feat: modify frontend

Migration 0003 failed when rerank_models table already exists from create_all().
Add table existence check to prevent duplicate creation error in CI environments with cached database.

.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:

.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:

.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

@@ -52,3 +52,6 @@ src/langbot/web/
 /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

@@ -19,9 +19,9 @@ English / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">Website</a> ｜
-<a href="https://docs.langbot.app/en/insight/features">Features</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide">Docs</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme">API</a> ｜
+<a href="https://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>
@@ -45,7 +45,7 @@ LangBot is an **open-source, production-grade platform** for building AI-powered
 - **Web Management Panel** — Configure, manage, and monitor your bots through an intuitive browser interface. No YAML editing required.
 - **Multi-Pipeline Architecture** — Different bots for different scenarios, with comprehensive monitoring and exception handling.
 
-[→ Learn more about all features](https://docs.langbot.app/en/insight/features)
+[→ Learn more about all features](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -76,7 +76,7 @@ docker compose up -d
 [![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)
 
-**More options:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker) · [Manual](https://docs.langbot.app/en/deploy/langbot/manual) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -124,7 +124,7 @@ docker compose up -d
 | [接口 AI](https://jiekou.ai/) | Gateway | ✅ |
 | [302.AI](https://share.302.ai/SuTG99) | Gateway | ✅ |
 
-[→ View all integrations](https://docs.langbot.app/en/insight/features)
+[→ View all integrations](https://link.langbot.app/en/docs/features)
 
 ---
 

README_CN.md

@@ -21,9 +21,9 @@
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
 
 <a href="https://langbot.app">官网</a> ｜
-<a href="https://docs.langbot.app/zh/insight/features.html">特性</a> ｜
-<a href="https://docs.langbot.app/zh/insight/guide.html">文档</a> ｜
-<a href="https://docs.langbot.app/zh/tags/readme.html">API</a> ｜
+<a href="https://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>
@@ -34,8 +34,6 @@
 
 ---
 
-## 什么是 LangBot？
-
 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
@@ -43,11 +41,11 @@ LangBot 是一个**开源的生产级平台**，用于构建 AI 驱动的即时
 - **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，事件驱动架构，组件扩展，适配 [MCP 协议](https://modelcontextprotocol.io/)。
+- **插件生态** — 数百个插件，跨进程的事件驱动架构，组件扩展，适配 [MCP 协议](https://modelcontextprotocol.io/)。
 - **Web 管理面板** — 通过浏览器直观地配置、管理和监控机器人，无需手动编辑配置文件。
 - **多流水线架构** — 不同机器人用于不同场景，具备全面的监控和异常处理能力。
 
-[→ 了解更多功能特性](https://docs.langbot.app/zh/insight/features.html)
+[→ 了解更多功能特性](https://link.langbot.app/zh/docs/features)
 
 ---
 
@@ -78,7 +76,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**更多方式：** [Docker](https://docs.langbot.app/zh/deploy/langbot/docker.html) · [手动部署](https://docs.langbot.app/zh/deploy/langbot/manual.html) · [宝塔面板](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -127,7 +125,7 @@ docker compose up -d
 | [小马算力](https://www.tokenpony.cn/453z1) | 聚合平台 | ✅ |
 | [百宝箱Tbox](https://www.tbox.cn/open) | 智能体平台 | ✅ |
 
-[→ 查看完整集成列表](https://docs.langbot.app/zh/insight/features.html)
+[→ 查看完整集成列表](https://link.langbot.app/zh/docs/features)
 
 ### TTS（语音合成）
 

README_ES.md

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">Inicio</a> ｜
-<a href="https://docs.langbot.app/en/insight/features.html">Características</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Documentación</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot es una **plataforma de código abierto y grado de producción** para con
 - **Panel de Gestión Web** — Configure, gestione y monitoree sus bots a través de una interfaz de navegador intuitiva. Sin necesidad de editar YAML.
 - **Arquitectura Multi-Pipeline** — Diferentes bots para diferentes escenarios, con monitoreo completo y manejo de excepciones.
 
-[→ Conocer más sobre todas las funcionalidades](https://docs.langbot.app/en/insight/features.html)
+[→ Conocer más sobre todas las funcionalidades](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**Más opciones:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Manual](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [接口 AI](https://jiekou.ai/) | Pasarela | ✅ |
 | [302.AI](https://share.302.ai/SuTG99) | Pasarela | ✅ |
 
-[→ Ver todas las integraciones](https://docs.langbot.app/en/insight/features.html)
+[→ Ver todas las integraciones](https://link.langbot.app/en/docs/features)
 
 ---
 

README_FR.md

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">Accueil</a> ｜
-<a href="https://docs.langbot.app/en/insight/features.html">Fonctionnalités</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Documentation</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot est une **plateforme open-source de niveau production** pour créer des
 - **Panneau de Gestion Web** — Configurez, gérez et surveillez vos bots via une interface navigateur intuitive. Aucune édition de YAML requise.
 - **Architecture Multi-Pipeline** — Différents bots pour différents scénarios, avec surveillance complète et gestion des exceptions.
 
-[→ En savoir plus sur toutes les fonctionnalités](https://docs.langbot.app/en/insight/features.html)
+[→ En savoir plus sur toutes les fonctionnalités](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**Plus d'options :** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Manuel](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Plateforme GPU | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plateforme GPU | ✅ |
 
-[→ Voir toutes les intégrations](https://docs.langbot.app/en/insight/features.html)
+[→ Voir toutes les intégrations](https://link.langbot.app/en/docs/features)
 
 ---
 

README_JP.md

@@ -19,9 +19,9 @@
 [![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</a> ｜
-<a href="https://docs.langbot.app/ja/insight/guide.html">ドキュメント</a> ｜
-<a href="https://docs.langbot.app/ja/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot は、AI搭載のインスタントメッセージングボットを構
 - **Web管理パネル** — 直感的なブラウザインターフェースからボットの設定、管理、監視が可能。YAML編集は不要。
 - **マルチパイプラインアーキテクチャ** — 異なるシナリオに異なるボットを配置し、包括的な監視と例外処理を実現。
 
-[→ すべての機能について詳しく見る](https://docs.langbot.app/ja/insight/features.html)
+[→ すべての機能について詳しく見る](https://link.langbot.app/ja/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![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)
 
-**その他:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [手動デプロイ](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [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 | ✅ |
 
-[→ すべての統合を表示](https://docs.langbot.app/en/insight/features.html)
+[→ すべての統合を表示](https://link.langbot.app/en/docs/features)
 
 ---
 

README_KO.md

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">홈</a> ｜
-<a href="https://docs.langbot.app/en/insight/features.html">기능</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">문서</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot은 AI 기반 인스턴트 메시징 봇을 구축하기 위한 **오픈
 - **웹 관리 패널** — 직관적인 브라우저 인터페이스로 봇을 구성, 관리 및 모니터링. YAML 편집 불필요.
 - **멀티 파이프라인 아키텍처** — 다양한 시나리오에 맞는 다양한 봇 구성, 종합 모니터링 및 예외 처리.
 
-[→ 모든 기능 자세히 보기](https://docs.langbot.app/en/insight/features.html)
+[→ 모든 기능 자세히 보기](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**더 많은 옵션:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [수동 배포](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [接口 AI](https://jiekou.ai/) | 게이트웨이 | ✅ |
 | [302.AI](https://share.302.ai/SuTG99) | 게이트웨이 | ✅ |
 
-[→ 모든 통합 보기](https://docs.langbot.app/en/insight/features.html)
+[→ 모든 통합 보기](https://link.langbot.app/en/docs/features)
 
 ---
 

README_RU.md

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">Главная</a> ｜
-<a href="https://docs.langbot.app/en/insight/features.html">Возможности</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Документация</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot — это **платформа с открытым исходным к
 - **Веб-панель управления** — Настраивайте, управляйте и мониторьте ваших ботов через интуитивный браузерный интерфейс. Ручное редактирование YAML не требуется.
 - **Мультиконвейерная архитектура** — Разные боты для разных сценариев с комплексным мониторингом и обработкой исключений.
 
-[→ Подробнее обо всех возможностях](https://docs.langbot.app/en/insight/features.html)
+[→ Подробнее обо всех возможностях](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**Другие варианты:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Ручная установка](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | Платформа GPU | ✅ |
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Платформа GPU | ✅ |
 
-[→ Смотреть все интеграции](https://docs.langbot.app/en/insight/features.html)
+[→ Смотреть все интеграции](https://link.langbot.app/en/docs/features)
 
 ---
 

README_TW.md

@@ -21,9 +21,9 @@
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
 
 <a href="https://langbot.app">官網</a> ｜
-<a href="https://docs.langbot.app/zh/insight/features.html">特性</a> ｜
-<a href="https://docs.langbot.app/zh/insight/guide.html">文件</a> ｜
-<a href="https://docs.langbot.app/zh/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -46,7 +46,7 @@ LangBot 是一個**開源的生產級平台**，用於建構 AI 驅動的即時
 - **Web 管理面板** — 透過瀏覽器直觀地配置、管理和監控機器人，無需手動編輯設定檔。
 - **多流水線架構** — 不同機器人用於不同場景，具備全面的監控和異常處理能力。
 
-[→ 了解更多功能特性](https://docs.langbot.app/zh/insight/features.html)
+[→ 了解更多功能特性](https://link.langbot.app/zh/docs/features)
 
 ---
 
@@ -77,7 +77,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**更多方式：** [Docker](https://docs.langbot.app/zh/deploy/langbot/docker.html) · [手動部署](https://docs.langbot.app/zh/deploy/langbot/manual.html) · [寶塔面板](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -139,7 +139,7 @@ docker compose up -d
 |-----------|------|
 | 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin) |
 
-[→ 查看完整整合列表](https://docs.langbot.app/zh/insight/features.html)
+[→ 查看完整整合列表](https://link.langbot.app/zh/docs/features)
 
 ---
 

README_VI.md

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)
 
 <a href="https://langbot.app">Trang chủ</a> ｜
-<a href="https://docs.langbot.app/en/insight/features.html">Tính năng</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">Tài liệu</a> ｜
-<a href="https://docs.langbot.app/en/tags/readme.html">API</a> ｜
+<a href="https://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>
 
@@ -44,7 +44,7 @@ LangBot là một **nền tảng mã nguồn mở, cấp sản xuất** để x
 - **Bảng quản lý Web** — Cấu hình, quản lý và giám sát bot thông qua giao diện trình duyệt trực quan. Không cần chỉnh sửa YAML.
 - **Kiến trúc đa Pipeline** — Các bot khác nhau cho các kịch bản khác nhau, với giám sát toàn diện và xử lý ngoại lệ.
 
-[→ Tìm hiểu thêm về tất cả tính năng](https://docs.langbot.app/en/insight/features.html)
+[→ Tìm hiểu thêm về tất cả tính năng](https://link.langbot.app/en/docs/features)
 
 ---
 
@@ -75,7 +75,7 @@ docker compose up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
 
-**Thêm tùy chọn:** [Docker](https://docs.langbot.app/en/deploy/langbot/docker.html) · [Thủ công](https://docs.langbot.app/en/deploy/langbot/manual.html) · [BTPanel](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html) · [Kubernetes](./docker/README_K8S.md)
+**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)
 
 ---
 
@@ -123,7 +123,7 @@ docker compose up -d
 | [接口 AI](https://jiekou.ai/) | Cổng | ✅ |
 | [302.AI](https://share.302.ai/SuTG99) | Cổng | ✅ |
 
-[→ Xem tất cả tích hợp](https://docs.langbot.app/en/insight/features.html)
+[→ Xem tất cả tích hợp](https://link.langbot.app/en/docs/features)
 
 ---
 

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

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.8.6"
+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 +61,22 @@ 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==0.2.7",
+    "pyseekdb==1.1.0.post3",
+    "langbot-plugin==0.3.8",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "tboxsdk>=0.0.10",
     "boto3>=1.35.0",
     "pymilvus>=2.6.4",
     "pgvector>=0.4.1",
+    "botocore>=1.42.39",
 ]
 keywords = [
     "bot",
@@ -110,12 +116,12 @@ 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__ = '4.8.6'
+__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()

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/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

@@ -456,6 +456,31 @@ class MonitoringRouterGroup(group.RouterGroup):
                     '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)
 
@@ -486,3 +511,63 @@ class MonitoringRouterGroup(group.RouterGroup):
             )
 
             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/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/plugins.py

@@ -265,6 +265,8 @@ 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,
@@ -295,12 +297,17 @@ class PluginsRouterGroup(group.RouterGroup):
 
             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,
             )
 
@@ -323,11 +330,13 @@ 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/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')
@@ -9,6 +13,24 @@ 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,
@@ -27,17 +49,83 @@ class SystemRouterGroup(group.RouterGroup):
                         '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:

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
 

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/model.py

@@ -105,11 +105,16 @@ 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']
 
@@ -362,3 +367,162 @@ 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(**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 +16,57 @@ class MonitoringService:
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
 
+    # ========== Cleanup Methods ==========
+
+    async def cleanup_expired_records(self, retention_days: int) -> dict[str, int]:
+        """Delete monitoring records older than the specified retention period.
+
+        Args:
+            retention_days: Number of days to retain records.
+
+        Returns:
+            A dict mapping table name to the number of deleted rows.
+        """
+        cutoff = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None) - datetime.timedelta(
+            days=retention_days
+        )
+
+        tables_and_columns: list[tuple[str, type, sqlalchemy.Column]] = [
+            (
+                'monitoring_messages',
+                persistence_monitoring.MonitoringMessage,
+                persistence_monitoring.MonitoringMessage.timestamp,
+            ),
+            (
+                'monitoring_llm_calls',
+                persistence_monitoring.MonitoringLLMCall,
+                persistence_monitoring.MonitoringLLMCall.timestamp,
+            ),
+            (
+                'monitoring_embedding_calls',
+                persistence_monitoring.MonitoringEmbeddingCall,
+                persistence_monitoring.MonitoringEmbeddingCall.timestamp,
+            ),
+            (
+                'monitoring_errors',
+                persistence_monitoring.MonitoringError,
+                persistence_monitoring.MonitoringError.timestamp,
+            ),
+            (
+                'monitoring_sessions',
+                persistence_monitoring.MonitoringSession,
+                persistence_monitoring.MonitoringSession.last_activity,
+            ),
+        ]
+
+        deleted_counts: dict[str, int] = {}
+
+        for table_name, model_cls, ts_column in tables_and_columns:
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.delete(model_cls).where(ts_column < cutoff))
+            deleted_counts[table_name] = result.rowcount
+
+        return deleted_counts
+
     # ========== Recording Methods ==========
 
     async def record_message(
@@ -30,6 +81,7 @@ 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',
@@ -49,6 +101,7 @@ class MonitoringService:
             'level': level,
             'platform': platform,
             'user_id': user_id,
+            'user_name': user_name,
             'runner_name': runner_name,
             'variables': variables,
             'role': role,
@@ -152,6 +205,7 @@ 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 = {
@@ -166,6 +220,7 @@ class MonitoringService:
             'is_active': True,
             'platform': platform,
             'user_id': user_id,
+            'user_name': user_name,
         }
 
         await self.ap.persistence_mgr.execute_async(
@@ -1128,3 +1183,314 @@ class MonitoringService:
             }
             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/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') 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

@@ -9,6 +9,7 @@ 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
@@ -29,14 +30,15 @@ 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 ..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
@@ -63,6 +65,7 @@ class Application:
     model_mgr: llm_model_mgr.ModelManager = None
 
     rag_mgr: rag_mgr.RAGManager = None
+    rag_runtime_service: RAGRuntimeService = None
 
     # TODO move to pipeline
     tool_mgr: llm_tool_mgr.ToolManager = None
@@ -130,6 +133,8 @@ 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
@@ -138,8 +143,6 @@ 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
@@ -187,6 +190,34 @@ class Application:
                 scopes=[core_entities.LifecycleControlScope.APPLICATION],
             )
 
+            # Start monitoring data cleanup task if enabled
+            monitoring_cfg = self.instance_config.data.get('monitoring', {})
+            auto_cleanup_cfg = monitoring_cfg.get('auto_cleanup', {})
+            if auto_cleanup_cfg.get('enabled', True):
+                retention_days = auto_cleanup_cfg.get('retention_days', 30)
+                check_interval_hours = auto_cleanup_cfg.get('check_interval_hours', 1)
+
+                async def monitoring_cleanup_loop():
+                    check_interval_seconds = check_interval_hours * 3600
+                    while True:
+                        try:
+                            deleted = await self.monitoring_service.cleanup_expired_records(retention_days)
+                            total_deleted = sum(deleted.values())
+                            if total_deleted > 0:
+                                self.logger.info(
+                                    f'Monitoring auto-cleanup: deleted {total_deleted} expired records '
+                                    f'(retention={retention_days}d): {deleted}'
+                                )
+                        except Exception as e:
+                            self.logger.warning(f'Monitoring auto-cleanup error: {e}')
+                        await asyncio.sleep(check_interval_seconds)
+
+                self.task_mgr.create_task(
+                    monitoring_cleanup_loop(),
+                    name='monitoring-cleanup',
+                    scopes=[core_entities.LifecycleControlScope.APPLICATION],
+                )
+
             self.task_mgr.create_task(
                 never_ending(),
                 name='never-ending-task',

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

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

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

@@ -12,6 +12,7 @@ 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
@@ -26,7 +27,6 @@ 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 ...discover import engine as discover_engine
 from ...storage import mgr as storagemgr
@@ -61,6 +61,9 @@ 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
 
@@ -73,9 +76,6 @@ 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
 
@@ -152,6 +152,9 @@ class BuildAppStage(stage.BootingStage):
         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()

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
@@ -146,16 +156,50 @@ 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}')

src/langbot/pkg/core/taskmgr.py

@@ -17,9 +17,13 @@ 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 +42,7 @@ 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:
@@ -211,9 +215,14 @@ 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,
         }
 

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

@@ -20,6 +20,7 @@ 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
@@ -64,6 +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):
@@ -104,3 +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/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

@@ -37,6 +37,7 @@ class PendingMessage:
     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)
 
 
@@ -125,6 +126,7 @@ class MessageAggregator:
         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
 
@@ -145,6 +147,7 @@ class MessageAggregator:
                 message_chain=message_chain,
                 adapter=adapter,
                 pipeline_uuid=pipeline_uuid,
+                routed_by_rule=routed_by_rule,
             )
             return
 
@@ -159,6 +162,7 @@ class MessageAggregator:
             message_chain=message_chain,
             adapter=adapter,
             pipeline_uuid=pipeline_uuid,
+            routed_by_rule=routed_by_rule,
         )
 
         force_flush = False
@@ -217,6 +221,7 @@ class MessageAggregator:
                 message_chain=msg.message_chain,
                 adapter=msg.adapter,
                 pipeline_uuid=msg.pipeline_uuid,
+                routed_by_rule=msg.routed_by_rule,
             )
             return
 
@@ -231,6 +236,7 @@ class MessageAggregator:
             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:

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
@@ -128,6 +139,15 @@ 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
+
             # Extract response content from resp_message_chain
             if hasattr(query, 'resp_message_chain') and query.resp_message_chain:
                 # Serialize the last response message chain
@@ -162,6 +182,7 @@ 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,
                 role='assistant',
             )
@@ -183,6 +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,
@@ -197,6 +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}')
@@ -420,6 +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,

src/langbot/pkg/pipeline/preproc/preproc.py

@@ -36,17 +36,36 @@ class PreProcessor(stage.PipelineStage):
         session = await self.ap.sess_mgr.get_session(query)
 
         # When not local-agent, llm_model is None
-        try:
-            llm_model = (
-                await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
-                if selected_runner == 'local-agent'
-                else None
-            )
-        except ValueError:
-            self.ap.logger.warning(
-                f'LLM model {query.pipeline_config["ai"]["local-agent"]["model"] + " "}not found or not configured'
-            )
-            llm_model = None
+        llm_model = None
+        if selected_runner == 'local-agent':
+            # Read model config — new format is { primary: str, fallbacks: [str] },
+            # but handle legacy plain string for backward compatibility
+            model_config = query.pipeline_config['ai']['local-agent'].get('model', {})
+            if isinstance(model_config, str):
+                # Legacy format: plain UUID string
+                primary_uuid = model_config
+                fallback_uuids = []
+            else:
+                primary_uuid = model_config.get('primary', '')
+                fallback_uuids = model_config.get('fallbacks', [])
+
+            if primary_uuid:
+                try:
+                    llm_model = await self.ap.model_mgr.get_model_by_uuid(primary_uuid)
+                except ValueError:
+                    self.ap.logger.warning(f'LLM model {primary_uuid} not found or not configured')
+
+            # Resolve fallback model UUIDs
+            if fallback_uuids:
+                valid_fallbacks = []
+                for fb_uuid in fallback_uuids:
+                    try:
+                        await self.ap.model_mgr.get_model_by_uuid(fb_uuid)
+                        valid_fallbacks.append(fb_uuid)
+                    except ValueError:
+                        self.ap.logger.warning(f'Fallback model {fb_uuid} not found, skipping')
+                if valid_fallbacks:
+                    query.variables['_fallback_model_uuids'] = valid_fallbacks
 
         conversation = await self.ap.sess_mgr.get_conversation(
             query,
@@ -61,20 +80,28 @@ class PreProcessor(stage.PipelineStage):
         query.prompt = conversation.prompt.copy()
         query.messages = conversation.messages.copy()
 
-        if selected_runner == 'local-agent' and llm_model:
+        if selected_runner == 'local-agent':
             query.use_funcs = []
-            query.use_llm_model_uuid = llm_model.model_entity.uuid
+            if llm_model:
+                query.use_llm_model_uuid = llm_model.model_entity.uuid
 
-            if llm_model.model_entity.abilities.__contains__('func_call'):
-                # Get bound plugins and MCP servers for filtering tools
+                if llm_model.model_entity.abilities.__contains__('func_call'):
+                    # Get bound plugins and MCP servers for filtering tools
+                    bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+                    bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
+                    query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
+
+                    self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
+                    self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
+                    self.ap.logger.debug(f'Use funcs: {query.use_funcs}')
+
+            # If primary model doesn't support func_call but fallback models exist,
+            # load tools anyway since fallback models may support them
+            if not query.use_funcs and query.variables.get('_fallback_model_uuids'):
                 bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                 bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
                 query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
 
-                self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
-                self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
-                self.ap.logger.debug(f'Use funcs: {query.use_funcs}')
-
         sender_name = ''
 
         if isinstance(query.message_event, platform_events.GroupMessage):
@@ -133,7 +160,6 @@ class PreProcessor(stage.PipelineStage):
                 elif me.url:
                     content_list.append(provider_message.ContentElement.from_file_url(me.url, 'voice'))
             elif isinstance(me, platform_message.File):
-                # if me.url is not None:
                 content_list.append(provider_message.ContentElement.from_file_url(me.url, me.name))
             elif isinstance(me, platform_message.Quote) and quote_msg:
                 for msg in me.origin:
@@ -145,10 +171,29 @@ class PreProcessor(stage.PipelineStage):
                         ):
                             if msg.base64 is not None:
                                 content_list.append(provider_message.ContentElement.from_image_base64(msg.base64))
+                    elif isinstance(msg, platform_message.File):
+                        content_list.append(provider_message.ContentElement.from_file_url(msg.url, msg.name))
+                    elif isinstance(msg, platform_message.Voice):
+                        if msg.base64:
+                            content_list.append(
+                                provider_message.ContentElement.from_file_base64(msg.base64, 'voice.silk')
+                            )
+                        elif msg.url:
+                            content_list.append(provider_message.ContentElement.from_file_url(msg.url, 'voice'))
 
         query.variables['user_message_text'] = plain_text
 
         query.user_message = provider_message.Message(role='user', content=content_list)
+
+        # Extract knowledge base UUIDs into query variables so plugins can modify them
+        # during PromptPreProcessing before the runner performs retrieval.
+        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
+        if not kb_uuids:
+            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
+            if old_kb_uuid and old_kb_uuid != '__none__':
+                kb_uuids = [old_kb_uuid]
+        query.variables['_knowledge_base_uuids'] = list(kb_uuids)
+
         # =========== 触发事件 PromptPreProcessing
 
         event = events.PromptPreProcessing(

src/langbot/pkg/pipeline/process/handlers/chat.py

@@ -12,7 +12,7 @@ from ... import entities
 from ....provider import runner as runner_module
 
 import langbot_plugin.api.entities.events as events
-from ....utils import importutil, constants
+from ....utils import importutil, constants, runner as runner_utils
 from ....provider import runners
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -61,6 +61,9 @@ class ChatMessageHandler(handler.MessageHandler):
 
                 yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
             else:
+                self.ap.logger.debug(
+                    f'NormalMessageReceived event prevented default for query {query.query_id} without reply'
+                )
                 yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
         else:
             if event_ctx.event.user_message_alter is not None:
@@ -149,12 +152,19 @@ class ChatMessageHandler(handler.MessageHandler):
                 self.ap.logger.error(f'Conversation({query.query_id}) Request Failed: {error_info}')
                 traceback.print_exc()
 
-                hide_exception_info = query.pipeline_config['output']['misc']['hide-exception']
+                exception_handling = query.pipeline_config['output']['misc'].get('exception-handling', 'show-hint')
+
+                if exception_handling == 'show-error':
+                    user_notice = f'{e}'
+                elif exception_handling == 'show-hint':
+                    user_notice = query.pipeline_config['output']['misc'].get('failure-hint', 'Request failed.')
+                else:  # hide
+                    user_notice = None
 
                 yield entities.StageProcessResult(
                     result_type=entities.ResultType.INTERRUPT,
                     new_query=query,
-                    user_notice='请求失败' if hide_exception_info else f'{e}',
+                    user_notice=user_notice,
                     error_notice=f'{e}',
                     debug_notice=traceback.format_exc(),
                 )
@@ -185,14 +195,20 @@ class ChatMessageHandler(handler.MessageHandler):
 
                     pipeline_plugins = query.variables.get('_pipeline_bound_plugins', None)
 
+                    runner_category = runner_utils.get_runner_category_from_runner(
+                        runner_name, runner, query.pipeline_config
+                    )
+
                     payload = {
                         'query_id': query.query_id,
                         'adapter': adapter_name,
                         'runner': runner_name,
+                        'runner_category': runner_category,
                         'duration_ms': duration_ms,
                         'model_name': model_name,
                         'version': constants.semantic_version,
                         'instance_id': constants.instance_id,
+                        'edition': constants.edition,
                         'pipeline_plugins': pipeline_plugins,
                         'error': locals().get('error_info', None),
                         'timestamp': datetime.utcnow().isoformat(),

src/langbot/pkg/pipeline/resprule/resprule.py

@@ -37,6 +37,10 @@ class GroupRespondRuleCheckStage(stage.PipelineStage):
         if query.launcher_type.value != 'group':  # 只处理群消息
             return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
 
+        # 通过路由规则明确指定的流水线，跳过群响应规则检查
+        if query.variables and query.variables.get('_routed_by_rule', False):
+            return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
+
         rules = query.pipeline_config['trigger']['group-respond-rules']
 
         use_rule = rules

src/langbot/pkg/platform/botmgr.py

@@ -1,6 +1,8 @@
 from __future__ import annotations
 
 import asyncio
+import json
+import re
 import traceback
 import sqlalchemy
 
@@ -9,6 +11,7 @@ from ..core import app, entities as core_entities, taskmgr
 from ..discover import engine
 
 from ..entity.persistence import bot as persistence_bot
+from ..entity.persistence import pipeline as persistence_pipeline
 
 from ..entity.errors import platform as platform_errors
 
@@ -51,6 +54,148 @@ class RuntimeBot:
         self.task_context = taskmgr.TaskContext()
         self.logger = logger
 
+    @staticmethod
+    def _match_operator(actual: str, operator: str, expected: str) -> bool:
+        """Evaluate a single operator condition."""
+        if operator == 'eq':
+            return actual == expected
+        elif operator == 'neq':
+            return actual != expected
+        elif operator == 'contains':
+            return expected in actual
+        elif operator == 'not_contains':
+            return expected not in actual
+        elif operator == 'starts_with':
+            return actual.startswith(expected)
+        elif operator == 'regex':
+            try:
+                return bool(re.search(expected, actual))
+            except re.error:
+                return False
+        return False
+
+    PIPELINE_DISCARD = '__discard__'
+    PIPELINE_DISCARD_DISPLAY_NAME = 'Discarded'
+
+    def resolve_pipeline_uuid(
+        self,
+        launcher_type: str,
+        launcher_id: str,
+        message_text: str,
+        message_element_types: list[str] | None = None,
+    ) -> tuple[str | None, bool]:
+        """Resolve pipeline UUID based on routing rules.
+
+        Rules are evaluated in order; first match wins.
+        Falls back to use_pipeline_uuid if no rule matches.
+
+        Rule types:
+          - launcher_type: session type ("person" / "group")
+          - launcher_id: session / group id
+          - message_content: message text content
+          - message_has_element: message contains element of given type
+            (Image, Voice, File, Forward, Face, At, AtAll, Quote)
+            Operators: eq (has), neq (doesn't have)
+
+        Operators: eq, neq, contains, not_contains, starts_with, regex
+
+        When pipeline_uuid is ``__discard__``, the message should be
+        silently dropped by the caller.
+
+        Returns:
+            tuple: (pipeline_uuid, routed_by_rule) - routed_by_rule is True
+            when a routing rule matched, False when falling back to default.
+        """
+        rules = self.bot_entity.pipeline_routing_rules or []
+        element_type_set = set(message_element_types or [])
+
+        for rule in rules:
+            rule_type = rule.get('type')
+            operator = rule.get('operator', 'eq')
+            rule_value = rule.get('value', '')
+            target_uuid = rule.get('pipeline_uuid')
+            if not rule_type or not target_uuid:
+                continue
+
+            if rule_type == 'launcher_type':
+                if self._match_operator(launcher_type, operator, rule_value):
+                    return target_uuid, True
+            elif rule_type == 'launcher_id':
+                if self._match_operator(str(launcher_id), operator, str(rule_value)):
+                    return target_uuid, True
+            elif rule_type == 'message_content':
+                if self._match_operator(message_text, operator, rule_value):
+                    return target_uuid, True
+            elif rule_type == 'message_has_element':
+                has_element = rule_value in element_type_set
+                if operator == 'eq' and has_element:
+                    return target_uuid, True
+                elif operator == 'neq' and not has_element:
+                    return target_uuid, True
+
+        return self.bot_entity.use_pipeline_uuid, False
+
+    async def _record_discarded_message(
+        self,
+        launcher_type: provider_session.LauncherTypes,
+        launcher_id: str | int,
+        sender_id: str | int,
+        message_event: platform_events.MessageEvent,
+        message_chain: platform_message.MessageChain,
+    ) -> None:
+        """Record a discarded message in the monitoring system."""
+        try:
+            if hasattr(message_chain, 'model_dump'):
+                message_content = json.dumps(message_chain.model_dump(), ensure_ascii=False)
+            else:
+                message_content = str(message_chain)
+
+            sender_name = None
+            if hasattr(message_event, 'sender'):
+                if hasattr(message_event.sender, 'nickname'):
+                    sender_name = message_event.sender.nickname
+                elif hasattr(message_event.sender, 'member_name'):
+                    sender_name = message_event.sender.member_name
+
+            # Use the same session_id format as monitoring_helper.py
+            session_id = f'{launcher_type}_{launcher_id}'
+            platform = launcher_type.value if hasattr(launcher_type, 'value') else str(launcher_type)
+
+            await self.ap.monitoring_service.record_message(
+                bot_id=self.bot_entity.uuid,
+                bot_name=self.bot_entity.name or self.bot_entity.uuid,
+                pipeline_id=self.PIPELINE_DISCARD,
+                pipeline_name=self.PIPELINE_DISCARD_DISPLAY_NAME,
+                message_content=message_content,
+                session_id=session_id,
+                status='discarded',
+                level='info',
+                platform=platform,
+                user_id=str(sender_id),
+                user_name=sender_name,
+            )
+
+            # Ensure the session exists so the message appears in the session monitor.
+            # Don't overwrite pipeline info — a session may have messages from
+            # multiple pipelines; discarding shouldn't change the displayed pipeline.
+            session_updated = await self.ap.monitoring_service.update_session_activity(
+                session_id,
+            )
+            if not session_updated:
+                # No session yet (first message for this launcher was discarded).
+                await self.ap.monitoring_service.record_session_start(
+                    session_id=session_id,
+                    bot_id=self.bot_entity.uuid,
+                    bot_name=self.bot_entity.name or self.bot_entity.uuid,
+                    pipeline_id=self.PIPELINE_DISCARD,
+                    pipeline_name=self.PIPELINE_DISCARD_DISPLAY_NAME,
+                    platform=platform,
+                    user_id=str(sender_id),
+                    user_name=sender_name,
+                )
+        except Exception as e:
+            await self.logger.error(f'Failed to record discarded message: {e}')
+
     async def initialize(self):
         async def on_friend_message(
             event: platform_events.FriendMessage,
@@ -82,6 +227,23 @@ class RuntimeBot:
                     if custom_launcher_id:
                         launcher_id = custom_launcher_id
 
+                message_text = str(event.message_chain)
+                element_types = [comp.type for comp in event.message_chain]
+                pipeline_uuid, routed_by_rule = self.resolve_pipeline_uuid(
+                    'person', launcher_id, message_text, element_types
+                )
+
+                if pipeline_uuid == self.PIPELINE_DISCARD:
+                    await self.logger.info('Person message discarded by routing rule')
+                    await self._record_discarded_message(
+                        provider_session.LauncherTypes.PERSON,
+                        launcher_id,
+                        event.sender.id,
+                        event,
+                        event.message_chain,
+                    )
+                    return
+
                 await self.ap.msg_aggregator.add_message(
                     bot_uuid=self.bot_entity.uuid,
                     launcher_type=provider_session.LauncherTypes.PERSON,
@@ -90,7 +252,8 @@ class RuntimeBot:
                     message_event=event,
                     message_chain=event.message_chain,
                     adapter=adapter,
-                    pipeline_uuid=self.bot_entity.use_pipeline_uuid,
+                    pipeline_uuid=pipeline_uuid,
+                    routed_by_rule=routed_by_rule,
                 )
             else:
                 await self.logger.info('Pipeline skipped for person message due to webhook response')
@@ -125,6 +288,23 @@ class RuntimeBot:
                     if custom_launcher_id:
                         launcher_id = custom_launcher_id
 
+                message_text = str(event.message_chain)
+                element_types = [comp.type for comp in event.message_chain]
+                pipeline_uuid, routed_by_rule = self.resolve_pipeline_uuid(
+                    'group', launcher_id, message_text, element_types
+                )
+
+                if pipeline_uuid == self.PIPELINE_DISCARD:
+                    await self.logger.info('Group message discarded by routing rule')
+                    await self._record_discarded_message(
+                        provider_session.LauncherTypes.GROUP,
+                        launcher_id,
+                        event.sender.id,
+                        event,
+                        event.message_chain,
+                    )
+                    return
+
                 await self.ap.msg_aggregator.add_message(
                     bot_uuid=self.bot_entity.uuid,
                     launcher_type=provider_session.LauncherTypes.GROUP,
@@ -133,7 +313,8 @@ class RuntimeBot:
                     message_event=event,
                     message_chain=event.message_chain,
                     adapter=adapter,
-                    pipeline_uuid=self.bot_entity.use_pipeline_uuid,
+                    pipeline_uuid=pipeline_uuid,
+                    routed_by_rule=routed_by_rule,
                 )
             else:
                 await self.logger.info('Pipeline skipped for group message due to webhook response')
@@ -141,6 +322,50 @@ class RuntimeBot:
         self.adapter.register_listener(platform_events.FriendMessage, on_friend_message)
         self.adapter.register_listener(platform_events.GroupMessage, on_group_message)
 
+        # Register feedback listener (only effective on adapters that support it)
+        async def on_feedback(
+            event: platform_events.FeedbackEvent,
+            adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter,
+        ):
+            try:
+                # Resolve pipeline name
+                pipeline_name = ''
+                if self.bot_entity.use_pipeline_uuid:
+                    try:
+                        pipeline_result = await self.ap.persistence_mgr.execute_async(
+                            sqlalchemy.select(persistence_pipeline.LegacyPipeline.name).where(
+                                persistence_pipeline.LegacyPipeline.uuid == self.bot_entity.use_pipeline_uuid
+                            )
+                        )
+                        pipeline_row = pipeline_result.first()
+                        if pipeline_row:
+                            pipeline_name = pipeline_row[0]
+                    except Exception:
+                        pass
+
+                await self.ap.monitoring_service.record_feedback(
+                    feedback_id=event.feedback_id,
+                    feedback_type=event.feedback_type,
+                    feedback_content=event.feedback_content,
+                    inaccurate_reasons=event.inaccurate_reasons,
+                    bot_id=self.bot_entity.uuid,
+                    bot_name=self.bot_entity.name,
+                    pipeline_id=self.bot_entity.use_pipeline_uuid or '',
+                    pipeline_name=pipeline_name,
+                    session_id=event.session_id,
+                    message_id=event.message_id,
+                    stream_id=event.stream_id,
+                    user_id=event.user_id,
+                    platform=adapter.__class__.__name__,
+                )
+                await self.logger.info(
+                    f'Recorded feedback: feedback_id={event.feedback_id}, type={event.feedback_type}'
+                )
+            except Exception:
+                await self.logger.error(f'Failed to record feedback: {traceback.format_exc()}')
+
+        self.adapter.register_listener(platform_events.FeedbackEvent, on_feedback)
+
     async def run(self):
         async def exception_wrapper():
             try:
@@ -196,12 +421,20 @@ class PlatformManager:
         # delete all bot log images
         await self.ap.storage_mgr.storage_provider.delete_dir_recursive('bot_log_images')
 
+        disabled_adapters = self.ap.instance_config.data.get('system', {}).get('disabled_adapters', []) or []
+
         self.adapter_components = self.ap.discover.get_components_by_kind('MessagePlatformAdapter')
         adapter_dict: dict[str, type[abstract_platform_adapter.AbstractMessagePlatformAdapter]] = {}
         for component in self.adapter_components:
+            if component.metadata.name in disabled_adapters:
+                continue
             adapter_dict[component.metadata.name] = component.get_python_component_class()
         self.adapter_dict = adapter_dict
 
+        # Filter out disabled adapters from components list (for API responses)
+        if disabled_adapters:
+            self.adapter_components = [c for c in self.adapter_components if c.metadata.name not in disabled_adapters]
+
         # initialize websocket adapter
         websocket_adapter_class = self.adapter_dict['websocket']
         websocket_logger = EventLogger(name='websocket-adapter', ap=self.ap)
@@ -282,6 +515,8 @@ class PlatformManager:
         return runtime_bot
 
     async def get_bot_by_uuid(self, bot_uuid: str) -> RuntimeBot | None:
+        if self.websocket_proxy_bot and self.websocket_proxy_bot.bot_entity.uuid == bot_uuid:
+            return self.websocket_proxy_bot
         for bot in self.bots:
             if bot.bot_entity.uuid == bot_uuid:
                 return bot

src/langbot/pkg/platform/sources/aiocqhttp.yaml

@@ -5,19 +5,29 @@ metadata:
   label:
     en_US: OneBot v11
     zh_Hans: OneBot v11
+    zh_Hant: OneBot v11
   description:
-    en_US: OneBot v11 Adapter
-    zh_Hans: OneBot v11 适配器，请查看文档了解使用方式
+    en_US: OneBot v11 Adapter, used for QQ bots
+    zh_Hans: OneBot v11 适配器，用于接入 QQ 机器人协议端，请查看文档了解使用方式
+    zh_Hant: OneBot v11 適配器，用於接入 QQ 機器人協定端，請查看文件了解使用方式
   icon: onebot.png
 spec:
+  categories:
+    - protocol
+  help_links:
+    zh: https://link.langbot.app/zh/platforms/aiocqhttp
+    en: https://link.langbot.app/en/platforms/aiocqhttp
+    ja: https://link.langbot.app/ja/platforms/aiocqhttp
   config:
     - name: host
       label:
         en_US: Host
         zh_Hans: 主机
+        zh_Hant: 主機
       description:
         en_US: The host that OneBot v11 listens on for reverse WebSocket connections. Unless you know what you're doing, use 0.0.0.0
         zh_Hans: OneBot v11 监听的反向 WS 主机，除非你知道自己在做什么，否则请写 0.0.0.0
+        zh_Hant: OneBot v11 監聽的反向 WS 主機，除非你知道自己在做什麼，否則請填 0.0.0.0
       type: string
       required: true
       default: 0.0.0.0
@@ -25,9 +35,11 @@ spec:
       label:
         en_US: Port
         zh_Hans: 端口
+        zh_Hant: 連接埠
       description:
         en_US: Port
         zh_Hans: 监听的端口
+        zh_Hant: 監聽的連接埠
       type: integer
       required: true
       default: 2280
@@ -35,9 +47,11 @@ spec:
       label:
         en_US: Access Token
         zh_Hans: 访问令牌
+        zh_Hant: 存取令牌
       description:
         en_US: Custom connection token for the protocol endpoint. If the protocol endpoint is not set, don't fill it
         zh_Hans: 自定义的与协议端的连接令牌，若协议端未设置，则不填
+        zh_Hant: 自訂的與協定端的連線令牌，若協定端未設定，則不填
       type: string
       required: false
       default: ""

src/langbot/pkg/platform/sources/dingtalk.py

@@ -71,7 +71,8 @@ class DingTalkMessageConverter(abstract_platform_adapter.AbstractMessageConverte
                     yiri_msg_list.append(platform_message.Image(base64=element['Picture']))
         else:
             # 回退到原有简单逻辑
-            if event.content:
+            # 对于音频消息，content 来自 recognition 转写文字，在下方音频处理块中统一处理
+            if event.content and event.type != 'audio':
                 text_content = event.content.replace('@' + bot_name, '')
                 yiri_msg_list.append(platform_message.Plain(text=text_content))
             if event.picture:
@@ -81,7 +82,38 @@ class DingTalkMessageConverter(abstract_platform_adapter.AbstractMessageConverte
         if event.file:
             yiri_msg_list.append(platform_message.File(url=event.file, name=event.name))
         if event.audio:
-            yiri_msg_list.append(platform_message.Voice(base64=event.audio))
+            # 优先使用钉钉自带的语音转写文字（recognition字段）
+            if event.content and event.type == 'audio':
+                yiri_msg_list.append(platform_message.Plain(text=event.content))
+            else:
+                yiri_msg_list.append(platform_message.Voice(base64=event.audio))
+
+        # Handle quoted/replied message - extract content as top-level components
+        # so that plugins like FileReader can process them the same way as direct messages
+        if event.quoted_message:
+            quote_info = event.quoted_message
+            msg_type = quote_info.get('msg_type', '')
+
+            # Process quoted file - add as top-level File component (same as private chat)
+            if msg_type == 'file' and quote_info.get('file_url'):
+                file_name = quote_info.get('file_name', 'file')
+                yiri_msg_list.append(platform_message.File(url=quote_info['file_url'], name=file_name))
+
+            # Process quoted image - add as top-level Image component
+            elif msg_type == 'picture' and quote_info.get('picture'):
+                yiri_msg_list.append(platform_message.Image(base64=quote_info['picture']))
+
+            # Process quoted audio - add as top-level Voice component
+            elif msg_type == 'audio' and quote_info.get('audio'):
+                yiri_msg_list.append(platform_message.Voice(base64=quote_info['audio']))
+
+            # Process quoted text - add as Plain text with context prefix
+            elif msg_type == 'text' and quote_info.get('content'):
+                yiri_msg_list.append(platform_message.Plain(text=f'[引用消息] {quote_info["content"]}'))
+
+            # Process quoted rich text - add as Plain text with context prefix
+            elif msg_type == 'richText' and quote_info.get('content'):
+                yiri_msg_list.append(platform_message.Plain(text=f'[引用消息] {quote_info["content"]}'))
 
         chain = platform_message.MessageChain(yiri_msg_list)
 

src/langbot/pkg/platform/sources/dingtalk.yaml

@@ -5,16 +5,25 @@ metadata:
   label:
     en_US: DingTalk
     zh_Hans: 钉钉
+    zh_Hant: 釘釘
   description:
     en_US: DingTalk Adapter
     zh_Hans: 钉钉适配器，请查看文档了解使用方式
+    zh_Hant: 釘釘適配器，請查看文件了解使用方式
   icon: dingtalk.svg
 spec:
+  categories:
+    - china
+  help_links:
+    zh: https://link.langbot.app/zh/platforms/dingtalk
+    en: https://link.langbot.app/en/platforms/dingtalk
+    ja: https://link.langbot.app/ja/platforms/dingtalk
   config:
     - name: client_id
       label:
         en_US: Client ID
         zh_Hans: 客户端ID
+        zh_Hant: 用戶端ID
       type: string
       required: true
       default: ""
@@ -22,6 +31,7 @@ spec:
       label:
         en_US: Client Secret
         zh_Hans: 客户端密钥
+        zh_Hant: 用戶端密鑰
       type: string
       required: true
       default: ""
@@ -29,6 +39,7 @@ spec:
       label:
         en_US: Robot Code
         zh_Hans: 机器人代码
+        zh_Hant: 機器人代碼
       type: string
       required: true
       default: ""
@@ -36,6 +47,7 @@ spec:
       label:
         en_US: Robot Name
         zh_Hans: 机器人名称
+        zh_Hant: 機器人名稱
       type: string
       required: true
       default: ""
@@ -43,6 +55,7 @@ spec:
       label:
         en_US: Markdown Card
         zh_Hans: 是否使用 Markdown 卡片
+        zh_Hant: 是否使用 Markdown 卡片
       type: boolean
       required: false
       default: true
@@ -50,9 +63,11 @@ spec:
       label:
         en_US: Enable Stream Reply Mode
         zh_Hans: 启用钉钉卡片流式回复模式
+        zh_Hant: 啟用釘釘卡片串流回覆模式
       description:
         en_US: If enabled, the bot will use the stream of lark reply mode
         zh_Hans: 如果启用，将使用钉钉卡片流式方式来回复内容
+        zh_Hant: 如果啟用，將使用釘釘卡片串流方式來回覆內容
       type: boolean
       required: true
       default: false
@@ -60,6 +75,7 @@ spec:
       label:
         en_US: Card Auto Layout
         zh_Hans: 卡片宽屏自动布局
+        zh_Hant: 卡片寬螢幕自動佈局
       type: boolean
       required: false
       default: false
@@ -67,6 +83,7 @@ spec:
       label:
         en_US: card template id
         zh_Hans: 卡片模板ID
+        zh_Hant: 卡片範本ID
       type: string
       required: true
       default: "填写你的卡片template_id"

src/langbot/pkg/platform/sources/discord.py

@@ -14,7 +14,7 @@ import io
 import asyncio
 from enum import Enum
 
-import aiohttp
+from langbot.pkg.utils import httpclient
 import pydantic
 
 import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
@@ -622,23 +622,23 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
                     image_bytes = base64.b64decode(base64_data)
                 elif ele.url:
                     # 从URL下载图片
-                    async with aiohttp.ClientSession() as session:
-                        async with session.get(ele.url) as response:
-                            image_bytes = await response.read()
-                            # 从URL或Content-Type推断文件类型
-                            content_type = response.headers.get('Content-Type', '')
-                            if 'jpeg' in content_type or 'jpg' in content_type:
-                                filename = f'{uuid.uuid4()}.jpg'
-                            elif 'gif' in content_type:
-                                filename = f'{uuid.uuid4()}.gif'
-                            elif 'webp' in content_type:
-                                filename = f'{uuid.uuid4()}.webp'
-                            elif ele.url.lower().endswith(('.jpg', '.jpeg')):
-                                filename = f'{uuid.uuid4()}.jpg'
-                            elif ele.url.lower().endswith('.gif'):
-                                filename = f'{uuid.uuid4()}.gif'
-                            elif ele.url.lower().endswith('.webp'):
-                                filename = f'{uuid.uuid4()}.webp'
+                    session = httpclient.get_session()
+                    async with session.get(ele.url) as response:
+                        image_bytes = await response.read()
+                        # 从URL或Content-Type推断文件类型
+                        content_type = response.headers.get('Content-Type', '')
+                        if 'jpeg' in content_type or 'jpg' in content_type:
+                            filename = f'{uuid.uuid4()}.jpg'
+                        elif 'gif' in content_type:
+                            filename = f'{uuid.uuid4()}.gif'
+                        elif 'webp' in content_type:
+                            filename = f'{uuid.uuid4()}.webp'
+                        elif ele.url.lower().endswith(('.jpg', '.jpeg')):
+                            filename = f'{uuid.uuid4()}.jpg'
+                        elif ele.url.lower().endswith('.gif'):
+                            filename = f'{uuid.uuid4()}.gif'
+                        elif ele.url.lower().endswith('.webp'):
+                            filename = f'{uuid.uuid4()}.webp'
                 elif ele.path:
                     # 从文件路径读取图片
                     # 确保路径没有空字节
@@ -702,9 +702,9 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
                     file_base64 = ele.base64.split(',')[-1]
                     file_bytes = base64.b64decode(file_base64)
                 elif ele.url:
-                    async with aiohttp.ClientSession() as session:
-                        async with session.get(ele.url) as response:
-                            file_bytes = await response.read()
+                    session = httpclient.get_session()
+                    async with session.get(ele.url) as response:
+                        file_bytes = await response.read()
                 if file_bytes:
                     files.append(discord.File(fp=io.BytesIO(file_bytes), filename=filename))
             elif isinstance(ele, platform_message.File):
@@ -717,9 +717,9 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
                     else:
                         file_bytes = base64.b64decode(ele.base64)
                 elif ele.url:
-                    async with aiohttp.ClientSession() as session:
-                        async with session.get(ele.url) as response:
-                            file_bytes = await response.read()
+                    session = httpclient.get_session()
+                    async with session.get(ele.url) as response:
+                        file_bytes = await response.read()
                 if file_bytes:
                     files.append(discord.File(fp=io.BytesIO(file_bytes), filename=filename))
             elif isinstance(ele, platform_message.Forward):
@@ -775,12 +775,12 @@ class DiscordMessageConverter(abstract_platform_adapter.AbstractMessageConverter
 
         # attachments
         for attachment in message.attachments:
-            async with aiohttp.ClientSession(trust_env=True) as session:
-                async with session.get(attachment.url) as response:
-                    image_data = await response.read()
-                    image_base64 = base64.b64encode(image_data).decode('utf-8')
-                    image_format = response.headers['Content-Type']
-                    element_list.append(platform_message.Image(base64=f'data:{image_format};base64,{image_base64}'))
+            session = httpclient.get_session(trust_env=True)
+            async with session.get(attachment.url) as response:
+                image_data = await response.read()
+                image_base64 = base64.b64encode(image_data).decode('utf-8')
+                image_format = response.headers['Content-Type']
+                element_list.append(platform_message.Image(base64=f'data:{image_format};base64,{image_base64}'))
 
         return platform_message.MessageChain(element_list)
 

src/langbot/pkg/platform/sources/discord.yaml

@@ -5,16 +5,38 @@ metadata:
   label:
     en_US: Discord
     zh_Hans: Discord
+    zh_Hant: Discord
+    ja_JP: Discord
+    th_TH: Discord
+    vi_VN: Discord
+    es_ES: Discord
   description:
     en_US: Discord Adapter
-    zh_Hans: Discord 适配器，请查看文档了解使用方式
+    zh_Hans: Discord 适配器，需要可连接 Discord 服务器的网络环境
+    zh_Hant: Discord 適配器，需要可連線 Discord 伺服器的網路環境
+    ja_JP: Discord アダプター、Discord サーバーに接続可能なネットワーク環境が必要です
+    th_TH: อะแดปเตอร์ Discord ต้องการสภาพแวดล้อมเครือข่ายที่สามารถเชื่อมต่อกับเซิร์ฟเวอร์ Discord ได้
+    vi_VN: Bộ điều hợp Discord, cần môi trường mạng có thể kết nối với máy chủ Discord
+    es_ES: Adaptador de Discord, requiere un entorno de red con acceso al servidor de Discord
   icon: discord.svg
 spec:
+  categories:
+    - popular
+    - global
+  help_links:
+    zh: https://link.langbot.app/zh/platforms/discord
+    en: https://link.langbot.app/en/platforms/discord
+    ja: https://link.langbot.app/ja/platforms/discord
   config:
     - name: client_id
       label:
         en_US: Client ID
         zh_Hans: 客户端ID
+        zh_Hant: 用戶端ID
+        ja_JP: クライアント ID
+        th_TH: รหัสไคลเอนต์
+        vi_VN: ID khách hàng
+        es_ES: ID de cliente
       type: string
       required: true
       default: ""
@@ -22,6 +44,11 @@ spec:
       label:
         en_US: Token
         zh_Hans: 令牌
+        zh_Hant: 令牌
+        ja_JP: トークン
+        th_TH: โทเค็น
+        vi_VN: Mã thông báo
+        es_ES: Token
       type: string
       required: true
       default: ""

src/langbot/pkg/platform/sources/kook.py

@@ -9,6 +9,8 @@ import traceback
 import time
 
 import aiohttp
+
+from langbot.pkg.utils import httpclient
 import websockets
 import pydantic
 
@@ -120,16 +122,16 @@ class KookMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
             if content:
                 # Download image and convert to base64
                 try:
-                    async with aiohttp.ClientSession() as session:
-                        async with session.get(content) as response:
-                            if response.status == 200:
-                                image_bytes = await response.read()
-                                image_base64 = base64.b64encode(image_bytes).decode('utf-8')
-                                # Detect image format
-                                content_type = response.headers.get('Content-Type', 'image/png')
-                                components.append(
-                                    platform_message.Image(base64=f'data:{content_type};base64,{image_base64}')
-                                )
+                    session = httpclient.get_session()
+                    async with session.get(content) as response:
+                        if response.status == 200:
+                            image_bytes = await response.read()
+                            image_base64 = base64.b64encode(image_bytes).decode('utf-8')
+                            # Detect image format
+                            content_type = response.headers.get('Content-Type', 'image/png')
+                            components.append(
+                                platform_message.Image(base64=f'data:{content_type};base64,{image_base64}')
+                            )
                 except Exception:
                     # If download fails, just add as plain text
                     components.append(platform_message.Plain(text=f'[Image: {content}]'))
@@ -295,17 +297,17 @@ class KookAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             'Authorization': f'Bot {self.config["token"]}',
         }
 
-        async with aiohttp.ClientSession() as session:
-            async with session.get(base_url, params=params, headers=headers) as response:
-                if response.status == 200:
-                    data = await response.json()
-                    if data.get('code') == 0:
-                        gateway_url = data['data']['url']
-                        return gateway_url
-                    else:
-                        raise Exception(f'Failed to get gateway URL: {data.get("message")}')
+        session = httpclient.get_session()
+        async with session.get(base_url, params=params, headers=headers) as response:
+            if response.status == 200:
+                data = await response.json()
+                if data.get('code') == 0:
+                    gateway_url = data['data']['url']
+                    return gateway_url
                 else:
-                    raise Exception(f'Failed to get gateway URL: HTTP {response.status}')
+                    raise Exception(f'Failed to get gateway URL: {data.get("message")}')
+            else:
+                raise Exception(f'Failed to get gateway URL: HTTP {response.status}')
 
     async def _get_bot_user_info(self) -> dict:
         """Get bot's own user information from KOOK API"""
@@ -315,17 +317,17 @@ class KookAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             'Authorization': f'Bot {self.config["token"]}',
         }
 
-        async with aiohttp.ClientSession() as session:
-            async with session.get(base_url, headers=headers) as response:
-                if response.status == 200:
-                    data = await response.json()
-                    if data.get('code') == 0:
-                        user_info = data['data']
-                        return user_info
-                    else:
-                        raise Exception(f'Failed to get bot user info: {data.get("message")}')
+        session = httpclient.get_session()
+        async with session.get(base_url, headers=headers) as response:
+            if response.status == 200:
+                data = await response.json()
+                if data.get('code') == 0:
+                    user_info = data['data']
+                    return user_info
                 else:
-                    raise Exception(f'Failed to get bot user info: HTTP {response.status}')
+                    raise Exception(f'Failed to get bot user info: {data.get("message")}')
+            else:
+                raise Exception(f'Failed to get bot user info: HTTP {response.status}')
 
     async def _handle_hello(self, data: dict):
         """Handle HELLO signal (signal 1)"""
@@ -510,7 +512,7 @@ class KookAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         try:
             if not self.http_session:
-                self.http_session = aiohttp.ClientSession()
+                self.http_session = httpclient.get_session()
 
             async with self.http_session.post(url, json=payload, headers=headers) as response:
                 if response.status == 200:
@@ -576,7 +578,7 @@ class KookAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         try:
             if not self.http_session:
-                self.http_session = aiohttp.ClientSession()
+                self.http_session = httpclient.get_session()
 
             async with self.http_session.post(url, json=payload, headers=headers) as response:
                 if response.status == 200:
@@ -624,7 +626,7 @@ class KookAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         try:
             # Create HTTP session
-            self.http_session = aiohttp.ClientSession()
+            self.http_session = httpclient.get_session()
 
             await self.logger.info('Starting KOOK adapter')
 

src/langbot/pkg/platform/sources/kook.yaml

@@ -5,16 +5,25 @@ metadata:
   label:
     en_US: KOOK
     zh_Hans: KOOK
+    zh_Hant: KOOK
   description:
     en_US: KOOK Adapter (formerly KaiHeiLa)
     zh_Hans: KOOK 适配器(原开黑啦)，支持频道消息和私聊消息
+    zh_Hant: KOOK 適配器（原開黑啦），支援頻道訊息和私聊訊息
   icon: kook.png
 spec:
+  categories:
+    - china
+  help_links:
+    zh: https://link.langbot.app/zh/platforms/kook
+    en: https://link.langbot.app/en/platforms/kook
+    ja: https://link.langbot.app/ja/platforms/kook
   config:
     - name: token
       label:
         en_US: Bot Token
         zh_Hans: 机器人令牌
+        zh_Hant: 機器人令牌
       type: string
       required: true
       default: ""

src/langbot/pkg/platform/sources/lark.py

@@ -17,7 +17,7 @@ import tempfile
 import os
 import mimetypes
 
-import aiohttp
+from langbot.pkg.utils import httpclient
 import lark_oapi.ws.exception
 import quart
 from lark_oapi.api.im.v1 import *
@@ -78,13 +78,13 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
                 return None
         elif msg.url:
             try:
-                async with aiohttp.ClientSession() as session:
-                    async with session.get(msg.url) as response:
-                        if response.status == 200:
-                            image_bytes = await response.read()
-                        else:
-                            print(f'Failed to download image from {msg.url}: HTTP {response.status}')
-                            return None
+                session = httpclient.get_session()
+                async with session.get(msg.url) as response:
+                    if response.status == 200:
+                        image_bytes = await response.read()
+                    else:
+                        print(f'Failed to download image from {msg.url}: HTTP {response.status}')
+                        return None
             except Exception as e:
                 print(f'Failed to download image from {msg.url}: {e}')
                 traceback.print_exc()
@@ -208,10 +208,10 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
                 pass
         elif msg.url:
             try:
-                async with aiohttp.ClientSession() as session:
-                    async with session.get(msg.url) as resp:
-                        if resp.status == 200:
-                            data = await resp.read()
+                session = httpclient.get_session()
+                async with session.get(msg.url) as resp:
+                    if resp.status == 200:
+                        data = await resp.read()
             except Exception:
                 pass
         elif msg.path:
@@ -575,6 +575,127 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
 
 
 class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
+    _processed_thread_quote_cache: typing.ClassVar[dict[str, float]] = {}
+    _processed_thread_quote_cache_max_size: typing.ClassVar[int] = 4096
+    _processed_thread_quote_cache_ttl_seconds: typing.ClassVar[int] = 86400
+
+    @classmethod
+    def _prune_processed_thread_quote_cache(cls, now: typing.Optional[float] = None) -> None:
+        if now is None:
+            now = time.time()
+
+        expire_before = now - cls._processed_thread_quote_cache_ttl_seconds
+        while cls._processed_thread_quote_cache:
+            oldest_key, oldest_ts = next(iter(cls._processed_thread_quote_cache.items()))
+            if oldest_ts >= expire_before:
+                break
+            cls._processed_thread_quote_cache.pop(oldest_key, None)
+
+        while len(cls._processed_thread_quote_cache) > cls._processed_thread_quote_cache_max_size:
+            oldest_key = next(iter(cls._processed_thread_quote_cache))
+            cls._processed_thread_quote_cache.pop(oldest_key, None)
+
+    @classmethod
+    def _mark_thread_quote_processed(cls, thread_id: str) -> None:
+        now = time.time()
+        cls._prune_processed_thread_quote_cache(now)
+        cls._processed_thread_quote_cache[thread_id] = now
+
+    @classmethod
+    def _extract_quote_message_id(cls, message: EventMessage) -> typing.Optional[str]:
+        """
+        Extract the message ID to quote from the given message.
+
+        Rules:
+        - First thread reply in a topic: return parent_id and mark topic as processed
+        - Follow-up thread replies in the same topic: return None
+        - Non-thread message: return parent_id if valid (non-empty, different from message_id)
+
+        Thread reply state is kept in a bounded TTL cache to avoid unbounded memory growth.
+        """
+        parent_id = getattr(message, 'parent_id', None)
+        if not parent_id:
+            return None
+
+        message_id = getattr(message, 'message_id', None)
+        if parent_id == message_id:
+            return None
+
+        thread_id = getattr(message, 'thread_id', None)
+        if thread_id:
+            cls._prune_processed_thread_quote_cache()
+            if thread_id in cls._processed_thread_quote_cache:
+                return None
+            cls._mark_thread_quote_processed(thread_id)
+
+        return parent_id
+
+    @staticmethod
+    def _build_event_message_from_message_item(message_item: Message) -> typing.Optional[EventMessage]:
+        """
+        Build EventMessage from SDK typed Message item.
+
+        Returns None if body or content is missing.
+        """
+        body = getattr(message_item, 'body', None)
+        if not body:
+            return None
+
+        content = getattr(body, 'content', None)
+        if not content:
+            return None
+
+        event_data = {
+            'message_id': message_item.message_id,
+            'message_type': message_item.msg_type,
+            'content': content,
+            'create_time': message_item.create_time,
+            'mentions': getattr(message_item, 'mentions', []) or [],
+        }
+
+        # Preserve thread-related fields
+        if hasattr(message_item, 'parent_id') and message_item.parent_id:
+            event_data['parent_id'] = message_item.parent_id
+        if hasattr(message_item, 'root_id') and message_item.root_id:
+            event_data['root_id'] = message_item.root_id
+        if hasattr(message_item, 'thread_id') and message_item.thread_id:
+            event_data['thread_id'] = message_item.thread_id
+        if hasattr(message_item, 'chat_id') and message_item.chat_id:
+            event_data['chat_id'] = message_item.chat_id
+
+        return EventMessage(event_data)
+
+    @staticmethod
+    async def _fetch_quoted_message(
+        quote_message_id: str,
+        api_client: lark_oapi.Client,
+    ) -> typing.Optional[platform_message.MessageChain]:
+        """
+        Fetch the quoted message and convert to MessageChain.
+
+        Returns None if:
+        - API call fails
+        - Response items is empty
+        - Message item normalization fails
+        """
+        request = GetMessageRequest.builder().message_id(quote_message_id).build()
+        response = await api_client.im.v1.message.aget(request)
+
+        if not response.success():
+            return None
+
+        items = getattr(response.data, 'items', None)
+        if not items:
+            return None
+
+        message_item = items[0]
+        event_message = LarkEventConverter._build_event_message_from_message_item(message_item)
+        if event_message is None:
+            return None
+
+        quote_chain = await LarkMessageConverter.target2yiri(event_message, api_client)
+        return quote_chain
+
     @staticmethod
     async def yiri2target(
         event: platform_events.MessageEvent,
@@ -587,6 +708,31 @@ class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
     ) -> platform_events.Event:
         message_chain = await LarkMessageConverter.target2yiri(event.event.message, api_client)
 
+        # Check for quote/reply message
+        # Extract files/images/voice from quote and add them as top-level components
+        # so that plugins like FileReader can process them the same way as direct messages
+        quote_message_id = LarkEventConverter._extract_quote_message_id(event.event.message)
+        if quote_message_id:
+            quote_chain = await LarkEventConverter._fetch_quoted_message(quote_message_id, api_client)
+            if quote_chain:
+                # Filter out Source component from quoted chain, keep only content
+                quote_components = [comp for comp in quote_chain if not isinstance(comp, platform_message.Source)]
+
+                # Add quoted content as top-level components instead of wrapping in Quote
+                for comp in quote_components:
+                    if isinstance(comp, platform_message.File):
+                        # Add file as top-level component (same as direct message)
+                        message_chain.append(comp)
+                    elif isinstance(comp, platform_message.Image):
+                        # Add image as top-level component
+                        message_chain.append(comp)
+                    elif isinstance(comp, platform_message.Voice):
+                        # Add voice as top-level component
+                        message_chain.append(comp)
+                    elif isinstance(comp, platform_message.Plain):
+                        # Add text with context prefix
+                        message_chain.append(platform_message.Plain(text=f'[引用消息] {comp.text}'))
+
         if event.event.message.chat_type == 'p2p':
             return platform_events.FriendMessage(
                 sender=platform_entities.Friend(
@@ -641,6 +787,13 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
     card_id_dict: dict[str, str]  # 消息id到卡片id的映射，便于创建卡片后的发送消息到指定卡片
 
+    # Monitoring message ID mapping for feedback correlation
+    # Temp: user Lark message ID → monitoring_message_id (populated by on_monitoring_message_created, consumed by create_message_card)
+    pending_monitoring_msg: dict[str, str]
+    # Final: reply Lark message ID → (monitoring_message_id, timestamp) (used by feedback callbacks)
+    reply_to_monitoring_msg: dict[str, tuple[str, float]]
+    _MONITORING_MAPPING_TTL = 600  # 10 minutes
+
     seq: int  # 用于在发送卡片消息中识别消息顺序，直接以seq作为标识
     bot_uuid: str = None  # 机器人UUID
     app_ticket: str = None  # 商店应用用到
@@ -659,8 +812,71 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         def sync_on_message(event: lark_oapi.im.v1.P2ImMessageReceiveV1):
             asyncio.create_task(on_message(event))
 
+        def sync_on_card_action(event):
+            try:
+                action_value_obj = getattr(getattr(event.event, 'action', None), 'value', {})
+                action_value = action_value_obj.get('feedback', '') if isinstance(action_value_obj, dict) else ''
+
+                if action_value == '有帮助':
+                    feedback_type = 1
+                elif action_value == '无帮助':
+                    feedback_type = 2
+                else:
+                    from lark_oapi.event.callback.model.p2_card_action_trigger import P2CardActionTriggerResponse
+
+                    return P2CardActionTriggerResponse({'toast': {'type': 'success', 'content': '操作成功'}})
+
+                operator = getattr(event.event, 'operator', None)
+                context = getattr(event.event, 'context', None)
+
+                user_id = getattr(operator, 'open_id', None) or getattr(operator, 'user_id', None)
+                open_chat_id = getattr(context, 'open_chat_id', None)
+                open_message_id = getattr(context, 'open_message_id', None)
+
+                if open_chat_id:
+                    session_id = f'group_{open_chat_id}'
+                elif user_id:
+                    session_id = f'person_{user_id}'
+                else:
+                    session_id = None
+
+                # Resolve monitoring message ID from reply message mapping
+                monitoring_msg_id = None
+                if open_message_id and open_message_id in self.reply_to_monitoring_msg:
+                    monitoring_msg_id = self.reply_to_monitoring_msg[open_message_id][0]
+
+                feedback_event = platform_events.FeedbackEvent(
+                    feedback_id=getattr(event.header, 'event_id', str(uuid.uuid4())),
+                    feedback_type=feedback_type,
+                    feedback_content=action_value,
+                    user_id=user_id,
+                    session_id=session_id,
+                    message_id=open_message_id,
+                    stream_id=monitoring_msg_id,
+                    source_platform_object=event,
+                )
+
+                if platform_events.FeedbackEvent in self.listeners:
+                    loop = asyncio.get_event_loop()
+                    if loop.is_running():
+                        asyncio.create_task(self.listeners[platform_events.FeedbackEvent](feedback_event, self))
+                    else:
+                        loop.run_until_complete(self.listeners[platform_events.FeedbackEvent](feedback_event, self))
+
+                from lark_oapi.event.callback.model.p2_card_action_trigger import P2CardActionTriggerResponse
+
+                return P2CardActionTriggerResponse({'toast': {'type': 'success', 'content': '感谢您的反馈'}})
+            except Exception:
+                asyncio.create_task(self.logger.error(f'Error in lark card action callback: {traceback.format_exc()}'))
+                from lark_oapi.event.callback.model.p2_card_action_trigger import P2CardActionTriggerResponse
+
+                return P2CardActionTriggerResponse({'toast': {'type': 'error', 'content': '反馈处理失败'}})
+
         event_handler = (
-            lark_oapi.EventDispatcherHandler.builder('', '').register_p2_im_message_receive_v1(sync_on_message).build()
+            lark_oapi.EventDispatcherHandler.builder('', '')
+            .register_p2_im_message_receive_v1(sync_on_message)
+            .register_p2_card_action_trigger(sync_on_card_action)
+            .build()
         )
 
         bot_account_id = config['bot_name']
@@ -675,6 +891,8 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             logger=logger,
             lark_tenant_key=config.get('lark_tenant_key', ''),
             card_id_dict={},
+            pending_monitoring_msg={},
+            reply_to_monitoring_msg={},
             seq=1,
             listeners={},
             quart_app=quart_app,
@@ -770,6 +988,32 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             self.request_tenant_access_token(tenant_key)
         return self.tenant_access_tokens.get(tenant_key)['token'] if self.tenant_access_tokens.get(tenant_key) else None
 
+    def get_launcher_id(self, event: platform_events.MessageEvent) -> str | None:
+        """
+        Get topic-scoped launcher_id for thread-aware session isolation.
+
+        For group thread messages, returns "{group_id}_{thread_id}"
+        to ensure conversation context stays stable per topic.
+
+        Returns None for non-thread messages or P2P messages.
+        """
+        source_event = getattr(event.source_platform_object, 'event', None)
+        if not source_event:
+            return None
+
+        message = getattr(source_event, 'message', None)
+        if not message:
+            return None
+
+        thread_id = getattr(message, 'thread_id', None)
+        if not thread_id:
+            return None
+
+        if isinstance(event, platform_events.GroupMessage):
+            return f'{event.group.id}_{thread_id}'
+
+        return None
+
     def build_api_client(self, config):
         app_id = config['app_id']
         app_secret = config['app_secret']
@@ -789,6 +1033,22 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             is_stream = True
         return is_stream
 
+    async def on_monitoring_message_created(self, query, monitoring_message_id: str):
+        """Called by pipeline after monitoring message is created, to map user message ID to monitoring message ID."""
+        try:
+            user_msg_id = query.message_event.message_chain.message_id
+            if user_msg_id:
+                self.pending_monitoring_msg[user_msg_id] = monitoring_message_id
+        except Exception as e:
+            await self.logger.debug(f'Failed to map message to monitoring message: {e}')
+
+    def _cleanup_monitoring_mapping(self):
+        """Remove entries older than TTL from the reply-to-monitoring mapping."""
+        now = time.time()
+        expired = [k for k, (_, ts) in self.reply_to_monitoring_msg.items() if now - ts > self._MONITORING_MAPPING_TTL]
+        for k in expired:
+            del self.reply_to_monitoring_msg[k]
+
     async def create_card_id(self, message_id):
         try:
             # self.logger.debug('飞书支持stream输出,创建卡片......')
@@ -924,6 +1184,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                                             'size': 'medium',
                                             'icon': {'tag': 'standard_icon', 'token': 'thumbsup_outlined'},
                                             'hover_tips': {'tag': 'plain_text', 'content': '有帮助'},
+                                            'behaviors': [{'type': 'callback', 'value': {'feedback': '有帮助'}}],
                                             'margin': '0px 0px 0px 0px',
                                         }
                                     ],
@@ -947,6 +1208,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                                             'size': 'medium',
                                             'icon': {'tag': 'standard_icon', 'token': 'thumbdown_outlined'},
                                             'hover_tips': {'tag': 'plain_text', 'content': '无帮助'},
+                                            'behaviors': [{'type': 'callback', 'value': {'feedback': '无帮助'}}],
                                             'margin': '0px 0px 0px 0px',
                                         }
                                     ],
@@ -1026,6 +1288,18 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             raise Exception(
                 f'client.im.v1.message.reply failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
             )
+
+        # Transfer monitoring message mapping: user msg ID → reply msg ID
+        try:
+            user_msg_id = event.message_chain.message_id
+            reply_msg_id = getattr(response.data, 'message_id', None)
+            monitoring_msg_id = self.pending_monitoring_msg.pop(user_msg_id, None)
+            if reply_msg_id and monitoring_msg_id:
+                self.reply_to_monitoring_msg[reply_msg_id] = (monitoring_msg_id, time.time())
+                self._cleanup_monitoring_mapping()
+        except Exception as e:
+            asyncio.create_task(self.logger.debug(f'Failed to transfer monitoring mapping in create_message_card: {e}'))
+
         return True
 
     async def reply_message(
@@ -1308,6 +1582,58 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
                 if event.__class__ in self.listeners:
                     await self.listeners[event.__class__](event, self)
+            elif 'card.action.trigger' == type:
+                try:
+                    event_data = data.get('event', {})
+                    operator = event_data.get('operator', {})
+                    action = event_data.get('action', {})
+                    context_data = event_data.get('context', {})
+
+                    action_value_obj = action.get('value', {})
+                    action_value = action_value_obj.get('feedback', '') if isinstance(action_value_obj, dict) else ''
+
+                    if action_value == '有帮助':
+                        feedback_type = 1
+                    elif action_value == '无帮助':
+                        feedback_type = 2
+                    else:
+                        return {'toast': {'type': 'success', 'content': '操作成功'}}
+
+                    user_id = operator.get('open_id') or operator.get('user_id')
+                    open_chat_id = context_data.get('open_chat_id')
+                    open_message_id = context_data.get('open_message_id')
+
+                    if open_chat_id:
+                        session_id = f'group_{open_chat_id}'
+                    elif user_id:
+                        session_id = f'person_{user_id}'
+                    else:
+                        session_id = None
+
+                    # Resolve monitoring message ID from reply message mapping
+                    monitoring_msg_id = None
+                    if open_message_id and open_message_id in self.reply_to_monitoring_msg:
+                        monitoring_msg_id = self.reply_to_monitoring_msg[open_message_id][0]
+
+                    feedback_event = platform_events.FeedbackEvent(
+                        feedback_id=data.get('header', {}).get('event_id', str(uuid.uuid4())),
+                        feedback_type=feedback_type,
+                        feedback_content=action_value,
+                        user_id=user_id,
+                        session_id=session_id,
+                        message_id=open_message_id,
+                        stream_id=monitoring_msg_id,
+                        source_platform_object=data,
+                    )
+
+                    if platform_events.FeedbackEvent in self.listeners:
+                        await self.listeners[platform_events.FeedbackEvent](feedback_event, self)
+
+                    return {'toast': {'type': 'success', 'content': '感谢您的反馈'}}
+                except Exception:
+                    await self.logger.error(f'Error in lark card action callback: {traceback.format_exc()}')
+                    return {'toast': {'type': 'error', 'content': '反馈处理失败'}}
+
             elif 'im.chat.member.bot.added_v1' == type:
                 try:
                     bot_added_welcome_msg = self.config.get('bot_added_welcome', '')