chore: update project version to 4.7.1

- Add Milvus db_name configuration and client parameter support.
- change kb_data uuid for Milvus. 3. add MAX_BATCH_SIZE for openai.
- support more vector_size.

.dockerignore

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

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

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

.github/workflows/run-tests.yml

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

AGENTS.md

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

Dockerfile

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

README.md

@@ -13,16 +13,18 @@
 [English](README_EN.md) / 简体中文 / [繁體中文](README_TW.md) / [日本語](README_JP.md) / [Español](README_ES.md) / [Français](README_FR.md) / [한국어](README_KO.md) / [Русский](README_RU.md) / [Tiếng Việt](README_VI.md)
 
 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
-[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-1030838208-blue)](https://qm.qq.com/q/DxZZcNxM1W)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
 
 <a href="https://langbot.app">项目主页</a> ｜
+<a href="https://docs.langbot.app/zh/insight/features.html">规格特性</a> ｜
 <a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a> ｜
-<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">插件介绍</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交插件</a>
+<a href="https://docs.langbot.app/zh/tags/readme.html">API 集成</a> ｜
+<a href="https://space.langbot.app">插件市场</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">路线图</a>
 
 </div>
 

README_EN.md

@@ -17,9 +17,11 @@ English / [简体中文](README.md) / [繁體中文](README_TW.md) / [日本語]
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">Home</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Features</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Deployment</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Submit Plugin</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">API Integration</a> ｜
+<a href="https://space.langbot.app">Plugin Market</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Roadmap</a>
 
 </div>
 

README_ES.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">Inicio</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Características</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Despliegue</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Enviar Plugin</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">Integración API</a> ｜
+<a href="https://space.langbot.app">Mercado de Plugins</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Hoja de Ruta</a>
 
 </div>
 

README_FR.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">Accueil</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Fonctionnalités</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Déploiement</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Soumettre un Plugin</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">Intégration API</a> ｜
+<a href="https://space.langbot.app">Marché des Plugins</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Feuille de Route</a>
 
 </div>
 

README_JP.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">ホーム</a> ｜
-<a href="https://docs.langbot.app/en/insight/guide.html">デプロイ</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">プラグイン</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">プラグインの提出</a>
+<a href="https://docs.langbot.app/ja/insight/features.html">機能仕様</a> ｜
+<a href="https://docs.langbot.app/ja/insight/guide.html">デプロイ</a> ｜
+<a href="https://docs.langbot.app/ja/tags/readme.html">API統合</a> ｜
+<a href="https://space.langbot.app">プラグインマーケット</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">ロードマップ</a>
 
 </div>
 

README_KO.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">홈</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">기능 사양</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">배포</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">플러그인</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">플러그인 제출</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">API 통합</a> ｜
+<a href="https://space.langbot.app">플러그인 마켓</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">로드맵</a>
 
 </div>
 

README_RU.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">Главная</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Характеристики</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Развертывание</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Плагин</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Отправить плагин</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">Интеграция API</a> ｜
+<a href="https://space.langbot.app">Магазин плагинов</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Дорожная карта</a>
 
 </div>
 

README_TW.md

@@ -17,9 +17,11 @@
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
 
 <a href="https://langbot.app">主頁</a> ｜
+<a href="https://docs.langbot.app/zh/insight/features.html">規格特性</a> ｜
 <a href="https://docs.langbot.app/zh/insight/guide.html">部署文件</a> ｜
-<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">外掛介紹</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交外掛</a>
+<a href="https://docs.langbot.app/zh/tags/readme.html">API 整合</a> ｜
+<a href="https://space.langbot.app">外掛市場</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">路線圖</a>
 
 </div>
 

README_VI.md

@@ -17,9 +17,11 @@
 <img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
 
 <a href="https://langbot.app">Trang chủ</a> ｜
+<a href="https://docs.langbot.app/en/insight/features.html">Tính năng</a> ｜
 <a href="https://docs.langbot.app/en/insight/guide.html">Triển khai</a> ｜
-<a href="https://docs.langbot.app/en/plugin/plugin-intro.html">Plugin</a> ｜
-<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">Gửi Plugin</a>
+<a href="https://docs.langbot.app/en/tags/readme.html">Tích hợp API</a> ｜
+<a href="https://space.langbot.app">Chợ Plugin</a> ｜
+<a href="https://langbot.featurebase.app/roadmap">Lộ trình</a>
 
 </div>
 

docker/docker-compose.yaml

@@ -7,7 +7,6 @@ services:
   langbot_plugin_runtime:
     image: rockchin/langbot:latest
     container_name: langbot_plugin_runtime
-    platform: linux/amd64 # For Apple Silicon compatibility
     volumes:
       - ./data/plugins:/app/data/plugins
     ports:
@@ -15,14 +14,13 @@ services:
     restart: on-failure
     environment:
       - TZ=Asia/Shanghai
-    command: ["uv", "run", "-m", "langbot_plugin.cli.__init__", "rt"]
+    command: ["uv", "run", "--no-sync", "-m", "langbot_plugin.cli.__init__", "rt"]
     networks:
       - langbot_network
 
   langbot:
     image: rockchin/langbot:latest
     container_name: langbot
-    platform: linux/amd64 # For Apple Silicon compatibility
     volumes:
       - ./data:/app/data
     restart: on-failure

docs/SEEKDB_INTEGRATION.md

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

pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "langbot"
-version = "4.6.4"
-description = "Easy-to-use global IM bot platform designed for LLM era"
+version = "4.7.1"
+description = "Production-grade platform for building IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
-requires-python = ">=3.10.1,<4.0"
+requires-python = ">=3.11,<4.0"
 dependencies = [
     "aiocqhttp>=1.4.4",
     "aiofiles>=24.1.0",
@@ -63,7 +63,8 @@ dependencies = [
     "langchain-text-splitters>=0.0.1",
     "chromadb>=0.4.24",
     "qdrant-client (>=1.15.1,<2.0.0)",
-    "langbot-plugin==0.2.3",
+    "pyseekdb>=0.1.0",
+    "langbot-plugin==0.2.4",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "tboxsdk>=0.0.10",

src/langbot/__init__.py

@@ -1,3 +1,3 @@
-"""LangBot - Easy-to-use global IM bot platform designed for LLM era"""
+"""LangBot - Production-grade platform for building IM bots"""
 
-__version__ = '4.6.4'
+__version__ = '4.7.1'

src/langbot/libs/dingtalk_api/api.py

@@ -1,8 +1,11 @@
+import asyncio
 import base64
 import json
 import time
+import urllib.parse
 from typing import Callable
 import dingtalk_stream  # type: ignore
+import websockets
 from .EchoHandler import EchoTextHandler
 from .dingtalkevent import DingTalkEvent
 import httpx
@@ -36,6 +39,7 @@ class DingTalkClient:
         self.access_token_expiry_time = ''
         self.markdown_card = markdown_card
         self.logger = logger
+        self._stopped = False  # Flag to control the event loop
 
     async def get_access_token(self):
         url = 'https://api.dingtalk.com/v1.0/oauth2/accessToken'
@@ -170,6 +174,9 @@ class DingTalkClient:
         """
         处理消息事件。
         """
+        # Skip message handling if stopped
+        if self._stopped:
+            return
         msg_type = event.conversation
         if msg_type in self._message_handlers:
             for handler in self._message_handlers[msg_type]:
@@ -378,4 +385,70 @@ class DingTalkClient:
 
     async def start(self):
         """启动 WebSocket 连接，监听消息"""
-        await self.client.start()
+        self._stopped = False
+        self.client.pre_start()
+
+        while not self._stopped:
+            try:
+                connection = self.client.open_connection()
+
+                if not connection:
+                    if self.logger:
+                        await self.logger.error('DingTalk: open connection failed')
+                    await asyncio.sleep(10)
+                    continue
+
+                uri = '%s?ticket=%s' % (connection['endpoint'], urllib.parse.quote_plus(connection['ticket']))
+                async with websockets.connect(uri) as websocket:
+                    self.client.websocket = websocket
+                    keepalive_task = asyncio.create_task(self._keepalive(websocket))
+                    try:
+                        async for raw_message in websocket:
+                            if self._stopped:
+                                break
+                            json_message = json.loads(raw_message)
+                            asyncio.create_task(self.client.background_task(json_message))
+                    finally:
+                        keepalive_task.cancel()
+                        try:
+                            await keepalive_task
+                        except asyncio.CancelledError:
+                            pass
+            except asyncio.CancelledError:
+                # Properly exit when task is cancelled
+                break
+            except websockets.exceptions.ConnectionClosedError as e:
+                if self._stopped:
+                    break
+                if self.logger:
+                    await self.logger.error(f'DingTalk: connection closed, reconnecting... error={e}')
+                await asyncio.sleep(5)
+                continue
+            except Exception as e:
+                if self._stopped:
+                    break
+                if self.logger:
+                    await self.logger.error(f'DingTalk: unknown exception, reconnecting... error={e}')
+                await asyncio.sleep(3)
+                continue
+
+    async def _keepalive(self, ws, ping_interval=60):
+        """Keep WebSocket connection alive"""
+        while not self._stopped:
+            await asyncio.sleep(ping_interval)
+            try:
+                await ws.ping()
+            except websockets.exceptions.ConnectionClosed:
+                break
+
+    async def stop(self):
+        """停止 WebSocket 连接"""
+        self._stopped = True
+        # Close WebSocket connection if exists
+        if self.client.websocket:
+            try:
+                await self.client.websocket.close()
+            except Exception:
+                pass
+        # Clear message handlers to prevent stale callbacks
+        self._message_handlers = {'example': []}

src/langbot/libs/official_account_api/api.py

@@ -23,12 +23,21 @@ xml_template = """
 
 
 class OAClient:
-    def __init__(self, token: str, EncodingAESKey: str, AppID: str, Appsecret: str, logger: None, unified_mode: bool = False):
+    def __init__(
+        self,
+        token: str,
+        EncodingAESKey: str,
+        AppID: str,
+        Appsecret: str,
+        logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://api.weixin.qq.com',
+    ):
         self.token = token
         self.aes = EncodingAESKey
         self.appid = AppID
         self.appsecret = Appsecret
-        self.base_url = 'https://api.weixin.qq.com'
+        self.base_url = api_base_url
         self.access_token = ''
         self.unified_mode = unified_mode
         self.app = Quart(__name__)
@@ -208,12 +217,13 @@ class OAClientForLongerResponse:
         LoadingMessage: str,
         logger: None,
         unified_mode: bool = False,
+        api_base_url: str = 'https://api.weixin.qq.com',
     ):
         self.token = token
         self.aes = EncodingAESKey
         self.appid = AppID
         self.appsecret = Appsecret
-        self.base_url = 'https://api.weixin.qq.com'
+        self.base_url = api_base_url
         self.access_token = ''
         self.unified_mode = unified_mode
         self.app = Quart(__name__)

src/langbot/libs/wecom_api/api.py

@@ -22,13 +22,14 @@ class WecomClient:
         contacts_secret: str,
         logger: None,
         unified_mode: bool = False,
+        api_base_url: str = 'https://qyapi.weixin.qq.com/cgi-bin',
     ):
         self.corpid = corpid
         self.secret = secret
         self.access_token_for_contacts = ''
         self.token = token
         self.aes = EncodingAESKey
-        self.base_url = 'https://qyapi.weixin.qq.com/cgi-bin'
+        self.base_url = api_base_url
         self.access_token = ''
         self.secret_for_contacts = contacts_secret
         self.logger = logger
@@ -56,7 +57,7 @@ class WecomClient:
         return bool(self.access_token_for_contacts and self.access_token_for_contacts.strip())
 
     async def get_access_token(self, secret):
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid={self.corpid}&corpsecret={secret}'
+        url = f'{self.base_url}/gettoken?corpid={self.corpid}&corpsecret={secret}'
         async with httpx.AsyncClient() as client:
             response = await client.get(url)
             data = response.json()
@@ -196,7 +197,7 @@ class WecomClient:
             self.access_token = await self.get_access_token(self.secret)
 
         url = self.base_url + '/message/send?access_token=' + self.access_token
-        async with httpx.AsyncClient() as client:
+        async with httpx.AsyncClient(timeout=None) as client:
             params = {
                 'touser': user_id,
                 'msgtype': 'text',

src/langbot/libs/wecom_customer_service_api/api.py

@@ -13,13 +13,22 @@ import aiofiles
 
 
 class WecomCSClient:
-    def __init__(self, corpid: str, secret: str, token: str, EncodingAESKey: str, logger: None, unified_mode: bool = False):
+    def __init__(
+        self,
+        corpid: str,
+        secret: str,
+        token: str,
+        EncodingAESKey: str,
+        logger: None,
+        unified_mode: bool = False,
+        api_base_url: str = 'https://qyapi.weixin.qq.com/cgi-bin',
+    ):
         self.corpid = corpid
         self.secret = secret
         self.access_token_for_contacts = ''
         self.token = token
         self.aes = EncodingAESKey
-        self.base_url = 'https://qyapi.weixin.qq.com/cgi-bin'
+        self.base_url = api_base_url
         self.access_token = ''
         self.logger = logger
         self.unified_mode = unified_mode
@@ -66,7 +75,7 @@ class WecomCSClient:
         return bool(self.access_token_for_contacts and self.access_token_for_contacts.strip())
 
     async def get_access_token(self, secret):
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid={self.corpid}&corpsecret={secret}'
+        url = f'{self.base_url}/gettoken?corpid={self.corpid}&corpsecret={secret}'
         async with httpx.AsyncClient() as client:
             response = await client.get(url)
             data = response.json()
@@ -172,7 +181,7 @@ class WecomCSClient:
         if not await self.check_access_token():
             self.access_token = await self.get_access_token(self.secret)
 
-        url = f'https://qyapi.weixin.qq.com/cgi-bin/kf/send_msg?access_token={self.access_token}'
+        url = f'{self.base_url}/kf/send_msg?access_token={self.access_token}'
 
         payload = {
             'touser': external_userid,

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

@@ -49,6 +49,14 @@ class PipelinesRouterGroup(group.RouterGroup):
 
                 return self.success()
 
+        @self.route('/<pipeline_uuid>/copy', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _(pipeline_uuid: str) -> str:
+            try:
+                new_uuid = await self.ap.pipeline_service.copy_pipeline(pipeline_uuid)
+                return self.success(data={'uuid': new_uuid})
+            except ValueError as e:
+                return self.http_status(404, -1, str(e))
+
         @self.route(
             '/<pipeline_uuid>/extensions', methods=['GET', 'PUT'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
         )

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

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

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

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

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

@@ -17,11 +17,13 @@ class SystemRouterGroup(group.RouterGroup):
                         'enable_marketplace', True
                     ),
                     'cloud_service_url': (
-                        self.ap.instance_config.data.get('plugin', {}).get(
-                            'cloud_service_url', 'https://space.langbot.app'
-                        )
-                        if 'cloud_service_url' in self.ap.instance_config.data.get('plugin', {})
-                        else 'https://space.langbot.app'
+                        self.ap.instance_config.data.get('space', {}).get('url', 'https://space.langbot.app')
+                    ),
+                    'allow_modify_login_info': self.ap.instance_config.data.get('system', {}).get(
+                        'allow_modify_login_info', True
+                    ),
+                    'disable_models_service': self.ap.instance_config.data.get('space', {}).get(
+                        'disable_models_service', False
                     ),
                 }
             )

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

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

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

@@ -11,6 +11,18 @@ from ....entity.persistence import pipeline as persistence_pipeline
 from ....provider.modelmgr import requester as model_requester
 
 
+def _parse_provider_api_keys(provider_dict: dict) -> dict:
+    """Parse api_keys if it's a JSON string"""
+    if isinstance(provider_dict.get('api_keys'), str):
+        import json
+
+        try:
+            provider_dict['api_keys'] = json.loads(provider_dict['api_keys'])
+        except Exception:
+            provider_dict['api_keys'] = []
+    return provider_dict
+
+
 class LLMModelsService:
     ap: app.Application
 
@@ -18,29 +30,72 @@ class LLMModelsService:
         self.ap = ap
 
     async def get_llm_models(self, include_secret: bool = True) -> list[dict]:
+        """Get all LLM models with provider info"""
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
-
         models = result.all()
 
-        masked_columns = []
-        if not include_secret:
-            masked_columns = ['api_keys']
+        # Get all providers for lookup
+        providers_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider)
+        )
+        providers = {p.uuid: p for p in providers_result.all()}
 
-        return [
-            self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model, masked_columns)
-            for model in models
-        ]
+        models_list = []
+        for model in models:
+            model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+            provider = providers.get(model.provider_uuid)
+            if provider:
+                provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+                provider_dict = _parse_provider_api_keys(provider_dict)
+                if not include_secret:
+                    provider_dict['api_keys'] = ['***'] * len(provider_dict.get('api_keys', []))
+                model_dict['provider'] = provider_dict
+            models_list.append(model_dict)
 
-    async def create_llm_model(self, model_data: dict) -> str:
-        model_data['uuid'] = str(uuid.uuid4())
+        return models_list
+
+    async def get_llm_models_by_provider(self, provider_uuid: str) -> list[dict]:
+        """Get LLM models by provider UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.LLMModel).where(
+                persistence_model.LLMModel.provider_uuid == provider_uuid
+            )
+        )
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, m) for m in models]
+
+    async def create_llm_model(self, model_data: dict, preserve_uuid: bool = False) -> str:
+        """Create a new LLM model"""
+        if not preserve_uuid:
+            model_data['uuid'] = str(uuid.uuid4())
+
+        # Handle provider creation if needed
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                # Create new provider
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
 
         await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_model.LLMModel).values(**model_data))
 
-        llm_model = await self.get_llm_model(model_data['uuid'])
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_llm_model(llm_model)
+        runtime_llm_model = await self.ap.model_mgr.load_llm_model_with_provider(
+            persistence_model.LLMModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.llm_models.append(runtime_llm_model)
 
-        # check if default pipeline has no model bound
+        # set the default pipeline model to this model
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
                 persistence_pipeline.LegacyPipeline.is_default == True
@@ -56,21 +111,47 @@ class LLMModelsService:
         return model_data['uuid']
 
     async def get_llm_model(self, model_uuid: str) -> dict | None:
+        """Get a single LLM model with provider info"""
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_model.LLMModel).where(persistence_model.LLMModel.uuid == model_uuid)
         )
-
         model = result.first()
-
         if model is None:
             return None
 
-        return self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+        model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model)
+
+        # Get provider
+        provider_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == model.provider_uuid
+            )
+        )
+        provider = provider_result.first()
+        if provider:
+            provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+            model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+
+        return model_dict
 
     async def update_llm_model(self, model_uuid: str, model_data: dict) -> None:
+        """Update an existing LLM model"""
         if 'uuid' in model_data:
             del model_data['uuid']
 
+        # Handle provider update if needed
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_model.LLMModel)
             .where(persistence_model.LLMModel.uuid == model_uuid)
@@ -79,18 +160,25 @@ class LLMModelsService:
 
         await self.ap.model_mgr.remove_llm_model(model_uuid)
 
-        llm_model = await self.get_llm_model(model_uuid)
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_llm_model(llm_model)
+        runtime_llm_model = await self.ap.model_mgr.load_llm_model_with_provider(
+            persistence_model.LLMModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.llm_models.append(runtime_llm_model)
 
     async def delete_llm_model(self, model_uuid: str) -> None:
+        """Delete an LLM model"""
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.delete(persistence_model.LLMModel).where(persistence_model.LLMModel.uuid == model_uuid)
         )
-
         await self.ap.model_mgr.remove_llm_model(model_uuid)
 
     async def test_llm_model(self, model_uuid: str, model_data: dict) -> None:
+        """Test an LLM model"""
         runtime_llm_model: model_requester.RuntimeLLMModel | None = None
 
         if model_uuid != '_':
@@ -98,25 +186,18 @@ class LLMModelsService:
                 if model.model_entity.uuid == model_uuid:
                     runtime_llm_model = model
                     break
-
             if runtime_llm_model is None:
                 raise Exception('model not found')
-
         else:
-            runtime_llm_model = await self.ap.model_mgr.init_runtime_llm_model(model_data)
+            runtime_llm_model = await self.ap.model_mgr.init_temporary_runtime_llm_model(model_data)
 
-        # Mon Nov 10 2025: Commented for some providers may not support thinking parameter
-        # # 有些模型厂商默认开启了思考功能，测试容易延迟
-        # extra_args = model_data.get('extra_args', {})
-        # if not extra_args or 'thinking' not in extra_args:
-        #     extra_args['thinking'] = {'type': 'disabled'}
-
-        await runtime_llm_model.requester.invoke_llm(
+        extra_args = model_data.get('extra_args', {})
+        await runtime_llm_model.provider.requester.invoke_llm(
             query=None,
             model=runtime_llm_model,
             messages=[provider_message.Message(role='user', content='Hello, world! Please just reply a "Hello".')],
             funcs=[],
-            # extra_args=extra_args,
+            extra_args=extra_args,
         )
 
 
@@ -127,42 +208,111 @@ class EmbeddingModelsService:
         self.ap = ap
 
     async def get_embedding_models(self) -> list[dict]:
+        """Get all embedding models with provider info"""
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
-
         models = result.all()
-        return [self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model) for model in models]
 
-    async def create_embedding_model(self, model_data: dict) -> str:
-        model_data['uuid'] = str(uuid.uuid4())
+        providers_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider)
+        )
+        providers = {p.uuid: p for p in providers_result.all()}
+
+        models_list = []
+        for model in models:
+            model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+            provider = providers.get(model.provider_uuid)
+            if provider:
+                provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+                model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+            models_list.append(model_dict)
+
+        return models_list
+
+    async def get_embedding_models_by_provider(self, provider_uuid: str) -> list[dict]:
+        """Get embedding models by provider UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.EmbeddingModel).where(
+                persistence_model.EmbeddingModel.provider_uuid == provider_uuid
+            )
+        )
+        models = result.all()
+        return [self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, m) for m in models]
+
+    async def create_embedding_model(self, model_data: dict, preserve_uuid: bool = False) -> str:
+        """Create a new embedding model"""
+        if not preserve_uuid:
+            model_data['uuid'] = str(uuid.uuid4())
+
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
 
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.insert(persistence_model.EmbeddingModel).values(**model_data)
         )
 
-        embedding_model = await self.get_embedding_model(model_data['uuid'])
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_embedding_model(embedding_model)
+        runtime_embedding_model = await self.ap.model_mgr.load_embedding_model_with_provider(
+            persistence_model.EmbeddingModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.embedding_models.append(runtime_embedding_model)
 
         return model_data['uuid']
 
     async def get_embedding_model(self, model_uuid: str) -> dict | None:
+        """Get a single embedding model with provider info"""
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_model.EmbeddingModel).where(
                 persistence_model.EmbeddingModel.uuid == model_uuid
             )
         )
-
         model = result.first()
-
         if model is None:
             return None
 
-        return self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+        model_dict = self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
+
+        provider_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == model.provider_uuid
+            )
+        )
+        provider = provider_result.first()
+        if provider:
+            provider_dict = self.ap.persistence_mgr.serialize_model(persistence_model.ModelProvider, provider)
+            model_dict['provider'] = _parse_provider_api_keys(provider_dict)
+
+        return model_dict
 
     async def update_embedding_model(self, model_uuid: str, model_data: dict) -> None:
+        """Update an existing embedding model"""
         if 'uuid' in model_data:
             del model_data['uuid']
 
+        if 'provider' in model_data:
+            provider_data = model_data.pop('provider')
+            if provider_data.get('uuid'):
+                model_data['provider_uuid'] = provider_data['uuid']
+            else:
+                provider_uuid = await self.ap.provider_service.find_or_create_provider(
+                    requester=provider_data.get('requester', ''),
+                    base_url=provider_data.get('base_url', ''),
+                    api_keys=provider_data.get('api_keys', []),
+                )
+                model_data['provider_uuid'] = provider_uuid
+
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_model.EmbeddingModel)
             .where(persistence_model.EmbeddingModel.uuid == model_uuid)
@@ -171,20 +321,27 @@ class EmbeddingModelsService:
 
         await self.ap.model_mgr.remove_embedding_model(model_uuid)
 
-        embedding_model = await self.get_embedding_model(model_uuid)
+        runtime_provider = self.ap.model_mgr.provider_dict.get(model_data['provider_uuid'])
+        if runtime_provider is None:
+            raise Exception('provider not found')
 
-        await self.ap.model_mgr.load_embedding_model(embedding_model)
+        runtime_embedding_model = await self.ap.model_mgr.load_embedding_model_with_provider(
+            persistence_model.EmbeddingModel(**model_data),
+            runtime_provider,
+        )
+        self.ap.model_mgr.embedding_models.append(runtime_embedding_model)
 
     async def delete_embedding_model(self, model_uuid: str) -> None:
+        """Delete an embedding model"""
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.delete(persistence_model.EmbeddingModel).where(
                 persistence_model.EmbeddingModel.uuid == model_uuid
             )
         )
-
         await self.ap.model_mgr.remove_embedding_model(model_uuid)
 
     async def test_embedding_model(self, model_uuid: str, model_data: dict) -> None:
+        """Test an embedding model"""
         runtime_embedding_model: model_requester.RuntimeEmbeddingModel | None = None
 
         if model_uuid != '_':
@@ -192,14 +349,12 @@ class EmbeddingModelsService:
                 if model.model_entity.uuid == model_uuid:
                     runtime_embedding_model = model
                     break
-
             if runtime_embedding_model is None:
                 raise Exception('model not found')
-
         else:
-            runtime_embedding_model = await self.ap.model_mgr.init_runtime_embedding_model(model_data)
+            runtime_embedding_model = await self.ap.model_mgr.init_temporary_runtime_embedding_model(model_data)
 
-        await runtime_embedding_model.requester.invoke_embedding(
+        await runtime_embedding_model.provider.requester.invoke_embedding(
             model=runtime_embedding_model,
             input_text=['Hello, world!'],
             extra_args={},

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

@@ -151,6 +151,52 @@ class PipelineService:
         )
         await self.ap.pipeline_mgr.remove_pipeline(pipeline_uuid)
 
+    async def copy_pipeline(self, pipeline_uuid: str) -> str:
+        """Copy a pipeline with all its configurations"""
+        # Get the original pipeline
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
+                persistence_pipeline.LegacyPipeline.uuid == pipeline_uuid
+            )
+        )
+
+        original_pipeline = result.first()
+        if original_pipeline is None:
+            raise ValueError(f'Pipeline {pipeline_uuid} not found')
+
+        # Create new pipeline data
+        new_uuid = str(uuid.uuid4())
+        new_pipeline_data = {
+            'uuid': new_uuid,
+            'name': f'{original_pipeline.name} (Copy)',
+            'description': original_pipeline.description,
+            'for_version': self.ap.ver_mgr.get_current_version(),
+            'stages': original_pipeline.stages.copy() if original_pipeline.stages else default_stage_order.copy(),
+            'config': original_pipeline.config.copy() if original_pipeline.config else {},
+            'is_default': False,
+            'extensions_preferences': (
+                original_pipeline.extensions_preferences.copy()
+                if original_pipeline.extensions_preferences
+                else {
+                    'enable_all_plugins': True,
+                    'enable_all_mcp_servers': True,
+                    'plugins': [],
+                    'mcp_servers': [],
+                }
+            ),
+        }
+
+        # Insert the new pipeline
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_pipeline.LegacyPipeline).values(**new_pipeline_data)
+        )
+
+        # Load the new pipeline
+        pipeline = await self.get_pipeline(new_uuid)
+        await self.ap.pipeline_mgr.load_pipeline(pipeline)
+
+        return new_uuid
+
     async def update_pipeline_extensions(
         self,
         pipeline_uuid: str,

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

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

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

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

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

@@ -4,17 +4,22 @@ import sqlalchemy
 import argon2
 import jwt
 import datetime
+import typing
+import asyncio
 
 from ....core import app
 from ....entity.persistence import user
 from ....utils import constants
+from ....entity.errors import account as account_errors
 
 
 class UserService:
     ap: app.Application
+    _create_user_lock: asyncio.Lock
 
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
+        self._create_user_lock = asyncio.Lock()
 
     async def is_initialized(self) -> bool:
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(user.User).limit(1))
@@ -28,7 +33,7 @@ class UserService:
         hashed_password = ph.hash(password)
 
         await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.insert(user.User).values(user=user_email, password=hashed_password)
+            sqlalchemy.insert(user.User).values(user=user_email, password=hashed_password, account_type='local')
         )
 
     async def get_user_by_email(self, user_email: str) -> user.User | None:
@@ -39,6 +44,15 @@ class UserService:
         result_list = result.all()
         return result_list[0] if result_list is not None and len(result_list) > 0 else None
 
+    async def get_user_by_space_account_uuid(self, space_account_uuid: str) -> user.User | None:
+        """Get user by Space account UUID"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(user.User).where(user.User.space_account_uuid == space_account_uuid)
+        )
+
+        result_list = result.all()
+        return result_list[0] if result_list is not None and len(result_list) > 0 else None
+
     async def authenticate(self, user_email: str, password: str) -> str | None:
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(user.User).where(user.User.user == user_email)
@@ -51,6 +65,10 @@ class UserService:
 
         user_obj = result_list[0]
 
+        # Check if this is a Space account
+        if user_obj.account_type == 'space':
+            raise ValueError('请使用 Space 账户登录')
+
         ph = argon2.PasswordHasher()
 
         ph.verify(user_obj.password, password)
@@ -90,6 +108,10 @@ class UserService:
         if user_obj is None:
             raise ValueError('User not found')
 
+        # Space accounts cannot change password locally
+        if user_obj.account_type == 'space':
+            raise ValueError('Space account cannot change password locally')
+
         ph.verify(user_obj.password, current_password)
 
         hashed_password = ph.hash(new_password)
@@ -97,3 +119,180 @@ class UserService:
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
         )
+
+    # Space user management
+
+    async def create_or_update_space_user(
+        self,
+        space_account_uuid: str,
+        email: str,
+        access_token: str,
+        refresh_token: str,
+        api_key: str,
+        expires_in: int = 0,
+    ) -> user.User:
+        """Create or update a Space user account (only if system not initialized or user exists)"""
+        expires_at = datetime.datetime.now() + datetime.timedelta(seconds=expires_in) if expires_in > 0 else None
+
+        async with self._create_user_lock:
+            # Check if user with this Space UUID already exists
+            existing_user = await self.get_user_by_space_account_uuid(space_account_uuid)
+
+            if existing_user:
+                # Update existing user's tokens
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.update(user.User)
+                    .where(user.User.space_account_uuid == space_account_uuid)
+                    .values(
+                        space_access_token=access_token,
+                        space_refresh_token=refresh_token,
+                        space_api_key=api_key,
+                        space_access_token_expires_at=expires_at,
+                    )
+                )
+                await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+                return await self.get_user_by_space_account_uuid(space_account_uuid)
+
+            # Check if user with same email exists
+            existing_email_user = await self.get_user_by_email(email)
+            if existing_email_user:
+                # Update existing user to link with Space account
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.update(user.User)
+                    .where(user.User.user == email)
+                    .values(
+                        account_type='space',
+                        space_account_uuid=space_account_uuid,
+                        space_access_token=access_token,
+                        space_refresh_token=refresh_token,
+                        space_api_key=api_key,
+                        space_access_token_expires_at=expires_at,
+                    )
+                )
+                await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+                return await self.get_user_by_email(email)
+
+            # Check if system is already initialized
+            is_initialized = await self.is_initialized()
+            if is_initialized:
+                raise account_errors.AccountEmailMismatchError()
+
+            # Create new Space user (first time initialization)
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.insert(user.User).values(
+                    user=email,
+                    password='',  # Space users don't have local password
+                    account_type='space',
+                    space_account_uuid=space_account_uuid,
+                    space_access_token=access_token,
+                    space_refresh_token=refresh_token,
+                    space_api_key=api_key,
+                    space_access_token_expires_at=expires_at,
+                )
+            )
+            await self.ap.provider_service.update_space_model_provider_api_keys(api_key)
+
+            return await self.get_user_by_space_account_uuid(space_account_uuid)
+
+    async def authenticate_space_user(
+        self, access_token: str, refresh_token: str, expires_in: int = 0
+    ) -> typing.Tuple[str, user.User]:
+        """Authenticate with Space and return JWT token"""
+        # Get user info from Space using raw API (token just obtained, no need to validate)
+        user_info = await self.ap.space_service.get_user_info_raw(access_token)
+
+        account = user_info.get('account', {})
+        api_key = user_info.get('api_key', '')
+
+        space_account_uuid = account.get('uuid')
+        email = account.get('email')
+
+        if not space_account_uuid or not email:
+            raise ValueError('Invalid Space user info')
+
+        # Create or update Space user in local database
+        user_obj = await self.create_or_update_space_user(
+            space_account_uuid=space_account_uuid,
+            email=email,
+            access_token=access_token,
+            refresh_token=refresh_token,
+            api_key=api_key,
+            expires_in=expires_in,
+        )
+
+        # Generate JWT token
+        jwt_token = await self.generate_jwt_token(email)
+
+        return jwt_token, user_obj
+
+    async def get_first_user(self) -> user.User | None:
+        """Get the first user (for single-user mode)"""
+        result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(user.User).limit(1))
+        result_list = result.all()
+        return result_list[0] if result_list else None
+
+    async def set_password(self, user_email: str, new_password: str, current_password: str | None = None) -> None:
+        """Set or change password for a user"""
+        ph = argon2.PasswordHasher()
+        user_obj = await self.get_user_by_email(user_email)
+
+        if user_obj is None:
+            raise ValueError('User not found')
+
+        # If user already has a password, verify current password
+        has_password = bool(user_obj.password and user_obj.password.strip())
+        if has_password:
+            if not current_password:
+                raise ValueError('Current password is required')
+            ph.verify(user_obj.password, current_password)
+
+        hashed_password = ph.hash(new_password)
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
+        )
+
+    async def bind_space_account(self, user_email: str, code: str) -> user.User:
+        """Bind Space account to existing local account"""
+        # Exchange code for tokens
+        token_data = await self.ap.space_service.exchange_oauth_code(code)
+        access_token = token_data.get('access_token')
+        refresh_token = token_data.get('refresh_token')
+        expires_in = token_data.get('expires_in', 0)
+
+        if not access_token:
+            raise ValueError('Failed to get access token from Space')
+
+        expires_at = datetime.datetime.now() + datetime.timedelta(seconds=expires_in) if expires_in > 0 else None
+
+        # Get Space user info (token just obtained, use raw API)
+        user_info = await self.ap.space_service.get_user_info_raw(access_token)
+        account = user_info.get('account', {})
+        api_key = user_info.get('api_key', '')
+
+        space_account_uuid = account.get('uuid')
+        space_email = account.get('email')
+
+        if not space_account_uuid or not space_email:
+            raise ValueError('Invalid Space user info')
+
+        # Check if this Space account is already bound to another user
+        existing_space_user = await self.get_user_by_space_account_uuid(space_account_uuid)
+        if existing_space_user and existing_space_user.user != user_email:
+            raise ValueError('This Space account is already bound to another user')
+
+        # Update local account to Space account
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User)
+            .where(user.User.user == user_email)
+            .values(
+                user=space_email,  # Update email to Space email
+                account_type='space',
+                space_account_uuid=space_account_uuid,
+                space_access_token=access_token,
+                space_refresh_token=refresh_token,
+                space_api_key=api_key,
+                space_access_token_expires_at=expires_at,
+            )
+        )
+
+        return await self.get_user_by_email(space_email)

src/langbot/pkg/core/app.py

@@ -19,7 +19,9 @@ from ..utils import version as version_mgr, proxy as proxy_mgr
 from ..persistence import mgr as persistencemgr
 from ..api.http.controller import main as http_controller
 from ..api.http.service import user as user_service
+from ..api.http.service import space as space_service
 from ..api.http.service import model as model_service
+from ..api.http.service import provider as provider_service
 from ..api.http.service import pipeline as pipeline_service
 from ..api.http.service import bot as bot_service
 from ..api.http.service import knowledge as knowledge_service
@@ -34,6 +36,7 @@ from . import taskmgr
 from . import entities as core_entities
 from ..rag.knowledge import kbmgr as rag_mgr
 from ..vector import mgr as vectordb_mgr
+from ..telemetry import telemetry as telemetry_module
 
 
 class Application:
@@ -75,6 +78,8 @@ class Application:
 
     instance_config: config_mgr.ConfigManager = None
 
+    instance_id: config_mgr.ConfigManager = None  # used to identify the instance
+
     # ======= Metadata config manager =======
 
     sensitive_meta: config_mgr.ConfigManager = None
@@ -114,10 +119,14 @@ class Application:
 
     user_service: user_service.UserService = None
 
+    space_service: space_service.SpaceService = None
+
     llm_model_service: model_service.LLMModelsService = None
 
     embedding_models_service: model_service.EmbeddingModelsService = None
 
+    provider_service: provider_service.ModelProviderService = None
+
     pipeline_service: pipeline_service.PipelineService = None
 
     bot_service: bot_service.BotService = None
@@ -132,6 +141,8 @@ class Application:
 
     webhook_service: webhook_service.WebhookService = None
 
+    telemetry: telemetry_module.TelemetryManager = None
+
     def __init__(self):
         pass
 

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

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

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

@@ -16,7 +16,9 @@ from ...platform.webhook_pusher import WebhookPusher
 from ...persistence import mgr as persistencemgr
 from ...api.http.controller import main as http_controller
 from ...api.http.service import user as user_service
+from ...api.http.service import space as space_service
 from ...api.http.service import model as model_service
+from ...api.http.service import provider as provider_service
 from ...api.http.service import pipeline as pipeline_service
 from ...api.http.service import bot as bot_service
 from ...api.http.service import knowledge as knowledge_service
@@ -29,6 +31,8 @@ from ...storage import mgr as storagemgr
 from ...utils import logcache
 from ...vector import mgr as vectordb_mgr
 from .. import taskmgr
+from ...telemetry import telemetry as telemetry_module
+
 
 
 @stage.stage_class('BuildAppStage')
@@ -43,6 +47,42 @@ class BuildAppStage(stage.BootingStage):
         discover.discover_blueprint('templates/components.yaml')
         ap.discover = discover
 
+        user_service_inst = user_service.UserService(ap)
+        ap.user_service = user_service_inst
+
+        space_service_inst = space_service.SpaceService(ap)
+        ap.space_service = space_service_inst
+
+        llm_model_service_inst = model_service.LLMModelsService(ap)
+        ap.llm_model_service = llm_model_service_inst
+
+        embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
+        ap.embedding_models_service = embedding_models_service_inst
+
+        provider_service_inst = provider_service.ModelProviderService(ap)
+        ap.provider_service = provider_service_inst
+
+        pipeline_service_inst = pipeline_service.PipelineService(ap)
+        ap.pipeline_service = pipeline_service_inst
+
+        bot_service_inst = bot_service.BotService(ap)
+        ap.bot_service = bot_service_inst
+
+        knowledge_service_inst = knowledge_service.KnowledgeService(ap)
+        ap.knowledge_service = knowledge_service_inst
+
+        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
+
+        apikey_service_inst = apikey_service.ApiKeyService(ap)
+        ap.apikey_service = apikey_service_inst
+
+        webhook_service_inst = webhook_service.WebhookService(ap)
+        ap.webhook_service = webhook_service_inst
+
         proxy_mgr = proxy.ProxyManager(ap)
         await proxy_mgr.initialize()
         ap.proxy_mgr = proxy_mgr
@@ -64,13 +104,18 @@ class BuildAppStage(stage.BootingStage):
         ap.persistence_mgr = persistence_mgr_inst
         await persistence_mgr_inst.initialize()
 
+        # Telemetry manager: attach to app so other components can call via self.ap.telemetry
+        telemetry_inst = telemetry_module.TelemetryManager(ap)
+        await telemetry_inst.initialize()
+        ap.telemetry = telemetry_inst
+
         cmd_mgr_inst = cmdmgr.CommandManager(ap)
         await cmd_mgr_inst.initialize()
         ap.cmd_mgr = cmd_mgr_inst
 
         llm_model_mgr_inst = llm_model_mgr.ModelManager(ap)
-        await llm_model_mgr_inst.initialize()
         ap.model_mgr = llm_model_mgr_inst
+        await llm_model_mgr_inst.initialize()
 
         llm_session_mgr_inst = llm_session_mgr.SessionManager(ap)
         await llm_session_mgr_inst.initialize()
@@ -105,36 +150,6 @@ class BuildAppStage(stage.BootingStage):
         await http_ctrl.initialize()
         ap.http_ctrl = http_ctrl
 
-        user_service_inst = user_service.UserService(ap)
-        ap.user_service = user_service_inst
-
-        llm_model_service_inst = model_service.LLMModelsService(ap)
-        ap.llm_model_service = llm_model_service_inst
-
-        embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
-        ap.embedding_models_service = embedding_models_service_inst
-
-        pipeline_service_inst = pipeline_service.PipelineService(ap)
-        ap.pipeline_service = pipeline_service_inst
-
-        bot_service_inst = bot_service.BotService(ap)
-        ap.bot_service = bot_service_inst
-
-        knowledge_service_inst = knowledge_service.KnowledgeService(ap)
-        ap.knowledge_service = knowledge_service_inst
-
-        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
-
-        apikey_service_inst = apikey_service.ApiKeyService(ap)
-        ap.apikey_service = apikey_service_inst
-
-        webhook_service_inst = webhook_service.WebhookService(ap)
-        ap.webhook_service = webhook_service_inst
-
         async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
             await asyncio.sleep(3)
             await plugin_connector_inst.initialize()

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

@@ -2,8 +2,11 @@ from __future__ import annotations
 
 import os
 from typing import Any
+from langbot.pkg.utils import constants
 import yaml
 import importlib.resources as resources
+import uuid
+import time
 
 from .. import stage, app
 from ..bootutils import config
@@ -142,6 +145,22 @@ 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,
+        )
+
+        constants.instance_id = ap.instance_id.data['instance_id']
+
+        print(f'LangBot instance id: {constants.instance_id}')
+
+        await ap.instance_id.dump_config()
+
         ap.sensitive_meta = await config.load_json_config(
             'data/metadata/sensitive-words.json',
             'metadata/sensitive-words.json',

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

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

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

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

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

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

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

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

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

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

src/langbot/pkg/persistence/mgr.py

@@ -9,7 +9,7 @@ import sqlalchemy.ext.asyncio as sqlalchemy_asyncio
 import sqlalchemy
 
 from . import database, migration
-from ..entity.persistence import base, pipeline, metadata
+from ..entity.persistence import base, pipeline, metadata, model as persistence_model
 from ..entity import persistence
 from ..core import app
 from ..utils import constants, importutil
@@ -79,6 +79,7 @@ class PersistenceManager:
             self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
 
         await self.write_default_pipeline()
+        await self.write_space_model_providers()
 
     async def create_tables(self):
         # create tables
@@ -123,7 +124,42 @@ class PersistenceManager:
 
             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'
+        )
+
+        # write space model providers
+        result = await self.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.requester == 'space-chat-completions'
+            )
+        )
+        exists_space_chat_completions_model_provider = result.first()
+
+        # api keys will be set/updated when the oauth callback
+        if exists_space_chat_completions_model_provider is None:
+            self.ap.logger.info('Creating space model providers...')
+            space_chat_completions_model_provider = {
+                'uuid': '00000000-0000-0000-0000-000000000000',
+                'name': 'LangBot Models',
+                'requester': 'space-chat-completions',
+                'base_url': space_models_gateway_api_url,
+                'api_keys': [],
+            }
+
+            await self.execute_async(
+                sqlalchemy.insert(persistence_model.ModelProvider).values(space_chat_completions_model_provider)
+            )
+        else:
+            if exists_space_chat_completions_model_provider.base_url != space_models_gateway_api_url:
+                await self.execute_async(
+                    sqlalchemy.update(persistence_model.ModelProvider)
+                    .where(persistence_model.ModelProvider.uuid == exists_space_chat_completions_model_provider.uuid)
+                    .values({'base_url': space_models_gateway_api_url})
+                )
+
+    # =================================
 
     async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
         async with self.get_db_engine().connect() as conn:

src/langbot/pkg/persistence/migrations/dbm014_space_account_support.py

@@ -0,0 +1,94 @@
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(14)
+class DBMigrateSpaceAccountSupport(migration.DBMigration):
+    """Add Space account support fields to users table"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # Get all column names from the users table
+        columns = []
+
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("SELECT column_name FROM information_schema.columns WHERE table_name = 'users';")
+            )
+            all_result = result.fetchall()
+            columns = [row[0] for row in all_result]
+        else:
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text('PRAGMA table_info(users);'))
+            all_result = result.fetchall()
+            columns = [row[1] for row in all_result]
+
+        # Add account_type column
+        if 'account_type' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text("ALTER TABLE users ADD COLUMN account_type VARCHAR(32) DEFAULT 'local' NOT NULL")
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text("ALTER TABLE users ADD COLUMN account_type VARCHAR(32) DEFAULT 'local' NOT NULL")
+                )
+
+        # Add space_account_uuid column
+        if 'space_account_uuid' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_account_uuid VARCHAR(255)')
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_account_uuid VARCHAR(255)')
+                )
+
+        # Add space_access_token column
+        if 'space_access_token' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_access_token TEXT')
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_access_token TEXT')
+                )
+
+        # Add space_refresh_token column
+        if 'space_refresh_token' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_refresh_token TEXT')
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_refresh_token TEXT')
+                )
+
+        # Add space_access_token_expires_at column
+        if 'space_access_token_expires_at' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_access_token_expires_at TIMESTAMP')
+                )
+
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_access_token_expires_at DATETIME')
+                )
+
+        # Add space_api_key column
+        if 'space_api_key' not in columns:
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_api_key VARCHAR(255)')
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('ALTER TABLE users ADD COLUMN space_api_key VARCHAR(255)')
+                )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm015_model_source_tracking.py

@@ -0,0 +1,15 @@
+from .. import migration
+
+
+# this is a deprecated migration
+@migration.migration_class(15)
+class DBMigrateModelSourceTracking(migration.DBMigration):
+    """Add source tracking fields to models tables for Space integration"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        pass
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm016_model_provider_refactor.py

@@ -0,0 +1,305 @@
+import uuid as uuid_lib
+
+import sqlalchemy
+from .. import migration
+
+
+@migration.migration_class(16)
+class DBMigrateModelProviderRefactor(migration.DBMigration):
+    """Refactor model structure: create providers from existing models and update references"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # Step 1: Create model_providers table if not exists
+        await self._create_providers_table()
+
+        # Step 2: Migrate existing models to use providers
+        await self._migrate_llm_models()
+        await self._migrate_embedding_models()
+
+        # Step 3: Remove deprecated columns
+        await self._cleanup_columns()
+
+    async def _create_providers_table(self):
+        """Create model_providers table"""
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("""
+                    CREATE TABLE IF NOT EXISTS model_providers (
+                        uuid VARCHAR(255) PRIMARY KEY,
+                        name VARCHAR(255) NOT NULL,
+                        requester VARCHAR(255) NOT NULL,
+                        base_url VARCHAR(512) NOT NULL,
+                        api_keys JSONB NOT NULL DEFAULT '[]',
+                        created_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP,
+                        updated_at TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP
+                    )
+                """)
+            )
+        else:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text("""
+                    CREATE TABLE IF NOT EXISTS model_providers (
+                        uuid VARCHAR(255) PRIMARY KEY,
+                        name VARCHAR(255) NOT NULL,
+                        requester VARCHAR(255) NOT NULL,
+                        base_url VARCHAR(512) NOT NULL,
+                        api_keys JSON NOT NULL DEFAULT '[]',
+                        created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+                        updated_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
+                    )
+                """)
+            )
+
+    async def _migrate_llm_models(self):
+        """Migrate LLM models to use providers"""
+        llm_columns = await self._get_columns('llm_models')
+
+        # Add provider_uuid column if not exists
+        if 'provider_uuid' not in llm_columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE llm_models ADD COLUMN provider_uuid VARCHAR(255)')
+            )
+
+        # Add prefered_ranking column if not exists
+        if 'prefered_ranking' not in llm_columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE llm_models ADD COLUMN prefered_ranking INTEGER NOT NULL DEFAULT 0')
+            )
+
+        # Only migrate if old columns exist
+        if 'requester' not in llm_columns:
+            return
+
+        # Get all LLM models with old structure
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, name, requester, requester_config, api_keys FROM llm_models')
+        )
+        models = result.fetchall()
+
+        # Create providers and update models
+        provider_cache = {}  # (requester, base_url, api_keys_str) -> provider_uuid
+
+        for model in models:
+            model_uuid, model_name, requester, requester_config, api_keys = model
+
+            # Extract base_url from requester_config
+            base_url = ''
+            if requester_config:
+                if isinstance(requester_config, str):
+                    import json
+
+                    requester_config = json.loads(requester_config)
+                base_url = requester_config.get('base_url', '') or requester_config.get('base-url', '')
+
+            # Parse api_keys if it's a string
+            if isinstance(api_keys, str):
+                import json
+
+                try:
+                    api_keys = json.loads(api_keys)
+                except Exception:
+                    api_keys = []
+            if not api_keys:
+                api_keys = []
+
+            # Create cache key
+            api_keys_str = str(sorted(api_keys)) if api_keys else '[]'
+            cache_key = (requester, base_url, api_keys_str)
+
+            if cache_key in provider_cache:
+                provider_uuid = provider_cache[cache_key]
+            else:
+                # Create new provider
+                provider_uuid = str(uuid_lib.uuid4())
+                provider_name = f'{requester}'
+                if base_url:
+                    # Extract domain for name
+                    try:
+                        from urllib.parse import urlparse
+
+                        parsed = urlparse(base_url)
+                        provider_name = parsed.netloc or requester
+                    except Exception:
+                        pass
+
+                import json
+
+                api_keys_json = json.dumps(api_keys) if api_keys else '[]'
+
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text("""
+                        INSERT INTO model_providers (uuid, name, requester, base_url, api_keys)
+                        VALUES (:uuid, :name, :requester, :base_url, :api_keys)
+                    """),
+                    {
+                        'uuid': provider_uuid,
+                        'name': provider_name,
+                        'requester': requester,
+                        'base_url': base_url,
+                        'api_keys': api_keys_json,
+                    },
+                )
+                provider_cache[cache_key] = provider_uuid
+
+            # Update model with provider_uuid
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('UPDATE llm_models SET provider_uuid = :provider_uuid WHERE uuid = :uuid'),
+                {'provider_uuid': provider_uuid, 'uuid': model_uuid},
+            )
+
+    async def _migrate_embedding_models(self):
+        """Migrate embedding models to use providers"""
+        embedding_columns = await self._get_columns('embedding_models')
+
+        # Add provider_uuid column if not exists
+        if 'provider_uuid' not in embedding_columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE embedding_models ADD COLUMN provider_uuid VARCHAR(255)')
+            )
+
+        # Add prefered_ranking column if not exists
+        if 'prefered_ranking' not in embedding_columns:
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('ALTER TABLE embedding_models ADD COLUMN prefered_ranking INTEGER NOT NULL DEFAULT 0')
+            )
+
+        # Only migrate if old columns exist
+        if 'requester' not in embedding_columns:
+            return
+
+        # Get all embedding models with old structure
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, name, requester, requester_config, api_keys FROM embedding_models')
+        )
+        models = result.fetchall()
+
+        # Get existing providers
+        provider_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, requester, base_url, api_keys FROM model_providers')
+        )
+        existing_providers = provider_result.fetchall()
+
+        provider_cache = {}
+        for p in existing_providers:
+            p_uuid, p_requester, p_base_url, p_api_keys = p
+            api_keys_str = str(sorted(p_api_keys)) if p_api_keys else '[]'
+            provider_cache[(p_requester, p_base_url, api_keys_str)] = p_uuid
+
+        for model in models:
+            model_uuid, model_name, requester, requester_config, api_keys = model
+
+            base_url = ''
+            if requester_config:
+                if isinstance(requester_config, str):
+                    import json
+
+                    requester_config = json.loads(requester_config)
+                base_url = requester_config.get('base_url', '') or requester_config.get('base-url', '')
+
+            # Parse api_keys if it's a string
+            if isinstance(api_keys, str):
+                import json
+
+                try:
+                    api_keys = json.loads(api_keys)
+                except Exception:
+                    api_keys = []
+            if not api_keys:
+                api_keys = []
+
+            api_keys_str = str(sorted(api_keys)) if api_keys else '[]'
+            cache_key = (requester, base_url, api_keys_str)
+
+            if cache_key in provider_cache:
+                provider_uuid = provider_cache[cache_key]
+            else:
+                provider_uuid = str(uuid_lib.uuid4())
+                provider_name = f'{requester}'
+                if base_url:
+                    try:
+                        from urllib.parse import urlparse
+
+                        parsed = urlparse(base_url)
+                        provider_name = parsed.netloc or requester
+                    except Exception:
+                        pass
+
+                import json
+
+                api_keys_json = json.dumps(api_keys) if api_keys else '[]'
+
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text("""
+                        INSERT INTO model_providers (uuid, name, requester, base_url, api_keys)
+                        VALUES (:uuid, :name, :requester, :base_url, :api_keys)
+                    """),
+                    {
+                        'uuid': provider_uuid,
+                        'name': provider_name,
+                        'requester': requester,
+                        'base_url': base_url,
+                        'api_keys': api_keys_json,
+                    },
+                )
+                provider_cache[cache_key] = provider_uuid
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text('UPDATE embedding_models SET provider_uuid = :provider_uuid WHERE uuid = :uuid'),
+                {'provider_uuid': provider_uuid, 'uuid': model_uuid},
+            )
+
+    async def _cleanup_columns(self):
+        """Remove deprecated columns from model tables"""
+
+        llm_columns = await self._get_columns('llm_models')
+        deprecated_llm_cols = ['requester', 'requester_config', 'api_keys', 'description', 'source', 'space_model_id']
+        for col in deprecated_llm_cols:
+            if col in llm_columns:
+                if self.ap.persistence_mgr.db.name == 'postgresql':
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(f'ALTER TABLE llm_models DROP COLUMN IF EXISTS {col}')
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(f'ALTER TABLE llm_models DROP COLUMN {col}')
+                    )
+
+        embedding_columns = await self._get_columns('embedding_models')
+        deprecated_embedding_cols = [
+            'requester',
+            'requester_config',
+            'api_keys',
+            'description',
+            'source',
+            'space_model_id',
+        ]
+        for col in deprecated_embedding_cols:
+            if col in embedding_columns:
+                if self.ap.persistence_mgr.db.name == 'postgresql':
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(f'ALTER TABLE embedding_models DROP COLUMN IF EXISTS {col}')
+                    )
+                else:
+                    await self.ap.persistence_mgr.execute_async(
+                        sqlalchemy.text(f'ALTER TABLE embedding_models DROP COLUMN {col}')
+                    )
+
+    async def _get_columns(self, table_name: str) -> list:
+        """Get column names for a table"""
+        if self.ap.persistence_mgr.db.name == 'postgresql':
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.text(
+                    f"SELECT column_name FROM information_schema.columns WHERE table_name = '{table_name}';"
+                )
+            )
+            all_result = result.fetchall()
+            return [row[0] for row in all_result]
+        else:
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text(f'PRAGMA table_info({table_name});'))
+            all_result = result.fetchall()
+            return [row[1] for row in all_result]
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/persistence/migrations/dbm017_move_cloud_service_url.py

@@ -0,0 +1,25 @@
+from .. import migration
+
+
+@migration.migration_class(17)
+class MoveCloudServiceUrl(migration.DBMigration):
+    """迁移云服务 URL 配置"""
+
+    async def upgrade(self):
+        """升级"""
+        if 'space' not in self.ap.instance_config.data:
+            self.ap.instance_config.data['space'] = {
+                'url': 'https://space.langbot.app',
+                'models_gateway_api_url': 'https://api.langbot.cloud/v1',
+                'oauth_authorize_url': 'https://space.langbot.app/auth/authorize',
+                'disable_models_service': False,
+            }
+
+        if 'plugin' in self.ap.instance_config.data:
+            self.ap.instance_config.data['plugin'].pop('cloud_service_url', None)
+
+        await self.ap.instance_config.dump_config()
+
+    async def downgrade(self):
+        """降级"""
+        pass

src/langbot/pkg/pipeline/controller.py

@@ -33,11 +33,14 @@ class Controller:
 
                     for query in queries:
                         session = await self.ap.sess_mgr.get_session(query)
-                        self.ap.logger.debug(f'Checking query {query} session {session}')
+                        # Debug logging removed from tight loop to prevent excessive log generation
+                        # that can cause memory overflow in high-traffic scenarios
 
                         if not session._semaphore.locked():
                             selected_query = query
                             await session._semaphore.acquire()
+                            # Only log when actually selecting a query
+                            self.ap.logger.debug(f'Selected query {query.query_id} for processing')
 
                             break
 

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

@@ -3,6 +3,8 @@ from __future__ import annotations
 import uuid
 import typing
 import traceback
+import time
+from datetime import datetime
 
 
 from .. import handler
@@ -10,10 +12,11 @@ from ... import entities
 from ....provider import runner as runner_module
 
 import langbot_plugin.api.entities.events as events
-from ....utils import importutil
+from ....utils import importutil, constants
 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
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
 importutil.import_modules_in_pkg(runners)
@@ -61,8 +64,14 @@ class ChatMessageHandler(handler.MessageHandler):
                 yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
         else:
             if event_ctx.event.user_message_alter is not None:
-                # if isinstance(event_ctx.event, str):  # 现在暂时不考虑多模态alter
-                query.user_message.content = event_ctx.event.user_message_alter
+                if isinstance(event_ctx.event.user_message_alter, list):
+                    query.user_message.content = event_ctx.event.user_message_alter
+                elif isinstance(event_ctx.event.user_message_alter, str):
+                    query.user_message.content = [
+                        provider_message.ContentElement.from_text(event_ctx.event.user_message_alter)
+                    ]
+                elif isinstance(event_ctx.event.user_message_alter, provider_message.ContentElement):
+                    query.user_message.content = [event_ctx.event.user_message_alter]
 
             text_length = 0
             try:
@@ -77,8 +86,12 @@ class ChatMessageHandler(handler.MessageHandler):
                         break
                 else:
                     raise ValueError(f'Request Runner not found: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                # Mark start time for telemetry
+                start_ts = time.time()
+
                 if is_stream:
                     resp_message_id = uuid.uuid4()
+                    chunk_count = 0  # Track streaming chunks to reduce excessive logging
 
                     async for result in runner.run(query):
                         result.resp_message_id = str(resp_message_id)
@@ -91,15 +104,30 @@ class ChatMessageHandler(handler.MessageHandler):
                             await query.adapter.create_message_card(str(resp_message_id), query.message_event)
                             is_create_card = True
                         query.resp_messages.append(result)
-                        self.ap.logger.info(
-                            f'Conversation({query.query_id}) Streaming Response: {self.cut_str(result.readable_str())}'
-                        )
+
+                        chunk_count += 1
+                        # Only log every 10th chunk to reduce excessive logging during streaming
+                        # This prevents memory overflow from thousands of log entries per conversation
+                        # First chunk uses INFO level to confirm connection establishment
+                        if chunk_count == 1:
+                            self.ap.logger.info(
+                                f'Conversation({query.query_id}) Streaming started: {self.cut_str(result.readable_str())}'
+                            )
+                        elif chunk_count % 10 == 0:
+                            self.ap.logger.debug(
+                                f'Conversation({query.query_id}) Streaming chunk {chunk_count}: {self.cut_str(result.readable_str())}'
+                            )
 
                         if result.content is not None:
                             text_length += len(result.content)
 
                         yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
 
+                    # Log final summary after streaming completes
+                    self.ap.logger.info(
+                        f'Conversation({query.query_id}) Streaming completed: {chunk_count} chunks, {text_length} chars'
+                    )
+
                 else:
                     async for result in runner.run(query):
                         query.resp_messages.append(result)
@@ -117,7 +145,8 @@ class ChatMessageHandler(handler.MessageHandler):
 
                 query.session.using_conversation.messages.extend(query.resp_messages)
             except Exception as e:
-                self.ap.logger.error(f'Conversation({query.query_id}) Request Failed: {type(e).__name__} {str(e)}')
+                error_info = f'{type(e).__name__} {str(e)}'
+                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']
@@ -130,5 +159,47 @@ class ChatMessageHandler(handler.MessageHandler):
                     debug_notice=traceback.format_exc(),
                 )
             finally:
-                # TODO statistics
-                pass
+                # Telemetry reporting: collect minimal per-query execution info and send asynchronously
+                try:
+                    end_ts = time.time()
+                    duration_ms = None
+                    if 'start_ts' in locals():
+                        duration_ms = int((end_ts - start_ts) * 1000)
+
+                    adapter_name = query.adapter.__class__.__name__ if hasattr(query, 'adapter') else None
+                    runner_name = (
+                        query.pipeline_config.get('ai', {}).get('runner', {}).get('runner')
+                        if query.pipeline_config
+                        else None
+                    )
+
+                    # Model name if using localagent
+                    model_name = None
+                    try:
+                        if runner_name == 'local-agent' and getattr(query, 'use_llm_model_uuid', None):
+                            m = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
+                            if m and getattr(m, 'model_entity', None):
+                                model_name = getattr(m.model_entity, 'name', None)
+                    except Exception:
+                        model_name = None
+
+                    pipeline_plugins = query.variables.get('_pipeline_bound_plugins', None)
+
+                    payload = {
+                        'query_id': query.query_id,
+                        'adapter': adapter_name,
+                        'runner': runner_name,
+                        'duration_ms': duration_ms,
+                        'model_name': model_name,
+                        'version': constants.semantic_version,
+                        'instance_id': constants.instance_id,
+                        'pipeline_plugins': pipeline_plugins,
+                        'error': locals().get('error_info', None),
+                        'timestamp': datetime.utcnow().isoformat(),
+                    }
+
+                    # Send telemetry asynchronously and do not block pipeline via app's telemetry manager
+                    await self.ap.telemetry.start_send_task(payload)
+                except Exception as ex:
+                    # Ensure telemetry issues do not affect normal flow
+                    self.ap.logger.warning(f'Failed to send telemetry: {ex}')

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

@@ -31,4 +31,8 @@ class AtBotRule(rule_model.GroupRespondRule):
         remove_at(message_chain)
         remove_at(message_chain)  # 回复消息时会at两次，检查并删除重复的
 
+        should_respond_at = rule_dict.get('at', None)
+        if should_respond_at is not None:
+            return entities.RuleJudgeResult(matching=found and bool(should_respond_at), replacement=message_chain)
+
         return entities.RuleJudgeResult(matching=found, replacement=message_chain)

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

@@ -260,7 +260,8 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         await self.bot.start()
 
     async def kill(self) -> bool:
-        return False
+        await self.bot.stop()
+        return True
 
     async def is_muted(self) -> bool:
         return False

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

@@ -9,9 +9,13 @@ import re
 import base64
 import uuid
 import json
+import time
 import datetime
 import hashlib
 from Crypto.Cipher import AES
+import tempfile
+import os
+import mimetypes
 
 import aiohttp
 import lark_oapi.ws.exception
@@ -19,6 +23,8 @@ import quart
 from lark_oapi.api.im.v1 import *
 import pydantic
 from lark_oapi.api.cardkit.v1 import *
+from lark_oapi.api.auth.v3 import *
+from lark_oapi.core.model import *
 
 import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
@@ -238,6 +244,7 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
 
         lb_msg_list.append(platform_message.Source(id=message.message_id, time=msg_create_time))
 
+
         if message.message_type == 'text':
             element_list = []
 
@@ -301,6 +308,10 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
             message_content['content'] = [
                 {'tag': 'file', 'file_key': message_content['file_key'], 'file_name': message_content['file_name']}
             ]
+        elif message.message_type == 'audio':
+            message_content['content'] = [
+                {'tag': 'audio', 'file_key': message_content['file_key'], "duration": message_content.get('duration',0)}
+            ]
 
         for ele in message_content['content']:
             if ele['tag'] == 'text':
@@ -331,6 +342,60 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
                 image_format = response.raw.headers['content-type']
 
                 lb_msg_list.append(platform_message.Image(base64=f'data:{image_format};base64,{image_base64}'))
+            elif ele['tag'] == 'audio':
+                file_key = ele['file_key']
+                duration = ele['duration']
+
+                # Download audio file
+                request: GetMessageResourceRequest = (
+                    GetMessageResourceRequest.builder()
+                    .message_id(message.message_id)
+                    .file_key(file_key)
+                    .type('file')
+                    .build()
+                )
+
+                try:
+                    response: GetMessageResourceResponse = await api_client.im.v1.message_resource.aget(request)
+
+                    if not response.success():
+                        print(f'Failed to download audio: code: {response.code}, msg: {response.msg}')
+                        lb_msg_list.append(platform_message.Plain(text='[Audio file download failed]'))
+                        return platform_message.MessageChain(lb_msg_list)
+
+                    # Read audio bytes
+                    audio_bytes = response.file.read()
+                    audio_base64 = base64.b64encode(audio_bytes).decode()
+
+
+                    # Get content type from response headers
+                    content_type = response.raw.headers.get('content-type', 'audio/mpeg')
+
+
+
+                    mime_main = content_type.split(';')[0].strip()
+                    ext = mimetypes.guess_extension(mime_main) or '.bin'
+                    temp_dir = tempfile.gettempdir()
+                    temp_file_path = os.path.join(temp_dir, f'lark_audio_{file_key}{ext}')
+
+                    with open(temp_file_path, 'wb') as f:
+                        f.write(audio_bytes)
+
+                    # Create Voice message: prefer path/url + length, include base64 as optional data URI
+                    lb_msg_list.append(
+                        platform_message.Voice(
+                            voice_id=file_key,
+                            url=f'file://{temp_file_path}',
+                            path=temp_file_path,
+                            base64=f'data:{content_type};base64,{audio_base64}',
+                            length=(duration // 1000) if duration else None,
+                        )
+                    )
+                except Exception as e:
+                    print(f'Error downloading audio: {e}')
+                    traceback.print_exc()
+                    lb_msg_list.append(platform_message.Plain(text='[Audio file download error]'))
+
             elif ele['tag'] == 'file':
                 file_key = ele['file_key']
                 file_name = ele['file_name']
@@ -353,12 +418,42 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
                 file_bytes = response.file.read()
                 file_base64 = base64.b64encode(file_bytes).decode()
 
+
                 file_format = response.raw.headers['content-type']
 
+                file_size = len(file_bytes)
+
+                # Determine extension from content-type if possible
+                content_type = response.raw.headers.get('content-type', '')
+                mime_main = content_type.split(';')[0].strip() if content_type else ''
+                ext = mimetypes.guess_extension(mime_main) or ''
+
+                # Ensure a safe filename (avoid path components)
+                safe_name = os.path.basename(file_name).replace('/', '_').replace('\\', '_')
+                if ext and not safe_name.lower().endswith(ext.lower()):
+                    filename_with_ext = f'{safe_name}{ext}'
+                else:
+                    filename_with_ext = safe_name
+
+                temp_dir = tempfile.gettempdir()
+                temp_file_path = os.path.join(temp_dir, f'lark_{file_key}_{filename_with_ext}')
+
+                with open(temp_file_path, 'wb') as f:
+                    f.write(file_bytes)
+
+                # Create File message with local path and file:// URL
                 lb_msg_list.append(
-                    platform_message.File(base64=f'data:{file_format};base64,{file_base64}', name=file_name)
+                    platform_message.File(
+                        id=file_key,
+                        name=file_name,
+                        size=file_size,
+                        url=f'file://{temp_file_path}',
+                        path=temp_file_path,
+                        base64=f'data:{file_format};base64,{file_base64}',  # not including base64 by default to save memory; can be added if needed
+                    )
                 )
 
+
         return platform_message.MessageChain(lb_msg_list)
 
 
@@ -384,6 +479,7 @@ class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 ),
                 message_chain=message_chain,
                 time=event.event.message.create_time,
+                source_platform_object=event,
             )
         elif event.event.message.chat_type == 'group':
             return platform_events.GroupMessage(
@@ -400,6 +496,7 @@ class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 ),
                 message_chain=message_chain,
                 time=event.event.message.create_time,
+                source_platform_object=event,
             )
 
 
@@ -429,6 +526,10 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
     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
+    app_access_token: str = None  # 商店应用用到
+    app_access_token_expire_at: int = None
+    tenant_access_tokens: dict[str, dict[str, str]] = {}  # 租户access_token映射
 
     def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, **kwargs):
         quart_app = quart.Quart(__name__)
@@ -448,8 +549,9 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         bot_account_id = config['bot_name']
 
         bot = lark_oapi.ws.Client(config['app_id'], config['app_secret'], event_handler=event_handler)
-        api_client = lark_oapi.Client.builder().app_id(config['app_id']).app_secret(config['app_secret']).build()
+        api_client = self.build_api_client(config)
         cipher = AESCipher(config.get('encrypt-key', ''))
+        self.request_app_ticket(api_client, config)
 
         super().__init__(
             config=config,
@@ -466,6 +568,101 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             **kwargs,
         )
 
+    def request_app_ticket(self, api_client, config):
+        app_id = config['app_id']
+        app_secret = config['app_secret']
+        print(f'Requesting app ticket for app_id: {app_id[:3]}***{app_id[-3:]}')
+        if 'isv' == config.get('app_type', 'self'):
+            request: ResendAppTicketRequest = (
+                ResendAppTicketRequest.builder()
+                .request_body(ResendAppTicketRequestBody.builder().app_id(app_id).app_secret(app_secret).build())
+                .build()
+            )
+            response: ResendAppTicketResponse = api_client.auth.v3.app_ticket.resend(request)
+            if not response.success():
+                raise Exception(
+                    f'client.auth.v3.auth.app_ticket_resend 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)}'
+                )
+
+    def request_app_access_token(self):
+        app_id = self.config['app_id']
+        app_secret = self.config['app_secret']
+        if 'isv' == self.config.get('app_type', 'self'):
+            request: CreateAppAccessTokenRequest = (
+                CreateAppAccessTokenRequest.builder()
+                .request_body(
+                    CreateAppAccessTokenRequestBody.builder()
+                    .app_id(app_id)
+                    .app_secret(app_secret)
+                    .app_ticket(self.app_ticket)
+                    .build()
+                )
+                .build()
+            )
+            response: CreateAppAccessTokenResponse = self.api_client.auth.v3.app_access_token.create(request)
+            if not response.success():
+                raise Exception(
+                    f'client.auth.v3.auth.app_access_token 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)}'
+                )
+            content = json.loads(response.raw.content)
+            self.app_access_token = content['app_access_token']
+            self.app_access_token_expire_at = int(time.time()) + content['expire'] - 300
+
+    def get_app_access_token(self):
+        if 'isv' != self.config.get('app_type', 'self'):
+            return None
+        if (
+            self.app_access_token is None
+            or self.app_access_token_expire_at is None
+            or int(time.time()) >= self.app_access_token_expire_at
+        ):
+            self.request_app_access_token()
+        return self.app_access_token
+
+    def request_tenant_access_token(self, tenant_key: str):
+        app_access_token = self.get_app_access_token()
+        if 'isv' == self.config.get('app_type', 'self'):
+            request: CreateTenantAccessTokenRequest = (
+                CreateTenantAccessTokenRequest.builder()
+                .request_body(
+                    CreateTenantAccessTokenRequestBody.builder()
+                    .app_access_token(app_access_token)
+                    .tenant_key(tenant_key)
+                    .build()
+                )
+                .build()
+            )
+            response: CreateTenantAccessTokenResponse = self.api_client.auth.v3.tenant_access_token.create(request)
+            if not response.success():
+                raise Exception(
+                    f'client.auth.v3.auth.tenant_access_token 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)}'
+                )
+            content = json.loads(response.raw.content)
+            tenant_access_token = content['tenant_access_token']
+            expire = content['expire']
+            self.tenant_access_tokens[tenant_key] = {
+                'token': tenant_access_token,
+                'expire_at': int(time.time()) + expire - 300,
+            }
+
+    def get_tenant_access_token(self, tenant_key: str):
+        if tenant_key is None or 'isv' != self.config.get('app_type', 'self'):
+            return None
+        tenant_access_token = self.tenant_access_tokens.get(tenant_key)
+        if tenant_access_token is None or int(time.time()) >= tenant_access_token['expire_at']:
+            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 build_api_client(self, config):
+        app_id = config['app_id']
+        app_secret = config['app_secret']
+        api_client = lark_oapi.Client.builder().app_id(app_id).app_secret(app_secret).build()
+        if 'isv' == config.get('app_type', 'self'):
+            api_client = (
+                lark_oapi.Client.builder().app_id(app_id).app_secret(app_secret).app_type(lark_oapi.AppType.ISV).build()
+            )
+        return api_client
+
     async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
         pass
 
@@ -693,9 +890,19 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             )
             .build()
         )
-
+        tenant_key = event.source_platform_object.header.tenant_key if event.source_platform_object else None
+        app_access_token = self.get_app_access_token()
+        tenant_access_token = self.get_tenant_access_token(tenant_key)
+        req_opt: RequestOption = (
+            RequestOption.builder()
+            .app_ticket(self.app_ticket)
+            .tenant_key(tenant_key)
+            .app_access_token(app_access_token)
+            .tenant_access_token(tenant_access_token)
+            .build()
+        )
         # 发起请求
-        response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request)
+        response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request, req_opt)
 
         # 处理失败返回
         if not response.success():
@@ -722,7 +929,6 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                     'content': text_elements,
                 },
             }
-
             request: ReplyMessageRequest = (
                 ReplyMessageRequest.builder()
                 .message_id(message_source.message_chain.message_id)
@@ -737,7 +943,22 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 .build()
             )
 
-            response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request)
+            tenant_key = (
+                message_source.source_platform_object.header.tenant_key
+                if message_source.source_platform_object
+                else None
+            )
+            app_access_token = self.get_app_access_token()
+            tenant_access_token = self.get_tenant_access_token(tenant_key)
+            req_opt: RequestOption = (
+                RequestOption.builder()
+                .app_ticket(self.app_ticket)
+                .tenant_key(tenant_key)
+                .app_access_token(app_access_token)
+                .tenant_access_token(tenant_access_token)
+                .build()
+            )
+            response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request, req_opt)
 
             if not response.success():
                 raise Exception(
@@ -762,7 +983,22 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 .build()
             )
 
-            response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request)
+            tenant_key = (
+                message_source.source_platform_object.header.tenant_key
+                if message_source.source_platform_object
+                else None
+            )
+            app_access_token = self.get_app_access_token()
+            tenant_access_token = self.get_tenant_access_token(tenant_key)
+            req_opt: RequestOption = (
+                RequestOption.builder()
+                .app_ticket(self.app_ticket)
+                .tenant_key(tenant_key)
+                .app_access_token(app_access_token)
+                .tenant_access_token(tenant_access_token)
+                .build()
+            )
+            response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request, req_opt)
 
             if not response.success():
                 raise Exception(
@@ -816,8 +1052,24 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             if is_final and bot_message.tool_calls is None:
                 # self.seq = 1  # 消息回复结束之后重置seq
                 self.card_id_dict.pop(message_id)  # 清理已经使用过的卡片
+
+            tenant_key = (
+                message_source.source_platform_object.header.tenant_key
+                if message_source.source_platform_object
+                else None
+            )
+            app_access_token = self.get_app_access_token()
+            tenant_access_token = self.get_tenant_access_token(tenant_key)
+            req_opt: RequestOption = (
+                RequestOption.builder()
+                .app_ticket(self.app_ticket)
+                .tenant_key(tenant_key)
+                .app_access_token(app_access_token)
+                .tenant_access_token(tenant_access_token)
+                .build()
+            )
             # 发起请求
-            response: ContentCardElementResponse = self.api_client.cardkit.v1.card_element.content(request)
+            response: ContentCardElementResponse = self.api_client.cardkit.v1.card_element.content(request, req_opt)
 
             # 处理失败返回
             if not response.success():
@@ -851,6 +1103,17 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         """设置 bot UUID（用于生成 webhook URL）"""
         self.bot_uuid = bot_uuid
 
+    def get_event_type(self, data):
+        schema = '1.0'
+        if 'schema' in data:
+            schema = data['schema']
+        if '2.0' == schema:
+            return data['header']['event_type']
+        elif 'event' in data:
+            return data['event']['type']
+        else:
+            return data['type']
+
     async def handle_unified_webhook(self, bot_uuid: str, path: str, request):
         """处理统一 webhook 请求。
         Args:
@@ -866,21 +1129,18 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             if 'encrypt' in data:
                 data = self.cipher.decrypt_string(data['encrypt'])
                 data = json.loads(data)
-            type = data.get('type')
-            if type is None:
-                context = EventContext(data)
-                type = context.header.event_type
-
+            type = self.get_event_type(data)
+            context = EventContext(data)
             if 'url_verification' == type:
                 # todo 验证verification token
                 return {'challenge': data.get('challenge')}
-            context = EventContext(data)
-            type = context.header.event_type
-            p2v1 = P2ImMessageReceiveV1()
-            p2v1.header = context.header
-            event = P2ImMessageReceiveV1Data()
-            if 'im.message.receive_v1' == type:
+            elif 'app_ticket' == type:
+                self.app_ticket = context.event['app_ticket']
+            elif 'im.message.receive_v1' == type:
                 try:
+                    p2v1 = P2ImMessageReceiveV1()
+                    p2v1.header = context.header
+                    event = P2ImMessageReceiveV1Data()
                     event.message = EventMessage(context.event['message'])
                     event.sender = EventSender(context.event['sender'])
                     p2v1.event = event
@@ -898,7 +1158,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                         final_content = {
                             'zh_Hans': {
                                 'title': '',
-                                'content': bot_added_welcome_msg,
+                                'content': [[{'tag': 'md', 'text': bot_added_welcome_msg}]],
                             },
                         }
                         chat_id = context.event['chat_id']
@@ -915,17 +1175,30 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                             )
                             .build()
                         )
-                        response: CreateMessageResponse = self.api_client.im.v1.message.create(request)
+                        tenant_key = context.header.tenant_key if context.header else None
+                        app_access_token = self.get_app_access_token()
+                        tenant_access_token = self.get_tenant_access_token(tenant_key)
+                        req_opt: RequestOption = (
+                            RequestOption.builder()
+                            .app_ticket(self.app_ticket)
+                            .tenant_key(tenant_key)
+                            .app_access_token(app_access_token)
+                            .tenant_access_token(tenant_access_token)
+                            .build()
+                        )
+                        response: CreateMessageResponse = self.api_client.im.v1.message.create(request, req_opt)
 
                         if not response.success():
                             raise Exception(
                                 f'client.im.v1.message.create failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
                             )
-                except Exception:
+                except Exception as e:
+                    print(f'im.chat.member.bot.added_v1: {e}')
                     await self.logger.error(f'Error in lark callback: {traceback.format_exc()}')
 
             return {'code': 200, 'message': 'ok'}
-        except Exception:
+        except Exception as e:
+            print(f'Error in lark callback: {e}')
             await self.logger.error(f'Error in lark callback: {traceback.format_exc()}')
             return {'code': 500, 'message': 'error'}
 

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

@@ -65,6 +65,25 @@ spec:
       type: boolean
       required: true
       default: false
+    - name: app_type
+      label:
+        en_US: App Type
+        zh_Hans: 应用类型
+      description:
+        en_US: Default to self-built application, refer to https://open.feishu.cn/document/platform-overveiw/overview
+        zh_Hans: 默认为企业自建应用，参考 https://open.feishu.cn/document/platform-overveiw/overview
+      type: select
+      options:
+        - name: self
+          label:
+            en_US: Self-built Application
+            zh_Hans: 自建应用
+        - name: isv
+          label:
+            en_US: Store Application
+            zh_Hans: 商店应用
+      required: false
+      default: self
     - name: bot_added_welcome
       label:
         en_US: Bot Welcome Message

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

@@ -76,6 +76,7 @@ class OfficialAccountAdapter(abstract_platform_adapter.AbstractMessagePlatformAd
                 AppID=config['AppID'],
                 logger=logger,
                 unified_mode=True,
+                api_base_url=config.get('api_base_url', 'https://api.weixin.qq.com'),
             )
         elif config['Mode'] == 'passive':
             bot = OAClientForLongerResponse(
@@ -86,6 +87,7 @@ class OfficialAccountAdapter(abstract_platform_adapter.AbstractMessagePlatformAd
                 LoadingMessage=config.get('LoadingMessage', ''),
                 logger=logger,
                 unified_mode=True,
+                api_base_url=config.get('api_base_url', 'https://api.weixin.qq.com'),
             )
         else:
             raise KeyError('请设置微信公众号通信模式')

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

@@ -53,6 +53,16 @@ spec:
       type: string
       required: true
       default: "AI正在思考中，请发送任意内容获取回复。"
+    - name: api_base_url
+      label:
+        en_US: API Base URL
+        zh_Hans: API 基础 URL
+      description:
+        en_US: API Base URL, used for accessing the Official Account API. If you are deploying in an internal network environment and accessing the Official Account API through a reverse proxy, please fill in this item according to the documentation.
+        zh_Hans: 可选，若您部署在内网环境并通过反向代理访问微信公众号 API，可根据文档修改此项
+      type: string
+      required: false
+      default: "https://api.weixin.qq.com"
 execution:
   python:
     path: ./officialaccount.py

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

@@ -65,6 +65,10 @@ class WebSocketAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
     outbound_message_queue: asyncio.Queue = pydantic.Field(default_factory=asyncio.Queue, exclude=True)
     """后端主动推送消息的队列"""
 
+    # 流式输出开关
+    stream_enabled: bool = pydantic.Field(default=True, exclude=True)
+    """是否启用流式输出"""
+
     def __init__(self, config: dict, logger: abstract_platform_logger.AbstractEventLogger, **kwargs):
         super().__init__(
             config=config,
@@ -77,6 +81,7 @@ class WebSocketAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
 
         self.bot_account_id = 'websocketbot'
         self.outbound_message_queue = asyncio.Queue()
+        self.stream_enabled = True
 
     async def send_message(
         self,
@@ -212,8 +217,8 @@ class WebSocketAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
         return message_data.model_dump()
 
     async def is_stream_output_supported(self) -> bool:
-        """WebSocket始终支持流式输出"""
-        return True
+        """根据stream_enabled标志返回是否支持流式输出"""
+        return self.stream_enabled
 
     def register_listener(
         self,
@@ -314,11 +319,16 @@ class WebSocketAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
 
         Args:
             connection: WebSocket连接对象
-            message_data: 消息数据
+            message_data: 消息数据，包含:
+                - message: 消息链
+                - stream: 是否启用流式输出 (可选，默认True)
         """
         pipeline_uuid = connection.pipeline_uuid
         session_type = connection.session_type
 
+        # 获取stream参数，默认为True
+        self.stream_enabled = message_data.get('stream', True)
+
         # 选择会话
         use_session = self.websocket_group_session if session_type == 'group' else self.websocket_person_session
 

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

@@ -15,6 +15,58 @@ import langbot_plugin.api.entities.builtin.platform.events as platform_events
 import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
 
 
+def split_string_by_bytes(text, limit=2048, encoding='utf-8'):
+    """
+    Splits a string into a list of strings, where each part is at most 'limit' bytes.
+    
+    Args:
+        text (str): The original string to split.
+        limit (int): The maximum byte size for each split part.
+        encoding (str): The encoding to use (default is 'utf-8').
+        
+    Returns:
+        list: A list of split strings.
+    """
+    # 1. Encode the entire string into bytes
+    bytes_data = text.encode(encoding)
+    total_len = len(bytes_data)
+    
+    parts = []
+    start = 0
+    
+    while start < total_len:
+        # 2. Determine the end index for the current chunk
+        # It shouldn't exceed the total length
+        end = min(start + limit, total_len)
+        
+        # 3. Slice the byte array
+        chunk = bytes_data[start:end]
+        
+        # 4. Attempt to decode the chunk
+        # Use errors='ignore' to drop any partial bytes at the end of the chunk
+        # (e.g., if a 3-byte character was cut after the 2nd byte)
+        part_str = chunk.decode(encoding, errors='ignore')
+        
+        # 5. Calculate the actual byte length of the successfully decoded string
+        # This tells us exactly where the valid character boundary ended
+        part_bytes = part_str.encode(encoding)
+        part_len = len(part_bytes)
+        
+        # Safety check: Prevent infinite loop if limit is too small (e.g., limit=1 for a Chinese char)
+        if part_len == 0 and end < total_len:
+            # Force advance by 1 byte to consume the un-decodable byte or raise error
+            # Here we just treat it as a part to avoid stuck loops, though it might be invalid
+            start += 1 
+            continue
+
+        parts.append(part_str)
+        
+        # 6. Move the start pointer by the actual length consumed
+        start += part_len
+        
+    return parts
+
+
 class WecomMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
     @staticmethod
     async def yiri2target(message_chain: platform_message.MessageChain, bot: WecomClient):
@@ -22,12 +74,14 @@ class WecomMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
 
         for msg in message_chain:
             if type(msg) is platform_message.Plain:
-                content_list.append(
+                chunks = split_string_by_bytes(msg.text)
+                content_list.extend([
                     {
                         'type': 'text',
-                        'content': msg.text,
+                        'content': chunk,
                     }
-                )
+                    for chunk in chunks
+                ])
             elif type(msg) is platform_message.Image:
                 content_list.append(
                     {
@@ -170,6 +224,7 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             contacts_secret=config['contacts_secret'],
             logger=logger,
             unified_mode=True,
+            api_base_url=config.get('api_base_url', 'https://qyapi.weixin.qq.com/cgi-bin'),
         )
 
         super().__init__(

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

@@ -46,6 +46,16 @@ spec:
       type: string
       required: true
       default: ""
+    - name: api_base_url
+      label:
+        en_US: API Base URL
+        zh_Hans: API 基础 URL
+      description:
+        en_US: API Base URL, used for accessing the WeCom API. If you are deploying in an internal network environment and accessing the WeCom Customer Service API through a reverse proxy, please fill in this item according to the documentation.
+        zh_Hans: 可选，若您部署在内网环境并通过反向代理访问企业微信 API，可根据文档填写此项
+      type: string
+      required: false
+      default: "https://qyapi.weixin.qq.com/cgi-bin"
 execution:
   python:
     path: ./wecom.py

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

@@ -141,6 +141,7 @@ class WecomCSAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             EncodingAESKey=config['EncodingAESKey'],
             logger=logger,
             unified_mode=True,
+            api_base_url=config.get('api_base_url', 'https://qyapi.weixin.qq.com/cgi-bin'),
         )
 
         super().__init__(

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

@@ -39,6 +39,16 @@ spec:
       type: string
       required: true
       default: ""
+    - name: api_base_url
+      label:
+        en_US: API Base URL
+        zh_Hans: API 基础 URL
+      description:
+        en_US: API Base URL, used for accessing the WeCom API. If you are deploying in an internal network environment and accessing the WeCom Customer Service API through a reverse proxy, please fill in this item according to the documentation.
+        zh_Hans: 可选，若您部署在内网环境并通过反向代理访问企业微信 API，可根据文档修改此项
+      type: string
+      required: false
+      default: "https://qyapi.weixin.qq.com/cgi-bin"
 execution:
   python:
     path: ./wecomcs.py

src/langbot/pkg/plugin/handler.py

@@ -324,7 +324,7 @@ class RuntimeConnectionHandler(handler.Handler):
             messages_obj = [provider_message.Message.model_validate(message) for message in messages]
             funcs_obj = [resource_tool.LLMTool.model_validate(func) for func in funcs]
 
-            result = await llm_model.requester.invoke_llm(
+            result = await llm_model.provider.requester.invoke_llm(
                 query=None,
                 model=llm_model,
                 messages=messages_obj,

src/langbot/pkg/provider/modelmgr/modelmgr.py

@@ -9,22 +9,24 @@ from ...discover import engine
 from . import token
 from ...entity.persistence import model as persistence_model
 from ...entity.errors import provider as provider_errors
-
-FETCH_MODEL_LIST_URL = 'https://api.qchatgpt.rockchin.top/api/v2/fetch/model_list'
+from async_lru import alru_cache
 
 
 class ModelManager:
-    """模型管理器"""
+    """Model manager"""
 
     ap: app.Application
 
+    provider_dict: dict[str, requester.RuntimeProvider]
+    """运行时模型提供商字典, uuid -> RuntimeProvider"""
+
     llm_models: list[requester.RuntimeLLMModel]
 
     embedding_models: list[requester.RuntimeEmbeddingModel]
 
     requester_components: list[engine.Component]
 
-    requester_dict: dict[str, type[requester.ProviderAPIRequester]]  # cache
+    requester_dict: dict[str, type[requester.ProviderAPIRequester]]
 
     def __init__(self, ap: app.Application):
         self.ap = ap
@@ -36,7 +38,6 @@ class ModelManager:
     async def initialize(self):
         self.requester_components = self.ap.discover.get_components_by_kind('LLMAPIRequester')
 
-        # forge requester class dict
         requester_dict: dict[str, type[requester.ProviderAPIRequester]] = {}
         for component in self.requester_components:
             requester_dict[component.metadata.name] = component.get_python_component_class()
@@ -45,139 +46,342 @@ class ModelManager:
 
         await self.load_models_from_db()
 
+        # Check if space models service is disabled
+        space_config = self.ap.instance_config.data.get('space', {})
+        if space_config.get('disable_models_service', False):
+            self.ap.logger.info('LangBot Space Models service is disabled, skipping sync.')
+            return
+
+        try:
+            await self.sync_new_models_from_space()
+        except Exception as e:
+            self.ap.logger.warning('Failed to sync new models from LangBot Space, model list may not be updated.')
+            self.ap.logger.warning(f'  - Error: {e}')
+
     async def load_models_from_db(self):
-        """从数据库加载模型"""
+        """Load models from database"""
         self.ap.logger.info('Loading models from db...')
 
         self.llm_models = []
         self.embedding_models = []
 
-        # llm models
+        # Load all providers first
+        self.provider_dict = {}
+        providers_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider)
+        )
+        for provider in providers_result.all():
+            try:
+                runtime_provider = await self.load_provider(provider)
+                self.provider_dict[provider.uuid] = runtime_provider
+            except provider_errors.RequesterNotFoundError as e:
+                self.ap.logger.warning(f'Requester {e.requester_name} not found, skipping provider {provider.uuid}')
+                continue
+            except Exception as e:
+                self.ap.logger.error(f'Failed to load provider {provider.uuid}: {e}\n{traceback.format_exc()}')
+
+        # Load LLM models
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
         llm_models = result.all()
         for llm_model in llm_models:
             try:
-                await self.load_llm_model(llm_model)
-            except provider_errors.RequesterNotFoundError as e:
-                self.ap.logger.warning(f'Requester {e.requester_name} not found, skipping llm model {llm_model.uuid}')
+                provider = self.provider_dict.get(llm_model.provider_uuid)
+                if provider is None:
+                    self.ap.logger.warning(f'Provider {llm_model.provider_uuid} not found for model {llm_model.uuid}')
+                    continue
+                runtime_llm_model = await self.load_llm_model_with_provider(llm_model, provider)
+                self.llm_models.append(runtime_llm_model)
             except Exception as e:
                 self.ap.logger.error(f'Failed to load model {llm_model.uuid}: {e}\n{traceback.format_exc()}')
 
-        # embedding models
+        # Load embedding models
         result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
         embedding_models = result.all()
         for embedding_model in embedding_models:
             try:
-                await self.load_embedding_model(embedding_model)
-            except provider_errors.RequesterNotFoundError as e:
-                self.ap.logger.warning(
-                    f'Requester {e.requester_name} not found, skipping embedding model {embedding_model.uuid}'
-                )
+                provider = self.provider_dict.get(embedding_model.provider_uuid)
+                if provider is None:
+                    self.ap.logger.warning(
+                        f'Provider {embedding_model.provider_uuid} not found for model {embedding_model.uuid}'
+                    )
+                    continue
+                runtime_embedding_model = await self.load_embedding_model_with_provider(embedding_model, provider)
+                self.embedding_models.append(runtime_embedding_model)
             except Exception as e:
                 self.ap.logger.error(f'Failed to load model {embedding_model.uuid}: {e}\n{traceback.format_exc()}')
 
-    async def init_runtime_llm_model(
+    async def sync_new_models_from_space(self):
+        """Sync models from Space"""
+        space_model_provider = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.requester == 'space-chat-completions'
+            )
+        )
+        result = space_model_provider.first()
+        if result is None:
+            raise provider_errors.ProviderNotFoundError('LangBot Models')
+
+        space_model_provider = result
+
+        # get the latest models from space
+        space_models = await self.ap.space_service.get_models()
+
+        exists_llm_models_uuids = [m['uuid'] for m in await self.ap.llm_model_service.get_llm_models()]
+        exists_embedding_models_uuids = [
+            m['uuid'] for m in await self.ap.embedding_models_service.get_embedding_models()
+        ]
+
+        for space_model in space_models:
+            if space_model.category == 'chat':
+                uuid = space_model.uuid
+
+                if uuid in exists_llm_models_uuids:
+                    continue
+
+                # model will be automatically loaded
+                await self.ap.llm_model_service.create_llm_model(
+                    {
+                        'uuid': space_model.uuid,
+                        'name': space_model.model_id,
+                        'provider_uuid': space_model_provider.uuid,
+                        'abilities': space_model.llm_abilities or [],
+                        'extra_args': {},
+                        'prefered_ranking': space_model.featured_order,
+                    },
+                    preserve_uuid=True,
+                )
+
+            elif space_model.category == 'embedding':
+                uuid = space_model.uuid
+
+                if uuid in exists_embedding_models_uuids:
+                    continue
+
+                # model will be automatically loaded
+                await self.ap.embedding_models_service.create_embedding_model(
+                    {
+                        'uuid': space_model.uuid,
+                        'name': space_model.model_id,
+                        'provider_uuid': space_model_provider.uuid,
+                        'extra_args': {},
+                        'prefered_ranking': space_model.featured_order,
+                    },
+                    preserve_uuid=True,
+                )
+
+    async def init_temporary_runtime_llm_model(
         self,
-        model_info: persistence_model.LLMModel | sqlalchemy.Row[persistence_model.LLMModel] | dict,
-    ):
-        """初始化运行时 LLM 模型"""
-        if isinstance(model_info, sqlalchemy.Row):
-            model_info = persistence_model.LLMModel(**model_info._mapping)
-        elif isinstance(model_info, dict):
-            model_info = persistence_model.LLMModel(**model_info)
+        model_info: dict,
+    ) -> requester.RuntimeLLMModel:
+        """Initialize runtime LLM model from dict (for testing)"""
+        provider_info = model_info.get('provider', {})
 
-        if model_info.requester not in self.requester_dict:
-            raise provider_errors.RequesterNotFoundError(model_info.requester)
-
-        requester_inst = self.requester_dict[model_info.requester](ap=self.ap, config=model_info.requester_config)
-
-        await requester_inst.initialize()
+        runtime_provider = await self.load_provider(provider_info)
 
         runtime_llm_model = requester.RuntimeLLMModel(
-            model_entity=model_info,
-            token_mgr=token.TokenManager(
-                name=model_info.uuid,
-                tokens=model_info.api_keys,
+            model_entity=persistence_model.LLMModel(
+                uuid=model_info.get('uuid', ''),
+                name=model_info.get('name', ''),
+                provider_uuid='',
+                abilities=model_info.get('abilities', []),
+                extra_args=model_info.get('extra_args', {}),
             ),
-            requester=requester_inst,
+            provider=runtime_provider,
         )
 
         return runtime_llm_model
 
-    async def init_runtime_embedding_model(
+    async def init_temporary_runtime_embedding_model(
         self,
-        model_info: persistence_model.EmbeddingModel | sqlalchemy.Row[persistence_model.EmbeddingModel] | dict,
-    ):
-        """初始化运行时 Embedding 模型"""
-        if isinstance(model_info, sqlalchemy.Row):
-            model_info = persistence_model.EmbeddingModel(**model_info._mapping)
-        elif isinstance(model_info, dict):
-            model_info = persistence_model.EmbeddingModel(**model_info)
-
-        if model_info.requester not in self.requester_dict:
-            raise provider_errors.RequesterNotFoundError(model_info.requester)
-
-        requester_inst = self.requester_dict[model_info.requester](ap=self.ap, config=model_info.requester_config)
-
-        await requester_inst.initialize()
+        model_info: dict,
+    ) -> requester.RuntimeEmbeddingModel:
+        """Initialize runtime embedding model from dict (for testing)"""
+        provider_info = model_info.get('provider', {})
+        runtime_provider = await self.load_provider(provider_info)
 
         runtime_embedding_model = requester.RuntimeEmbeddingModel(
-            model_entity=model_info,
-            token_mgr=token.TokenManager(
-                name=model_info.uuid,
-                tokens=model_info.api_keys,
+            model_entity=persistence_model.EmbeddingModel(
+                uuid=model_info.get('uuid', ''),
+                name=model_info.get('name', ''),
+                provider_uuid='',
+                extra_args=model_info.get('extra_args', {}),
             ),
-            requester=requester_inst,
+            provider=runtime_provider,
         )
 
         return runtime_embedding_model
 
-    async def load_llm_model(
-        self,
-        model_info: persistence_model.LLMModel | sqlalchemy.Row[persistence_model.LLMModel] | dict,
-    ):
-        """加载 LLM 模型"""
-        runtime_llm_model = await self.init_runtime_llm_model(model_info)
-        self.llm_models.append(runtime_llm_model)
+    async def load_provider(
+        self, provider_info: persistence_model.ModelProvider | sqlalchemy.Row | dict
+    ) -> requester.RuntimeProvider:
+        """Load provider from dict"""
+        if isinstance(provider_info, sqlalchemy.Row):
+            provider_entity = persistence_model.ModelProvider(**provider_info._mapping)
+        elif isinstance(provider_info, dict):
+            provider_entity = persistence_model.ModelProvider(**provider_info)
+        else:
+            provider_entity = provider_info
 
-    async def load_embedding_model(
-        self,
-        model_info: persistence_model.EmbeddingModel | sqlalchemy.Row[persistence_model.EmbeddingModel] | dict,
-    ):
-        """加载 Embedding 模型"""
-        runtime_embedding_model = await self.init_runtime_embedding_model(model_info)
-        self.embedding_models.append(runtime_embedding_model)
+        if provider_entity.requester not in self.requester_dict:
+            raise provider_errors.RequesterNotFoundError(provider_entity.requester)
 
+        requester_inst = self.requester_dict[provider_entity.requester](
+            ap=self.ap, config={'base_url': provider_entity.base_url}
+        )
+        await requester_inst.initialize()
+
+        token_mgr = token.TokenManager(name=provider_entity.uuid, tokens=provider_entity.api_keys or [])
+
+        provider = requester.RuntimeProvider(
+            provider_entity=provider_entity,
+            token_mgr=token_mgr,
+            requester=requester_inst,
+        )
+        return provider
+
+    async def remove_provider(self, provider_uuid: str):
+        """Remove provider
+
+        This method will not consider the models using this provider,
+        because the models should be removed by the caller.
+        """
+        del self.provider_dict[provider_uuid]
+
+    async def reload_provider(self, provider_uuid: str):
+        """Reload provider"""
+        provider_entity = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_model.ModelProvider).where(
+                persistence_model.ModelProvider.uuid == provider_uuid
+            )
+        )
+        provider_entity = provider_entity.first()
+        if provider_entity is None:
+            raise provider_errors.ProviderNotFoundError(provider_uuid)
+
+        new_runtime_provider = await self.load_provider(provider_entity)
+
+        # update refs in runtime models
+        for model in self.llm_models:
+            if model.provider.provider_entity.uuid == provider_uuid:
+                model.provider = new_runtime_provider
+        for model in self.embedding_models:
+            if model.provider.provider_entity.uuid == provider_uuid:
+                model.provider = new_runtime_provider
+
+        # update ref in provider dict
+        self.provider_dict[provider_uuid] = new_runtime_provider
+
+    async def load_llm_model_with_provider(
+        self,
+        model_info: persistence_model.LLMModel | sqlalchemy.Row,
+        provider: requester.RuntimeProvider,
+    ) -> requester.RuntimeLLMModel:
+        """Load LLM model with provider info"""
+        if isinstance(model_info, sqlalchemy.Row):
+            model_info = persistence_model.LLMModel(**model_info._mapping)
+
+        runtime_llm_model = requester.RuntimeLLMModel(
+            model_entity=model_info,
+            provider=provider,
+        )
+
+        return runtime_llm_model
+
+    async def load_embedding_model_with_provider(
+        self,
+        model_info: persistence_model.EmbeddingModel | sqlalchemy.Row,
+        provider: requester.RuntimeProvider,
+    ) -> requester.RuntimeEmbeddingModel:
+        """Load embedding model with provider info"""
+        if isinstance(model_info, sqlalchemy.Row):
+            model_info = persistence_model.EmbeddingModel(**model_info._mapping)
+
+        runtime_embedding_model = requester.RuntimeEmbeddingModel(
+            model_entity=model_info,
+            provider=provider,
+        )
+
+        return runtime_embedding_model
+
+    async def load_llm_model(self, model_info: dict):
+        """Load LLM model from dict (with provider info)"""
+        provider_info = model_info.get('provider', {})
+        if not provider_info:
+            raise ValueError('Provider info is required')
+
+        model_entity = persistence_model.LLMModel(
+            uuid=model_info.get('uuid', ''),
+            name=model_info.get('name', ''),
+            provider_uuid=model_info.get('provider_uuid', ''),
+            abilities=model_info.get('abilities', []),
+            extra_args=model_info.get('extra_args', {}),
+        )
+
+        provider_entity = persistence_model.ModelProvider(
+            uuid=provider_info.get('uuid', ''),
+            name=provider_info.get('name', ''),
+            requester=provider_info.get('requester', ''),
+            base_url=provider_info.get('base_url', ''),
+            api_keys=provider_info.get('api_keys', []),
+        )
+
+        await self.load_llm_model_with_provider(model_entity, provider_entity)
+
+    async def load_embedding_model(self, model_info: dict):
+        """Load embedding model from dict (with provider info)"""
+        provider_info = model_info.get('provider', {})
+        if not provider_info:
+            raise ValueError('Provider info is required')
+
+        model_entity = persistence_model.EmbeddingModel(
+            uuid=model_info.get('uuid', ''),
+            name=model_info.get('name', ''),
+            provider_uuid=model_info.get('provider_uuid', ''),
+            extra_args=model_info.get('extra_args', {}),
+        )
+
+        provider_entity = persistence_model.ModelProvider(
+            uuid=provider_info.get('uuid', ''),
+            name=provider_info.get('name', ''),
+            requester=provider_info.get('requester', ''),
+            base_url=provider_info.get('base_url', ''),
+            api_keys=provider_info.get('api_keys', []),
+        )
+
+        await self.load_embedding_model_with_provider(model_entity, provider_entity)
+
+    @alru_cache(ttl=60 * 5)
     async def get_model_by_uuid(self, uuid: str) -> requester.RuntimeLLMModel:
-        """通过uuid获取 LLM 模型"""
+        """Get LLM model by uuid"""
         for model in self.llm_models:
             if model.model_entity.uuid == uuid:
                 return model
         raise ValueError(f'LLM model {uuid} not found')
 
+    @alru_cache(ttl=60 * 5)
     async def get_embedding_model_by_uuid(self, uuid: str) -> requester.RuntimeEmbeddingModel:
-        """通过uuid获取 Embedding 模型"""
+        """Get embedding model by uuid"""
         for model in self.embedding_models:
             if model.model_entity.uuid == uuid:
                 return model
         raise ValueError(f'Embedding model {uuid} not found')
 
     async def remove_llm_model(self, model_uuid: str):
-        """移除 LLM 模型"""
+        """Remove LLM model"""
         for model in self.llm_models:
             if model.model_entity.uuid == model_uuid:
                 self.llm_models.remove(model)
                 return
 
     async def remove_embedding_model(self, model_uuid: str):
-        """移除 Embedding 模型"""
+        """Remove embedding model"""
         for model in self.embedding_models:
             if model.model_entity.uuid == model_uuid:
                 self.embedding_models.remove(model)
                 return
 
     def get_available_requesters_info(self, model_type: str) -> list[dict]:
-        """获取所有可用的请求器"""
+        """Get all available requesters"""
         if model_type != '':
             return [
                 component.to_plain_dict()
@@ -188,14 +392,14 @@ class ModelManager:
             return [component.to_plain_dict() for component in self.requester_components]
 
     def get_available_requester_info_by_name(self, name: str) -> dict | None:
-        """通过名称获取请求器信息"""
+        """Get requester info by name"""
         for component in self.requester_components:
             if component.metadata.name == name:
                 return component.to_plain_dict()
         return None
 
     def get_available_requester_manifest_by_name(self, name: str) -> engine.Component | None:
-        """通过名称获取请求器清单"""
+        """Get requester manifest by name"""
         for component in self.requester_components:
             if component.metadata.name == name:
                 return component

src/langbot/pkg/provider/modelmgr/requester.py

@@ -11,11 +11,11 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
-class RuntimeLLMModel:
-    """运行时模型"""
+class RuntimeProvider:
+    """运行时模型提供商"""
 
-    model_entity: persistence_model.LLMModel
-    """模型数据"""
+    provider_entity: persistence_model.ModelProvider
+    """提供商数据"""
 
     token_mgr: token.TokenManager
     """api key管理器"""
@@ -25,36 +25,49 @@ class RuntimeLLMModel:
 
     def __init__(
         self,
-        model_entity: persistence_model.LLMModel,
+        provider_entity: persistence_model.ModelProvider,
         token_mgr: token.TokenManager,
         requester: ProviderAPIRequester,
     ):
-        self.model_entity = model_entity
+        self.provider_entity = provider_entity
         self.token_mgr = token_mgr
         self.requester = requester
 
 
+class RuntimeLLMModel:
+    """运行时模型"""
+
+    model_entity: persistence_model.LLMModel
+    """模型数据"""
+
+    provider: RuntimeProvider
+    """提供商实例"""
+
+    def __init__(
+        self,
+        model_entity: persistence_model.LLMModel,
+        provider: RuntimeProvider,
+    ):
+        self.model_entity = model_entity
+        self.provider = provider
+
+
 class RuntimeEmbeddingModel:
     """运行时 Embedding 模型"""
 
     model_entity: persistence_model.EmbeddingModel
     """模型数据"""
 
-    token_mgr: token.TokenManager
-    """api key管理器"""
-
-    requester: ProviderAPIRequester
-    """请求器实例"""
+    provider: RuntimeProvider
+    """提供商实例"""
 
     def __init__(
         self,
         model_entity: persistence_model.EmbeddingModel,
-        token_mgr: token.TokenManager,
-        requester: ProviderAPIRequester,
+        provider: RuntimeProvider,
     ):
         self.model_entity = model_entity
-        self.token_mgr = token_mgr
-        self.requester = requester
+        self.provider = provider
 
 
 class ProviderAPIRequester(metaclass=abc.ABCMeta):

src/langbot/pkg/provider/modelmgr/requesters/anthropicmsgs.py

@@ -56,7 +56,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = model.token_mgr.get_token()
+        self.client.api_key = model.provider.token_mgr.get_token()
 
         args = extra_args.copy()
         args['model'] = model.model_entity.name
@@ -190,7 +190,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = model.token_mgr.get_token()
+        self.client.api_key = model.provider.token_mgr.get_token()
 
         args = extra_args.copy()
         args['model'] = model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/bailianchatcmpl.py

@@ -30,7 +30,7 @@ class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name
@@ -117,7 +117,7 @@ class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
         if is_use_dashscope_call:
             response = dashscope.MultiModalConversation.call(
                 # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
-                api_key=use_model.token_mgr.get_token(),
+                api_key=use_model.provider.token_mgr.get_token(),
                 model=use_model.model_entity.name,
                 messages=messages,
                 result_format='message',

src/langbot/pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -4,7 +4,7 @@ import asyncio
 import typing
 
 import openai
-import openai.types.chat.chat_completion as chat_completion
+import openai.types.chat.chat_completion as chat_completion_module
 import httpx
 
 from .. import errors, requester
@@ -35,7 +35,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         self,
         args: dict,
         extra_body: dict = {},
-    ) -> chat_completion.ChatCompletion:
+    ) -> chat_completion_module.ChatCompletion:
         return await self.client.chat.completions.create(**args, extra_body=extra_body)
 
     async def _req_stream(
@@ -48,9 +48,12 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
 
     async def _make_msg(
         self,
-        chat_completion: chat_completion.ChatCompletion,
+        chat_completion: chat_completion_module.ChatCompletion,
         remove_think: bool = False,
     ) -> provider_message.Message:
+        if not isinstance(chat_completion, chat_completion_module.ChatCompletion):
+            raise TypeError(f'Expected ChatCompletion, got {type(chat_completion).__name__}: {chat_completion[:16]}')
+
         chatcmpl_message = chat_completion.choices[0].message.model_dump()
 
         # 确保 role 字段存在且不为 None
@@ -130,7 +133,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.MessageChunk:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name
@@ -251,7 +254,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name
@@ -337,7 +340,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
     ) -> list[list[float]]:
         """调用 Embedding API"""
-        self.client.api_key = model.token_mgr.get_token()
+        self.client.api_key = model.provider.token_mgr.get_token()
 
         args = {
             'model': model.model_entity.name,

src/langbot/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py

@@ -26,7 +26,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/geminichatcmpl.py

@@ -29,7 +29,7 @@ class GeminiChatCompletions(chatcmpl.OpenAIChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.MessageChunk:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/jiekouaichatcmpl.py

@@ -109,7 +109,7 @@ class JieKouAIChatCompletions(chatcmpl.OpenAIChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -131,7 +131,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name
@@ -181,7 +181,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py

@@ -27,7 +27,7 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/ppiochatcmpl.py

@@ -109,7 +109,7 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
         extra_args: dict[str, typing.Any] = {},
         remove_think: bool = False,
     ) -> provider_message.Message | typing.AsyncGenerator[provider_message.MessageChunk, None]:
-        self.client.api_key = use_model.token_mgr.get_token()
+        self.client.api_key = use_model.provider.token_mgr.get_token()
 
         args = {}
         args['model'] = use_model.model_entity.name

src/langbot/pkg/provider/modelmgr/requesters/seekdb.svg

@@ -0,0 +1,8 @@
+<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <rect width="24" height="24" rx="5" fill="#1E3A5F"/>
+  <path d="M6 12C6 8.68629 8.68629 6 12 6C15.3137 6 18 8.68629 18 12" stroke="#4FC3F7" stroke-width="2" stroke-linecap="round"/>
+  <path d="M18 12C18 15.3137 15.3137 18 12 18C8.68629 18 6 15.3137 6 12" stroke="#81D4FA" stroke-width="2" stroke-linecap="round"/>
+  <circle cx="12" cy="12" r="2" fill="#4FC3F7"/>
+  <circle cx="6" cy="12" r="1.5" fill="#81D4FA"/>
+  <circle cx="18" cy="12" r="1.5" fill="#4FC3F7"/>
+</svg>

src/langbot/pkg/provider/modelmgr/requesters/seekdbembed.py

@@ -0,0 +1,59 @@
+from __future__ import annotations
+
+import typing
+
+from .. import requester
+
+REQUESTER_NAME: str = 'seekdb-embedding'
+
+
+class SeekDBEmbedding(requester.ProviderAPIRequester):
+    """SeekDB built-in embedding requester.
+
+    Uses pyseekdb's local embedding function (all-MiniLM-L6-v2).
+    The base_url config is reserved for future remote embedding support.
+    """
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': '',
+    }
+
+    _embedding_function = None
+
+    async def initialize(self):
+        try:
+            import pyseekdb
+        except ImportError:
+            raise ImportError('pyseekdb is not installed. Install it with: pip install pyseekdb')
+
+        self._embedding_function = pyseekdb.get_default_embedding_function()
+
+    async def invoke_llm(
+        self,
+        query,
+        model: requester.RuntimeLLMModel,
+        messages: typing.List,
+        funcs: typing.List = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ):
+        raise NotImplementedError('SeekDB embedding does not support LLM inference')
+
+    async def invoke_embedding(
+        self,
+        model: requester.RuntimeEmbeddingModel,
+        input_text: typing.List[str],
+        extra_args: dict[str, typing.Any] = {},
+    ) -> typing.List[typing.List[float]]:
+        """Generate embeddings using SeekDB's built-in embedding function."""
+        try:
+            if self._embedding_function is None:
+                await self.initialize()
+
+            if self._embedding_function is None:
+                raise RuntimeError("SeekDB embedding function initialization failed")
+
+            return self._embedding_function(input_text)
+        except Exception as e:
+            from .. import errors
+            raise errors.RequesterError(f'SeekDB embedding failed: {str(e)}')

src/langbot/pkg/provider/modelmgr/requesters/seekdbembed.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: seekdb-embedding
+  label:
+    en_US: SeekDB Embedding
+    zh_Hans: SeekDB 嵌入
+  description:
+    en_US: SeekDB Python library built-in embedding model (all-MiniLM-L6-v2), it will take time to download the model file for the first time
+    zh_Hans: 使用来自 SeekDB Python 库的内置嵌入模型 (all-MiniLM-L6-v2)，首次使用时将会花费时间自动下载模型文件
+    ja_JP: SeekDB Python ライブラリの組み込み埋め込みモデル (all-MiniLM-L6-v2) を使用します。初回使用時にモデルファイルのダウンロードに時間がかかります。
+  icon: seekdb.svg
+spec:
+  config: []
+  support_type:
+  - text-embedding
+  provider_category: builtin
+execution:
+  python:
+    path: ./seekdbembed.py
+    attr: SeekDBEmbedding

src/langbot/pkg/provider/modelmgr/requesters/spacechatcmpl.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+import typing
+import openai
+
+from . import chatcmpl
+
+
+class LangBotSpaceChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """LangBot Space ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'https://api.langbot.cloud/v1',
+        'timeout': 120,
+    }

src/langbot/pkg/provider/modelmgr/requesters/spacechatcmpl.yaml

@@ -0,0 +1,32 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: space-chat-completions
+  label:
+    en_US: Space
+    zh_Hans: Space
+  icon: space.webp
+spec:
+  config:
+  - name: base_url
+    label:
+      en_US: Base URL
+      zh_Hans: 基础 URL
+    type: string
+    required: true
+    default: https://api.langbot.cloud/v1
+  - name: timeout
+    label:
+      en_US: Timeout
+      zh_Hans: 超时时间
+    type: integer
+    required: true
+    default: 120
+  support_type:
+  - llm
+  - text-embedding
+  provider_category: maas
+execution:
+  python:
+    path: ./spacechatcmpl.py
+    attr: LangBotSpaceChatCompletions

src/langbot/pkg/provider/modelmgr/token.py

@@ -18,6 +18,8 @@ class TokenManager:
         self.using_token_index = 0
 
     def get_token(self) -> str:
+        if len(self.tokens) == 0:
+            return ''
         return self.tokens[self.using_token_index]
 
     def next_token(self):

src/langbot/pkg/provider/runners/difysvapi.py

@@ -152,7 +152,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         self, query: pipeline_query.Query
     ) -> typing.AsyncGenerator[provider_message.Message, None]:
         """调用聊天助手"""
-        cov_id = query.session.using_conversation.uuid or ''
+        cov_id = query.session.using_conversation.uuid or None
         query.variables['conversation_id'] = cov_id
 
         plain_text, upload_files = await self._preprocess_user_message(query)
@@ -218,7 +218,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         self, query: pipeline_query.Query
     ) -> typing.AsyncGenerator[provider_message.Message, None]:
         """调用聊天助手"""
-        cov_id = query.session.using_conversation.uuid or ''
+        cov_id = query.session.using_conversation.uuid or None
         query.variables['conversation_id'] = cov_id
 
         plain_text, upload_files = await self._preprocess_user_message(query)
@@ -387,7 +387,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         self, query: pipeline_query.Query
     ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
         """调用聊天助手"""
-        cov_id = query.session.using_conversation.uuid or ''
+        cov_id = query.session.using_conversation.uuid or None
         query.variables['conversation_id'] = cov_id
 
         plain_text, upload_files = await self._preprocess_user_message(query)
@@ -471,7 +471,7 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         self, query: pipeline_query.Query
     ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
         """调用聊天助手"""
-        cov_id = query.session.using_conversation.uuid or ''
+        cov_id = query.session.using_conversation.uuid or None
         query.variables['conversation_id'] = cov_id
 
         plain_text, upload_files = await self._preprocess_user_message(query)

src/langbot/pkg/provider/runners/localagent.py

@@ -130,7 +130,7 @@ class LocalAgentRunner(runner.RequestRunner):
         if not is_stream:
             # 非流式输出，直接请求
 
-            msg = await use_llm_model.requester.invoke_llm(
+            msg = await use_llm_model.provider.requester.invoke_llm(
                 query,
                 use_llm_model,
                 req_messages,
@@ -147,7 +147,7 @@ class LocalAgentRunner(runner.RequestRunner):
             accumulated_content = ''  # 从开始累积的所有内容
             last_role = 'assistant'
             msg_sequence = 1
-            async for msg in use_llm_model.requester.invoke_llm_stream(
+            async for msg in use_llm_model.provider.requester.invoke_llm_stream(
                 query,
                 use_llm_model,
                 req_messages,
@@ -250,7 +250,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 last_role = 'assistant'
                 msg_sequence = first_end_sequence
 
-                async for msg in use_llm_model.requester.invoke_llm_stream(
+                async for msg in use_llm_model.provider.requester.invoke_llm_stream(
                     query,
                     use_llm_model,
                     req_messages,
@@ -306,7 +306,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 )
             else:
                 # 处理完所有调用，再次请求
-                msg = await use_llm_model.requester.invoke_llm(
+                msg = await use_llm_model.provider.requester.invoke_llm(
                     query,
                     use_llm_model,
                     req_messages,

src/langbot/pkg/provider/runners/n8nsvapi.py

@@ -70,30 +70,88 @@ class N8nServiceAPIRunner(runner.RequestRunner):
 
     async def _process_stream_response(self, response: aiohttp.ClientResponse) -> typing.AsyncGenerator[
         provider_message.Message, None]:
-        """处理流式响应"""
+        """处理流式响应——支持部分 JSON 和多个 JSON 对象在同一 chunk 的情况"""
         full_content = ""
-        message_idx = 0
+        chunk_idx = 0
         is_final = False
-        async for chunk in response.content.iter_chunked(1024):
-            if not chunk:
+        message_idx = 0
+
+        buffer = ""
+        decoder = json.JSONDecoder()
+
+        async for raw_chunk in response.content.iter_chunked(1024):
+            if not raw_chunk:
                 continue
 
             try:
-                data = json.loads(chunk)
-                if data.get('type') == 'item' and 'content' in data:
+                # 将 bytes 解码为字符串（容忍错误）
+                if isinstance(raw_chunk, (bytes, bytearray)):
+                    chunk_str = raw_chunk.decode('utf-8', errors='replace')
+                else:
+                    chunk_str = str(raw_chunk)
+
+                buffer += chunk_str
+
+                # 尝试从 buffer 中循环解析出 JSON 对象（处理多个对象或部分对象）
+                while buffer:
+                    buffer = buffer.lstrip()
+                    if not buffer:
+                        break
+                    try:
+                        obj, idx = decoder.raw_decode(buffer)
+                        buffer = buffer[idx:]
+
+                        if not isinstance(obj, dict):
+                            # 忽略非字典类型的顶级 JSON
+                            continue
+
+                        if obj.get('type') == 'item' and 'content' in obj:
+                            chunk_idx += 1
+                            content = obj['content']
+                            full_content += content
+                        elif obj.get('type') == 'end':
+                            is_final = True
+
+                        if is_final or chunk_idx % 8 == 0:
+                            message_idx += 1
+                            yield provider_message.MessageChunk(
+                                role='assistant',
+                                content=full_content,
+                                is_final=is_final,
+                                msg_sequence=message_idx,
+                            )
+                    except json.JSONDecodeError:
+                        # buffer 末尾可能是一个不完整的 JSON，等待更多数据
+                        break
+            except Exception as e:
+                # 记录解析失败并继续接收后续 chunk
+                try:
+                    preview = chunk_str[:200]
+                except Exception:
+                    preview = '<unavailable>'
+                self.ap.logger.warning(f"Failed to process chunk: {e}; chunk preview: {preview}")
+
+        # 流结束后，尝试解析残余 buffer
+        if buffer:
+            try:
+                buffer = buffer.strip()
+                if buffer:
+                    obj, _ = decoder.raw_decode(buffer)
+                    if isinstance(obj, dict):
+                        if obj.get('type') == 'item' and 'content' in obj:
+                            full_content += obj['content']
+                        elif obj.get('type') == 'end':
+                            is_final = True
                     message_idx += 1
-                    content = data['content']
-                    full_content += content
-                elif data.get('type') == 'end':
-                    is_final = True
-                if is_final or message_idx % 8 == 0:
                     yield provider_message.MessageChunk(
                         role='assistant',
                         content=full_content,
                         is_final=is_final,
+                        msg_sequence=message_idx,
                     )
-            except json.JSONDecodeError:
-                self.ap.logger.warning(f"Failed to parse final JSON line: {response.text()}")
+            except Exception as e:
+                preview = buffer[:200]
+                self.ap.logger.warning(f"Failed to parse remaining buffer: {e}; buffer preview: {preview}")
 
     async def _call_webhook(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
         """调用n8n webhook"""

src/langbot/pkg/provider/tools/loaders/mcp.py

@@ -7,7 +7,7 @@ import traceback
 from langbot_plugin.api.entities.events import pipeline_query
 import sqlalchemy
 import asyncio
-
+import uuid as uuid_module
 from mcp import ClientSession, StdioServerParameters
 from mcp.client.stdio import stdio_client
 from mcp.client.sse import sse_client
@@ -287,6 +287,14 @@ class MCPLoader(loader.ToolLoader):
                 - enable: 是否启用
                 - extra_args: 额外的配置参数 (可选)
         """
+        uuid_ = server_config.get('uuid')
+        if not uuid_:
+            self.ap.logger.warning(
+                'Server UUID is None for MCP server, maybe testing in the config page.'
+            )
+            uuid_ = str(uuid_module.uuid4())
+            server_config['uuid'] = uuid_
+
 
         name = server_config['name']
         uuid = server_config['uuid']

src/langbot/pkg/rag/knowledge/services/embedder.py

@@ -32,12 +32,18 @@ class Embedder(BaseService):
 
         await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.Chunk).values(chunk_dicts))
 
-        # get embeddings
-        embeddings_list: list[list[float]] = await embedding_model.requester.invoke_embedding(
-            model=embedding_model,
-            input_text=chunks,
-            extra_args={},  # TODO: add extra args
-        )
+        # get embeddings (batch size limit: 64 for OpenAI)
+        MAX_BATCH_SIZE = 64
+        embeddings_list: list[list[float]] = []
+        
+        for i in range(0, len(chunks), MAX_BATCH_SIZE):
+            batch = chunks[i:i + MAX_BATCH_SIZE]
+            batch_embeddings = await embedding_model.provider.requester.invoke_embedding(
+                model=embedding_model,
+                input_text=batch,
+                extra_args={},  # TODO: add extra args
+            )
+            embeddings_list.extend(batch_embeddings)
 
         # save embeddings to vdb
         await self.ap.vector_db_mgr.vector_db.add_embeddings(kb_id, chunk_ids, embeddings_list, chunk_dicts)

src/langbot/pkg/rag/knowledge/services/retriever.py

@@ -19,7 +19,7 @@ class Retriever(base_service.BaseService):
             f"Retrieving for query: '{query[:10]}' with k={k} using {embedding_model.model_entity.uuid}"
         )
 
-        query_embedding: list[float] = await embedding_model.requester.invoke_embedding(
+        query_embedding: list[float] = await embedding_model.provider.requester.invoke_embedding(
             model=embedding_model,
             input_text=[query],
             extra_args={},  # TODO: add extra args

src/langbot/pkg/telemetry/telemetry.py

@@ -0,0 +1,121 @@
+from __future__ import annotations
+
+import asyncio
+import httpx
+from ..core import app as core_app
+
+
+class TelemetryManager:
+    """TelemetryManager handles sending telemetry for a given application instance.
+
+    Usage:
+        telemetry = TelemetryManager(ap)
+        await telemetry.send({ ... })
+    """
+
+    send_tasks: list[asyncio.Task] = []
+
+    def __init__(self, ap: core_app.Application):
+        self.ap = ap
+
+        self.telemetry_config = {}
+
+    async def initialize(self):
+        self.telemetry_config = self.ap.instance_config.data.get('space', {})
+
+    async def start_send_task(self, payload: dict):
+        task = asyncio.create_task(self.send(payload))
+        self.send_tasks.append(task)
+
+    async def send(self, payload: dict):
+        """Send telemetry payload to configured telemetry server (non-blocking).
+
+        Expects ap.instance_config.data.telemetry to have:
+          - enabled: bool
+          - server: str (base URL, e.g. https://space.example.com)
+          - timeout_seconds: optional int, overall request timeout (default 10)
+
+        Posts to {server.rstrip('/')}/api/v1/telemetry as JSON. Failures are logged but do not raise.
+        """
+
+        try:
+            cfg = self.telemetry_config
+            if not cfg:
+                return
+            if cfg.get('disable_telemetry', False):
+                return
+            server = cfg.get('url', '')
+            if not server:
+                return
+
+            # Normalize URL
+            url = server.rstrip('/') + '/api/v1/telemetry'
+
+            try:
+                # Sanitize payload so string fields are strings and not nulls
+                sanitized = dict(payload)
+                if 'query_id' in sanitized:
+                    try:
+                        sanitized['query_id'] = '' if sanitized['query_id'] is None else str(sanitized['query_id'])
+                    except Exception:
+                        sanitized['query_id'] = str(sanitized.get('query_id', ''))
+
+                for sfield in ('adapter', 'runner', 'model_name', 'version', 'error', 'timestamp'):
+                    v = sanitized.get(sfield)
+                    sanitized[sfield] = '' if v is None else str(v)
+
+                if 'duration_ms' in sanitized:
+                    try:
+                        sanitized['duration_ms'] = (
+                            int(sanitized['duration_ms']) if sanitized['duration_ms'] is not None else 0
+                        )
+                    except Exception:
+                        sanitized['duration_ms'] = 0
+
+                async with httpx.AsyncClient(timeout=httpx.Timeout(10)) as client:
+                    try:
+                        # Use asyncio.wait_for to ensure we always bound the total time
+                        resp = await asyncio.wait_for(client.post(url, json=sanitized), timeout=10 + 1)
+
+                        if resp.status_code >= 400:
+                            self.ap.logger.warning(
+                                f'Telemetry post to {url} returned status {resp.status_code} - {resp.text}'
+                            )
+                        else:
+                            # Detect application-level errors inside HTTP 200 responses
+                            app_err = False
+                            try:
+                                j = resp.json()
+                                if isinstance(j, dict) and j.get('code') is not None and int(j.get('code')) >= 400:
+                                    app_err = True
+                                    self.ap.logger.warning(
+                                        f'Telemetry post to {url} returned application error code {j.get("code")} - {j.get("msg")}'
+                                    )
+                            except Exception:
+                                pass
+
+                            if app_err:
+                                self.ap.logger.warning(
+                                    f'Telemetry post to {url} returned app-level error - response: {resp.text[:200]}'
+                                )
+                            else:
+                                self.ap.logger.debug(
+                                    f'Telemetry posted to {url}, status {resp.status_code} - response: {resp.text[:200]}'
+                                )
+                    except asyncio.TimeoutError:
+                        self.ap.logger.warning(f'Telemetry post to {url} timed out')
+                    except Exception as e:
+                        self.ap.logger.warning(f'Failed to post telemetry to {url}: {e}', exc_info=True)
+            except Exception as e:
+                try:
+                    self.ap.logger.warning(
+                        f'Failed to create HTTP client for telemetry or sanitize payload: {e}', exc_info=True
+                    )
+                except Exception:
+                    pass
+        except Exception as e:
+            # Never raise from telemetry; surface as warning for visibility
+            try:
+                self.ap.logger.warning(f'Unexpected telemetry error: {e}', exc_info=True)
+            except Exception:
+                pass

src/langbot/pkg/utils/constants.py

@@ -2,9 +2,11 @@ import langbot
 
 semantic_version = f'v{langbot.__version__}'
 
-required_database_version = 13
+required_database_version = 17
 """Tag the version of the database schema, used to check if the database needs to be migrated"""
 
 debug_mode = False
 
 edition = 'community'
+
+instance_id = ''

src/langbot/pkg/utils/image.py

@@ -153,7 +153,9 @@ async def get_qq_image_bytes(image_url: str, query: dict = {}) -> tuple[bytes, s
     ssl_context.check_hostname = False
     ssl_context.verify_mode = ssl.CERT_NONE
     async with aiohttp.ClientSession(trust_env=False) as session:
-        async with session.get(image_url, params=query, ssl=ssl_context) as resp:
+        async with session.get(
+            image_url, params=query, ssl=ssl_context, timeout=aiohttp.ClientTimeout(total=30.0)
+        ) as resp:
             resp.raise_for_status()
             file_bytes = await resp.read()
             content_type = resp.headers.get('Content-Type')

src/langbot/pkg/vector/mgr.py

@@ -4,6 +4,7 @@ from ..core import app
 from .vdb import VectorDatabase
 from .vdbs.chroma import ChromaVectorDatabase
 from .vdbs.qdrant import QdrantVectorDatabase
+from .vdbs.seekdb import SeekDBVectorDatabase
 from .vdbs.milvus import MilvusVectorDatabase
 from .vdbs.pgvector_db import PgVectorDatabase
 
@@ -27,13 +28,17 @@ class VectorDBManager:
             elif vdb_type == 'qdrant':
                 self.vector_db = QdrantVectorDatabase(self.ap)
                 self.ap.logger.info('Initialized Qdrant vector database backend.')
+            elif vdb_type == 'seekdb':
+                self.vector_db = SeekDBVectorDatabase(self.ap)
+                self.ap.logger.info('Initialized SeekDB vector database backend.')
 
             elif vdb_type == 'milvus':
                 # Get Milvus configuration
                 milvus_config = kb_config.get('milvus', {})
                 uri = milvus_config.get('uri', './data/milvus.db')
                 token = milvus_config.get('token')
-                self.vector_db = MilvusVectorDatabase(self.ap, uri=uri, token=token)
+                db_name = milvus_config.get('db_name', 'default')
+                self.vector_db = MilvusVectorDatabase(self.ap, uri=uri, token=token, db_name=db_name)
                 self.ap.logger.info('Initialized Milvus vector database backend.')
 
             elif vdb_type == 'pgvector':

src/langbot/pkg/vector/vdbs/__init__.py

@@ -0,0 +1,7 @@
+"""Vector database implementations for LangBot."""
+
+from .chroma import ChromaVectorDatabase
+from .qdrant import QdrantVectorDatabase
+from .seekdb import SeekDBVectorDatabase
+
+__all__ = ['ChromaVectorDatabase', 'QdrantVectorDatabase', 'SeekDBVectorDatabase']

src/langbot/pkg/vector/vdbs/milvus.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 import asyncio
 from typing import Any, Dict
-from pymilvus import MilvusClient, DataType
+from pymilvus import MilvusClient, DataType, CollectionSchema, FieldSchema
+from pymilvus.milvus_client.index import IndexParams
 from langbot.pkg.vector.vdb import VectorDatabase
 from langbot.pkg.core import app
 
@@ -9,7 +10,7 @@ from langbot.pkg.core import app
 class MilvusVectorDatabase(VectorDatabase):
     """Milvus vector database implementation"""
 
-    def __init__(self, ap: app.Application, uri: str = "milvus.db", token: str = None):
+    def __init__(self, ap: app.Application, uri: str = "milvus.db", token: str = None, db_name: str = None):
         """Initialize Milvus vector database
 
         Args:
@@ -21,30 +22,76 @@ class MilvusVectorDatabase(VectorDatabase):
         self.ap = ap
         self.uri = uri
         self.token = token
+        self.db_name = db_name
         self.client = None
-        self._collections = {}
+        self._collections: set[str] = set()
         self._initialize_client()
 
     def _initialize_client(self):
         """Initialize Milvus client connection"""
         try:
             if self.token:
-                self.client = MilvusClient(uri=self.uri, token=self.token)
+                self.client = MilvusClient(uri=self.uri, token=self.token, db_name=self.db_name)
             else:
-                self.client = MilvusClient(uri=self.uri)
+                self.client = MilvusClient(uri=self.uri, db_name=self.db_name)
             self.ap.logger.info(f"Connected to Milvus at {self.uri}")
         except Exception as e:
             self.ap.logger.error(f"Failed to connect to Milvus: {e}")
             raise
 
-    async def get_or_create_collection(self, collection: str):
-        """Get or create a Milvus collection
+    @staticmethod
+    def _normalize_collection_name(collection: str) -> str:
+        """Normalize collection name to comply with Milvus naming requirements.
+        
+        Milvus requirements:
+        - First character must be an underscore or letter
+        - Can only contain numbers, letters and underscores
+        
+        Args:
+            collection: Original collection name (e.g., UUID with hyphens)
+            
+        Returns:
+            Normalized collection name that complies with Milvus requirements
+        """
+        # Replace hyphens with underscores
+        normalized = collection.replace('-', '_')
+        
+        # If first character is not a letter or underscore, prepend 'kb_'
+        if normalized and not (normalized[0].isalpha() or normalized[0] == '_'):
+            normalized = 'kb_' + normalized
+            
+        return normalized
+
+    async def _ensure_vector_index(self, collection: str) -> None:
+        """Ensure the vector field has an index.
+
+        Args:
+            collection: Normalized collection name
+        """
+        index_params = IndexParams()
+        index_params.add_index(
+            field_name="vector",
+            index_type="AUTOINDEX",
+            metric_type="COSINE",
+        )
+        await asyncio.to_thread(
+            self.client.create_index,
+            collection_name=collection,
+            index_params=index_params
+        )
+
+    async def _get_or_create_collection_internal(self, collection: str, vector_size: int = None):
+        """Internal method to get or create a Milvus collection with proper configuration.
 
         Args:
             collection: Collection name (corresponds to knowledge base UUID)
+            vector_size: Dimension of the vectors (if None, defaults to 1536)
         """
+        # Normalize collection name for Milvus compatibility
+        collection = self._normalize_collection_name(collection)
+        
         if collection in self._collections:
-            return self._collections[collection]
+            return collection
 
         # Check if collection exists
         has_collection = await asyncio.to_thread(
@@ -52,12 +99,13 @@ class MilvusVectorDatabase(VectorDatabase):
         )
 
         if not has_collection:
-            # Create collection with custom schema to support string IDs
-            from pymilvus import CollectionSchema, FieldSchema, DataType
+            # Default dimension if not specified (for backward compatibility)
+            if vector_size is None:
+                vector_size = 1536
 
             fields = [
                 FieldSchema(name="id", dtype=DataType.VARCHAR, is_primary=True, max_length=255),
-                FieldSchema(name="vector", dtype=DataType.FLOAT_VECTOR, dim=1536),
+                FieldSchema(name="vector", dtype=DataType.FLOAT_VECTOR, dim=vector_size),
                 FieldSchema(name="text", dtype=DataType.VARCHAR, max_length=65535),
                 FieldSchema(name="file_id", dtype=DataType.VARCHAR, max_length=255),
                 FieldSchema(name="chunk_uuid", dtype=DataType.VARCHAR, max_length=255),
@@ -72,26 +120,42 @@ class MilvusVectorDatabase(VectorDatabase):
                 metric_type="COSINE",
             )
 
-            # Create index for vector field (required for loading/searching)
-            index_params = {
-                "metric_type": "COSINE",
-                "index_type": "AUTOINDEX",
-                "params": {}
-            }
-            await asyncio.to_thread(
-                self.client.create_index,
-                collection_name=collection,
-                field_name="vector",
-                index_params=index_params
-            )
-
-            self.ap.logger.info(f"Created Milvus collection '{collection}' with index")
+            await self._ensure_vector_index(collection)
+            self.ap.logger.info(f"Created Milvus collection '{collection}' with dimension={vector_size}, index=AUTOINDEX")
         else:
+            # Ensure index exists for existing collection
+            await self._ensure_index_if_missing(collection)
             self.ap.logger.info(f"Milvus collection '{collection}' already exists")
 
-        self._collections[collection] = collection
+        self._collections.add(collection)
         return collection
 
+    async def _ensure_index_if_missing(self, collection: str) -> None:
+        """Check if index exists for collection and create if missing.
+
+        Args:
+            collection: Normalized collection name
+        """
+        try:
+            indexes = await asyncio.to_thread(
+                self.client.list_indexes,
+                collection_name=collection
+            )
+            if "vector" not in indexes:
+                await self._ensure_vector_index(collection)
+                self.ap.logger.info(f"Created index for existing Milvus collection '{collection}'")
+        except Exception as e:
+            self.ap.logger.warning(f"Could not verify/create index for collection '{collection}': {e}")
+
+    async def get_or_create_collection(self, collection: str):
+        """Get or create a Milvus collection (without vector size - will use default).
+
+        Args:
+            collection: Collection name (corresponds to knowledge base UUID)
+        """
+        collection = self._normalize_collection_name(collection)
+        return await self._get_or_create_collection_internal(collection)
+
     async def add_embeddings(
         self,
         collection: str,
@@ -107,7 +171,14 @@ class MilvusVectorDatabase(VectorDatabase):
             embeddings_list: List of embedding vectors
             metadatas: List of metadata dictionaries for each vector
         """
-        await self.get_or_create_collection(collection)
+        collection = self._normalize_collection_name(collection)
+        
+        if not embeddings_list:
+            return
+
+        # Ensure collection exists with correct dimension
+        vector_size = len(embeddings_list[0])
+        await self._get_or_create_collection_internal(collection, vector_size)
 
         # Prepare data in Milvus format
         data = []
@@ -156,6 +227,7 @@ class MilvusVectorDatabase(VectorDatabase):
         Returns:
             Dictionary with search results in Chroma-compatible format
         """
+        collection = self._normalize_collection_name(collection)
         await self.get_or_create_collection(collection)
 
         # Perform search
@@ -214,6 +286,7 @@ class MilvusVectorDatabase(VectorDatabase):
             collection: Collection name
             file_id: File ID to filter deletion
         """
+        collection = self._normalize_collection_name(collection)
         await self.get_or_create_collection(collection)
 
         # Delete entities matching the file_id
@@ -232,8 +305,9 @@ class MilvusVectorDatabase(VectorDatabase):
         Args:
             collection: Collection name to delete
         """
-        if collection in self._collections:
-            del self._collections[collection]
+        collection = self._normalize_collection_name(collection)
+        
+        self._collections.discard(collection)
 
         # Check if collection exists before attempting deletion
         has_collection = await asyncio.to_thread(

src/langbot/pkg/vector/vdbs/seekdb.py

@@ -0,0 +1,252 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Any, Dict, List
+
+import sqlalchemy
+
+from langbot.pkg.core import app
+from langbot.pkg.entity.persistence import model as persistence_model
+from langbot.pkg.vector.vdb import VectorDatabase
+
+try:
+    import pyseekdb
+    from pyseekdb import HNSWConfiguration
+
+    SEEKDB_AVAILABLE = True
+except ImportError:
+    SEEKDB_AVAILABLE = False
+
+SEEKDB_EMBEDDING_MODEL_UUID = 'seekdb-builtin-embedding'
+SEEKDB_EMBEDDING_REQUESTER = 'seekdb-embedding'
+
+
+class SeekDBVectorDatabase(VectorDatabase):
+    """SeekDB vector database adapter for LangBot.
+
+    SeekDB is an AI-native search database by OceanBase that unifies
+    relational, vector, text, JSON and GIS in a single engine.
+
+    Supports both embedded mode and remote server mode.
+    """
+
+    def __init__(self, ap: app.Application):
+        if not SEEKDB_AVAILABLE:
+            raise ImportError('pyseekdb is not installed. Install it with: pip install pyseekdb')
+
+        self.ap = ap
+        config = self.ap.instance_config.data['vdb']['seekdb']
+
+        # Determine connection mode based on config
+        mode = config.get('mode', 'embedded')  # 'embedded' or 'server'
+
+        if mode == 'embedded':
+            # Embedded mode: local database
+            path = config.get('path', './data/seekdb')
+            database = config.get('database', 'langbot')
+
+            # Use AdminClient for database management operations
+            admin_client = pyseekdb.AdminClient(path=path)
+            # Check if database exists using public API
+            existing_dbs = [db.name for db in admin_client.list_databases()]
+            if database not in existing_dbs:
+                # Use public API to create database
+                admin_client.create_database(database)
+                self.ap.logger.info(f"Created SeekDB database '{database}'")
+
+            self.client = pyseekdb.Client(path=path, database=database)
+            self.ap.logger.info(f"Initialized SeekDB in embedded mode at '{path}', database '{database}'")
+        elif mode == 'server':
+            # Server mode: remote SeekDB or OceanBase server
+            host = config.get('host', 'localhost')
+            port = config.get('port', 2881)
+            database = config.get('database', 'langbot')
+            user = config.get('user', 'root')
+            password = config.get('password', '')
+            tenant = config.get('tenant', None)  # Optional, for OceanBase
+
+            connection_params = {
+                'host': host,
+                'port': int(port),
+                'database': database,
+                'user': user,
+                'password': password,
+            }
+
+            if tenant:
+                connection_params['tenant'] = tenant
+
+            self.client = pyseekdb.Client(**connection_params)
+            self.ap.logger.info(
+                f"Initialized SeekDB in server mode: {host}:{port}, database '{database}'"
+                + (f", tenant '{tenant}'" if tenant else '')
+            )
+        else:
+            raise ValueError(f"Invalid SeekDB mode: {mode}. Must be 'embedded' or 'server'")
+
+        self._collections: Dict[str, Any] = {}
+        self._collection_configs: Dict[str, HNSWConfiguration] = {}
+
+        self._escape_table = str.maketrans({
+            '\x00': '',
+            '\\': '\\\\',
+            '"': '\\"',
+            '\n': '\\n',
+            '\r': '\\r',
+            '\t': '\\t',
+        })
+
+    async def _get_or_create_collection_internal(self, collection: str, vector_size: int = None) -> Any:
+        """Internal method to get or create a collection with proper configuration."""
+        if collection in self._collections:
+            return self._collections[collection]
+
+        # Check if collection exists
+        if await asyncio.to_thread(self.client.has_collection, collection):
+            # Collection exists, get it
+            coll = await asyncio.to_thread(self.client.get_collection, collection, embedding_function=None)
+            self._collections[collection] = coll
+            self.ap.logger.info(f"SeekDB collection '{collection}' retrieved.")
+            return coll
+
+        # Collection doesn't exist, create it
+        if vector_size is None:
+            # Default dimension if not specified
+            vector_size = 384
+
+        # Create HNSW configuration
+        config = HNSWConfiguration(dimension=vector_size, distance='cosine')
+        self._collection_configs[collection] = config
+
+        # Create collection without embedding function (we manage embeddings externally)
+        coll = await asyncio.to_thread(
+            self.client.create_collection,
+            name=collection,
+            configuration=config,
+            embedding_function=None,  # Disable automatic embedding
+        )
+
+        self._collections[collection] = coll
+        self.ap.logger.info(f"SeekDB collection '{collection}' created with dimension={vector_size}, distance='cosine'")
+        return coll
+
+    def _clean_metadata(self, meta: Dict[str, Any]) -> Dict[str, Any]:
+        """SeekDB metadata doesn't support \\ and ", insert will error 3104"""
+        return {
+            k: v.translate(self._escape_table) if isinstance(v, str)
+            else v if v is None or isinstance(v, (int, float, bool))
+            else str(v)
+            for k, v in meta.items()
+            if v is not None
+        }
+
+    async def get_or_create_collection(self, collection: str):
+        """Get or create collection (without vector size - will use default)."""
+        return await self._get_or_create_collection_internal(collection)
+
+    async def add_embeddings(
+        self,
+        collection: str,
+        ids: List[str],
+        embeddings_list: List[List[float]],
+        metadatas: List[Dict[str, Any]]
+    ) -> None:
+        """Add vector embeddings to the specified collection.
+
+        Args:
+            collection: Collection name
+            ids: List of document IDs
+            embeddings_list: List of embedding vectors
+            metadatas: List of metadata dictionaries
+        """
+        if not embeddings_list:
+            return
+
+        # Ensure collection exists with correct dimension
+        vector_size = len(embeddings_list[0])
+        coll = await self._get_or_create_collection_internal(collection, vector_size)
+
+        cleaned_metadatas = [self._clean_metadata(meta) for meta in metadatas]
+
+        await asyncio.to_thread(coll.add, ids=ids, embeddings=embeddings_list, metadatas=cleaned_metadatas)
+
+        self.ap.logger.info(f"Added {len(ids)} embeddings to SeekDB collection '{collection}'")
+
+    async def search(self, collection: str, query_embedding: List[float], k: int = 5) -> Dict[str, Any]:
+        """Search for the most similar vectors in the specified collection.
+
+        Args:
+            collection: Collection name
+            query_embedding: Query vector
+            k: Number of results to return
+
+        Returns:
+            Dictionary with 'ids', 'metadatas', 'distances' keys
+        """
+        # Check if collection exists
+        exists = await asyncio.to_thread(self.client.has_collection, collection)
+        if not exists:
+            return {'ids': [[]], 'metadatas': [[]], 'distances': [[]]}
+
+        # Get collection
+        if collection not in self._collections:
+            coll = await asyncio.to_thread(self.client.get_collection, collection, embedding_function=None)
+            self._collections[collection] = coll
+        else:
+            coll = self._collections[collection]
+
+        # Perform query
+        # SeekDB's query() returns: {'ids': [[...]], 'metadatas': [[...]], 'distances': [[...]]}
+        results = await asyncio.to_thread(coll.query, query_embeddings=query_embedding, n_results=k)
+
+        self.ap.logger.info(f"SeekDB search in '{collection}' returned {len(results.get('ids', [[]])[0])} results")
+
+        return results
+
+    async def delete_by_file_id(self, collection: str, file_id: str) -> None:
+        """Delete vectors from the collection by file_id metadata.
+
+        Args:
+            collection: Collection name
+            file_id: File ID to delete
+        """
+        # Check if collection exists
+        exists = await asyncio.to_thread(self.client.has_collection, collection)
+        if not exists:
+            self.ap.logger.warning(f"SeekDB collection '{collection}' not found for deletion")
+            return
+
+        # Get collection
+        if collection not in self._collections:
+            coll = await asyncio.to_thread(self.client.get_collection, collection, embedding_function=None)
+            self._collections[collection] = coll
+        else:
+            coll = self._collections[collection]
+
+        # SeekDB's delete() expects a where clause for filtering
+        # Delete all records where metadata['file_id'] == file_id
+        await asyncio.to_thread(coll.delete, where={'file_id': file_id})
+
+        self.ap.logger.info(f"Deleted embeddings from SeekDB collection '{collection}' with file_id: {file_id}")
+
+    async def delete_collection(self, collection: str):
+        """Delete the entire collection.
+
+        Args:
+            collection: Collection name
+        """
+        # Remove from cache
+        if collection in self._collections:
+            del self._collections[collection]
+        if collection in self._collection_configs:
+            del self._collection_configs[collection]
+
+        # Check if collection exists
+        exists = await asyncio.to_thread(self.client.has_collection, collection)
+        if not exists:
+            self.ap.logger.warning(f"SeekDB collection '{collection}' not found for deletion")
+            return
+
+        # Delete collection
+        await asyncio.to_thread(self.client.delete_collection, collection)
+        self.ap.logger.info(f"SeekDB collection '{collection}' deleted")

src/langbot/templates/config.yaml

@@ -16,6 +16,7 @@ proxy:
     https: ''
 system:
     recovery_key: ''
+    allow_modify_login_info: true
     jwt:
         expire: 604800
         secret: ''
@@ -36,9 +37,21 @@ vdb:
         host: localhost
         port: 6333
         api_key: ''
+    seekdb:
+        mode: embedded  # 'embedded' or 'server'
+        # Embedded mode options:
+        path: './data/seekdb'
+        database: 'langbot'
+        # Server mode options (used when mode='server'):
+        host: 'localhost'
+        port: 2881
+        user: 'root'
+        password: ''
+        tenant: ''  # Optional, for OceanBase server
     milvus:
         uri: 'http://127.0.0.1:19530'
         token: ''
+        db_name: ''
     pgvector:
         host: '127.0.0.1'
         port: 5433
@@ -57,5 +70,13 @@ plugin:
     enable: true
     runtime_ws_url: 'ws://langbot_plugin_runtime:5400/control/ws'
     enable_marketplace: true
-    cloud_service_url: 'https://space.langbot.app'
     display_plugin_debug_url: 'ws://localhost:5401/plugin/debug/ws'
+space:
+    # Space service URL for OAuth and API
+    url: 'https://space.langbot.app'
+    # Space API URL for model requests (MaaS)
+    models_gateway_api_url: 'https://api.langbot.cloud/v1'
+    # OAuth authorization page URL (user will be redirected here)
+    oauth_authorize_url: 'https://space.langbot.app/auth/authorize'
+    disable_models_service: false
+    disable_telemetry: false

web/package.json

@@ -25,6 +25,7 @@
     "@hookform/resolvers": "^5.0.1",
     "@radix-ui/react-alert-dialog": "^1.1.15",
     "@radix-ui/react-checkbox": "^1.3.1",
+    "@radix-ui/react-collapsible": "^1.1.12",
     "@radix-ui/react-context-menu": "^2.2.15",
     "@radix-ui/react-dialog": "^1.1.14",
     "@radix-ui/react-dropdown-menu": "^2.1.16",
@@ -33,7 +34,7 @@
     "@radix-ui/react-popover": "^1.1.14",
     "@radix-ui/react-scroll-area": "^1.2.9",
     "@radix-ui/react-select": "^2.2.4",
-    "@radix-ui/react-separator": "^1.1.7",
+    "@radix-ui/react-separator": "^1.1.8",
     "@radix-ui/react-slot": "^1.2.3",
     "@radix-ui/react-switch": "^1.2.4",
     "@radix-ui/react-tabs": "^1.1.11",
@@ -51,9 +52,10 @@
     "input-otp": "^1.4.2",
     "lodash": "^4.17.21",
     "lucide-react": "^0.507.0",
-    "next": "~15.5.7",
+    "next": "~15.5.9",
     "next-themes": "^0.4.6",
     "postcss": "^8.5.3",
+    "qrcode": "^1.5.4",
     "react": "19.2.1",
     "react-dom": "19.2.1",
     "react-hook-form": "^7.56.3",
@@ -82,6 +84,7 @@
     "@types/mdast": "^4.0.4",
     "@types/ms": "^2.1.0",
     "@types/node": "^20",
+    "@types/qrcode": "^1.5.6",
     "@types/react": "~19.2.7",
     "@types/react-dom": "~19.2.3",
     "@types/react-syntax-highlighter": "^15.5.13",

web/pnpm-lock.yaml

@@ -23,6 +23,9 @@ dependencies:
   '@radix-ui/react-checkbox':
     specifier: ^1.3.1
     version: 1.3.3(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
+  '@radix-ui/react-collapsible':
+    specifier: ^1.1.12
+    version: 1.1.12(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
   '@radix-ui/react-context-menu':
     specifier: ^2.2.15
     version: 2.2.16(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
@@ -48,7 +51,7 @@ dependencies:
     specifier: ^2.2.4
     version: 2.2.6(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
   '@radix-ui/react-separator':
-    specifier: ^1.1.7
+    specifier: ^1.1.8
     version: 1.1.8(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
   '@radix-ui/react-slot':
     specifier: ^1.2.3
@@ -102,14 +105,17 @@ dependencies:
     specifier: ^0.507.0
     version: 0.507.0(react@19.2.1)
   next:
-    specifier: ~15.5.7
-    version: 15.5.7(react-dom@19.2.1)(react@19.2.1)
+    specifier: ~15.5.9
+    version: 15.5.9(react-dom@19.2.1)(react@19.2.1)
   next-themes:
     specifier: ^0.4.6
     version: 0.4.6(react-dom@19.2.1)(react@19.2.1)
   postcss:
     specifier: ^8.5.3
     version: 8.5.6
+  qrcode:
+    specifier: ^1.5.4
+    version: 1.5.4
   react:
     specifier: 19.2.1
     version: 19.2.1
@@ -190,6 +196,9 @@ devDependencies:
   '@types/node':
     specifier: ^20
     version: 20.19.25
+  '@types/qrcode':
+    specifier: ^1.5.6
+    version: 1.5.6
   '@types/react':
     specifier: ~19.2.7
     version: 19.2.7
@@ -718,8 +727,8 @@ packages:
     dev: true
     optional: true
 
-  /@next/env@15.5.7:
-    resolution: {integrity: sha512-4h6Y2NyEkIEN7Z8YxkA27pq6zTkS09bUSYC0xjd0NpwFxjnIKeZEeH591o5WECSmjpUhLn3H2QLJcDye3Uzcvg==}
+  /@next/env@15.5.9:
+    resolution: {integrity: sha512-4GlTZ+EJM7WaW2HEZcyU317tIQDjkQIyENDLxYJfSWlfqguN+dHkZgyQTV/7ykvobU7yEH5gKvreNrH4B6QgIg==}
     dev: false
 
   /@next/eslint-plugin-next@15.2.4:
@@ -911,6 +920,33 @@ packages:
       react-dom: 19.2.1(react@19.2.1)
     dev: false
 
+  /@radix-ui/react-collapsible@1.1.12(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1):
+    resolution: {integrity: sha512-Uu+mSh4agx2ib1uIGPP4/CKNULyajb3p92LsVXmH2EHVMTfZWpll88XJ0j4W0z3f8NK1eYl1+Mf/szHPmcHzyA==}
+    peerDependencies:
+      '@types/react': '*'
+      '@types/react-dom': '*'
+      react: ^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc
+      react-dom: ^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc
+    peerDependenciesMeta:
+      '@types/react':
+        optional: true
+      '@types/react-dom':
+        optional: true
+    dependencies:
+      '@radix-ui/primitive': 1.1.3
+      '@radix-ui/react-compose-refs': 1.1.2(@types/react@19.2.7)(react@19.2.1)
+      '@radix-ui/react-context': 1.1.2(@types/react@19.2.7)(react@19.2.1)
+      '@radix-ui/react-id': 1.1.1(@types/react@19.2.7)(react@19.2.1)
+      '@radix-ui/react-presence': 1.1.5(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
+      '@radix-ui/react-primitive': 2.1.3(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1)
+      '@radix-ui/react-use-controllable-state': 1.2.2(@types/react@19.2.7)(react@19.2.1)
+      '@radix-ui/react-use-layout-effect': 1.1.1(@types/react@19.2.7)(react@19.2.1)
+      '@types/react': 19.2.7
+      '@types/react-dom': 19.2.3(@types/react@19.2.7)
+      react: 19.2.1
+      react-dom: 19.2.1(react@19.2.1)
+    dev: false
+
   /@radix-ui/react-collection@1.1.7(@types/react-dom@19.2.3)(@types/react@19.2.7)(react-dom@19.2.1)(react@19.2.1):
     resolution: {integrity: sha512-Fh9rGN0MoI4ZFUNyfFVNU4y9LUz93u9/0K+yLgA2bwRojxM8JU1DyvvMBabnZPBgMWREAJvU2jjVzq+LrFUglw==}
     peerDependencies:
@@ -2015,6 +2051,12 @@ packages:
     resolution: {integrity: sha512-AUZTa7hQ2KY5L7AmtSiqxlhWxb4ina0yd8hNbl4TWuqnv/pFP0nDMb3YrfSBf4hJVGLh2YEIBfKaBW/9UEl6IQ==}
     dev: false
 
+  /@types/qrcode@1.5.6:
+    resolution: {integrity: sha512-te7NQcV2BOvdj2b1hCAHzAoMNuj65kNBMz0KBaxM6c3VGBOhU0dURQKOtH8CFNI/dsKkwlv32p26qYQTWoB5bw==}
+    dependencies:
+      '@types/node': 20.19.25
+    dev: true
+
   /@types/react-dom@19.2.3(@types/react@19.2.7):
     resolution: {integrity: sha512-jp2L/eY6fn+KgVVQAOqYItbF0VY/YApe5Mz2F0aykSO8gx31bYCZyvSeYxCHKvzHG5eZjc+zyaS5BrBWya2+kQ==}
     peerDependencies:
@@ -2369,6 +2411,11 @@ packages:
       environment: 1.1.0
     dev: true
 
+  /ansi-regex@5.0.1:
+    resolution: {integrity: sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==}
+    engines: {node: '>=8'}
+    dev: false
+
   /ansi-regex@6.2.2:
     resolution: {integrity: sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg==}
     engines: {node: '>=12'}
@@ -2379,7 +2426,6 @@ packages:
     engines: {node: '>=8'}
     dependencies:
       color-convert: 2.0.1
-    dev: true
 
   /ansi-styles@6.2.3:
     resolution: {integrity: sha512-4Dj6M28JB+oAH8kFkTLUo+a2jwOFkuqb3yucU0CANcRRUbxS0cP0nZYCGjcc3BNXwRIsUVmDGgzawme7zvJHvg==}
@@ -2591,6 +2637,11 @@ packages:
     engines: {node: '>=6'}
     dev: true
 
+  /camelcase@5.3.1:
+    resolution: {integrity: sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg==}
+    engines: {node: '>=6'}
+    dev: false
+
   /caniuse-lite@1.0.30001757:
     resolution: {integrity: sha512-r0nnL/I28Zi/yjk1el6ilj27tKcdjLsNqAOZr0yVjWPrSQyHgKI2INaEWw21bAQSv2LXRt1XuCS/GomNpWOxsQ==}
     dev: false
@@ -2653,6 +2704,14 @@ packages:
     resolution: {integrity: sha512-IV3Ou0jSMzZrd3pZ48nLkT9DA7Ag1pnPzaiQhpW7c3RbcqqzvzzVu+L8gfqMp/8IM2MQtSiqaCxrrcfu8I8rMA==}
     dev: false
 
+  /cliui@6.0.0:
+    resolution: {integrity: sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ==}
+    dependencies:
+      string-width: 4.2.3
+      strip-ansi: 6.0.1
+      wrap-ansi: 6.2.0
+    dev: false
+
   /clsx@2.1.1:
     resolution: {integrity: sha512-eYm0QWBtUrBWZWG0d386OGAw16Z995PiOVo2B7bjWSbHedGl5e0ZWaq65kOGgUSNesEIDkB9ISbTg/JK9dhCZA==}
     engines: {node: '>=6'}
@@ -2663,11 +2722,9 @@ packages:
     engines: {node: '>=7.0.0'}
     dependencies:
       color-name: 1.1.4
-    dev: true
 
   /color-name@1.1.4:
     resolution: {integrity: sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==}
-    dev: true
 
   /colorette@2.0.20:
     resolution: {integrity: sha512-IfEDxwoWIjkeXL1eXcDiow4UbKjhLdq6/EuSVR9GMN7KVH3r9gQ83e73hsz1Nd1T3ijd5xv1wcWRYO+D6kCI2w==}
@@ -2758,6 +2815,11 @@ packages:
     dependencies:
       ms: 2.1.3
 
+  /decamelize@1.2.0:
+    resolution: {integrity: sha512-z2S+W9X73hAUUki+N+9Za2lBlun89zigOyGrsax+KUQ6wKW4ZoWpEYBkGhQjwAjjDCkWxhY0VKEhk8wzY7F5cA==}
+    engines: {node: '>=0.10.0'}
+    dev: false
+
   /decode-named-character-reference@1.2.0:
     resolution: {integrity: sha512-c6fcElNV6ShtZXmsgNgFFV5tVX2PaV4g+MOAkb8eXHvn6sryJBrZa9r0zV6+dtTyoCKxtDy5tyQ5ZwQuidtd+Q==}
     dependencies:
@@ -2811,6 +2873,10 @@ packages:
       dequal: 2.0.3
     dev: false
 
+  /dijkstrajs@1.0.3:
+    resolution: {integrity: sha512-qiSlmBq9+BCdCA/L46dw8Uy93mloxsPSbwnm5yrKn2vMPiy8KyAskTF6zuV/j5BMsmOGZDPs7KjU+mjb670kfA==}
+    dev: false
+
   /doctrine@2.1.0:
     resolution: {integrity: sha512-35mSku4ZXK0vfCuHEDAwt55dg2jNajHZ1odvF+8SSr82EsZY4QmXfuWso8oEd8zRhVObSN18aM0CjSdoBX7zIw==}
     engines: {node: '>=0.10.0'}
@@ -2830,6 +2896,10 @@ packages:
     resolution: {integrity: sha512-toUI84YS5YmxW219erniWD0CIVOo46xGKColeNQRgOzDorgBi1v4D71/OFzgD9GO2UGKIv1C3Sp8DAn0+j5w7A==}
     dev: true
 
+  /emoji-regex@8.0.0:
+    resolution: {integrity: sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==}
+    dev: false
+
   /emoji-regex@9.2.2:
     resolution: {integrity: sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg==}
     dev: true
@@ -3394,6 +3464,14 @@ packages:
       to-regex-range: 5.0.1
     dev: true
 
+  /find-up@4.1.0:
+    resolution: {integrity: sha512-PpOwAdQ/YlXQ2vj8a3h8IipDuYRi3wceVQQGYWxNINccq40Anw7BlsEXCMbt1Zt+OLA6Fq9suIpIWD0OsnISlw==}
+    engines: {node: '>=8'}
+    dependencies:
+      locate-path: 5.0.0
+      path-exists: 4.0.0
+    dev: false
+
   /find-up@5.0.0:
     resolution: {integrity: sha512-78/PXT1wlLLDgTzDs7sjq9hzz0vXD+zn+7wypEe4fXQxCmdmqfGsEPQxmiCSQI3ajFV91bVSsvNtrJRiW6nGng==}
     engines: {node: '>=10'}
@@ -3471,6 +3549,11 @@ packages:
     engines: {node: '>= 0.4'}
     dev: true
 
+  /get-caller-file@2.0.5:
+    resolution: {integrity: sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==}
+    engines: {node: 6.* || 8.* || >= 10.*}
+    dev: false
+
   /get-east-asian-width@1.4.0:
     resolution: {integrity: sha512-QZjmEOC+IT1uk6Rx0sX22V6uHWVwbdbxf1faPqJ1QhLdGgsRGCZoyaQBm/piRdJy/D2um6hM1UP7ZEeQ4EkP+Q==}
     engines: {node: '>=18'}
@@ -3912,6 +3995,11 @@ packages:
       call-bound: 1.0.4
     dev: true
 
+  /is-fullwidth-code-point@3.0.0:
+    resolution: {integrity: sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==}
+    engines: {node: '>=8'}
+    dev: false
+
   /is-fullwidth-code-point@4.0.0:
     resolution: {integrity: sha512-O4L094N2/dZ7xqVdrXhh9r1KODPJpFms8B5sGdJLPy664AgvXsreZUyCQQNItZRDlYug4xStLjNp/sz3HvBowQ==}
     engines: {node: '>=12'}
@@ -4289,6 +4377,13 @@ packages:
       wrap-ansi: 9.0.2
     dev: true
 
+  /locate-path@5.0.0:
+    resolution: {integrity: sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g==}
+    engines: {node: '>=8'}
+    dependencies:
+      p-locate: 4.1.0
+    dev: false
+
   /locate-path@6.0.0:
     resolution: {integrity: sha512-iPZK6eYjbxRu3uB4/WZ3EsEIMJFMqAoopl3R+zuq0UjcAm/MO6KCweDgPfP3elTztoKP3KtnVHxTn2NHBSDVUw==}
     engines: {node: '>=10'}
@@ -4878,8 +4973,8 @@ packages:
       react-dom: 19.2.1(react@19.2.1)
     dev: false
 
-  /next@15.5.7(react-dom@19.2.1)(react@19.2.1):
-    resolution: {integrity: sha512-+t2/0jIJ48kUpGKkdlhgkv+zPTEOoXyr60qXe68eB/pl3CMJaLeIGjzp5D6Oqt25hCBiBTt8wEeeAzfJvUKnPQ==}
+  /next@15.5.9(react-dom@19.2.1)(react@19.2.1):
+    resolution: {integrity: sha512-agNLK89seZEtC5zUHwtut0+tNrc0Xw4FT/Dg+B/VLEo9pAcS9rtTKpek3V6kVcVwsB2YlqMaHdfZL4eLEVYuCg==}
     engines: {node: ^18.18.0 || ^19.8.0 || >= 20.0.0}
     hasBin: true
     peerDependencies:
@@ -4899,7 +4994,7 @@ packages:
       sass:
         optional: true
     dependencies:
-      '@next/env': 15.5.7
+      '@next/env': 15.5.9
       '@swc/helpers': 0.5.15
       caniuse-lite: 1.0.30001757
       postcss: 8.4.31
@@ -5029,6 +5124,13 @@ packages:
       safe-push-apply: 1.0.0
     dev: true
 
+  /p-limit@2.3.0:
+    resolution: {integrity: sha512-//88mFWSJx8lxCzwdAABTJL2MyWB12+eIY7MDL2SqLmAkeKU9qxRvWuSyTjm3FUmpBEMuFfckAIqEaVGUDxb6w==}
+    engines: {node: '>=6'}
+    dependencies:
+      p-try: 2.2.0
+    dev: false
+
   /p-limit@3.1.0:
     resolution: {integrity: sha512-TYOanM3wGwNGsZN2cVTYPArw454xnXj5qmWF1bEoAc4+cU/ol7GVh7odevjp1FNHduHc3KZMcFduxU5Xc6uJRQ==}
     engines: {node: '>=10'}
@@ -5036,6 +5138,13 @@ packages:
       yocto-queue: 0.1.0
     dev: true
 
+  /p-locate@4.1.0:
+    resolution: {integrity: sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A==}
+    engines: {node: '>=8'}
+    dependencies:
+      p-limit: 2.3.0
+    dev: false
+
   /p-locate@5.0.0:
     resolution: {integrity: sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw==}
     engines: {node: '>=10'}
@@ -5043,6 +5152,11 @@ packages:
       p-limit: 3.1.0
     dev: true
 
+  /p-try@2.2.0:
+    resolution: {integrity: sha512-R4nPAVTAU0B9D35/Gk3uJf/7XYbQcyohSKdvAxIRSNghFl4e71hVoGnBNQz9cWaXxO2I10KTC+3jMdvvoKw6dQ==}
+    engines: {node: '>=6'}
+    dev: false
+
   /parent-module@1.0.1:
     resolution: {integrity: sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g==}
     engines: {node: '>=6'}
@@ -5071,7 +5185,6 @@ packages:
   /path-exists@4.0.0:
     resolution: {integrity: sha512-ak9Qy5Q7jYb2Wwcey5Fpvg2KoAc/ZIhLSLOSBmRmygPsGwkVVt0fZa0qrtMz+m6tJTAHfZQ8FnmB4MG4LWy7/w==}
     engines: {node: '>=8'}
-    dev: true
 
   /path-key@3.1.1:
     resolution: {integrity: sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==}
@@ -5107,6 +5220,11 @@ packages:
     hasBin: true
     dev: true
 
+  /pngjs@5.0.0:
+    resolution: {integrity: sha512-40QW5YalBNfQo5yRYmiw7Yz6TKKVr3h6970B2YE+3fQpsWcrbj1PzJgxeJ19DRQjhMbKPIuMY8rFaXc8moolVw==}
+    engines: {node: '>=10.13.0'}
+    dev: false
+
   /possible-typed-array-names@1.1.0:
     resolution: {integrity: sha512-/+5VFTchJDoVj3bhoqi6UeymcD00DAwb1nJwamzPvHEszJ4FpF6SNNbUbOS8yI56qHzdV8eK0qEfOSiodkTdxg==}
     engines: {node: '>= 0.4'}
@@ -5178,6 +5296,16 @@ packages:
     engines: {node: '>=6'}
     dev: true
 
+  /qrcode@1.5.4:
+    resolution: {integrity: sha512-1ca71Zgiu6ORjHqFBDpnSMTR2ReToX4l1Au1VFLyVeBTFavzQnv5JxMFr3ukHVKpSrSA2MCk0lNJSykjUfz7Zg==}
+    engines: {node: '>=10.13.0'}
+    hasBin: true
+    dependencies:
+      dijkstrajs: 1.0.3
+      pngjs: 5.0.0
+      yargs: 15.4.1
+    dev: false
+
   /queue-microtask@1.2.3:
     resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==}
     dev: true
@@ -5448,6 +5576,15 @@ packages:
       unified: 11.0.5
     dev: false
 
+  /require-directory@2.1.1:
+    resolution: {integrity: sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==}
+    engines: {node: '>=0.10.0'}
+    dev: false
+
+  /require-main-filename@2.0.0:
+    resolution: {integrity: sha512-NKN5kMDylKuldxYLSUfrbo5Tuzh4hd+2E8NPPX02mZtn1VuREQToYe/ZdlJy+J3uCpfaiGF05e7B8W0iXbQHmg==}
+    dev: false
+
   /resolve-from@4.0.0:
     resolution: {integrity: sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==}
     engines: {node: '>=4'}
@@ -5541,6 +5678,10 @@ packages:
     engines: {node: '>=10'}
     hasBin: true
 
+  /set-blocking@2.0.0:
+    resolution: {integrity: sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw==}
+    dev: false
+
   /set-function-length@1.2.2:
     resolution: {integrity: sha512-pgRc4hJ4/sNjWCSS9AmnS40x3bNMDTknHgL5UaMBTMyJnU90EgWh1Rz+MC9eFu4BuN/UwZjKQuY/1v3rM7HMfg==}
     engines: {node: '>= 0.4'}
@@ -5717,6 +5858,15 @@ packages:
     engines: {node: '>=0.6.19'}
     dev: true
 
+  /string-width@4.2.3:
+    resolution: {integrity: sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==}
+    engines: {node: '>=8'}
+    dependencies:
+      emoji-regex: 8.0.0
+      is-fullwidth-code-point: 3.0.0
+      strip-ansi: 6.0.1
+    dev: false
+
   /string-width@7.2.0:
     resolution: {integrity: sha512-tsaTIkKW9b4N+AEj+SVA+WhJzV7/zMhcSu78mLKWSk7cXMOSHsBKFWUs0fWwq8QyK3MgJBQRX6Gbi4kYbdvGkQ==}
     engines: {node: '>=18'}
@@ -5800,6 +5950,13 @@ packages:
       character-entities-legacy: 3.0.0
     dev: false
 
+  /strip-ansi@6.0.1:
+    resolution: {integrity: sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==}
+    engines: {node: '>=8'}
+    dependencies:
+      ansi-regex: 5.0.1
+    dev: false
+
   /strip-ansi@7.1.2:
     resolution: {integrity: sha512-gmBGslpoQJtgnMAvOVqGZpEz9dyoKTCzy2nfz/n8aIFhN/jCE/rCmcxabB6jOOHV+0WNnylOxaxBQPSvcWklhA==}
     engines: {node: '>=12'}
@@ -6210,6 +6367,10 @@ packages:
       is-weakset: 2.0.4
     dev: true
 
+  /which-module@2.0.1:
+    resolution: {integrity: sha512-iBdZ57RDvnOR9AGBhML2vFZf7h8vmBjhoaZqODJBFWHVtKkDmKuHai3cx5PgVMrX5YDNp27AofYbAwctSS+vhQ==}
+    dev: false
+
   /which-typed-array@1.1.19:
     resolution: {integrity: sha512-rEvr90Bck4WZt9HHFC4DJMsjvu7x+r6bImz0/BrbWb7A2djJ8hnZMrWnHo9F8ssv0OMErasDhftrfROTyqSDrw==}
     engines: {node: '>= 0.4'}
@@ -6236,6 +6397,15 @@ packages:
     engines: {node: '>=0.10.0'}
     dev: true
 
+  /wrap-ansi@6.2.0:
+    resolution: {integrity: sha512-r6lPcBGxZXlIcymEu7InxDMhdW0KDxpLgoFLcguasxCaJ/SOIZwINatK9KY/tf+ZrlywOKU0UDj3ATXUBfxJXA==}
+    engines: {node: '>=8'}
+    dependencies:
+      ansi-styles: 4.3.0
+      string-width: 4.2.3
+      strip-ansi: 6.0.1
+    dev: false
+
   /wrap-ansi@9.0.2:
     resolution: {integrity: sha512-42AtmgqjV+X1VpdOfyTGOYRi0/zsoLqtXQckTmqTeybT+BDIbM/Guxo7x3pE2vtpr1ok6xRqM9OpBe+Jyoqyww==}
     engines: {node: '>=18'}
@@ -6245,12 +6415,41 @@ packages:
       strip-ansi: 7.1.2
     dev: true
 
+  /y18n@4.0.3:
+    resolution: {integrity: sha512-JKhqTOwSrqNA1NY5lSztJ1GrBiUodLMmIZuLiDaMRJ+itFd+ABVE8XBjOvIWL+rSqNDC74LCSFmlb/U4UZ4hJQ==}
+    dev: false
+
   /yaml@2.8.1:
     resolution: {integrity: sha512-lcYcMxX2PO9XMGvAJkJ3OsNMw+/7FKes7/hgerGUYWIoWu5j/+YQqcZr5JnPZWzOsEBgMbSbiSTn/dv/69Mkpw==}
     engines: {node: '>= 14.6'}
     hasBin: true
     dev: true
 
+  /yargs-parser@18.1.3:
+    resolution: {integrity: sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ==}
+    engines: {node: '>=6'}
+    dependencies:
+      camelcase: 5.3.1
+      decamelize: 1.2.0
+    dev: false
+
+  /yargs@15.4.1:
+    resolution: {integrity: sha512-aePbxDmcYW++PaqBsJ+HYUFwCdv4LVvdnhBy78E57PIor8/OVvhMrADFFEDh8DHDFRv/O9i3lPhsENjO7QX0+A==}
+    engines: {node: '>=8'}
+    dependencies:
+      cliui: 6.0.0
+      decamelize: 1.2.0
+      find-up: 4.1.0
+      get-caller-file: 2.0.5
+      require-directory: 2.1.1
+      require-main-filename: 2.0.0
+      set-blocking: 2.0.0
+      string-width: 4.2.3
+      which-module: 2.0.1
+      y18n: 4.0.3
+      yargs-parser: 18.1.3
+    dev: false
+
   /yocto-queue@0.1.0:
     resolution: {integrity: sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q==}
     engines: {node: '>=10'}

web/src/app/auth/space/callback/page.tsx

@@ -0,0 +1,248 @@
+'use client';
+
+import { useEffect, useState, useCallback, Suspense } from 'react';
+import { useRouter, useSearchParams } from 'next/navigation';
+import { httpClient } from '@/app/infra/http/HttpClient';
+import { toast } from 'sonner';
+import { useTranslation } from 'react-i18next';
+import {
+  Loader2,
+  AlertCircle,
+  CheckCircle2,
+  AlertTriangle,
+} from 'lucide-react';
+import {
+  Card,
+  CardContent,
+  CardHeader,
+  CardTitle,
+  CardDescription,
+} from '@/components/ui/card';
+import { Button } from '@/components/ui/button';
+import langbotIcon from '@/app/assets/langbot-logo.webp';
+
+function SpaceOAuthCallbackContent() {
+  const router = useRouter();
+  const searchParams = useSearchParams();
+  const { t } = useTranslation();
+
+  const [status, setStatus] = useState<
+    'loading' | 'confirm' | 'success' | 'error'
+  >('loading');
+  const [errorMessage, setErrorMessage] = useState<string>('');
+  const [isBindMode, setIsBindMode] = useState(false);
+  const [code, setCode] = useState<string | null>(null);
+  const [isProcessing, setIsProcessing] = useState(false);
+  const [localEmail, setLocalEmail] = useState<string>('');
+
+  const handleOAuthCallback = useCallback(
+    async (authCode: string) => {
+      try {
+        const response = await httpClient.exchangeSpaceOAuthCode(authCode);
+        localStorage.setItem('token', response.token);
+        if (response.user) {
+          localStorage.setItem('userEmail', response.user);
+        }
+        setStatus('success');
+        toast.success(t('common.spaceLoginSuccess'));
+        setTimeout(() => {
+          router.push('/home');
+        }, 1000);
+      } catch (err) {
+        setStatus('error');
+        const errorObj = err as { msg?: string };
+        const errMsg = (errorObj?.msg || '').toLowerCase();
+        if (errMsg.includes('account email mismatch')) {
+          setErrorMessage(t('account.spaceEmailMismatch'));
+        } else {
+          setErrorMessage(t('common.spaceLoginFailed'));
+        }
+      }
+    },
+    [router, t],
+  );
+
+  const [bindState, setBindState] = useState<string | null>(null);
+
+  const handleBindAccount = useCallback(
+    async (authCode: string, state: string) => {
+      setIsProcessing(true);
+      try {
+        const response = await httpClient.bindSpaceAccount(authCode, state);
+        localStorage.setItem('token', response.token);
+        if (response.user) {
+          localStorage.setItem('userEmail', response.user);
+        }
+        setStatus('success');
+        toast.success(t('account.bindSpaceSuccess'));
+        setTimeout(() => {
+          router.push('/home');
+        }, 1000);
+      } catch (err) {
+        setStatus('error');
+        const errorObj = err as { msg?: string };
+        const errMsg = (errorObj?.msg || '').toLowerCase();
+        if (errMsg.includes('account email mismatch')) {
+          setErrorMessage(t('account.spaceEmailMismatch'));
+        } else {
+          setErrorMessage(t('account.bindSpaceFailed'));
+        }
+      } finally {
+        setIsProcessing(false);
+      }
+    },
+    [router, t],
+  );
+
+  useEffect(() => {
+    const authCode = searchParams.get('code');
+    const error = searchParams.get('error');
+    const errorDescription = searchParams.get('error_description');
+    const mode = searchParams.get('mode');
+    const state = searchParams.get('state');
+
+    if (error) {
+      setStatus('error');
+      setErrorMessage(
+        errorDescription || error || t('common.spaceLoginFailed'),
+      );
+      return;
+    }
+
+    if (!authCode) {
+      setStatus('error');
+      setErrorMessage(t('common.spaceLoginNoCode'));
+      return;
+    }
+
+    setCode(authCode);
+
+    if (mode === 'bind') {
+      // Bind mode - verify state (token) exists
+      if (!state) {
+        setStatus('error');
+        setErrorMessage(t('account.bindSpaceInvalidState'));
+        return;
+      }
+      setBindState(state);
+      setIsBindMode(true);
+      setLocalEmail(localStorage.getItem('userEmail') || '');
+      setStatus('confirm');
+    } else {
+      // Normal login/register mode
+      handleOAuthCallback(authCode);
+    }
+  }, [searchParams, handleOAuthCallback, t]);
+
+  const handleConfirmBind = () => {
+    if (code && bindState) {
+      handleBindAccount(code, bindState);
+    }
+  };
+
+  const handleCancelBind = () => {
+    router.push('/home');
+  };
+
+  return (
+    <div className="min-h-screen flex items-center justify-center bg-gray-50 dark:bg-neutral-900">
+      <Card className="w-[400px] shadow-lg dark:shadow-white/10">
+        <CardHeader className="text-center">
+          <img
+            src={langbotIcon.src}
+            alt="LangBot"
+            className="w-16 h-16 mb-4 mx-auto"
+          />
+          <CardTitle className="text-xl">
+            {status === 'loading' && t('common.spaceLoginProcessing')}
+            {status === 'confirm' && t('account.bindSpaceConfirmTitle')}
+            {status === 'success' &&
+              (isBindMode
+                ? t('account.bindSpaceSuccess')
+                : t('common.spaceLoginSuccess'))}
+            {status === 'error' &&
+              (isBindMode
+                ? t('account.bindSpaceFailed')
+                : t('common.spaceLoginError'))}
+          </CardTitle>
+          <CardDescription>
+            {status === 'loading' &&
+              t('common.spaceLoginProcessingDescription')}
+            {status === 'confirm' && t('account.bindSpaceConfirmDescription')}
+            {status === 'success' && t('common.spaceLoginSuccessDescription')}
+            {status === 'error' && errorMessage}
+          </CardDescription>
+        </CardHeader>
+        <CardContent className="flex flex-col items-center space-y-4">
+          {status === 'loading' && (
+            <Loader2 className="h-12 w-12 animate-spin text-primary" />
+          )}
+          {status === 'confirm' && (
+            <>
+              <AlertTriangle className="h-12 w-12 text-yellow-500" />
+              <p className="text-sm text-center text-muted-foreground px-4">
+                {t('account.bindSpaceWarning', {
+                  localEmail: localEmail || '-',
+                })}
+              </p>
+              <div className="flex gap-3 w-full">
+                <Button
+                  variant="outline"
+                  className="flex-1"
+                  onClick={handleCancelBind}
+                  disabled={isProcessing}
+                >
+                  {t('common.cancel')}
+                </Button>
+                <Button
+                  className="flex-1"
+                  onClick={handleConfirmBind}
+                  disabled={isProcessing}
+                >
+                  {isProcessing ? (
+                    <Loader2 className="mr-2 h-4 w-4 animate-spin" />
+                  ) : null}
+                  {t('common.confirm')}
+                </Button>
+              </div>
+            </>
+          )}
+          {status === 'success' && (
+            <CheckCircle2 className="h-12 w-12 text-green-500" />
+          )}
+          {status === 'error' && (
+            <>
+              <AlertCircle className="h-12 w-12 text-red-500" />
+              <Button
+                onClick={() => router.push(isBindMode ? '/home' : '/login')}
+                className="w-full mt-4"
+              >
+                {isBindMode ? t('common.backToHome') : t('common.backToLogin')}
+              </Button>
+            </>
+          )}
+        </CardContent>
+      </Card>
+    </div>
+  );
+}
+
+function LoadingFallback() {
+  return (
+    <div className="min-h-screen flex items-center justify-center bg-gray-50 dark:bg-neutral-900">
+      <Card className="w-[400px] shadow-lg dark:shadow-white/10">
+        <CardContent className="flex flex-col items-center py-12">
+          <Loader2 className="h-12 w-12 animate-spin text-primary" />
+        </CardContent>
+      </Card>
+    </div>
+  );
+}
+
+export default function SpaceOAuthCallback() {
+  return (
+    <Suspense fallback={<LoadingFallback />}>
+      <SpaceOAuthCallbackContent />
+    </Suspense>
+  );
+}

web/src/app/home/bots/components/bot-form/BotForm.tsx

@@ -19,6 +19,7 @@ import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 import { toast } from 'sonner';
 import { useTranslation } from 'react-i18next';
+import { Copy, Check } from 'lucide-react';
 
 import {
   Dialog,
@@ -48,6 +49,7 @@ import {
 } from '@/components/ui/select';
 import { Switch } from '@/components/ui/switch';
 import { extractI18nObject } from '@/i18n/I18nProvider';
+import { CustomApiError } from '@/app/infra/entities/common';
 
 const getFormSchema = (t: (key: string) => string) =>
   z.object({
@@ -116,6 +118,7 @@ export default function BotForm({
   const [, setIsLoading] = useState<boolean>(false);
   const [webhookUrl, setWebhookUrl] = useState<string>('');
   const webhookInputRef = React.useRef<HTMLInputElement>(null);
+  const [copied, setCopied] = useState<boolean>(false);
 
   // Watch adapter and adapter_config for filtering
   const currentAdapter = form.watch('adapter');
@@ -153,7 +156,6 @@ export default function BotForm({
     const inputElement = webhookInputRef.current;
     if (!inputElement) {
       console.error('[Copy] Input element not found');
-      toast.error(t('common.copyFailed'));
       return;
     }
 
@@ -178,7 +180,8 @@ export default function BotForm({
             console.log('[Copy] Clipboard API success');
             inputElement.blur(); // 取消选中
             inputElement.readOnly = true;
-            toast.success(t('bots.webhookUrlCopied'));
+            setCopied(true);
+            setTimeout(() => setCopied(false), 2000);
           })
           .catch((err) => {
             console.error(
@@ -191,9 +194,8 @@ export default function BotForm({
             inputElement.blur();
             inputElement.readOnly = true;
             if (successful) {
-              toast.success(t('bots.webhookUrlCopied'));
-            } else {
-              toast.error(t('common.copyFailed'));
+              setCopied(true);
+              setTimeout(() => setCopied(false), 2000);
             }
           });
       } else {
@@ -207,15 +209,13 @@ export default function BotForm({
         inputElement.blur();
         inputElement.readOnly = true;
         if (successful) {
-          toast.success(t('bots.webhookUrlCopied'));
-        } else {
-          toast.error(t('common.copyFailed'));
+          setCopied(true);
+          setTimeout(() => setCopied(false), 2000);
         }
       }
     } catch (err) {
       console.error('[Copy] Copy failed:', err);
       inputElement.readOnly = true;
-      toast.error(t('common.copyFailed'));
     }
   };
 
@@ -242,7 +242,9 @@ export default function BotForm({
             }
           })
           .catch((err) => {
-            toast.error(t('bots.getBotConfigError') + err.message);
+            toast.error(
+              t('bots.getBotConfigError') + (err as CustomApiError).msg,
+            );
           });
       } else {
         form.reset();
@@ -310,6 +312,7 @@ export default function BotForm({
               name: item.name,
               required: item.required,
               type: parseDynamicFormItemType(item.type),
+              options: item.options,
             }),
         ),
       );
@@ -384,7 +387,7 @@ export default function BotForm({
           toast.success(t('bots.saveSuccess'));
         })
         .catch((err) => {
-          toast.error(t('bots.saveError') + err.message);
+          toast.error(t('bots.saveError') + err.msg);
         })
         .finally(() => {
           setIsLoading(false);
@@ -410,7 +413,7 @@ export default function BotForm({
           onNewBotCreated(res.uuid);
         })
         .catch((err) => {
-          toast.error(t('bots.createError') + err.message);
+          toast.error(t('bots.createError') + err.msg);
         })
         .finally(() => {
           setIsLoading(false);
@@ -429,7 +432,7 @@ export default function BotForm({
           toast.success(t('bots.deleteSuccess'));
         })
         .catch((err) => {
-          toast.error(t('bots.deleteError') + err.message);
+          toast.error(t('bots.deleteError') + err.msg);
         });
     }
   }
@@ -547,6 +550,11 @@ export default function BotForm({
                           size="sm"
                           onClick={copyToClipboard}
                         >
+                          {copied ? (
+                            <Check className="h-4 w-4 text-green-600 mr-2" />
+                          ) : (
+                            <Copy className="h-4 w-4 mr-2" />
+                          )}
                           {t('common.copy')}
                         </Button>
                       </div>

web/src/app/home/bots/components/bot-log/view/BotLogCard.tsx

@@ -1,15 +1,17 @@
 'use client';
 
+import { useState } from 'react';
 import { BotLog } from '@/app/infra/http/requestParam/bots/GetBotLogsResponse';
 import styles from './botLog.module.css';
 import { httpClient } from '@/app/infra/http/HttpClient';
 import { PhotoProvider } from 'react-photo-view';
 import { useTranslation } from 'react-i18next';
-import { toast } from 'sonner';
+import { Check } from 'lucide-react';
 
 export function BotLogCard({ botLog }: { botLog: BotLog }) {
   const { t } = useTranslation();
   const baseURL = httpClient.getBaseUrl();
+  const [copied, setCopied] = useState(false);
 
   function formatTime(timestamp: number) {
     const now = new Date();
@@ -75,42 +77,47 @@ export function BotLogCard({ botLog }: { botLog: BotLog }) {
           </div>
           {botLog.message_session_id && (
             <div
-              className={`${styles.tag} ${styles.chatTag}`}
+              className={`${styles.tag} ${styles.chatTag} relative`}
               onClick={() => {
                 navigator.clipboard
                   .writeText(botLog.message_session_id)
                   .then(() => {
-                    toast.success(t('common.copySuccess'));
+                    setCopied(true);
+                    setTimeout(() => setCopied(false), 2000);
                   });
               }}
               title={t('common.clickToCopy')}
             >
-              <svg
-                className="icon"
-                viewBox="0 0 1024 1024"
-                version="1.1"
-                xmlns="http://www.w3.org/2000/svg"
-                p-id="1664"
-                width="16"
-                height="16"
-                fill="currentColor"
-              >
-                <path
-                  d="M96.1 575.7a32.2 32.1 0 1 0 64.4 0 32.2 32.1 0 1 0-64.4 0Z"
-                  p-id="1665"
+              {copied ? (
+                <Check className="w-4 h-4 text-green-600" />
+              ) : (
+                <svg
+                  className="icon"
+                  viewBox="0 0 1024 1024"
+                  version="1.1"
+                  xmlns="http://www.w3.org/2000/svg"
+                  p-id="1664"
+                  width="16"
+                  height="16"
                   fill="currentColor"
-                ></path>
-                <path
-                  d="M742.1 450.7l-269.5-2.1c-14.3-0.1-26 13.8-26 31s11.7 31.3 26 31.4l269.5 2.1c14.3 0.1 26-13.8 26-31s-11.7-31.3-26-31.4zM742.1 577.7l-269.5-2.1c-14.3-0.1-26 13.8-26 31s11.7 31.3 26 31.4l269.5 2.1c14.3 0.2 26-13.8 26-31s-11.7-31.3-26-31.4z"
-                  p-id="1666"
-                  fill="currentColor"
-                ></path>
-                <path
-                  d="M736.1 63.9H417c-70.4 0-128 57.6-128 128h-64.9c-70.4 0-128 57.6-128 128v128c-0.1 17.7 14.4 32 32.2 32 17.8 0 32.2-14.4 32.2-32.1V320c0-35.2 28.8-64 64-64H289v447.8c0 70.4 57.6 128 128 128h255.1c-0.1 35.2-28.8 63.8-64 63.8H224.5c-35.2 0-64-28.8-64-64V703.5c0-17.7-14.4-32.1-32.2-32.1-17.8 0-32.3 14.4-32.3 32.1v128.3c0 70.4 57.6 128 128 128h384.1c70.4 0 128-57.6 128-128h65c70.4 0 128-57.6 128-128V255.9l-193-192z m0.1 63.4l127.7 128.3H800c-35.2 0-64-28.8-64-64v-64.3h0.2z m64 641H416.1c-35.2 0-64-28.8-64-64v-513c0-35.2 28.8-64 64-64H671V191c0 70.4 57.6 128 128 128h65.2v385.3c0 35.2-28.8 64-64 64z"
-                  p-id="1667"
-                  fill="currentColor"
-                ></path>
-              </svg>
+                >
+                  <path
+                    d="M96.1 575.7a32.2 32.1 0 1 0 64.4 0 32.2 32.1 0 1 0-64.4 0Z"
+                    p-id="1665"
+                    fill="currentColor"
+                  ></path>
+                  <path
+                    d="M742.1 450.7l-269.5-2.1c-14.3-0.1-26 13.8-26 31s11.7 31.3 26 31.4l269.5 2.1c14.3 0.1 26-13.8 26-31s-11.7-31.3-26-31.4zM742.1 577.7l-269.5-2.1c-14.3-0.1-26 13.8-26 31s11.7 31.3 26 31.4l269.5 2.1c14.3 0.2 26-13.8 26-31s-11.7-31.3-26-31.4z"
+                    p-id="1666"
+                    fill="currentColor"
+                  ></path>
+                  <path
+                    d="M736.1 63.9H417c-70.4 0-128 57.6-128 128h-64.9c-70.4 0-128 57.6-128 128v128c-0.1 17.7 14.4 32 32.2 32 17.8 0 32.2-14.4 32.2-32.1V320c0-35.2 28.8-64 64-64H289v447.8c0 70.4 57.6 128 128 128h255.1c-0.1 35.2-28.8 63.8-64 63.8H224.5c-35.2 0-64-28.8-64-64V703.5c0-17.7-14.4-32.1-32.2-32.1-17.8 0-32.3 14.4-32.3 32.1v128.3c0 70.4 57.6 128 128 128h384.1c70.4 0 128-57.6 128-128h65c70.4 0 128-57.6 128-128V255.9l-193-192z m0.1 63.4l127.7 128.3H800c-35.2 0-64-28.8-64-64v-64.3h0.2z m64 641H416.1c-35.2 0-64-28.8-64-64v-513c0-35.2 28.8-64 64-64H671V191c0 70.4 57.6 128 128 128h65.2v385.3c0 35.2-28.8 64-64 64z"
+                    p-id="1667"
+                    fill="currentColor"
+                  ></path>
+                </svg>
+              )}
 
               <span className={`${styles.chatId}`}>
                 {getSubChatId(botLog.message_session_id)}

web/src/app/home/bots/page.tsx

@@ -11,6 +11,7 @@ import { toast } from 'sonner';
 import { useTranslation } from 'react-i18next';
 import { extractI18nObject } from '@/i18n/I18nProvider';
 import BotDetailDialog from '@/app/home/bots/BotDetailDialog';
+import { CustomApiError } from '@/app/infra/entities/common';
 
 export default function BotConfigPage() {
   const { t } = useTranslation();
@@ -54,10 +55,7 @@ export default function BotConfigPage() {
       })
       .catch((err) => {
         console.error('get bot list error', err);
-        toast.error(t('bots.getBotListError') + err.message);
-      })
-      .finally(() => {
-        // setIsLoading(false);
+        toast.error(t('bots.getBotListError') + (err as CustomApiError).msg);
       });
   }