fix: optimize configuration function

* fix:wecombot file and image

* fix: add enable-stream-reply config

.dockerignore

@@ -0,0 +1,8 @@
+.github
+.venv
+.vscode
+.data
+.temp
+web/.next
+web/node_modules
+web/.env

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -19,7 +19,7 @@ body:
   - type: textarea
     attributes:
       label: 复现步骤
-      description: 提供越多信息，我们会越快解决问题，建议多提供配置截图；**如果你不认真填写（只一两句话概括），我们会很生气并且立即关闭 issue 或两年后才回复你**
+      description: 提供越多信息，我们会越快解决问题，建议多提供配置截图；**如果涉及 Dify、n8n、Langflow 等外部平台，请提供应用的导出文件（如 Dify 应用的 DSL），我们将更快回复您。**
     validations:
       required: false
   - type: textarea

.github/ISSUE_TEMPLATE/bug-report_en.yml

@@ -19,7 +19,7 @@ body:
   - type: textarea
     attributes:
       label: Reproduction steps
-      description: How to reproduce this problem, the more detailed the better; the more information you provide, the faster we will solve the problem. 【注意】请务必认真填写此部分，若不提供完整信息（如只有一两句话的概括），我们将不会回复！
+      description: How to reproduce this problem, the more detailed the better; the more information you provide, the faster we will solve the problem.
     validations:
       required: false
   - type: textarea

.github/workflows/build-docker-image.yml

@@ -3,7 +3,6 @@ on:
   ## 发布release的时候会自动构建
   release:
     types: [published]
-  workflow_dispatch:
 jobs:
   publish-docker-image:
     runs-on: ubuntu-latest
@@ -42,7 +41,7 @@ jobs:
         run: docker buildx create --name mybuilder --use
       - name: Build for Release # only relase, exlude pre-release
         if: ${{ github.event.release.prerelease == false }}
-        run: docker buildx build --platform linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} -t rockchin/langbot:latest . --push
+        run: docker buildx build --platform linux/arm64,linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} -t rockchin/langbot:latest . --push
       - name: Build for Pre-release # no update for latest tag
         if: ${{ github.event.release.prerelease == true }}
-        run: docker buildx build --platform linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} . --push
+        run: docker buildx build --platform linux/arm64,linux/amd64 -t rockchin/langbot:${{ steps.check_version.outputs.version }} . --push

.github/workflows/lint.yml

@@ -0,0 +1,60 @@
+name: Lint
+
+on:
+  push:
+    branches:
+      - main
+      - master
+      - dev
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+
+jobs:
+  ruff:
+    name: Ruff Lint & Format
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync --dev
+
+      - name: Run ruff check
+        run: uv run ruff check src
+
+      - name: Run ruff format
+        run: uv run ruff format src --check
+
+  frontend:
+    name: Frontend Lint
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '25'
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Install dependencies
+        working-directory: web
+        run: pnpm install
+
+      - name: Run lint
+        working-directory: web
+        run: pnpm lint

.github/workflows/run-tests.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.11', '3.12', '3.13']
       fail-fast: false
 
     steps:

.gitignore

@@ -42,7 +42,6 @@ botpy.log*
 test.py
 /web_ui
 .venv/
-uv.lock
 /test
 plugins.bak
 coverage.xml

.mcp.json

@@ -0,0 +1,37 @@
+{
+  "mcpServers": {
+    "shadcn": {
+      "command": "npx",
+      "args": [
+        "shadcn@latest",
+        "mcp"
+      ]
+    },
+    "sequential-thinking": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
+      "env": {}
+    },
+    "github": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-github"],
+      "env": {
+        "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_PERSONAL_ACCESS_TOKEN}"
+      }
+    },
+    "fetch": {
+      "type": "stdio",
+      "command": "uvx",
+      "args": ["mcp-server-fetch"],
+      "env": {}
+    },
+    "playwright": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@playwright/mcp@latest"],
+      "env": {}
+    }
+  }
+}

.pre-commit-config.yaml

@@ -9,16 +9,14 @@ repos:
       # Run the formatter of backend.
       - id: ruff-format
 
-  - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v3.1.0
-    hooks:
-      - id: prettier
-        types_or: [javascript, jsx, ts, tsx, css, scss]
-        additional_dependencies:
-          - prettier@3.1.0
-
   - repo: local
     hooks:
+      - id: prettier
+        name: prettier
+        entry: npx --prefix web prettier --write --ignore-unknown
+        language: system
+        types_or: [javascript, jsx, ts, tsx, css, scss]
+
       - id: lint-staged
         name: lint-staged
         entry: cd web && pnpm lint-staged

AGENTS.md

@@ -8,16 +8,17 @@ LangBot is a open-source LLM native instant messaging bot development platform,
 
 LangBot has a comprehensive frontend, all operations can be performed through the frontend. The project splited into these major parts:
 
-- `./pkg`: The core python package of the project backend.
-    - `./pkg/platform`: The platform module of the project, containing the logic of message platform adapters, bot managers, message session managers, etc.
-    - `./pkg/provider`: The provider module of the project, containing the logic of LLM providers, tool providers, etc.
-    - `./pkg/pipeline`: The pipeline module of the project, containing the logic of pipelines, stages, query pool, etc.
-    - `./pkg/api`: The api module of the project, containing the http api controllers and services.
-    - `./pkg/plugin`: LangBot bridge for connecting with plugin system.
-- `./libs`: Some SDKs we previously developed for the project, such as `qq_official_api`, `wecom_api`, etc.
-- `./templates`: Templates of config files, components, etc.
-- `./web`: Frontend codebase, built with Next.js + **shadcn** + **Tailwind CSS**.
-- `./docker`: docker-compose deployment files.
+- `./src/langbot`: The main python package of the project, below are the main modules in this package:
+    - `./pkg`: The core python package of the project backend.
+        - `./pkg/platform`: The platform module of the project, containing the logic of message platform adapters, bot managers, message session managers, etc.
+        - `./pkg/provider`: The provider module of the project, containing the logic of LLM providers, tool providers, etc.
+        - `./pkg/pipeline`: The pipeline module of the project, containing the logic of pipelines, stages, query pool, etc.
+        - `./pkg/api`: The api module of the project, containing the http api controllers and services.
+        - `./pkg/plugin`: LangBot bridge for connecting with plugin system.
+    - `./libs`: Some SDKs we previously developed for the project, such as `qq_official_api`, `wecom_api`, etc.
+    - `./templates`: Templates of config files, components, etc.
+    - `./web`: Frontend codebase, built with Next.js + **shadcn** + **Tailwind CSS**.
+    - `./docker`: docker-compose deployment files.
 
 ## Backend Development
 
@@ -69,6 +70,7 @@ Plugin Runtime automatically starts each installed plugin and interacts through
     - type: must be a specific type, such as feat (new feature), fix (bug fix), docs (documentation), style (code style), refactor (refactoring), perf (performance optimization), etc.
     - scope: the scope of the commit, such as the package name, the file name, the function name, the class name, the module name, etc.
     - subject: the subject of the commit, such as the description of the commit, the reason for the commit, the impact of the commit, etc.
+- If you changed the definition of database entities, please update the migration file in `src/langbot/pkg/persistence/migrations/` and update the constants.py file in `src/langbot/pkg/utils/constants.py` with the new migration number.
 
 ## Some Principles
 

Dockerfile

@@ -20,4 +20,4 @@ RUN apt update \
     && uv sync \
     && touch /.dockerenv
 
-CMD [ "uv", "run", "main.py" ]
+CMD [ "uv", "run", "--no-sync", "main.py" ]

README.md

@@ -1,47 +1,69 @@
-
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
+<img width="130" src="res/logo-blue.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>
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" 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)
+<h3>Production-grade platform for building agentic IM bots.</h3>
+<h4>Quickly build, debug, and ship AI bots to Slack, Discord, Telegram, WeChat, and more.</h4>
+
+English / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
 
 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
-
-<a href="https://langbot.app">项目主页</a> ｜
-<a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a> ｜
-<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">插件介绍</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
+<a href="https://langbot.app">Website</a> ｜
+<a href="https://docs.langbot.app/en/insight/features">Features</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide">Docs</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme">API</a> ｜
+<a href="https://space.langbot.app/cloud">Cloud</a> ｜
+<a href="https://space.langbot.app">Plugin Market</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Roadmap</a>
 
 </div>
 
 </p>
 
-LangBot 是一个开源的大语言模型原生即时通信机器人开发平台，旨在提供开箱即用的 IM 机器人开发体验，具有 Agent、RAG、MCP 等多种 LLM 应用功能，适配全球主流即时通信平台，并提供丰富的 API 接口，支持自定义开发。
+---
 
-## 📦 开始使用
+## What is LangBot?
 
-#### 快速部署
+LangBot is an **open-source, production-grade platform** for building AI-powered instant messaging bots. It connects Large Language Models (LLMs) to any chat platform, enabling you to create intelligent agents that can converse, execute tasks, and integrate with your existing workflows.
 
-使用 `uvx` 一键启动（需要先安装 [uv](https://docs.astral.sh/uv/getting-started/installation/)）：
+### Key Capabilities
+
+- **AI Conversations & Agents** — Multi-turn dialogues, tool calling, multi-modal support, streaming output. Built-in RAG (knowledge base) with deep integration to [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Universal IM Platform Support** — One codebase for Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
+- **Production-Ready** — Access control, rate limiting, sensitive word filtering, comprehensive monitoring, and exception handling. Trusted by enterprises.
+- **Plugin Ecosystem** — Hundreds of plugins, event-driven architecture, component extensions, and [MCP protocol](https://modelcontextprotocol.io/) support.
+- **Web Management Panel** — Configure, manage, and monitor your bots through an intuitive browser interface. No YAML editing required.
+- **Multi-Pipeline Architecture** — Different bots for different scenarios, with comprehensive monitoring and exception handling.
+
+[→ Learn more about all features](https://docs.langbot.app/en/insight/features)
+
+---
+
+## Quick Start
+
+### ☁️ LangBot Cloud (Recommended)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Zero deployment, ready to use.
+
+### One-Line Launch
 
 ```bash
 uvx langbot
 ```
 
-访问 http://localhost:5300 即可开始使用。
+> Requires [uv](https://docs.astral.sh/uv/getting-started/installation/). Visit http://localhost:5300 — done.
 
-#### Docker Compose 部署
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -49,122 +71,102 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-访问 http://localhost:5300 即可开始使用。
-
-详细文档[Docker 部署](https://docs.langbot.app/zh/deploy/langbot/docker.html)。
-
-#### 宝塔面板部署
-
-已上架宝塔面板，若您已安装宝塔面板，可以根据[文档](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html)使用。
-
-#### Zeabur 云部署
-
-社区贡献的 Zeabur 模板。
-
-[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
-
-#### Railway 云部署
+### One-Click Cloud Deploy
 
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### 手动部署
+**More options:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker) · [Manual](https://docs.langbot.app/en/deploy/langbot/manual) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt) · [Kubernetes](./docker/README_K8S.md)
 
-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)。
+---
 
-#### Kubernetes 部署
+## Supported Platforms
 
-参考 [Kubernetes 部署](./docker/README_K8S.md) 文档。
-
-## 😎 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)
-
-## ✨ 特性
-
-- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态、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。
-
-详细规格特性请访问[文档](https://docs.langbot.app/zh/insight/features.html)。
-
-或访问 demo 环境：https://demo.langbot.dev/  
-  - 登录信息：邮箱：`demo@langbot.app` 密码：`langbot123456`
-  - 注意：仅展示 WebUI 效果，公开环境，请不要在其中填入您的任何敏感信息。
-
-### 消息平台
-
-| 平台 | 状态 | 备注 |
-| --- | --- | --- |
-| QQ 个人号 | ✅ | QQ 个人号私聊、群聊 |
-| QQ 官方机器人 | ✅ | QQ 官方机器人，支持频道、私聊、群聊 |
-| 企业微信 | ✅ |  |
-| 企微对外客服 | ✅ |  |
-| 企微智能机器人 | ✅ |  |
-| 个人微信 | ✅ |  |
-| 微信公众号 | ✅ |  |
-| 飞书 | ✅ |  |
-| 钉钉 | ✅ |  |
+| Platform | Status | Notes |
+|----------|--------|-------|
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
 | LINE | ✅ |  |
+| QQ | ✅ | Personal & Official API |
+| WeCom | ✅ | Enterprise WeChat, External CS, AI Bot |
+| WeChat | ✅ | Personal & Official Account |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
 
-### 大模型能力
+---
 
-| 模型 | 状态 | 备注 |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | 可接入任何 OpenAI 接口格式模型 |
-| [DeepSeek](https://www.deepseek.com/) | ✅ |  |
-| [Moonshot](https://www.moonshot.cn/) | ✅ |  |
-| [Anthropic](https://www.anthropic.com/) | ✅ |  |
-| [xAI](https://x.ai/) | ✅ |  |
-| [智谱AI](https://open.bigmodel.cn/) | ✅ |  |
-| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 全球大模型都可调用（友情推荐） |
-| [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 |
-| [接口 AI](https://jiekou.ai/) | ✅ | 大模型聚合平台，专注全球大模型接入 |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
-| [Ollama](https://ollama.com/) | ✅ | 本地大模型运行平台 |
-| [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型运行平台 |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | 大模型接口聚合平台 |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
-| [小马算力](https://www.tokenpony.cn/453z1) | ✅ | 大模型聚合平台 |
-| [阿里云百炼](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/) | ✅ | 支持通过 MCP 协议获取工具 |
-| [百宝箱Tbox](https://www.tbox.cn/open) | ✅ | 蚂蚁百宝箱智能体平台，每月免费10亿大模型Token |
+## Supported LLMs & Integrations
 
-### TTS
+| Provider | Type | Status |
+|----------|------|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | Local LLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | Local LLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | Protocol | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | Gateway | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | Gateway | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Gateway | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Gateway | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | Gateway | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU Platform | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU Platform | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPU Platform | ✅ |
+| [接口 AI](https://jiekou.ai/) | Gateway | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | Gateway | ✅ |
 
-| 平台/模型 | 备注 |
-| --- | --- |
-| [FishAudio](https://fish.audio/zh-CN/discovery/) | [插件](https://github.com/the-lazy-me/NewChatVoice) |
-| [海豚 AI](https://www.ttson.cn/?source=thelazy) | [插件](https://github.com/the-lazy-me/NewChatVoice) |
-| [AzureTTS](https://portal.azure.com/) | [插件](https://github.com/Ingnaryk/LangBot_AzureTTS) |
+[→ View all integrations](https://docs.langbot.app/en/insight/features)
 
-### 文生图
+---
 
-| 平台/模型 | 备注 |
-| --- | --- |
-| 阿里云百炼 | [插件](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
+## Why LangBot?
 
-## 😘 社区贡献
+| Use Case | How LangBot Helps |
+|----------|-------------------|
+| **Customer Support** | Deploy AI agents to Slack/Discord/Telegram that answer questions using your knowledge base |
+| **Internal Tools** | Connect n8n/Dify workflows to WeCom/DingTalk for automated business processes |
+| **Community Management** | Moderate QQ/Discord groups with AI-powered content filtering and interaction |
+| **Multi-Platform Presence** | One bot, all platforms. Manage from a single dashboard |
 
-感谢以下[代码贡献者](https://github.com/langbot-app/LangBot/graphs/contributors)和社区里其他成员对 LangBot 的贡献：
+---
+
+## Live Demo
+
+**Try it now:** https://demo.langbot.dev/
+- Email: `demo@langbot.app`
+- Password: `langbot123456`
+
+*Note: Public demo environment. Do not enter sensitive information.*
+
+---
+
+## Community
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Discord Community](https://discord.gg/wdNEHETs87)
+
+---
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## Contributors
+
+Thanks to all [contributors](https://github.com/langbot-app/LangBot/graphs/contributors) who have helped make LangBot better:
 
 <a href="https://github.com/langbot-app/LangBot/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
 </a>
-
-<!--
-## For Code Agents
-
-If you're a code agent based on LLM, you should read [AGENTS.md](AGENTS.md) to understand the project structure and development process before you start any development.
--->

README_CN.md

@@ -0,0 +1,195 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.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>
+
+<h3>生产级 AI 即时通信机器人开发平台。</h3>
+<h4>快速构建、调试和部署 AI 机器人到微信、QQ、飞书、Slack、Discord、Telegram 等平台。</h4>
+
+[English](README.md) / 简体中文 / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
+
+[![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%A4-1030838208-blue)](https://qm.qq.com/q/DxZZcNxM1W)
+[![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">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
+
+<a href="https://langbot.app">官网</a> ｜
+<a href="https://docs.langbot.app/zh/insight/features.html">特性</a> ｜
+<a href="https://docs.langbot.app/zh/insight/guide.html">文档</a> ｜
+<a href="https://docs.langbot.app/zh/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app/cloud">Cloud</a> ｜
+<a href="https://space.langbot.app">插件市场</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">路线图</a>
+
+</div>
+
+</p>
+
+---
+
+LangBot 是一个**开源的生产级平台**，用于构建 AI 驱动的即时通信机器人。它将大语言模型（LLM）连接到各种聊天平台，帮助你创建能够对话、执行任务、并集成到现有工作流程中的智能 Agent。
+
+### 核心能力
+
+- **AI 对话与 Agent** — 多轮对话、工具调用、多模态、流式输出。自带 RAG（知识库），深度集成 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) 等 LLMOps 平台。
+- **全平台支持** — 一套代码，覆盖 QQ、微信、企业微信、飞书、钉钉、Discord、Telegram、Slack、LINE、KOOK 等平台。
+- **生产就绪** — 访问控制、限速、敏感词过滤、全面监控与异常处理，已被多家企业采用。
+- **插件生态** — 数百个插件，跨进程的事件驱动架构，组件扩展，适配 [MCP 协议](https://modelcontextprotocol.io/)。
+- **Web 管理面板** — 通过浏览器直观地配置、管理和监控机器人，无需手动编辑配置文件。
+- **多流水线架构** — 不同机器人用于不同场景，具备全面的监控和异常处理能力。
+
+[→ 了解更多功能特性](https://docs.langbot.app/zh/insight/features.html)
+
+---
+
+## 快速开始
+
+### ☁️ LangBot Cloud（推荐）
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — 免部署，开箱即用。
+
+### 一键启动
+
+```bash
+uvx langbot
+```
+
+> 需要安装 [uv](https://docs.astral.sh/uv/getting-started/installation/)。访问 http://localhost:5300 即可使用。
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### 一键云部署
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**更多方式：** [Docker](https://docs.langbot.app/zh/deploy/langbot/docker.html) · [手动部署](https://docs.langbot.app/zh/deploy/langbot/manual.html) · [宝塔面板](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## 支持的平台
+
+| 平台 | 状态 | 备注 |
+|------|------|------|
+| QQ | ✅ | 个人号、官方机器人（频道、私聊、群聊） |
+| 微信 | ✅ | 个人微信、微信公众号 |
+| 企业微信 | ✅ | 应用消息、对外客服、智能机器人 |
+| 飞书 | ✅ |  |
+| 钉钉 | ✅ |  |
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| KOOK | ✅ |  |
+
+---
+
+## 支持的大模型与集成
+
+| 提供商 | 类型 | 状态 |
+|--------|------|------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [智谱AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | 本地 LLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | 本地 LLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | 协议 | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | 聚合平台 | ✅ |
+| [阿里云百炼](https://bailian.console.aliyun.com/) | 聚合平台 | ✅ |
+| [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | 聚合平台 | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | 聚合平台 | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | 聚合平台 | ✅ |
+| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPU 平台 | ✅ |
+| [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU 平台 | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 平台 | ✅ |
+| [接口 AI](https://jiekou.ai/) | 聚合平台 | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | 聚合平台 | ✅ |
+| [小马算力](https://www.tokenpony.cn/453z1) | 聚合平台 | ✅ |
+| [百宝箱Tbox](https://www.tbox.cn/open) | 智能体平台 | ✅ |
+
+[→ 查看完整集成列表](https://docs.langbot.app/zh/insight/features.html)
+
+### TTS（语音合成）
+
+| 平台/模型 | 备注 |
+|-----------|------|
+| [FishAudio](https://fish.audio/zh-CN/discovery/) | [插件](https://github.com/the-lazy-me/NewChatVoice) |
+| [海豚 AI](https://www.ttson.cn/?source=thelazy) | [插件](https://github.com/the-lazy-me/NewChatVoice) |
+| [AzureTTS](https://portal.azure.com/) | [插件](https://github.com/Ingnaryk/LangBot_AzureTTS) |
+
+### 文生图
+
+| 平台/模型 | 备注 |
+|-----------|------|
+| 阿里云百炼 | [插件](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin) |
+
+---
+
+## 为什么选择 LangBot？
+
+| 使用场景 | LangBot 如何帮助 |
+|----------|------------------|
+| **客户服务** | 将 AI Agent 部署到微信/企微/钉钉/飞书，基于知识库自动回答用户问题 |
+| **内部工具** | 将 n8n/Dify 工作流接入企微/钉钉，实现业务流程自动化 |
+| **社群运营** | 在 QQ/Discord 群中使用 AI 驱动的内容审核与智能互动 |
+| **多平台触达** | 一个机器人，覆盖所有平台。通过统一面板集中管理 |
+
+---
+
+## 在线演示
+
+**立即体验：** https://demo.langbot.dev/
+- 邮箱：`demo@langbot.app`
+- 密码：`langbot123456`
+
+*注意：公开演示环境，请不要在其中填入任何敏感信息。*
+
+---
+
+## 社区
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-1030838208-blue)](https://qm.qq.com/q/DxZZcNxM1W)
+
+- [Discord 社区](https://discord.gg/wdNEHETs87)
+- [QQ 社区群](https://qm.qq.com/q/DxZZcNxM1W)
+
+---
+
+## Star 趋势
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## 贡献者
+
+感谢所有[贡献者](https://github.com/langbot-app/LangBot/graphs/contributors)对 LangBot 的帮助：
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>
+
+<!--
+## For Code Agents
+
+If you're a code agent based on LLM, you should read [AGENTS.md](AGENTS.md) to understand the project structure and development process before you start any development.
+-->

README_EN.md

@@ -1,141 +0,0 @@
-<p align="center">
-<a href="https://langbot.app">
-<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
-</a>
-
-<div align="center">
-
-English / [简体中文](README.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)
-
-[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
-
-<a href="https://langbot.app">Home</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Deployment</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>
-
-</div>
-
-</p>
-
-LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.
-
-## 📦 Getting Started
-
-#### Quick Start
-
-Use `uvx` to start with one command (need to install [uv](https://docs.astral.sh/uv/getting-started/installation/)):
-
-```bash
-uvx langbot
-```
-
-Visit http://localhost:5300 to start using it.
-
-#### Docker Compose Deployment
-
-```bash
-git clone https://github.com/langbot-app/LangBot
-cd LangBot/docker
-docker compose up -d
-```
-
-Visit http://localhost:5300 to start using it.
-
-Detailed documentation [Docker Deployment](https://docs.langbot.app/en/deploy/langbot/docker.html).
-
-#### One-click Deployment on BTPanel
-
-LangBot has been listed on the BTPanel, if you have installed the BTPanel, you can use the [document](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) to use it.
-
-#### Zeabur Cloud Deployment
-
-Community contributed Zeabur template.
-
-[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Railway Cloud Deployment
-
-[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
-
-#### Other Deployment Methods
-
-Directly use the released version to run, see the [Manual Deployment](https://docs.langbot.app/en/deploy/langbot/manual.html) documentation.
-
-#### Kubernetes Deployment
-
-Refer to the [Kubernetes Deployment](./docker/README_K8S.md) documentation.
-
-## 😎 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)
-
-## ✨ Features
-
-- 💬 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.
-
-For more detailed specifications, please refer to the [documentation](https://docs.langbot.app/en/insight/features.html).
-
-Or visit the demo environment: https://demo.langbot.dev/
-  - Login information: Email: `demo@langbot.app` Password: `langbot123456`
-  - Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.
-
-### Message Platform
-
-| Platform | Status | Remarks |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| Personal QQ | ✅ |  |
-| QQ Official API | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| Personal WeChat | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
-
-### LLMs
-
-| LLM | Status | Remarks |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | Available for any OpenAI interface format model |
-| [DeepSeek](https://www.deepseek.com/) | ✅ |  |
-| [Moonshot](https://www.moonshot.cn/) | ✅ |  |
-| [Anthropic](https://www.anthropic.com/) | ✅ |  |
-| [xAI](https://x.ai/) | ✅ |  |
-| [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
-| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | LLM and GPU resource platform |
-| [Dify](https://dify.ai) | ✅ | LLMOps platform |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
-| [接口 AI](https://jiekou.ai/) | ✅ | LLM aggregation platform, dedicated to global LLMs |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM and GPU resource platform |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |
-| [LMStudio](https://lmstudio.ai/) | ✅ | Local LLM running platform |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | LLM interface gateway(MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | LLM gateway(MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | LLM gateway(MaaS), LLMOps platform |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | LLM gateway(MaaS), LLMOps platform |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | LLM gateway(MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | Support tool access through MCP protocol |
-
-## 🤝 Community Contribution
-
-Thank you for the following [code contributors](https://github.com/langbot-app/LangBot/graphs/contributors) and other members in the community for their contributions to LangBot:
-
-<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
-</a>

README_ES.md

@@ -0,0 +1,171 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
+</a>
+
+<div align="center">
+
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>Plataforma de grado de producción para construir bots de mensajería instantánea con agentes de IA.</h3>
+<h4>Construya, depure y despliegue bots de IA rápidamente en Slack, Discord, Telegram, WeChat y más.</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / Español / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+
+<a href="https://langbot.app">Inicio</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Características</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide.html">Documentación</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">Mercado de Plugins</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Hoja de Ruta</a>
+
+</div>
+
+</p>
+
+---
+
+## ¿Qué es LangBot?
+
+LangBot es una **plataforma de código abierto y grado de producción** para construir bots de mensajería instantánea impulsados por IA. Conecta modelos de lenguaje de gran escala (LLMs) con cualquier plataforma de chat, permitiéndole crear agentes inteligentes que pueden conversar, ejecutar tareas e integrarse con sus flujos de trabajo existentes.
+
+### Capacidades Clave
+
+- **Conversaciones e Agentes IA** — Diálogos de múltiples turnos, llamadas a herramientas, soporte multimodal, salida en streaming. RAG (base de conocimientos) incorporado con integración profunda con [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Soporte Universal de Plataformas de MI** — Un solo código base para Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
+- **Listo para Producción** — Control de acceso, limitación de velocidad, filtrado de palabras sensibles, monitoreo completo y manejo de excepciones. De confianza para empresas.
+- **Ecosistema de Plugins** — Cientos de plugins, arquitectura basada en eventos, extensiones de componentes y soporte del [protocolo MCP](https://modelcontextprotocol.io/).
+- **Panel de Gestión Web** — Configure, gestione y monitoree sus bots a través de una interfaz de navegador intuitiva. Sin necesidad de editar YAML.
+- **Arquitectura Multi-Pipeline** — Diferentes bots para diferentes escenarios, con monitoreo completo y manejo de excepciones.
+
+[→ Conocer más sobre todas las funcionalidades](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Inicio Rápido
+
+### ☁️ LangBot Cloud (Recomendado)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Sin despliegue, listo para usar.
+
+### Lanzamiento en una línea
+
+```bash
+uvx langbot
+```
+
+> Requiere [uv](https://docs.astral.sh/uv/getting-started/installation/). Visite http://localhost:5300 — listo.
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### Despliegue en la Nube con un Clic
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**Más opciones:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Manual](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## Plataformas Soportadas
+
+| Plataforma | Estado | Notas |
+|----------|--------|-------|
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| QQ | ✅ | Personal y API Oficial |
+| WeCom | ✅ | WeChat Empresarial, CS Externo, AI Bot |
+| WeChat | ✅ | Personal y Cuenta Oficial |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
+
+---
+
+## LLMs e Integraciones Soportadas
+
+| Proveedor | Tipo | Estado |
+|----------|------|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | LLM Local | ✅ |
+| [LM Studio](https://lmstudio.ai/) | LLM Local | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | Protocolo | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | Pasarela | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | Pasarela | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Pasarela | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Pasarela | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | Pasarela | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Plataforma GPU | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Plataforma GPU | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plataforma GPU | ✅ |
+| [接口 AI](https://jiekou.ai/) | Pasarela | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | Pasarela | ✅ |
+
+[→ Ver todas las integraciones](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## ¿Por qué LangBot?
+
+| Caso de Uso | Cómo Ayuda LangBot |
+|----------|-------------------|
+| **Atención al cliente** | Despliegue agentes de IA en Slack/Discord/Telegram que respondan preguntas usando su base de conocimientos |
+| **Herramientas internas** | Conecte flujos de trabajo de n8n/Dify a WeCom/DingTalk para procesos empresariales automatizados |
+| **Gestión de comunidades** | Modere grupos de QQ/Discord con filtrado de contenido e interacción impulsados por IA |
+| **Presencia multiplataforma** | Un solo bot, todas las plataformas. Gestione desde un único panel de control |
+
+---
+
+## Demo en Vivo
+
+**Pruébelo ahora:** https://demo.langbot.dev/
+- Correo electrónico: `demo@langbot.app`
+- Contraseña: `langbot123456`
+
+*Nota: Entorno de demostración público. No ingrese información confidencial.*
+
+---
+
+## Comunidad
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Comunidad de Discord](https://discord.gg/wdNEHETs87)
+
+---
+
+## Historial de Stars
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## Colaboradores
+
+Gracias a todos los [colaboradores](https://github.com/langbot-app/LangBot/graphs/contributors) que han ayudado a mejorar LangBot:
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>

README_FR.md

@@ -0,0 +1,171 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
+</a>
+
+<div align="center">
+
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>Plateforme de niveau production pour construire des bots de messagerie instantanée avec agents IA.</h3>
+<h4>Créez, déboguez et déployez rapidement des bots IA sur Slack, Discord, Telegram, WeChat et plus.</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / Français / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+
+<a href="https://langbot.app">Accueil</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Fonctionnalités</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide.html">Documentation</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">Marché des Plugins</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Feuille de Route</a>
+
+</div>
+
+</p>
+
+---
+
+## Qu'est-ce que LangBot ?
+
+LangBot est une **plateforme open-source de niveau production** pour créer des bots de messagerie instantanée alimentés par l'IA. Elle connecte les grands modèles de langage (LLMs) à n'importe quelle plateforme de chat, vous permettant de créer des agents intelligents capables de converser, d'exécuter des tâches et de s'intégrer à vos workflows existants.
+
+### Capacités Clés
+
+- **Conversations IA & Agents** — Dialogues multi-tours, appels d'outils, support multimodal, sortie en streaming. RAG (base de connaissances) intégré avec intégration profonde de [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Support Universel des Plateformes de MI** — Un seul code pour Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
+- **Prêt pour la Production** — Contrôle d'accès, limitation de débit, filtrage de mots sensibles, surveillance complète et gestion des exceptions. Approuvé par les entreprises.
+- **Écosystème de Plugins** — Des centaines de plugins, architecture événementielle, extensions de composants, et support du [protocole MCP](https://modelcontextprotocol.io/).
+- **Panneau de Gestion Web** — Configurez, gérez et surveillez vos bots via une interface navigateur intuitive. Aucune édition de YAML requise.
+- **Architecture Multi-Pipeline** — Différents bots pour différents scénarios, avec surveillance complète et gestion des exceptions.
+
+[→ En savoir plus sur toutes les fonctionnalités](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Démarrage Rapide
+
+### ☁️ LangBot Cloud (Recommandé)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Sans déploiement, prêt à utiliser.
+
+### Lancement en une ligne
+
+```bash
+uvx langbot
+```
+
+> Nécessite [uv](https://docs.astral.sh/uv/getting-started/installation/). Visitez http://localhost:5300 — c'est prêt.
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### Déploiement Cloud en un Clic
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**Plus d'options :** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Manuel](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## Plateformes Supportées
+
+| Plateforme | Statut | Notes |
+|----------|--------|-------|
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| QQ | ✅ | Personnel & API Officielle |
+| WeCom | ✅ | WeChat Entreprise, CS Externe, AI Bot |
+| WeChat | ✅ | Personnel & Compte Officiel |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
+
+---
+
+## LLMs et Intégrations Supportés
+
+| Fournisseur | Type | Statut |
+|----------|------|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | LLM Local | ✅ |
+| [LM Studio](https://lmstudio.ai/) | LLM Local | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | Protocole | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | Passerelle | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | Passerelle | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Passerelle | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Passerelle | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | Passerelle | ✅ |
+| [接口 AI](https://jiekou.ai/) | Passerelle | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | Passerelle | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Plateforme GPU | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Plateforme GPU | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plateforme GPU | ✅ |
+
+[→ Voir toutes les intégrations](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Pourquoi LangBot ?
+
+| Cas d'Usage | Comment LangBot Aide |
+|----------|-------------------|
+| **Support Client** | Déployez des agents IA sur Slack/Discord/Telegram qui répondent aux questions en utilisant votre base de connaissances |
+| **Outils Internes** | Connectez les workflows n8n/Dify à WeCom/DingTalk pour automatiser vos processus métier |
+| **Gestion de Communauté** | Modérez les groupes QQ/Discord avec un filtrage de contenu et des interactions alimentés par l'IA |
+| **Présence Multi-plateforme** | Un seul bot, toutes les plateformes. Gérez tout depuis un tableau de bord unique |
+
+---
+
+## Démo en Ligne
+
+**Essayez maintenant :** https://demo.langbot.dev/
+- Email : `demo@langbot.app`
+- Mot de passe : `langbot123456`
+
+*Note : Environnement de démonstration public. Ne saisissez pas d'informations sensibles.*
+
+---
+
+## Communauté
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Communauté Discord](https://discord.gg/wdNEHETs87)
+
+---
+
+## Historique des Stars
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## Contributeurs
+
+Merci à tous les [contributeurs](https://github.com/langbot-app/LangBot/graphs/contributors) qui ont aidé à améliorer LangBot :
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>

README_JP.md

@@ -1,41 +1,68 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social_en.png" alt="LangBot"/>
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
 </a>
 
 <div align="center">
 
-[English](README_EN.md) / [简体中文](README.md) / [繁體中文](README_TW.md) / 日本語 / (PR for your language)
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>AIエージェント搭載IMボットを構築するための本番グレードプラットフォーム。</h3>
+<h4>Slack、Discord、Telegram、WeChat などに AI ボットを素早く構築、デバッグ、デプロイ。</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / 日本語 / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
 
 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">ホーム</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">デプロイ</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">プラグイン</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>
+<a href="https://docs.langbot.app/ja/insight/features.html">機能</a> ｜
+<a href="https://docs.langbot.app/ja/insight/guide.html">ドキュメント</a> ｜
+<a href="https://docs.langbot.app/ja/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">プラグインマーケット</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">ロードマップ</a>
 
 </div>
 
 </p>
 
-LangBot は、エージェント、RAG、MCP などの LLM アプリケーション機能を備えた、オープンソースの LLM ネイティブのインスタントメッセージングロボット開発プラットフォームです。世界中のインスタントメッセージングプラットフォームに適応し、豊富な API インターフェースを提供し、カスタム開発をサポートします。
+---
 
-## 📦 始め方
+## LangBot とは？
 
-#### クイックスタート
+LangBot は、AI搭載のインスタントメッセージングボットを構築するための**オープンソースの本番グレードプラットフォーム**です。大規模言語モデル（LLM）をあらゆるチャットプラットフォームに接続し、会話、タスク実行、既存のワークフローとの統合が可能なインテリジェントエージェントを作成できます。
 
-`uvx` を使用した迅速なデプロイ（[uv](https://docs.astral.sh/uv/getting-started/installation/) が必要です）：
+### 主な機能
+
+- **AI対話とエージェント** — マルチターン対話、ツール呼び出し、マルチモーダル対応、ストリーミング出力。RAG（ナレッジベース）を内蔵し、[Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) と深く統合。
+- **ユニバーサルIMプラットフォーム対応** — 単一のコードベースで Discord、Telegram、Slack、LINE、QQ、WeChat、WeCom、Lark、DingTalk、KOOK に対応。
+- **本番環境対応** — アクセス制御、レート制限、センシティブワードフィルタリング、包括的な監視、例外処理を搭載。エンタープライズの信頼に応える品質。
+- **プラグインエコシステム** — 数百のプラグイン、イベント駆動アーキテクチャ、コンポーネント拡張、[MCPプロトコル](https://modelcontextprotocol.io/)対応。
+- **Web管理パネル** — 直感的なブラウザインターフェースからボットの設定、管理、監視が可能。YAML編集は不要。
+- **マルチパイプラインアーキテクチャ** — 異なるシナリオに異なるボットを配置し、包括的な監視と例外処理を実現。
+
+[→ すべての機能について詳しく見る](https://docs.langbot.app/ja/insight/features.html)
+
+---
+
+## クイックスタート
+
+### ☁️ LangBot Cloud（推奨）
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — デプロイ不要、すぐに使えます。
+
+### ワンライン起動
 
 ```bash
 uvx langbot
 ```
 
-http://localhost:5300 にアクセスして使用を開始します。
+> [uv](https://docs.astral.sh/uv/getting-started/installation/) が必要です。http://localhost:5300 にアクセスして完了。
 
-#### Docker Compose デプロイ
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -43,98 +70,101 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-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。
-
-#### 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。
-
-#### Zeaburクラウドデプロイ
-
-コミュニティが提供するZeaburテンプレート。
+### ワンクリッククラウドデプロイ
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Railwayクラウドデプロイ
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### その他のデプロイ方法
+**その他:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [手動デプロイ](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
 
-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。
+---
 
-#### Kubernetes デプロイ
-
-[Kubernetes デプロイ](./docker/README_K8S.md) ドキュメントを参照してください。
-
-## 😎 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)
-
-## ✨ 機能
-
-- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル、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。
-
-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。
-
-または、デモ環境にアクセスしてください: https://demo.langbot.dev/
-  - ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
-  - 注意: WebUI のデモンストレーションのみの場合、公開環境では機密情報を入力しないでください。
-
-### メッセージプラットフォーム
+## 対応プラットフォーム
 
 | プラットフォーム | ステータス | 備考 |
-| --- | --- | --- |
+|----------|--------|-------|
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
 | LINE | ✅ |  |
-| 個人QQ | ✅ |  |
-| QQ公式API | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| 個人WeChat | ✅ | |
+| QQ | ✅ | 個人 & 公式API |
+| WeCom | ✅ | 企業WeChat、外部CS、AIボット |
+| WeChat | ✅ | 個人 & 公式アカウント |
 | Lark | ✅ |  |
 | DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
 
-### LLMs
+---
 
-| LLM | ステータス | 備考 |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | 任意のOpenAIインターフェース形式モデルに対応 |
-| [DeepSeek](https://www.deepseek.com/) | ✅ |  |
-| [Moonshot](https://www.moonshot.cn/) | ✅ |  |
-| [Anthropic](https://www.anthropic.com/) | ✅ |  |
-| [xAI](https://x.ai/) | ✅ |  |
-| [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
-| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
-| [接口 AI](https://jiekou.ai/) | ✅ | LLMゲートウェイ(MaaS) |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLMとGPUリソースプラットフォーム |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |
-| [Ollama](https://ollama.com/) | ✅ | ローカルLLM実行プラットフォーム |
-| [LMStudio](https://lmstudio.ai/) | ✅ | ローカルLLM実行プラットフォーム |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | LLMインターフェースゲートウェイ(MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | LLMゲートウェイ(MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | LLMゲートウェイ(MaaS), LLMOpsプラットフォーム |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | LLMゲートウェイ(MaaS), LLMOpsプラットフォーム |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | LLMゲートウェイ(MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | MCPプロトコルをサポート |
+## 対応LLMと統合
 
-## 🤝 コミュニティ貢献
+| プロバイダー | タイプ | ステータス |
+|----------|------|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | ローカルLLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | ローカルLLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | プロトコル | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | ゲートウェイ | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ゲートウェイ | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ゲートウェイ | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ゲートウェイ | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | ゲートウェイ | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPUプラットフォーム | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPUプラットフォーム | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPUプラットフォーム | ✅ |
+| [接口 AI](https://jiekou.ai/) | ゲートウェイ | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | ゲートウェイ | ✅ |
 
-LangBot への貢献に対して、以下の [コード貢献者](https://github.com/langbot-app/LangBot/graphs/contributors) とコミュニティの他のメンバーに感謝します。
+[→ すべての統合を表示](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## なぜ LangBot？
+
+| ユースケース | LangBot の活用方法 |
+|----------|-------------------|
+| **カスタマーサポート** | ナレッジベースを活用して質問に回答するAIエージェントをSlack/Discord/Telegramにデプロイ |
+| **社内ツール** | n8n/Difyのワークフローを WeCom/DingTalk に接続し、業務プロセスを自動化 |
+| **コミュニティ管理** | AI搭載のコンテンツフィルタリングとインタラクションでQQ/Discordグループをモデレーション |
+| **マルチプラットフォーム展開** | 1つのボットで全プラットフォームに対応。単一のダッシュボードから管理 |
+
+---
+
+## ライブデモ
+
+**今すぐ試す:** https://demo.langbot.dev/
+- メール: `demo@langbot.app`
+- パスワード: `langbot123456`
+
+*注意: 公開デモ環境です。機密情報を入力しないでください。*
+
+---
+
+## コミュニティ
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Discord コミュニティ](https://discord.gg/wdNEHETs87)
+
+---
+
+## Star 推移
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## コントリビューター
+
+LangBot をより良くするために貢献してくださったすべての[コントリビューター](https://github.com/langbot-app/LangBot/graphs/contributors)に感謝します:
 
 <a href="https://github.com/langbot-app/LangBot/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />

README_KO.md

@@ -0,0 +1,171 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
+</a>
+
+<div align="center">
+
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>AI 에이전트 IM 봇 구축을 위한 프로덕션 등급 플랫폼.</h3>
+<h4>Slack, Discord, Telegram, WeChat 등에 AI 봇을 빠르게 구축, 디버그 및 배포.</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / 한국어 / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+
+<a href="https://langbot.app">홈</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">기능</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide.html">문서</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">플러그인 마켓</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">로드맵</a>
+
+</div>
+
+</p>
+
+---
+
+## LangBot이란?
+
+LangBot은 AI 기반 인스턴트 메시징 봇을 구축하기 위한 **오픈소스 프로덕션 등급 플랫폼**입니다. 대규모 언어 모델(LLM)을 모든 채팅 플랫폼에 연결하여 대화, 작업 실행, 기존 워크플로우와의 통합이 가능한 지능형 에이전트를 만들 수 있습니다.
+
+### 핵심 기능
+
+- **AI 대화 및 에이전트** — 멀티턴 대화, 도구 호출, 멀티모달 지원, 스트리밍 출력. 내장 RAG(지식 베이스)와 [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) 심층 통합.
+- **유니버설 IM 플랫폼 지원** — 단일 코드베이스로 Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK 지원.
+- **프로덕션 레디** — 접근 제어, 속도 제한, 민감어 필터링, 종합 모니터링 및 예외 처리. 기업 환경에서 검증됨.
+- **플러그인 생태계** — 수백 개의 플러그인, 이벤트 기반 아키텍처, 컴포넌트 확장, [MCP 프로토콜](https://modelcontextprotocol.io/) 지원.
+- **웹 관리 패널** — 직관적인 브라우저 인터페이스로 봇을 구성, 관리 및 모니터링. YAML 편집 불필요.
+- **멀티 파이프라인 아키텍처** — 다양한 시나리오에 맞는 다양한 봇 구성, 종합 모니터링 및 예외 처리.
+
+[→ 모든 기능 자세히 보기](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## 빠른 시작
+
+### ☁️ LangBot Cloud (추천)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — 배포 없이 바로 사용.
+
+### 원라인 실행
+
+```bash
+uvx langbot
+```
+
+> [uv](https://docs.astral.sh/uv/getting-started/installation/) 설치 필요. http://localhost:5300 방문 — 완료.
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### 원클릭 클라우드 배포
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**더 많은 옵션:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [수동 배포](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## 지원 플랫폼
+
+| 플랫폼 | 상태 | 비고 |
+|--------|------|------|
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| QQ | ✅ | 개인 및 공식 API |
+| WeCom | ✅ | 기업 WeChat, 외부 CS, AI Bot |
+| WeChat | ✅ | 개인 및 공식 계정 |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
+
+---
+
+## 지원 LLM 및 통합
+
+| 제공자 | 유형 | 상태 |
+|--------|------|------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | 로컬 LLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | 로컬 LLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | 프로토콜 | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | 게이트웨이 | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | 게이트웨이 | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | 게이트웨이 | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | 게이트웨이 | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | 게이트웨이 | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU 플랫폼 | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 플랫폼 | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPU 플랫폼 | ✅ |
+| [接口 AI](https://jiekou.ai/) | 게이트웨이 | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | 게이트웨이 | ✅ |
+
+[→ 모든 통합 보기](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## 왜 LangBot인가?
+
+| 사용 사례 | LangBot 활용 방법 |
+|-----------|-------------------|
+| **고객 지원** | 지식 베이스를 활용하여 질문에 답변하는 AI 에이전트를 Slack/Discord/Telegram에 배포 |
+| **내부 도구** | n8n/Dify 워크플로우를 WeCom/DingTalk에 연결하여 비즈니스 프로세스 자동화 |
+| **커뮤니티 관리** | AI 기반 콘텐츠 필터링 및 상호작용으로 QQ/Discord 그룹 관리 |
+| **멀티 플랫폼** | 하나의 봇으로 모든 플랫폼 지원. 단일 대시보드에서 관리 |
+
+---
+
+## 라이브 데모
+
+**지금 체험:** https://demo.langbot.dev/
+- 이메일: `demo@langbot.app`
+- 비밀번호: `langbot123456`
+
+*참고: 공개 데모 환경입니다. 민감한 정보를 입력하지 마세요.*
+
+---
+
+## 커뮤니티
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Discord 커뮤니티](https://discord.gg/wdNEHETs87)
+
+---
+
+## Star 추이
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## 기여자
+
+LangBot을 더 나은 프로젝트로 만들어 주신 모든 [기여자](https://github.com/langbot-app/LangBot/graphs/contributors)분들께 감사드립니다:
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>

README_RU.md

@@ -0,0 +1,171 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
+</a>
+
+<div align="center">
+
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>Платформа производственного уровня для создания агентных IM-ботов.</h3>
+<h4>Быстро создавайте, отлаживайте и развертывайте ИИ-ботов в Slack, Discord, Telegram, WeChat и других платформах.</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / Русский / [Tiếng Việt](README_VI.md)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+
+<a href="https://langbot.app">Главная</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Возможности</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide.html">Документация</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">Магазин плагинов</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Дорожная карта</a>
+
+</div>
+
+</p>
+
+---
+
+## Что такое LangBot?
+
+LangBot — это **платформа с открытым исходным кодом производственного уровня** для создания ИИ-ботов в мессенджерах. Она связывает большие языковые модели (LLM) с любой чат-платформой, позволяя создавать интеллектуальных агентов, которые могут вести диалоги, выполнять задачи и интегрироваться с вашими существующими рабочими процессами.
+
+### Ключевые возможности
+
+- **ИИ-диалоги и агенты** — Многораундовые диалоги, вызов инструментов, мультимодальная поддержка, потоковый вывод. Встроенная реализация RAG (база знаний) с глубокой интеграцией в [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Универсальная поддержка IM-платформ** — Единая кодовая база для Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
+- **Готовность к продакшену** — Контроль доступа, ограничение скорости, фильтрация чувствительных слов, комплексный мониторинг и обработка исключений. Проверено в корпоративной среде.
+- **Экосистема плагинов** — Сотни плагинов, событийно-ориентированная архитектура, расширения компонентов и поддержка [протокола MCP](https://modelcontextprotocol.io/).
+- **Веб-панель управления** — Настраивайте, управляйте и мониторьте ваших ботов через интуитивный браузерный интерфейс. Ручное редактирование YAML не требуется.
+- **Мультиконвейерная архитектура** — Разные боты для разных сценариев с комплексным мониторингом и обработкой исключений.
+
+[→ Подробнее обо всех возможностях](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Быстрый старт
+
+### ☁️ LangBot Cloud (Рекомендуется)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Без развёртывания, готово к использованию.
+
+### Запуск одной командой
+
+```bash
+uvx langbot
+```
+
+> Требуется [uv](https://docs.astral.sh/uv/getting-started/installation/). Откройте http://localhost:5300 — готово.
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### Облачное развертывание одним кликом
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**Другие варианты:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Ручная установка](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## Поддерживаемые платформы
+
+| Платформа | Статус | Примечания |
+|-----------|--------|------------|
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| QQ | ✅ | Личный и официальный API |
+| WeCom | ✅ | Корпоративный WeChat, внешний CS, AI-бот |
+| WeChat | ✅ | Личный и официальный аккаунт |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
+
+---
+
+## Поддерживаемые LLM и интеграции
+
+| Провайдер | Тип | Статус |
+|-----------|-----|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | Локальный LLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | Локальный LLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | Протокол | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | Шлюз | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | Шлюз | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Шлюз | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Шлюз | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | Шлюз | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | Шлюз | ✅ |
+| [接口 AI](https://jiekou.ai/) | Шлюз | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Платформа GPU | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Платформа GPU | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Платформа GPU | ✅ |
+
+[→ Смотреть все интеграции](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Почему LangBot?
+
+| Сценарий использования | Как помогает LangBot |
+|------------------------|----------------------|
+| **Поддержка клиентов** | Разверните ИИ-агентов в Slack/Discord/Telegram, которые отвечают на вопросы, используя вашу базу знаний |
+| **Внутренние инструменты** | Подключите рабочие процессы n8n/Dify к WeCom/DingTalk для автоматизации бизнес-процессов |
+| **Управление сообществом** | Модерируйте группы QQ/Discord с помощью ИИ-фильтрации контента и взаимодействия |
+| **Мультиплатформенное присутствие** | Один бот — все платформы. Управляйте из единой панели |
+
+---
+
+## Демо
+
+**Попробуйте прямо сейчас:** https://demo.langbot.dev/
+- Email: `demo@langbot.app`
+- Пароль: `langbot123456`
+
+*Примечание: Публичная демо-среда. Не вводите конфиденциальную информацию.*
+
+---
+
+## Сообщество
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Сообщество Discord](https://discord.gg/wdNEHETs87)
+
+---
+
+## История Stars
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## Участники
+
+Спасибо всем [участникам](https://github.com/langbot-app/LangBot/graphs/contributors), которые помогли сделать LangBot лучше:
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>

README_TW.md

@@ -1,43 +1,70 @@
 <p align="center">
 <a href="https://langbot.app">
-<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
+<img width="130" src="res/logo-blue.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>
+<div align="center">
 
-[English](README_EN.md) / [简体中文](README.md) / 繁體中文 / [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>
+
+<h3>生產級 AI 即時通訊機器人開發平台。</h3>
+<h4>快速建構、除錯和部署 AI 機器人到微信、QQ、飛書、Slack、Discord、Telegram 等平台。</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / 繁體中文 / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
 
 [![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">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 [![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>
+<a href="https://langbot.app">官網</a> ｜
+<a href="https://docs.langbot.app/zh/insight/features.html">特性</a> ｜
+<a href="https://docs.langbot.app/zh/insight/guide.html">文件</a> ｜
+<a href="https://docs.langbot.app/zh/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">外掛市場</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">路線圖</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
+## 什麼是 LangBot？
 
-#### 快速部署
+LangBot 是一個**開源的生產級平台**，用於建構 AI 驅動的即時通訊機器人。它將大語言模型（LLM）連接到各種聊天平台，幫助你創建能夠對話、執行任務、並整合到現有工作流程中的智能 Agent。
 
-使用 `uvx` 一鍵啟動（需要先安裝 [uv](https://docs.astral.sh/uv/getting-started/installation/) ）：
+### 核心能力
+
+- **AI 對話與 Agent** — 多輪對話、工具調用、多模態、流式輸出。自帶 RAG（知識庫），深度整合 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) 等 LLMOps 平台。
+- **全平台支援** — 一套程式碼，覆蓋 QQ、微信、企業微信、飛書、釘釘、Discord、Telegram、Slack、LINE、KOOK 等平台。
+- **生產就緒** — 存取控制、限速、敏感詞過濾、全面監控與異常處理，已被多家企業採用。
+- **外掛生態** — 數百個外掛，事件驅動架構，組件擴展，適配 [MCP 協議](https://modelcontextprotocol.io/)。
+- **Web 管理面板** — 透過瀏覽器直觀地配置、管理和監控機器人，無需手動編輯設定檔。
+- **多流水線架構** — 不同機器人用於不同場景，具備全面的監控和異常處理能力。
+
+[→ 了解更多功能特性](https://docs.langbot.app/zh/insight/features.html)
+
+---
+
+## 快速開始
+
+### ☁️ LangBot Cloud（推薦）
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — 免部署，開箱即用。
+
+### 一鍵啟動
 
 ```bash
 uvx langbot
 ```
 
-訪問 http://localhost:5300 即可開始使用。
+> 需要安裝 [uv](https://docs.astral.sh/uv/getting-started/installation/)。訪問 http://localhost:5300 即可使用。
 
-#### Docker Compose 部署
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -45,99 +72,63 @@ cd LangBot/docker
 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。
+### 一鍵雲端部署
 
 [![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
+**更多方式：** [Docker](https://docs.langbot.app/zh/deploy/langbot/docker.html) · [手動部署](https://docs.langbot.app/zh/deploy/langbot/manual.html) · [寶塔面板](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
 
-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)。
+---
 
-#### Kubernetes 部署
-
-參考 [Kubernetes 部署](./docker/README_K8S.md) 文件。
-
-## 😎 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
+## 支援的平台
 
 | 平台 | 狀態 | 備註 |
-| --- | --- | --- |
+|------|------|------|
+| QQ | ✅ | 個人號、官方機器人（頻道、私聊、群聊） |
+| 微信 | ✅ | 個人微信、微信公眾號 |
+| 企業微信 | ✅ | 應用訊息、對外客服、智能機器人 |
+| 飛書 | ✅ |  |
+| 釘釘 | ✅ |  |
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
 | Slack | ✅ |  |
 | LINE | ✅ |  |
-| 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 | ✅ |  |
-| 企微智能機器人 | ✅ |  |
-| 微信公眾號 | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
 
-### 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 |
-| [接口 AI](https://jiekou.ai/) | ✅ | 大模型聚合平台，專注全球大模型接入 |
-| [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 |
+## 支援的大模型與整合
 
-### TTS
+| 提供商 | 類型 | 狀態 |
+|--------|------|------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [智譜AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | 本地 LLM | ✅ |
+| [LM Studio](https://lmstudio.ai/) | 本地 LLM | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | 協議 | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | 聚合平台 | ✅ |
+| [阿里雲百煉](https://bailian.console.aliyun.com/) | 聚合平台 | ✅ |
+| [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | 聚合平台 | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | 聚合平台 | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | 聚合平台 | ✅ |
+| [勝算雲](https://www.shengsuanyun.com/?from=CH_KYIPP758) | GPU 平台 | ✅ |
+| [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | GPU 平台 | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | GPU 平台 | ✅ |
+| [接口 AI](https://jiekou.ai/) | 聚合平台 | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | 聚合平台 | ✅ |
+
+### TTS（語音合成）
 
 | 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) |
@@ -145,13 +136,54 @@ docker compose up -d
 ### 文生圖
 
 | 平台/模型 | 備註 |
-| --- | --- |
-| 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
+|-----------|------|
+| 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin) |
 
-## 😘 社群貢獻
+[→ 查看完整整合列表](https://docs.langbot.app/zh/insight/features.html)
 
-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：
+---
+
+## 為什麼選擇 LangBot？
+
+| 使用場景 | LangBot 如何幫助 |
+|----------|------------------|
+| **客戶服務** | 將 AI Agent 部署到微信/企微/釘釘/飛書，基於知識庫自動回答使用者問題 |
+| **內部工具** | 將 n8n/Dify 工作流接入企微/釘釘，實現業務流程自動化 |
+| **社群運營** | 在 QQ/Discord 群中使用 AI 驅動的內容審核與智能互動 |
+| **多平台觸達** | 一個機器人，覆蓋所有平台。透過統一面板集中管理 |
+
+---
+
+## 線上演示
+
+**立即體驗：** https://demo.langbot.dev/
+- 信箱：`demo@langbot.app`
+- 密碼：`langbot123456`
+
+*注意：公開演示環境，請不要在其中填入任何敏感資訊。*
+
+---
+
+## 社群
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](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)
+
+- [Discord 社群](https://discord.gg/wdNEHETs87)
+- [QQ 社群群](https://qm.qq.com/q/JLi38whHum)
+
+---
+
+## Star 趨勢
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## 貢獻者
+
+感謝所有[貢獻者](https://github.com/langbot-app/LangBot/graphs/contributors)對 LangBot 的幫助：
 
 <a href="https://github.com/langbot-app/LangBot/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
-</a> 
+</a>

README_VI.md

@@ -0,0 +1,171 @@
+<p align="center">
+<a href="https://langbot.app">
+<img width="130" src="res/logo-blue.png" alt="LangBot"/>
+</a>
+
+<div align="center">
+
+<a href="https://www.producthunt.com/products/langbot?utm_source=badge-follow&utm_medium=badge&utm_source=badge-langbot" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/follow.svg?product_id=1077185&theme=light" alt="LangBot - Production&#0045;grade&#0032;IM&#0032;bot&#0032;made&#0032;easy&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+<h3>Nền tảng cấp sản xuất để xây dựng bot IM với AI agent.</h3>
+<h4>Xây dựng, gỡ lỗi và triển khai bot AI nhanh chóng trên Slack, Discord, Telegram, WeChat và nhiều nền tảng khác.</h4>
+
+[English](README.md) / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / Tiếng Việt
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
+
+<a href="https://langbot.app">Trang chủ</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Tính năng</a> ｜
+<a href="https://docs.langbot.app/en/insight/guide.html">Tài liệu</a> ｜
+<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://space.langbot.app">Chợ Plugin</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Lộ trình</a>
+
+</div>
+
+</p>
+
+---
+
+## LangBot là gì?
+
+LangBot là một **nền tảng mã nguồn mở, cấp sản xuất** để xây dựng bot nhắn tin tức thời được hỗ trợ bởi AI. Nó kết nối các Mô hình Ngôn ngữ Lớn (LLM) với bất kỳ nền tảng chat nào, cho phép bạn tạo các agent thông minh có thể trò chuyện, thực hiện tác vụ và tích hợp với quy trình làm việc hiện có của bạn.
+
+### Khả năng chính
+
+- **Hội thoại AI & Agent** — Đối thoại nhiều lượt, gọi công cụ, hỗ trợ đa phương thức, đầu ra streaming. RAG (cơ sở kiến thức) tích hợp sẵn với tích hợp sâu vào [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Hỗ trợ đa nền tảng IM** — Một mã nguồn cho Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
+- **Sẵn sàng cho sản xuất** — Kiểm soát truy cập, giới hạn tốc độ, lọc từ nhạy cảm, giám sát toàn diện và xử lý ngoại lệ. Được doanh nghiệp tin dùng.
+- **Hệ sinh thái Plugin** — Hàng trăm plugin, kiến trúc hướng sự kiện, mở rộng thành phần, và hỗ trợ [giao thức MCP](https://modelcontextprotocol.io/).
+- **Bảng quản lý Web** — Cấu hình, quản lý và giám sát bot thông qua giao diện trình duyệt trực quan. Không cần chỉnh sửa YAML.
+- **Kiến trúc đa Pipeline** — Các bot khác nhau cho các kịch bản khác nhau, với giám sát toàn diện và xử lý ngoại lệ.
+
+[→ Tìm hiểu thêm về tất cả tính năng](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Bắt đầu nhanh
+
+### ☁️ LangBot Cloud (Khuyên dùng)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Không cần triển khai, sẵn sàng sử dụng.
+
+### Khởi chạy một dòng
+
+```bash
+uvx langbot
+```
+
+> Yêu cầu [uv](https://docs.astral.sh/uv/getting-started/installation/). Truy cập http://localhost:5300 — xong.
+
+### Docker Compose
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot/docker
+docker compose up -d
+```
+
+### Triển khai đám mây một cú nhấp
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+**Thêm tùy chọn:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Thủ công](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+
+---
+
+## Nền tảng được hỗ trợ
+
+| Nền tảng | Trạng thái | Ghi chú |
+|----------|--------|-------|
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+| LINE | ✅ |  |
+| QQ | ✅ | Cá nhân & API chính thức |
+| WeCom | ✅ | WeChat doanh nghiệp, CS bên ngoài, AI Bot |
+| WeChat | ✅ | Cá nhân & Tài khoản công khai |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| KOOK | ✅ |  |
+| Satori | ✅ |  |
+
+---
+
+## LLM và tích hợp được hỗ trợ
+
+| Nhà cung cấp | Loại | Trạng thái |
+|----------|------|--------|
+| [OpenAI](https://platform.openai.com/) | LLM | ✅ |
+| [Anthropic](https://www.anthropic.com/) | LLM | ✅ |
+| [DeepSeek](https://www.deepseek.com/) | LLM | ✅ |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | LLM | ✅ |
+| [xAI](https://x.ai/) | LLM | ✅ |
+| [Moonshot](https://www.moonshot.cn/) | LLM | ✅ |
+| [Zhipu AI](https://open.bigmodel.cn/) | LLM | ✅ |
+| [Ollama](https://ollama.com/) | LLM cục bộ | ✅ |
+| [LM Studio](https://lmstudio.ai/) | LLM cục bộ | ✅ |
+| [Dify](https://dify.ai) | LLMOps | ✅ |
+| [MCP](https://modelcontextprotocol.io/) | Giao thức | ✅ |
+| [SiliconFlow](https://siliconflow.cn/) | Cổng | ✅ |
+| [Aliyun Bailian](https://bailian.console.aliyun.com/) | Cổng | ✅ |
+| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | Cổng | ✅ |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | Cổng | ✅ |
+| [GiteeAI](https://ai.gitee.com/) | Cổng | ✅ |
+| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | Nền tảng GPU | ✅ |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Nền tảng GPU | ✅ |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Nền tảng GPU | ✅ |
+| [接口 AI](https://jiekou.ai/) | Cổng | ✅ |
+| [302.AI](https://share.302.ai/SuTG99) | Cổng | ✅ |
+
+[→ Xem tất cả tích hợp](https://docs.langbot.app/en/insight/features.html)
+
+---
+
+## Tại sao chọn LangBot?
+
+| Trường hợp sử dụng | LangBot giúp như thế nào |
+|----------|-------------------|
+| **Hỗ trợ khách hàng** | Triển khai agent AI trên Slack/Discord/Telegram để trả lời câu hỏi bằng cơ sở kiến thức của bạn |
+| **Công cụ nội bộ** | Kết nối quy trình n8n/Dify với WeCom/DingTalk để tự động hóa quy trình kinh doanh |
+| **Quản lý cộng đồng** | Quản lý nhóm QQ/Discord với tính năng lọc nội dung và tương tác được hỗ trợ bởi AI |
+| **Đa nền tảng** | Một bot, tất cả nền tảng. Quản lý từ một bảng điều khiển duy nhất |
+
+---
+
+## Demo trực tuyến
+
+**Thử ngay:** https://demo.langbot.dev/
+- Email: `demo@langbot.app`
+- Mật khẩu: `langbot123456`
+
+*Lưu ý: Môi trường demo công khai. Không nhập thông tin nhạy cảm.*
+
+---
+
+## Cộng đồng
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
+
+- [Cộng đồng Discord](https://discord.gg/wdNEHETs87)
+
+---
+
+## Lịch sử Star
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langbot-app/LangBot&type=Date)](https://star-history.com/#langbot-app/LangBot&Date)
+
+---
+
+## Người đóng góp
+
+Cảm ơn tất cả [người đóng góp](https://github.com/langbot-app/LangBot/graphs/contributors) đã giúp LangBot trở nên tốt hơn:
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a>

docker/docker-compose.yaml

@@ -7,7 +7,6 @@ services:
   langbot_plugin_runtime:
     image: rockchin/langbot:latest
     container_name: langbot_plugin_runtime
-    platform: linux/amd64 # For Apple Silicon compatibility
     volumes:
       - ./data/plugins:/app/data/plugins
     ports:
@@ -15,23 +14,21 @@ services:
     restart: on-failure
     environment:
       - TZ=Asia/Shanghai
-    command: ["uv", "run", "-m", "langbot_plugin.cli.__init__", "rt"]
+    command: ["uv", "run", "--no-sync", "-m", "langbot_plugin.cli.__init__", "rt"]
     networks:
       - langbot_network
 
   langbot:
     image: rockchin/langbot:latest
     container_name: langbot
-    platform: linux/amd64 # For Apple Silicon compatibility
     volumes:
       - ./data:/app/data
-      - ./plugins:/app/plugins
     restart: on-failure
     environment:
       - TZ=Asia/Shanghai
     ports:
-      - 5300:5300  # For web ui
-      - 2280-2290:2280-2290  # For platform webhook
+      - 5300:5300  # For web ui and webhook callback
+      - 2280-2285:2280-2285  # For platform reverse connection
     networks:
       - langbot_network
 

docs/MIGRATION_SUMMARY.md

@@ -0,0 +1,412 @@
+# WebChat 到 WebSocket 迁移总结
+
+## 概述
+
+已完全移除旧的基于SSE的WebChat系统，并替换为基于WebSocket的双向实时通信系统。这是一个内置在LangBot中的完整IM系统，支持流式输出。
+
+## 已删除的文件
+
+### 后端
+- ❌ `src/langbot/pkg/api/http/controller/groups/pipelines/webchat.py` - 旧的SSE路由
+- ❌ `src/langbot/pkg/platform/sources/webchat.py` - 旧的WebChat适配器
+- ❌ `src/langbot/pkg/platform/sources/webchat.yaml` - 旧的配置文件
+
+### 前端
+- ❌ BackendClient中所有SSE相关代码已完全移除
+- ❌ DebugDialog中所有SSE相关逻辑已完全替换
+
+## 新增的文件
+
+### 后端核心文件
+
+**1. WebSocket连接管理器**
+```
+src/langbot/pkg/platform/sources/websocket_manager.py
+```
+- 管理所有并发WebSocket连接
+- 线程安全的连接池
+- 按流水线、会话类型分组
+- 广播和单播消息功能
+- 连接统计和监控
+
+**2. WebSocket适配器**
+```
+src/langbot/pkg/platform/sources/websocket_adapter.py
+```
+- 实现平台适配器接口
+- **完整流式支持** (`reply_message_chunk` 方法)
+- 双向消息流处理
+- 消息历史管理
+- 会话管理
+
+**3. WebSocket路由控制器**
+```
+src/langbot/pkg/api/http/controller/groups/pipelines/websocket_chat.py
+```
+- WebSocket端点处理
+- REST API接口
+- 心跳机制
+- 连接生命周期管理
+
+**4. 配置文件**
+```
+src/langbot/pkg/platform/sources/websocket.yaml
+```
+- WebSocket适配器元数据
+
+### 前端核心文件
+
+**1. WebSocket客户端**
+```
+web/src/app/infra/websocket/WebSocketClient.ts
+```
+- WebSocket连接管理
+- 自动重连（最多5次）
+- 心跳机制（30秒）
+- 事件回调系统
+
+**2. 更新的组件**
+```
+web/src/app/home/pipelines/components/debug-dialog/DebugDialog.tsx
+```
+- 完全重写，使用WebSocket
+- 实时连接状态显示
+- 流式消息支持
+- 自动重连
+
+**3. HTTP客户端更新**
+```
+web/src/app/infra/http/BackendClient.ts
+```
+- 移除所有旧的WebChat API
+- 仅保留WebSocket API
+
+### 测试工具
+
+**Python测试客户端**
+```
+test_websocket_client.py
+```
+- 单连接交互测试
+- 多连接并发测试
+- 命令行工具
+
+### 文档
+
+**使用文档**
+```
+WEBSOCKET_README.md
+```
+- 完整的API文档
+- 架构说明
+- 使用示例
+- 故障排查
+
+## 核心变更
+
+### 后端变更
+
+**1. botmgr.py**
+- ❌ 移除 `webchat_proxy_bot`
+- ✅ 仅保留 `websocket_proxy_bot`
+- ✅ 更新适配器过滤逻辑（排除`websocket`而非`webchat`）
+
+**2. 适配器注册**
+```python
+# 旧代码（已删除）
+webchat_adapter_class = self.adapter_dict['webchat']
+self.webchat_proxy_bot = RuntimeBot(...)
+
+# 新代码
+websocket_adapter_class = self.adapter_dict['websocket']
+self.websocket_proxy_bot = RuntimeBot(
+    uuid='websocket-proxy-bot',
+    name='WebSocket',
+    adapter='websocket',
+    ...
+)
+```
+
+### 前端变更
+
+**1. API调用完全更换**
+
+旧代码（已删除）:
+```typescript
+// SSE流式请求
+await fetch(url, {
+  method: 'POST',
+  body: JSON.stringify({ is_stream: true })
+})
+// 手动解析 text/event-stream
+```
+
+新代码:
+```typescript
+// WebSocket实时通信
+const wsClient = new WebSocketClient(pipelineId, sessionType);
+await wsClient.connect();
+
+wsClient.onMessage((message) => {
+  // 流式消息自动处理
+  setMessages(prev => [...prev, message]);
+});
+
+wsClient.sendMessage(messageChain);
+```
+
+**2. 连接状态管理**
+
+新增功能:
+- ✅ 实时连接状态指示器（绿色/红色圆点）
+- ✅ 连接/断开toast提示
+- ✅ 自动重连逻辑
+- ✅ 心跳保活
+
+**3. 流式支持**
+
+完整的流式消息处理:
+```typescript
+wsClient.onMessage((message) => {
+  if (message.is_final) {
+    // 最终消息
+    finalizeBotMessage(message);
+  } else {
+    // 中间消息块，实时更新UI
+    updateBotMessage(message);
+  }
+});
+```
+
+## API对比
+
+### WebSocket端点
+
+**连接**
+```
+ws://localhost:8000/api/v1/pipelines/<pipeline_uuid>/ws/connect?session_type=<person|group>
+```
+
+**消息格式**
+
+客户端发送:
+```json
+{
+  "type": "message",
+  "message": [
+    {"type": "Plain", "text": "你好"}
+  ]
+}
+```
+
+服务器响应（流式）:
+```json
+{
+  "type": "response",
+  "data": {
+    "id": 1,
+    "role": "assistant",
+    "content": "你好，我是...",
+    "is_final": false,
+    "timestamp": "2025-01-28T..."
+  }
+}
+```
+
+### REST API
+
+| 端点 | 方法 | 说明 |
+|------|------|------|
+| `/api/v1/pipelines/<uuid>/ws/messages/<type>` | GET | 获取消息历史 |
+| `/api/v1/pipelines/<uuid>/ws/reset/<type>` | POST | 重置会话 |
+| `/api/v1/pipelines/<uuid>/ws/connections` | GET | 获取连接统计 |
+| `/api/v1/pipelines/<uuid>/ws/broadcast` | POST | 广播消息 |
+
+## 流式支持详解
+
+### 后端流式实现
+
+**WebSocket Adapter**
+```python
+async def reply_message_chunk(
+    self,
+    message_source: platform_events.MessageEvent,
+    bot_message,
+    message: platform_message.MessageChain,
+    quote_origin: bool = False,
+    is_final: bool = False,
+) -> dict:
+    """回复消息块 - 流式"""
+    message_data = WebSocketMessage(
+        id=-1,
+        role='assistant',
+        content=str(message),
+        message_chain=[component.__dict__ for component in message],
+        timestamp=datetime.now().isoformat(),
+        is_final=is_final and bot_message.tool_calls is None,
+    )
+
+    # 发送到队列，由WebSocket连接处理发送
+    await session.resp_queues[message_id].put(message_data)
+    return message_data.model_dump()
+
+async def is_stream_output_supported(self) -> bool:
+    """WebSocket始终支持流式输出"""
+    return True
+```
+
+### 前端流式处理
+
+**DebugDialog组件**
+```typescript
+wsClient.onMessage((message) => {
+  setMessages((prevMessages) => {
+    const existingIndex = prevMessages.findIndex(
+      (msg) => msg.role === 'assistant' && msg.content === 'Generating...'
+    );
+
+    if (existingIndex !== -1) {
+      // 更新正在生成的消息
+      const updatedMessages = [...prevMessages];
+      updatedMessages[existingIndex] = message;
+      return updatedMessages;
+    } else {
+      // 添加新消息
+      return [...prevMessages, message];
+    }
+  });
+});
+```
+
+## 兼容性说明
+
+### ⚠️ 不兼容旧版本
+
+此次迁移**完全不兼容**旧的WebChat系统：
+
+1. **API端点变更**
+   - 旧: `/api/v1/pipelines/<uuid>/chat/send`
+   - 新: `ws://.../<uuid>/ws/connect`
+
+2. **通信协议变更**
+   - 旧: HTTP + SSE (Server-Sent Events)
+   - 新: WebSocket (双向)
+
+3. **流式实现变更**
+   - 旧: `text/event-stream` 格式
+   - 新: WebSocket JSON消息
+
+### 迁移要求
+
+使用新系统需要:
+1. ✅ 前端必须支持WebSocket
+2. ✅ 后端必须运行新的WebSocket适配器
+3. ✅ 清除旧的WebChat相关配置
+
+## 优势对比
+
+| 特性 | 旧WebChat (SSE) | 新WebSocket |
+|------|----------------|-------------|
+| 双向通信 | ❌ 单向（服务器→客户端） | ✅ 双向 |
+| 主动推送 | ❌ 不支持 | ✅ 支持 |
+| 连接管理 | ❌ 无状态 | ✅ 有状态，完整生命周期 |
+| 流式输出 | ✅ 支持 | ✅ 支持（更优） |
+| 心跳机制 | ❌ 无 | ✅ 30秒心跳 |
+| 自动重连 | ❌ 无 | ✅ 最多5次 |
+| 多连接 | ⚠️ 难以管理 | ✅ 完整支持 |
+| 连接状态 | ❌ 不可见 | ✅ 实时显示 |
+| 广播功能 | ❌ 不支持 | ✅ 支持 |
+
+## 测试方式
+
+### 1. Python测试客户端
+
+```bash
+# 单连接测试
+python test_websocket_client.py <pipeline_uuid>
+
+# 指定会话类型
+python test_websocket_client.py <pipeline_uuid> --session-type group
+
+# 多连接并发测试（5个连接）
+python test_websocket_client.py <pipeline_uuid> --multi 5
+```
+
+### 2. 前端测试
+
+1. 启动LangBot服务器
+2. 访问前端界面
+3. 打开流水线调试对话框
+4. 观察连接状态指示器（左下角圆点）
+5. 发送消息测试流式响应
+
+### 3. 浏览器控制台测试
+
+```javascript
+const ws = new WebSocket('ws://localhost:8000/api/v1/pipelines/<uuid>/ws/connect?session_type=person');
+
+ws.onopen = () => {
+  console.log('已连接');
+  ws.send(JSON.stringify({
+    type: 'message',
+    message: [{type: 'Plain', text: '你好'}]
+  }));
+};
+
+ws.onmessage = (event) => {
+  console.log('收到:', JSON.parse(event.data));
+};
+```
+
+## 常见问题
+
+### Q: 为什么完全删除旧代码而不保留兼容性？
+A: 根据需求，不需要考虑任何对老版本的兼容性，彻底迁移可以避免代码冗余和维护负担。
+
+### Q: 流式输出如何工作？
+A:
+1. 后端通过`reply_message_chunk`发送消息块
+2. 消息块放入队列
+3. WebSocket连接从队列取出并发送
+4. 前端实时更新UI
+5. `is_final=true`表示最后一块
+
+### Q: 如何确保连接不断开？
+A:
+1. 客户端每30秒发送心跳（ping）
+2. 服务器响应pong
+3. 连接断开时自动重连（最多5次）
+
+### Q: 如何实现后端主动推送？
+A:
+1. 调用 `/api/v1/pipelines/<uuid>/ws/broadcast` API
+2. 消息会被推送到该流水线的所有连接
+3. 前端通过`onBroadcast`回调接收
+
+## 总结
+
+✅ **完成的工作**
+- 完全移除旧的WebChat/SSE系统
+- 实现完整的WebSocket双向通信系统
+- 支持流式输出
+- 支持多连接并发
+- 实现自动重连和心跳机制
+- 提供完整的测试工具和文档
+
+✅ **核心特性**
+- 双向实时通信
+- 流式消息支持
+- 多连接管理
+- 自动重连
+- 心跳保活
+- 连接状态可视化
+- 广播消息
+
+✅ **技术亮点**
+- 异步架构（asyncio）
+- 线程安全的连接管理
+- 独立的消息队列
+- 完整的错误处理
+- 模块化设计
+
+🎉 系统已完全迁移到WebSocket，无任何旧代码遗留！

docs/SEEKDB_INTEGRATION.md

@@ -0,0 +1,259 @@
+# SeekDB Vector Database Integration
+
+This document describes how to use OceanBase SeekDB as the vector database backend for LangBot's knowledge base feature.
+
+## What is SeekDB?
+
+**OceanBase SeekDB** is an AI-native search database that unifies relational, vector, text, JSON and GIS in a single engine, enabling hybrid search and in-database AI workflows. It's developed by OceanBase and released under Apache 2.0 license.
+
+### Key Features
+
+- **Hybrid Search**: Combine vector search, full-text search and relational query in a single statement
+- **Multi-Model Support**: Support relational, vector, text, JSON and GIS in a single engine
+- **Lightweight**: Requires as little as 1 CPU core and 2 GB of memory
+- **Multiple Deployment Modes**: Supports both embedded mode and client/server mode
+- **MySQL Compatible**: Powered by OceanBase engine with full ACID compliance and MySQL compatibility
+
+## Installation
+
+SeekDB support is automatically included when you install LangBot. The required dependency `pyseekdb` is listed in `pyproject.toml`.
+
+If you need to install it manually:
+
+```bash
+pip install pyseekdb
+```
+
+## ⚠️ Platform Compatibility
+
+### Embedded Mode
+
+| Platform | Status | Notes |
+|----------|--------|-------|
+| Linux | ✅ Supported | Full embedded mode support via `pylibseekdb` |
+| macOS | ❌ Not Supported | `pylibseekdb` is Linux-only; use server mode instead |
+| Windows | ❌ Not Supported | `pylibseekdb` is Linux-only; use server mode instead |
+
+**Important**: Embedded mode requires the `pylibseekdb` library, which is only available on Linux. If you're on macOS or Windows, you must use server mode.
+
+### Server Mode (Docker)
+
+| Platform | Status | Notes |
+|----------|--------|-------|
+| Linux | ✅ Supported | Full Docker support |
+| macOS | ⚠️ Known Issue | Docker container initialization failure - [See Issue #36](https://github.com/oceanbase/seekdb/issues/36) |
+| Windows | ⚠️ Untested | Should work but not yet tested |
+
+**macOS Users**: Currently, SeekDB Docker containers have an initialization issue on macOS ([oceanbase/seekdb#36](https://github.com/oceanbase/seekdb/issues/36)). Until this is resolved, we recommend:
+- Using ChromaDB or Qdrant as alternatives
+- Connecting to a remote SeekDB server on Linux if available
+
+### Server Mode (Remote Connection)
+
+| Platform | Status | Notes |
+|----------|--------|-------|
+| All Platforms | ✅ Supported | Connect to SeekDB running on a remote Linux server |
+
+**Recommendation for macOS/Windows users**: Deploy SeekDB on a Linux server and connect via server mode configuration.
+
+## Configuration
+
+### Embedded Mode (Recommended for Development)
+
+Embedded mode runs SeekDB directly within the LangBot process, storing data locally. This is the simplest setup and requires no external services.
+
+Edit your `config.yaml`:
+
+```yaml
+vdb:
+  use: seekdb
+  seekdb:
+    mode: embedded
+    path: './data/seekdb'  # Path to store SeekDB data
+    database: 'langbot'    # Database name
+```
+
+### Server Mode (For Production)
+
+Server mode connects to a remote SeekDB server or OceanBase server. This is recommended for production deployments.
+
+#### SeekDB Server
+
+```yaml
+vdb:
+  use: seekdb
+  seekdb:
+    mode: server
+    host: 'localhost'
+    port: 2881
+    database: 'langbot'
+    user: 'root'
+    password: ''  # Can also use SEEKDB_PASSWORD env var
+```
+
+#### OceanBase Server
+
+If you're using OceanBase with seekdb capabilities:
+
+```yaml
+vdb:
+  use: seekdb
+  seekdb:
+    mode: server
+    host: 'localhost'
+    port: 2881
+    tenant: 'sys'        # OceanBase tenant name
+    database: 'langbot'
+    user: 'root'
+    password: ''
+```
+
+## Configuration Parameters
+
+| Parameter  | Required | Default      | Description |
+|-----------|----------|--------------|-------------|
+| `mode`    | No       | `embedded`   | Deployment mode: `embedded` or `server` |
+| `path`    | No       | `./data/seekdb` | Data directory for embedded mode |
+| `database` | No      | `langbot`    | Database name |
+| `host`    | No       | `localhost`  | Server host (server mode only) |
+| `port`    | No       | `2881`       | Server port (server mode only) |
+| `user`    | No       | `root`       | Username (server mode only) |
+| `password` | No      | `''`         | Password (server mode only) |
+| `tenant`  | No       | None         | OceanBase tenant (optional, server mode only) |
+
+## Usage
+
+Once configured, SeekDB will be used automatically for all knowledge base operations in LangBot:
+
+1. **Creating Knowledge Bases**: Vectors will be stored in SeekDB collections
+2. **Adding Documents**: Document embeddings will be indexed in SeekDB
+3. **Searching**: Vector similarity search will use SeekDB's efficient indexing
+4. **Deleting**: Document removal will delete vectors from SeekDB
+
+No code changes are required - just update your configuration!
+
+## Architecture Details
+
+### Implementation
+
+The SeekDB adapter is implemented in `src/langbot/pkg/vector/vdbs/seekdb.py` and follows the same `VectorDatabase` interface as Chroma and Qdrant adapters.
+
+Key methods:
+- `add_embeddings()`: Add vectors with metadata to a collection
+- `search()`: Perform vector similarity search
+- `delete_by_file_id()`: Delete vectors by file ID metadata
+- `get_or_create_collection()`: Manage collections
+- `delete_collection()`: Remove entire collections
+
+### Vector Storage
+
+- Collections are created with HNSW (Hierarchical Navigable Small World) index
+- Default distance metric: Cosine similarity
+- Default vector dimension: 384 (adjusts automatically based on embeddings)
+- Metadata is stored alongside vectors for filtering
+
+## Advantages Over Other Vector Databases
+
+### vs. ChromaDB
+- ✅ Better MySQL compatibility
+- ✅ Hybrid search capabilities (vector + full-text + SQL)
+- ✅ Production-grade distributed mode support
+- ✅ Lightweight embedded mode
+
+### vs. Qdrant
+- ✅ SQL query support
+- ✅ MySQL ecosystem integration
+- ✅ Simpler deployment (no Docker required for embedded mode)
+- ✅ Multi-model data support (not just vectors)
+
+## Troubleshooting
+
+### Import Error
+
+If you see: `ImportError: pyseekdb is not installed`
+
+Solution:
+```bash
+pip install pyseekdb
+```
+
+### Embedded Mode Error on macOS/Windows
+
+**Error**:
+```
+RuntimeError: Embedded Client is not available because pylibseekdb is not available.
+Please install pylibseekdb (Linux only) or use RemoteServerClient (host/port) instead.
+```
+
+**Cause**: `pylibseekdb` is only available on Linux platforms.
+
+**Solution**: Use server mode instead:
+1. Deploy SeekDB on a Linux server or VM
+2. Configure LangBot to use server mode:
+```yaml
+vdb:
+  use: seekdb
+  seekdb:
+    mode: server
+    host: 'your-seekdb-server-ip'
+    port: 2881
+    database: 'langbot'
+    user: 'root'
+    password: ''
+```
+
+**Alternative**: Use ChromaDB or Qdrant, which work on all platforms:
+```yaml
+vdb:
+  use: chroma  # or qdrant
+```
+
+### Docker Container Fails on macOS
+
+**Symptoms**:
+```bash
+docker run -d -p 2881:2881 oceanbase/seekdb:latest
+# Container exits immediately with code 30
+```
+
+**Error in logs**:
+```
+[ERROR] Code: Agent.SeekDB.Not.Exists
+Message: initialize failed: init agent failed: SeekDB not exists in current directory.
+```
+
+**Cause**: This is a known issue with SeekDB Docker containers on macOS. See [oceanbase/seekdb#36](https://github.com/oceanbase/seekdb/issues/36).
+
+**Status**: Under investigation by OceanBase team.
+
+**Workaround Options**:
+1. **Use alternatives**: ChromaDB or Qdrant work perfectly on macOS
+2. **Remote server**: Deploy SeekDB on a Linux server and connect remotely
+3. **Wait for fix**: Monitor the GitHub issue for updates
+
+### Connection Error (Server Mode)
+
+If SeekDB server is not reachable, check:
+1. Server is running: `ps aux | grep observer`
+2. Port is accessible: `nc -zv localhost 2881`
+3. Credentials are correct in config
+4. Firewall allows connections on port 2881
+
+### Performance Issues
+
+For large datasets:
+- Use server mode instead of embedded mode
+- Ensure adequate memory allocation
+- Consider using OceanBase distributed mode for very large scale
+- Adjust HNSW index parameters if needed
+
+## Resources
+
+- SeekDB GitHub: https://github.com/oceanbase/seekdb
+- pyseekdb SDK: https://github.com/oceanbase/pyseekdb
+- OceanBase Documentation: https://oceanbase.ai
+- LangBot Documentation: https://docs.langbot.app
+
+## License
+
+SeekDB is licensed under Apache License 2.0.

docs/WEBSOCKET_README.md

@@ -0,0 +1,394 @@
+# LangBot WebSocket 双向通信系统
+
+## 概述
+
+这是一个内置在 LangBot 中的完整 IM (即时通讯) 系统，支持：
+
+- ✅ WebSocket 双向实时通信
+- ✅ 多个客户端并发连接
+- ✅ 前端到后端的消息发送
+- ✅ 后端到前端的主动推送
+- ✅ 流式响应支持
+- ✅ 连接管理和会话隔离
+- ✅ 心跳机制
+- ✅ 广播消息功能
+
+## 架构设计
+
+### 核心组件
+
+1. **WebSocketConnectionManager** (`websocket_manager.py`)
+   - 管理所有活跃的 WebSocket 连接
+   - 支持按流水线、会话类型查询连接
+   - 提供广播和单播功能
+   - 线程安全的并发访问控制
+
+2. **WebSocketAdapter** (`websocket_adapter.py`)
+   - 实现平台适配器接口
+   - 处理消息的接收和发送
+   - 支持流式输出
+   - 管理消息历史
+
+3. **WebSocketChatRouterGroup** (`websocket_chat.py`)
+   - WebSocket 路由控制器
+   - 处理连接建立、消息收发
+   - 实现心跳机制
+   - 提供 REST API 接口
+
+## API 接口
+
+### WebSocket 连接
+
+#### 建立连接
+
+```
+ws://localhost:8000/api/v1/pipelines/<pipeline_uuid>/ws/connect?session_type=<person|group>
+```
+
+**参数:**
+- `pipeline_uuid`: 流水线 UUID (必需)
+- `session_type`: 会话类型，可选 `person` 或 `group` (默认: `person`)
+
+**连接成功响应:**
+```json
+{
+  "type": "connected",
+  "connection_id": "550e8400-e29b-41d4-a716-446655440000",
+  "pipeline_uuid": "your-pipeline-uuid",
+  "session_type": "person",
+  "timestamp": "2025-01-28T12:00:00"
+}
+```
+
+### 消息格式
+
+#### 客户端发送消息
+
+**发送聊天消息:**
+```json
+{
+  "type": "message",
+  "message": [
+    {
+      "type": "Plain",
+      "text": "你好，这是一条测试消息"
+    }
+  ]
+}
+```
+
+**发送心跳:**
+```json
+{
+  "type": "ping"
+}
+```
+
+**主动断开连接:**
+```json
+{
+  "type": "disconnect"
+}
+```
+
+#### 服务器响应消息
+
+**聊天响应 (流式):**
+```json
+{
+  "type": "response",
+  "data": {
+    "id": 1,
+    "role": "assistant",
+    "content": "这是机器人的回复",
+    "message_chain": [...],
+    "timestamp": "2025-01-28T12:00:00",
+    "is_final": false,
+    "connection_id": "..."
+  }
+}
+```
+
+**心跳响应:**
+```json
+{
+  "type": "pong",
+  "timestamp": "2025-01-28T12:00:00"
+}
+```
+
+**广播消息:**
+```json
+{
+  "type": "broadcast",
+  "message": "这是一条广播消息",
+  "timestamp": "2025-01-28T12:00:00"
+}
+```
+
+**错误消息:**
+```json
+{
+  "type": "error",
+  "message": "错误描述"
+}
+```
+
+### REST API 接口
+
+#### 1. 获取消息历史
+
+```http
+GET /api/v1/pipelines/<pipeline_uuid>/ws/messages/<session_type>
+```
+
+**响应:**
+```json
+{
+  "code": 0,
+  "msg": "ok",
+  "data": {
+    "messages": [...]
+  }
+}
+```
+
+#### 2. 重置会话
+
+```http
+POST /api/v1/pipelines/<pipeline_uuid>/ws/reset/<session_type>
+```
+
+**响应:**
+```json
+{
+  "code": 0,
+  "msg": "ok",
+  "data": {
+    "message": "Session reset successfully"
+  }
+}
+```
+
+#### 3. 获取连接统计
+
+```http
+GET /api/v1/pipelines/<pipeline_uuid>/ws/connections
+```
+
+**响应:**
+```json
+{
+  "code": 0,
+  "msg": "ok",
+  "data": {
+    "stats": {
+      "total_connections": 5,
+      "pipelines": 2,
+      "connections_by_pipeline": {
+        "pipeline-1": 3,
+        "pipeline-2": 2
+      },
+      "connections_by_session_type": {
+        "person": 4,
+        "group": 1
+      }
+    },
+    "connections": [
+      {
+        "connection_id": "...",
+        "session_type": "person",
+        "created_at": "2025-01-28T12:00:00",
+        "last_active": "2025-01-28T12:05:00",
+        "is_active": true
+      }
+    ]
+  }
+}
+```
+
+#### 4. 广播消息 (后端主动推送)
+
+```http
+POST /api/v1/pipelines/<pipeline_uuid>/ws/broadcast
+Content-Type: application/json
+
+{
+  "message": "这是一条广播消息"
+}
+```
+
+**响应:**
+```json
+{
+  "code": 0,
+  "msg": "ok",
+  "data": {
+    "message": "Broadcast sent successfully"
+  }
+}
+```
+
+## 使用示例
+
+### Python 客户端示例
+
+使用提供的测试客户端：
+
+```bash
+# 安装依赖
+pip install websockets
+
+# 单个连接测试
+python test_websocket_client.py <pipeline_uuid>
+
+# 指定会话类型
+python test_websocket_client.py <pipeline_uuid> --session-type group
+
+# 多连接并发测试
+python test_websocket_client.py <pipeline_uuid> --multi 5
+```
+
+### JavaScript 客户端示例
+
+```javascript
+// 建立 WebSocket 连接
+const ws = new WebSocket('ws://localhost:8000/api/v1/pipelines/your-pipeline-uuid/ws/connect?session_type=person');
+
+// 连接建立
+ws.onopen = () => {
+  console.log('WebSocket 连接已建立');
+
+  // 发送消息
+  ws.send(JSON.stringify({
+    type: 'message',
+    message: [
+      {
+        type: 'Plain',
+        text: '你好'
+      }
+    ]
+  }));
+};
+
+// 接收消息
+ws.onmessage = (event) => {
+  const data = JSON.parse(event.data);
+
+  if (data.type === 'connected') {
+    console.log('连接成功:', data.connection_id);
+  } else if (data.type === 'response') {
+    console.log('机器人回复:', data.data.content);
+    if (data.data.is_final) {
+      console.log('响应完成');
+    }
+  } else if (data.type === 'broadcast') {
+    console.log('收到广播:', data.message);
+  }
+};
+
+// 连接关闭
+ws.onclose = () => {
+  console.log('WebSocket 连接已关闭');
+};
+
+// 错误处理
+ws.onerror = (error) => {
+  console.error('WebSocket 错误:', error);
+};
+
+// 发送心跳
+setInterval(() => {
+  if (ws.readyState === WebSocket.OPEN) {
+    ws.send(JSON.stringify({ type: 'ping' }));
+  }
+}, 30000); // 每 30 秒发送一次心跳
+```
+
+## 特性说明
+
+### 1. 多连接支持
+
+系统支持同时建立多个 WebSocket 连接，每个连接都有唯一的 `connection_id`。连接按照流水线和会话类型进行分组管理。
+
+### 2. 双向通信
+
+- **前端 → 后端**: 客户端可以主动发送消息给服务器
+- **后端 → 前端**: 服务器可以通过广播 API 主动推送消息给客户端
+
+### 3. 流式响应
+
+支持流式输出，机器人的响应会分块发送，客户端可以实时显示部分响应内容。
+
+### 4. 会话隔离
+
+支持 `person` 和 `group` 两种会话类型，不同类型的会话消息历史互不影响。
+
+### 5. 连接管理
+
+- 自动追踪连接状态
+- 记录最后活跃时间
+- 支持连接统计查询
+- 连接断开时自动清理资源
+
+### 6. 心跳机制
+
+客户端可以定期发送 `ping` 消息，服务器会响应 `pong`，用于保持连接活跃和检测连接状态。
+
+## 架构优势
+
+1. **高并发**: 使用 asyncio 异步架构，支持大量并发连接
+2. **可扩展**: 模块化设计，易于扩展新功能
+3. **线程安全**: 连接管理器使用锁机制保证并发安全
+4. **消息队列**: 每个连接独立的发送队列，避免消息混乱
+5. **灵活路由**: 支持按流水线、会话类型灵活路由消息
+
+## 注意事项
+
+1. **认证**: 当前 WebSocket 连接不需要认证，生产环境建议添加认证机制
+2. **心跳**: 建议客户端实现心跳机制，避免连接超时
+3. **重连**: 客户端应实现断线重连逻辑
+4. **消息大小**: 注意控制单条消息大小，避免内存溢出
+5. **连接数限制**: 生产环境建议设置最大连接数限制
+
+## 故障排查
+
+### 连接失败
+
+1. 检查流水线 UUID 是否正确
+2. 检查服务器是否正常运行
+3. 检查防火墙设置
+
+### 消息发送失败
+
+1. 检查消息格式是否正确
+2. 检查连接是否仍然活跃
+3. 查看服务器日志获取详细错误信息
+
+### 性能问题
+
+1. 检查并发连接数是否过多
+2. 检查消息处理速度
+3. 考虑使用连接池或负载均衡
+
+## 开发调试
+
+启用详细日志：
+
+```python
+import logging
+logging.getLogger('langbot.pkg.platform.sources.websocket_adapter').setLevel(logging.DEBUG)
+logging.getLogger('langbot.pkg.platform.sources.websocket_manager').setLevel(logging.DEBUG)
+logging.getLogger('langbot.pkg.api.http.controller.groups.pipelines.websocket_chat').setLevel(logging.DEBUG)
+```
+
+## 后续改进建议
+
+1. 添加用户认证和授权机制
+2. 实现消息持久化
+3. 添加消息加密
+4. 实现更丰富的消息类型 (图片、文件等)
+5. 添加消息已读/未读状态
+6. 实现群组聊天功能
+7. 添加在线状态显示
+8. 实现消息撤回功能

docs/service-api-openapi.json

@@ -9,7 +9,7 @@
       "url": "https://langbot.app"
     },
     "license": {
-      "name": "AGPL-3.0",
+      "name": "Apache-2.0",
       "url": "https://github.com/langbot-app/LangBot/blob/master/LICENSE"
     }
   },

pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "langbot"
-version = "4.5.3"
-description = "Easy-to-use global IM bot platform designed for LLM era"
+version = "4.9.4"
+description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
-requires-python = ">=3.10.1,<4.0"
+requires-python = ">=3.11,<4.0"
 dependencies = [
     "aiocqhttp>=1.4.4",
     "aiofiles>=24.1.0",
@@ -17,13 +17,13 @@ dependencies = [
     "certifi>=2025.4.26",
     "colorlog~=6.6.0",
     "cryptography>=44.0.3",
-    "dashscope>=1.23.2",
+    "dashscope>=1.25.10",
     "dingtalk-stream>=0.24.0",
     "discord-py>=2.5.2",
     "pynacl>=1.5.0", # Required for Discord voice support
     "gewechat-client>=0.1.5",
     "lark-oapi>=1.4.15",
-    "mcp>=1.8.1",
+    "mcp>=1.25.0",
     "nakuru-project-idk>=0.0.2.1",
     "ollama>=0.4.8",
     "openai>1.0.0",
@@ -61,13 +61,17 @@ dependencies = [
     "html2text>=2024.2.26",
     "langchain>=0.2.0",
     "langchain-text-splitters>=0.0.1",
-    "chromadb>=0.4.24",
+    "chromadb>=1.0.0,<2.0.0",
     "qdrant-client (>=1.15.1,<2.0.0)",
-    "langbot-plugin==0.1.11",
+    "pyseekdb==1.1.0.post3",
+    "langbot-plugin==0.3.5",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "tboxsdk>=0.0.10",
     "boto3>=1.35.0",
+    "pymilvus>=2.6.4",
+    "pgvector>=0.4.1",
+    "botocore>=1.42.39",
 ]
 keywords = [
     "bot",

pytest.ini

@@ -26,7 +26,7 @@ markers =
 
 # Coverage options (when using pytest-cov)
 [coverage:run]
-source = langbot.pkg
+source = langbot
 omit =
     */tests/*
     */test_*.py

run_tests.sh

@@ -22,7 +22,7 @@ echo "Running all unit tests..."
 
 # Run tests with coverage
 pytest tests/unit_tests/ -v --tb=short \
-    --cov=pkg \
+    --cov=langbot \
     --cov-report=xml \
     "$@"
 

src/langbot/__init__.py

@@ -1,3 +1,3 @@
-"""LangBot - Easy-to-use global IM bot platform designed for LLM era"""
+"""LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.5.3'
+__version__ = '4.9.4'

src/langbot/libs/dify_service_api/v1/client.py

@@ -32,6 +32,7 @@ class AsyncDifyServiceClient:
         conversation_id: str = '',
         files: list[dict[str, typing.Any]] = [],
         timeout: float = 30.0,
+        model_config: dict[str, typing.Any] | None = None,
     ) -> typing.AsyncGenerator[dict[str, typing.Any], None]:
         """发送消息"""
         if response_mode != 'streaming':
@@ -42,6 +43,16 @@ class AsyncDifyServiceClient:
             trust_env=True,
             timeout=timeout,
         ) as client:
+            payload = {
+                'inputs': inputs,
+                'query': query,
+                'user': user,
+                'response_mode': response_mode,
+                'conversation_id': conversation_id,
+                'files': files,
+                'model_config': model_config or {},
+            }
+
             async with client.stream(
                 'POST',
                 '/chat-messages',
@@ -49,14 +60,7 @@ class AsyncDifyServiceClient:
                     'Authorization': f'Bearer {self.api_key}',
                     'Content-Type': 'application/json',
                 },
-                json={
-                    'inputs': inputs,
-                    'query': query,
-                    'user': user,
-                    'response_mode': response_mode,
-                    'conversation_id': conversation_id,
-                    'files': files,
-                },
+                json=payload,
             ) as r:
                 async for chunk in r.aiter_lines():
                     if r.status_code != 200:

src/langbot/libs/dingtalk_api/api.py

@@ -1,8 +1,11 @@
+import asyncio
 import base64
 import json
 import time
+import urllib.parse
 from typing import Callable
 import dingtalk_stream  # type: ignore
+import websockets
 from .EchoHandler import EchoTextHandler
 from .dingtalkevent import DingTalkEvent
 import httpx
@@ -36,6 +39,7 @@ class DingTalkClient:
         self.access_token_expiry_time = ''
         self.markdown_card = markdown_card
         self.logger = logger
+        self._stopped = False  # Flag to control the event loop
 
     async def get_access_token(self):
         url = 'https://api.dingtalk.com/v1.0/oauth2/accessToken'
@@ -170,6 +174,9 @@ class DingTalkClient:
         """
         处理消息事件。
         """
+        # Skip message handling if stopped
+        if self._stopped:
+            return
         msg_type = event.conversation
         if msg_type in self._message_handlers:
             for handler in self._message_handlers[msg_type]:
@@ -265,15 +272,30 @@ class DingTalkClient:
 
                 message_data['Type'] = 'audio'
             elif incoming_message.message_type == 'file':
-                down_list = incoming_message.get_down_list()
-                if len(down_list) >= 2:
-                    message_data['File'] = await self.get_file_url(down_list[0])
-                    message_data['Name'] = down_list[1]
+                # 获取原始数据字典并提取嵌套的文件信息
+                raw_data = incoming_message.to_dict()
+                file_info = raw_data.get('content', {})
+
+                # 兼容处理：如果 content 仍为 JSON 字符串则进行解析
+                if isinstance(file_info, str):
+                    try:
+                        file_info = json.loads(file_info)
+                    except (json.JSONDecodeError, TypeError):
+                        file_info = {}
+
+                download_code = file_info.get('downloadCode')
+                file_name = file_info.get('fileName')
+
+                if download_code and file_name:
+                    # 转换 downloadCode 为可下载的真实 URL
+                    message_data['File'] = await self.get_file_url(download_code)
+                    message_data['Name'] = file_name
                 else:
                     if self.logger:
-                        await self.logger.error(f'get_down_list() returned fewer than 2 elements: {down_list}')
+                        await self.logger.error(f'Failed to extract file info from message content: {file_info}')
                     message_data['File'] = None
                     message_data['Name'] = None
+
                 message_data['Type'] = 'file'
 
             copy_message_data = message_data.copy()
@@ -340,10 +362,15 @@ class DingTalkClient:
             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
+        self,
+        temp_card_id: str,
+        incoming_message: dingtalk_stream.ChatbotMessage,
+        quote_origin: bool = False,
+        card_auto_layout: bool = False,
     ):
-        content_key = 'content'
-        card_data = {content_key: ''}
+        card_data = {}
+        card_data['config'] = json.dumps({'autoLayout': card_auto_layout})
+        card_data['content'] = ''
 
         card_instance = dingtalk_stream.AICardReplier(self.client, incoming_message)
         # print(card_instance)
@@ -378,4 +405,70 @@ class DingTalkClient:
 
     async def start(self):
         """启动 WebSocket 连接，监听消息"""
-        await self.client.start()
+        self._stopped = False
+        self.client.pre_start()
+
+        while not self._stopped:
+            try:
+                connection = self.client.open_connection()
+
+                if not connection:
+                    if self.logger:
+                        await self.logger.error('DingTalk: open connection failed')
+                    await asyncio.sleep(10)
+                    continue
+
+                uri = '%s?ticket=%s' % (connection['endpoint'], urllib.parse.quote_plus(connection['ticket']))
+                async with websockets.connect(uri) as websocket:
+                    self.client.websocket = websocket
+                    keepalive_task = asyncio.create_task(self._keepalive(websocket))
+                    try:
+                        async for raw_message in websocket:
+                            if self._stopped:
+                                break
+                            json_message = json.loads(raw_message)
+                            asyncio.create_task(self.client.background_task(json_message))
+                    finally:
+                        keepalive_task.cancel()
+                        try:
+                            await keepalive_task
+                        except asyncio.CancelledError:
+                            pass
+            except asyncio.CancelledError:
+                # Properly exit when task is cancelled
+                break
+            except websockets.exceptions.ConnectionClosedError as e:
+                if self._stopped:
+                    break
+                if self.logger:
+                    await self.logger.error(f'DingTalk: connection closed, reconnecting... error={e}')
+                await asyncio.sleep(5)
+                continue
+            except Exception as e:
+                if self._stopped:
+                    break
+                if self.logger:
+                    await self.logger.error(f'DingTalk: unknown exception, reconnecting... error={e}')
+                await asyncio.sleep(3)
+                continue
+
+    async def _keepalive(self, ws, ping_interval=60):
+        """Keep WebSocket connection alive"""
+        while not self._stopped:
+            await asyncio.sleep(ping_interval)
+            try:
+                await ws.ping()
+            except websockets.exceptions.ConnectionClosed:
+                break
+
+    async def stop(self):
+        """停止 WebSocket 连接"""
+        self._stopped = True
+        # Close WebSocket connection if exists
+        if self.client.websocket:
+            try:
+                await self.client.websocket.close()
+            except Exception:
+                pass
+        # Clear message handlers to prevent stale callbacks
+        self._message_handlers = {'example': []}

src/langbot/libs/official_account_api/api.py

@@ -23,20 +23,34 @@ xml_template = """
 
 
 class OAClient:
-    def __init__(self, token: str, EncodingAESKey: str, AppID: str, Appsecret: str, logger: None):
+    def __init__(
+        self,
+        token: str,
+        EncodingAESKey: str,
+        AppID: str,
+        Appsecret: str,
+        logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://api.weixin.qq.com',
+    ):
         self.token = token
         self.aes = EncodingAESKey
         self.appid = AppID
         self.appsecret = Appsecret
-        self.base_url = 'https://api.weixin.qq.com'
+        self.base_url = api_base_url
         self.access_token = ''
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command',
-            'handle_callback',
-            self.handle_callback_request,
-            methods=['GET', 'POST'],
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command',
+                'handle_callback',
+                self.handle_callback_request,
+                methods=['GET', 'POST'],
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -46,19 +60,39 @@ class OAClient:
         self.logger = logger
 
     async def handle_callback_request(self):
+        """处理回调请求（独立端口模式，使用全局 request）。"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
+        """
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """处理回调请求的内部实现，包括 GET 验证和 POST 消息接收。
+
+        Args:
+            req: Quart Request 对象
+        """
         try:
             # 每隔100毫秒查询是否生成ai回答
             start_time = time.time()
-            signature = request.args.get('signature', '')
-            timestamp = request.args.get('timestamp', '')
-            nonce = request.args.get('nonce', '')
-            echostr = request.args.get('echostr', '')
-            msg_signature = request.args.get('msg_signature', '')
+            signature = req.args.get('signature', '')
+            timestamp = req.args.get('timestamp', '')
+            nonce = req.args.get('nonce', '')
+            echostr = req.args.get('echostr', '')
+            msg_signature = req.args.get('msg_signature', '')
             if msg_signature is None:
                 await self.logger.error('msg_signature不在请求体中')
                 raise Exception('msg_signature不在请求体中')
 
-            if request.method == 'GET':
+            if req.method == 'GET':
                 # 校验签名
                 check_str = ''.join(sorted([self.token, timestamp, nonce]))
                 check_signature = hashlib.sha1(check_str.encode('utf-8')).hexdigest()
@@ -68,8 +102,8 @@ class OAClient:
                 else:
                     await self.logger.error('拒绝请求')
                     raise Exception('拒绝请求')
-            elif request.method == 'POST':
-                encryt_msg = await request.data
+            elif req.method == 'POST':
+                encryt_msg = await req.data
                 wxcpt = WXBizMsgCrypt(self.token, self.aes, self.appid)
                 ret, xml_msg = wxcpt.DecryptMsg(encryt_msg, msg_signature, timestamp, nonce)
                 xml_msg = xml_msg.decode('utf-8')
@@ -182,20 +216,27 @@ class OAClientForLongerResponse:
         Appsecret: str,
         LoadingMessage: str,
         logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://api.weixin.qq.com',
     ):
         self.token = token
         self.aes = EncodingAESKey
         self.appid = AppID
         self.appsecret = Appsecret
-        self.base_url = 'https://api.weixin.qq.com'
+        self.base_url = api_base_url
         self.access_token = ''
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command',
-            'handle_callback',
-            self.handle_callback_request,
-            methods=['GET', 'POST'],
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command',
+                'handle_callback',
+                self.handle_callback_request,
+                methods=['GET', 'POST'],
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -206,24 +247,44 @@ class OAClientForLongerResponse:
         self.logger = logger
 
     async def handle_callback_request(self):
+        """处理回调请求（独立端口模式，使用全局 request）。"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
+        """
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """处理回调请求的内部实现，包括 GET 验证和 POST 消息接收。
+
+        Args:
+            req: Quart Request 对象
+        """
         try:
-            signature = request.args.get('signature', '')
-            timestamp = request.args.get('timestamp', '')
-            nonce = request.args.get('nonce', '')
-            echostr = request.args.get('echostr', '')
-            msg_signature = request.args.get('msg_signature', '')
+            signature = req.args.get('signature', '')
+            timestamp = req.args.get('timestamp', '')
+            nonce = req.args.get('nonce', '')
+            echostr = req.args.get('echostr', '')
+            msg_signature = req.args.get('msg_signature', '')
 
             if msg_signature is None:
                 await self.logger.error('msg_signature不在请求体中')
                 raise Exception('msg_signature不在请求体中')
 
-            if request.method == 'GET':
+            if req.method == 'GET':
                 check_str = ''.join(sorted([self.token, timestamp, nonce]))
                 check_signature = hashlib.sha1(check_str.encode('utf-8')).hexdigest()
                 return echostr if check_signature == signature else '拒绝请求'
 
-            elif request.method == 'POST':
-                encryt_msg = await request.data
+            elif req.method == 'POST':
+                encryt_msg = await req.data
                 wxcpt = WXBizMsgCrypt(self.token, self.aes, self.appid)
                 ret, xml_msg = wxcpt.DecryptMsg(encryt_msg, msg_signature, timestamp, nonce)
                 xml_msg = xml_msg.decode('utf-8')

src/langbot/libs/openclaw_weixin_api/__init__.py

@@ -0,0 +1,3 @@
+from .client import OpenClawWeixinClient as OpenClawWeixinClient
+from .types import ApiError as ApiError
+from .types import LoginResult as LoginResult

src/langbot/libs/openclaw_weixin_api/client.py

@@ -0,0 +1,807 @@
+"""Async HTTP client for the OpenClaw WeChat API.
+
+Implements the iLink Bot API protocol.
+Reference: https://github.com/epiral/weixin-bot
+
+Endpoints: getUpdates (long-poll), sendMessage, getUploadUrl, getConfig, sendTyping.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import base64
+import io
+import logging
+import os
+import struct
+import typing
+import uuid
+from typing import Optional
+from urllib.parse import quote
+
+import aiohttp
+
+from .types import (
+    ApiError,
+    CDNMedia,
+    FileItem,
+    GetConfigResponse,
+    GetUpdatesResponse,
+    GetUploadUrlResponse,
+    ImageItem,
+    LoginResult,
+    MessageItem,
+    QRCodeResponse,
+    QRStatusResponse,
+    RefMessage,
+    TextItem,
+    VideoItem,
+    VoiceItem,
+    WeixinMessage,
+)
+
+logger = logging.getLogger('openclaw-weixin-sdk')
+
+DEFAULT_BASE_URL = 'https://ilinkai.weixin.qq.com'
+CDN_BASE_URL = 'https://novac2c.cdn.weixin.qq.com/c2c'
+
+CHANNEL_VERSION = '1.0.0'
+
+DEFAULT_API_TIMEOUT = 15
+DEFAULT_LONG_POLL_TIMEOUT = 40
+DEFAULT_CONFIG_TIMEOUT = 10
+DEFAULT_QR_POLL_TIMEOUT = 35
+
+SESSION_EXPIRED_ERRCODE = -14
+
+DEFAULT_BOT_TYPE = '3'
+
+# Maximum text length per message chunk (WeChat limit)
+MAX_TEXT_CHUNK_SIZE = 2000
+
+
+def _random_wechat_uin() -> str:
+    """Generate the X-WECHAT-UIN header: random uint32 -> decimal string -> base64."""
+    rand_bytes = os.urandom(4)
+    uint32_val = struct.unpack('>I', rand_bytes)[0]
+    return base64.b64encode(str(uint32_val).encode('utf-8')).decode('utf-8')
+
+
+def _build_base_info() -> dict:
+    """Build the base_info payload included in every API request."""
+    return {'channel_version': CHANNEL_VERSION}
+
+
+def _chunk_text(text: str, max_size: int = MAX_TEXT_CHUNK_SIZE) -> list[str]:
+    """Split long text into chunks that fit within WeChat's message size limit."""
+    if len(text) <= max_size:
+        return [text]
+    chunks = []
+    while text:
+        chunks.append(text[:max_size])
+        text = text[max_size:]
+    return chunks
+
+
+class OpenClawWeixinClient:
+    """Async client for the OpenClaw WeChat HTTP JSON API."""
+
+    def __init__(self, base_url: str, token: str):
+        self.base_url = base_url.rstrip('/')
+        self.token = token
+        self._session: Optional[aiohttp.ClientSession] = None
+
+    async def _get_session(self) -> aiohttp.ClientSession:
+        if self._session is None or self._session.closed:
+            self._session = aiohttp.ClientSession()
+        return self._session
+
+    async def close(self):
+        if self._session and not self._session.closed:
+            await self._session.close()
+
+    def _build_headers(self) -> dict[str, str]:
+        headers = {
+            'Content-Type': 'application/json',
+            'AuthorizationType': 'ilink_bot_token',
+            'X-WECHAT-UIN': _random_wechat_uin(),
+        }
+        if self.token:
+            headers['Authorization'] = f'Bearer {self.token}'
+        return headers
+
+    async def _post(self, endpoint: str, payload: dict, timeout: float = DEFAULT_API_TIMEOUT) -> dict:
+        """Make a POST request and return the JSON response.
+
+        Raises ApiError on HTTP errors or when the response contains a non-zero errcode.
+        """
+        payload['base_info'] = _build_base_info()
+
+        session = await self._get_session()
+        url = f'{self.base_url}/{endpoint}'
+        headers = self._build_headers()
+
+        async with session.post(
+            url, json=payload, headers=headers, timeout=aiohttp.ClientTimeout(total=timeout)
+        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise ApiError(
+                    f'OpenClaw API error {resp.status}: {text}',
+                    status=resp.status,
+                )
+            data = await resp.json(content_type=None)
+
+        # Check for application-level errors in the response body
+        errcode = data.get('errcode') or data.get('ret')
+        if errcode and errcode != 0:
+            raise ApiError(
+                data.get('errmsg') or f'API errcode {errcode}',
+                status=200,
+                code=errcode,
+                payload=data,
+            )
+
+        return data
+
+    async def get_updates(
+        self, get_updates_buf: str = '', timeout: float = DEFAULT_LONG_POLL_TIMEOUT
+    ) -> GetUpdatesResponse:
+        """Long-poll for new messages.
+
+        Note: This method does NOT raise ApiError for errcode responses —
+        it returns them in the GetUpdatesResponse so the caller can handle
+        session expiry and other errors with full context.
+        """
+        try:
+            # Bypass the errcode check in _post since get_updates needs
+            # to return error info (e.g. session expired) to the caller.
+            payload: dict = {'get_updates_buf': get_updates_buf}
+            payload['base_info'] = _build_base_info()
+
+            session = await self._get_session()
+            url = f'{self.base_url}/ilink/bot/getupdates'
+            headers = self._build_headers()
+
+            async with session.post(
+                url,
+                json=payload,
+                headers=headers,
+                timeout=aiohttp.ClientTimeout(total=timeout),
+            ) as resp:
+                if resp.status != 200:
+                    text = await resp.text()
+                    raise ApiError(
+                        f'OpenClaw API error {resp.status}: {text}',
+                        status=resp.status,
+                    )
+                data = await resp.json(content_type=None)
+
+        except (asyncio.TimeoutError, aiohttp.ServerTimeoutError):
+            return GetUpdatesResponse(ret=0, msgs=[], get_updates_buf=get_updates_buf)
+        except ApiError:
+            raise
+        except Exception as e:
+            if 'timeout' in str(e).lower():
+                return GetUpdatesResponse(ret=0, msgs=[], get_updates_buf=get_updates_buf)
+            raise
+
+        return _parse_get_updates_response(data)
+
+    async def send_message(
+        self,
+        to_user_id: str,
+        item_list: list[MessageItem],
+        context_token: str = '',
+    ) -> None:
+        """Send a message to a user."""
+        items_payload = [_message_item_to_dict(item) for item in item_list]
+
+        payload = {
+            'msg': {
+                'from_user_id': '',
+                'to_user_id': to_user_id,
+                'client_id': f'langbot-{uuid.uuid4().hex[:16]}',
+                'message_type': WeixinMessage.TYPE_BOT,
+                'message_state': WeixinMessage.STATE_FINISH,
+                'item_list': items_payload,
+                'context_token': context_token or None,
+            }
+        }
+        await self._post('ilink/bot/sendmessage', payload)
+
+    async def send_text(self, to_user_id: str, text: str, context_token: str = '') -> None:
+        """Send a plain text message, automatically chunking if too long."""
+        chunks = _chunk_text(text)
+        for chunk in chunks:
+            item = MessageItem(type=MessageItem.TEXT, text_item=TextItem(text=chunk))
+            await self.send_message(to_user_id, [item], context_token)
+
+    async def get_config(self, ilink_user_id: str, context_token: str = '') -> GetConfigResponse:
+        """Get bot config including typing_ticket."""
+        data = await self._post(
+            'ilink/bot/getconfig',
+            {'ilink_user_id': ilink_user_id, 'context_token': context_token or None},
+            timeout=DEFAULT_CONFIG_TIMEOUT,
+        )
+        return GetConfigResponse(
+            ret=data.get('ret'),
+            errmsg=data.get('errmsg'),
+            typing_ticket=data.get('typing_ticket'),
+        )
+
+    async def send_typing(self, ilink_user_id: str, typing_ticket: str, status: int = 1) -> None:
+        """Send typing indicator. status: 1=typing, 2=cancel."""
+        await self._post(
+            'ilink/bot/sendtyping',
+            {
+                'ilink_user_id': ilink_user_id,
+                'typing_ticket': typing_ticket,
+                'status': status,
+            },
+            timeout=DEFAULT_CONFIG_TIMEOUT,
+        )
+
+    async def stop_typing(self, ilink_user_id: str, typing_ticket: str) -> None:
+        """Cancel the typing indicator for a user."""
+        await self.send_typing(ilink_user_id, typing_ticket, status=2)
+
+    async def download_media(
+        self,
+        media: CDNMedia,
+    ) -> bytes:
+        """Download and decrypt a file from the WeChat CDN.
+
+        Args:
+            media: CDNMedia object with encrypt_query_param and aes_key.
+
+        Returns:
+            Decrypted file bytes.
+        """
+        from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
+        from cryptography.hazmat.primitives.padding import PKCS7
+
+        if not media.encrypt_query_param:
+            raise ApiError('CDN media has no encrypt_query_param', status=0)
+        if not media.aes_key:
+            raise ApiError('CDN media has no aes_key', status=0)
+
+        # Derive 16-byte AES key
+        # aes_key is base64-encoded; the decoded content may be:
+        #   - raw 16 bytes (direct AES key)
+        #   - 32-char hex string (decode hex to get 16 bytes)
+        raw = base64.b64decode(media.aes_key)
+        if len(raw) == 16:
+            aes_key = raw
+        elif len(raw) == 32:
+            # Hex-encoded 16-byte key
+            aes_key = bytes.fromhex(raw.decode('utf-8'))
+        else:
+            raise ApiError(f'Invalid AES key length: {len(raw)} (expected 16 or 32)', status=0)
+
+        # Download encrypted bytes from CDN
+        session = await self._get_session()
+        cdn_url = f'{CDN_BASE_URL}/download?encrypted_query_param={quote(media.encrypt_query_param, safe="")}'
+
+        async with session.get(cdn_url, timeout=aiohttp.ClientTimeout(total=120)) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise ApiError(f'CDN download failed: {resp.status} {text}', status=resp.status)
+            encrypted = await resp.read()
+
+        # Decrypt AES-128-ECB with PKCS7 padding
+        cipher = Cipher(algorithms.AES(aes_key), modes.ECB())
+        decryptor = cipher.decryptor()
+        padded = decryptor.update(encrypted) + decryptor.finalize()
+
+        unpadder = PKCS7(128).unpadder()
+        return unpadder.update(padded) + unpadder.finalize()
+
+    async def upload_media(
+        self,
+        file_bytes: bytes,
+        to_user_id: str,
+        media_type: int,
+    ) -> CDNMedia:
+        """Encrypt and upload media to WeChat CDN.
+
+        Args:
+            file_bytes: Raw file bytes to upload.
+            to_user_id: Recipient user ID.
+            media_type: 1=IMAGE, 2=VIDEO, 3=FILE, 4=VOICE.
+
+        Returns:
+            CDNMedia with encrypt_query_param and aes_key for use in sendMessage.
+        """
+        import hashlib
+
+        from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
+        from cryptography.hazmat.primitives.padding import PKCS7
+
+        # 1. Generate random 16-byte AES key
+        raw_key = os.urandom(16)
+        aes_key_hex = raw_key.hex()  # 32-char hex string
+
+        # 2. Encode key for CDNMedia: base64(hex_string) — same for all media types
+        # Matches official SDK: Buffer.from(aeskey_hex).toString("base64")
+        encoded_key = base64.b64encode(aes_key_hex.encode('utf-8')).decode('utf-8')
+
+        # 3. Encrypt file with AES-128-ECB + PKCS7
+        padder = PKCS7(128).padder()
+        padded = padder.update(file_bytes) + padder.finalize()
+        cipher = Cipher(algorithms.AES(raw_key), modes.ECB())
+        encryptor = cipher.encryptor()
+        encrypted = encryptor.update(padded) + encryptor.finalize()
+
+        # 4. Get upload URL
+        raw_md5 = hashlib.md5(file_bytes).hexdigest()
+        filekey = os.urandom(16).hex()  # 32-char hex, matches official SDK
+
+        upload_resp = await self.get_upload_url(
+            filekey=filekey,
+            media_type=media_type,
+            to_user_id=to_user_id,
+            rawsize=len(file_bytes),
+            rawfilemd5=raw_md5,
+            filesize=len(encrypted),
+            aeskey=aes_key_hex,  # hex string, as expected by the API
+        )
+
+        if not upload_resp.upload_param:
+            raise ApiError('Failed to get upload URL', status=0)
+
+        # 5. Upload to CDN
+        # upload_param is an opaque token from the server — pass it as-is
+        session = await self._get_session()
+        cdn_url = f'{CDN_BASE_URL}/upload?encrypted_query_param={quote(upload_resp.upload_param, safe="")}&filekey={quote(filekey, safe="")}'
+        logger.debug(
+            'CDN upload: url=%s raw_size=%d encrypted_size=%d md5=%s aeskey=%s',
+            cdn_url,
+            len(file_bytes),
+            len(encrypted),
+            raw_md5,
+            encoded_key,
+        )
+
+        async with session.post(
+            cdn_url,
+            data=encrypted,
+            headers={'Content-Type': 'application/octet-stream'},
+            timeout=aiohttp.ClientTimeout(total=120),
+        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                logger.error('CDN upload failed: status=%d url=%s body=%s', resp.status, cdn_url, text[:500])
+                raise ApiError(f'CDN upload failed: {resp.status} {text}', status=resp.status)
+            download_param = resp.headers.get('x-encrypted-param', '')
+
+        if not download_param:
+            raise ApiError('CDN upload succeeded but no x-encrypted-param returned', status=0)
+
+        return CDNMedia(
+            encrypt_query_param=download_param,
+            aes_key=encoded_key,
+            encrypt_type=1,
+        )
+
+    async def send_image(
+        self,
+        to_user_id: str,
+        image_bytes: bytes,
+        context_token: str = '',
+    ) -> None:
+        """Upload an image to CDN and send it."""
+        media = await self.upload_media(image_bytes, to_user_id, media_type=1)
+        item = MessageItem(
+            type=MessageItem.IMAGE,
+            image_item=ImageItem(
+                media=media,
+                aeskey=media.aes_key,
+            ),
+        )
+        await self.send_message(to_user_id, [item], context_token)
+
+    async def send_file(
+        self,
+        to_user_id: str,
+        file_bytes: bytes,
+        file_name: str,
+        context_token: str = '',
+    ) -> None:
+        """Upload a file to CDN and send it."""
+        import hashlib
+
+        media = await self.upload_media(file_bytes, to_user_id, media_type=3)
+        item = MessageItem(
+            type=MessageItem.FILE,
+            file_item=FileItem(
+                media=media,
+                file_name=file_name,
+                md5=hashlib.md5(file_bytes).hexdigest(),
+                len=str(len(file_bytes)),
+            ),
+        )
+        await self.send_message(to_user_id, [item], context_token)
+
+    async def send_voice(
+        self,
+        to_user_id: str,
+        voice_bytes: bytes,
+        playtime: int = 0,
+        context_token: str = '',
+    ) -> None:
+        """Upload a voice message to CDN and send it."""
+        media = await self.upload_media(voice_bytes, to_user_id, media_type=4)
+        item = MessageItem(
+            type=MessageItem.VOICE,
+            voice_item=VoiceItem(
+                media=media,
+                playtime=playtime,
+            ),
+        )
+        await self.send_message(to_user_id, [item], context_token)
+
+    async def get_upload_url(
+        self,
+        filekey: str,
+        media_type: int,
+        to_user_id: str,
+        rawsize: int,
+        rawfilemd5: str,
+        filesize: int,
+        thumb_rawsize: Optional[int] = None,
+        thumb_rawfilemd5: Optional[str] = None,
+        thumb_filesize: Optional[int] = None,
+        aeskey: Optional[str] = None,
+    ) -> GetUploadUrlResponse:
+        """Get a pre-signed CDN upload URL."""
+        payload: dict = {
+            'filekey': filekey,
+            'media_type': media_type,
+            'to_user_id': to_user_id,
+            'rawsize': rawsize,
+            'rawfilemd5': rawfilemd5,
+            'filesize': filesize,
+            'no_need_thumb': True,
+        }
+        if thumb_rawsize is not None:
+            payload['thumb_rawsize'] = thumb_rawsize
+        if thumb_rawfilemd5 is not None:
+            payload['thumb_rawfilemd5'] = thumb_rawfilemd5
+        if thumb_filesize is not None:
+            payload['thumb_filesize'] = thumb_filesize
+        if aeskey is not None:
+            payload['aeskey'] = aeskey
+
+        data = await self._post('ilink/bot/getuploadurl', payload)
+        logger.debug('get_upload_url response: %s', data)
+        return GetUploadUrlResponse(
+            upload_param=data.get('upload_param'),
+            thumb_upload_param=data.get('thumb_upload_param'),
+        )
+
+    # -----------------------------------------------------------------------
+    # QR Code Login
+    # -----------------------------------------------------------------------
+
+    async def fetch_qrcode(self, bot_type: str = DEFAULT_BOT_TYPE) -> QRCodeResponse:
+        """Fetch a QR code for WeChat login authorization (GET, no auth needed)."""
+        session = await self._get_session()
+        url = f'{self.base_url}/ilink/bot/get_bot_qrcode?bot_type={bot_type}'
+
+        async with session.get(url, timeout=aiohttp.ClientTimeout(total=DEFAULT_API_TIMEOUT)) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise ApiError(
+                    f'Failed to fetch QR code: {resp.status} {text}',
+                    status=resp.status,
+                )
+            data = await resp.json(content_type=None)
+
+        logger.debug(
+            'fetch_qrcode response: qrcode=%s, img=%s', data.get('qrcode'), bool(data.get('qrcode_img_content'))
+        )
+
+        return QRCodeResponse(
+            qrcode=data.get('qrcode'),
+            qrcode_img_content=data.get('qrcode_img_content'),
+        )
+
+    async def _fetch_qr_image_base64(self, url: str) -> str:
+        """Generate a QR code image from the URL and return a data URI string.
+
+        The qrcode_img_content URL points to an HTML page (not a raw image),
+        so we generate the QR code locally using the qrcode library.
+        """
+        import qrcode
+
+        qr = qrcode.QRCode(error_correction=qrcode.constants.ERROR_CORRECT_L)
+        qr.add_data(url)
+        qr.make(fit=True)
+        img = qr.make_image(fill_color='black', back_color='white')
+
+        buf = io.BytesIO()
+        img.save(buf, format='PNG')
+        b64 = base64.b64encode(buf.getvalue()).decode('utf-8')
+        return f'data:image/png;base64,{b64}'
+
+    async def poll_qrcode_status(self, qrcode: str) -> QRStatusResponse:
+        """Long-poll the QR code scan status (GET with iLink-App-ClientVersion header)."""
+        session = await self._get_session()
+        url = f'{self.base_url}/ilink/bot/get_qrcode_status?qrcode={quote(qrcode, safe="")}'
+        headers = {'iLink-App-ClientVersion': '1'}
+
+        try:
+            async with session.get(
+                url, headers=headers, timeout=aiohttp.ClientTimeout(total=DEFAULT_QR_POLL_TIMEOUT)
+            ) as resp:
+                if resp.status != 200:
+                    text = await resp.text()
+                    raise ApiError(
+                        f'Failed to poll QR status: {resp.status} {text}',
+                        status=resp.status,
+                    )
+                data = await resp.json(content_type=None)
+                logger.debug('QR status poll response: %s', data)
+        except (asyncio.TimeoutError, aiohttp.ServerTimeoutError):
+            return QRStatusResponse(status='wait')
+
+        return QRStatusResponse(
+            status=data.get('status'),
+            bot_token=data.get('bot_token'),
+            ilink_bot_id=data.get('ilink_bot_id'),
+            baseurl=data.get('baseurl'),
+            ilink_user_id=data.get('ilink_user_id'),
+        )
+
+    async def login(
+        self,
+        max_retries: int = 5,
+        poll_timeout_ms: int = 480_000,
+        on_qrcode: Optional[typing.Callable[[str, str], typing.Any]] = None,
+        on_status: Optional[typing.Callable[[str], typing.Any]] = None,
+    ) -> LoginResult:
+        """Complete QR code login flow with auto-retry on expiry.
+
+        Args:
+            max_retries: Max number of QR code refreshes on expiry.
+            poll_timeout_ms: Timeout per QR code in milliseconds.
+            on_qrcode: Callback(qr_image_base64, qr_url) called each time a
+                        new QR code is fetched. Use this to display the QR code.
+            on_status: Callback(status_str) called on each status poll change.
+
+        Returns:
+            LoginResult with token, base_url, and account_id.
+
+        Raises:
+            ApiError: On unrecoverable API errors.
+            Exception: If all retries are exhausted.
+        """
+        last_qr_base64: Optional[str] = None
+
+        for attempt in range(max_retries):
+            qr_resp = await self.fetch_qrcode()
+            if not qr_resp.qrcode or not qr_resp.qrcode_img_content:
+                raise ApiError('Failed to get QR code from server', status=0)
+
+            # Convert QR image to base64 and notify caller
+            last_qr_base64 = await self._fetch_qr_image_base64(qr_resp.qrcode_img_content)
+            if on_qrcode:
+                try:
+                    result = on_qrcode(last_qr_base64, qr_resp.qrcode_img_content)
+                    if asyncio.iscoroutine(result) or asyncio.isfuture(result):
+                        await result
+                except Exception as e:
+                    logger.warning('on_qrcode callback error: %s', e)
+
+            # Poll until confirmed / expired / timeout
+            loop = asyncio.get_running_loop()
+            deadline = loop.time() + poll_timeout_ms / 1000.0
+
+            while loop.time() < deadline:
+                try:
+                    status_resp = await self.poll_qrcode_status(qr_resp.qrcode)
+                except Exception as e:
+                    logger.error('Error polling QR status: %s', e)
+                    await asyncio.sleep(2)
+                    continue
+
+                if on_status:
+                    try:
+                        cb_result = on_status(status_resp.status or 'unknown')
+                        if asyncio.iscoroutine(cb_result) or asyncio.isfuture(cb_result):
+                            await cb_result
+                    except Exception as e:
+                        logger.warning('on_status callback error: %s', e)
+
+                if status_resp.status == 'confirmed' and status_resp.bot_token:
+                    new_base_url = status_resp.baseurl or self.base_url
+                    # Update this client instance as well
+                    self.token = status_resp.bot_token
+                    self.base_url = new_base_url.rstrip('/')
+                    return LoginResult(
+                        token=status_resp.bot_token,
+                        base_url=new_base_url,
+                        account_id=status_resp.ilink_bot_id or '',
+                        qr_image_base64=last_qr_base64,
+                    )
+
+                if status_resp.status == 'expired':
+                    break  # retry with a new QR code
+
+                await asyncio.sleep(1)
+            else:
+                # While-loop ended without break → poll timeout, treat as expired
+                pass
+
+            remaining = max_retries - attempt - 1
+            if remaining > 0:
+                logger.info('QR code expired, refreshing... (%d retries left)', remaining)
+            else:
+                raise ApiError('QR code login failed: max retries exceeded', status=0)
+
+        # Should not reach here, but just in case
+        raise ApiError('QR code login failed', status=0)
+
+
+# ---------------------------------------------------------------------------
+# Parsing helpers
+# ---------------------------------------------------------------------------
+
+
+def _parse_cdn_media(data: Optional[dict]) -> Optional[CDNMedia]:
+    if not data:
+        return None
+    return CDNMedia(
+        encrypt_query_param=data.get('encrypt_query_param'),
+        aes_key=data.get('aes_key'),
+        encrypt_type=data.get('encrypt_type'),
+    )
+
+
+def _parse_message_item(data: dict) -> MessageItem:
+    item = MessageItem(
+        type=data.get('type'),
+        create_time_ms=data.get('create_time_ms'),
+        update_time_ms=data.get('update_time_ms'),
+        is_completed=data.get('is_completed'),
+        msg_id=data.get('msg_id'),
+    )
+
+    if data.get('text_item'):
+        item.text_item = TextItem(text=data['text_item'].get('text'))
+
+    if data.get('image_item'):
+        img = data['image_item']
+        item.image_item = ImageItem(
+            media=_parse_cdn_media(img.get('media')),
+            thumb_media=_parse_cdn_media(img.get('thumb_media')),
+            aeskey=img.get('aeskey'),
+            url=img.get('url'),
+            mid_size=img.get('mid_size'),
+        )
+
+    if data.get('voice_item'):
+        v = data['voice_item']
+        item.voice_item = VoiceItem(
+            media=_parse_cdn_media(v.get('media')),
+            encode_type=v.get('encode_type'),
+            playtime=v.get('playtime'),
+            text=v.get('text'),
+        )
+
+    if data.get('file_item'):
+        f = data['file_item']
+        item.file_item = FileItem(
+            media=_parse_cdn_media(f.get('media')),
+            file_name=f.get('file_name'),
+            md5=f.get('md5'),
+            len=f.get('len'),
+        )
+
+    if data.get('video_item'):
+        vid = data['video_item']
+        item.video_item = VideoItem(
+            media=_parse_cdn_media(vid.get('media')),
+            video_size=vid.get('video_size'),
+            play_length=vid.get('play_length'),
+            video_md5=vid.get('video_md5'),
+            thumb_media=_parse_cdn_media(vid.get('thumb_media')),
+        )
+
+    if data.get('ref_msg'):
+        ref = data['ref_msg']
+        item.ref_msg = RefMessage(
+            title=ref.get('title'),
+            message_item=_parse_message_item(ref['message_item']) if ref.get('message_item') else None,
+        )
+
+    return item
+
+
+def _parse_weixin_message(data: dict) -> WeixinMessage:
+    msg = WeixinMessage(
+        seq=data.get('seq'),
+        message_id=data.get('message_id'),
+        from_user_id=data.get('from_user_id'),
+        to_user_id=data.get('to_user_id'),
+        client_id=data.get('client_id'),
+        create_time_ms=data.get('create_time_ms'),
+        session_id=data.get('session_id'),
+        group_id=data.get('group_id'),
+        message_type=data.get('message_type'),
+        message_state=data.get('message_state'),
+        context_token=data.get('context_token'),
+    )
+    if data.get('item_list'):
+        msg.item_list = [_parse_message_item(item) for item in data['item_list']]
+    return msg
+
+
+def _parse_get_updates_response(data: dict) -> GetUpdatesResponse:
+    resp = GetUpdatesResponse(
+        ret=data.get('ret'),
+        errcode=data.get('errcode'),
+        errmsg=data.get('errmsg'),
+        get_updates_buf=data.get('get_updates_buf'),
+        longpolling_timeout_ms=data.get('longpolling_timeout_ms'),
+    )
+    if data.get('msgs'):
+        resp.msgs = [_parse_weixin_message(m) for m in data['msgs']]
+    return resp
+
+
+def _cdn_media_to_dict(media: Optional[CDNMedia]) -> Optional[dict]:
+    if not media:
+        return None
+    d: dict = {}
+    if media.encrypt_query_param is not None:
+        d['encrypt_query_param'] = media.encrypt_query_param
+    if media.aes_key is not None:
+        d['aes_key'] = media.aes_key
+    if media.encrypt_type is not None:
+        d['encrypt_type'] = media.encrypt_type
+    return d or None
+
+
+def _message_item_to_dict(item: MessageItem) -> dict:
+    d: dict = {'type': item.type}
+
+    if item.text_item:
+        d['text_item'] = {'text': item.text_item.text}
+
+    if item.image_item:
+        img_d: dict = {}
+        if item.image_item.media:
+            img_d['media'] = _cdn_media_to_dict(item.image_item.media)
+        if item.image_item.mid_size is not None:
+            img_d['mid_size'] = item.image_item.mid_size
+        d['image_item'] = img_d
+
+    if item.voice_item:
+        voice_d: dict = {}
+        if item.voice_item.media:
+            voice_d['media'] = _cdn_media_to_dict(item.voice_item.media)
+        if item.voice_item.playtime is not None:
+            voice_d['playtime'] = item.voice_item.playtime
+        d['voice_item'] = voice_d
+
+    if item.file_item:
+        file_d: dict = {}
+        if item.file_item.media:
+            file_d['media'] = _cdn_media_to_dict(item.file_item.media)
+        if item.file_item.file_name:
+            file_d['file_name'] = item.file_item.file_name
+        if item.file_item.len:
+            file_d['len'] = item.file_item.len
+        d['file_item'] = file_d
+
+    if item.video_item:
+        vid_d: dict = {}
+        if item.video_item.media:
+            vid_d['media'] = _cdn_media_to_dict(item.video_item.media)
+        if item.video_item.video_size is not None:
+            vid_d['video_size'] = item.video_item.video_size
+        d['video_item'] = vid_d
+
+    return d

src/langbot/libs/openclaw_weixin_api/types.py

@@ -0,0 +1,200 @@
+"""Type definitions for the OpenClaw WeChat API, mirroring the upstream protocol."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Optional
+
+SESSION_EXPIRED_ERRCODE = -14
+
+
+class ApiError(Exception):
+    """Structured error raised by the OpenClaw WeChat API."""
+
+    def __init__(
+        self,
+        message: str,
+        *,
+        status: int = 0,
+        code: int | None = None,
+        payload: Any = None,
+    ):
+        super().__init__(message)
+        self.status = status
+        self.code = code
+        self.payload = payload
+
+    @property
+    def is_session_expired(self) -> bool:
+        return self.code == SESSION_EXPIRED_ERRCODE
+
+
+@dataclass
+class CDNMedia:
+    encrypt_query_param: Optional[str] = None
+    aes_key: Optional[str] = None
+    encrypt_type: Optional[int] = None
+
+
+@dataclass
+class TextItem:
+    text: Optional[str] = None
+
+
+@dataclass
+class ImageItem:
+    media: Optional[CDNMedia] = None
+    thumb_media: Optional[CDNMedia] = None
+    aeskey: Optional[str] = None
+    url: Optional[str] = None
+    mid_size: Optional[int] = None
+    thumb_size: Optional[int] = None
+    thumb_height: Optional[int] = None
+    thumb_width: Optional[int] = None
+    hd_size: Optional[int] = None
+    _downloaded_bytes: Optional[bytes] = field(default=None, repr=False)
+
+
+@dataclass
+class VoiceItem:
+    media: Optional[CDNMedia] = None
+    encode_type: Optional[int] = None
+    bits_per_sample: Optional[int] = None
+    sample_rate: Optional[int] = None
+    playtime: Optional[int] = None
+    text: Optional[str] = None
+    _downloaded_bytes: Optional[bytes] = field(default=None, repr=False)
+
+
+@dataclass
+class FileItem:
+    media: Optional[CDNMedia] = None
+    file_name: Optional[str] = None
+    md5: Optional[str] = None
+    len: Optional[str] = None
+    _downloaded_bytes: Optional[bytes] = field(default=None, repr=False)
+
+
+@dataclass
+class VideoItem:
+    media: Optional[CDNMedia] = None
+    video_size: Optional[int] = None
+    play_length: Optional[int] = None
+    video_md5: Optional[str] = None
+    thumb_media: Optional[CDNMedia] = None
+    thumb_size: Optional[int] = None
+    thumb_height: Optional[int] = None
+    thumb_width: Optional[int] = None
+    _downloaded_bytes: Optional[bytes] = field(default=None, repr=False)
+
+
+@dataclass
+class RefMessage:
+    message_item: Optional[MessageItem] = None
+    title: Optional[str] = None
+
+
+@dataclass
+class MessageItem:
+    """A single content item inside a WeixinMessage."""
+
+    # Item types
+    NONE = 0
+    TEXT = 1
+    IMAGE = 2
+    VOICE = 3
+    FILE = 4
+    VIDEO = 5
+
+    type: Optional[int] = None
+    create_time_ms: Optional[int] = None
+    update_time_ms: Optional[int] = None
+    is_completed: Optional[bool] = None
+    msg_id: Optional[str] = None
+    ref_msg: Optional[RefMessage] = None
+    text_item: Optional[TextItem] = None
+    image_item: Optional[ImageItem] = None
+    voice_item: Optional[VoiceItem] = None
+    file_item: Optional[FileItem] = None
+    video_item: Optional[VideoItem] = None
+
+
+@dataclass
+class WeixinMessage:
+    """Unified message from getUpdates or for sendMessage."""
+
+    # Message types
+    TYPE_USER = 1
+    TYPE_BOT = 2
+
+    # Message states
+    STATE_NEW = 0
+    STATE_GENERATING = 1
+    STATE_FINISH = 2
+
+    seq: Optional[int] = None
+    message_id: Optional[int] = None
+    from_user_id: Optional[str] = None
+    to_user_id: Optional[str] = None
+    client_id: Optional[str] = None
+    create_time_ms: Optional[int] = None
+    update_time_ms: Optional[int] = None
+    delete_time_ms: Optional[int] = None
+    session_id: Optional[str] = None
+    group_id: Optional[str] = None
+    message_type: Optional[int] = None
+    message_state: Optional[int] = None
+    item_list: Optional[list[MessageItem]] = None
+    context_token: Optional[str] = None
+
+
+@dataclass
+class GetUpdatesResponse:
+    ret: Optional[int] = None
+    errcode: Optional[int] = None
+    errmsg: Optional[str] = None
+    msgs: list[WeixinMessage] = field(default_factory=list)
+    get_updates_buf: Optional[str] = None
+    longpolling_timeout_ms: Optional[int] = None
+
+
+@dataclass
+class GetConfigResponse:
+    ret: Optional[int] = None
+    errmsg: Optional[str] = None
+    typing_ticket: Optional[str] = None
+
+
+@dataclass
+class GetUploadUrlResponse:
+    upload_param: Optional[str] = None
+    thumb_upload_param: Optional[str] = None
+
+
+@dataclass
+class QRCodeResponse:
+    """Response from get_bot_qrcode endpoint."""
+
+    qrcode: Optional[str] = None
+    qrcode_img_content: Optional[str] = None
+
+
+@dataclass
+class QRStatusResponse:
+    """Response from get_qrcode_status endpoint."""
+
+    status: Optional[str] = None  # "wait" | "scaned" | "confirmed" | "expired"
+    bot_token: Optional[str] = None
+    ilink_bot_id: Optional[str] = None
+    baseurl: Optional[str] = None
+    ilink_user_id: Optional[str] = None
+
+
+@dataclass
+class LoginResult:
+    """Result returned by the login flow."""
+
+    token: str
+    base_url: str
+    account_id: str
+    qr_image_base64: Optional[str] = None  # data URI of the last QR code shown

src/langbot/libs/qq_official_api/api.py

@@ -10,38 +10,20 @@ import traceback
 from cryptography.hazmat.primitives.asymmetric import ed25519
 
 
-def handle_validation(body: dict, bot_secret: str):
-    # bot正确的secert是32位的，此处仅为了适配演示demo
-    while len(bot_secret) < 32:
-        bot_secret = bot_secret * 2
-    bot_secret = bot_secret[:32]
-    # 实际使用场景中以上三行内容可清除
-
-    seed_bytes = bot_secret.encode()
-
-    signing_key = ed25519.Ed25519PrivateKey.from_private_bytes(seed_bytes)
-
-    msg = body['d']['event_ts'] + body['d']['plain_token']
-    msg_bytes = msg.encode()
-
-    signature = signing_key.sign(msg_bytes)
-
-    signature_hex = signature.hex()
-
-    response = {'plain_token': body['d']['plain_token'], 'signature': signature_hex}
-
-    return response
-
-
 class QQOfficialClient:
-    def __init__(self, secret: str, token: str, app_id: str, logger: None):
+    def __init__(self, secret: str, token: str, app_id: str, logger: None, unified_mode: bool = False):
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command',
-            'handle_callback',
-            self.handle_callback_request,
-            methods=['GET', 'POST'],
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command',
+                'handle_callback',
+                self.handle_callback_request,
+                methods=['GET', 'POST'],
+            )
+
         self.secret = secret
         self.token = token
         self.app_id = app_id
@@ -82,18 +64,43 @@ class QQOfficialClient:
                 raise Exception(f'获取access_token失败: {e}')
 
     async def handle_callback_request(self):
-        """处理回调请求"""
+        """处理回调请求（独立端口模式，使用全局 request）"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
+        """
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """处理回调请求的内部实现。
+
+        Args:
+            req: Quart Request 对象
+        """
         try:
-            # 读取请求数据
-            body = await request.get_data()
+            body = await req.get_data()
+
+            print(f'[QQ Official] Received request, body length: {len(body)}')
+
+            if not body or len(body) == 0:
+                print('[QQ Official] Received empty body, might be health check or GET request')
+                return {'code': 0, 'message': 'ok'}, 200
+
             payload = json.loads(body)
 
-            # 验证是否为回调验证请求
             if payload.get('op') == 13:
-                # 生成签名
-                response = handle_validation(payload, self.secret)
-
-                return response
+                validation_data = payload.get('d')
+                if not validation_data:
+                    return {'error': "missing 'd' field"}, 400
+                response = await self.verify(validation_data)
+                return response, 200
 
             if payload.get('op') == 0:
                 message_data = await self.get_message(payload)
@@ -104,6 +111,7 @@ class QQOfficialClient:
             return {'code': 0, 'message': 'success'}
 
         except Exception as e:
+            print(f'[QQ Official] ERROR: {traceback.format_exc()}')
             await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
             return {'error': str(e)}, 400
 
@@ -261,3 +269,26 @@ class QQOfficialClient:
         if self.access_token_expiry_time is None:
             return True
         return time.time() > self.access_token_expiry_time
+
+    async def repeat_seed(self, bot_secret: str, target_size: int = 32) -> bytes:
+        seed = bot_secret
+        while len(seed) < target_size:
+            seed *= 2
+        return seed[:target_size].encode('utf-8')
+
+    async def verify(self, validation_payload: dict):
+        seed = await self.repeat_seed(self.secret)
+        private_key = ed25519.Ed25519PrivateKey.from_private_bytes(seed)
+
+        event_ts = validation_payload.get('event_ts', '')
+        plain_token = validation_payload.get('plain_token', '')
+        msg = event_ts + plain_token
+
+        # sign
+        signature = private_key.sign(msg.encode()).hex()
+
+        response = {
+            'plain_token': plain_token,
+            'signature': signature,
+        }
+        return response

src/langbot/libs/slack_api/api.py

@@ -8,14 +8,19 @@ import langbot_plugin.api.entities.builtin.platform.events as platform_events
 
 
 class SlackClient:
-    def __init__(self, bot_token: str, signing_secret: str, logger: None):
+    def __init__(self, bot_token: str, signing_secret: str, logger: None, unified_mode: bool = False):
         self.bot_token = bot_token
         self.signing_secret = signing_secret
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
         self.client = AsyncWebClient(self.bot_token)
-        self.app.add_url_rule(
-            '/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST']
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST']
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -23,8 +28,28 @@ class SlackClient:
         self.logger = logger
 
     async def handle_callback_request(self):
+        """处理回调请求（独立端口模式，使用全局 request）"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
+        """
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """处理回调请求的内部实现。
+
+        Args:
+            req: Quart Request 对象
+        """
         try:
-            body = await request.get_data()
+            body = await req.get_data()
             data = json.loads(body)
             if 'type' in data:
                 if data['type'] == 'url_verification':

src/langbot/libs/wechatpad_api/util/http_util.py

@@ -1,5 +1,5 @@
 import requests
-import aiohttp
+from langbot.pkg.utils import httpclient
 
 
 def post_json(base_url, token, data=None):
@@ -63,16 +63,16 @@ async def async_request(
     """
     headers = {'Content-Type': 'application/json'}
     url = f'{base_url}?key={token_key}'
-    async with aiohttp.ClientSession() as session:
-        async with session.request(
-            method=method, 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()
-            # print(result)
-            return result
-            # if result.get('Code') == 200:
-            #
-            #     return await result
-            # else:
-            #     raise RuntimeError("请求失败",response.text)
+    session = httpclient.get_session()
+    async with session.request(
+        method=method, 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()
+        # print(result)
+        return result
+        # if result.get('Code') == 200:
+        #
+        #     return await result
+        # else:
+        #     raise RuntimeError("请求失败",response.text)

src/langbot/libs/wecom_ai_bot_api/api.py

@@ -6,7 +6,8 @@ import traceback
 import uuid
 import xml.etree.ElementTree as ET
 from dataclasses import dataclass, field
-from typing import Any, Callable, Optional
+import re
+from typing import Any, Callable, Optional, Tuple
 from urllib.parse import unquote
 
 import httpx
@@ -199,8 +200,368 @@ class StreamSessionManager:
                 self._msg_index.pop(msg_id, None)
 
 
+def _decrypt_file(encrypted_data: bytes, aes_key_str: str) -> bytes:
+    """Decrypt AES-256-CBC encrypted file data.
+
+    Aligned with the official WeCom AI Bot Python SDK (crypto_utils.py).
+
+    Args:
+        encrypted_data: The raw encrypted bytes.
+        aes_key_str: Base64-encoded AES key (may lack padding).
+
+    Returns:
+        Decrypted bytes with PKCS#7 padding removed.
+    """
+    if not encrypted_data:
+        raise ValueError('encrypted_data is empty')
+    if not aes_key_str:
+        raise ValueError('aes_key is empty')
+
+    # Python's base64.b64decode requires proper padding (length % 4 == 0).
+    # Node.js Buffer.from tolerates missing '=', so we must pad manually.
+    remainder = len(aes_key_str) % 4
+    if remainder != 0:
+        aes_key_str = aes_key_str + '=' * (4 - remainder)
+    key = base64.b64decode(aes_key_str)
+
+    iv = key[:16]
+
+    cipher = AES.new(key, AES.MODE_CBC, iv)
+
+    # Ensure encrypted data is aligned to AES block size (16 bytes).
+    # Node.js setAutoPadding(false) silently handles unaligned data,
+    # but PyCryptodome will raise an error.
+    block_size = 16
+    data_remainder = len(encrypted_data) % block_size
+    if data_remainder != 0:
+        encrypted_data = encrypted_data + b'\x00' * (block_size - data_remainder)
+
+    decrypted = cipher.decrypt(encrypted_data)
+
+    # Remove PKCS#7 padding with validation
+    if len(decrypted) == 0:
+        raise ValueError('Decrypted data is empty')
+
+    pad_len = decrypted[-1]
+    if pad_len < 1 or pad_len > 32 or pad_len > len(decrypted):
+        raise ValueError(f'Invalid PKCS#7 padding value: {pad_len}')
+
+    # Verify all padding bytes are consistent
+    for i in range(len(decrypted) - pad_len, len(decrypted)):
+        if decrypted[i] != pad_len:
+            raise ValueError('Invalid PKCS#7 padding: padding bytes mismatch')
+
+    return decrypted[: len(decrypted) - pad_len]
+
+
+def _extract_filename(content_disposition: str) -> Optional[str]:
+    """Extract filename from a Content-Disposition header value."""
+    if not content_disposition:
+        return None
+    # RFC 5987: filename*=UTF-8''xxx
+    utf8_match = re.search(r"filename\*=UTF-8''([^;\s]+)", content_disposition, re.IGNORECASE)
+    if utf8_match:
+        return unquote(utf8_match.group(1))
+    # Standard: filename="xxx" or filename=xxx
+    match = re.search(r'filename="?([^";\s]+)"?', content_disposition, re.IGNORECASE)
+    if match:
+        return unquote(match.group(1))
+    return None
+
+
+def _bytes_to_data_uri(data: bytes) -> str:
+    """Convert raw bytes to a data URI with auto-detected MIME type."""
+    if data.startswith(b'\xff\xd8'):
+        mime_type = 'image/jpeg'
+    elif data.startswith(b'\x89PNG'):
+        mime_type = 'image/png'
+    elif data.startswith((b'GIF87a', b'GIF89a')):
+        mime_type = 'image/gif'
+    elif data.startswith(b'BM'):
+        mime_type = 'image/bmp'
+    elif data.startswith(b'II*\x00') or data.startswith(b'MM\x00*'):
+        mime_type = 'image/tiff'
+    elif data[:4] == b'%PDF':
+        mime_type = 'application/pdf'
+    elif data[:4] == b'PK\x03\x04':
+        mime_type = 'application/zip'
+    else:
+        mime_type = 'application/octet-stream'
+
+    base64_str = base64.b64encode(data).decode('utf-8')
+    return f'data:{mime_type};base64,{base64_str}'
+
+
+async def download_encrypted_file(
+    download_url: str, aes_key: str, logger: EventLogger
+) -> Tuple[Optional[bytes], Optional[str]]:
+    """Download an AES-encrypted file from WeChat Work and decrypt it.
+
+    Args:
+        download_url: The encrypted file download URL.
+        aes_key: The AES key for decryption (base64-encoded, per-message aeskey
+                 or platform EncodingAESKey).
+        logger: Logger instance.
+
+    Returns:
+        A tuple of (decrypted_bytes, filename) or (None, None) on failure.
+    """
+    if not download_url:
+        return None, None
+    if not aes_key:
+        await logger.error('download_encrypted_file: aes_key is empty, cannot decrypt')
+        return None, None
+
+    filename: Optional[str] = None
+    try:
+        async with httpx.AsyncClient(timeout=30.0) as client:
+            response = await client.get(download_url)
+            if response.status_code != 200:
+                await logger.error(f'Failed to download file (HTTP {response.status_code}): {response.text[:200]}')
+                return None, None
+            encrypted_bytes = response.content
+            filename = _extract_filename(response.headers.get('content-disposition', ''))
+    except Exception:
+        await logger.error(f'Failed to download file: {traceback.format_exc()}')
+        return None, None
+
+    try:
+        decrypted = _decrypt_file(encrypted_bytes, aes_key)
+        return decrypted, filename
+    except Exception:
+        await logger.error(f'Failed to decrypt file: {traceback.format_exc()}')
+        return None, None
+
+
+async def parse_wecom_bot_message(
+    msg_json: dict[str, Any], encoding_aes_key: str, logger: EventLogger
+) -> dict[str, Any]:
+    """Parse a decrypted WeChat Work AI Bot message JSON into a unified message dict.
+
+    This is the shared message parsing logic used by both webhook and WebSocket modes.
+
+    Args:
+        msg_json: The decrypted message JSON from WeChat Work.
+        encoding_aes_key: AES key for file decryption.
+        logger: Logger instance.
+
+    Returns:
+        A dict suitable for constructing a WecomBotEvent.
+    """
+    message_data: dict[str, Any] = {}
+
+    msg_type = msg_json.get('msgtype', '')
+    if msg_type:
+        message_data['msgtype'] = msg_type
+
+    if msg_json.get('chattype', '') == 'single':
+        message_data['type'] = 'single'
+    elif msg_json.get('chattype', '') == 'group':
+        message_data['type'] = 'group'
+
+    max_inline_file_size = 5 * 1024 * 1024
+
+    async def _safe_download(url: str, per_msg_aeskey: str = '') -> Tuple[Optional[bytes], Optional[str]]:
+        """Download and decrypt a file, preferring per-message aeskey over platform key."""
+        if not url:
+            return None, None
+        key = per_msg_aeskey or encoding_aes_key
+        if not key:
+            await logger.warning('No AES key available for file decryption, skipping download')
+            return None, None
+        return await download_encrypted_file(url, key, logger)
+
+    async def _safe_download_as_data_uri(url: str, per_msg_aeskey: str = '') -> Optional[str]:
+        """Download, decrypt, and convert to data URI for backward compatibility."""
+        data, _filename = await _safe_download(url, per_msg_aeskey)
+        if data:
+            return _bytes_to_data_uri(data)
+        return None
+
+    if msg_type == 'text':
+        message_data['content'] = msg_json.get('text', {}).get('content')
+    elif msg_type == 'markdown':
+        message_data['content'] = msg_json.get('markdown', {}).get('content') or msg_json.get('text', {}).get(
+            'content', ''
+        )
+    elif msg_type == 'image':
+        image_info = msg_json.get('image', {})
+        picurl = image_info.get('url', '')
+        per_msg_aeskey = image_info.get('aeskey', '')
+        base64_data = await _safe_download_as_data_uri(picurl, per_msg_aeskey)
+        if base64_data:
+            message_data['picurl'] = base64_data
+            message_data['images'] = [base64_data]
+    elif msg_type == 'voice':
+        voice_info = msg_json.get('voice', {}) or {}
+        download_url = voice_info.get('url')
+        per_msg_aeskey = voice_info.get('aeskey', '')
+        message_data['voice'] = {
+            'url': download_url,
+            'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
+            'filesize': voice_info.get('filesize') or voice_info.get('size'),
+            'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
+        }
+        if voice_info.get('content'):
+            message_data['content'] = voice_info.get('content')
+        if (message_data['voice'].get('filesize') or 0) <= max_inline_file_size:
+            voice_base64 = await _safe_download_as_data_uri(download_url, per_msg_aeskey)
+            if voice_base64:
+                message_data['voice']['base64'] = voice_base64
+    elif msg_type == 'video':
+        video_info = msg_json.get('video', {}) or {}
+        download_url = video_info.get('url')
+        per_msg_aeskey = video_info.get('aeskey', '')
+        video_data = {
+            'url': download_url,
+            'filesize': video_info.get('filesize') or video_info.get('size'),
+            'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
+            'md5sum': video_info.get('md5sum') or video_info.get('md5'),
+            'filename': video_info.get('filename') or video_info.get('name'),
+        }
+        if (video_data.get('filesize') or 0) <= max_inline_file_size:
+            video_base64 = await _safe_download_as_data_uri(download_url, per_msg_aeskey)
+            if video_base64:
+                video_data['base64'] = video_base64
+        message_data['video'] = video_data
+    elif msg_type == 'file':
+        file_info = msg_json.get('file', {}) or {}
+        download_url = file_info.get('url') or file_info.get('fileurl')
+        per_msg_aeskey = file_info.get('aeskey', '')
+        file_data = {
+            'filename': file_info.get('filename') or file_info.get('name'),
+            'filesize': file_info.get('filesize') or file_info.get('size'),
+            'md5sum': file_info.get('md5sum') or file_info.get('md5'),
+            'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
+            'download_url': download_url,
+            'extra': file_info,
+        }
+        if (file_data.get('filesize') or 0) <= max_inline_file_size:
+            file_bytes, dl_filename = await _safe_download(download_url, per_msg_aeskey)
+            if file_bytes:
+                file_data['base64'] = _bytes_to_data_uri(file_bytes)
+                if dl_filename and not file_data.get('filename'):
+                    file_data['filename'] = dl_filename
+        message_data['file'] = file_data
+    elif msg_type == 'link':
+        message_data['link'] = msg_json.get('link', {})
+        if not message_data.get('content'):
+            title = message_data['link'].get('title', '')
+            desc = message_data['link'].get('description') or message_data['link'].get('digest', '')
+            message_data['content'] = '\n'.join(filter(None, [title, desc]))
+    elif msg_type == 'mixed':
+        items = msg_json.get('mixed', {}).get('msg_item', [])
+        texts = []
+        images = []
+        files = []
+        voices = []
+        videos = []
+        links = []
+        for item in items:
+            item_type = item.get('msgtype')
+            if item_type == 'text':
+                texts.append(item.get('text', {}).get('content', ''))
+            elif item_type == 'image':
+                img_info = item.get('image', {})
+                img_url = img_info.get('url')
+                img_aeskey = img_info.get('aeskey', '')
+                base64_data = await _safe_download_as_data_uri(img_url, img_aeskey)
+                if base64_data:
+                    images.append(base64_data)
+            elif item_type == 'file':
+                file_info = item.get('file', {}) or {}
+                download_url = file_info.get('url') or file_info.get('fileurl')
+                item_aeskey = file_info.get('aeskey', '')
+                file_data = {
+                    'filename': file_info.get('filename') or file_info.get('name'),
+                    'filesize': file_info.get('filesize') or file_info.get('size'),
+                    'md5sum': file_info.get('md5sum') or file_info.get('md5'),
+                    'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
+                    'download_url': download_url,
+                    'extra': file_info,
+                }
+                if (file_data.get('filesize') or 0) <= max_inline_file_size:
+                    file_bytes, dl_filename = await _safe_download(download_url, item_aeskey)
+                    if file_bytes:
+                        file_data['base64'] = _bytes_to_data_uri(file_bytes)
+                        if dl_filename and not file_data.get('filename'):
+                            file_data['filename'] = dl_filename
+                files.append(file_data)
+            elif item_type == 'voice':
+                voice_info = item.get('voice', {}) or {}
+                download_url = voice_info.get('url')
+                item_aeskey = voice_info.get('aeskey', '')
+                voice_data = {
+                    'url': download_url,
+                    'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
+                    'filesize': voice_info.get('filesize') or voice_info.get('size'),
+                    'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
+                }
+                if voice_info.get('content'):
+                    texts.append(voice_info.get('content'))
+                if (voice_data.get('filesize') or 0) <= max_inline_file_size:
+                    voice_base64 = await _safe_download_as_data_uri(download_url, item_aeskey)
+                    if voice_base64:
+                        voice_data['base64'] = voice_base64
+                voices.append(voice_data)
+            elif item_type == 'video':
+                video_info = item.get('video', {}) or {}
+                download_url = video_info.get('url')
+                item_aeskey = video_info.get('aeskey', '')
+                video_data = {
+                    'url': download_url,
+                    'filesize': video_info.get('filesize') or video_info.get('size'),
+                    'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
+                    'md5sum': video_info.get('md5sum') or video_info.get('md5'),
+                    'filename': video_info.get('filename') or video_info.get('name'),
+                }
+                if (video_data.get('filesize') or 0) <= max_inline_file_size:
+                    video_base64 = await _safe_download_as_data_uri(download_url, item_aeskey)
+                    if video_base64:
+                        video_data['base64'] = video_base64
+                videos.append(video_data)
+            elif item_type == 'link':
+                links.append(item.get('link', {}))
+
+        if texts:
+            message_data['content'] = ' '.join(texts)
+        if images:
+            message_data['images'] = images
+            message_data['picurl'] = images[0]
+        if files:
+            message_data['files'] = files
+            message_data['file'] = files[0]
+        if voices:
+            message_data['voices'] = voices
+            message_data['voice'] = voices[0]
+        if videos:
+            message_data['videos'] = videos
+            message_data['video'] = videos[0]
+        if links:
+            message_data['link'] = links[0]
+        if items:
+            message_data['attachments'] = items
+    else:
+        message_data['raw_msg'] = msg_json
+
+    from_info = msg_json.get('from', {})
+    message_data['userid'] = from_info.get('userid', '')
+    message_data['username'] = from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
+
+    if msg_json.get('chattype', '') == 'group':
+        message_data['chatid'] = msg_json.get('chatid', '')
+        message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
+
+    message_data['msgid'] = msg_json.get('msgid', '')
+
+    if msg_json.get('aibotid'):
+        message_data['aibotid'] = msg_json.get('aibotid', '')
+
+    return message_data
+
+
 class WecomBotClient:
-    def __init__(self, Token: str, EnCodingAESKey: str, Corpid: str, logger: EventLogger):
+    def __init__(self, Token: str, EnCodingAESKey: str, Corpid: str, logger: EventLogger, unified_mode: bool = False):
         """企业微信智能机器人客户端。
 
         Args:
@@ -208,6 +569,7 @@ class WecomBotClient:
             EnCodingAESKey: 企业微信消息加解密密钥。
             Corpid: 企业 ID。
             logger: 日志记录器。
+            unified_mode: 是否使用统一 webhook 模式（默认 False）。
 
         Example:
             >>> client = WecomBotClient(Token='token', EnCodingAESKey='aeskey', Corpid='corp', logger=logger)
@@ -217,10 +579,15 @@ class WecomBotClient:
         self.EnCodingAESKey = EnCodingAESKey
         self.Corpid = Corpid
         self.ReceiveId = ''
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command', 'handle_callback', self.handle_callback_request, methods=['POST', 'GET']
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command', 'handle_callback', self.handle_callback_request, methods=['POST', 'GET']
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -359,7 +726,7 @@ class WecomBotClient:
         return await self._encrypt_and_reply(payload, nonce)
 
     async def handle_callback_request(self):
-        """企业微信回调入口。
+        """企业微信回调入口（独立端口模式，使用全局 request）。
 
         Returns:
             Quart Response: 根据请求类型返回验证、首包或刷新结果。
@@ -367,15 +734,33 @@ class WecomBotClient:
         Example:
             作为 Quart 路由处理函数直接注册并使用。
         """
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
+        """
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """处理回调请求的内部实现，包括 GET 验证和 POST 消息接收。
+
+        Args:
+            req: Quart Request 对象
+        """
         try:
             self.wxcpt = WXBizMsgCrypt(self.Token, self.EnCodingAESKey, '')
-            await self.logger.info(f'{request.method} {request.url} {str(request.args)}')
 
-            if request.method == 'GET':
-                return await self._handle_get_callback()
+            if req.method == 'GET':
+                return await self._handle_get_callback(req)
 
-            if request.method == 'POST':
-                return await self._handle_post_callback()
+            if req.method == 'POST':
+                return await self._handle_post_callback(req)
 
             return Response('', status=405)
 
@@ -383,13 +768,13 @@ class WecomBotClient:
             await self.logger.error(traceback.format_exc())
             return Response('Internal Server Error', status=500)
 
-    async def _handle_get_callback(self) -> tuple[Response, int] | Response:
+    async def _handle_get_callback(self, req) -> tuple[Response, int] | Response:
         """处理企业微信的 GET 验证请求。"""
 
-        msg_signature = unquote(request.args.get('msg_signature', ''))
-        timestamp = unquote(request.args.get('timestamp', ''))
-        nonce = unquote(request.args.get('nonce', ''))
-        echostr = unquote(request.args.get('echostr', ''))
+        msg_signature = unquote(req.args.get('msg_signature', ''))
+        timestamp = unquote(req.args.get('timestamp', ''))
+        nonce = unquote(req.args.get('nonce', ''))
+        echostr = unquote(req.args.get('echostr', ''))
 
         if not all([msg_signature, timestamp, nonce, echostr]):
             await self.logger.error('请求参数缺失')
@@ -402,16 +787,16 @@ class WecomBotClient:
 
         return Response(decrypted_str, mimetype='text/plain')
 
-    async def _handle_post_callback(self) -> tuple[Response, int] | Response:
+    async def _handle_post_callback(self, req) -> tuple[Response, int] | Response:
         """处理企业微信的 POST 回调请求。"""
 
         self.stream_sessions.cleanup()
 
-        msg_signature = unquote(request.args.get('msg_signature', ''))
-        timestamp = unquote(request.args.get('timestamp', ''))
-        nonce = unquote(request.args.get('nonce', ''))
+        msg_signature = unquote(req.args.get('msg_signature', ''))
+        timestamp = unquote(req.args.get('timestamp', ''))
+        nonce = unquote(req.args.get('nonce', ''))
 
-        encrypted_json = await request.get_json()
+        encrypted_json = await req.get_json()
         encrypted_msg = (encrypted_json or {}).get('encrypt', '')
         if not encrypted_msg:
             await self.logger.error("请求体中缺少 'encrypt' 字段")
@@ -431,54 +816,7 @@ class WecomBotClient:
         return await self._handle_post_initial_response(msg_json, nonce)
 
     async def get_message(self, msg_json):
-        message_data = {}
-
-        if msg_json.get('chattype', '') == 'single':
-            message_data['type'] = 'single'
-        elif msg_json.get('chattype', '') == 'group':
-            message_data['type'] = 'group'
-
-        if msg_json.get('msgtype') == 'text':
-            message_data['content'] = msg_json.get('text', {}).get('content')
-        elif msg_json.get('msgtype') == 'image':
-            picurl = msg_json.get('image', {}).get('url', '')
-            base64 = await self.download_url_to_base64(picurl, self.EnCodingAESKey)
-            message_data['picurl'] = base64
-        elif msg_json.get('msgtype') == 'mixed':
-            items = msg_json.get('mixed', {}).get('msg_item', [])
-            texts = []
-            picurl = None
-            for item in items:
-                if item.get('msgtype') == 'text':
-                    texts.append(item.get('text', {}).get('content', ''))
-                elif item.get('msgtype') == 'image' and picurl is None:
-                    picurl = item.get('image', {}).get('url')
-
-            if texts:
-                message_data['content'] = ''.join(texts)  # 拼接所有 text
-            if picurl:
-                base64 = await self.download_url_to_base64(picurl, self.EnCodingAESKey)
-                message_data['picurl'] = base64  # 只保留第一个 image
-
-        # Extract user information
-        from_info = msg_json.get('from', {})
-        message_data['userid'] = from_info.get('userid', '')
-        message_data['username'] = (
-            from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
-        )
-
-        # Extract chat/group information
-        if msg_json.get('chattype', '') == 'group':
-            message_data['chatid'] = msg_json.get('chatid', '')
-            # Try to get group name if available
-            message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
-
-        message_data['msgid'] = msg_json.get('msgid', '')
-
-        if msg_json.get('aibotid'):
-            message_data['aibotid'] = msg_json.get('aibotid', '')
-
-        return message_data
+        return await parse_wecom_bot_message(msg_json, self.EnCodingAESKey, self.logger)
 
     async def _handle_message(self, event: wecombotevent.WecomBotEvent):
         """
@@ -546,39 +884,10 @@ class WecomBotClient:
         return decorator
 
     async def download_url_to_base64(self, download_url, encoding_aes_key):
-        async with httpx.AsyncClient() as client:
-            response = await client.get(download_url)
-            if response.status_code != 200:
-                await self.logger.error(f'failed to get file: {response.text}')
-                return None
-
-            encrypted_bytes = response.content
-
-        aes_key = base64.b64decode(encoding_aes_key + '=')  # base64 补齐
-        iv = aes_key[:16]
-
-        cipher = AES.new(aes_key, AES.MODE_CBC, iv)
-        decrypted = cipher.decrypt(encrypted_bytes)
-
-        pad_len = decrypted[-1]
-        decrypted = decrypted[:-pad_len]
-
-        if decrypted.startswith(b'\xff\xd8'):  # JPEG
-            mime_type = 'image/jpeg'
-        elif decrypted.startswith(b'\x89PNG'):  # PNG
-            mime_type = 'image/png'
-        elif decrypted.startswith((b'GIF87a', b'GIF89a')):  # GIF
-            mime_type = 'image/gif'
-        elif decrypted.startswith(b'BM'):  # BMP
-            mime_type = 'image/bmp'
-        elif decrypted.startswith(b'II*\x00') or decrypted.startswith(b'MM\x00*'):  # TIFF
-            mime_type = 'image/tiff'
-        else:
-            mime_type = 'application/octet-stream'
-
-        # 转 base64
-        base64_str = base64.b64encode(decrypted).decode('utf-8')
-        return f'data:{mime_type};base64,{base64_str}'
+        data, _filename = await download_encrypted_file(download_url, encoding_aes_key, self.logger)
+        if data:
+            return _bytes_to_data_uri(data)
+        return None
 
     async def run_task(self, host: str, port: int, *args, **kwargs):
         """

src/langbot/libs/wecom_ai_bot_api/wecombotevent.py

@@ -17,6 +17,13 @@ class WecomBotEvent(dict):
         """
         return self.get('type', '')
 
+    @property
+    def msgtype(self) -> str:
+        """
+        消息 msgtype
+        """
+        return self.get('msgtype', '')
+
     @property
     def userid(self) -> str:
         """
@@ -57,6 +64,55 @@ class WecomBotEvent(dict):
         """
         return self.get('picurl', '')
 
+    @property
+    def images(self):
+        """
+        图片列表（兼容 mixed）
+        """
+        return self.get('images', [])
+
+    @property
+    def file(self):
+        """
+        文件信息
+        """
+        return self.get('file', {})
+
+    @property
+    def voice(self):
+        """
+        语音信息
+        """
+        return self.get('voice', {})
+
+    @property
+    def video(self):
+        """
+        视频信息
+        """
+        return self.get('video', {})
+
+    @property
+    def link(self):
+        """
+        链接消息信息
+        """
+        return self.get('link', {})
+
+    @property
+    def location(self):
+        """
+        位置信息
+        """
+        return self.get('location', {})
+
+    @property
+    def attachments(self):
+        """
+        原始 mixed 中的附件项
+        """
+        return self.get('attachments', [])
+
     @property
     def chatid(self) -> str:
         """

src/langbot/libs/wecom_ai_bot_api/ws_client.py

@@ -0,0 +1,596 @@
+"""WeChat Work AI Bot WebSocket long connection client.
+
+Implements the WebSocket protocol for receiving messages and sending replies
+via a persistent connection to wss://openws.work.weixin.qq.com, as an
+alternative to the HTTP callback (webhook) mode.
+
+Protocol reference: https://developer.work.weixin.qq.com/document/path/101463
+Official Node.js SDK: https://github.com/WecomTeam/aibot-node-sdk
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import secrets
+import time
+import traceback
+from typing import Any, Callable, Optional
+
+import aiohttp
+
+from langbot.libs.wecom_ai_bot_api import wecombotevent
+from langbot.libs.wecom_ai_bot_api.api import parse_wecom_bot_message
+from langbot.pkg.platform.logger import EventLogger
+
+DEFAULT_WS_URL = 'wss://openws.work.weixin.qq.com'
+
+# WebSocket frame command constants
+CMD_SUBSCRIBE = 'aibot_subscribe'
+CMD_HEARTBEAT = 'ping'
+CMD_MSG_CALLBACK = 'aibot_msg_callback'
+CMD_EVENT_CALLBACK = 'aibot_event_callback'
+CMD_RESPOND_MSG = 'aibot_respond_msg'
+CMD_RESPOND_WELCOME = 'aibot_respond_welcome_msg'
+CMD_RESPOND_UPDATE = 'aibot_respond_update_msg'
+CMD_SEND_MSG = 'aibot_send_msg'
+
+
+def _generate_req_id(prefix: str) -> str:
+    """Generate a unique request ID in the format: {prefix}_{timestamp}_{random}."""
+    ts = int(time.time() * 1000)
+    rand = secrets.token_hex(4)
+    return f'{prefix}_{ts}_{rand}'
+
+
+class WecomBotWsClient:
+    """WeChat Work AI Bot WebSocket long connection client.
+
+    Provides message receiving, streaming reply, proactive message sending,
+    and event callback handling over a persistent WebSocket connection.
+    """
+
+    def __init__(
+        self,
+        bot_id: str,
+        secret: str,
+        logger: EventLogger,
+        encoding_aes_key: str = '',
+        ws_url: str = DEFAULT_WS_URL,
+        heartbeat_interval: float = 30.0,
+        max_reconnect_attempts: int = -1,
+        reconnect_base_delay: float = 1.0,
+        reconnect_max_delay: float = 30.0,
+    ):
+        self.bot_id = bot_id
+        self.secret = secret
+        self.logger = logger
+        self.encoding_aes_key = encoding_aes_key
+        self.ws_url = ws_url
+        self.heartbeat_interval = heartbeat_interval
+        self.max_reconnect_attempts = max_reconnect_attempts
+        self.reconnect_base_delay = reconnect_base_delay
+        self.reconnect_max_delay = reconnect_max_delay
+
+        self._ws: Optional[aiohttp.ClientWebSocketResponse] = None
+        self._session: Optional[aiohttp.ClientSession] = None
+        self._running = False
+        self._heartbeat_task: Optional[asyncio.Task] = None
+        self._missed_pong_count = 0
+        self._max_missed_pong = 2
+        self._reconnect_attempts = 0
+
+        # Message handler registry (same pattern as WecomBotClient)
+        self._message_handlers: dict[str, list[Callable]] = {}
+        # Message deduplication
+        self._msg_id_map: dict[str, int] = {}
+
+        # Pending ACK futures: req_id -> Future[dict]
+        self._pending_acks: dict[str, asyncio.Future] = {}
+        # Per-req_id serial reply queues
+        self._reply_queues: dict[str, asyncio.Queue] = {}
+        self._reply_workers: dict[str, asyncio.Task] = {}
+        self._reply_ack_timeout = 5.0
+
+        # Stream ID tracking for WebSocket mode
+        self._stream_ids: dict[str, str] = {}  # msg_id -> req_id|stream_id
+        # Dedup: skip sending when content hasn't changed
+        self._stream_last_content: dict[str, str] = {}  # msg_id -> last content sent
+
+    # ── Public API ──────────────────────────────────────────────────
+
+    async def connect(self):
+        """Connect to WebSocket server with automatic reconnection.
+
+        This method blocks until disconnect() is called or max reconnect
+        attempts are exhausted.
+        """
+        self._running = True
+        self._reconnect_attempts = 0
+
+        while self._running:
+            try:
+                await self._connect_once()
+            except Exception:
+                if not self._running:
+                    break
+                await self.logger.error(f'WebSocket connection error: {traceback.format_exc()}')
+
+            if not self._running:
+                break
+
+            # Reconnect with exponential backoff
+            if self.max_reconnect_attempts != -1 and self._reconnect_attempts >= self.max_reconnect_attempts:
+                await self.logger.error(f'Max reconnect attempts reached ({self.max_reconnect_attempts}), giving up')
+                break
+
+            self._reconnect_attempts += 1
+            delay = min(
+                self.reconnect_base_delay * (2 ** (self._reconnect_attempts - 1)),
+                self.reconnect_max_delay,
+            )
+            await self.logger.info(f'Reconnecting in {delay:.1f}s (attempt {self._reconnect_attempts})...')
+            await asyncio.sleep(delay)
+
+    async def disconnect(self):
+        """Gracefully disconnect from the WebSocket server."""
+        self._running = False
+        if self._heartbeat_task and not self._heartbeat_task.done():
+            self._heartbeat_task.cancel()
+        for task in self._reply_workers.values():
+            if not task.done():
+                task.cancel()
+        if self._ws and not self._ws.closed:
+            await self._ws.close()
+        self._ws = None
+        if self._session and not self._session.closed:
+            await self._session.close()
+        self._session = None
+
+    def on_message(self, msg_type: str) -> Callable:
+        """Decorator to register a message handler.
+
+        Same interface as WecomBotClient.on_message for compatibility.
+
+        Args:
+            msg_type: 'single', 'group', or specific message type.
+        """
+
+        def decorator(func: Callable[[wecombotevent.WecomBotEvent], Any]):
+            if msg_type not in self._message_handlers:
+                self._message_handlers[msg_type] = []
+            self._message_handlers[msg_type].append(func)
+            return func
+
+        return decorator
+
+    async def reply_stream(
+        self,
+        req_id: str,
+        stream_id: str,
+        content: str,
+        finish: bool = False,
+    ) -> Optional[dict]:
+        """Send a streaming reply frame.
+
+        Args:
+            req_id: The req_id from the original message frame (must be passed through).
+            stream_id: The stream ID for this streaming session.
+            content: The content to send (supports Markdown).
+            finish: Whether this is the final chunk.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        body = {
+            'msgtype': 'stream',
+            'stream': {
+                'id': stream_id,
+                'finish': finish,
+                'content': content,
+            },
+        }
+        return await self._send_reply(req_id, body)
+
+    async def reply_text(self, req_id: str, content: str) -> Optional[dict]:
+        """Send a non-streaming text reply.
+
+        Args:
+            req_id: The req_id from the original message frame.
+            content: The text content to reply.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        body = {
+            'msgtype': 'markdown',
+            'markdown': {
+                'content': content,
+            },
+        }
+        return await self._send_reply(req_id, body)
+
+    async def send_message(self, chat_id: str, content: str, msgtype: str = 'markdown') -> Optional[dict]:
+        """Proactively send a message to a specified chat.
+
+        Args:
+            chat_id: The chat ID (userid for single chat, chatid for group chat).
+            content: The message content.
+            msgtype: Message type, 'markdown' by default.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        req_id = _generate_req_id(CMD_SEND_MSG)
+        body: dict[str, Any] = {
+            'chatid': chat_id,
+            'msgtype': msgtype,
+        }
+        if msgtype == 'markdown':
+            body['markdown'] = {'content': content}
+        elif msgtype == 'text':
+            body['text'] = {'content': content}
+        return await self._send_reply(req_id, body, cmd=CMD_SEND_MSG)
+
+    async def push_stream_chunk(self, msg_id: str, content: str, is_final: bool = False) -> bool:
+        """Push a streaming chunk for a given message ID.
+
+        Compatible interface with WecomBotClient.push_stream_chunk.
+
+        Args:
+            msg_id: The original message ID.
+            content: The cumulative content from the pipeline.
+            is_final: Whether this is the final chunk.
+
+        Returns:
+            True if the stream session exists and chunk was sent.
+        """
+        key = self._stream_ids.get(msg_id)
+        if not key:
+            return False
+        req_id, stream_id = key.split('|', 1)
+        try:
+            # Skip sending if content hasn't changed (e.g. during tool call argument streaming)
+            if not is_final and content == self._stream_last_content.get(msg_id):
+                return True
+            await self.reply_stream(req_id, stream_id, content, finish=is_final)
+            self._stream_last_content[msg_id] = content
+            if is_final:
+                self._stream_ids.pop(msg_id, None)
+                self._stream_last_content.pop(msg_id, None)
+            return True
+        except Exception:
+            await self.logger.error(f'Failed to push stream chunk: {traceback.format_exc()}')
+            return False
+
+    async def set_message(self, msg_id: str, content: str):
+        """Fallback: send content as a final stream chunk or direct reply.
+
+        Compatible interface with WecomBotClient.set_message.
+        """
+        handled = await self.push_stream_chunk(msg_id, content, is_final=True)
+        if not handled:
+            await self.logger.warning(f'No active stream for msg_id={msg_id}, message dropped')
+
+    # ── Connection lifecycle ────────────────────────────────────────
+
+    async def _connect_once(self):
+        """Establish a single WebSocket connection, authenticate, and listen."""
+        await self.logger.info(f'Connecting to {self.ws_url}...')
+
+        self._session = aiohttp.ClientSession()
+        try:
+            self._ws = await self._session.ws_connect(self.ws_url)
+            self._missed_pong_count = 0
+            self._reconnect_attempts = 0
+            await self.logger.info('WebSocket connected, sending auth...')
+
+            await self._send_auth()
+
+            # Wait for auth response
+            auth_ok = await self._wait_for_auth()
+            if not auth_ok:
+                await self.logger.error('Authentication failed')
+                return
+
+            await self.logger.info('Authenticated successfully')
+
+            # Start heartbeat
+            self._heartbeat_task = asyncio.create_task(self._heartbeat_loop())
+
+            try:
+                await self._listen_loop()
+            finally:
+                if self._heartbeat_task and not self._heartbeat_task.done():
+                    self._heartbeat_task.cancel()
+                self._clear_pending_acks('Connection closed')
+        finally:
+            if self._ws and not self._ws.closed:
+                await self._ws.close()
+            self._ws = None
+            if self._session and not self._session.closed:
+                await self._session.close()
+            self._session = None
+
+    async def _send_auth(self):
+        """Send the authentication frame."""
+        frame = {
+            'cmd': CMD_SUBSCRIBE,
+            'headers': {'req_id': _generate_req_id(CMD_SUBSCRIBE)},
+            'body': {
+                'bot_id': self.bot_id,
+                'secret': self.secret,
+            },
+        }
+        await self._send_frame(frame)
+
+    async def _wait_for_auth(self) -> bool:
+        """Wait for and validate the authentication response."""
+        try:
+            msg = await asyncio.wait_for(self._ws.receive(), timeout=10.0)
+            if msg.type in (aiohttp.WSMsgType.TEXT,):
+                frame = json.loads(msg.data)
+                req_id = frame.get('headers', {}).get('req_id', '')
+                if req_id.startswith(CMD_SUBSCRIBE) and frame.get('errcode') == 0:
+                    return True
+                await self.logger.error(f'Auth response: errcode={frame.get("errcode")}, errmsg={frame.get("errmsg")}')
+                return False
+            elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSED, aiohttp.WSMsgType.CLOSING):
+                await self.logger.error(f'WebSocket closed during auth: {msg.type}')
+                return False
+            await self.logger.error(f'Unexpected message type during auth: {msg.type}')
+            return False
+        except asyncio.TimeoutError:
+            await self.logger.error('Auth response timeout')
+            return False
+
+    async def _heartbeat_loop(self):
+        """Periodically send heartbeat pings."""
+        try:
+            while self._running and self._ws and not self._ws.closed:
+                await asyncio.sleep(self.heartbeat_interval)
+                if not self._running or not self._ws or self._ws.closed:
+                    break
+
+                if self._missed_pong_count >= self._max_missed_pong:
+                    await self.logger.warning(
+                        f'No heartbeat ack for {self._missed_pong_count} consecutive pings, connection considered dead'
+                    )
+                    await self._ws.close()
+                    break
+
+                self._missed_pong_count += 1
+                frame = {
+                    'cmd': CMD_HEARTBEAT,
+                    'headers': {'req_id': _generate_req_id(CMD_HEARTBEAT)},
+                }
+                try:
+                    await self._send_frame(frame)
+                except Exception:
+                    break
+        except asyncio.CancelledError:
+            pass
+
+    async def _listen_loop(self):
+        """Listen for incoming WebSocket frames and dispatch them."""
+        async for msg in self._ws:
+            if not self._running:
+                break
+            if msg.type == aiohttp.WSMsgType.TEXT:
+                try:
+                    frame = json.loads(msg.data)
+                    await self._handle_frame(frame)
+                except json.JSONDecodeError:
+                    await self.logger.error(f'Failed to parse WebSocket message: {str(msg.data)[:200]}')
+                except Exception:
+                    await self.logger.error(f'Error handling frame: {traceback.format_exc()}')
+            elif msg.type == aiohttp.WSMsgType.BINARY:
+                try:
+                    frame = json.loads(msg.data)
+                    await self._handle_frame(frame)
+                except Exception:
+                    await self.logger.error(f'Error handling binary frame: {traceback.format_exc()}')
+            elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSED, aiohttp.WSMsgType.CLOSING):
+                await self.logger.warning(f'WebSocket connection closed: {msg.type}')
+                break
+
+    # ── Frame handling ──────────────────────────────────────────────
+
+    async def _handle_frame(self, frame: dict):
+        """Route an incoming frame to the appropriate handler."""
+        cmd = frame.get('cmd', '')
+
+        # Message push
+        if cmd == CMD_MSG_CALLBACK:
+            asyncio.create_task(self._handle_message_callback(frame))
+            return
+
+        # Event push
+        if cmd == CMD_EVENT_CALLBACK:
+            asyncio.create_task(self._handle_event_callback(frame))
+            return
+
+        # No cmd → response/ACK frame, dispatch by req_id prefix
+        req_id = frame.get('headers', {}).get('req_id', '')
+
+        # Check pending ACKs first
+        if req_id in self._pending_acks:
+            future = self._pending_acks.pop(req_id)
+            if not future.done():
+                future.set_result(frame)
+            return
+
+        # Heartbeat response
+        if req_id.startswith(CMD_HEARTBEAT):
+            if frame.get('errcode') == 0:
+                self._missed_pong_count = 0
+            return
+
+        # Unknown frame
+        await self.logger.warning(f'Unknown frame: {json.dumps(frame, ensure_ascii=False)[:200]}')
+
+    async def _handle_message_callback(self, frame: dict):
+        """Handle an incoming message callback frame."""
+        try:
+            body = frame.get('body', {})
+            req_id = frame.get('headers', {}).get('req_id', '')
+
+            # Parse message using shared logic
+            message_data = await parse_wecom_bot_message(body, self.encoding_aes_key, self.logger)
+            if not message_data:
+                return
+
+            # Generate stream_id for this message and store the mapping
+            stream_id = _generate_req_id('stream')
+            msg_id = message_data.get('msgid', '')
+            if msg_id:
+                self._stream_ids[msg_id] = f'{req_id}|{stream_id}'
+            message_data['stream_id'] = stream_id
+            message_data['req_id'] = req_id
+
+            event = wecombotevent.WecomBotEvent(message_data)
+            await self._dispatch_event(event)
+        except Exception:
+            await self.logger.error(f'Error in message callback: {traceback.format_exc()}')
+
+    async def _handle_event_callback(self, frame: dict):
+        """Handle an incoming event callback frame (enter_chat, template_card_event, etc.)."""
+        try:
+            body = frame.get('body', {})
+            req_id = frame.get('headers', {}).get('req_id', '')
+
+            event_info = body.get('event', {})
+            event_type = event_info.get('eventtype', '')
+
+            message_data = {
+                'msgtype': 'event',
+                'type': body.get('chattype', 'single'),
+                'event': event_info,
+                'eventtype': event_type,
+                'msgid': body.get('msgid', ''),
+                'aibotid': body.get('aibotid', ''),
+                'req_id': req_id,
+            }
+
+            from_info = body.get('from', {})
+            message_data['userid'] = from_info.get('userid', '')
+            message_data['username'] = from_info.get('alias', '') or from_info.get('userid', '')
+
+            if body.get('chatid'):
+                message_data['chatid'] = body.get('chatid', '')
+
+            event = wecombotevent.WecomBotEvent(message_data)
+
+            # Dispatch to event-specific handlers
+            if event_type in self._message_handlers:
+                for handler in self._message_handlers[event_type]:
+                    await handler(event)
+
+            # Also dispatch to generic 'event' handlers
+            if 'event' in self._message_handlers:
+                for handler in self._message_handlers['event']:
+                    await handler(event)
+
+        except Exception:
+            await self.logger.error(f'Error in event callback: {traceback.format_exc()}')
+
+    async def _dispatch_event(self, event: wecombotevent.WecomBotEvent):
+        """Dispatch a message event to registered handlers with deduplication."""
+        try:
+            message_id = event.message_id
+            if message_id in self._msg_id_map:
+                self._msg_id_map[message_id] += 1
+                return
+            self._msg_id_map[message_id] = 1
+
+            msg_type = event.type
+            if msg_type in self._message_handlers:
+                for handler in self._message_handlers[msg_type]:
+                    await handler(event)
+        except Exception:
+            await self.logger.error(f'Error dispatching event: {traceback.format_exc()}')
+
+    # ── Reply sending with serial queue ─────────────────────────────
+
+    async def _send_reply(
+        self,
+        req_id: str,
+        body: dict,
+        cmd: str = CMD_RESPOND_MSG,
+    ) -> Optional[dict]:
+        """Send a reply frame and wait for ACK.
+
+        Replies with the same req_id are serialized to maintain ordering.
+        """
+        if not self._ws or self._ws.closed:
+            return None
+
+        frame = {
+            'cmd': cmd,
+            'headers': {'req_id': req_id},
+            'body': body,
+        }
+
+        # Ensure serial delivery per req_id
+        if req_id not in self._reply_queues:
+            self._reply_queues[req_id] = asyncio.Queue()
+            self._reply_workers[req_id] = asyncio.create_task(self._reply_queue_worker(req_id))
+
+        future: asyncio.Future = asyncio.get_event_loop().create_future()
+        await self._reply_queues[req_id].put((frame, future))
+        return await future
+
+    async def _reply_queue_worker(self, req_id: str):
+        """Process reply queue items serially for a given req_id."""
+        queue = self._reply_queues[req_id]
+        try:
+            while self._running:
+                try:
+                    frame, future = await asyncio.wait_for(queue.get(), timeout=60.0)
+                except asyncio.TimeoutError:
+                    # Queue idle, clean up worker
+                    break
+
+                try:
+                    ack = await self._send_and_wait_ack(frame)
+                    if not future.done():
+                        future.set_result(ack)
+                except Exception as e:
+                    if not future.done():
+                        future.set_exception(e)
+        except asyncio.CancelledError:
+            pass
+        finally:
+            self._reply_queues.pop(req_id, None)
+            self._reply_workers.pop(req_id, None)
+
+    async def _send_and_wait_ack(self, frame: dict) -> Optional[dict]:
+        """Send a frame and wait for the corresponding ACK."""
+        req_id = frame['headers']['req_id']
+        ack_future: asyncio.Future = asyncio.get_event_loop().create_future()
+        self._pending_acks[req_id] = ack_future
+
+        try:
+            await self._send_frame(frame)
+            result = await asyncio.wait_for(ack_future, timeout=self._reply_ack_timeout)
+            if result.get('errcode', 0) != 0:
+                await self.logger.warning(
+                    f'Reply ACK error: errcode={result.get("errcode")}, errmsg={result.get("errmsg")}'
+                )
+            return result
+        except asyncio.TimeoutError:
+            self._pending_acks.pop(req_id, None)
+            await self.logger.warning(f'Reply ACK timeout ({self._reply_ack_timeout}s) for req_id={req_id}')
+            return None
+
+    async def _send_frame(self, frame: dict):
+        """Send a JSON frame over the WebSocket connection."""
+        if self._ws and not self._ws.closed:
+            await self._ws.send_str(json.dumps(frame, ensure_ascii=False))
+
+    def _clear_pending_acks(self, reason: str):
+        """Reject all pending ACK futures on disconnection."""
+        for req_id, future in self._pending_acks.items():
+            if not future.done():
+                future.set_exception(ConnectionError(reason))
+        self._pending_acks.clear()

src/langbot/libs/wecom_api/api.py

@@ -4,6 +4,7 @@ import base64
 import binascii
 import httpx
 import traceback
+from urllib.parse import quote
 from quart import Quart
 import xml.etree.ElementTree as ET
 from typing import Callable, Dict, Any
@@ -21,23 +22,30 @@ class WecomClient:
         EncodingAESKey: str,
         contacts_secret: str,
         logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://qyapi.weixin.qq.com/cgi-bin',
     ):
         self.corpid = corpid
         self.secret = secret
         self.access_token_for_contacts = ''
         self.token = token
         self.aes = EncodingAESKey
-        self.base_url = 'https://qyapi.weixin.qq.com/cgi-bin'
+        self.base_url = api_base_url
         self.access_token = ''
         self.secret_for_contacts = contacts_secret
         self.logger = logger
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command',
-            'handle_callback',
-            self.handle_callback_request,
-            methods=['GET', 'POST'],
-        )
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command',
+                'handle_callback',
+                self.handle_callback_request,
+                methods=['GET', 'POST'],
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -50,7 +58,7 @@ class WecomClient:
         return bool(self.access_token_for_contacts and self.access_token_for_contacts.strip())
 
     async def get_access_token(self, secret):
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid={self.corpid}&corpsecret={secret}'
+        url = f'{self.base_url}/gettoken?corpid={self.corpid}&corpsecret={secret}'
         async with httpx.AsyncClient() as client:
             response = await client.get(url)
             data = response.json()
@@ -60,6 +68,31 @@ class WecomClient:
                 await self.logger.error(f'获取accesstoken失败:{response.json()}')
                 raise Exception(f'未获取access token: {data}')
 
+    async def get_user_info(self, userid: str) -> dict:
+        """
+        Get user information by user ID using the application secret.
+
+        Args:
+            userid: The user ID to look up.
+
+        Returns:
+            dict: User information including 'name' field.
+        """
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+
+        url = self.base_url + '/user/get?access_token=' + self.access_token + '&userid=' + quote(userid)
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url)
+            data = response.json()
+            if data.get('errcode') == 40014 or data.get('errcode') == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.get_user_info(userid)
+            if data.get('errcode', 0) != 0:
+                await self.logger.error(f'获取用户信息失败:{data}')
+                return {}
+            return data
+
     async def get_users(self):
         if not self.check_access_token_for_contacts():
             self.access_token_for_contacts = await self.get_access_token(self.secret_for_contacts)
@@ -133,12 +166,64 @@ class WecomClient:
                 await self.logger.error(f'发送图片失败:{data}')
                 raise Exception('Failed to send image: ' + str(data))
 
+    async def send_voice(self, user_id: str, agent_id: int, media_id: str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url + '/message/send?access_token=' + self.access_token
+        async with httpx.AsyncClient() as client:
+            params = {
+                'touser': user_id,
+                'msgtype': 'voice',
+                'agentid': agent_id,
+                'voice': {
+                    'media_id': media_id,
+                },
+                'safe': 0,
+                'enable_id_trans': 0,
+                'enable_duplicate_check': 0,
+                'duplicate_check_interval': 1800,
+            }
+            response = await client.post(url, json=params)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.send_voice(user_id, agent_id, media_id)
+            if data['errcode'] != 0:
+                await self.logger.error(f'发送语音失败:{data}')
+                raise Exception('Failed to send voice: ' + str(data))
+
+    async def send_file(self, user_id: str, agent_id: int, media_id: str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url + '/message/send?access_token=' + self.access_token
+        async with httpx.AsyncClient() as client:
+            params = {
+                'touser': user_id,
+                'msgtype': 'file',
+                'agentid': agent_id,
+                'file': {
+                    'media_id': media_id,
+                },
+                'safe': 0,
+                'enable_id_trans': 0,
+                'enable_duplicate_check': 0,
+                'duplicate_check_interval': 1800,
+            }
+            response = await client.post(url, json=params)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.send_file(user_id, agent_id, media_id)
+            if data['errcode'] != 0:
+                await self.logger.error(f'发送文件失败:{data}')
+                raise Exception('Failed to send file: ' + str(data))
+
     async def send_private_msg(self, user_id: str, agent_id: int, content: str):
         if not await self.check_access_token():
             self.access_token = await self.get_access_token(self.secret)
 
         url = self.base_url + '/message/send?access_token=' + self.access_token
-        async with httpx.AsyncClient() as client:
+        async with httpx.AsyncClient(timeout=None) as client:
             params = {
                 'touser': user_id,
                 'msgtype': 'text',
@@ -161,25 +246,43 @@ class WecomClient:
                 raise Exception('Failed to send message: ' + str(data))
 
     async def handle_callback_request(self):
+        """处理回调请求（独立端口模式，使用全局 request）。"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
         """
-        处理回调请求，包括 GET 验证和 POST 消息接收。
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """
+        处理回调请求的内部实现，包括 GET 验证和 POST 消息接收。
+
+        Args:
+            req: Quart Request 对象
         """
         try:
-            msg_signature = request.args.get('msg_signature')
-            timestamp = request.args.get('timestamp')
-            nonce = request.args.get('nonce')
+            msg_signature = req.args.get('msg_signature')
+            timestamp = req.args.get('timestamp')
+            nonce = req.args.get('nonce')
 
             wxcpt = WXBizMsgCrypt(self.token, self.aes, self.corpid)
-            if request.method == 'GET':
-                echostr = request.args.get('echostr')
+            if req.method == 'GET':
+                echostr = req.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')
                     raise Exception(f'验证失败，错误码: {ret}')
                 return reply_echo_str
 
-            elif request.method == 'POST':
-                encrypt_msg = await request.data
+            elif req.method == 'POST':
+                encrypt_msg = await req.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')
@@ -263,7 +366,7 @@ class WecomClient:
                 return ext
         return 'jpg'  # 默认返回jpg
 
-    async def upload_to_work(self, image: platform_message.Image):
+    async def upload_image_to_work(self, image: platform_message.Image):
         """
         获取 media_id
         """
@@ -280,7 +383,7 @@ class WecomClient:
                 file_bytes = await f.read()
                 file_name = image.path.split('/')[-1]
         elif image.url:
-            file_bytes = await self.download_image_to_bytes(image.url)
+            file_bytes = await self.download_media_to_bytes(image.url)
             file_name = image.url.split('/')[-1]
         elif image.base64:
             try:
@@ -315,7 +418,7 @@ class WecomClient:
             data = response.json()
             if data['errcode'] == 40014 or data['errcode'] == 42001:
                 self.access_token = await self.get_access_token(self.secret)
-                media_id = await self.upload_to_work(image)
+                media_id = await self.upload_image_to_work(image)
             if data.get('errcode', 0) != 0:
                 await self.logger.error(f'上传图片失败:{data}')
                 raise Exception('failed to upload file')
@@ -323,13 +426,128 @@ class WecomClient:
             media_id = data.get('media_id')
             return media_id
 
-    async def download_image_to_bytes(self, url: str) -> bytes:
+    async def upload_voice_to_work(self, voice: platform_message.Voice):
+        """
+        上传语音文件到企业微信
+        """
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url + '/media/upload?access_token=' + self.access_token + '&type=file'
+        file_bytes = None
+        file_name = 'voice.mp3'
+
+        if voice.path:
+            async with aiofiles.open(voice.path, 'rb') as f:
+                file_bytes = await f.read()
+                file_name = voice.path.split('/')[-1]
+        elif voice.url:
+            file_bytes = await self.download_media_to_bytes(voice.url)
+            file_name = voice.url.split('/')[-1]
+        elif voice.base64:
+            try:
+                base64_data = voice.base64
+                if ',' in base64_data:
+                    base64_data = base64_data.split(',', 1)[1]
+                padding = 4 - (len(base64_data) % 4) if len(base64_data) % 4 else 0
+                padded_base64 = base64_data + '=' * padding
+                file_bytes = base64.b64decode(padded_base64)
+            except binascii.Error as e:
+                raise ValueError(f'Invalid base64 string: {str(e)}')
+        else:
+            await self.logger.error('Voice对象出错')
+            raise ValueError('voice对象出错')
+
+        boundary = '-------------------------acebdf13572468'
+        headers = {'Content-Type': f'multipart/form-data; boundary={boundary}'}
+        body = (
+            (
+                f'--{boundary}\r\n'
+                f'Content-Disposition: form-data; name="media"; filename="{file_name}"; filelength={len(file_bytes)}\r\n'
+                f'Content-Type: application/octet-stream\r\n\r\n'
+            ).encode('utf-8')
+            + file_bytes
+            + f'\r\n--{boundary}--\r\n'.encode('utf-8')
+        )
+
+        # print(body)
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, headers=headers, content=body)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                media_id = await self.upload_voice_to_work(voice)
+            if data.get('errcode', 0) != 0:
+                await self.logger.error(f'上传语音文件失败:{data}')
+                raise Exception('failed to upload file')
+            media_id = data.get('media_id')
+            return media_id
+
+    async def upload_file_to_work(self, file: platform_message.File):
+        """
+        上传文件到企业微信
+        """
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url + '/media/upload?access_token=' + self.access_token + '&type=file'
+        file_bytes = None
+        file_name = 'file.txt'
+        if file.path:
+            async with aiofiles.open(file.path, 'rb') as f:
+                file_bytes = await f.read()
+                file_name = file.path.split('/')[-1]
+        elif file.url:
+            file_bytes = await self.download_media_to_bytes(file.url)
+            file_name = file.url.split('/')[-1]
+        elif file.base64:
+            try:
+                base64_data = file.base64
+                if ',' in base64_data:
+                    base64_data = base64_data.split(',', 1)[1]
+                padding = 4 - (len(base64_data) % 4) if len(base64_data) % 4 else 0
+                padded_base64 = base64_data + '=' * padding
+                file_bytes = base64.b64decode(padded_base64)
+            except binascii.Error as e:
+                raise ValueError(f'Invalid base64 string: {str(e)}')
+        else:
+            await self.logger.error('File对象出错')
+            raise ValueError('file对象出错')
+        boundary = '-------------------------acebdf13572468'
+        headers = {'Content-Type': f'multipart/form-data; boundary={boundary}'}
+        body = (
+            (
+                f'--{boundary}\r\n'
+                f'Content-Disposition: form-data; name="media"; filename="{file_name}"; filelength={len(file_bytes)}\r\n'
+                f'Content-Type: application/octet-stream\r\n\r\n'
+            ).encode('utf-8')
+            + file_bytes
+            + f'\r\n--{boundary}--\r\n'.encode('utf-8')
+        )
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, headers=headers, content=body)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                media_id = await self.upload_file_to_work(file)
+            if data.get('errcode', 0) != 0:
+                await self.logger.error(f'上传文件失败:{data}')
+                raise Exception('failed to upload file')
+            media_id = data.get('media_id')
+            return media_id
+
+    async def download_media_to_bytes(self, url: str) -> bytes:
         async with httpx.AsyncClient() as client:
             response = await client.get(url)
             response.raise_for_status()
             return response.content
 
     # 进行media_id的获取
-    async def get_media_id(self, image: platform_message.Image):
-        media_id = await self.upload_to_work(image=image)
+    async def get_media_id(self, media: platform_message.Image | platform_message.Voice | platform_message.File):
+        if isinstance(media, platform_message.Image):
+            media_id = await self.upload_image_to_work(image=media)
+        elif isinstance(media, platform_message.Voice):
+            media_id = await self.upload_voice_to_work(voice=media)
+        elif isinstance(media, platform_message.File):
+            media_id = await self.upload_file_to_work(file=media)
+        else:
+            raise ValueError('Unsupported media type')
         return media_id

src/langbot/libs/wecom_customer_service_api/api.py

@@ -10,22 +10,41 @@ from typing import Callable
 from .wecomcsevent import WecomCSEvent
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import aiofiles
+import time
 
 
 class WecomCSClient:
-    def __init__(self, corpid: str, secret: str, token: str, EncodingAESKey: str, logger: None):
+    def __init__(
+        self,
+        corpid: str,
+        secret: str,
+        token: str,
+        EncodingAESKey: str,
+        logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://qyapi.weixin.qq.com/cgi-bin',
+    ):
         self.corpid = corpid
         self.secret = secret
         self.access_token_for_contacts = ''
         self.token = token
         self.aes = EncodingAESKey
-        self.base_url = 'https://qyapi.weixin.qq.com/cgi-bin'
+        self.base_url = api_base_url
         self.access_token = ''
         self.logger = logger
+        self.unified_mode = unified_mode
         self.app = Quart(__name__)
-        self.app.add_url_rule(
-            '/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST']
-        )
+
+        # Customer info cache: {external_userid: (info_dict, timestamp)}
+        self._customer_cache: dict[str, tuple[dict, float]] = {}
+        self._cache_ttl = 60  # Cache TTL in seconds (1 minute)
+
+        # 只有在非统一模式下才注册独立路由
+        if not self.unified_mode:
+            self.app.add_url_rule(
+                '/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST']
+            )
+
         self._message_handlers = {
             'example': [],
         }
@@ -61,7 +80,7 @@ class WecomCSClient:
         return bool(self.access_token_for_contacts and self.access_token_for_contacts.strip())
 
     async def get_access_token(self, secret):
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid={self.corpid}&corpsecret={secret}'
+        url = f'{self.base_url}/gettoken?corpid={self.corpid}&corpsecret={secret}'
         async with httpx.AsyncClient() as client:
             response = await client.get(url)
             data = response.json()
@@ -167,7 +186,7 @@ class WecomCSClient:
         if not await self.check_access_token():
             self.access_token = await self.get_access_token(self.secret)
 
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/kf/send_msg?access_token={self.access_token}'
+        url = f'{self.base_url}/kf/send_msg?access_token={self.access_token}'
 
         payload = {
             'touser': external_userid,
@@ -192,27 +211,45 @@ class WecomCSClient:
             return data
 
     async def handle_callback_request(self):
+        """处理回调请求（独立端口模式，使用全局 request）。"""
+        return await self._handle_callback_internal(request)
+
+    async def handle_unified_webhook(self, req):
+        """处理回调请求（统一 webhook 模式，显式传递 request）。
+
+        Args:
+            req: Quart Request 对象
+
+        Returns:
+            响应数据
         """
-        处理回调请求，包括 GET 验证和 POST 消息接收。
+        return await self._handle_callback_internal(req)
+
+    async def _handle_callback_internal(self, req):
+        """
+        处理回调请求的内部实现，包括 GET 验证和 POST 消息接收。
+
+        Args:
+            req: Quart Request 对象
         """
         try:
-            msg_signature = request.args.get('msg_signature')
-            timestamp = request.args.get('timestamp')
-            nonce = request.args.get('nonce')
+            msg_signature = req.args.get('msg_signature')
+            timestamp = req.args.get('timestamp')
+            nonce = req.args.get('nonce')
             try:
                 wxcpt = WXBizMsgCrypt(self.token, self.aes, self.corpid)
             except Exception as e:
                 raise Exception(f'初始化失败，错误码: {e}')
 
-            if request.method == 'GET':
-                echostr = request.args.get('echostr')
+            if req.method == 'GET':
+                echostr = req.args.get('echostr')
                 ret, reply_echo_str = wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
                 if ret != 0:
                     raise Exception(f'验证失败，错误码: {ret}')
                 return reply_echo_str
 
-            elif request.method == 'POST':
-                encrypt_msg = await request.data
+            elif req.method == 'POST':
+                encrypt_msg = await req.data
                 ret, xml_msg = wxcpt.DecryptMsg(encrypt_msg, msg_signature, timestamp, nonce)
                 if ret != 0:
                     raise Exception(f'消息解密失败，错误码: {ret}')
@@ -346,3 +383,53 @@ class WecomCSClient:
     async def get_media_id(self, image: platform_message.Image):
         media_id = await self.upload_to_work(image=image)
         return media_id
+
+    async def get_customer_info(self, external_userid: str) -> dict | None:
+        """
+        Get customer information by external_userid with caching.
+
+        Uses a 1-minute cache to avoid repeated API calls for the same user.
+
+        Args:
+            external_userid: The external user ID of the customer.
+
+        Returns:
+            Customer info dict with 'nickname', 'avatar', etc., or None if not found.
+        """
+        # Check cache first
+        current_time = time.time()
+        if external_userid in self._customer_cache:
+            cached_info, cached_time = self._customer_cache[external_userid]
+            if current_time - cached_time < self._cache_ttl:
+                return cached_info
+
+        # Cache miss or expired, fetch from API
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+
+        url = f'{self.base_url}/kf/customer/batchget?access_token={self.access_token}'
+
+        payload = {
+            'external_userid_list': [external_userid],
+        }
+
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, json=payload)
+            data = response.json()
+
+            if data.get('errcode') in [40014, 42001]:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.get_customer_info(external_userid)
+
+            if data.get('errcode', 0) != 0:
+                if self.logger:
+                    await self.logger.warning(f'Failed to get customer info: {data}')
+                return None
+
+            customer_list = data.get('customer_list', [])
+            if customer_list:
+                customer_info = customer_list[0]
+                # Store in cache
+                self._customer_cache[external_userid] = (customer_info, current_time)
+                return customer_info
+            return None

src/langbot/pkg/api/http/controller/groups/files.py

@@ -13,9 +13,9 @@ from .. import group
 @group.group_class('files', '/api/v1/files')
 class FilesRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('/image/<image_key>', methods=['GET'], auth_type=group.AuthType.NONE)
+        @self.route('/image/<path:image_key>', methods=['GET'], auth_type=group.AuthType.NONE)
         async def _(image_key: str) -> quart.Response:
-            if '/' in image_key or '\\' in image_key:
+            if '..' in image_key or '\\' in image_key:
                 return quart.Response(status=404)
 
             if not await self.ap.storage_mgr.storage_provider.exists(image_key):
@@ -28,8 +28,56 @@ class FilesRouterGroup(group.RouterGroup):
 
             return quart.Response(image_bytes, mimetype=mime_type)
 
-        @self.route('/documents', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
-        async def _() -> quart.Response:
+        @self.route('/images', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def upload_image() -> quart.Response:
+            request = quart.request
+
+            # Check file size limit before reading the file
+            content_length = request.content_length
+            if content_length and content_length > group.MAX_FILE_SIZE:
+                return self.fail(400, 'Image size exceeds 10MB limit.')
+
+            # get file bytes from 'file'
+            files = await request.files
+            if 'file' not in files:
+                return self.fail(400, 'No image file provided')
+
+            file = files['file']
+            assert isinstance(file, quart.datastructures.FileStorage)
+
+            file_bytes = await asyncio.to_thread(file.stream.read)
+
+            # Double-check actual file size after reading
+            if len(file_bytes) > group.MAX_FILE_SIZE:
+                return self.fail(400, 'Image size exceeds 10MB limit.')
+
+            # Validate image file extension
+            allowed_extensions = {'jpg', 'jpeg', 'png', 'gif', 'webp'}
+            if '.' in file.filename:
+                file_name, extension = file.filename.rsplit('.', 1)
+                extension = extension.lower()
+            else:
+                return self.fail(400, 'Invalid image file: no file extension')
+
+            if extension not in allowed_extensions:
+                return self.fail(400, f'Invalid image format. Allowed formats: {", ".join(allowed_extensions)}')
+
+            # check if file name contains '/' or '\'
+            if '/' in file_name or '\\' in file_name:
+                return self.fail(400, 'File name contains invalid characters')
+
+            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_key': file_key,
+                }
+            )
+
+        @self.route('/documents', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def upload_document() -> quart.Response:
             request = quart.request
 
             # Check file size limit before reading the file

src/langbot/pkg/api/http/controller/groups/knowledge/base.py

@@ -5,7 +5,7 @@ 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'])
+        @self.route('', methods=['POST', 'GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def handle_knowledge_bases() -> quart.Response:
             if quart.request.method == 'GET':
                 knowledge_bases = await self.ap.knowledge_service.get_knowledge_bases()
@@ -13,7 +13,10 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
 
             elif quart.request.method == 'POST':
                 json_data = await quart.request.json
-                knowledge_base_uuid = await self.ap.knowledge_service.create_knowledge_base(json_data)
+                try:
+                    knowledge_base_uuid = await self.ap.knowledge_service.create_knowledge_base(json_data)
+                except ValueError as e:
+                    return self.http_status(400, -1, str(e))
                 return self.success(data={'uuid': knowledge_base_uuid})
 
             return self.http_status(405, -1, 'Method not allowed')
@@ -21,6 +24,7 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
         @self.route(
             '/<knowledge_base_uuid>',
             methods=['GET', 'DELETE', 'PUT'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def handle_specific_knowledge_base(knowledge_base_uuid: str) -> quart.Response:
             if quart.request.method == 'GET':
@@ -38,7 +42,7 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
             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({})
+                return self.success(data={'uuid': knowledge_base_uuid})
 
             elif quart.request.method == 'DELETE':
                 await self.ap.knowledge_service.delete_knowledge_base(knowledge_base_uuid)
@@ -47,6 +51,7 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
         @self.route(
             '/<knowledge_base_uuid>/files',
             methods=['GET', 'POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def get_knowledge_base_files(knowledge_base_uuid: str) -> str:
             if quart.request.method == 'GET':
@@ -63,8 +68,12 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
                 if not file_id:
                     return self.http_status(400, -1, 'File ID is required')
 
+                parser_plugin_id = json_data.get('parser_plugin_id')
+
                 # 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)
+                task_id = await self.ap.knowledge_service.store_file(
+                    knowledge_base_uuid, file_id, parser_plugin_id=parser_plugin_id
+                )
                 return self.success(
                     {
                         'task_id': task_id,
@@ -74,6 +83,7 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
         @self.route(
             '/<knowledge_base_uuid>/files/<file_id>',
             methods=['DELETE'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         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)
@@ -82,9 +92,18 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
         @self.route(
             '/<knowledge_base_uuid>/retrieve',
             methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         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)
+
+            if not query or not query.strip():
+                return self.http_status(400, -1, 'Query is required and cannot be empty')
+
+            # Extract retrieval_settings to allow dynamic control over Knowledge Engine behavior (e.g. top_k, filters)
+            retrieval_settings = json_data.get('retrieval_settings', {})
+            results = await self.ap.knowledge_service.retrieve_knowledge_base(
+                knowledge_base_uuid, query, retrieval_settings
+            )
             return self.success(data={'results': results})

src/langbot/pkg/api/http/controller/groups/knowledge/engines.py

@@ -0,0 +1,45 @@
+import quart
+from urllib.parse import unquote
+from ... import group
+
+
+@group.group_class('knowledge_engines', '/api/v1/knowledge/engines')
+class KnowledgeEnginesRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def list_knowledge_engines() -> quart.Response:
+            """List all available Knowledge Engines from plugins.
+
+            Returns a list of Knowledge Engines with their capabilities and configuration schemas.
+            This is used by the frontend to render the knowledge base creation wizard.
+            """
+            engines = await self.ap.knowledge_service.list_knowledge_engines()
+            return self.success(data={'engines': engines})
+
+        @self.route(
+            '/<path:plugin_id>/creation-schema', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def get_engine_creation_schema(plugin_id: str) -> quart.Response:
+            """Get creation settings schema for a specific Knowledge Engine.
+
+            plugin_id is in 'author/name' format, captured via <path:> converter.
+            """
+            plugin_id = unquote(plugin_id)
+            if '/' not in plugin_id:
+                return self.http_status(400, -1, 'Invalid plugin_id format. Expected author/name.')
+            schema = await self.ap.knowledge_service.get_engine_creation_schema(plugin_id)
+            return self.success(data={'schema': schema})
+
+        @self.route(
+            '/<path:plugin_id>/retrieval-schema', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def get_engine_retrieval_schema(plugin_id: str) -> quart.Response:
+            """Get retrieval settings schema for a specific Knowledge Engine.
+
+            plugin_id is in 'author/name' format, captured via <path:> converter.
+            """
+            plugin_id = unquote(plugin_id)
+            if '/' not in plugin_id:
+                return self.http_status(400, -1, 'Invalid plugin_id format. Expected author/name.')
+            schema = await self.ap.knowledge_service.get_engine_retrieval_schema(plugin_id)
+            return self.success(data={'schema': schema})

src/langbot/pkg/api/http/controller/groups/knowledge/migration.py

@@ -0,0 +1,372 @@
+import asyncio
+import json
+
+import httpx
+import quart
+import sqlalchemy
+
+from ... import group
+from ......core import taskmgr
+from ......entity.persistence import metadata as persistence_metadata
+from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
+
+LANGRAG_PLUGIN_AUTHOR = 'langbot-team'
+LANGRAG_PLUGIN_NAME = 'LangRAG'
+LANGRAG_PLUGIN_ID = f'{LANGRAG_PLUGIN_AUTHOR}/{LANGRAG_PLUGIN_NAME}'
+DEFAULT_SPACE_URL = 'https://space.langbot.app'
+
+# Old Retriever plugin_name -> New Connector plugin_name
+EXTERNAL_PLUGIN_NAME_MAPPING = {
+    'DifyDatasetsRetriever': 'DifyDatasetsConnector',
+    'RAGFlowRetriever': 'RAGFlowConnector',
+    'FastGPTRetriever': 'FastGPTConnector',
+}
+
+# Per-plugin: which old retriever_config fields belong to creation_settings.
+# Remaining fields go to retrieval_settings.
+# None means ALL fields go to creation_settings (no retrieval_schema).
+EXTERNAL_PLUGIN_CREATION_FIELDS: dict[str, set[str] | None] = {
+    'langbot-team/DifyDatasetsConnector': {'api_base_url', 'dify_apikey', 'dataset_id'},
+    'langbot-team/RAGFlowConnector': {'api_base_url', 'api_key', 'dataset_ids'},
+    'langbot-team/FastGPTConnector': None,  # all fields -> creation_settings
+}
+
+
+@group.group_class('knowledge/migration', '/api/v1/knowledge/migration')
+class KnowledgeMigrationRouterGroup(group.RouterGroup):
+    async def _get_migration_flag(self) -> bool:
+        """Check if rag_plugin_migration_needed flag is set."""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_metadata.Metadata).where(
+                persistence_metadata.Metadata.key == 'rag_plugin_migration_needed'
+            )
+        )
+        row = result.first()
+        return row is not None and row.value == 'true'
+
+    async def _set_migration_flag(self, value: str):
+        """Set rag_plugin_migration_needed flag."""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_metadata.Metadata)
+            .where(persistence_metadata.Metadata.key == 'rag_plugin_migration_needed')
+            .values(value=value)
+        )
+
+    async def _table_exists(self, table_name: str) -> bool:
+        """Check if a table exists."""
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    'SELECT EXISTS (SELECT FROM information_schema.tables WHERE table_name = :table_name);'
+                ).bindparams(table_name=table_name)
+            )
+            return result.scalar()
+        else:
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("SELECT name FROM sqlite_master WHERE type='table' AND name=:table_name;").bindparams(
+                    table_name=table_name
+                )
+            )
+            return result.first() is not None
+
+    async def _install_plugin_from_marketplace(
+        self, plugin_id: str, task_context: taskmgr.TaskContext, space_url: str
+    ) -> None:
+        """Install a single plugin from the marketplace."""
+        p_author, p_name = plugin_id.split('/', 1)
+        self.ap.logger.info(f'RAG migration: installing plugin {plugin_id} from marketplace...')
+        task_context.trace(f'Installing plugin {plugin_id} from marketplace...')
+
+        async with httpx.AsyncClient(trust_env=True, timeout=15) as client:
+            resp = await client.get(f'{space_url}/api/v1/marketplace/plugins/{p_author}/{p_name}')
+            resp.raise_for_status()
+            p_data = resp.json().get('data', {}).get('plugin', {})
+            p_version = p_data.get('latest_version')
+            if not p_version:
+                raise Exception(f'Could not determine latest version for {plugin_id}')
+
+        await self.ap.plugin_connector.install_plugin(
+            PluginInstallSource.MARKETPLACE,
+            {
+                'plugin_author': p_author,
+                'plugin_name': p_name,
+                'plugin_version': p_version,
+            },
+            task_context=task_context,
+        )
+        self.ap.logger.info(f'RAG migration: plugin {plugin_id} install request sent.')
+
+    async def _execute_rag_migration(self, task_context: taskmgr.TaskContext, install_plugin: bool = True):
+        """Execute RAG migration: install required plugins and restore backup data."""
+        warnings = []
+
+        # Collect all plugins we need: LangRAG (always) + connector plugins (from external KBs)
+        needed_plugins: dict[str, str] = {
+            LANGRAG_PLUGIN_ID: LANGRAG_PLUGIN_NAME,
+        }
+
+        has_external = await self._table_exists('external_knowledge_bases')
+        if has_external:
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('SELECT DISTINCT plugin_author, plugin_name FROM external_knowledge_bases;')
+            )
+            for row in result.fetchall():
+                plugin_author = row[0] or ''
+                plugin_name = row[1] or ''
+                mapped_name = EXTERNAL_PLUGIN_NAME_MAPPING.get(plugin_name, plugin_name)
+                plugin_id = f'{plugin_author}/{mapped_name}'
+                if plugin_id not in needed_plugins:
+                    needed_plugins[plugin_id] = mapped_name
+
+        self.ap.logger.info(f'RAG migration: plugins needed: {list(needed_plugins.keys())}')
+
+        if install_plugin:
+            # Step 1: Install all required plugins from marketplace
+            task_context.trace('Installing required plugins...', action='install-plugin')
+            space_url = self.ap.instance_config.data.get('space', {}).get('url', DEFAULT_SPACE_URL).rstrip('/')
+
+            for plugin_id in needed_plugins:
+                try:
+                    await self._install_plugin_from_marketplace(plugin_id, task_context, space_url)
+                except Exception as e:
+                    self.ap.logger.warning(f'RAG migration: plugin {plugin_id} install returned: {e}')
+                    task_context.trace(f'Plugin install note ({plugin_id}): {e}')
+
+            # Step 2: Wait for all plugins to become available as knowledge engines
+            task_context.trace(
+                f'Waiting for plugins to become available: {list(needed_plugins.keys())}...',
+                action='wait-plugin',
+            )
+            max_retries = 30
+            engine_id_set: set[str] = set()
+            for i in range(max_retries):
+                try:
+                    engines = await self.ap.plugin_connector.list_knowledge_engines()
+                    engine_id_set = {e.get('plugin_id') for e in engines}
+                except Exception:
+                    pass
+                if all(pid in engine_id_set for pid in needed_plugins):
+                    self.ap.logger.info(f'RAG migration: all plugins ready: {engine_id_set}')
+                    task_context.trace('All required plugins are ready.')
+                    break
+                if i == max_retries - 1:
+                    still_missing = [pid for pid in needed_plugins if pid not in engine_id_set]
+                    warning = f'Plugin(s) {still_missing} did not become available after {max_retries} retries'
+                    self.ap.logger.warning(f'RAG migration: {warning}')
+                    warnings.append(warning)
+                    task_context.trace(warning)
+                await asyncio.sleep(2)
+        else:
+            try:
+                engines = await self.ap.plugin_connector.list_knowledge_engines()
+                engine_id_set = {e.get('plugin_id') for e in engines}
+            except Exception:
+                engine_id_set = set()
+
+        # Step 3: Restore internal knowledge bases from backup
+        task_context.trace('Restoring internal knowledge bases...', action='restore-internal')
+        if await self._table_exists('knowledge_bases_backup'):
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('SELECT * FROM knowledge_bases_backup;')
+            )
+            rows = result.fetchall()
+            columns = result.keys()
+
+            for row in rows:
+                row_dict = dict(zip(columns, row))
+                kb_uuid = row_dict.get('uuid')
+                name = row_dict.get('name', 'Untitled')
+                description = row_dict.get('description', '')
+                emoji = row_dict.get('emoji', '\U0001f4da')
+                embedding_model_uuid = row_dict.get('embedding_model_uuid', '')
+                top_k = row_dict.get('top_k', 5)
+                created_at = row_dict.get('created_at')
+                updated_at = row_dict.get('updated_at')
+
+                creation_settings = json.dumps({'embedding_model_uuid': embedding_model_uuid})
+                retrieval_settings = json.dumps({'top_k': top_k})
+
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'INSERT INTO knowledge_bases '
+                        '(uuid, name, description, emoji, created_at, updated_at, '
+                        'knowledge_engine_plugin_id, collection_id, creation_settings, retrieval_settings) '
+                        'VALUES (:uuid, :name, :description, :emoji, :created_at, :updated_at, '
+                        ':plugin_id, :collection_id, :creation_settings, :retrieval_settings);'
+                    ).bindparams(
+                        uuid=kb_uuid,
+                        name=name,
+                        description=description,
+                        emoji=emoji,
+                        created_at=created_at,
+                        updated_at=updated_at,
+                        plugin_id=LANGRAG_PLUGIN_ID,
+                        collection_id=kb_uuid,
+                        creation_settings=creation_settings,
+                        retrieval_settings=retrieval_settings,
+                    )
+                )
+
+                try:
+                    config = {'embedding_model_uuid': embedding_model_uuid}
+                    await self.ap.plugin_connector.rag_on_kb_create(LANGRAG_PLUGIN_ID, kb_uuid, config)
+                    task_context.trace(f'Restored internal KB: {name} ({kb_uuid})')
+                except Exception as e:
+                    warning = f'Failed to notify plugin for KB {name} ({kb_uuid}): {e}'
+                    warnings.append(warning)
+                    task_context.trace(warning)
+
+            await self.ap.rag_mgr.load_knowledge_bases_from_db()
+
+        # Step 4: Restore external knowledge bases
+        task_context.trace('Restoring external knowledge bases...', action='restore-external')
+        if has_external:
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('SELECT * FROM external_knowledge_bases;')
+            )
+            rows = result.fetchall()
+            columns = result.keys()
+
+            self.ap.logger.info(
+                f'RAG migration: {len(rows)} external KB(s) to restore. Available engines: {engine_id_set}'
+            )
+            task_context.trace(f'Found {len(rows)} external KB(s). Available engines: {engine_id_set}')
+
+            for row in rows:
+                row_dict = dict(zip(columns, row))
+                kb_uuid = row_dict.get('uuid')
+                name = row_dict.get('name', 'Untitled')
+                description = row_dict.get('description', '')
+                emoji = row_dict.get('emoji', '\U0001f517')
+                plugin_author = row_dict.get('plugin_author', '')
+                plugin_name = row_dict.get('plugin_name', '')
+                retriever_config = row_dict.get('retriever_config', {})
+                created_at = row_dict.get('created_at')
+
+                mapped_plugin_name = EXTERNAL_PLUGIN_NAME_MAPPING.get(plugin_name, plugin_name)
+                external_plugin_id = f'{plugin_author}/{mapped_plugin_name}'
+
+                self.ap.logger.info(
+                    f'RAG migration: processing external KB "{name}" ({kb_uuid}), '
+                    f'plugin: {plugin_author}/{plugin_name} -> {external_plugin_id}'
+                )
+
+                if isinstance(retriever_config, str):
+                    try:
+                        retriever_config = json.loads(retriever_config)
+                    except (json.JSONDecodeError, TypeError):
+                        retriever_config = {}
+
+                creation_fields = EXTERNAL_PLUGIN_CREATION_FIELDS.get(external_plugin_id)
+                if creation_fields is None:
+                    creation_settings_dict = retriever_config
+                    retrieval_settings_dict = {}
+                else:
+                    creation_settings_dict = {k: v for k, v in retriever_config.items() if k in creation_fields}
+                    retrieval_settings_dict = {k: v for k, v in retriever_config.items() if k not in creation_fields}
+
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'INSERT INTO knowledge_bases '
+                        '(uuid, name, description, emoji, created_at, updated_at, '
+                        'knowledge_engine_plugin_id, collection_id, creation_settings, retrieval_settings) '
+                        'VALUES (:uuid, :name, :description, :emoji, :created_at, :updated_at, '
+                        ':plugin_id, :collection_id, :creation_settings, :retrieval_settings);'
+                    ).bindparams(
+                        uuid=kb_uuid,
+                        name=name,
+                        description=description,
+                        emoji=emoji,
+                        created_at=created_at,
+                        updated_at=created_at,
+                        plugin_id=external_plugin_id,
+                        collection_id=kb_uuid,
+                        creation_settings=json.dumps(creation_settings_dict),
+                        retrieval_settings=json.dumps(retrieval_settings_dict),
+                    )
+                )
+
+                if external_plugin_id not in engine_id_set:
+                    warning = (
+                        f'External KB "{name}" ({kb_uuid}) record saved, but plugin {external_plugin_id} '
+                        f'is not installed yet. Install the connector plugin to use it.'
+                    )
+                    warnings.append(warning)
+                    task_context.trace(warning)
+                else:
+                    try:
+                        await self.ap.plugin_connector.rag_on_kb_create(
+                            external_plugin_id, kb_uuid, creation_settings_dict
+                        )
+                        task_context.trace(f'Restored external KB: {name} ({kb_uuid})')
+                    except Exception as e:
+                        warning = f'Failed to notify plugin for external KB {name} ({kb_uuid}): {e}'
+                        warnings.append(warning)
+                        task_context.trace(warning)
+
+            await self.ap.rag_mgr.load_knowledge_bases_from_db()
+
+        # Step 5: Clear migration flag
+        await self._set_migration_flag('false')
+        task_context.trace('RAG migration completed.', action='done')
+
+        if warnings:
+            task_context.trace(f'Completed with {len(warnings)} warning(s).')
+
+    async def initialize(self) -> None:
+        @self.route('/status', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+
+            internal_kb_count = 0
+            external_kb_count = 0
+
+            if needed:
+                if await self._table_exists('knowledge_bases_backup'):
+                    result = await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text('SELECT COUNT(*) FROM knowledge_bases_backup;')
+                    )
+                    internal_kb_count = result.scalar() or 0
+
+                if await self._table_exists('external_knowledge_bases'):
+                    result = await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text('SELECT COUNT(*) FROM external_knowledge_bases;')
+                    )
+                    external_kb_count = result.scalar() or 0
+
+            return self.success(
+                data={
+                    'needed': needed,
+                    'internal_kb_count': internal_kb_count,
+                    'external_kb_count': external_kb_count,
+                }
+            )
+
+        @self.route('/execute', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+            if not needed:
+                return self.http_status(400, -1, 'RAG migration is not needed')
+
+            data = await quart.request.get_json(silent=True) or {}
+            install_plugin = data.get('install_plugin', True)
+
+            ctx = taskmgr.TaskContext.new()
+            wrapper = self.ap.task_mgr.create_user_task(
+                self._execute_rag_migration(task_context=ctx, install_plugin=install_plugin),
+                kind='rag-migration',
+                name='rag-migration-execute',
+                label='Migrating knowledge bases to plugin architecture',
+                context=ctx,
+            )
+
+            return self.success(data={'task_id': wrapper.id})
+
+        @self.route('/dismiss', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            needed = await self._get_migration_flag()
+            if not needed:
+                return self.http_status(400, -1, 'RAG migration is not needed')
+
+            await self._set_migration_flag('false')
+            return self.success()

src/langbot/pkg/api/http/controller/groups/knowledge/parsers.py

@@ -0,0 +1,16 @@
+import quart
+from ... import group
+
+
+@group.group_class('parsers', '/api/v1/knowledge/parsers')
+class ParsersRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def list_parsers() -> quart.Response:
+            """List all available parsers from plugins.
+
+            Optional query parameter `mime_type` to filter parsers by supported MIME type.
+            """
+            mime_type = quart.request.args.get('mime_type')
+            parsers = await self.ap.knowledge_service.list_parsers(mime_type)
+            return self.success(data={'parsers': parsers})

src/langbot/pkg/api/http/controller/groups/monitoring.py

@@ -0,0 +1,488 @@
+from __future__ import annotations
+
+import datetime
+import quart
+
+from .. import group
+
+
+def parse_iso_datetime(datetime_str: str | None) -> datetime.datetime | None:
+    """Parse ISO 8601 datetime string, handling 'Z' suffix for UTC timezone"""
+    if not datetime_str:
+        return None
+    # Replace 'Z' with '+00:00' for Python 3.10 compatibility
+    if datetime_str.endswith('Z'):
+        datetime_str = datetime_str[:-1] + '+00:00'
+    dt = datetime.datetime.fromisoformat(datetime_str)
+    # Convert to UTC and remove timezone info to match database storage (which stores UTC as naive datetime)
+    if dt.tzinfo is not None:
+        # Convert to UTC and remove timezone info
+        dt = dt.astimezone(datetime.timezone.utc).replace(tzinfo=None)
+    return dt
+
+
+@group.group_class('monitoring', '/api/v1/monitoring')
+class MonitoringRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('/overview', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_overview() -> str:
+            """Get overview metrics"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            metrics = await self.ap.monitoring_service.get_overview_metrics(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+            )
+
+            return self.success(data=metrics)
+
+        @self.route('/messages', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_messages() -> str:
+            """Get message logs"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            session_ids = quart.request.args.getlist('sessionId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            messages, total = await self.ap.monitoring_service.get_messages(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                session_ids=session_ids if session_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'messages': messages,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
+        @self.route('/llm-calls', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_llm_calls() -> str:
+            """Get LLM call records"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            llm_calls, total = await self.ap.monitoring_service.get_llm_calls(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'llm_calls': llm_calls,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
+        @self.route('/embedding-calls', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_embedding_calls() -> str:
+            """Get embedding call records"""
+            # Parse query parameters
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            knowledge_base_id = quart.request.args.get('knowledgeBaseId')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            embedding_calls, total = await self.ap.monitoring_service.get_embedding_calls(
+                start_time=start_time,
+                end_time=end_time,
+                knowledge_base_id=knowledge_base_id if knowledge_base_id else None,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'embedding_calls': embedding_calls,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
+        @self.route('/sessions', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_sessions() -> str:
+            """Get session information"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            is_active_str = quart.request.args.get('isActive')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            # Parse is_active
+            is_active = None
+            if is_active_str:
+                is_active = is_active_str.lower() == 'true'
+
+            sessions, total = await self.ap.monitoring_service.get_sessions(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                is_active=is_active,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'sessions': sessions,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
+        @self.route('/errors', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_errors() -> str:
+            """Get error logs"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            errors, total = await self.ap.monitoring_service.get_errors(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'errors': errors,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
+        @self.route('/data', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_all_data() -> str:
+            """Get all monitoring data in a single request"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 50))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            # Get overview metrics
+            overview = await self.ap.monitoring_service.get_overview_metrics(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+            )
+
+            # Get messages
+            messages, messages_total = await self.ap.monitoring_service.get_messages(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=0,
+            )
+
+            # Get LLM calls
+            llm_calls, llm_calls_total = await self.ap.monitoring_service.get_llm_calls(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=0,
+            )
+
+            # Get sessions
+            sessions, sessions_total = await self.ap.monitoring_service.get_sessions(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                is_active=None,
+                limit=limit,
+                offset=0,
+            )
+
+            # Get errors
+            errors, errors_total = await self.ap.monitoring_service.get_errors(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=0,
+            )
+
+            # Get embedding calls
+            embedding_calls, embedding_calls_total = await self.ap.monitoring_service.get_embedding_calls(
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=0,
+            )
+
+            return self.success(
+                data={
+                    'overview': overview,
+                    'messages': messages,
+                    'llmCalls': llm_calls,
+                    'embeddingCalls': embedding_calls,
+                    'sessions': sessions,
+                    'errors': errors,
+                    'totalCount': {
+                        'messages': messages_total,
+                        'llmCalls': llm_calls_total,
+                        'embeddingCalls': embedding_calls_total,
+                        'sessions': sessions_total,
+                        'errors': errors_total,
+                    },
+                }
+            )
+
+        @self.route('/sessions/<session_id>/analysis', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_session_analysis(session_id: str) -> str:
+            """Get detailed analysis for a specific session"""
+            analysis = await self.ap.monitoring_service.get_session_analysis(session_id)
+
+            # Always return success with the analysis data
+            # The frontend will handle the 'found: false' case
+            return self.success(data=analysis)
+
+        @self.route('/messages/<message_id>/details', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_message_details(message_id: str) -> str:
+            """Get detailed information for a specific message"""
+            details = await self.ap.monitoring_service.get_message_details(message_id)
+
+            if not details.get('found'):
+                return self.error(message=f'Message {message_id} not found', code=404)
+
+            return self.success(data=details)
+
+        @self.route('/export', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def export_data() -> tuple[str, int]:
+            """Export monitoring data as CSV"""
+            # Parse query parameters
+            export_type = quart.request.args.get('type', 'messages')
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 100000))
+
+            # Parse datetime
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            # Get data based on export type
+            if export_type == 'messages':
+                data = await self.ap.monitoring_service.export_messages(
+                    bot_ids=bot_ids if bot_ids else None,
+                    pipeline_ids=pipeline_ids if pipeline_ids else None,
+                    start_time=start_time,
+                    end_time=end_time,
+                    limit=limit,
+                )
+                headers = [
+                    'id',
+                    'timestamp',
+                    'bot_id',
+                    'bot_name',
+                    'pipeline_id',
+                    'pipeline_name',
+                    'runner_name',
+                    'message_content',
+                    'message_text',
+                    'session_id',
+                    'status',
+                    'level',
+                    'platform',
+                    'user_id',
+                ]
+            elif export_type == 'llm-calls':
+                data = await self.ap.monitoring_service.export_llm_calls(
+                    bot_ids=bot_ids if bot_ids else None,
+                    pipeline_ids=pipeline_ids if pipeline_ids else None,
+                    start_time=start_time,
+                    end_time=end_time,
+                    limit=limit,
+                )
+                headers = [
+                    'id',
+                    'timestamp',
+                    'model_name',
+                    'input_tokens',
+                    'output_tokens',
+                    'total_tokens',
+                    'duration_ms',
+                    'cost',
+                    'status',
+                    'bot_id',
+                    'bot_name',
+                    'pipeline_id',
+                    'pipeline_name',
+                    'session_id',
+                    'message_id',
+                    'error_message',
+                ]
+            elif export_type == 'embedding-calls':
+                data = await self.ap.monitoring_service.export_embedding_calls(
+                    start_time=start_time,
+                    end_time=end_time,
+                    limit=limit,
+                )
+                headers = [
+                    'id',
+                    'timestamp',
+                    'model_name',
+                    'prompt_tokens',
+                    'total_tokens',
+                    'duration_ms',
+                    'input_count',
+                    'status',
+                    'error_message',
+                    'knowledge_base_id',
+                    'query_text',
+                    'session_id',
+                    'message_id',
+                    'call_type',
+                ]
+            elif export_type == 'errors':
+                data = await self.ap.monitoring_service.export_errors(
+                    bot_ids=bot_ids if bot_ids else None,
+                    pipeline_ids=pipeline_ids if pipeline_ids else None,
+                    start_time=start_time,
+                    end_time=end_time,
+                    limit=limit,
+                )
+                headers = [
+                    'id',
+                    'timestamp',
+                    'error_type',
+                    'error_message',
+                    'bot_id',
+                    'bot_name',
+                    'pipeline_id',
+                    'pipeline_name',
+                    'session_id',
+                    'message_id',
+                    'stack_trace',
+                ]
+            elif export_type == 'sessions':
+                data = await self.ap.monitoring_service.export_sessions(
+                    bot_ids=bot_ids if bot_ids else None,
+                    pipeline_ids=pipeline_ids if pipeline_ids else None,
+                    start_time=start_time,
+                    end_time=end_time,
+                    limit=limit,
+                )
+                headers = [
+                    'session_id',
+                    'bot_id',
+                    'bot_name',
+                    'pipeline_id',
+                    'pipeline_name',
+                    'message_count',
+                    'start_time',
+                    'last_activity',
+                    'is_active',
+                    'platform',
+                    'user_id',
+                ]
+            else:
+                return self.error(message=f'Invalid export type: {export_type}', code=400)
+
+            # Generate CSV content with UTF-8 BOM for Excel compatibility
+            import io
+
+            output = io.StringIO()
+            # Write UTF-8 BOM for Excel
+            output.write('\ufeff')
+            # Write header
+            output.write(','.join(headers) + '\n')
+
+            # Escape and write each row
+            for row in data:
+                escaped_values = []
+                for header in headers:
+                    value = row.get(header, '')
+                    escaped_values.append(self.ap.monitoring_service._escape_csv_field(value))
+                output.write(','.join(escaped_values) + '\n')
+
+            csv_content = output.getvalue()
+
+            # Return as file download
+            response = await quart.make_response(csv_content)
+            response.headers['Content-Type'] = 'text/csv; charset=utf-8'
+            response.headers['Content-Disposition'] = (
+                f'attachment; filename="monitoring-{export_type}-{int(datetime.datetime.now().timestamp())}.csv"'
+            )
+
+            return response, 200

src/langbot/pkg/api/http/controller/groups/pipelines/pipelines.py

@@ -49,6 +49,14 @@ class PipelinesRouterGroup(group.RouterGroup):
 
                 return self.success()
 
+        @self.route('/<pipeline_uuid>/copy', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(pipeline_uuid: str) -> str:
+            try:
+                new_uuid = await self.ap.pipeline_service.copy_pipeline(pipeline_uuid)
+                return self.success(data={'uuid': new_uuid})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
         @self.route(
             '/<pipeline_uuid>/extensions', methods=['GET', 'PUT'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
         )
@@ -59,25 +67,33 @@ class PipelinesRouterGroup(group.RouterGroup):
                 if pipeline is None:
                     return self.http_status(404, -1, 'pipeline not found')
 
-                plugins = await self.ap.plugin_connector.list_plugins()
+                # Only include plugins with pipeline-related components (Command, EventListener, Tool)
+                # Plugins that only have KnowledgeEngine components are not suitable for pipeline extensions
+                pipeline_component_kinds = ['Command', 'EventListener', 'Tool']
+                plugins = await self.ap.plugin_connector.list_plugins(component_kinds=pipeline_component_kinds)
                 mcp_servers = await self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True)
 
+                extensions_prefs = pipeline.get('extensions_preferences', {})
                 return self.success(
                     data={
-                        'bound_plugins': pipeline.get('extensions_preferences', {}).get('plugins', []),
+                        'enable_all_plugins': extensions_prefs.get('enable_all_plugins', True),
+                        'enable_all_mcp_servers': extensions_prefs.get('enable_all_mcp_servers', True),
+                        'bound_plugins': extensions_prefs.get('plugins', []),
                         'available_plugins': plugins,
-                        'bound_mcp_servers': pipeline.get('extensions_preferences', {}).get('mcp_servers', []),
+                        'bound_mcp_servers': extensions_prefs.get('mcp_servers', []),
                         'available_mcp_servers': mcp_servers,
                     }
                 )
             elif quart.request.method == 'PUT':
                 # Update bound plugins and MCP servers for this pipeline
                 json_data = await quart.request.json
+                enable_all_plugins = json_data.get('enable_all_plugins', True)
+                enable_all_mcp_servers = json_data.get('enable_all_mcp_servers', True)
                 bound_plugins = json_data.get('bound_plugins', [])
                 bound_mcp_servers = json_data.get('bound_mcp_servers', [])
 
                 await self.ap.pipeline_service.update_pipeline_extensions(
-                    pipeline_uuid, bound_plugins, bound_mcp_servers
+                    pipeline_uuid, bound_plugins, bound_mcp_servers, enable_all_plugins, enable_all_mcp_servers
                 )
 
                 return self.success()

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

@@ -1,109 +0,0 @@
-import json
-
-import quart
-
-from ... import group
-
-
-@group.group_class('webchat', '/api/v1/pipelines/<pipeline_uuid>/chat')
-class WebChatDebugRouterGroup(group.RouterGroup):
-    async def initialize(self) -> None:
-        @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')
-
-                if session_type not in ['person', 'group']:
-                    return self.http_status(400, -1, 'session_type must be person or group')
-
-                webchat_adapter = self.ap.platform_mgr.webchat_proxy_bot.adapter
-
-                if not webchat_adapter:
-                    return self.http_status(404, -1, 'WebChat adapter not found')
-
-                if is_stream:
-                    generator = webchat_adapter.send_webchat_message(
-                        pipeline_uuid, session_type, message_chain_obj, is_stream
-                    )
-                    # 设置正确的响应头
-                    headers = {
-                        'Content-Type': 'text/event-stream',
-                        'Transfer-Encoding': 'chunked',
-                        'Cache-Control': 'no-cache',
-                        'Connection': 'keep-alive',
-                    }
-                    return quart.Response(stream_generator(generator), mimetype='text/event-stream', headers=headers)
-
-                else:  # non-stream
-                    result = None
-                    async for message in webchat_adapter.send_webchat_message(
-                        pipeline_uuid, session_type, message_chain_obj
-                    ):
-                        result = message
-                    if result is not None:
-                        return self.success(
-                            data={
-                                'message': result,
-                            }
-                        )
-                    else:
-                        return self.http_status(400, -1, 'message is required')
-
-            except Exception as e:
-                return self.http_status(500, -1, f'Internal server error: {str(e)}')
-
-        @self.route('/messages/<session_type>', methods=['GET'])
-        async def get_messages(pipeline_uuid: str, session_type: str) -> str:
-            """Get the message history of the pipeline for debugging"""
-            try:
-                if session_type not in ['person', 'group']:
-                    return self.http_status(400, -1, 'session_type must be person or group')
-
-                webchat_adapter = self.ap.platform_mgr.webchat_proxy_bot.adapter
-
-                if not webchat_adapter:
-                    return self.http_status(404, -1, 'WebChat adapter not found')
-
-                messages = webchat_adapter.get_webchat_messages(pipeline_uuid, session_type)
-
-                return self.success(data={'messages': messages})
-
-            except Exception as e:
-                return self.http_status(500, -1, f'Internal server error: {str(e)}')
-
-        @self.route('/reset/<session_type>', methods=['POST'])
-        async def reset_session(session_type: str) -> str:
-            """Reset the debug session"""
-            try:
-                if session_type not in ['person', 'group']:
-                    return self.http_status(400, -1, 'session_type must be person or group')
-
-                webchat_adapter = None
-                for bot in self.ap.platform_mgr.bots:
-                    if hasattr(bot.adapter, '__class__') and bot.adapter.__class__.__name__ == 'WebChatAdapter':
-                        webchat_adapter = bot.adapter
-                        break
-
-                if not webchat_adapter:
-                    return self.http_status(404, -1, 'WebChat adapter not found')
-
-                webchat_adapter.reset_debug_session(session_type)
-
-                return self.success(data={'message': 'Session reset successfully'})
-
-            except Exception as e:
-                return self.http_status(500, -1, f'Internal server error: {str(e)}')

src/langbot/pkg/api/http/controller/groups/pipelines/websocket_chat.py

@@ -0,0 +1,243 @@
+"""WebSocket聊天路由 - 支持双向实时通信"""
+
+import asyncio
+import datetime
+import json
+import logging
+
+import quart
+
+from ... import group
+from ......platform.sources.websocket_manager import ws_connection_manager
+
+logger = logging.getLogger(__name__)
+
+
+@group.group_class('websocket_chat', '/api/v1/pipelines/<pipeline_uuid>/ws')
+class WebSocketChatRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        # 直接使用 quart_app 注册 WebSocket 路由
+        @self.quart_app.websocket(self.path + '/connect')
+        async def websocket_connect(pipeline_uuid: str):
+            """
+            建立WebSocket连接
+
+            URL参数:
+                - pipeline_uuid: 流水线UUID
+                - session_type: 会话类型 (person/group)
+            """
+            try:
+                # 获取参数 - 在WebSocket上下文中使用 quart.websocket.args
+                session_type = quart.websocket.args.get('session_type', 'person')
+
+                if session_type not in ['person', 'group']:
+                    await quart.websocket.send(
+                        json.dumps({'type': 'error', 'message': 'session_type must be person or group'})
+                    )
+                    return
+
+                # 获取WebSocket适配器
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    await quart.websocket.send(json.dumps({'type': 'error', 'message': 'WebSocket adapter not found'}))
+                    return
+
+                # 注册连接
+                connection = await ws_connection_manager.add_connection(
+                    websocket=quart.websocket._get_current_object(),
+                    pipeline_uuid=pipeline_uuid,
+                    session_type=session_type,
+                    metadata={'user_agent': quart.websocket.headers.get('User-Agent', '')},
+                )
+
+                # 发送连接成功消息
+                await quart.websocket.send(
+                    json.dumps(
+                        {
+                            'type': 'connected',
+                            'connection_id': connection.connection_id,
+                            'pipeline_uuid': pipeline_uuid,
+                            'session_type': session_type,
+                            'timestamp': connection.created_at.isoformat(),
+                        }
+                    )
+                )
+
+                logger.debug(
+                    f'WebSocket connection established: {connection.connection_id} '
+                    f'(pipeline={pipeline_uuid}, session_type={session_type})'
+                )
+
+                # 创建接收和发送任务
+                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter))
+                send_task = asyncio.create_task(self._handle_send(connection))
+
+                # 等待任务完成
+                try:
+                    await asyncio.gather(receive_task, send_task)
+                except Exception as e:
+                    logger.error(f'WebSocket task execution error: {e}')
+                finally:
+                    # 清理连接
+                    await ws_connection_manager.remove_connection(connection.connection_id)
+                    logger.debug(f'WebSocket connection cleaned: {connection.connection_id}')
+
+            except Exception as e:
+                logger.error(f'WebSocket connection error: {e}', exc_info=True)
+                try:
+                    await quart.websocket.send(json.dumps({'type': 'error', 'message': str(e)}))
+                except:
+                    pass
+
+        @self.route('/messages/<session_type>', methods=['GET'])
+        async def get_messages(pipeline_uuid: str, session_type: str) -> str:
+            """获取消息历史"""
+            try:
+                if session_type not in ['person', 'group']:
+                    return self.http_status(400, -1, 'session_type must be person or group')
+
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    return self.http_status(404, -1, 'WebSocket adapter not found')
+
+                messages = websocket_adapter.get_websocket_messages(pipeline_uuid, session_type)
+
+                return self.success(data={'messages': messages})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/reset/<session_type>', methods=['POST'])
+        async def reset_session(pipeline_uuid: str, session_type: str) -> str:
+            """重置会话"""
+            try:
+                if session_type not in ['person', 'group']:
+                    return self.http_status(400, -1, 'session_type must be person or group')
+
+                websocket_adapter = self.ap.platform_mgr.websocket_proxy_bot.adapter
+
+                if not websocket_adapter:
+                    return self.http_status(404, -1, 'WebSocket adapter not found')
+
+                websocket_adapter.reset_session(pipeline_uuid, session_type)
+
+                return self.success(data={'message': 'Session reset successfully'})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/connections', methods=['GET'])
+        async def get_connections(pipeline_uuid: str) -> str:
+            """获取当前连接统计"""
+            try:
+                stats = ws_connection_manager.get_stats()
+                connections = await ws_connection_manager.get_connections_by_pipeline(pipeline_uuid)
+
+                return self.success(
+                    data={
+                        'stats': stats,
+                        'connections': [
+                            {
+                                'connection_id': conn.connection_id,
+                                'session_type': conn.session_type,
+                                'created_at': conn.created_at.isoformat(),
+                                'last_active': conn.last_active.isoformat(),
+                                'is_active': conn.is_active,
+                            }
+                            for conn in connections
+                        ],
+                    }
+                )
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+        @self.route('/broadcast', methods=['POST'])
+        async def broadcast_message(pipeline_uuid: str) -> str:
+            """向所有连接广播消息（后端主动推送）"""
+            try:
+                data = await quart.request.get_json()
+                message = data.get('message')
+
+                if not message:
+                    return self.http_status(400, -1, 'message is required')
+
+                # 广播消息
+                broadcast_data = {
+                    'type': 'broadcast',
+                    'message': message,
+                    'timestamp': datetime.datetime.now().isoformat(),
+                }
+
+                await ws_connection_manager.broadcast_to_pipeline(pipeline_uuid, broadcast_data)
+
+                return self.success(data={'message': 'Broadcast sent successfully'})
+
+            except Exception as e:
+                return self.http_status(500, -1, f'Internal server error: {str(e)}')
+
+    async def _handle_receive(self, connection, websocket_adapter):
+        """处理接收消息的任务"""
+        try:
+            while connection.is_active:
+                # 接收消息
+                message = await quart.websocket.receive()
+
+                # 更新活跃时间
+                await ws_connection_manager.update_activity(connection.connection_id)
+
+                try:
+                    data = json.loads(message)
+                    message_type = data.get('type', 'message')
+
+                    if message_type == 'ping':
+                        # 心跳响应
+                        await connection.send_queue.put(
+                            {'type': 'pong', 'timestamp': datetime.datetime.now().isoformat()}
+                        )
+
+                    elif message_type == 'message':
+                        # 处理用户消息
+                        logger.debug(f'收到消息: {data} from {connection.connection_id}')
+
+                        # 处理消息（不等待响应，响应会通过broadcast异步发送）
+                        await websocket_adapter.handle_websocket_message(connection, data)
+
+                    elif message_type == 'disconnect':
+                        # 客户端主动断开
+                        logger.debug(f'Client disconnected: {connection.connection_id}')
+                        break
+
+                    else:
+                        logger.warning(f'Unknown message type: {message_type}')
+
+                except json.JSONDecodeError:
+                    logger.error(f'Invalid JSON message: {message}')
+                    await connection.send_queue.put({'type': 'error', 'message': 'Invalid JSON format'})
+
+        except Exception as e:
+            logger.error(f'Receive message error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False
+
+    async def _handle_send(self, connection):
+        """处理发送消息的任务"""
+        try:
+            while connection.is_active:
+                # 从队列获取消息
+                try:
+                    message = await asyncio.wait_for(connection.send_queue.get(), timeout=1.0)
+
+                    # 发送消息
+                    await quart.websocket.send(json.dumps(message))
+
+                except asyncio.TimeoutError:
+                    # 超时继续循环
+                    continue
+
+        except Exception as e:
+            logger.error(f'Send message error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False

src/langbot/pkg/api/http/controller/groups/platform/bots.py

@@ -18,7 +18,8 @@ class BotsRouterGroup(group.RouterGroup):
         @self.route('/<bot_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _(bot_uuid: str) -> str:
             if quart.request.method == 'GET':
-                bot = await self.ap.bot_service.get_bot(bot_uuid)
+                # 返回运行时信息，包括webhook地址等
+                bot = await self.ap.bot_service.get_runtime_bot_info(bot_uuid)
                 if bot is None:
                     return self.http_status(404, -1, 'bot not found')
                 return self.success(data={'bot': bot})
@@ -42,3 +43,32 @@ class BotsRouterGroup(group.RouterGroup):
                     'total_count': total_count,
                 }
             )
+
+        @self.route('/<bot_uuid>/send_message', methods=['POST'], auth_type=group.AuthType.API_KEY)
+        async def _(bot_uuid: str) -> str:
+            """Send message to a specific target via bot"""
+            json_data = await quart.request.json
+            target_type = json_data.get('target_type')
+            target_id = json_data.get('target_id')
+            message_chain_data = json_data.get('message_chain')
+
+            # Validate required fields
+            if not target_type:
+                return self.http_status(400, -1, 'target_type is required')
+            if not target_id:
+                return self.http_status(400, -1, 'target_id is required')
+            if not message_chain_data:
+                return self.http_status(400, -1, 'message_chain is required')
+
+            # Validate target_type
+            if target_type not in ['person', 'group']:
+                return self.http_status(400, -1, 'target_type must be either "person" or "group"')
+
+            try:
+                await self.ap.bot_service.send_message(bot_uuid, target_type, target_id, message_chain_data)
+                return self.success(data={'sent': True})
+            except Exception as e:
+                import traceback
+
+                traceback.print_exc()
+                return self.http_status(500, -1, f'Failed to send message: {str(e)}')

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

@@ -14,17 +14,45 @@ from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
 
 @group.group_class('plugins', '/api/v1/plugins')
 class PluginsRouterGroup(group.RouterGroup):
+    async def _check_extensions_limit(self) -> str | None:
+        """Check if extensions limit is reached. Returns error response if limit exceeded, None otherwise."""
+        limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
+        max_extensions = limitation.get('max_extensions', -1)
+        if max_extensions >= 0:
+            plugins = await self.ap.plugin_connector.list_plugins()
+            mcp_servers = await self.ap.mcp_service.get_mcp_servers()
+            total_extensions = len(plugins) + len(mcp_servers)
+            if total_extensions >= max_extensions:
+                return self.http_status(400, -1, f'Maximum number of extensions ({max_extensions}) reached')
+        return None
+
     async def initialize(self) -> None:
-        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             plugins = await self.ap.plugin_connector.list_plugins()
 
             return self.success(data={'plugins': plugins})
 
+        @self.route('/debug-info', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            """Get plugin debug information including debug URL and key"""
+            debug_info = await self.ap.plugin_connector.get_debug_info()
+
+            # Get debug URL from config
+            plugin_config = self.ap.instance_config.data.get('plugin', {})
+            debug_url = plugin_config.get('display_plugin_debug_url', 'http://localhost:5401')
+
+            return self.success(
+                data={
+                    'debug_url': debug_url,
+                    'plugin_debug_key': debug_info.get('plugin_debug_key', ''),
+                }
+            )
+
         @self.route(
             '/<author>/<plugin_name>/upgrade',
             methods=['POST'],
-            auth_type=group.AuthType.USER_TOKEN,
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def _(author: str, plugin_name: str) -> str:
             ctx = taskmgr.TaskContext.new()
@@ -40,7 +68,7 @@ class PluginsRouterGroup(group.RouterGroup):
         @self.route(
             '/<author>/<plugin_name>',
             methods=['GET', 'DELETE'],
-            auth_type=group.AuthType.USER_TOKEN,
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def _(author: str, plugin_name: str) -> str:
             if quart.request.method == 'GET':
@@ -66,7 +94,7 @@ class PluginsRouterGroup(group.RouterGroup):
         @self.route(
             '/<author>/<plugin_name>/config',
             methods=['GET', 'PUT'],
-            auth_type=group.AuthType.USER_TOKEN,
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def _(author: str, plugin_name: str) -> quart.Response:
             plugin = await self.ap.plugin_connector.get_plugin_info(author, plugin_name)
@@ -82,6 +110,16 @@ class PluginsRouterGroup(group.RouterGroup):
 
                 return self.success(data={})
 
+        @self.route(
+            '/<author>/<plugin_name>/readme',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(author: str, plugin_name: str) -> quart.Response:
+            language = quart.request.args.get('language', 'en')
+            readme = await self.ap.plugin_connector.get_plugin_readme(author, plugin_name, language=language)
+            return self.success(data={'readme': readme})
+
         @self.route(
             '/<author>/<plugin_name>/icon',
             methods=['GET'],
@@ -96,7 +134,18 @@ class PluginsRouterGroup(group.RouterGroup):
 
             return quart.Response(icon_data, mimetype=mime_type)
 
-        @self.route('/github/releases', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route(
+            '/<author>/<plugin_name>/assets/<filepath>',
+            methods=['GET'],
+            auth_type=group.AuthType.NONE,
+        )
+        async def _(author: str, plugin_name: str, filepath: str) -> quart.Response:
+            asset_data = await self.ap.plugin_connector.get_plugin_assets(author, plugin_name, filepath)
+            asset_bytes = base64.b64decode(asset_data['asset_base64'])
+            mime_type = asset_data['mime_type']
+            return quart.Response(asset_bytes, mimetype=mime_type)
+
+        @self.route('/github/releases', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             """Get releases from a GitHub repository URL"""
             data = await quart.request.json
@@ -145,7 +194,7 @@ class PluginsRouterGroup(group.RouterGroup):
         @self.route(
             '/github/release-assets',
             methods=['POST'],
-            auth_type=group.AuthType.USER_TOKEN,
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def _() -> str:
             """Get assets from a specific GitHub release"""
@@ -199,9 +248,13 @@ class PluginsRouterGroup(group.RouterGroup):
             except httpx.RequestError as e:
                 return self.http_status(500, -1, f'Failed to fetch release assets: {str(e)}')
 
-        @self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             """Install plugin from GitHub release asset"""
+            limit_error = await self._check_extensions_limit()
+            if limit_error is not None:
+                return limit_error
+
             data = await quart.request.json
             asset_url = data.get('asset_url', '')
             owner = data.get('owner', '')
@@ -233,9 +286,13 @@ class PluginsRouterGroup(group.RouterGroup):
         @self.route(
             '/install/marketplace',
             methods=['POST'],
-            auth_type=group.AuthType.USER_TOKEN,
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
         )
         async def _() -> str:
+            limit_error = await self._check_extensions_limit()
+            if limit_error is not None:
+                return limit_error
+
             data = await quart.request.json
 
             ctx = taskmgr.TaskContext.new()
@@ -249,8 +306,12 @@ class PluginsRouterGroup(group.RouterGroup):
 
             return self.success(data={'task_id': wrapper.id})
 
-        @self.route('/install/local', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/install/local', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
+            limit_error = await self._check_extensions_limit()
+            if limit_error is not None:
+                return limit_error
+
             file = (await quart.request.files).get('file')
             if file is None:
                 return self.http_status(400, -1, 'file is required')

src/langbot/pkg/api/http/controller/groups/provider/models.py

@@ -9,12 +9,15 @@ class LLMModelsRouterGroup(group.RouterGroup):
         @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
+                provider_uuid = quart.request.args.get('provider_uuid')
+                if provider_uuid:
+                    return self.success(
+                        data={'models': await self.ap.llm_model_service.get_llm_models_by_provider(provider_uuid)}
+                    )
                 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.llm_model_service.create_llm_model(json_data)
-
                 return self.success(data={'uuid': model_uuid})
 
         @self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
@@ -52,12 +55,19 @@ class EmbeddingModelsRouterGroup(group.RouterGroup):
         @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             if quart.request.method == 'GET':
+                provider_uuid = quart.request.args.get('provider_uuid')
+                if provider_uuid:
+                    return self.success(
+                        data={
+                            'models': await self.ap.embedding_models_service.get_embedding_models_by_provider(
+                                provider_uuid
+                            )
+                        }
+                    )
                 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'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)

src/langbot/pkg/api/http/controller/groups/provider/providers.py

@@ -0,0 +1,45 @@
+import quart
+
+from ... import group
+
+
+@group.group_class('models/providers', '/api/v1/provider/providers')
+class ModelProvidersRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                providers = await self.ap.provider_service.get_providers()
+                # Add model counts
+                for provider in providers:
+                    counts = await self.ap.provider_service.get_provider_model_counts(provider['uuid'])
+                    provider['llm_count'] = counts['llm_count']
+                    provider['embedding_count'] = counts['embedding_count']
+                return self.success(data={'providers': providers})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                provider_uuid = await self.ap.provider_service.create_provider(json_data)
+                return self.success(data={'uuid': provider_uuid})
+
+        @self.route(
+            '/<provider_uuid>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def _(provider_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                provider = await self.ap.provider_service.get_provider(provider_uuid)
+                if provider is None:
+                    return self.http_status(404, -1, 'provider not found')
+                counts = await self.ap.provider_service.get_provider_model_counts(provider_uuid)
+                provider['llm_count'] = counts['llm_count']
+                provider['embedding_count'] = counts['embedding_count']
+                return self.success(data={'provider': provider})
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                await self.ap.provider_service.update_provider(provider_uuid, json_data)
+                return self.success()
+            elif quart.request.method == 'DELETE':
+                try:
+                    await self.ap.provider_service.delete_provider(provider_uuid)
+                    return self.success()
+                except ValueError as e:
+                    return self.http_status(400, -1, str(e))

src/langbot/pkg/api/http/controller/groups/survey.py

@@ -0,0 +1,47 @@
+import quart
+
+from .. import group
+
+
+@group.group_class('survey', '/api/v1/survey')
+class SurveyRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('/pending', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _get_pending() -> str:
+            """Get pending survey for the frontend to display."""
+            survey = self.ap.survey.get_pending_survey() if self.ap.survey else None
+            return self.success(data={'survey': survey})
+
+        @self.route('/respond', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _respond() -> str:
+            """Submit survey response."""
+            json_data = await quart.request.json
+            survey_id = json_data.get('survey_id')
+            answers = json_data.get('answers', {})
+            completed = json_data.get('completed', True)
+
+            if not survey_id:
+                return self.fail(1, 'survey_id required')
+
+            if self.ap.survey:
+                ok = await self.ap.survey.submit_response(survey_id, answers, completed)
+                if ok:
+                    return self.success()
+                return self.fail(2, 'Failed to submit response')
+            return self.fail(3, 'Survey not available')
+
+        @self.route('/dismiss', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _dismiss() -> str:
+            """Dismiss survey."""
+            json_data = await quart.request.json
+            survey_id = json_data.get('survey_id')
+
+            if not survey_id:
+                return self.fail(1, 'survey_id required')
+
+            if self.ap.survey:
+                ok = await self.ap.survey.dismiss_survey(survey_id)
+                if ok:
+                    return self.success()
+                return self.fail(2, 'Failed to dismiss')
+            return self.fail(3, 'Survey not available')

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

@@ -13,16 +13,20 @@ class SystemRouterGroup(group.RouterGroup):
                 data={
                     'version': constants.semantic_version,
                     'debug': constants.debug_mode,
+                    'edition': constants.edition,
                     'enable_marketplace': self.ap.instance_config.data.get('plugin', {}).get(
                         'enable_marketplace', True
                     ),
                     'cloud_service_url': (
-                        self.ap.instance_config.data.get('plugin', {}).get(
-                            'cloud_service_url', 'https://space.langbot.app'
-                        )
-                        if 'cloud_service_url' in self.ap.instance_config.data.get('plugin', {})
-                        else 'https://space.langbot.app'
+                        self.ap.instance_config.data.get('space', {}).get('url', 'https://space.langbot.app')
                     ),
+                    'allow_modify_login_info': self.ap.instance_config.data.get('system', {}).get(
+                        'allow_modify_login_info', True
+                    ),
+                    'disable_models_service': self.ap.instance_config.data.get('space', {}).get(
+                        'disable_models_service', False
+                    ),
+                    'limitation': self.ap.instance_config.data.get('system', {}).get('limitation', {}),
                 }
             )
 
@@ -55,17 +59,6 @@ class SystemRouterGroup(group.RouterGroup):
 
             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'],

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

@@ -1,8 +1,10 @@
 import quart
 import argon2
 import asyncio
+import traceback
 
 from .. import group
+from .....entity.errors import account as account_errors
 
 
 @group.group_class('user', '/api/v1/user')
@@ -33,6 +35,8 @@ class UserRouterGroup(group.RouterGroup):
                 token = await self.ap.user_service.authenticate(json_data['user'], json_data['password'])
             except argon2.exceptions.VerifyMismatchError:
                 return self.fail(1, 'Invalid username or password')
+            except ValueError as e:
+                return self.fail(1, str(e))
 
             return self.success(data={'token': token})
 
@@ -70,6 +74,13 @@ class UserRouterGroup(group.RouterGroup):
 
         @self.route('/change-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _(user_email: str) -> str:
+            # Check if password change is allowed
+            allow_modify_login_info = self.ap.instance_config.data.get('system', {}).get(
+                'allow_modify_login_info', True
+            )
+            if not allow_modify_login_info:
+                return self.http_status(403, -1, 'Modifying login info is disabled')
+
             json_data = await quart.request.json
 
             current_password = json_data['current_password']
@@ -83,3 +94,169 @@ class UserRouterGroup(group.RouterGroup):
                 return self.http_status(400, -1, str(e))
 
             return self.success(data={'user': user_email})
+
+        # Space OAuth endpoints (redirect flow)
+
+        @self.route('/space/authorize-url', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def _() -> str:
+            """Get Space OAuth authorization URL for redirect"""
+            redirect_uri = quart.request.args.get('redirect_uri', '')
+            state = quart.request.args.get('state', '')
+
+            if not redirect_uri:
+                return self.fail(1, 'Missing redirect_uri parameter')
+
+            try:
+                authorize_url = self.ap.space_service.get_oauth_authorize_url(redirect_uri, state)
+                return self.success(data={'authorize_url': authorize_url})
+            except Exception as e:
+                return self.fail(1, str(e))
+
+        @self.route('/space/callback', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def _() -> str:
+            """Handle OAuth callback - exchange code for tokens and authenticate"""
+            json_data = await quart.request.json
+            code = json_data.get('code')
+
+            if not code:
+                return self.fail(1, 'Missing authorization code')
+
+            try:
+                # Exchange code for tokens
+                token_data = await self.ap.space_service.exchange_oauth_code(code)
+                access_token = token_data.get('access_token')
+                refresh_token = token_data.get('refresh_token')
+                expires_in = token_data.get('expires_in', 0)
+
+                if not access_token:
+                    return self.fail(1, 'Failed to get access token from Space')
+
+                # Authenticate and create/update local user
+                jwt_token, user_obj = await self.ap.user_service.authenticate_space_user(
+                    access_token, refresh_token, expires_in
+                )
+
+                return self.success(
+                    data={
+                        'token': jwt_token,
+                        'user': user_obj.user,
+                    }
+                )
+            except account_errors.AccountEmailMismatchError as e:
+                return self.fail(3, str(e))
+            except ValueError as e:
+                traceback.print_exc()
+                return self.fail(1, str(e))
+            except Exception as e:
+                traceback.print_exc()
+                return self.fail(2, f'OAuth callback failed: {str(e)}')
+
+        @self.route('/info', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(user_email: str) -> str:
+            """Get current user information including account type"""
+            user_obj = await self.ap.user_service.get_user_by_email(user_email)
+
+            if user_obj is None:
+                return self.http_status(404, -1, 'User not found')
+
+            return self.success(
+                data={
+                    'user': user_obj.user,
+                    'account_type': user_obj.account_type,
+                    'has_password': bool(user_obj.password and user_obj.password.strip()),
+                }
+            )
+
+        @self.route('/space-credits', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(user_email: str) -> str:
+            """Get Space credits balance for current user"""
+            credits = await self.ap.space_service.get_credits(user_email)
+            return self.success(data={'credits': credits})
+
+        @self.route('/account-info', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def _() -> str:
+            """Get account info for login page (account type and has_password)"""
+            if not await self.ap.user_service.is_initialized():
+                return self.success(data={'initialized': False})
+
+            user_obj = await self.ap.user_service.get_first_user()
+            if user_obj is None:
+                return self.success(data={'initialized': False})
+
+            return self.success(
+                data={
+                    'initialized': True,
+                    'account_type': user_obj.account_type,
+                    'has_password': bool(user_obj.password and user_obj.password.strip()),
+                }
+            )
+
+        @self.route('/set-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(user_email: str) -> str:
+            """Set password for Space account (first time) or change password"""
+            json_data = await quart.request.json
+            new_password = json_data.get('new_password')
+            current_password = json_data.get('current_password')
+
+            if not new_password:
+                return self.http_status(400, -1, 'New password is required')
+
+            user_obj = await self.ap.user_service.get_user_by_email(user_email)
+            if user_obj is None:
+                return self.http_status(404, -1, 'User not found')
+
+            try:
+                await self.ap.user_service.set_password(user_email, new_password, current_password)
+                return self.success(data={'user': user_email})
+            except ValueError as e:
+                return self.http_status(400, -1, str(e))
+            except argon2.exceptions.VerifyMismatchError:
+                return self.http_status(400, -1, 'Current password is incorrect')
+
+        @self.route('/bind-space', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def _() -> str:
+            """Bind Space account to existing local account"""
+            # Check if modifying login info is allowed
+            allow_modify_login_info = self.ap.instance_config.data.get('system', {}).get(
+                'allow_modify_login_info', True
+            )
+            if not allow_modify_login_info:
+                return self.http_status(403, -1, 'Modifying login info is disabled')
+
+            json_data = await quart.request.json
+            code = json_data.get('code')
+            state = json_data.get('state')  # JWT token passed as state
+
+            if not code:
+                return self.http_status(400, -1, 'Missing authorization code')
+
+            if not state:
+                return self.http_status(400, -1, 'Missing state parameter')
+
+            # Verify state is a valid JWT token
+            try:
+                user_email = await self.ap.user_service.verify_jwt_token(state)
+            except Exception:
+                return self.http_status(401, -1, 'Invalid or expired state')
+
+            user_obj = await self.ap.user_service.get_user_by_email(user_email)
+            if user_obj is None:
+                return self.http_status(404, -1, 'User not found')
+
+            if user_obj.account_type != 'local':
+                return self.http_status(400, -1, 'Only local accounts can bind to Space')
+
+            try:
+                updated_user = await self.ap.user_service.bind_space_account(user_email, code)
+                jwt_token = await self.ap.user_service.generate_jwt_token(updated_user.user)
+                return self.success(
+                    data={
+                        'token': jwt_token,
+                        'user': updated_user.user,
+                        'account_type': updated_user.account_type,
+                    }
+                )
+            except ValueError as e:
+                return self.http_status(400, -1, str(e))
+            except Exception as e:
+                return self.http_status(500, -1, f'Failed to bind Space account: {str(e)}')

src/langbot/pkg/api/http/controller/groups/webhook_mgmt.py

@@ -0,0 +1,49 @@
+import quart
+
+from .. import group
+
+
+@group.group_class('webhook_mgmt', '/api/v1/webhooks')
+class WebhookManagementRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'])
+        async def _() -> str:
+            if quart.request.method == 'GET':
+                webhooks = await self.ap.webhook_service.get_webhooks()
+                return self.success(data={'webhooks': webhooks})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                name = json_data.get('name', '')
+                url = json_data.get('url', '')
+                description = json_data.get('description', '')
+                enabled = json_data.get('enabled', True)
+
+                if not name:
+                    return self.http_status(400, -1, 'Name is required')
+                if not url:
+                    return self.http_status(400, -1, 'URL is required')
+
+                webhook = await self.ap.webhook_service.create_webhook(name, url, description, enabled)
+                return self.success(data={'webhook': webhook})
+
+        @self.route('/<int:webhook_id>', methods=['GET', 'PUT', 'DELETE'])
+        async def _(webhook_id: int) -> str:
+            if quart.request.method == 'GET':
+                webhook = await self.ap.webhook_service.get_webhook(webhook_id)
+                if webhook is None:
+                    return self.http_status(404, -1, 'Webhook not found')
+                return self.success(data={'webhook': webhook})
+
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+                name = json_data.get('name')
+                url = json_data.get('url')
+                description = json_data.get('description')
+                enabled = json_data.get('enabled')
+
+                await self.ap.webhook_service.update_webhook(webhook_id, name, url, description, enabled)
+                return self.success()
+
+            elif quart.request.method == 'DELETE':
+                await self.ap.webhook_service.delete_webhook(webhook_id)
+                return self.success()

src/langbot/pkg/api/http/controller/groups/webhooks.py

@@ -1,49 +1,54 @@
+from __future__ import annotations
+
 import quart
+import traceback
 
 from .. import group
 
 
-@group.group_class('webhooks', '/api/v1/webhooks')
-class WebhooksRouterGroup(group.RouterGroup):
+@group.group_class('webhooks', '/bots')
+class WebhookRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
-        @self.route('', methods=['GET', 'POST'])
-        async def _() -> str:
-            if quart.request.method == 'GET':
-                webhooks = await self.ap.webhook_service.get_webhooks()
-                return self.success(data={'webhooks': webhooks})
-            elif quart.request.method == 'POST':
-                json_data = await quart.request.json
-                name = json_data.get('name', '')
-                url = json_data.get('url', '')
-                description = json_data.get('description', '')
-                enabled = json_data.get('enabled', True)
+        @self.route('/<bot_uuid>', methods=['GET', 'POST'], auth_type=group.AuthType.NONE)
+        async def handle_webhook(bot_uuid: str):
+            """处理 bot webhook 回调（无子路径）"""
+            return await self._dispatch_webhook(bot_uuid, '')
 
-                if not name:
-                    return self.http_status(400, -1, 'Name is required')
-                if not url:
-                    return self.http_status(400, -1, 'URL is required')
+        @self.route('/<bot_uuid>/<path:path>', methods=['GET', 'POST'], auth_type=group.AuthType.NONE)
+        async def handle_webhook_with_path(bot_uuid: str, path: str):
+            """处理 bot webhook 回调（带子路径）"""
+            return await self._dispatch_webhook(bot_uuid, path)
 
-                webhook = await self.ap.webhook_service.create_webhook(name, url, description, enabled)
-                return self.success(data={'webhook': webhook})
+    async def _dispatch_webhook(self, bot_uuid: str, path: str):
+        """分发 webhook 请求到对应的 bot adapter
 
-        @self.route('/<int:webhook_id>', methods=['GET', 'PUT', 'DELETE'])
-        async def _(webhook_id: int) -> str:
-            if quart.request.method == 'GET':
-                webhook = await self.ap.webhook_service.get_webhook(webhook_id)
-                if webhook is None:
-                    return self.http_status(404, -1, 'Webhook not found')
-                return self.success(data={'webhook': webhook})
+        Args:
+            bot_uuid: Bot 的 UUID
+            path: 子路径（如果有的话）
 
-            elif quart.request.method == 'PUT':
-                json_data = await quart.request.json
-                name = json_data.get('name')
-                url = json_data.get('url')
-                description = json_data.get('description')
-                enabled = json_data.get('enabled')
+        Returns:
+            适配器返回的响应
+        """
+        try:
+            runtime_bot = await self.ap.platform_mgr.get_bot_by_uuid(bot_uuid)
 
-                await self.ap.webhook_service.update_webhook(webhook_id, name, url, description, enabled)
-                return self.success()
+            if not runtime_bot:
+                return quart.jsonify({'error': 'Bot not found'}), 404
 
-            elif quart.request.method == 'DELETE':
-                await self.ap.webhook_service.delete_webhook(webhook_id)
-                return self.success()
+            if not runtime_bot.enable:
+                return quart.jsonify({'error': 'Bot is disabled'}), 403
+
+            if not hasattr(runtime_bot.adapter, 'handle_unified_webhook'):
+                return quart.jsonify({'error': 'Adapter does not support unified webhook'}), 501
+
+            response = await runtime_bot.adapter.handle_unified_webhook(
+                bot_uuid=bot_uuid,
+                path=path,
+                request=quart.request,
+            )
+
+            return response
+
+        except Exception as e:
+            self.ap.logger.error(f'Webhook dispatch error for bot {bot_uuid}: {traceback.format_exc()}')
+            return quart.jsonify({'error': str(e)}), 500

src/langbot/pkg/api/http/controller/main.py

@@ -92,7 +92,11 @@ class HTTPController:
 
         @self.quart_app.route('/')
         async def index():
-            return await quart.send_from_directory(frontend_path, 'index.html', mimetype='text/html')
+            response = await quart.send_from_directory(frontend_path, 'index.html', mimetype='text/html')
+            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+            response.headers['Pragma'] = 'no-cache'
+            response.headers['Expires'] = '0'
+            return response
 
         @self.quart_app.route('/<path:path>')
         async def static_file(path: str):
@@ -101,6 +105,28 @@ class HTTPController:
             ):
                 if os.path.exists(os.path.join(frontend_path, path + '.html')):
                     path += '.html'
+                elif path.startswith('home/'):
+                    # SPA fallback for /home/* sub-routes.
+                    # Entity detail views use query params (e.g. /home/bots?id=uuid),
+                    # so the pre-rendered list page is served directly via path + '.html'.
+                    # This fallback handles any remaining unmatched sub-paths.
+                    segments = path.rstrip('/').split('/')
+
+                    # Walk up parent segments looking for matching .html files
+                    for i in range(len(segments) - 1, 0, -1):
+                        parent_path = '/'.join(segments[:i]) + '.html'
+                        if os.path.exists(os.path.join(frontend_path, parent_path)):
+                            response = await quart.send_from_directory(frontend_path, parent_path, mimetype='text/html')
+                            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                            response.headers['Pragma'] = 'no-cache'
+                            response.headers['Expires'] = '0'
+                            return response
+                    # Final fallback to index.html for /home/* routes
+                    response = await quart.send_from_directory(frontend_path, 'index.html', mimetype='text/html')
+                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                    response.headers['Pragma'] = 'no-cache'
+                    response.headers['Expires'] = '0'
+                    return response
                 else:
                     return await quart.send_from_directory(frontend_path, '404.html')
 

src/langbot/pkg/api/http/service/bot.py

@@ -58,12 +58,44 @@ class BotService:
         if runtime_bot is not None:
             adapter_runtime_values['bot_account_id'] = runtime_bot.adapter.bot_account_id
 
+        # Webhook URL for unified webhook adapters (independent of bot running state)
+        if persistence_bot['adapter'] in [
+            'wecom',
+            'wecombot',
+            'officialaccount',
+            'qqofficial',
+            'slack',
+            'wecomcs',
+            'LINE',
+            'lark',
+        ]:
+            webhook_prefix = self.ap.instance_config.data['api'].get('webhook_prefix', 'http://127.0.0.1:5300')
+            extra_webhook_prefix = self.ap.instance_config.data['api'].get('extra_webhook_prefix', '')
+            webhook_url = f'/bots/{bot_uuid}'
+            adapter_runtime_values['webhook_url'] = webhook_url
+            adapter_runtime_values['webhook_full_url'] = f'{webhook_prefix}{webhook_url}'
+            adapter_runtime_values['extra_webhook_full_url'] = (
+                f'{extra_webhook_prefix}{webhook_url}' if extra_webhook_prefix else ''
+            )
+        else:
+            adapter_runtime_values['webhook_url'] = None
+            adapter_runtime_values['webhook_full_url'] = None
+            adapter_runtime_values['extra_webhook_full_url'] = None
+
         persistence_bot['adapter_runtime_values'] = adapter_runtime_values
 
         return persistence_bot
 
     async def create_bot(self, bot_data: dict) -> str:
         """Create bot"""
+        # Check limitation
+        limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
+        max_bots = limitation.get('max_bots', -1)
+        if max_bots >= 0:
+            existing_bots = await self.get_bots()
+            if len(existing_bots) >= max_bots:
+                raise ValueError(f'Maximum number of bots ({max_bots}) reached')
+
         # TODO: 检查配置信息格式
         bot_data['uuid'] = str(uuid.uuid4())
 
@@ -139,3 +171,29 @@ class BotService:
         logs, total_count = await runtime_bot.logger.get_logs(from_index, max_count)
 
         return [log.to_json() for log in logs], total_count
+
+    async def send_message(self, bot_uuid: str, target_type: str, target_id: str, message_chain_data: dict) -> None:
+        """Send message to a specific target via bot
+
+        Args:
+            bot_uuid: The UUID of the bot
+            target_type: The type of the target, can be "group", "person"
+            target_id: The ID of the target
+            message_chain_data: The message chain data in dict format
+        """
+        # Import here to avoid circular imports
+        import langbot_plugin.api.entities.builtin.platform.message as platform_message
+
+        # Get runtime bot
+        runtime_bot = await self.ap.platform_mgr.get_bot_by_uuid(bot_uuid)
+        if runtime_bot is None:
+            raise Exception(f'Bot not found: {bot_uuid}')
+
+        # Validate and convert message chain
+        try:
+            message_chain = platform_message.MessageChain.model_validate(message_chain_data)
+        except Exception as e:
+            raise Exception(f'Invalid message_chain format: {str(e)}')
+
+        # Send message via adapter
+        await runtime_bot.adapter.send_message(target_type, str(target_id), message_chain)

src/langbot/pkg/api/http/service/knowledge.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import uuid
 import sqlalchemy
 
 from ....core import app
@@ -17,70 +16,99 @@ class KnowledgeService:
 
     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
-        ]
+        return await self.ap.rag_mgr.get_all_knowledge_base_details()
 
     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)
+        return await self.ap.rag_mgr.get_knowledge_base_details(kb_uuid)
 
     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))
+        # In new architecture, we delegate entirely to RAGManager which uses plugins.
+        # Legacy internal KB creation is removed.
 
-        kb = await self.get_knowledge_base(kb_data['uuid'])
+        knowledge_engine_plugin_id = kb_data.get('knowledge_engine_plugin_id')
+        if not knowledge_engine_plugin_id:
+            raise ValueError('knowledge_engine_plugin_id is required')
 
-        await self.ap.rag_mgr.load_knowledge_base(kb)
-
-        return kb_data['uuid']
+        kb = await self.ap.rag_mgr.create_knowledge_base(
+            name=kb_data.get('name', 'Untitled'),
+            knowledge_engine_plugin_id=knowledge_engine_plugin_id,
+            creation_settings=kb_data.get('creation_settings', {}),
+            retrieval_settings=kb_data.get('retrieval_settings', {}),
+            description=kb_data.get('description', ''),
+        )
+        return kb.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']
+        # Filter to only mutable fields
+        filtered_data = {k: v for k, v in kb_data.items() if k in persistence_rag.KnowledgeBase.MUTABLE_FIELDS}
 
-        if 'embedding_model_uuid' in kb_data:
-            del kb_data['embedding_model_uuid']
+        if not filtered_data:
+            return
 
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_rag.KnowledgeBase)
-            .values(kb_data)
+            .values(filtered_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)
+        if kb is None:
+            raise Exception('Knowledge base not found after update')
 
         await self.ap.rag_mgr.load_knowledge_base(kb)
 
-    async def store_file(self, kb_uuid: str, file_id: str) -> int:
+    async def _check_doc_capability(self, kb_uuid: str, operation: str) -> None:
+        """Check if the KB's Knowledge Engine supports document operations.
+
+        Args:
+            kb_uuid: Knowledge base UUID.
+            operation: Human-readable operation name for error messages.
+
+        Raises:
+            Exception: If the KB does not support doc_ingestion.
+        """
+        kb_info = await self.ap.rag_mgr.get_knowledge_base_details(kb_uuid)
+        if not kb_info:
+            raise Exception('Knowledge base not found')
+        capabilities = kb_info.get('knowledge_engine', {}).get('capabilities', [])
+        if 'doc_ingestion' not in capabilities:
+            raise Exception(f'This knowledge base does not support {operation}')
+
+    async def store_file(self, kb_uuid: str, file_id: str, parser_plugin_id: str | None = None) -> str:
         """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]:
+        await self._check_doc_capability(kb_uuid, 'document upload')
+
+        result = await runtime_kb.store_file(file_id, parser_plugin_id=parser_plugin_id)
+
+        # Update the KB's updated_at timestamp
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_rag.KnowledgeBase)
+            .values(updated_at=sqlalchemy.func.now())
+            .where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
+        )
+
+        return result
+
+    async def retrieve_knowledge_base(
+        self, kb_uuid: str, query: str, retrieval_settings: dict | None = None
+    ) -> 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)
-        ]
+
+        # Pass retrieval_settings
+        results = await runtime_kb.retrieve(query, settings=retrieval_settings)
+
+        return [result.model_dump() for result in results]
 
     async def get_files_by_knowledge_base(self, kb_uuid: str) -> list[dict]:
         """获取知识库文件"""
@@ -95,17 +123,28 @@ class KnowledgeService:
         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 self._check_doc_capability(kb_uuid, 'document deletion')
+
         await runtime_kb.delete_file(file_id)
 
+        # Update the KB's updated_at timestamp
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_rag.KnowledgeBase)
+            .values(updated_at=sqlalchemy.func.now())
+            .where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
+        )
+
     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)
-
+        # Delete from DB first to commit the deletion, then clean up runtime/plugin (best-effort)
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.delete(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
         )
 
         # delete files
+        # NOTE: Chunk cleanup is for legacy (pre-plugin) KBs that stored chunks locally.
+        # For plugin-based Knowledge Engines, the Chunk table is not populated, so this is a no-op.
         files = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
         )
@@ -118,3 +157,53 @@ class KnowledgeService:
             await self.ap.persistence_mgr.execute_async(
                 sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file.uuid)
             )
+
+        # Remove from runtime and notify plugin (best-effort, DB is already cleaned up)
+        await self.ap.rag_mgr.delete_knowledge_base(kb_uuid)
+
+    # ================= Knowledge Engine Discovery =================
+
+    async def list_knowledge_engines(self) -> list[dict]:
+        """List all available Knowledge Engines from plugins."""
+        engines = []
+
+        if not self.ap.plugin_connector.is_enable_plugin:
+            return engines
+
+        # Get KnowledgeEngine plugins
+        try:
+            knowledge_engines = await self.ap.plugin_connector.list_knowledge_engines()
+            engines.extend(knowledge_engines)
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to list Knowledge Engines from plugins: {e}')
+
+        return engines
+
+    async def list_parsers(self, mime_type: str | None = None) -> list[dict]:
+        """List available parsers, optionally filtered by MIME type."""
+        if not self.ap.plugin_connector.is_enable_plugin:
+            return []
+        try:
+            parsers = await self.ap.plugin_connector.list_parsers()
+            if mime_type:
+                parsers = [p for p in parsers if mime_type in p.get('supported_mime_types', [])]
+            return parsers
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to list parsers: {e}')
+            return []
+
+    async def get_engine_creation_schema(self, plugin_id: str) -> dict:
+        """Get creation settings schema for a specific Knowledge Engine."""
+        try:
+            return await self.ap.plugin_connector.get_rag_creation_schema(plugin_id)
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to get creation schema for {plugin_id}: {e}')
+            return {}
+
+    async def get_engine_retrieval_schema(self, plugin_id: str) -> dict:
+        """Get retrieval settings schema for a specific Knowledge Engine."""
+        try:
+            return await self.ap.plugin_connector.get_rag_retrieval_schema(plugin_id)
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to get retrieval schema for {plugin_id}: {e}')
+            return {}

src/langbot/pkg/api/http/service/mcp.py

@@ -38,6 +38,16 @@ class MCPService:
         return serialized_servers
 
     async def create_mcp_server(self, server_data: dict) -> str:
+        # Check limitation (extensions = MCP servers + plugins)
+        limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
+        max_extensions = limitation.get('max_extensions', -1)
+        if max_extensions >= 0:
+            existing_mcp_servers = await self.get_mcp_servers()
+            plugins = await self.ap.plugin_connector.list_plugins()
+            total_extensions = len(existing_mcp_servers) + len(plugins)
+            if total_extensions >= max_extensions:
+                raise ValueError(f'Maximum number of extensions ({max_extensions}) reached')
+
         server_data['uuid'] = str(uuid.uuid4())
         await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_mcp.MCPServer).values(server_data))
 

src/langbot/pkg/api/http/service/model.py

@@ -11,6 +11,18 @@ from ....entity.persistence import pipeline as persistence_pipeline
 from ....provider.modelmgr import requester as model_requester
 
 
+def _parse_provider_api_keys(provider_dict: dict) -> dict:
+    """Parse api_keys if it's a JSON string"""
+    if isinstance(provider_dict.get('api_keys'), str):
+        import json
+
+        try:
+            provider_dict['api_keys'] = json.loads(provider_dict['api_keys'])
+        except Exception:
+            provider_dict['api_keys'] = []
+    return provider_dict
+
+
 class LLMModelsService:
     ap: app.Application
 
@@ -18,59 +30,136 @@ class LLMModelsService:
         self.ap = ap
 
     async def get_llm_models(self, include_secret: bool = True) -> list[dict]:
+        """Get all LLM models with provider info"""
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
-
         models = result.all()
 
-        masked_columns = []
-        if not include_secret:
-            masked_columns = ['api_keys']
+        # Get all providers for lookup
+        providers_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider)
+        )
+        providers = {p.uuid: p for p in providers_result.all()}
 
-        return [
-            self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model, masked_columns)
-            for model in models
-        ]
+        models_list = []
+        for model in models:
+            model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+            provider = providers.get(model.provider_uuid)
+            if provider:
+                provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+                provider_dict = _parse_provider_api_keys(provider_dict)
+                if not include_secret:
+                    provider_dict['api_keys'] = ['***'] * len(provider_dict.get('api_keys', []))
+                model_dict['provider'] = provider_dict
+            models_list.append(model_dict)
 
-    async def create_llm_model(self, model_data: dict) -> str:
-        model_data['uuid'] = str(uuid.uuid4())
+        return models_list
+
+    async def get_llm_models_by_provider(self, provider_uuid: str) -> list[dict]:
+        """Get LLM models by provider UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.LLMModel).where(
+                persistence_model.LLMModel.provider_uuid == provider_uuid
+            )
+        )
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, m) for m in models]
+
+    async def create_llm_model(
+        self, model_data: dict, preserve_uuid: bool = False, auto_set_to_default_pipeline: bool = True
+    ) -> str:
+        """Create a new LLM model"""
+        if not preserve_uuid:
+            model_data['uuid'] = str(uuid.uuid4())
+
+        # Handle provider creation if needed
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                # Create new provider
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
 
         await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_model.LLMModel).values(**model_data))
 
-        llm_model = await self.get_llm_model(model_data['uuid'])
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_llm_model(llm_model)
-
-        # check if default pipeline has no model bound
-        result = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
-                persistence_pipeline.LegacyPipeline.is_default == True
-            )
+        runtime_llm_model = await self.ap.model_mgr.load_llm_model_with_provider(
+            persistence_model.LLMModel(**model_data),
+            runtime_provider,
         )
-        pipeline = result.first()
-        if pipeline is not None and pipeline.config['ai']['local-agent']['model'] == '':
-            pipeline_config = pipeline.config
-            pipeline_config['ai']['local-agent']['model'] = model_data['uuid']
-            pipeline_data = {'config': pipeline_config}
-            await self.ap.pipeline_service.update_pipeline(pipeline.uuid, pipeline_data)
+        self.ap.model_mgr.llm_models.append(runtime_llm_model)
+
+        if auto_set_to_default_pipeline:
+            # set the default pipeline model to this model
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                    persistence_pipeline.LegacyPipeline.is_default == True
+                )
+            )
+            pipeline = result.first()
+            if pipeline is not None:
+                model_config = pipeline.config.get('ai', {}).get('local-agent', {}).get('model', {})
+                if not model_config.get('primary', ''):
+                    pipeline_config = pipeline.config
+                    pipeline_config['ai']['local-agent']['model'] = {
+                        'primary': model_data['uuid'],
+                        'fallbacks': [],
+                    }
+                    pipeline_data = {'config': pipeline_config}
+                    await self.ap.pipeline_service.update_pipeline(pipeline.uuid, pipeline_data)
 
         return model_data['uuid']
 
     async def get_llm_model(self, model_uuid: str) -> dict | None:
+        """Get a single LLM model with provider info"""
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_model.LLMModel).where(persistence_model.LLMModel.uuid == model_uuid)
         )
-
         model = result.first()
-
         if model is None:
             return None
 
-        return self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+        model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+
+        # Get provider
+        provider_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == model.provider_uuid
+            )
+        )
+        provider = provider_result.first()
+        if provider:
+            provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+            model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+
+        return model_dict
 
     async def update_llm_model(self, model_uuid: str, model_data: dict) -> None:
+        """Update an existing LLM model"""
         if 'uuid' in model_data:
             del model_data['uuid']
 
+        # Handle provider update if needed
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_model.LLMModel)
             .where(persistence_model.LLMModel.uuid == model_uuid)
@@ -79,18 +168,25 @@ class LLMModelsService:
 
         await self.ap.model_mgr.remove_llm_model(model_uuid)
 
-        llm_model = await self.get_llm_model(model_uuid)
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_llm_model(llm_model)
+        runtime_llm_model = await self.ap.model_mgr.load_llm_model_with_provider(
+            persistence_model.LLMModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.llm_models.append(runtime_llm_model)
 
     async def delete_llm_model(self, model_uuid: str) -> None:
+        """Delete an LLM model"""
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.delete(persistence_model.LLMModel).where(persistence_model.LLMModel.uuid == model_uuid)
         )
-
         await self.ap.model_mgr.remove_llm_model(model_uuid)
 
     async def test_llm_model(self, model_uuid: str, model_data: dict) -> None:
+        """Test an LLM model"""
         runtime_llm_model: model_requester.RuntimeLLMModel | None = None
 
         if model_uuid != '_':
@@ -98,25 +194,18 @@ class LLMModelsService:
                 if model.model_entity.uuid == model_uuid:
                     runtime_llm_model = model
                     break
-
             if runtime_llm_model is None:
                 raise Exception('model not found')
-
         else:
-            runtime_llm_model = await self.ap.model_mgr.init_runtime_llm_model(model_data)
+            runtime_llm_model = await self.ap.model_mgr.init_temporary_runtime_llm_model(model_data)
 
-        # Mon Nov 10 2025: Commented for some providers may not support thinking parameter
-        # # 有些模型厂商默认开启了思考功能，测试容易延迟
-        # extra_args = model_data.get('extra_args', {})
-        # if not extra_args or 'thinking' not in extra_args:
-        #     extra_args['thinking'] = {'type': 'disabled'}
-
-        await runtime_llm_model.requester.invoke_llm(
+        extra_args = model_data.get('extra_args', {})
+        await runtime_llm_model.provider.invoke_llm(
             query=None,
             model=runtime_llm_model,
             messages=[provider_message.Message(role='user', content='Hello, world! Please just reply a "Hello".')],
             funcs=[],
-            # extra_args=extra_args,
+            extra_args=extra_args,
         )
 
 
@@ -127,42 +216,111 @@ class EmbeddingModelsService:
         self.ap = ap
 
     async def get_embedding_models(self) -> list[dict]:
+        """Get all embedding models with provider info"""
         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())
+        providers_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider)
+        )
+        providers = {p.uuid: p for p in providers_result.all()}
+
+        models_list = []
+        for model in models:
+            model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+            provider = providers.get(model.provider_uuid)
+            if provider:
+                provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+                model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+            models_list.append(model_dict)
+
+        return models_list
+
+    async def get_embedding_models_by_provider(self, provider_uuid: str) -> list[dict]:
+        """Get embedding models by provider UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.EmbeddingModel).where(
+                persistence_model.EmbeddingModel.provider_uuid == provider_uuid
+            )
+        )
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, m) for m in models]
+
+    async def create_embedding_model(self, model_data: dict, preserve_uuid: bool = False) -> str:
+        """Create a new embedding model"""
+        if not preserve_uuid:
+            model_data['uuid'] = str(uuid.uuid4())
+
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
 
         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'])
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_embedding_model(embedding_model)
+        runtime_embedding_model = await self.ap.model_mgr.load_embedding_model_with_provider(
+            persistence_model.EmbeddingModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.embedding_models.append(runtime_embedding_model)
 
         return model_data['uuid']
 
     async def get_embedding_model(self, model_uuid: str) -> dict | None:
+        """Get a single embedding model with provider info"""
         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)
+        model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+
+        provider_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == model.provider_uuid
+            )
+        )
+        provider = provider_result.first()
+        if provider:
+            provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+            model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+
+        return model_dict
 
     async def update_embedding_model(self, model_uuid: str, model_data: dict) -> None:
+        """Update an existing embedding model"""
         if 'uuid' in model_data:
             del model_data['uuid']
 
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_model.EmbeddingModel)
             .where(persistence_model.EmbeddingModel.uuid == model_uuid)
@@ -171,20 +329,27 @@ class EmbeddingModelsService:
 
         await self.ap.model_mgr.remove_embedding_model(model_uuid)
 
-        embedding_model = await self.get_embedding_model(model_uuid)
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_embedding_model(embedding_model)
+        runtime_embedding_model = await self.ap.model_mgr.load_embedding_model_with_provider(
+            persistence_model.EmbeddingModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.embedding_models.append(runtime_embedding_model)
 
     async def delete_embedding_model(self, model_uuid: str) -> None:
+        """Delete an embedding model"""
         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:
+        """Test an embedding model"""
         runtime_embedding_model: model_requester.RuntimeEmbeddingModel | None = None
 
         if model_uuid != '_':
@@ -192,14 +357,12 @@ class EmbeddingModelsService:
                 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)
+            runtime_embedding_model = await self.ap.model_mgr.init_temporary_runtime_embedding_model(model_data)
 
-        await runtime_embedding_model.requester.invoke_embedding(
+        await runtime_embedding_model.provider.invoke_embedding(
             model=runtime_embedding_model,
             input_text=['Hello, world!'],
             extra_args={},

src/langbot/pkg/api/http/service/pipeline.py

@@ -76,6 +76,14 @@ class PipelineService:
     async def create_pipeline(self, pipeline_data: dict, default: bool = False) -> str:
         from ....utils import paths as path_utils
 
+        # Check limitation
+        limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
+        max_pipelines = limitation.get('max_pipelines', -1)
+        if max_pipelines >= 0:
+            existing_pipelines = await self.get_pipelines()
+            if len(existing_pipelines) >= max_pipelines:
+                raise ValueError(f'Maximum number of pipelines ({max_pipelines}) reached')
+
         pipeline_data['uuid'] = str(uuid.uuid4())
         pipeline_data['for_version'] = self.ap.ver_mgr.get_current_version()
         pipeline_data['stages'] = default_stage_order.copy()
@@ -85,6 +93,15 @@ class PipelineService:
         with open(template_path, 'r', encoding='utf-8') as f:
             pipeline_data['config'] = json.load(f)
 
+        # Ensure extensions_preferences is set with enable_all_plugins and enable_all_mcp_servers=True by default
+        if 'extensions_preferences' not in pipeline_data:
+            pipeline_data['extensions_preferences'] = {
+                'enable_all_plugins': True,
+                'enable_all_mcp_servers': True,
+                'plugins': [],
+                'mcp_servers': [],
+            }
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.insert(persistence_pipeline.LegacyPipeline).values(**pipeline_data)
         )
@@ -142,8 +159,67 @@ class PipelineService:
         )
         await self.ap.pipeline_mgr.remove_pipeline(pipeline_uuid)
 
+    async def copy_pipeline(self, pipeline_uuid: str) -> str:
+        """Copy a pipeline with all its configurations"""
+        # Check limitation
+        limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
+        max_pipelines = limitation.get('max_pipelines', -1)
+        if max_pipelines >= 0:
+            existing_pipelines = await self.get_pipelines()
+            if len(existing_pipelines) >= max_pipelines:
+                raise ValueError(f'Maximum number of pipelines ({max_pipelines}) reached')
+
+        # Get the original pipeline
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                persistence_pipeline.LegacyPipeline.uuid == pipeline_uuid
+            )
+        )
+
+        original_pipeline = result.first()
+        if original_pipeline is None:
+            raise ValueError(f'Pipeline {pipeline_uuid} not found')
+
+        # Create new pipeline data
+        new_uuid = str(uuid.uuid4())
+        new_pipeline_data = {
+            'uuid': new_uuid,
+            'name': f'{original_pipeline.name} (Copy)',
+            'description': original_pipeline.description,
+            'for_version': self.ap.ver_mgr.get_current_version(),
+            'stages': original_pipeline.stages.copy() if original_pipeline.stages else default_stage_order.copy(),
+            'config': original_pipeline.config.copy() if original_pipeline.config else {},
+            'is_default': False,
+            'extensions_preferences': (
+                original_pipeline.extensions_preferences.copy()
+                if original_pipeline.extensions_preferences
+                else {
+                    'enable_all_plugins': True,
+                    'enable_all_mcp_servers': True,
+                    'plugins': [],
+                    'mcp_servers': [],
+                }
+            ),
+        }
+
+        # Insert the new pipeline
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_pipeline.LegacyPipeline).values(**new_pipeline_data)
+        )
+
+        # Load the new pipeline
+        pipeline = await self.get_pipeline(new_uuid)
+        await self.ap.pipeline_mgr.load_pipeline(pipeline)
+
+        return new_uuid
+
     async def update_pipeline_extensions(
-        self, pipeline_uuid: str, bound_plugins: list[dict], bound_mcp_servers: list[str] = None
+        self,
+        pipeline_uuid: str,
+        bound_plugins: list[dict],
+        bound_mcp_servers: list[str] = None,
+        enable_all_plugins: bool = True,
+        enable_all_mcp_servers: bool = True,
     ) -> None:
         """Update the bound plugins and MCP servers for a pipeline"""
         # Get current pipeline
@@ -159,6 +235,8 @@ class PipelineService:
 
         # Update extensions_preferences
         extensions_preferences = pipeline.extensions_preferences or {}
+        extensions_preferences['enable_all_plugins'] = enable_all_plugins
+        extensions_preferences['enable_all_mcp_servers'] = enable_all_mcp_servers
         extensions_preferences['plugins'] = bound_plugins
         if bound_mcp_servers is not None:
             extensions_preferences['mcp_servers'] = bound_mcp_servers

src/langbot/pkg/api/http/service/provider.py

@@ -0,0 +1,166 @@
+from __future__ import annotations
+
+import uuid
+
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import model as persistence_model
+
+
+class ModelProviderService:
+    """Service for managing model providers"""
+
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_providers(self) -> list[dict]:
+        """Get all providers"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.ModelProvider))
+        providers = result.all()
+        providers_list = []
+        for p in providers:
+            provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, p)
+            # Parse api_keys if it's a JSON string
+            if isinstance(provider_dict.get('api_keys'), str):
+                import json
+
+                try:
+                    provider_dict['api_keys'] = json.loads(provider_dict['api_keys'])
+                except Exception:
+                    provider_dict['api_keys'] = []
+            providers_list.append(provider_dict)
+        return providers_list
+
+    async def get_provider(self, provider_uuid: str) -> dict | None:
+        """Get a single provider by UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == provider_uuid
+            )
+        )
+        provider = result.first()
+        if provider is None:
+            return None
+        provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+        # Parse api_keys if it's a JSON string
+        if isinstance(provider_dict.get('api_keys'), str):
+            import json
+
+            try:
+                provider_dict['api_keys'] = json.loads(provider_dict['api_keys'])
+            except Exception:
+                provider_dict['api_keys'] = []
+        return provider_dict
+
+    async def create_provider(self, provider_data: dict) -> str:
+        """Create a new provider"""
+        provider_data['uuid'] = str(uuid.uuid4())
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_model.ModelProvider).values(**provider_data)
+        )
+
+        # load to runtime
+        runtime_provider = await self.ap.model_mgr.load_provider(provider_data)
+        self.ap.model_mgr.provider_dict[runtime_provider.provider_entity.uuid] = runtime_provider
+        return provider_data['uuid']
+
+    async def update_provider(self, provider_uuid: str, provider_data: dict) -> None:
+        """Update an existing provider"""
+        if 'uuid' in provider_data:
+            del provider_data['uuid']
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_model.ModelProvider)
+            .where(persistence_model.ModelProvider.uuid == provider_uuid)
+            .values(**provider_data)
+        )
+        await self.ap.model_mgr.reload_provider(provider_uuid)
+
+    async def delete_provider(self, provider_uuid: str) -> None:
+        """Delete a provider (only if no models reference it)"""
+        # Check if any models use this provider
+        llm_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.LLMModel).where(
+                persistence_model.LLMModel.provider_uuid == provider_uuid
+            )
+        )
+        if llm_result.first() is not None:
+            raise ValueError('Cannot delete provider: LLM models still reference it')
+
+        embedding_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.EmbeddingModel).where(
+                persistence_model.EmbeddingModel.provider_uuid == provider_uuid
+            )
+        )
+        if embedding_result.first() is not None:
+            raise ValueError('Cannot delete provider: Embedding models still reference it')
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == provider_uuid
+            )
+        )
+
+        await self.ap.model_mgr.remove_provider(provider_uuid)
+
+    async def get_provider_model_counts(self, provider_uuid: str) -> dict:
+        """Get count of models using this provider"""
+        llm_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(sqlalchemy.func.count())
+            .select_from(persistence_model.LLMModel)
+            .where(persistence_model.LLMModel.provider_uuid == provider_uuid)
+        )
+        llm_count = llm_result.scalar() or 0
+
+        embedding_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(sqlalchemy.func.count())
+            .select_from(persistence_model.EmbeddingModel)
+            .where(persistence_model.EmbeddingModel.provider_uuid == provider_uuid)
+        )
+        embedding_count = embedding_result.scalar() or 0
+
+        return {'llm_count': llm_count, 'embedding_count': embedding_count}
+
+    async def find_or_create_provider(self, requester: str, base_url: str, api_keys: list) -> str:
+        """Find existing provider or create new one"""
+        # Try to find existing provider with same config
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.requester == requester,
+                persistence_model.ModelProvider.base_url == base_url,
+            )
+        )
+        for provider in result.all():
+            if sorted(provider.api_keys or []) == sorted(api_keys or []):
+                return provider.uuid
+
+        # Create new provider
+        provider_name = requester
+        if base_url:
+            try:
+                from urllib.parse import urlparse
+
+                parsed = urlparse(base_url)
+                provider_name = parsed.netloc or requester
+            except Exception:
+                pass
+
+        return await self.create_provider(
+            {
+                'name': provider_name,
+                'requester': requester,
+                'base_url': base_url,
+                'api_keys': api_keys or [],
+            }
+        )
+
+    async def update_space_model_provider_api_keys(self, api_key: str) -> None:
+        """Update Space model provider API keys"""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(persistence_model.ModelProvider)
+            .where(persistence_model.ModelProvider.uuid == '00000000-0000-0000-0000-000000000000')
+            .values(api_keys=[api_key])
+        )
+        await self.ap.model_mgr.reload_provider('00000000-0000-0000-0000-000000000000')

src/langbot/pkg/api/http/service/space.py

@@ -0,0 +1,189 @@
+from __future__ import annotations
+
+from langbot.pkg.utils import httpclient
+import typing
+import datetime
+import time
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import user
+from ....entity.dto.space_model import SpaceModel
+
+
+class SpaceService:
+    """Service for interacting with LangBot Space API"""
+
+    ap: app.Application
+    _credits_cache: typing.Dict[str, typing.Tuple[int, float]]  # {user_email: (credits, timestamp)}
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+        self._credits_cache = {}
+
+    def _get_space_config(self) -> typing.Dict[str, str]:
+        """Get Space configuration from config file"""
+        space_config = self.ap.instance_config.data.get('space', {})
+        return {
+            'url': space_config.get('url', 'https://space.langbot.app'),
+            'oauth_authorize_url': space_config.get('oauth_authorize_url', 'https://space.langbot.app/auth/authorize'),
+        }
+
+    async def _get_user_by_email(self, user_email: str) -> user.User | None:
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(user.User).where(user.User.user == user_email)
+        )
+        result_list = result.all()
+        return result_list[0] if result_list else None
+
+    async def _ensure_valid_token(self, user_email: str) -> str | None:
+        """Ensure access token is valid, refresh if expired. Returns valid access_token or None."""
+        user_obj = await self._get_user_by_email(user_email)
+        if not user_obj or user_obj.account_type != 'space':
+            return None
+
+        if not user_obj.space_access_token:
+            return None
+
+        # Check if token is expired (with 60s buffer)
+        if user_obj.space_access_token_expires_at:
+            if datetime.datetime.now() >= user_obj.space_access_token_expires_at - datetime.timedelta(seconds=60):
+                # Token expired, try to refresh
+                if user_obj.space_refresh_token:
+                    try:
+                        new_token = await self._refresh_and_save_token(user_obj)
+                        return new_token
+                    except Exception:
+                        return None
+                return None
+
+        return user_obj.space_access_token
+
+    async def _refresh_and_save_token(self, user_obj: user.User) -> str:
+        """Refresh token and save to database"""
+        token_data = await self.refresh_token(user_obj.space_refresh_token)
+        access_token = token_data.get('access_token')
+        expires_in = token_data.get('expires_in', 0)
+
+        if not access_token:
+            raise ValueError('Failed to refresh token')
+
+        expires_at = datetime.datetime.now() + datetime.timedelta(seconds=expires_in) if expires_in > 0 else None
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User)
+            .where(user.User.user == user_obj.user)
+            .values(
+                space_access_token=access_token,
+                space_access_token_expires_at=expires_at,
+            )
+        )
+
+        return access_token
+
+    # === Raw API calls (no token validation) ===
+
+    def get_oauth_authorize_url(self, redirect_uri: str, state: str = '') -> str:
+        """Get the Space OAuth authorization URL for redirect"""
+        space_config = self._get_space_config()
+        authorize_url = space_config['oauth_authorize_url']
+        params = f'redirect_uri={redirect_uri}'
+        if state:
+            params += f'&state={state}'
+        return f'{authorize_url}?{params}'
+
+    async def exchange_oauth_code(self, code: str) -> typing.Dict:
+        """Exchange OAuth authorization code for tokens"""
+        from langbot.pkg.utils import constants
+
+        space_config = self._get_space_config()
+        space_url = space_config['url']
+
+        session = httpclient.get_session()
+        async with session.post(
+            f'{space_url}/api/v1/accounts/oauth/token',
+            json={'code': code, 'instance_id': constants.instance_id},
+        ) as response:
+            if response.status != 200:
+                raise ValueError(f'Failed to exchange OAuth code: {await response.text()}')
+            data = await response.json()
+            if data.get('code') != 0:
+                raise ValueError(f'Failed to exchange OAuth code: {data.get("msg")}')
+            return data.get('data', {})
+
+    async def refresh_token(self, refresh_token: str) -> typing.Dict:
+        """Refresh Space access token"""
+        space_config = self._get_space_config()
+        space_url = space_config['url']
+
+        session = httpclient.get_session()
+        async with session.post(
+            f'{space_url}/api/v1/accounts/token/refresh', json={'refresh_token': refresh_token}
+        ) as response:
+            if response.status != 200:
+                raise ValueError(f'Failed to refresh token: {await response.text()}')
+            data = await response.json()
+            if data.get('code') != 0:
+                raise ValueError(f'Failed to refresh token: {data.get("msg")}')
+            return data.get('data', {})
+
+    async def get_user_info_raw(self, access_token: str) -> typing.Dict:
+        """Get user info from Space using access token (no validation)"""
+        space_config = self._get_space_config()
+        space_url = space_config['url']
+
+        session = httpclient.get_session()
+        async with session.get(
+            f'{space_url}/api/v1/accounts/me', headers={'Authorization': f'Bearer {access_token}'}
+        ) as response:
+            if response.status != 200:
+                raise ValueError(f'Failed to get user info: {await response.text()}')
+            data = await response.json()
+            if data.get('code') != 0:
+                raise ValueError(f'Failed to get user info: {data.get("msg")}')
+            return data.get('data', {})
+
+    # === API calls with token validation ===
+
+    async def get_user_info(self, user_email: str) -> typing.Dict | None:
+        """Get user info from Space (with token validation)"""
+        access_token = await self._ensure_valid_token(user_email)
+        if not access_token:
+            return None
+        return await self.get_user_info_raw(access_token)
+
+    async def get_credits(self, user_email: str, force_refresh: bool = False) -> int | None:
+        """Get Space credits for user with caching (60s TTL)"""
+        cache_ttl = 60
+
+        if not force_refresh and user_email in self._credits_cache:
+            credits, ts = self._credits_cache[user_email]
+            if time.time() - ts < cache_ttl:
+                return credits
+
+        try:
+            info = await self.get_user_info(user_email)
+            if info is None:
+                return None
+            credits = info.get('credits')
+            if credits is not None:
+                self._credits_cache[user_email] = (credits, time.time())
+            return credits
+        except Exception:
+            return self._credits_cache.get(user_email, (None, 0))[0]
+
+    async def get_models(self) -> typing.List[SpaceModel]:
+        """Get models from Space"""
+
+        space_config = self._get_space_config()
+        space_url = space_config['url']
+
+        session = httpclient.get_session()
+        async with session.get(f'{space_url}/api/v1/models') as response:
+            if response.status != 200:
+                raise ValueError(f'Failed to get models: {await response.text()}')
+            data = await response.json()
+            if data.get('code') != 0:
+                raise ValueError(f'Failed to get models: {data.get("msg")}')
+            models_data = data.get('data', {}).get('models', [])
+            return [SpaceModel.model_validate(model_dict) for model_dict in models_data]

src/langbot/pkg/api/http/service/user.py

@@ -4,17 +4,22 @@ import sqlalchemy
 import argon2
 import jwt
 import datetime
+import typing
+import asyncio
 
 from ....core import app
 from ....entity.persistence import user
 from ....utils import constants
+from ....entity.errors import account as account_errors
 
 
 class UserService:
     ap: app.Application
+    _create_user_lock: asyncio.Lock
 
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
+        self._create_user_lock = asyncio.Lock()
 
     async def is_initialized(self) -> bool:
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(user.User).limit(1))
@@ -28,7 +33,7 @@ class UserService:
         hashed_password = ph.hash(password)
 
         await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.insert(user.User).values(user=user_email, password=hashed_password)
+            sqlalchemy.insert(user.User).values(user=user_email, password=hashed_password, account_type='local')
         )
 
     async def get_user_by_email(self, user_email: str) -> user.User | None:
@@ -39,6 +44,15 @@ class UserService:
         result_list = result.all()
         return result_list[0] if result_list is not None and len(result_list) > 0 else None
 
+    async def get_user_by_space_account_uuid(self, space_account_uuid: str) -> user.User | None:
+        """Get user by Space account UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(user.User).where(user.User.space_account_uuid == space_account_uuid)
+        )
+
+        result_list = result.all()
+        return result_list[0] if result_list is not None and len(result_list) > 0 else None
+
     async def authenticate(self, user_email: str, password: str) -> str | None:
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(user.User).where(user.User.user == user_email)
@@ -51,6 +65,10 @@ class UserService:
 
         user_obj = result_list[0]
 
+        # Check if this is a Space account
+        if user_obj.account_type == 'space':
+            raise ValueError('请使用 Space 账户登录')
+
         ph = argon2.PasswordHasher()
 
         ph.verify(user_obj.password, password)
@@ -90,6 +108,10 @@ class UserService:
         if user_obj is None:
             raise ValueError('User not found')
 
+        # Space accounts cannot change password locally
+        if user_obj.account_type == 'space':
+            raise ValueError('Space account cannot change password locally')
+
         ph.verify(user_obj.password, current_password)
 
         hashed_password = ph.hash(new_password)
@@ -97,3 +119,183 @@ class UserService:
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
         )
+
+    # Space user management
+
+    async def create_or_update_space_user(
+        self,
+        space_account_uuid: str,
+        email: str,
+        access_token: str,
+        refresh_token: str,
+        api_key: str,
+        expires_in: int = 0,
+    ) -> user.User:
+        """Create or update a Space user account (only if system not initialized or user exists)"""
+        expires_at = datetime.datetime.now() + datetime.timedelta(seconds=expires_in) if expires_in > 0 else None
+
+        async with self._create_user_lock:
+            # Check if user with this Space UUID already exists
+            existing_user = await self.get_user_by_space_account_uuid(space_account_uuid)
+
+            if existing_user:
+                # Update existing user's tokens
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.update(user.User)
+                    .where(user.User.space_account_uuid == space_account_uuid)
+                    .values(
+                        space_access_token=access_token,
+                        space_refresh_token=refresh_token,
+                        space_api_key=api_key,
+                        space_access_token_expires_at=expires_at,
+                    )
+                )
+                await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+                return await self.get_user_by_space_account_uuid(space_account_uuid)
+
+            # Check if user with same email exists
+            existing_email_user = await self.get_user_by_email(email)
+            if existing_email_user:
+                # Update existing user to link with Space account
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.update(user.User)
+                    .where(user.User.user == email)
+                    .values(
+                        account_type='space',
+                        space_account_uuid=space_account_uuid,
+                        space_access_token=access_token,
+                        space_refresh_token=refresh_token,
+                        space_api_key=api_key,
+                        space_access_token_expires_at=expires_at,
+                    )
+                )
+                await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+                return await self.get_user_by_email(email)
+
+            # Check if system is already initialized
+            is_initialized = await self.is_initialized()
+            if is_initialized:
+                raise account_errors.AccountEmailMismatchError()
+
+            # Create new Space user (first time initialization)
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.insert(user.User).values(
+                    user=email,
+                    password='',  # Space users don't have local password
+                    account_type='space',
+                    space_account_uuid=space_account_uuid,
+                    space_access_token=access_token,
+                    space_refresh_token=refresh_token,
+                    space_api_key=api_key,
+                    space_access_token_expires_at=expires_at,
+                )
+            )
+            await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+
+            return await self.get_user_by_space_account_uuid(space_account_uuid)
+
+    async def authenticate_space_user(
+        self, access_token: str, refresh_token: str, expires_in: int = 0
+    ) -> typing.Tuple[str, user.User]:
+        """Authenticate with Space and return JWT token"""
+        # Get user info from Space using raw API (token just obtained, no need to validate)
+        user_info = await self.ap.space_service.get_user_info_raw(access_token)
+
+        account = user_info.get('account', {})
+        api_key = user_info.get('api_key', '')
+
+        space_account_uuid = account.get('uuid')
+        email = account.get('email')
+
+        if not space_account_uuid or not email:
+            raise ValueError('Invalid Space user info')
+
+        # Create or update Space user in local database
+        user_obj = await self.create_or_update_space_user(
+            space_account_uuid=space_account_uuid,
+            email=email,
+            access_token=access_token,
+            refresh_token=refresh_token,
+            api_key=api_key,
+            expires_in=expires_in,
+        )
+
+        # Generate JWT token
+        jwt_token = await self.generate_jwt_token(email)
+
+        return jwt_token, user_obj
+
+    async def get_first_user(self) -> user.User | None:
+        """Get the first user (for single-user mode)"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(user.User).limit(1))
+        result_list = result.all()
+        return result_list[0] if result_list else None
+
+    async def set_password(self, user_email: str, new_password: str, current_password: str | None = None) -> None:
+        """Set or change password for a user"""
+        ph = argon2.PasswordHasher()
+        user_obj = await self.get_user_by_email(user_email)
+
+        if user_obj is None:
+            raise ValueError('User not found')
+
+        # If user already has a password, verify current password
+        has_password = bool(user_obj.password and user_obj.password.strip())
+        if has_password:
+            if not current_password:
+                raise ValueError('Current password is required')
+            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)
+        )
+
+    async def bind_space_account(self, user_email: str, code: str) -> user.User:
+        """Bind Space account to existing local account"""
+        # Exchange code for tokens
+        token_data = await self.ap.space_service.exchange_oauth_code(code)
+        access_token = token_data.get('access_token')
+        refresh_token = token_data.get('refresh_token')
+        expires_in = token_data.get('expires_in', 0)
+
+        if not access_token:
+            raise ValueError('Failed to get access token from Space')
+
+        expires_at = datetime.datetime.now() + datetime.timedelta(seconds=expires_in) if expires_in > 0 else None
+
+        # Get Space user info (token just obtained, use raw API)
+        user_info = await self.ap.space_service.get_user_info_raw(access_token)
+        account = user_info.get('account', {})
+        api_key = user_info.get('api_key', '')
+
+        space_account_uuid = account.get('uuid')
+        space_email = account.get('email')
+
+        if not space_account_uuid or not space_email:
+            raise ValueError('Invalid Space user info')
+
+        # Check if this Space account is already bound to another user
+        existing_space_user = await self.get_user_by_space_account_uuid(space_account_uuid)
+        if existing_space_user and existing_space_user.user != user_email:
+            raise ValueError('This Space account is already bound to another user')
+
+        # Update local account to Space account
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User)
+            .where(user.User.user == user_email)
+            .values(
+                user=space_email,  # Update email to Space email
+                account_type='space',
+                space_account_uuid=space_account_uuid,
+                space_access_token=access_token,
+                space_refresh_token=refresh_token,
+                space_api_key=api_key,
+                space_access_token_expires_at=expires_at,
+            )
+        )
+
+        # Update Space model provider API keys
+        await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+
+        return await self.get_user_by_email(space_email)

src/langbot/pkg/core/app.py

@@ -9,30 +9,39 @@ from ..platform import botmgr as im_mgr
 from ..platform.webhook_pusher import WebhookPusher
 from ..provider.session import sessionmgr as llm_session_mgr
 from ..provider.modelmgr import modelmgr as llm_model_mgr
+
 from langbot.pkg.provider.tools import toolmgr as llm_tool_mgr
 from ..config import manager as config_mgr
 from ..command import cmdmgr
 from ..plugin import connector as plugin_connector
 from ..pipeline import pool
 from ..pipeline import controller, pipelinemgr
+from ..pipeline import aggregator as message_aggregator
 from ..utils import version as version_mgr, proxy as proxy_mgr
 from ..persistence import mgr as persistencemgr
 from ..api.http.controller import main as http_controller
 from ..api.http.service import user as user_service
+from ..api.http.service import space as space_service
 from ..api.http.service import model as model_service
+from ..api.http.service import provider as provider_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 ..api.http.service import mcp as mcp_service
 from ..api.http.service import apikey as apikey_service
 from ..api.http.service import webhook as webhook_service
+from ..api.http.service import monitoring as monitoring_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 ..rag.service import RAGRuntimeService
 from ..vector import mgr as vectordb_mgr
+from ..telemetry import telemetry as telemetry_module
+from ..survey import manager as survey_module
 
 
 class Application:
@@ -56,6 +65,7 @@ class Application:
     model_mgr: llm_model_mgr.ModelManager = None
 
     rag_mgr: rag_mgr.RAGManager = None
+    rag_runtime_service: RAGRuntimeService = None
 
     # TODO move to pipeline
     tool_mgr: llm_tool_mgr.ToolManager = None
@@ -74,6 +84,8 @@ class Application:
 
     instance_config: config_mgr.ConfigManager = None
 
+    instance_id: config_mgr.ConfigManager = None  # used to identify the instance
+
     # ======= Metadata config manager =======
 
     sensitive_meta: config_mgr.ConfigManager = None
@@ -89,6 +101,8 @@ class Application:
 
     query_pool: pool.QueryPool = None
 
+    msg_aggregator: message_aggregator.MessageAggregator = None
+
     ctrl: controller.Controller = None
 
     pipeline_mgr: pipelinemgr.PipelineManager = None
@@ -113,10 +127,14 @@ class Application:
 
     user_service: user_service.UserService = None
 
+    space_service: space_service.SpaceService = None
+
     llm_model_service: model_service.LLMModelsService = None
 
     embedding_models_service: model_service.EmbeddingModelsService = None
 
+    provider_service: provider_service.ModelProviderService = None
+
     pipeline_service: pipeline_service.PipelineService = None
 
     bot_service: bot_service.BotService = None
@@ -129,6 +147,12 @@ class Application:
 
     webhook_service: webhook_service.WebhookService = None
 
+    telemetry: telemetry_module.TelemetryManager = None
+
+    survey: survey_module.SurveyManager = None
+
+    monitoring_service: monitoring_service.MonitoringService = None
+
     def __init__(self):
         pass
 
@@ -164,6 +188,34 @@ class Application:
                 scopes=[core_entities.LifecycleControlScope.APPLICATION],
             )
 
+            # Start monitoring data cleanup task if enabled
+            monitoring_cfg = self.instance_config.data.get('monitoring', {})
+            auto_cleanup_cfg = monitoring_cfg.get('auto_cleanup', {})
+            if auto_cleanup_cfg.get('enabled', True):
+                retention_days = auto_cleanup_cfg.get('retention_days', 30)
+                check_interval_hours = auto_cleanup_cfg.get('check_interval_hours', 1)
+
+                async def monitoring_cleanup_loop():
+                    check_interval_seconds = check_interval_hours * 3600
+                    while True:
+                        try:
+                            deleted = await self.monitoring_service.cleanup_expired_records(retention_days)
+                            total_deleted = sum(deleted.values())
+                            if total_deleted > 0:
+                                self.logger.info(
+                                    f'Monitoring auto-cleanup: deleted {total_deleted} expired records '
+                                    f'(retention={retention_days}d): {deleted}'
+                                )
+                        except Exception as e:
+                            self.logger.warning(f'Monitoring auto-cleanup error: {e}')
+                        await asyncio.sleep(check_interval_seconds)
+
+                self.task_mgr.create_task(
+                    monitoring_cleanup_loop(),
+                    name='monitoring-cleanup',
+                    scopes=[core_entities.LifecycleControlScope.APPLICATION],
+                )
+
             self.task_mgr.create_task(
                 never_ending(),
                 name='never-ending-task',

src/langbot/pkg/core/bootutils/deps.py

@@ -1,3 +1,4 @@
+import importlib.util
 import pip
 import os
 from ...utils import pkgmgr
@@ -49,9 +50,10 @@ async def check_deps() -> list[str]:
 
     missing_deps = []
     for dep in required_deps:
-        try:
-            __import__(dep)
-        except ImportError:
+        # Use find_spec instead of __import__ to avoid actually loading
+        # all modules into memory. find_spec only checks if the module
+        # can be found, without executing module-level code.
+        if importlib.util.find_spec(dep) is None:
             missing_deps.append(dep)
     return missing_deps
 

src/langbot/pkg/core/bootutils/log.py

@@ -1,4 +1,5 @@
 import logging
+import logging.handlers
 import sys
 import time
 
@@ -15,6 +16,10 @@ log_colors_config = {
     'CRITICAL': 'cyan',
 }
 
+# Log rotation configuration to prevent unbounded log file growth
+LOG_FILE_MAX_BYTES = 10 * 1024 * 1024  # 10MB per file
+LOG_FILE_BACKUP_COUNT = 5  # Keep 5 backup files (total ~50MB max)
+
 
 async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.Logger:
     # Remove all existing loggers
@@ -43,9 +48,17 @@ async def init_logging(extra_handlers: list[logging.Handler] = None) -> logging.
     # stream_handler.setFormatter(color_formatter)
     stream_handler.stream = open(sys.stdout.fileno(), mode='w', encoding='utf-8', buffering=1)
 
+    # Use RotatingFileHandler to prevent unbounded log file growth
+    rotating_file_handler = logging.handlers.RotatingFileHandler(
+        log_file_name,
+        encoding='utf-8',
+        maxBytes=LOG_FILE_MAX_BYTES,
+        backupCount=LOG_FILE_BACKUP_COUNT,
+    )
+
     log_handlers: list[logging.Handler] = [
         stream_handler,
-        logging.FileHandler(log_file_name, encoding='utf-8'),
+        rotating_file_handler,
     ]
     log_handlers += extra_handlers if extra_handlers is not None else []
 

src/langbot/pkg/core/migrations/m041_dingtalk_card_autolayout_config.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class('dingtalk_card_auto_layout', 41)
+class DingTalkCardAutoLayoutMigration(migration.Migration):
+    """迁移"""
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移"""
+        return True
+
+    async def run(self):
+        """执行迁移"""
+        self.ap.platform_cfg.data['platform-adapters']['app']['dingtalk']['card_auto_layout'] = False
+        await self.ap.platform_cfg.dump_config()

src/langbot/pkg/core/stages/build_app.py

@@ -5,29 +5,36 @@ import asyncio
 from .. import stage, app
 from ...utils import version, proxy
 from ...pipeline import pool, controller, pipelinemgr
+from ...pipeline import aggregator as message_aggregator
 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 ...rag.service import RAGRuntimeService
 from ...platform import botmgr as im_mgr
 from ...platform.webhook_pusher import WebhookPusher
 from ...persistence import mgr as persistencemgr
 from ...api.http.controller import main as http_controller
 from ...api.http.service import user as user_service
+from ...api.http.service import space as space_service
 from ...api.http.service import model as model_service
+from ...api.http.service import provider as provider_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 ...api.http.service import mcp as mcp_service
 from ...api.http.service import apikey as apikey_service
 from ...api.http.service import webhook as webhook_service
+from ...api.http.service import monitoring as monitoring_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
+from ...telemetry import telemetry as telemetry_module
+from ...survey import manager as survey_module
 
 
 @stage.stage_class('BuildAppStage')
@@ -42,6 +49,39 @@ class BuildAppStage(stage.BootingStage):
         discover.discover_blueprint('templates/components.yaml')
         ap.discover = discover
 
+        user_service_inst = user_service.UserService(ap)
+        ap.user_service = user_service_inst
+
+        space_service_inst = space_service.SpaceService(ap)
+        ap.space_service = space_service_inst
+
+        llm_model_service_inst = model_service.LLMModelsService(ap)
+        ap.llm_model_service = llm_model_service_inst
+
+        embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
+        ap.embedding_models_service = embedding_models_service_inst
+
+        provider_service_inst = provider_service.ModelProviderService(ap)
+        ap.provider_service = provider_service_inst
+
+        pipeline_service_inst = pipeline_service.PipelineService(ap)
+        ap.pipeline_service = pipeline_service_inst
+
+        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
+
+        mcp_service_inst = mcp_service.MCPService(ap)
+        ap.mcp_service = mcp_service_inst
+
+        apikey_service_inst = apikey_service.ApiKeyService(ap)
+        ap.apikey_service = apikey_service_inst
+
+        webhook_service_inst = webhook_service.WebhookService(ap)
+        ap.webhook_service = webhook_service_inst
+
         proxy_mgr = proxy.ProxyManager(ap)
         await proxy_mgr.initialize()
         ap.proxy_mgr = proxy_mgr
@@ -63,21 +103,23 @@ class BuildAppStage(stage.BootingStage):
         ap.persistence_mgr = persistence_mgr_inst
         await persistence_mgr_inst.initialize()
 
-        async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
-            await asyncio.sleep(3)
-            await plugin_connector_inst.initialize()
+        # Telemetry manager: attach to app so other components can call via self.ap.telemetry
+        telemetry_inst = telemetry_module.TelemetryManager(ap)
+        await telemetry_inst.initialize()
+        ap.telemetry = telemetry_inst
 
-        plugin_connector_inst = plugin_connector.PluginRuntimeConnector(ap, runtime_disconnect_callback)
-        await plugin_connector_inst.initialize()
-        ap.plugin_connector = plugin_connector_inst
+        # Survey manager
+        survey_inst = survey_module.SurveyManager(ap)
+        await survey_inst.initialize()
+        ap.survey = survey_inst
 
         cmd_mgr_inst = cmdmgr.CommandManager(ap)
         await cmd_mgr_inst.initialize()
         ap.cmd_mgr = cmd_mgr_inst
 
         llm_model_mgr_inst = llm_model_mgr.ModelManager(ap)
-        await llm_model_mgr_inst.initialize()
         ap.model_mgr = llm_model_mgr_inst
+        await llm_model_mgr_inst.initialize()
 
         llm_session_mgr_inst = llm_session_mgr.SessionManager(ap)
         await llm_session_mgr_inst.initialize()
@@ -99,10 +141,17 @@ class BuildAppStage(stage.BootingStage):
         await pipeline_mgr.initialize()
         ap.pipeline_mgr = pipeline_mgr
 
+        # Initialize message aggregator (after pipeline_mgr, as it needs pipeline config)
+        msg_aggregator_inst = message_aggregator.MessageAggregator(ap)
+        ap.msg_aggregator = msg_aggregator_inst
+
         rag_mgr_inst = rag_mgr.RAGManager(ap)
         await rag_mgr_inst.initialize()
         ap.rag_mgr = rag_mgr_inst
 
+        # Initialize RAG Runtime Service for plugins
+        ap.rag_runtime_service = RAGRuntimeService(ap)
+
         # 初始化向量数据库管理器
         vectordb_mgr_inst = vectordb_mgr.VectorDBManager(ap)
         await vectordb_mgr_inst.initialize()
@@ -112,32 +161,16 @@ class BuildAppStage(stage.BootingStage):
         await http_ctrl.initialize()
         ap.http_ctrl = http_ctrl
 
-        user_service_inst = user_service.UserService(ap)
-        ap.user_service = user_service_inst
+        monitoring_service_inst = monitoring_service.MonitoringService(ap)
+        ap.monitoring_service = monitoring_service_inst
 
-        llm_model_service_inst = model_service.LLMModelsService(ap)
-        ap.llm_model_service = llm_model_service_inst
+        async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
+            await asyncio.sleep(3)
+            await plugin_connector_inst.initialize()
 
-        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
-
-        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
-
-        mcp_service_inst = mcp_service.MCPService(ap)
-        ap.mcp_service = mcp_service_inst
-
-        apikey_service_inst = apikey_service.ApiKeyService(ap)
-        ap.apikey_service = apikey_service_inst
-
-        webhook_service_inst = webhook_service.WebhookService(ap)
-        ap.webhook_service = webhook_service_inst
+        plugin_connector_inst = plugin_connector.PluginRuntimeConnector(ap, runtime_disconnect_callback)
+        await plugin_connector_inst.initialize()
+        ap.plugin_connector = plugin_connector_inst
 
         ctrl = controller.Controller(ap)
         ap.ctrl = ctrl

src/langbot/pkg/core/stages/load_config.py

@@ -2,8 +2,11 @@ from __future__ import annotations
 
 import os
 from typing import Any
+from langbot.pkg.utils import constants
 import yaml
 import importlib.resources as resources
+import uuid
+import time
 
 from .. import stage, app
 from ..bootutils import config
@@ -71,20 +74,26 @@ def _apply_env_overrides_to_config(cfg: dict) -> dict:
         current = cfg
 
         for i, key in enumerate(keys):
-            if not isinstance(current, dict) or key not in current:
+            if not isinstance(current, dict):
                 break
 
             if i == len(keys) - 1:
-                # At the final key - check if it's a scalar value
-                if isinstance(current[key], (dict, list)):
-                    # Skip dict and list types
-                    pass
+                # At the final key
+                if key in current:
+                    if isinstance(current[key], (dict, list)):
+                        # Skip dict and list types
+                        pass
+                    else:
+                        # Valid scalar value - convert and set it
+                        converted_value = convert_value(env_value, current[key])
+                        current[key] = converted_value
                 else:
-                    # Valid scalar value - convert and set it
-                    converted_value = convert_value(env_value, current[key])
-                    current[key] = converted_value
+                    # Key doesn't exist yet - create it as string
+                    current[key] = env_value
             else:
-                # Navigate deeper
+                # Navigate deeper - create intermediate dict if needed
+                if key not in current:
+                    current[key] = {}
                 current = current[key]
 
     return cfg
@@ -142,6 +151,58 @@ class LoadConfigStage(stage.BootingStage):
 
         await ap.instance_config.dump_config()
 
+        # load or generate instance id
+        # Priority:
+        # 1. system.instance_id from config.yaml (can be set via SYSTEM__INSTANCE_ID env var)
+        # 2. data/labels/instance_id.json (if file exists)
+        # 3. Generate new and save to file
+        config_instance_id = ap.instance_config.data.get('system', {}).get('instance_id', '')
+
+        if config_instance_id:
+            # Use the instance_id from config.yaml
+            constants.instance_id = config_instance_id
+            # Still load/create the file for backward compat, but don't use its value
+            ap.instance_id = await config.load_json_config(
+                'data/labels/instance_id.json',
+                template_data={
+                    'instance_id': f'instance_{str(uuid.uuid4())}',
+                    'instance_create_ts': int(time.time()),
+                },
+                completion=False,
+            )
+        else:
+            # Try loading file-based instance id
+            instance_id_path = os.path.join('data', 'labels', 'instance_id.json')
+            if os.path.exists(instance_id_path):
+                # File exists, read it
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': '',
+                        'instance_create_ts': 0,
+                    },
+                    completion=False,
+                )
+                constants.instance_id = ap.instance_id.data['instance_id']
+            else:
+                # Neither config nor file, generate new and save to file
+                new_id = f'instance_{str(uuid.uuid4())}'
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': new_id,
+                        'instance_create_ts': int(time.time()),
+                    },
+                    completion=False,
+                )
+                constants.instance_id = new_id
+        constants.edition = ap.instance_config.data.get('system', {}).get('edition', 'community')
+
+        print(f'LangBot instance id: {constants.instance_id}')
+        print(f'LangBot edition: {constants.edition}')
+
+        await ap.instance_id.dump_config()
+
         ap.sensitive_meta = await config.load_json_config(
             'data/metadata/sensitive-words.json',
             'metadata/sensitive-words.json',

src/langbot/pkg/entity/dto/space_model.py

@@ -0,0 +1,49 @@
+# [
+#   {
+#     "uuid": "7652ebdb-54dc-412c-a830-e9268ac88471",
+#     "model_id": "claude-opus-4-5-20251101",
+#     "display_name": {
+#       "en_US": "claude-opus-4-5-20251101",
+#       "zh_Hans": "claude-opus-4-5-20251101"
+#     },
+#     "description": {},
+#     "provider": "anthropic",
+#     "category": "chat",
+#     "icon_url": "Claude.Color",
+#     "tags": {},
+#     "is_featured": true,
+#     "featured_order": 999,
+#     "model_ratio": 2.5,
+#     "completion_ratio": 5,
+#     "quota_type": 0,
+#     "model_price": 0,
+#     "input_credits": 500,
+#     "output_credits": 2500,
+#     "vendor_id": 1,
+#     "vendor_name": "Anthropic",
+#     "vendor_icon": "Claude.Color",
+#     "supported_endpoints": [
+#       "anthropic",
+#       "openai"
+#     ],
+#     "status": "active",
+#     "metadata": null,
+#     "created_at": "2025-12-30T22:23:38.337207+08:00",
+#     "updated_at": "2025-12-30T22:23:38.337207+08:00"
+#   }
+# ]
+
+import pydantic
+
+
+class SpaceModel(pydantic.BaseModel):
+    uuid: str
+    model_id: str
+    provider: str
+    category: str  # chat / embedding
+    llm_abilities: list[str] | None = None
+    is_featured: bool = False
+    featured_order: int = 0
+    status: str
+    created_at: str | None = None
+    updated_at: str | None = None

src/langbot/pkg/entity/errors/account.py

@@ -0,0 +1,6 @@
+from __future__ import annotations
+
+
+class AccountEmailMismatchError(Exception):
+    def __str__(self):
+        return 'Account email mismatch'

src/langbot/pkg/entity/errors/provider.py

@@ -7,3 +7,11 @@ class RequesterNotFoundError(Exception):
 
     def __str__(self):
         return f'Requester {self.requester_name} not found'
+
+
+class ProviderNotFoundError(Exception):
+    def __init__(self, provider_name: str):
+        self.provider_name = provider_name
+
+    def __str__(self):
+        return f'Provider {self.provider_name} not found'

src/langbot/pkg/entity/persistence/mcp.py

@@ -9,7 +9,7 @@ class MCPServer(Base):
     uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
     name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
     enable = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
-    mode = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)  # stdio, sse
+    mode = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)  # stdio, sse, http
     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(

src/langbot/pkg/entity/persistence/model.py

@@ -3,6 +3,25 @@ import sqlalchemy
 from .base import Base
 
 
+class ModelProvider(Base):
+    """Model provider"""
+
+    __tablename__ = 'model_providers'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    requester = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    base_url = sqlalchemy.Column(sqlalchemy.String(512), nullable=False)
+    api_keys = 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(),
+    )
+
+
 class LLMModel(Base):
     """LLM model"""
 
@@ -10,12 +29,10 @@ class LLMModel(Base):
 
     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)
+    provider_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
     abilities = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=[])
     extra_args = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    prefered_ranking = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,
@@ -26,17 +43,15 @@ class LLMModel(Base):
 
 
 class EmbeddingModel(Base):
-    """Embedding 模型"""
+    """Embedding model"""
 
     __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)
+    provider_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
     extra_args = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    prefered_ranking = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,

src/langbot/pkg/entity/persistence/monitoring.py

@@ -0,0 +1,108 @@
+import sqlalchemy
+
+from .base import Base
+
+
+class MonitoringMessage(Base):
+    """Monitoring message records"""
+
+    __tablename__ = 'monitoring_messages'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    message_content = sqlalchemy.Column(sqlalchemy.Text, nullable=False)
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    status = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # success, error, pending
+    level = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # info, warning, error, debug
+    platform = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    user_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    user_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)  # User display name
+    runner_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)  # Runner name for this query
+    variables = sqlalchemy.Column(sqlalchemy.Text, nullable=True)  # Query variables as JSON string
+    role = sqlalchemy.Column(sqlalchemy.String(50), nullable=True, default='user')  # user, assistant
+
+
+class MonitoringLLMCall(Base):
+    """LLM call records"""
+
+    __tablename__ = 'monitoring_llm_calls'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    model_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    input_tokens = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    output_tokens = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    total_tokens = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    duration = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)  # milliseconds
+    cost = sqlalchemy.Column(sqlalchemy.Float, nullable=True)
+    status = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # success, error
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    error_message = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)  # Associated message ID
+
+
+class MonitoringSession(Base):
+    """Session tracking records"""
+
+    __tablename__ = 'monitoring_sessions'
+
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    message_count = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
+    start_time = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    last_activity = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    is_active = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True, index=True)
+    platform = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    user_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    user_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)  # User display name
+
+
+class MonitoringError(Base):
+    """Error log records"""
+
+    __tablename__ = 'monitoring_errors'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    error_type = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    error_message = sqlalchemy.Column(sqlalchemy.Text, nullable=False)
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    stack_trace = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)  # Associated message ID
+
+
+class MonitoringEmbeddingCall(Base):
+    """Embedding call records"""
+
+    __tablename__ = 'monitoring_embedding_calls'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    model_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    prompt_tokens = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    total_tokens = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)
+    duration = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)  # milliseconds
+    input_count = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)  # Number of input texts
+    status = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # success, error
+    error_message = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    # Optional context fields
+    knowledge_base_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    query_text = sqlalchemy.Column(sqlalchemy.Text, nullable=True)  # For retrieval calls
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    call_type = sqlalchemy.Column(sqlalchemy.String(50), nullable=True)  # embedding, retrieve

src/langbot/pkg/entity/persistence/pipeline.py

@@ -11,6 +11,7 @@ class LegacyPipeline(Base):
     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)
+    emoji = sqlalchemy.Column(sqlalchemy.String(10), nullable=True, default='⚙️')
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,
@@ -22,7 +23,11 @@ class LegacyPipeline(Base):
     is_default = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
     stages = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
     config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
-    extensions_preferences = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
+    extensions_preferences = sqlalchemy.Column(
+        sqlalchemy.JSON,
+        nullable=False,
+        default={'enable_all_plugins': True, 'enable_all_mcp_servers': True, 'plugins': [], 'mcp_servers': []},
+    )
 
 
 class PipelineRunRecord(Base):

src/langbot/pkg/entity/persistence/rag.py

@@ -1,29 +1,30 @@
 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)
+    emoji = sqlalchemy.Column(sqlalchemy.String(10), nullable=True, default='📚')
     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)
+    updated_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now(), onupdate=sqlalchemy.func.now())
+    # New fields for plugin-based RAG
+    knowledge_engine_plugin_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
+    collection_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
+    creation_settings = sqlalchemy.Column(sqlalchemy.JSON, nullable=True, default=None)
+    retrieval_settings = sqlalchemy.Column(sqlalchemy.JSON, nullable=True, default=None)
+
+    # Field sets for different operations
+    MUTABLE_FIELDS = {'name', 'description', 'retrieval_settings'}
+    """Fields that can be updated after creation."""
+
+    CREATE_FIELDS = MUTABLE_FIELDS | {'uuid', 'knowledge_engine_plugin_id', 'collection_id', 'creation_settings'}
+    """Fields used when creating a new knowledge base."""
+
+    ALL_DB_FIELDS = CREATE_FIELDS | {'emoji', 'created_at', 'updated_at'}
+    """All fields stored in database (for loading from DB row)."""
 
 
 class File(Base):
@@ -41,10 +42,3 @@ class Chunk(Base):
     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)

src/langbot/pkg/entity/persistence/user.py

@@ -9,6 +9,17 @@ class User(Base):
     id = sqlalchemy.Column(sqlalchemy.Integer, primary_key=True)
     user = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
     password = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+
+    # Account type: 'local' (default) or 'space'
+    account_type = sqlalchemy.Column(sqlalchemy.String(32), nullable=False, server_default='local')
+
+    # Space account fields (nullable, only used when account_type='space')
+    space_account_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    space_access_token = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    space_refresh_token = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    space_access_token_expires_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=True)
+    space_api_key = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,

src/langbot/pkg/entity/rag/retriever.py

@@ -1,13 +0,0 @@
-from __future__ import annotations
-
-import pydantic
-
-from typing import Any
-
-
-class RetrieveResultEntry(pydantic.BaseModel):
-    id: str
-
-    metadata: dict[str, Any]
-
-    distance: float

src/langbot/pkg/persistence/mgr.py

@@ -2,18 +2,16 @@ from __future__ import annotations
 
 import datetime
 import typing
-import json
-import uuid
+
 
 import sqlalchemy.ext.asyncio as sqlalchemy_asyncio
 import sqlalchemy
 
 from . import database, migration
-from ..entity.persistence import base, pipeline, metadata
+from ..entity.persistence import base, metadata, model as persistence_model
 from ..entity import persistence
 from ..core import app
 from ..utils import constants, importutil
-from ..api.http.service import pipeline as pipeline_service
 from . import databases, migrations
 
 importutil.import_modules_in_pkg(databases)
@@ -78,7 +76,7 @@ class PersistenceManager:
 
             self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
 
-        await self.write_default_pipeline()
+        await self.write_space_model_providers()
 
     async def create_tables(self):
         # create tables
@@ -100,30 +98,42 @@ class PersistenceManager:
             if row is None:
                 await self.execute_async(sqlalchemy.insert(metadata.Metadata).values(item))
 
-    async def write_default_pipeline(self):
-        # write default pipeline
-        result = await self.execute_async(sqlalchemy.select(pipeline.LegacyPipeline))
-        default_pipeline_uuid = None
-        if result.first() is None:
-            self.ap.logger.info('Creating default pipeline...')
+    async def write_space_model_providers(self):
+        space_models_gateway_api_url = self.ap.instance_config.data.get('space', {}).get(
+            'models_gateway_api_url', 'https://api.langbot.cloud/v1'
+        )
 
-            pipeline_config = json.loads(importutil.read_resource_file('templates/default-pipeline-config.json'))
+        # write space model providers
+        result = await self.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.requester == 'space-chat-completions'
+            )
+        )
+        exists_space_chat_completions_model_provider = result.first()
 
-            default_pipeline_uuid = str(uuid.uuid4())
-            pipeline_data = {
-                'uuid': default_pipeline_uuid,
-                'for_version': self.ap.ver_mgr.get_current_version(),
-                'stages': pipeline_service.default_stage_order,
-                'is_default': True,
-                'name': 'ChatPipeline',
-                '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,
-                'extensions_preferences': {},
+        # api keys will be set/updated when the oauth callback
+        if exists_space_chat_completions_model_provider is None:
+            self.ap.logger.info('Creating space model providers...')
+            space_chat_completions_model_provider = {
+                'uuid': '00000000-0000-0000-0000-000000000000',
+                'name': 'LangBot Models',
+                'requester': 'space-chat-completions',
+                'base_url': space_models_gateway_api_url,
+                'api_keys': [],
             }
 
-            await self.execute_async(sqlalchemy.insert(pipeline.LegacyPipeline).values(pipeline_data))
+            await self.execute_async(
+                sqlalchemy.insert(persistence_model.ModelProvider).values(space_chat_completions_model_provider)
+            )
+        else:
+            if exists_space_chat_completions_model_provider.base_url != space_models_gateway_api_url:
+                await self.execute_async(
+                    sqlalchemy.update(persistence_model.ModelProvider)
+                    .where(persistence_model.ModelProvider.uuid == exists_space_chat_completions_model_provider.uuid)
+                    .values({'base_url': space_models_gateway_api_url})
+                )
 
-        # =================================
+    # =================================
 
     async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
         async with self.get_db_engine().connect() as conn:

src/langbot/pkg/persistence/migrations/dbm002_combine_quote_msg_config.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(2)
@@ -11,30 +10,45 @@ class DBMigrateCombineQuoteMsgConfig(migration.DBMigration):
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure 'trigger' exists
+            if 'trigger' not in config:
+                config['trigger'] = {}
+
+            # Ensure 'misc' exists in 'trigger'
             if 'misc' not in config['trigger']:
                 config['trigger']['misc'] = {}
 
+            # Add 'combine-quote-message' if not exists
             if 'combine-quote-message' not in config['trigger']['misc']:
                 config['trigger']['misc']['combine-quote-message'] = 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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/persistence/migrations/dbm003_n8n_config.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(3)
@@ -11,14 +10,23 @@ class DBMigrateN8nConfig(migration.DBMigration):
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure 'ai' exists
+            if 'ai' not in config:
+                config['ai'] = {}
+
+            # Add 'n8n-service-api' if not exists
             if 'n8n-service-api' not in config['ai']:
                 config['ai']['n8n-service-api'] = {
                     'webhook-url': 'http://your-n8n-webhook-url',
@@ -33,16 +41,21 @@ class DBMigrateN8nConfig(migration.DBMigration):
                     'output-key': 'response',
                 }
 
-            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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/persistence/migrations/dbm004_rag_kb_uuid.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(4)
@@ -11,27 +10,43 @@ class DBMigrateRAGKBUUID(migration.DBMigration):
 
     async def upgrade(self):
         """升级"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure nested structure exists
+            if 'ai' not in config:
+                config['ai'] = {}
+            if 'local-agent' not in config['ai']:
+                config['ai']['local-agent'] = {}
+
+            # Add 'knowledge-base' if not exists
             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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """降级"""

src/langbot/pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(5)
@@ -11,27 +10,43 @@ class DBMigratePipelineRemoveCotConfig(migration.DBMigration):
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure nested structure exists
+            if 'output' not in config:
+                config['output'] = {}
+            if 'misc' not in config['output']:
+                config['output']['misc'] = {}
+
+            # Add 'remove-think' if not exists
             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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/persistence/migrations/dbm006_langflow_api_config.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(6)
@@ -11,14 +10,23 @@ class DBMigrateLangflowApiConfig(migration.DBMigration):
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure 'ai' exists
+            if 'ai' not in config:
+                config['ai'] = {}
+
+            # Add 'langflow-api' if not exists
             if 'langflow-api' not in config['ai']:
                 config['ai']['langflow-api'] = {
                     'base-url': 'http://localhost:7860',
@@ -29,16 +37,21 @@ class DBMigrateLangflowApiConfig(migration.DBMigration):
                     'tweaks': '{}',
                 }
 
-            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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/persistence/migrations/dbm010_pipeline_multi_knowledge_base.py

@@ -1,8 +1,7 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(10)
@@ -11,16 +10,20 @@ class DBMigratePipelineMultiKnowledgeBase(migration.DBMigration):
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
             # Convert knowledge-base from string to array
-            if 'local-agent' in config['ai']:
+            if 'ai' in config and 'local-agent' in config['ai']:
                 current_kb = config['ai']['local-agent'].get('knowledge-base', '')
 
                 # If it's already a list, skip
@@ -37,29 +40,38 @@ class DBMigratePipelineMultiKnowledgeBase(migration.DBMigration):
                 if 'knowledge-base' in config['ai']['local-agent']:
                     del 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(),
-                    }
-                )
-            )
+                # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+                if self.ap.persistence_mgr.db.name == 'postgresql':
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(
+                            'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                        ),
+                        {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(
+                            'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                        ),
+                        {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                    )
 
     async def downgrade(self):
         """Downgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
             # Convert knowledge-bases from array back to string
-            if 'local-agent' in config['ai']:
+            if 'ai' in config and 'local-agent' in config['ai']:
                 current_kbs = config['ai']['local-agent'].get('knowledge-bases', [])
 
                 # If it's already a string, skip
@@ -76,13 +88,18 @@ class DBMigratePipelineMultiKnowledgeBase(migration.DBMigration):
                 if 'knowledge-bases' in config['ai']['local-agent']:
                     del config['ai']['local-agent']['knowledge-bases']
 
-            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(),
-                    }
-                )
-            )
+                # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+                if self.ap.persistence_mgr.db.name == 'postgresql':
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(
+                            'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                        ),
+                        {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(
+                            'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                        ),
+                        {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                    )

src/langbot/pkg/persistence/migrations/dbm011_dify_base_prompt_config.py

@@ -1,39 +1,54 @@
 from .. import migration
 
 import sqlalchemy
-
-from ...entity.persistence import pipeline as persistence_pipeline
+import json
 
 
 @migration.migration_class(11)
 class DBMigrateDifyApiConfig(migration.DBMigration):
-    """Langflow API config"""
+    """Dify base prompt config"""
 
     async def upgrade(self):
         """Upgrade"""
-        # read all pipelines
-        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
 
-        for pipeline in pipelines:
-            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+        current_version = self.ap.ver_mgr.get_current_version()
 
-            config = serialized_pipeline['config']
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
 
+            # Ensure nested structure exists
+            if 'ai' not in config:
+                config['ai'] = {}
+            if 'dify-service-api' not in config['ai']:
+                config['ai']['dify-service-api'] = {}
+
+            # Add 'base-prompt' if not exists
             if 'base-prompt' not in config['ai']['dify-service-api']:
                 config['ai']['dify-service-api']['base-prompt'] = (
                     'When the file content is readable, please read the content of this file. When the file is an image, describe the content of this image.',
                 )
 
-            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(),
-                    }
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
                 )
-            )
 
     async def downgrade(self):
         """Downgrade"""

src/langbot/pkg/persistence/migrations/dbm012_pipeline_extensions_enable_all.py

@@ -0,0 +1,73 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(12)
+class DBMigratePipelineExtensionsEnableAll(migration.DBMigration):
+    """Pipeline extensions enable all"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # Read all pipelines using raw SQL
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, extensions_preferences FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            extensions_preferences = (
+                json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
+            )
+
+            # Ensure extensions_preferences is a dict
+            if extensions_preferences is None:
+                extensions_preferences = {}
+
+            # Add 'enable_all_plugins' if not exists
+            if 'enable_all_plugins' not in extensions_preferences:
+                if 'plugins' in extensions_preferences:
+                    extensions_preferences['enable_all_plugins'] = False
+                else:
+                    extensions_preferences['enable_all_plugins'] = True
+                    extensions_preferences['plugins'] = []
+
+            # Add 'enable_all_mcp_servers' if not exists
+            if 'enable_all_mcp_servers' not in extensions_preferences:
+                if 'mcp_servers' in extensions_preferences:
+                    extensions_preferences['enable_all_mcp_servers'] = False
+                else:
+                    extensions_preferences['enable_all_mcp_servers'] = True
+                    extensions_preferences['mcp_servers'] = []
+
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET extensions_preferences = :extensions_preferences::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {
+                        'extensions_preferences': json.dumps(extensions_preferences),
+                        'for_version': current_version,
+                        'uuid': uuid,
+                    },
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET extensions_preferences = :extensions_preferences, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {
+                        'extensions_preferences': json.dumps(extensions_preferences),
+                        'for_version': current_version,
+                        'uuid': uuid,
+                    },
+                )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm013_knowledge_base_updated_at.py

@@ -0,0 +1,49 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(13)
+class DBMigrateKnowledgeBaseUpdatedAt(migration.DBMigration):
+    """Add updated_at field to knowledge_bases table"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # Get all column names from the table
+        columns = []
+
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    "SELECT column_name FROM information_schema.columns WHERE table_name = 'knowledge_bases';"
+                )
+            )
+            all_result = result.fetchall()
+            columns = [row[0] for row in all_result]
+        else:
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text('PRAGMA table_info(knowledge_bases);'))
+            all_result = result.fetchall()
+            columns = [row[1] for row in all_result]
+
+        # Check and add updated_at column
+        if 'updated_at' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'ALTER TABLE knowledge_bases ADD COLUMN updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP'
+                    )
+                )
+            else:
+                # SQLite doesn't support DEFAULT CURRENT_TIMESTAMP in ALTER TABLE
+                # Add column without default first
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE knowledge_bases ADD COLUMN updated_at DATETIME')
+                )
+
+            # Set initial updated_at values to created_at for existing records
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('UPDATE knowledge_bases SET updated_at = created_at WHERE updated_at IS NULL')
+            )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass