update:智控台添加版本号 (#793)

* update: 优化系统prompt

* Update Deployment_all.md

更新部分的安装配置文档，后续需要修改 docker-compose.yaml

* Update docker-compose_all.yml

- 直接提供全量的部署配置，包括 mysql 与 Redis 实现真正意义上的一键配置。
- 将 MySQL 的数据内容本地挂载存储，需要备份迁移的时候，直接打包复制文件夹即可。MySQL 容器删除的时候也不会出现数据丢失的问题。

* Update Deployment_all.md

- 使用 docker compose 部署的时候，不应该每次更新的时候都把原来的 docker-compose 文件删除，再重新配置。
- 如果没有自己部署数据库需求的话，目前可以直接开箱即用，同步更新了 server 中的 Redis 与 MySQL 的镜像服务配置。

* Update Deployment_all.md

- MySQL 与 Redis 的安装是可选的

* 现在新版本的 docker 直接集成了 compose 命令，不需要手动安装与执行 docker-compose 命令了，提高兼容性

* fix:manager下发配置字符转数字bug

* update: 优化三方模块打印日志报错问题

* update: 修复Dify对接未过滤全量数据问题

* update:通过代理转发接口api

* fix：number熟知去掉小数点后的00

* update:优化docker启动

* update:优化参数读取

---------

Co-authored-by: haotian <haotian@codemao.cn>
Co-authored-by: expoli <31023767+expoli@users.noreply.github.com>
Co-authored-by: GoodyHao <865700600@qq.com>

.gitignore

@@ -158,4 +158,5 @@ my_wakeup_words.mp3
 main/manager-api/.vscode
 
 # Ignore webpack cache directory
-main/manager-web/.webpack_cache/
+main/manager-web/.webpack_cache/
+main/xiaozhi-server/mysql

README.md

@@ -145,42 +145,24 @@ server:
 
 ---
 
-## 部署方式 🚀
+## 部署文档
 
-[![Banners](docs/images/banner2.png)](./docs/Deployment.md)
+本项目提供两种部署方式，请根据您的具体需求选择：
 
-### 部署文档
+#### 🚀 部署方式选择
 
-本项目支持`最简化`安装和`全模块`安装。请根据具体需求选择安装方式。
+| 部署方式 | 特点 | 适用场景 | Docker部署文档 | 源码部署文档 |
+|---------|------|---------|---------|---------|
+| **最简化安装** | 智能对话、IOT功能，数据存储在配置文件 | 低配置环境，无需数据库 | [Docker只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) | [本地源码只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)|
+| **全模块安装** | 智能对话、IOT、OTA、智控台，数据存储在数据库 | 完整功能体验 |[Docker运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) | [本地源码运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97) |
 
-`最简化`适合在较低资源配置中运行，无需数据库。[请参考-最简化安装架构图](./docs/images/deploy1.png)
+> 💡 提示：以下是按最新代码部署后的测试平台，有需要可烧录测试，并发为6个，每天会清空数据
-
-`全模块`适合想体验完整功能，过程复杂。[请参考-全模块安装架构图](./docs/images/deploy2.png)
-
-#### 1、 最简化安装
-
-`最简化`安装包含：智能对话、IOT等功能，数据存储在`配置文件`。我们提供了两种安装教程，如果你决定使用最简化安装，可选择`Docker只运行Server`或`本地源码只运行Server`任意一种方式。
-
-##### 1.1. Docker只运行Server
-
-你可以使用编译好的docker镜像安装，[点击Docker只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)。优点：减少环境配置的烦恼；缺点：版本可能有点旧，镜像文件较大。
-
-##### 2.2. 本地源码只运行Server
-
-你可以以本地源码的方式运行，[点击本地源码只运行Server](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E5%8F%AA%E8%BF%90%E8%A1%8Cserver)。优点：可以随时更新最新代码；缺点：安装Conda环境较为复杂。
-
-#### 2、 全模块安装
-
-`全模块`安装包含：智能对话、IOT、OTA、智控台，数据存储在`数据库`中。我们提供了两种安装教程，如果你决定使用全模块安装，可选择`Docker运行全模块`或`本地源码运行全模块`任意一种方式。
-
-##### 2.1. Docker运行全模块
-
-你可以使用编译好的docker镜像安装，[点击Docker运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97)。优点：减少环境配置的烦恼；缺点：版本可能有点旧，镜像文件较大。
-
-##### 2.2. 本地源码运行全模块
-
-你可以以本地源码的方式运行，[点击本地源码运行全模块](./docs/Deployment_all.md#%E6%96%B9%E5%BC%8F%E4%BA%8C%E6%9C%AC%E5%9C%B0%E6%BA%90%E7%A0%81%E8%BF%90%E8%A1%8C%E5%85%A8%E6%A8%A1%E5%9D%97)。优点：可以随时更新最新代码；缺点：安装Java、Node.js、Conda环境较为复杂。
 
+```
+智控台地址: https://2662r3426b.vicp.fun
+OTA接口地址: htts://2662r3426b.vicp.fun/xiaozhi/ota/
+Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
+```
 ---
 
 ## 常见问题 ❓
@@ -188,54 +170,41 @@ server:
 如遇到问题或产品建议反馈[点这里](docs/FAQ.md)。
 
 ---
-
-## 产品生态 👬
-小智是一个生态，当你使用这个产品时，也可以看看其他在这个生态圈的优秀项目
-
-- [小智安卓客户端](https://github.com/TOM88812/xiaozhi-android-client)
-
-  一个基于xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本，打通IOS、Android端。
-- [小智电脑客户端](https://github.com/Huang-junsen/py-xiaozhi)
-
-  该项目提供了一个基于 Python 实现的小白 AI 客户端，使得在不具备实体硬件条件的情况下，依然能够体过代码体验小智 AI 的功能。主要功能包括 AI 语音交互、视觉多模态识别、IoT 设备集成、联网音乐播放、语音唤醒、自动对话模式、图形化界面、命令行模式、跨平台支持、音量控制、会话管理、加密音频传输、自动验证码处理等。
-- [小智Java服务端](https://github.com/joey-zhou/xiaozhi-esp32-server-java) 
-
-  小智开源后端服务 Java 版本是一个基于 Java 的开源项目，它包括前后端的服务，旨在为用户提供一个完整的后端服务解决方案。
----
 ## 功能清单 ✨
 
 ### 已实现 ✅
 
-- **通信协议**  
+| 功能模块 | 描述 |
-  基于 `xiaozhi-esp32` 协议，通过 WebSocket 实现数据交互。
+|---------|------|
-- **对话交互**  
+| 通信协议 | 基于 `xiaozhi-esp32` 协议，通过 WebSocket 实现数据交互 |
-  支持唤醒对话、手动对话及实时打断。长时间无对话时自动休眠
+| 对话交互 | 支持唤醒对话、手动对话及实时打断。长时间无对话时自动休眠 |
-- **意图识别**  
+| 意图识别 | 支持使用LLM意图识别、function call函数调用，减少硬编码意图判断 |
-  支持使用LLM意图识别、function call函数调用，减少硬编码意图判断
+| 多语言识别 | 支持国语、粤语、英语、日语、韩语（默认使用 FunASR） |
-- **多语言识别**  
+| LLM 模块 | 支持灵活切换 LLM 模块，默认使用 ChatGLMLLM，也可选用阿里百炼、DeepSeek、Ollama 等接口 |
-  支持国语、粤语、英语、日语、韩语（默认使用 FunASR）。
+| TTS 模块 | 支持 EdgeTTS（默认）、火山引擎豆包 TTS 等多种 TTS 接口，满足语音合成需求 |
-- **LLM 模块**  
+| 记忆功能 | 支持超长记忆、本地总结记忆、无记忆三种模式，满足不同场景需求 |
-  支持灵活切换 LLM 模块，默认使用 ChatGLMLLM，也可选用阿里百炼、DeepSeek、Ollama 等接口。
+| IOT功能 | 支持管理注册设备IOT功能，支持基于对话上下文语境下的智能物联网控制 |
-- **TTS 模块**  
+| 智控台 | 提供Web管理界面，支持智能体管理、用户管理、系统配置等功能，方便管理员和用户进行管理 |
-  支持 EdgeTTS（默认）、火山引擎豆包 TTS 等多种 TTS 接口，满足语音合成需求。
-- **记忆功能**  
-  支持超长记忆、本地总结记忆、无记忆三种模式，满足不同场景需求。
-- **IOT功能**  
-  支持管理注册设备IOT功能，支持基于对话上下文语境下的智能物联网控制。
-- **智控台**
-  提供Web管理界面，支持智能体管理、用户管理、系统配置等功能，方便管理员和用户进行管理。
-
 
 ### 正在开发 🚧
 
-- 多种心情模式
+想了解具体开发计划进度，[请点击这里](https://github.com/users/xinnan-tech/projects/3)
-
-想了解具体开发进度，[请点击这里](https://github.com/users/xinnan-tech/projects/3)
 
 如果你是一名软件开发者，这里有一份[《致开发者的公开信》](docs/contributor_open_letter.md)，欢迎加入！
 
 ---
 
+## 产品生态 👬
+小智是一个生态，当你使用这个产品时，也可以看看其他在这个生态圈的优秀项目
+
+| 项目名称  | 项目地址 | 项目描述 |
+|:---------------------|:--------|:--------|
+| 小智安卓客户端  | [xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) | 一个基于xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。<br/>现在是flutter版本，打通IOS、Android端。 |
+| 小智电脑客户端  | [py-xiaozhi](https://github.com/Huang-junsen/py-xiaozhi) | 该项目提供了一个基于 Python 实现的小白 AI 客户端，使得在不具备实体硬件条件的情况下，<br/>依然能够体过代码体验小智 AI 的功能。 |
+| 小智Java服务端  | [xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) | 小智开源后端服务 Java 版本是一个基于 Java 的开源项目。<br/>它包括前后端的服务，旨在为用户提供一个完整的后端服务解决方案。 |
+
+---
+
 ## 本项目支持的平台/组件列表 📋
 
 ### LLM 语言模型
@@ -298,10 +267,17 @@ server:
 
 ## 鸣谢 🙏
 
-- 本项目受 [百聆语音对话机器人](https://github.com/wwbin2017/bailing) 启发，并在其基础上实现。
+| Logo | 项目/公司 | 说明 |
-- 感谢 [十方融海](https://www.tenclass.com/) 对小智通讯协议提供的详尽文档支持。
+|:---:|:---:|:---|
+| <img src="./docs/images/logo_bailing.png" width="160"> | [百聆语音对话机器人](https://github.com/wwbin2017/bailing) | 本项目受[百聆语音对话机器人](https://github.com/wwbin2017/bailing)启发，并在其基础上实现 |
+| <img src="./docs/images/logo_tenclass.png" width="160"> | [十方融海](https://www.tenclass.com/) | 感谢[十方融海](https://www.tenclass.com/)为小智生态制定了标准的通讯协议、多设备兼容性方案及高并发场景实践示范；为本项目提供了全链路技术文档支持 |
+| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [玄凤科技](https://github.com/Eric0308) | 感谢[玄凤科技](https://github.com/Eric0308)贡献函数调用框架、MCP通信协议及插件化调用机制的实现代码，通过标准化的指令调度体系与动态扩展能力，显著提升了前端设备(IoT)的交互效率和功能延展性 |
+| <img src="./docs/images/logo_huiyuan.png" width="160"> | [汇远设计](http://ui.kwd988.net/) | 感谢[汇远设计](http://ui.kwd988.net/)为本项目提供专业视觉解决方案，用其服务超千家企业的设计实战经验，赋能本项目产品用户体验 |
+| <img src="./docs/images/logo_qinren.png" width="160"> | [西安勤人信息科技](https://www.029app.com/) | 感谢[西安勤人信息科技](https://www.029app.com/)深化本项目视觉体系，确保整体设计风格在多场景应用中的一致性和扩展性 |
+
 
 <a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">
+
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date&theme=dark" />
    <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />

docs/Deployment.md

@@ -137,7 +137,10 @@ docker logs -f xiaozhi-esp32-server
 ```
 docker stop xiaozhi-esp32-server
 docker rm xiaozhi-esp32-server
+docker stop xiaozhi-esp32-server-web
+docker rm xiaozhi-esp32-server-web
 docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
+docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
 ```
 
 5.3、重新按docker方式部署
@@ -221,7 +224,7 @@ python app.py
 ## 配置项目
 
 如果你的`xiaozhi-server`目录没有`data`，你需要创建`data`目录。
-如果你的`data`下面没有`.config.yaml`文件，你可以把源码目录下的`config.yaml`文件复制一份，重命名为`.config.yaml`
+如果你的`data`下面没有`.config.yaml`文件，你可以把`xiaozhi-server`目录下的`config.yaml`文件复制到`data`，并重命名为`.config.yaml`
 
 修改`xiaozhi-server`下`data`目录下的`.config.yaml`文件，配置本项目必须的一个配置。
 

docs/Deployment_all.md

@@ -44,6 +44,8 @@ xiaozhi-server
 在页面的右侧找到名称为`RAW`按钮，在`RAW`按钮的旁边，找到下载的图标，点击下载按钮，下载`docker-compose_all.yml`文件。 把文件下载到你的
 `xiaozhi-server`中。
 
+或者直接执行 `wget https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/docker-compose_all.yml` 下载。
+
 下载完后，回到本教程继续往下。
 
 ##### 1.3.2 下载 config_from_api.yaml
@@ -53,6 +55,8 @@ xiaozhi-server
 在页面的右侧找到名称为`RAW`按钮，在`RAW`按钮的旁边，找到下载的图标，点击下载按钮，下载`config_from_api.yaml`文件。 把文件下载到你的
 `xiaozhi-server`下面的`data`文件夹中，然后把`config_from_api.yaml`文件重命名为`.config.yaml`。
 
+或者直接执行 `wget https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/config_from_api.yaml` 下载保存。
+
 下载完配置文件后，我们确认一下整个`xiaozhi-server`里面的文件如下所示：
 
 ```
@@ -67,57 +71,37 @@ xiaozhi-server
 
 如果你的文件目录结构也是上面的，就继续往下。如果不是，你就再仔细看看是不是漏操作了什么。
 
-## 2. 安装Mysql和Redis
+## 2. 备份数据
 
-### 2.1 安装Mysql数据库
+如果你之前已经成功运行智控台，如果上面保存有你的密钥信息，请先从智控台上拷贝重要数据下来。因为升级过程中，有可能会覆盖原来的数据。
-如果本机已经安装了MySQL，可以直接在数据库中创建名为`xiaozhi_esp32_server`的数据库。
-
-```sql
-CREATE DATABASE xiaozhi_esp32_server CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;
-```
-
-如果还没有MySQL，你可以通过docker安装mysql
-
-```
-docker run --name xiaozhi-esp32-server-db -e MYSQL_ROOT_PASSWORD=123456 -p 3306:3306 -e MYSQL_DATABASE=xiaozhi_esp32_server -e MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci" -d mysql:latest
-```
-
-### 2.2 安装Redis
-
-如果还没有Redis，你可以通过docker安装redis
-
-```
-docker run --name xiaozhi-esp32-server-redis -d -p 6379:6379 redis
-```
-
-## 3. 配置docker-compose_all.yml文件文件
-
-在`xiaozhi-server`目录，打开docker-compose_all.yml，
-
-1、修改`SPRING_DATASOURCE_DRUID_URL`里，把`192.168.1.25`修改成部署mysql的电脑局域网ip，如果是你本地，你要查看一下你本机的局域网ip是什么
-
-2、修改`SPRING_DATA_REDIS_HOST`里，把`192.168.1.25`修改成部署redis的电脑局域网ip，如果是你本地，你要查看一下你本机的局域网ip是什么
-
-3、确认一下mysql的用户名`SPRING_DATASOURCE_DRUID_USERNAME`和密码`SPRING_DATASOURCE_DRUID_PASSWORD`
-
-## 4. 运行程序
-
-确认mysql和redis是否运行正常，输入
-```
-docker ps
-```
-如果你能看到`xiaozhi-esp32-server-redis`和`xiaozhi-esp32-server-db`信息，就可以继续往下，如果看不到，说明你的`mysql`和`redis`没有安装或没有启动。需要继续回到上面的教程，看看哪一步漏了。
-
-```
-CONTAINER ID             IMAGE   COMMAND   CREATED  TATUS   PORTS               NAMES
-xxx       redis          "xx"   xxx   xxx   0.0.0.0:6379->6379/tcp              xiaozhi-esp32-server-redis
-xxx       mysql:latest   "xx"   xxx   xxx   0.0.0.0:3306->3306/tcp, 33060/tcp   xiaozhi-esp32-server-db
-```
 
+## 3. 清除历史版本镜像和容器
 接下来打开命令行工具，使用`终端`或`命令行`工具 进入到你的`xiaozhi-server`，执行以下命令
 
 ```
-docker-compose -f docker-compose_all.yml up -d
+docker compose -f docker-compose_all.yml down
+
+docker stop xiaozhi-esp32-server
+docker rm xiaozhi-esp32-server
+
+docker stop xiaozhi-esp32-server-web
+docker rm xiaozhi-esp32-server-web
+
+docker stop xiaozhi-esp32-server-db
+docker rm xiaozhi-esp32-server-db
+
+docker stop xiaozhi-esp32-server-redis
+docker rm xiaozhi-esp32-server-redis
+
+docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
+docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
+```
+
+## 4. 运行程序
+执行以下命令启动新版本容器
+
+```
+docker compose -f docker-compose_all.yml up -d
 ```
 
 执行完后，再执行以下命令，查看日志信息。
@@ -150,17 +134,16 @@ http://localhost:8002/xiaozhi/doc.html
 
 ```
 manager-api:
-  url: http://127.0.0.1:8002/xiaozhi
+  url:  http://127.0.0.1:8002/xiaozhi
   secret: 你的server.secret值
 ```
 1、把你刚才从`智控台`复制过来的`server.secret`的`参数值`复制到`.config.yaml`文件里的`secret`里。
-
+2、注意，把`url`改成下面的`http://xiaozhi-esp32-server-web/xiaozhi`
-2、把`url`里的`127.0.0.1`改成你电脑局域网内的ip
 
 类似这样的效果
 ```
 manager-api:
-  url: http://192.168.1.25:8002/xiaozhi
+  url: http://xiaozhi-esp32-server-web/xiaozhi
   secret: 12345678-xxxx-xxxx-xxxx-123456789000
 ```
 
@@ -202,24 +185,6 @@ ws://你电脑局域网的ip:8000/xiaozhi/v1/
 接下来，你就可以开始 [编译esp32固件](firmware-build.md)了。
 
 
-## 6. 版本升级操作
-
-如果后期想升级版本，先备份你的模型密钥。
-
-进入`xiaozhi-server`目录
-
-5.1、执行以下命令
-
-```
-docker-compose down
-docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
-docker rmi ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
-```
-
-5.2、删掉`docker-compose_all.yaml`文件
-
-5.3、重新按1.1开始部署
-
 # 方式二：本地源码运行全模块
 
 ## 1.安装MySQL数据库
@@ -388,6 +353,9 @@ pip install -r requirements.txt
 
 `server.secret`需要说明一下，这个`参数值`很重要，作用是让我们的`Server`端连接`manager-api`。`server.secret`是每次从零部署manager模块时，会自动随机生成的密钥。
 
+如果你的`xiaozhi-server`目录没有`data`，你需要创建`data`目录。
+如果你的`data`下面没有`.config.yaml`文件，你可以把`xiaozhi-server`目录下的`config_from_api.yaml`文件复制到`data`，并重命名为`.config.yaml`
+
 复制`参数值`后，打开`xiaozhi-server`下的`data`目录的`.config.yaml`文件。此刻你的配置文件内容应该是这样的：
 
 ```

main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentServiceImpl.java

@@ -44,7 +44,7 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
     @Override
     public PageData<AgentEntity> adminAgentList(Map<String, Object> params) {
         IPage<AgentEntity> page = agentDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, "agent_name", true),
                 new QueryWrapper<>());
         return new PageData<>(page.getRecords(), page.getTotal());
     }

main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java

@@ -171,7 +171,13 @@ public class ConfigServiceImpl implements ConfigService {
             switch (param.getValueType().toLowerCase()) {
                 case "number":
                     try {
-                        current.put(lastKey, Double.parseDouble(value));
+                        double doubleValue = Double.parseDouble(value);
+                        // 如果数值是整数形式，则转换为Integer
+                        if (doubleValue == (int) doubleValue) {
+                            current.put(lastKey, (int) doubleValue);
+                        } else {
+                            current.put(lastKey, doubleValue);
+                        }
                     } catch (NumberFormatException e) {
                         current.put(lastKey, value);
                     }
@@ -231,8 +237,9 @@ public class ConfigServiceImpl implements ConfigService {
             boolean isCache) {
         Map<String, String> selectedModule = new HashMap<>();
 
-        String[] modelTypes = { "VAD", "ASR", "LLM", "TTS", "Memory", "Intent" };
+        String[] modelTypes = { "VAD", "ASR", "TTS", "Memory", "Intent", "LLM" };
-        String[] modelIds = { vadModelId, asrModelId, llmModelId, ttsModelId, memModelId, intentModelId };
+        String[] modelIds = { vadModelId, asrModelId, ttsModelId, memModelId, intentModelId, llmModelId };
+        String intentLLMModelId = null;
 
         for (int i = 0; i < modelIds.length; i++) {
             if (modelIds[i] == null) {
@@ -246,10 +253,27 @@ public class ConfigServiceImpl implements ConfigService {
                 if ("TTS".equals(modelTypes[i]) && voice != null) {
                     ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
                 }
+                // 如果是Intent类型，且type=intent_llm，则给他添加附加模型
+                if ("Intent".equals(modelTypes[i])) {
+                    Map<String, Object> map = (Map<String, Object>) model.getConfigJson();
+                    if ("intent_llm".equals(map.get("type"))) {
+                        intentLLMModelId = (String) map.get("llm");
+                        if (intentLLMModelId != null && intentLLMModelId.equals(llmModelId)) {
+                            intentLLMModelId = null;
+                        }
+                    }
+                }
+                // 如果是LLM类型，且intentLLMModelId不为空，则添加附加模型
+                if ("LLM".equals(modelTypes[i]) && intentLLMModelId != null) {
+                    ModelConfigEntity intentLLM = modelConfigService.getModelById(intentLLMModelId, isCache);
+                    typeConfig.put(intentLLM.getId(), intentLLM.getConfigJson());
+                }
             }
             result.put(modelTypes[i], typeConfig);
+
             selectedModule.put(modelTypes[i], model.getId());
         }
+
         result.put("selected_module", selectedModule);
         if (StringUtils.isNotBlank(prompt)) {
             prompt = prompt.replace("{{assistant_name}}", "小智");

main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java

@@ -221,7 +221,7 @@ public class DeviceServiceImpl extends BaseServiceImpl<DeviceDao, DeviceEntity>
         params.put(Constant.PAGE, dto.getPage());
         params.put(Constant.LIMIT, dto.getLimit());
         IPage<DeviceEntity> page = baseDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, "mac_address", true),
                 // 定义查询条件
                 new QueryWrapper<DeviceEntity>()
                         // 必须设备关键词查找

main/manager-api/src/main/java/xiaozhi/modules/security/config/ShiroConfig.java

@@ -76,6 +76,7 @@ public class ShiroConfig {
         filterMap.put("/favicon.ico", "anon");
         filterMap.put("/user/captcha", "anon");
         filterMap.put("/user/login", "anon");
+        filterMap.put("/user/pub-config", "anon");
         filterMap.put("/user/register", "anon");
         filterMap.put("/config/server-base", "anon");
         filterMap.put("/config/agent-models", "anon");

main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java

@@ -1,6 +1,8 @@
 package xiaozhi.modules.security.controller;
 
 import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
 
 import org.springframework.web.bind.annotation.GetMapping;
 import org.springframework.web.bind.annotation.PostMapping;
@@ -111,4 +113,12 @@ public class LoginController {
         sysUserTokenService.changePassword(userId, passwordDTO);
         return new Result<>();
     }
+
+    @GetMapping("/pub-config")
+    @Operation(summary = "公共配置")
+    public Result<Map<String, Object>> pubConfig() {
+        Map<String, Object> config = new HashMap<>();
+        config.put("version", "0.3.3");
+        return new Result<Map<String, Object>>().ok(config);
+    }
 }

main/manager-api/src/main/java/xiaozhi/modules/sys/service/impl/SysParamsServiceImpl.java

@@ -37,7 +37,7 @@ public class SysParamsServiceImpl extends BaseServiceImpl<SysParamsDao, SysParam
     @Override
     public PageData<SysParamsDTO> page(Map<String, Object> params) {
         IPage<SysParamsEntity> page = baseDao.selectPage(
-                getPage(params, Constant.CREATE_DATE, false),
+                getPage(params, null, false),
                 getWrapper(params));
 
         return getPageData(page, SysParamsDTO.class);

main/manager-api/src/main/java/xiaozhi/modules/timbre/service/impl/TimbreServiceImpl.java

@@ -47,7 +47,7 @@ public class TimbreServiceImpl extends BaseServiceImpl<TimbreDao, TimbreEntity>
         params.put(Constant.PAGE, dto.getPage());
         params.put(Constant.LIMIT, dto.getLimit());
         IPage<TimbreEntity> page = baseDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, null, true),
                 // 定义查询条件
                 new QueryWrapper<TimbreEntity>()
                         // 必须按照ttsID查找

main/manager-api/src/main/resources/db/changelog/202504131542.sql

@@ -0,0 +1,3 @@
+-- 对0.3.0版本之前的参数进行修改
+update `sys_params` set param_value = '.mp3;.wav;.p3' where  param_code = 'plugins.play_music.music_ext';
+update `ai_model_config` set config_json =  '{\"type\": \"intent_llm\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Intent_intent_llm';

main/manager-api/src/main/resources/db/changelog/202504131543.sql

@@ -0,0 +1,18 @@
+-- 对0.3.0版本之前的参数进行修改
+update `sys_params` set param_value = '.mp3;.wav;.p3' where  param_code = 'plugins.play_music.music_ext';
+update `ai_model_config` set config_json =  '{\"type\": \"intent_llm\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Intent_intent_llm';
+
+-- 添加edge音色
+delete from `ai_tts_voice` where tts_model_id = 'TTS_EdgeTTS';
+INSERT INTO `ai_tts_voice` VALUES 
+('TTS_EdgeTTS0001', 'TTS_EdgeTTS', 'EdgeTTS女声-晓晓', 'zh-CN-XiaoxiaoNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0002', 'TTS_EdgeTTS', 'EdgeTTS男声-云扬', 'zh-CN-YunyangNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0003', 'TTS_EdgeTTS', 'EdgeTTS女声-晓伊', 'zh-CN-XiaoyiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0004', 'TTS_EdgeTTS', 'EdgeTTS男声-云健', 'zh-CN-YunjianNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0005', 'TTS_EdgeTTS', 'EdgeTTS男声-云希', 'zh-CN-YunxiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0006', 'TTS_EdgeTTS', 'EdgeTTS男声-云夏', 'zh-CN-YunxiaNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0007', 'TTS_EdgeTTS', 'EdgeTTS女声-辽宁小贝', 'zh-CN-liaoning-XiaobeiNeural', '辽宁', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0008', 'TTS_EdgeTTS', 'EdgeTTS女声-陕西小妮', 'zh-CN-shaanxi-XiaoniNeural', '陕西', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0009', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海佳', 'zh-HK-HiuGaaiNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0010', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海曼', 'zh-HK-HiuMaanNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0011', 'TTS_EdgeTTS', 'EdgeTTS男声-香港万龙', 'zh-HK-WanLungNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL);

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -50,4 +50,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202504112058.sql
+            path: classpath:db/changelog/202504112058.sql
+  - changeSet:
+      id: 202504131543
+      author: John
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202504131543.sql

main/manager-web/.env.development

@@ -1,4 +1 @@
-# 暂时使用群主的接口
+VUE_APP_API_BASE_URL=/xiaozhi
-# VUE_APP_API_BASE_URL=https://2662r3426b.vicp.fun/xiaozhi
-# 如果本地开发，请使用以下接口
-VUE_APP_API_BASE_URL=http://localhost:8002/xiaozhi

main/manager-web/src/apis/module/model.js

@@ -1,7 +1,6 @@
 import { getServiceUrl } from '../api';
 import RequestService from '../httpRequest';
 
-
 export default {
   // 获取模型配置列表
   getModelList(params, callback) {
@@ -162,21 +161,25 @@ export default {
   // 更新模型配置
   updateModel(params, callback) {
     const { modelType, provideCode, id, formData } = params;
+    const payload = {
+      ...formData,
+      configJson: formData.configJson
+    };
     RequestService.sendRequest()
-      .url(`${getServiceUrl()}/models/${modelType}/${provideCode}/${id}`)
+        .url(`${getServiceUrl()}/models/${modelType}/${provideCode}/${id}`)
-      .method('PUT')
+        .method('PUT')
-      .data(formData)
+        .data(payload)
-      .success((res) => {
+        .success((res) => {
-        RequestService.clearRequestTime();
+            RequestService.clearRequestTime();
-        callback(res);
+            callback(res);
-      })
+        })
-      .fail((err) => {
+        .fail((err) => {
-        console.error('更新模型失败:', err);
+            console.error('更新模型失败:', err);
-        this.$message.error(err.msg || '更新模型失败');
+            this.$message.error(err.msg || '更新模型失败');
-        RequestService.reAjaxFun(() => {
+            RequestService.reAjaxFun(() => {
-          this.updateModel(params, callback);
+                this.updateModel(params, callback);
-        });
+            });
-      }).send();
+        }).send();
   },
   // 设置默认模型
   setDefaultModel(id, callback) {

main/manager-web/src/apis/module/user.js

@@ -106,7 +106,7 @@ export default {
     },
     // 修改用户状态
     changeUserStatus(status, userIds, successCallback) {
-        console.log(555,userIds)
+        console.log(555, userIds)
         RequestService.sendRequest()
             .url(`${getServiceUrl()}/admin/users/changeStatus/${status}`)
             .method('put')
@@ -122,4 +122,20 @@ export default {
                 })
             }).send()
     },
+    // 获取公共配置
+    getPubConfig(callback) {
+        RequestService.sendRequest()
+            .url(`${getServiceUrl()}/user/pub-config`)
+            .method('GET')
+            .success((res) => {
+                RequestService.clearRequestTime();
+                callback(res);
+            })
+            .fail((err) => {
+                console.error('获取公共配置失败:', err);
+                RequestService.reAjaxFun(() => {
+                    this.getPubConfig(callback);
+                });
+            }).send();
+    },
 }

main/manager-web/src/components/ModelEditDialog.vue

@@ -94,14 +94,6 @@
 <script>
 import Api from '@/apis/api';
 
-const DEFAULT_CONFIG_JSON = {
-    type: "",
-    base_url: "",
-    model_name: "",
-    api_key: "",
-    empty: false
-};
-
 export default {
   name: "ModelEditDialog",
   props: {
@@ -132,7 +124,7 @@ export default {
         docLink: "",
         remark: "",
         sort: 0,
-        configJson: JSON.parse(JSON.stringify(DEFAULT_CONFIG_JSON))
+        configJson: {}
       }
     };
   },
@@ -183,8 +175,11 @@ export default {
             docLink: "",
             remark: "",
             sort: 0,
-            configJson: JSON.parse(JSON.stringify(DEFAULT_CONFIG_JSON))
+            configJson: {}
         };
+        this.dynamicCallInfoFields.forEach(field => {
+          this.$set(this.form.configJson, field.prop, '');
+        });
     },
     resetProviders() {
       this.providers = [];
@@ -266,6 +261,8 @@ export default {
       this.dynamicCallInfoFields.forEach(field => {
         if (!configJson.hasOwnProperty(field.prop)) {
           configJson[field.prop] = '';
+        } else if (typeof configJson[field.prop] !== 'string') {
+          configJson[field.prop] = String(configJson[field.prop]);
         }
       });
 
@@ -280,7 +277,6 @@ export default {
         remark: model.remark,
         sort: Number(model.sort) || 0,
         configJson: {
-          ...DEFAULT_CONFIG_JSON,
           ...configJson
         }
       };

main/manager-web/src/components/VersionFooter.vue

@@ -0,0 +1,39 @@
+<template>
+    <div class="copyright">
+        ©2025 xiaozhi-esp32-server v{{ version }}
+    </div>
+</template>
+
+<script>
+import Api from '@/apis/api';
+
+export default {
+    name: 'VersionFooter',
+    data() {
+        return {
+            version: ''
+        }
+    },
+    mounted() {
+        this.getSystemVersion();
+    },
+    methods: {
+        getSystemVersion() {
+            const storedVersion = sessionStorage.getItem('systemVersion');
+            if (storedVersion) {
+                this.version = storedVersion;
+                return;
+            }
+
+            Api.user.getPubConfig(({ data }) => {
+                if (data.code === 0 && data.data.version) {
+                    this.version = data.data.version;
+                    sessionStorage.setItem('systemVersion', data.data.version);
+                }
+            });
+        }
+    }
+}
+</script>
+
+<style scoped></style>

main/manager-web/src/views/DeviceManagement.vue

@@ -4,10 +4,9 @@
     <el-main style="padding: 20px; display: flex; flex-direction: column;">
       <div class="table-container">
         <h3 class="device-list-title">设备列表</h3>
-        <el-button type="primary" class="add-device-btn" @click="handleAddDevice">
+        <el-table ref="deviceTable" :data="paginatedDeviceList" @selection-change="handleSelectionChange"
-          + 添加设备
+          style="width: 100%; margin-top: 20px" border stripe>
-        </el-button>
+          <el-table-column type="selection" align="center" width="60"></el-table-column>
-        <el-table :data="paginatedDeviceList" style="width: 100%; margin-top: 20px" border stripe>
           <el-table-column label="设备型号" prop="model" flex></el-table-column>
           <el-table-column label="固件版本" prop="firmwareVersion" width="120"></el-table-column>
           <el-table-column label="Mac地址" prop="macAddress"></el-table-column>
@@ -39,12 +38,26 @@
             </template>
           </el-table-column>
         </el-table>
-        <el-pagination class="pagination" @size-change="handleSizeChange" @current-change="handleCurrentChange"
+        <div class="table_bottom">
-          :current-page="currentPage" :page-sizes="[5, 10, 20, 50]" :page-size="pageSize"
+          <div class="ctrl_btn">
-          layout="total, sizes, prev, pager, next, jumper" :total="deviceList.length"></el-pagination>
+            <el-button size="mini" type="primary" class="select-all-btn" @click="toggleAllSelection">
-      </div>
+              {{ isAllSelected ? '取消全选' : '全选' }}
-      <div class="copyright">
+            </el-button>
-        ©2025 xiaozhi-esp32-server
+            <el-button type="primary" size="mini" class="add-device-btn" @click="handleAddDevice">
+              新增
+            </el-button>
+          </div>
+          <div class="custom-pagination">
+            <button class="pagination-btn" :disabled="currentPage === 1" @click="goFirst">首页</button>
+            <button class="pagination-btn" :disabled="currentPage === 1" @click="goPrev">上一页</button>
+            <button v-for="page in visiblePages" :key="page" class="pagination-btn"
+              :class="{ active: page === currentPage }" @click="goToPage(page)">
+              {{ page }}
+            </button>
+            <button class="pagination-btn" :disabled="currentPage === pageCount" @click="goNext">下一页</button>
+            <span class="total-text">共{{ deviceList.length }}条记录</span>
+          </div>
+        </div>
       </div>
       <AddDeviceDialog :visible.sync="addDeviceDialogVisible" :agent-id="currentAgentId"
         @refresh="fetchBindDevices(currentAgentId)" />
@@ -62,6 +75,8 @@ export default {
   data() {
     return {
       addDeviceDialogVisible: false,
+      selectedDevices: [],
+      isAllSelected: false,
       currentAgentId: this.$route.query.agentId || '',
       currentPage: 1,
       pageSize: 5,
@@ -75,7 +90,25 @@ export default {
       const start = (this.currentPage - 1) * this.pageSize;
       const end = start + this.pageSize;
       return this.deviceList.slice(start, end);
-    }
+    },
+    pageCount() {
+      return Math.ceil(this.deviceList.length / this.pageSize);
+    },
+    visiblePages() {
+      const pages = [];
+      const maxVisible = 3;
+      let start = Math.max(1, this.currentPage - 1);
+      let end = Math.min(this.pageCount, start + maxVisible - 1);
+
+      if (end - start + 1 < maxVisible) {
+        start = Math.max(1, end - maxVisible + 1);
+      }
+
+      for (let i = start; i <= end; i++) {
+        pages.push(i);
+      }
+      return pages;
+    },
   },
   mounted() {
     const agentId = this.$route.query.agentId;
@@ -84,6 +117,16 @@ export default {
     }
   },
   methods: {
+
+    handleSelectionChange(val) {
+      this.selectedDevices = val;
+      this.isAllSelected = val.length === this.paginatedDeviceList.length;
+    },
+    toggleAllSelection() {
+      this.$refs.deviceTable.toggleAllSelection();
+    },
+
+
     handleAddDevice() {
       this.addDeviceDialogVisible = true;
     },
@@ -115,12 +158,19 @@ export default {
         });
       });
     },
-    handleSizeChange(val) {
+    goFirst() {
-      this.pageSize = val;
+      this.currentPage = 1;
     },
-    handleCurrentChange(val) {
+    goPrev() {
-      this.currentPage = val;
+      if (this.currentPage > 1) this.currentPage--;
     },
+    goNext() {
+      if (this.currentPage < this.pageCount) this.currentPage++;
+    },
+    goToPage(page) {
+      this.currentPage = page;
+    },
+
     fetchBindDevices(agentId) {
       this.loading = true;
       Api.device.getAgentBindDevices(agentId, ({ data }) => {
@@ -180,21 +230,18 @@ export default {
 }
 
 .add-device-btn {
-  float: right;
+  background: linear-gradient(135deg, #6b8cff, #a966ff) !important;
-  background: #409eff;
+  border: none !important;
-  border: none;
+  color: white !important;
-  border-radius: 10px;
+  margin-left: 10px;
-  width: 105px;
   height: 32px;
-  display: flex;
+  padding: 7px 12px;
-  align-items: center;
+  border-radius: 4px !important;
-  justify-content: center;
+  box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
-  font-size: 14px;
-  gap: 8px;
-  margin-bottom: 15px;
 
   &:hover {
-    background: #3a8ee6;
+    transform: translateY(-1px);
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
   }
 }
 
@@ -213,8 +260,83 @@ export default {
   vertical-align: middle;
 }
 
-.pagination {
+.custom-pagination {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  margin-top: 15px;
+}
+
+.pagination-btn {
+  min-width: 28px;
+  height: 32px;
+  padding: 0 12px;
+  border-radius: 4px;
+  border: 1px solid #e4e7ed;
+  background: #dee7ff;
+  color: #606266;
+  font-size: 14px;
+  cursor: pointer;
+  transition: all 0.3s ease;
+}
+
+.pagination-btn:first-child,
+.pagination-btn:nth-child(2),
+.pagination-btn:nth-last-child(2) {
+  min-width: 60px;
+}
+
+.pagination-btn:hover {
+  background: #d7dce6;
+}
+
+.pagination-btn:disabled {
+  opacity: 0.6;
+  cursor: not-allowed;
+}
+
+.pagination-btn.active {
+  background: #5f70f3 !important;
+  color: #ffffff !important;
+  border-color: #5f70f3 !important;
+}
+
+.total-text {
+  color: #909399;
+  font-size: 14px;
+  margin-left: 10px;
+}
+
+.table_bottom {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
   margin-top: 20px;
-  text-align: right;
+}
+
+.ctrl_btn {
+  display: flex;
+  gap: 8px;
+  padding-left: 26px;
+
+  .el-button {
+    min-width: 72px;
+    height: 32px;
+    padding: 7px 12px;
+    border-radius: 4px;
+    border: none;
+    transition: all 0.3s;
+    box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
+
+    &:hover {
+      transform: translateY(-1px);
+      box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
+    }
+  }
+
+  .el-button--primary {
+    background: #5f70f3;
+    color: white;
+  }
 }
 </style>

main/manager-web/src/views/ModelConfig.vue

@@ -3,21 +3,15 @@
     <HeaderBar />
 
     <div class="operation-bar">
-        <h2 class="page-title">{{ modelTypeText }}</h2>
+      <h2 class="page-title">{{ modelTypeText }}</h2>
       <div class="action-group">
-            <div class="search-group">
+        <div class="search-group">
-                <el-input
+          <el-input placeholder="请输入模型名称查询" v-model="search" class="search-input" clearable
-                    placeholder="请输入模型名称查询"
+            @keyup.enter.native="handleSearch" style="width: 240px" />
-                    v-model="search"
+          <el-button class="btn-search" @click="handleSearch">
-                    class="search-input"
+            搜索
-                    clearable
+          </el-button>
-                    @keyup.enter.native="handleSearch"
+        </div>
-                    style="width: 240px"
-                />
-                <el-button class="btn-search" @click="handleSearch">
-                  搜索
-                </el-button>
-            </div>
       </div>
     </div>
 
@@ -93,9 +87,9 @@
 
           <div class="table-footer">
             <div class="batch-actions">
-              <el-button size="mini" type="primary" @click="selectAll" >
+              <el-button size="mini" type="primary" @click="selectAll">
                 {{ isAllSelected ?
-                '取消全选' : '全选' }}
+                  '取消全选' : '全选' }}
               </el-button>
               <el-button type="success" size="mini" @click="addModel" class="add-btn">
                 新增
@@ -125,10 +119,6 @@
       <TtsModel :visible.sync="ttsDialogVisible" :ttsModelId="selectedTtsModelId" />
       <AddModelDialog :modelType="activeTab" :visible.sync="addDialogVisible" @confirm="handleAddConfirm" />
     </div>
-
-    <div class="copyright">
-      ©2025 xiaozhi-esp32-server
-    </div>
   </div>
 </template>
 
@@ -639,20 +629,6 @@ export default {
   gap: 8px;
 }
 
-.copyright {
-  text-align: center;
-  color: #979db1;
-  font-size: 12px;
-  font-weight: 400;
-  margin-top: auto;
-  padding: 30px 0 20px;
-  position: absolute;
-  bottom: 0;
-  left: 50%;
-  transform: translateX(-50%);
-  width: 100%;
-}
-
 .title-wrapper {
   display: flex;
   align-items: center;

main/manager-web/src/views/ParamsManagement.vue

@@ -64,8 +64,6 @@
         <!-- 新增/编辑参数对话框 -->
         <param-dialog :title="dialogTitle" :visible.sync="dialogVisible" :form="paramForm" @submit="handleSubmit"
             @cancel="dialogVisible = false" />
-
-        <div class="copyright">©2025 xiaozhi-esp32-server</div>
     </div>
 </template>
 
@@ -382,20 +380,6 @@ export default {
     }
 }
 
-.copyright {
-    text-align: center;
-    color: #979db1;
-    font-size: 12px;
-    font-weight: 400;
-    margin-top: auto;
-    padding: 30px 0 20px;
-    position: absolute;
-    bottom: 0;
-    left: 50%;
-    transform: translateX(-50%);
-    width: 100%;
-}
-
 .custom-pagination {
     display: flex;
     align-items: center;

main/manager-web/src/views/UserManagement.vue

@@ -42,7 +42,7 @@
             <div class="table_bottom">
               <div class="ctrl_btn">
                 <el-button size="mini" type="primary" class="select-all-btn" @click="handleSelectAll">
-                    {{ isAllSelected ? '取消全选' : '全选' }}
+                  {{ isAllSelected ? '取消全选' : '全选' }}
                 </el-button>
                 <el-button size="mini" type="success" icon="el-icon-circle-check" @click="batchEnable">启用</el-button>
                 <el-button size="mini" type="warning" @click="batchDisable"><i
@@ -69,8 +69,6 @@
         </div>
       </div>
     </div>
-
-    <div class="copyright">©2025 xiaozhi-esp32-server</div>
     <view-password-dialog :visible.sync="showViewPassword" :password="currentPassword" />
   </div>
 </template>
@@ -465,20 +463,6 @@ export default {
   color: black;
 }
 
-.copyright {
-  text-align: center;
-  color: #979db1;
-  font-size: 12px;
-  font-weight: 400;
-  margin-top: auto;
-  padding: 30px 0 20px;
-  position: absolute;
-  bottom: 0;
-  left: 50%;
-  transform: translateX(-50%);
-  width: 100%;
-}
-
 .custom-pagination {
   display: flex;
   align-items: center;

main/manager-web/src/views/home.vue

@@ -35,11 +35,11 @@
             @deviceManage="handleDeviceManage" @delete="handleDeleteAgent" />
         </div>
       </div>
-      <div class="copyright">
-        ©2025 xiaozhi-esp32-server
-      </div>
       <AddWisdomBodyDialog :visible.sync="addDeviceDialogVisible" @confirm="handleWisdomBodyAdded" />
     </el-main>
+    <el-footer>
+      <version-footer />
+    </el-footer>
   </div>
 
 </template>
@@ -49,10 +49,11 @@ import Api from '@/apis/api';
 import AddWisdomBodyDialog from '@/components/AddWisdomBodyDialog.vue';
 import DeviceItem from '@/components/DeviceItem.vue';
 import HeaderBar from '@/components/HeaderBar.vue';
+import VersionFooter from '@/components/VersionFooter.vue';
 
 export default {
   name: 'HomePage',
-  components: { DeviceItem, AddWisdomBodyDialog, HeaderBar },
+  components: { DeviceItem, AddWisdomBodyDialog, HeaderBar, VersionFooter },
   data() {
     return {
       addDeviceDialogVisible: false,

main/manager-web/src/views/login.vue

@@ -51,9 +51,7 @@
         </div>
       </el-main>
       <el-footer>
-        <div class="copyright">
+        <version-footer />
-          ©2025 xiaozhi-esp32-server
-        </div>
       </el-footer>
     </el-container>
   </div>
@@ -61,11 +59,14 @@
 
 <script>
 import Api from '@/apis/api';
+import VersionFooter from '@/components/VersionFooter.vue';
 import { getUUID, goToPage, showDanger, showSuccess } from '@/utils';
 
-
 export default {
   name: 'login',
+  components: {
+    VersionFooter
+  },
   data() {
     return {
       activeName: "username",
@@ -76,11 +77,13 @@ export default {
         captchaId: ''
       },
       captchaUuid: '',
-      captchaUrl: ''
+      captchaUrl: '',
+      version: ''
     }
   },
   mounted() {
     this.fetchCaptcha();
+    this.getSystemVersion();
   },
   methods: {
     fetchCaptcha() {
@@ -144,6 +147,21 @@ export default {
 
     goToRegister() {
       goToPage('/register')
+    },
+
+    getSystemVersion() {
+      const storedVersion = sessionStorage.getItem('systemVersion');
+      if (storedVersion) {
+        this.version = storedVersion;
+        return;
+      }
+
+      Api.user.getPubConfig(({ data }) => {
+        if (data.code === 0 && data.data.version) {
+          this.version = data.data.version;
+          sessionStorage.setItem('systemVersion', data.data.version);
+        }
+      });
     }
   }
 }

main/manager-web/src/views/register.vue

@@ -72,9 +72,7 @@
 
       <!-- 保持相同的页脚 -->
       <el-footer>
-        <div class="copyright">
+        <version-footer />
-          ©2025 xiaozhi-esp32-server
-        </div>
       </el-footer>
     </el-container>
   </div>
@@ -82,10 +80,14 @@
 
 <script>
 import Api from '@/apis/api';
+import VersionFooter from '@/components/VersionFooter.vue';
 import { getUUID, goToPage, showDanger, showSuccess } from '@/utils';
 
 export default {
   name: 'register',
+  components: {
+    VersionFooter
+  },
   data() {
     return {
       form: {

main/manager-web/src/views/roleConfig.vue

@@ -81,9 +81,6 @@
           </div>
         </div>
       </div>
-      <div class="copyright">
-        ©2025 xiaozhi-esp32-server
-      </div>
     </el-main>
   </div>
 </template>

main/manager-web/vue.config.js

@@ -15,6 +15,10 @@ module.exports = defineConfig({
   devServer: {
     port: 8001, // 指定端口为 8001
     proxy: {
+      '/xiaozhi': {
+        target: 'http://127.0.0.1:8002',
+        changeOrigin: true
+      }
     },
     client: {
       overlay: false, // 不显示 webpack 错误覆盖层

main/xiaozhi-server/config/logger.py

@@ -3,7 +3,7 @@ import sys
 from loguru import logger
 from config.config_loader import load_config
 
-SERVER_VERSION = "0.3.1"
+SERVER_VERSION = "0.3.3"
 
 
 def get_module_abbreviation(module_name, module_dict):
@@ -25,6 +25,12 @@ def build_module_string(selected_module):
     )
 
 
+def formatter(record):
+    """为没有 tag 的日志添加默认值"""
+    record["extra"].setdefault("tag", record["name"])
+    return record["message"]
+
+
 def setup_logging():
     """从配置文件中读取日志配置，并设置日志输出格式和级别"""
     config = load_config()
@@ -56,9 +62,14 @@ def setup_logging():
     logger.remove()
 
     # 输出到控制台
-    logger.add(sys.stdout, format=log_format, level=log_level)
+    logger.add(sys.stdout, format=log_format, level=log_level, filter=formatter)
 
     # 输出到文件
-    logger.add(os.path.join(log_dir, log_file), format=log_format_file, level=log_level)
+    logger.add(
+        os.path.join(log_dir, log_file),
+        format=log_format_file,
+        level=log_level,
+        filter=formatter,
+    )
 
     return logger

main/xiaozhi-server/core/connection.py

@@ -104,8 +104,6 @@ class ConnectionHandler:
 
         self.close_after_chat = False  # 是否在聊天结束后关闭连接
         self.use_function_call_mode = False
-        if self.config["selected_module"]["Intent"] == "function_call":
-            self.use_function_call_mode = True
 
     async def handle_connection(self, ws):
         try:
@@ -206,7 +204,7 @@ class ConnectionHandler:
                 self.headers.get("device-id", None),
                 self.headers.get("client-id", None),
             )
-            private_config["delete_audio"] = self.config["delete_audio"]
+            private_config["delete_audio"] = bool(self.config.get("delete_audio", True))
             self.logger.bind(tag=TAG).info(f"获取差异化配置成功: {private_config}")
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"获取差异化配置失败: {e}")
@@ -222,37 +220,37 @@ class ConnectionHandler:
         )
         if private_config.get("VAD", None) is not None:
             init_vad = True
-            self.config["vad"] = private_config["VAD"]
+            self.config["VAD"] = private_config["VAD"]
             self.config["selected_module"]["VAD"] = private_config["selected_module"][
                 "VAD"
             ]
         if private_config.get("ASR", None) is not None:
             init_asr = True
-            self.config["asr"] = private_config["ASR"]
+            self.config["ASR"] = private_config["ASR"]
             self.config["selected_module"]["ASR"] = private_config["selected_module"][
                 "ASR"
             ]
         if private_config.get("LLM", None) is not None:
             init_llm = True
-            self.config["llm"] = private_config["LLM"]
+            self.config["LLM"] = private_config["LLM"]
             self.config["selected_module"]["LLM"] = private_config["selected_module"][
                 "LLM"
             ]
         if private_config.get("TTS", None) is not None:
             init_tts = True
-            self.config["tts"] = private_config["TTS"]
+            self.config["TTS"] = private_config["TTS"]
             self.config["selected_module"]["TTS"] = private_config["selected_module"][
                 "TTS"
             ]
         if private_config.get("Memory", None) is not None:
             init_memory = True
-            self.config["memory"] = private_config["Memory"]
+            self.config["Memory"] = private_config["Memory"]
             self.config["selected_module"]["Memory"] = private_config[
                 "selected_module"
             ]["Memory"]
         if private_config.get("Intent", None) is not None:
             init_intent = True
-            self.config["intent"] = private_config["Intent"]
+            self.config["Intent"] = private_config["Intent"]
             self.config["selected_module"]["Intent"] = private_config[
                 "selected_module"
             ]["Intent"]
@@ -287,17 +285,26 @@ class ConnectionHandler:
         self.memory.init_memory(device_id, self.llm)
 
     def _initialize_intent(self):
+        if (
+            self.config["Intent"][self.config["selected_module"]["Intent"]]["type"]
+            == "function_call"
+        ):
+            self.use_function_call_mode = True
         """初始化意图识别模块"""
         # 获取意图识别配置
         intent_config = self.config["Intent"]
-        intent_type = self.config["selected_module"]["Intent"]
+        intent_type = self.config["Intent"][self.config["selected_module"]["Intent"]][
+            "type"
+        ]
 
         # 如果使用 nointent，直接返回
         if intent_type == "nointent":
             return
         # 使用 intent_llm 模式
         elif intent_type == "intent_llm":
-            intent_llm_name = intent_config["intent_llm"]["llm"]
+            intent_llm_name = intent_config[self.config["selected_module"]["Intent"]][
+                "llm"
+            ]
 
             if intent_llm_name and intent_llm_name in self.config["LLM"]:
                 # 如果配置了专用LLM，则创建独立的LLM实例
@@ -328,10 +335,8 @@ class ConnectionHandler:
 
     def change_system_prompt(self, prompt):
         self.prompt = prompt
-        # 找到原来的role==system，替换原来的系统提示
+        # 更新系统prompt至上下文
-        for m in self.dialogue.dialogue:
+        self.dialogue.update_system_message(self.prompt)
-            if m.role == "system":
-                m.content = prompt
 
     def chat(self, query):
 
@@ -695,7 +700,7 @@ class ConnectionHandler:
                 opus_datas, text_index, tts_file = [], 0, None
                 try:
                     self.logger.bind(tag=TAG).debug("正在处理TTS任务...")
-                    tts_timeout = self.config.get("tts_timeout", 10)
+                    tts_timeout = int(self.config.get("tts_timeout", 10))
                     tts_file, text, text_index = future.result(timeout=tts_timeout)
                     if text is None or len(text) <= 0:
                         self.logger.bind(tag=TAG).error(

main/xiaozhi-server/core/handle/functionHandler.py

@@ -57,7 +57,9 @@ class FunctionHandler:
 
     def register_config_functions(self):
         """注册配置中的函数,可以不同客户端使用不同的配置"""
-        for func in self.config["Intent"]["function_call"].get("functions", []):
+        for func in self.config["Intent"][self.config["selected_module"]["Intent"]].get(
+            "functions", []
+        ):
             self.function_registry.register_function(func)
 
         """home assistant需要初始化提示词"""

main/xiaozhi-server/core/handle/intentHandler.py

@@ -76,6 +76,11 @@ async def process_intent_result(conn, intent_result, original_text):
             if function_name == "continue_chat":
                 return False
 
+            if function_name == "play_music":
+                funcItem = conn.func_handler.get_function(function_name)
+                if not funcItem:
+                    conn.func_handler.function_registry.register_function("play_music")
+
             function_args = None
             if "arguments" in intent_data["function_call"]:
                 function_args = intent_data["function_call"]["arguments"]

main/xiaozhi-server/core/handle/iotHandle.py

@@ -269,14 +269,12 @@ def register_device_type(descriptor):
 
 # 用于接受前端设备推送的搜索iot描述
 async def handleIotDescriptors(conn, descriptors):
-    if not conn.use_function_call_mode:
-        return
     wait_max_time = 5
     while conn.func_handler is None or not conn.func_handler.finish_init:
         await asyncio.sleep(1)
         wait_max_time -= 1
         if wait_max_time <= 0:
-            logger.bind(tag=TAG).error("连接对象没有func_handler")
+            logger.bind(tag=TAG).debug("连接对象没有func_handler")
             return
     """处理物联网描述"""
     functions_changed = False

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -71,8 +71,8 @@ async def no_voice_close_connect(conn):
         conn.client_no_voice_last_time = time.time() * 1000
     else:
         no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
-        close_connection_no_voice_time = conn.config.get(
+        close_connection_no_voice_time = int(
-            "close_connection_no_voice_time", 120
+            conn.config.get("close_connection_no_voice_time", 120)
         )
         if (
             not conn.close_after_chat

main/xiaozhi-server/core/providers/llm/dify/dify.py

@@ -58,7 +58,8 @@ class LLMProvider(LLMProviderBase):
                                 self.session_conversation_map[session_id] = (
                                     conversation_id  # 更新映射
                                 )
-                            if event.get("answer"):
+                            # 过滤 message_replace 事件，此事件会全量推一次
+                            if event.get("event") != "message_replace" and event.get("answer"):
                                 yield event["answer"]
                 elif self.mode == "workflows/run":
                     for line in r.iter_lines():
@@ -73,7 +74,8 @@ class LLMProvider(LLMProviderBase):
                     for line in r.iter_lines():
                         if line.startswith(b"data: "):
                             event = json.loads(line[6:])
-                            if event.get("answer"):
+                            # 过滤 message_replace 事件，此事件会全量推一次
+                            if event.get("event") != "message_replace" and event.get("answer"):
                                 yield event["answer"]
 
         except Exception as e:

main/xiaozhi-server/core/providers/llm/openai/openai.py

@@ -15,7 +15,15 @@ class LLMProvider(LLMProviderBase):
             self.base_url = config.get("base_url")
         else:
             self.base_url = config.get("url")
-        self.max_tokens = config.get("max_tokens", 500)
+        max_tokens = config.get("max_tokens")
+        if max_tokens is None or max_tokens == "":
+            max_tokens = 500
+
+        try:
+            max_tokens = int(max_tokens)
+        except (ValueError, TypeError):
+            max_tokens = 500
+        self.max_tokens = max_tokens
 
         check_model_key("LLM", self.api_key)
         self.client = openai.OpenAI(api_key=self.api_key, base_url=self.base_url)

main/xiaozhi-server/core/providers/tts/cozecn.py

@@ -12,14 +12,20 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
         self.access_token = config.get("access_token")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.response_format = config.get("response_format")
 
         self.host = "api.coze.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -30,9 +36,11 @@ class TTSProvider(TTSProviderBase):
         }
         headers = {
             "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
-        response = requests.request("POST", self.api_url, json=request_json, headers=headers)
+        response = requests.request(
+            "POST", self.api_url, json=request_json, headers=headers
+        )
         data = response.content
         file_to_save = open(output_file, "wb")
         file_to_save.write(data)

main/xiaozhi-server/core/providers/tts/doubao.py

@@ -18,7 +18,12 @@ class TTSProvider(TTSProviderBase):
         self.appid = config.get("appid")
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
-        self.voice = config.get("voice")
+
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
+
         self.api_url = config.get("api_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}

main/xiaozhi-server/core/providers/tts/edge.py

@@ -8,20 +8,26 @@ from core.providers.tts.base import TTSProviderBase
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         communicate = edge_tts.Communicate(text, voice=self.voice)
         # 确保目录存在并创建空文件
         os.makedirs(os.path.dirname(output_file), exist_ok=True)
-        with open(output_file, 'wb') as f:
+        with open(output_file, "wb") as f:
             pass
-        
+
         # 流式写入音频数据
-        with open(output_file, 'ab') as f:  # 改为追加模式避免覆盖
+        with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
             async for chunk in communicate.stream():
                 if chunk["type"] == "audio":  # 只处理音频数据块
                     f.write(chunk["data"])

main/xiaozhi-server/core/providers/tts/fishspeech.py

@@ -89,19 +89,19 @@ class TTSProvider(TTSProviderBase):
         self.reference_audio = config.get("reference_audio", [])
         self.reference_text = config.get("reference_text", [])
         self.format = config.get("format", "wav")
-        self.channels = config.get("channels", 1)
+        self.channels = int(config.get("channels", 1))
-        self.rate = config.get("rate", 44100)
+        self.rate = int(config.get("rate", 44100))
         self.api_key = config.get("api_key", "YOUR_API_KEY")
         have_key = check_model_key("FishSpeech TTS", self.api_key)
         if not have_key:
             return
         self.normalize = config.get("normalize", True)
-        self.max_new_tokens = config.get("max_new_tokens", 1024)
+        self.max_new_tokens = int(config.get("max_new_tokens", 1024))
-        self.chunk_length = config.get("chunk_length", 200)
+        self.chunk_length = int(config.get("chunk_length", 200))
-        self.top_p = config.get("top_p", 0.7)
+        self.top_p = float(config.get("top_p", 0.7))
-        self.repetition_penalty = config.get("repetition_penalty", 1.2)
+        self.repetition_penalty = float(config.get("repetition_penalty", 1.2))
-        self.temperature = config.get("temperature", 0.7)
+        self.temperature = float(config.get("temperature", 0.7))
-        self.streaming = config.get("streaming", False)
+        self.streaming = bool(config.get("streaming", False))
         self.use_memory_cache = config.get("use_memory_cache", "on")
         self.seed = config.get("seed")
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")

main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py

@@ -10,6 +10,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -18,23 +19,26 @@ class TTSProvider(TTSProviderBase):
         self.ref_audio_path = config.get("ref_audio_path")
         self.prompt_text = config.get("prompt_text")
         self.prompt_lang = config.get("prompt_lang", "zh")
-        self.top_k = config.get("top_k", 5)
+        self.top_k = int(config.get("top_k", 5))
-        self.top_p = config.get("top_p", 1)
+        self.top_p = float(config.get("top_p", 1))
-        self.temperature = config.get("temperature", 1)
+        self.temperature = float(config.get("temperature", 1))
         self.text_split_method = config.get("text_split_method", "cut0")
-        self.batch_size = config.get("batch_size", 1)
+        self.batch_size = int(config.get("batch_size", 1))
-        self.batch_threshold = config.get("batch_threshold", 0.75)
+        self.batch_threshold = float(config.get("batch_threshold", 0.75))
-        self.split_bucket = config.get("split_bucket", True)
+        self.split_bucket = bool(config.get("split_bucket", True))
-        self.return_fragment = config.get("return_fragment", False)
+        self.return_fragment = bool(config.get("return_fragment", False))
-        self.speed_factor = config.get("speed_factor", 1.0)
+        self.speed_factor = float(config.get("speed_factor", 1.0))
-        self.streaming_mode = config.get("streaming_mode", False)
+        self.streaming_mode = bool(config.get("streaming_mode", False))
-        self.seed = config.get("seed", -1)
+        self.seed = int(config.get("seed", -1))
-        self.parallel_infer = config.get("parallel_infer", True)
+        self.parallel_infer = bool(config.get("parallel_infer", True))
-        self.repetition_penalty = config.get("repetition_penalty", 1.35)
+        self.repetition_penalty = float(config.get("repetition_penalty", 1.35))
         self.aux_ref_audio_paths = config.get("aux_ref_audio_paths", [])
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -56,7 +60,7 @@ class TTSProvider(TTSProviderBase):
             "streaming_mode": self.streaming_mode,
             "seed": self.seed,
             "parallel_infer": self.parallel_infer,
-            "repetition_penalty": self.repetition_penalty
+            "repetition_penalty": self.repetition_penalty,
         }
 
         resp = requests.post(self.url, json=request_json)
@@ -64,4 +68,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -8,6 +8,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -16,18 +17,20 @@ class TTSProvider(TTSProviderBase):
         self.prompt_text = config.get("prompt_text")
         self.prompt_language = config.get("prompt_language")
         self.text_language = config.get("text_language", "audo")
-        self.top_k = config.get("top_k", 15)
+        self.top_k = int(config.get("top_k", 15))
-        self.top_p = config.get("top_p", 1.0)
+        self.top_p = float(config.get("top_p", 1.0))
-        self.temperature = config.get("temperature", 1.0)
+        self.temperature = float(config.get("temperature", 1.0))
-        self.cut_punc = config.get("cut_punc","")
+        self.cut_punc = config.get("cut_punc", "")
-        self.speed = config.get("speed", 1.0)
+        self.speed = float(config.get("speed", 1.0))
-        self.inp_refs = config.get("inp_refs",[])
+        self.inp_refs = config.get("inp_refs", [])
-        self.sample_steps = config.get("sample_steps",32)
+        self.sample_steps = int(config.get("sample_steps", 32))
-        self.if_sr = config.get("if_sr",False)
+        self.if_sr = bool(config.get("if_sr", False))
-
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_params = {
@@ -51,4 +54,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

main/xiaozhi-server/core/providers/tts/minimax.py

@@ -12,28 +12,33 @@ class TTSProvider(TTSProviderBase):
         self.group_id = config.get("group_id")
         self.api_key = config.get("api_key")
         self.model = config.get("model")
-        self.voice_id = config.get("voice_id")
+        if config.get("private_voice"):
+            self.voice_id = config.get("private_voice")
+        else:
+            self.voice_id = config.get("voice_id")
 
         default_voice_setting = {
             "voice_id": "female-shaonv",
             "speed": 1,
             "vol": 1,
             "pitch": 0,
-            "emotion": "happy"
+            "emotion": "happy",
-        }
-        default_pronunciation_dict = {
-            "tone": [
-                "处理/(chu3)(li3)", "危险/dangerous"
-            ]
         }
+        default_pronunciation_dict = {"tone": ["处理/(chu3)(li3)", "危险/dangerous"]}
         defult_audio_setting = {
             "sample_rate": 32000,
             "bitrate": 128000,
             "format": "mp3",
-            "channel": 1
+            "channel": 1,
+        }
+        self.voice_setting = {
+            **default_voice_setting,
+            **config.get("voice_setting", {}),
+        }
+        self.pronunciation_dict = {
+            **default_pronunciation_dict,
+            **config.get("pronunciation_dict", {}),
         }
-        self.voice_setting = {**default_voice_setting, **config.get("voice_setting", {})}
-        self.pronunciation_dict = {**default_pronunciation_dict, **config.get("pronunciation_dict", {})}
         self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
         self.timber_weights = config.get("timber_weights", [])
 
@@ -44,11 +49,14 @@ class TTSProvider(TTSProviderBase):
         self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"
         self.header = {
             "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}"
+            "Authorization": f"Bearer {self.api_key}",
         }
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -65,13 +73,17 @@ class TTSProvider(TTSProviderBase):
             request_json["voice_setting"]["voice_id"] = ""
 
         try:
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=self.header
+            )
             # 检查返回请求数据的status_code是否为0
             if resp.json()["base_resp"]["status_code"] == 0:
-                data = resp.json()['data']['audio']
+                data = resp.json()["data"]["audio"]
                 file_to_save = open(output_file, "wb")
                 file_to_save.write(bytes.fromhex(data))
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

main/xiaozhi-server/core/providers/tts/openai.py

@@ -16,9 +16,12 @@ class TTSProvider(TTSProviderBase):
         self.api_key = config.get("api_key")
         self.api_url = config.get("api_url", "https://api.openai.com/v1/audio/speech")
         self.model = config.get("model", "tts-1")
-        self.voice = config.get("voice", "alloy")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
-        self.speed = config.get("speed", 1.0)
+        self.speed = float(config.get("speed", 1.0))
         self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 

main/xiaozhi-server/core/providers/tts/siliconflow.py

@@ -10,17 +10,23 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
         self.access_token = config.get("access_token")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.response_format = config.get("response_format")
         self.sample_rate = config.get("sample_rate")
-        self.speed = config.get("speed")
+        self.speed = float(config.get("speed"))
         self.gain = config.get("gain")
 
         self.host = "api.siliconflow.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -31,9 +37,11 @@ class TTSProvider(TTSProviderBase):
         }
         headers = {
             "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
-        response = requests.request("POST", self.api_url, json=request_json, headers=headers)
+        response = requests.request(
+            "POST", self.api_url, json=request_json, headers=headers
+        )
         data = response.content
         file_to_save = open(output_file, "wb")
         file_to_save.write(data)

main/xiaozhi-server/core/providers/tts/tencent.py

@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
         self.appid = config.get("appid")
         self.secret_id = config.get("secret_id")
         self.secret_key = config.get("secret_key")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = int(config.get("voice"))
         self.api_url = "https://tts.tencentcloudapi.com"  # 正确的API端点
         self.region = config.get("region")
         self.output_file = config.get("output_dir")
@@ -25,35 +28,36 @@ class TTSProvider(TTSProviderBase):
         """生成鉴权请求头"""
         # 获取当前UTC时间戳
         timestamp = int(time.time())
-        
+
         # 使用UTC时间计算日期
-        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime('%Y-%m-%d')
+        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime(
-        
+            "%Y-%m-%d"
+        )
+
         # 服务名称必须是 "tts"
         service = "tts"
-        
+
         # 拼接凭证范围
         credential_scope = f"{utc_date}/{service}/tc3_request"
-        
+
         # 使用TC3-HMAC-SHA256签名方法
         algorithm = "TC3-HMAC-SHA256"
-        
+
         # 构建规范请求字符串
         http_request_method = "POST"
         canonical_uri = "/"
         canonical_querystring = ""
-        
+
         # 请求头必须包含host和content-type，且按字典序排列
         canonical_headers = (
-            f"content-type:application/json\n"
+            f"content-type:application/json\n" f"host:tts.tencentcloudapi.com\n"
-            f"host:tts.tencentcloudapi.com\n"
         )
         signed_headers = "content-type;host"
-        
+
         # 请求体哈希值
         payload = json.dumps(request_body)
-        payload_hash = hashlib.sha256(payload.encode('utf-8')).hexdigest()
+        payload_hash = hashlib.sha256(payload.encode("utf-8")).hexdigest()
-        
+
         # 构建规范请求字符串
         canonical_request = (
             f"{http_request_method}\n"
@@ -63,10 +67,12 @@ class TTSProvider(TTSProviderBase):
             f"{signed_headers}\n"
             f"{payload_hash}"
         )
-        
+
         # 计算规范请求的哈希值
-        hashed_canonical_request = hashlib.sha256(canonical_request.encode('utf-8')).hexdigest()
+        hashed_canonical_request = hashlib.sha256(
-        
+            canonical_request.encode("utf-8")
+        ).hexdigest()
+
         # 构建待签名字符串
         string_to_sign = (
             f"{algorithm}\n"
@@ -74,19 +80,19 @@ class TTSProvider(TTSProviderBase):
             f"{credential_scope}\n"
             f"{hashed_canonical_request}"
         )
-        
+
         # 计算签名密钥
-        secret_date = self._hmac_sha256(f"TC3{self.secret_key}".encode('utf-8'), utc_date)
+        secret_date = self._hmac_sha256(
+            f"TC3{self.secret_key}".encode("utf-8"), utc_date
+        )
         secret_service = self._hmac_sha256(secret_date, service)
         secret_signing = self._hmac_sha256(secret_service, "tc3_request")
-        
+
         # 计算签名
         signature = hmac.new(
-            secret_signing, 
+            secret_signing, string_to_sign.encode("utf-8"), hashlib.sha256
-            string_to_sign.encode('utf-8'), 
-            hashlib.sha256
         ).hexdigest()
-        
+
         # 构建授权头
         authorization = (
             f"{algorithm} "
@@ -94,7 +100,7 @@ class TTSProvider(TTSProviderBase):
             f"SignedHeaders={signed_headers}, "
             f"Signature={signature}"
         )
-        
+
         # 构建请求头
         headers = {
             "Content-Type": "application/json",
@@ -104,19 +110,22 @@ class TTSProvider(TTSProviderBase):
             "X-TC-Timestamp": str(timestamp),
             "X-TC-Version": "2019-08-23",
             "X-TC-Region": self.region,
-            "X-TC-Language": "zh-CN"
+            "X-TC-Language": "zh-CN",
         }
-        
+
         return headers
-    
+
     def _hmac_sha256(self, key, msg):
         """HMAC-SHA256加密"""
         if isinstance(msg, str):
-            msg = msg.encode('utf-8')
+            msg = msg.encode("utf-8")
         return hmac.new(key, msg, hashlib.sha256).digest()
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         # 构建请求体
@@ -129,19 +138,23 @@ class TTSProvider(TTSProviderBase):
         try:
             # 获取请求头（每次请求都重新生成，以确保时间戳和签名是最新的）
             headers = self._get_auth_headers(request_json)
-            
+
             # 发送请求
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=headers)
+            resp = requests.post(
-            
+                self.api_url, json.dumps(request_json), headers=headers
+            )
+
             # 检查响应
             if resp.status_code == 200:
                 response_data = resp.json()
-                
+
                 # 检查是否成功
                 if response_data.get("Response", {}).get("Error") is not None:
                     error_info = response_data["Response"]["Error"]
-                    raise Exception(f"API返回错误: {error_info['Code']}: {error_info['Message']}")
+                    raise Exception(
-                
+                        f"API返回错误: {error_info['Code']}: {error_info['Message']}"
+                    )
+
                 # 提取音频数据
                 audio_data = response_data["Response"].get("Audio")
                 if audio_data:
@@ -151,6 +164,8 @@ class TTSProvider(TTSProviderBase):
                 else:
                     raise Exception(f"{__name__}: 没有返回音频数据: {response_data}")
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

main/xiaozhi-server/core/providers/tts/ttson.py

@@ -10,48 +10,62 @@ from core.providers.tts.base import TTSProviderBase
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        self.url = config.get("url", "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=")
+        self.url = config.get(
-        self.voice_id = config.get("voice_id", 1695)
+            "url",
+            "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=",
+        )
+        if config.get("private_voice"):
+            self.voice_id = int(config.get("private_voice"))
+        else:
+            self.voice_id = int(config.get("voice_id", 1695))
         self.token = config.get("token")
         self.to_lang = config.get("to_lang")
-        self.volume_change_dB = config.get("volume_change_dB", 0)
+        self.volume_change_dB = int(config.get("volume_change_dB", 0))
-        self.speed_factor = config.get("speed_factor", 1)
+        self.speed_factor = int(config.get("speed_factor", 1))
-        self.stream = config.get("stream", False)
+        self.stream = bool(config.get("stream", False))
         self.output_file = config.get("output_dir")
-        self.pitch_factor = config.get("pitch_factor", 0)
+        self.pitch_factor = int(config.get("pitch_factor", 0))
         self.format = config.get("format", "mp3")
-        self.emotion = config.get("emotion", 1)
+        self.emotion = int(config.get("emotion", 1))
-        self.header = {
+        self.header = {"Content-Type": "application/json"}
-            "Content-Type": "application/json"
-        }
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
-        url = f'{self.url}{self.token}'
+        url = f"{self.url}{self.token}"
         result = "firefly"
-        payload = json.dumps({
+        payload = json.dumps(
-            "to_lang": self.to_lang,
+            {
-            "text": text,
+                "to_lang": self.to_lang,
-            "emotion": self.emotion,
+                "text": text,
-            "format": self.format,
+                "emotion": self.emotion,
-            "volume_change_dB": self.volume_change_dB,
+                "format": self.format,
-            "voice_id": self.voice_id,
+                "volume_change_dB": self.volume_change_dB,
-            "pitch_factor": self.pitch_factor,
+                "voice_id": self.voice_id,
-            "speed_factor": self.speed_factor,
+                "pitch_factor": self.pitch_factor,
-            "token": self.token
+                "speed_factor": self.speed_factor,
-        })
+                "token": self.token,
+            }
+        )
 
         resp = requests.request("POST", url, data=payload)
         if resp.status_code != 200:
             return None
         resp_json = resp.json()
         try:
-            result = resp_json['url'] + ':' + str(
+            result = (
-                resp_json[
+                resp_json["url"]
-                    'port']) + '/flashsummary/retrieveFileData?stream=True&token=' + self.token + '&voice_audio_path=' + \
+                + ":"
-                     resp_json['voice_path']
+                + str(resp_json["port"])
+                + "/flashsummary/retrieveFileData?stream=True&token="
+                + self.token
+                + "&voice_audio_path="
+                + resp_json["voice_path"]
+            )
         except Exception as e:
             print("error:", e)
 

main/xiaozhi-server/core/providers/vad/silero.py

@@ -21,8 +21,8 @@ class VADProvider(VADProviderBase):
         (get_speech_timestamps, _, _, _, _) = self.utils
 
         self.decoder = opuslib_next.Decoder(16000, 1)
-        self.vad_threshold = config.get("threshold")
+        self.vad_threshold = float(config.get("threshold", 0.5))
-        self.silence_threshold_ms = config.get("min_silence_duration_ms")
+        self.silence_threshold_ms = int(config.get("min_silence_duration_ms", 1000))
 
     def is_vad(self, conn, opus_packet):
         try:
@@ -42,7 +42,8 @@ class VADProvider(VADProviderBase):
                 audio_tensor = torch.from_numpy(audio_float32)
 
                 # 检测语音活动
-                speech_prob = self.model(audio_tensor, 16000).item()
+                with torch.no_grad():
+                    speech_prob = self.model(audio_tensor, 16000).item()
                 client_have_voice = speech_prob >= self.vad_threshold
 
                 # 如果之前有声音，但本次没有声音，且与上次有声音的时间查已经超过了静默阈值，则认为已经说完一句话

main/xiaozhi-server/core/utils/util.py

@@ -230,7 +230,7 @@ def initialize_modules(
         modules["tts"] = tts.create_instance(
             tts_type,
             config["TTS"][config["selected_module"]["TTS"]],
-            config["delete_audio"],
+            bool(config.get("delete_audio", True)),
         )
         logger.bind(tag=TAG).info(f"初始化组件: tts成功")
 
@@ -294,7 +294,7 @@ def initialize_modules(
         modules["asr"] = asr.create_instance(
             asr_type,
             config["ASR"][config["selected_module"]["ASR"]],
-            config["delete_audio"],
+            bool(config.get("delete_audio", True)),
         )
         logger.bind(tag=TAG).info(f"初始化组件: asr成功")
 

main/xiaozhi-server/core/websocket_server.py

@@ -25,7 +25,7 @@ class WebSocketServer:
     async def start(self):
         server_config = self.config["server"]
         host = server_config["ip"]
-        port = server_config["port"]
+        port = int(server_config.get("port", 8000))
 
         self.logger.bind(tag=TAG).info(
             "Server is running at ws://{}:{}/xiaozhi/v1/", get_local_ip(), port

main/xiaozhi-server/docker-compose_all.yml

@@ -1,25 +1,17 @@
 # Docker安装全模块
 
-# 1、安装mysql
-# |- 如果本机已经安装了MySQL，可以直接在数据库中创建名为`xiaozhi_esp32_server`的数据库。
-# |- 如果还没有MySQL，你可以通过docker安装mysql,执行以下一句话
-# |- docker run --name xiaozhi-esp32-server-db -e MYSQL_ROOT_PASSWORD=123456 -p 3306:3306 -e MYSQL_DATABASE=xiaozhi_esp32_server -e MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci" -d mysql:latest
-# |- 记得修改下方SPRING_DATASOURCE_DRUID_URL的IP，ip不能写127.0.0.1或localhost，否则容器无法访问，要写你电脑局域网ip
-
-# 2、安装redis
-# |- 如果本机已经安装了Redis，看一下你安装的redis端口、密码，然后修改下方redis的地址和端口
-# |- 如果还没有Redis，你可以通过docker安装redis,执行以下一句话
-# |- docker run --name xiaozhi-esp32-server-redis -d -p 6379:6379 redis
-# |- 记得修改SPRING_DATA_REDIS_HOST的IP，ip不能写127.0.0.1或localhost，否则容器无法访问，要写你电脑局域网ip
-
-
 version: '3'
 services:
   # Server模块
   xiaozhi-esp32-server:
     image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
     container_name: xiaozhi-esp32-server
+    depends_on:
+      - xiaozhi-esp32-server-db
+      - xiaozhi-esp32-server-redis
     restart: always
+    networks:
+      - default
     ports:
       # ws服务端
       - "8000:8000"
@@ -38,14 +30,55 @@ services:
     image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
     container_name: xiaozhi-esp32-server-web
     restart: always
+    networks:
+      - default
+    depends_on:
+      xiaozhi-esp32-server-db:
+        condition: service_healthy
+      xiaozhi-esp32-server-redis:
+        condition: service_healthy
     ports:
       # 智控台
       - "8002:8002"
     environment:
       - TZ=Asia/Shanghai
       ##记得改mysql和redis IP 密码
-      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://192.168.1.25:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai
+      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://xiaozhi-esp32-server-db:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai&nullCatalogMeansCurrent=true&connectTimeout=30000&socketTimeout=30000&autoReconnect=true&failOverReadOnly=false&maxReconnects=10
       - SPRING_DATASOURCE_DRUID_USERNAME=root
       - SPRING_DATASOURCE_DRUID_PASSWORD=123456
-      - SPRING_DATA_REDIS_HOST=192.168.1.25
+      - SPRING_DATA_REDIS_HOST=xiaozhi-esp32-server-redis
       - SPRING_DATA_REDIS_PORT=6379
+  xiaozhi-esp32-server-db:
+    image: mysql:latest
+    container_name: xiaozhi-esp32-server-db
+    healthcheck:
+      test: [ "CMD", "mysqladmin" ,"ping", "-h", "localhost" ]
+      timeout: 45s
+      interval: 10s
+      retries: 10
+    restart: always
+    networks:
+      - default
+    expose:
+      - "3306:3306"
+    volumes:
+      - ./mysql/data:/var/lib/mysql
+    environment:
+      - TZ=Asia/Shanghai
+      - MYSQL_ROOT_PASSWORD=123456
+      - MYSQL_DATABASE=xiaozhi_esp32_server
+      - MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci"
+  xiaozhi-esp32-server-redis:
+    image: redis
+    expose:
+      - 6379
+    container_name: xiaozhi-esp32-server-redis
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+    networks:
+      - default
+networks:
+  default:

main/xiaozhi-server/plugins_func/functions/handle_exit_intent.py

@@ -1,34 +1,43 @@
-from plugins_func.register import register_function,ToolType, ActionResponse, Action
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
 from config.logger import setup_logging
 
 TAG = __name__
 logger = setup_logging()
 
 handle_exit_intent_function_desc = {
-                "type": "function",
+    "type": "function",
-                "function": {
+    "function": {
-                    "name": "handle_exit_intent",
+        "name": "handle_exit_intent",
-                    "description": "当用户想结束对话或需要退出系统时调用",
+        "description": "当用户想结束对话或需要退出系统时调用",
-                    "parameters": {
+        "parameters": {
-                        "type": "object",
+            "type": "object",
-                        "properties": {
+            "properties": {
-                            "say_goodbye": {
+                "say_goodbye": {
-                                "type": "string",
+                    "type": "string",
-                                "description": "和用户友好结束对话的告别语"
+                    "description": "和用户友好结束对话的告别语",
-                            }
-                        },
-                        "required": ["say_goodbye"]
-                    }
                 }
-            }
+            },
+            "required": ["say_goodbye"],
+        },
+    },
+}
 
-@register_function('handle_exit_intent', handle_exit_intent_function_desc, ToolType.SYSTEM_CTL)
+
-def handle_exit_intent(conn, say_goodbye: str):
+@register_function(
+    "handle_exit_intent", handle_exit_intent_function_desc, ToolType.SYSTEM_CTL
+)
+def handle_exit_intent(conn, say_goodbye: str | None = None):
     # 处理退出意图
     try:
+        if say_goodbye is None:
+            say_goodbye = "再见，祝您生活愉快！"
         conn.close_after_chat = True
         logger.bind(tag=TAG).info(f"退出意图已处理:{say_goodbye}")
-        return ActionResponse(action=Action.RESPONSE, result="退出意图已处理", response=say_goodbye)
+        return ActionResponse(
+            action=Action.RESPONSE, result="退出意图已处理", response=say_goodbye
+        )
     except Exception as e:
         logger.bind(tag=TAG).error(f"处理退出意图错误: {e}")
-        return ActionResponse(action=Action.NONE, result="退出意图处理失败", response="")
+        return ActionResponse(
+            action=Action.NONE, result="退出意图处理失败", response=""
+        )

main/xiaozhi-server/plugins_func/functions/hass_init.py

@@ -9,7 +9,9 @@ HASS_CACHE = {}
 
 def append_devices_to_prompt(conn):
     if conn.use_function_call_mode:
-        funcs = conn.config["Intent"]["function_call"].get("functions", [])
+        funcs = conn.config["Intent"][conn.config["selected_module"]["Intent"]].get(
+            "functions", []
+        )
         if "hass_get_state" in funcs or "hass_set_state" in funcs:
             prompt = "下面是我家智能设备，可以通过homeassistant控制\n"
             devices = conn.config["plugins"]["home_assistant"].get("devices", [])
@@ -26,7 +28,9 @@ def initialize_hass_handler(conn):
     global HASS_CACHE
     if HASS_CACHE == {}:
         if conn.use_function_call_mode:
-            funcs = conn.config["Intent"]["function_call"].get("functions", [])
+            funcs = conn.config["Intent"][conn.config["selected_module"]["Intent"]].get(
+                "functions", []
+            )
             if "hass_get_state" in funcs or "hass_set_state" in funcs:
                 HASS_CACHE["base_url"] = conn.config["plugins"]["home_assistant"].get(
                     "base_url"