Add OSS and commercial workspace boundaries

* fix model runtime uuid after updates

* test: avoid local agent constructor coupling

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,5 +1,5 @@
 name: 漏洞反馈
-description: 【供中文用户】报错或漏洞请使用这个模板创建，不使用此模板创建的异常、漏洞相关issue将被直接关闭。由于自己操作不当/不甚了解所用技术栈引起的网络连接问题恕无法解决，请勿提 issue。容器间网络连接问题，参考文档 https://docs.langbot.app/zh/workshop/network-details.html  
+description: 【供中文用户】报错或漏洞请使用这个模板创建，不使用此模板创建的异常、漏洞相关issue将被直接关闭。由于自己操作不当/不甚了解所用技术栈引起的网络连接问题恕无法解决，请勿提 issue。容器间网络连接问题，参考文档 https://link.langbot.app/zh/docs/network  
 title: "[Bug]: "
 labels: ["bug?"]
 body:
@@ -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

@@ -1,5 +1,5 @@
 name: Bug report
-description: Report bugs or vulnerabilities using this template. For container network connection issues, refer to the documentation https://docs.langbot.app/en/workshop/network-details.html
+description: Report bugs or vulnerabilities using this template. For container network connection issues, refer to the documentation https://link.langbot.app/en/docs/network
 title: "[Bug]: "
 labels: ["bug?"]
 body:
@@ -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-release-artifacts.yaml

@@ -43,10 +43,10 @@ jobs:
         run: |
           cd /tmp/langbot_build_web/web
           npm install
-          npm run build
+          npx vite build
       - name: Package Output
         run: |
-          cp -r /tmp/langbot_build_web/web/out ./web
+          cp -r /tmp/langbot_build_web/web/dist ./web
       - name: Upload Artifact
         uses: actions/upload-artifact@v4
         with:

.github/workflows/check-i18n.yml

@@ -0,0 +1,25 @@
+name: Check i18n Keys
+
+on:
+  push:
+    branches:
+      - main
+      - master
+
+jobs:
+  check-i18n:
+    name: Check i18n Key Consistency
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Check i18n keys against en-US reference
+        run: node web/scripts/check-i18n.mjs

.github/workflows/publish-to-pypi.yml

@@ -29,8 +29,8 @@ jobs:
           npm install -g pnpm
           pnpm install
           pnpm build
-          mkdir -p ../src/langbot/web/out
-          cp -r out ../src/langbot/web/
+          mkdir -p ../src/langbot/web/dist
+          cp -r dist ../src/langbot/web/
 
       - name: Install the latest version of uv
         uses: astral-sh/setup-uv@v6

.github/workflows/test-migrations.yml

@@ -0,0 +1,171 @@
+name: Test Migrations
+
+on:
+  push:
+    branches:
+      - main
+      - master
+      - dev
+    paths:
+      - 'src/langbot/pkg/persistence/**'
+      - 'src/langbot/pkg/entity/persistence/**'
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review]
+    paths:
+      - 'src/langbot/pkg/persistence/**'
+      - 'src/langbot/pkg/entity/persistence/**'
+
+jobs:
+  test-migrations-sqlite:
+    name: Migrations (SQLite)
+    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: Test Alembic upgrade (SQLite)
+        run: |
+          uv run python -c "
+          import asyncio
+          from sqlalchemy.ext.asyncio import create_async_engine
+          from langbot.pkg.entity.persistence.base import Base
+          from langbot.pkg.persistence.alembic_runner import run_alembic_upgrade, run_alembic_stamp, get_alembic_current
+
+          async def main():
+              engine = create_async_engine('sqlite+aiosqlite:///test_migrations.db')
+
+              # Create all tables (simulates existing DB)
+              async with engine.begin() as conn:
+                  await conn.run_sync(Base.metadata.create_all)
+
+              # Stamp baseline
+              await run_alembic_stamp(engine, '0001_baseline')
+              rev = await get_alembic_current(engine)
+              assert rev == '0001_baseline', f'Expected 0001_baseline, got {rev}'
+              print(f'Stamped: {rev}')
+
+              # Upgrade to head
+              await run_alembic_upgrade(engine, 'head')
+              rev = await get_alembic_current(engine)
+              print(f'After upgrade: {rev}')
+              assert rev is not None, 'Expected a revision after upgrade'
+
+              # Verify idempotent
+              await run_alembic_upgrade(engine, 'head')
+              rev2 = await get_alembic_current(engine)
+              assert rev2 == rev, f'Expected {rev}, got {rev2}'
+              print(f'Idempotent check passed: {rev2}')
+
+              # Fresh DB: upgrade from scratch
+              engine2 = create_async_engine('sqlite+aiosqlite:///test_migrations_fresh.db')
+              async with engine2.begin() as conn:
+                  await conn.run_sync(Base.metadata.create_all)
+              await run_alembic_upgrade(engine2, 'head')
+              rev3 = await get_alembic_current(engine2)
+              print(f'Fresh DB upgrade: {rev3}')
+              assert rev3 is not None
+
+              print('All SQLite migration tests passed!')
+
+          asyncio.run(main())
+          "
+
+  test-migrations-postgres:
+    name: Migrations (PostgreSQL)
+    runs-on: ubuntu-latest
+    services:
+      postgres:
+        image: postgres:16
+        env:
+          POSTGRES_USER: langbot
+          POSTGRES_PASSWORD: langbot
+          POSTGRES_DB: langbot_test
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd="pg_isready -U langbot"
+          --health-interval=5s
+          --health-timeout=5s
+          --health-retries=5
+
+    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: Test Alembic upgrade (PostgreSQL)
+        run: |
+          uv run python -c "
+          import asyncio
+          from sqlalchemy.ext.asyncio import create_async_engine
+          from langbot.pkg.entity.persistence.base import Base
+          from langbot.pkg.persistence.alembic_runner import run_alembic_upgrade, run_alembic_stamp, get_alembic_current
+
+          DB_URL = 'postgresql+asyncpg://langbot:langbot@localhost:5432/langbot_test'
+
+          async def main():
+              engine = create_async_engine(DB_URL)
+
+              # Create all tables
+              async with engine.begin() as conn:
+                  await conn.run_sync(Base.metadata.create_all)
+
+              # Stamp baseline
+              await run_alembic_stamp(engine, '0001_baseline')
+              rev = await get_alembic_current(engine)
+              assert rev == '0001_baseline', f'Expected 0001_baseline, got {rev}'
+              print(f'Stamped: {rev}')
+
+              # Upgrade to head
+              await run_alembic_upgrade(engine, 'head')
+              rev = await get_alembic_current(engine)
+              print(f'After upgrade: {rev}')
+              assert rev is not None
+
+              # Verify idempotent
+              await run_alembic_upgrade(engine, 'head')
+              rev2 = await get_alembic_current(engine)
+              assert rev2 == rev, f'Expected {rev}, got {rev2}'
+              print(f'Idempotent check passed: {rev2}')
+
+              # Fresh DB: drop all and upgrade from scratch
+              engine2 = create_async_engine(DB_URL.replace('langbot_test', 'langbot_fresh'))
+
+              # Create fresh database
+              from sqlalchemy import text
+              async with engine.connect() as conn:
+                  await conn.execute(text('COMMIT'))
+                  await conn.execute(text('CREATE DATABASE langbot_fresh'))
+
+              async with engine2.begin() as conn:
+                  await conn.run_sync(Base.metadata.create_all)
+              await run_alembic_upgrade(engine2, 'head')
+              rev3 = await get_alembic_current(engine2)
+              print(f'Fresh DB upgrade: {rev3}')
+              assert rev3 is not None
+
+              print('All PostgreSQL migration tests passed!')
+
+          asyncio.run(main())
+          "

.gitignore

@@ -47,8 +47,12 @@ plugins.bak
 coverage.xml
 .coverage
 src/langbot/web/
+testsdk/
 
 # Build artifacts
 /dist
 /build
 *.egg-info
+
+# Next.js build cache (legacy)
+web/.next/

.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

@@ -70,7 +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.
+- LangBot uses [Alembic](https://alembic.sqlalchemy.org/) to manage database migrations, supporting both SQLite and PostgreSQL. Migration files are located in `src/langbot/pkg/persistence/alembic/versions/`. If you changed the definition of database entities (ORM models), generate a new migration script by running `uv run python -m langbot.pkg.persistence.alembic_runner autogenerate "description of your change"` in the project root (requires `data/config.yaml` to exist). Review and edit the generated script before committing. Migrations are executed automatically on LangBot startup. For data migrations (e.g. modifying JSON field content), you need to manually add the migration code in the generated script.
 
 ## Some Principles
 

Dockerfile

@@ -4,7 +4,7 @@ WORKDIR /app
 
 COPY web ./web
 
-RUN cd web && npm install && npm run build
+RUN cd web && npm install && npx vite build
 
 FROM python:3.12.7-slim
 
@@ -12,7 +12,7 @@ WORKDIR /app
 
 COPY . .
 
-COPY --from=node /app/web/out ./web/out
+COPY --from=node /app/web/dist ./web/dist
 
 RUN apt update \
     && apt install gcc -y \

README.md

@@ -1,49 +1,69 @@
-
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.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>
 
-<h3>使用 LangBot 快速构建、调试、部署即时通信机器人。</h3>
+<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](README_EN.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)
+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%A4-1030838208-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">
-[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
+[![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">项目主页</a> ｜
-<a href="https://docs.langbot.app/zh/insight/features.html">规格特性</a> ｜
-<a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a> ｜
-<a href="https://docs.langbot.app/zh/tags/readme.html">API 集成</a> ｜
-<a href="https://space.langbot.app">插件市场</a> ｜
-<a href="https://langbot.featurebase.app/roadmap">路线图</a>
+<a href="https://langbot.app">Website</a> ｜
+<a href="https://link.langbot.app/en/docs/features">Features</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">Docs</a> ｜
+<a href="https://link.langbot.app/en/docs/api">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>
 
+---
 
-## 📦 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://link.langbot.app/en/docs/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
@@ -51,127 +71,106 @@ 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://link.langbot.app/en/docs/docker) · [Manual](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [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。
+| Platform | Status | Notes |
+|----------|--------|-------|
+| Discord | ✅ | Official |
+| Telegram | ✅ | Official |
+| Slack | ✅ | Official |
+| LINE | ✅ | Official |
+| QQ | ✅ | Personal & Official API (Channel, DM, Group) |
+| WeCom | ✅ | Enterprise WeChat, External CS, AI Bot |
+| WeChat | ✅ | Personal & Official Account |
+| Lark | ✅ | Official |
+| DingTalk | ✅ | Official |
+| KOOK | ✅ | Official |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Supports multiple bridged platforms such as Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip, and more |
 
-## 😎 保持更新
+---
 
-点击仓库右上角 Star 和 Watch 按钮，获取最新动态。
+## Supported LLMs & Integrations
 
-![star gif](https://docs.langbot.app/star.gif)
+| 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      | ✅     |
+| [Qiniu](https://www.qiniu.com/ai/agent)                                                                           | Gateway      | ✅     |
 
-## ✨ 特性
+[→ View all integrations](https://link.langbot.app/en/docs/features)
 
-<img width="500" src="https://docs.langbot.app/ui/bot-page-zh-rounded.png" />
+---
 
+## Why LangBot?
 
-- 💬 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)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)等 LLMOps 平台。
-- 🤖 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、KOOK、Slack、LINE 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。
-- 🧩 插件扩展、活跃社区：高稳定性、高安全性的生产级插件系统，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：提供先进的 WebUI 管理面板，用最直观的方式配置、管理、监控机器人。
-- 📊 生产级特性：支持多流水线配置，不同机器人用于不同应用场景。具有全面的监控和异常处理能力。已被多家企业采用。
+| 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                                     |
 
-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。
+## Live Demo
 
-### 消息平台
+**Try it now:** https://demo.langbot.dev/
 
-| 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 | ✅ |  |
-| KOOK | ✅ |  |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
+- Email: `demo@langbot.app`
+- Password: `langbot123456`
 
-### 大模型能力
+_Note: Public demo environment. Do not enter sensitive information._
 
-| 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 |
+---
 
-### TTS
+## Community
 
-| 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) |
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
 
-### 文生图
+- [Discord Community](https://discord.gg/wdNEHETs87)
 
-| 平台/模型 | 备注 |
-| --- | --- |
-| 阿里云百炼 | [插件](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
+---
 
-## 😘 社区贡献
+## Star History
 
-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：
+[![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 +1,199 @@
+<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://link.langbot.app/zh/docs/features">特性</a> ｜
+<a href="https://link.langbot.app/zh/docs/guide">文档</a> ｜
+<a href="https://link.langbot.app/zh/docs/api">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://link.langbot.app/zh/docs/features)
+
+---
+
+## 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://link.langbot.app/zh/docs/docker) · [手动部署](https://link.langbot.app/zh/docs/manual-deploy) · [宝塔面板](https://link.langbot.app/zh/docs/bt-panel) · [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 | ✅ | 官方 |
+| 钉钉 | ✅ | 官方 |
+| Satori | ✅ |  |
+| Discord | ✅ | 官方 |
+| Telegram | ✅ | 官方 |
+| Slack | ✅ | 官方 |
+| LINE | ✅ | 官方 |
+| KOOK | ✅ | 官方 |
+| Email | ✅ | 只 Matrix、Satori |
+| Matrix | ✅ | 支持多种桥接平台，如 Signal、WhatsApp、Messenger、iMessage、Mattermost、Google Chat、IRC、XMPP、Zulip 等 |
+
+---
+
+## 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 | ✅ |
+| [七牛云Qiniu](https://www.qiniu.com/ai/agent) | 聚合平台 | ✅ |
+
+[→ 查看完整集成列表](https://link.langbot.app/zh/docs/features)
+
+### 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

@@ -1,151 +0,0 @@
-<p align="center">
-<a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.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>Quickly build, debug, and ship IM bots with LangBot.</h3>
-
-English / [简体中文](README.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)
-[![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/features.html">Features</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Deployment</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API Integration</a> ｜
-<a href="https://space.langbot.app">Plugin Market</a> ｜
-<a href="https://langbot.featurebase.app/roadmap">Roadmap</a>
-
-</div>
-
-</p>
-
-
-## 📦 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
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 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), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) etc. LLMOps platforms.
-- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE, etc.
-- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods.
-- 🧩 Plugin Extension, Active Community: High stability, high security production-level plugin system; 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.
-- 📊 Production-grade Features: Supports multiple pipeline configurations, different bots can be used for different scenarios. Has comprehensive monitoring and exception handling capabilities.
-
-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 | ✅ |  |
-| KOOK | ✅ |  |
-
-### 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

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>Cree, depure y despliegue bots de mensajería instantánea rápidamente con LangBot.</h3>
+<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_EN.md) / [简体中文](README.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)
+[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">Despliegue</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">Integración API</a> ｜
+<a href="https://link.langbot.app/en/docs/features">Características</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">Documentación</a> ｜
+<a href="https://link.langbot.app/en/docs/api">API</a> ｜
 <a href="https://space.langbot.app">Mercado de Plugins</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Hoja de Ruta</a>
 
@@ -27,20 +29,40 @@
 
 </p>
 
+---
 
-## 📦 Comenzar
+## ¿Qué es LangBot?
 
-#### Inicio Rápido
+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.
 
-Use `uvx` para iniciar con un comando (necesita instalar [uv](https://docs.astral.sh/uv/getting-started/installation/)):
+### 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://link.langbot.app/en/docs/features)
+
+---
+
+## Inicio Rápido
+
+### ☁️ LangBot Cloud (Recomendado)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Sin despliegue, listo para usar.
+
+### Lanzamiento en una línea
 
 ```bash
 uvx langbot
 ```
 
-Visite http://localhost:5300 para comenzar a usarlo.
+> Requiere [uv](https://docs.astral.sh/uv/getting-started/installation/). Visite http://localhost:5300 — listo.
 
-#### Despliegue con Docker Compose
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -48,103 +70,104 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-Visite http://localhost:5300 para comenzar a usarlo.
-
-Documentación detallada [Despliegue con Docker](https://docs.langbot.app/en/deploy/langbot/docker.html).
-
-#### Despliegue con un clic en BTPanel
-
-LangBot ha sido listado en BTPanel. Si tiene BTPanel instalado, puede usar la [documentación](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) para usarlo.
-
-#### Despliegue en la Nube Zeabur
-
-Plantilla de Zeabur contribuida por la comunidad.
+### Despliegue en la Nube con un Clic
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Despliegue en la Nube Railway
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### Otros Métodos de Despliegue
+**Más opciones:** [Docker](https://link.langbot.app/en/docs/docker) · [Manual](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](./docker/README_K8S.md)
 
-Use directamente la versión publicada para ejecutar, consulte la documentación de [Despliegue Manual](https://docs.langbot.app/en/deploy/langbot/manual.html).
+---
 
-#### Despliegue en Kubernetes
+## Plataformas Soportadas
 
-Consulte la documentación de [Despliegue en Kubernetes](./docker/README_K8S.md).
+| Plataforma | Estado | Notas |
+|----------|--------|-------|
+| Discord | ✅ | Oficial |
+| Telegram | ✅ | Oficial |
+| Slack | ✅ | Oficial |
+| LINE | ✅ | Oficial |
+| QQ | ✅ | Personal y API Oficial (Canal, DM, Grupo) |
+| WeCom | ✅ | WeChat Empresarial, CS Externo, AI Bot |
+| WeChat | ✅ | Personal y Cuenta Oficial |
+| Lark | ✅ | Oficial |
+| DingTalk | ✅ | Oficial |
+| KOOK | ✅ | Oficial |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Admite varias plataformas puenteadas como Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip y más |
 
-## 😎 Manténgase Actualizado
+---
 
-Haga clic en los botones Star y Watch en la esquina superior derecha del repositorio para obtener las últimas actualizaciones.
+## LLMs e Integraciones Soportadas
 
-![star gif](https://docs.langbot.app/star.gif)
+| 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | Pasarela | ✅ |
 
-## ✨ Características
+[→ Ver todas las integraciones](https://link.langbot.app/en/docs/features)
 
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
+---
 
+## ¿Por qué LangBot?
 
-- 💬 Chat con LLM / Agent: Compatible con múltiples LLMs, adaptado para chats grupales y privados; Admite conversaciones de múltiples rondas, llamadas a herramientas, capacidades multimodales y de salida en streaming. Implementación RAG (base de conocimientos) incorporada, e integración profunda con [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) etc. LLMOps platforms.
-- 🤖 Soporte Multiplataforma: Actualmente compatible con QQ, QQ Channel, WeCom, WeChat personal, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE, etc.
-- 🛠️ Alta Estabilidad, Rico en Funciones: Control de acceso nativo, limitación de velocidad, filtrado de palabras sensibles, etc.; Fácil de usar, admite múltiples métodos de despliegue.
-- 🧩 Extensión de Plugin, Comunidad Activa: Sistema de plugin de alta estabilidad, alta seguridad de nivel de producción; Compatible con mecanismos de plugin impulsados por eventos, extensión de componentes, etc.; Integración del protocolo [MCP](https://modelcontextprotocol.io/) de Anthropic; Actualmente cuenta con cientos de plugins.
-- 😻 Interfaz Web: Admite la gestión de instancias de LangBot a través del navegador. No es necesario escribir archivos de configuración manualmente.
-- 📊 Características de Nivel de Producción: Compatible con múltiples configuraciones de pipeline, diferentes bots para diferentes escenarios. Cuenta con capacidades completas de monitoreo y manejo de excepciones.
+| 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 |
 
-Para especificaciones más detalladas, consulte la [documentación](https://docs.langbot.app/en/insight/features.html).
+---
 
-O visite el entorno de demostración: https://demo.langbot.dev/
-  - Información de inicio de sesión: Correo electrónico: `demo@langbot.app` Contraseña: `langbot123456`
-  - Nota: Solo para demostración de WebUI, por favor no ingrese información confidencial en el entorno público.
+## Demo en Vivo
 
-### Plataformas de Mensajería
+**Pruébelo ahora:** https://demo.langbot.dev/
+- Correo electrónico: `demo@langbot.app`
+- Contraseña: `langbot123456`
 
-| Plataforma | Estado | Observaciones |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| QQ Personal | ✅ |  |
-| QQ API Oficial | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| WeChat Personal | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
-| KOOK | ✅ |  |
+*Nota: Entorno de demostración público. No ingrese información confidencial.*
 
-### LLMs
+---
 
-| LLM | Estado | Observaciones |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | Disponible para cualquier modelo con formato de interfaz OpenAI |
-| [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) | ✅ | Plataforma de recursos LLM y GPU |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | Plataforma de recursos LLM y GPU |
-| [接口 AI](https://jiekou.ai/) | ✅ | Plataforma de agregación LLM |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | Plataforma de recursos LLM y GPU |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | Gateway LLM (MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | Plataforma LLMOps |
-| [Ollama](https://ollama.com/) | ✅ | Plataforma de ejecución de LLM local |
-| [LMStudio](https://lmstudio.ai/) | ✅ | Plataforma de ejecución de LLM local |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | Gateway de interfaz LLM (MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | Gateway LLM (MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | Gateway LLM (MaaS), plataforma LLMOps |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | Gateway LLM (MaaS), plataforma LLMOps |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | Gateway LLM (MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | Compatible con acceso a herramientas a través del protocolo MCP |
+## Comunidad
 
-## 🤝 Contribución de la Comunidad
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
 
-Gracias a los siguientes [contribuidores de código](https://github.com/langbot-app/LangBot/graphs/contributors) y otros miembros de la comunidad por sus contribuciones a LangBot:
+- [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" />

README_FR.md

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>Créez, déboguez et déployez rapidement des bots de messagerie instantanée avec LangBot.</h3>
+<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_EN.md) / [简体中文](README.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)
+[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">Déploiement</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">Intégration API</a> ｜
+<a href="https://link.langbot.app/en/docs/features">Fonctionnalités</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">Documentation</a> ｜
+<a href="https://link.langbot.app/en/docs/api">API</a> ｜
 <a href="https://space.langbot.app">Marché des Plugins</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Feuille de Route</a>
 
@@ -27,19 +29,40 @@
 
 </p>
 
-## 📦 Commencer
+---
 
-#### Démarrage Rapide
+## Qu'est-ce que LangBot ?
 
-Utilisez `uvx` pour démarrer avec une commande (besoin d'installer [uv](https://docs.astral.sh/uv/getting-started/installation/)) :
+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://link.langbot.app/en/docs/features)
+
+---
+
+## Démarrage Rapide
+
+### ☁️ LangBot Cloud (Recommandé)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Sans déploiement, prêt à utiliser.
+
+### Lancement en une ligne
 
 ```bash
 uvx langbot
 ```
 
-Visitez http://localhost:5300 pour commencer à l'utiliser.
+> Nécessite [uv](https://docs.astral.sh/uv/getting-started/installation/). Visitez http://localhost:5300 — c'est prêt.
 
-#### Déploiement avec Docker Compose
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -47,103 +70,104 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-Visitez http://localhost:5300 pour commencer à l'utiliser.
-
-Documentation détaillée [Déploiement Docker](https://docs.langbot.app/en/deploy/langbot/docker.html).
-
-#### Déploiement en un clic sur BTPanel
-
-LangBot a été répertorié sur BTPanel. Si vous avez installé BTPanel, vous pouvez utiliser la [documentation](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) pour l'utiliser.
-
-#### Déploiement Cloud Zeabur
-
-Modèle Zeabur contribué par la communauté.
+### Déploiement Cloud en un Clic
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Déploiement Cloud Railway
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### Autres Méthodes de Déploiement
+**Plus d'options :** [Docker](https://link.langbot.app/en/docs/docker) · [Manuel](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](./docker/README_K8S.md)
 
-Utilisez directement la version publiée pour exécuter, consultez la documentation de [Déploiement Manuel](https://docs.langbot.app/en/deploy/langbot/manual.html).
+---
 
-#### Déploiement Kubernetes
+## Plateformes Supportées
 
-Consultez la documentation de [Déploiement Kubernetes](./docker/README_K8S.md).
+| Plateforme | Statut | Notes |
+|----------|--------|-------|
+| Discord | ✅ | Officiel |
+| Telegram | ✅ | Officiel |
+| Slack | ✅ | Officiel |
+| LINE | ✅ | Officiel |
+| QQ | ✅ | Personnel & API Officielle (Canal, DM, Groupe) |
+| WeCom | ✅ | WeChat Entreprise, CS Externe, AI Bot |
+| WeChat | ✅ | Personnel & Compte Officiel |
+| Lark | ✅ | Officiel |
+| DingTalk | ✅ | Officiel |
+| KOOK | ✅ | Officiel |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Prend en charge plusieurs plateformes via ponts, comme Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip, etc. |
 
-## 😎 Restez à Jour
+---
 
-Cliquez sur les boutons Star et Watch dans le coin supérieur droit du dépôt pour obtenir les dernières mises à jour.
+## LLMs et Intégrations Supportés
 
-![star gif](https://docs.langbot.app/star.gif)
+| 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | Passerelle | ✅ |
 
-## ✨ Fonctionnalités
+[→ Voir toutes les intégrations](https://link.langbot.app/en/docs/features)
 
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
+---
 
+## Pourquoi LangBot ?
 
-- 💬 Chat avec LLM / Agent : Prend en charge plusieurs LLM, adapté aux chats de groupe et privés ; Prend en charge les conversations multi-tours, les appels d'outils, les capacités multimodales et de sortie en streaming. Implémentation RAG (base de connaissances) intégrée, et intégration profonde avec [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) etc. LLMOps platforms.
-- 🤖 Support Multi-plateforme : Actuellement compatible avec QQ, QQ Channel, WeCom, WeChat personnel, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE, etc.
-- 🛠️ Haute Stabilité, Riche en Fonctionnalités : Contrôle d'accès natif, limitation de débit, filtrage de mots sensibles, etc. ; Facile à utiliser, prend en charge plusieurs méthodes de déploiement.
-- 🧩 Extension de Plugin, Communauté Active : Système de plugin de haute stabilité, haute sécurité de niveau production; Prend en charge les mécanismes de plugin pilotés par événements, l'extension de composants, etc. ; Intégration du protocole [MCP](https://modelcontextprotocol.io/) d'Anthropic ; Dispose actuellement de centaines de plugins.
-- 😻 Interface Web : Prend en charge la gestion des instances LangBot via le navigateur. Pas besoin d'écrire manuellement les fichiers de configuration.
-- 📊 Fonctionnalités de Niveau Production : Prend en charge plusieurs configurations de pipeline, différents bots pour différents scénarios. Dispose de capacités complètes de surveillance et de gestion des exceptions.
+| 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 |
 
-Pour des spécifications plus détaillées, veuillez consulter la [documentation](https://docs.langbot.app/en/insight/features.html).
+---
 
-Ou visitez l'environnement de démonstration : https://demo.langbot.dev/
-  - Informations de connexion : Email : `demo@langbot.app` Mot de passe : `langbot123456`
-  - Note : Pour la démonstration WebUI uniquement, veuillez ne pas entrer d'informations sensibles dans l'environnement public.
+## Démo en Ligne
 
-### Plateformes de Messagerie
+**Essayez maintenant :** https://demo.langbot.dev/
+- Email : `demo@langbot.app`
+- Mot de passe : `langbot123456`
 
-| Plateforme | Statut | Remarques |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| QQ Personnel | ✅ |  |
-| API Officielle QQ | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| WeChat Personnel | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
-| KOOK | ✅ |  |
+*Note : Environnement de démonstration public. Ne saisissez pas d'informations sensibles.*
 
-### LLMs
+---
 
-| LLM | Statut | Remarques |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | Disponible pour tout modèle au format d'interface OpenAI |
-| [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) | ✅ | Plateforme de ressources LLM et GPU |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | Plateforme de ressources LLM et GPU |
-| [接口 AI](https://jiekou.ai/) | ✅ | Plateforme d'agrégation LLM |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | Plateforme de ressources LLM et GPU |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | Passerelle LLM (MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | Plateforme LLMOps |
-| [Ollama](https://ollama.com/) | ✅ | Plateforme d'exécution LLM locale |
-| [LMStudio](https://lmstudio.ai/) | ✅ | Plateforme d'exécution LLM locale |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | Passerelle d'interface LLM (MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | Passerelle LLM (MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | Passerelle LLM (MaaS), plateforme LLMOps |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | Passerelle LLM (MaaS), plateforme LLMOps |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | Passerelle LLM (MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | Prend en charge l'accès aux outils via le protocole MCP |
+## Communauté
 
-## 🤝 Contribution de la Communauté
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&label=Discord)](https://discord.gg/wdNEHETs87)
 
-Merci aux [contributeurs de code](https://github.com/langbot-app/LangBot/graphs/contributors) suivants et aux autres membres de la communauté pour leurs contributions à LangBot :
+- [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" />

README_JP.md

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>LangBotでIMボットを素早く構築、デバッグ、デプロイ。</h3>
+<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_EN.md) / [简体中文](README.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)
+[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/ja/insight/features.html">機能仕様</a> ｜
-<a href="https://docs.langbot.app/ja/insight/guide.html">デプロイ</a> ｜
-<a href="https://docs.langbot.app/ja/tags/readme.html">API統合</a> ｜
+<a href="https://link.langbot.app/ja/docs/features">機能</a> ｜
+<a href="https://link.langbot.app/ja/docs/guide">ドキュメント</a> ｜
+<a href="https://link.langbot.app/ja/docs/api">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>
 
@@ -27,19 +29,40 @@
 
 </p>
 
-## 📦 始め方
+---
 
-#### クイックスタート
+## LangBot とは？
 
-`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）：
+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。
+
+### 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://link.langbot.app/ja/docs/features)
+
+---
+
+## 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
@@ -47,103 +70,104 @@ 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://link.langbot.app/en/docs/docker) · [手動デプロイ](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [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
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 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)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)などの LLMOps プラットフォームと深く統合。
-- 🤖 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、KOOK、Slack、LINE 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。
-- 🧩 プラグイン拡張、活発なコミュニティ: 高い安定性、高いセキュリティの生産レベルのプラグインシステム；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。
-- 📊 生産レベルの機能: 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。包括的な監視と例外処理機能を備えています。
-
-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 | ✅ | |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
-| KOOK | ✅ |  |
+|----------|--------|-------|
+| Discord | ✅ | 公式 |
+| Telegram | ✅ | 公式 |
+| Slack | ✅ | 公式 |
+| LINE | ✅ | 公式 |
+| QQ | ✅ | 個人・公式API（チャンネル・DM・グループ） |
+| WeCom | ✅ | 企業WeChat、外部CS、AIボット |
+| WeChat | ✅ | 個人・公式アカウント |
+| Lark | ✅ | 公式 |
+| DingTalk | ✅ | 公式 |
+| KOOK | ✅ | 公式 |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix、Satori |
+| Matrix | ✅ | Signal、WhatsApp、Messenger、iMessage、Mattermost、Google Chat、IRC、XMPP、Zulip など複数のブリッジ先プラットフォームに対応 |
 
-### 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | 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://link.langbot.app/en/docs/features)
+
+---
+
+## 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

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>LangBot으로 IM 봇을 빠르게 구축, 디버그 및 배포하세요.</h3>
+<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_EN.md) / [简体中文](README.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)
+[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 사양</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">배포</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API 통합</a> ｜
+<a href="https://link.langbot.app/en/docs/features">기능</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">문서</a> ｜
+<a href="https://link.langbot.app/en/docs/api">API</a> ｜
 <a href="https://space.langbot.app">플러그인 마켓</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">로드맵</a>
 
@@ -27,19 +29,40 @@
 
 </p>
 
-## 📦 시작하기
+---
 
-#### 빠른 시작
+## LangBot이란?
 
-`uvx`를 사용하여 한 명령으로 시작하세요 ([uv](https://docs.astral.sh/uv/getting-started/installation/) 설치 필요):
+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://link.langbot.app/en/docs/features)
+
+---
+
+## 빠른 시작
+
+### ☁️ LangBot Cloud (추천)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — 배포 없이 바로 사용.
+
+### 원라인 실행
 
 ```bash
 uvx langbot
 ```
 
-http://localhost:5300을 방문하여 사용을 시작하세요.
+> [uv](https://docs.astral.sh/uv/getting-started/installation/) 설치 필요. http://localhost:5300 방문 — 완료.
 
-#### Docker Compose 배포
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -47,103 +70,104 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-http://localhost:5300을 방문하여 사용을 시작하세요.
-
-자세한 문서는 [Docker 배포](https://docs.langbot.app/en/deploy/langbot/docker.html)를 참조하세요.
-
-#### BTPanel 원클릭 배포
-
-LangBot은 BTPanel에 등록되어 있습니다. BTPanel을 설치한 경우 [문서](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html)를 사용하여 사용할 수 있습니다.
-
-#### Zeabur 클라우드 배포
-
-커뮤니티에서 제공하는 Zeabur 템플릿입니다.
+### 원클릭 클라우드 배포
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Railway 클라우드 배포
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### 기타 배포 방법
+**더 많은 옵션:** [Docker](https://link.langbot.app/en/docs/docker) · [수동 배포](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](./docker/README_K8S.md)
 
-릴리스 버전을 직접 사용하여 실행하려면 [수동 배포](https://docs.langbot.app/en/deploy/langbot/manual.html) 문서를 참조하세요.
+---
 
-#### Kubernetes 배포
-
-[Kubernetes 배포](./docker/README_K8S.md) 문서를 참조하세요.
-
-## 😎 최신 정보 받기
-
-리포지토리 오른쪽 상단의 Star 및 Watch 버튼을 클릭하여 최신 업데이트를 받으세요.
-
-![star gif](https://docs.langbot.app/star.gif)
-
-## ✨ 기능
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 LLM / Agent와 채팅: 여러 LLM을 지원하며 그룹 채팅 및 개인 채팅에 적응; 멀티 라운드 대화, 도구 호출, 멀티모달, 스트리밍 출력 기능을 지원합니다. 내장된 RAG(지식 베이스) 구현 및 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)등의 LLMOps 플랫폼과 깊이 통합됩니다.
-- 🤖 다중 플랫폼 지원: 현재 QQ, QQ Channel, WeCom, 개인 WeChat, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE 등을 지원합니다.
-- 🛠️ 높은 안정성, 풍부한 기능: 네이티브 액세스 제어, 속도 제한, 민감한 단어 필터링 등의 메커니즘; 사용하기 쉽고 여러 배포 방법을 지원합니다.
-- 🧩 플러그인 확장, 활발한 커뮤니티: 고안정성, 고보안 생산 수준의 플러그인 시스템; 이벤트 기반, 컴포넌트 확장 등의 플러그인 메커니즘을 지원; Anthropic [MCP 프로토콜](https://modelcontextprotocol.io/) 통합; 현재 수백 개의 플러그인이 있습니다.
-- 😻 웹 UI: 브라우저를 통해 LangBot 인스턴스 관리를 지원합니다. 구성 파일을 수동으로 작성할 필요가 없습니다.
-- 📊 생산 수준의 기능: 여러 파이프라인 구성을 지원하며 다양한 시나리오에 대해 다른 봇을 사용할 수 있습니다. 포괄적인 모니터링 및 예외 처리 기능을 갖추고 있습니다.
-
-더 자세한 사양은 [문서](https://docs.langbot.app/en/insight/features.html)를 참조하세요.
-
-또는 데모 환경을 방문하세요: https://demo.langbot.dev/
-  - 로그인 정보: 이메일: `demo@langbot.app` 비밀번호: `langbot123456`
-  - 참고: WebUI 데모 전용이므로 공개 환경에서는 민감한 정보를 입력하지 마세요.
-
-### 메시징 플랫폼
+## 지원 플랫폼
 
 | 플랫폼 | 상태 | 비고 |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| 개인 QQ | ✅ |  |
-| QQ 공식 API | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| 개인 WeChat | ✅ |  |
-| KOOK | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
+|--------|------|------|
+| Discord | ✅ | 공식 |
+| Telegram | ✅ | 공식 |
+| Slack | ✅ | 공식 |
+| LINE | ✅ | 공식 |
+| QQ | ✅ | 개인 및 공식 API (채널, DM, 그룹) |
+| WeCom | ✅ | 기업 WeChat, 외부 CS, AI Bot |
+| WeChat | ✅ | 개인 및 공식 계정 |
+| Lark | ✅ | 공식 |
+| DingTalk | ✅ | 공식 |
+| KOOK | ✅ | 공식 |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip 등 여러 브리지 플랫폼 지원 |
 
-### LLMs
+---
 
-| LLM | 상태 | 비고 |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | 모든 OpenAI 인터페이스 형식 모델에 사용 가능 |
-| [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 및 GPU 리소스 플랫폼 |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM 및 GPU 리소스 플랫폼 |
-| [接口 AI](https://jiekou.ai/) | ✅ | LLM 집계 플랫폼 |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM 및 GPU 리소스 플랫폼 |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM 게이트웨이(MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | LLMOps 플랫폼 |
-| [Ollama](https://ollama.com/) | ✅ | 로컬 LLM 실행 플랫폼 |
-| [LMStudio](https://lmstudio.ai/) | ✅ | 로컬 LLM 실행 플랫폼 |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | LLM 인터페이스 게이트웨이(MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | LLM 게이트웨이(MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | LLM 게이트웨이(MaaS), LLMOps 플랫폼 |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | LLM 게이트웨이(MaaS), LLMOps 플랫폼 |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | LLM 게이트웨이(MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | MCP 프로토콜을 통한 도구 액세스 지원 |
+## 지원 LLM 및 통합
 
-## 🤝 커뮤니티 기여
+| 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | 게이트웨이 | ✅ |
 
-다음 [코드 기여자](https://github.com/langbot-app/LangBot/graphs/contributors) 및 커뮤니티의 다른 구성원들의 LangBot 기여에 감사드립니다:
+[→ 모든 통합 보기](https://link.langbot.app/en/docs/features)
+
+---
+
+## 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" />

README_RU.md

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>Быстро создавайте, отлаживайте и развертывайте IM-ботов с LangBot.</h3>
+<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_EN.md) / [简体中文](README.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)
+[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">Характеристики</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Развертывание</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">Интеграция API</a> ｜
+<a href="https://link.langbot.app/en/docs/features">Возможности</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">Документация</a> ｜
+<a href="https://link.langbot.app/en/docs/api">API</a> ｜
 <a href="https://space.langbot.app">Магазин плагинов</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Дорожная карта</a>
 
@@ -27,19 +29,40 @@
 
 </p>
 
-## 📦 Начало работы
+---
 
-#### Быстрый старт
+## Что такое LangBot?
 
-Используйте `uvx` для запуска одной командой (требуется установка [uv](https://docs.astral.sh/uv/getting-started/installation/)):
+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://link.langbot.app/en/docs/features)
+
+---
+
+## Быстрый старт
+
+### ☁️ LangBot Cloud (Рекомендуется)
+
+**[LangBot Cloud](https://space.langbot.app/cloud)** — Без развёртывания, готово к использованию.
+
+### Запуск одной командой
 
 ```bash
 uvx langbot
 ```
 
-Посетите http://localhost:5300, чтобы начать использование.
+> Требуется [uv](https://docs.astral.sh/uv/getting-started/installation/). Откройте http://localhost:5300 — готово.
 
-#### Развертывание с Docker Compose
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -47,103 +70,104 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-Посетите http://localhost:5300, чтобы начать использование.
-
-Подробная документация [Развертывание Docker](https://docs.langbot.app/en/deploy/langbot/docker.html).
-
-#### Развертывание одним кликом на BTPanel
-
-LangBot добавлен в BTPanel. Если у вас установлен BTPanel, вы можете использовать [документацию](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) для его использования.
-
-#### Облачное развертывание Zeabur
-
-Шаблон Zeabur, предоставленный сообществом.
+### Облачное развертывание одним кликом
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Облачное развертывание Railway
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### Другие методы развертывания
+**Другие варианты:** [Docker](https://link.langbot.app/en/docs/docker) · [Ручная установка](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](./docker/README_K8S.md)
 
-Используйте выпущенную версию напрямую для запуска, см. документацию [Ручное развертывание](https://docs.langbot.app/en/deploy/langbot/manual.html).
+---
 
-#### Развертывание Kubernetes
-
-См. документацию [Развертывание Kubernetes](./docker/README_K8S.md).
-
-## 😎 Оставайтесь в курсе
-
-Нажмите кнопки Star и Watch в правом верхнем углу репозитория, чтобы получать последние обновления.
-
-![star gif](https://docs.langbot.app/star.gif)
-
-## ✨ Функции
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 Чат с LLM / Agent: Поддержка нескольких LLM, адаптация к групповым и личным чатам; Поддержка многораундовых разговоров, вызовов инструментов, мультимодальных возможностей и потоковой передачи. Встроенная реализация RAG (база знаний) и глубокая интеграция с [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) и др. LLMOps платформами.
-- 🤖 Многоплатформенная поддержка: В настоящее время поддерживает QQ, QQ Channel, WeCom, личный WeChat, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE и т.д.
-- 🛠️ Высокая стабильность, богатство функций: Нативный контроль доступа, ограничение скорости, фильтрация чувствительных слов и т.д.; Простота в использовании, поддержка нескольких методов развертывания.
-- 🧩 Расширение плагинов, активное сообщество: Высокая стабильность, высокая безопасность уровня производства; Поддержка механизмов плагинов, управляемых событиями, расширения компонентов и т.д.; Интеграция протокола [MCP](https://modelcontextprotocol.io/) от Anthropic; В настоящее время сотни плагинов.
-- 😻 Веб-интерфейс: Поддержка управления экземплярами LangBot через браузер. Нет необходимости вручную писать конфигурационные файлы.
-- 📊 Функции уровня производства: Поддержка нескольких конфигураций конвейера, разные боты для разных сценариев. Имеет комплексные возможности мониторинга и обработки исключений.
-
-Для более подробных спецификаций обратитесь к [документации](https://docs.langbot.app/en/insight/features.html).
-
-Или посетите демонстрационную среду: https://demo.langbot.dev/
-  - Информация для входа: Email: `demo@langbot.app` Пароль: `langbot123456`
-  - Примечание: Только для демонстрации WebUI, пожалуйста, не вводите конфиденциальную информацию в общедоступной среде.
-
-### Платформы обмена сообщениями
+## Поддерживаемые платформы
 
 | Платформа | Статус | Примечания |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| Личный QQ | ✅ |  |
-| Официальный API QQ | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| Личный WeChat | ✅ |  |
-| KOOK | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
+|-----------|--------|------------|
+| Discord | ✅ | Официальный |
+| Telegram | ✅ | Официальный |
+| Slack | ✅ | Официальный |
+| LINE | ✅ | Официальный |
+| QQ | ✅ | Личный и официальный API (Канал, ЛС, Группа) |
+| WeCom | ✅ | Корпоративный WeChat, внешний CS, AI-бот |
+| WeChat | ✅ | Личный и официальный аккаунт |
+| Lark | ✅ | Официальный |
+| DingTalk | ✅ | Официальный |
+| KOOK | ✅ | Официальный |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Поддерживает несколько платформ через мосты, включая Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip и другие |
 
-### LLMs
+---
 
-| LLM | Статус | Примечания |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | Доступна для любой модели формата интерфейса OpenAI |
-| [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) | ✅ | Платформа ресурсов LLM и GPU |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | Платформа ресурсов LLM и GPU |
-| [接口 AI](https://jiekou.ai/) | ✅ | Платформа агрегации LLM |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | Платформа ресурсов LLM и GPU |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | Шлюз LLM (MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | Платформа LLMOps |
-| [Ollama](https://ollama.com/) | ✅ | Платформа локального запуска LLM |
-| [LMStudio](https://lmstudio.ai/) | ✅ | Платформа локального запуска LLM |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | Шлюз интерфейса LLM (MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | Шлюз LLM (MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | Шлюз LLM (MaaS), платформа LLMOps |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | Шлюз LLM (MaaS), платформа LLMOps |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | Шлюз LLM (MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | Поддержка доступа к инструментам через протокол MCP |
+## Поддерживаемые LLM и интеграции
 
-## 🤝 Вклад сообщества
+| 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | Шлюз | ✅ |
 
-Спасибо следующим [контрибьюторам кода](https://github.com/langbot-app/LangBot/graphs/contributors) и другим членам сообщества за их вклад в LangBot:
+[→ Смотреть все интеграции](https://link.langbot.app/en/docs/features)
+
+---
+
+## 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" />

README_TW.md

@@ -1,25 +1,29 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.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">
 
-<h3>使用 LangBot 快速建構、除錯和部署 IM 機器人。</h3>
+<a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
 
-[English](README_EN.md) / [简体中文](README.md) / 繁體中文 / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
+<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/features.html">規格特性</a> ｜
-<a href="https://docs.langbot.app/zh/insight/guide.html">部署文件</a> ｜
-<a href="https://docs.langbot.app/zh/tags/readme.html">API 整合</a> ｜
+<a href="https://langbot.app">官網</a> ｜
+<a href="https://link.langbot.app/zh/docs/features">特性</a> ｜
+<a href="https://link.langbot.app/zh/docs/guide">文件</a> ｜
+<a href="https://link.langbot.app/zh/docs/api">API</a> ｜
 <a href="https://space.langbot.app">外掛市場</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">路線圖</a>
 
@@ -27,19 +31,40 @@
 
 </p>
 
-## 📦 開始使用
+---
 
-#### 快速部署
+## 什麼是 LangBot？
 
-使用 `uvx` 一鍵啟動（需要先安裝 [uv](https://docs.astral.sh/uv/getting-started/installation/) ）：
+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。
+
+### 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://link.langbot.app/zh/docs/features)
+
+---
+
+## 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
@@ -47,104 +72,66 @@ 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://link.langbot.app/zh/docs/docker) · [手動部署](https://link.langbot.app/zh/docs/manual-deploy) · [寶塔面板](https://link.langbot.app/zh/docs/bt-panel) · [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
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 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)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)等 LLMOps 平台。
-- 🤖 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、KOOK、Slack、LINE 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。
-- 🧩 外掛擴展、活躍社群：高穩定性、高安全性的生產級外掛系統；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：提供先進的 WebUI 管理面板，用最直觀的方式配置、管理、監控機器人。
-- 📊 生產級特性：支援多流水線配置，不同機器人用於不同應用場景。具有全面的監控和異常處理能力。
-
-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 |
-| --- | --- | --- |
-| 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 | ✅ |  |
-| KOOK | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
+|------|------|------|
+| Discord | ✅ | 官方 |
+| Telegram | ✅ | 官方 |
+| Slack | ✅ | 官方 |
+| LINE | ✅ | 官方 |
+| QQ | ✅ | 個人號、官方機器人（頻道、私聊、群聊） |
+| 企業微信 | ✅ | 應用訊息、對外客服、智能機器人 |
+| 微信 | ✅ | 個人微信、微信公眾號 |
+| 飛書 | ✅ | 官方 |
+| 釘釘 | ✅ | 官方 |
+| KOOK | ✅ | 官方 |
+| Satori | ✅ |  |
+| Email | ✅ | 只 Matrix、Satori |
+| Matrix | ✅ | 支援多種橋接平台，如 Signal、WhatsApp、Messenger、iMessage、Mattermost、Google Chat、IRC、XMPP、Zulip 等 |
 
-### 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | 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) |
@@ -152,13 +139,54 @@ 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://link.langbot.app/zh/docs/features)
 
-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

@@ -1,25 +1,27 @@
 <p align="center">
 <a href="https://langbot.app">
-<img width="130" src="https://docs.langbot.app/langbot-logo.png" alt="LangBot"/>
+<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>Xây dựng, gỡ lỗi và triển khai bot IM nhanh chóng với LangBot.</h3>
+<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_EN.md) / [简体中文](README.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
+[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">Triển khai</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">Tích hợp API</a> ｜
+<a href="https://link.langbot.app/en/docs/features">Tính năng</a> ｜
+<a href="https://link.langbot.app/en/docs/guide">Tài liệu</a> ｜
+<a href="https://link.langbot.app/en/docs/api">API</a> ｜
 <a href="https://space.langbot.app">Chợ Plugin</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Lộ trình</a>
 
@@ -27,19 +29,40 @@
 
 </p>
 
-## 📦 Bắt đầu
+---
 
-#### Khởi động Nhanh
+## LangBot là gì?
 
-Sử dụng `uvx` để khởi động bằng một lệnh (cần cài đặt [uv](https://docs.astral.sh/uv/getting-started/installation/)):
+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://link.langbot.app/en/docs/features)
+
+---
+
+## 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
 ```
 
-Truy cập http://localhost:5300 để bắt đầu sử dụng.
+> Yêu cầu [uv](https://docs.astral.sh/uv/getting-started/installation/). Truy cập http://localhost:5300 — xong.
 
-#### Triển khai Docker Compose
+### Docker Compose
 
 ```bash
 git clone https://github.com/langbot-app/LangBot
@@ -47,103 +70,104 @@ cd LangBot/docker
 docker compose up -d
 ```
 
-Truy cập http://localhost:5300 để bắt đầu sử dụng.
-
-Tài liệu chi tiết [Triển khai Docker](https://docs.langbot.app/en/deploy/langbot/docker.html).
-
-#### Triển khai Một cú nhấp chuột trên BTPanel
-
-LangBot đã được liệt kê trên BTPanel. Nếu bạn đã cài đặt BTPanel, bạn có thể sử dụng [tài liệu](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) để sử dụng nó.
-
-#### Triển khai Cloud Zeabur
-
-Mẫu Zeabur được đóng góp bởi cộng đồng.
+### Triển khai đám mây một cú nhấp
 
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
-
-#### Triển khai Cloud Railway
-
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-#### Các Phương pháp Triển khai Khác
+**Thêm tùy chọn:** [Docker](https://link.langbot.app/en/docs/docker) · [Thủ công](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](./docker/README_K8S.md)
 
-Sử dụng trực tiếp phiên bản phát hành để chạy, xem tài liệu [Triển khai Thủ công](https://docs.langbot.app/en/deploy/langbot/manual.html).
+---
 
-#### Triển khai Kubernetes
-
-Tham khảo tài liệu [Triển khai Kubernetes](./docker/README_K8S.md).
-
-## 😎 Cập nhật Mới nhất
-
-Nhấp vào các nút Star và Watch ở góc trên bên phải của kho lưu trữ để nhận các bản cập nhật mới nhất.
-
-![star gif](https://docs.langbot.app/star.gif)
-
-## ✨ Tính năng
-
-<img width="500" src="https://docs.langbot.app/ui/bot-page-en-rounded.png" />
-
-
-- 💬 Chat với LLM / Agent: Hỗ trợ nhiều LLM, thích ứng với chat nhóm và chat riêng tư; Hỗ trợ các cuộc trò chuyện nhiều vòng, gọi công cụ, khả năng đa phương thức và đầu ra streaming. Triển khai RAG (cơ sở kiến thức) tích hợp sẵn và tích hợp sâu với [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) v.v. LLMOps platforms.
-- 🤖 Hỗ trợ Đa nền tảng: Hiện hỗ trợ QQ, QQ Channel, WeCom, WeChat cá nhân, Lark, DingTalk, Discord, Telegram, KOOK, Slack, LINE, v.v.
-- 🛠️ Độ ổn định Cao, Tính năng Phong phú: Kiểm soát truy cập gốc, giới hạn tốc độ, lọc từ nhạy cảm, v.v.; Dễ sử dụng, hỗ trợ nhiều phương pháp triển khai.
-- 🧩 Mở rộng Plugin, Cộng đồng Hoạt động: Hỗ trợ các cơ chế plugin hướng sự kiện, mở rộng thành phần, v.v.; Tích hợp giao thức [MCP](https://modelcontextprotocol.io/) của Anthropic; Hiện có hàng trăng plugin.
-- 😻 Giao diện Web: Hỗ trợ quản lý các phiên bản LangBot thông qua trình duyệt. Không cần viết tệp cấu hình thủ công.
-- 📊 Tính năng Cấp sản xuất: Hỗ trợ nhiều cấu hình pipeline, các bot khác nhau cho các kịch bản khác nhau. Có khả năng giám sát toàn diện và xử lý ngoại lệ.
-
-Để biết thêm thông số kỹ thuật chi tiết, vui lòng tham khảo [tài liệu](https://docs.langbot.app/en/insight/features.html).
-
-Hoặc truy cập môi trường demo: https://demo.langbot.dev/
-  - Thông tin đăng nhập: Email: `demo@langbot.app` Mật khẩu: `langbot123456`
-  - Lưu ý: Chỉ dành cho demo WebUI, vui lòng không nhập bất kỳ thông tin nhạy cảm nào trong môi trường công cộng.
-
-### Nền tảng Nhắn tin
+## Nền tảng được hỗ trợ
 
 | Nền tảng | Trạng thái | Ghi chú |
-| --- | --- | --- |
-| Discord | ✅ |  |
-| Telegram | ✅ |  |
-| Slack | ✅ |  |
-| LINE | ✅ |  |
-| QQ Cá nhân | ✅ |  |
-| QQ API Chính thức | ✅ |  |
-| WeCom | ✅ |  |
-| WeComCS | ✅ |  |
-| WeCom AI Bot | ✅ |  |
-| WeChat Cá nhân | ✅ |  |
-| KOOK | ✅ |  |
-| Lark | ✅ |  |
-| DingTalk | ✅ |  |
+|----------|--------|-------|
+| Discord | ✅ | Chính thức |
+| Telegram | ✅ | Chính thức |
+| Slack | ✅ | Chính thức |
+| LINE | ✅ | Chính thức |
+| QQ | ✅ | Cá nhân & API chính thức (Kênh, DM, Nhóm) |
+| WeCom | ✅ | WeChat doanh nghiệp, CS bên ngoài, AI Bot |
+| WeChat | ✅ | Cá nhân & Tài khoản công khai |
+| Lark | ✅ | Chính thức |
+| DingTalk | ✅ | Chính thức |
+| KOOK | ✅ | Chính thức |
+| Satori | ✅ |  |
+| Email | ✅ | Matrix, Satori |
+| Matrix | ✅ | Hỗ trợ nhiều nền tảng qua bridge như Signal, WhatsApp, Messenger, iMessage, Mattermost, Google Chat, IRC, XMPP, Zulip và hơn thế nữa |
 
-### LLMs
+---
 
-| LLM | Trạng thái | Ghi chú |
-| --- | --- | --- |
-| [OpenAI](https://platform.openai.com/) | ✅ | Có sẵn cho bất kỳ mô hình định dạng giao diện OpenAI nào |
-| [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) | ✅ | Nền tảng tài nguyên LLM và GPU |
-| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | Nền tảng tài nguyên LLM và GPU |
-| [接口 AI](https://jiekou.ai/) | ✅ | Nền tảng tổng hợp LLM |
-| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | Nền tảng tài nguyên LLM và GPU |
-| [302.AI](https://share.302.ai/SuTG99) | ✅ | Cổng LLM (MaaS) |
-| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
-| [Dify](https://dify.ai) | ✅ | Nền tảng LLMOps |
-| [Ollama](https://ollama.com/) | ✅ | Nền tảng chạy LLM cục bộ |
-| [LMStudio](https://lmstudio.ai/) | ✅ | Nền tảng chạy LLM cục bộ |
-| [GiteeAI](https://ai.gitee.com/) | ✅ | Cổng giao diện LLM (MaaS) |
-| [SiliconFlow](https://siliconflow.cn/) | ✅ | Cổng LLM (MaaS) |
-| [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | Cổng LLM (MaaS), nền tảng LLMOps |
-| [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | Cổng LLM (MaaS), nền tảng LLMOps |
-| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | Cổng LLM (MaaS) |
-| [MCP](https://modelcontextprotocol.io/) | ✅ | Hỗ trợ truy cập công cụ qua giao thức MCP |
+## LLM và tích hợp được hỗ trợ
 
-## 🤝 Đóng góp Cộng đồng
+| 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 | ✅ |
+| [Qiniu](https://www.qiniu.com/ai/agent) | Cổng | ✅ |
 
-Cảm ơn các [người đóng góp mã](https://github.com/langbot-app/LangBot/graphs/contributors) sau đây và các thành viên khác trong cộng đồng vì những đóng góp của họ cho LangBot:
+[→ Xem tất cả tích hợp](https://link.langbot.app/en/docs/features)
+
+---
+
+## 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" />

docker/README_K8S.md

@@ -312,7 +312,7 @@ spec:
 ### 参考资源
 
 - [LangBot 官方文档](https://docs.langbot.app)
-- [Docker 部署文档](https://docs.langbot.app/zh/deploy/langbot/docker.html)
+- [Docker 部署文档](https://link.langbot.app/zh/docs/docker)
 - [Kubernetes 官方文档](https://kubernetes.io/docs/)
 
 ---
@@ -625,5 +625,5 @@ spec:
 ### References
 
 - [LangBot Official Documentation](https://docs.langbot.app)
-- [Docker Deployment Guide](https://docs.langbot.app/zh/deploy/langbot/docker.html)
+- [Docker Deployment Guide](https://link.langbot.app/zh/docs/docker)
 - [Kubernetes Official Documentation](https://kubernetes.io/docs/)

docker/docker-compose.yaml

@@ -34,4 +34,4 @@ services:
 
 networks:
   langbot_network:
-    driver: bridge
+    driver: bridge

docs/multi-tenant/workspace-multi-user-architecture.md

@@ -0,0 +1,858 @@
+# LangBot 多租户与多用户改造方案
+
+## 目标
+
+本方案面向 LangBot 从“单实例单管理员”演进到 SaaS 友好的“多 workspace、多账户、多权限”架构。
+
+核心定义：
+
+- Account：登录主体。一个自然人或服务账号，可加入多个 workspace。
+- Workspace：租户边界。一个 workspace 内可拥有多个用户、机器人、流水线、模型、知识库、扩展、监控数据与 API Key。
+- Membership：账户与 workspace 的关系，承载角色与权限。
+- Role/Permission：workspace 内权限，不再用“是否是当前唯一用户”来决定访问能力。
+
+目标体验：
+
+- 新用户登录后可以创建 workspace、加入 workspace、切换 workspace。
+- 同一个账户可加入多个 workspace，每个 workspace 权限不同。
+- 一个 workspace 可邀请多个用户协作，并分别设置 owner/admin/editor/viewer 等权限。
+- 所有业务资源默认属于某个 workspace，所有 API 默认在当前 workspace 下工作。
+- Plugin SDK、MCP、知识库、模型调用、监控日志都能拿到稳定的 workspace 上下文，并且不跨租户泄露数据。
+
+## 调研结论
+
+### 当前 LangBot 的单用户假设
+
+LangBot 现在已经有 `users` 表和 JWT 登录，但仍是单用户/单租户模型：
+
+- `src/langbot/pkg/entity/persistence/user.py` 的 `User` 只保存 `user/password/account_type/space_*`，没有角色、状态、workspace 关系。
+- `src/langbot/pkg/api/http/service/user.py` 通过 `is_initialized()` 判断系统是否已有用户；`create_or_update_space_user()` 在系统已初始化且邮箱不匹配时拒绝新用户，这直接限制了多用户登录。
+- `src/langbot/pkg/api/http/controller/group.py` 的 `AuthType.USER_TOKEN` 验证后只向 handler 注入 `user_email`；JWT payload 也只有 `user`，没有 `account_id`、`workspace_id`、`role`、`permissions`。
+- `src/langbot/pkg/api/http/service/apikey.py` 的 API Key 只验证 key 是否存在，没有 owner、scope、workspace。
+- `web/src/app/infra/http/BaseHttpClient.ts` 从 `localStorage.token` 读取单个 token，并在所有请求上加 `Authorization`；前端没有 workspace selector，也没有当前 workspace 上下文。
+
+当前登录流程更像“初始化一个本地管理账号”，而不是 SaaS 账户体系。要支持多用户，必须把“初始化状态”和“首个 workspace 创建”拆开。
+
+### 业务资源当前都是全局资源
+
+主要持久化表没有租户字段：
+
+- Bot：`bots`
+- Pipeline：`legacy_pipelines`、`pipeline_run_records`
+- Model：`model_providers`、`llm_models`、`embedding_models`、`rerank_models`
+- Plugin：`plugin_settings`
+- MCP：`mcp_servers`
+- RAG：`knowledge_bases`、`knowledge_base_files`、`knowledge_base_chunks`
+- Monitoring：`monitoring_messages`、`monitoring_llm_calls`、`monitoring_sessions`、`monitoring_errors`、`monitoring_embedding_calls`、`monitoring_feedback`
+- API Key：`api_keys`
+- Webhook：`webhooks`
+- Metadata：`metadata`
+- Binary storage：`binary_storages`
+
+对应服务也直接 select 全表，例如：
+
+- `BotService.get_bots()` 返回所有 bot。
+- `PipelineService.get_pipelines()` 返回所有 pipeline。
+- `ModelProviderService.get_providers()` 返回所有 provider。
+- `MCPService.get_mcp_servers()` 返回所有 MCP server。
+- 插件和二进制存储没有 workspace 维度，插件 workspace storage 在 SDK 里还硬编码为 `default`。
+
+所以改造重点不是只给用户表加字段，而是给资源访问层统一加入 workspace scope。
+
+### 运行时也存在全局单例假设
+
+`src/langbot/pkg/core/stages/build_app.py` 初始化的是一个全局 `Application`，其中包含单例：
+
+- `platform_mgr`
+- `pipeline_mgr`
+- `model_mgr`
+- `tool_mgr`
+- `plugin_connector`
+- `sess_mgr`
+- `rag_mgr`
+- `vector_db_mgr`
+
+当前运行时把所有 bot、pipeline、model、plugin、MCP 都加载到同一套内存管理器。多租户改造需要决定：是共享运行时并在对象上带 workspace 过滤，还是每个 workspace 拆 runtime shard。第一阶段建议共享进程、强制 workspace-aware；等规模变大后再演进为按 workspace 分片。
+
+### Plugin SDK 对 workspace 的假设
+
+SDK 当前只认识 bot/pipeline/query/session，不认识租户：
+
+- `src/langbot_plugin/api/entities/builtin/pipeline/query.py` 的 `Query` 有 `query_id/launcher_type/launcher_id/sender_id/bot_uuid/pipeline_uuid`，没有 `workspace_id/account_id`。
+- `src/langbot_plugin/api/entities/builtin/provider/session.py` 的 `Session` 只按 `launcher_type + launcher_id` 表达会话。
+- `src/langbot_plugin/api/proxies/langbot_api.py` 暴露 `get_bots/get_llm_models/invoke_llm/list_tools/vector_*` 等 Host API，都是全局语义。
+- `src/langbot_plugin/runtime/io/handlers/plugin.py` 的 `set_workspace_storage/get_workspace_storage` 把 `owner_type` 设为 `workspace`，但 `owner` 固定为 `default`。
+- LangBot 侧 `src/langbot/pkg/plugin/handler.py` 处理插件请求时，会把 `GET_BOTS`、`GET_LLM_MODELS`、`VECTOR_*` 等转到全局服务。
+
+这意味着多租户落地时，不能只在 Web API 层过滤；插件可以通过 Host API 访问全局资源，所以 SDK/Runtime 通信也必须传递 workspace context。
+
+## 开源版与商业版产品边界
+
+LangBot 是开源软件，但多 workspace 能力本质上是 SaaS 控制面能力。如果把完整多 workspace、成员协作、订阅权益和配额代码都放进开源仓库，只靠本地 feature flag 或本地 license check，无法有效避免第三方 fork 后自建 SaaS。因此建议采用 open-core 架构：开源版保留单 workspace 执行能力，账户、订阅、权益和多 workspace 协作能力放到 LangBot Space/Cloud Control Plane 和商业模块中。
+
+### 版本边界
+
+推荐拆成三层：
+
+- `LangBot Core OSS`：开源，自托管，默认只有一个隐式 `default workspace`。它可以在数据结构上兼容 workspace，但产品能力上不提供创建多个 workspace、切换 workspace、成员邀请、成员权限管理、审计和多租户配额。
+- `LangBot Space / Cloud Control Plane`：托管控制面，负责 account、workspace、membership、subscription、billing、entitlement、license token、workspace quota、marketplace 权益等能力。
+- `LangBot Commercial Module`：商业闭源或私有包，承载多 workspace、团队协作、RBAC、自定义角色、审计日志、SAML/SSO、企业私有化授权等能力。
+
+企业私有化版本可以采用 `LangBot Core + Commercial Module + License Token` 的形式交付。开源 Core 仍然可独立运行，但只能作为单 workspace 自托管产品，不提供 SaaS 多租户控制面。
+
+### OSS 中如何保留兼容但不开放多 workspace
+
+为了让后续商业版复用同一套资源隔离模型，OSS 代码里可以保留 `workspace_uuid` 相关字段和默认 workspace 迁移，但应限制为单 workspace：
+
+- 首次初始化时创建一个 `Default Workspace`。
+- 所有资源自动归属这个 default workspace。
+- 不暴露 `POST /api/v1/workspaces`。
+- 不暴露 workspace switcher。
+- 不暴露成员邀请和成员角色管理。
+- 不支持一个 account 加入多个 workspace。
+- 不支持 workspace 数量大于 1。
+- 前端不展示 workspace selector。
+- API 层如果收到非 default workspace 的 `X-Workspace-Id`，直接拒绝。
+
+也就是说，OSS 可以是 workspace-aware，但不是 multi-workspace-enabled。这样做的价值是：代码结构提前适配租户隔离，未来商业版不用重写所有资源模型；同时开源版用户无法直接通过 UI/API 获得 SaaS 型多租户能力。
+
+### 账户、订阅和权益抽到 Space
+
+账户和订阅体系建议从 LangBot Core 中抽出，交给 Space 控制面：
+
+```text
+LangBot Space
+  -> Account
+  -> Workspace
+  -> Membership
+  -> Subscription
+  -> Entitlement
+  -> License Token
+
+LangBot Core
+  -> Validate entitlement / license
+  -> Run bots, pipelines, plugins, MCP, RAG
+  -> Enforce local resource scope
+  -> Report usage
+```
+
+这样做有几个原因：
+
+- 账号体系如果完全在本地，第三方容易直接改库创建 workspace/membership。
+- 订阅、配额和商业权益如果完全在本地，容易绕过。
+- Space 可以统一处理 OAuth、组织、邀请、付款、发票、套餐、权益、Marketplace 分发权限。
+- LangBot Core 只作为执行面消费 Space 下发的 entitlement，减少商业规则暴露。
+
+### Entitlement 设计
+
+Space 向 LangBot Core 下发签名权益，可以是在线校验，也可以为企业版提供短期/长期离线 license token。
+
+示例：
+
+```json
+{
+  "edition": "oss",
+  "workspace_limit": 1,
+  "member_limit": 1,
+  "multi_workspace": false,
+  "rbac": false,
+  "audit_log": false,
+  "custom_roles": false,
+  "sso": false,
+  "commercial_use": false,
+  "expires_at": 1893456000
+}
+```
+
+OSS 默认权益：
+
+- `workspace_limit = 1`
+- `member_limit = 1`
+- `multi_workspace = false`
+- `rbac = false`
+- `audit_log = false`
+- `sso = false`
+
+Cloud/Pro/Enterprise 权益：
+
+- `workspace_limit > 1`
+- `member_limit > 1`
+- `multi_workspace = true`
+- `rbac = true`
+- 可按套餐打开 audit、custom roles、SSO、usage reporting、enterprise support 等能力。
+
+Core 执行面需要在关键入口强制校验 entitlement：
+
+- 创建 workspace。
+- 邀请成员。
+- 修改成员角色。
+- 切换 workspace。
+- 创建超过 quota 的资源。
+- 开启商业模块功能。
+
+### 商业模块边界
+
+以下能力不建议进入 OSS 仓库的完整实现：
+
+- 多 workspace 创建和切换。
+- Workspace 成员邀请。
+- Workspace RBAC 和自定义角色。
+- Workspace 审计日志。
+- Workspace 级用量和配额管理。
+- 订阅、账单、发票。
+- 企业 SSO/SAML/OIDC。
+- 在线/离线 license 管理。
+- 多租户 SaaS 运营控制台。
+
+OSS 仓库可以保留接口占位、默认 workspace 兼容和必要的数据隔离字段，但完整交互、管理 UI、权益校验器和多 workspace policy engine 应由 Space 或商业模块提供。
+
+### 防自建 SaaS 的现实边界
+
+技术上无法 100% 阻止别人 fork 开源代码后自行改造。更可靠的策略是组合：
+
+- 不把完整商业多 workspace 实现放进 OSS。
+- Space 控制面提供账号、订阅、权益、Marketplace 和官方托管能力。
+- 商业模块闭源或私有分发。
+- 使用商标、云服务条款和商业 license 限制“自称官方 LangBot SaaS”或未经授权商用托管。
+- 如果当前开源 license 对托管商用限制不足，需要单独评估 license 策略，必要时引入 open-core license 或新增商业附加条款。具体 license 调整需要法律评审。
+
+结论：多 workspace 的底层 schema 可以在 OSS 中以 default workspace 兼容方式铺路，但多 workspace 产品能力、账户订阅权益、协作管理和 SaaS 控制面应放到 Space/商业模块，不作为开源版可直接使用的能力。
+
+## 推荐总体架构
+
+采用“单实例多 workspace，资源行级隔离，运行时上下文隔离”的架构：
+
+```mermaid
+flowchart TD
+    A["Account"] --> B["WorkspaceMembership"]
+    B --> C["Workspace"]
+    C --> D["Bots"]
+    C --> E["Pipelines"]
+    C --> F["Models & Providers"]
+    C --> G["Knowledge Bases"]
+    C --> H["Extensions: Plugins / MCP"]
+    C --> I["API Keys & Webhooks"]
+    C --> J["Monitoring"]
+    D --> K["Runtime Query"]
+    E --> K
+    K --> L["Plugin Runtime"]
+    K --> M["MCP Runtime"]
+    L --> N["Workspace-scoped Host APIs"]
+```
+
+原则：
+
+- 账户全局唯一，workspace 是所有业务资源的归属边界。
+- 所有 HTTP handler 在进入业务服务前解析出 `RequestContext(account, workspace, membership, permissions)`。
+- 所有 service 方法显式接收 `ctx` 或 `workspace_id`，禁止在业务服务里无条件 select 全表。
+- 运行时对象的 key 从 `uuid` 扩展为 `(workspace_id, uuid)` 或使用全局唯一 uuid 但必须记录 workspace_id 并校验。
+- 插件/MCP/知识库/模型调用都按 query 所属 workspace 过滤可用资源。
+
+## 数据模型设计
+
+### Account
+
+替代现有 `users` 的语义，建议保留表名但升级字段，避免过大迁移：
+
+字段建议：
+
+- `id`
+- `uuid`
+- `email`
+- `password_hash`
+- `display_name`
+- `avatar_url`
+- `account_type`: `local | space`
+- `status`: `active | disabled | deleted`
+- `space_account_uuid`
+- `space_access_token`
+- `space_refresh_token`
+- `space_access_token_expires_at`
+- `space_api_key`
+- `created_at`
+- `updated_at`
+
+兼容策略：
+
+- 旧字段 `user` 迁移为 `email`，可以短期保留 alias。
+- 旧 `password` 迁移为 `password_hash`，也可先保持列名不变，service 层改命名。
+- JWT 中不要继续只放 email，应放 `sub=account_uuid`。
+
+### Workspace
+
+新增 `workspaces`：
+
+- `uuid`
+- `name`
+- `slug`
+- `avatar_url`
+- `type`: `personal | team`
+- `status`: `active | suspended | deleted`
+- `default_language`
+- `created_by_account_uuid`
+- `created_at`
+- `updated_at`
+
+每个账户首次登录时自动创建一个 personal workspace。旧单用户实例迁移时创建一个 `Default Workspace`。
+
+### WorkspaceMembership
+
+新增 `workspace_memberships`：
+
+- `workspace_uuid`
+- `account_uuid`
+- `role`: `owner | admin | developer | operator | viewer`
+- `status`: `active | invited | disabled`
+- `invited_by_account_uuid`
+- `joined_at`
+- `created_at`
+- `updated_at`
+
+唯一索引：
+
+- `(workspace_uuid, account_uuid)`
+
+### WorkspaceInvitation
+
+新增 `workspace_invitations`：
+
+- `uuid`
+- `workspace_uuid`
+- `email`
+- `role`
+- `token_hash`
+- `expires_at`
+- `accepted_at`
+- `created_by_account_uuid`
+- `created_at`
+
+用于邀请外部用户加入 workspace。Space OAuth 登录时可以根据 email 自动匹配未接受邀请。
+
+### Role 与 Permission
+
+先用固定角色，后续再做自定义角色。
+
+建议权限：
+
+- `workspace.manage`
+- `member.view`
+- `member.invite`
+- `member.update_role`
+- `member.remove`
+- `bot.view`
+- `bot.manage`
+- `pipeline.view`
+- `pipeline.manage`
+- `model.view`
+- `model.manage`
+- `knowledge.view`
+- `knowledge.manage`
+- `extension.view`
+- `extension.manage`
+- `monitoring.view`
+- `apikey.manage`
+- `webhook.manage`
+- `billing.view`
+- `billing.manage`
+
+角色映射：
+
+| Role | 说明 | 权限 |
+| --- | --- | --- |
+| owner | workspace 拥有者 | 全部权限；可转让 owner；不可被其他角色移除 |
+| admin | 管理员 | 除 owner 转让和删除 workspace 外的全部权限 |
+| developer | 构建者 | 管理 bot、pipeline、model、knowledge、extension、webhook，可看监控 |
+| operator | 运营者 | 查看和启停 bot、查看监控、查看配置，不可改密钥和删除资源 |
+| viewer | 只读成员 | 只读资源和监控 |
+
+### 业务资源加 workspace_uuid
+
+以下表需要新增 `workspace_uuid`：
+
+- `bots`
+- `legacy_pipelines`
+- `pipeline_run_records`
+- `model_providers`
+- `llm_models`
+- `embedding_models`
+- `rerank_models`
+- `plugin_settings`
+- `mcp_servers`
+- `knowledge_bases`
+- `knowledge_base_files`
+- `knowledge_base_chunks`
+- `monitoring_*`
+- `api_keys`
+- `webhooks`
+- `binary_storages`
+- `metadata`
+
+索引建议：
+
+- 所有资源表加 `(workspace_uuid, created_at)` 或 `(workspace_uuid, updated_at)`。
+- 资源唯一键从单列改为 workspace 复合唯一：
+  - `bots.uuid` 可保持全局唯一，但查询仍必须带 workspace。
+  - `plugin_settings` 主键从 `(plugin_author, plugin_name)` 改为 `(workspace_uuid, plugin_author, plugin_name)`。
+  - `mcp_servers.name` 如果未来要求唯一，必须是 `(workspace_uuid, name)`。
+  - `metadata.key` 改为 `(workspace_uuid, key)`，系统级 metadata 单独放 `system_metadata` 或使用 `workspace_uuid=NULL`。
+  - `binary_storages.unique_key` 建议改为 `workspace_uuid + owner_type + owner + key` 的 hash。
+
+### API Key
+
+API Key 必须归属于 workspace：
+
+- `workspace_uuid`
+- `created_by_account_uuid`
+- `scopes`
+- `expires_at`
+- `last_used_at`
+- `status`
+
+验证 API Key 后生成 `RequestContext`：
+
+- `account_uuid=None` 或 service account uuid
+- `workspace_uuid=key.workspace_uuid`
+- `permissions=key.scopes`
+
+这样 `/api/v1/platform/bots/<uuid>/send_message` 之类接口不会跨 workspace 操作 bot。
+
+## 后端改造方案
+
+### RequestContext
+
+新增统一上下文对象，例如：
+
+```python
+class RequestContext:
+    account_uuid: str | None
+    workspace_uuid: str
+    role: str | None
+    permissions: set[str]
+    auth_type: Literal["user_token", "api_key"]
+```
+
+改造 `RouterGroup.route()`：
+
+- `USER_TOKEN`：验证 JWT，读取 `account_uuid`，再从 header/query/cookie 中解析 current workspace。
+- `API_KEY`：验证 API Key，直接得到 workspace。
+- `USER_TOKEN_OR_API_KEY`：两者都返回同一种 `RequestContext`。
+- handler 参数从可选 `user_email` 升级为可选 `ctx`；兼容期同时支持 `user_email`。
+
+当前 workspace 传递方式：
+
+- 推荐 header：`X-Workspace-Id: <workspace_uuid>`
+- Web 前端同时把当前 workspace 存在 localStorage。
+- 如果未传，后端用账户最近使用 workspace 或第一个 active membership。
+
+JWT payload：
+
+```json
+{
+  "sub": "account_uuid",
+  "email": "user@example.com",
+  "iss": "LangBot-...",
+  "exp": 1234567890
+}
+```
+
+不要把 workspace 写死在 JWT 里，否则切换 workspace 需要刷新 token。可以额外支持短 TTL workspace token，但第一阶段不必。
+
+### 服务层改造模式
+
+所有 service 方法增加 `ctx` 或 `workspace_uuid`：
+
+```python
+async def get_bots(self, ctx: RequestContext, include_secret: bool = True):
+    require(ctx, "bot.view")
+    query = sqlalchemy.select(Bot).where(Bot.workspace_uuid == ctx.workspace_uuid)
+```
+
+需要改造的服务：
+
+- `UserService`：拆成 AccountService + WorkspaceService 更清晰。
+- `ApiKeyService`：按 workspace 管理 key。
+- `BotService`：所有 bot 查询/创建/更新/删除按 workspace。
+- `PipelineService`：所有 pipeline 查询/默认 pipeline 按 workspace。
+- `ModelProviderService` 和 model services：按 workspace 隔离 provider 和 model。
+- `MCPService`：按 workspace 管理 MCP server，运行时按 workspace host。
+- `KnowledgeService/RAGRuntimeService`：按 workspace 管理 KB、文件、collection。
+- `MonitoringService`：记录和查询都带 workspace。
+- `WebhookService`：按 workspace 管理 webhook。
+- `PluginRuntimeConnector`：插件安装、设置、配置按 workspace。
+
+### HTTP API 形态
+
+保留现有路径，靠 `X-Workspace-Id` 表示当前 workspace，可减少前端和 SDK 破坏：
+
+- `GET /api/v1/workspaces`
+- `POST /api/v1/workspaces`
+- `GET /api/v1/workspaces/current`
+- `PUT /api/v1/workspaces/current`
+- `GET /api/v1/workspaces/<workspace_uuid>/members`
+- `POST /api/v1/workspaces/<workspace_uuid>/invitations`
+- `PUT /api/v1/workspaces/<workspace_uuid>/members/<account_uuid>`
+- `DELETE /api/v1/workspaces/<workspace_uuid>/members/<account_uuid>`
+
+现有资源 API：
+
+- `/api/v1/platform/bots`
+- `/api/v1/pipelines`
+- `/api/v1/provider/*`
+- `/api/v1/plugins`
+- `/api/v1/mcp`
+- `/api/v1/knowledge`
+
+继续保留，但必须从 `RequestContext.workspace_uuid` 过滤。
+
+对外 API Key 也使用相同路径，只是由 key 决定 workspace。
+
+### 初始化流程
+
+现有 `/api/v1/user/init` 含义改为“创建首个账号和首个 workspace”：
+
+1. 如果系统没有任何 account：
+   - 创建 account。
+   - 创建 personal/team workspace。
+   - 创建 owner membership。
+   - 创建默认 pipeline。
+   - 标记 wizard status 到该 workspace metadata。
+2. 如果系统已有 account：
+   - 禁止无邀请注册，除非配置允许公开注册。
+   - Space OAuth 登录后，如果没有 membership，引导创建 workspace 或接受邀请。
+
+`/api/v1/user/account-info` 不应再只返回 first user，应返回：
+
+- `initialized`
+- `registration_mode`
+- `space_enabled`
+- `default_login_methods`
+
+登录成功后前端调用 `/api/v1/workspaces` 选择 workspace。
+
+### 运行时隔离
+
+第一阶段采用共享进程 + workspace-aware runtime：
+
+- `RuntimeBot` 增加 `workspace_uuid`。
+- `RuntimePipeline` 增加 `workspace_uuid`。
+- `Query` 增加 `workspace_uuid`，从 bot/pipeline 派生。
+- `SessionManager.get_session()` key 从 `(launcher_type, launcher_id)` 改为 `(workspace_uuid, bot_uuid, launcher_type, launcher_id)`。
+- `PipelineManager.pipeline_dict` key 可保持 pipeline uuid，但所有 load/get 都校验 workspace；如果 uuid 不是全局唯一则改为 `(workspace_uuid, pipeline_uuid)`。
+- `ModelManager` provider/model 加 workspace 过滤；`get_model_by_uuid` 必须确保 query workspace 可访问。
+- `ToolManager` 中 MCP tools、plugin tools 按 query workspace 过滤。
+
+后续规模化时可演进：
+
+- workspace runtime shard：每个 workspace 一套 plugin runtime/MCP runtime。
+- 大客户独立进程或独立数据库。
+
+## Plugin SDK 与 Runtime 改造
+
+### Query/Event 增加 workspace context
+
+SDK `Query` 增加：
+
+- `workspace_uuid: str`
+- `workspace_slug: str | None`
+- `account_uuid: str | None`，仅 Web/API 触发时可能有，聊天平台消息通常为空。
+
+Event 模型通过 `event.query.workspace_uuid` 可拿到租户上下文；序列化时也应包含这些字段。
+
+向后兼容：
+
+- 字段可选，默认 `None`。
+- 老插件不感知这些字段也能跑。
+- 新插件可通过 `ctx.event.query.workspace_uuid` 或新增 `ctx.get_workspace()` 访问。
+
+### Host API 默认按当前 workspace 限制
+
+`LangBotAPIProxy` 的以下方法必须由 Host 端按 workspace 过滤：
+
+- `get_bots`
+- `get_bot_info`
+- `send_message`
+- `get_llm_models`
+- `invoke_llm`
+- `list_plugins_manifest`
+- `list_commands`
+- `list_tools`
+- `call_tool`
+- `invoke_embedding`
+- `vector_*`
+- `list_knowledge_bases`
+- `retrieve_knowledge`
+
+建议新增显式方法：
+
+- `get_workspace_info()`
+- `get_current_account()`
+- `get_workspace_storage(...)`
+
+但不要让插件传入任意 workspace id 来越权访问。插件请求的 workspace 应由 Runtime 根据当前 query/plugin connection 填充。
+
+### Workspace storage 修复
+
+当前 SDK runtime 中：
+
+```python
+data["owner_type"] = "workspace"
+data["owner"] = "default"
+```
+
+必须改为：
+
+- 如果请求来自 query/event：owner 为 `workspace_uuid`。
+- 如果请求来自后台插件任务：owner 为 plugin 安装所属 workspace。
+- Host 侧 `binary_storages` 加 `workspace_uuid`，并在 unique key 中包含 workspace。
+
+Plugin storage 建议也同时加 workspace：
+
+- 现在 plugin storage owner 是 `author/name`，这会导致同一插件在不同 workspace 的私有数据冲突。
+- 应改为 `(workspace_uuid, plugin_id, key)`。
+
+### 插件安装与配置
+
+`plugin_settings` 从全局变为 workspace-scoped：
+
+- 同一个插件可安装到多个 workspace。
+- 每个 workspace 有自己的 enabled、priority、config、install_source、install_info。
+- 插件 runtime 列表需要能按 workspace 过滤。
+
+实现路线有两种：
+
+1. 共享插件进程，插件代码只加载一份，设置和调用时附带 workspace。
+2. 每个 workspace 一个插件容器实例，隔离最彻底但资源占用更高。
+
+推荐第一阶段采用方案 1，但要求：
+
+- 所有 RuntimeToLangBot/PluginToRuntime action 都能携带 `workspace_uuid`。
+- 插件 config 获取时按 workspace 返回。
+- 插件 page API 请求必须校验当前用户在该 workspace 有访问权限。
+
+### MCP
+
+MCP server 是租户资源：
+
+- `mcp_servers.workspace_uuid`。
+- MCP session key 从 `server_name` 改为 `(workspace_uuid, server_name)` 或使用全局 uuid。
+- Pipeline extension preferences 中绑定 MCP server uuid 时，只能绑定同 workspace 的 server。
+- MCP tool 列表在 query 执行时按 query.workspace_uuid + pipeline 绑定关系过滤。
+
+## 前端改造
+
+### Workspace selector
+
+Home layout 顶部或 sidebar 增加 workspace selector：
+
+- 当前 workspace 名称和头像。
+- 切换 workspace 后写入 `localStorage.currentWorkspaceId`。
+- 所有请求自动带 `X-Workspace-Id`。
+- 切换后刷新 sidebar 数据和页面缓存。
+
+`BaseHttpClient` request interceptor 增加：
+
+```ts
+const workspaceId = localStorage.getItem("currentWorkspaceId");
+if (workspaceId) config.headers["X-Workspace-Id"] = workspaceId;
+```
+
+### 用户与成员管理页面
+
+新增页面：
+
+- `/home/workspace/settings`
+- `/home/workspace/members`
+- `/home/workspace/invitations`
+
+能力：
+
+- owner/admin 邀请成员。
+- owner/admin 修改成员角色。
+- owner 移除成员、转让 owner。
+- 所有人可切换 workspace。
+- viewer/operator 在 UI 上隐藏不可操作按钮，但后端仍做权限校验。
+
+### 登录与注册
+
+登录后流程：
+
+1. `authUser` 拿 token。
+2. `initializeUserInfo()` 获取 account info。
+3. `GET /api/v1/workspaces`。
+4. 如果没有 workspace：进入创建 workspace 向导。
+5. 如果有多个 workspace：默认进入最近使用 workspace，可切换。
+
+注册页不再表达“初始化管理员账号”，而是：
+
+- 首次系统启动：创建首个 owner + default workspace。
+- 后续：根据配置允许公开注册，或只能接受邀请。
+
+### 旧页面影响
+
+需要逐个检查这些页面的数据加载是否都依赖当前 workspace：
+
+- Bots
+- Pipelines
+- Plugins/Market/MCP
+- Knowledge
+- Monitoring
+- Models dialog
+- API integration dialog
+- Wizard
+
+## 迁移方案
+
+### 迁移阶段 0：准备
+
+- 引入 `workspaces`、`workspace_memberships`、`workspace_invitations`。
+- 给 `users` 增加 `uuid/status/display_name` 等字段。
+- 创建 `RequestContext`，但先不强制所有服务改完。
+
+### 迁移阶段 1：默认 workspace
+
+对现有实例执行迁移：
+
+1. 创建 `Default Workspace`。
+2. 找到现有第一个 user，设为 owner。
+3. 所有已有资源写入 `workspace_uuid=default_workspace_uuid`。
+4. `metadata` 迁入 default workspace；确实全局的配置放到 `system_metadata`。
+5. `binary_storages` 中 `owner_type=workspace, owner=default` 改为 owner 为 default workspace uuid。
+6. 插件 `plugin_settings` 归入 default workspace。
+
+### 迁移阶段 2：服务层强制 scope
+
+- 改所有 service 查询，必须要求 `workspace_uuid`。
+- API Key 迁移为 workspace key。
+- 所有写操作必须检查权限。
+- 监控和任务查询按 workspace 过滤。
+
+### 迁移阶段 3：运行时上下文
+
+- `Query`、`Session`、`RuntimeBot`、`RuntimePipeline` 增加 workspace。
+- Plugin/MCP/Model/RAG runtime 全部按 workspace 过滤。
+- 修复 SDK workspace storage。
+
+### 迁移阶段 4：前端多 workspace
+
+- 登录后 workspace 选择。
+- Header/sidebar workspace switcher。
+- 成员和邀请管理。
+- 所有 API 请求带 `X-Workspace-Id`。
+
+### 迁移阶段 5：安全收敛
+
+- 添加跨 workspace 越权测试。
+- 添加 API Key scope 测试。
+- 添加插件 Host API 过滤测试。
+- 添加 MCP 和 RAG 隔离测试。
+
+## 安全边界
+
+必须防的场景：
+
+- 用户 A 修改 URL 中 bot uuid，访问用户 B workspace 的 bot。
+- API Key 来自 workspace A，但调用 workspace B 的 bot。
+- 插件通过 `get_bots()` 枚举所有 workspace 的 bot。
+- 插件通过 `workspace_storage` 读取其它 workspace 的数据。
+- MCP server 名称相同导致 session 复用。
+- monitoring session_id 相同导致数据串租户。
+- Space OAuth 登录时，同 email 账户被错误绑定到已有本地 account。
+
+建议策略：
+
+- 所有资源访问都使用 `workspace_uuid + resource_id`。
+- 所有 service 方法入口做权限检查。
+- 插件 Host API 的 workspace 不信任插件入参，只信任 query/runtime connection 上下文。
+- API Key 只授予最小 scope，默认不允许成员管理。
+- owner 角色不能被普通 admin 移除或降权。
+
+## 实施优先级
+
+### P0：基础租户骨架
+
+- Account uuid/status。
+- Workspace / Membership / Invitation。
+- RequestContext。
+- JWT 改为 account uuid。
+- 前端 current workspace header。
+
+### P1：资源行级隔离
+
+- Bots、Pipelines、Models、MCP、Plugins、Knowledge、Monitoring、API Keys 全部加 workspace_uuid。
+- service 查询统一加 workspace filter。
+- 权限矩阵落地。
+
+### P2：运行时隔离
+
+- Query、Session、RuntimeBot、RuntimePipeline 加 workspace。
+- Plugin Host API 和 MCP tools 按 workspace 过滤。
+- SDK workspace storage 从 `default` 改为真实 workspace。
+
+### P3：协作体验
+
+- 邀请成员。
+- 成员列表和角色管理。
+- workspace switcher。
+- 最近使用 workspace。
+
+### P4：SaaS 运维增强
+
+- Workspace 级用量统计。
+- Workspace 级限额：max_bots/max_pipelines/max_extensions/tokens/storage。
+- 审计日志。
+- workspace suspend/delete。
+- 可选自定义角色。
+
+## 测试计划
+
+后端测试：
+
+- 账户可加入多个 workspace。
+- 同账户在不同 workspace 权限不同。
+- viewer 不能创建/修改资源。
+- API Key 只能访问所属 workspace。
+- 所有资源 list/get/update/delete 都不能跨 workspace。
+- 默认 workspace 迁移后旧数据可用。
+
+运行时测试：
+
+- 两个 workspace 使用相同 `launcher_id` 不共享 session。
+- 两个 workspace 使用相同 MCP server name 不共享 MCP session。
+- 插件 `get_bots()` 只能看到当前 workspace bot。
+- 插件 `workspace_storage` 在不同 workspace 读写隔离。
+- Pipeline 只调用当前 workspace 绑定的插件和 MCP tools。
+
+前端测试：
+
+- 登录后自动进入最近 workspace。
+- 切换 workspace 后列表数据变化。
+- 无权限按钮隐藏，直接调用 API 也被后端拒绝。
+- 邀请成员流程完整。
+
+迁移测试：
+
+- SQLite 老实例迁移。
+- PostgreSQL 老实例迁移。
+- 已有 local account 迁移为 default workspace owner。
+- 已有 Space account token 和 Space model provider API key 不丢失。
+
+## 关键实现注意事项
+
+- 不建议在第一版做数据库 schema-per-tenant。LangBot 当前 ORM 和运行时均以单库单表为主，先做 shared schema + workspace_uuid 成本更低。
+- 不建议每个 workspace 立即启动独立 plugin runtime。先共享 runtime，强制 action 带 workspace；大客户隔离可作为后续部署形态。
+- 不要只在前端过滤 workspace。插件、API Key、MCP、RAG 都能绕过前端，必须在后端和运行时层过滤。
+- `metadata` 要拆清楚：wizard status 属于 workspace，系统版本/迁移信息属于 system。
+- `users.user` 用 email 当主键语义不稳，应尽快引入 `account_uuid` 并让 JWT 以 uuid 为准。
+- `plugin_settings` 当前主键没有 workspace，改造时要先改主键/唯一约束，否则同插件无法在多个 workspace 配不同配置。
+
+## 建议落地顺序
+
+1. 新增 workspace/account/membership 表和 RequestContext。
+2. 迁移旧数据到 default workspace。
+3. 改 auth 和前端请求头，让每个请求都有 current workspace。
+4. 从最核心资源开始逐个加 scope：bot -> pipeline -> provider/model -> plugin/MCP -> knowledge -> monitoring。
+5. 改 SDK Query/Event 和 runtime storage。
+6. 上成员管理 UI 和邀请。
+7. 做越权测试和迁移测试。
+
+这个顺序的好处是可以较早让主 UI 在一个 workspace 下继续工作，同时把最危险的跨租户泄露面逐步收紧。

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

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.8.3"
+version = "4.9.6"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -8,7 +8,7 @@ requires-python = ">=3.11,<4.0"
 dependencies = [
     "aiocqhttp>=1.4.4",
     "aiofiles>=24.1.0",
-    "aiohttp>=3.11.18",
+    "aiohttp>=3.13.4",
     "aioshutil>=1.5",
     "aiosqlite>=0.21.0",
     "anthropic>=0.51.0",
@@ -16,7 +16,7 @@ dependencies = [
     "async-lru>=2.0.5",
     "certifi>=2025.4.26",
     "colorlog~=6.6.0",
-    "cryptography>=44.0.3",
+    "cryptography>=46.0.7",
     "dashscope>=1.25.10",
     "dingtalk-stream>=0.24.0",
     "discord-py>=2.5.2",
@@ -27,7 +27,7 @@ dependencies = [
     "nakuru-project-idk>=0.0.2.1",
     "ollama>=0.4.8",
     "openai>1.0.0",
-    "pillow>=11.2.1",
+    "pillow>=12.2.0",
     "psutil>=7.0.0",
     "pycryptodome>=3.22.0",
     "pydantic>2.0",
@@ -39,6 +39,7 @@ dependencies = [
     "quart-cors>=0.8.0",
     "requests>=2.32.3",
     "slack-sdk>=3.35.0",
+    "alembic>=1.15.0",
     "sqlalchemy[asyncio]>=2.0.40",
     "sqlmodel>=0.0.24",
     "telegramify-markdown>=0.5.1",
@@ -49,7 +50,7 @@ dependencies = [
     "pip>=25.1.1",
     "ruff>=0.11.9",
     "pre-commit>=4.2.0",
-    "uv>=0.7.11",
+    "uv>=0.11.6",
     "mypy>=1.16.0",
     "PyPDF2>=3.0.1",
     "python-docx>=1.1.0",
@@ -60,17 +61,23 @@ dependencies = [
     "ebooklib>=0.18",
     "html2text>=2024.2.26",
     "langchain>=0.2.0",
-    "langchain-text-splitters>=0.0.1",
-    "chromadb>=0.4.24",
+    "langchain-core>=1.2.28",
+    "langsmith>=0.7.31",
+    "python-multipart>=0.0.26",
+    "Mako>=1.3.11",
+    "langchain-text-splitters>=1.1.2",
+    "chromadb>=1.0.0,<2.0.0",
     "qdrant-client (>=1.15.1,<2.0.0)",
-    "pyseekdb==1.0.0b7",
-    "langbot-plugin==0.2.5",
+    "pyseekdb==1.1.0.post3",
+    "langbot-plugin==0.3.10",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
+    "matrix-nio>=0.25.2",
     "tboxsdk>=0.0.10",
     "boto3>=1.35.0",
     "pymilvus>=2.6.4",
     "pgvector>=0.4.1",
+    "botocore>=1.42.39",
 ]
 keywords = [
     "bot",
@@ -110,12 +117,12 @@ requires = ["setuptools>=61.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
-package-data = { "langbot" = ["templates/**", "pkg/provider/modelmgr/requesters/*", "pkg/platform/sources/*", "web/out/**"] }
+package-data = { "langbot" = ["templates/**", "pkg/provider/modelmgr/requesters/*", "pkg/platform/sources/*", "web/dist/**", "pkg/persistence/alembic/**"] }
 
 [dependency-groups]
 dev = [
     "pre-commit>=4.2.0",
-    "pytest>=8.4.1",
+    "pytest>=9.0.3",
     "pytest-asyncio>=1.0.0",
     "pytest-cov>=7.0.0",
     "ruff>=0.11.9",

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.8.3'
+__version__ = '4.9.6'

src/langbot/libs/dingtalk_api/api.py

@@ -182,6 +182,88 @@ class DingTalkClient:
             for handler in self._message_handlers[msg_type]:
                 await handler(event)
 
+    async def _parse_quoted_message(self, replied_msg: dict) -> dict:
+        """Parse the quoted/replied message and extract its content.
+
+        Args:
+            replied_msg: The repliedMsg object from DingTalk message
+
+        Returns:
+            A dict containing the quoted message info with keys:
+            - message_id: The original message ID
+            - msg_type: The message type (text, file, picture, audio, etc.)
+            - content: The text content (if any)
+            - file_url: The file download URL (if file type)
+            - file_name: The file name (if file type)
+            - picture: The picture base64 (if picture type)
+            - audio: The audio base64 (if audio type)
+        """
+        quote_info = {
+            'message_id': replied_msg.get('msgId', ''),
+            'msg_type': replied_msg.get('msgType', ''),
+            'sender_id': replied_msg.get('senderId', ''),
+        }
+
+        msg_type = replied_msg.get('msgType', '')
+        content = replied_msg.get('content', {})
+
+        # Handle content as string (JSON) or dict
+        if isinstance(content, str):
+            try:
+                content = json.loads(content)
+            except (json.JSONDecodeError, TypeError):
+                content = {}
+
+        if msg_type == 'text':
+            # Text message
+            if isinstance(content, dict):
+                quote_info['content'] = content.get('content', '')
+            else:
+                quote_info['content'] = str(content)
+
+        elif msg_type == 'file':
+            # File message
+            download_code = content.get('downloadCode')
+            file_name = content.get('fileName')
+            if download_code and file_name:
+                try:
+                    quote_info['file_url'] = await self.get_file_url(download_code)
+                    quote_info['file_name'] = file_name
+                except Exception as e:
+                    if self.logger:
+                        await self.logger.error(f'Failed to get quoted file URL: {e}')
+
+        elif msg_type == 'picture':
+            # Picture message
+            download_code = content.get('downloadCode')
+            if download_code:
+                try:
+                    quote_info['picture'] = await self.download_image(download_code)
+                except Exception as e:
+                    if self.logger:
+                        await self.logger.error(f'Failed to download quoted image: {e}')
+
+        elif msg_type == 'audio':
+            # Audio message
+            download_code = content.get('downloadCode')
+            if download_code:
+                try:
+                    quote_info['audio'] = await self.get_audio_url(download_code)
+                except Exception as e:
+                    if self.logger:
+                        await self.logger.error(f'Failed to get quoted audio: {e}')
+
+        elif msg_type == 'richText':
+            # Rich text message - extract text content
+            rich_text = content.get('richText', [])
+            texts = []
+            for item in rich_text:
+                if 'text' in item and item['text'] != '\n':
+                    texts.append(item['text'])
+            quote_info['content'] = '\n'.join(texts)
+
+        return quote_info
+
     async def get_message(self, incoming_message: dingtalk_stream.chatbot.ChatbotMessage):
         try:
             # print(json.dumps(incoming_message.to_dict(), indent=4, ensure_ascii=False))
@@ -193,6 +275,15 @@ class DingTalkClient:
             elif str(incoming_message.conversation_type) == '2':
                 message_data['conversation_type'] = 'GroupMessage'
 
+            # Check for quoted/replied message
+            raw_data = incoming_message.to_dict()
+            text_data = raw_data.get('text', {})
+            if isinstance(text_data, dict) and text_data.get('isReplyMsg'):
+                replied_msg = text_data.get('repliedMsg', {})
+                if replied_msg:
+                    quote_info = await self._parse_quoted_message(replied_msg)
+                    message_data['QuotedMessage'] = quote_info
+
             if incoming_message.message_type == 'richText':
                 data = incoming_message.rich_text_content.to_dict()
 
@@ -268,19 +359,52 @@ class DingTalkClient:
 
                 message_data['Type'] = 'image'
             elif incoming_message.message_type == 'audio':
-                message_data['Audio'] = await self.get_audio_url(incoming_message.to_dict()['content']['downloadCode'])
+                raw_content = incoming_message.to_dict().get('content', {})
+                # 兼容处理：如果 content 仍为 JSON 字符串则进行解析
+                if isinstance(raw_content, str):
+                    try:
+                        raw_content = json.loads(raw_content)
+                    except (json.JSONDecodeError, TypeError):
+                        raw_content = {}
+
+                if self.logger:
+                    await self.logger.info(f'DingTalk audio raw content: {json.dumps(raw_content, ensure_ascii=False)}')
+
+                # 提取钉钉自带的语音转写文字（Powered by Qwen）
+                recognition = raw_content.get('recognition', '')
+                if recognition:
+                    message_data['Content'] = recognition
+
+                download_code = raw_content.get('downloadCode')
+                if download_code:
+                    message_data['Audio'] = await self.get_audio_url(download_code)
 
                 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()
@@ -357,6 +481,12 @@ class DingTalkClient:
         card_data['config'] = json.dumps({'autoLayout': card_auto_layout})
         card_data['content'] = ''
 
+        # 将用户的消息内容作为卡片的查询参数，方便后续处理
+        if incoming_message.message_type == 'text':
+            card_data['query'] = incoming_message.get_text_list()[0]
+        else:
+            card_data['query'] = '...'
+
         card_instance = dingtalk_stream.AICardReplier(self.client, incoming_message)
         # print(card_instance)
         # 先投放卡片: https://open.dingtalk.com/document/orgapp/create-and-deliver-cards

src/langbot/libs/dingtalk_api/dingtalkevent.py

@@ -47,6 +47,22 @@ class DingTalkEvent(dict):
     def conversation(self):
         return self.get('conversation_type', '')
 
+    @property
+    def quoted_message(self) -> Optional[Dict[str, Any]]:
+        """Get the quoted/replied message info if this is a reply message.
+
+        Returns:
+            A dict containing:
+            - message_id: The original message ID
+            - msg_type: The message type (text, file, picture, audio, etc.)
+            - content: The text content (if any)
+            - file_url: The file download URL (if file type)
+            - file_name: The file name (if file type)
+            - picture: The picture base64 (if picture type)
+            - audio: The audio base64 (if audio type)
+        """
+        return self.get('QuotedMessage')
+
     def __getattr__(self, key: str) -> Optional[Any]:
         """
         允许通过属性访问数据中的任意字段。

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

@@ -1,8 +1,10 @@
+import re
 import time
+import asyncio
 from quart import request
 import httpx
 from quart import Quart
-from typing import Callable, Dict, Any
+from typing import Callable, Dict, Any, Optional
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 from .qqofficialevent import QQOfficialEvent
 import json
@@ -32,6 +34,8 @@ class QQOfficialClient:
         self.access_token = ''
         self.access_token_expiry_time = None
         self.logger = logger
+        self._msg_seq_counter = 0
+        self._token_refresh_task: Optional[asyncio.Task] = None
 
     async def check_access_token(self):
         """检查access_token是否存在"""
@@ -50,18 +54,18 @@ class QQOfficialClient:
             headers = {
                 'content-type': 'application/json',
             }
-            try:
-                response = await client.post(url, json=params, headers=headers)
-                if response.status_code == 200:
-                    response_data = response.json()
-                access_token = response_data.get('access_token')
-                expires_in = int(response_data.get('expires_in', 7200))
-                self.access_token_expiry_time = time.time() + expires_in - 60
-                if access_token:
-                    self.access_token = access_token
-            except Exception as e:
-                await self.logger.error(f'获取access_token失败: {response_data}')
-                raise Exception(f'获取access_token失败: {e}')
+            response = await client.post(url, json=params, headers=headers)
+            if response.status_code != 200:
+                raise Exception(f'Failed to get access_token: HTTP {response.status_code} {response.text}')
+            response_data = response.json()
+            access_token = response_data.get('access_token')
+            expires_in = int(response_data.get('expires_in', 7200))
+            self.access_token_expiry_time = time.time() + expires_in - 60
+            if access_token:
+                self.access_token = access_token
+                await self.logger.info(f'access_token obtained, expires_in={expires_in}s')
+            else:
+                raise Exception('Failed to get access_token: no access_token in response')
 
     async def handle_callback_request(self):
         """处理回调请求（独立端口模式，使用全局 request）"""
@@ -87,10 +91,10 @@ class QQOfficialClient:
         try:
             body = await req.get_data()
 
-            print(f'[QQ Official] Received request, body length: {len(body)}')
+            await self.logger.info(f'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')
+                await self.logger.info('Received empty body, might be health check or GET request')
                 return {'code': 0, 'message': 'ok'}, 200
 
             payload = json.loads(body)
@@ -111,7 +115,6 @@ 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
 
@@ -139,21 +142,24 @@ class QQOfficialClient:
 
     async def get_message(self, msg: dict) -> Dict[str, Any]:
         """获取消息"""
+        d = msg.get('d', {})
+        if not isinstance(d, dict):
+            return {}
         message_data = {
             't': msg.get('t', {}),
-            'user_openid': msg.get('d', {}).get('author', {}).get('user_openid', {}),
-            'timestamp': msg.get('d', {}).get('timestamp', {}),
-            'd_author_id': msg.get('d', {}).get('author', {}).get('id', {}),
-            'content': msg.get('d', {}).get('content', {}),
-            'd_id': msg.get('d', {}).get('id', {}),
+            'user_openid': d.get('author', {}).get('user_openid', {}),
+            'timestamp': d.get('timestamp', {}),
+            'd_author_id': d.get('author', {}).get('id', {}),
+            'content': d.get('content', {}),
+            'd_id': d.get('id', {}),
             'id': msg.get('id', {}),
-            'channel_id': msg.get('d', {}).get('channel_id', {}),
-            'username': msg.get('d', {}).get('author', {}).get('username', {}),
-            'guild_id': msg.get('d', {}).get('guild_id', {}),
-            'member_openid': msg.get('d', {}).get('author', {}).get('openid', {}),
-            'group_openid': msg.get('d', {}).get('group_openid', {}),
+            'channel_id': d.get('channel_id', {}),
+            'username': d.get('author', {}).get('username', {}),
+            'guild_id': d.get('guild_id', {}),
+            'member_openid': d.get('author', {}).get('openid', {}),
+            'group_openid': d.get('group_openid', {}),
         }
-        attachments = msg.get('d', {}).get('attachments', [])
+        attachments = d.get('attachments', [])
         image_attachments = [attachment['url'] for attachment in attachments if await self.is_image(attachment)]
         image_attachments_type = [
             attachment['content_type'] for attachment in attachments if await self.is_image(attachment)
@@ -192,7 +198,7 @@ class QQOfficialClient:
             if response.status_code == 200:
                 return
             else:
-                await self.logger.error(f'发送私聊消息失败: {response_data}')
+                await self.logger.error(f'Failed to send private message: {response_data}')
                 raise ValueError(response)
 
     async def send_group_text_msg(self, group_openid: str, content: str, msg_id: str):
@@ -215,7 +221,7 @@ class QQOfficialClient:
             if response.status_code == 200:
                 return
             else:
-                await self.logger.error(f'发送群聊消息失败:{response.json()}')
+                await self.logger.error(f'Failed to send group message: {response.json()}')
                 raise Exception(response.read().decode())
 
     async def send_channle_group_text_msg(self, channel_id: str, content: str, msg_id: str):
@@ -238,7 +244,7 @@ class QQOfficialClient:
             if response.status_code == 200:
                 return True
             else:
-                await self.logger.error(f'发送频道群聊消息失败: {response.json()}')
+                await self.logger.error(f'Failed to send channel group message: {response.json()}')
                 raise Exception(response)
 
     async def send_channle_private_text_msg(self, guild_id: str, content: str, msg_id: str):
@@ -261,9 +267,224 @@ class QQOfficialClient:
             if response.status_code == 200:
                 return True
             else:
-                await self.logger.error(f'发送频道私聊消息失败: {response.json()}')
+                await self.logger.error(f'Failed to send channel private message: {response.json()}')
                 raise Exception(response)
 
+    # ---- 富媒体消息 ----
+
+    # 媒体文件类型
+    MEDIA_TYPE_IMAGE = 1
+    MEDIA_TYPE_VIDEO = 2
+    MEDIA_TYPE_VOICE = 3
+    MEDIA_TYPE_FILE = 4
+
+    async def upload_media(
+        self,
+        target_type: str,
+        target_id: str,
+        file_type: int,
+        file_url: str = None,
+        file_data: str = None,
+        file_name: str = None,
+    ) -> str:
+        """上传媒体文件，返回 file_info。
+
+        Args:
+            target_type: 'c2c' | 'group'
+            target_id: 用户 openid 或群 openid
+            file_type: 1=图片, 2=视频, 3=语音, 4=文件
+            file_url: 在线 URL（与 file_data 二选一）
+            file_data: base64 编码的文件数据或 data URL（与 file_url 二选一）
+            file_name: 文件名（file_type=4 时必填）
+        """
+        if not await self.check_access_token():
+            await self.get_access_token()
+
+        if target_type == 'c2c':
+            url = f'{self.base_url}/v2/users/{target_id}/files'
+        elif target_type == 'group':
+            url = f'{self.base_url}/v2/groups/{target_id}/files'
+        else:
+            raise ValueError(f'Unsupported target_type: {target_type}')
+
+        body = {
+            'file_type': file_type,
+            'srv_send_msg': False,
+        }
+        if file_url:
+            body['url'] = file_url
+        elif file_data:
+            # 处理 data URL 格式: data:image/png;base64,xxxxx
+            if file_data.startswith('data:'):
+                match = re.match(r'^data:[^;]+;base64,(.+)$', file_data, re.DOTALL)
+                if match:
+                    body['file_data'] = match.group(1)
+                else:
+                    body['file_data'] = file_data
+            else:
+                body['file_data'] = file_data
+        else:
+            raise ValueError('file_url or file_data is required')
+
+        if file_type == self.MEDIA_TYPE_FILE and file_name:
+            body['file_name'] = file_name
+
+        async with httpx.AsyncClient(timeout=120) as client:
+            headers = {
+                'Authorization': f'QQBot {self.access_token}',
+                'Content-Type': 'application/json',
+            }
+            response = await client.post(url, headers=headers, json=body)
+            if response.status_code == 200:
+                data = response.json()
+                file_info = data.get('file_info', '')
+                preview = file_info[:80] + '...' if len(file_info) > 80 else file_info
+                await self.logger.info(f'Upload media success, file_info={preview}')
+                return file_info
+            else:
+                raise Exception(f'Failed to upload media: HTTP {response.status_code} {response.text}')
+
+    async def _send_media_msg(
+        self,
+        target_type: str,
+        target_id: str,
+        file_info: str,
+        msg_id: str = None,
+        content: str = None,
+    ):
+        """发送富媒体消息（msg_type=7）"""
+        if not await self.check_access_token():
+            await self.get_access_token()
+
+        if target_type == 'c2c':
+            url = f'{self.base_url}/v2/users/{target_id}/messages'
+        elif target_type == 'group':
+            url = f'{self.base_url}/v2/groups/{target_id}/messages'
+        else:
+            raise ValueError(f'Unsupported target_type: {target_type}')
+
+        self._msg_seq_counter += 1
+        msg_seq = self._msg_seq_counter
+        body = {
+            'msg_type': 7,
+            'media': {'file_info': file_info},
+            'msg_seq': msg_seq,
+        }
+        if content:
+            body['content'] = content
+        if msg_id:
+            body['msg_id'] = msg_id
+
+        async with httpx.AsyncClient(timeout=120) as client:
+            headers = {
+                'Authorization': f'QQBot {self.access_token}',
+                'Content-Type': 'application/json',
+            }
+            await self.logger.info(f'Sending rich media: {json.dumps(body, ensure_ascii=False)[:200]}')
+            response = await client.post(url, headers=headers, json=body)
+            if response.status_code != 200:
+                raise Exception(f'Failed to send rich media message: HTTP {response.status_code} {response.text}')
+
+    async def send_image_msg(
+        self,
+        target_type: str,
+        target_id: str,
+        file_url: str = None,
+        file_data: str = None,
+        msg_id: str = None,
+        content: str = None,
+    ):
+        """发送图片消息"""
+        file_info = await self.upload_media(
+            target_type,
+            target_id,
+            self.MEDIA_TYPE_IMAGE,
+            file_url=file_url,
+            file_data=file_data,
+        )
+        await self._send_media_msg(target_type, target_id, file_info, msg_id, content)
+
+    async def send_voice_msg(
+        self,
+        target_type: str,
+        target_id: str,
+        file_url: str = None,
+        file_data: str = None,
+        msg_id: str = None,
+    ):
+        """发送语音消息"""
+        file_info = await self.upload_media(
+            target_type,
+            target_id,
+            self.MEDIA_TYPE_VOICE,
+            file_url=file_url,
+            file_data=file_data,
+        )
+        await self._send_media_msg(target_type, target_id, file_info, msg_id)
+
+    async def send_file_msg(
+        self,
+        target_type: str,
+        target_id: str,
+        file_url: str = None,
+        file_data: str = None,
+        file_name: str = None,
+        msg_id: str = None,
+    ):
+        """发送文件消息（含视频）"""
+        file_info = await self.upload_media(
+            target_type,
+            target_id,
+            self.MEDIA_TYPE_FILE,
+            file_url=file_url,
+            file_data=file_data,
+            file_name=file_name,
+        )
+        await self._send_media_msg(target_type, target_id, file_info, msg_id)
+
+    async def send_stream_msg(
+        self,
+        user_openid: str,
+        content: str,
+        event_id: str,
+        msg_id: str,
+        msg_seq: int = 1,
+        index: int = 0,
+        stream_msg_id: str = None,
+        input_state: int = 1,
+    ):
+        """发送流式消息（C2C 私聊）。
+
+        Args:
+            input_state: 1=生成中, 10=生成结束
+        """
+        if not await self.check_access_token():
+            await self.get_access_token()
+
+        url = f'{self.base_url}/v2/users/{user_openid}/stream_messages'
+        body = {
+            'input_mode': 'replace',
+            'input_state': input_state,
+            'content_type': 'markdown',
+            'content_raw': content,
+            'event_id': event_id,
+            'msg_id': msg_id,
+            'msg_seq': msg_seq,
+            'index': index,
+        }
+        if stream_msg_id:
+            body['stream_msg_id'] = stream_msg_id
+
+        async with httpx.AsyncClient(timeout=120) as client:
+            headers = {
+                'Authorization': f'QQBot {self.access_token}',
+                'Content-Type': 'application/json',
+            }
+            response = await client.post(url, headers=headers, json=body)
+            if response.status_code != 200:
+                raise Exception(f'Failed to send stream message: HTTP {response.status_code} {response.text}')
+            return response.json()
+
     async def is_token_expired(self):
         """检查token是否过期"""
         if self.access_token_expiry_time is None:
@@ -292,3 +513,325 @@ class QQOfficialClient:
             'signature': signature,
         }
         return response
+
+    # ---- WebSocket Gateway ----
+    # Reference: https://bot.q.qq.com/wiki/develop/api-v2/dev-prepare/interface-framework/event-emit.html
+
+    INTENT_GUILDS = 1 << 0
+    INTENT_GUILD_MEMBERS = 1 << 1
+    INTENT_PUBLIC_GUILD_MESSAGES = 1 << 30
+    INTENT_DIRECT_MESSAGE = 1 << 12
+    INTENT_GROUP_AND_C2C = 1 << 25
+    INTENT_INTERACTION = 1 << 26
+
+    FULL_INTENTS = (
+        INTENT_GUILDS
+        | INTENT_GUILD_MEMBERS
+        | INTENT_PUBLIC_GUILD_MESSAGES
+        | INTENT_DIRECT_MESSAGE
+        | INTENT_GROUP_AND_C2C
+        | INTENT_INTERACTION
+    )
+
+    async def get_gateway_url(self) -> str:
+        """获取 WebSocket 网关地址"""
+        if not await self.check_access_token():
+            await self.get_access_token()
+
+        url = f'{self.base_url}/gateway'
+        async with httpx.AsyncClient() as client:
+            headers = {
+                'Authorization': f'QQBot {self.access_token}',
+            }
+            response = await client.get(url, headers=headers)
+            if response.status_code == 200:
+                data = response.json()
+                ws_url = data.get('url', '')
+                if not ws_url:
+                    raise Exception('Gateway URL is empty')
+                return ws_url
+            else:
+                raise Exception(f'Failed to get Gateway URL: HTTP {response.status_code} {response.text}')
+
+    async def _background_token_refresh(self):
+        """在 token 到期前主动刷新"""
+        try:
+            while True:
+                if self.access_token_expiry_time:
+                    remain = self.access_token_expiry_time - time.time()
+                    if remain > 120:
+                        await asyncio.sleep(remain - 60)
+                        continue
+                self.access_token = ''
+                self.access_token_expiry_time = None
+                if await self.check_access_token():
+                    await asyncio.sleep(60)
+                else:
+                    await self.get_access_token()
+                    await asyncio.sleep(60)
+        except asyncio.CancelledError:
+            pass
+
+    async def connect_gateway(
+        self,
+        on_event: Callable[[str, dict], Any],
+        on_ready: Optional[Callable[[], Any]] = None,
+        on_error: Optional[Callable[[Exception], Any]] = None,
+    ):
+        """WebSocket 网关连接，含重连逻辑。持续重连直到达到最大次数或被取消。
+
+        Args:
+            on_event: 收到 op=0 Dispatch 事件时的回调，参数为 (event_type, event_data)
+            on_ready: 连接就绪 (收到 READY) 时的回调
+            on_error: 发生错误时的回调
+        """
+        import websockets
+
+        session_id = ''
+        last_seq = 0
+        reconnect_attempts = 0
+        max_reconnect_attempts = 100
+        backoff_delays = [1, 2, 5, 10, 30, 60]
+        rate_limit_delay = 60
+
+        # Cancel previous token refresh task if any
+        if self._token_refresh_task and not self._token_refresh_task.done():
+            self._token_refresh_task.cancel()
+            try:
+                await self._token_refresh_task
+            except asyncio.CancelledError:
+                pass
+            self._token_refresh_task = None
+
+        while reconnect_attempts <= max_reconnect_attempts:
+            heartbeat_interval = 45000
+            should_refresh_token = False
+            ws = None
+            heartbeat_task = None
+
+            # Refresh token if needed
+            if should_refresh_token:
+                self.access_token = ''
+                self.access_token_expiry_time = None
+
+            try:
+                ws_url = await self.get_gateway_url()
+                await self.logger.info(f'Gateway URL obtained: {ws_url[:60]}...')
+            except Exception as e:
+                error_msg = str(e)
+                await self.logger.error(f'Failed to get gateway URL: {e}')
+                reconnect_attempts += 1
+                if '100017' in error_msg or '频率' in error_msg or 'Too many' in error_msg:
+                    delay = rate_limit_delay
+                else:
+                    delay = backoff_delays[min(reconnect_attempts - 1, len(backoff_delays) - 1)]
+                await self.logger.info(f'Reconnecting in {delay}s (attempt {reconnect_attempts})')
+                await asyncio.sleep(delay)
+                continue
+
+            try:
+                await self.logger.info('Connecting to WebSocket gateway...')
+                ws = await websockets.connect(ws_url)
+                await self.logger.info('WebSocket connected')
+            except Exception as e:
+                await self.logger.error(f'WebSocket connection failed: {e}')
+                reconnect_attempts += 1
+                delay = backoff_delays[min(reconnect_attempts - 1, len(backoff_delays) - 1)]
+                await self.logger.info(f'Reconnecting in {delay}s (attempt {reconnect_attempts})')
+                await asyncio.sleep(delay)
+                continue
+
+            try:
+                async for raw_msg in ws:
+                    try:
+                        payload = json.loads(raw_msg)
+                    except json.JSONDecodeError:
+                        await self.logger.error(f'Failed to parse message: {raw_msg}')
+                        continue
+
+                    op = payload.get('op')
+                    d = payload.get('d', {})
+                    s = payload.get('s')
+                    t = payload.get('t')
+
+                    if not isinstance(d, dict):
+                        d = {}
+
+                    if op == 10:  # Hello
+                        heartbeat_interval = d.get('heartbeat_interval', 45000)
+                        await self.logger.info(f'Received Hello, heartbeat_interval={heartbeat_interval}ms')
+
+                        # Send Identify or Resume
+                        if session_id and last_seq > 0:
+                            resume_payload = {
+                                'op': 6,
+                                'd': {
+                                    'token': f'QQBot {self.access_token}',
+                                    'session_id': session_id,
+                                    'seq': last_seq,
+                                },
+                            }
+                            await ws.send(json.dumps(resume_payload))
+                            await self.logger.info(f'Sent Resume, session_id={session_id}, seq={last_seq}')
+                        else:
+                            identify_payload = {
+                                'op': 2,
+                                'd': {
+                                    'token': f'QQBot {self.access_token}',
+                                    'intents': self.FULL_INTENTS,
+                                    'shard': [0, 1],
+                                },
+                            }
+                            await ws.send(json.dumps(identify_payload))
+                            await self.logger.info(f'Sent Identify, intents={self.FULL_INTENTS}')
+
+                        # Start heartbeat
+                        async def _heartbeat_loop(conn, interval_ms):
+                            interval_sec = interval_ms / 1000.0
+                            try:
+                                while True:
+                                    await asyncio.sleep(interval_sec)
+                                    try:
+                                        hb_payload = {'op': 1, 'd': last_seq}
+                                        await conn.send(json.dumps(hb_payload))
+                                    except Exception:
+                                        break
+                            except asyncio.CancelledError:
+                                pass
+
+                        heartbeat_task = asyncio.create_task(_heartbeat_loop(ws, heartbeat_interval))
+
+                    elif op == 0:  # Dispatch
+                        if s is not None:
+                            last_seq = s
+
+                        if t == 'READY':
+                            session_id = d.get('session_id', '')
+                            reconnect_attempts = 0
+                            await self.logger.info(f'READY, session_id={session_id}')
+                            if on_ready:
+                                try:
+                                    result = on_ready()
+                                    if asyncio.iscoroutine(result):
+                                        await result
+                                except Exception:
+                                    pass
+                            # Track token refresh task to avoid leaks
+                            if self._token_refresh_task and not self._token_refresh_task.done():
+                                self._token_refresh_task.cancel()
+                                try:
+                                    await self._token_refresh_task
+                                except asyncio.CancelledError:
+                                    pass
+                            self._token_refresh_task = asyncio.create_task(self._background_token_refresh())
+
+                        elif t == 'RESUMED':
+                            reconnect_attempts = 0
+                            await self.logger.info('RESUMED')
+
+                        else:
+                            await self.logger.debug(f'Received event: {t}, seq={s}')
+                            if on_event:
+                                try:
+                                    result = on_event(t, d)
+                                    if asyncio.iscoroutine(result):
+                                        await result
+                                except Exception:
+                                    await self.logger.error(f'Error handling event {t}: {traceback.format_exc()}')
+
+                    elif op == 11:  # Heartbeat ACK
+                        pass
+
+                    elif op == 7:  # Reconnect
+                        await self.logger.info('Received Reconnect directive')
+                        break
+
+                    elif op == 9:  # Invalid Session
+                        can_resume = d.get('can_resume', False)
+                        await self.logger.warning(f'Invalid Session, can_resume={can_resume}')
+                        if not can_resume:
+                            session_id = ''
+                            last_seq = 0
+                            should_refresh_token = True
+                        break
+
+                # Connection closed normally (end of async for)
+                try:
+                    close_code = ws.close_code
+                    close_reason = ws.close_reason or ''
+                except Exception:
+                    close_code = None
+                    close_reason = ''
+                await self.logger.info(f'Connection closed, code={close_code}, reason={close_reason}')
+
+                if close_code == 4004:
+                    should_refresh_token = True
+                elif close_code in (4006, 4007, 4009):
+                    session_id = ''
+                    last_seq = 0
+                    should_refresh_token = True
+                elif close_code == 4008:
+                    reconnect_attempts += 1
+                    delay = rate_limit_delay
+                    await self.logger.info(
+                        f'Rate limited, waiting {delay}s before reconnect (attempt {reconnect_attempts})'
+                    )
+                    await asyncio.sleep(delay)
+                    continue
+                elif close_code in (4914, 4915):
+                    err = Exception(f'Bot disconnected/banned (close_code={close_code})')
+                    if on_error:
+                        await self._safe_callback(on_error, err)
+                    return
+                elif close_code in (4900, 4901, 4902, 4903, 4904, 4905, 4906, 4907, 4908, 4909, 4910, 4911, 4912, 4913):
+                    session_id = ''
+                    last_seq = 0
+
+                if close_code == 1000:
+                    return
+
+            except asyncio.CancelledError:
+                raise
+            except Exception:
+                await self.logger.error(f'Unexpected error in WebSocket loop: {traceback.format_exc()}')
+            finally:
+                if heartbeat_task:
+                    heartbeat_task.cancel()
+                    try:
+                        await heartbeat_task
+                    except asyncio.CancelledError:
+                        pass
+                if ws:
+                    try:
+                        await ws.close()
+                    except Exception:
+                        pass
+
+            # If we reach here, we need to reconnect
+            reconnect_attempts += 1
+            if reconnect_attempts > max_reconnect_attempts:
+                await self.logger.error(f'Max reconnect attempts ({max_reconnect_attempts}) reached, stopping')
+                if on_error:
+                    await self._safe_callback(on_error, Exception('Max reconnect attempts reached'))
+                return
+            delay = backoff_delays[min(reconnect_attempts - 1, len(backoff_delays) - 1)]
+            await self.logger.info(f'Reconnecting in {delay}s (attempt {reconnect_attempts})')
+            await asyncio.sleep(delay)
+
+    async def _safe_callback(self, callback, *args):
+        """Safely invoke a callback, handling both sync and async functions."""
+        try:
+            result = callback(*args)
+            if asyncio.iscoroutine(result):
+                await result
+        except Exception:
+            pass
+
+    async def connect_gateway_loop(
+        self,
+        on_event: Callable[[str, dict], Any],
+        on_ready: Optional[Callable[[], Any]] = None,
+        on_error: Optional[Callable[[Exception], Any]] = None,
+    ):
+        """持续重连的网关循环。"""
+        await self.connect_gateway(on_event, on_ready, on_error)

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
@@ -63,16 +64,25 @@ class StreamSession:
     # 缓存最近一次片段，处理重试或超时兜底
     last_chunk: Optional[StreamChunk] = None
 
+    # 反馈 ID，用于接收用户点赞/点踩反馈
+    feedback_id: Optional[str] = None
+
 
 class StreamSessionManager:
     """管理 stream 会话的生命周期，并负责队列的生产消费。"""
 
+    # Sessions with registered feedback_ids use a longer TTL to survive the
+    # full like → cancel → dislike feedback flow. Must align with the adapter's
+    # _stream_to_monitoring_msg TTL (wecombot.py).
+    _FEEDBACK_SESSION_TTL = 600  # 10 minutes
+
     def __init__(self, logger: EventLogger, ttl: int = 60) -> None:
         self.logger = logger
 
         self.ttl = ttl  # 超时时间（秒），超过该时间未被访问的会话会被清理由 cleanup
         self._sessions: dict[str, StreamSession] = {}  # stream_id -> StreamSession 映射
         self._msg_index: dict[str, str] = {}  # msgid -> stream_id 映射，便于流水线根据消息 ID 找到会话
+        self._feedback_index: dict[str, str] = {}  # feedback_id -> stream_id 映射
 
     def get_stream_id_by_msg(self, msg_id: str) -> Optional[str]:
         if not msg_id:
@@ -82,6 +92,32 @@ class StreamSessionManager:
     def get_session(self, stream_id: str) -> Optional[StreamSession]:
         return self._sessions.get(stream_id)
 
+    def get_session_by_feedback_id(self, feedback_id: str) -> Optional[StreamSession]:
+        """根据 feedback_id 查找会话。
+
+        Args:
+            feedback_id: 企业微信反馈事件中的反馈 ID。
+
+        Returns:
+            Optional[StreamSession]: 找到的会话实例，未找到返回 None。
+        """
+        if not feedback_id:
+            return None
+        stream_id = self._feedback_index.get(feedback_id)
+        if stream_id:
+            return self._sessions.get(stream_id)
+        return None
+
+    def register_feedback_id(self, stream_id: str, feedback_id: str) -> None:
+        """注册 feedback_id 与 stream_id 的映射。
+
+        Args:
+            stream_id: 企业微信流式会话 ID。
+            feedback_id: 反馈 ID。
+        """
+        if feedback_id and stream_id:
+            self._feedback_index[feedback_id] = stream_id
+
     def create_or_get(self, msg_json: dict[str, Any]) -> tuple[StreamSession, bool]:
         """根据企业微信回调创建或获取会话。
 
@@ -183,11 +219,17 @@ class StreamSessionManager:
             session.last_access = time.time()
 
     def cleanup(self) -> None:
-        """定期清理过期会话，防止队列与映射无上限累积。"""
+        """定期清理过期会话，防止队列与映射无上限累积。
+
+        已注册 feedback_id 的会话使用更长的 TTL，确保用户在点赞/取消/点踩流程中
+        不会因为 session 被提前清除而丢失上下文信息。
+        """
         now = time.time()
         expired: list[str] = []
         for stream_id, session in self._sessions.items():
-            if now - session.last_access > self.ttl:
+            # Sessions with registered feedback_ids use a longer TTL
+            effective_ttl = self._FEEDBACK_SESSION_TTL if session.feedback_id else self.ttl
+            if now - session.last_access > effective_ttl:
                 expired.append(stream_id)
 
         for stream_id in expired:
@@ -197,6 +239,488 @@ class StreamSessionManager:
             msg_id = session.msg_id
             if msg_id and self._msg_index.get(msg_id) == stream_id:
                 self._msg_index.pop(msg_id, None)
+            # Clean up feedback index for expired sessions
+            if session.feedback_id:
+                self._feedback_index.pop(session.feedback_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
+        # 应为需要解密，但是目前暂时不能下载到内部进行解密，所以先将下载链接拼接aeskey返回给用户，由插件去处理该链接的下载和解密逻辑
+        video_data['download_url'] = download_url + f'?aeskey={per_msg_aeskey}'
+        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
+
+        # 应为需要解密，但是目前暂时不能下载到内部进行解密，所以先将下载链接拼接aeskey返回给用户，由插件去处理该链接的下载和解密逻辑
+        file_data['download_url'] = download_url + f'?aeskey={per_msg_aeskey}'
+        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', '')
+
+    # Handle quote (referenced message) - important for group chat file references
+    quote_info = msg_json.get('quote')
+    if quote_info:
+        quote_data: dict[str, Any] = {}
+        quote_type = quote_info.get('msgtype', '')
+        quote_data['msgtype'] = quote_type
+
+        if quote_type == 'text':
+            quote_data['content'] = quote_info.get('text', {}).get('content', '')
+        elif quote_type == 'image':
+            img_info = quote_info.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:
+                quote_data['picurl'] = base64_data
+                quote_data['images'] = [base64_data]
+        elif quote_type == 'file':
+            file_info = quote_info.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,
+            }
+            # Same as private chat: append aeskey to download_url for plugin processing
+            if download_url and item_aeskey:
+                file_data['download_url'] = download_url + f'?aeskey={item_aeskey}'
+            quote_data['file'] = file_data
+        elif quote_type == 'voice':
+            voice_info = quote_info.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'):
+                quote_data['content'] = voice_info.get('content')
+            # Same as private chat: append aeskey to url for plugin processing
+            if download_url and item_aeskey:
+                voice_data['url'] = download_url + f'?aeskey={item_aeskey}'
+            quote_data['voice'] = voice_data
+        elif quote_type == 'video':
+            video_info = quote_info.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'),
+            }
+            # Same as private chat: append aeskey to download_url for plugin processing
+            if download_url and item_aeskey:
+                video_data['download_url'] = download_url + f'?aeskey={item_aeskey}'
+            quote_data['video'] = video_data
+        elif quote_type == 'link':
+            quote_data['link'] = quote_info.get('link', {})
+            link = quote_data['link']
+            title = link.get('title', '')
+            desc = link.get('description') or link.get('digest', '')
+            quote_data['content'] = '\n'.join(filter(None, [title, desc]))
+        elif quote_type == 'mixed':
+            # Handle mixed type in quote (text + images + files etc.)
+            items = quote_info.get('mixed', {}).get('msg_item', [])
+            texts = []
+            images = []
+            files = []
+            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,
+                    }
+                    # Same as private chat: append aeskey to download_url for plugin processing
+                    if download_url and item_aeskey:
+                        file_data['download_url'] = download_url + f'?aeskey={item_aeskey}'
+                    files.append(file_data)
+            if texts:
+                quote_data['content'] = ' '.join(texts)
+            if images:
+                quote_data['images'] = images
+                quote_data['picurl'] = images[0]
+            if files:
+                quote_data['files'] = files
+                quote_data['file'] = files[0]
+
+        message_data['quote'] = quote_data
+
+    return message_data
 
 
 class WecomBotClient:
@@ -236,14 +760,27 @@ class WecomBotClient:
         self.stream_sessions = StreamSessionManager(logger=logger)
         self.stream_poll_timeout = 0.5
 
+        self._feedback_callback: Optional[Callable] = None
+
+    def set_feedback_callback(self, callback: Callable) -> None:
+        """设置反馈回调函数。
+
+        Args:
+            callback: 反馈回调函数，签名: async def callback(feedback_id, feedback_type, feedback_content, inaccurate_reasons, session)
+        """
+        self._feedback_callback = callback
+
     @staticmethod
-    def _build_stream_payload(stream_id: str, content: str, finish: bool) -> dict[str, Any]:
+    def _build_stream_payload(
+        stream_id: str, content: str, finish: bool, feedback_id: Optional[str] = None
+    ) -> dict[str, Any]:
         """按照企业微信协议拼装返回报文。
 
         Args:
             stream_id: 企业微信会话 ID。
             content: 推送的文本内容。
             finish: 是否为最终片段。
+            feedback_id: 反馈 ID，用于接收用户点赞/点踩反馈。
 
         Returns:
             dict[str, Any]: 可直接加密返回的 payload。
@@ -251,13 +788,16 @@ class WecomBotClient:
         Example:
             组装 `{'msgtype': 'stream', 'stream': {'id': 'sid', ...}}` 结构。
         """
+        stream_payload = {
+            'id': stream_id,
+            'finish': finish,
+            'content': content,
+        }
+        if feedback_id:
+            stream_payload['feedback'] = {'id': feedback_id}
         return {
             'msgtype': 'stream',
-            'stream': {
-                'id': stream_id,
-                'finish': finish,
-                'content': content,
-            },
+            'stream': stream_payload,
         }
 
     async def _encrypt_and_reply(self, payload: dict[str, Any], nonce: str) -> tuple[Response, int]:
@@ -313,9 +853,14 @@ class WecomBotClient:
         """
         session, is_new = self.stream_sessions.create_or_get(msg_json)
 
+        feedback_id = str(uuid.uuid4())
+        session.feedback_id = feedback_id
+        self.stream_sessions.register_feedback_id(session.stream_id, feedback_id)
+
         message_data = await self.get_message(msg_json)
         if message_data:
             message_data['stream_id'] = session.stream_id
+            message_data['feedback_id'] = feedback_id
             try:
                 event = wecombotevent.WecomBotEvent(message_data)
             except Exception:
@@ -324,7 +869,7 @@ class WecomBotClient:
                 if is_new:
                     asyncio.create_task(self._dispatch_event(event))
 
-        payload = self._build_stream_payload(session.stream_id, '', False)
+        payload = self._build_stream_payload(session.stream_id, '', False, feedback_id)
         return await self._encrypt_and_reply(payload, nonce)
 
     async def _handle_post_followup_response(self, msg_json: dict[str, Any], nonce: str) -> tuple[Response, int]:
@@ -449,202 +994,83 @@ class WecomBotClient:
 
         msg_json = json.loads(decrypted_xml)
 
+        event = msg_json.get('event', {})
+        event_type = event.get('eventtype', '')
+
+        if event_type == 'feedback_event':
+            return await self._handle_feedback_event(msg_json, nonce)
+
         if msg_json.get('msgtype') == 'stream':
             return await self._handle_post_followup_response(msg_json, nonce)
 
         return await self._handle_post_initial_response(msg_json, nonce)
 
-    async def get_message(self, msg_json):
-        message_data = {}
+    async def _handle_feedback_event(self, msg_json: dict[str, Any], nonce: str) -> tuple[Response, int]:
+        """处理企业微信用户反馈事件（点赞/点踩）。
 
-        msg_type = msg_json.get('msgtype', '')
-        if msg_type:
-            message_data['msgtype'] = msg_type
+        Args:
+            msg_json: 解密后的企业微信反馈事件 JSON。
+            nonce: 企业微信回调参数 nonce。
 
-        if msg_json.get('chattype', '') == 'single':
-            message_data['type'] = 'single'
-        elif msg_json.get('chattype', '') == 'group':
-            message_data['type'] = 'group'
+        Returns:
+            Tuple[Response, int]: Quart Response 及状态码。
 
-        max_inline_file_size = 5 * 1024 * 1024  # avoid decoding very large payloads by default
+        Note:
+            企业微信协议要求：反馈事件目前仅支持回复空包。
+        """
+        try:
+            feedback_event = msg_json.get('event', {}).get('feedback_event', {})
+            feedback_id = feedback_event.get('id', '')
+            feedback_type = feedback_event.get('type', 0)
+            feedback_content = feedback_event.get('content', '')
+            inaccurate_reasons = feedback_event.get('inaccurate_reason_list', [])
 
-        async def _safe_download(url: str):
-            if not url:
-                return None
-            return await self.download_url_to_base64(url, self.EnCodingAESKey)
-
-        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', ''
+            await self.logger.info(
+                f'收到用户反馈事件: feedback_id={feedback_id}, type={feedback_type}, '
+                f'content={feedback_content}, reasons={inaccurate_reasons}'
             )
-        elif msg_type == 'image':
-            picurl = msg_json.get('image', {}).get('url', '')
-            base64_data = await _safe_download(picurl)
-            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')
-            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'),
-            }
-            # 企业微信智能转写文本（如果已有）直接复用，避免重复转写
-            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(download_url)
-                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')
-            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(download_url)
-                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')
-            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_base64 = await _safe_download(download_url)
-                if file_base64:
-                    file_data['base64'] = file_base64
-            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_url = item.get('image', {}).get('url')
-                    base64_data = await _safe_download(img_url)
-                    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')
-                    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_base64 = await _safe_download(download_url)
-                        if file_base64:
-                            file_data['base64'] = file_base64
-                    files.append(file_data)
-                elif item_type == 'voice':
-                    voice_info = item.get('voice', {}) or {}
-                    download_url = voice_info.get('url')
-                    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(download_url)
-                        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')
-                    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(download_url)
-                        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)  # 拼接所有 text
-            if images:
-                message_data['images'] = images
-                message_data['picurl'] = images[0]  # 只保留第一个 image
-            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
+            session = self.stream_sessions.get_session_by_feedback_id(feedback_id)
 
-        # 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', '')
-        )
+            if session:
+                await self.logger.info(
+                    f'反馈关联到会话: stream_id={session.stream_id}, msg_id={session.msg_id}, user_id={session.user_id}'
+                )
+            else:
+                await self.logger.warning(f'未找到 feedback_id={feedback_id} 对应的会话，仍将记录反馈')
 
-        # 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', '')
+            # Dispatch feedback event regardless of session availability
+            for handler in self._message_handlers.get('feedback', []):
+                try:
+                    await handler(
+                        feedback_id=feedback_id,
+                        feedback_type=feedback_type,
+                        feedback_content=feedback_content,
+                        inaccurate_reasons=inaccurate_reasons,
+                        session=session,
+                    )
+                except Exception:
+                    await self.logger.error(traceback.format_exc())
 
-        message_data['msgid'] = msg_json.get('msgid', '')
+            if self._feedback_callback:
+                try:
+                    await self._feedback_callback(
+                        feedback_id=feedback_id,
+                        feedback_type=feedback_type,
+                        feedback_content=feedback_content,
+                        inaccurate_reasons=inaccurate_reasons,
+                        session=session,
+                    )
+                except Exception:
+                    await self.logger.error(traceback.format_exc())
 
-        if msg_json.get('aibotid'):
-            message_data['aibotid'] = msg_json.get('aibotid', '')
+        except Exception:
+            await self.logger.error(traceback.format_exc())
 
-        return message_data
+        return await self._encrypt_and_reply({}, nonce)
+
+    async def get_message(self, msg_json):
+        return await parse_wecom_bot_message(msg_json, self.EnCodingAESKey, self.logger)
 
     async def _handle_message(self, event: wecombotevent.WecomBotEvent):
         """
@@ -711,40 +1137,20 @@ class WecomBotClient:
 
         return decorator
 
+    def on_feedback(self):
+        def decorator(func: Callable):
+            if 'feedback' not in self._message_handlers:
+                self._message_handlers['feedback'] = []
+            self._message_handlers['feedback'].append(func)
+            return func
+
+        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

@@ -133,3 +133,24 @@ class WecomBotEvent(dict):
         AI Bot ID
         """
         return self.get('aibotid', '')
+
+    @property
+    def feedback_id(self) -> str:
+        """
+        反馈 ID，用于关联用户点赞/点踩反馈
+        """
+        return self.get('feedback_id', '')
+
+    @property
+    def stream_id(self) -> str:
+        """
+        流式消息 ID
+        """
+        return self.get('stream_id', '')
+
+    @property
+    def quote(self):
+        """
+        引用消息信息（群聊中用户引用其他消息时返回）
+        """
+        return self.get('quote', {})

src/langbot/libs/wecom_ai_bot_api/ws_client.py

@@ -0,0 +1,683 @@
+"""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, StreamSession
+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
+        # Stream session info for feedback tracking
+        self._stream_sessions: dict[str, dict] = {}  # msg_id -> session info
+        # Feedback tracking: feedback_id -> session info
+        self._feedback_sessions: dict[str, dict] = {}  # feedback_id -> {msg_id, user_id, chat_id, stream_id, req_id}
+        # msg_id -> feedback_id (for associating feedback with message)
+        self._msg_feedback_ids: dict[str, str] = {}  # msg_id -> feedback_id
+
+    # ── 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
+
+    def on_feedback(self) -> Callable:
+        """Decorator to register a feedback event handler.
+
+        Same interface as WecomBotClient.on_feedback for compatibility.
+        """
+
+        def decorator(func: Callable):
+            if 'feedback' not in self._message_handlers:
+                self._message_handlers['feedback'] = []
+            self._message_handlers['feedback'].append(func)
+            return func
+
+        return decorator
+
+    async def reply_stream(
+        self,
+        req_id: str,
+        stream_id: str,
+        content: str,
+        finish: bool = False,
+        feedback_id: str = '',
+    ) -> 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.
+            feedback_id: Optional feedback ID for receiving user feedback (like/dislike).
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        stream_payload = {
+            'id': stream_id,
+            'finish': finish,
+            'content': content,
+        }
+        if feedback_id:
+            stream_payload['feedback'] = {'id': feedback_id}
+
+        body = {
+            'msgtype': 'stream',
+            'stream': stream_payload,
+        }
+        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
+
+            # Generate feedback_id for final chunk
+            feedback_id = ''
+            if is_final:
+                feedback_id = _generate_req_id('feedback')
+                self._msg_feedback_ids[msg_id] = feedback_id
+                # Store session info for feedback tracking
+                session_info = self._stream_sessions.get(msg_id)
+                if session_info:
+                    self._feedback_sessions[feedback_id] = session_info
+
+            await self.reply_stream(req_id, stream_id, content, finish=is_final, feedback_id=feedback_id)
+            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)
+                self._stream_sessions.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}'
+                # Store session info for feedback tracking
+                self._stream_sessions[msg_id] = {
+                    'req_id': req_id,
+                    'stream_id': stream_id,
+                    'msg_id': msg_id,
+                    'user_id': message_data.get('userid', ''),
+                    'chat_id': message_data.get('chatid', ''),
+                    'chat_type': message_data.get('type', 'single'),
+                }
+            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, feedback_event, disconnected_event)."""
+        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', '')
+
+            if event_type == 'feedback_event':
+                feedback_event = event_info.get('feedback_event', {})
+                feedback_id = feedback_event.get('id', '')
+                feedback_type = feedback_event.get('type', 0)
+                feedback_content = feedback_event.get('content', '')
+                inaccurate_reasons = feedback_event.get('inaccurate_reason_list', [])
+
+                await self.logger.info(
+                    f'收到用户反馈事件: feedback_id={feedback_id}, type={feedback_type}, '
+                    f'content={feedback_content}, reasons={inaccurate_reasons}'
+                )
+
+                # Look up session by feedback_id
+                session_info = self._feedback_sessions.get(feedback_id)
+                session = None
+                if session_info:
+                    session = StreamSession(
+                        stream_id=session_info.get('stream_id', ''),
+                        msg_id=session_info.get('msg_id', ''),
+                        chat_id=session_info.get('chat_id') or None,
+                        user_id=session_info.get('user_id') or None,
+                        feedback_id=feedback_id,
+                    )
+                    await self.logger.info(
+                        f'反馈关联到会话: stream_id={session.stream_id}, msg_id={session.msg_id}, user_id={session.user_id}'
+                    )
+                else:
+                    await self.logger.warning(f'未找到 feedback_id={feedback_id} 对应的会话')
+
+                for handler in self._message_handlers.get('feedback', []):
+                    try:
+                        await handler(
+                            feedback_id=feedback_id,
+                            feedback_type=feedback_type,
+                            feedback_content=feedback_content,
+                            inaccurate_reasons=inaccurate_reasons,
+                            session=session,
+                        )
+                    except Exception:
+                        await self.logger.error(f'Error in feedback handler: {traceback.format_exc()}')
+                return
+
+            event = wecombotevent.WecomBotEvent(message_data)
+
+            if event_type in self._message_handlers:
+                for handler in self._message_handlers[event_type]:
+                    await handler(event)
+
+            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
@@ -67,6 +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)

src/langbot/libs/wecom_customer_service_api/api.py

@@ -10,6 +10,7 @@ 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:
@@ -34,6 +35,10 @@ class WecomCSClient:
         self.unified_mode = unified_mode
         self.app = Quart(__name__)
 
+        # 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(
@@ -378,3 +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):

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

@@ -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')
@@ -39,7 +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)
@@ -65,8 +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,
@@ -90,5 +97,13 @@ class KnowledgeBaseRouterGroup(group.RouterGroup):
         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/external.py

@@ -1,61 +0,0 @@
-import quart
-from ... import group
-
-
-@group.group_class('external_knowledge_base', '/api/v1/knowledge/external-bases')
-class ExternalKnowledgeBaseRouterGroup(group.RouterGroup):
-    async def initialize(self) -> None:
-        @self.route('/retrievers', methods=['GET'])
-        async def list_knowledge_retrievers() -> quart.Response:
-            """List all available knowledge retrievers from plugins."""
-            retrievers = await self.ap.plugin_connector.list_knowledge_retrievers()
-            return self.success(data={'retrievers': retrievers})
-
-        @self.route('', methods=['POST', 'GET'])
-        async def handle_external_knowledge_bases() -> quart.Response:
-            if quart.request.method == 'GET':
-                external_kbs = await self.ap.external_kb_service.get_external_knowledge_bases()
-                return self.success(data={'bases': external_kbs})
-
-            elif quart.request.method == 'POST':
-                json_data = await quart.request.json
-                kb_uuid = await self.ap.external_kb_service.create_external_knowledge_base(json_data)
-                return self.success(data={'uuid': kb_uuid})
-
-            return self.http_status(405, -1, 'Method not allowed')
-
-        @self.route(
-            '/<kb_uuid>',
-            methods=['GET', 'DELETE', 'PUT'],
-        )
-        async def handle_specific_external_knowledge_base(kb_uuid: str) -> quart.Response:
-            if quart.request.method == 'GET':
-                external_kb = await self.ap.external_kb_service.get_external_knowledge_base(kb_uuid)
-
-                if external_kb is None:
-                    return self.http_status(404, -1, 'external knowledge base not found')
-
-                return self.success(
-                    data={
-                        'base': external_kb,
-                    }
-                )
-
-            elif quart.request.method == 'PUT':
-                json_data = await quart.request.json
-                await self.ap.external_kb_service.update_external_knowledge_base(kb_uuid, json_data)
-                return self.success({})
-
-            elif quart.request.method == 'DELETE':
-                await self.ap.external_kb_service.delete_external_knowledge_base(kb_uuid)
-                return self.success({})
-
-        @self.route(
-            '/<kb_uuid>/retrieve',
-            methods=['POST'],
-        )
-        async def retrieve_external_knowledge_base(kb_uuid: str) -> str:
-            json_data = await quart.request.json
-            query = json_data.get('query')
-            results = await self.ap.external_kb_service.retrieve_external_knowledge_base(kb_uuid, query)
-            return self.success(data={'results': results})

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

@@ -52,6 +52,7 @@ class MonitoringRouterGroup(group.RouterGroup):
             # 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))
@@ -64,6 +65,7 @@ class MonitoringRouterGroup(group.RouterGroup):
             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,
@@ -323,3 +325,249 @@ class MonitoringRouterGroup(group.RouterGroup):
                 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',
+                ]
+            elif export_type == 'feedback':
+                data = await self.ap.monitoring_service.export_feedback(
+                    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',
+                    'feedback_id',
+                    'feedback_type',
+                    'feedback_content',
+                    'inaccurate_reasons',
+                    'bot_id',
+                    'bot_name',
+                    'pipeline_id',
+                    'pipeline_name',
+                    'session_id',
+                    'message_id',
+                    'stream_id',
+                    'user_id',
+                    'platform',
+                ]
+            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
+
+        @self.route('/feedback/stats', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_feedback_stats() -> str:
+            """Get feedback statistics"""
+            # 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)
+
+            stats = await self.ap.monitoring_service.get_feedback_stats(
+                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=stats)
+
+        @self.route('/feedback', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_feedback() -> str:
+            """Get feedback list"""
+            # Parse query parameters
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            feedback_type_str = quart.request.args.get('feedbackType')
+            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)
+
+            # Parse feedback type
+            feedback_type = int(feedback_type_str) if feedback_type_str else None
+
+            feedback_list, total = await self.ap.monitoring_service.get_feedback_list(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                feedback_type=feedback_type,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'feedback': feedback_list,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )

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

@@ -0,0 +1,384 @@
+"""Embed widget routes - serve embeddable chat widget for external websites.
+
+All user-facing URLs are keyed by **bot_uuid** (not pipeline_uuid) so that
+internal pipeline identifiers are never exposed to end-users.  Each handler
+resolves the bot_uuid to the owning ``web_page_bot`` RuntimeBot and extracts
+the bound pipeline_uuid for internal routing.
+"""
+
+import asyncio
+import datetime
+import json
+import logging
+import uuid
+import hmac
+import hashlib
+import time
+import re
+import httpx
+
+import quart
+
+from ... import group
+from ......utils import paths
+from ......platform.sources.websocket_manager import ws_connection_manager
+
+logger = logging.getLogger(__name__)
+
+# Cache the widget template content
+_widget_template_cache: str | None = None
+_logo_bytes_cache: bytes | None = None
+
+
+def _is_valid_uuid(s: str) -> bool:
+    return bool(re.match(r'^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$', s))
+
+
+def _get_widget_template() -> str:
+    """Load and cache the widget JS template."""
+    global _widget_template_cache
+    if _widget_template_cache is None:
+        template_path = paths.get_resource_path('templates/embed/widget.js')
+        with open(template_path, 'r', encoding='utf-8') as f:
+            _widget_template_cache = f.read()
+    return _widget_template_cache
+
+
+def _get_logo_bytes() -> bytes:
+    """Load and cache the logo image."""
+    global _logo_bytes_cache
+    if _logo_bytes_cache is None:
+        logo_path = paths.get_resource_path('templates/embed/logo.webp')
+        with open(logo_path, 'rb') as f:
+            _logo_bytes_cache = f.read()
+    return _logo_bytes_cache
+
+
+@group.group_class('embed', '/api/v1/embed')
+class EmbedRouterGroup(group.RouterGroup):
+    # -- helpers -------------------------------------------------------------
+
+    def _resolve_bot(self, bot_uuid: str):
+        """Resolve *bot_uuid* to ``(runtime_bot, pipeline_uuid)``.
+
+        Returns ``(None, None)`` when the bot does not exist, is not a
+        ``web_page_bot``, is disabled, or has no pipeline bound.
+        """
+        for bot in self.ap.platform_mgr.bots:
+            if (
+                bot.bot_entity.uuid == bot_uuid
+                and bot.bot_entity.adapter == 'web_page_bot'
+                and bot.bot_entity.enable
+                and bot.bot_entity.use_pipeline_uuid
+            ):
+                return bot, bot.bot_entity.use_pipeline_uuid
+        return None, None
+
+    def _get_bot_config(self, bot_uuid: str) -> dict:
+        for bot in self.ap.platform_mgr.bots:
+            if bot.bot_entity.uuid == bot_uuid and bot.bot_entity.adapter == 'web_page_bot':
+                return bot.bot_entity.adapter_config
+        return {}
+
+    async def _verify_session_token(self, request, bot_uuid: str) -> bool:
+        config = self._get_bot_config(bot_uuid)
+        secret = config.get('turnstile_secret_key', '')
+        if not secret:
+            return True
+        auth_header = request.headers.get('Authorization', '')
+        if not auth_header.startswith('Bearer '):
+            return False
+        token = auth_header[7:]
+        try:
+            ts_str, mac = token.split('.', 1)
+            ts = float(ts_str)
+            if time.time() - ts > 86400:
+                return False
+            expected_mac = hmac.new(secret.encode(), f'{ts_str}'.encode(), hashlib.sha256).hexdigest()
+            return hmac.compare_digest(mac, expected_mac)
+        except Exception:
+            return False
+
+    # -- routes --------------------------------------------------------------
+
+    async def initialize(self) -> None:
+        @self.route('/<bot_uuid>/turnstile/verify', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def verify_turnstile(bot_uuid: str) -> str:
+            if not _is_valid_uuid(bot_uuid):
+                return self.http_status(400, -1, 'Invalid bot_uuid format')
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                return self.http_status(404, -1, 'Bot not found or not available')
+            try:
+                data = await quart.request.get_json()
+                token = data.get('token')
+                if not token:
+                    return self.http_status(400, -1, 'Token is required')
+
+                config = self._get_bot_config(bot_uuid)
+                secret = config.get('turnstile_secret_key', '')
+                if not secret:
+                    ts = time.time()
+                    return self.success(data={'token': f'{ts}.dummy'})
+
+                async with httpx.AsyncClient() as client:
+                    resp = await client.post(
+                        'https://challenges.cloudflare.com/turnstile/v0/siteverify',
+                        data={'secret': secret, 'response': token},
+                    )
+                    result = resp.json()
+
+                if not result.get('success'):
+                    return self.http_status(403, -1, 'Turnstile verification failed')
+
+                ts = time.time()
+                mac = hmac.new(secret.encode(), f'{ts}'.encode(), hashlib.sha256).hexdigest()
+                session_token = f'{ts}.{mac}'
+
+                return self.success(data={'token': session_token})
+
+            except Exception as e:
+                logger.error(f'Turnstile verify failed: {e}', exc_info=True)
+                return self.http_status(500, -1, 'Internal server error')
+
+        @self.route('/<bot_uuid>/widget.js', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def serve_widget(bot_uuid: str) -> quart.Response:
+            """Serve the embed widget JavaScript with injected configuration."""
+            if not _is_valid_uuid(bot_uuid):
+                return self.http_status(400, -1, 'Invalid bot_uuid format')
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                return quart.Response(
+                    '// Bot not found or not available', status=404, content_type='application/javascript'
+                )
+            try:
+                template = _get_widget_template()
+            except FileNotFoundError:
+                return quart.Response('// Widget template not found', status=404, content_type='application/javascript')
+
+            base_url = quart.request.host_url.rstrip('/')
+            webhook_prefix = self.ap.instance_config.data.get('api', {}).get('webhook_prefix', '')
+            if webhook_prefix:
+                base_url = webhook_prefix.rstrip('/')
+
+            if not re.match(r'^https?://[a-zA-Z0-9._:/-]+$', base_url):
+                base_url = quart.request.host_url.rstrip('/')
+
+            config = self._get_bot_config(bot_uuid)
+            site_key = config.get('turnstile_site_key', '')
+            locale = config.get('language', 'en_US') or 'en_US'
+            bubble_icon = config.get('bubble_icon', 'logo') or 'logo'
+            widget_js = template.replace('__LANGBOT_TURNSTILE_SITE_KEY__', site_key)
+            widget_js = widget_js.replace('__LANGBOT_BOT_UUID__', bot_uuid)
+            widget_js = widget_js.replace('__LANGBOT_BASE_URL__', base_url)
+            widget_js = widget_js.replace('__LANGBOT_LOCALE__', locale)
+            widget_js = widget_js.replace('__LANGBOT_BUBBLE_ICON__', bubble_icon)
+
+            response = quart.Response(widget_js, content_type='application/javascript; charset=utf-8')
+            response.headers['Cache-Control'] = 'public, max-age=300'
+            return response
+
+        @self.route('/logo', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def serve_logo() -> quart.Response:
+            """Serve the LangBot logo for the embed widget."""
+            try:
+                logo_data = _get_logo_bytes()
+            except FileNotFoundError:
+                return quart.Response('', status=404)
+
+            response = quart.Response(logo_data, content_type='image/webp')
+            response.headers['Cache-Control'] = 'public, max-age=86400'
+            return response
+
+        @self.route('/<bot_uuid>/messages/<session_type>', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def get_embed_messages(bot_uuid: str, session_type: str) -> str:
+            if not _is_valid_uuid(bot_uuid):
+                return self.http_status(400, -1, 'Invalid bot_uuid format')
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                return self.http_status(404, -1, 'Bot not found or not available')
+            if not await self._verify_session_token(quart.request, bot_uuid):
+                return self.http_status(403, -1, 'Unauthorized or session expired')
+            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:
+                logger.error(f'Failed to get embed messages: {e}', exc_info=True)
+                return self.http_status(500, -1, 'Internal server error')
+
+        @self.route('/<bot_uuid>/reset/<session_type>', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def reset_embed_session(bot_uuid: str, session_type: str) -> str:
+            if not _is_valid_uuid(bot_uuid):
+                return self.http_status(400, -1, 'Invalid bot_uuid format')
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                return self.http_status(404, -1, 'Bot not found or not available')
+            if not await self._verify_session_token(quart.request, bot_uuid):
+                return self.http_status(403, -1, 'Unauthorized or session expired')
+            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:
+                logger.error(f'Failed to reset embed session: {e}', exc_info=True)
+                return self.http_status(500, -1, 'Internal server error')
+
+        @self.route('/<bot_uuid>/feedback', methods=['POST'], auth_type=group.AuthType.NONE)
+        async def submit_feedback(bot_uuid: str) -> str:
+            if not _is_valid_uuid(bot_uuid):
+                return self.http_status(400, -1, 'Invalid bot_uuid format')
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                return self.http_status(404, -1, 'Bot not found or not available')
+            if not await self._verify_session_token(quart.request, bot_uuid):
+                return self.http_status(403, -1, 'Unauthorized or session expired')
+            try:
+                data = await quart.request.get_json()
+                message_id = data.get('message_id', '')
+                feedback_type = data.get('feedback_type')
+
+                if feedback_type not in (1, 2, 3):
+                    return self.http_status(400, -1, 'feedback_type must be 1 (like), 2 (dislike), or 3 (cancel)')
+
+                feedback_id = f'embed_{uuid.uuid4().hex[:12]}'
+
+                await self.ap.monitoring_service.record_feedback(
+                    feedback_id=feedback_id,
+                    feedback_type=feedback_type,
+                    bot_id=runtime_bot.bot_entity.uuid,
+                    bot_name=runtime_bot.bot_entity.name or bot_uuid,
+                    pipeline_id=pipeline_uuid,
+                    message_id=str(message_id),
+                    platform='web_page_bot',
+                )
+
+                return self.success(data={'feedback_id': feedback_id})
+
+            except Exception as e:
+                logger.error(f'Failed to record feedback: {e}', exc_info=True)
+                return self.http_status(500, -1, 'Internal server error')
+
+        # -- Embed WebSocket endpoint ----------------------------------------
+
+        @self.quart_app.websocket(self.path + '/<bot_uuid>/ws/connect')
+        async def embed_websocket_connect(bot_uuid: str):
+            """WebSocket connection for embed widget, keyed by bot_uuid."""
+            if not _is_valid_uuid(bot_uuid):
+                await quart.websocket.send(json.dumps({'type': 'error', 'message': 'Invalid bot_uuid format'}))
+                return
+
+            runtime_bot, pipeline_uuid = self._resolve_bot(bot_uuid)
+            if runtime_bot is None:
+                await quart.websocket.send(json.dumps({'type': 'error', 'message': 'Bot not found or not available'}))
+                return
+
+            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
+
+            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
+
+            try:
+                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', '')},
+                )
+
+                await quart.websocket.send(
+                    json.dumps(
+                        {
+                            'type': 'connected',
+                            'connection_id': connection.connection_id,
+                            'bot_uuid': bot_uuid,
+                            'session_type': session_type,
+                            'timestamp': connection.created_at.isoformat(),
+                        }
+                    )
+                )
+
+                logger.debug(
+                    f'Embed WebSocket connected: {connection.connection_id} '
+                    f'(bot={bot_uuid}, pipeline={pipeline_uuid}, session_type={session_type})'
+                )
+
+                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter, runtime_bot))
+                send_task = asyncio.create_task(self._handle_send(connection))
+
+                try:
+                    await asyncio.gather(receive_task, send_task)
+                except Exception as e:
+                    logger.error(f'Embed WebSocket task error: {e}')
+                finally:
+                    await ws_connection_manager.remove_connection(connection.connection_id)
+
+            except Exception as e:
+                logger.error(f'Embed WebSocket connection error: {e}', exc_info=True)
+                try:
+                    await quart.websocket.send(json.dumps({'type': 'error', 'message': 'Internal server error'}))
+                except Exception:
+                    pass
+
+    # -- WebSocket receive/send helpers --------------------------------------
+
+    async def _handle_receive(self, connection, websocket_adapter, owner_bot):
+        try:
+            while connection.is_active:
+                message = await quart.websocket.receive()
+                await ws_connection_manager.update_activity(connection.connection_id)
+
+                try:
+                    data = json.loads(message)
+                    message_type = data.get('type', 'message')
+
+                    if message_type == 'ping':
+                        await connection.send_queue.put(
+                            {'type': 'pong', 'timestamp': datetime.datetime.now().isoformat()}
+                        )
+                    elif message_type == 'message':
+                        await websocket_adapter.handle_websocket_message(connection, data, owner_bot=owner_bot)
+                    elif message_type == 'disconnect':
+                        break
+
+                except json.JSONDecodeError:
+                    await connection.send_queue.put({'type': 'error', 'message': 'Invalid JSON format'})
+
+        except Exception as e:
+            logger.error(f'Embed receive error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False
+
+    async def _handle_send(self, connection):
+        try:
+            while connection.is_active:
+                try:
+                    message = await asyncio.wait_for(connection.send_queue.get(), timeout=1.0)
+                    await quart.websocket.send(json.dumps(message))
+                except asyncio.TimeoutError:
+                    continue
+        except Exception as e:
+            logger.error(f'Embed send error: {e}', exc_info=True)
+        finally:
+            connection.is_active = False

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

@@ -68,7 +68,7 @@ class PipelinesRouterGroup(group.RouterGroup):
                     return self.http_status(404, -1, 'pipeline not found')
 
                 # Only include plugins with pipeline-related components (Command, EventListener, Tool)
-                # Plugins that only have KnowledgeRetriever components are not suitable for pipeline extensions
+                # 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)

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

@@ -43,6 +43,9 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                     await quart.websocket.send(json.dumps({'type': 'error', 'message': 'WebSocket adapter not found'}))
                     return
 
+                # Find the owning bot for this pipeline (e.g. a web_page_bot)
+                owner_bot = self._find_owner_bot(pipeline_uuid)
+
                 # 注册连接
                 connection = await ws_connection_manager.add_connection(
                     websocket=quart.websocket._get_current_object(),
@@ -70,7 +73,7 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                 )
 
                 # 创建接收和发送任务
-                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter))
+                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter, owner_bot))
                 send_task = asyncio.create_task(self._handle_send(connection))
 
                 # 等待任务完成
@@ -178,7 +181,14 @@ class WebSocketChatRouterGroup(group.RouterGroup):
             except Exception as e:
                 return self.http_status(500, -1, f'Internal server error: {str(e)}')
 
-    async def _handle_receive(self, connection, websocket_adapter):
+    def _find_owner_bot(self, pipeline_uuid: str):
+        """Find a user-created bot (e.g. web_page_bot) that owns this pipeline."""
+        for bot in self.ap.platform_mgr.bots:
+            if bot.bot_entity.adapter == 'web_page_bot' and bot.bot_entity.use_pipeline_uuid == pipeline_uuid:
+                return bot
+        return None
+
+    async def _handle_receive(self, connection, websocket_adapter, owner_bot=None):
         """处理接收消息的任务"""
         try:
             while connection.is_active:
@@ -203,7 +213,7 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                         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)
+                        await websocket_adapter.handle_websocket_message(connection, data, owner_bot=owner_bot)
 
                     elif message_type == 'disconnect':
                         # 客户端主动断开

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

@@ -6,15 +6,63 @@ import re
 import httpx
 import uuid
 import os
+import posixpath
 
 from .....core import taskmgr
 from .. import group
 from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
 
+# Resolve the built-in page SDK JS from the langbot_plugin package
+_PAGE_SDK_PATH = None
+try:
+    import langbot_plugin.assets as _assets_pkg
+
+    _candidate = os.path.join(os.path.dirname(_assets_pkg.__file__), 'langbot-page-sdk.js')
+    if os.path.exists(_candidate):
+        _PAGE_SDK_PATH = _candidate
+except Exception:
+    pass
+
+
+def _normalize_plugin_asset_path(filepath: str) -> str | None:
+    filepath = filepath.replace('\\', '/')
+    if filepath.startswith('/'):
+        return None
+
+    normalized = posixpath.normpath(filepath)
+    if normalized == '.' or normalized.startswith('../') or normalized == '..':
+        return None
+
+    if normalized.startswith('components/pages/'):
+        return normalized
+
+    return f'assets/{normalized}'
+
 
 @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('/_sdk/page-sdk.js', methods=['GET'], auth_type=group.AuthType.NONE)
+        async def _() -> quart.Response:
+            """Serve the built-in LangBot page SDK JavaScript."""
+            if _PAGE_SDK_PATH and os.path.exists(_PAGE_SDK_PATH):
+                with open(_PAGE_SDK_PATH, 'r') as f:
+                    content = f.read()
+                return quart.Response(content, mimetype='application/javascript')
+            return quart.Response('// SDK not found', status=404, mimetype='application/javascript')
+
         @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
             plugins = await self.ap.plugin_connector.list_plugins()
@@ -123,15 +171,62 @@ class PluginsRouterGroup(group.RouterGroup):
             return quart.Response(icon_data, mimetype=mime_type)
 
         @self.route(
-            '/<author>/<plugin_name>/assets/<filepath>',
+            '/<author>/<plugin_name>/assets/<path: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_path = _normalize_plugin_asset_path(filepath)
+            if asset_path is None:
+                return quart.Response('Asset not found', status=404)
+
+            asset_data = await self.ap.plugin_connector.get_plugin_assets(author, plugin_name, asset_path)
+            if not asset_data.get('asset_base64'):
+                return quart.Response('Asset not found', status=404)
             asset_bytes = base64.b64decode(asset_data['asset_base64'])
             mime_type = asset_data['mime_type']
-            return quart.Response(asset_bytes, mimetype=mime_type)
+            resp = quart.Response(asset_bytes, mimetype=mime_type)
+            # CSP for HTML pages served to sandboxed iframes (opaque origin).
+            # 'self' doesn't work in sandboxed iframes — use actual server origin.
+            if mime_type and mime_type.startswith('text/html'):
+                origin = f'{quart.request.scheme}://{quart.request.host}'
+                resp.headers['Content-Security-Policy'] = (
+                    f'default-src {origin}; '
+                    f"script-src {origin} 'unsafe-inline'; "
+                    f"style-src {origin} 'unsafe-inline'; "
+                    f'img-src {origin} data:; '
+                    f'connect-src {origin}; '
+                    "frame-src 'none'; "
+                    "object-src 'none'"
+                )
+            return resp
+
+        @self.route(
+            '/<author>/<plugin_name>/page-api',
+            methods=['POST'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(author: str, plugin_name: str) -> str:
+            """Forward a page API request to the plugin."""
+            data = await quart.request.json
+            if not isinstance(data, dict):
+                return self.http_status(400, -1, 'invalid request body')
+
+            page_id = data.get('page_id', '')
+            endpoint = data.get('endpoint', '')
+            method = data.get('method', 'POST')
+            body = data.get('body')
+            if not isinstance(page_id, str) or not isinstance(endpoint, str) or not isinstance(method, str):
+                return self.http_status(400, -1, 'invalid page api request')
+            if not endpoint.startswith('/') or '..' in endpoint:
+                return self.http_status(400, -1, 'invalid endpoint')
+
+            result = await self.ap.plugin_connector.handle_page_api(
+                author, plugin_name, page_id, endpoint, method.upper(), body
+            )
+            if result.get('error'):
+                return self.http_status(400, -1, result['error'])
+            return self.success(data=result.get('data'))
 
         @self.route('/github/releases', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
         async def _() -> str:
@@ -239,6 +334,10 @@ class PluginsRouterGroup(group.RouterGroup):
         @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', '')
@@ -249,6 +348,8 @@ class PluginsRouterGroup(group.RouterGroup):
                 return self.http_status(400, -1, 'Missing asset_url parameter')
 
             ctx = taskmgr.TaskContext.new()
+            ctx.metadata['plugin_name'] = f'{owner}/{repo}'
+            ctx.metadata['install_source'] = 'github'
             install_info = {
                 'asset_url': asset_url,
                 'owner': owner,
@@ -273,14 +374,23 @@ class PluginsRouterGroup(group.RouterGroup):
             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
 
+            plugin_author = data.get('plugin_author', '')
+            plugin_name = data.get('plugin_name', '')
+
             ctx = taskmgr.TaskContext.new()
+            ctx.metadata['plugin_name'] = f'{plugin_author}/{plugin_name}'
+            ctx.metadata['install_source'] = 'marketplace'
             wrapper = self.ap.task_mgr.create_user_task(
                 self.ap.plugin_connector.install_plugin(PluginInstallSource.MARKETPLACE, data, task_context=ctx),
                 kind='plugin-operation',
                 name='plugin-install-marketplace',
-                label=f'Installing plugin from marketplace ...{data}',
+                label=f'Installing plugin from marketplace {plugin_author}/{plugin_name}',
                 context=ctx,
             )
 
@@ -288,6 +398,10 @@ class PluginsRouterGroup(group.RouterGroup):
 
         @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')
@@ -299,11 +413,13 @@ class PluginsRouterGroup(group.RouterGroup):
             }
 
             ctx = taskmgr.TaskContext.new()
+            ctx.metadata['plugin_name'] = file.filename or 'local plugin'
+            ctx.metadata['install_source'] = 'local'
             wrapper = self.ap.task_mgr.create_user_task(
                 self.ap.plugin_connector.install_plugin(PluginInstallSource.LOCAL, data, task_context=ctx),
                 kind='plugin-operation',
                 name='plugin-install-local',
-                label=f'Installing plugin from local ...{file.filename}',
+                label=f'Installing plugin from local {file.filename}',
                 context=ctx,
             )
 

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

@@ -97,3 +97,51 @@ class EmbeddingModelsRouterGroup(group.RouterGroup):
             await self.ap.embedding_models_service.test_embedding_model(model_uuid, json_data)
 
             return self.success()
+
+
+@group.group_class('models/rerank', '/api/v1/provider/models/rerank')
+class RerankModelsRouterGroup(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':
+                provider_uuid = quart.request.args.get('provider_uuid')
+                if provider_uuid:
+                    return self.success(
+                        data={
+                            'models': await self.ap.rerank_models_service.get_rerank_models_by_provider(provider_uuid)
+                        }
+                    )
+                return self.success(data={'models': await self.ap.rerank_models_service.get_rerank_models()})
+            elif quart.request.method == 'POST':
+                json_data = await quart.request.json
+                model_uuid = await self.ap.rerank_models_service.create_rerank_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)
+        async def _(model_uuid: str) -> str:
+            if quart.request.method == 'GET':
+                model = await self.ap.rerank_models_service.get_rerank_model(model_uuid)
+
+                if model is None:
+                    return self.http_status(404, -1, 'model not found')
+
+                return self.success(data={'model': model})
+            elif quart.request.method == 'PUT':
+                json_data = await quart.request.json
+
+                await self.ap.rerank_models_service.update_rerank_model(model_uuid, json_data)
+
+                return self.success()
+            elif quart.request.method == 'DELETE':
+                await self.ap.rerank_models_service.delete_rerank_model(model_uuid)
+
+                return self.success()
+
+        @self.route('/<model_uuid>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(model_uuid: str) -> str:
+            json_data = await quart.request.json
+
+            await self.ap.rerank_models_service.test_rerank_model(model_uuid, json_data)
+
+            return self.success()

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

@@ -15,6 +15,7 @@ class ModelProvidersRouterGroup(group.RouterGroup):
                     counts = await self.ap.provider_service.get_provider_model_counts(provider['uuid'])
                     provider['llm_count'] = counts['llm_count']
                     provider['embedding_count'] = counts['embedding_count']
+                    provider['rerank_count'] = counts['rerank_count']
                 return self.success(data={'providers': providers})
             elif quart.request.method == 'POST':
                 json_data = await quart.request.json
@@ -32,6 +33,7 @@ class ModelProvidersRouterGroup(group.RouterGroup):
                 counts = await self.ap.provider_service.get_provider_model_counts(provider_uuid)
                 provider['llm_count'] = counts['llm_count']
                 provider['embedding_count'] = counts['embedding_count']
+                provider['rerank_count'] = counts['rerank_count']
                 return self.success(data={'provider': provider})
             elif quart.request.method == 'PUT':
                 json_data = await quart.request.json
@@ -43,3 +45,12 @@ class ModelProvidersRouterGroup(group.RouterGroup):
                     return self.success()
                 except ValueError as e:
                     return self.http_status(400, -1, str(e))
+
+        @self.route('/<provider_uuid>/scan-models', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(provider_uuid: str) -> str:
+            try:
+                model_type = quart.request.args.get('type')
+                result = await self.ap.provider_service.scan_provider_models(provider_uuid, model_type)
+                return self.success(data=result)
+            except ValueError as e:
+                return self.http_status(400, -1, str(e))

src/langbot/pkg/api/http/controller/groups/resources/tools.py

@@ -0,0 +1,45 @@
+from __future__ import annotations
+
+from ... import group
+
+
+@group.group_class('tools', '/api/v1/tools')
+class ToolsRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """获取所有可用工具列表"""
+            tools = await self.ap.tool_mgr.get_all_tools()
+
+            tool_list = []
+            for tool in tools:
+                tool_list.append(
+                    {
+                        'name': tool.name,
+                        'description': tool.description,
+                        'human_desc': tool.human_desc,
+                        'parameters': tool.parameters,
+                    }
+                )
+
+            return self.success(data={'tools': tool_list})
+
+        @self.route('/<tool_name>', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(tool_name: str) -> str:
+            """获取特定工具详情"""
+            tools = await self.ap.tool_mgr.get_all_tools()
+
+            for tool in tools:
+                if tool.name == tool_name:
+                    return self.success(
+                        data={
+                            'tool': {
+                                'name': tool.name,
+                                'description': tool.description,
+                                'human_desc': tool.human_desc,
+                                'parameters': tool.parameters,
+                            }
+                        }
+                    )
+
+            return self.http_status(404, -1, f'Tool not found: {tool_name}')

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

@@ -1,7 +1,11 @@
+import json
+
 import quart
+import sqlalchemy
 
 from .. import group
 from .....utils import constants
+from .....entity.persistence.metadata import Metadata
 
 
 @group.group_class('system', '/api/v1/system')
@@ -9,10 +13,29 @@ class SystemRouterGroup(group.RouterGroup):
     async def initialize(self) -> None:
         @self.route('/info', methods=['GET'], auth_type=group.AuthType.NONE)
         async def _() -> str:
+            # Read wizard_status and wizard_progress from metadata table
+            wizard_status = 'none'
+            wizard_progress = None
+            try:
+                result = await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.select(Metadata).where(Metadata.key.in_(['wizard_status', 'wizard_progress']))
+                )
+                for row in result:
+                    if row.key == 'wizard_status':
+                        wizard_status = row.value
+                    elif row.key == 'wizard_progress':
+                        try:
+                            wizard_progress = json.loads(row.value)
+                        except (json.JSONDecodeError, TypeError):
+                            wizard_progress = None
+            except Exception:
+                pass
+
             return self.success(
                 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
                     ),
@@ -25,17 +48,84 @@ class SystemRouterGroup(group.RouterGroup):
                     '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', {}),
+                    'wizard_status': wizard_status,
+                    'wizard_progress': wizard_progress,
                 }
             )
 
+        @self.route('/wizard/completed', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """Mark wizard status in metadata table and clear progress.
+
+            Accepts JSON body: { "status": "skipped" | "completed" }
+            """
+            data = await quart.request.get_json(silent=True) or {}
+            status = data.get('status', 'completed')
+            if status not in ('skipped', 'completed'):
+                return self.http_status(400, 400, f'Invalid wizard status: {status}')
+
+            try:
+                result = await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.select(Metadata).where(Metadata.key == 'wizard_status')
+                )
+                if result.first():
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.update(Metadata).where(Metadata.key == 'wizard_status').values(value=status)
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.insert(Metadata).values(key='wizard_status', value=status)
+                    )
+
+                # Clear wizard progress when wizard is completed/skipped
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.delete(Metadata).where(Metadata.key == 'wizard_progress')
+                )
+            except Exception as e:
+                return self.http_status(500, 500, f'Failed to update wizard status: {e}')
+
+            return self.success(data={})
+
+        @self.route('/wizard/progress', methods=['PUT'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            """Save wizard progress to metadata table.
+
+            Accepts JSON body with wizard state fields:
+            { "step": int, "selected_adapter": str|null, "created_bot_uuid": str|null,
+              "bot_saved": bool, "selected_runner": str|null }
+            """
+            data = await quart.request.get_json(silent=True) or {}
+            progress_json = json.dumps(data, ensure_ascii=False)
+
+            try:
+                result = await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.select(Metadata).where(Metadata.key == 'wizard_progress')
+                )
+                if result.first():
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.update(Metadata).where(Metadata.key == 'wizard_progress').values(value=progress_json)
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.insert(Metadata).values(key='wizard_progress', value=progress_json)
+                    )
+            except Exception as e:
+                return self.http_status(500, 500, f'Failed to save wizard progress: {e}')
+
+            return self.success(data={})
+
         @self.route('/tasks', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
             task_type = quart.request.args.get('type')
+            task_kind = quart.request.args.get('kind')
 
             if task_type == '':
                 task_type = None
+            if task_kind == '':
+                task_kind = None
 
-            return self.success(data=self.ap.task_mgr.get_tasks_dict(task_type))
+            return self.success(data=self.ap.task_mgr.get_tasks_dict(task_type, task_kind))
 
         @self.route('/tasks/<task_id>', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
         async def _(task_id: str) -> str:
@@ -46,6 +136,10 @@ class SystemRouterGroup(group.RouterGroup):
 
             return self.success(data=task.to_dict())
 
+        @self.route('/storage-analysis', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            return self.success(data=await self.ap.maintenance_service.get_storage_analysis())
+
         @self.route('/debug/exec', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
             if not constants.debug_mode:

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

@@ -105,6 +105,29 @@ class HTTPController:
             ):
                 if os.path.exists(os.path.join(frontend_path, path + '.html')):
                     path += '.html'
+                elif not path.startswith('api/'):
+                    # SPA fallback: serve index.html for all non-API, non-static routes
+                    # so that React Router can handle client-side routing (Vite SPA).
+                    # For /home/* sub-routes, first try parent .html files (pre-rendered pages).
+                    if path.startswith('home/'):
+                        segments = path.rstrip('/').split('/')
+                        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
+
+                    # Fallback to index.html for SPA client-side routing
+                    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

@@ -70,12 +70,17 @@ class BotService:
             '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
 
@@ -83,6 +88,14 @@ class BotService:
 
     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())
 

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

@@ -1,80 +0,0 @@
-from __future__ import annotations
-
-from ....core import app
-import sqlalchemy
-from langbot.pkg.entity.persistence import rag as persistence_rag
-import uuid
-
-
-class ExternalKBService:
-    """External KB service"""
-
-    ap: app.Application
-
-    def __init__(self, ap: app.Application) -> None:
-        self.ap = ap
-
-    # External Knowledge Base methods
-    async def get_external_knowledge_bases(self) -> list[dict]:
-        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_rag.ExternalKnowledgeBase))
-        external_kbs = result.all()
-        return [
-            self.ap.persistence_mgr.serialize_model(persistence_rag.ExternalKnowledgeBase, external_kb)
-            for external_kb in external_kbs
-        ]
-
-    async def get_external_knowledge_base(self, kb_uuid: str) -> dict | None:
-        result = await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.select(persistence_rag.ExternalKnowledgeBase).where(
-                persistence_rag.ExternalKnowledgeBase.uuid == kb_uuid
-            )
-        )
-        external_kb = result.first()
-        if external_kb is None:
-            return None
-        return self.ap.persistence_mgr.serialize_model(persistence_rag.ExternalKnowledgeBase, external_kb)
-
-    async def create_external_knowledge_base(self, kb_data: dict) -> str:
-        kb_data['uuid'] = str(uuid.uuid4())
-        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.insert(persistence_rag.ExternalKnowledgeBase).values(kb_data)
-        )
-
-        kb = await self.get_external_knowledge_base(kb_data['uuid'])
-
-        await self.ap.rag_mgr.load_external_knowledge_base(kb)
-
-        return kb_data['uuid']
-
-    async def retrieve_external_knowledge_base(self, kb_uuid: str, query: str) -> list[dict]:
-        """Retrieve external knowledge base"""
-        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, 5)
-        ]  # top_k is just a placeholder for external knowledge base
-
-    async def update_external_knowledge_base(self, kb_uuid: str, kb_data: dict) -> None:
-        if 'uuid' in kb_data:
-            del kb_data['uuid']
-
-        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.update(persistence_rag.ExternalKnowledgeBase)
-            .values(kb_data)
-            .where(persistence_rag.ExternalKnowledgeBase.uuid == kb_uuid)
-        )
-        await self.ap.rag_mgr.remove_knowledge_base_from_runtime(kb_uuid)
-
-        kb = await self.get_external_knowledge_base(kb_uuid)
-
-        await self.ap.rag_mgr.load_external_knowledge_base(kb)
-
-    async def delete_external_knowledge_base(self, kb_uuid: str) -> None:
-        await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.delete(persistence_rag.ExternalKnowledgeBase).where(
-                persistence_rag.ExternalKnowledgeBase.uuid == kb_uuid
-            )
-        )
-
-        await self.ap.rag_mgr.delete_knowledge_base(kb_uuid)

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

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import uuid
 import sqlalchemy
 
 from ....core import app
@@ -17,64 +16,77 @@ 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')
-        # Only internal KBs support file storage
-        if runtime_kb.get_type() != 'internal':
-            raise Exception('Only internal knowledge bases support file storage')
-        result = await runtime_kb.store_file(file_id)
+
+        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(
@@ -85,14 +97,18 @@ class KnowledgeService:
 
         return result
 
-    async def retrieve_knowledge_base(self, kb_uuid: str, query: str) -> list[dict]:
+    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"""
@@ -107,9 +123,9 @@ 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')
-        # Only internal KBs support file deletion
-        if runtime_kb.get_type() != 'internal':
-            raise Exception('Only internal knowledge bases support file deletion')
+
+        await self._check_doc_capability(kb_uuid, 'document deletion')
+
         await runtime_kb.delete_file(file_id)
 
         # Update the KB's updated_at timestamp
@@ -121,13 +137,14 @@ class KnowledgeService:
 
     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)
         )
@@ -140,3 +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/maintenance.py

@@ -0,0 +1,309 @@
+from __future__ import annotations
+
+import datetime
+import os
+import re
+from pathlib import Path
+from typing import Any
+
+import sqlalchemy
+
+from ....core import app
+from ....entity.persistence import bstorage as persistence_bstorage
+from ....entity.persistence import monitoring as persistence_monitoring
+
+
+LOG_FILE_PATTERN = re.compile(r'^langbot-(\d{4}-\d{2}-\d{2})\.log(?:\.\d+)?$')
+DEFAULT_UPLOAD_FILE_RETENTION_DAYS = 7
+DEFAULT_LOG_RETENTION_DAYS = 3
+
+
+class MaintenanceService:
+    """Storage maintenance and diagnostics."""
+
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def cleanup_expired_files(self) -> dict[str, int]:
+        cleanup_cfg = self.ap.instance_config.data.get('storage', {}).get('cleanup', {})
+        upload_retention_days = self._positive_int(
+            cleanup_cfg.get('uploaded_file_retention_days'),
+            DEFAULT_UPLOAD_FILE_RETENTION_DAYS,
+            'storage.cleanup.uploaded_file_retention_days',
+        )
+        log_retention_days = self._positive_int(
+            cleanup_cfg.get('log_retention_days'),
+            DEFAULT_LOG_RETENTION_DAYS,
+            'storage.cleanup.log_retention_days',
+        )
+
+        return {
+            'uploaded_files': await self._cleanup_expired_uploaded_files(upload_retention_days),
+            'log_files': self._cleanup_expired_log_files(log_retention_days),
+        }
+
+    async def get_storage_analysis(self) -> dict[str, Any]:
+        cleanup_cfg = self.ap.instance_config.data.get('storage', {}).get('cleanup', {})
+        upload_retention_days = self._positive_int(
+            cleanup_cfg.get('uploaded_file_retention_days'),
+            DEFAULT_UPLOAD_FILE_RETENTION_DAYS,
+            'storage.cleanup.uploaded_file_retention_days',
+        )
+        log_retention_days = self._positive_int(
+            cleanup_cfg.get('log_retention_days'),
+            DEFAULT_LOG_RETENTION_DAYS,
+            'storage.cleanup.log_retention_days',
+        )
+
+        database_cfg = self.ap.instance_config.data.get('database', {})
+        database_type = database_cfg.get('use', 'sqlite')
+        database_path = (
+            Path(database_cfg.get('sqlite', {}).get('path', 'data/langbot.db')) if database_type == 'sqlite' else None
+        )
+        roots: list[tuple[str, Path | None]] = [
+            ('database', database_path),
+            ('logs', Path('data/logs')),
+            ('storage', Path('data/storage')),
+            ('vector_store', Path('data/chroma')),
+            ('plugins', Path('data/plugins')),
+            ('mcp', Path('data/mcp')),
+            ('temp', Path('data/temp')),
+        ]
+
+        sections = []
+        for key, path in roots:
+            sections.append(
+                {
+                    'key': key,
+                    'path': str(path) if path else '',
+                    'exists': path.exists() if path else False,
+                    'size_bytes': self._path_size(path) if path else 0,
+                    'file_count': self._file_count(path) if path else 0,
+                }
+            )
+
+        monitoring_counts = await self._monitoring_counts()
+        binary_storage = await self._binary_storage_stats()
+        upload_candidates = await self._expired_uploaded_candidates(upload_retention_days)
+        log_candidates = self._expired_log_candidates(log_retention_days)
+
+        return {
+            'generated_at': datetime.datetime.now(datetime.timezone.utc).isoformat(),
+            'cleanup_policy': {
+                'uploaded_file_retention_days': upload_retention_days,
+                'log_retention_days': log_retention_days,
+            },
+            'sections': sections,
+            'database': {
+                'type': database_type,
+                'monitoring_counts': monitoring_counts,
+                'binary_storage': binary_storage,
+            },
+            'cleanup_candidates': {
+                'uploaded_files': upload_candidates,
+                'log_files': log_candidates,
+            },
+            'tasks': self.ap.task_mgr.get_stats() if self.ap.task_mgr else {},
+        }
+
+    async def _cleanup_expired_uploaded_files(self, retention_days: int) -> int:
+        provider = self.ap.storage_mgr.storage_provider
+        provider_name = provider.__class__.__name__
+        if provider_name == 'LocalStorageProvider':
+            candidates = self._expired_local_upload_candidates(retention_days, include_paths=True)
+            deleted = 0
+            for item in candidates:
+                try:
+                    os.remove(item['path'])
+                    deleted += 1
+                except FileNotFoundError:
+                    pass
+                except Exception as e:
+                    self.ap.logger.warning(f'Failed to delete expired uploaded file {item["key"]}: {e}')
+            return deleted
+
+        if provider_name == 'S3StorageProvider':
+            return await self._cleanup_expired_s3_uploaded_files(retention_days)
+
+        return 0
+
+    async def _expired_uploaded_candidates(self, retention_days: int) -> list[dict[str, Any]]:
+        provider_name = self.ap.storage_mgr.storage_provider.__class__.__name__
+        if provider_name == 'LocalStorageProvider':
+            return self._expired_local_upload_candidates(retention_days)
+        if provider_name == 'S3StorageProvider':
+            return await self._expired_s3_upload_candidates(retention_days)
+        return []
+
+    async def _cleanup_expired_s3_uploaded_files(self, retention_days: int) -> int:
+        provider = self.ap.storage_mgr.storage_provider
+        candidates = await self._expired_s3_upload_candidates(retention_days)
+        deleted = 0
+        for item in candidates:
+            await provider.delete(item['key'])
+            deleted += 1
+        return deleted
+
+    async def _expired_s3_upload_candidates(self, retention_days: int) -> list[dict[str, Any]]:
+        provider = self.ap.storage_mgr.storage_provider
+        cutoff = datetime.datetime.now(datetime.timezone.utc) - datetime.timedelta(days=retention_days)
+        candidates = []
+        paginator = provider.s3_client.get_paginator('list_objects_v2')
+
+        for page in paginator.paginate(Bucket=provider.bucket_name):
+            for obj in page.get('Contents', []):
+                key = obj.get('Key', '')
+                last_modified = obj.get('LastModified')
+                if not self._is_uploaded_file_key(key):
+                    continue
+                if last_modified and last_modified < cutoff:
+                    candidates.append(
+                        {
+                            'key': key,
+                            'size_bytes': obj.get('Size', 0),
+                            'modified_at': last_modified.isoformat(),
+                        }
+                    )
+
+        return candidates
+
+    def _cleanup_expired_log_files(self, retention_days: int) -> int:
+        deleted = 0
+        for item in self._expired_log_candidates(retention_days, include_paths=True):
+            try:
+                os.remove(item['path'])
+                deleted += 1
+            except FileNotFoundError:
+                pass
+            except Exception as e:
+                self.ap.logger.warning(f'Failed to delete expired log file {item["name"]}: {e}')
+        return deleted
+
+    def _expired_local_upload_candidates(
+        self, retention_days: int, include_paths: bool = False
+    ) -> list[dict[str, Any]]:
+        storage_root = Path('data/storage')
+        if not storage_root.exists():
+            return []
+
+        cutoff = datetime.datetime.now().timestamp() - retention_days * 86400
+        candidates = []
+        for entry in storage_root.iterdir():
+            if not entry.is_file() or not self._is_uploaded_file_key(entry.name):
+                continue
+            stat = entry.stat()
+            if stat.st_mtime >= cutoff:
+                continue
+            item = {
+                'key': entry.name,
+                'size_bytes': stat.st_size,
+                'modified_at': datetime.datetime.fromtimestamp(stat.st_mtime, datetime.timezone.utc).isoformat(),
+            }
+            if include_paths:
+                item['path'] = str(entry)
+            candidates.append(item)
+        return candidates
+
+    def _expired_log_candidates(self, retention_days: int, include_paths: bool = False) -> list[dict[str, Any]]:
+        log_root = Path('data/logs')
+        if not log_root.exists():
+            return []
+
+        cutoff_date = datetime.date.today() - datetime.timedelta(days=retention_days - 1)
+        candidates = []
+        for entry in log_root.iterdir():
+            if not entry.is_file():
+                continue
+            match = LOG_FILE_PATTERN.match(entry.name)
+            if not match:
+                continue
+            try:
+                file_date = datetime.date.fromisoformat(match.group(1))
+            except ValueError:
+                continue
+            if file_date >= cutoff_date:
+                continue
+            stat = entry.stat()
+            item = {
+                'name': entry.name,
+                'date': file_date.isoformat(),
+                'size_bytes': stat.st_size,
+            }
+            if include_paths:
+                item['path'] = str(entry)
+            candidates.append(item)
+        return candidates
+
+    def _is_uploaded_file_key(self, key: str) -> bool:
+        return '/' not in key and not key.startswith('plugin_config_')
+
+    async def _monitoring_counts(self) -> dict[str, int]:
+        tables = {
+            'messages': persistence_monitoring.MonitoringMessage.id,
+            'llm_calls': persistence_monitoring.MonitoringLLMCall.id,
+            'embedding_calls': persistence_monitoring.MonitoringEmbeddingCall.id,
+            'errors': persistence_monitoring.MonitoringError.id,
+            'sessions': persistence_monitoring.MonitoringSession.session_id,
+            'feedback': persistence_monitoring.MonitoringFeedback.id,
+        }
+        counts: dict[str, int] = {}
+        for key, column in tables.items():
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(sqlalchemy.func.count(column)))
+            counts[key] = result.scalar() or 0
+        return counts
+
+    async def _binary_storage_stats(self) -> dict[str, Any]:
+        count_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(sqlalchemy.func.count(persistence_bstorage.BinaryStorage.unique_key))
+        )
+        size_bytes = None
+        try:
+            size_result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.select(sqlalchemy.func.sum(sqlalchemy.func.length(persistence_bstorage.BinaryStorage.value)))
+            )
+            size_bytes = size_result.scalar() or 0
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to estimate binary storage size: {e}')
+
+        return {
+            'count': count_result.scalar() or 0,
+            'size_bytes': size_bytes,
+        }
+
+    def _path_size(self, path: Path) -> int:
+        if not path.exists():
+            return 0
+        if path.is_file():
+            return path.stat().st_size
+        total = 0
+        for root, _, files in os.walk(path):
+            for file_name in files:
+                file_path = Path(root) / file_name
+                try:
+                    total += file_path.stat().st_size
+                except FileNotFoundError:
+                    pass
+        return total
+
+    def _file_count(self, path: Path) -> int:
+        if not path.exists():
+            return 0
+        if path.is_file():
+            return 1
+        count = 0
+        for _, _, files in os.walk(path):
+            count += len(files)
+        return count
+
+    def _positive_int(self, value: Any, default: int, name: str) -> int:
+        try:
+            parsed = int(value)
+        except (TypeError, ValueError):
+            self.ap.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        if parsed < 1:
+            self.ap.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        return parsed

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

@@ -23,6 +23,17 @@ def _parse_provider_api_keys(provider_dict: dict) -> dict:
     return provider_dict
 
 
+def _runtime_model_data(model_uuid: str, model_data: dict) -> dict:
+    """Return model data for rebuilding runtime models after an update.
+
+    Update payloads intentionally omit uuid before writing to the database.
+    Runtime model entities still need the stable uuid so pipeline configs can
+    resolve the in-memory model immediately after an edit, without requiring a
+    process restart.
+    """
+    return {**model_data, 'uuid': model_uuid}
+
+
 class LLMModelsService:
     ap: app.Application
 
@@ -105,11 +116,16 @@ class LLMModelsService:
                 )
             )
             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)
+            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']
 
@@ -168,7 +184,7 @@ class LLMModelsService:
             raise Exception('provider not found')
 
         runtime_llm_model = await self.ap.model_mgr.load_llm_model_with_provider(
-            persistence_model.LLMModel(**model_data),
+            persistence_model.LLMModel(**_runtime_model_data(model_uuid, model_data)),
             runtime_provider,
         )
         self.ap.model_mgr.llm_models.append(runtime_llm_model)
@@ -329,7 +345,7 @@ class EmbeddingModelsService:
             raise Exception('provider not found')
 
         runtime_embedding_model = await self.ap.model_mgr.load_embedding_model_with_provider(
-            persistence_model.EmbeddingModel(**model_data),
+            persistence_model.EmbeddingModel(**_runtime_model_data(model_uuid, model_data)),
             runtime_provider,
         )
         self.ap.model_mgr.embedding_models.append(runtime_embedding_model)
@@ -362,3 +378,162 @@ class EmbeddingModelsService:
             input_text=['Hello, world!'],
             extra_args={},
         )
+
+
+class RerankModelsService:
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    async def get_rerank_models(self) -> list[dict]:
+        """Get all rerank models with provider info"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.RerankModel))
+        models = result.all()
+
+        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.RerankModel, 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_rerank_models_by_provider(self, provider_uuid: str) -> list[dict]:
+        """Get rerank models by provider UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.RerankModel).where(
+                persistence_model.RerankModel.provider_uuid == provider_uuid
+            )
+        )
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, m) for m in models]
+
+    async def create_rerank_model(self, model_data: dict, preserve_uuid: bool = False) -> str:
+        """Create a new rerank 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.RerankModel).values(**model_data)
+        )
+
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
+
+        runtime_rerank_model = await self.ap.model_mgr.load_rerank_model_with_provider(
+            persistence_model.RerankModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.rerank_models.append(runtime_rerank_model)
+
+        return model_data['uuid']
+
+    async def get_rerank_model(self, model_uuid: str) -> dict | None:
+        """Get a single rerank model with provider info"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.RerankModel).where(persistence_model.RerankModel.uuid == model_uuid)
+        )
+        model = result.first()
+        if model is None:
+            return None
+
+        model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.RerankModel, 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_rerank_model(self, model_uuid: str, model_data: dict) -> None:
+        """Update an existing rerank 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.RerankModel)
+            .where(persistence_model.RerankModel.uuid == model_uuid)
+            .values(**model_data)
+        )
+
+        await self.ap.model_mgr.remove_rerank_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')
+
+        runtime_rerank_model = await self.ap.model_mgr.load_rerank_model_with_provider(
+            persistence_model.RerankModel(**_runtime_model_data(model_uuid, model_data)),
+            runtime_provider,
+        )
+        self.ap.model_mgr.rerank_models.append(runtime_rerank_model)
+
+    async def delete_rerank_model(self, model_uuid: str) -> None:
+        """Delete a rerank model"""
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.delete(persistence_model.RerankModel).where(persistence_model.RerankModel.uuid == model_uuid)
+        )
+        await self.ap.model_mgr.remove_rerank_model(model_uuid)
+
+    async def test_rerank_model(self, model_uuid: str, model_data: dict) -> None:
+        """Test a rerank model"""
+        runtime_rerank_model: model_requester.RuntimeRerankModel | None = None
+
+        if model_uuid != '_':
+            for model in self.ap.model_mgr.rerank_models:
+                if model.model_entity.uuid == model_uuid:
+                    runtime_rerank_model = model
+                    break
+            if runtime_rerank_model is None:
+                raise Exception('model not found')
+        else:
+            runtime_rerank_model = await self.ap.model_mgr.init_temporary_runtime_rerank_model(model_data)
+
+        await runtime_rerank_model.provider.invoke_rerank(
+            model=runtime_rerank_model,
+            query='What is artificial intelligence?',
+            documents=[
+                'Artificial intelligence is a branch of computer science.',
+                'The weather is nice today.',
+            ],
+        )

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

@@ -16,6 +16,121 @@ class MonitoringService:
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
 
+    # ========== Cleanup Methods ==========
+
+    async def cleanup_expired_records(self, retention_days: int, batch_size: int = 1000) -> dict[str, int]:
+        """Delete monitoring records older than the specified retention period.
+
+        Args:
+            retention_days: Number of days to retain records.
+            batch_size: Maximum rows to delete per table batch.
+
+        Returns:
+            A dict mapping table name to the number of deleted rows.
+        """
+        if retention_days < 1:
+            raise ValueError('retention_days must be >= 1')
+        if batch_size < 1:
+            raise ValueError('batch_size must be >= 1')
+
+        cutoff = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None) - datetime.timedelta(
+            days=retention_days
+        )
+
+        tables_and_columns: list[tuple[str, type, sqlalchemy.Column, sqlalchemy.Column]] = [
+            (
+                'monitoring_messages',
+                persistence_monitoring.MonitoringMessage,
+                persistence_monitoring.MonitoringMessage.timestamp,
+                persistence_monitoring.MonitoringMessage.id,
+            ),
+            (
+                'monitoring_llm_calls',
+                persistence_monitoring.MonitoringLLMCall,
+                persistence_monitoring.MonitoringLLMCall.timestamp,
+                persistence_monitoring.MonitoringLLMCall.id,
+            ),
+            (
+                'monitoring_embedding_calls',
+                persistence_monitoring.MonitoringEmbeddingCall,
+                persistence_monitoring.MonitoringEmbeddingCall.timestamp,
+                persistence_monitoring.MonitoringEmbeddingCall.id,
+            ),
+            (
+                'monitoring_errors',
+                persistence_monitoring.MonitoringError,
+                persistence_monitoring.MonitoringError.timestamp,
+                persistence_monitoring.MonitoringError.id,
+            ),
+            (
+                'monitoring_sessions',
+                persistence_monitoring.MonitoringSession,
+                persistence_monitoring.MonitoringSession.last_activity,
+                persistence_monitoring.MonitoringSession.session_id,
+            ),
+            (
+                'monitoring_feedback',
+                persistence_monitoring.MonitoringFeedback,
+                persistence_monitoring.MonitoringFeedback.timestamp,
+                persistence_monitoring.MonitoringFeedback.id,
+            ),
+        ]
+
+        deleted_counts: dict[str, int] = {}
+
+        for table_name, model_cls, ts_column, pk_column in tables_and_columns:
+            deleted_counts[table_name] = await self._delete_expired_in_batches(
+                model_cls=model_cls,
+                ts_column=ts_column,
+                pk_column=pk_column,
+                cutoff=cutoff,
+                batch_size=batch_size,
+            )
+
+        if sum(deleted_counts.values()) > 0:
+            await self._release_sqlite_space()
+
+        return deleted_counts
+
+    async def _delete_expired_in_batches(
+        self,
+        model_cls: type,
+        ts_column: sqlalchemy.Column,
+        pk_column: sqlalchemy.Column,
+        cutoff: datetime.datetime,
+        batch_size: int,
+    ) -> int:
+        deleted_total = 0
+
+        while True:
+            select_result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.select(pk_column).where(ts_column < cutoff).limit(batch_size)
+            )
+            pk_values = list(select_result.scalars().all())
+            if not pk_values:
+                break
+
+            delete_result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(model_cls).where(pk_column.in_(pk_values))
+            )
+            deleted = delete_result.rowcount or 0
+            deleted_total += deleted
+
+            if len(pk_values) < batch_size:
+                break
+
+        return deleted_total
+
+    async def _release_sqlite_space(self) -> None:
+        database_type = self.ap.instance_config.data.get('database', {}).get('use', 'sqlite')
+        if database_type != 'sqlite':
+            return
+
+        async with self.ap.persistence_mgr.get_db_engine().connect() as conn:
+            autocommit_conn = await conn.execution_options(isolation_level='AUTOCOMMIT')
+            await autocommit_conn.execute(sqlalchemy.text('PRAGMA wal_checkpoint(TRUNCATE)'))
+            await autocommit_conn.execute(sqlalchemy.text('VACUUM'))
+
     # ========== Recording Methods ==========
 
     async def record_message(
@@ -30,8 +145,10 @@ class MonitoringService:
         level: str = 'info',
         platform: str | None = None,
         user_id: str | None = None,
+        user_name: str | None = None,
         runner_name: str | None = None,
         variables: str | None = None,
+        role: str = 'user',
     ) -> str:
         """Record a message"""
         message_id = str(uuid.uuid4())
@@ -48,8 +165,10 @@ class MonitoringService:
             'level': level,
             'platform': platform,
             'user_id': user_id,
+            'user_name': user_name,
             'runner_name': runner_name,
             'variables': variables,
+            'role': role,
         }
 
         await self.ap.persistence_mgr.execute_async(
@@ -150,6 +269,7 @@ class MonitoringService:
         pipeline_name: str,
         platform: str | None = None,
         user_id: str | None = None,
+        user_name: str | None = None,
     ) -> None:
         """Record a new session"""
         session_data = {
@@ -164,6 +284,7 @@ class MonitoringService:
             'is_active': True,
             'platform': platform,
             'user_id': user_id,
+            'user_name': user_name,
         }
 
         await self.ap.persistence_mgr.execute_async(
@@ -355,6 +476,7 @@ class MonitoringService:
         self,
         bot_ids: list[str] | None = None,
         pipeline_ids: list[str] | None = None,
+        session_ids: list[str] | None = None,
         start_time: datetime.datetime | None = None,
         end_time: datetime.datetime | None = None,
         limit: int = 100,
@@ -367,6 +489,8 @@ class MonitoringService:
             conditions.append(persistence_monitoring.MonitoringMessage.bot_id.in_(bot_ids))
         if pipeline_ids:
             conditions.append(persistence_monitoring.MonitoringMessage.pipeline_id.in_(pipeline_ids))
+        if session_ids:
+            conditions.append(persistence_monitoring.MonitoringMessage.session_id.in_(session_ids))
         if start_time:
             conditions.append(persistence_monitoring.MonitoringMessage.timestamp >= start_time)
         if end_time:
@@ -794,3 +918,643 @@ class MonitoringService:
             },
             'errors': errors,
         }
+
+    # ========== Export Methods ==========
+
+    def _escape_csv_field(self, field: str | None) -> str:
+        """Escape a field for CSV output"""
+        if field is None:
+            return ''
+        # Convert non-string types to string first
+        if not isinstance(field, str):
+            field = str(field)
+        # Replace common escape sequences
+        field = field.replace('\r\n', '\n').replace('\r', '\n')
+        # If field contains comma, double quote, or newline, wrap in quotes
+        if ',' in field or '"' in field or '\n' in field:
+            # Escape double quotes by doubling them
+            field = '"' + field.replace('"', '""') + '"'
+        return field
+
+    def _format_timestamp(self, dt: datetime.datetime) -> str:
+        """Format datetime to ISO format string"""
+        return dt.strftime('%Y-%m-%d %H:%M:%S')
+
+    def _extract_message_text(self, message_content: str) -> str:
+        """Extract plain text from message chain JSON"""
+        if not message_content:
+            return ''
+
+        try:
+            import json
+
+            message_chain = json.loads(message_content)
+            if not isinstance(message_chain, list):
+                return message_content
+
+            text_parts = []
+            for component in message_chain:
+                if not isinstance(component, dict):
+                    continue
+                component_type = component.get('type')
+                if component_type == 'Plain':
+                    text = component.get('text', '')
+                    text_parts.append(text)
+                elif component_type == 'At':
+                    display = component.get('display', '')
+                    target = component.get('target', '')
+                    if display:
+                        text_parts.append(f'@{display}')
+                    elif target:
+                        text_parts.append(f'@{target}')
+                elif component_type == 'AtAll':
+                    text_parts.append('@All')
+                elif component_type == 'Image':
+                    text_parts.append('[Image]')
+                elif component_type == 'File':
+                    name = component.get('name', 'File')
+                    text_parts.append(f'[File: {name}]')
+                elif component_type == 'Voice':
+                    length = component.get('length', 0)
+                    text_parts.append(f'[Voice {length}s]')
+                elif component_type == 'Quote':
+                    # Quote content is in 'origin' field
+                    origin = component.get('origin', [])
+                    if isinstance(origin, list):
+                        for item in origin:
+                            if isinstance(item, dict) and item.get('type') == 'Plain':
+                                text_parts.append(f'> {item.get("text", "")}')
+                elif component_type == 'Source':
+                    # Skip Source component
+                    continue
+                else:
+                    # Other unknown types
+                    text_parts.append(f'[{component_type}]')
+
+            return ''.join(text_parts)
+        except (json.JSONDecodeError, TypeError, KeyError):
+            # If not valid JSON, return as-is
+            return message_content
+
+    async def export_messages(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export messages as list of dictionaries for CSV conversion"""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringMessage.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringMessage.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringMessage.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringMessage.timestamp <= end_time)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringMessage).order_by(
+            persistence_monitoring.MonitoringMessage.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'id': row[0].id if isinstance(row, tuple) else row.id,
+                'timestamp': self._format_timestamp(row[0].timestamp if isinstance(row, tuple) else row.timestamp),
+                'bot_id': row[0].bot_id if isinstance(row, tuple) else row.bot_id,
+                'bot_name': row[0].bot_name if isinstance(row, tuple) else row.bot_name,
+                'pipeline_id': row[0].pipeline_id if isinstance(row, tuple) else row.pipeline_id,
+                'pipeline_name': row[0].pipeline_name if isinstance(row, tuple) else row.pipeline_name,
+                'runner_name': row[0].runner_name if isinstance(row, tuple) else row.runner_name,
+                'message_content': row[0].message_content if isinstance(row, tuple) else row.message_content,
+                'message_text': self._extract_message_text(
+                    row[0].message_content if isinstance(row, tuple) else row.message_content
+                ),
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'status': row[0].status if isinstance(row, tuple) else row.status,
+                'level': row[0].level if isinstance(row, tuple) else row.level,
+                'platform': row[0].platform if isinstance(row, tuple) else row.platform,
+                'user_id': row[0].user_id if isinstance(row, tuple) else row.user_id,
+            }
+            for row in rows
+        ]
+
+    async def export_llm_calls(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export LLM calls as list of dictionaries for CSV conversion"""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringLLMCall.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringLLMCall.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringLLMCall.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringLLMCall.timestamp <= end_time)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringLLMCall).order_by(
+            persistence_monitoring.MonitoringLLMCall.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'id': row[0].id if isinstance(row, tuple) else row.id,
+                'timestamp': self._format_timestamp(row[0].timestamp if isinstance(row, tuple) else row.timestamp),
+                'model_name': row[0].model_name if isinstance(row, tuple) else row.model_name,
+                'input_tokens': row[0].input_tokens if isinstance(row, tuple) else row.input_tokens,
+                'output_tokens': row[0].output_tokens if isinstance(row, tuple) else row.output_tokens,
+                'total_tokens': row[0].total_tokens if isinstance(row, tuple) else row.total_tokens,
+                'duration_ms': row[0].duration if isinstance(row, tuple) else row.duration,
+                'cost': row[0].cost if isinstance(row, tuple) else row.cost,
+                'status': row[0].status if isinstance(row, tuple) else row.status,
+                'bot_id': row[0].bot_id if isinstance(row, tuple) else row.bot_id,
+                'bot_name': row[0].bot_name if isinstance(row, tuple) else row.bot_name,
+                'pipeline_id': row[0].pipeline_id if isinstance(row, tuple) else row.pipeline_id,
+                'pipeline_name': row[0].pipeline_name if isinstance(row, tuple) else row.pipeline_name,
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'message_id': row[0].message_id if isinstance(row, tuple) else row.message_id,
+                'error_message': row[0].error_message if isinstance(row, tuple) else row.error_message,
+            }
+            for row in rows
+        ]
+
+    async def export_embedding_calls(
+        self,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        knowledge_base_id: str | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export embedding calls as list of dictionaries for CSV conversion"""
+        conditions = []
+
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringEmbeddingCall.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringEmbeddingCall.timestamp <= end_time)
+        if knowledge_base_id:
+            conditions.append(persistence_monitoring.MonitoringEmbeddingCall.knowledge_base_id == knowledge_base_id)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringEmbeddingCall).order_by(
+            persistence_monitoring.MonitoringEmbeddingCall.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'id': row[0].id if isinstance(row, tuple) else row.id,
+                'timestamp': self._format_timestamp(row[0].timestamp if isinstance(row, tuple) else row.timestamp),
+                'model_name': row[0].model_name if isinstance(row, tuple) else row.model_name,
+                'prompt_tokens': row[0].prompt_tokens if isinstance(row, tuple) else row.prompt_tokens,
+                'total_tokens': row[0].total_tokens if isinstance(row, tuple) else row.total_tokens,
+                'duration_ms': row[0].duration if isinstance(row, tuple) else row.duration,
+                'input_count': row[0].input_count if isinstance(row, tuple) else row.input_count,
+                'status': row[0].status if isinstance(row, tuple) else row.status,
+                'error_message': row[0].error_message if isinstance(row, tuple) else row.error_message,
+                'knowledge_base_id': row[0].knowledge_base_id if isinstance(row, tuple) else row.knowledge_base_id,
+                'query_text': row[0].query_text if isinstance(row, tuple) else row.query_text,
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'message_id': row[0].message_id if isinstance(row, tuple) else row.message_id,
+                'call_type': row[0].call_type if isinstance(row, tuple) else row.call_type,
+            }
+            for row in rows
+        ]
+
+    async def export_errors(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export errors as list of dictionaries for CSV conversion"""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringError.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringError.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringError.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringError.timestamp <= end_time)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringError).order_by(
+            persistence_monitoring.MonitoringError.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'id': row[0].id if isinstance(row, tuple) else row.id,
+                'timestamp': self._format_timestamp(row[0].timestamp if isinstance(row, tuple) else row.timestamp),
+                'error_type': row[0].error_type if isinstance(row, tuple) else row.error_type,
+                'error_message': row[0].error_message if isinstance(row, tuple) else row.error_message,
+                'bot_id': row[0].bot_id if isinstance(row, tuple) else row.bot_id,
+                'bot_name': row[0].bot_name if isinstance(row, tuple) else row.bot_name,
+                'pipeline_id': row[0].pipeline_id if isinstance(row, tuple) else row.pipeline_id,
+                'pipeline_name': row[0].pipeline_name if isinstance(row, tuple) else row.pipeline_name,
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'message_id': row[0].message_id if isinstance(row, tuple) else row.message_id,
+                'stack_trace': row[0].stack_trace if isinstance(row, tuple) else row.stack_trace,
+            }
+            for row in rows
+        ]
+
+    async def export_sessions(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export sessions as list of dictionaries for CSV conversion"""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringSession.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringSession.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringSession.start_time >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringSession.start_time <= end_time)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringSession).order_by(
+            persistence_monitoring.MonitoringSession.last_activity.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'bot_id': row[0].bot_id if isinstance(row, tuple) else row.bot_id,
+                'bot_name': row[0].bot_name if isinstance(row, tuple) else row.bot_name,
+                'pipeline_id': row[0].pipeline_id if isinstance(row, tuple) else row.pipeline_id,
+                'pipeline_name': row[0].pipeline_name if isinstance(row, tuple) else row.pipeline_name,
+                'message_count': row[0].message_count if isinstance(row, tuple) else row.message_count,
+                'start_time': self._format_timestamp(row[0].start_time if isinstance(row, tuple) else row.start_time),
+                'last_activity': self._format_timestamp(
+                    row[0].last_activity if isinstance(row, tuple) else row.last_activity
+                ),
+                'is_active': str(row[0].is_active if isinstance(row, tuple) else row.is_active),
+                'platform': row[0].platform if isinstance(row, tuple) else row.platform,
+                'user_id': row[0].user_id if isinstance(row, tuple) else row.user_id,
+            }
+            for row in rows
+        ]
+
+    # ========== Feedback Methods ==========
+
+    async def record_feedback(
+        self,
+        feedback_id: str,
+        feedback_type: int,
+        feedback_content: str | None = None,
+        inaccurate_reasons: list[str] | None = None,
+        bot_id: str | None = None,
+        bot_name: str | None = None,
+        pipeline_id: str | None = None,
+        pipeline_name: str | None = None,
+        session_id: str | None = None,
+        message_id: str | None = None,
+        stream_id: str | None = None,
+        user_id: str | None = None,
+        platform: str | None = None,
+    ) -> str:
+        """Record user feedback (like/dislike) from AI Bot conversation.
+
+        Args:
+            feedback_id: Unique feedback identifier from platform (e.g., WeChat Work)
+            feedback_type: 1 = like (thumbs up), 2 = dislike (thumbs down)
+            feedback_content: Optional user feedback text
+            inaccurate_reasons: List of reasons for inaccurate response (for dislike)
+            bot_id: Bot ID
+            bot_name: Bot name
+            pipeline_id: Pipeline ID
+            pipeline_name: Pipeline name
+            session_id: Session ID
+            message_id: Message ID
+            stream_id: Stream ID (for WeChat Work streaming messages)
+            user_id: User ID
+            platform: Platform name (e.g., 'wecom')
+
+        Returns:
+            The record ID
+        """
+        import json
+
+        now = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+        reasons_json = json.dumps(inaccurate_reasons, ensure_ascii=False) if inaccurate_reasons else None
+
+        MonitoringFeedback = persistence_monitoring.MonitoringFeedback
+
+        # Handle cancel feedback (type=3): delete existing record
+        if feedback_type == 3:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(MonitoringFeedback).where(MonitoringFeedback.feedback_id == feedback_id)
+            )
+            return None
+
+        # Check if record with this feedback_id already exists
+        existing_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(MonitoringFeedback).where(MonitoringFeedback.feedback_id == feedback_id)
+        )
+        existing_row = existing_result.first()
+
+        if existing_row:
+            # UPDATE existing record
+            existing = existing_row[0] if isinstance(existing_row, tuple) else existing_row
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(MonitoringFeedback)
+                .where(MonitoringFeedback.feedback_id == feedback_id)
+                .values(
+                    timestamp=now,
+                    feedback_type=feedback_type,
+                    feedback_content=feedback_content,
+                    inaccurate_reasons=reasons_json,
+                    bot_id=bot_id or existing.bot_id,
+                    bot_name=bot_name or existing.bot_name,
+                    pipeline_id=pipeline_id or existing.pipeline_id,
+                    pipeline_name=pipeline_name or existing.pipeline_name,
+                    session_id=session_id or existing.session_id,
+                    message_id=message_id or existing.message_id,
+                    stream_id=stream_id or existing.stream_id,
+                    user_id=user_id or existing.user_id,
+                    platform=platform or existing.platform,
+                )
+            )
+            return existing.id
+        else:
+            # INSERT new record with IntegrityError defense
+            record_id = str(uuid.uuid4())
+            record_data = {
+                'id': record_id,
+                'timestamp': now,
+                'feedback_id': feedback_id,
+                'feedback_type': feedback_type,
+                'feedback_content': feedback_content,
+                'inaccurate_reasons': reasons_json,
+                'bot_id': bot_id,
+                'bot_name': bot_name,
+                'pipeline_id': pipeline_id,
+                'pipeline_name': pipeline_name,
+                'session_id': session_id,
+                'message_id': message_id,
+                'stream_id': stream_id,
+                'user_id': user_id,
+                'platform': platform,
+            }
+            try:
+                await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(MonitoringFeedback).values(record_data))
+                return record_id
+            except Exception:
+                # UNIQUE constraint conflict (concurrent feedback for same feedback_id)
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.update(MonitoringFeedback)
+                    .where(MonitoringFeedback.feedback_id == feedback_id)
+                    .values(
+                        timestamp=now,
+                        feedback_type=feedback_type,
+                        feedback_content=feedback_content,
+                        inaccurate_reasons=reasons_json,
+                    )
+                )
+                return feedback_id
+
+    async def get_feedback_stats(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+    ) -> dict:
+        """Get feedback statistics.
+
+        Returns:
+            Dictionary with total likes, dislikes, and breakdown by bot/pipeline
+        """
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp <= end_time)
+
+        # Get total likes (feedback_type = 1)
+        likes_query = sqlalchemy.select(sqlalchemy.func.count(persistence_monitoring.MonitoringFeedback.id)).where(
+            persistence_monitoring.MonitoringFeedback.feedback_type == 1
+        )
+        if conditions:
+            likes_query = likes_query.where(sqlalchemy.and_(*conditions))
+        likes_result = await self.ap.persistence_mgr.execute_async(likes_query)
+        total_likes = likes_result.scalar() or 0
+
+        # Get total dislikes (feedback_type = 2)
+        dislikes_query = sqlalchemy.select(sqlalchemy.func.count(persistence_monitoring.MonitoringFeedback.id)).where(
+            persistence_monitoring.MonitoringFeedback.feedback_type == 2
+        )
+        if conditions:
+            dislikes_query = dislikes_query.where(sqlalchemy.and_(*conditions))
+        dislikes_result = await self.ap.persistence_mgr.execute_async(dislikes_query)
+        total_dislikes = dislikes_result.scalar() or 0
+
+        # Get total feedback count
+        total_query = sqlalchemy.select(sqlalchemy.func.count(persistence_monitoring.MonitoringFeedback.id))
+        if conditions:
+            total_query = total_query.where(sqlalchemy.and_(*conditions))
+        total_result = await self.ap.persistence_mgr.execute_async(total_query)
+        total_feedback = total_result.scalar() or 0
+
+        # Calculate satisfaction rate
+        satisfaction_rate = (total_likes / total_feedback * 100) if total_feedback > 0 else 0
+
+        # Get feedback by bot
+        bot_stats_query = sqlalchemy.select(
+            persistence_monitoring.MonitoringFeedback.bot_id,
+            persistence_monitoring.MonitoringFeedback.bot_name,
+            sqlalchemy.func.count(persistence_monitoring.MonitoringFeedback.id).label('total'),
+            sqlalchemy.func.sum(
+                sqlalchemy.case((persistence_monitoring.MonitoringFeedback.feedback_type == 1, 1), else_=0)
+            ).label('likes'),
+            sqlalchemy.func.sum(
+                sqlalchemy.case((persistence_monitoring.MonitoringFeedback.feedback_type == 2, 1), else_=0)
+            ).label('dislikes'),
+        ).group_by(
+            persistence_monitoring.MonitoringFeedback.bot_id,
+            persistence_monitoring.MonitoringFeedback.bot_name,
+        )
+        if conditions:
+            bot_stats_query = bot_stats_query.where(sqlalchemy.and_(*conditions))
+        bot_stats_result = await self.ap.persistence_mgr.execute_async(bot_stats_query)
+        bot_stats = [
+            {
+                'bot_id': row.bot_id,
+                'bot_name': row.bot_name,
+                'total': row.total,
+                'likes': row.likes or 0,
+                'dislikes': row.dislikes or 0,
+            }
+            for row in bot_stats_result.all()
+        ]
+
+        return {
+            'total_feedback': total_feedback,
+            'total_likes': total_likes,
+            'total_dislikes': total_dislikes,
+            'satisfaction_rate': round(satisfaction_rate, 2),
+            'by_bot': bot_stats,
+        }
+
+    async def get_feedback_list(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        feedback_type: int | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100,
+        offset: int = 0,
+    ) -> tuple[list[dict], int]:
+        """Get feedback list with filters."""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.pipeline_id.in_(pipeline_ids))
+        if feedback_type is not None:
+            conditions.append(persistence_monitoring.MonitoringFeedback.feedback_type == feedback_type)
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp <= end_time)
+
+        # Get total count
+        count_query = sqlalchemy.select(sqlalchemy.func.count(persistence_monitoring.MonitoringFeedback.id))
+        if conditions:
+            count_query = count_query.where(sqlalchemy.and_(*conditions))
+        count_result = await self.ap.persistence_mgr.execute_async(count_query)
+        total = count_result.scalar() or 0
+
+        # Get feedback list
+        query = sqlalchemy.select(persistence_monitoring.MonitoringFeedback).order_by(
+            persistence_monitoring.MonitoringFeedback.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+        query = query.limit(limit).offset(offset)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return (
+            [
+                self.ap.persistence_mgr.serialize_model(
+                    persistence_monitoring.MonitoringFeedback, row[0] if isinstance(row, tuple) else row
+                )
+                for row in rows
+            ],
+            total,
+        )
+
+    async def export_feedback(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100000,
+    ) -> list[dict]:
+        """Export feedback as list of dictionaries for CSV conversion."""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringFeedback.pipeline_id.in_(pipeline_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringFeedback.timestamp <= end_time)
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringFeedback).order_by(
+            persistence_monitoring.MonitoringFeedback.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+        query = query.limit(limit)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        rows = result.all()
+
+        return [
+            {
+                'id': row[0].id if isinstance(row, tuple) else row.id,
+                'timestamp': self._format_timestamp(row[0].timestamp if isinstance(row, tuple) else row.timestamp),
+                'feedback_id': row[0].feedback_id if isinstance(row, tuple) else row.feedback_id,
+                'feedback_type': 'like'
+                if (row[0].feedback_type if isinstance(row, tuple) else row.feedback_type) == 1
+                else 'dislike',
+                'feedback_content': row[0].feedback_content if isinstance(row, tuple) else row.feedback_content,
+                'inaccurate_reasons': row[0].inaccurate_reasons if isinstance(row, tuple) else row.inaccurate_reasons,
+                'bot_id': row[0].bot_id if isinstance(row, tuple) else row.bot_id,
+                'bot_name': row[0].bot_name if isinstance(row, tuple) else row.bot_name,
+                'pipeline_id': row[0].pipeline_id if isinstance(row, tuple) else row.pipeline_id,
+                'pipeline_name': row[0].pipeline_name if isinstance(row, tuple) else row.pipeline_name,
+                'session_id': row[0].session_id if isinstance(row, tuple) else row.session_id,
+                'message_id': row[0].message_id if isinstance(row, tuple) else row.message_id,
+                'stream_id': row[0].stream_id if isinstance(row, tuple) else row.stream_id,
+                'user_id': row[0].user_id if isinstance(row, tuple) else row.user_id,
+                'platform': row[0].platform if isinstance(row, tuple) else row.platform,
+            }
+            for row in rows
+        ]

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()
@@ -153,6 +161,14 @@ class PipelineService:
 
     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(

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

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import uuid
+import traceback
 
 import sqlalchemy
 
@@ -97,6 +98,14 @@ class ModelProviderService:
         if embedding_result.first() is not None:
             raise ValueError('Cannot delete provider: Embedding models still reference it')
 
+        rerank_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.RerankModel).where(
+                persistence_model.RerankModel.provider_uuid == provider_uuid
+            )
+        )
+        if rerank_result.first() is not None:
+            raise ValueError('Cannot delete provider: Rerank models still reference it')
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.delete(persistence_model.ModelProvider).where(
                 persistence_model.ModelProvider.uuid == provider_uuid
@@ -121,7 +130,14 @@ class ModelProviderService:
         )
         embedding_count = embedding_result.scalar() or 0
 
-        return {'llm_count': llm_count, 'embedding_count': embedding_count}
+        rerank_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(sqlalchemy.func.count())
+            .select_from(persistence_model.RerankModel)
+            .where(persistence_model.RerankModel.provider_uuid == provider_uuid)
+        )
+        rerank_count = rerank_result.scalar() or 0
+
+        return {'llm_count': llm_count, 'embedding_count': embedding_count, 'rerank_count': rerank_count}
 
     async def find_or_create_provider(self, requester: str, base_url: str, api_keys: list) -> str:
         """Find existing provider or create new one"""
@@ -164,3 +180,66 @@ class ModelProviderService:
             .values(api_keys=[api_key])
         )
         await self.ap.model_mgr.reload_provider('00000000-0000-0000-0000-000000000000')
+
+    async def scan_provider_models(self, provider_uuid: str, model_type: str | None = None) -> dict:
+        provider = await self.get_provider(provider_uuid)
+        if provider is None:
+            raise ValueError('provider not found')
+
+        runtime_provider = await self.ap.model_mgr.load_provider(provider)
+
+        try:
+            scan_result = await runtime_provider.requester.scan_models(
+                runtime_provider.token_mgr.get_token() if runtime_provider.token_mgr.tokens else None
+            )
+        except NotImplementedError:
+            raise ValueError('current provider does not support model scanning')
+        except Exception as exc:
+            self.ap.logger.warning(
+                f'Failed to scan models for provider {provider_uuid}: {exc}\n{traceback.format_exc()}'
+            )
+            raise ValueError(str(exc)) from exc
+
+        if isinstance(scan_result, dict):
+            scanned_models = scan_result.get('models', [])
+            debug_info = scan_result.get('debug')
+        else:
+            scanned_models = scan_result
+            debug_info = None
+
+        llm_models = await self.ap.llm_model_service.get_llm_models_by_provider(provider_uuid)
+        embedding_models = await self.ap.embedding_models_service.get_embedding_models_by_provider(provider_uuid)
+        existing_llm_names = {model['name'] for model in llm_models}
+        existing_embedding_names = {model['name'] for model in embedding_models}
+
+        filtered_models = []
+        for model in scanned_models:
+            scanned_type = model.get('type', 'llm')
+            if model_type and scanned_type != model_type:
+                continue
+
+            model_name = model.get('name') or model.get('id')
+            if not model_name:
+                continue
+
+            filtered_models.append(
+                {
+                    'id': model.get('id', model_name),
+                    'name': model_name,
+                    'type': scanned_type,
+                    'abilities': model.get('abilities', []),
+                    'display_name': model.get('display_name'),
+                    'description': model.get('description'),
+                    'context_length': model.get('context_length'),
+                    'owned_by': model.get('owned_by'),
+                    'input_modalities': model.get('input_modalities', []),
+                    'output_modalities': model.get('output_modalities', []),
+                    'already_added': (
+                        model_name in existing_embedding_names
+                        if scanned_type == 'embedding'
+                        else model_name in existing_llm_names
+                    ),
+                }
+            )
+
+        return {'models': filtered_models, 'debug': debug_info}

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

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-import aiohttp
+from langbot.pkg.utils import httpclient
 import typing
 import datetime
 import time
@@ -99,49 +99,49 @@ class SpaceService:
         space_config = self._get_space_config()
         space_url = space_config['url']
 
-        async with aiohttp.ClientSession() as 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', {})
+        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']
 
-        async with aiohttp.ClientSession() as 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', {})
+        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']
 
-        async with aiohttp.ClientSession() as 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', {})
+        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 ===
 
@@ -178,12 +178,12 @@ class SpaceService:
         space_config = self._get_space_config()
         space_url = space_config['url']
 
-        async with aiohttp.ClientSession() as 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]
+        session = httpclient.get_session()
+        async with session.get(f'{space_url}/api/v1/models', params={'page_size': 100}) 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

@@ -65,8 +65,8 @@ class UserService:
 
         user_obj = result_list[0]
 
-        # Check if this is a Space account
-        if user_obj.account_type == 'space':
+        # Check if this user has a local password set
+        if not user_obj.password:
             raise ValueError('请使用 Space 账户登录')
 
         ph = argon2.PasswordHasher()
@@ -108,9 +108,8 @@ 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')
+        if not user_obj.password:
+            raise ValueError('No local password set, please set a password first')
 
         ph.verify(user_obj.password, current_password)
 

src/langbot/pkg/core/app.py

@@ -9,12 +9,14 @@ 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
@@ -28,16 +30,19 @@ 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 external_kb as external_kb_service
 from ..api.http.service import monitoring as monitoring_service
+from ..api.http.service import maintenance as maintenance_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:
@@ -61,6 +66,7 @@ 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
@@ -96,6 +102,8 @@ class Application:
 
     query_pool: pool.QueryPool = None
 
+    msg_aggregator: message_aggregator.MessageAggregator = None
+
     ctrl: controller.Controller = None
 
     pipeline_mgr: pipelinemgr.PipelineManager = None
@@ -126,6 +134,8 @@ class Application:
 
     embedding_models_service: model_service.EmbeddingModelsService = None
 
+    rerank_models_service: model_service.RerankModelsService = None
+
     provider_service: provider_service.ModelProviderService = None
 
     pipeline_service: pipeline_service.PipelineService = None
@@ -134,8 +144,6 @@ class Application:
 
     knowledge_service: knowledge_service.KnowledgeService = None
 
-    external_kb_service: external_kb_service.ExternalKBService = None
-
     mcp_service: mcp_service.MCPService = None
 
     apikey_service: apikey_service.ApiKeyService = None
@@ -144,8 +152,12 @@ class Application:
 
     telemetry: telemetry_module.TelemetryManager = None
 
+    survey: survey_module.SurveyManager = None
+
     monitoring_service: monitoring_service.MonitoringService = None
 
+    maintenance_service: maintenance_service.MaintenanceService = None
+
     def __init__(self):
         pass
 
@@ -181,6 +193,77 @@ 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 = self._get_positive_int_config(
+                    auto_cleanup_cfg.get('retention_days', 30),
+                    default=30,
+                    name='monitoring.auto_cleanup.retention_days',
+                )
+                delete_batch_size = self._get_positive_int_config(
+                    auto_cleanup_cfg.get('delete_batch_size', 1000),
+                    default=1000,
+                    name='monitoring.auto_cleanup.delete_batch_size',
+                )
+                check_interval_hours = self._get_positive_float_config(
+                    auto_cleanup_cfg.get('check_interval_hours', 1),
+                    default=1,
+                    name='monitoring.auto_cleanup.check_interval_hours',
+                )
+
+                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,
+                                batch_size=delete_batch_size,
+                            )
+                            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],
+                )
+
+            # Start storage/log maintenance task if enabled
+            storage_cleanup_cfg = self.instance_config.data.get('storage', {}).get('cleanup', {})
+            if storage_cleanup_cfg.get('enabled', True) and self.maintenance_service is not None:
+                check_interval_hours = self._get_positive_float_config(
+                    storage_cleanup_cfg.get('check_interval_hours', 1),
+                    default=1,
+                    name='storage.cleanup.check_interval_hours',
+                )
+
+                async def storage_cleanup_loop():
+                    check_interval_seconds = check_interval_hours * 3600
+                    while True:
+                        try:
+                            deleted = await self.maintenance_service.cleanup_expired_files()
+                            total_deleted = sum(deleted.values())
+                            if total_deleted > 0:
+                                self.logger.info(f'Storage maintenance: deleted expired files: {deleted}')
+                        except Exception as e:
+                            self.logger.warning(f'Storage maintenance error: {e}')
+                        await asyncio.sleep(check_interval_seconds)
+
+                self.task_mgr.create_task(
+                    storage_cleanup_loop(),
+                    name='storage-maintenance',
+                    scopes=[core_entities.LifecycleControlScope.APPLICATION],
+                )
+
             self.task_mgr.create_task(
                 never_ending(),
                 name='never-ending-task',
@@ -195,6 +278,28 @@ class Application:
             self.logger.error(f'Application runtime fatal exception: {e}')
             self.logger.debug(f'Traceback: {traceback.format_exc()}')
 
+    def _get_positive_int_config(self, value, default: int, name: str) -> int:
+        try:
+            parsed = int(value)
+        except (TypeError, ValueError):
+            self.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        if parsed < 1:
+            self.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        return parsed
+
+    def _get_positive_float_config(self, value, default: float, name: str) -> float:
+        try:
+            parsed = float(value)
+        except (TypeError, ValueError):
+            self.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        if parsed <= 0:
+            self.logger.warning(f'Invalid {name}: {value!r}, using {default}')
+            return default
+        return parsed
+
     def dispose(self):
         self.plugin_connector.dispose()
 

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/stages/build_app.py

@@ -5,12 +5,14 @@ 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
@@ -25,14 +27,15 @@ 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 external_kb as external_kb_service
 from ...api.http.service import monitoring as monitoring_service
+from ...api.http.service import maintenance as maintenance_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')
@@ -59,6 +62,9 @@ class BuildAppStage(stage.BootingStage):
         embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
         ap.embedding_models_service = embedding_models_service_inst
 
+        rerank_models_service_inst = model_service.RerankModelsService(ap)
+        ap.rerank_models_service = rerank_models_service_inst
+
         provider_service_inst = provider_service.ModelProviderService(ap)
         ap.provider_service = provider_service_inst
 
@@ -71,9 +77,6 @@ class BuildAppStage(stage.BootingStage):
         knowledge_service_inst = knowledge_service.KnowledgeService(ap)
         ap.knowledge_service = knowledge_service_inst
 
-        external_kb_service_inst = external_kb_service.ExternalKBService(ap)
-        ap.external_kb_service = external_kb_service_inst
-
         mcp_service_inst = mcp_service.MCPService(ap)
         ap.mcp_service = mcp_service_inst
 
@@ -109,6 +112,11 @@ class BuildAppStage(stage.BootingStage):
         await telemetry_inst.initialize()
         ap.telemetry = telemetry_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
@@ -137,10 +145,17 @@ 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()
@@ -153,6 +168,9 @@ class BuildAppStage(stage.BootingStage):
         monitoring_service_inst = monitoring_service.MonitoringService(ap)
         ap.monitoring_service = monitoring_service_inst
 
+        maintenance_service_inst = maintenance_service.MaintenanceService(ap)
+        ap.maintenance_service = maintenance_service_inst
+
         async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
             await asyncio.sleep(3)
             await plugin_connector_inst.initialize()

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

@@ -74,20 +74,30 @@ 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], list):
+                        # Convert comma-separated string to list
+                        # e.g., SYSTEM__DISABLED_ADAPTERS="aiocqhttp,dingtalk"
+                        current[key] = [item.strip() for item in env_value.split(',') if item.strip()]
+                    elif isinstance(current[key], dict):
+                        # Skip dict 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
@@ -146,18 +156,54 @@ class LoadConfigStage(stage.BootingStage):
         await ap.instance_config.dump_config()
 
         # load or generate instance id
-        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,
-        )
+        # 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', '')
 
-        constants.instance_id = ap.instance_id.data['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()
 

src/langbot/pkg/core/taskmgr.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import asyncio
 import typing
 import datetime
+import time
 
 from . import app
 from . import entities as core_entities
@@ -17,9 +18,13 @@ class TaskContext:
     log: str
     """Log"""
 
+    metadata: dict
+    """Structured metadata for progress reporting"""
+
     def __init__(self):
         self.current_action = 'default'
         self.log = ''
+        self.metadata = {}
 
     def _log(self, msg: str):
         self.log += msg + '\n'
@@ -38,7 +43,7 @@ class TaskContext:
         self._log(f'{datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")} | {self.current_action} | {msg}')
 
     def to_dict(self) -> dict:
-        return {'current_action': self.current_action, 'log': self.log}
+        return {'current_action': self.current_action, 'log': self.log, 'metadata': self.metadata}
 
     @staticmethod
     def new() -> TaskContext:
@@ -115,6 +120,7 @@ class TaskWrapper:
         self.label = label if label != '' else name
         self.task.set_name(name)
         self.scopes = scopes
+        self.created_at = time.time()
 
     def assume_exception(self):
         try:
@@ -150,6 +156,7 @@ class TaskWrapper:
             'name': self.name,
             'label': self.label,
             'scopes': [scope.value for scope in self.scopes],
+            'created_at': self.created_at,
             'task_context': self.task_context.to_dict(),
             'runtime': {
                 'done': self.task.done(),
@@ -189,6 +196,8 @@ class AsyncTaskManager:
     ) -> TaskWrapper:
         wrapper = TaskWrapper(self.ap, coro, task_type, kind, name, label, context, scopes)
         self.tasks.append(wrapper)
+        wrapper.task.add_done_callback(lambda _: self._prune_completed_tasks())
+        self._prune_completed_tasks()
         return wrapper
 
     def create_user_task(
@@ -211,9 +220,23 @@ class AsyncTaskManager:
     def get_tasks_dict(
         self,
         type: str = None,
+        kind: str = None,
     ) -> dict:
         return {
-            'tasks': [t.to_dict() for t in self.tasks if type is None or t.task_type == type],
+            'tasks': [
+                t.to_dict()
+                for t in self.tasks
+                if (type is None or t.task_type == type) and (kind is None or t.kind == kind)
+            ],
+            'id_index': TaskWrapper._id_index,
+        }
+
+    def get_stats(self) -> dict:
+        completed = sum(1 for t in self.tasks if t.task.done())
+        return {
+            'total': len(self.tasks),
+            'running': len(self.tasks) - completed,
+            'completed': completed,
             'id_index': TaskWrapper._id_index,
         }
 
@@ -234,3 +257,27 @@ class AsyncTaskManager:
                 if not wrapper.task.done():
                     wrapper.task.cancel()
                 return
+
+    def _prune_completed_tasks(self):
+        completed_limit = (
+            self.ap.instance_config.data.get('system', {})
+            .get('task_retention', {})
+            .get(
+                'completed_limit',
+                200,
+            )
+        )
+        try:
+            completed_limit = int(completed_limit)
+        except (TypeError, ValueError):
+            completed_limit = 200
+        if completed_limit < 1:
+            completed_limit = 1
+
+        completed_tasks = [wrapper for wrapper in self.tasks if wrapper.task.done()]
+        overflow = len(completed_tasks) - completed_limit
+        if overflow <= 0:
+            return
+
+        remove_ids = {wrapper.id for wrapper in completed_tasks[:overflow]}
+        self.tasks = [wrapper for wrapper in self.tasks if wrapper.id not in remove_ids]

src/langbot/pkg/discover/engine.py

@@ -17,11 +17,23 @@ class I18nString(pydantic.BaseModel):
     """英文"""
 
     zh_Hans: typing.Optional[str] = None
-    """中文"""
+    """简体中文"""
+
+    zh_Hant: typing.Optional[str] = None
+    """繁体中文"""
 
     ja_JP: typing.Optional[str] = None
     """日文"""
 
+    th_TH: typing.Optional[str] = None
+    """泰文"""
+
+    vi_VN: typing.Optional[str] = None
+    """越南文"""
+
+    es_ES: typing.Optional[str] = None
+    """西班牙文"""
+
     def to_dict(self) -> dict:
         """转换为字典"""
         dic = {}
@@ -29,8 +41,16 @@ class I18nString(pydantic.BaseModel):
             dic['en_US'] = self.en_US
         if self.zh_Hans is not None:
             dic['zh_Hans'] = self.zh_Hans
+        if self.zh_Hant is not None:
+            dic['zh_Hant'] = self.zh_Hant
         if self.ja_JP is not None:
             dic['ja_JP'] = self.ja_JP
+        if self.th_TH is not None:
+            dic['th_TH'] = self.th_TH
+        if self.vi_VN is not None:
+            dic['vi_VN'] = self.vi_VN
+        if self.es_ES is not None:
+            dic['es_ES'] = self.es_ES
         return dic
 
 

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

@@ -16,6 +16,7 @@ class Bot(Base):
     enable = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
     use_pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
     use_pipeline_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    pipeline_routing_rules = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, server_default='[]')
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(
         sqlalchemy.DateTime,

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

@@ -59,3 +59,22 @@ class EmbeddingModel(Base):
         server_default=sqlalchemy.func.now(),
         onupdate=sqlalchemy.func.now(),
     )
+
+
+class RerankModel(Base):
+    """Rerank model"""
+
+    __tablename__ = 'rerank_models'
+
+    uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
+    name = sqlalchemy.Column(sqlalchemy.String(255), 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,
+        nullable=False,
+        server_default=sqlalchemy.func.now(),
+        onupdate=sqlalchemy.func.now(),
+    )

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

@@ -20,8 +20,10 @@ class MonitoringMessage(Base):
     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):
@@ -63,6 +65,7 @@ class MonitoringSession(Base):
     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):
@@ -103,3 +106,26 @@ class MonitoringEmbeddingCall(Base):
     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
+
+
+class MonitoringFeedback(Base):
+    """User feedback records (like/dislike) from AI Bot conversations"""
+
+    __tablename__ = 'monitoring_feedback'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    feedback_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, unique=True, index=True)
+    feedback_type = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)  # 1=like, 2=dislike
+    feedback_content = sqlalchemy.Column(sqlalchemy.Text, nullable=True)  # User feedback text
+    inaccurate_reasons = sqlalchemy.Column(sqlalchemy.Text, nullable=True)  # JSON list of inaccurate reasons
+    # Context fields
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    stream_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    user_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
+    platform = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)  # e.g., wecom

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

@@ -10,8 +10,21 @@ class KnowledgeBase(Base):
     emoji = sqlalchemy.Column(sqlalchemy.String(10), nullable=True, default='📚')
     created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())
     updated_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now(), onupdate=sqlalchemy.func.now())
-    embedding_model_uuid = sqlalchemy.Column(sqlalchemy.String, default='')
-    top_k = sqlalchemy.Column(sqlalchemy.Integer, default=5)
+    # 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):
@@ -29,16 +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 ExternalKnowledgeBase(Base):
-    __tablename__ = 'external_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='🔗')
-    plugin_author = sqlalchemy.Column(sqlalchemy.String, nullable=False)
-    plugin_name = sqlalchemy.Column(sqlalchemy.String, nullable=False)
-    retriever_name = sqlalchemy.Column(sqlalchemy.String, nullable=False)
-    retriever_config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
-    created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())

src/langbot/pkg/persistence/alembic/env.py

@@ -0,0 +1,51 @@
+"""Alembic environment for LangBot.
+
+This env.py is designed to be called programmatically (not via CLI).
+It supports both SQLite and PostgreSQL.
+
+The sync connection is passed via config attributes by the runner.
+"""
+
+from __future__ import annotations
+
+from alembic import context
+from sqlalchemy.engine import Connection
+
+from langbot.pkg.entity.persistence.base import Base
+
+target_metadata = Base.metadata
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode — emit SQL without a live connection."""
+    url = context.config.get_main_option('sqlalchemy.url')
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={'paramstyle': 'named'},
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations with a live sync connection passed via config attributes."""
+    connection: Connection = context.config.attributes.get('connection')
+    if connection is None:
+        raise RuntimeError('connection not provided in alembic config attributes')
+
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,
+        # render_as_batch=True is critical for SQLite ALTER TABLE support
+        render_as_batch=True,
+    )
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

src/langbot/pkg/persistence/alembic/script.py.mako

@@ -0,0 +1,24 @@
+# Alembic script.py.mako — template for auto-generated revisions
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

src/langbot/pkg/persistence/alembic/versions/0001_baseline.py

@@ -0,0 +1,24 @@
+"""baseline: stamp existing schema (db version 25)
+
+This is a no-op migration that marks the starting point for Alembic.
+All tables already exist via create_all() + legacy DBMigration system.
+
+Revision ID: 0001_baseline
+Revises: None
+Create Date: 2026-04-08
+"""
+
+revision = '0001_baseline'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # No-op: existing schema is already at database_version=25
+    # This revision serves as the Alembic baseline.
+    pass
+
+
+def downgrade() -> None:
+    pass

src/langbot/pkg/persistence/alembic/versions/0002_sample.py

@@ -0,0 +1,62 @@
+"""example: sample migration demonstrating Alembic patterns
+
+This is a SAMPLE showing how to write migrations that work
+seamlessly across SQLite and PostgreSQL. Delete or adapt as needed.
+
+Revision ID: 0002_sample
+Revises: 0001_baseline
+Create Date: 2026-04-08
+
+Patterns demonstrated:
+  1. Schema change (add column) — works on both DBs via render_as_batch
+  2. Data migration (read + modify JSON) — pure SQLAlchemy, no dialect branching
+"""
+
+revision = '0002_sample'
+down_revision = '0001_baseline'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    """
+    EXAMPLE: Uncomment to use. This shows the patterns.
+
+    # --- Pattern 1: Schema change (add/drop column) ---
+    # render_as_batch=True in env.py makes this work on SQLite too.
+    #
+    # op.add_column('pipelines', sa.Column('description', sa.String(512), server_default=''))
+
+    # --- Pattern 2: Data migration (read + modify JSON field) ---
+    # No if/else for sqlite vs postgres needed!
+    #
+    # conn = op.get_bind()
+    # rows = conn.execute(sa.text("SELECT uuid, config FROM pipelines")).fetchall()
+    # for row in rows:
+    #     config = json.loads(row[1]) if isinstance(row[1], str) else row[1]
+    #     # Modify the config
+    #     config.setdefault('ai', {}).setdefault('some_new_key', 'default_value')
+    #     conn.execute(
+    #         sa.text("UPDATE pipelines SET config = :cfg WHERE uuid = :uuid"),
+    #         {"cfg": json.dumps(config), "uuid": row[0]}
+    #     )
+
+    # --- Pattern 3: Create a new table ---
+    #
+    # op.create_table(
+    #     'audit_log',
+    #     sa.Column('id', sa.Integer, primary_key=True, autoincrement=True),
+    #     sa.Column('action', sa.String(255), nullable=False),
+    #     sa.Column('detail', sa.Text),
+    #     sa.Column('created_at', sa.DateTime, server_default=sa.func.now()),
+    # )
+    """
+    pass
+
+
+def downgrade() -> None:
+    """
+    # op.drop_column('pipelines', 'description')
+    # op.drop_table('audit_log')
+    """
+    pass

src/langbot/pkg/persistence/alembic/versions/0003_add_rerank_models.py

@@ -0,0 +1,35 @@
+"""add rerank_models table
+
+Revision ID: 0003_add_rerank_models
+Revises: 0002_sample
+Create Date: 2026-04-19
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = '0003_add_rerank_models'
+down_revision = '0002_sample'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Check if table already exists (may have been created by create_all())
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    if 'rerank_models' not in inspector.get_table_names():
+        op.create_table(
+            'rerank_models',
+            sa.Column('uuid', sa.String(255), primary_key=True, unique=True),
+            sa.Column('name', sa.String(255), nullable=False),
+            sa.Column('provider_uuid', sa.String(255), nullable=False),
+            sa.Column('extra_args', sa.JSON, nullable=False, server_default='{}'),
+            sa.Column('prefered_ranking', sa.Integer, nullable=False, server_default='0'),
+            sa.Column('created_at', sa.DateTime, nullable=False, server_default=sa.func.now()),
+            sa.Column('updated_at', sa.DateTime, nullable=False, server_default=sa.func.now()),
+        )
+
+
+def downgrade() -> None:
+    op.drop_table('rerank_models')

src/langbot/pkg/persistence/alembic_runner.py

@@ -0,0 +1,150 @@
+"""Programmatic Alembic runner for LangBot.
+
+Usage from async code:
+    from langbot.pkg.persistence.alembic_runner import run_alembic_upgrade
+    await run_alembic_upgrade(async_engine)
+
+CLI usage (autogenerate):
+    python -m langbot.pkg.persistence.alembic_runner autogenerate "add description column"
+    python -m langbot.pkg.persistence.alembic_runner upgrade
+    python -m langbot.pkg.persistence.alembic_runner current
+"""
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING
+
+from alembic.config import Config
+from alembic import command
+from alembic.runtime.migration import MigrationContext
+
+if TYPE_CHECKING:
+    from sqlalchemy.ext.asyncio import AsyncEngine
+    from sqlalchemy.engine import Connection
+
+
+_ALEMBIC_DIR = os.path.join(os.path.dirname(__file__), 'alembic')
+
+
+def _build_config(connection: Connection) -> Config:
+    """Build an Alembic Config with sync connection attached."""
+    cfg = Config()
+    cfg.set_main_option('script_location', _ALEMBIC_DIR)
+    cfg.attributes['connection'] = connection
+    return cfg
+
+
+def _do_upgrade(connection: Connection, revision: str = 'head') -> None:
+    """Synchronous upgrade — runs inside run_sync."""
+    cfg = _build_config(connection)
+    command.upgrade(cfg, revision)
+
+
+def _do_stamp(connection: Connection, revision: str = 'head') -> None:
+    """Synchronous stamp — runs inside run_sync."""
+    cfg = _build_config(connection)
+    command.stamp(cfg, revision)
+
+
+def _do_get_current(connection: Connection) -> str | None:
+    """Get current alembic revision synchronously."""
+    ctx = MigrationContext.configure(connection)
+    return ctx.get_current_revision()
+
+
+def _do_autogenerate(connection: Connection, message: str = 'auto migration') -> None:
+    """Synchronous autogenerate — runs inside run_sync."""
+    cfg = _build_config(connection)
+    command.revision(cfg, message=message, autogenerate=True)
+
+
+async def run_alembic_upgrade(async_engine: AsyncEngine, revision: str = 'head') -> None:
+    """Run Alembic upgrade to the given revision."""
+    async with async_engine.connect() as conn:
+        await conn.run_sync(_do_upgrade, revision)
+        await conn.commit()
+
+
+async def run_alembic_stamp(async_engine: AsyncEngine, revision: str = 'head') -> None:
+    """Stamp the database with a revision without running migrations."""
+    async with async_engine.connect() as conn:
+        await conn.run_sync(_do_stamp, revision)
+        await conn.commit()
+
+
+async def get_alembic_current(async_engine: AsyncEngine) -> str | None:
+    """Get current alembic revision, or None if not stamped."""
+    async with async_engine.connect() as conn:
+        return await conn.run_sync(_do_get_current)
+
+
+async def run_alembic_autogenerate(async_engine: AsyncEngine, message: str = 'auto migration') -> None:
+    """Compare ORM models against DB schema and generate a migration script."""
+    async with async_engine.connect() as conn:
+        await conn.run_sync(_do_autogenerate, message)
+
+
+# CLI entrypoint: python -m langbot.pkg.persistence.alembic_runner <command> [args]
+if __name__ == '__main__':
+    import sys
+    import asyncio
+
+    def _get_engine():
+        """Create engine from data/config.yaml or default SQLite."""
+        from sqlalchemy.ext.asyncio import create_async_engine
+
+        try:
+            import yaml
+
+            with open('data/config.yaml') as f:
+                config = yaml.safe_load(f)
+            db_cfg = config.get('database', {})
+            db_type = db_cfg.get('use', 'sqlite')
+            if db_type == 'postgresql':
+                pg = db_cfg.get('postgresql', {})
+                url = (
+                    f'postgresql+asyncpg://{pg.get("user", "postgres")}:{pg.get("password", "postgres")}'
+                    f'@{pg.get("host", "127.0.0.1")}:{pg.get("port", 5432)}/{pg.get("database", "postgres")}'
+                )
+            else:
+                path = db_cfg.get('sqlite', {}).get('path', 'data/langbot.db')
+                url = f'sqlite+aiosqlite:///{path}'
+        except Exception:
+            url = 'sqlite+aiosqlite:///data/langbot.db'
+
+        return create_async_engine(url)
+
+    def main():
+        if len(sys.argv) < 2:
+            print('Usage: python -m langbot.pkg.persistence.alembic_runner <command> [args]')
+            print('Commands:')
+            print('  autogenerate "message"  — Generate migration from ORM model diff')
+            print('  upgrade [revision]      — Upgrade database (default: head)')
+            print('  stamp [revision]        — Stamp revision without running (default: head)')
+            print('  current                 — Show current revision')
+            sys.exit(1)
+
+        cmd = sys.argv[1]
+        engine = _get_engine()
+
+        if cmd == 'autogenerate':
+            msg = sys.argv[2] if len(sys.argv) > 2 else 'auto migration'
+            asyncio.run(run_alembic_autogenerate(engine, msg))
+            print(f'Migration generated: {msg}')
+        elif cmd == 'upgrade':
+            rev = sys.argv[2] if len(sys.argv) > 2 else 'head'
+            asyncio.run(run_alembic_upgrade(engine, rev))
+            print(f'Upgraded to: {rev}')
+        elif cmd == 'stamp':
+            rev = sys.argv[2] if len(sys.argv) > 2 else 'head'
+            asyncio.run(run_alembic_stamp(engine, rev))
+            print(f'Stamped: {rev}')
+        elif cmd == 'current':
+            rev = asyncio.run(get_alembic_current(engine))
+            print(f'Current revision: {rev}')
+        else:
+            print(f'Unknown command: {cmd}')
+            sys.exit(1)
+
+    main()

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, model as persistence_model
+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 +76,9 @@ class PersistenceManager:
 
             self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
 
-        await self.write_default_pipeline()
+        # Run Alembic migrations (new migration system)
+        await self._run_alembic_migrations()
+
         await self.write_space_model_providers()
 
     async def create_tables(self):
@@ -101,29 +101,6 @@ 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...')
-
-            pipeline_config = json.loads(importutil.read_resource_file('templates/default-pipeline-config.json'))
-
-            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': {},
-            }
-
-            await self.execute_async(sqlalchemy.insert(pipeline.LegacyPipeline).values(pipeline_data))
-
     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'
@@ -161,6 +138,28 @@ class PersistenceManager:
 
     # =================================
 
+    async def _run_alembic_migrations(self):
+        """Run Alembic-based migrations after legacy migrations complete."""
+        from . import alembic_runner
+
+        engine = self.get_db_engine()
+
+        try:
+            current_rev = await alembic_runner.get_alembic_current(engine)
+
+            if current_rev is None:
+                # First time: stamp baseline so Alembic knows existing schema is up-to-date
+                self.ap.logger.info('Alembic: no revision found, stamping baseline...')
+                await alembic_runner.run_alembic_stamp(engine, '0001_baseline')
+                current_rev = '0001_baseline'
+
+            # Upgrade to head
+            await alembic_runner.run_alembic_upgrade(engine, 'head')
+            self.ap.logger.info('Alembic migrations completed.')
+        except Exception as e:
+            self.ap.logger.error(f'Alembic migration failed: {e}', exc_info=True)
+            raise
+
     async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
         async with self.get_db_engine().connect() as conn:
             result = await conn.execute(*args, **kwargs)

src/langbot/pkg/persistence/migrations/dbm019_monitoring_message_role.py

@@ -0,0 +1,24 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(19)
+class DBMigrateMonitoringMessageRole(migration.DBMigration):
+    """Add role column to monitoring_messages table"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        try:
+            sql_text = sqlalchemy.text("ALTER TABLE monitoring_messages ADD COLUMN role VARCHAR(50) DEFAULT 'user'")
+            await self.ap.persistence_mgr.execute_async(sql_text)
+        except Exception:
+            # Column may already exist
+            pass
+
+    async def downgrade(self):
+        """Downgrade"""
+        try:
+            sql_text = sqlalchemy.text('ALTER TABLE monitoring_messages DROP COLUMN role')
+            await self.ap.persistence_mgr.execute_async(sql_text)
+        except Exception:
+            pass

src/langbot/pkg/persistence/migrations/dbm020_knowledge_engine_plugin_architecture.py

@@ -0,0 +1,161 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(20)
+class DBMigrateKnowledgeEnginePluginArchitecture(migration.DBMigration):
+    """Migrate to unified Knowledge Engine plugin architecture.
+
+    Changes:
+    - Backup existing knowledge_bases data to knowledge_bases_backup
+    - Clear knowledge_bases table and add new plugin architecture columns
+    - Drop old columns (PostgreSQL only; SQLite leaves them unmapped)
+    - Preserve external_knowledge_bases table as-is for future migration
+    - Set rag_plugin_migration_needed flag in metadata if old data exists
+    """
+
+    async def upgrade(self):
+        """Upgrade"""
+        has_internal_data = await self._backup_knowledge_bases()
+        has_external_data = await self._check_external_knowledge_bases()
+        await self._clear_knowledge_bases()
+        await self._add_columns_to_knowledge_bases()
+        await self._drop_old_columns()
+        if has_internal_data or has_external_data:
+            await self._set_migration_flag()
+
+    async def _get_table_columns(self, table_name: str) -> list[str]:
+        """Get column names from a table (works for both SQLite and PostgreSQL)."""
+        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 = :table_name;'
+                ).bindparams(table_name=table_name)
+            )
+            return [row[0] for row in result.fetchall()]
+        else:
+            # SQLite PRAGMA does not support bind parameters; validate identifier.
+            if not table_name.isidentifier():
+                raise ValueError(f'Invalid table name: {table_name}')
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text(f'PRAGMA table_info({table_name});'))
+            return [row[1] for row in result.fetchall()]
+
+    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 _backup_knowledge_bases(self) -> bool:
+        """Backup knowledge_bases data. Returns True if data was backed up."""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text('SELECT COUNT(*) FROM knowledge_bases;'))
+        count = result.scalar()
+        if count == 0:
+            return False
+
+        # Drop backup table if it already exists (from a previous failed migration)
+        if await self._table_exists('knowledge_bases_backup'):
+            await self.ap.persistence_mgr.execute_async(sqlalchemy.text('DROP TABLE knowledge_bases_backup;'))
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('CREATE TABLE knowledge_bases_backup AS SELECT * FROM knowledge_bases;')
+        )
+        self.ap.logger.info(
+            'Backed up %d knowledge base(s) to knowledge_bases_backup table.',
+            count,
+        )
+        return True
+
+    async def _check_external_knowledge_bases(self) -> bool:
+        """Check if external_knowledge_bases table exists and has data.
+
+        The table is preserved as-is (not dropped) for future migration.
+        """
+        if not await self._table_exists('external_knowledge_bases'):
+            return False
+
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT COUNT(*) FROM external_knowledge_bases;')
+        )
+        count = result.scalar()
+        if count > 0:
+            self.ap.logger.info(
+                'Found %d external knowledge base(s) in external_knowledge_bases table. '
+                'Table preserved for future migration.',
+                count,
+            )
+        return count > 0
+
+    async def _clear_knowledge_bases(self):
+        """Clear all rows from knowledge_bases table (preserve table structure)."""
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.text('DELETE FROM knowledge_bases;'))
+
+    async def _add_columns_to_knowledge_bases(self):
+        """Add new RAG plugin architecture columns to knowledge_bases table."""
+        columns = await self._get_table_columns('knowledge_bases')
+
+        new_columns = {
+            'knowledge_engine_plugin_id': 'VARCHAR',
+            'collection_id': 'VARCHAR',
+            'creation_settings': 'TEXT',  # JSON stored as TEXT for SQLite compatibility
+            'retrieval_settings': 'TEXT',
+        }
+
+        for col_name, col_type in new_columns.items():
+            if col_name not in columns:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(f'ALTER TABLE knowledge_bases ADD COLUMN {col_name} {col_type};')
+                )
+
+    async def _drop_old_columns(self):
+        """Drop embedding_model_uuid and top_k columns (PostgreSQL only).
+
+        SQLite does not support DROP COLUMN in older versions, so we leave the
+        columns in place — the SQLAlchemy entity simply won't map them.
+        """
+        if self.ap.persistence_mgr.db.name != 'postgresql':
+            return
+
+        columns = await self._get_table_columns('knowledge_bases')
+
+        if 'embedding_model_uuid' in columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE knowledge_bases DROP COLUMN embedding_model_uuid;')
+            )
+
+        if 'top_k' in columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE knowledge_bases DROP COLUMN top_k;')
+            )
+
+    async def _set_migration_flag(self):
+        """Set rag_plugin_migration_needed flag in metadata table."""
+        # Check if the key already exists
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text("SELECT value FROM metadata WHERE key = 'rag_plugin_migration_needed';")
+        )
+        row = result.first()
+        if row is not None:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("UPDATE metadata SET value = 'true' WHERE key = 'rag_plugin_migration_needed';")
+            )
+        else:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("INSERT INTO metadata (key, value) VALUES ('rag_plugin_migration_needed', 'true');")
+            )
+        self.ap.logger.info('Set rag_plugin_migration_needed=true in metadata.')
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm021_merge_exception_handling.py

@@ -0,0 +1,74 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(21)
+class DBMigrateMergeExceptionHandling(migration.DBMigration):
+    """Merge hide-exception and block-failed-request-output into a single exception-handling select option,
+    and add failure-hint field.
+
+    Conversion logic:
+    - block-failed-request-output=true  ->  exception-handling: hide
+    - hide-exception=true               ->  exception-handling: show-hint
+    - hide-exception=false              ->  exception-handling: show-error
+    """
+
+    async def upgrade(self):
+        """Upgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        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]
+
+            if 'output' not in config:
+                config['output'] = {}
+            if 'misc' not in config['output']:
+                config['output']['misc'] = {}
+
+            misc = config['output']['misc']
+
+            # Determine new exception-handling value from legacy fields
+            hide_exception = misc.get('hide-exception', True)
+            block_failed = misc.get('block-failed-request-output', False)
+
+            if block_failed:
+                exception_handling = 'hide'
+            elif hide_exception:
+                exception_handling = 'show-hint'
+            else:
+                exception_handling = 'show-error'
+
+            misc['exception-handling'] = exception_handling
+
+            # Add failure-hint with default value
+            misc['failure-hint'] = 'Request failed.'
+
+            # Remove legacy fields
+            misc.pop('hide-exception', None)
+
+            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"""
+        pass

src/langbot/pkg/persistence/migrations/dbm022_monitoring_user_name.py

@@ -0,0 +1,73 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(22)
+class DBMigrateMonitoringUserId(migration.DBMigration):
+    """Add user_id and user_name columns to monitoring_sessions table
+
+    This migration adds the missing user_id column and also ensures user_name
+    column exists (in case migration 21 failed or was skipped).
+    """
+
+    async def _table_exists(self, table_name: str) -> bool:
+        """Check if a table exists (works for both SQLite and PostgreSQL)."""
+        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 bool(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 _get_table_columns(self, table_name: str) -> list[str]:
+        """Get column names from a table (works for both SQLite and PostgreSQL)."""
+        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 = :table_name;'
+                ).bindparams(table_name=table_name)
+            )
+            return [row[0] for row in result.fetchall()]
+        else:
+            if not table_name.isidentifier():
+                raise ValueError(f'Invalid table name: {table_name}')
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text(f'PRAGMA table_info({table_name});'))
+            return [row[1] for row in result.fetchall()]
+
+    async def _add_column_if_not_exists(self, table_name: str, column_name: str, column_type: str):
+        """Add a column to a table if it does not already exist."""
+        columns = await self._get_table_columns(table_name)
+        if column_name in columns:
+            self.ap.logger.debug('%s column already exists in %s.', column_name, table_name)
+            return
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text(f'ALTER TABLE {table_name} ADD COLUMN {column_name} {column_type};')
+        )
+        self.ap.logger.info('Added %s column to %s table.', column_name, table_name)
+
+    async def upgrade(self):
+        # Check if monitoring_sessions table exists
+        if not await self._table_exists('monitoring_sessions'):
+            self.ap.logger.warning('monitoring_sessions table does not exist, skipping migration.')
+            return
+
+        # Add user_id column to monitoring_sessions table
+        await self._add_column_if_not_exists('monitoring_sessions', 'user_id', 'VARCHAR(255)')
+
+        # Add user_name column to monitoring_sessions table (in case migration 21 failed)
+        await self._add_column_if_not_exists('monitoring_sessions', 'user_name', 'VARCHAR(255)')
+
+        # Add user_name column to monitoring_messages table (in case migration 21 failed)
+        if await self._table_exists('monitoring_messages'):
+            await self._add_column_if_not_exists('monitoring_messages', 'user_name', 'VARCHAR(255)')
+
+    async def downgrade(self):
+        pass

src/langbot/pkg/persistence/migrations/dbm023_model_fallback_config.py

@@ -0,0 +1,102 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(23)
+class DBMigrateModelFallbackConfig(migration.DBMigration):
+    """Convert model field from plain UUID string to object with primary/fallbacks"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        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]
+
+            if 'ai' not in config or 'local-agent' not in config['ai']:
+                continue
+
+            local_agent = config['ai']['local-agent']
+            changed = False
+
+            # Convert model from string to object
+            model_value = local_agent.get('model', '')
+            if isinstance(model_value, str):
+                local_agent['model'] = {
+                    'primary': model_value,
+                    'fallbacks': [],
+                }
+                changed = True
+
+            # Remove leftover fallback-models field if present
+            if 'fallback-models' in local_agent:
+                del local_agent['fallback-models']
+                changed = True
+
+            if not changed:
+                continue
+
+            # 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"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        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]
+
+            if 'ai' not in config or 'local-agent' not in config['ai']:
+                continue
+
+            local_agent = config['ai']['local-agent']
+
+            # Convert model from object back to string
+            model_value = local_agent.get('model', '')
+            if isinstance(model_value, dict):
+                local_agent['model'] = model_value.get('primary', '')
+            else:
+                continue
+
+            # 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/dbm024_wecombot_websocket_mode.py

@@ -0,0 +1,49 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(24)
+class DBMigrateWecomBotWebSocketMode(migration.DBMigration):
+    """Add enable-webhook field to existing wecombot adapter configs.
+
+    Existing wecombot bots were all using webhook mode, so we set
+    enable-webhook=true to preserve their behavior after the new
+    WebSocket long connection mode is introduced as default.
+    """
+
+    async def upgrade(self):
+        """Upgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text("SELECT uuid, adapter_config FROM bots WHERE adapter = 'wecombot'")
+        )
+        bots = result.fetchall()
+
+        for bot_row in bots:
+            bot_uuid = bot_row[0]
+            adapter_config = json.loads(bot_row[1]) if isinstance(bot_row[1], str) else bot_row[1]
+
+            if 'enable-webhook' in adapter_config:
+                continue
+
+            # Determine mode based on existing config: if webhook fields are present, keep webhook mode
+            has_webhook_config = bool(
+                adapter_config.get('Token') and adapter_config.get('EncodingAESKey') and adapter_config.get('Corpid')
+            )
+            adapter_config['enable-webhook'] = has_webhook_config
+
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('UPDATE bots SET adapter_config = :config::jsonb WHERE uuid = :uuid'),
+                    {'config': json.dumps(adapter_config), 'uuid': bot_uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('UPDATE bots SET adapter_config = :config WHERE uuid = :uuid'),
+                    {'config': json.dumps(adapter_config), 'uuid': bot_uuid},
+                )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm025_bot_pipeline_routing_rules.py

@@ -0,0 +1,15 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(25)
+class DBMigrateBotPipelineRoutingRules(migration.DBMigration):
+    """Add pipeline_routing_rules column to bots table"""
+
+    async def upgrade(self):
+        sql_text = sqlalchemy.text("ALTER TABLE bots ADD COLUMN pipeline_routing_rules JSON NOT NULL DEFAULT '[]'")
+        await self.ap.persistence_mgr.execute_async(sql_text)
+
+    async def downgrade(self):
+        sql_text = sqlalchemy.text('ALTER TABLE bots DROP COLUMN pipeline_routing_rules')
+        await self.ap.persistence_mgr.execute_async(sql_text)

src/langbot/pkg/pipeline/aggregator.py

@@ -0,0 +1,295 @@
+"""Message Aggregator Module
+
+This module provides message aggregation/debounce functionality.
+When users send multiple messages consecutively, the aggregator will wait
+for a configurable delay period and merge them into a single message
+before processing.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import time
+import typing
+from dataclasses import dataclass, field
+
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
+import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
+
+if typing.TYPE_CHECKING:
+    from ..core import app
+
+# Maximum number of messages to buffer before forcing a flush
+MAX_BUFFER_MESSAGES = 10
+
+
+@dataclass
+class PendingMessage:
+    """A pending message waiting to be aggregated"""
+
+    bot_uuid: str
+    launcher_type: provider_session.LauncherTypes
+    launcher_id: typing.Union[int, str]
+    sender_id: typing.Union[int, str]
+    message_event: platform_events.MessageEvent
+    message_chain: platform_message.MessageChain
+    adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter
+    pipeline_uuid: typing.Optional[str]
+    routed_by_rule: bool = False
+    timestamp: float = field(default_factory=time.time)
+
+
+@dataclass
+class SessionBuffer:
+    """Buffer for a single session's pending messages"""
+
+    session_id: str
+    messages: list[PendingMessage] = field(default_factory=list)
+    timer_task: typing.Optional[asyncio.Task] = None
+    last_message_time: float = field(default_factory=time.time)
+
+
+class MessageAggregator:
+    """Message aggregator that buffers and merges consecutive messages
+
+    This class implements a debounce mechanism for incoming messages.
+    When a message arrives, it starts a timer. If more messages arrive
+    before the timer expires, they are buffered. When the timer expires,
+    all buffered messages are merged and sent to the query pool.
+    """
+
+    ap: app.Application
+
+    buffers: dict[str, SessionBuffer]
+    """Session ID -> SessionBuffer mapping"""
+
+    lock: asyncio.Lock
+    """Lock for thread-safe buffer operations"""
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+        self.buffers = {}
+        self.lock = asyncio.Lock()
+
+    def _get_session_id(
+        self,
+        bot_uuid: str,
+        launcher_type: provider_session.LauncherTypes,
+        launcher_id: typing.Union[int, str],
+    ) -> str:
+        """Generate a unique session ID"""
+        return f'{bot_uuid}:{launcher_type.value}:{launcher_id}'
+
+    async def _get_aggregation_config(self, pipeline_uuid: typing.Optional[str]) -> tuple[bool, float]:
+        """Get aggregation configuration for a pipeline
+
+        Returns:
+            tuple: (enabled, delay_seconds)
+        """
+        default_enabled = False
+        default_delay = 1.5
+
+        if pipeline_uuid is None:
+            return default_enabled, default_delay
+
+        # Get pipeline from pipeline manager
+        pipeline = await self.ap.pipeline_mgr.get_pipeline_by_uuid(pipeline_uuid)
+        if pipeline is None:
+            return default_enabled, default_delay
+
+        config = pipeline.pipeline_entity.config or {}
+        trigger_config = config.get('trigger', {})
+        aggregation_config = trigger_config.get('message-aggregation', {})
+
+        enabled = aggregation_config.get('enabled', default_enabled)
+
+        delay_raw = aggregation_config.get('delay', default_delay)
+        try:
+            delay = float(delay_raw)
+        except (TypeError, ValueError):
+            delay = default_delay
+
+        # Clamp delay to valid range
+        delay = max(1.0, min(10.0, delay))
+
+        return enabled, delay
+
+    async def add_message(
+        self,
+        bot_uuid: str,
+        launcher_type: provider_session.LauncherTypes,
+        launcher_id: typing.Union[int, str],
+        sender_id: typing.Union[int, str],
+        message_event: platform_events.MessageEvent,
+        message_chain: platform_message.MessageChain,
+        adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter,
+        pipeline_uuid: typing.Optional[str] = None,
+        routed_by_rule: bool = False,
+    ) -> None:
+        """Add a message to the aggregation buffer
+
+        If aggregation is disabled for the pipeline, the message is sent
+        directly to the query pool. Otherwise, it's buffered and will be
+        merged with other messages from the same session.
+        """
+        enabled, delay = await self._get_aggregation_config(pipeline_uuid)
+
+        if not enabled:
+            # Aggregation disabled, send directly to query pool
+            await self.ap.query_pool.add_query(
+                bot_uuid=bot_uuid,
+                launcher_type=launcher_type,
+                launcher_id=launcher_id,
+                sender_id=sender_id,
+                message_event=message_event,
+                message_chain=message_chain,
+                adapter=adapter,
+                pipeline_uuid=pipeline_uuid,
+                routed_by_rule=routed_by_rule,
+            )
+            return
+
+        session_id = self._get_session_id(bot_uuid, launcher_type, launcher_id)
+
+        pending_msg = PendingMessage(
+            bot_uuid=bot_uuid,
+            launcher_type=launcher_type,
+            launcher_id=launcher_id,
+            sender_id=sender_id,
+            message_event=message_event,
+            message_chain=message_chain,
+            adapter=adapter,
+            pipeline_uuid=pipeline_uuid,
+            routed_by_rule=routed_by_rule,
+        )
+
+        force_flush = False
+        async with self.lock:
+            if session_id in self.buffers:
+                buffer = self.buffers[session_id]
+                # Cancel existing timer (just cancel, don't await inside lock)
+                if buffer.timer_task and not buffer.timer_task.done():
+                    buffer.timer_task.cancel()
+                buffer.messages.append(pending_msg)
+            else:
+                buffer = SessionBuffer(
+                    session_id=session_id,
+                    messages=[pending_msg],
+                )
+                self.buffers[session_id] = buffer
+
+            buffer.last_message_time = time.time()
+
+            # Check if buffer reached max capacity
+            if len(buffer.messages) >= MAX_BUFFER_MESSAGES:
+                force_flush = True
+            else:
+                # Start new timer
+                buffer.timer_task = asyncio.create_task(self._delayed_flush(session_id, delay))
+
+        if force_flush:
+            await self._flush_buffer(session_id)
+
+    async def _delayed_flush(self, session_id: str, delay: float) -> None:
+        """Wait for delay then flush the buffer"""
+        try:
+            await asyncio.sleep(delay)
+            await self._flush_buffer(session_id)
+        except asyncio.CancelledError:
+            # Timer was cancelled, new message arrived
+            pass
+
+    async def _flush_buffer(self, session_id: str) -> None:
+        """Flush the buffer for a session, merging all messages"""
+        async with self.lock:
+            buffer = self.buffers.pop(session_id, None)
+
+        if buffer is None or not buffer.messages:
+            return
+
+        if len(buffer.messages) == 1:
+            # Only one message, no need to merge
+            msg = buffer.messages[0]
+            await self.ap.query_pool.add_query(
+                bot_uuid=msg.bot_uuid,
+                launcher_type=msg.launcher_type,
+                launcher_id=msg.launcher_id,
+                sender_id=msg.sender_id,
+                message_event=msg.message_event,
+                message_chain=msg.message_chain,
+                adapter=msg.adapter,
+                pipeline_uuid=msg.pipeline_uuid,
+                routed_by_rule=msg.routed_by_rule,
+            )
+            return
+
+        # Merge multiple messages
+        merged_msg = self._merge_messages(buffer.messages)
+        await self.ap.query_pool.add_query(
+            bot_uuid=merged_msg.bot_uuid,
+            launcher_type=merged_msg.launcher_type,
+            launcher_id=merged_msg.launcher_id,
+            sender_id=merged_msg.sender_id,
+            message_event=merged_msg.message_event,
+            message_chain=merged_msg.message_chain,
+            adapter=merged_msg.adapter,
+            pipeline_uuid=merged_msg.pipeline_uuid,
+            routed_by_rule=merged_msg.routed_by_rule,
+        )
+
+    def _merge_messages(self, messages: list[PendingMessage]) -> PendingMessage:
+        """Merge multiple messages into one
+
+        The merged message uses the first message as base and combines
+        all message chains with newline separators.
+        The original message_event is kept unmodified to preserve
+        message metadata (message_id, etc.) for reply/quote.
+        """
+        if len(messages) == 1:
+            return messages[0]
+
+        base_msg = messages[0]
+
+        # Build merged message chain
+        merged_chain = platform_message.MessageChain([])
+
+        for i, msg in enumerate(messages):
+            if i > 0:
+                # Add newline separator between messages
+                merged_chain.append(platform_message.Plain(text='\n'))
+
+            # Copy all components from this message
+            for component in msg.message_chain:
+                merged_chain.append(component)
+
+        # Keep message_event unmodified (preserves original message_id and
+        # metadata for reply/quote), only pass merged chain separately
+        return PendingMessage(
+            bot_uuid=base_msg.bot_uuid,
+            launcher_type=base_msg.launcher_type,
+            launcher_id=base_msg.launcher_id,
+            sender_id=base_msg.sender_id,
+            message_event=base_msg.message_event,
+            message_chain=merged_chain,
+            adapter=base_msg.adapter,
+            pipeline_uuid=base_msg.pipeline_uuid,
+        )
+
+    async def flush_all(self) -> None:
+        """Flush all pending buffers immediately
+
+        This is useful during shutdown to ensure no messages are lost.
+        """
+        # Snapshot session IDs and cancel all timers under lock
+        async with self.lock:
+            session_ids = list(self.buffers.keys())
+            for sid in session_ids:
+                buffer = self.buffers.get(sid)
+                if buffer and buffer.timer_task and not buffer.timer_task.done():
+                    buffer.timer_task.cancel()
+
+        # Flush each buffer outside the lock
+        for session_id in session_ids:
+            await self._flush_buffer(session_id)

src/langbot/pkg/pipeline/cntfilter/filters/baiduexamine.py

@@ -1,10 +1,9 @@
 from __future__ import annotations
 
-import aiohttp
-
 from .. import entities
 from .. import filter as filter_model
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+from langbot.pkg.utils import httpclient
 
 BAIDU_EXAMINE_URL = 'https://aip.baidubce.com/rest/2.0/solution/v1/text_censor/v2/user_defined?access_token={}'
 BAIDU_EXAMINE_TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'
@@ -15,50 +14,50 @@ class BaiduCloudExamine(filter_model.ContentFilter):
     """百度云内容审核"""
 
     async def _get_token(self) -> str:
-        async with aiohttp.ClientSession() as session:
-            async with session.post(
-                BAIDU_EXAMINE_TOKEN_URL,
-                params={
-                    'grant_type': 'client_credentials',
-                    'client_id': self.ap.pipeline_cfg.data['baidu-cloud-examine']['api-key'],
-                    'client_secret': self.ap.pipeline_cfg.data['baidu-cloud-examine']['api-secret'],
-                },
-            ) as resp:
-                return (await resp.json())['access_token']
+        session = httpclient.get_session()
+        async with session.post(
+            BAIDU_EXAMINE_TOKEN_URL,
+            params={
+                'grant_type': 'client_credentials',
+                'client_id': self.ap.pipeline_cfg.data['baidu-cloud-examine']['api-key'],
+                'client_secret': self.ap.pipeline_cfg.data['baidu-cloud-examine']['api-secret'],
+            },
+        ) as resp:
+            return (await resp.json())['access_token']
 
     async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
-        async with aiohttp.ClientSession() as session:
-            async with session.post(
-                BAIDU_EXAMINE_URL.format(await self._get_token()),
-                headers={
-                    'Content-Type': 'application/x-www-form-urlencoded',
-                    'Accept': 'application/json',
-                },
-                data=f'text={message}'.encode('utf-8'),
-            ) as resp:
-                result = await resp.json()
+        session = httpclient.get_session()
+        async with session.post(
+            BAIDU_EXAMINE_URL.format(await self._get_token()),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Accept': 'application/json',
+            },
+            data=f'text={message}'.encode('utf-8'),
+        ) as resp:
+            result = await resp.json()
 
-                if 'error_code' in result:
+            if 'error_code' in result:
+                return entities.FilterResult(
+                    level=entities.ResultLevel.BLOCK,
+                    replacement=message,
+                    user_notice='',
+                    console_notice=f'百度云判定出错，错误信息：{result["error_msg"]}',
+                )
+            else:
+                conclusion = result['conclusion']
+
+                if conclusion in ('合规'):
+                    return entities.FilterResult(
+                        level=entities.ResultLevel.PASS,
+                        replacement=message,
+                        user_notice='',
+                        console_notice=f'百度云判定结果：{conclusion}',
+                    )
+                else:
                     return entities.FilterResult(
                         level=entities.ResultLevel.BLOCK,
                         replacement=message,
-                        user_notice='',
-                        console_notice=f'百度云判定出错，错误信息：{result["error_msg"]}',
+                        user_notice='消息中存在不合适的内容, 请修改',
+                        console_notice=f'百度云判定结果：{conclusion}',
                     )
-                else:
-                    conclusion = result['conclusion']
-
-                    if conclusion in ('合规'):
-                        return entities.FilterResult(
-                            level=entities.ResultLevel.PASS,
-                            replacement=message,
-                            user_notice='',
-                            console_notice=f'百度云判定结果：{conclusion}',
-                        )
-                    else:
-                        return entities.FilterResult(
-                            level=entities.ResultLevel.BLOCK,
-                            replacement=message,
-                            user_notice='消息中存在不合适的内容, 请修改',
-                            console_notice=f'百度云判定结果：{conclusion}',
-                        )

src/langbot/pkg/pipeline/config_coercion.py

@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+import logging
+
+logger = logging.getLogger(__name__)
+
+# metadata type -> coercion function
+_COERCE_MAP = {
+    'integer': lambda v: int(v),
+    'number': lambda v: float(v),
+    'float': lambda v: float(v),
+}
+
+
+def _coerce_bool(v):
+    if isinstance(v, bool):
+        return v
+    if isinstance(v, str):
+        if v.lower() == 'true':
+            return True
+        if v.lower() == 'false':
+            return False
+        raise ValueError(f'Cannot convert string {v!r} to bool')
+    return bool(v)
+
+
+def _coerce_value(value, expected_type: str):
+    """Convert a single value to the expected type.
+
+    Returns the converted value, or the original value if no conversion needed.
+    """
+    if value is None:
+        return value
+
+    if expected_type == 'boolean':
+        if isinstance(value, bool):
+            return value
+        return _coerce_bool(value)
+
+    coerce_fn = _COERCE_MAP.get(expected_type)
+    if coerce_fn is None:
+        return value
+
+    # Already the correct type
+    if expected_type == 'integer' and isinstance(value, int) and not isinstance(value, bool):
+        return value
+    if expected_type in ('number', 'float') and isinstance(value, (int, float)) and not isinstance(value, bool):
+        return float(value)
+
+    return coerce_fn(value)
+
+
+def coerce_pipeline_config(
+    config: dict,
+    *metadata_list: dict,
+) -> None:
+    """Coerce pipeline config values according to metadata type definitions.
+
+    Walks each metadata dict (trigger, safety, ai, output) and converts
+    config values in-place so that strings coming from the JSON column are
+    cast to their declared types (integer, number/float, boolean).
+
+    Args:
+        config: The pipeline config dict to modify in-place.
+        *metadata_list: Metadata dicts loaded from the YAML templates.
+    """
+    for meta in metadata_list:
+        section_name = meta.get('name')
+        if not section_name or section_name not in config:
+            continue
+
+        section = config[section_name]
+        if not isinstance(section, dict):
+            continue
+
+        for stage_def in meta.get('stages', []):
+            stage_name = stage_def.get('name')
+            if not stage_name or stage_name not in section:
+                continue
+
+            stage_config = section[stage_name]
+            if not isinstance(stage_config, dict):
+                continue
+
+            for field_def in stage_def.get('config', []):
+                field_name = field_def.get('name')
+                field_type = field_def.get('type')
+                if not field_name or not field_type or field_name not in stage_config:
+                    continue
+
+                old_value = stage_config[field_name]
+                try:
+                    new_value = _coerce_value(old_value, field_type)
+                    if new_value is not old_value:
+                        stage_config[field_name] = new_value
+                except (ValueError, TypeError) as e:
+                    logger.warning(
+                        'Failed to coerce config %s.%s.%s (%r) to %s: %s',
+                        section_name,
+                        stage_name,
+                        field_name,
+                        old_value,
+                        field_type,
+                        e,
+                    )

src/langbot/pkg/pipeline/controller.py

@@ -63,6 +63,14 @@ class Controller:
                                 pipeline = await self.ap.pipeline_mgr.get_pipeline_by_uuid(pipeline_uuid)
                                 if pipeline:
                                     await pipeline.run(selected_query)
+                                else:
+                                    self.ap.logger.warning(
+                                        f'Pipeline {pipeline_uuid} not found for query {selected_query.query_id}, query dropped'
+                                    )
+                            else:
+                                self.ap.logger.warning(
+                                    f'No pipeline_uuid for query {selected_query.query_id}, query dropped'
+                                )
 
                         async with self.ap.query_pool:
                             (await self.ap.sess_mgr.get_session(selected_query))._semaphore.release()

src/langbot/pkg/pipeline/monitoring_helper.py

@@ -34,6 +34,15 @@ class MonitoringHelper:
             # Check if session exists, if not, record session start
             session_id = f'{query.launcher_type}_{query.launcher_id}'
 
+            # Get sender name from message event
+            sender_name = None
+            if hasattr(query, 'message_event'):
+                if hasattr(query.message_event, 'sender'):
+                    if hasattr(query.message_event.sender, 'nickname'):
+                        sender_name = query.message_event.sender.nickname
+                    elif hasattr(query.message_event.sender, 'member_name'):
+                        sender_name = query.message_event.sender.member_name
+
             # Try to record message
             # Use JSON serialization to preserve message chain structure (including image URLs, etc.)
             if hasattr(query, 'message_chain') and hasattr(query.message_chain, 'model_dump'):
@@ -57,6 +66,7 @@ class MonitoringHelper:
                 if hasattr(query.launcher_type, 'value')
                 else str(query.launcher_type),
                 user_id=query.sender_id,
+                user_name=sender_name,
                 runner_name=runner_name,
                 variables=None,  # Will be updated in record_query_success
             )
@@ -80,6 +90,7 @@ class MonitoringHelper:
                     if hasattr(query.launcher_type, 'value')
                     else str(query.launcher_type),
                     user_id=query.sender_id,
+                    user_name=sender_name,
                 )
 
             return message_id
@@ -114,6 +125,70 @@ class MonitoringHelper:
         except Exception as e:
             ap.logger.error(f'Failed to record query success: {e}')
 
+    @staticmethod
+    async def record_query_response(
+        ap: app.Application,
+        query: pipeline_query.Query,
+        bot_id: str,
+        bot_name: str,
+        pipeline_id: str,
+        pipeline_name: str,
+        runner_name: str | None = None,
+    ):
+        """Record bot response message to monitoring"""
+        try:
+            session_id = f'{query.launcher_type}_{query.launcher_id}'
+
+            # Get sender name from message event
+            sender_name = None
+            if hasattr(query, 'message_event'):
+                if hasattr(query.message_event, 'sender'):
+                    if hasattr(query.message_event.sender, 'nickname'):
+                        sender_name = query.message_event.sender.nickname
+                    elif hasattr(query.message_event.sender, 'member_name'):
+                        sender_name = query.message_event.sender.member_name
+
+            # Extract response content from resp_message_chain
+            if hasattr(query, 'resp_message_chain') and query.resp_message_chain:
+                # Serialize the last response message chain
+                last_resp = query.resp_message_chain[-1]
+                if hasattr(last_resp, 'model_dump'):
+                    message_content = json.dumps(last_resp.model_dump(), ensure_ascii=False)
+                else:
+                    message_content = str(last_resp)
+            elif hasattr(query, 'resp_messages') and query.resp_messages:
+                last_resp = query.resp_messages[-1]
+                if hasattr(last_resp, 'get_content_platform_message_chain'):
+                    chain = last_resp.get_content_platform_message_chain()
+                    if hasattr(chain, 'model_dump'):
+                        message_content = json.dumps(chain.model_dump(), ensure_ascii=False)
+                    else:
+                        message_content = str(chain)
+                else:
+                    message_content = str(last_resp)
+            else:
+                return  # No response to record
+
+            await ap.monitoring_service.record_message(
+                bot_id=bot_id,
+                bot_name=bot_name,
+                pipeline_id=pipeline_id,
+                pipeline_name=pipeline_name,
+                message_content=message_content,
+                session_id=session_id,
+                status='success',
+                level='info',
+                platform=query.launcher_type.value
+                if hasattr(query.launcher_type, 'value')
+                else str(query.launcher_type),
+                user_id=query.sender_id,
+                user_name=sender_name,
+                runner_name=runner_name,
+                role='assistant',
+            )
+        except Exception as e:
+            ap.logger.error(f'Failed to record query response: {e}')
+
     @staticmethod
     async def record_query_error(
         ap: app.Application,
@@ -129,6 +204,15 @@ class MonitoringHelper:
         try:
             session_id = f'{query.launcher_type}_{query.launcher_id}'
 
+            # Get sender name from message event
+            sender_name = None
+            if hasattr(query, 'message_event'):
+                if hasattr(query.message_event, 'sender'):
+                    if hasattr(query.message_event.sender, 'nickname'):
+                        sender_name = query.message_event.sender.nickname
+                    elif hasattr(query.message_event.sender, 'member_name'):
+                        sender_name = query.message_event.sender.member_name
+
             # Record error message
             message_id = await ap.monitoring_service.record_message(
                 bot_id=bot_id,
@@ -143,6 +227,7 @@ class MonitoringHelper:
                 if hasattr(query.launcher_type, 'value')
                 else str(query.launcher_type),
                 user_id=query.sender_id,
+                user_name=sender_name,
                 runner_name=runner_name,
             )
 

src/langbot/pkg/pipeline/pipelinemgr.py

@@ -13,6 +13,7 @@ import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.events as events
 from ..utils import importutil
+from .config_coercion import coerce_pipeline_config
 
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -296,6 +297,9 @@ class RuntimePipeline:
             )
             # Store message_id in query variables for LLM call monitoring
             query.variables['_monitoring_message_id'] = message_id
+            # Notify adapter so it can map platform-specific IDs to monitoring message ID
+            if hasattr(query.adapter, 'on_monitoring_message_created'):
+                await query.adapter.on_monitoring_message_created(query, message_id)
         except Exception as e:
             self.ap.logger.error(f'Failed to record query start: {e}')
 
@@ -322,6 +326,9 @@ class RuntimePipeline:
             event_ctx = await self.ap.plugin_connector.emit_event(event_obj, bound_plugins)
 
             if event_ctx.is_prevented_default():
+                self.ap.logger.debug(
+                    f'MessageReceived event prevented default for query {query.query_id}, pipeline={pipeline_name}'
+                )
                 return
 
             self.ap.logger.debug(f'Processing query {query.query_id}')
@@ -339,6 +346,20 @@ class RuntimePipeline:
                 except Exception as e:
                     self.ap.logger.error(f'Failed to record query success: {e}')
 
+                # Record bot response message
+                try:
+                    await monitoring_helper.MonitoringHelper.record_query_response(
+                        ap=self.ap,
+                        query=query,
+                        bot_id=query.bot_uuid or 'unknown',
+                        bot_name=bot_name,
+                        pipeline_id=self.pipeline_entity.uuid,
+                        pipeline_name=pipeline_name,
+                        runner_name=runner_name,
+                    )
+                except Exception as e:
+                    self.ap.logger.error(f'Failed to record query response: {e}')
+
         except Exception as e:
             inst_name = query.current_stage_name if query.current_stage_name else 'unknown'
             self.ap.logger.error(f'Error processing query {query.query_id} stage={inst_name} : {e}')
@@ -369,8 +390,6 @@ class RuntimePipeline:
 class PipelineManager:
     """流水线管理器"""
 
-    # ====== 4.0 ======
-
     ap: app.Application
 
     pipelines: list[RuntimePipeline]
@@ -408,6 +427,14 @@ class PipelineManager:
         elif isinstance(pipeline_entity, dict):
             pipeline_entity = persistence_pipeline.LegacyPipeline(**pipeline_entity)
 
+        coerce_pipeline_config(
+            pipeline_entity.config,
+            getattr(self.ap, 'pipeline_config_meta_trigger', {'name': 'trigger', 'stages': []}),
+            getattr(self.ap, 'pipeline_config_meta_safety', {'name': 'safety', 'stages': []}),
+            getattr(self.ap, 'pipeline_config_meta_ai', {'name': 'ai', 'stages': []}),
+            getattr(self.ap, 'pipeline_config_meta_output', {'name': 'output', 'stages': []}),
+        )
+
         # initialize stage containers according to pipeline_entity.stages
         stage_containers: list[StageInstContainer] = []
         for stage_name in pipeline_entity.stages:

src/langbot/pkg/pipeline/pool.py

@@ -41,6 +41,7 @@ class QueryPool:
         message_chain: platform_message.MessageChain,
         adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter,
         pipeline_uuid: typing.Optional[str] = None,
+        routed_by_rule: bool = False,
     ) -> pipeline_query.Query:
         async with self.condition:
             query_id = self.query_id_counter
@@ -52,7 +53,7 @@ class QueryPool:
                 sender_id=sender_id,
                 message_event=message_event,
                 message_chain=message_chain,
-                variables={},
+                variables={'_routed_by_rule': routed_by_rule},
                 resp_messages=[],
                 resp_message_chain=[],
                 adapter=adapter,