npm - @lobehub/chat - Versions diffs - 1.55.1 → 1.55.3 - Mend

@lobehub/chat 1.55.1 → 1.55.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (23) hide show

package/CHANGELOG.md CHANGED Viewed

@@ -2,6 +2,56 @@
 # Changelog
+### [Version 1.55.3](https://github.com/lobehub/lobe-chat/compare/v1.55.2...v1.55.3)
+<sup>Released on **2025-02-15**</sup>
+#### 💄 Styles
+- **misc**: Add deepseek r1 distill models for qwen series.
+<br/>
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+#### Styles
+- **misc**: Add deepseek r1 distill models for qwen series, closes [#5850](https://github.com/lobehub/lobe-chat/issues/5850) ([4a96a05](https://github.com/lobehub/lobe-chat/commit/4a96a05))
+</details>
+<div align="right">
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+</div>
+### [Version 1.55.2](https://github.com/lobehub/lobe-chat/compare/v1.55.1...v1.55.2)
+<sup>Released on **2025-02-15**</sup>
+#### 🐛 Bug Fixes
+- **misc**: Avoid blank reasoning with OpenRouter.
+<br/>
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+#### What's fixed
+- **misc**: Avoid blank reasoning with OpenRouter, closes [#6153](https://github.com/lobehub/lobe-chat/issues/6153) ([c2278d1](https://github.com/lobehub/lobe-chat/commit/c2278d1))
+</details>
+<div align="right">
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+</div>
 ### [Version 1.55.1](https://github.com/lobehub/lobe-chat/compare/v1.55.0...v1.55.1)
 <sup>Released on **2025-02-15**</sup>

package/changelog/v1.json CHANGED Viewed

@@ -1,4 +1,22 @@
 [
+  {
+    "children": {
+      "improvements": [
+        "Add deepseek r1 distill models for qwen series."
+      ]
+    },
+    "date": "2025-02-15",
+    "version": "1.55.3"
+  },
+  {
+    "children": {
+      "fixes": [
+        "Avoid blank reasoning with OpenRouter."
+      ]
+    },
+    "date": "2025-02-15",
+    "version": "1.55.2"
+  },
   {
     "children": {
       "fixes": [

package/docs/changelog/2025-02-02-deepseek-r1.mdx CHANGED Viewed

@@ -1,10 +1,10 @@
 ---
 title: >-
-  LobeChat Integrates DeepSeek R1, Bringing a Revolutionary Chain of Thought Experience
+  LobeChat Integrates DeepSeek R1, Bringing a Revolutionary Chain of Thought
+  Experience
 description: >-
-  LobeChat v1.49.12 fully supports the DeepSeek R1 model, providing users with an unprecedented interactive experience in the chain of thought.
+  LobeChat v1.49.12 fully supports the DeepSeek R1 model, providing users with
+  an unprecedented interactive experience in the chain of thought.
 tags:
   - LobeChat
   - DeepSeek

package/docs/self-hosting/advanced/auth/next-auth/casdoor.mdx CHANGED Viewed

@@ -113,12 +113,13 @@ If you are deploying using a public network, the following assumptions apply:
   - Method: `POST`
   - Content Type: `application/json`
   - Headers: `casdoor-secret`: `Your Webhook Secret`
-  > The secret is generated by yourself, you can visit https://generate-secret.vercel.app/10 to generate a 10 bit secret.
+  > The secret is generated by yourself, you can visit [https://generate-secret.vercel.app/10](https://generate-secret.vercel.app/10) to generate a 10 bit secret.
   - Event: `update-user`
   - Is user extented: `true`
-  Save and Exit, then copy the Webhook secret and fill it in the environment variable `CASDOOR_WEBHOOK_SECRET.
+  Save and Exit, then copy the Webhook secret and fill it in the environment variable \`CASDOOR\_WEBHOOK\_SECRET.
   ### Configure Environment Variables
@@ -140,7 +141,7 @@ If you are deploying using a public network, the following assumptions apply:
   | `AUTH_CASDOOR_SECRET`     | Required | The client secret from the Casdoor application details page.                                                                                                                                       |
   | `AUTH_CASDOOR_ISSUER`     | Required | The OpenID Connect issuer for the Casdoor provider.                                                                                                                                                |
   | `NEXTAUTH_URL`            | Required | This URL specifies the callback address for Auth.js during OAuth verification and needs to be set only if the default generated redirect address is incorrect. `https://lobe.example.com/api/auth` |
-  | `CASDOOR_WEBHOOK_SECRET`  | Optional | A key used to verify whether the request sent by Casdoor is legal.                                                                                                                                |
+  | `CASDOOR_WEBHOOK_SECRET`  | Optional | A key used to verify whether the request sent by Casdoor is legal.                                                                                                                                 |
   <Callout type={'tip'}>
     Visit [📘 Environment Variables](/docs/self-hosting/environment-variables/auth#casdoor) for

package/docs/self-hosting/advanced/auth/next-auth/casdoor.zh-CN.mdx CHANGED Viewed

@@ -102,7 +102,8 @@ tags:
   - 方法：`POST`
   - 内容类型：`application/json`
   - 协议头：`casdoor-secret`: `你的Webhook密钥`
-  > 密钥由你自己生成，用于验证 Casdoor 发送的请求是否合法。 可以前往 https://generate-secret.vercel.app/10 生成一个 10 位的密钥。
+  > 密钥由你自己生成，用于验证 Casdoor 发送的请求是否合法。 可以前往 [https://generate-secret.vercel.app/10](https://generate-secret.vercel.app/10) 生成一个 10 位的密钥。
   - 事件：`update-user`
   - 拓展用户字段：`true`
@@ -112,7 +113,7 @@ tags:
   ### 关闭注册
   为了保证你的应用安全，建议关闭 Casdoor 的注册功能，改为由管理员手动添加用户。
   前往 `身份认证` -> `应用`，将 `启用注册` 设置为 `否`。
   <Callout type={'warning'}>
@@ -139,7 +140,7 @@ tags:
   | `AUTH_CASDOOR_SECRET`     | 必选 | Casdoor 应用详情页的客户端密钥                                                                              |
   | `AUTH_CASDOOR_ISSUER`     | 必选 | Casdoor 提供程序的 OpenID Connect 颁发者。                                                                |
   | `NEXTAUTH_URL`            | 必选 | 该 URL 用于指定 Auth.js 在执行 OAuth 验证时的回调地址，当默认生成的重定向地址发生不正确时才需要设置。`https://lobe.example.com/api/auth` |
-  | `CASDOOR_WEBHOOK_SECRET`  | 可选 | 用于验证 Casdoor 发送的 Webhook 请求是否合法的密钥。 |
+  | `CASDOOR_WEBHOOK_SECRET`  | 可选 | 用于验证 Casdoor 发送的 Webhook 请求是否合法的密钥。                                                              |
   <Callout type={'tip'}>
     前往 [📘 环境变量](/zh/docs/self-hosting/environment-variables/auth#casdoor) 可查阅相关变量详情。

package/docs/self-hosting/advanced/auth/next-auth/logto.mdx CHANGED Viewed

@@ -67,15 +67,15 @@ If you are using Logto Cloud, assume its endpoint domain is `https://example.log
   When deploying LobeChat, you need to configure the following environment variables:
-  | Environment Variable      | Type     | Description                                                                                                                                                                            |
-  | ------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-  | `NEXT_AUTH_SECRET`        | Required | The key used to encrypt Auth.js session tokens. You can generate a key using the command: `openssl rand -base64 32`                                                                    |
-  | `NEXT_AUTH_SSO_PROVIDERS` | Required | Select the single sign-on provider for LobeChat. For Logto, enter `logto`.                                                                                                             |
-  | `AUTH_LOGTO_ID`           | Required | The Client ID from the Logto App details page                                                                                                                                          |
-  | `AUTH_LOGTO_SECRET`       | Required | The Client Secret from the Logto App details page                                                                                                                                      |
-  | `AUTH_LOGTO_ISSUER`       | Required | OpenID Connect issuer of the Logto provider                                                                                                                                            |
-  | `NEXTAUTH_URL`            | Required | This URL specifies the callback address for Auth.js during OAuth verification, needed only if the default generated redirect address is incorrect. `https://lobe.example.com/api/auth` |
-  | `LOGTO_WEBHOOK_SIGNING_KEY` | Optional | The key used to verify the legality of Webhook requests sent by Logto.                                                                                                               |
+  | Environment Variable        | Type     | Description                                                                                                                                                                            |
+  | --------------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+  | `NEXT_AUTH_SECRET`          | Required | The key used to encrypt Auth.js session tokens. You can generate a key using the command: `openssl rand -base64 32`                                                                    |
+  | `NEXT_AUTH_SSO_PROVIDERS`   | Required | Select the single sign-on provider for LobeChat. For Logto, enter `logto`.                                                                                                             |
+  | `AUTH_LOGTO_ID`             | Required | The Client ID from the Logto App details page                                                                                                                                          |
+  | `AUTH_LOGTO_SECRET`         | Required | The Client Secret from the Logto App details page                                                                                                                                      |
+  | `AUTH_LOGTO_ISSUER`         | Required | OpenID Connect issuer of the Logto provider                                                                                                                                            |
+  | `NEXTAUTH_URL`              | Required | This URL specifies the callback address for Auth.js during OAuth verification, needed only if the default generated redirect address is incorrect. `https://lobe.example.com/api/auth` |
+  | `LOGTO_WEBHOOK_SIGNING_KEY` | Optional | The key used to verify the legality of Webhook requests sent by Logto.                                                                                                                 |
   <Callout type={'tip'}>
     Visit [📘 Environment Variables](/docs/self-hosting/environment-variables/auth#logto) for details on related variables.

package/docs/self-hosting/advanced/auth/next-auth/logto.zh-CN.mdx CHANGED Viewed

@@ -64,15 +64,15 @@ tags:
   在部署 LobeChat 时，你需要配置以下环境变量：
-  | 环境变量                      | 类型 | 描述                                                                                               |
-  | ------------------------- | -- | ------------------------------------------------------------------------------------------------ |
-  | `NEXT_AUTH_SECRET`        | 必选 | 用于加密 Auth.js 会话令牌的密钥。您可以使用以下命令生成秘钥： `openssl rand -base64 32`                                    |
-  | `NEXT_AUTH_SSO_PROVIDERS` | 必选 | 选择 LoboChat 的单点登录提供商。使用 Logto 请填写 `logto`。                                                       |
-  | `AUTH_LOGTO_ID`           | 必选 | Logto App 详情页的 Client ID                                                                         |
-  | `AUTH_LOGTO_SECRET`       | 必选 | Logto App 详情页的 Client Secret                                                                     |
-  | `AUTH_LOGTO_ISSUER`       | 必选 | Logto 提供程序的 OpenID Connect 颁发者                                                                   |
-  | `NEXTAUTH_URL`            | 必选 | 该 URL 用于指定 Auth.js 在执行 OAuth 验证时的回调地址，当默认生成的重定向地址发生不正确时才需要设置。`https://lobe.example.com/api/auth` |
-  | `LOGTO_WEBHOOK_SIGNING_KEY` | 可选 | 用于验证 Logto 发送的 Webhook 请求是否合法的密钥。 |
+  | 环境变量                        | 类型 | 描述                                                                                               |
+  | --------------------------- | -- | ------------------------------------------------------------------------------------------------ |
+  | `NEXT_AUTH_SECRET`          | 必选 | 用于加密 Auth.js 会话令牌的密钥。您可以使用以下命令生成秘钥： `openssl rand -base64 32`                                    |
+  | `NEXT_AUTH_SSO_PROVIDERS`   | 必选 | 选择 LoboChat 的单点登录提供商。使用 Logto 请填写 `logto`。                                                       |
+  | `AUTH_LOGTO_ID`             | 必选 | Logto App 详情页的 Client ID                                                                         |
+  | `AUTH_LOGTO_SECRET`         | 必选 | Logto App 详情页的 Client Secret                                                                     |
+  | `AUTH_LOGTO_ISSUER`         | 必选 | Logto 提供程序的 OpenID Connect 颁发者                                                                   |
+  | `NEXTAUTH_URL`              | 必选 | 该 URL 用于指定 Auth.js 在执行 OAuth 验证时的回调地址，当默认生成的重定向地址发生不正确时才需要设置。`https://lobe.example.com/api/auth` |
+  | `LOGTO_WEBHOOK_SIGNING_KEY` | 可选 | 用于验证 Logto 发送的 Webhook 请求是否合法的密钥。                                                                |
   <Callout type={'tip'}>
     前往 [📘 环境变量](/zh/docs/self-hosting/environment-variables/auth#logto) 可查阅相关变量详情。

package/docs/self-hosting/advanced/model-list.zh-CN.mdx CHANGED Viewed

@@ -43,9 +43,9 @@ id=displayName<maxToken:vision:reasoning:fc:file>
 目前支持的扩展能力有：
-| ---         | 描述                                  |
-| ----------- | ------------------------------------- |
-| `fc`        | 函数调用（function calling）          |
-| `vision`    | 视觉识别                              |
-| `reasoning` | 支持推理                              |
-| `file`      | 文件上传（比较 hack，不建议日常使用） |
+| ---         | 描述                     |
+| ----------- | ---------------------- |
+| `fc`        | 函数调用（function calling） |
+| `vision`    | 视觉识别                   |
+| `reasoning` | 支持推理                   |
+| `file`      | 文件上传（比较 hack，不建议日常使用）  |

package/docs/self-hosting/advanced/observability/langfuse.zh-CN.mdx ADDED Viewed

@@ -0,0 +1,70 @@
+---
+title: LobeChat 的可观测性和追踪
+description: 使用 Langfuse 为你的 LobeChat 应用增强开源可观测性和追踪功能。自动捕获每个请求的详细追踪和指标，以优化和调试你的对话。
+tags:
+  - 可观测性
+  - 追踪
+  - Langfuse
+---
+# 使用 Langfuse 监控你的 LobeChat 应用
+## 什么是 Langfuse？
+[Langfuse](https://langfuse.com/) 是一个 **开源的 LLM 可观测性平台**。启用 Langfuse 集成后，你可以追踪应用数据，以开发、监控和优化 LobeChat 的使用，包括：
+- 应用 [追踪](https://langfuse.com/docs/tracing)
+- 使用模式
+- 按用户和模型的成本数据
+- [评估](https://langfuse.com/docs/scores/overview)
+## 快速开始
+<Steps>
+  ### 设置 Langfuse
+  通过注册 [Langfuse Cloud](https://cloud.langfuse.com) 或 [自托管](https://langfuse.com/docs/deployment/self-host) Langfuse 来获取你的 Langfuse API 密钥。
+  ### 设置 LobeChat
+  有多种方式可以 [自托管 LobeChat](https://lobehub.com/docs/self-hosting/start)。在本示例中，我们将使用 Docker Desktop 部署。
+  <Tabs items={["环境变量", "Docker Desktop 示例"]}>
+    <Tab>
+      在部署 LobeChat 之前，使用你在上一步创建的 Langfuse API 密钥设置以下四个环境变量。
+      ```sh
+      ENABLE_LANGFUSE = '1'
+      LANGFUSE_SECRET_KEY = 'sk-lf...'
+      LANGFUSE_PUBLIC_KEY = 'pk-lf...'
+      LANGFUSE_HOST = 'https://cloud.langfuse.com'
+      ```
+    </Tab>
+    <Tab>
+      在运行 Docker 容器之前，在 Docker Desktop 中设置环境变量，并填入你在上一步创建的 Langfuse API 密钥。
+      <Image alt={'Docker Desktop 中的环境变量'} src={'https://langfuse.com/images/docs/lobechat-docker-desktop-env.png'} />
+    </Tab>
+  </Tabs>
+  ### 在设置中启用分析功能
+  当 LobeChat 运行后，进入 **设置** 中的 **关于** 选项卡，并启用分析功能。这是将追踪数据发送到 Langfuse 所必需的。
+  <Image alt={'LobeChat 设置'} src={'https://langfuse.com/images/docs/lobechat-settings.png'} />
+  ### 在 Langfuse 中查看聊天追踪
+  设置好 LLM 模型密钥后，你就可以开始与 LobeChat 进行交互。
+  <Image alt={'LobeChat 对话'} src={'https://langfuse.com/images/docs/lobechat-converstation.png'} />
+  所有对话都会被自动追踪并发送到 Langfuse。你可以在 Langfuse UI 的 [追踪部分](https://langfuse.com/docs/tracing) 查看这些数据。
+  <Image alt={'LobeChat Trace 示例'} src={'https://langfuse.com/images/docs/lobechat-example-trace.png'} />
+</Steps>
+## 反馈
+如果你有任何反馈或需求，请在 GitHub 上创建 [Issue](https://langfuse.com/issue)，或在 [Discord](https://discord.langfuse.com/) 上与 Langfuse 社区分享你的想法。

package/docs/self-hosting/environment-variables/auth.mdx CHANGED Viewed

@@ -23,11 +23,11 @@ LobeChat provides a complete authentication service capability when deployed. Th
 - Changes after v1.52.0.
-- For users who deploy with Vercel using Next Auth, it is necessary to add the environment variable NEXT_PUBLIC_ENABLE_NEXT_AUTH=1 to ensure that Next Auth is enabled.
-- For users who use Clerk in their self-built image, it is necessary to configure the environment variable NEXT_PUBLIC_ENABLE_NEXT_AUTH=0 to disable Next Auth.\n
-- Other standard deployment scenarios (using Clerk on Vercel and next-auth in Docker) are not affected
+- For users who deploy with Vercel using Next Auth, it is necessary to add the environment variable NEXT\_PUBLIC\_ENABLE\_NEXT\_AUTH=1 to ensure that Next Auth is enabled.
+- For users who use Clerk in their self-built image, it is necessary to configure the environment variable NEXT\_PUBLIC\_ENABLE\_NEXT\_AUTH=0 to disable Next Auth.\n
+- Other standard deployment scenarios (using Clerk on Vercel and next-auth in Docker) are not affected
 #### `NEXT_AUTH_SECRET`

package/docs/self-hosting/environment-variables/auth.zh-CN.mdx CHANGED Viewed

@@ -18,9 +18,10 @@ LobeChat 在部署时提供了完善的身份验证服务能力，以下是相
 ### 通用设置
 #### `NEXT_PUBLIC_ENABLE_NEXT_AUTH`
 - v1.52.0 之后有变更
-- 针对使用 Vercel 部署中使用 next-auth 的用户，需要额外添加 NEXT_PUBLIC_ENABLE_NEXT_AUTH=1 环境变量来确保开启 Next Auth
-- 针对使用自构建镜像中使用 clerk 的用户，需要额外配置 NEXT_PUBLIC_ENABLE_NEXT_AUTH=0 环境变量来关闭 Next Auth
+- 针对使用 Vercel 部署中使用 next-auth 的用户，需要额外添加 NEXT\_PUBLIC\_ENABLE\_NEXT\_AUTH=1 环境变量来确保开启 Next Auth
+- 针对使用自构建镜像中使用 clerk 的用户，需要额外配置 NEXT\_PUBLIC\_ENABLE\_NEXT\_AUTH=0 环境变量来关闭 Next Auth
 - 其他标准部署场景（Vercel 中使用 Clerk 与 Docker 中使用 next-auth ）不受影响
 #### `NEXT_AUTH_SECRET`

package/docs/self-hosting/platform/btpanel.mdx CHANGED Viewed

@@ -37,7 +37,7 @@ To install aaPanel, go to the [aaPanel](https://www.aapanel.com/new/download.htm
 6. After submission, the panel will automatically initialize the application, which will take about `1-3` minutes. It can be accessed after the initialization is completed.
 <Callout type="warning">
-  ⚠️ Do not enable any form of cache in the reverse proxy settings of the panel to avoid affecting the normal operation of the service. Read more at https://github.com/lobehub/lobe-chat/discussions/5986
+  ⚠️ Do not enable any form of cache in the reverse proxy settings of the panel to avoid affecting the normal operation of the service. Read more at [https://github.com/lobehub/lobe-chat/discussions/5986](https://github.com/lobehub/lobe-chat/discussions/5986)
 </Callout>
 ## Visit LobeChat

package/docs/self-hosting/platform/btpanel.zh-CN.mdx CHANGED Viewed

@@ -41,7 +41,7 @@ tags:
 5. 提交后面板会自动进行应用初始化，大概需要`1-3`分钟，初始化完成后即可访问。
 <Callout type="warning">
-  ⚠️ 请不要在面板的反向代理设置中开启任何形式的缓存，以免影响服务的正常运行。详情请见 https://github.com/lobehub/lobe-chat/discussions/5986
+  ⚠️ 请不要在面板的反向代理设置中开启任何形式的缓存，以免影响服务的正常运行。详情请见 [https://github.com/lobehub/lobe-chat/discussions/5986](https://github.com/lobehub/lobe-chat/discussions/5986)
 </Callout>
 ## 访问 LobeChat

package/docs/self-hosting/platform/tencentcloud-lighthouse.mdx CHANGED Viewed

@@ -1,6 +1,9 @@
 ---
 title: Deploy LobeChat on TencentCloud Lighthouse
-description: Learn how to deploy the LobeChat application on TencentCloud Lighthouse, including preparing the large model API Key, clicking the deploy button, and other operations.
+description: >-
+  Learn how to deploy the LobeChat application on TencentCloud Lighthouse,
+  including preparing the large model API Key, clicking the deploy button, and
+  other operations.
 tags:
   - TencentCloud Lighthouse
   - TencentCloud
@@ -15,18 +18,15 @@ If you want to deploy LobeChat on TencentCloud Lighthouse, you can follow the st
 ## Tencent Cloud Deployment Process
 <Steps>
+  ### Prepare your API Key
-### Prepare your API Key
+  Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
-Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+  ### One-click to deploy
+  [![][deploy-button-image]][deploy-link]
-### One-click to deploy
-[![][deploy-button-image]][deploy-link]
-### Once deployed, you can start using it
+  ### Once deployed, you can start using it
 </Steps>
 [deploy-button-image]: https://cloudcache.tencent-cloud.com/qcloud/ui/static/static_source_business/d65fb782-4fb0-4348-ad85-f2943d6bee8f.svg

package/docs/self-hosting/platform/tencentcloud-lighthouse.zh-CN.mdx CHANGED Viewed

@@ -16,18 +16,16 @@ tags:
 ## 腾讯轻量云 部署流程
 <Steps>
+  ### 准备好你的 API Key
-### 准备好你的 API Key
+  前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
-前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+  ### 点击下方按钮进行部署
-### 点击下方按钮进行部署
-[![][deploy-button-image]][deploy-link]
-### 部署完毕后，即可开始使用
+  [![][deploy-button-image]][deploy-link]
+  ### 部署完毕后，即可开始使用
 </Steps>
 [deploy-button-image]: https://cloudcache.tencent-cloud.com/qcloud/ui/static/static_source_business/d65fb782-4fb0-4348-ad85-f2943d6bee8f.svg
-[deploy-link]: https://buy.cloud.tencent.com/lighthouse?blueprintType=APP_OS&amp;blueprintOfficialId=lhbp-6u0ti132&amp;regionId=8&amp;zone=ap-beijing-3&amp;bundleId=bundle_starter_mc_med2_01&amp;loginSet=AUTO&amp;rule=true&amp;from=lobechat
+[deploy-link]: https://buy.cloud.tencent.com/lighthouse?blueprintType=APP_OS&blueprintOfficialId=lhbp-6u0ti132&regionId=8&zone=ap-beijing-3&bundleId=bundle_starter_mc_med2_01&loginSet=AUTO&rule=true&from=lobechat

package/docs/self-hosting/server-database/docker-compose.mdx CHANGED Viewed

@@ -315,8 +315,7 @@ The script supports the following deployment modes; please choose the appropriat
 ## Custom Deployment
-This section mainly introduces the configurations that need to be modified to customize the deployment of the LobeChat service in different network environments.
-Before starting, you can download the [Docker Compose configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml) and the [environment variable configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/.env.en_US.example).
+This section mainly introduces the configurations that need to be modified to customize the deployment of the LobeChat service in different network environments. Before starting, you can download the [Docker Compose configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml) and the [environment variable configuration file](https://raw.githubusercontent.com/lobehub/lobe-chat/refs/heads/main/docker-compose/local/.env.example).
 ```sh
 curl -O https://raw.githubusercontent.com/lobehub/lobe-chat/HEAD/docker-compose/local/docker-compose.yml
@@ -696,7 +695,6 @@ MINIO_ROOT_PASSWORD=Crj1570768
 MINIO_LOBE_BUCKET=lobe
 S3_ACCESS_KEY_ID=dB6Uq9CYZPdWSZouPyEd
 S3_SECRET_ACCESS_KEY=aPBW8CVULkh8bw1GatlT0GjLihcXHLNwRml4pieS
 ```
 - `docker-compose.yml`

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

@@ -95,7 +95,7 @@ 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/usage/providers/wenxin.mdx CHANGED Viewed

@@ -35,6 +35,7 @@ This article will guide you on how to use Wenxin Qianfan in LobeChat.
   - Copy the `API Key` and keep it safe
   <Image alt={'Create API Key'} inStep src={'https://github.com/user-attachments/assets/6d068fe0-8100-4b43-b0c3-7934f54e688f'} />
   <Image alt={'Copy API Key'} inStep src={'https://github.com/user-attachments/assets/629adf4e-e9e1-40dc-b9e5-d7b908878170'} />
   ### Step 2: Configure Wenxin Qianfan in LobeChat

package/docs/usage/providers/wenxin.zh-CN.mdx CHANGED Viewed

@@ -33,6 +33,7 @@ tags:
   - 复制 `API Key` 并妥善保存
   <Image alt={'创建密钥'} inStep src={'https://github.com/user-attachments/assets/6d068fe0-8100-4b43-b0c3-7934f54e688f'} />
   <Image alt={'复制密钥'} inStep src={'https://github.com/user-attachments/assets/629adf4e-e9e1-40dc-b9e5-d7b908878170'} />
   ### 步骤二：在 LobeChat 中配置文心千帆

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.55.1",
+  "version": "1.55.3",
   "description": "Lobe Chat - an open-source, high-performance chatbot 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",

package/src/config/aiModels/qwen.ts CHANGED Viewed

@@ -376,7 +376,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 131_072,
-    description:
+    description:
       '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
     displayName: 'Qwen2.5 VL 72B',
     id: 'qwen2.5-vl-72b-instruct',
@@ -394,7 +394,7 @@ const qwenChatModels: AIChatModelCard[] = [
       vision: true,
     },
     contextWindowTokens: 131_072,
-    description:
+    description:
       '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
     displayName: 'Qwen2.5 VL 7B',
     id: 'qwen2.5-vl-7b-instruct',
@@ -412,8 +412,8 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 131_072,
-    description:
-      'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力，尤其在数学、代码、自然语言推理等任务上。',
+    description:
+      'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力。在数学、代码、自然语言推理等任务上，性能较高，能力较强。',
     displayName: 'DeepSeek R1',
     enabled: true,
     id: 'deepseek-r1',
@@ -431,7 +431,7 @@ const qwenChatModels: AIChatModelCard[] = [
       functionCall: true,
     },
     contextWindowTokens: 131_072,
-    description:
+    description:
       'DeepSeek-V3 为自研 MoE 模型，671B 参数，激活 37B，在 14.8T token 上进行了预训练，在长文本、代码、数学、百科、中文能力上表现优秀。',
     displayName: 'DeepSeek V3',
     enabled: true,
@@ -450,8 +450,8 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true,
     },
     contextWindowTokens: 131_072,
-    description:
-      'DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。',
+    description:
+      'DeepSeek-R1-Distill-Qwen-1.5B 是一个基于 Qwen2.5-Math-1.5B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
     displayName: 'DeepSeek R1 Distill Qwen 1.5B',
     id: 'deepseek-r1-distill-qwen-1.5b',
     maxOutput: 8192,
@@ -467,7 +467,7 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
+    description: "DeepSeek-R1-Distill-Qwen-7B 是一个基于 Qwen2.5-Math-7B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
     displayName: "DeepSeek R1 Distill Qwen 7B",
     id: "deepseek-r1-distill-qwen-7b",
     maxOutput: 8192,
@@ -483,9 +483,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Llama 8B",
-    id: "deepseek-r1-distill-llama-8b",
+    description: "DeepSeek-R1-Distill-Qwen-14B 是一个基于 Qwen2.5-14B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Qwen 14B",
+    id: "deepseek-r1-distill-qwen-14b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -499,9 +499,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Qwen 14B",
-    id: "deepseek-r1-distill-qwen-14b",
+    description: "DeepSeek-R1-Distill-Qwen-32B 是一个基于 Qwen2.5-32B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Qwen 32B",
+    id: "deepseek-r1-distill-qwen-32b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -515,9 +515,9 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
-    displayName: "DeepSeek R1 Distill Qwen 32B",
-    id: "deepseek-r1-distill-qwen-32b",
+    description: "DeepSeek-R1-Distill-Llama-8B 是一个基于 Llama-3.1-8B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
+    displayName: "DeepSeek R1 Distill Llama 8B",
+    id: "deepseek-r1-distill-llama-8b",
     maxOutput: 8192,
     pricing: {
       currency: "CNY",
@@ -531,7 +531,7 @@ const qwenChatModels: AIChatModelCard[] = [
       reasoning: true
     },
     contextWindowTokens: 131_072,
-    description: "DeepSeek-R1-Distill 系列模型通过知识蒸馏技术，将 DeepSeek-R1 生成的样本对 Qwen、Llama 等开源模型进行微调后得到。",
+    description: "DeepSeek-R1-Distill-Llama-70B 是一个基于 Llama-3.3-70B-Instruct 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。",
     displayName: "DeepSeek R1 Distill Llama 70B",
     id: "deepseek-r1-distill-llama-70b",
     maxOutput: 8192,

package/src/config/modelProviders/qwen.ts CHANGED Viewed

@@ -294,7 +294,7 @@ const Qwen: ModelProviderCard = {
     },
     {
       contextWindowTokens: 128_000,
-      description:
+      description:
         '指令跟随、数学、解题、代码整体提升，万物识别能力提升，支持多样格式直接精准定位视觉元素，支持对长视频文件（最长10分钟）进行理解和秒级别的事件时刻定位，能理解时间先后和快慢，基于解析和定位能力支持操控OS或Mobile的Agent，关键信息抽取能力和Json格式输出能力强，此版本为72B版本，本系列能力最强的版本。',
       displayName: 'Qwen2.5 VL 72B',
       id: 'qwen2.5-vl-72b-instruct',
@@ -307,9 +307,9 @@ const Qwen: ModelProviderCard = {
       vision: true,
     },
     {
-      contextWindowTokens: 65_536,
-      description:
-        'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力，尤其在数学、代码、自然语言推理等任务上。',
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1 在后训练阶段大规模使用了强化学习技术，在仅有极少标注数据的情况下，极大提升了模型推理能力。在数学、代码、自然语言推理等任务上，性能较高，能力较强。',
       displayName: 'DeepSeek R1',
       id: 'deepseek-r1',
       pricing: {
@@ -320,8 +320,8 @@ const Qwen: ModelProviderCard = {
       releasedAt: '2025-01-27',
     },
     {
-      contextWindowTokens: 65_536,
-      description:
+      contextWindowTokens: 131_072,
+      description:
         'DeepSeek-V3 为自研 MoE 模型，671B 参数，激活 37B，在 14.8T token 上进行了预训练，在长文本、代码、数学、百科、中文能力上表现优秀。',
       displayName: 'DeepSeek V3',
       id: 'deepseek-v3',
@@ -332,6 +332,84 @@ const Qwen: ModelProviderCard = {
       },
       releasedAt: '2025-01-27',
     },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-1.5B 是一个基于 Qwen2.5-Math-1.5B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 1.5B',
+      id: 'deepseek-r1-distill-qwen-1.5b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-7B 是一个基于 Qwen2.5-Math-7B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 7B',
+      id: 'deepseek-r1-distill-qwen-7b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-14B 是一个基于 Qwen2.5-14B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 14B',
+      id: 'deepseek-r1-distill-qwen-14b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Qwen-32B 是一个基于 Qwen2.5-32B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Qwen 32B',
+      id: 'deepseek-r1-distill-qwen-32b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Llama-8B 是一个基于 Llama-3.1-8B 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Llama 8B',
+      id: 'deepseek-r1-distill-llama-8b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
+    {
+      contextWindowTokens: 131_072,
+      description:
+        'DeepSeek-R1-Distill-Llama-70B 是一个基于 Llama-3.3-70B-Instruct 的蒸馏大型语言模型，使用了 DeepSeek R1 的输出。',
+      displayName: 'DeepSeek R1 Distill Llama 70B',
+      id: 'deepseek-r1-distill-llama-70b',
+      pricing: {
+        currency: 'CNY',
+        input: 0,
+        output: 0,
+      },
+      releasedAt: '2025-02-05',
+    },
   ],
   checkModel: 'qwen-turbo-latest',
   description:

package/src/features/Conversation/Messages/Assistant/index.tsx CHANGED Viewed

@@ -27,7 +27,11 @@ export const AssistantMessage = memo<
   const isReasoning = useChatStore(aiChatSelectors.isMessageInReasoning(id));
-  const showReasoning = !!props.reasoning || (!props.reasoning && isReasoning);
+  // remove \n to avoid empty content
+  // refs: https://github.com/lobehub/lobe-chat/pull/6153
+  const showReasoning =
+    (!!props.reasoning && props.reasoning.content?.trim() !== '') ||
+    (!props.reasoning && isReasoning);
   return editing ? (
     <DefaultMessage