@lobehub/lobehub 2.0.0-next.332 → 2.0.0-next.333

package/docs/self-hosting/server-database/vercel.mdx

@@ -1,13 +1,13 @@
 ---
 title: Deploy LobeChat with database on Vercel
 description: >-
-  Learn how to deploy LobeChat with database on Vercel with ease, including: database, authentication and S3 storage service.
-
+  Learn how to deploy LobeChat with database on Vercel with ease, including:
+  database, authentication and S3 storage service.
 tags:
   - Deploy LobeChat
   - Vercel Deployment
-  - OpenAI API Key
-  - Custom Domain Binding
+  - Better Auth
+  - S3 Storage
 ---
 
 # Deploying Server Database Version on Vercel
@@ -18,7 +18,6 @@ This article will detail how to deploy the server database version of LobeChat o
   Before proceeding, please make sure of the following:
 
   - Export all data, as after deploying the server-side database, existing user data cannot be automatically migrated and can only be manually imported after backup!
-  - The `ACCESS_CODE` in the environment variables is either unset or cleared!
   - When configuring the environment variables required for the server-side database, make sure to fill in all of them before deployment, otherwise you may encounter database migration issues!
 </Callout>
 
@@ -50,9 +49,6 @@ This article will detail how to deploy the server database version of LobeChat o
       ```shell
       # Serverless Postgres DB Url
       DATABASE_URL=
-
-      # Specify service mode as server, otherwise it will not enter the server-side database
-      NEXT_PUBLIC_SERVICE_MODE=server
       ```
 
       An example of filling in Vercel is as follows:
@@ -69,9 +65,6 @@ This article will detail how to deploy the server database version of LobeChat o
 
       # Specify Postgres database driver as node
       DATABASE_DRIVER=node
-
-      # Specify service mode as server, otherwise it will not enter the server-side database
-      NEXT_PUBLIC_SERVICE_MODE=server
       ```
 
       An example of filling in Vercel is as follows:
@@ -88,11 +81,9 @@ This article will detail how to deploy the server database version of LobeChat o
 
   ### Add the `KEY_VAULTS_SECRET` Environment Variable
 
-  After adding the `DATABASE_URL` environment variable for the database, you need to add a `KEY_VAULTS_SECRET` environment variable. This variable is used to encrypt sensitive information such as apikeys stored by users. You can generate a random 32-character string as the key using `openssl rand -base64 32`.
+  After adding the `DATABASE_URL` environment variable for the database, you need to add a `KEY_VAULTS_SECRET` environment variable. This variable is used to encrypt sensitive information such as apikeys stored by users. Click the button below to generate:
 
-  ```shell
-  KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
-  ```
+  <GenerateSecret envName="KEY_VAULTS_SECRET" />
 
   Make sure to add this to the Vercel environment variables as well.
 
@@ -106,66 +97,26 @@ This article will detail how to deploy the server database version of LobeChat o
 The server-side database needs to be paired with a user authentication service to function properly. Therefore, the corresponding authentication service needs to be configured.
 
 <Steps>
-  ### Prepare Clerk Authentication Service
-
-  Go to [Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) to register and create an application to obtain the corresponding Public Key and Secret Key.
-
-  <Callout type={'info'}>
-    If you are not familiar with Clerk, you can refer to [Authentication
-    Service-Clerk](/en/docs/self-hosting/advanced/authentication#clerk) for details on using Clerk.
-  </Callout>
-
-  ### Add Public and Private Key Environment Variables in Vercel
-
-  In Vercel's deployment environment variables, add the `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` and `CLERK_SECRET_KEY` environment variables. You can click on "API Keys" in the menu, then copy the corresponding values and paste them into Vercel's environment variables.
-
-  <Image alt={'Find the corresponding public and private key environment variables in Clerk'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/89883703-7a1a-4a11-b944-5d804544e57c'} />
-
-  The environment variables required for this step are as follows:
-
-  ```shell
-  NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-  CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-  ```
-
-  Add the above variables to Vercel:
+  ### Add Authentication Environment Variables
 
-  <Image alt={'Add Clerk public and private key environment variables in Vercel'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/2bfa13df-6e20-4768-97c0-4dad06c85a2f'} />
+  In Vercel's deployment environment variables, add the following environment variables to enable authentication (powered by [Better Auth](https://www.better-auth.com)):
 
-  ### Create and Configure Webhook in Clerk
+  Click the button below to generate `AUTH_SECRET` (session encryption key):
 
-  Since we let Clerk fully handle user authentication and management, we need Clerk to notify our application and store data in the database when there are changes in the user's lifecycle (create, update, delete). We achieve this requirement through the Webhook provided by Clerk.
+  <GenerateSecret envName="AUTH_SECRET" />
 
-  We need to add an endpoint in Clerk's Webhooks to inform Clerk to send notifications to this endpoint when a user's information changes.
+  You also need to configure the `JWKS_KEY` environment variable for signing and verifying JWTs. Click the button below to generate:
 
-  <Image alt={'Add Webhooks endpoint in Clerk'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/f50f47fb-5e8e-4930-bf4e-8cf6f5b8afb9'} />
+  <GenerateJWKSKey />
 
-  Fill in the endpoint with the URL of your Vercel project, such as `https://your-project.vercel.app/api/webhooks/clerk`. Then, subscribe to events by checking the three user events (`user.created`, `user.deleted`, `user.updated`), and click create.
+  With these variables, users can register and login with email and password.
 
-  <Callout type={'warning'}>
-    The `https://` in the URL is essential to maintain the integrity of the URL.
+  <Callout type={'info'}>
+    For advanced features like SSO providers, magic link login, and email verification, see [Authentication Service](/docs/self-hosting/advanced/auth).
   </Callout>
-
-  <Image alt={'Configure URL and user events when adding Clerk Webhooks'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/0249ea56-ab17-4aa9-a56c-9ebd556c2645'} />
-
-  ### Add Webhook Secret to Vercel Environment Variables
-
-  After creation, you can find the secret of this Webhook in the bottom right corner:
-
-  <Image alt={'View Clerk Webhooks secret'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/fab4abb2-584b-49de-9340-813382951635'} />
-
-  The environment variable corresponding to this secret is `CLERK_WEBHOOK_SECRET`:
-
-  ```shell
-  CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
-  ```
-
-  Add it to Vercel's environment variables:
-
-  <Image alt={'Add Clerk Webhooks secret in Vercel'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/5fdc9479-007f-46ab-9d6e-a9603e949116'} />
 </Steps>
 
-By completing these steps, you have successfully configured the Clerk authentication service. Next, we will configure the S3 storage service.
+By completing these steps, you have successfully configured the authentication service. Next, we will configure the S3 storage service.
 
 ## 3. Configure S3 Storage Service
 
@@ -320,17 +271,13 @@ For easy copying, here is a summary of the environment variables required to con
 ```shell
 APP_URL=https://your-project.com
 
-# Specify the service mode as server
-NEXT_PUBLIC_SERVICE_MODE=server
-
 # Postgres database URL
 DATABASE_URL=
 KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
 
-# Clerk related configurations
-NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+# Authentication
+AUTH_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
+JWKS_KEY='{"keys":[...]}'
 
 # S3 related configurations
 # S3 keys

package/docs/self-hosting/server-database/vercel.zh-CN.mdx

@@ -4,7 +4,7 @@ description: 本文详细介绍如何在 Vercel 中部署服务端数据库版 L
 tags:
   - 服务端数据库
   - Postgres
-  - Clerk
+  - Better Auth
   - S3存储服务
   - Vercel部署
   - 数据库配置
@@ -20,7 +20,6 @@ tags:
   进行后续操作前，请务必确认以下事项：
 
   - 导出所有数据，部署服务端数据库后，原有用户数据无法自动迁移，只能提前备份后进行手动导入！
-  - 环境变量中的`ACCESS_CODE`未设置或已清除！
   - 配置服务端数据库所需要的环境变量时，需全部填入后再进行部署，否则可能遭遇数据库迁移问题！
 </Callout>
 
@@ -51,9 +50,6 @@ tags:
       ```shell
       # Serverless Postgres DB Url
       DATABASE_URL=
-
-      # 指定 service mode 为 server，否则不会进入服务端数据库
-      NEXT_PUBLIC_SERVICE_MODE=server
       ```
 
       在 Vercel 中填写的示例如下：
@@ -70,9 +66,6 @@ tags:
 
       # 指定 Postgres database driver 为 node
       DATABASE_DRIVER=node
-
-      # 指定 service mode 为 server，否则不会进入服务端数据库
-      NEXT_PUBLIC_SERVICE_MODE=server
       ```
 
       在 Vercel 中填写的示例如下：
@@ -88,11 +81,9 @@ tags:
 
   ### 添加 `KEY_VAULTS_SECRET` 环境变量
 
-  在完成数据库 `DATABASE_URL` 环境变量添加后，需要添加一个 `KEY_VAULTS_SECRET` 环境变量。该变量用于加密用户存储的 apikey 等敏感信息。你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为密钥。
+  在完成数据库 `DATABASE_URL` 环境变量添加后，需要添加一个 `KEY_VAULTS_SECRET` 环境变量。该变量用于加密用户存储的 apikey 等敏感信息。点击下方按钮一键生成：
 
-  ```shell
-  KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
-  ```
+  <GenerateSecret envName="KEY_VAULTS_SECRET" />
 
   同样需要将其添加到 Vercel 环境变量中。
 
@@ -106,64 +97,26 @@ tags:
 服务端数据库需要搭配用户身份验证服务才可以正常使用。因此需要配置对应的身份验证服务。
 
 <Steps>
-  ### 准备 Clerk 身份验证服务
-
-  前往 [Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) 注册并创建应用，获取相应的 Public Key 和 Secret Key。
-
-  <Callout type={'info'}>
-    如果对 Clerk 不太了解，可以查阅 [身份验证服务 -
-    Clerk](/zh/docs/self-hosting/advanced/authentication#clerk) 了解 Clerk 的使用详情。
-  </Callout>
-
-  ### 在 Vercel 中添加公、私钥环境变量
-
-  在 Vercel 的部署环境变量中，添加 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 和 `CLERK_SECRET_KEY` 环境变量。你可以在菜单中点击「API Keys」，然后复制对应的值填入 Vercel 的环境变量中。
-
-  <Image alt={'在 Clerk 中找到对应的公私钥环境变量'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/89883703-7a1a-4a11-b944-5d804544e57c'} />
-
-  此步骤所需的环境变量如下：
-
-  ```shell
-  NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-  CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-  ```
+  ### 添加身份验证环境变量
 
-  添加上述变量到 Vercel 中：
+  在 Vercel 的部署环境变量中，添加以下环境变量以启用身份验证（基于 [Better Auth](https://www.better-auth.com)）：
 
-  <Image alt={'在 Vercel 中添加 Clerk 公私钥环境变量'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/2bfa13df-6e20-4768-97c0-4dad06c85a2f'} />
+  点击下方按钮一键生成 `AUTH_SECRET`（会话加密密钥）：
 
-  ### 在 Clerk 中创建并配置 Webhook
+  <GenerateSecret envName="AUTH_SECRET" />
 
-  由于我们让 Clerk 完全接管用户鉴权与管理，因此我们需要在 Clerk 用户生命周期变更时（创建、更新、删除）中通知我们的应用并存储落库。我们通过 Clerk 提供的 Webhook 来实现这一诉求。
+  同时需要配置 `JWKS_KEY` 环境变量，用于签名和验证 JWT。点击下方按钮一键生成：
 
-  我们需要在 Clerk 的 Webhooks 中添加一个端点（Endpoint），告诉 Clerk 当用户发生变更时，向这个端点发送通知。
+  <GenerateJWKSKey />
 
-  <Image alt={'Clerk 添加 Webhooks 端点'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/f50f47fb-5e8e-4930-bf4e-8cf6f5b8afb9'} />
+  配置这些变量后，用户即可使用邮箱和密码注册登录。
 
-  在 endpoint 中填写你的 Vercel 项目的 URL，如 `https://your-project.vercel.app/api/webhooks/clerk`。然后在订阅事件（Subscribe to events）中，勾选 user 的三个事件（`user.created` 、`user.deleted`、`user.updated`），然后点击创建。
-
-  <Callout type={'warning'}>URL 的`https://`不可缺失，须保持 URL 的完整性</Callout>
-
-  <Image alt={'添加 Clerk Webhooks 时，配置 URL 和用户事件'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/0249ea56-ab17-4aa9-a56c-9ebd556c2645'} />
-
-  ### 将 Webhook 秘钥添加到 Vercel 环境变量
-
-  创建完毕后，可以在右下角找到该 Webhook 的秘钥：
-
-  <Image alt={'查看 Clerk Webhooks 秘钥'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/fab4abb2-584b-49de-9340-813382951635'} />
-
-  这个秘钥所对应的环境变量名为 `CLERK_WEBHOOK_SECRET`：
-
-  ```shell
-  CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
-  ```
-
-  将其添加到 Vercel 的环境变量中：
-
-  <Image alt={'在 Vercel 中 添加 Clerk Webhooks 秘钥'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/5fdc9479-007f-46ab-9d6e-a9603e949116'} />
+  <Callout type={'info'}>
+    如需 SSO 登录、魔法链接登录、邮箱验证等高级功能，请参阅 [身份验证服务](/zh/docs/self-hosting/advanced/auth)。
+  </Callout>
 </Steps>
 
-这样，你已经成功配置了 Clerk 身份验证服务。接下来我们将配置 S3 存储服务。
+这样，你已经成功配置了身份验证服务。接下来我们将配置 S3 存储服务。
 
 ## 三、 配置 S3 存储服务
 
@@ -313,17 +266,13 @@ tags:
 ```shell
 APP_URL=https://your-project.com
 
-# 指定服务模式为 server
-NEXT_PUBLIC_SERVICE_MODE=server
-
 # Postgres 数据库 URL
 DATABASE_URL=
 KEY_VAULTS_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
 
-# Clerk 相关配置
-NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_live_xxxxxxxxxxx
-CLERK_SECRET_KEY=sk_live_xxxxxxxxxxxxxxxxxxxxxx
-CLERK_WEBHOOK_SECRET=whsec_xxxxxxxxxxxxxxxxxxxxxx
+# 身份验证
+AUTH_SECRET=jgwsK28dspyVQoIf8/M3IIHl1h6LYYceSYNXeLpy6uk=
+JWKS_KEY='{"keys":[...]}'
 
 # S3 相关配置
 # S3 秘钥

package/docs/self-hosting/server-database/zeabur.mdx

@@ -1,8 +1,8 @@
 ---
 title: Deploying LobeChat Database on Zeabur
 description: >-
-  Learn how to deploy LobeChat on Zeabur with ease. Follow the provided steps to set up your chat application seamlessly.
-
+  Learn how to deploy LobeChat on Zeabur with ease. Follow the provided steps to
+  set up your chat application seamlessly.
 tags:
   - Deploy LobeChat
   - Zeabur Deployment

package/docs/self-hosting/server-database.mdx

@@ -47,24 +47,6 @@ Before deployment, make sure you have a Postgres database instance ready. You ca
 Since we support file-based conversations/knowledge base conversations, we need to install the `pgvector` plugin for Postgres. This plugin provides vector search capabilities and is a key component for LobeChat to implement RAG.
 
 <Steps>
-  ### `NEXT_PUBLIC_SERVICE_MODE`
-
-  LobeChat supports both client-side and server-side databases, so we provide an environment variable for switching modes, which is `NEXT_PUBLIC_SERVICE_MODE`, with a default value of `client`.
-
-  For server-side database deployment scenarios, you need to set `NEXT_PUBLIC_SERVICE_MODE` to `server`.
-
-  <Callout type={'info'}>
-    In the official `lobe-chat-database` Docker image, this environment variable is already set to
-    `server` by default. Therefore, if you deploy using the Docker image, you do not need to configure
-    this environment variable again.
-  </Callout>
-
-  <Callout type={'tip'}>
-    Since environment variables starting with `NEXT_PUBLIC` take effect in the front-end code, they cannot be modified through container runtime injection. (Refer to the `next.js` documentation [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables)). This is why we chose to create a separate DB version image.
-
-    If you need to modify variables with the `NEXT_PUBLIC` prefix in a Docker deployment, you must build the image yourself and inject your own `NEXT_PUBLIC` prefixed environment variables during the build.
-  </Callout>
-
   ### `DATABASE_URL`
 
   The core of configuring the database is to add the `DATABASE_URL` environment variable and fill in the Postgres database connection URL you have prepared. The typical format of the database connection URL is `postgres://username:password@host:port/database`.
@@ -95,7 +77,7 @@ Since we support file-based conversations/knowledge base conversations, we need
 
   <Callout type={'info'}>
     You can generate a random 32-character string as the value of `KEY_VAULTS_SECRET` using `openssl
-                                                      rand -base64 32`.
+                                                              rand -base64 32`.
   </Callout>
 </Steps>
 

package/docs/self-hosting/server-database.zh-CN.mdx

@@ -45,23 +45,6 @@ LobeChat 默认使用客户端数据库（IndexedDB），同时也支持使用
 同时，由于我们支持了文件对话 / 知识库对话的能力，因此我们需要为 Postgres 安装 `pgvector` 插件，该插件提供了向量搜索的能力，是 LobeChat 实现 RAG 的重要构件之一。
 
 <Steps>
-  ### `NEXT_PUBLIC_SERVICE_MODE`
-
-  LobeChat 同时支持了客户端数据库和服务端数据库，因此我们提供了一个环境变量用于切换模式，这个变量为 `NEXT_PUBLIC_SERVICE_MODE`，该值默认为 `client`。
-
-  针对服务端数据库部署场景，你需要将 `NEXT_PUBLIC_SERVICE_MODE` 设置为 `server`。
-
-  <Callout type={'info'}>
-    在官方的 `lobe-chat-database` Docker 镜像中，已经默认将该环境变量设为 `server`，因此如果你使用
-    Docker 镜像部署，则无需再配置该环境变量。
-  </Callout>
-
-  <Callout type={'tip'}>
-    由于 `NEXT_PUBLIC` 开头的环境变量是在前端代码中生效的，而因此无法通过容器运行时注入进行修改。 （`next.js`的参考文档 [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables) ) 这也是为什么我们选择再打一个 DB 版镜像的原因。
-
-    如果你需要在 Docker 部署中修改 `NEXT_PUBLIC` 前缀的变量，你必须自行构建镜像，在 build 时就把自己的 `NEXT_PUBLIC` 开头的环境变量打进去。
-  </Callout>
-
   ### `DATABASE_URL`
 
   配置数据库，核心是添加 `DATABASE_URL` 环境变量，将你准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。

package/docs/self-hosting/start.mdx

@@ -1,8 +1,8 @@
 ---
 title: Build Your Own LobeChat - Choose Your Deployment Platform
 description: >-
-  Explore multiple deployment platforms like Vercel, Docker, Docker Compose, and more to deploy LobeChat. Choose the platform that best suits your needs.
-
+  Explore multiple deployment platforms like Vercel, Docker, Docker Compose, and
+  more to deploy LobeChat. Choose the platform that best suits your needs.
 tags:
   - Lobe Chat
   - Deployment Platform

package/docs/self-hosting/start.zh-CN.mdx

@@ -1,8 +1,8 @@
 ---
 title: 构建属于自己的 LobeChat - 自选部署平台
 description: >-
-  选择适合自己的部署平台，构建个性化的 Lobe Chat。支持 Docker、Docker Compose、Netlify、Railway、Repocloud、Sealos、Vercel 和 Zeabur 部署。
-
+  选择适合自己的部署平台，构建个性化的 Lobe Chat。支持 Docker、Docker
+  Compose、Netlify、Railway、Repocloud、Sealos、Vercel 和 Zeabur 部署。
 tags:
   - Lobe Chat
   - 部署平台

package/locales/en-US/desktop-onboarding.json

@@ -73,6 +73,7 @@
   "screen5.badge": "Sign in",
   "screen5.description": "Sign in to sync Agents, Groups, settings, and Context across all devices.",
   "screen5.errors.desktopOnlyOidc": "OIDC authorization is only available in the desktop app runtime.",
+  "screen5.legacyLocalDb.link": "Migrate legacy local database",
   "screen5.methods.cloud.description": "Sign in with your LobeHub Cloud account to sync everything seamlessly",
   "screen5.methods.cloud.name": "LobeHub Cloud",
   "screen5.methods.selfhost.description": "Connect to your own LobeHub server instance",

package/locales/zh-CN/desktop-onboarding.json

@@ -73,6 +73,7 @@
   "screen5.badge": "登录",
   "screen5.description": "登录以在所有设备间同步代理、群组、设置和上下文。",
   "screen5.errors.desktopOnlyOidc": "OIDC 授权仅在桌面端运行时可用。",
+  "screen5.legacyLocalDb.link": "迁移旧版本地数据库",
   "screen5.methods.cloud.description": "使用您的 LobeHub 云账户登录，实现无缝同步",
   "screen5.methods.cloud.name": "LobeHub Cloud",
   "screen5.methods.selfhost.description": "连接到你自己的 LobeHub 服务实例",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/lobehub",
-  "version": "2.0.0-next.332",
+  "version": "2.0.0-next.333",
   "description": "LobeHub - an open-source,comprehensive AI Agent framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",
@@ -207,7 +207,7 @@
     "@lobehub/icons": "^4.0.2",
     "@lobehub/market-sdk": "0.29.1",
     "@lobehub/tts": "^4.0.2",
-    "@lobehub/ui": "^4.24.0",
+    "@lobehub/ui": "^4.25.0",
     "@modelcontextprotocol/sdk": "^1.25.1",
     "@neondatabase/serverless": "^1.0.2",
     "@next/third-parties": "^16.1.1",

package/packages/builtin-tool-cloud-sandbox/src/systemRole.ts

@@ -11,6 +11,58 @@ export const systemPrompt = `You have access to a Cloud Sandbox that provides a
 </sandbox_environment>
 
 
+<preinstalled_software>
+**IMPORTANT: Prefer Pre-installed Software**
+The sandbox comes with pre-installed software and libraries. **Always prioritize using these pre-installed tools** when they can solve the user's problem, rather than installing additional packages.
+
+**Operating System:**
+- Debian 12
+
+**Programming Languages & Runtimes:**
+- Python (with pip)
+- Node.js (with npm)
+
+**Build Tools:**
+- build-essential 12.9
+- gcc/g++ 12.2.0
+
+**Python Libraries (Pre-installed):**
+- numpy 2.4.1 - Numerical computing
+- scipy 1.17.0 - Scientific computing
+- pandas 2.3.3 - Data analysis
+- matplotlib 3.10.8 - Static visualization
+- plotly 6.5.2 - Interactive visualization
+- scikit-learn 1.8.0 - Machine learning
+- opencv-python 4.13.0.90 - Computer vision
+- Pillow 12.1.0 - Image processing
+- wheel 0.45.1 - Python package installer
+
+**Document & Media Tools:**
+- LibreOffice - Office document processing
+- Pandoc - Document format conversion
+- pdftoppm - PDF to image conversion
+- FFmpeg 5.1.8-0+deb12u1 - Audio/video processing
+
+**Browser Automation:**
+- Playwright - Browser automation
+- marpc-cli - Browser-based PPTX generation
+
+**Fonts:**
+- Noto Sans CJK - Chinese/Japanese/Korean sans-serif font
+- Noto Serif CJK - Chinese/Japanese/Korean serif font
+
+**NOT Available (do not attempt to use):**
+- Tesseract (OCR) - Not installed
+- Puppeteer - Not installed, use Playwright instead
+- mermaid-cli - Not installed
+
+**Installation Guidelines:**
+- Only install additional packages when pre-installed software cannot fulfill the requirement
+- When Python libraries are already available, use them directly without pip install
+- For document generation, prioritize LibreOffice and Pandoc before Python libraries
+</preinstalled_software>
+
+
 <core_capabilities>
 You have access to the following tools for interacting with the cloud sandbox:
 
@@ -114,7 +166,15 @@ When code execution produces any output files (documents, images, data, etc.), y
 When executing Python code:
 
 
+**Using Pre-installed Libraries:**
+- **Always check if required libraries are pre-installed** (see preinstalled_software section)
+- numpy, scipy, pandas, matplotlib, plotly, scikit-learn, opencv-python, Pillow are already available
+- **Skip pip install** for pre-installed libraries - use them directly
+- Only use \`pip install\` for libraries NOT in the pre-installed list
+
+
 **Visualization with Matplotlib:**
+- matplotlib 3.10.8 is pre-installed - use directly without installation
 - Never use seaborn library
 - Give each chart its own distinct plot (no subplots)
 - Never set specific colors unless explicitly asked by the user
@@ -127,10 +187,10 @@ You MUST use the following libraries for each supported file format:
 - **DOCX**: Use \`python-docx\`
 - **XLSX**: Use \`openpyxl\`
 - **PPTX**: Use \`python-pptx\`
-- **CSV**: Use \`pandas\`
+- **CSV**: Use pre-installed \`pandas\` (no installation needed)
 - **ODS/ODT/ODP**: Use \`odfpy\`
 
-Install required packages first: \`pip install <package-name>\`
+For libraries NOT pre-installed: Install with \`pip install <package-name>\` before use.
 **After successful generation, automatically export the document file.**
 
 

package/packages/conversation-flow/src/__tests__/fixtures/inputs/tasks/index.ts

@@ -1,8 +1,10 @@
 import type { Message } from '../../../../types';
+import multiTasksWithSummary from './multi-tasks-with-summary.json';
 import simple from './simple.json';
 import withSummary from './with-summary.json';
 
 export const tasks = {
+  multiTasksWithSummary: multiTasksWithSummary as Message[],
   simple: simple as Message[],
   withSummary: withSummary as Message[],
 };