+    @author: @ydzat
+    @version: 1.0
+    @since: 2025-07-04
+    """
+
+    def __init__(self, guild_id: int, channel_id: int, channel_name: str = None):
+        """
+        初始化语音连接信息
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 语音频道ID
+            channel_name (str, optional): 语音频道名称
+        """
+        self.guild_id = guild_id
+        self.channel_id = channel_id
+        self.channel_name = channel_name or f'Channel-{channel_id}'
+        self.connected = False
+        self.connection_time: datetime.datetime = None
+        self.last_activity = datetime.datetime.now()
+        self.status = VoiceConnectionStatus.IDLE
+        self.user_count = 0
+        self.latency = 0.0
+        self.connection_health = 'unknown'
+        self.voice_client = None
+
+    def update_status(self, status: VoiceConnectionStatus):
+        """
+        更新连接状态
+
+        @author: @ydzat
+
+        Args:
+            status (VoiceConnectionStatus): 新的连接状态
+        """
+        self.status = status
+        self.last_activity = datetime.datetime.now()
+
+        if status == VoiceConnectionStatus.CONNECTED:
+            self.connected = True
+            if self.connection_time is None:
+                self.connection_time = datetime.datetime.now()
+        elif status in [VoiceConnectionStatus.IDLE, VoiceConnectionStatus.FAILED]:
+            self.connected = False
+            self.connection_time = None
+            self.voice_client = None
+
+    def to_dict(self) -> dict:
+        """
+        转换为字典格式
+
+        @author: @ydzat
+
+        Returns:
+            dict: 连接信息的字典表示
+        """
+        return {
+            'guild_id': self.guild_id,
+            'channel_id': self.channel_id,
+            'channel_name': self.channel_name,
+            'connected': self.connected,
+            'connection_time': self.connection_time.isoformat() if self.connection_time else None,
+            'last_activity': self.last_activity.isoformat(),
+            'status': self.status.value,
+            'user_count': self.user_count,
+            'latency': self.latency,
+            'connection_health': self.connection_health,
+        }
+
+
+class VoiceConnectionManager:
+    """
+    语音连接管理器
+
+    负责管理多个服务器的语音连接，提供连接建立、断开、状态查询等功能。
+    采用单例模式确保全局只有一个连接管理器实例。
+
+    @author: @ydzat
+    @version: 1.0
+    @since: 2025-07-04
+    """
+
+    def __init__(self, bot: discord.Client, logger: EventLogger):
+        """
+        初始化语音连接管理器
+
+        @author: @ydzat
+
+        Args:
+            bot (discord.Client): Discord 客户端实例
+            logger (EventLogger): 事件日志记录器
+        """
+        self.bot = bot
+        self.logger = logger
+        self.connections: typing.Dict[int, VoiceConnectionInfo] = {}
+        self._connection_lock = asyncio.Lock()
+        self._cleanup_task = None
+        self._monitoring_enabled = True
+
+    async def join_voice_channel(self, guild_id: int, channel_id: int, user_id: int = None) -> discord.VoiceClient:
+        """
+        加入语音频道
+
+        验证用户权限和频道状态后，建立到指定语音频道的连接。
+        支持连接复用和自动重连机制。
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 语音频道ID
+            user_id (int, optional): 请求用户ID，用于权限验证
+
+        Returns:
+            discord.VoiceClient: 语音客户端实例
+
+        Raises:
+            VoicePermissionError: 权限不足时抛出
+            VoiceNetworkError: 网络连接失败时抛出
+            VoiceConnectionError: 其他连接错误时抛出
+        """
+        async with self._connection_lock:
+            try:
+                # 获取服务器和频道对象
+                guild = self.bot.get_guild(guild_id)
+                if not guild:
+                    raise VoiceConnectionError(f'无法找到服务器 {guild_id}', 'GUILD_NOT_FOUND', guild_id)
+
+                channel = guild.get_channel(channel_id)
+                if not channel or not isinstance(channel, discord.VoiceChannel):
+                    raise VoiceConnectionError(f'无法找到语音频道 {channel_id}', 'CHANNEL_NOT_FOUND', guild_id)
+
+                # 验证用户是否在语音频道中（如果提供了用户ID）
+                if user_id:
+                    await self._validate_user_in_channel(guild, channel, user_id)
+
+                # 验证机器人权限
+                await self._validate_bot_permissions(channel)
+
+                # 检查是否已有连接
+                if guild_id in self.connections:
+                    existing_conn = self.connections[guild_id]
+                    if existing_conn.connected and existing_conn.voice_client:
+                        if existing_conn.channel_id == channel_id:
+                            # 已连接到相同频道，返回现有连接
+                            await self.logger.info(f'复用现有语音连接: {guild.name} -> {channel.name}')
+                            return existing_conn.voice_client
+                        else:
+                            # 连接到不同频道，先断开旧连接
+                            await self._disconnect_internal(guild_id)
+
+                # 建立新连接
+                voice_client = await channel.connect()
+
+                # 更新连接信息
+                conn_info = VoiceConnectionInfo(guild_id, channel_id, channel.name)
+                conn_info.voice_client = voice_client
+                conn_info.update_status(VoiceConnectionStatus.CONNECTED)
+                conn_info.user_count = len(channel.members)
+                self.connections[guild_id] = conn_info
+
+                await self.logger.info(f'成功连接到语音频道: {guild.name} -> {channel.name}')
+                return voice_client
+
+            except discord.ClientException as e:
+                raise VoiceNetworkError(f'Discord 客户端错误: {str(e)}')
+            except discord.opus.OpusNotLoaded as e:
+                raise VoiceConnectionError(f'Opus 编码器未加载: {str(e)}', 'OPUS_NOT_LOADED', guild_id)
+            except Exception as e:
+                await self.logger.error(f'连接语音频道时发生未知错误: {str(e)}')
+                raise VoiceConnectionError(f'连接失败: {str(e)}', 'UNKNOWN_ERROR', guild_id)
+
+    async def leave_voice_channel(self, guild_id: int) -> bool:
+        """
+        离开语音频道
+
+        断开指定服务器的语音连接，清理相关资源和状态信息。
+        确保音频播放停止后再断开连接。
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+
+        Returns:
+            bool: 断开是否成功
+        """
+        async with self._connection_lock:
+            return await self._disconnect_internal(guild_id)
+
+    async def _disconnect_internal(self, guild_id: int) -> bool:
+        """
+        内部断开连接方法
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+
+        Returns:
+            bool: 断开是否成功
+        """
+        if guild_id not in self.connections:
+            return True
+
+        conn_info = self.connections[guild_id]
+
+        try:
+            if conn_info.voice_client and conn_info.voice_client.is_connected():
+                # 停止当前播放
+                if conn_info.voice_client.is_playing():
+                    conn_info.voice_client.stop()
+
+                # 等待播放完全停止
+                await asyncio.sleep(0.1)
+
+                # 断开连接
+                await conn_info.voice_client.disconnect()
+
+            conn_info.update_status(VoiceConnectionStatus.IDLE)
+            del self.connections[guild_id]
+
+            await self.logger.info(f'已断开语音连接: Guild {guild_id}')
+            return True
+
+        except Exception as e:
+            await self.logger.error(f'断开语音连接时发生错误: {str(e)}')
+            # 即使出错也要清理连接记录
+            conn_info.update_status(VoiceConnectionStatus.FAILED)
+            if guild_id in self.connections:
+                del self.connections[guild_id]
+            return False
+
+    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
+        """
+        获取语音客户端
+
+        返回指定服务器的语音客户端实例，如果未连接则返回 None。
+        会验证连接的有效性，自动清理无效连接。
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+
+        Returns:
+            Optional[discord.VoiceClient]: 语音客户端实例或 None
+        """
+        if guild_id not in self.connections:
+            return None
+
+        conn_info = self.connections[guild_id]
+
+        # 验证连接是否仍然有效
+        if conn_info.voice_client and not conn_info.voice_client.is_connected():
+            # 连接已失效，清理状态
+            await self._disconnect_internal(guild_id)
+            return None
+
+        return conn_info.voice_client if conn_info.connected else None
+
+    async def is_connected_to_voice(self, guild_id: int) -> bool:
+        """
+        检查是否连接到语音频道
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+
+        Returns:
+            bool: 是否已连接
+        """
+        if guild_id not in self.connections:
+            return False
+
+        conn_info = self.connections[guild_id]
+
+        # 检查实际连接状态
+        if conn_info.voice_client and not conn_info.voice_client.is_connected():
+            # 连接已失效，清理状态
+            await self._disconnect_internal(guild_id)
+            return False
+
+        return conn_info.connected
+
+    async def get_connection_status(self, guild_id: int) -> typing.Optional[dict]:
+        """
+        获取连接状态信息
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+
+        Returns:
+            Optional[dict]: 连接状态信息字典或 None
+        """
+        if guild_id not in self.connections:
+            return None
+
+        conn_info = self.connections[guild_id]
+
+        # 更新实时信息
+        if conn_info.voice_client and conn_info.voice_client.is_connected():
+            conn_info.latency = conn_info.voice_client.latency * 1000  # 转换为毫秒
+            conn_info.connection_health = 'good' if conn_info.latency < 100 else 'poor'
+
+            # 更新频道用户数
+            guild = self.bot.get_guild(guild_id)
+            if guild:
+                channel = guild.get_channel(conn_info.channel_id)
+                if channel and isinstance(channel, discord.VoiceChannel):
+                    conn_info.user_count = len(channel.members)
+
+        return conn_info.to_dict()
+
+    async def list_active_connections(self) -> typing.List[dict]:
+        """
+        列出所有活跃连接
+
+        @author: @ydzat
+
+        Returns:
+            List[dict]: 活跃连接列表
+        """
+        active_connections = []
+
+        for guild_id, conn_info in self.connections.items():
+            if conn_info.connected:
+                status = await self.get_connection_status(guild_id)
+                if status:
+                    active_connections.append(status)
+
+        return active_connections
+
+    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
+        """
+        获取语音频道信息
+
+        @author: @ydzat
+
+        Args:
+            guild_id (int): 服务器ID
+            channel_id (int): 频道ID
+
+        Returns:
+            Optional[dict]: 频道信息字典或 None
+        """
+        guild = self.bot.get_guild(guild_id)
+        if not guild:
+            return None
+
+        channel = guild.get_channel(channel_id)
+        if not channel or not isinstance(channel, discord.VoiceChannel):
+            return None
+
+        # 获取用户信息
+        users = []
+        for member in channel.members:
+            users.append(
+                {'id': member.id, 'name': member.display_name, 'status': str(member.status), 'is_bot': member.bot}
+            )
+
+        # 获取权限信息
+        bot_member = guild.me
+        permissions = channel.permissions_for(bot_member)
+
+        return {
+            'channel_id': channel_id,
+            'channel_name': channel.name,
+            'guild_id': guild_id,
+            'guild_name': guild.name,
+            'user_limit': channel.user_limit,
+            'current_users': users,
+            'user_count': len(users),
+            'bitrate': channel.bitrate,
+            'permissions': {
+                'connect': permissions.connect,
+                'speak': permissions.speak,
+                'use_voice_activation': permissions.use_voice_activation,
+                'priority_speaker': permissions.priority_speaker,
+            },
+        }
+
+    async def _validate_user_in_channel(self, guild: discord.Guild, channel: discord.VoiceChannel, user_id: int):
+        """
+        验证用户是否在语音频道中
+
+        @author: @ydzat
+
+        Args:
+            guild: Discord 服务器对象
+            channel: 语音频道对象
+            user_id: 用户ID
+
+        Raises:
+            VoicePermissionError: 用户不在频道中时抛出
+        """
+        member = guild.get_member(user_id)
+        if not member:
+            raise VoicePermissionError(f'无法找到用户 {user_id}', ['member_not_found'], user_id, channel.id)
+
+        if not member.voice or member.voice.channel != channel:
+            raise VoicePermissionError(
+                f'用户 {member.display_name} 不在语音频道 {channel.name} 中',
+                ['user_not_in_channel'],
+                user_id,
+                channel.id,
+            )
+
+    async def _validate_bot_permissions(self, channel: discord.VoiceChannel):
+        """
+        验证机器人权限
+
+        @author: @ydzat
+
+        Args:
+            channel: 语音频道对象
+
+        Raises:
+            VoicePermissionError: 权限不足时抛出
+        """
+        bot_member = channel.guild.me
+        permissions = channel.permissions_for(bot_member)
+
+        missing_permissions = []
+
+        if not permissions.connect:
+            missing_permissions.append('connect')
+        if not permissions.speak:
+            missing_permissions.append('speak')
+
+        if missing_permissions:
+            raise VoicePermissionError(
+                f'机器人在频道 {channel.name} 中缺少权限: {", ".join(missing_permissions)}',
+                missing_permissions,
+                channel_id=channel.id,
+            )
+
+    async def cleanup_inactive_connections(self):
+        """
+        清理无效连接
+
+        定期检查并清理已断开或无效的语音连接，释放资源。
+
+        @author: @ydzat
+        """
+        cleanup_guilds = []
+
+        for guild_id, conn_info in self.connections.items():
+            if not conn_info.voice_client or not conn_info.voice_client.is_connected():
+                cleanup_guilds.append(guild_id)
+
+        for guild_id in cleanup_guilds:
+            await self._disconnect_internal(guild_id)
+
+        if cleanup_guilds:
+            await self.logger.info(f'清理了 {len(cleanup_guilds)} 个无效的语音连接')
+
+    async def start_monitoring(self):
+        """
+        开始连接监控
+
+        @author: @ydzat
+        """
+        if self._cleanup_task is None and self._monitoring_enabled:
+            self._cleanup_task = asyncio.create_task(self._monitoring_loop())
+
+    async def stop_monitoring(self):
+        """
+        停止连接监控
+
+        @author: @ydzat
+        """
+        self._monitoring_enabled = False
+        if self._cleanup_task:
+            self._cleanup_task.cancel()
+            try:
+                await self._cleanup_task
+            except asyncio.CancelledError:
+                pass
+            self._cleanup_task = None
+
+    async def _monitoring_loop(self):
+        """
+        监控循环
+
+        @author: @ydzat
+        """
+        try:
+            while self._monitoring_enabled:
+                await asyncio.sleep(60)  # 每分钟检查一次
+                await self.cleanup_inactive_connections()
+        except asyncio.CancelledError:
+            pass
+
+    async def disconnect_all(self):
+        """
+        断开所有连接
+
+        @author: @ydzat
+        """
+        async with self._connection_lock:
+            guild_ids = list(self.connections.keys())
+            for guild_id in guild_ids:
+                await self._disconnect_internal(guild_id)
+
+        await self.stop_monitoring()


 class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
@@ -35,28 +599,89 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
        for ele in message_chain:
            if isinstance(ele, platform_message.Image):
                image_bytes = None
+                filename = f'{uuid.uuid4()}.png'  # 默认文件名

                if ele.base64:
-                    image_bytes = base64.b64decode(ele.base64)
+                    # 处理base64编码的图片
+                    if ele.base64.startswith('data:'):
+                        # 从data URL中提取文件类型
+                        data_header = ele.base64.split(',')[0]
+                        if 'jpeg' in data_header or 'jpg' in data_header:
+                            filename = f'{uuid.uuid4()}.jpg'
+                        elif 'gif' in data_header:
+                            filename = f'{uuid.uuid4()}.gif'
+                        elif 'webp' in data_header:
+                            filename = f'{uuid.uuid4()}.webp'
+                        # 去掉data:image/xxx;base64,前缀
+                        base64_data = ele.base64.split(',')[1]
+                    else:
+                        base64_data = ele.base64
+                    image_bytes = base64.b64decode(base64_data)
                elif ele.url:
+                    # 从URL下载图片
                    async with aiohttp.ClientSession() as session:
                        async with session.get(ele.url) as response:
                            image_bytes = await response.read()
+                            # 从URL或Content-Type推断文件类型
+                            content_type = response.headers.get('Content-Type', '')
+                            if 'jpeg' in content_type or 'jpg' in content_type:
+                                filename = f'{uuid.uuid4()}.jpg'
+                            elif 'gif' in content_type:
+                                filename = f'{uuid.uuid4()}.gif'
+                            elif 'webp' in content_type:
+                                filename = f'{uuid.uuid4()}.webp'
+                            elif ele.url.lower().endswith(('.jpg', '.jpeg')):
+                                filename = f'{uuid.uuid4()}.jpg'
+                            elif ele.url.lower().endswith('.gif'):
+                                filename = f'{uuid.uuid4()}.gif'
+                            elif ele.url.lower().endswith('.webp'):
+                                filename = f'{uuid.uuid4()}.webp'
                elif ele.path:
-                    with open(ele.path, 'rb') as f:
-                        image_bytes = f.read()
+                    # 从文件路径读取图片
+                    # 确保路径没有空字节
+                    clean_path = ele.path.replace('\x00', '')
+                    clean_path = os.path.abspath(clean_path)

-                image_files.append(discord.File(fp=image_bytes, filename=f'{uuid.uuid4()}.png'))
+                    if not os.path.exists(clean_path):
+                        continue  # 跳过不存在的文件
+
+                    try:
+                        with open(clean_path, 'rb') as f:
+                            image_bytes = f.read()
+                        # 从文件路径获取文件名，保持原始扩展名
+                        original_filename = os.path.basename(clean_path)
+                        if original_filename and '.' in original_filename:
+                            # 保持原始文件名的扩展名
+                            ext = original_filename.split('.')[-1].lower()
+                            filename = f'{uuid.uuid4()}.{ext}'
+                        else:
+                            # 如果没有扩展名，尝试从文件内容检测
+                            if image_bytes.startswith(b'\xff\xd8\xff'):
+                                filename = f'{uuid.uuid4()}.jpg'
+                            elif image_bytes.startswith(b'GIF'):
+                                filename = f'{uuid.uuid4()}.gif'
+                            elif image_bytes.startswith(b'RIFF') and b'WEBP' in image_bytes[:20]:
+                                filename = f'{uuid.uuid4()}.webp'
+                            # 默认保持PNG
+                    except Exception as e:
+                        print(f'Error reading image file {clean_path}: {e}')
+                        continue  # 跳过读取失败的文件
+
+                if image_bytes:
+                    # 使用BytesIO创建文件对象，避免路径问题
+                    import io
+
+                    image_files.append(discord.File(fp=io.BytesIO(image_bytes), filename=filename))
            elif isinstance(ele, platform_message.Plain):
                text_string += ele.text
            elif isinstance(ele, platform_message.Forward):
                for node in ele.node_list:
                    (
-                        text_string,
-                        image_files,
+                        node_text,
+                        node_images,
                    ) = await DiscordMessageConverter.yiri2target(node.message_chain)
-                    text_string += text_string
-                    image_files.extend(image_files)
+                    text_string += node_text
+                    image_files.extend(node_images)

        return text_string, image_files

@@ -165,11 +790,16 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        typing.Callable[[platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None],
    ] = {}

-    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger):
+    voice_manager: VoiceConnectionManager | None = pydantic.Field(exclude=True, default=None)
+
+    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, **kwargs):
        bot_account_id = config['client_id']

        listeners = {}

+        # 初始化语音连接管理器
+        # self.voice_manager: VoiceConnectionManager = None
+
        adapter_self = self

        class MyClient(discord.Client):
@@ -196,10 +826,194 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
            bot_account_id=bot_account_id,
            listeners=listeners,
            bot=bot,
+            voice_manager=None,
+            **kwargs,
        )

+    # Voice functionality methods
+    async def join_voice_channel(self, guild_id: int, channel_id: int, user_id: int = None) -> discord.VoiceClient:
+        """
+        加入语音频道
+
+        为指定服务器的语音频道建立连接，支持用户权限验证和连接复用。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+            channel_id (int): 语音频道ID
+            user_id (int, optional): 请求用户ID，用于权限验证
+
+        Returns:
+            discord.VoiceClient: 语音客户端实例
+
+        Raises:
+            VoicePermissionError: 权限不足
+            VoiceNetworkError: 网络连接失败
+            VoiceConnectionError: 其他连接错误
+        """
+        if not self.voice_manager:
+            raise VoiceConnectionError('语音管理器未初始化', 'MANAGER_NOT_READY')
+
+        return await self.voice_manager.join_voice_channel(guild_id, channel_id, user_id)
+
+    async def leave_voice_channel(self, guild_id: int) -> bool:
+        """
+        离开语音频道
+
+        断开指定服务器的语音连接，清理相关资源。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+
+        Returns:
+            bool: 是否成功断开连接
+        """
+        if not self.voice_manager:
+            return False
+
+        return await self.voice_manager.leave_voice_channel(guild_id)
+
+    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
+        """
+        获取语音客户端
+
+        返回指定服务器的语音客户端实例，用于音频播放控制。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+
+        Returns:
+            Optional[discord.VoiceClient]: 语音客户端实例或 None
+        """
+        if not self.voice_manager:
+            return None
+
+        return await self.voice_manager.get_voice_client(guild_id)
+
+    async def is_connected_to_voice(self, guild_id: int) -> bool:
+        """
+        检查语音连接状态
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+
+        Returns:
+            bool: 是否已连接到语音频道
+        """
+        if not self.voice_manager:
+            return False
+
+        return await self.voice_manager.is_connected_to_voice(guild_id)
+
+    async def get_voice_connection_status(self, guild_id: int) -> typing.Optional[dict]:
+        """
+        获取语音连接详细状态
+
+        返回包含连接时间、延迟、用户数等详细信息的状态字典。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+
+        Returns:
+            Optional[dict]: 连接状态信息或 None
+        """
+        if not self.voice_manager:
+            return None
+
+        return await self.voice_manager.get_connection_status(guild_id)
+
+    async def list_active_voice_connections(self) -> typing.List[dict]:
+        """
+        列出所有活跃的语音连接
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Returns:
+            List[dict]: 活跃语音连接列表
+        """
+        if not self.voice_manager:
+            return []
+
+        return await self.voice_manager.list_active_connections()
+
+    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
+        """
+        获取语音频道详细信息
+
+        包括频道名称、用户列表、权限信息等。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+
+        Args:
+            guild_id (int): Discord 服务器ID
+            channel_id (int): 语音频道ID
+
+        Returns:
+            Optional[dict]: 频道信息字典或 None
+        """
+        if not self.voice_manager:
+            return None
+
+        return await self.voice_manager.get_voice_channel_info(guild_id, channel_id)
+
+    async def cleanup_voice_connections(self):
+        """
+        清理无效的语音连接
+
+        手动触发语音连接清理，移除已断开或无效的连接。
+
+        @author: @ydzat
+        @version: 1.0
+        @since: 2025-07-04
+        """
+        if self.voice_manager:
+            await self.voice_manager.cleanup_inactive_connections()
+
    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
-        pass
+        msg_to_send, image_files = await self.message_converter.yiri2target(message)
+
+        try:
+            # 获取频道对象
+            channel = self.bot.get_channel(int(target_id))
+            if channel is None:
+                # 如果本地缓存中没有，尝试从API获取
+                channel = await self.bot.fetch_channel(int(target_id))
+
+            args = {
+                'content': msg_to_send,
+            }
+
+            if len(image_files) > 0:
+                args['files'] = image_files
+
+            await channel.send(**args)
+
+        except Exception as e:
+            await self.logger.error(f'Discord send_message failed: {e}')
+            raise e

    async def reply_message(
        self,
@@ -220,7 +1034,14 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        if quote_origin:
            args['reference'] = message_source.source_platform_object

-        if message.has(platform_message.At):
+        has_at = False
+
+        for component in message.root:
+            if isinstance(component, platform_message.At):
+                has_at = True
+                break
+
+        if has_at:
            args['mention_author'] = True

        await message_source.source_platform_object.channel.send(**args)
@@ -247,9 +1068,31 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        self.listeners.pop(event_type)

    async def run_async(self):
+        """
+        启动 Discord 适配器
+
+        初始化语音管理器并启动 Discord 客户端连接。
+
+        @author: @ydzat (修改)
+        """
        async with self.bot:
+            # 初始化语音管理器
+            self.voice_manager = VoiceConnectionManager(self.bot, self.logger)
+            await self.voice_manager.start_monitoring()
+
+            await self.logger.info('Discord 适配器语音功能已启用')
            await self.bot.start(self.config['token'], reconnect=True)

    async def kill(self) -> bool:
+        """
+        关闭 Discord 适配器
+
+        清理语音连接并关闭 Discord 客户端。
+
+        @author: @ydzat (修改)
+        """
+        if self.voice_manager:
+            await self.voice_manager.disconnect_all()
+
        await self.bot.close()
        return True
--- a/pkg/platform/sources/lark.py
+++ b/pkg/platform/sources/lark.py
@@ -18,6 +18,7 @@ import lark_oapi.ws.exception
 import quart
 from lark_oapi.api.im.v1 import *
 import pydantic
+from lark_oapi.api.cardkit.v1 import *

 import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
@@ -320,10 +321,17 @@ class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
            )


+CARD_ID_CACHE_SIZE = 500
+CARD_ID_CACHE_MAX_LIFETIME = 20 * 60  # 20分钟
+
+
 class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
    bot: lark_oapi.ws.Client = pydantic.Field(exclude=True)
    api_client: lark_oapi.Client = pydantic.Field(exclude=True)

+    bot_account_id: str  # 用于在流水线中识别at是否是本bot，直接以bot_name作为标识
+    lark_tenant_key: str = pydantic.Field(exclude=True, default='')  # 飞书企业key
+
    message_converter: LarkMessageConverter = LarkMessageConverter()
    event_converter: LarkEventConverter = LarkEventConverter()

@@ -334,7 +342,11 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

    quart_app: quart.Quart = pydantic.Field(exclude=True)

-    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger):
+    card_id_dict: dict[str, str]  # 消息id到卡片id的映射，便于创建卡片后的发送消息到指定卡片
+
+    seq: int  # 用于在发送卡片消息中识别消息顺序，直接以seq作为标识
+
+    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, **kwargs):
        quart_app = quart.Quart(__name__)

        @quart_app.route('/lark/callback', methods=['POST'])
@@ -343,7 +355,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                data = await quart.request.json

                if 'encrypt' in data:
-                    cipher = AESCipher(self.config['encrypt-key'])
+                    cipher = AESCipher(config['encrypt-key'])
                    data = cipher.decrypt_string(data['encrypt'])
                    data = json.loads(data)

@@ -398,16 +410,256 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        super().__init__(
            config=config,
            logger=logger,
+            lark_tenant_key=config.get('lark_tenant_key', ''),
+            card_id_dict={},
+            seq=1,
            listeners={},
            quart_app=quart_app,
            bot=bot,
            api_client=api_client,
            bot_account_id=bot_account_id,
+            **kwargs,
        )

    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
        pass

+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
+    async def create_card_id(self, message_id):
+        try:
+            # self.logger.debug('飞书支持stream输出,创建卡片......')
+
+            card_data = {
+                'schema': '2.0',
+                'config': {
+                    'update_multi': True,
+                    'streaming_mode': True,
+                    'streaming_config': {
+                        'print_step': {'default': 1},
+                        'print_frequency_ms': {'default': 70},
+                        'print_strategy': 'fast',
+                    },
+                },
+                'body': {
+                    'direction': 'vertical',
+                    'padding': '12px 12px 12px 12px',
+                    'elements': [
+                        {
+                            'tag': 'div',
+                            'text': {
+                                'tag': 'plain_text',
+                                'content': 'LangBot',
+                                'text_size': 'normal',
+                                'text_align': 'left',
+                                'text_color': 'default',
+                            },
+                            'icon': {
+                                'tag': 'custom_icon',
+                                'img_key': 'img_v3_02p3_05c65d5d-9bad-440a-a2fb-c89571bfd5bg',
+                            },
+                        },
+                        {
+                            'tag': 'markdown',
+                            'content': '',
+                            'text_align': 'left',
+                            'text_size': 'normal',
+                            'margin': '0px 0px 0px 0px',
+                            'element_id': 'streaming_txt',
+                        },
+                        {
+                            'tag': 'markdown',
+                            'content': '',
+                            'text_align': 'left',
+                            'text_size': 'normal',
+                            'margin': '0px 0px 0px 0px',
+                        },
+                        {
+                            'tag': 'column_set',
+                            'horizontal_spacing': '8px',
+                            'horizontal_align': 'left',
+                            'columns': [
+                                {
+                                    'tag': 'column',
+                                    'width': 'weighted',
+                                    'elements': [
+                                        {
+                                            'tag': 'markdown',
+                                            'content': '',
+                                            'text_align': 'left',
+                                            'text_size': 'normal',
+                                            'margin': '0px 0px 0px 0px',
+                                        },
+                                        {
+                                            'tag': 'markdown',
+                                            'content': '',
+                                            'text_align': 'left',
+                                            'text_size': 'normal',
+                                            'margin': '0px 0px 0px 0px',
+                                        },
+                                        {
+                                            'tag': 'markdown',
+                                            'content': '',
+                                            'text_align': 'left',
+                                            'text_size': 'normal',
+                                            'margin': '0px 0px 0px 0px',
+                                        },
+                                    ],
+                                    'padding': '0px 0px 0px 0px',
+                                    'direction': 'vertical',
+                                    'horizontal_spacing': '8px',
+                                    'vertical_spacing': '2px',
+                                    'horizontal_align': 'left',
+                                    'vertical_align': 'top',
+                                    'margin': '0px 0px 0px 0px',
+                                    'weight': 1,
+                                }
+                            ],
+                            'margin': '0px 0px 0px 0px',
+                        },
+                        {'tag': 'hr', 'margin': '0px 0px 0px 0px'},
+                        {
+                            'tag': 'column_set',
+                            'horizontal_spacing': '12px',
+                            'horizontal_align': 'right',
+                            'columns': [
+                                {
+                                    'tag': 'column',
+                                    'width': 'weighted',
+                                    'elements': [
+                                        {
+                                            'tag': 'markdown',
+                                            'content': '<font color="grey-600">以上内容由 AI 生成，仅供参考。更多详细、准确信息可点击引用链接查看</font>',
+                                            'text_align': 'left',
+                                            'text_size': 'notation',
+                                            'margin': '4px 0px 0px 0px',
+                                            'icon': {
+                                                'tag': 'standard_icon',
+                                                'token': 'robot_outlined',
+                                                'color': 'grey',
+                                            },
+                                        }
+                                    ],
+                                    'padding': '0px 0px 0px 0px',
+                                    'direction': 'vertical',
+                                    'horizontal_spacing': '8px',
+                                    'vertical_spacing': '8px',
+                                    'horizontal_align': 'left',
+                                    'vertical_align': 'top',
+                                    'margin': '0px 0px 0px 0px',
+                                    'weight': 1,
+                                },
+                                {
+                                    'tag': 'column',
+                                    'width': '20px',
+                                    'elements': [
+                                        {
+                                            'tag': 'button',
+                                            'text': {'tag': 'plain_text', 'content': ''},
+                                            'type': 'text',
+                                            'width': 'fill',
+                                            'size': 'medium',
+                                            'icon': {'tag': 'standard_icon', 'token': 'thumbsup_outlined'},
+                                            'hover_tips': {'tag': 'plain_text', 'content': '有帮助'},
+                                            'margin': '0px 0px 0px 0px',
+                                        }
+                                    ],
+                                    'padding': '0px 0px 0px 0px',
+                                    'direction': 'vertical',
+                                    'horizontal_spacing': '8px',
+                                    'vertical_spacing': '8px',
+                                    'horizontal_align': 'left',
+                                    'vertical_align': 'top',
+                                    'margin': '0px 0px 0px 0px',
+                                },
+                                {
+                                    'tag': 'column',
+                                    'width': '30px',
+                                    'elements': [
+                                        {
+                                            'tag': 'button',
+                                            'text': {'tag': 'plain_text', 'content': ''},
+                                            'type': 'text',
+                                            'width': 'default',
+                                            'size': 'medium',
+                                            'icon': {'tag': 'standard_icon', 'token': 'thumbdown_outlined'},
+                                            'hover_tips': {'tag': 'plain_text', 'content': '无帮助'},
+                                            'margin': '0px 0px 0px 0px',
+                                        }
+                                    ],
+                                    'padding': '0px 0px 0px 0px',
+                                    'vertical_spacing': '8px',
+                                    'horizontal_align': 'left',
+                                    'vertical_align': 'top',
+                                    'margin': '0px 0px 0px 0px',
+                                },
+                            ],
+                            'margin': '0px 0px 4px 0px',
+                        },
+                    ],
+                },
+            }
+            # delay / fast 创建卡片模板，delay 延迟打印，fast 实时打印，可以自定义更好看的消息模板
+
+            request: CreateCardRequest = (
+                CreateCardRequest.builder()
+                .request_body(CreateCardRequestBody.builder().type('card_json').data(json.dumps(card_data)).build())
+                .build()
+            )
+
+            # 发起请求
+            response: CreateCardResponse = self.api_client.cardkit.v1.card.create(request)
+
+            # 处理失败返回
+            if not response.success():
+                raise Exception(
+                    f'client.cardkit.v1.card.create failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+                )
+
+            self.ap.logger.debug(f'飞书卡片创建成功,卡片ID: {response.data.card_id}')
+            self.card_id_dict[message_id] = response.data.card_id
+
+            card_id = response.data.card_id
+            return card_id
+
+        except Exception as e:
+            self.ap.logger.error(f'飞书卡片创建失败,错误信息: {e}')
+
+    async def create_message_card(self, message_id, event) -> str:
+        """
+        创建卡片消息。
+        使用卡片消息是因为普通消息更新次数有限制，而大模型流式返回结果可能很多而超过限制，而飞书卡片没有这个限制（api免费次数有限）
+        """
+        # message_id = event.message_chain.message_id
+
+        card_id = await self.create_card_id(message_id)
+        content = {
+            'type': 'card',
+            'data': {'card_id': card_id, 'template_variable': {'content': 'Thinking...'}},
+        }  # 当收到消息时发送消息模板，可添加模板变量，详情查看飞书中接口文档
+        request: ReplyMessageRequest = (
+            ReplyMessageRequest.builder()
+            .message_id(event.message_chain.message_id)
+            .request_body(
+                ReplyMessageRequestBody.builder().content(json.dumps(content)).msg_type('interactive').build()
+            )
+            .build()
+        )
+
+        # 发起请求
+        response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request)
+
+        # 处理失败返回
+        if not response.success():
+            raise Exception(
+                f'client.im.v1.message.reply failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+            )
+        return True
+
    async def reply_message(
        self,
        message_source: platform_events.MessageEvent,
@@ -446,6 +698,62 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                f'client.im.v1.message.reply failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
            )

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        """
+        回复消息变成更新卡片消息
+        """
+        # self.seq += 1
+        message_id = bot_message.resp_message_id
+        msg_seq = bot_message.msg_sequence
+        if msg_seq % 8 == 0 or is_final:
+            lark_message = await self.message_converter.yiri2target(message, self.api_client)
+
+            text_message = ''
+            for ele in lark_message[0]:
+                if ele['tag'] == 'text':
+                    text_message += ele['text']
+                elif ele['tag'] == 'md':
+                    text_message += ele['text']
+
+            # content = {
+            #     'type': 'card_json',
+            #     'data': {'card_id': self.card_id_dict[message_id], 'elements': {'content': text_message}},
+            # }
+
+            request: ContentCardElementRequest = (
+                ContentCardElementRequest.builder()
+                .card_id(self.card_id_dict[message_id])
+                .element_id('streaming_txt')
+                .request_body(
+                    ContentCardElementRequestBody.builder()
+                    # .uuid("a0d69e20-1dd1-458b-k525-dfeca4015204")
+                    .content(text_message)
+                    .sequence(msg_seq)
+                    .build()
+                )
+                .build()
+            )
+
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.card_id_dict.pop(message_id)  # 清理已经使用过的卡片
+            # 发起请求
+            response: ContentCardElementResponse = self.api_client.cardkit.v1.card_element.content(request)
+
+            # 处理失败返回
+            if not response.success():
+                raise Exception(
+                    f'client.im.v1.message.patch failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+                )
+                return
+
    async def is_muted(self, group_id: int) -> bool:
        return False

@@ -495,4 +803,9 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
            )

    async def kill(self) -> bool:
+        # 需要断开连接，不然旧的连接会继续运行，导致飞书消息来时会随机选择一个连接
+        # 断开时lark.ws.Client的_receive_message_loop会打印error日志: receive message loop exit。然后进行重连，
+        # 所以要设置_auto_reconnect=False,让其不重连。
+        self.bot._auto_reconnect = False
+        await self.bot._disconnect()
        return False
--- a/pkg/platform/sources/lark.yaml
+++ b/pkg/platform/sources/lark.yaml
@@ -65,6 +65,16 @@ spec:
      type: string
      required: true
      default: ""
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用飞书流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of lark reply mode
+        zh_Hans: 如果启用，将使用飞书流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
 execution:
  python:
    path: ./lark.py
--- a/pkg/platform/sources/telegram.py
+++ b/pkg/platform/sources/telegram.py
@@ -1,5 +1,6 @@
 from __future__ import annotations

+
 import telegram
 import telegram.ext
 from telegram import Update
@@ -136,6 +137,12 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
    message_converter: TelegramMessageConverter = TelegramMessageConverter()
    event_converter: TelegramEventConverter = TelegramEventConverter()

+    config: dict
+
+    msg_stream_id: dict  # 流式消息id字典，key为流式消息id，value为首次消息源id，用于在流式消息时判断编辑那条消息
+
+    seq: int  # 消息中识别消息顺序，直接以seq作为标识
+
    listeners: typing.Dict[
        typing.Type[platform_events.Event],
        typing.Callable[[platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None],
@@ -149,6 +156,7 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
            try:
                lb_event = await self.event_converter.target2yiri(update, self.bot, self.bot_account_id)
                await self.listeners[type(lb_event)](lb_event, self)
+                await self.is_stream_output_supported()
            except Exception:
                await self.logger.error(f'Error in telegram callback: {traceback.format_exc()}')

@@ -158,6 +166,8 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        super().__init__(
            config=config,
            logger=logger,
+            msg_stream_id={},
+            seq=1,
            bot=bot,
            application=application,
            bot_account_id='',
@@ -195,6 +205,70 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

        await self.bot.send_message(**args)

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        msg_seq = bot_message.msg_sequence
+        if (msg_seq - 1) % 8 == 0 or is_final:
+            assert isinstance(message_source.source_platform_object, Update)
+            components = await TelegramMessageConverter.yiri2target(message, self.bot)
+            args = {}
+            message_id = message_source.source_platform_object.message.id
+            if quote_origin:
+                args['reply_to_message_id'] = message_source.source_platform_object.message.id
+
+            component = components[0]
+            if message_id not in self.msg_stream_id:  # 当消息回复第一次时，发送新消息
+                # time.sleep(0.6)
+                if component['type'] == 'text':
+                    if self.config['markdown_card'] is True:
+                        content = telegramify_markdown.markdownify(
+                            content=component['text'],
+                        )
+                    else:
+                        content = component['text']
+                    args = {
+                        'chat_id': message_source.source_platform_object.effective_chat.id,
+                        'text': content,
+                    }
+                    if self.config['markdown_card'] is True:
+                        args['parse_mode'] = 'MarkdownV2'
+
+                send_msg = await self.bot.send_message(**args)
+                send_msg_id = send_msg.message_id
+                self.msg_stream_id[message_id] = send_msg_id
+            else:  # 存在消息的时候直接编辑消息1
+                if component['type'] == 'text':
+                    if self.config['markdown_card'] is True:
+                        content = telegramify_markdown.markdownify(
+                            content=component['text'],
+                        )
+                    else:
+                        content = component['text']
+                    args = {
+                        'message_id': self.msg_stream_id[message_id],
+                        'chat_id': message_source.source_platform_object.effective_chat.id,
+                        'text': content,
+                    }
+                    if self.config['markdown_card'] is True:
+                        args['parse_mode'] = 'MarkdownV2'
+
+                await self.bot.edit_message_text(**args)
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.msg_stream_id.pop(message_id)  # 消息回复结束之后删除流式消息id
+
+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
    async def is_muted(self, group_id: int) -> bool:
        return False

@@ -221,8 +295,12 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        self.bot_account_id = (await self.bot.get_me()).username
        await self.application.updater.start_polling(allowed_updates=Update.ALL_TYPES)
        await self.application.start()
+        await self.logger.info('Telegram adapter running')

    async def kill(self) -> bool:
        if self.application.running:
            await self.application.stop()
+            if self.application.updater:
+                await self.application.updater.stop()
+            await self.logger.info('Telegram adapter stopped')
        return True
--- a/pkg/platform/sources/telegram.yaml
+++ b/pkg/platform/sources/telegram.yaml
@@ -25,6 +25,16 @@ spec:
      type: boolean
      required: false
      default: true
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用电报流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of telegram reply mode
+        zh_Hans: 如果启用，将使用电报流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
 execution:
  python:
    path: ./telegram.py
--- a/pkg/platform/sources/webchat.py
+++ b/pkg/platform/sources/webchat.py
@@ -9,8 +9,8 @@ import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platf
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
-from ...core import app
 import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_platform_logger
+from ...core import app

 logger = logging.getLogger(__name__)

@@ -21,17 +21,20 @@ class WebChatMessage(pydantic.BaseModel):
    content: str
    message_chain: list[dict]
    timestamp: str
+    is_final: bool = False


 class WebChatSession:
    id: str
    message_lists: dict[str, list[WebChatMessage]] = {}
    resp_waiters: dict[int, asyncio.Future[WebChatMessage]]
+    resp_queues: dict[int, asyncio.Queue[WebChatMessage]]

    def __init__(self, id: str):
        self.id = id
        self.message_lists = {}
        self.resp_waiters = {}
+        self.resp_queues = {}

    def get_message_list(self, pipeline_uuid: str) -> list[WebChatMessage]:
        if pipeline_uuid not in self.message_lists:
@@ -46,20 +49,21 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
    webchat_person_session: WebChatSession = pydantic.Field(exclude=True, default_factory=WebChatSession)
    webchat_group_session: WebChatSession = pydantic.Field(exclude=True, default_factory=WebChatSession)

-    ap: app.Application = pydantic.Field(exclude=True)  # set by bot manager
-
    listeners: dict[
        typing.Type[platform_events.Event],
        typing.Callable[[platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None],
    ] = pydantic.Field(default_factory=dict, exclude=True)

+    is_stream: bool = pydantic.Field(exclude=True)
    debug_messages: dict[str, list[dict]] = pydantic.Field(default_factory=dict, exclude=True)

-    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, ap: app.Application):
+    ap: app.Application = pydantic.Field(exclude=True)
+
+    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, **kwargs):
        super().__init__(
            config=config,
            logger=logger,
-            ap=ap,
+            **kwargs,
        )

        self.webchat_person_session = WebChatSession(id='webchatperson')
@@ -112,12 +116,53 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

        # notify waiter
        if isinstance(message_source, platform_events.FriendMessage):
-            self.webchat_person_session.resp_waiters[message_source.message_chain.message_id].set_result(message_data)
+            await self.webchat_person_session.resp_queues[message_source.message_chain.message_id].put(message_data)
        elif isinstance(message_source, platform_events.GroupMessage):
-            self.webchat_group_session.resp_waiters[message_source.message_chain.message_id].set_result(message_data)
+            await self.webchat_group_session.resp_queues[message_source.message_chain.message_id].put(message_data)

        return message_data.model_dump()

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ) -> dict:
+        """回复消息"""
+        message_data = WebChatMessage(
+            id=-1,
+            role='assistant',
+            content=str(message),
+            message_chain=[component.__dict__ for component in message],
+            timestamp=datetime.now().isoformat(),
+        )
+
+        # notify waiter
+        session = (
+            self.webchat_group_session
+            if isinstance(message_source, platform_events.GroupMessage)
+            else self.webchat_person_session
+        )
+        if message_source.message_chain.message_id not in session.resp_waiters:
+            # session.resp_waiters[message_source.message_chain.message_id] = asyncio.Queue()
+            queue = session.resp_queues[message_source.message_chain.message_id]
+
+        # if isinstance(message_source, platform_events.FriendMessage):
+        #     queue = self.webchat_person_session.resp_queues[message_source.message_chain.message_id]
+        # elif isinstance(message_source, platform_events.GroupMessage):
+        #     queue = self.webchat_group_session.resp_queues[message_source.message_chain.message_id]
+        if is_final and bot_message.tool_calls is None:
+            message_data.is_final = True
+        # print(message_data)
+        await queue.put(message_data)
+
+        return message_data.model_dump()
+
+    async def is_stream_output_supported(self) -> bool:
+        return self.is_stream
+
    def register_listener(
        self,
        event_type: typing.Type[platform_events.Event],
@@ -157,8 +202,13 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        await self.logger.info('WebChat调试适配器正在停止')

    async def send_webchat_message(
-        self, pipeline_uuid: str, session_type: str, message_chain_obj: typing.List[dict]
+        self,
+        pipeline_uuid: str,
+        session_type: str,
+        message_chain_obj: typing.List[dict],
+        is_stream: bool = False,
    ) -> dict:
+        self.is_stream = is_stream
        """发送调试消息到流水线"""
        if session_type == 'person':
            use_session = self.webchat_person_session
@@ -169,6 +219,9 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

        message_id = len(use_session.get_message_list(pipeline_uuid)) + 1

+        use_session.resp_queues[message_id] = asyncio.Queue()
+        logger.debug(f'Initialized queue for message_id: {message_id}')
+
        use_session.get_message_list(pipeline_uuid).append(
            WebChatMessage(
                id=message_id,
@@ -182,7 +235,7 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        message_chain.insert(0, platform_message.Source(id=message_id, time=datetime.now().timestamp()))

        if session_type == 'person':
-            sender = platform_entities.Friend(id='webchatperson', nickname='User')
+            sender = platform_entities.Friend(id='webchatperson', nickname='User', remark='User')
            event = platform_events.FriendMessage(
                sender=sender, message_chain=message_chain, time=datetime.now().timestamp()
            )
@@ -202,21 +255,46 @@ class WebChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):

        self.ap.platform_mgr.webchat_proxy_bot.bot_entity.use_pipeline_uuid = pipeline_uuid

+        # trigger pipeline
        if event.__class__ in self.listeners:
            await self.listeners[event.__class__](event, self)

-        # set waiter
-        waiter = asyncio.Future[WebChatMessage]()
-        use_session.resp_waiters[message_id] = waiter
-        waiter.add_done_callback(lambda future: use_session.resp_waiters.pop(message_id))
+        if is_stream:
+            queue = use_session.resp_queues[message_id]
+            msg_id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            while True:
+                resp_message = await queue.get()
+                resp_message.id = msg_id
+                if resp_message.is_final:
+                    resp_message.id = msg_id
+                    use_session.get_message_list(pipeline_uuid).append(resp_message)
+                    yield resp_message.model_dump()
+                    break
+                yield resp_message.model_dump()
+            use_session.resp_queues.pop(message_id)

-        resp_message = await waiter
+        else:  # non-stream
+            # set waiter
+            # waiter = asyncio.Future[WebChatMessage]()
+            # use_session.resp_waiters[message_id] = waiter
+            # # waiter.add_done_callback(lambda future: use_session.resp_waiters.pop(message_id))
+            #
+            # resp_message = await waiter
+            #
+            # resp_message.id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            #
+            # use_session.get_message_list(pipeline_uuid).append(resp_message)
+            #
+            # yield resp_message.model_dump()
+            msg_id = len(use_session.get_message_list(pipeline_uuid)) + 1

-        resp_message.id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            queue = use_session.resp_queues[message_id]
+            resp_message = await queue.get()
+            use_session.get_message_list(pipeline_uuid).append(resp_message)
+            resp_message.id = msg_id
+            resp_message.is_final = True

-        use_session.get_message_list(pipeline_uuid).append(resp_message)
-
-        return resp_message.model_dump()
+            yield resp_message.model_dump()

    def get_webchat_messages(self, pipeline_uuid: str, session_type: str) -> list[dict]:
        """获取调试消息历史"""
--- a/pkg/platform/sources/webchat.yaml
+++ b/pkg/platform/sources/webchat.yaml
@@ -9,7 +9,8 @@ metadata:
    en_US: "WebChat adapter for pipeline debugging"
    zh_Hans: "用于流水线调试的网页聊天适配器"
  icon: ""
-spec: {}
+spec:
+  config: []
 execution:
  python:
    path: "webchat.py"
--- a/pkg/platform/sources/wechatpad.py
+++ b/pkg/platform/sources/wechatpad.py
@@ -11,13 +11,11 @@ import asyncio
 import traceback
 import re
 import base64
-import os
 import copy
 import threading

 import quart

-from ...core import app
 from ..logger import EventLogger
 import xml.etree.ElementTree as ET
 from typing import Optional, Tuple
@@ -27,21 +25,23 @@ import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
 import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
+import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_platform_logger


 class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
-    def __init__(self, config: dict):
+    def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger):
        self.config = config
        self.bot = WeChatPadClient(self.config['wechatpad_url'], self.config['token'])
-        self.logger = logging.getLogger('WeChatPadMessageConverter')
+        self.logger = logger

    @staticmethod
    async def yiri2target(message_chain: platform_message.MessageChain) -> list[dict]:
        content_list = []
-        _ = os.path.abspath(__file__)

        for component in message_chain:
-            if isinstance(component, platform_message.At):
+            if isinstance(component, platform_message.AtAll):
+                content_list.append({'type': 'at', 'target': 'all'})
+            elif isinstance(component, platform_message.At):
                content_list.append({'type': 'at', 'target': component.target})
            elif isinstance(component, platform_message.Plain):
                content_list.append({'type': 'text', 'content': component.text})
@@ -75,20 +75,34 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert

        return content_list

-    async def target2yiri(self, message: dict, bot_account_id: str) -> platform_message.MessageChain:
+    async def target2yiri(
+        self,
+        message: dict,
+        bot_account_id: str,
+    ) -> platform_message.MessageChain:
        """外部消息转平台消息"""
        # 数据预处理
        message_list = []
+        bot_wxid = self.config['wxid']
        ats_bot = False  # 是否被@
        content = message['content']['str']
        content_no_preifx = content  # 群消息则去掉前缀
        is_group_message = self._is_group_message(message)
        if is_group_message:
            ats_bot = self._ats_bot(message, bot_account_id)
+
+            self.logger.info(f'ats_bot: {ats_bot}; bot_account_id: {bot_account_id}; bot_wxid: {bot_wxid}')
            if '@所有人' in content:
                message_list.append(platform_message.AtAll())
-            elif ats_bot:
+            if ats_bot:
                message_list.append(platform_message.At(target=bot_account_id))
+
+            # 解析@信息并生成At组件
+            at_targets = self._extract_at_targets(message)
+            for target_id in at_targets:
+                if target_id != bot_wxid:  # 避免重复添加机器人的At
+                    message_list.append(platform_message.At(target=target_id))
+
            content_no_preifx, _ = self._extract_content_and_sender(content)

        msg_type = message['msg_type']
@@ -226,8 +240,8 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
        #         self.logger.info("_handler_compound_quote", ET.tostring(xml_data, encoding='unicode'))
        appmsg_data = xml_data.find('.//appmsg')
        quote_data = ''  # 引用原文
-        quote_id = None  # 引用消息的原发送者
-        tousername = None  # 接收方: 所属微信的wxid
+        # quote_id = None  # 引用消息的原发送者
+        # tousername = None  # 接收方: 所属微信的wxid
        user_data = ''  # 用户消息
        sender_id = xml_data.findtext('.//fromusername')  # 发送方：单聊用户/群member

@@ -235,13 +249,10 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
        if appmsg_data:
            user_data = appmsg_data.findtext('.//title') or ''
            quote_data = appmsg_data.find('.//refermsg').findtext('.//content')
-            quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
+            # quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
            message_list.append(platform_message.WeChatAppMsg(app_msg=ET.tostring(appmsg_data, encoding='unicode')))
-        if message:
-            tousername = message['to_user_name']['str']
-
-        _ = tousername
-        _ = quote_id
+        # if message:
+        #     tousername = message['to_user_name']['str']

        if quote_data:
            quote_data_message_list = platform_message.MessageChain()
@@ -397,6 +408,23 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert
        finally:
            return ats_bot

+    # 提取一下at的wxid列表
+    def _extract_at_targets(self, message: dict) -> list[str]:
+        """从消息中提取被@用户的ID列表"""
+        at_targets = []
+        try:
+            # 从msg_source中解析atuserlist
+            msg_source = message.get('msg_source', '') or ''
+            if len(msg_source) > 0:
+                msg_source_data = ET.fromstring(msg_source)
+                at_user_list = msg_source_data.findtext('atuserlist') or ''
+                if at_user_list:
+                    # atuserlist格式通常是逗号分隔的用户ID列表
+                    at_targets = [user_id.strip() for user_id in at_user_list.split(',') if user_id.strip()]
+        except Exception as e:
+            self.logger.error(f'_extract_at_targets got except: {e}')
+        return at_targets
+
    # 提取一下content前面的sender_id, 和去掉前缀的内容
    def _extract_content_and_sender(self, raw_content: str) -> Tuple[str, Optional[str]]:
        try:
@@ -420,16 +448,20 @@ class WeChatPadMessageConverter(abstract_platform_adapter.AbstractMessageConvert


 class WeChatPadEventConverter(abstract_platform_adapter.AbstractEventConverter):
-    def __init__(self, config: dict):
+    def __init__(self, config: dict, logger: logging.Logger):
        self.config = config
-        self.message_converter = WeChatPadMessageConverter(config)
-        self.logger = logging.getLogger('WeChatPadEventConverter')
+        self.message_converter = WeChatPadMessageConverter(config, logger)
+        self.logger = logger

    @staticmethod
    async def yiri2target(event: platform_events.MessageEvent) -> dict:
        pass

-    async def target2yiri(self, event: dict, bot_account_id: str) -> platform_events.MessageEvent:
+    async def target2yiri(
+        self,
+        event: dict,
+        bot_account_id: str,
+    ) -> platform_events.MessageEvent:
        # 排除公众号以及微信团队消息
        if (
            event['from_user_name']['str'].startswith('gh_')
@@ -489,8 +521,6 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)

    config: dict

-    ap: app.Application
-
    logger: EventLogger

    message_converter: WeChatPadMessageConverter
@@ -501,14 +531,13 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
        typing.Callable[[platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None],
    ] = {}

-    def __init__(self, config: dict, ap: app.Application, logger: EventLogger):
+    def __init__(self, config: dict, logger: EventLogger):
        self.config = config
-        self.ap = ap
        self.logger = logger
        self.quart_app = quart.Quart(__name__)

-        self.message_converter = WeChatPadMessageConverter(config)
-        self.event_converter = WeChatPadEventConverter(config)
+        self.message_converter = WeChatPadMessageConverter(config, logger)
+        self.event_converter = WeChatPadEventConverter(config, logger)

    async def ws_message(self, data):
        """处理接收到的消息"""
@@ -541,19 +570,22 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
        for msg in content_list:
            # 文本消息处理@
            if msg['type'] == 'text' and at_targets:
-                at_nick_name_list = []
-                for member in member_info:
-                    if member['user_name'] in at_targets:
-                        at_nick_name_list.append(f'@{member["nick_name"]}')
-                msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'
+                if 'all' in at_targets:
+                    msg['content'] = f'@所有人 {msg["content"]}'
+                else:
+                    at_nick_name_list = []
+                    for member in member_info:
+                        if member['user_name'] in at_targets:
+                            at_nick_name_list.append(f'@{member["nick_name"]}')
+                    msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'

            # 统一消息派发
            handler_map = {
                'text': lambda msg: self.bot.send_text_message(
-                    to_wxid=target_id, message=msg['content'], ats=at_targets
+                    to_wxid=target_id, message=msg['content'], ats=['notify@all'] if 'all' in at_targets else at_targets
                ),
                'image': lambda msg: self.bot.send_image_message(
-                    to_wxid=target_id, img_url=msg['image'], ats=at_targets
+                    to_wxid=target_id, img_url=msg['image'], ats=['notify@all'] if 'all' in at_targets else at_targets
                ),
                'WeChatEmoji': lambda msg: self.bot.send_emoji_message(
                    to_wxid=target_id, emoji_md5=msg['emoji_md5'], emoji_size=msg['emoji_size']
@@ -575,7 +607,7 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
            if handler := handler_map.get(msg['type']):
                handler(msg)
            else:
-                print(f'未处理的消息类型: {msg["type"]}')
+                self.logger.warning(f'未处理的消息类型: {msg["type"]}')
                continue

    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
@@ -650,7 +682,7 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
            # url = login_data['Data']["QrCodeUrl"]

            profile = self.bot.get_profile()
-            self.logger.info(profile)
+            # self.logger.info(profile)

            self.bot_account_id = profile['Data']['userInfo']['nickName']['str']
            self.config['wxid'] = profile['Data']['userInfo']['userName']['str']
@@ -670,18 +702,18 @@ class WeChatPadAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
                    # 这里需要确保ws_message是同步的，或者使用asyncio.run调用异步方法
                    asyncio.run(self.ws_message(data))
                except json.JSONDecodeError:
-                    print(f'Non-JSON message: {message[:100]}...')
+                    self.logger.error(f'Non-JSON message: {message[:100]}...')

            def on_error(ws, error):
-                print(f'WebSocket error: {str(error)[:200]}')
+                self.logger.error(f'WebSocket error: {str(error)[:200]}')

            def on_close(ws, close_status_code, close_msg):
-                print('WebSocket closed, reconnecting...')
+                self.logger.info('WebSocket closed, reconnecting...')
                time.sleep(5)
                connect_websocket_sync()  # 自动重连

            def on_open(ws):
-                print('WebSocket connected successfully!')
+                self.logger.info('WebSocket connected successfully!')

            ws = websocket.WebSocketApp(
                uri, on_message=on_message, on_error=on_error, on_close=on_close, on_open=on_open
--- a/pkg/platform/sources/wecomcs.py
+++ b/pkg/platform/sources/wecomcs.py
@@ -144,9 +144,9 @@ class WecomCSAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
        super().__init__(
            config=config,
            logger=logger,
-            bot=bot,
            bot_account_id='',
            listeners={},
+            bot=bot,
        )

    async def reply_message(
--- a/pkg/plugin/connector.py
+++ b/pkg/plugin/connector.py
@@ -51,7 +51,7 @@ class PluginRuntimeConnector:
    async def initialize(self):
        async def new_connection_callback(connection: base_connection.Connection):
            async def disconnect_callback(rchandler: handler.RuntimeConnectionHandler) -> bool:
-                if platform.get_platform() == 'docker':
+                if platform.get_platform() == 'docker' or platform.use_websocket_to_connect_plugin_runtime():
                    self.ap.logger.error('Disconnected from plugin runtime, trying to reconnect...')
                    await self.runtime_disconnect_callback(self)
                    return False
@@ -69,7 +69,7 @@ class PluginRuntimeConnector:

        task: asyncio.Task | None = None

-        if platform.get_platform() == 'docker':  # use websocket
+        if platform.get_platform() == 'docker' or platform.use_websocket_to_connect_plugin_runtime():  # use websocket
            self.ap.logger.info('use websocket to connect to plugin runtime')
            ws_url = self.ap.instance_config.data['plugin']['runtime_ws_url']

--- a/pkg/plugin/handler.py
+++ b/pkg/plugin/handler.py
@@ -97,7 +97,7 @@ class RuntimeConnectionHandler(handler.Handler):
            )

            data = {
-                'enabled': False,
+                'enabled': True,
                'priority': 0,
                'plugin_config': {},
                'install_source': 'local',
--- a/pkg/provider/modelmgr/entities.py
+++ b/pkg/provider/modelmgr/entities.py
@@ -17,7 +17,7 @@ class LLMModelInfo(pydantic.BaseModel):

    token_mgr: token.TokenManager

-    requester: requester.LLMAPIRequester
+    requester: requester.ProviderAPIRequester

    tool_call_supported: typing.Optional[bool] = False

--- a/pkg/provider/modelmgr/modelmgr.py
+++ b/pkg/provider/modelmgr/modelmgr.py
@@ -20,13 +20,16 @@ class ModelManager:

    llm_models: list[requester.RuntimeLLMModel]

+    embedding_models: list[requester.RuntimeEmbeddingModel]
+
    requester_components: list[engine.Component]

-    requester_dict: dict[str, type[requester.LLMAPIRequester]]  # cache
+    requester_dict: dict[str, type[requester.ProviderAPIRequester]]  # cache

    def __init__(self, ap: app.Application):
        self.ap = ap
        self.llm_models = []
+        self.embedding_models = []
        self.requester_components = []
        self.requester_dict = {}

@@ -34,7 +37,7 @@ class ModelManager:
        self.requester_components = self.ap.discover.get_components_by_kind('LLMAPIRequester')

        # forge requester class dict
-        requester_dict: dict[str, type[requester.LLMAPIRequester]] = {}
+        requester_dict: dict[str, type[requester.ProviderAPIRequester]] = {}
        for component in self.requester_components:
            requester_dict[component.metadata.name] = component.get_python_component_class()

@@ -47,13 +50,11 @@ class ModelManager:
        self.ap.logger.info('Loading models from db...')

        self.llm_models = []
+        self.embedding_models = []

        # llm models
        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
-
        llm_models = result.all()
-
-        # load models
        for llm_model in llm_models:
            try:
                await self.load_llm_model(llm_model)
@@ -62,11 +63,17 @@ class ModelManager:
            except Exception as e:
                self.ap.logger.error(f'Failed to load model {llm_model.uuid}: {e}\n{traceback.format_exc()}')

+        # embedding models
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
+        embedding_models = result.all()
+        for embedding_model in embedding_models:
+            await self.load_embedding_model(embedding_model)
+
    async def init_runtime_llm_model(
        self,
        model_info: persistence_model.LLMModel | sqlalchemy.Row[persistence_model.LLMModel] | dict,
    ):
-        """初始化运行时模型"""
+        """初始化运行时 LLM 模型"""
        if isinstance(model_info, sqlalchemy.Row):
            model_info = persistence_model.LLMModel(**model_info._mapping)
        elif isinstance(model_info, dict):
@@ -90,31 +97,85 @@ class ModelManager:

        return runtime_llm_model

+    async def init_runtime_embedding_model(
+        self,
+        model_info: persistence_model.EmbeddingModel | sqlalchemy.Row[persistence_model.EmbeddingModel] | dict,
+    ):
+        """初始化运行时 Embedding 模型"""
+        if isinstance(model_info, sqlalchemy.Row):
+            model_info = persistence_model.EmbeddingModel(**model_info._mapping)
+        elif isinstance(model_info, dict):
+            model_info = persistence_model.EmbeddingModel(**model_info)
+
+        requester_inst = self.requester_dict[model_info.requester](ap=self.ap, config=model_info.requester_config)
+
+        await requester_inst.initialize()
+
+        runtime_embedding_model = requester.RuntimeEmbeddingModel(
+            model_entity=model_info,
+            token_mgr=token.TokenManager(
+                name=model_info.uuid,
+                tokens=model_info.api_keys,
+            ),
+            requester=requester_inst,
+        )
+
+        return runtime_embedding_model
+
    async def load_llm_model(
        self,
        model_info: persistence_model.LLMModel | sqlalchemy.Row[persistence_model.LLMModel] | dict,
    ):
-        """加载模型"""
+        """加载 LLM 模型"""
        runtime_llm_model = await self.init_runtime_llm_model(model_info)
        self.llm_models.append(runtime_llm_model)

+    async def load_embedding_model(
+        self,
+        model_info: persistence_model.EmbeddingModel | sqlalchemy.Row[persistence_model.EmbeddingModel] | dict,
+    ):
+        """加载 Embedding 模型"""
+        runtime_embedding_model = await self.init_runtime_embedding_model(model_info)
+        self.embedding_models.append(runtime_embedding_model)
+
    async def get_model_by_uuid(self, uuid: str) -> requester.RuntimeLLMModel:
-        """通过uuid获取模型"""
+        """通过uuid获取 LLM 模型"""
        for model in self.llm_models:
            if model.model_entity.uuid == uuid:
                return model
-        raise ValueError(f'model {uuid} not found')
+        raise ValueError(f'LLM model {uuid} not found')
+
+    async def get_embedding_model_by_uuid(self, uuid: str) -> requester.RuntimeEmbeddingModel:
+        """通过uuid获取 Embedding 模型"""
+        for model in self.embedding_models:
+            if model.model_entity.uuid == uuid:
+                return model
+        raise ValueError(f'Embedding model {uuid} not found')

    async def remove_llm_model(self, model_uuid: str):
-        """移除模型"""
+        """移除 LLM 模型"""
        for model in self.llm_models:
            if model.model_entity.uuid == model_uuid:
                self.llm_models.remove(model)
                return

-    def get_available_requesters_info(self) -> list[dict]:
+    async def remove_embedding_model(self, model_uuid: str):
+        """移除 Embedding 模型"""
+        for model in self.embedding_models:
+            if model.model_entity.uuid == model_uuid:
+                self.embedding_models.remove(model)
+                return
+
+    def get_available_requesters_info(self, model_type: str) -> list[dict]:
        """获取所有可用的请求器"""
-        return [component.to_plain_dict() for component in self.requester_components]
+        if model_type != '':
+            return [
+                component.to_plain_dict()
+                for component in self.requester_components
+                if model_type in component.spec['support_type']
+            ]
+        else:
+            return [component.to_plain_dict() for component in self.requester_components]

    def get_available_requester_info_by_name(self, name: str) -> dict | None:
        """通过名称获取请求器信息"""
--- a/Show More
+++ b/Show More