chore: bump version 4.3.0b4

* feat: add ZIP file upload support for knowledge base

- Add _parse_zip method to FileParser class using zipfile library
- Support extraction and processing of TXT, PDF, DOCX, MD, HTML files from ZIP
- Update FileUploadZone to accept .zip files
- Add ZIP format to supported formats in internationalization files
- Implement error handling for invalid ZIP files and unsupported content
- Follow existing async parsing patterns and error handling conventions

Co-Authored-By: Rock <rockchinq@gmail.com>

* refactor: modify ZIP processing to store each document as separate file

- Remove _parse_zip method from FileParser as ZIP handling now occurs at knowledge base level
- Add _store_zip_file method to RuntimeKnowledgeBase to extract and store each document separately
- Each document in ZIP is now stored as individual file entry in knowledge base
- Process ZIP files in memory using io.BytesIO to avoid filesystem writes
- Generate unique file names for extracted documents to prevent conflicts

Co-Authored-By: Rock <rockchinq@gmail.com>

* perf: delete temp files

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Rock <rockchinq@gmail.com>

.gitignore

@@ -43,3 +43,4 @@ test.py
 /web_ui
 .venv/
 uv.lock
+/test

README.md

@@ -6,14 +6,16 @@
 
 <div align="center">
 
-简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)
+<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/langbot-app/LangBot/star/badge.svg)](https://gitcode.com/langbot-app/LangBot)
+[![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> ｜
@@ -25,12 +27,7 @@
 
 </p>
 
-## ✨ 特性
+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。
-
-- 💬 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。
 
 ## 📦 开始使用
 
@@ -64,23 +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/
+或访问 demo 环境：https://demo.langbot.dev/  
-    - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
+  - 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。
+  - 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
 
 ### 消息平台
 
@@ -97,10 +96,6 @@ docker compose up -d
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: 正在开发中
 
 ### 大模型能力
 
@@ -114,6 +109,7 @@ docker compose up -d
 | [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 |
+| [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 |
@@ -147,9 +143,3 @@ docker compose up -d
 <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)

README_EN.md

@@ -5,7 +5,7 @@
 
 <div align="center">
 
-[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
+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)
@@ -21,12 +21,7 @@
 
 </p>
 
-## ✨ Features
+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.
-
-- 💬 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.
 
 ## 📦 Getting Started
 
@@ -60,23 +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/
+Or visit the demo environment: https://demo.langbot.dev/
-    - Login information: Email: `demo@langbot.app` Password: `langbot123456`
+  - 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.
+  - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.
-
-## 🔌 Component Compatibility
 
 ### Message Platform
 
@@ -92,10 +89,6 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
-| LINE | 🚧 |  |
-| WhatsApp | 🚧 |  |
-
-🚧: In development
 
 ### LLMs
 
@@ -110,6 +103,7 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | [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 |
+| [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 |
@@ -128,9 +122,3 @@ Thank you for the following [code contributors](https://github.com/langbot-app/L
 <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)

README_JP.md

@@ -5,7 +5,7 @@
 
 <div align="center">
 
-[简体中文](README.md) / [English](README_EN.md) / 日本語 / (PR for your language)
+[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)
@@ -21,12 +21,7 @@
 
 </p>
 
-## ✨ 機能
+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。
-
-- 💬 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。
 
 ## 📦 始め方
 
@@ -42,7 +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。
 
@@ -60,23 +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/
+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`
+  - 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。
+  - 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。
-
-## 🔌 コンポーネントの互換性
 
 ### メッセージプラットフォーム
 
@@ -92,10 +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
 
@@ -109,6 +102,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [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 |
+| [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 |
@@ -128,9 +122,3 @@ LangBot への貢献に対して、以下の [コード貢献者](https://github
 <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)

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> 

components.yaml

@@ -9,7 +9,6 @@ spec:
   components:
     ComponentTemplate:
       fromFiles:
-        - pkg/platform/adapter.yaml
         - pkg/provider/modelmgr/requester.yaml
     MessagePlatformAdapter:
       fromDirs:

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
+      - 5300:5300  # For web ui
-      - 2280-2290:2280-2290  # 供消息平台适配器方向连接
+      - 2280-2290:2280-2290  # For platform webhook
-    # 根据具体环境配置网络
+    networks:
+      - langbot_network
+
+networks:
+  langbot_network:
+    driver: bridge

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()

libs/qq_official_api/api.py

@@ -3,7 +3,7 @@ from quart import request
 import httpx
 from quart import Quart
 from typing import Callable, Dict, Any
-from pkg.platform.types import events as platform_events
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
 from .qqofficialevent import QQOfficialEvent
 import json
 import traceback
@@ -104,7 +104,7 @@ class QQOfficialClient:
             return {'code': 0, 'message': 'success'}
 
         except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
             return {'error': str(e)}, 400
 
     async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -168,7 +168,6 @@ class QQOfficialClient:
         if not await self.check_access_token():
             await self.get_access_token()
 
-
         url = self.base_url + '/v2/users/' + user_openid + '/messages'
         async with httpx.AsyncClient() as client:
             headers = {
@@ -193,7 +192,6 @@ class QQOfficialClient:
         if not await self.check_access_token():
             await self.get_access_token()
 
-
         url = self.base_url + '/v2/groups/' + group_openid + '/messages'
         async with httpx.AsyncClient() as client:
             headers = {
@@ -209,7 +207,7 @@ class QQOfficialClient:
             if response.status_code == 200:
                 return
             else:
-                await self.logger.error(f"发送群聊消息失败:{response.json()}")
+                await self.logger.error(f'发送群聊消息失败:{response.json()}')
                 raise Exception(response.read().decode())
 
     async def send_channle_group_text_msg(self, channel_id: str, content: str, msg_id: str):
@@ -217,7 +215,6 @@ class QQOfficialClient:
         if not await self.check_access_token():
             await self.get_access_token()
 
-
         url = self.base_url + '/channels/' + channel_id + '/messages'
         async with httpx.AsyncClient() as client:
             headers = {
@@ -241,7 +238,6 @@ class QQOfficialClient:
         if not await self.check_access_token():
             await self.get_access_token()
 
-
         url = self.base_url + '/dms/' + guild_id + '/messages'
         async with httpx.AsyncClient() as client:
             headers = {

libs/slack_api/api.py

@@ -4,7 +4,7 @@ from quart import Quart, jsonify, request
 from slack_sdk.web.async_client import AsyncWebClient
 from .slackevent import SlackEvent
 from typing import Callable
-from pkg.platform.types import events as platform_events
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
 
 
 class SlackClient:
@@ -35,7 +35,6 @@ class SlackClient:
             if self.bot_user_id and bot_user_id == self.bot_user_id:
                 return jsonify({'status': 'ok'})
 
-
             # 处理私信
             if data and data.get('event', {}).get('channel_type') in ['im']:
                 event = SlackEvent.from_payload(data)
@@ -52,7 +51,7 @@ class SlackClient:
             return jsonify({'status': 'ok'})
 
         except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
             raise (e)
 
     async def _handle_message(self, event: SlackEvent):
@@ -82,7 +81,7 @@ class SlackClient:
                 self.bot_user_id = response['message']['bot_id']
             return
         except Exception as e:
-            await self.logger.error(f"Error in send_message: {e}")
+            await self.logger.error(f'Error in send_message: {e}')
             raise e
 
     async def send_message_to_one(self, text: str, user_id: str):
@@ -93,7 +92,7 @@ class SlackClient:
 
             return
         except Exception as e:
-            await self.logger.error(f"Error in send_message: {traceback.format_exc()}")
+            await self.logger.error(f'Error in send_message: {traceback.format_exc()}')
             raise e
 
     async def run_task(self, host: str, port: int, *args, **kwargs):

libs/wechatpad_api/__init__.py

@@ -1 +1 @@
-from .client import WeChatPadClient
+from .client import WeChatPadClient as WeChatPadClient

libs/wechatpad_api/api/chatroom.py

@@ -1,4 +1,4 @@
-from libs.wechatpad_api.util.http_util import async_request, post_json
+from libs.wechatpad_api.util.http_util import post_json
 
 
 class ChatRoomApi:
@@ -7,8 +7,6 @@ class ChatRoomApi:
         self.token = token
 
     def get_chatroom_member_detail(self, chatroom_name):
-        params = {
+        params = {'ChatRoomName': chatroom_name}
-            "ChatRoomName": chatroom_name
-        }
         url = self.base_url + '/group/GetChatroomMemberDetail'
         return post_json(url, token=self.token, data=params)

libs/wechatpad_api/api/downloadpai.py

@@ -1,32 +1,23 @@
-from libs.wechatpad_api.util.http_util import async_request, post_json
+from libs.wechatpad_api.util.http_util import post_json
 import httpx
 import base64
 
+
 class DownloadApi:
     def __init__(self, base_url, token):
         self.base_url = base_url
         self.token = token
 
     def send_download(self, aeskey, file_type, file_url):
-        json_data = {
+        json_data = {'AesKey': aeskey, 'FileType': file_type, 'FileURL': file_url}
-                  "AesKey": aeskey,
+        url = self.base_url + '/message/SendCdnDownload'
-                  "FileType": file_type,
-                  "FileURL": file_url
-                }
-        url = self.base_url + "/message/SendCdnDownload"
         return post_json(url, token=self.token, data=json_data)
 
-    def get_msg_voice(self,buf_id, length, new_msgid):
+    def get_msg_voice(self, buf_id, length, new_msgid):
-        json_data = {
+        json_data = {'Bufid': buf_id, 'Length': length, 'NewMsgId': new_msgid, 'ToUserName': ''}
-            "Bufid": buf_id,
+        url = self.base_url + '/message/GetMsgVoice'
-            "Length": length,
-            "NewMsgId": new_msgid,
-            "ToUserName": ""
-        }
-        url = self.base_url + "/message/GetMsgVoice"
         return post_json(url, token=self.token, data=json_data)
 
-
     async def download_url_to_base64(self, download_url):
         async with httpx.AsyncClient() as client:
             response = await client.get(download_url)

libs/wechatpad_api/api/friend.py

@@ -1,11 +1,6 @@
-from libs.wechatpad_api.util.http_util import post_json,async_request
-from typing import List, Dict, Any, Optional
-
-
 class FriendApi:
     """联系人API类，处理所有与联系人相关的操作"""
 
     def __init__(self, base_url: str, token: str):
         self.base_url = base_url
         self.token = token
-

libs/wechatpad_api/api/login.py

@@ -1,37 +1,34 @@
-from libs.wechatpad_api.util.http_util import async_request,post_json,get_json
+from libs.wechatpad_api.util.http_util import post_json, get_json
 
 
 class LoginApi:
     def __init__(self, base_url: str, token: str = None, admin_key: str = None):
-        '''
+        """
 
         Args:
             base_url: 原始路径
             token: token
             admin_key: 管理员key
-        '''
+        """
         self.base_url = base_url
         self.token = token
         # self.admin_key = admin_key
 
-    def get_token(self, admin_key, day: int=365):
+    def get_token(self, admin_key, day: int = 365):
         # 获取普通token
-        url = f"{self.base_url}/admin/GenAuthKey1"
+        url = f'{self.base_url}/admin/GenAuthKey1'
-        json_data = {
+        json_data = {'Count': 1, 'Days': day}
-                "Count": 1,
-                "Days": day
-            }
         return post_json(base_url=url, token=admin_key, data=json_data)
 
-    def get_login_qr(self, Proxy: str = ""):
+    def get_login_qr(self, Proxy: str = ''):
-        '''
+        """
 
         Args:
             Proxy:异地使用时代理
 
         Returns:json数据
 
-        '''
+        """
         """
         
         {
@@ -49,54 +46,37 @@ class LoginApi:
 }
         
         """
-        #获取登录二维码
+        # 获取登录二维码
-        url = f"{self.base_url}/login/GetLoginQrCodeNew"
+        url = f'{self.base_url}/login/GetLoginQrCodeNew'
         check = False
-        if Proxy != "":
+        if Proxy != '':
             check = True
-        json_data = {
+        json_data = {'Check': check, 'Proxy': Proxy}
-              "Check": check,
-              "Proxy": Proxy
-            }
         return post_json(base_url=url, token=self.token, data=json_data)
 
-
     def get_login_status(self):
         # 获取登录状态
         url = f'{self.base_url}/login/GetLoginStatus'
         return get_json(base_url=url, token=self.token)
 
-
-
     def logout(self):
         # 退出登录
         url = f'{self.base_url}/login/LogOut'
         return post_json(base_url=url, token=self.token)
 
-
+    def wake_up_login(self, Proxy: str = ''):
-
-
-    def wake_up_login(self, Proxy: str = ""):
         # 唤醒登录
         url = f'{self.base_url}/login/WakeUpLogin'
         check = False
-        if Proxy != "":
+        if Proxy != '':
             check = True
-        json_data = {
+        json_data = {'Check': check, 'Proxy': ''}
-            "Check": check,
-            "Proxy": ""
-        }
 
         return post_json(base_url=url, token=self.token, data=json_data)
 
-
+    def login(self, admin_key):
-
-    def login(self,admin_key):
         login_status = self.get_login_status()
-        if login_status["Code"] == 300 and login_status["Text"] == "你已退出微信":
+        if login_status['Code'] == 300 and login_status['Text'] == '你已退出微信':
-            print("token已经失效，重新获取")
+            print('token已经失效，重新获取')
             token_data = self.get_token(admin_key)
-            self.token = token_data["Data"][0]
+            self.token = token_data['Data'][0]
-
-
-

libs/wechatpad_api/api/message.py

@@ -1,5 +1,4 @@
-
+from libs.wechatpad_api.util.http_util import post_json
-from libs.wechatpad_api.util.http_util import async_request, post_json
 
 
 class MessageApi:
@@ -7,8 +6,8 @@ class MessageApi:
         self.base_url = base_url
         self.token = token
 
-    def post_text(self, to_wxid, content, ats: list= []):
+    def post_text(self, to_wxid, content, ats: list = []):
-        '''
+        """
 
         Args:
             app_id: 微信id
@@ -18,106 +17,64 @@ class MessageApi:
 
         Returns:
 
-        '''
+        """
-        url = self.base_url + "/message/SendTextMessage"
+        url = self.base_url + '/message/SendTextMessage'
         """发送文字消息"""
         json_data = {
-                      "MsgItem": [
+            'MsgItem': [
-                        {
+                {'AtWxIDList': ats, 'ImageContent': '', 'MsgType': 0, 'TextContent': content, 'ToUserName': to_wxid}
-                          "AtWxIDList": ats,
+            ]
-                          "ImageContent": "",
+        }
-                          "MsgType": 0,
+        return post_json(base_url=url, token=self.token, data=json_data)
-                          "TextContent": content,
-                          "ToUserName": to_wxid
-                        }
-                      ]
-                    }
-        return  post_json(base_url=url, token=self.token, data=json_data)
 
-
+    def post_image(self, to_wxid, img_url, ats: list = []):
-
-
-    def post_image(self, to_wxid, img_url, ats: list= []):
         """发送图片消息"""
         # 这里好像可以尝试发送多个暂时未测试
         json_data = {
-            "MsgItem": [
+            'MsgItem': [
-                {
+                {'AtWxIDList': ats, 'ImageContent': img_url, 'MsgType': 0, 'TextContent': '', 'ToUserName': to_wxid}
-                    "AtWxIDList": ats,
-                    "ImageContent": img_url,
-                    "MsgType": 0,
-                    "TextContent": '',
-                    "ToUserName": to_wxid
-                }
             ]
         }
-        url = self.base_url + "/message/SendImageMessage"
+        url = self.base_url + '/message/SendImageMessage'
         return post_json(base_url=url, token=self.token, data=json_data)
 
     def post_voice(self, to_wxid, voice_data, voice_forma, voice_duration):
         """发送语音消息"""
         json_data = {
-            "ToUserName": to_wxid,
+            'ToUserName': to_wxid,
-            "VoiceData": voice_data,
+            'VoiceData': voice_data,
-            "VoiceFormat": voice_forma,
+            'VoiceFormat': voice_forma,
-            "VoiceSecond": voice_duration
+            'VoiceSecond': voice_duration,
         }
-        url = self.base_url + "/message/SendVoice"
+        url = self.base_url + '/message/SendVoice'
         return post_json(base_url=url, token=self.token, data=json_data)
 
-
-
-
-
     def post_name_card(self, alias, to_wxid, nick_name, name_card_wxid, flag):
         """发送名片消息"""
         param = {
-                "CardAlias": alias,
+            'CardAlias': alias,
-                "CardFlag": flag,
+            'CardFlag': flag,
-                "CardNickName": nick_name,
+            'CardNickName': nick_name,
-                "CardWxId": name_card_wxid,
+            'CardWxId': name_card_wxid,
-                "ToUserName": to_wxid
+            'ToUserName': to_wxid,
         }
-        url = f"{self.base_url}/message/ShareCardMessage"
+        url = f'{self.base_url}/message/ShareCardMessage'
         return post_json(base_url=url, token=self.token, data=param)
 
-    def post_emoji(self, to_wxid, emoji_md5, emoji_size:int=0):
+    def post_emoji(self, to_wxid, emoji_md5, emoji_size: int = 0):
         """发送emoji消息"""
-        json_data = {
+        json_data = {'EmojiList': [{'EmojiMd5': emoji_md5, 'EmojiSize': emoji_size, 'ToUserName': to_wxid}]}
-            "EmojiList": [
+        url = f'{self.base_url}/message/SendEmojiMessage'
-                {
-                    "EmojiMd5": emoji_md5,
-                    "EmojiSize": emoji_size,
-                    "ToUserName": to_wxid
-                }
-            ]
-        }
-        url = f"{self.base_url}/message/SendEmojiMessage"
         return post_json(base_url=url, token=self.token, data=json_data)
 
-    def post_app_msg(self, to_wxid,xml_data, contenttype:int=0):
+    def post_app_msg(self, to_wxid, xml_data, contenttype: int = 0):
         """发送appmsg消息"""
-        json_data = {
+        json_data = {'AppList': [{'ContentType': contenttype, 'ContentXML': xml_data, 'ToUserName': to_wxid}]}
-            "AppList": [
+        url = f'{self.base_url}/message/SendAppMessage'
-                {
-                    "ContentType": contenttype,
-                    "ContentXML": xml_data,
-                    "ToUserName": to_wxid
-                }
-            ]
-        }
-        url = f"{self.base_url}/message/SendAppMessage"
         return post_json(base_url=url, token=self.token, data=json_data)
 
-
-
     def revoke_msg(self, to_wxid, msg_id, new_msg_id, create_time):
         """撤回消息"""
-        param = {
+        param = {'ClientMsgId': msg_id, 'CreateTime': create_time, 'NewMsgId': new_msg_id, 'ToUserName': to_wxid}
-              "ClientMsgId": msg_id,
+        url = f'{self.base_url}/message/RevokeMsg'
-              "CreateTime": create_time,
-              "NewMsgId": new_msg_id,
-              "ToUserName": to_wxid
-            }
-        url = f"{self.base_url}/message/RevokeMsg"
         return post_json(base_url=url, token=self.token, data=param)

libs/wechatpad_api/api/user.py

@@ -12,12 +12,9 @@ class UserApi:
 
         return get_json(base_url=url, token=self.token)
 
-    def get_qr_code(self, recover:bool=True, style:int=8):
+    def get_qr_code(self, recover: bool = True, style: int = 8):
         """获取自己的二维码"""
-        param = {
+        param = {'Recover': recover, 'Style': style}
-              "Recover": recover,
-              "Style": style
-            }
         url = f'{self.base_url}/user/GetMyQRCode'
         return post_json(base_url=url, token=self.token, data=param)
 
@@ -26,12 +23,8 @@ class UserApi:
         url = f'{self.base_url}/equipment/GetSafetyInfo'
         return post_json(base_url=url, token=self.token)
 
-
+    async def update_head_img(self, head_img_base64):
-
-    async def update_head_img(self,  head_img_base64):
         """修改头像"""
-        param = {
+        param = {'Base64': head_img_base64}
-              "Base64": head_img_base64
-            }
         url = f'{self.base_url}/user/UploadHeadImage'
         return await async_request(base_url=url, token_key=self.token, json=param)

libs/wechatpad_api/client.py

@@ -1,4 +1,3 @@
-
 from libs.wechatpad_api.api.login import LoginApi
 from libs.wechatpad_api.api.friend import FriendApi
 from libs.wechatpad_api.api.message import MessageApi
@@ -7,9 +6,6 @@ from libs.wechatpad_api.api.downloadpai import DownloadApi
 from libs.wechatpad_api.api.chatroom import ChatRoomApi
 
 
-
-
-
 class WeChatPadClient:
     def __init__(self, base_url, token, logger=None):
         self._login_api = LoginApi(base_url, token)
@@ -20,16 +16,16 @@ class WeChatPadClient:
         self._chatroom_api = ChatRoomApi(base_url, token)
         self.logger = logger
 
-    def get_token(self,admin_key, day: int):
+    def get_token(self, admin_key, day: int):
-        '''获取token'''
+        """获取token"""
         return self._login_api.get_token(admin_key, day)
 
-    def get_login_qr(self, Proxy:str=""):
+    def get_login_qr(self, Proxy: str = ''):
         """登录二维码"""
         return self._login_api.get_login_qr(Proxy=Proxy)
 
-    def awaken_login(self, Proxy:str=""):
+    def awaken_login(self, Proxy: str = ''):
-        '''唤醒登录'''
+        """唤醒登录"""
         return self._login_api.wake_up_login(Proxy=Proxy)
 
     def log_out(self):
@@ -40,59 +36,57 @@ class WeChatPadClient:
         """获取登录状态"""
         return self._login_api.get_login_status()
 
-    def send_text_message(self, to_wxid, message, ats: list=[]):
+    def send_text_message(self, to_wxid, message, ats: list = []):
         """发送文本消息"""
-        return  self._message_api.post_text(to_wxid, message, ats)
+        return self._message_api.post_text(to_wxid, message, ats)
 
-    def send_image_message(self, to_wxid, img_url, ats: list=[]):
+    def send_image_message(self, to_wxid, img_url, ats: list = []):
         """发送图片消息"""
-        return  self._message_api.post_image(to_wxid, img_url, ats)
+        return self._message_api.post_image(to_wxid, img_url, ats)
 
     def send_voice_message(self, to_wxid, voice_data, voice_forma, voice_duration):
         """发送音频消息"""
-        return  self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)
+        return self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)
 
     def send_app_message(self, to_wxid, app_message, type):
         """发送app消息"""
-        return  self._message_api.post_app_msg(to_wxid, app_message, type)
+        return self._message_api.post_app_msg(to_wxid, app_message, type)
 
     def send_emoji_message(self, to_wxid, emoji_md5, emoji_size):
         """发送emoji消息"""
-        return  self._message_api.post_emoji(to_wxid,emoji_md5,emoji_size)
+        return self._message_api.post_emoji(to_wxid, emoji_md5, emoji_size)
 
     def revoke_msg(self, to_wxid, msg_id, new_msg_id, create_time):
         """撤回消息"""
-        return  self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)
+        return self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)
 
     def get_profile(self):
         """获取用户信息"""
         return self._user_api.get_profile()
 
-    def get_qr_code(self, recover:bool=True, style:int=8):
+    def get_qr_code(self, recover: bool = True, style: int = 8):
         """获取用户二维码"""
-        return  self._user_api.get_qr_code(recover=recover, style=style)
+        return self._user_api.get_qr_code(recover=recover, style=style)
 
     def get_safety_info(self):
         """获取设备信息"""
-        return  self._user_api.get_safety_info()
+        return self._user_api.get_safety_info()
 
-    def update_head_img(self,  head_img_base64):
+    def update_head_img(self, head_img_base64):
         """上传用户头像"""
-        return  self._user_api.update_head_img(head_img_base64)
+        return self._user_api.update_head_img(head_img_base64)
 
     def cdn_download(self, aeskey, file_type, file_url):
         """cdn下载"""
-        return self._download_api.send_download( aeskey, file_type, file_url)
+        return self._download_api.send_download(aeskey, file_type, file_url)
 
-    def get_msg_voice(self,buf_id, length, msgid):
+    def get_msg_voice(self, buf_id, length, msgid):
         """下载语音"""
         return self._download_api.get_msg_voice(buf_id, length, msgid)
 
-    async def download_base64(self,url):
+    async def download_base64(self, url):
         return await self._download_api.download_url_to_base64(download_url=url)
 
     def get_chatroom_member_detail(self, chatroom_name):
         """查看群成员详情"""
         return self._chatroom_api.get_chatroom_member_detail(chatroom_name)
-
-

libs/wechatpad_api/util/http_util.py

@@ -1,10 +1,9 @@
 import requests
+import aiohttp
+
 
 def post_json(base_url, token, data=None):
-    headers = {
+    headers = {'Content-Type': 'application/json'}
-        'Content-Type': 'application/json'
-    }
-
 
     url = base_url + f'?key={token}'
 
@@ -18,14 +17,12 @@ def post_json(base_url, token, data=None):
         else:
             raise RuntimeError(response.text)
     except Exception as e:
-        print(f"http请求失败, url={url}, exception={e}")
+        print(f'http请求失败, url={url}, exception={e}')
         raise RuntimeError(str(e))
 
-def get_json(base_url, token):
-    headers = {
-        'Content-Type': 'application/json'
-    }
 
+def get_json(base_url, token):
+    headers = {'Content-Type': 'application/json'}
 
     url = base_url + f'?key={token}'
 
@@ -39,21 +36,18 @@ def get_json(base_url, token):
         else:
             raise RuntimeError(response.text)
     except Exception as e:
-        print(f"http请求失败, url={url}, exception={e}")
+        print(f'http请求失败, url={url}, exception={e}')
         raise RuntimeError(str(e))
 
-import aiohttp
-import asyncio
-
 
 async def async_request(
-        base_url: str,
+    base_url: str,
-        token_key: str,
+    token_key: str,
-        method: str = 'POST',
+    method: str = 'POST',
-        params: dict = None,
+    params: dict = None,
-        # headers: dict = None,
+    # headers: dict = None,
-        data: dict = None,
+    data: dict = None,
-        json: dict = None
+    json: dict = None,
 ):
     """
     通用异步请求函数
@@ -67,18 +61,11 @@ async def async_request(
     :param json: JSON数据
     :return: 响应文本
     """
-    headers = {
+    headers = {'Content-Type': 'application/json'}
-        'Content-Type': 'application/json'
+    url = f'{base_url}?key={token_key}'
-    }
-    url = f"{base_url}?key={token_key}"
     async with aiohttp.ClientSession() as session:
         async with session.request(
-                method=method,
+            method=method, url=url, params=params, headers=headers, data=data, json=json
-                url=url,
-                params=params,
-                headers=headers,
-                data=data,
-                json=json
         ) as response:
             response.raise_for_status()  # 如果状态码不是200，抛出异常
             result = await response.json()
@@ -89,4 +76,3 @@ async def async_request(
             #     return await result
             # else:
             #     raise RuntimeError("请求失败",response.text)
-

libs/wechatpad_api/util/terminal_printer.py

@@ -1,13 +1,17 @@
 import qrcode
 
+
 def print_green(text):
-    print(f"\033[32m{text}\033[0m")
+    print(f'\033[32m{text}\033[0m')
+
 
 def print_yellow(text):
-    print(f"\033[33m{text}\033[0m")
+    print(f'\033[33m{text}\033[0m')
+
 
 def print_red(text):
-    print(f"\033[31m{text}\033[0m")
+    print(f'\033[31m{text}\033[0m')
+
 
 def make_and_print_qr(url):
     """生成并打印二维码
@@ -22,10 +26,9 @@ def make_and_print_qr(url):
         1. 在终端打印二维码的ASCII图形
         2. 同时提供在线二维码生成链接作为备选
     """
-    print_green("请扫描下方二维码登录")
+    print_green('请扫描下方二维码登录')
     qr = qrcode.QRCode()
     qr.add_data(url)
     qr.make()
     qr.print_ascii(invert=True)
-    print_green(f"也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}")
+    print_green(f'也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}')
-

libs/wecom_api/api.py

@@ -8,7 +8,7 @@ from quart import Quart
 import xml.etree.ElementTree as ET
 from typing import Callable, Dict, Any
 from .wecomevent import WecomEvent
-from pkg.platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import aiofiles
 
 
@@ -57,7 +57,7 @@ class WecomClient:
             if 'access_token' in data:
                 return data['access_token']
             else:
-                await self.logger.error(f"获取accesstoken失败:{response.json()}")
+                await self.logger.error(f'获取accesstoken失败:{response.json()}')
                 raise Exception(f'未获取access token: {data}')
 
     async def get_users(self):
@@ -129,7 +129,7 @@ class WecomClient:
                 response = await client.post(url, json=params)
                 data = response.json()
             except Exception as e:
-                await self.logger.error(f"发送图片失败:{data}")
+                await self.logger.error(f'发送图片失败:{data}')
                 raise Exception('Failed to send image: ' + str(e))
 
             # 企业微信错误码40014和42001，代表accesstoken问题
@@ -164,7 +164,7 @@ class WecomClient:
                 self.access_token = await self.get_access_token(self.secret)
                 return await self.send_private_msg(user_id, agent_id, content)
             if data['errcode'] != 0:
-                await self.logger.error(f"发送消息失败:{data}")
+                await self.logger.error(f'发送消息失败:{data}')
                 raise Exception('Failed to send message: ' + str(data))
 
     async def handle_callback_request(self):
@@ -181,7 +181,7 @@ class WecomClient:
                 echostr = request.args.get('echostr')
                 ret, reply_echo_str = wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
                 if ret != 0:
-                    await self.logger.error("验证失败")
+                    await self.logger.error('验证失败')
                     raise Exception(f'验证失败，错误码: {ret}')
                 return reply_echo_str
 
@@ -189,10 +189,9 @@ class WecomClient:
                 encrypt_msg = await request.data
                 ret, xml_msg = wxcpt.DecryptMsg(encrypt_msg, msg_signature, timestamp, nonce)
                 if ret != 0:
-                    await self.logger.error("消息解密失败")
+                    await self.logger.error('消息解密失败')
                     raise Exception(f'消息解密失败，错误码: {ret}')
 
-
                 # 解析消息并处理
                 message_data = await self.get_message(xml_msg)
                 if message_data:
@@ -202,7 +201,7 @@ class WecomClient:
 
                 return 'success'
         except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
             return f'Error processing request: {str(e)}', 400
 
     async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -301,7 +300,7 @@ class WecomClient:
             except binascii.Error as e:
                 raise ValueError(f'Invalid base64 string: {str(e)}')
         else:
-            await self.logger.error("Image对象出错")
+            await self.logger.error('Image对象出错')
             raise ValueError('image对象出错')
 
         # 设置 multipart/form-data 格式的文件
@@ -325,7 +324,7 @@ class WecomClient:
                 self.access_token = await self.get_access_token(self.secret)
                 media_id = await self.upload_to_work(image)
             if data.get('errcode', 0) != 0:
-                await self.logger.error(f"上传图片失败:{data}")
+                await self.logger.error(f'上传图片失败:{data}')
                 raise Exception('failed to upload file')
 
             media_id = data.get('media_id')

libs/wecom_customer_service_api/api.py

@@ -8,7 +8,7 @@ from quart import Quart
 import xml.etree.ElementTree as ET
 from typing import Callable
 from .wecomcsevent import WecomCSEvent
-from pkg.platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import aiofiles
 
 
@@ -187,7 +187,7 @@ class WecomCSClient:
                 self.access_token = await self.get_access_token(self.secret)
                 return await self.send_text_msg(open_kfid, external_userid, msgid, content)
             if data['errcode'] != 0:
-                await self.logger.error(f"发送消息失败：{data}")
+                await self.logger.error(f'发送消息失败：{data}')
                 raise Exception('Failed to send message')
             return data
 
@@ -227,7 +227,7 @@ class WecomCSClient:
                 return 'success'
         except Exception as e:
             if self.logger:
-                await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+                await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
             else:
                 traceback.print_exc()
             return f'Error processing request: {str(e)}', 400

main.py

@@ -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
@@ -47,13 +53,13 @@ async def main_entry(loop: asyncio.AbstractEventLoop):
     if not args.skip_plugin_deps_check:
         await deps.precheck_plugin_deps()
 
-    # 检查pydantic版本，如果没有 pydantic.v1，则把 pydantic 映射为 v1
+    # # 检查pydantic版本，如果没有 pydantic.v1，则把 pydantic 映射为 v1
-    import pydantic.version
+    # import pydantic.version
 
-    if pydantic.version.VERSION < '2.0':
+    # if pydantic.version.VERSION < '2.0':
-        import pydantic
+    #     import pydantic
 
-        sys.modules['pydantic.v1'] = pydantic
+    #     sys.modules['pydantic.v1'] = pydantic
 
     # 检查配置文件
 

pkg/api/http/controller/group.py

@@ -14,8 +14,8 @@ preregistered_groups: list[type[RouterGroup]] = []
 """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]]:
-    """Register a RouterGroup"""
+    """注册一个 RouterGroup"""
 
     def decorator(cls: typing.Type[RouterGroup]) -> typing.Type[RouterGroup]:
         cls.name = name
@@ -86,10 +86,11 @@ class RouterGroup(abc.ABC):
 
                 try:
                     return await f(*args, **kwargs)
-                except Exception:  # auto 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('/', '__')
@@ -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]:
-        """Return a response with a specified status code"""
+        """返回一个指定状态码的响应"""
-        return self.fail(code, msg), status
+        return (self.fail(code, msg), status)

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,
+                }
+            )

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})

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
 

pkg/api/http/controller/groups/pipelines/webchat.py

@@ -1,3 +1,5 @@
+import json
+
 import quart
 
 from ... import group
@@ -9,10 +11,18 @@ class WebChatDebugRouterGroup(group.RouterGroup):
         @self.route('/send', methods=['POST'])
         async def send_message(pipeline_uuid: str) -> str:
             """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')
@@ -25,13 +35,33 @@ 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)
+                if is_stream:
-
+                    generator = webchat_adapter.send_webchat_message(
-                return self.success(
+                        pipeline_uuid, session_type, message_chain_obj, is_stream
-                    data={
+                    )
-                        'message': result,
+                    # 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)}')

pkg/api/http/controller/groups/plugins.py

@@ -1,10 +1,11 @@
 from __future__ import annotations
 
-
+import base64
 import quart
 
 from .....core import taskmgr
 from .. import group
+from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
 
 
 @group.group_class('plugins', '/api/v1/plugins')
@@ -12,35 +13,22 @@ class PluginsRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
         @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
-            plugins = self.ap.plugin_mgr.plugins()
+            plugins = await self.ap.plugin_connector.list_plugins()
 
-            plugins_data = [plugin.model_dump() for plugin in plugins]
+            return self.success(data={'plugins': plugins})
-
-            return self.success(data={'plugins': plugins_data})
 
         @self.route(
-            '/<author>/<plugin_name>/toggle',
+            '/<author>/<plugin_name>/upgrade',
-            methods=['PUT'],
-            auth_type=group.AuthType.USER_TOKEN,
-        )
-        async def _(author: str, plugin_name: str) -> str:
-            data = await quart.request.json
-            target_enabled = data.get('target_enabled')
-            await self.ap.plugin_mgr.update_plugin_switch(plugin_name, target_enabled)
-            return self.success()
-
-        @self.route(
-            '/<author>/<plugin_name>/update',
             methods=['POST'],
             auth_type=group.AuthType.USER_TOKEN,
         )
         async def _(author: str, plugin_name: str) -> str:
             ctx = taskmgr.TaskContext.new()
             wrapper = self.ap.task_mgr.create_user_task(
-                self.ap.plugin_mgr.update_plugin(plugin_name, task_context=ctx),
+                self.ap.plugin_connector.upgrade_plugin(author, plugin_name, task_context=ctx),
                 kind='plugin-operation',
-                name=f'plugin-update-{plugin_name}',
+                name=f'plugin-upgrade-{plugin_name}',
-                label=f'Updating plugin {plugin_name}',
+                label=f'Upgrading plugin {plugin_name}',
                 context=ctx,
             )
             return self.success(data={'task_id': wrapper.id})
@@ -52,14 +40,14 @@ class PluginsRouterGroup(group.RouterGroup):
         )
         async def _(author: str, plugin_name: str) -> str:
             if quart.request.method == 'GET':
-                plugin = self.ap.plugin_mgr.get_plugin(author, plugin_name)
+                plugin = await self.ap.plugin_connector.get_plugin_info(author, plugin_name)
                 if plugin is None:
                     return self.http_status(404, -1, 'plugin not found')
-                return self.success(data={'plugin': plugin.model_dump()})
+                return self.success(data={'plugin': plugin})
             elif quart.request.method == 'DELETE':
                 ctx = taskmgr.TaskContext.new()
                 wrapper = self.ap.task_mgr.create_user_task(
-                    self.ap.plugin_mgr.uninstall_plugin(plugin_name, task_context=ctx),
+                    self.ap.plugin_connector.delete_plugin(author, plugin_name, task_context=ctx),
                     kind='plugin-operation',
                     name=f'plugin-remove-{plugin_name}',
                     label=f'Removing plugin {plugin_name}',
@@ -74,24 +62,19 @@ class PluginsRouterGroup(group.RouterGroup):
             auth_type=group.AuthType.USER_TOKEN,
         )
         async def _(author: str, plugin_name: str) -> quart.Response:
-            plugin = self.ap.plugin_mgr.get_plugin(author, plugin_name)
+            plugin = await self.ap.plugin_connector.get_plugin_info(author, plugin_name)
             if plugin is None:
                 return self.http_status(404, -1, 'plugin not found')
+
             if quart.request.method == 'GET':
-                return self.success(data={'config': plugin.plugin_config})
+                return self.success(data={'config': plugin['plugin_config']})
             elif quart.request.method == 'PUT':
                 data = await quart.request.json
 
-                await self.ap.plugin_mgr.set_plugin_config(plugin, data)
+                await self.ap.plugin_connector.set_plugin_config(author, plugin_name, data)
 
                 return self.success(data={})
 
-        @self.route('/reorder', methods=['PUT'], auth_type=group.AuthType.USER_TOKEN)
-        async def _() -> str:
-            data = await quart.request.json
-            await self.ap.plugin_mgr.reorder_plugins(data.get('plugins'))
-            return self.success()
-
         @self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
             data = await quart.request.json
@@ -102,7 +85,47 @@ class PluginsRouterGroup(group.RouterGroup):
                 self.ap.plugin_mgr.install_plugin(data['source'], task_context=ctx),
                 kind='plugin-operation',
                 name='plugin-install-github',
-                label=f'Installing plugin ...{short_source_str}',
+                label=f'Installing plugin from github ...{short_source_str}',
+                context=ctx,
+            )
+
+            return self.success(data={'task_id': wrapper.id})
+
+        @self.route('/install/marketplace', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            data = await quart.request.json
+
+            ctx = taskmgr.TaskContext.new()
+            wrapper = self.ap.task_mgr.create_user_task(
+                self.ap.plugin_connector.install_plugin(PluginInstallSource.MARKETPLACE, data, task_context=ctx),
+                kind='plugin-operation',
+                name='plugin-install-marketplace',
+                label=f'Installing plugin from marketplace ...{data}',
+                context=ctx,
+            )
+
+            return self.success(data={'task_id': wrapper.id})
+
+        @self.route('/install/local', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            file = (await quart.request.files).get('file')
+            if file is None:
+                return self.http_status(400, -1, 'file is required')
+
+            file_bytes = file.read()
+
+            file_base64 = base64.b64encode(file_bytes).decode('utf-8')
+
+            data = {
+                'plugin_file': file_base64,
+            }
+
+            ctx = taskmgr.TaskContext.new()
+            wrapper = self.ap.task_mgr.create_user_task(
+                self.ap.plugin_connector.install_plugin(PluginInstallSource.LOCAL, data, task_context=ctx),
+                kind='plugin-operation',
+                name='plugin-install-local',
+                label=f'Installing plugin from local ...{file.filename}',
                 context=ctx,
             )
 

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()

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:

pkg/api/http/controller/groups/system.py

@@ -14,6 +14,11 @@ class SystemRouterGroup(group.RouterGroup):
                     'version': constants.semantic_version,
                     'debug': constants.debug_mode,
                     'enabled_platform_count': len(self.ap.platform_mgr.get_running_adapters()),
+                    'cloud_service_url': (
+                        self.ap.instance_config.data['plugin']['cloud_service_url']
+                        if 'cloud_service_url' in self.ap.instance_config.data['plugin']
+                        else 'https://space.langbot.app'
+                    ),
                 }
             )
 
@@ -35,16 +40,7 @@ class SystemRouterGroup(group.RouterGroup):
 
             return self.success(data=task.to_dict())
 
-        @self.route('/reload', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/debug/exec', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
-        async def _() -> str:
-            json_data = await quart.request.json
-
-            scope = json_data.get('scope')
-
-            await self.ap.reload(scope=scope)
-            return self.success()
-
-        @self.route('/_debug/exec', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
             if not constants.debug_mode:
                 return self.http_status(403, 403, 'Forbidden')
@@ -54,3 +50,39 @@ class SystemRouterGroup(group.RouterGroup):
             ap = self.ap
 
             return self.success(data=exec(py_code, {'ap': ap}))
+
+        @self.route('/debug/tools/call', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            if not constants.debug_mode:
+                return self.http_status(403, 403, 'Forbidden')
+
+            data = await quart.request.json
+
+            return self.success(
+                data=await self.ap.tool_mgr.execute_func_call(data['tool_name'], data['tool_parameters'])
+            )
+
+        @self.route(
+            '/debug/plugin/action',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN,
+        )
+        async def _() -> str:
+            if not constants.debug_mode:
+                return self.http_status(403, 403, 'Forbidden')
+
+            data = await quart.request.json
+
+            class AnoymousAction:
+                value = 'anonymous_action'
+
+                def __init__(self, value: str):
+                    self.value = value
+
+            resp = await self.ap.plugin_connector.handler.call_action(
+                AnoymousAction(data['action']),
+                data['data'],
+                timeout=data.get('timeout', 10),
+            )
+
+            return self.success(data=resp)

pkg/api/http/controller/groups/user.py

@@ -67,3 +67,19 @@ class UserRouterGroup(group.RouterGroup):
             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})

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:

pkg/api/http/service/bot.py

@@ -17,16 +17,20 @@ class BotService:
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
 
-    async def get_bots(self) -> list[dict]:
+    async def get_bots(self, include_secret: bool = True) -> list[dict]:
-        """Get all bots"""
+        """获取所有机器人"""
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_bot.Bot))
 
         bots = result.all()
 
-        return [self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot) for bot in bots]
+        masked_columns = []
+        if not include_secret:
+            masked_columns = ['adapter_config']
 
-    async def get_bot(self, bot_uuid: str) -> dict | None:
+        return [self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot, masked_columns) for bot in bots]
-        """Get bot"""
+
+    async def get_bot(self, bot_uuid: str, include_secret: bool = True) -> dict | None:
+        """获取机器人"""
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_uuid)
         )
@@ -36,7 +40,27 @@ class BotService:
         if bot is None:
             return None
 
-        return self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot)
+        masked_columns = []
+        if not include_secret:
+            masked_columns = ['adapter_config']
+
+        return self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot, masked_columns)
+
+    async def get_runtime_bot_info(self, bot_uuid: str, include_secret: bool = True) -> dict:
+        """获取机器人运行时信息"""
+        persistence_bot = await self.get_bot(bot_uuid, include_secret)
+        if persistence_bot is None:
+            raise Exception('Bot not found')
+
+        adapter_runtime_values = {}
+
+        runtime_bot = await self.ap.platform_mgr.get_bot_by_uuid(bot_uuid)
+        if runtime_bot is not None:
+            adapter_runtime_values['bot_account_id'] = runtime_bot.adapter.bot_account_id
+
+        persistence_bot['adapter_runtime_values'] = adapter_runtime_values
+
+        return persistence_bot
 
     async def create_bot(self, bot_data: dict) -> str:
         """Create bot"""

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)
+            )

pkg/api/http/service/model.py

@@ -7,20 +7,28 @@ from ....core import app
 from ....entity.persistence import model as persistence_model
 from ....entity.persistence import pipeline as persistence_pipeline
 from ....provider.modelmgr import requester as model_requester
-from ....provider import entities as llm_entities
+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:
         self.ap = ap
 
-    async def get_llm_models(self) -> list[dict]:
+    async def get_llm_models(self, include_secret: bool = True) -> list[dict]:
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
 
         models = result.all()
-        return [self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model) for model in models]
+
+        masked_columns = []
+        if not include_secret:
+            masked_columns = ['api_keys']
+
+        return [
+            self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model, masked_columns)
+            for model in models
+        ]
 
     async def create_llm_model(self, model_data: dict) -> str:
         model_data['uuid'] = str(uuid.uuid4())
@@ -99,7 +107,93 @@ class ModelsService:
         await runtime_llm_model.requester.invoke_llm(
             query=None,
             model=runtime_llm_model,
-            messages=[llm_entities.Message(role='user', content='Hello, world!')],
+            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={},
         )

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

pkg/api/http/service/user.py

@@ -82,3 +82,18 @@ class UserService:
         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)
+        )

pkg/command/cmdmgr.py

@@ -2,9 +2,12 @@ from __future__ import annotations
 
 import typing
 
-from ..core import app, entities as core_entities
+from ..core import app
-from . import entities, operator, errors
+from . import operator
 from ..utils import importutil
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 # 引入所有算子以便注册
 from . import operators
@@ -13,13 +16,11 @@ importutil.import_modules_in_pkg(operators)
 
 
 class CommandManager:
-    """命令管理器"""
-
     ap: app.Application
 
     cmd_list: list[operator.CommandOperator]
     """
-    运行时命令列表，扁平存储，各个对象包含对应的子节点引用
+    Runtime command list, flat storage, each object contains a reference to the corresponding child node
     """
 
     def __init__(self, ap: app.Application):
@@ -55,43 +56,28 @@ class CommandManager:
 
     async def _execute(
         self,
-        context: entities.ExecuteContext,
+        context: command_context.ExecuteContext,
         operator_list: list[operator.CommandOperator],
         operator: operator.CommandOperator = None,
-    ) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行命令"""
 
-        found = False
+        command_list = await self.ap.plugin_connector.list_commands()
-        if len(context.crt_params) > 0:  # 查找下一个参数是否对应此节点的某个子节点名
-            for oper in operator_list:
-                if (context.crt_params[0] == oper.name or context.crt_params[0] in oper.alias) and (
-                    oper.parent_class is None or oper.parent_class == operator.__class__
-                ):
-                    found = True
 
-                    context.crt_command = context.crt_params[0]
+        for command in command_list:
-                    context.crt_params = context.crt_params[1:]
+            if command.metadata.name == context.command:
-
+                async for ret in self.ap.plugin_connector.execute_command(context):
-                    async for ret in self._execute(context, oper.children, oper):
+                    yield ret
-                        yield ret
+                break
-                    break
+        else:
-
+            yield command_context.CommandReturn(error=command_errors.CommandNotFoundError(context.command))
-        if not found:  # 如果下一个参数未在此节点的子节点中找到，则执行此节点或者报错
-            if operator is None:
-                yield entities.CommandReturn(error=errors.CommandNotFoundError(context.crt_params[0]))
-            else:
-                if operator.lowest_privilege > context.privilege:
-                    yield entities.CommandReturn(error=errors.CommandPrivilegeError(operator.name))
-                else:
-                    async for ret in operator.execute(context):
-                        yield ret
 
     async def execute(
         self,
         command_text: str,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
-        session: core_entities.Session,
+        session: provider_session.Session,
-    ) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行命令"""
 
         privilege = 1
@@ -99,8 +85,8 @@ class CommandManager:
         if f'{query.launcher_type.value}_{query.launcher_id}' in self.ap.instance_config.data['admins']:
             privilege = 2
 
-        ctx = entities.ExecuteContext(
+        ctx = command_context.ExecuteContext(
-            query=query,
+            query_id=query.query_id,
             session=session,
             command_text=command_text,
             command='',
@@ -110,5 +96,9 @@ class CommandManager:
             privilege=privilege,
         )
 
+        ctx.command = ctx.params[0]
+
+        ctx.shift()
+
         async for ret in self._execute(ctx, self.cmd_list):
             yield ret

pkg/command/entities.py

@@ -1,74 +0,0 @@
-from __future__ import annotations
-
-import typing
-
-import pydantic.v1 as pydantic
-
-from ..core import entities as core_entities
-from . import errors
-from ..platform.types import message as platform_message
-
-
-class CommandReturn(pydantic.BaseModel):
-    """命令返回值"""
-
-    text: typing.Optional[str] = None
-    """文本
-    """
-
-    image: typing.Optional[platform_message.Image] = None
-    """弃用"""
-
-    image_url: typing.Optional[str] = None
-    """图片链接
-    """
-
-    error: typing.Optional[errors.CommandError] = None
-    """错误
-    """
-
-    class Config:
-        arbitrary_types_allowed = True
-
-
-class ExecuteContext(pydantic.BaseModel):
-    """单次命令执行上下文"""
-
-    query: core_entities.Query
-    """本次消息的请求对象"""
-
-    session: core_entities.Session
-    """本次消息所属的会话对象"""
-
-    command_text: str
-    """命令完整文本"""
-
-    command: str
-    """命令名称"""
-
-    crt_command: str
-    """当前命令
-    
-    多级命令中crt_command为当前命令，command为根命令。
-    例如：!plugin on Webwlkr
-    处理到plugin时，command为plugin，crt_command为plugin
-    处理到on时，command为plugin，crt_command为on
-    """
-
-    params: list[str]
-    """命令参数
-    
-    整个命令以空格分割后的参数列表
-    """
-
-    crt_params: list[str]
-    """当前命令参数
-
-    多级命令中crt_params为当前命令参数，params为根命令参数。
-    例如：!plugin on Webwlkr
-    处理到plugin时，params为['on', 'Webwlkr']，crt_params为['on', 'Webwlkr']
-    处理到on时，params为['on', 'Webwlkr']，crt_params为['Webwlkr']
-    """
-
-    privilege: int
-    """发起人权限"""

pkg/command/errors.py

@@ -1,26 +0,0 @@
-class CommandError(Exception):
-    def __init__(self, message: str = None):
-        self.message = message
-
-    def __str__(self):
-        return self.message
-
-
-class CommandNotFoundError(CommandError):
-    def __init__(self, message: str = None):
-        super().__init__('未知命令: ' + message)
-
-
-class CommandPrivilegeError(CommandError):
-    def __init__(self, message: str = None):
-        super().__init__('权限不足: ' + message)
-
-
-class ParamNotEnoughError(CommandError):
-    def __init__(self, message: str = None):
-        super().__init__('参数不足: ' + message)
-
-
-class CommandOperationError(CommandError):
-    def __init__(self, message: str = None):
-        super().__init__('操作失败: ' + message)

pkg/command/operator.py

@@ -4,7 +4,7 @@ import typing
 import abc
 
 from ..core import app
-from . import entities
+from langbot_plugin.api.entities.builtin.command import context as command_context
 
 
 preregistered_operators: list[typing.Type[CommandOperator]] = []
@@ -95,16 +95,18 @@ class CommandOperator(metaclass=abc.ABCMeta):
         pass
 
     @abc.abstractmethod
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """实现此方法以执行命令
 
         支持多次yield以返回多个结果。
         例如：一个安装插件的命令，可能会有下载、解压、安装等多个步骤，每个步骤都可以返回一个结果。
 
         Args:
-            context (entities.ExecuteContext): 命令执行上下文
+            context (command_context.ExecuteContext): 命令执行上下文
 
         Yields:
-            entities.CommandReturn: 命令返回封装
+            command_context.CommandReturn: 命令返回封装
         """
         pass

pkg/command/operators/cmd.py

@@ -2,14 +2,17 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='cmd', help='显示命令列表', usage='!cmd\n!cmd <命令名称>')
 class CmdOperator(operator.CommandOperator):
     """命令列表"""
 
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行"""
         if len(context.crt_params) == 0:
             reply_str = '当前所有命令: \n\n'
@@ -20,7 +23,7 @@ class CmdOperator(operator.CommandOperator):
 
             reply_str += '\n使用 !cmd <命令名称> 查看命令的详细帮助'
 
-            yield entities.CommandReturn(text=reply_str.strip())
+            yield command_context.CommandReturn(text=reply_str.strip())
 
         else:
             cmd_name = context.crt_params[0]
@@ -33,9 +36,9 @@ class CmdOperator(operator.CommandOperator):
                     break
 
             if cmd is None:
-                yield entities.CommandReturn(error=errors.CommandNotFoundError(cmd_name))
+                yield command_context.CommandReturn(error=command_errors.CommandNotFoundError(cmd_name))
             else:
                 reply_str = f'{cmd.name}: {cmd.help}\n\n'
                 reply_str += f'使用方法: \n{cmd.usage}'
 
-                yield entities.CommandReturn(text=reply_str.strip())
+                yield command_context.CommandReturn(text=reply_str.strip())

pkg/command/operators/delc.py

@@ -2,23 +2,26 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='del', help='删除当前会话的历史记录', usage='!del <序号>\n!del all')
 class DelOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if context.session.conversations:
             delete_index = 0
             if len(context.crt_params) > 0:
                 try:
                     delete_index = int(context.crt_params[0])
                 except Exception:
-                    yield entities.CommandReturn(error=errors.CommandOperationError('索引必须是整数'))
+                    yield command_context.CommandReturn(error=command_errors.CommandOperationError('索引必须是整数'))
                     return
 
             if delete_index < 0 or delete_index >= len(context.session.conversations):
-                yield entities.CommandReturn(error=errors.CommandOperationError('索引超出范围'))
+                yield command_context.CommandReturn(error=command_errors.CommandOperationError('索引超出范围'))
                 return
 
             # 倒序
@@ -29,15 +32,17 @@ class DelOperator(operator.CommandOperator):
 
             del context.session.conversations[to_delete_index]
 
-            yield entities.CommandReturn(text=f'已删除对话: {delete_index}')
+            yield command_context.CommandReturn(text=f'已删除对话: {delete_index}')
         else:
-            yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
+            yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))
 
 
 @operator.operator_class(name='all', help='删除此会话的所有历史记录', parent_class=DelOperator)
 class DelAllOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         context.session.conversations = []
         context.session.using_conversation = None
 
-        yield entities.CommandReturn(text='已删除所有对话')
+        yield command_context.CommandReturn(text='已删除所有对话')

pkg/command/operators/func.py

@@ -1,19 +1,20 @@
 from __future__ import annotations
 from typing import AsyncGenerator
 
-from .. import operator, entities
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context
 
 
 @operator.operator_class(name='func', help='查看所有已注册的内容函数', usage='!func')
 class FuncOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> AsyncGenerator[command_context.CommandReturn, None]:
         reply_str = '当前已启用的内容函数: \n\n'
 
         index = 1
 
-        all_functions = await self.ap.tool_mgr.get_all_functions(
+        all_functions = await self.ap.tool_mgr.get_all_tools()
-            plugin_enabled=True,
-        )
 
         for func in all_functions:
             reply_str += '{}. {}:\n{}\n\n'.format(
@@ -23,4 +24,4 @@ class FuncOperator(operator.CommandOperator):
             )
             index += 1
 
-        yield entities.CommandReturn(text=reply_str)
+        yield command_context.CommandReturn(text=reply_str)

pkg/command/operators/help.py

@@ -2,14 +2,17 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context
 
 
 @operator.operator_class(name='help', help='显示帮助', usage='!help\n!help <命令名称>')
 class HelpOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         help = 'LangBot - 大语言模型原生即时通信机器人平台\n链接：https://langbot.app'
 
         help += '\n发送命令 !cmd 可查看命令列表'
 
-        yield entities.CommandReturn(text=help)
+        yield command_context.CommandReturn(text=help)

pkg/command/operators/last.py

@@ -3,26 +3,31 @@ from __future__ import annotations
 import typing
 
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='last', help='切换到前一个对话', usage='!last')
 class LastOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if context.session.conversations:
             # 找到当前会话的上一个会话
             for index in range(len(context.session.conversations) - 1, -1, -1):
                 if context.session.conversations[index] == context.session.using_conversation:
                     if index == 0:
-                        yield entities.CommandReturn(error=errors.CommandOperationError('已经是第一个对话了'))
+                        yield command_context.CommandReturn(
+                            error=command_errors.CommandOperationError('已经是第一个对话了')
+                        )
                         return
                     else:
                         context.session.using_conversation = context.session.conversations[index - 1]
                         time_str = context.session.using_conversation.create_time.strftime('%Y-%m-%d %H:%M:%S')
 
-                        yield entities.CommandReturn(
+                        yield command_context.CommandReturn(
                             text=f'已切换到上一个对话: {index} {time_str}: {context.session.using_conversation.messages[0].readable_str()}'
                         )
                         return
         else:
-            yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
+            yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))

pkg/command/operators/list.py

@@ -2,19 +2,22 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='list', help='列出此会话中的所有历史对话', usage='!list\n!list <页码>')
 class ListOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         page = 0
 
         if len(context.crt_params) > 0:
             try:
                 page = int(context.crt_params[0] - 1)
             except Exception:
-                yield entities.CommandReturn(error=errors.CommandOperationError('页码应为整数'))
+                yield command_context.CommandReturn(error=command_errors.CommandOperationError('页码应为整数'))
                 return
 
         record_per_page = 10
@@ -45,4 +48,4 @@ class ListOperator(operator.CommandOperator):
             else:
                 content += f'\n当前会话: {using_conv_index} {context.session.using_conversation.create_time.strftime("%Y-%m-%d %H:%M:%S")}: {context.session.using_conversation.messages[0].readable_str() if len(context.session.using_conversation.messages) > 0 else "无内容"}'
 
-        yield entities.CommandReturn(text=f'第 {page + 1} 页 (时间倒序):\n{content}')
+        yield command_context.CommandReturn(text=f'第 {page + 1} 页 (时间倒序):\n{content}')

pkg/command/operators/next.py

@@ -2,26 +2,31 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='next', help='切换到后一个对话', usage='!next')
 class NextOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if context.session.conversations:
             # 找到当前会话的下一个会话
             for index in range(len(context.session.conversations)):
                 if context.session.conversations[index] == context.session.using_conversation:
                     if index == len(context.session.conversations) - 1:
-                        yield entities.CommandReturn(error=errors.CommandOperationError('已经是最后一个对话了'))
+                        yield command_context.CommandReturn(
+                            error=command_errors.CommandOperationError('已经是最后一个对话了')
+                        )
                         return
                     else:
                         context.session.using_conversation = context.session.conversations[index + 1]
                         time_str = context.session.using_conversation.create_time.strftime('%Y-%m-%d %H:%M:%S')
 
-                        yield entities.CommandReturn(
+                        yield command_context.CommandReturn(
                             text=f'已切换到后一个对话: {index} {time_str}: {context.session.using_conversation.messages[0].content}'
                         )
                         return
         else:
-            yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
+            yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))

pkg/command/operators/plugin.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 import typing
 import traceback
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(
@@ -11,7 +12,9 @@ from .. import operator, entities, errors
     usage='!plugin\n!plugin get <插件仓库地址>\n!plugin update\n!plugin del <插件名>\n!plugin on <插件名>\n!plugin off <插件名>',
 )
 class PluginOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         plugin_list = self.ap.plugin_mgr.plugins()
         reply_str = '所有插件({}):\n'.format(len(plugin_list))
         idx = 0
@@ -27,32 +30,36 @@ class PluginOperator(operator.CommandOperator):
 
             idx += 1
 
-        yield entities.CommandReturn(text=reply_str)
+        yield command_context.CommandReturn(text=reply_str)
 
 
 @operator.operator_class(name='get', help='安装插件', privilege=2, parent_class=PluginOperator)
 class PluginGetOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if len(context.crt_params) == 0:
-            yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件仓库地址'))
+            yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件仓库地址'))
         else:
             repo = context.crt_params[0]
 
-            yield entities.CommandReturn(text='正在安装插件...')
+            yield command_context.CommandReturn(text='正在安装插件...')
 
             try:
                 await self.ap.plugin_mgr.install_plugin(repo)
-                yield entities.CommandReturn(text='插件安装成功，请重启程序以加载插件')
+                yield command_context.CommandReturn(text='插件安装成功，请重启程序以加载插件')
             except Exception as e:
                 traceback.print_exc()
-                yield entities.CommandReturn(error=errors.CommandError('插件安装失败: ' + str(e)))
+                yield command_context.CommandReturn(error=command_errors.CommandError('插件安装失败: ' + str(e)))
 
 
 @operator.operator_class(name='update', help='更新插件', privilege=2, parent_class=PluginOperator)
 class PluginUpdateOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if len(context.crt_params) == 0:
-            yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
+            yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
         else:
             plugin_name = context.crt_params[0]
 
@@ -60,24 +67,26 @@ class PluginUpdateOperator(operator.CommandOperator):
                 plugin_container = self.ap.plugin_mgr.get_plugin_by_name(plugin_name)
 
                 if plugin_container is not None:
-                    yield entities.CommandReturn(text='正在更新插件...')
+                    yield command_context.CommandReturn(text='正在更新插件...')
                     await self.ap.plugin_mgr.update_plugin(plugin_name)
-                    yield entities.CommandReturn(text='插件更新成功，请重启程序以加载插件')
+                    yield command_context.CommandReturn(text='插件更新成功，请重启程序以加载插件')
                 else:
-                    yield entities.CommandReturn(error=errors.CommandError('插件更新失败: 未找到插件'))
+                    yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: 未找到插件'))
             except Exception as e:
                 traceback.print_exc()
-                yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
+                yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
 
 
 @operator.operator_class(name='all', help='更新所有插件', privilege=2, parent_class=PluginUpdateOperator)
 class PluginUpdateAllOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         try:
             plugins = [p.plugin_name for p in self.ap.plugin_mgr.plugins()]
 
             if plugins:
-                yield entities.CommandReturn(text='正在更新插件...')
+                yield command_context.CommandReturn(text='正在更新插件...')
                 updated = []
                 try:
                     for plugin_name in plugins:
@@ -85,20 +94,22 @@ class PluginUpdateAllOperator(operator.CommandOperator):
                         updated.append(plugin_name)
                 except Exception as e:
                     traceback.print_exc()
-                    yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
+                    yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
-                yield entities.CommandReturn(text='已更新插件: {}'.format(', '.join(updated)))
+                yield command_context.CommandReturn(text='已更新插件: {}'.format(', '.join(updated)))
             else:
-                yield entities.CommandReturn(text='没有可更新的插件')
+                yield command_context.CommandReturn(text='没有可更新的插件')
         except Exception as e:
             traceback.print_exc()
-            yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
+            yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
 
 
 @operator.operator_class(name='del', help='删除插件', privilege=2, parent_class=PluginOperator)
 class PluginDelOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if len(context.crt_params) == 0:
-            yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
+            yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
         else:
             plugin_name = context.crt_params[0]
 
@@ -106,51 +117,55 @@ class PluginDelOperator(operator.CommandOperator):
                 plugin_container = self.ap.plugin_mgr.get_plugin_by_name(plugin_name)
 
                 if plugin_container is not None:
-                    yield entities.CommandReturn(text='正在删除插件...')
+                    yield command_context.CommandReturn(text='正在删除插件...')
                     await self.ap.plugin_mgr.uninstall_plugin(plugin_name)
-                    yield entities.CommandReturn(text='插件删除成功，请重启程序以加载插件')
+                    yield command_context.CommandReturn(text='插件删除成功，请重启程序以加载插件')
                 else:
-                    yield entities.CommandReturn(error=errors.CommandError('插件删除失败: 未找到插件'))
+                    yield command_context.CommandReturn(error=command_errors.CommandError('插件删除失败: 未找到插件'))
             except Exception as e:
                 traceback.print_exc()
-                yield entities.CommandReturn(error=errors.CommandError('插件删除失败: ' + str(e)))
+                yield command_context.CommandReturn(error=command_errors.CommandError('插件删除失败: ' + str(e)))
 
 
 @operator.operator_class(name='on', help='启用插件', privilege=2, parent_class=PluginOperator)
 class PluginEnableOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if len(context.crt_params) == 0:
-            yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
+            yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
         else:
             plugin_name = context.crt_params[0]
 
             try:
                 if await self.ap.plugin_mgr.update_plugin_switch(plugin_name, True):
-                    yield entities.CommandReturn(text='已启用插件: {}'.format(plugin_name))
+                    yield command_context.CommandReturn(text='已启用插件: {}'.format(plugin_name))
                 else:
-                    yield entities.CommandReturn(
+                    yield command_context.CommandReturn(
-                        error=errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
+                        error=command_errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
                     )
             except Exception as e:
                 traceback.print_exc()
-                yield entities.CommandReturn(error=errors.CommandError('插件状态修改失败: ' + str(e)))
+                yield command_context.CommandReturn(error=command_errors.CommandError('插件状态修改失败: ' + str(e)))
 
 
 @operator.operator_class(name='off', help='禁用插件', privilege=2, parent_class=PluginOperator)
 class PluginDisableOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         if len(context.crt_params) == 0:
-            yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
+            yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
         else:
             plugin_name = context.crt_params[0]
 
             try:
                 if await self.ap.plugin_mgr.update_plugin_switch(plugin_name, False):
-                    yield entities.CommandReturn(text='已禁用插件: {}'.format(plugin_name))
+                    yield command_context.CommandReturn(text='已禁用插件: {}'.format(plugin_name))
                 else:
-                    yield entities.CommandReturn(
+                    yield command_context.CommandReturn(
-                        error=errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
+                        error=command_errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
                     )
             except Exception as e:
                 traceback.print_exc()
-                yield entities.CommandReturn(error=errors.CommandError('插件状态修改失败: ' + str(e)))
+                yield command_context.CommandReturn(error=command_errors.CommandError('插件状态修改失败: ' + str(e)))

pkg/command/operators/prompt.py

@@ -2,19 +2,22 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='prompt', help='查看当前对话的前文', usage='!prompt')
 class PromptOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行"""
         if context.session.using_conversation is None:
-            yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
+            yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))
         else:
             reply_str = '当前对话所有内容:\n\n'
 
             for msg in context.session.using_conversation.messages:
                 reply_str += f'{msg.role}: {msg.content}\n'
 
-            yield entities.CommandReturn(text=reply_str)
+            yield command_context.CommandReturn(text=reply_str)

pkg/command/operators/resend.py

@@ -2,15 +2,18 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities, errors
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
 
 
 @operator.operator_class(name='resend', help='重发当前会话的最后一条消息', usage='!resend')
 class ResendOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         # 回滚到最后一条用户message前
         if context.session.using_conversation is None:
-            yield entities.CommandReturn(error=errors.CommandError('当前没有对话'))
+            yield command_context.CommandReturn(error=command_errors.CommandError('当前没有对话'))
         else:
             conv_msg = context.session.using_conversation.messages
 
@@ -23,4 +26,4 @@ class ResendOperator(operator.CommandOperator):
                 conv_msg.pop()
 
             # 不重发了，提示用户已删除就行了
-            yield entities.CommandReturn(text='已删除最后一次请求记录')
+            yield command_context.CommandReturn(text='已删除最后一次请求记录')

pkg/command/operators/reset.py

@@ -2,13 +2,16 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context
 
 
 @operator.operator_class(name='reset', help='重置当前会话', usage='!reset')
 class ResetOperator(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         """执行"""
         context.session.using_conversation = None
 
-        yield entities.CommandReturn(text='已重置当前会话')
+        yield command_context.CommandReturn(text='已重置当前会话')

pkg/command/operators/update.py

@@ -1,11 +0,0 @@
-from __future__ import annotations
-
-import typing
-
-from .. import operator, entities
-
-
-@operator.operator_class(name='update', help='更新程序', usage='!update', privilege=2)
-class UpdateCommand(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
-        yield entities.CommandReturn(text='不再支持通过命令更新，请查看 LangBot 文档。')

pkg/command/operators/version.py

@@ -2,12 +2,15 @@ from __future__ import annotations
 
 import typing
 
-from .. import operator, entities
+from .. import operator
+from langbot_plugin.api.entities.builtin.command import context as command_context
 
 
 @operator.operator_class(name='version', help='显示版本信息', usage='!version')
 class VersionCommand(operator.CommandOperator):
-    async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
+    async def execute(
+        self, context: command_context.ExecuteContext
+    ) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
         reply_str = f'当前版本: \n{self.ap.ver_mgr.get_current_version()}'
 
         try:
@@ -16,4 +19,4 @@ class VersionCommand(operator.CommandOperator):
         except Exception:
             pass
 
-        yield entities.CommandReturn(text=reply_str.strip())
+        yield command_context.CommandReturn(text=reply_str.strip())

pkg/core/app.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import logging
 import asyncio
 import traceback
-import sys
 import os
 
 from ..platform import botmgr as im_mgr
@@ -12,7 +11,7 @@ from ..provider.modelmgr import modelmgr as llm_model_mgr
 from ..provider.tools import toolmgr as llm_tool_mgr
 from ..config import manager as config_mgr
 from ..command import cmdmgr
-from ..plugin import manager as plugin_mgr
+from ..plugin import connector as plugin_connector
 from ..pipeline import pool
 from ..pipeline import controller, pipelinemgr
 from ..utils import version as version_mgr, proxy as proxy_mgr, announce as announce_mgr
@@ -22,11 +21,14 @@ 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:
@@ -47,6 +49,8 @@ class Application:
 
     model_mgr: llm_model_mgr.ModelManager = None
 
+    rag_mgr: rag_mgr.RAGManager = None
+
     # TODO move to pipeline
     tool_mgr: llm_tool_mgr.ToolManager = None
 
@@ -75,7 +79,7 @@ class Application:
 
     # =========================
 
-    plugin_mgr: plugin_mgr.PluginManager = None
+    plugin_connector: plugin_connector.PluginRuntimeConnector = None
 
     query_pool: pool.QueryPool = None
 
@@ -93,6 +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
@@ -103,12 +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
 
@@ -117,7 +127,7 @@ class Application:
 
     async def run(self):
         try:
-            await self.plugin_mgr.initialize_plugins()
+            await self.plugin_connector.initialize_plugins()
 
             # 后续可能会允许动态重启其他任务
             # 故为了防止程序在非 Ctrl-C 情况下退出，这里创建一个不会结束的协程
@@ -143,6 +153,7 @@ class Application:
                 name='http-api-controller',
                 scopes=[core_entities.LifecycleControlScope.APPLICATION],
             )
+
             self.task_mgr.create_task(
                 never_ending(),
                 name='never-ending-task',
@@ -157,6 +168,9 @@ class Application:
             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):
         """Print access webui tips"""
 
@@ -183,59 +197,3 @@ class Application:
 """.strip()
         for line in tips.split('\n'):
             self.logger.info(line)
-
-    async def reload(
-        self,
-        scope: core_entities.LifecycleControlScope,
-    ):
-        match scope:
-            case core_entities.LifecycleControlScope.PLATFORM.value:
-                self.logger.info('Hot reload scope=' + scope)
-                await self.platform_mgr.shutdown()
-
-                self.platform_mgr = im_mgr.PlatformManager(self)
-
-                await self.platform_mgr.initialize()
-
-                self.task_mgr.create_task(
-                    self.platform_mgr.run(),
-                    name='platform-manager',
-                    scopes=[
-                        core_entities.LifecycleControlScope.APPLICATION,
-                        core_entities.LifecycleControlScope.PLATFORM,
-                    ],
-                )
-            case core_entities.LifecycleControlScope.PLUGIN.value:
-                self.logger.info('Hot reload scope=' + scope)
-                await self.plugin_mgr.destroy_plugins()
-
-                # 删除 sys.module 中所有的 plugins/* 下的模块
-                for mod in list(sys.modules.keys()):
-                    if mod.startswith('plugins.'):
-                        del sys.modules[mod]
-
-                self.plugin_mgr = plugin_mgr.PluginManager(self)
-                await self.plugin_mgr.initialize()
-
-                await self.plugin_mgr.initialize_plugins()
-
-                await self.plugin_mgr.load_plugins()
-                await self.plugin_mgr.initialize_plugins()
-            case core_entities.LifecycleControlScope.PROVIDER.value:
-                self.logger.info('Hot reload scope=' + scope)
-
-                await self.tool_mgr.shutdown()
-
-                llm_model_mgr_inst = llm_model_mgr.ModelManager(self)
-                await llm_model_mgr_inst.initialize()
-                self.model_mgr = llm_model_mgr_inst
-
-                llm_session_mgr_inst = llm_session_mgr.SessionManager(self)
-                await llm_session_mgr_inst.initialize()
-                self.sess_mgr = llm_session_mgr_inst
-
-                llm_tool_mgr_inst = llm_tool_mgr.ToolManager(self)
-                await llm_tool_mgr_inst.initialize()
-                self.tool_mgr = llm_tool_mgr_inst
-            case _:
-                pass

pkg/core/boot.py

@@ -51,8 +51,8 @@ async def main(loop: asyncio.AbstractEventLoop):
         import signal
 
         def signal_handler(sig, frame):
+            app_inst.dispose()
             print('[Signal] Program exit.')
-            # ap.shutdown()
             os._exit(0)
 
         signal.signal(signal.SIGINT, signal_handler)

pkg/core/entities.py

@@ -1,18 +1,6 @@
 from __future__ import annotations
 
 import enum
-import typing
-import datetime
-import asyncio
-
-import pydantic.v1 as pydantic
-
-from ..provider import entities as llm_entities
-from ..provider.modelmgr import requester
-from ..provider.tools import entities as tools_entities
-from ..platform import adapter as msadapter
-from ..platform.types import message as platform_message
-from ..platform.types import events as platform_events
 
 
 class LifecycleControlScope(enum.Enum):
@@ -20,157 +8,3 @@ class LifecycleControlScope(enum.Enum):
     PLATFORM = 'platform'
     PLUGIN = 'plugin'
     PROVIDER = 'provider'
-
-
-class LauncherTypes(enum.Enum):
-    """一个请求的发起者类型"""
-
-    PERSON = 'person'
-    """私聊"""
-
-    GROUP = 'group'
-    """群聊"""
-
-
-class Query(pydantic.BaseModel):
-    """一次请求的信息封装"""
-
-    query_id: int
-    """请求ID，添加进请求池时生成"""
-
-    launcher_type: LauncherTypes
-    """会话类型，platform处理阶段设置"""
-
-    launcher_id: typing.Union[int, str]
-    """会话ID，platform处理阶段设置"""
-
-    sender_id: typing.Union[int, str]
-    """发送者ID，platform处理阶段设置"""
-
-    message_event: platform_events.MessageEvent
-    """事件，platform收到的原始事件"""
-
-    message_chain: platform_message.MessageChain
-    """消息链，platform收到的原始消息链"""
-
-    bot_uuid: typing.Optional[str] = None
-    """机器人UUID。"""
-
-    pipeline_uuid: typing.Optional[str] = None
-    """流水线UUID。"""
-
-    pipeline_config: typing.Optional[dict[str, typing.Any]] = None
-    """流水线配置，由 Pipeline 在运行开始时设置。"""
-
-    adapter: msadapter.MessagePlatformAdapter
-    """消息平台适配器对象，单个app中可能启用了多个消息平台适配器，此对象表明发起此query的适配器"""
-
-    session: typing.Optional[Session] = None
-    """会话对象，由前置处理器阶段设置"""
-
-    messages: typing.Optional[list[llm_entities.Message]] = []
-    """历史消息列表，由前置处理器阶段设置"""
-
-    prompt: typing.Optional[llm_entities.Prompt] = None
-    """情景预设内容，由前置处理器阶段设置"""
-
-    user_message: typing.Optional[llm_entities.Message] = None
-    """此次请求的用户消息对象，由前置处理器阶段设置"""
-
-    variables: typing.Optional[dict[str, typing.Any]] = None
-    """变量，由前置处理器阶段设置。在prompt中嵌入或由 Runner 传递到 LLMOps 平台。"""
-
-    use_llm_model: typing.Optional[requester.RuntimeLLMModel] = None
-    """使用的对话模型，由前置处理器阶段设置"""
-
-    use_funcs: typing.Optional[list[tools_entities.LLMFunction]] = None
-    """使用的函数，由前置处理器阶段设置"""
-
-    resp_messages: (
-        typing.Optional[list[llm_entities.Message]] | typing.Optional[list[platform_message.MessageChain]]
-    ) = []
-    """由Process阶段生成的回复消息对象列表"""
-
-    resp_message_chain: typing.Optional[list[platform_message.MessageChain]] = None
-    """回复消息链，从resp_messages包装而得"""
-
-    # ======= 内部保留 =======
-    current_stage: typing.Optional['pkg.pipeline.pipelinemgr.StageInstContainer'] = None
-    """当前所处阶段"""
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    # ========== 插件可调用的 API（请求 API） ==========
-
-    def set_variable(self, key: str, value: typing.Any):
-        """设置变量"""
-        if self.variables is None:
-            self.variables = {}
-        self.variables[key] = value
-
-    def get_variable(self, key: str) -> typing.Any:
-        """获取变量"""
-        if self.variables is None:
-            return None
-        return self.variables.get(key)
-
-    def get_variables(self) -> dict[str, typing.Any]:
-        """获取所有变量"""
-        if self.variables is None:
-            return {}
-        return self.variables
-
-
-class Conversation(pydantic.BaseModel):
-    """对话，包含于 Session 中，一个 Session 可以有多个历史 Conversation，但只有一个当前使用的 Conversation"""
-
-    prompt: llm_entities.Prompt
-
-    messages: list[llm_entities.Message]
-
-    create_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
-
-    update_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
-
-    use_llm_model: typing.Optional[requester.RuntimeLLMModel] = None
-
-    use_funcs: typing.Optional[list[tools_entities.LLMFunction]]
-
-    pipeline_uuid: str
-    """流水线UUID。"""
-
-    bot_uuid: str
-    """机器人UUID。"""
-
-    uuid: typing.Optional[str] = None
-    """该对话的 uuid，在创建时不会自动生成。而是当使用 Dify API 等由外部管理对话信息的服务时，用于绑定外部的会话。具体如何使用，取决于 Runner。"""
-
-    class Config:
-        arbitrary_types_allowed = True
-
-
-class Session(pydantic.BaseModel):
-    """会话，一个 Session 对应一个 {launcher_type.value}_{launcher_id}"""
-
-    launcher_type: LauncherTypes
-
-    launcher_id: typing.Union[int, str]
-
-    sender_id: typing.Optional[typing.Union[int, str]] = 0
-
-    use_prompt_name: typing.Optional[str] = 'default'
-
-    using_conversation: typing.Optional[Conversation] = None
-
-    conversations: typing.Optional[list[Conversation]] = pydantic.Field(default_factory=list)
-
-    create_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
-
-    update_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
-
-    semaphore: typing.Optional[asyncio.Semaphore] = None
-    """当前会话的信号量，用于限制并发"""
-
-    class Config:
-        arbitrary_types_allowed = True

pkg/core/stages/build_app.py

@@ -1,14 +1,16 @@
 from __future__ import annotations
 
+import asyncio
 
 from .. import stage, app
 from ...utils import version, proxy, announce
 from ...pipeline import pool, controller, pipelinemgr
-from ...plugin import manager as plugin_mgr
+from ...plugin import connector as plugin_connector
 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
@@ -16,9 +18,11 @@ 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
 
 
@@ -59,10 +63,13 @@ class BuildAppStage(stage.BootingStage):
         ap.persistence_mgr = persistence_mgr_inst
         await persistence_mgr_inst.initialize()
 
-        plugin_mgr_inst = plugin_mgr.PluginManager(ap)
+        async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
-        await plugin_mgr_inst.initialize()
+            await asyncio.sleep(3)
-        ap.plugin_mgr = plugin_mgr_inst
+            await plugin_connector_inst.initialize()
-        await plugin_mgr_inst.load_plugins()
+
+        plugin_connector_inst = plugin_connector.PluginRuntimeConnector(ap, runtime_disconnect_callback)
+        await plugin_connector_inst.initialize()
+        ap.plugin_connector = plugin_connector_inst
 
         cmd_mgr_inst = cmdmgr.CommandManager(ap)
         await cmd_mgr_inst.initialize()
@@ -88,6 +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
@@ -95,8 +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)
+        llm_model_service_inst = model_service.LLMModelsService(ap)
-        ap.model_service = model_service_inst
+        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
@@ -104,5 +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

pkg/entity/persistence/bstorage.py

@@ -0,0 +1,22 @@
+import sqlalchemy
+
+from .base import Base
+
+
+class BinaryStorage(Base):
+    """Current for plugin use only"""
+
+    __tablename__ = 'binary_storages'
+
+    unique_key = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    key = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    owner_type = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    owner = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    value = sqlalchemy.Column(sqlalchemy.LargeBinary, nullable=False)
+    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(),
+    )

pkg/entity/persistence/model.py

@@ -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(),
+    )

pkg/entity/persistence/pipeline.py

@@ -20,7 +20,6 @@ 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)
 
@@ -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)

pkg/entity/persistence/plugin.py

@@ -13,6 +13,8 @@ class PluginSetting(Base):
     enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
     priority = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
     config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=dict)
+    install_source = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, default='github')
+    install_info = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=dict)
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,

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)

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')

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

pkg/persistence/mgr.py

@@ -44,6 +44,38 @@ class PersistenceManager:
 
         await self.create_tables()
 
+        # run migrations
+        database_version = await self.execute_async(
+            sqlalchemy.select(metadata.Metadata).where(metadata.Metadata.key == 'database_version')
+        )
+
+        database_version = int(database_version.fetchone()[1])
+        required_database_version = constants.required_database_version
+
+        if database_version < required_database_version:
+            migrations = migration.preregistered_db_migrations
+            migrations.sort(key=lambda x: x.number)
+
+            last_migration_number = database_version
+
+            for migration_cls in migrations:
+                migration_instance = migration_cls(self.ap)
+
+                if (
+                    migration_instance.number > database_version
+                    and migration_instance.number <= required_database_version
+                ):
+                    await migration_instance.upgrade()
+                    await self.execute_async(
+                        sqlalchemy.update(metadata.Metadata)
+                        .where(metadata.Metadata.key == 'database_version')
+                        .values({'value': str(migration_instance.number)})
+                    )
+                    last_migration_number = migration_instance.number
+                    self.ap.logger.info(f'Migration {migration_instance.number} completed.')
+
+            self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
+
     async def create_tables(self):
         # create tables
         async with self.get_db_engine().connect() as conn:
@@ -79,7 +111,7 @@ class PersistenceManager:
                 'stages': pipeline_service.default_stage_order,
                 'is_default': True,
                 'name': 'ChatPipeline',
-                'description': 'Default pipeline provided, your new bots will be automatically 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',
+                '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,
             }
 
@@ -87,38 +119,6 @@ class PersistenceManager:
 
         # =================================
 
-        # run migrations
-        database_version = await self.execute_async(
-            sqlalchemy.select(metadata.Metadata).where(metadata.Metadata.key == 'database_version')
-        )
-
-        database_version = int(database_version.fetchone()[1])
-        required_database_version = constants.required_database_version
-
-        if database_version < required_database_version:
-            migrations = migration.preregistered_db_migrations
-            migrations.sort(key=lambda x: x.number)
-
-            last_migration_number = database_version
-
-            for migration_cls in migrations:
-                migration_instance = migration_cls(self.ap)
-
-                if (
-                    migration_instance.number > database_version
-                    and migration_instance.number <= required_database_version
-                ):
-                    await migration_instance.upgrade()
-                    await self.execute_async(
-                        sqlalchemy.update(metadata.Metadata)
-                        .where(metadata.Metadata.key == 'database_version')
-                        .values({'value': str(migration_instance.number)})
-                    )
-                    last_migration_number = migration_instance.number
-                    self.ap.logger.info(f'Migration {migration_instance.number} completed.')
-
-            self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
-
     async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
         async with self.get_db_engine().connect() as conn:
             result = await conn.execute(*args, **kwargs)
@@ -128,10 +128,13 @@ class PersistenceManager:
     def get_db_engine(self) -> sqlalchemy_asyncio.AsyncEngine:
         return self.db.get_engine()
 
-    def serialize_model(self, model: typing.Type[sqlalchemy.Base], data: sqlalchemy.Base) -> dict:
+    def serialize_model(
+        self, model: typing.Type[sqlalchemy.Base], data: sqlalchemy.Base, masked_columns: list[str] = []
+    ) -> dict:
         return {
             column.name: getattr(data, column.name)
             if not isinstance(getattr(data, column.name), (datetime.datetime))
             else getattr(data, column.name).isoformat()
             for column in model.__table__.columns
+            if column.name not in masked_columns
         }

pkg/persistence/migrations/dbm004_plugin_config.py

@@ -0,0 +1,20 @@
+from .. import migration
+
+
+@migration.migration_class(4)
+class DBMigratePluginConfig(migration.DBMigration):
+    """插件配置"""
+
+    async def upgrade(self):
+        """升级"""
+
+        if 'plugin' not in self.ap.instance_config.data:
+            self.ap.instance_config.data['plugin'] = {
+                'runtime_ws_url': 'ws://localhost:5400/control/ws',
+            }
+
+            await self.ap.instance_config.dump_config()
+
+    async def downgrade(self):
+        """降级"""
+        pass

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

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

pkg/persistence/migrations/dbm006_plugin_install_source.py

@@ -0,0 +1,32 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(6)
+class DBMigratePluginInstallSource(migration.DBMigration):
+    """插件安装来源"""
+
+    async def upgrade(self):
+        """升级"""
+        # 查询表结构获取所有列名（异步执行 SQL）
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text('PRAGMA table_info(plugin_settings);'))
+        # fetchall() 是同步方法，无需 await
+        columns = [row[1] for row in result.fetchall()]
+
+        # 检查并添加 install_source 列
+        if 'install_source' not in columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    "ALTER TABLE plugin_settings ADD COLUMN install_source VARCHAR(255) NOT NULL DEFAULT 'github'"
+                )
+            )
+
+        # 检查并添加 install_info 列
+        if 'install_info' not in columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("ALTER TABLE plugin_settings ADD COLUMN install_info JSON NOT NULL DEFAULT '{}'")
+            )
+
+    async def downgrade(self):
+        """降级"""
+        pass

pkg/pipeline/bansess/bansess.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from .. import stage, entities
-from ...core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @stage.stage_class('BanSessionCheckStage')
@@ -14,7 +14,7 @@ class BanSessionCheckStage(stage.PipelineStage):
     async def initialize(self, pipeline_config: dict):
         pass
 
-    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
+    async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
         found = False
 
         mode = query.pipeline_config['trigger']['access-control']['mode']

pkg/pipeline/cntfilter/cntfilter.py

@@ -3,12 +3,11 @@ from __future__ import annotations
 from ...core import app
 
 from .. import stage, entities
-from ...core import entities as core_entities
 from . import filter as filter_model, entities as filter_entities
-from ...provider import entities as llm_entities
+from langbot_plugin.api.entities.builtin.provider import message as provider_message
-from ...platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 from ...utils import importutil
-
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 from . import filters
 
 importutil.import_modules_in_pkg(filters)
@@ -58,7 +57,7 @@ class ContentFilterStage(stage.PipelineStage):
     async def _pre_process(
         self,
         message: str,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
     ) -> entities.StageProcessResult:
         """请求llm前处理消息
         只要有一个不通过就不放行，只放行 PASS 的消息
@@ -86,14 +85,14 @@ class ContentFilterStage(stage.PipelineStage):
                     elif result.level == filter_entities.ResultLevel.PASS:  # 传到下一个
                         message = result.replacement
 
-            query.message_chain = platform_message.MessageChain(platform_message.Plain(message))
+            query.message_chain = platform_message.MessageChain([platform_message.Plain(text=message)])
 
             return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
 
     async def _post_process(
         self,
         message: str,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
     ) -> entities.StageProcessResult:
         """请求llm后处理响应
         只要是 PASS 或者 MASKED 的就通过此 filter，将其 replacement 设置为message，进入下一个 filter
@@ -123,7 +122,7 @@ class ContentFilterStage(stage.PipelineStage):
 
             return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
 
-    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
+    async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
         """处理"""
         if stage_inst_name == 'PreContentFilterStage':
             contain_non_text = False
@@ -142,7 +141,7 @@ class ContentFilterStage(stage.PipelineStage):
             return await self._pre_process(str(query.message_chain).strip(), query)
         elif stage_inst_name == 'PostContentFilterStage':
             # 仅处理 query.resp_messages[-1].content 是 str 的情况
-            if isinstance(query.resp_messages[-1], llm_entities.Message) and isinstance(
+            if isinstance(query.resp_messages[-1], provider_message.Message) and isinstance(
                 query.resp_messages[-1].content, str
             ):
                 return await self._post_process(query.resp_messages[-1].content, query)

pkg/pipeline/cntfilter/entities.py

@@ -1,6 +1,6 @@
 import enum
 
-import pydantic.v1 as pydantic
+import pydantic
 
 
 class ResultLevel(enum.Enum):

pkg/pipeline/cntfilter/filter.py

@@ -3,9 +3,9 @@ from __future__ import annotations
 import abc
 import typing
 
-from ...core import app, entities as core_entities
+from ...core import app
 from . import entities
-
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 preregistered_filters: list[typing.Type[ContentFilter]] = []
 
@@ -60,8 +60,8 @@ class ContentFilter(metaclass=abc.ABCMeta):
         pass
 
     @abc.abstractmethod
-    async def process(self, query: core_entities.Query, message: str = None, image_url=None) -> entities.FilterResult:
+    async def process(self, query: pipeline_query.Query, message: str = None, image_url=None) -> entities.FilterResult:
-        """Process message
+        """处理消息
 
         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.

pkg/pipeline/cntfilter/filters/baiduexamine.py

@@ -4,8 +4,7 @@ import aiohttp
 
 from .. import entities
 from .. import filter as filter_model
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
-
 
 BAIDU_EXAMINE_URL = 'https://aip.baidubce.com/rest/2.0/solution/v1/text_censor/v2/user_defined?access_token={}'
 BAIDU_EXAMINE_TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'
@@ -27,7 +26,7 @@ class BaiduCloudExamine(filter_model.ContentFilter):
             ) as resp:
                 return (await resp.json())['access_token']
 
-    async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
+    async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
         async with aiohttp.ClientSession() as session:
             async with session.post(
                 BAIDU_EXAMINE_URL.format(await self._get_token()),

pkg/pipeline/cntfilter/filters/banwords.py

@@ -3,7 +3,7 @@ import re
 
 from .. import filter as filter_model
 from .. import entities
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @filter_model.filter_class('ban-word-filter')
@@ -13,7 +13,7 @@ class BanWordFilter(filter_model.ContentFilter):
     async def initialize(self):
         pass
 
-    async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
+    async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
         found = False
 
         for word in self.ap.sensitive_meta.data['words']:

pkg/pipeline/cntfilter/filters/cntignore.py

@@ -3,7 +3,7 @@ import re
 
 from .. import entities
 from .. import filter as filter_model
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @filter_model.filter_class('content-ignore')
@@ -16,7 +16,7 @@ class ContentIgnore(filter_model.ContentFilter):
             entities.EnableStage.PRE,
         ]
 
-    async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
+    async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
         if 'prefix' in query.pipeline_config['trigger']['ignore-rules']:
             for rule in query.pipeline_config['trigger']['ignore-rules']['prefix']:
                 if message.startswith(rule):

pkg/pipeline/controller.py

@@ -3,7 +3,10 @@ from __future__ import annotations
 import asyncio
 import traceback
 
-from ..core import app, entities
+from ..core import app
+from ..core import entities as core_entities
+
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 class Controller:
@@ -22,19 +25,19 @@ class Controller:
         """事件处理循环"""
         try:
             while True:
-                selected_query: entities.Query = None
+                selected_query: pipeline_query.Query = None
 
                 # 取请求
                 async with self.ap.query_pool:
-                    queries: list[entities.Query] = self.ap.query_pool.queries
+                    queries: list[pipeline_query.Query] = self.ap.query_pool.queries
 
                     for query in queries:
                         session = await self.ap.sess_mgr.get_session(query)
                         self.ap.logger.debug(f'Checking query {query} session {session}')
 
-                        if not session.semaphore.locked():
+                        if not session._semaphore.locked():
                             selected_query = query
-                            await session.semaphore.acquire()
+                            await session._semaphore.acquire()
 
                             break
 
@@ -46,7 +49,7 @@ class Controller:
 
                 if selected_query:
 
-                    async def _process_query(selected_query: entities.Query):
+                    async def _process_query(selected_query: pipeline_query.Query):
                         async with self.semaphore:  # 总并发上限
                             # find pipeline
                             # Here firstly find the bot, then find the pipeline, in case the bot adapter's config is not the latest one.
@@ -59,7 +62,7 @@ class Controller:
                                     await pipeline.run(selected_query)
 
                         async with self.ap.query_pool:
-                            (await self.ap.sess_mgr.get_session(selected_query)).semaphore.release()
+                            (await self.ap.sess_mgr.get_session(selected_query))._semaphore.release()
                             # 通知其他协程，有新的请求可以处理了
                             self.ap.query_pool.condition.notify_all()
 
@@ -68,8 +71,8 @@ class Controller:
                         kind='query',
                         name=f'query-{selected_query.query_id}',
                         scopes=[
-                            entities.LifecycleControlScope.APPLICATION,
+                            core_entities.LifecycleControlScope.APPLICATION,
-                            entities.LifecycleControlScope.PLATFORM,
+                            core_entities.LifecycleControlScope.PLATFORM,
                         ],
                     )
 

pkg/pipeline/entities.py

@@ -3,10 +3,10 @@ from __future__ import annotations
 import enum
 import typing
 
-import pydantic.v1 as pydantic
+import pydantic
-from ..platform.types import message as platform_message
 
-from ..core import entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 
 
 class ResultType(enum.Enum):
@@ -20,7 +20,7 @@ class ResultType(enum.Enum):
 class StageProcessResult(pydantic.BaseModel):
     result_type: ResultType
 
-    new_query: entities.Query
+    new_query: pipeline_query.Query
 
     user_notice: typing.Optional[
         typing.Union[

pkg/pipeline/longtext/longtext.py

@@ -5,10 +5,9 @@ import traceback
 
 from . import strategy
 from .. import stage, entities
-from ...core import entities as core_entities
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
-from ...platform.types import message as platform_message
 from ...utils import importutil
-
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 from . import strategies
 
 importutil.import_modules_in_pkg(strategies)
@@ -67,8 +66,8 @@ class LongTextProcessStage(stage.PipelineStage):
 
         await self.strategy_impl.initialize()
 
-    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
+    async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
-        # Check if it contains non-Plain components
+        # 检查是否包含非 Plain 组件
         contains_non_plain = False
 
         for msg in query.resp_message_chain[-1]:

pkg/pipeline/longtext/strategies/forward.py

@@ -3,9 +3,9 @@ from __future__ import annotations
 
 
 from .. import strategy as strategy_model
-from ....core import entities as core_entities
-from ....platform.types import message as platform_message
 
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 
 ForwardMessageDiaplay = platform_message.ForwardMessageDiaplay
 Forward = platform_message.Forward
@@ -13,7 +13,7 @@ Forward = platform_message.Forward
 
 @strategy_model.strategy_class('forward')
 class ForwardComponentStrategy(strategy_model.LongTextStrategy):
-    async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
+    async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
         display = ForwardMessageDiaplay(
             title='Group chat history',
             brief='[Chat history]',

pkg/pipeline/longtext/strategies/image.py

@@ -8,10 +8,10 @@ import re
 from PIL import Image, ImageDraw, ImageFont
 
 import functools
-from ....platform.types import message as platform_message
 
 from .. import strategy as strategy_model
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
 
 
 @strategy_model.strategy_class('image')
@@ -27,7 +27,7 @@ class Text2ImageStrategy(strategy_model.LongTextStrategy):
             encoding='utf-8',
         )
 
-    async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
+    async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
         img_path = self.text_to_image(
             text_str=message,
             save_as='temp/{}.png'.format(int(time.time())),
@@ -131,7 +131,7 @@ class Text2ImageStrategy(strategy_model.LongTextStrategy):
         text_str: str,
         save_as='temp.png',
         width=800,
-        query: core_entities.Query = None,
+        query: pipeline_query.Query = None,
     ):
         text_str = text_str.replace('\t', '    ')
 

pkg/pipeline/longtext/strategy.py

@@ -4,8 +4,9 @@ import typing
 
 
 from ...core import app
-from ...core import entities as core_entities
+
-from ...platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 preregistered_strategies: list[typing.Type[LongTextStrategy]] = []
@@ -49,8 +50,8 @@ class LongTextStrategy(metaclass=abc.ABCMeta):
         pass
 
     @abc.abstractmethod
-    async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
+    async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
-        """Process long text
+        """处理长文本
 
         If the text length exceeds the threshold, this method will be called.
 

pkg/pipeline/msgtrun/msgtrun.py

@@ -1,10 +1,9 @@
 from __future__ import annotations
 
 from .. import stage, entities
-from ...core import entities as core_entities
 from . import truncator
 from ...utils import importutil
-
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 from . import truncators
 
 importutil.import_modules_in_pkg(truncators)
@@ -29,8 +28,8 @@ class ConversationMessageTruncator(stage.PipelineStage):
         else:
             raise ValueError(f'Unknown truncator: {use_method}')
 
-    async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
+    async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
-        """Process"""
+        """处理"""
         query = await self.trun.truncate(query)
 
         return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

pkg/pipeline/msgtrun/truncator.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import typing
 import abc
 
-from ...core import entities as core_entities, app
+from ...core import app
-
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 preregistered_truncators: list[typing.Type[Truncator]] = []
 
@@ -47,7 +47,7 @@ class Truncator(abc.ABC):
         pass
 
     @abc.abstractmethod
-    async def truncate(self, query: core_entities.Query) -> core_entities.Query:
+    async def truncate(self, query: pipeline_query.Query) -> pipeline_query.Query:
         """截断
 
         一般只需要操作query.messages，也可以扩展操作query.prompt, query.user_message。

pkg/pipeline/msgtrun/truncators/round.py

@@ -1,15 +1,15 @@
 from __future__ import annotations
 
 from .. import truncator
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @truncator.truncator_class('round')
 class RoundTruncator(truncator.Truncator):
     """Truncate the conversation message chain to adapt to the LLM message length limit."""
 
-    async def truncate(self, query: core_entities.Query) -> core_entities.Query:
+    async def truncate(self, query: pipeline_query.Query) -> pipeline_query.Query:
-        """Truncate"""
+        """截断"""
         max_round = query.pipeline_config['ai']['local-agent']['max-round']
 
         temp_messages = []

pkg/pipeline/pipelinemgr.py

@@ -5,14 +5,18 @@ import traceback
 
 import sqlalchemy
 
-from ..core import app, entities
+from ..core import app
 from . import entities as pipeline_entities
 from ..entity.persistence import pipeline as persistence_pipeline
 from . import stage
-from ..platform.types import message as platform_message, events as platform_events
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
-from ..plugin import events
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
+import langbot_plugin.api.entities.events as events
 from ..utils import importutil
 
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
 from . import (
     resprule,
     bansess,
@@ -75,17 +79,17 @@ class RuntimePipeline:
         self.pipeline_entity = pipeline_entity
         self.stage_containers = stage_containers
 
-    async def run(self, query: entities.Query):
+    async def run(self, query: pipeline_query.Query):
         query.pipeline_config = self.pipeline_entity.config
         await self.process_query(query)
 
-    async def _check_output(self, query: entities.Query, result: pipeline_entities.StageProcessResult):
+    async def _check_output(self, query: pipeline_query.Query, result: pipeline_entities.StageProcessResult):
         """检查输出"""
         if result.user_notice:
             # 处理str类型
 
             if isinstance(result.user_notice, str):
-                result.user_notice = platform_message.MessageChain(platform_message.Plain(result.user_notice))
+                result.user_notice = platform_message.MessageChain([platform_message.Plain(text=result.user_notice)])
             elif isinstance(result.user_notice, list):
                 result.user_notice = platform_message.MessageChain(*result.user_notice)
 
@@ -93,12 +97,20 @@ class RuntimePipeline:
                 query.message_event, platform_events.GroupMessage
             ):
                 result.user_notice.insert(0, platform_message.At(query.message_event.sender.id))
-
+            if await query.adapter.is_stream_output_supported():
-            await query.adapter.reply_message(
+                await query.adapter.reply_message_chunk(
-                message_source=query.message_event,
+                    message_source=query.message_event,
-                message=result.user_notice,
+                    bot_message=query.resp_messages[-1],
-                quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
+                    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:
@@ -109,7 +121,7 @@ class RuntimePipeline:
     async def _execute_from_stage(
         self,
         stage_index: int,
-        query: entities.Query,
+        query: pipeline_query.Query,
     ):
         """从指定阶段开始执行，实现了责任链模式和基于生成器的阶段分叉功能。
 
@@ -136,7 +148,7 @@ class RuntimePipeline:
         while i < len(self.stage_containers):
             stage_container = self.stage_containers[i]
 
-            query.current_stage = stage_container  # 标记到 Query 对象里
+            query.current_stage_name = stage_container.inst_name  # 标记到 Query 对象里
 
             result = stage_container.inst.process(query, stage_container.inst_name)
 
@@ -144,23 +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
@@ -169,38 +185,39 @@ class RuntimePipeline:
 
             i += 1
 
-    async def process_query(self, query: entities.Query):
+    async def process_query(self, query: pipeline_query.Query):
         """处理请求"""
         try:
             # ======== 触发 MessageReceived 事件 ========
             event_type = (
                 events.PersonMessageReceived
-                if query.launcher_type == entities.LauncherTypes.PERSON
+                if query.launcher_type == provider_session.LauncherTypes.PERSON
                 else events.GroupMessageReceived
             )
 
-            event_ctx = await self.ap.plugin_mgr.emit_event(
+            event_obj = event_type(
-                event=event_type(
+                query=query,
-                    launcher_type=query.launcher_type.value,
+                launcher_type=query.launcher_type.value,
-                    launcher_id=query.launcher_id,
+                launcher_id=query.launcher_id,
-                    sender_id=query.sender_id,
+                sender_id=query.sender_id,
-                    message_chain=query.message_chain,
+                message_chain=query.message_chain,
-                    query=query,
-                )
             )
 
+            event_ctx = await self.ap.plugin_connector.emit_event(event_obj)
+
             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:
-            inst_name = query.current_stage.inst_name if query.current_stage else 'unknown'
+            inst_name = query.current_stage_name if query.current_stage_name else 'unknown'
             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]
 
 
 class PipelineManager:

pkg/pipeline/pool.py

@@ -3,10 +3,11 @@ from __future__ import annotations
 import asyncio
 import typing
 
-from ..core import entities
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
-from ..platform import adapter as msadapter
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
-from ..platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
-from ..platform.types import events as platform_events
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
 
 
 class QueryPool:
@@ -16,7 +17,10 @@ class QueryPool:
 
     pool_lock: asyncio.Lock
 
-    queries: list[entities.Query]
+    queries: list[pipeline_query.Query]
+
+    cached_queries: dict[int, pipeline_query.Query]
+    """Cached queries, used for plugin backward api call, will be removed after the query completely processed"""
 
     condition: asyncio.Condition
 
@@ -24,34 +28,38 @@ class QueryPool:
         self.query_id_counter = 0
         self.pool_lock = asyncio.Lock()
         self.queries = []
+        self.cached_queries = {}
         self.condition = asyncio.Condition(self.pool_lock)
 
     async def add_query(
         self,
         bot_uuid: str,
-        launcher_type: entities.LauncherTypes,
+        launcher_type: provider_session.LauncherTypes,
         launcher_id: typing.Union[int, str],
         sender_id: typing.Union[int, str],
         message_event: platform_events.MessageEvent,
         message_chain: platform_message.MessageChain,
-        adapter: msadapter.MessagePlatformAdapter,
+        adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter,
         pipeline_uuid: typing.Optional[str] = None,
-    ) -> entities.Query:
+    ) -> pipeline_query.Query:
         async with self.condition:
-            query = entities.Query(
+            query_id = self.query_id_counter
+            query = pipeline_query.Query(
                 bot_uuid=bot_uuid,
-                query_id=self.query_id_counter,
+                query_id=query_id,
                 launcher_type=launcher_type,
                 launcher_id=launcher_id,
                 sender_id=sender_id,
                 message_event=message_event,
                 message_chain=message_chain,
+                variables={},
                 resp_messages=[],
                 resp_message_chain=[],
                 adapter=adapter,
                 pipeline_uuid=pipeline_uuid,
             )
             self.queries.append(query)
+            self.cached_queries[query_id] = query
             self.query_id_counter += 1
             self.condition.notify_all()
 

pkg/pipeline/preproc/preproc.py

@@ -3,10 +3,10 @@ from __future__ import annotations
 import datetime
 
 from .. import stage, entities
-from ...core import entities as core_entities
+from langbot_plugin.api.entities.builtin.provider import message as provider_message
-from ...provider import entities as llm_entities
+import langbot_plugin.api.entities.events as events
-from ...plugin import events
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
-from ...platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @stage.stage_class('PreProcessor')
@@ -26,7 +26,7 @@ class PreProcessor(stage.PipelineStage):
 
     async def process(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         stage_inst_name: str,
     ) -> entities.StageProcessResult:
         """Process"""
@@ -49,77 +49,73 @@ class PreProcessor(stage.PipelineStage):
             query.bot_uuid,
         )
 
-        conversation.use_llm_model = llm_model
+        # 设置query
-
-        # Set query
         query.session = session
         query.prompt = conversation.prompt.copy()
         query.messages = conversation.messages.copy()
 
-        query.use_llm_model = llm_model
+        query.use_llm_model_uuid = llm_model.model_entity.uuid
 
         if selected_runner == 'local-agent':
-            query.use_funcs = (
+            query.use_funcs = []
-                conversation.use_funcs if query.use_llm_model.model_entity.abilities.__contains__('func_call') else None
-            )
 
-        query.variables = {
+            if llm_model.model_entity.abilities.__contains__('func_call'):
+                query.use_funcs = await self.ap.tool_mgr.get_all_tools()
+
+        variables = {
             'session_id': f'{query.session.launcher_type.value}_{query.session.launcher_id}',
             'conversation_id': conversation.uuid,
             'msg_create_time': (
                 int(query.message_event.time) if query.message_event.time else int(datetime.datetime.now().timestamp())
             ),
         }
+        query.variables.update(variables)
 
         # Check if this model supports vision, if not, remove all images
         # TODO this checking should be performed in runner, and in this stage, the image should be reserved
-        if selected_runner == 'local-agent' and not query.use_llm_model.model_entity.abilities.__contains__('vision'):
+        if selected_runner == 'local-agent' and not llm_model.model_entity.abilities.__contains__('vision'):
             for msg in query.messages:
                 if isinstance(msg.content, list):
                     for me in msg.content:
                         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')
 
         for me in query.message_chain:
             if isinstance(me, platform_message.Plain):
-                content_list.append(llm_entities.ContentElement.from_text(me.text))
+                content_list.append(provider_message.ContentElement.from_text(me.text))
                 plain_text += me.text
             elif isinstance(me, platform_message.Image):
-                if selected_runner != 'local-agent' or query.use_llm_model.model_entity.abilities.__contains__(
+                if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
-                    'vision'
-                ):
                     if me.base64 is not None:
-                        content_list.append(llm_entities.ContentElement.from_image_base64(me.base64))
+                        content_list.append(provider_message.ContentElement.from_image_base64(me.base64))
             elif isinstance(me, platform_message.Quote) and qoute_msg:
                 for msg in me.origin:
                     if isinstance(msg, platform_message.Plain):
-                        content_list.append(llm_entities.ContentElement.from_text(msg.text))
+                        content_list.append(provider_message.ContentElement.from_text(msg.text))
                     elif isinstance(msg, platform_message.Image):
-                        if selected_runner != 'local-agent' or query.use_llm_model.model_entity.abilities.__contains__(
+                        if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
-                            'vision'
-                        ):
                             if msg.base64 is not None:
-                                content_list.append(llm_entities.ContentElement.from_image_base64(msg.base64))
+                                content_list.append(provider_message.ContentElement.from_image_base64(msg.base64))
 
         query.variables['user_message_text'] = plain_text
 
-        query.user_message = llm_entities.Message(role='user', content=content_list)
+        query.user_message = provider_message.Message(role='user', content=content_list)
-        # =========== Trigger event PromptPreProcessing
+        # =========== 触发事件 PromptPreProcessing
 
-        event_ctx = await self.ap.plugin_mgr.emit_event(
+        event = events.PromptPreProcessing(
-            event=events.PromptPreProcessing(
+            session_name=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
-                session_name=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
+            default_prompt=query.prompt.messages,
-                default_prompt=query.prompt.messages,
+            prompt=query.messages,
-                prompt=query.messages,
+            query=query,
-                query=query,
-            )
         )
 
+        event_ctx = await self.ap.plugin_connector.emit_event(event)
+
         query.prompt.messages = event_ctx.event.default_prompt
         query.messages = event_ctx.event.prompt
 

pkg/pipeline/process/handler.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import abc
 
 from ...core import app
-from ...core import entities as core_entities
 from .. import entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 class MessageHandler(metaclass=abc.ABCMeta):
@@ -19,7 +19,7 @@ class MessageHandler(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     async def handle(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
     ) -> entities.StageProcessResult:
         raise NotImplementedError
 

pkg/pipeline/process/handlers/chat.py

@@ -1,18 +1,21 @@
 from __future__ import annotations
 
+import uuid
 import typing
 import traceback
 
 
 from .. import handler
 from ... import entities
-from ....core import entities as core_entities
 from ....provider import runner as runner_module
-from ....plugin import events
 
-from ....platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+import langbot_plugin.api.entities.events as events
 from ....utils import importutil
 from ....provider import runners
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
 
 importutil.import_modules_in_pkg(runners)
 
@@ -20,33 +23,32 @@ importutil.import_modules_in_pkg(runners)
 class ChatMessageHandler(handler.MessageHandler):
     async def handle(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
     ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
-        """Process"""
+        """处理"""
-        # Call API
+        # 调API
-        #   generator
+        #   生成器
 
-        # Trigger plugin event
+        # 触发插件事件
         event_class = (
             events.PersonNormalMessageReceived
-            if query.launcher_type == core_entities.LauncherTypes.PERSON
+            if query.launcher_type == provider_session.LauncherTypes.PERSON
             else events.GroupNormalMessageReceived
         )
 
-        event_ctx = await self.ap.plugin_mgr.emit_event(
+        event = event_class(
-            event=event_class(
+            launcher_type=query.launcher_type.value,
-                launcher_type=query.launcher_type.value,
+            launcher_id=query.launcher_id,
-                launcher_id=query.launcher_id,
+            sender_id=query.sender_id,
-                sender_id=query.sender_id,
+            text_message=str(query.message_chain),
-                text_message=str(query.message_chain),
+            query=query,
-                query=query,
-            )
         )
 
+        event_ctx = await self.ap.plugin_connector.emit_event(event)
+
         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)
@@ -54,10 +56,14 @@ class ChatMessageHandler(handler.MessageHandler):
                 yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
         else:
             if event_ctx.event.alter is not None:
-                # if isinstance(event_ctx.event, str):  # Currently not considering multi-modal alter
+                # if isinstance(event_ctx.event, str):  # 现在暂时不考虑多模态alter
                 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:
@@ -65,22 +71,42 @@ class ChatMessageHandler(handler.MessageHandler):
                         runner = r(self.ap, query.pipeline_config)
                         break
                 else:
-                    raise ValueError(f'Request runner not found: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                    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'Response({query.query_id}): {self.cut_str(result.readable_str())}')
+                        if result.content is not None:
+                            text_length += len(result.content)
 
-                    if result.content is not None:
+                        yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
-                        text_length += len(result.content)
 
-                    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'Request failed({query.query_id}): {type(e).__name__} {str(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']
 

pkg/pipeline/process/handlers/command.py

@@ -4,16 +4,17 @@ import typing
 
 from .. import handler
 from ... import entities
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
-from ....provider import entities as llm_entities
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
-from ....plugin import events
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
-from ....platform.types import message as platform_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.events as events
 
 
 class CommandHandler(handler.MessageHandler):
     async def handle(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
     ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
         """Process"""
 
@@ -28,23 +29,23 @@ class CommandHandler(handler.MessageHandler):
 
         event_class = (
             events.PersonCommandSent
-            if query.launcher_type == core_entities.LauncherTypes.PERSON
+            if query.launcher_type == provider_session.LauncherTypes.PERSON
             else events.GroupCommandSent
         )
 
-        event_ctx = await self.ap.plugin_mgr.emit_event(
+        event = event_class(
-            event=event_class(
+            launcher_type=query.launcher_type.value,
-                launcher_type=query.launcher_type.value,
+            launcher_id=query.launcher_id,
-                launcher_id=query.launcher_id,
+            sender_id=query.sender_id,
-                sender_id=query.sender_id,
+            command=spt[0],
-                command=spt[0],
+            params=spt[1:] if len(spt) > 1 else [],
-                params=spt[1:] if len(spt) > 1 else [],
+            text_message=str(query.message_chain),
-                text_message=str(query.message_chain),
+            is_admin=(privilege == 2),
-                is_admin=(privilege == 2),
+            query=query,
-                query=query,
-            )
         )
 
+        event_ctx = await self.ap.plugin_connector.emit_event(event)
+
         if event_ctx.is_prevented_default():
             if event_ctx.event.reply is not None:
                 mc = platform_message.MessageChain(event_ctx.event.reply)
@@ -64,7 +65,7 @@ class CommandHandler(handler.MessageHandler):
             async for ret in self.ap.cmd_mgr.execute(command_text=command_text, query=query, session=session):
                 if ret.error is not None:
                     query.resp_messages.append(
-                        llm_entities.Message(
+                        provider_message.Message(
                             role='command',
                             content=str(ret.error),
                         )
@@ -74,16 +75,16 @@ class CommandHandler(handler.MessageHandler):
 
                     yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
                 elif ret.text is not None or ret.image_url is not None:
-                    content: list[llm_entities.ContentElement] = []
+                    content: list[provider_message.ContentElement] = []
 
                     if ret.text is not None:
-                        content.append(llm_entities.ContentElement.from_text(ret.text))
+                        content.append(provider_message.ContentElement.from_text(ret.text))
 
                     if ret.image_url is not None:
-                        content.append(llm_entities.ContentElement.from_image_url(ret.image_url))
+                        content.append(provider_message.ContentElement.from_image_url(ret.image_url))
 
                     query.resp_messages.append(
-                        llm_entities.Message(
+                        provider_message.Message(
                             role='command',
                             content=content,
                         )

pkg/pipeline/process/process.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-from ...core import entities as core_entities
 from . import handler
 from .handlers import chat, command
 from .. import entities
 from .. import stage
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 @stage.stage_class('MessageProcessor')
@@ -30,7 +30,7 @@ class Processor(stage.PipelineStage):
 
     async def process(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         stage_inst_name: str,
     ) -> entities.StageProcessResult:
         """Process"""

pkg/pipeline/ratelimit/algo.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 import abc
 import typing
 
-from ...core import app, entities as core_entities
+from ...core import app
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 preregistered_algos: list[typing.Type[ReteLimitAlgo]] = []
@@ -33,7 +34,7 @@ class ReteLimitAlgo(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     async def require_access(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         launcher_type: str,
         launcher_id: typing.Union[int, str],
     ) -> bool:
@@ -53,7 +54,7 @@ class ReteLimitAlgo(metaclass=abc.ABCMeta):
     @abc.abstractmethod
     async def release_access(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         launcher_type: str,
         launcher_id: typing.Union[int, str],
     ):

pkg/pipeline/ratelimit/algos/fixedwin.py

@@ -3,7 +3,7 @@ import asyncio
 import time
 import typing
 from .. import algo
-from ....core import entities as core_entities
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 
 
 # 固定窗口算法
@@ -32,7 +32,7 @@ class FixedWindowAlgo(algo.ReteLimitAlgo):
 
     async def require_access(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         launcher_type: str,
         launcher_id: typing.Union[int, str],
     ) -> bool:
@@ -91,7 +91,7 @@ class FixedWindowAlgo(algo.ReteLimitAlgo):
 
     async def release_access(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         launcher_type: str,
         launcher_id: typing.Union[int, str],
     ):

pkg/pipeline/ratelimit/ratelimit.py

@@ -4,9 +4,10 @@ import typing
 
 from .. import entities, stage
 from . import algo
-from ...core import entities as core_entities
 from ...utils import importutil
 
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
 from . import algos
 
 importutil.import_modules_in_pkg(algos)
@@ -39,7 +40,7 @@ class RateLimit(stage.PipelineStage):
 
     async def process(
         self,
-        query: core_entities.Query,
+        query: pipeline_query.Query,
         stage_inst_name: str,
     ) -> typing.Union[
         entities.StageProcessResult,