update:新增SLM唤醒词回复

Perf：新增联网搜索工具类、修复新闻描述配置获取源问题

.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: pip
+    directory: /main/xiaozhi-server
+    schedule:
+      interval: weekly

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

@@ -0,0 +1,49 @@
+name: Build Base Image
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'main/xiaozhi-server/requirements.txt'
+      - 'Dockerfile-server-base'
+      - '.github/workflows/build-base-image.yml'
+
+jobs:
+  build-base:
+    name: Build and push server base image
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.TOKEN }}
+
+      - name: Build and push server-base
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile-server-base
+          push: true
+          tags: ghcr.io/${{ github.repository }}:server-base
+          platforms: linux/amd64,linux/arm64
+          cache-from: type=gha,scope=server-base
+          cache-to: type=gha,mode=max,scope=server-base
+          build-args: |
+            BUILDKIT_PROGRESS=plain
+
+      - name: Output image info
+        run: |
+          echo "✅ Base image built and pushed successfully!"
+          echo "📦 Tag: ghcr.io/${{ github.repository }}:server-base"

.github/workflows/docker-image.yml

@@ -5,6 +5,10 @@ on:
     tags:
       - 'v*.*.*'  # 只在以 v 开头的标签推送时触发，例如 v1.0.0
   workflow_dispatch:
+  workflow_run:
+    workflows: ["Build Base Image"]
+    types:
+      - completed
 
 jobs:
   release:
@@ -31,6 +35,9 @@ jobs:
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            network=host
 
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
@@ -60,6 +67,10 @@ jobs:
           tags: |
             ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:server_{1},ghcr.io/{0}:server_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:server_latest', github.repository) }}
           platforms: linux/amd64,linux/arm64
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: |
+            BUILDKIT_PROGRESS=plain
 
       # 构建 manager-api 镜像
       - name: Build and push manager-web
@@ -71,3 +82,7 @@ jobs:
           tags: |
             ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:web_{1},ghcr.io/{0}:web_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:web_latest', github.repository) }}
           platforms: linux/amd64,linux/arm64
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: |
+            BUILDKIT_PROGRESS=plain

.gitignore

@@ -3,6 +3,9 @@ __pycache__/
 .idea/
 *.py[cod]
 *$py.class
+.vscode
+.claude
+AGENTS.md
 
 # C extensions
 *.so
@@ -146,6 +149,7 @@ tmp
 .history
 .DS_Store
 main/xiaozhi-server/data
+main/xiaozhi-server/.claude
 
 main/manager-web/node_modules
 .config.yaml
@@ -174,3 +178,17 @@ main/xiaozhi-server/mysql
 uploadfile
 *.json
 .vscode
+.cursor
+ 
+!package.json
+!**/package.json
+
+# Do not ignore env and json files inside manager-mobile
+!main/manager-mobile/**/env/
+!main/manager-mobile/**/.env*
+!main/manager-mobile/**/*.json
+!main/xiaozhi-server/**/*.json
+!main/digital-human/**/*.json
+main/digital-human/wakeword_runtime/models
+main/digital-human/wakeword_runtime/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
+sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2

Dockerfile-server

@@ -1,28 +1,6 @@
-# 第一阶段：构建Python依赖
+# 生产镜像，仅包含应用代码
-FROM python:3.10-slim AS builder
+FROM ghcr.io/xinnan-tech/xiaozhi-esp32-server:server-base
 
-WORKDIR /app
-
-COPY main/xiaozhi-server/requirements.txt .
-
-# 安装Python依赖
-RUN pip install --no-cache-dir -r requirements.txt
-
-# 第二阶段：生产镜像
-FROM python:3.10-slim
-
-WORKDIR /opt/xiaozhi-esp32-server
-
-# 安装系统依赖
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends libopus0 ffmpeg && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-
-# 从构建阶段复制Python包和前端构建产物
-COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
-
-# 复制应用代码
 COPY main/xiaozhi-server .
 
 # 启动应用

Dockerfile-server-base

@@ -0,0 +1,32 @@
+# Dockerfile-server-base
+# 基础镜像，包含系统依赖和Python包
+FROM python:3.10-slim
+
+# 安装系统依赖
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends libopus0 ffmpeg locales && \
+    sed -i '/zh_CN.UTF-8/s/^# //g' /etc/locale.gen && \
+    locale-gen && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 配置pip使用国内镜像源（阿里云）并设置超时和重试
+RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple/ && \
+    pip config set global.trusted-host mirrors.aliyun.com && \
+    pip config set global.timeout 120 && \
+    pip config set install.retries 5
+
+# 设置环境变量以确保正确的字符编码
+ENV LANG=zh_CN.UTF-8 \
+    LC_ALL=zh_CN.UTF-8 \
+    LANGUAGE=zh_CN:zh \
+    PYTHONIOENCODING=utf-8
+
+WORKDIR /opt/xiaozhi-esp32-server
+
+# 复制requirements.txt
+COPY main/xiaozhi-server/requirements.txt .
+
+# 安装Python依赖
+RUN pip install --no-cache-dir --upgrade pip setuptools wheel && \
+    pip install --no-cache-dir -r requirements.txt --default-timeout=120 --retries 5

Dockerfile-web

@@ -1,5 +1,5 @@
 # 第一阶段：构建Vue前端
-FROM node:18 as web-builder
+FROM node:18 AS web-builder
 WORKDIR /app
 COPY main/manager-web/package*.json ./
 RUN npm install
@@ -7,7 +7,7 @@ COPY main/manager-web .
 RUN npm run build
 
 # 第二阶段：构建Java后端
-FROM maven:3.9.4-eclipse-temurin-21 as api-builder
+FROM maven:3.9.4-eclipse-temurin-21 AS api-builder
 WORKDIR /app
 COPY main/manager-api/pom.xml .
 COPY main/manager-api/src ./src
@@ -18,12 +18,19 @@ FROM bellsoft/liberica-runtime-container:jre-21-glibc
 
 # 安装Nginx和字体库
 RUN apk update && \
-    apk add --no-cache nginx bash && \
+    apk add --no-cache --no-scripts \
-    apk add --no-cache fontconfig ttf-dejavu msttcorefonts-installer && \
+        nginx \
-    rm -rf /var/cache/apk/*
+        bash \
+        fontconfig \
+        ttf-dejavu \
+    && rm -rf /var/cache/apk/* \
+    && mkdir -p /run/nginx /var/log/nginx /var/tmp/nginx /etc/nginx/conf.d
+
+# 复制项目自带的中文字体
+COPY main/manager-web/public/generator/static/fonts/*.ttf /usr/share/fonts/
 
 # 更新字体缓存
-RUN printf 'YES\n' | update-ms-fonts && fc-cache -f -v
+RUN fc-cache -f -v
 
 # 配置Nginx
 COPY docs/docker/nginx.conf /etc/nginx/nginx.conf

README.md

@@ -3,32 +3,28 @@
 <h1 align="center">小智后端服务xiaozhi-esp32-server</h1>
 
 <p align="center">
-本项目为开源智能硬件项目
+本项目基于人机共生智能理论和技术研发智能终端软硬件体系<br/>为开源智能硬件项目
 <a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a>提供后端服务<br/>
 根据<a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">小智通信协议</a>使用Python、Java、Vue实现<br/>
-帮助您快速搭建小智服务器
+支持MQTT+UDP协议、Websocket协议、MCP接入点、声纹识别、知识库
 </p>
 
 <p align="center">
-<a href="./README_en.md">English</a>
+<a href="./docs/FAQ.md">常见问题</a>
-· <a href="./docs/FAQ.md">常见问题</a>
 · <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">反馈问题</a>
 · <a href="./README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">部署文档</a>
 · <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">更新日志</a>
 </p>
+
 <p align="center">
+  <a href="./README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DBEDFA"></a>
+  <a href="./docs/readme/README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
+  <a href="./docs/readme/README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
+  <a href="./docs/readme/README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
+  <a href="./docs/readme/README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
   <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
     <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
   </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors">
-    <img alt="GitHub Contributors" src="https://img.shields.io/github/contributors/xinnan-tech/xiaozhi-esp32-server?logo=github" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">
-    <img alt="Issues" src="https://img.shields.io/github/issues/xinnan-tech/xiaozhi-esp32-server?color=0088ff" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/pulls">
-    <img alt="GitHub pull requests" src="https://img.shields.io/github/issues-pr/xinnan-tech/xiaozhi-esp32-server?color=0088ff" />
-  </a>
   <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
     <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
   </a>
@@ -37,6 +33,14 @@
   </a>
 </p>
 
+<p align="center">
+Spearheaded by Professor Siyuan Liu's Team (South China University of Technology)
+</br>
+刘思源教授团队主导研发（华南理工大学）
+</br>
+<img src="./docs/images/hnlg.jpg" alt="华南理工大学" width="50%">
+</p>
+
 ---
 
 ## 适用人群 👥
@@ -51,24 +55,40 @@
     <td>
         <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
          <picture>
-           <img alt="小智esp32连接自己的后台模型" src="docs/images/demo1.png" />
+           <img alt="响应速度感受" src="docs/images/demo9.png" />
          </picture>
         </a>
     </td>
     <td>
-        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
+        <a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
          <picture>
-           <img alt="自定义音色" src="docs/images/demo2.png" />
+           <img alt="速度优化秘诀" src="docs/images/demo6.png" />
          </picture>
         </a>
     </td>
     <td>
-        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+        <a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
          <picture>
-           <img alt="使用粤语交流" src="docs/images/demo3.png" />
+           <img alt="复杂医疗场景" src="docs/images/demo1.png" />
          </picture>
         </a>
     </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
+         <picture>
+           <img alt="MQTT指令下发" src="docs/images/demo4.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
+         <picture>
+           <img alt="声纹识别" src="docs/images/demo14.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
     <td>
         <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
          <picture>
@@ -77,18 +97,16 @@
         </a>
     </td>
     <td>
-        <a href="https://www.bilibili.com/video/BV1kgA2eYEQ9" target="_blank">
+        <a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
          <picture>
-           <img alt="成本最低配置" src="docs/images/demo4.png" />
+           <img alt="MCP接入点" src="docs/images/demo13.png" />
          </picture>
         </a>
     </td>
-  </tr>
-  <tr>
     <td>
-        <a href="https://www.bilibili.com/video/BV1Vy96YCE3R" target="_blank">
+      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
          <picture>
-           <img alt="自定义音色" src="docs/images/demo6.png" />
+           <img alt="多指令任务" src="docs/images/demo11.png" />
          </picture>
         </a>
     </td>
@@ -106,20 +124,6 @@
          </picture>
         </a>
     </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV178XuYfEpi" target="_blank">
-         <picture>
-           <img alt="IOT指令控制设备" src="docs/images/demo9.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
-         <picture>
-           <img alt="播报新闻" src="docs/images/demo0.png" />
-         </picture>
-        </a>
-    </td>
   </tr>
   <tr>
     <td>
@@ -137,15 +141,25 @@
         </a>
     </td>
     <td>
-      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
+        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
          <picture>
-           <img alt="多指令任务" src="docs/images/demo11.png" />
+           <img alt="自定义音色" src="docs/images/demo2.png" />
          </picture>
         </a>
     </td>
     <td>
+        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+         <picture>
+           <img alt="使用粤语交流" src="docs/images/demo3.png" />
+         </picture>
+        </a>
     </td>
     <td>
+        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
+         <picture>
+           <img alt="播报新闻" src="docs/images/demo0.png" />
+         </picture>
+        </a>
     </td>
   </tr>
 </table>
@@ -170,14 +184,16 @@
 #### 🚀 部署方式选择
 | 部署方式 | 特点 | 适用场景 | 部署文档 | 配置要求 | 视频教程 | 
 |---------|------|---------|---------|---------|---------|
-| **最简化安装** | 智能对话、IOT、MCP、视觉感知，数据存储在配置文件 | 低配置环境，无需数据库 | [①Docker版](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②源码部署](./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)| 如果使用`FunASR`要2核4G，如果全API，要2核2G | - | 
+| **最简化安装** | 智能对话、单智能体管理 | 低配置环境，数据存储在配置文件，无需数据库 | [①Docker版](./docs/Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②源码部署](./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)| 如果使用`FunASR`要2核4G，如果全API，要2核2G | - | 
-| **全模块安装** | 智能对话、IOT、MCP、视觉感知、OTA、智控台，数据存储在数据库 | 完整功能体验 |[①Docker版](./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) / [②源码部署](./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) / [③源码部署自动更新教程](./docs/dev-ops-integration.md) | 如果使用`FunASR`要4核8G，如果全API，要2核4G| [本地源码启动视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) | 
+| **全模块安装** | 智能对话、多用户管理、多智能体管理、智控台界面操作 | 完整功能体验，数据存储在数据库 |[①Docker版](./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) / [②源码部署](./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) / [③源码部署自动更新教程](./docs/dev-ops-integration.md) | 如果使用`FunASR`要4核8G，如果全API，要2核4G| [本地源码启动视频教程](https://www.bilibili.com/video/BV1wBJhz4Ewe) | 
 
+常见问题及相关教程，可参考[这个链接](./docs/FAQ.md)
 
-> 💡 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
+> 💡 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，
 
 ```
 智控台地址: https://2662r3426b.vicp.fun
+智控台(h5版): https://2662r3426b.vicp.fun/h5/index.html
 
 服务测试工具： https://2662r3426b.vicp.fun/test/
 OTA接口地址: https://2662r3426b.vicp.fun/xiaozhi/ota/
@@ -196,72 +212,71 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 
 | 模块名称 | 入门全免费设置 | 流式配置 |
 |:---:|:---:|:---:|
-| ASR(语音识别) | FunASR(本地) | 👍FunASRServer 或 👍DoubaoStreamASR |
+| ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) |
-| LLM(大模型) | ChatGLMLLM(智谱glm-4-flash) | 👍DoubaoLLM(火山doubao-1-5-pro-32k-250115) |
+| LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) |
-| VLLM(视觉大模型) | ChatGLMVLLM(智谱glm-4v-flash) | 👍QwenVLVLLM(千问qwen2.5-vl-3b-instructh) |
+| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen3.5-flash(阿里百炼) |
-| TTS(语音合成) | ✅LinkeraiTTS(灵犀流式) | 👍HuoshanDoubleStreamTTS(火山双流式语音合成) |
+| TTS(语音合成) | EdgeTTS(微软) | 👍HuoshanDoubleStreamTTS(火山流式) |
 | Intent(意图识别) | function_call(函数调用) | function_call(函数调用) |
 | Memory(记忆功能) | mem_local_short(本地短期记忆） | mem_local_short（本地短期记忆） |
 
+如果您关心各组件的耗时，请查阅[小智各组件性能测试报告](https://github.com/xinnan-tech/xiaozhi-performance-research)，可按报告中的测试方法在您的环境中实际测试。
+
 #### 🔧 测试工具
 本项目提供以下测试工具，帮助您验证系统和选择合适的模型：
 
 | 工具名称 | 位置 | 使用方法 | 功能说明 |
 |:---:|:---|:---:|:---:|
-| 音频交互测试工具 | main》xiaozhi-server》test》test_page.html | 使用谷歌浏览器直接打开 | 测试音频播放和接收功能，验证Python端音频处理是否正常 |
+| 音频交互测试工具 | main》digital-human》index.html | 在 `main/digital-human` 执行 `python start.py` 后访问 `http://127.0.0.1:8006/index.html` | 测试音频播放和接收功能，验证Python端音频处理是否正常 |
-| 模型响应测试工具1 | main》xiaozhi-server》performance_tester.py | 执行 `python performance_tester.py` | 测试ASR(语音识别)、LLM(大模型)、TTS(语音合成)三个核心模块的响应速度 |
+| 模型响应测试工具 | main》xiaozhi-server》performance_tester.py | 执行 `python performance_tester.py` | 测试ASR(语音识别)、LLM(大模型)、VLLM(视觉模型)、TTS(语音合成)三个核心模块的响应速度 |
-| 模型响应测试工具2 | main》xiaozhi-server》performance_tester_vllm.py | 执行 `python performance_tester_vllm.py` | 测试VLLM(视觉模型)的响应速度 |
 
 > 💡 提示：测试模型速度时，只会测试配置了密钥的模型。
 
 ---
 ## 功能清单 ✨
 ### 已实现 ✅
-
+![请参考-全模块安装架构图](docs/images/deploy2.png)
 | 功能模块 | 描述 |
 |:---:|:---|
-| 核心服务架构 | 基于WebSocket和HTTP服务器，提供完整的控制台管理和认证系统 |
+| 核心架构 | 基于[MQTT+UDP网关](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md)、WebSocket、HTTP服务器，提供完整的控制台管理和认证系统 |
-| 语音交互系统 | 支持流式ASR(语音识别)、流式TTS(语音合成)、VAD(语音活动检测)，支持多语言识别和语音处理 |
+| 语音交互 | 支持流式ASR(语音识别)、流式TTS(语音合成)、VAD(语音活动检测)，支持多语言识别和语音处理 |
-| 智能对话系统 | 支持多种LLM(大语言模型)，实现智能对话 |
+| 声纹识别 | 支持多用户声纹注册、管理和识别，与ASR并行处理，实时识别说话人身份并传递给LLM进行个性化回应 |
-| 视觉感知系统 | 支持多种VLLM(视觉大模型)，实现多模态交互 |
+| 智能对话 | 支持多种LLM(大语言模型)，实现智能对话 |
-| 意图识别系统 | 支持LLM意图识别、Function Call函数调用，提供插件化意图处理机制 |
+| 视觉感知 | 支持多种VLLM(视觉大模型)，实现多模态交互 |
-| 记忆系统 | 支持本地短期记忆、mem0ai接口记忆，具备记忆总结功能 |
+| 意图识别 | 支持外挂的大模型意图识别、大模型自主函数调用，提供插件化意图处理机制 |
-| IOT/MCP控制协议 | 支持设备注册管理、智能控制接口，同时支持IOT、MCP控制协议 |
+| 记忆系统 | 支持本地短期记忆、mem0ai接口记忆、PowerMem智能记忆，具备记忆总结功能 |
-| 管理后台 | 提供Web管理界面，支持用户管理、系统配置和设备管理 |
+| 知识库 | 支持RAGFlow知识库，让大模型判断需要调度知识库后再回答 |
+| 工具调用 | 支持客户端IOT协议、客户MCP协议、服务端MCP协议、MCP接入点协议、自定义工具函数 |
+| 指令下发 | 依托MQTT协议，支持从智控台将MCP指令下发到ESP32设备 |
+| 管理后台 | 提供Web管理界面，支持用户管理、系统配置和设备管理；界面支持中文简体、中文繁体、英文显示 |
 | 测试工具 | 提供性能测试工具、视觉模型测试工具和音频交互测试工具 |
 | 部署支持 | 支持Docker部署和本地部署，提供完整的配置文件管理 |
 | 插件系统 | 支持功能插件扩展、自定义插件开发和插件热加载 |
 
 ### 正在开发 🚧
 
-想了解具体开发计划进度，[请点击这里](https://github.com/users/xinnan-tech/projects/3)
+想了解具体开发计划进度，[请点击这里](https://github.com/users/xinnan-tech/projects/3)。常见问题及相关教程，可参考[这个链接](./docs/FAQ.md)
 
 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
+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](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE)
-
-| 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
 
 | 使用方式 | 支持平台 | 免费平台 |
 |:---:|:---:|:---:|
-| openai 接口调用 | 阿里百炼、火山引擎豆包、深度求索、智谱ChatGLM、Gemini | 智谱ChatGLM、Gemini |
+| openai 接口调用 | 阿里百炼、火山引擎、DeepSeek、智谱、Gemini、科大讯飞 | 智谱、Gemini |
 | ollama 接口调用 | Ollama | - |
 | dify 接口调用 | Dify | - |
 | fastgpt 接口调用 | Fastgpt | - |
 | coze 接口调用 | Coze | - |
+| xinference 接口调用 | Xinference | - |
+| homeassistant 接口调用 | HomeAssistant | - |
 
 实际上，任何支持 openai 接口调用的 LLM 均可接入使用。
 
@@ -281,8 +296,8 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 
 | 使用方式 | 支持平台 | 免费平台 |
 |:---:|:---:|:---:|
-| 接口调用 | EdgeTTS、火山引擎豆包TTS、腾讯云、阿里云TTS、CosyVoiceSiliconflow、TTS302AI、CozeCnTTS、GizwitsTTS、ACGNTTS、OpenAITTS、灵犀流式TTS | 灵犀流式TTS、EdgeTTS、CosyVoiceSiliconflow(部分) |
+| 接口调用 | EdgeTTS、科大讯飞、火山引擎、腾讯云、阿里云及百炼、CosyVoiceSiliconflow、TTS302AI、CozeCnTTS、GizwitsTTS、ACGNTTS、OpenAITTS、灵犀流式TTS、MinimaxTTS | 灵犀流式TTS、EdgeTTS、CosyVoiceSiliconflow(部分) |
-| 本地服务 | FishSpeech、GPT_SOVITS_V2、GPT_SOVITS_V3、MinimaxTTS | FishSpeech、GPT_SOVITS_V2、GPT_SOVITS_V3、MinimaxTTS |
+| 本地服务 | FishSpeech、GPT_SOVITS_V2、GPT_SOVITS_V3、Index-TTS、PaddleSpeech | Index-TTS、PaddleSpeech、FishSpeech、GPT_SOVITS_V2、GPT_SOVITS_V3 |
 
 ---
 
@@ -299,7 +314,15 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 | 使用方式 | 支持平台 | 免费平台 |
 |:---:|:---:|:---:|
 | 本地使用 | FunASR、SherpaASR | FunASR、SherpaASR |
-| 接口调用 | DoubaoASR、FunASRServer、TencentASR、AliyunASR | FunASRServer |
+| 接口调用 | FunASRServer、火山引擎、科大讯飞、腾讯云、阿里云、百度云、OpenAI ASR | FunASRServer |
+
+---
+
+### Voiceprint 声纹识别
+
+| 使用方式 | 支持平台 | 免费平台 |
+|:---:|:---:|:---:|
+| 本地使用 | 3D-Speaker | 3D-Speaker |
 
 ---
 
@@ -308,7 +331,9 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |   类型   |      平台名称       | 使用方式 |   收费模式    | 备注 |
 |:------:|:---------------:|:----:|:---------:|:--:|
 | Memory |     mem0ai      | 接口调用 | 1000次/月额度 |    |
+| Memory |     [powermem](./docs/powermem-integration.md)    | 本地总结 | 取决于LLM和DB |  OceanBase开源，支持智能检索  |
 | Memory | mem_local_short | 本地总结 |    免费     |    |
+| Memory |     nomem       | 无记忆模式 |    免费     |    |
 
 ---
 
@@ -318,6 +343,15 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 |:------:|:-------------:|:----:|:-------:|:---------------------:|
 | Intent |  intent_llm   | 接口调用 | 根据LLM收费 |    通过大模型识别意图，通用性强     |
 | Intent | function_call | 接口调用 | 根据LLM收费 | 通过大模型函数调用完成意图，速度快，效果好 |
+| Intent |    nointent   | 无意图模式 |    免费     |    不进行意图识别，直接返回对话结果     |
+
+---
+
+### Rag 检索增强生成
+
+|   类型   |     平台名称      | 使用方式 |  收费模式   |          备注           |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Rag |  ragflow   | 接口调用 | 根据切片、分词消耗的token收费 |    借助RagFlow的检索增强生成功能，提供更准确的对话回复     |
 
 ---
 
@@ -328,8 +362,10 @@ Websocket接口地址: wss://2662r3426b.vicp.fun/xiaozhi/v1/
 | <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_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | 感谢[huangjunsen](https://github.com/huangjunsen0406) 贡献`智控台移动端`模块，实现了跨平台移动设备的高效控制与实时交互，大幅提升了系统在移动场景下的操作便捷性和管理效率 |
 | <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 |
+| <img src="./docs/images/logo_contributors.png" width="160"> | [代码贡献者](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | 感谢[所有代码贡献者](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors)贡献者，你们的付出让项目更加健壮和强大。 |
 
 
 <a href="https://star-history.com/#xinnan-tech/xiaozhi-esp32-server&Date">

README_en.md

@@ -1,311 +0,0 @@
-[![Banners](docs/images/banner1.png)](https://github.com/xinnan-tech/xiaozhi-esp32-server)
-
-<h1 align="center">Xiaozhi Backend Service xiaozhi-esp32-server</h1>
-
-<p align="center">
-This project provides backend services for the open-source smart hardware project
-<a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a><br/>
-Implemented using Python, Java, and Vue according to the <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Xiaozhi Communication Protocol</a><br/>
-Helps you quickly set up your Xiaozhi server
-</p>
-
-<p align="center">
-<a href="./README.md">中文</a>
-· <a href="./docs/FAQ.md">FAQ</a>
-· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Report Issues</a>
-· <a href="./README_en.md#deployment-documentation">Deployment Guide</a>
-· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Release Notes</a>
-</p>
-<p align="center">
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
-    <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors">
-    <img alt="GitHub Contributors" src="https://img.shields.io/github/contributors/xinnan-tech/xiaozhi-esp32-server?logo=github" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">
-    <img alt="Issues" src="https://img.shields.io/github/issues/xinnan-tech/xiaozhi-esp32-server?color=0088ff" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/pulls">
-    <img alt="GitHub pull requests" src="https://img.shields.io/github/issues-pr/xinnan-tech/xiaozhi-esp32-server?color=0088ff" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
-    <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
-  </a>
-  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server">
-    <img alt="stars" src="https://img.shields.io/github/stars/xinnan-tech/xiaozhi-esp32-server?color=ffcb47&labelColor=black" />
-  </a>
-</p>
-
----
-
-## Target Users 👥
-
-This project requires ESP32 hardware devices. If you have purchased ESP32-related hardware, successfully connected to Brother Xia's backend service, and want to set up your own `xiaozhi-esp32` backend service, then this project is perfect for you.
-
-Want to see it in action? Check out these videos 🎥
-
-<table>
-  <tr>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
-         <picture>
-           <img alt="Xiaozhi esp32 connecting to own backend model" src="docs/images/demo1.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
-         <picture>
-           <img alt="Custom voice" src="docs/images/demo2.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
-         <picture>
-           <img alt="Using Cantonese" src="docs/images/demo3.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
-         <picture>
-           <img alt="Control home appliances" src="docs/images/demo5.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1kgA2eYEQ9" target="_blank">
-         <picture>
-           <img alt="Lowest cost configuration" src="docs/images/demo4.png" />
-         </picture>
-        </a>
-    </td>
-  </tr>
-  <tr>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1Vy96YCE3R" target="_blank">
-         <picture>
-           <img alt="Custom voice" src="docs/images/demo6.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
-         <picture>
-           <img alt="Play music" src="docs/images/demo7.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
-         <picture>
-           <img alt="Weather plugin" src="docs/images/demo8.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV178XuYfEpi" target="_blank">
-         <picture>
-           <img alt="IOT command control" src="docs/images/demo9.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
-         <picture>
-           <img alt="News broadcast" src="docs/images/demo0.png" />
-         </picture>
-        </a>
-    </td>
-  </tr>
-  <tr>
-    <td>
-      <a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
-         <picture>
-           <img alt="Real-time interruption" src="docs/images/demo10.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-      <a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
-         <picture>
-           <img alt="Photo recognition" src="docs/images/demo12.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
-         <picture>
-           <img alt="Multi-command tasks" src="docs/images/demo11.png" />
-         </picture>
-        </a>
-    </td>
-    <td>
-    </td>
-    <td>
-    </td>
-  </tr>
-</table>
-
----
-
-## Warning ⚠️
-
-1. This project is open-source software. This software has no commercial relationship with any third-party API service providers (including but not limited to speech recognition, large models, speech synthesis, and other platforms) and does not provide any form of guarantee for their service quality or financial security.
-It is recommended that users prioritize service providers with relevant business licenses and carefully read their service agreements and privacy policies. This software does not host any account keys, does not participate in fund transfers, and does not bear the risk of recharge fund losses.
-
-2. This project's functionality is not complete and has not passed network security testing. Please do not use it in production environments. If you deploy this project for learning in a public network environment, please ensure necessary protection measures are in place.
-
----
-
-## Deployment Documentation
-
-![Banners](docs/images/banner2.png)
-
-This project provides two deployment methods. Please choose according to your specific needs:
-
-#### 🚀 Deployment Method Selection
-| Deployment Method | Features | Suitable Scenarios | Deployment Guide | Requirements | Video Tutorial | 
-|---------|------|---------|---------|---------|---------|
-| **Simplified Installation** | Smart dialogue, IOT functionality, data stored in configuration files | Low-configuration environment, no database needed | [Docker Version](./docs/Deployment.md#method-1-docker-server-only) / [Source Code Deployment](./docs/Deployment.md#method-2-local-source-code-server-only) | 2 cores 4G if using `FunASR`, 2 cores 2G if using all APIs | - | 
-| **Full Module Installation** | Smart dialogue, IOT, OTA, Control Panel, data stored in database | Complete functionality experience | [Docker Version](./docs/Deployment_all.md#method-1-docker-full-modules) / [Source Code Deployment](./docs/Deployment_all.md#method-2-local-source-code-full-modules) | 4 cores 8G if using `FunASR`, 2 cores 4G if using all APIs | [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) / [Local Source Code Auto-Update Tutorial](./docs/dev-ops-integration.md) | 
-
-> 💡 Note: Below are the test platforms deployed with the latest code. You can flash and test if needed. Concurrent users: 6, data will be cleared daily
-
-```
-Control Panel Address: https://2662r3426b.vicp.fun
-
-Service Test Tool: https://2662r3426b.vicp.fun/test/
-OTA Interface Address: https://2662r3426b.vicp.fun/xiaozhi/ota/
-Websocket Interface Address: wss://2662r3426b.vicp.fun/xiaozhi/v1/
-```
-
-#### 🚩 Configuration Description and Recommendations
-> [!Note]
-> The default configuration of this project is `Entry Level Free` settings. For better results, we recommend using `Full Streaming Configuration`.
-> 
-> Since version `0.5.2`, this project supports full streaming throughout the entire lifecycle. Compared to versions before `0.5`, response speed has improved by approximately `2.5 seconds`
-
-| Module Name | Entry Level Free Settings | Full Streaming Configuration |
-|---------|---------|------|
-| ASR(Speech Recognition) | FunASR(Local) | ✅DoubaoASR(Volcano Streaming Speech Recognition) |
-| LLM(Large Language Model) | ChatGLMLLM(Zhipu glm-4-flash) | ✅DoubaoLLM(Volcano doubao-1-5-pro-32k-250115) |
-| VLLM(Vision Large Model) | ChatGLMVLLM(Zhipu glm-4v-flash) | ✅ChatGLMVLLM(Zhipu glm-4v-flash) |
-| TTS(Speech Synthesis) | EdgeTTS(Microsoft Speech) | ✅HuoshanDoubleStreamTTS(Volcano Double Streaming Speech Synthesis) |
-| Intent(Intent Recognition) | function_call(Function Call) | ✅function_call(Function Call) |
-| Memory(Memory Function) | mem_local_short(Local Short-term Memory) | ✅mem_local_short(Local Short-term Memory) |
-
----
-## Feature List ✨
-### Implemented ✅
-
-| Feature Module | Description |
-|---------|------|
-| Communication Protocol | Based on `xiaozhi-esp32` protocol, implements data interaction through WebSocket |
-| Dialogue Interaction | Supports wake-up dialogue, manual dialogue, and real-time interruption. Auto-sleep after long periods of no dialogue |
-| Intent Recognition | Supports LLM intent recognition, function call, reducing hard-coded intent judgment |
-| Multi-language Recognition | Supports Mandarin, Cantonese, English, Japanese, Korean (default using FunASR) |
-| LLM Module | Supports flexible LLM module switching, default using ChatGLMLLM, can also use Ali Bailian, DeepSeek, Ollama, etc. |
-| TTS Module | Supports EdgeTTS (default), Volcano Engine Doubao TTS, and other TTS interfaces |
-| Memory Function | Supports ultra-long memory, local summary memory, and no memory modes |
-| IOT Function | Supports managing registered device IOT functionality, supports smart IoT control based on dialogue context |
-| Control Panel | Provides Web management interface, supports agent management, user management, system configuration, etc. |
-
-### In Development 🚧
-
-To learn about specific development progress, [click here](https://github.com/users/xinnan-tech/projects/3)
-
-If you are a software developer, here is an [Open Letter to Developers](docs/contributor_open_letter.md). Welcome to join!
-
----
-
-## Product Ecosystem 👬
-Xiaozhi is an ecosystem. When using this product, you might also want to check out other excellent projects in this ecosystem
-
-| Project Name | Project Address | Project Description |
-|:---------------------|:--------|:--------|
-| Xiaozhi Android Client | [xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) | A Flutter-based Android and iOS voice dialogue application supporting real-time voice interaction and text dialogue. |
-| Xiaozhi PC Client | [py-xiaozhi](https://github.com/Huang-junsen/py-xiaozhi) | This project provides a Python-based Xiaozhi AI client, allowing you to experience Xiaozhi AI's functionality through code even without physical hardware. |
-| Xiaozhi Java Server | [xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) | The Java version of Xiaozhi open-source backend service is a Java-based open-source project.<br/>It includes both frontend and backend services, aiming to provide users with a complete backend service solution. |
-
----
-
-## Supported Platforms/Components List 📋
-
-### LLM Language Models
-
-| Usage Method | Supported Platforms | Free Platforms |
-|:---:|:---:|:---:|
-| openai interface call | Ali Bailian, Volcano Engine Doubao, DeepSeek, Zhipu ChatGLM, Gemini | Zhipu ChatGLM, Gemini |
-| ollama interface call | Ollama | - |
-| dify interface call | Dify | - |
-| fastgpt interface call | Fastgpt | - |
-| coze interface call | Coze | - |
-
-In fact, any LLM that supports openai interface calls can be integrated and used.
-
-### TTS Speech Synthesis
-
-| Usage Method | Supported Platforms | Free Platforms |
-|:---:|:---:|:---:|
-| API Call | EdgeTTS, Volcano Engine Doubao TTS, Tencent Cloud, Alibaba Cloud TTS, CosyVoiceSiliconflow, TTS302AI, CozeCnTTS, GizwitsTTS, ACGNTTS, OpenAITTS | EdgeTTS, CosyVoiceSiliconflow(partial) |
-| Local Service | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, MinimaxTTS | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, MinimaxTTS |
-
----
-
-### VAD Voice Activity Detection
-
-| Type | Platform Name | Usage Method | Pricing Model | Notes |
-|:---:|:---------:|:----:|:----:|:--:|
-| VAD | SileroVAD | Local Usage | Free | |
-
----
-
-### ASR Speech Recognition
-
-| Usage Method | Supported Platforms | Free Platforms |
-|:---:|:---:|:---:|
-| Local Usage | FunASR, SherpaASR | FunASR, SherpaASR |
-| API Call | DoubaoASR, FunASRServer, TencentASR, AliyunASR | FunASRServer |
-
----
-
-### Memory Storage
-
-| Type | Platform Name | Usage Method | Pricing Model | Notes |
-|:------:|:---------------:|:----:|:---------:|:--:|
-| Memory | mem0ai | API Call | 1000 calls/month quota | |
-| Memory | mem_local_short | Local Summary | Free | |
-
----
-
-### Intent Recognition
-
-| Type | Platform Name | Usage Method | Pricing Model | Notes |
-|:------:|:-------------:|:----:|:-------:|:---------------------:|
-| Intent | intent_llm | API Call | Based on LLM pricing | Uses large model for intent recognition, highly versatile |
-| Intent | function_call | API Call | Based on LLM pricing | Uses large model function calls for intent, fast and effective |
-
----
-
-## Acknowledgments 🙏
-
-| Logo | Project/Company | Description |
-|:---:|:---:|:---|
-| <img src="./docs/images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | This project was inspired by [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) and implemented based on it |
-| <img src="./docs/images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Thanks to [Tenclass](https://www.tenclass.com/) for establishing standard communication protocols, multi-device compatibility solutions, and high-concurrency scenario practices for the Xiaozhi ecosystem; providing full-chain technical documentation support for this project |
-| <img src="./docs/images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Thanks to [Xuanfeng Technology](https://github.com/Eric0308) for contributing the function call framework, MCP communication protocol, and plugin call mechanism implementation code, significantly improving front-end device (IoT) interaction efficiency and functional extensibility through standardized instruction scheduling system and dynamic expansion capabilities |
-| <img src="./docs/images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Thanks to [Huiyuan Design](http://ui.kwd988.net/) for providing professional visual solutions for this project, empowering the product user experience with their design experience serving over a thousand enterprises |
-| <img src="./docs/images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Thanks to [Xi'an Qinren Information Technology](https://www.029app.com/) for deepening the visual system of this project, ensuring consistency and extensibility of the overall design style in multi-scenario applications |
-
-
-<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" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />
- </picture>
-</a>

docker-setup.sh

@@ -1,105 +1,413 @@
 #!/bin/sh
+# 脚本作者@VanillaNahida
 # 本文件是用于一键自动下载本项目所需文件，自动创建好目录
-# 所需条件（否则无法使用）：
+# 暂且只支持X86版本的Ubuntu系统，其他系统未测试
-# 1、请确保你的环境可以正常访问 GitHub 否则无法下载脚本
+
-#
+# 定义中断处理函数
-# 检测操作系统类型
+handle_interrupt() {
-case "$(uname -s)" in
+    echo ""
-    Linux*)     OS=Linux;;
+    echo "安装已被用户中断(Ctrl+C或Esc)"
-    Darwin*)    OS=Mac;;
+    echo "如需重新安装，请再次运行脚本"
-    CYGWIN*)    OS=Windows;;
+    exit 1
-    MINGW*)     OS=Windows;;
+}
-    MSYS*)      OS=Windows;;
+
-    *)          OS=UNKNOWN;;
+# 设置信号捕获，处理Ctrl+C
+trap handle_interrupt SIGINT
+
+# 处理Esc键
+# 保存终端设置
+old_stty_settings=$(stty -g)
+# 设置终端立即响应，不回显
+stty -icanon -echo min 1 time 0
+
+# 后台进程检测Esc键
+(while true; do
+    read -r key
+    if [[ $key == $'\e' ]]; then
+        # 检测到Esc键，触发中断处理
+        kill -SIGINT $$
+        break
+    fi
+done) &
+
+# 脚本结束时恢复终端设置
+trap 'stty "$old_stty_settings"' EXIT
+
+
+# 打印彩色字符画
+echo -e "\e[1;32m"  # 设置颜色为亮绿色
+cat << "EOF"
+脚本作者：@Bilibili 香草味的纳西妲喵
+ __      __            _  _  _            _   _         _      _      _        
+ \ \    / /           (_)| || |          | \ | |       | |    (_)    | |       
+  \ \  / /__ _  _ __   _ | || |  __ _    |  \| |  __ _ | |__   _   __| |  __ _ 
+   \ \/ // _` || '_ \ | || || | / _` |   | . ` | / _` || '_ \ | | / _` | / _` |
+    \  /| (_| || | | || || || || (_| |   | |\  || (_| || | | || || (_| || (_| |
+     \/  \__,_||_| |_||_||_||_| \__,_|   |_| \_| \__,_||_| |_||_| \__,_| \__,_|                                                                                                                                                                                                                               
+EOF
+echo -e "\e[0m"  # 重置颜色
+echo -e "\e[1;36m  小智服务端全量部署一键安装脚本 Ver 0.2 2025年8月20日更新 \e[0m\n"
+sleep 1
+
+
+
+# 检查并安装whiptail
+check_whiptail() {
+    if ! command -v whiptail &> /dev/null; then
+        echo "正在安装whiptail..."
+        apt update
+        apt install -y whiptail
+    fi
+}
+
+check_whiptail
+
+# 创建确认对话框
+whiptail --title "安装确认" --yesno "即将安装小智服务端，是否继续？" \
+  --yes-button "继续" --no-button "退出" 10 50
+
+# 根据用户选择执行操作
+case $? in
+  0)
+    ;;
+  1)
+    exit 1
+    ;;
 esac
 
-# 设置颜色（Windows CMD 不支持，但不影响使用）
+# 检查root权限
-if [ "$OS" = "Windows" ]; then
+if [ $EUID -ne 0 ]; then
-    GREEN=""
+    whiptail --title "权限错误" --msgbox "请使用root权限运行本脚本" 10 50
-    RED=""
-    NC=""
-else
-    GREEN='\033[0;32m'
-    RED='\033[0;31m'
-    NC='\033[0m'
-fi
-
-echo "${GREEN}开始安装小智服务端...${NC}"
-
-# 创建必要的目录
-echo "创建目录结构..."
-mkdir -p xiaozhi-server/data xiaozhi-server/models/SenseVoiceSmall
-cd xiaozhi-server || exit
-
-# 根据操作系统选择下载命令
-if [ "$OS" = "Windows" ]; then
-    DOWNLOAD_CMD="curl -L -o"
-    if ! command -v curl >/dev/null 2>&1; then
-        DOWNLOAD_CMD="powershell -Command Invoke-WebRequest -Uri"
-        DOWNLOAD_CMD_SUFFIX="-OutFile"
-    fi
-else
-    if command -v curl >/dev/null 2>&1; then
-        DOWNLOAD_CMD="curl -L -o"
-    elif command -v wget >/dev/null 2>&1; then
-        DOWNLOAD_CMD="wget -O"
-    else
-        echo "${RED}错误: 需要安装 curl 或 wget${NC}"
-        exit 1
-    fi
-fi
-
-# 下载语音识别模型
-echo "下载语音识别模型..."
-if [ "$DOWNLOAD_CMD" = "powershell -Command Invoke-WebRequest -Uri" ]; then
-    $DOWNLOAD_CMD "https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt" $DOWNLOAD_CMD_SUFFIX "models/SenseVoiceSmall/model.pt"
-else
-    $DOWNLOAD_CMD "models/SenseVoiceSmall/model.pt" "https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt"
-fi
-
-if [ $? -ne 0 ]; then
-    echo "${RED}模型下载失败。请手动从以下地址下载：${NC}"
-    echo "1. https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt"
-    echo "2. 百度网盘: https://pan.baidu.com/share/init?surl=QlgM58FHhYv1tFnUT_A8Sg (提取码: qvna)"
-    echo "下载后请将文件放置在 models/SenseVoiceSmall/model.pt"
-fi
-
-# 下载配置文件
-echo "下载配置文件..."
-if [ "$DOWNLOAD_CMD" = "powershell -Command Invoke-WebRequest -Uri" ]; then
-    $DOWNLOAD_CMD "https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/main/xiaozhi-server/docker-compose.yml" $DOWNLOAD_CMD_SUFFIX "docker-compose.yml"
-    $DOWNLOAD_CMD "https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/main/xiaozhi-server/config.yaml" $DOWNLOAD_CMD_SUFFIX "data/.config.yaml"
-else
-    $DOWNLOAD_CMD "docker-compose.yml" "https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/main/xiaozhi-server/docker-compose.yml"
-    $DOWNLOAD_CMD "data/.config.yaml" "https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/main/xiaozhi-server/config.yaml"
-fi
-
-# 检查文件是否存在
-echo "检查文件完整性..."
-FILES_TO_CHECK="docker-compose.yml data/.config.yaml models/SenseVoiceSmall/model.pt"
-ALL_FILES_EXIST=true
-
-for FILE in $FILES_TO_CHECK; do
-    if [ ! -f "$FILE" ]; then
-        echo "${RED}错误: $FILE 不存在${NC}"
-        ALL_FILES_EXIST=false
-    fi
-done
-
-if [ "$ALL_FILES_EXIST" = false ]; then
-    echo "${RED}某些文件下载失败，请检查上述错误信息并手动下载缺失的文件。${NC}"
     exit 1
 fi
 
-echo "${GREEN}文件下载完成！${NC}"
+# 检查系统版本
-echo "请编辑 data/.config.yaml 文件配置你的API密钥。"
+if [ -f /etc/os-release ]; then
-echo "配置完成后，运行以下命令启动服务："
+    . /etc/os-release
-echo "${GREEN}docker-compose up -d${NC}"
+    if [ "$ID" != "debian" ] && [ "$ID" != "ubuntu" ]; then
-echo "查看日志请运行："
+        whiptail --title "系统错误" --msgbox "该脚本只支持Debian/Ubuntu系统执行" 10 60
-echo "${GREEN}docker logs -f xiaozhi-esp32-server${NC}"
+        exit 1
+    fi
+else
+    whiptail --title "系统错误" --msgbox "无法确定系统版本，该脚本只支持Debian/Ubuntu系统执行" 10 60
+    exit 1
+fi
 
-# 提示用户编辑配置文件
+# 下载配置文件函数
-echo "\n${RED}重要提示：${NC}"
+check_and_download() {
-echo "1. 请确保编辑 data/.config.yaml 文件，配置必要的API密钥"
+    local filepath=$1
-echo "2. 特别是 ChatGLM 和 mem0ai 的密钥必须配置"
+    local url=$2
-echo "3. 配置完成后再启动 docker 服务"
+    if [ ! -f "$filepath" ]; then
+        if ! curl -fL --progress-bar "$url" -o "$filepath"; then
+            whiptail --title "错误" --msgbox "${filepath}文件下载失败" 10 50
+            exit 1
+        fi
+    else
+        echo "${filepath}文件已存在，跳过下载"
+    fi
+}
+
+# 检查是否已安装
+check_installed() {
+    # 检查目录是否存在且非空
+    if [ -d "/opt/xiaozhi-server/" ] && [ "$(ls -A /opt/xiaozhi-server/)" ]; then
+        DIR_CHECK=1
+    else
+        DIR_CHECK=0
+    fi
+    
+    # 检查容器是否存在
+    if docker inspect xiaozhi-esp32-server > /dev/null 2>&1; then
+        CONTAINER_CHECK=1
+    else
+        CONTAINER_CHECK=0
+    fi
+    
+    # 两次检查都通过
+    if [ $DIR_CHECK -eq 1 ] && [ $CONTAINER_CHECK -eq 1 ]; then
+        return 0  # 已安装
+    else
+        return 1  # 未安装
+    fi
+}
+
+# 更新相关
+if check_installed; then
+    if whiptail --title "已安装检测" --yesno "检测到小智服务端已安装，是否进行升级？" 10 60; then
+        # 用户选择升级，执行清理操作
+        echo "开始升级操作..."
+        
+        # 停止并移除所有docker-compose服务
+        docker compose -f /opt/xiaozhi-server/docker-compose_all.yml down
+        
+        # 停止并删除特定容器（考虑容器可能不存在的情况）
+        containers=(
+            "xiaozhi-esp32-server"
+            "xiaozhi-esp32-server-web"
+            "xiaozhi-esp32-server-db"
+            "xiaozhi-esp32-server-redis"
+        )
+        
+        for container in "${containers[@]}"; do
+            if docker ps -a --format '{{.Names}}' | grep -q "^${container}$"; then
+                docker stop "$container" >/dev/null 2>&1 && \
+                docker rm "$container" >/dev/null 2>&1 && \
+                echo "成功移除容器: $container"
+            else
+                echo "容器不存在，跳过: $container"
+            fi
+        done
+        
+        # 删除特定镜像（考虑镜像可能不存在的情况）
+        images=(
+            "ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest"
+            "ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest"
+        )
+        
+        for image in "${images[@]}"; do
+            if docker images --format '{{.Repository}}:{{.Tag}}' | grep -q "^${image}$"; then
+                docker rmi "$image" >/dev/null 2>&1 && \
+                echo "成功删除镜像: $image"
+            else
+                echo "镜像不存在，跳过: $image"
+            fi
+        done
+        
+        echo "所有清理操作完成"
+        
+        # 备份原有配置文件
+        mkdir -p /opt/xiaozhi-server/backup/
+        if [ -f /opt/xiaozhi-server/data/.config.yaml ]; then
+            cp /opt/xiaozhi-server/data/.config.yaml /opt/xiaozhi-server/backup/.config.yaml
+            echo "已备份原有配置文件到 /opt/xiaozhi-server/backup/.config.yaml"
+        fi
+        
+        # 下载最新版配置文件
+        check_and_download "/opt/xiaozhi-server/docker-compose_all.yml" "https://ghfast.top/https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/docker-compose_all.yml"
+        check_and_download "/opt/xiaozhi-server/data/.config.yaml" "https://ghfast.top/https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/config_from_api.yaml"
+        
+        # 启动Docker服务
+        echo "开始启动最新版本服务..."
+        # 升级完成后标记，跳过后续下载步骤
+        UPGRADE_COMPLETED=1
+        docker compose -f /opt/xiaozhi-server/docker-compose_all.yml up -d
+    else
+          whiptail --title "跳过升级" --msgbox "已取消升级，将继续使用当前版本。" 10 50
+          # 跳过升级，继续执行后续安装流程
+    fi
+fi
+
+
+# 检查curl安装
+if ! command -v curl &> /dev/null; then
+    echo "------------------------------------------------------------"
+    echo "未检测到curl，正在安装..."
+    apt update
+    apt install -y curl
+else
+    echo "------------------------------------------------------------"
+    echo "curl已安装，跳过安装步骤"
+fi
+
+# 检查Docker安装
+if ! command -v docker &> /dev/null; then
+    echo "------------------------------------------------------------"
+    echo "未检测到Docker，正在安装..."
+    
+    # 使用国内镜像源替代官方源
+    DISTRO=$(lsb_release -cs)
+    MIRROR_URL="https://mirrors.aliyun.com/docker-ce/linux/ubuntu"
+    GPG_URL="https://mirrors.aliyun.com/docker-ce/linux/ubuntu/gpg"
+    
+    # 安装基础依赖
+    apt update
+    apt install -y apt-transport-https ca-certificates curl software-properties-common gnupg
+    
+    # 创建密钥目录并添加国内镜像源密钥
+    mkdir -p /etc/apt/keyrings
+    curl -fsSL "$GPG_URL" | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
+    
+    # 添加国内镜像源
+    echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] $MIRROR_URL $DISTRO stable" \
+        > /etc/apt/sources.list.d/docker.list
+    
+    # 添加备用官方源密钥（避免国内源密钥验证失败）
+    apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 7EA0A9C3F273FCD8 2>/dev/null || \
+    echo "警告：部分密钥添加失败，继续尝试安装..."
+    
+    # 安装Docker
+    apt update
+    apt install -y docker-ce docker-ce-cli containerd.io
+    
+    # 启动服务
+    systemctl start docker
+    systemctl enable docker
+    
+    # 检查是否安装成功
+    if docker --version; then
+        echo "------------------------------------------------------------"
+        echo "Docker安装完成！"
+    else
+        whiptail --title "错误" --msgbox "Docker安装失败，请检查日志。" 10 50
+        exit 1
+    fi
+else
+    echo "Docker已安装，跳过安装步骤"
+fi
+
+# Docker镜像源配置
+MIRROR_OPTIONS=(
+    "1" "轩辕镜像 (推荐)"
+    "2" "腾讯云镜像源"
+    "3" "中科大镜像源"
+    "4" "网易163镜像源"
+    "5" "华为云镜像源"
+    "6" "阿里云镜像源"
+    "7" "自定义镜像源"
+    "8" "跳过配置"
+)
+
+MIRROR_CHOICE=$(whiptail --title "选择Docker镜像源" --menu "请选择要使用的Docker镜像源" 20 60 10 \
+"${MIRROR_OPTIONS[@]}" 3>&1 1>&2 2>&3) || {
+    echo "用户取消选择，退出脚本"
+    exit 1
+}
+
+case $MIRROR_CHOICE in
+    1) MIRROR_URL="https://docker.xuanyuan.me" ;; 
+    2) MIRROR_URL="https://mirror.ccs.tencentyun.com" ;; 
+    3) MIRROR_URL="https://docker.mirrors.ustc.edu.cn" ;; 
+    4) MIRROR_URL="https://hub-mirror.c.163.com" ;; 
+    5) MIRROR_URL="https://05f073ad3c0010ea0f4bc00b7105ec20.mirror.swr.myhuaweicloud.com" ;; 
+    6) MIRROR_URL="https://registry.aliyuncs.com" ;; 
+    7) MIRROR_URL=$(whiptail --title "自定义镜像源" --inputbox "请输入完整的镜像源URL:" 10 60 3>&1 1>&2 2>&3) ;; 
+    8) MIRROR_URL="" ;; 
+esac
+
+if [ -n "$MIRROR_URL" ]; then
+    mkdir -p /etc/docker
+    if [ -f /etc/docker/daemon.json ]; then
+        cp /etc/docker/daemon.json /etc/docker/daemon.json.bak
+    fi
+    cat > /etc/docker/daemon.json <<EOF
+{
+    "dns": ["8.8.8.8", "114.114.114.114"],
+    "registry-mirrors": ["$MIRROR_URL"]
+}
+EOF
+    whiptail --title "配置成功" --msgbox "已成功添加镜像源: $MIRROR_URL\n请按Enter键重启Docker服务并继续..." 12 60
+    echo "------------------------------------------------------------"
+    echo "开始重启Docker服务..."
+    systemctl restart docker.service
+fi
+
+# 创建安装目录
+echo "------------------------------------------------------------"
+echo "开始创建安装目录..."
+# 检查并创建数据目录
+if [ ! -d /opt/xiaozhi-server/data ]; then
+    mkdir -p /opt/xiaozhi-server/data
+    echo "已创建数据目录: /opt/xiaozhi-server/data"
+else
+    echo "目录xiaozhi-server/data已存在，跳过创建"
+fi
+
+# 检查并创建模型目录
+if [ ! -d /opt/xiaozhi-server/models/SenseVoiceSmall ]; then
+    mkdir -p /opt/xiaozhi-server/models/SenseVoiceSmall
+    echo "已创建模型目录: /opt/xiaozhi-server/models/SenseVoiceSmall"
+else
+    echo "目录xiaozhi-server/models/SenseVoiceSmall已存在，跳过创建"
+fi
+
+echo "------------------------------------------------------------"
+echo "开始下载语音识别模型"
+# 下载模型文件
+MODEL_PATH="/opt/xiaozhi-server/models/SenseVoiceSmall/model.pt"
+if [ ! -f "$MODEL_PATH" ]; then
+    (
+    for i in {1..20}; do
+        echo $((i*5))
+        sleep 0.5
+    done
+    ) | whiptail --title "下载中" --gauge "开始下载语音识别模型..." 10 60 0
+    curl -fL --progress-bar https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt -o "$MODEL_PATH" || {
+        whiptail --title "错误" --msgbox "model.pt文件下载失败" 10 50
+        exit 1
+    }
+else
+    echo "model.pt文件已存在，跳过下载"
+fi
+
+# 如果不是升级完成，才执行下载
+if [ -z "$UPGRADE_COMPLETED" ]; then
+    check_and_download "/opt/xiaozhi-server/docker-compose_all.yml" "https://ghfast.top/https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/docker-compose_all.yml"
+    check_and_download "/opt/xiaozhi-server/data/.config.yaml" "https://ghfast.top/https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/refs/heads/main/main/xiaozhi-server/config_from_api.yaml"
+fi
+
+# 启动Docker服务
+(
+echo "------------------------------------------------------------"
+echo "正在拉取Docker镜像..."
+echo "这可能需要几分钟时间，请耐心等待"
+docker compose -f /opt/xiaozhi-server/docker-compose_all.yml up -d
+
+if [ $? -ne 0 ]; then
+    whiptail --title "错误" --msgbox "Docker服务启动失败，请尝试更换镜像源后重新执行本脚本" 10 60
+    exit 1
+fi
+
+echo "------------------------------------------------------------"
+echo "正在检查服务启动状态..."
+TIMEOUT=300
+START_TIME=$(date +%s)
+while true; do
+    CURRENT_TIME=$(date +%s)
+    if [ $((CURRENT_TIME - START_TIME)) -gt $TIMEOUT ]; then
+        whiptail --title "错误" --msgbox "服务启动超时，未在指定时间内找到预期日志内容" 10 60
+        exit 1
+    fi
+    
+    if docker logs xiaozhi-esp32-server-web 2>&1 | grep -q "Started AdminApplication in"; then
+        break
+    fi
+    sleep 1
+done
+
+    echo "服务端启动成功！正在完成配置..."
+    echo "正在启动服务..."
+    docker compose -f /opt/xiaozhi-server/docker-compose_all.yml up -d
+    echo "服务启动完成！"
+)
+
+# 密钥配置
+
+# 获取服务器公网地址
+PUBLIC_IP=$(hostname -I | awk '{print $1}')
+whiptail --title "配置服务器密钥" --msgbox "请使用浏览器，访问下方链接，打开智控台并注册账号: \n\n内网地址：http://127.0.0.1:8002/\n公网地址：http://$PUBLIC_IP:8002/ (若是云服务器请在服务器安全组放行端口 8000 8001 8002)。\n\n注册的第一个用户即是超级管理员，以后注册的用户都是普通用户。普通用户只能绑定设备和配置智能体; 超级管理员可以进行模型管理、用户管理、参数配置等功能。\n\n注册好后请按Enter键继续" 18 70
+SECRET_KEY=$(whiptail --title "配置服务器密钥" --inputbox "请使用超级管理员账号登录智控台\n内网地址：http://127.0.0.1:8002/\n公网地址：http://$PUBLIC_IP:8002/\n在顶部菜单 参数字典 → 参数管理 找到参数编码: server.secret (服务器密钥) \n复制该参数值并输入到下面输入框\n\n请输入密钥(留空则跳过配置):" 15 60 3>&1 1>&2 2>&3)
+
+if [ -n "$SECRET_KEY" ]; then
+    python3 -c "
+import sys, yaml; 
+config_path = '/opt/xiaozhi-server/data/.config.yaml'; 
+with open(config_path, 'r') as f: 
+    config = yaml.safe_load(f) or {}; 
+config['manager-api'] = {'url': 'http://xiaozhi-esp32-server-web:8002/xiaozhi', 'secret': '$SECRET_KEY'}; 
+with open(config_path, 'w') as f: 
+    yaml.dump(config, f); 
+"
+    docker restart xiaozhi-esp32-server
+fi
+
+# 获取并显示地址信息
+LOCAL_IP=$(hostname -I | awk '{print $1}')
+
+# 修复日志文件获取不到ws的问题，改为硬编码
+whiptail --title "安装完成！" --msgbox "\
+服务端相关地址如下：\n\
+管理后台访问地址: http://$LOCAL_IP:8002\n\
+OTA 地址: http://$LOCAL_IP:8002/xiaozhi/ota/\n\
+视觉分析接口地址: http://$LOCAL_IP:8003/mcp/vision/explain\n\
+WebSocket 地址: ws://$LOCAL_IP:8000/xiaozhi/v1/\n\
+\n安装完毕！感谢您的使用！\n按Enter键退出..." 16 70

docs/Deployment.md

@@ -2,53 +2,19 @@
 ![请参考-最简化架构图](../docs/images/deploy1.png)
 # 方式一：Docker只运行Server
 
-docker镜像已支持x86架构、arm64架构的CPU，支持在国产操作系统上运行。
+`0.8.2`版本开始，本项目发行的docker镜像只支持`x86架构`，如果需要在`arm64架构`的CPU上部署，可按照[这个教程](docker-build.md)在本机编译`arm64的镜像`。
 
 ## 1. 安装docker
 
 如果您的电脑还没安装docker，可以按照这里的教程安装：[docker安装](https://www.runoob.com/docker/ubuntu-docker-install.html)
 
-如果你已经安装好docker，你可以[1.1使用懒人脚本](#11-懒人脚本)自动帮你下载所需的文件和配置文件，你可以使用docker[1.2手动部署](#12-手动部署)。
+安装好docker后，进继续。
 
-### 1.1 懒人脚本
+### 1.1 手动部署
 
-你可以使用以下命令一键下载并执行部署脚本：
+#### 1.1.1 创建目录
-请确保你的环境可以正常访问 GitHub 否则无法下载脚本。
-```bash
-curl -L -o docker-setup.sh https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/docker-setup.sh
-```
 
-如果您的电脑是windows系统，请使用使用 Git Bash、WSL、PowerShell 或 CMD 运行以下命令：
+安装完docker后，你需要为这个项目找一个安放配置文件的目录，例如我们可以新建一个文件夹叫`xiaozhi-server`。
-```bash
-# Git Bash 或 WSL
-sh docker-setup.sh
-# PowerShell 或 CMD
-.\docker-setup.sh
-```
-
-如果您的电脑是linux 或者 macos 系统，请使用终端运行以下命令：
-```bash
-chmod +x docker-setup.sh
-./docker-setup.sh
-```
-
-脚本会自动完成以下操作：
-> 1. 创建必要的目录结构
-> 2. 下载语音识别模型
-> 3. 下载配置文件
-> 4. 检查文件完整性
->
-> 执行完成后，请按照提示配置 API 密钥。
-
-当你一切顺利完成以上操作后，继续操作[配置项目文件](#2-配置项目文件)
-
-### 1.2 手动部署
-
-如果懒人脚本无法正常运行，请按本章节1.2进行手动部署。
-
-#### 1.2.1 创建目录
-
-安装完后，你需要为这个项目找一个安放配置文件的目录，例如我们可以新建一个文件夹叫`xiaozhi-server`。
 
 创建好目录后，你需要在`xiaozhi-server`下面创建`data`文件夹和`models`文件夹，`models`下面还要再创建`SenseVoiceSmall`文件夹。
 
@@ -61,18 +27,18 @@ xiaozhi-server
      ├─ SenseVoiceSmall
 ```
 
-#### 1.2.2 下载语音识别模型文件
+#### 1.1.2 下载语音识别模型文件
 
 你需要下载语音识别的模型文件，因为本项目的默认语音识别用的是本地离线语音识别方案。可通过这个方式下载
 [跳转到下载语音识别模型文件](#模型文件)
 
 下载完后，回到本教程。
 
-#### 1.2.3 下载配置文件
+#### 1.1.3 下载配置文件
 
 你需要下载两个配置文件：`docker-compose.yaml` 和 `config.yaml`。需要从项目仓库下载这两个文件。
 
-##### 1.2.3.1 下载 docker-compose.yaml
+##### 1.1.3.1 下载 docker-compose.yaml
 
 用浏览器打开[这个链接](../main/xiaozhi-server/docker-compose.yml)。
 
@@ -81,7 +47,7 @@ xiaozhi-server
 
 下载完后，回到本教程继续往下。
 
-##### 1.2.3.2 创建 config.yaml
+##### 1.1.3.2 创建 config.yaml
 
 用浏览器打开[这个链接](../main/xiaozhi-server/config.yaml)。
 
@@ -114,7 +80,7 @@ xiaozhi-server
 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 up -d
+docker compose up -d
 ```
 
 执行完后，再执行以下命令，查看日志信息。
@@ -173,6 +139,9 @@ conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/
 
 conda install libopus -y
 conda install ffmpeg -y
+
+# 在 Linux 环境下进行部署时,如出现类似缺失 libiconv.so.2 动态库的报错 请通过以下命令进行安装
+conda install libiconv -y
 ```
 
 请注意，以上命令，不是一股脑执行就成功的，你需要一步步执行，每一步执行完后，都检查一下输出的日志，查看是否成功。
@@ -260,7 +229,7 @@ LLM:
 文件放在`models/SenseVoiceSmall`
 目录下。下面两个下载路线任选一个。
 
-- 线路一：阿里魔塔下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
+- 线路一：阿里魔搭下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
 - 线路二：百度网盘下载[SenseVoiceSmall](https://pan.baidu.com/share/init?surl=QlgM58FHhYv1tFnUT_A8Sg&pwd=qvna) 提取码:
   `qvna`
 
@@ -272,7 +241,7 @@ LLM:
 250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-OTA接口是           http://192.168.4.123:8003/xiaozhi/ota/
 250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-Websocket地址是     ws://192.168.4.123:8000/xiaozhi/v1/
 250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
-250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
+250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
 250427 13:04:20[0.3.11_SiFuChTTnofu][__main__]-INFO-=======================================================
 ```
 
@@ -290,19 +259,33 @@ LLM:
 
 2、 [基于虾哥编译好的固件配置自定义服务器](firmware-setting.md)了。
 
-
+# 常见问题
 以下是一些常见问题，供参考：
 
-[1、为什么我说的话，小智识别出来很多韩文、日文、英文](./FAQ.md)
+1、[为什么我说的话，小智识别出来很多韩文、日文、英文](./FAQ.md)<br/>
-
+2、[为什么会出现“TTS 任务出错 文件不存在”？](./FAQ.md)<br/>
-[2、为什么会出现“TTS 任务出错 文件不存在”？](./FAQ.md)
+3、[TTS 经常失败，经常超时](./FAQ.md)<br/>
-
+4、[使用Wifi能连接自建服务器，但是4G模式却接不上](./FAQ.md)<br/>
-[3、TTS 经常失败，经常超时](./FAQ.md)
+5、[如何提高小智对话响应速度？](./FAQ.md)<br/>
-
+6、[我说话很慢，停顿时小智老是抢话](./FAQ.md)<br/>
-[4、使用Wifi能连接自建服务器，但是4G模式却接不上](./FAQ.md)
+## 部署相关教程
-
+1、[如何自动拉取本项目最新代码自动编译和启动](./dev-ops-integration.md)<br/>
-[5、如何提高小智对话响应速度？](./FAQ.md)
+2、[如何部署MQTT网关开启MQTT+UDP协议](./mqtt-gateway-integration.md)<br/>
-
+3、[如何与Nginx集成](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/791)<br/>
-[6、我说话很慢，停顿时小智老是抢话](./FAQ.md)
+## 拓展相关教程
-
+1、[如何开启手机号码注册智控台](./ali-sms-integration.md)<br/>
-[7、我想通过小智控制电灯、空调、远程开关机等操作](./FAQ.md)
+2、[如何集成HomeAssistant实现智能家居控制](./homeassistant-integration.md)<br/>
+3、[如何开启视觉模型实现拍照识物](./mcp-vision-integration.md)<br/>
+4、[如何部署MCP接入点](./mcp-endpoint-enable.md)<br/>
+5、[如何接入MCP接入点](./mcp-endpoint-integration.md)<br/>
+6、[如何开启声纹识别](./voiceprint-integration.md)<br/>
+7、[新闻插件源配置指南](./newsnow_plugin_config.md)<br/>
+8、[天气插件使用指南](./weather-integration.md)<br/>
+## 语音克隆、本地语音部署相关教程
+1、[如何在智控台克隆音色](./huoshan-streamTTS-voice-cloning.md)<br/>
+2、[如何部署集成index-tts本地语音](./index-stream-integration.md)<br/>
+3、[如何部署集成fish-speech本地语音](./fish-speech-integration.md)<br/>
+4、[如何部署集成PaddleSpeech本地语音](./paddlespeech-deploy.md)<br/>
+## 性能测试教程
+1、[各组件速度测试指南](./performance_tester.md)<br/>
+2、[定期公开测试结果](https://github.com/xinnan-tech/xiaozhi-performance-research)<br/>

docs/Deployment_all.md

@@ -1,13 +1,40 @@
 # 部署架构图
 ![请参考-全模块安装架构图](../docs/images/deploy2.png)
 # 方式一：Docker运行全模块
-docker镜像已支持x86架构、arm64架构的CPU，支持在国产操作系统上运行。
+`0.8.2`版本开始，本项目发行的docker镜像只支持`x86架构`，如果需要在`arm64架构`的CPU上部署，可按照[这个教程](docker-build.md)在本机编译`arm64的镜像`。
 
 ## 1. 安装docker
 
 如果您的电脑还没安装docker，可以按照这里的教程安装：[docker安装](https://www.runoob.com/docker/ubuntu-docker-install.html)
 
-#### 1.1 创建目录
+docker 安装全模块有两种方式，你可以[使用懒人脚本](./Deployment_all.md#11-懒人脚本)（作者[@VanillaNahida](https://github.com/VanillaNahida)）  
+脚本会自动帮你下载所需的文件和配置文件，你也可以使用[手动部署](./Deployment_all.md#12-手动部署)从零搭建。
+
+
+
+### 1.1 懒人脚本
+部署简便，可以参考[视频教程](https://www.bilibili.com/video/BV17bbvzHExd/) ，文字版教程如下：
+> [!NOTE]  
+> 暂且只支持Ubuntu服务器一键部署，其他系统未尝试，可能会有一些奇怪的bug
+
+使用SSH工具连接到服务器，以root权限执行如下脚本
+```bash
+sudo bash -c "$(wget -qO- https://ghfast.top/https://raw.githubusercontent.com/xinnan-tech/xiaozhi-esp32-server/main/docker-setup.sh)"
+```
+
+脚本会自动完成以下操作：
+> 1. 安装Docker
+> 2. 配置镜像源
+> 3. 下载/拉取镜像
+> 4. 下载语音识别模型文件
+> 5. 引导配置服务端
+>
+
+执行完成后简单配置后，再参照[4. 运行程序](#4. 运行程序)和[5.重启xiaozhi-esp32-server](#5.重启xiaozhi-esp32-server)里提到的最重要的3件事情，完成3这三项配置后即可使用。
+
+### 1.2 手动部署
+
+#### 1.2.1 创建目录
 
 安装完后，你需要为这个项目找一个安放配置文件的目录，例如我们可以新建一个文件夹叫`xiaozhi-server`。
 
@@ -22,22 +49,22 @@ xiaozhi-server
      ├─ SenseVoiceSmall
 ```
 
-#### 1.2 下载语音识别模型文件
+#### 1.2.2 下载语音识别模型文件
 
 本项目语音识别模型，默认使用`SenseVoiceSmall`模型，进行语音转文字。因为模型较大，需要独立下载，下载后把`model.pt`
 文件放在`models/SenseVoiceSmall`
 目录下。下面两个下载路线任选一个。
 
-- 线路一：阿里魔塔下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
+- 线路一：阿里魔搭下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
 - 线路二：百度网盘下载[SenseVoiceSmall](https://pan.baidu.com/share/init?surl=QlgM58FHhYv1tFnUT_A8Sg&pwd=qvna) 提取码:
   `qvna`
 
 
-#### 1.3 下载配置文件
+#### 1.2.3 下载配置文件
 
 你需要下载两个配置文件：`docker-compose_all.yaml` 和 `config_from_api.yaml`。需要从项目仓库下载这两个文件。
 
-##### 1.3.1 下载 docker-compose_all.yaml
+##### 1.2.3.1 下载 docker-compose_all.yaml
 
 用浏览器打开[这个链接](../main/xiaozhi-server/docker-compose_all.yml)。
 
@@ -48,7 +75,7 @@ xiaozhi-server
 
 下载完后，回到本教程继续往下。
 
-##### 1.3.2 下载 config_from_api.yaml
+##### 1.2.3.2 下载 config_from_api.yaml
 
 用浏览器打开[这个链接](../main/xiaozhi-server/config_from_api.yaml)。
 
@@ -171,7 +198,7 @@ docker logs -f xiaozhi-esp32-server
 ```
 25-02-23 12:01:09[core.websocket_server] - INFO - Websocket地址是      ws://xxx.xx.xx.xx:8000/xiaozhi/v1/
 25-02-23 12:01:09[core.websocket_server] - INFO - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
-25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
+25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
 25-02-23 12:01:09[core.websocket_server] - INFO - =======================================================
 ```
 
@@ -179,12 +206,12 @@ docker logs -f xiaozhi-esp32-server
 
 OTA接口：
 ```
-http://你电脑局域网的ip:8002/xiaozhi/ota/
+http://你宿主机局域网的ip:8002/xiaozhi/ota/
 ```
 
 Websocket接口：
 ```
-ws://你电脑局域网的ip:8000/xiaozhi/v1/
+ws://你宿主机的ip:8000/xiaozhi/v1/
 ```
 
 ### 第三件重要的事情
@@ -328,6 +355,9 @@ conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/
 
 conda install libopus -y
 conda install ffmpeg -y
+
+# 在 Linux 环境下进行部署时,如出现类似缺失 libiconv.so.2 动态库的报错 请通过以下命令进行安装
+conda install libiconv -y
 ```
 
 请注意，以上命令，不是一股脑执行就成功的，你需要一步步执行，每一步执行完后，都检查一下输出的日志，查看是否成功。
@@ -358,7 +388,7 @@ pip install -r requirements.txt
 文件放在`models/SenseVoiceSmall`
 目录下。下面两个下载路线任选一个。
 
-- 线路一：阿里魔塔下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
+- 线路一：阿里魔搭下载[SenseVoiceSmall](https://modelscope.cn/models/iic/SenseVoiceSmall/resolve/master/model.pt)
 - 线路二：百度网盘下载[SenseVoiceSmall](https://pan.baidu.com/share/init?surl=QlgM58FHhYv1tFnUT_A8Sg&pwd=qvna) 提取码:
   `qvna`
 
@@ -388,7 +418,7 @@ manager-api:
   secret: 12345678-xxxx-xxxx-xxxx-123456789000
 ```
 
-## 5.运行项目
+## 9.运行项目
 
 ```
 # 确保在xiaozhi-server目录下执行
@@ -401,7 +431,7 @@ python app.py
 ```
 25-02-23 12:01:09[core.websocket_server] - INFO - Server is running at ws://xxx.xx.xx.xx:8000/xiaozhi/v1/
 25-02-23 12:01:09[core.websocket_server] - INFO - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
-25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
+25-02-23 12:01:09[core.websocket_server] - INFO - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
 25-02-23 12:01:09[core.websocket_server] - INFO - =======================================================
 ```
 
@@ -431,19 +461,32 @@ ws://你电脑局域网的ip:8000/xiaozhi/v1/
 2、 [基于虾哥编译好的固件配置自定义服务器](firmware-setting.md)了。
 
 # 常见问题
-
 以下是一些常见问题，供参考：
 
-[1、为什么我说的话，小智识别出来很多韩文、日文、英文](./FAQ.md)
+1、[为什么我说的话，小智识别出来很多韩文、日文、英文](./FAQ.md)<br/>
-
+2、[为什么会出现“TTS 任务出错 文件不存在”？](./FAQ.md)<br/>
-[2、为什么会出现“TTS 任务出错 文件不存在”？](./FAQ.md)
+3、[TTS 经常失败，经常超时](./FAQ.md)<br/>
-
+4、[使用Wifi能连接自建服务器，但是4G模式却接不上](./FAQ.md)<br/>
-[3、TTS 经常失败，经常超时](./FAQ.md)
+5、[如何提高小智对话响应速度？](./FAQ.md)<br/>
-
+6、[我说话很慢，停顿时小智老是抢话](./FAQ.md)<br/>
-[4、使用Wifi能连接自建服务器，但是4G模式却接不上](./FAQ.md)
+## 部署相关教程
-
+1、[如何自动拉取本项目最新代码自动编译和启动](./dev-ops-integration.md)<br/>
-[5、如何提高小智对话响应速度？](./FAQ.md)
+2、[如何部署MQTT网关开启MQTT+UDP协议](./mqtt-gateway-integration.md)<br/>
-
+3、[如何与Nginx集成](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/791)<br/>
-[6、我说话很慢，停顿时小智老是抢话](./FAQ.md)
+## 拓展相关教程
-
+1、[如何开启手机号码注册智控台](./ali-sms-integration.md)<br/>
-[7、我想通过小智控制电灯、空调、远程开关机等操作](./FAQ.md)
+2、[如何集成HomeAssistant实现智能家居控制](./homeassistant-integration.md)<br/>
+3、[如何开启视觉模型实现拍照识物](./mcp-vision-integration.md)<br/>
+4、[如何部署MCP接入点](./mcp-endpoint-enable.md)<br/>
+5、[如何接入MCP接入点](./mcp-endpoint-integration.md)<br/>
+6、[如何开启声纹识别](./voiceprint-integration.md)<br/>
+7、[新闻插件源配置指南](./newsnow_plugin_config.md)<br/>
+8、[天气插件使用指南](./weather-integration.md)<br/>
+## 语音克隆、本地语音部署相关教程
+1、[如何在智控台克隆音色](./huoshan-streamTTS-voice-cloning.md)<br/>
+2、[如何部署集成index-tts本地语音](./index-stream-integration.md)<br/>
+3、[如何部署集成fish-speech本地语音](./fish-speech-integration.md)<br/>
+4、[如何部署集成PaddleSpeech本地语音](./paddlespeech-deploy.md)<br/>
+## 性能测试教程
+1、[各组件速度测试指南](./performance_tester.md)<br/>
+2、[定期公开测试结果](https://github.com/xinnan-tech/xiaozhi-performance-research)<br/>

docs/FAQ.md

@@ -34,59 +34,18 @@ conda install conda-forge::ffmpeg
 ### 5、如何提高小智对话响应速度？ ⚡
 
 本项目默认配置为低成本方案，建议初学者先使用默认免费模型，解决"跑得动"的问题，再优化"跑得快"。  
-如需提升响应速度，可尝试更换各组件。以下为各组件的响应速度测试数据（仅供参考，不构成承诺）：
+如需提升响应速度，可尝试更换各组件。自`0.5.2`版本起，项目支持流式配置，相比早期版本，响应速度提升约`2.5秒`，显著改善用户体验。
 
-| 影响因素  |       因素值        | 
+| 模块名称 | 入门全免费设置 | 流式配置 |
-|:-----:|:----------------:|
+|:---:|:---:|:---:|
-| 测试地点  |    广东省广州市海珠区     |
+| ASR(语音识别) | FunASR(本地) | 👍XunfeiStreamASR(讯飞流式) |
-| 测试时间  | 2025年2月19日 12:52 |
+| LLM(大模型) | glm-4-flash(智谱) | 👍qwen-flash(阿里百炼) |
-| 宽带运营商 |       中国联通       |
+| VLLM(视觉大模型) | glm-4v-flash(智谱) | 👍qwen3.5-flash(阿里百炼) |
+| TTS(语音合成) | EdgeTTS(微软) | 👍HuoshanDoubleStreamTTS(火山流式) |
+| Intent(意图识别) | function_call(函数调用) | function_call(函数调用) |
+| Memory(记忆功能) | mem_local_short(本地短期记忆） | mem_local_short（本地短期记忆） |
 
-测试方法：
+如果您关心各组件的耗时，请查阅[小智各组件性能测试报告](https://github.com/xinnan-tech/xiaozhi-performance-research)，可按报告中的测试方法在您的环境中实际测试。
-
-1、把各组件的密钥配置上去，只有配置了密钥的组件才参与测试。
-
-2、配置完密钥后，执行以下方法
-
-```
-# 进入项目根目录，执行以下命令：
-conda activate xiaozhi-esp32-server
-python performance_tester.py 
-```
-
-生成报告如下
-
-LLM 性能排行:
-
-| 模块名称       | 平均首Token时间 | 平均总响应时间 |
-|:-----------|:-----------|:--------|
-| AliLLM     | 0.547s     | 1.485s  |
-| ChatGLMLLM | 0.677s     | 3.057s  |
-
-TTS 性能排行:
-
-| 模块名称                 | 平均合成时间 |
-|----------------------|--------|
-| EdgeTTS              | 1.019s |
-| DoubaoTTS            | 0.503s |
-| CosyVoiceSiliconflow | 3.732s |
-
-推荐配置组合 (综合响应速度):
-
-| 组合方案                          | 综合得分  | LLM首Token | TTS合成  |
-|-------------------------------|-------|-----------|--------|
-| AliLLM + DoubaoTTS            | 0.539 | 0.547s    | 0.503s |
-| AliLLM + EdgeTTS              | 0.642 | 0.547s    | 1.019s |
-| ChatGLMLLM + DoubaoTTS        | 0.642 | 0.677s    | 0.503s |
-| ChatGLMLLM + EdgeTTS          | 0.745 | 0.677s    | 1.019s |
-| AliLLM + CosyVoiceSiliconflow | 1.184 | 0.547s    | 3.732s |
-
-### 结论 🔍
-
-`2025年2月19日`，如果我的电脑在`广东省广州市海珠区`，且使用的是`中国联通`网络，我会优先使用：
-
-- LLM：`AliLLM`
-- TTS：`DoubaoTTS`
 
 ### 6、我说话很慢，停顿时小智老是抢话 🗣️
 
@@ -100,20 +59,46 @@ VAD:
     min_silence_duration_ms: 700  # 如果说话停顿较长，可将此值调大
 ```
 
-### 7、我想通过小智控制电灯、空调、远程开关机等操作 💡
+### 7、部署相关教程
+1、[如何进行最简化部署](./Deployment.md)<br/>
+2、[如何进行全模块部署](./Deployment_all.md)<br/>
+3、[如何部署MQTT网关开启MQTT+UDP协议](./mqtt-gateway-integration.md)<br/>
+4、[如何自动拉取本项目最新代码自动编译和启动](./dev-ops-integration.md)<br/>
+5、[如何与Nginx集成](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/791)<br/>
 
-参考教程[ESP32设备与HomeAssistant集成指南](./homeassistant-integration.md)
+### 8、编译固件相关教程
+1、[如何自己编译小智固件](./firmware-build.md)<br/>
+2、[如何基于虾哥编译好的固件修改OTA地址](./firmware-setting.md)<br/>
+3、[单模块部署如何配置固件OTA自动升级](./ota-upgrade-guide.md)<br/>
 
-### 8、如何开启手机注册智控台 📱
+### 9、拓展相关教程
+1、[如何开启手机号码注册智控台](./ali-sms-integration.md)<br/>
+2、[如何集成HomeAssistant实现智能家居控制](./homeassistant-integration.md)<br/>
+3、[如何开启视觉模型实现拍照识物](./mcp-vision-integration.md)<br/>
+4、[如何部署MCP接入点](./mcp-endpoint-enable.md)<br/>
+5、[如何接入MCP接入点](./mcp-endpoint-integration.md)<br/>
+6、[MCP方法如何获取设备信息](./mcp-get-device-info.md)<br/>
+7、[如何开启声纹识别](./voiceprint-integration.md)<br/>
+8、[新闻插件源配置指南](./newsnow_plugin_config.md)<br/>
+9、[知识库ragflow集成指南](./ragflow-integration.md)<br/>
+10、[如何部署上下文源](./context-provider-integration.md)<br/>
+11、[如何集成PowerMem智能记忆](./powermem-integration.md)<br/>
+12、[如何配置天气插件查询天气](./weather-integration.md)<br/>
 
-参考教程[阿里云短信集成指南](./ali-sms-integration.md)
+### 10、数字人相关教程
+1、[数字人digital-human启动方法](./digital-human-wakeword.md)<br/>
+2、[如何在N100迷你主机上部署数字人digital-human](./all-in-one-digital-human-setup.md)<br/>
 
-### 9、如何开启视觉模型实现拍照识物 📷
+### 11、语音克隆、本地语音部署相关教程
+1、[如何在智控台克隆音色](./huoshan-streamTTS-voice-cloning.md)<br/>
+2、[如何部署集成index-tts本地语音](./index-stream-integration.md)<br/>
+3、[如何部署集成fish-speech本地语音](./fish-speech-integration.md)<br/>
+4、[如何部署集成PaddleSpeech本地语音](./paddlespeech-deploy.md)<br/>
 
-参考教程[视觉模型使用指南](./mcp-vision-integration.md)
+### 12、性能测试教程
+1、[各组件速度测试指南](./performance_tester.md)<br/>
+2、[定期公开测试结果](https://github.com/xinnan-tech/xiaozhi-performance-research)<br/>
 
-### 10、更多问题，可联系我们反馈 💬
+### 13、更多问题，可联系我们反馈 💬
 
 可以在[issues](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues)提交您的问题。
-
-也可以发邮件我们取得联系：huangrongzhuang@xin-nan.com

docs/all-in-one-digital-human-setup.md

@@ -0,0 +1,442 @@
+# 一体机数字人配置指南
+
+本项目用于在 x86 架构设备（如迷你主机、工控机、普通电脑等）上部署一套完整的数字人展示系统，实现以下功能：
+- 开机自动进入 Kiosk 全屏浏览器，展示指定网页
+- 后台运行唤醒词检测服务，支持语音交互
+
+> **说明**：本文档以 **Intel N100 迷你主机（天虹 QN10-100B4）** 为例进行部署演示，其他 x86 设备可参考调整（注意网络配置和声卡设备差异）。
+
+## 适用环境
+
+| 项目 | 说明 |
+|------|------|
+| 示例硬件 | 天虹 QN10-100B4（Intel N100） |
+| 操作系统 | Ubuntu 24.04 LTS (Noble Numbat) |
+| 示例用户 | xz（请根据实际情况替换） |
+| 网络 | Wi-Fi 连接，固定 IP（可按需改为有线） |
+
+## 部署流程
+
+1. 系统初始化（换源、连网）
+2. 安装图形组件与 Kiosk 浏览器
+3. 配置自动登录与图形界面
+4. 部署唤醒词服务（Python 环境 + 麦克风）
+5. 优化开机速度与隐藏启动信息
+
+---
+
+
+### 系统初始化（换源、连网）
+
+```
+sudo cp /etc/apt/sources.list /etc/apt/sources.list.bak
+
+sudo tee /etc/apt/sources.list > /dev/null <<EOF
+deb http://mirrors.aliyun.com/ubuntu/ noble main restricted universe multiverse
+# deb-src http://mirrors.aliyun.com/ubuntu/ noble main restricted universe multiverse
+
+deb http://mirrors.aliyun.com/ubuntu/ noble-security main restricted universe multiverse
+# deb-src http://mirrors.aliyun.com/ubuntu/ noble-security main restricted universe multiverse
+
+deb http://mirrors.aliyun.com/ubuntu/ noble-updates main restricted universe multiverse
+# deb-src http://mirrors.aliyun.com/ubuntu/ noble-updates main restricted universe multiverse
+
+deb http://mirrors.aliyun.com/ubuntu/ noble-proposed main restricted universe multiverse
+# deb-src http://mirrors.aliyun.com/ubuntu/ noble-proposed main restricted universe multiverse
+
+deb http://mirrors.aliyun.com/ubuntu/ noble-backports main restricted universe multiverse
+# deb-src http://mirrors.aliyun.com/ubuntu/ noble-backports main restricted universe multiverse
+EOF
+
+echo 'Acquire::ForceIPv4 "true";' | sudo tee /etc/apt/apt.conf.d/99force-ipv4
+```
+
+
+安装网络管理工具（若已存在可忽略）
+
+Bash
+
+```
+sudo apt update
+sudo apt install network-manager -y
+sudo systemctl start NetworkManager
+sudo systemctl enable NetworkManager
+```
+
+
+设置wifi密码，固定ip
+
+> **提醒**：以下命令中的 Wi-Fi 名称、密码、IP 地址均为示例，请务必替换为你自己的实际信息。
+
+Bash
+
+```
+sudo nmcli device wifi connect "MERCURY_1812" password "12345678"
+
+sudo nmcli connection modify "MERCURY_1812" ipv4.addresses "192.168.0.86/24" ipv4.gateway "192.168.0.1" ipv4.dns "8.8.8.8,114.114.114.114" ipv4.method "manual"
+
+sudo nmcli connection up "MERCURY_1812"
+```
+
+
+### 第一步：安装核心图形组件与浏览器
+
+这里我们坚持“极简主义”，坚决不装多余的桌面环境（如 GNOME/KDE），只装底层驱动、最轻量的窗口管理器（Openbox）、隐藏鼠标工具以及 Chromium 浏览器。
+
+Bash
+
+```
+sudo timedatectl set-timezone Asia/Shanghai
+
+
+sudo apt install net-tools vim fonts-wqy-microhei fonts-wqy-zenhei alsa-utils pulseaudio -y
+sudo apt install --no-install-recommends xserver-xorg x11-xserver-utils xinit openbox unclutter -y
+
+wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
+sudo apt install ./google-chrome-stable_current_amd64.deb -y
+rm google-chrome-stable_current_amd64.deb
+
+sudo apt purge snapd -y
+
+```
+
+### 第二步：配置 TTY1 开机免密自动登录
+
+为了避免手动输入账号密码的尴尬，我们通过修改 systemd 服务，让系统一开机就自动以 `xz` 的身份登录。这里使用一键写入命令，彻底避开由于 `nano` 或 `vi` 操作不当导致的保存失败问题。
+
+**1. 创建配置目录：**
+
+Bash
+
+```
+sudo mkdir -p /etc/systemd/system/getty@tty1.service.d/
+```
+
+**2. 写入自动登录规则：**
+
+Bash
+
+```
+echo -e "[Service]\nExecStart=\nExecStart=-/sbin/agetty --autologin xz --noclear %I \$TERM" | sudo tee /etc/systemd/system/getty@tty1.service.d/override.conf
+```
+
+**3. 重载服务并设置默认启动目标：**
+
+Bash
+
+```
+sudo systemctl daemon-reload
+sudo systemctl set-default multi-user.target
+```
+
+### 第三步：配置登录后自动启动图形界面
+
+系统自动登录后默认停留在黑底白字的命令行，我们需要配置脚本，让它一旦登录立马启动 X11 图形环境。
+
+**1. 触发 `startx` 的启动逻辑：**
+
+直接将触发代码追加写入你的个人环境配置文件中：
+
+Bash
+
+```
+cat << 'EOF' >> ~/.bash_profile
+if [ -z "$DISPLAY" ] && [ "$(fgconsole)" -eq 1 ]; then
+    exec startx
+fi
+EOF
+```
+
+**2. 告诉 `startx` 去启动 Openbox：**
+
+Bash
+
+```
+echo "exec openbox-session" > ~/.xinitrc
+```
+
+### 第四步：配置“铜墙铁壁”的 Openbox 与浏览器
+
+这是最核心的一步：关闭屏幕休眠、隐藏鼠标、全屏锁定浏览器，并写一个“死循环”保证浏览器被意外关闭后也能瞬间复活。
+
+**1. 创建 Openbox 配置目录：**
+
+Bash
+
+```
+mkdir -p ~/.config/openbox
+```
+
+**2. 写入自启动脚本 (`autostart`)：**
+
+复制以下整段代码并回车（这会自动把所有保护规则写进文件里）：
+
+Bash
+
+```
+cat << 'EOF' > ~/.config/openbox/autostart
+# 关闭屏幕保护
+xset -dpms
+xset s noblank
+xset s off
+
+# 隐藏鼠标
+unclutter -idle 0.1 -root &
+
+# 死循环启动 Chromium（崩溃或被关也能秒重启）
+while true; do
+    google-chrome \
+        --kiosk \
+        --no-first-run \
+        --no-default-browser-check \
+        --disable-infobars \
+        --disable-session-crashed-bubble \
+        --disable-translate \
+        --disable-external-intent-requests \
+        --autoplay-policy=no-user-gesture-required \
+        --use-fake-ui-for-media-stream \
+        "https://www.douyin.com"
+    sleep 2
+done &
+EOF
+```
+
+**3. 屏蔽 `Alt+F4` 退出快捷键：**
+
+为了防止别人插上键盘强行关掉窗口，我们把 Openbox 默认的系统快捷键干掉。
+
+Bash
+
+```
+cp /etc/xdg/openbox/rc.xml ~/.config/openbox/
+sed -i '/<keybind key="A-F4">/,/<\/keybind>/d' ~/.config/openbox/rc.xml
+```
+
+### 第五步：重启验收成果
+
+如果拔掉网线或不需要等待所有网络上线，可禁用网络等待服务，避免开机卡顿
+
+Bash
+
+```
+sudo systemctl mask systemd-networkd-wait-online.service
+sudo systemctl mask NetworkManager-wait-online.service
+```
+
+隐藏开机信息（GRUB）
+
+Bash
+
+```
+sudo sed -i 's/GRUB_CMDLINE_LINUX_DEFAULT=.*/GRUB_CMDLINE_LINUX_DEFAULT="quiet loglevel=3 systemd.show_status=false vt.global_cursor_default=0"/g' /etc/default/grub
+
+echo 'GRUB_TIMEOUT_STYLE="hidden"' | sudo tee -a /etc/default/grub
+echo 'GRUB_RECORDFAIL_TIMEOUT=0' | sudo tee -a /etc/default/grub
+
+sudo update-grub
+```
+
+声音设置成100%，然后 重启：
+
+Bash
+
+```
+amixer -q sset Master 100% unmute
+sudo reboot
+```
+
+### 部署唤醒词服务
+
+在一体机上部署唤醒词检测服务，需要安装 Python 环境、上传项目文件、配置 Camera 麦克风和开机自启。
+
+#### 1. 安装 Miniconda
+
+```bash
+wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
+bash Miniconda3-latest-Linux-x86_64.sh -b -p $HOME/miniconda3
+~/miniconda3/bin/conda init bash
+source ~/.bashrc
+rm Miniconda3-latest-Linux-x86_64.sh
+```
+
+
+确保登录时自动进入conda环境
+
+```bash
+if ! grep -q '.bashrc' ~/.bash_profile; then
+    cat << 'EOF' >> ~/.bash_profile
+
+if [ -f ~/.bashrc ]; then
+    . ~/.bashrc
+fi
+EOF
+fi
+```
+
+
+#### 2. 创建 Python 虚拟环境
+
+```bash
+conda create -n test python=3.10 -y
+conda activate test
+```
+
+若出现 Terms of Service have not been accepted 错误，执行：
+
+```bash
+conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/main
+conda tos accept --override-channels --channel https://repo.anaconda.com/pkgs/r
+```
+
+#### 3. 上传项目文件
+
+将开发机上的 `main/digital-human/` 整个目录上传到一体机的 `~/digital-human/` 目录：
+
+```bash
+# 在开发机上执行（将 <一体机IP> 替换为实际 IP）
+scp -r main/digital-human/ xz@<一体机IP>:~/digital-human/
+```
+
+#### 4. 安装系统依赖
+
+唤醒词服务需要音频采集库和 ALSA PulseAudio 插件：
+
+```bash
+sudo apt install libportaudio2 portaudio19-dev libasound2-plugins -y
+```
+
+#### 5. 安装 Python 依赖
+
+```bash
+cd ~/digital-human/wakeword_runtime
+pip install numpy
+pip install -r requirements.txt
+```
+
+#### 6. 下载唤醒词模型
+
+模型文件不包含在项目中，需要单独下载配置，详见 [docs/digital-human-wakeword.md](digital-human-wakeword.md) 中的“模型下载”章节。
+
+#### 7. 修改 Openbox 自启动脚本
+
+需要在 autostart 中加上 PulseAudio 和 Camera 麦克风配置，并将 Chrome 地址改为测试页面。
+
+先确认 Camera 麦克风在 PulseAudio 中的设备名：
+
+```bash
+pulseaudio --start
+pactl list sources short
+```
+
+找到包含 `USB_Camera` 的那一行，记下完整名称，例如：
+
+```
+alsa_input.usb-SN0002_2K_USB_Camera_46435000_P030D00_SN0002-02.mono-fallback
+```
+
+然后用完整内容覆盖 autostart（将 `TARGET_MIC` 替换为你的实际设备名）：
+
+```bash
+cat << 'EOF' > ~/.config/openbox/autostart
+# 1. 启动声音服务并稍作等待
+pulseaudio --start
+sleep 1
+
+# 2. 锁定 Camera 的麦克风（请替换为你的实际设备名）
+TARGET_MIC="alsa_input.usb-SN0002_2K_USB_Camera_46435000_P030D00_SN0002-02.mono-fallback"
+
+# 3. 设为系统默认麦克风
+pactl set-default-source "$TARGET_MIC"
+
+# 4. 解除静音
+pactl set-source-mute "$TARGET_MIC" 0
+
+# 5. 音量拉到 100%
+pactl set-source-volume "$TARGET_MIC" 100%
+
+# --- 极简桌面与浏览器环境配置 ---
+
+# 关闭屏幕保护
+xset -dpms
+xset s noblank
+xset s off
+
+# 隐藏鼠标
+unclutter -idle 0.1 -root &
+
+# 死循环启动浏览器（崩溃或被关也能秒重启）
+while true; do
+    google-chrome \
+        --kiosk \
+        --no-first-run \
+        --no-default-browser-check \
+        --disable-infobars \
+        --disable-session-crashed-bubble \
+        --disable-translate \
+        --disable-external-intent-requests \
+        --autoplay-policy=no-user-gesture-required \
+        --use-fake-ui-for-media-stream \
+        "http://127.0.0.1:8006/index.html"
+    sleep 2
+done &
+EOF
+```
+
+#### 8. 配置唤醒词服务开机自启
+
+创建 systemd 服务文件，让唤醒词服务开机自动运行。
+
+先确认当前用户的 UID：
+
+```bash
+id -u $(whoami)
+```
+
+然后用查到的 UID 替换下面 `1000`（通常第一个用户就是 1000）：
+
+```bash
+sudo tee /etc/systemd/system/digital-human.service << 'EOF'
+[Unit]
+Description=Digital Human Runtime
+After=network.target sound.target
+
+[Service]
+Type=simple
+User=xz
+Environment=XDG_RUNTIME_DIR=/run/user/1000
+Environment=PULSE_SERVER=unix:/run/user/1000/pulse/native
+WorkingDirectory=/home/xz/digital-human
+ExecStartPre=/bin/sleep 10
+ExecStart=/home/xz/miniconda3/envs/test/bin/python start.py
+Restart=on-failure
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target
+EOF
+```
+
+> **重要说明**：
+> - `User=xz` — 替换为你的实际用户名
+> - `/run/user/1000` — 替换为你实际的 UID
+> - `WorkingDirectory` 和 `ExecStart` 中的路径 — 替换为你的实际部署路径
+> - `Environment` 中的 PulseAudio 环境变量**必须保留**，否则唤醒词服务和浏览器无法同时使用 Camera 麦克风
+
+启用并启动服务：
+
+```bash
+sudo systemctl daemon-reload
+sudo systemctl enable digital-human
+sudo systemctl start digital-human
+```
+
+#### 9. 常用服务管理命令
+
+```bash
+sudo systemctl start digital-human     # 立即启动
+sudo systemctl stop digital-human      # 停止
+sudo systemctl restart digital-human   # 重启
+sudo systemctl status digital-human    # 查看状态
+journalctl -u digital-human -f         # 查看实时日志
+```
+

docs/context-provider-integration.md

@@ -0,0 +1,224 @@
+# 上下文源使用教程
+
+## 概述
+
+`上下文源`，就是为小智系统提示词的上下文添加【数据源】。
+
+`上下文源` 在小智在唤醒那一刻，获取外部系统的数据，并将其动态注入到大模型的系统提示词（System Prompt）中。
+让其做到唤醒时感知世界某个事物的状态。
+
+它和MCP、记忆有本质的区别：`上下文源`是强制让小智感知世界的数据；`记忆(Mem)`是让他知道之前聊了什么内容；`MCP(functionc all)`是当需要调用某项能力/知识的时候使用调用。
+
+通过这个功能，在小智唤醒的一刹那，“感知”到：
+- 人体健康传感器状态（体温、血压、血氧状态等）
+- 业务系统的实时数据（服务器负载、待办数据、股票信息等）
+- 任何可以通过 HTTP API 获取的文本信息
+
+**注意**：该功能只是方便小智在唤醒的时候感知事物的状态，而如果想要小智唤醒后实时获取事物的状态，建议在此功能上再结合MCP工具的调用。
+
+## 工作原理
+
+1. **配置源**：用户配置一个或多个 HTTP API 地址。
+2. **触发请求**：当系统构建 Prompt 时，如果发现模板中包含 `{{ dynamic_context }}` 占位符，会请求所有配置的 API。
+3. **自动注入**：系统会自动将 API 返回的数据格式化为 Markdown 列表，替换 `{{ dynamic_context }}` 占位符。
+
+## 接口规范
+
+为了让小智正确解析数据，您的 API 需要满足以下规范：
+
+- **请求方式**：`GET`
+- **请求头**：系统会自动添加 `device-id` 字段到 Request Header。
+- **响应格式**：必须返回 JSON 格式，且包含 `code` 和 `data` 字段。
+
+### 响应示例
+
+**情况 1：返回键值对**
+```json
+{
+  "code": 0,
+  "msg": "success",
+  "data": {
+    "客厅温度": "26℃",
+    "客厅湿度": "45%",
+    "大门状态": "已关闭"
+  }
+}
+```
+*注入效果：*
+```markdown
+<context>
+- **客厅温度：** 26℃
+- **客厅湿度：** 45%
+- **大门状态：** 已关闭
+</context>
+```
+
+**情况 2：返回列表**
+```json
+{
+  "code": 0,
+  "data": [
+    "您有10个待办事项",
+    "当前汽车的行驶速度是100km每小时"
+  ]
+}
+```
+*注入效果：*
+```markdown
+<context>
+- 您有10个待办事项
+- 当前汽车的行驶速度是100km每小时
+</context>
+```
+
+## 配置指南
+
+### 方式 1：智控台配置（全模块部署）
+
+1. 登录智控台，进入**角色配置**页面。
+2. 找到**上下文源**配置项（点击“编辑源”按钮）。
+3. 点击**添加**，输入您的 API 地址。
+4. 如果 API 需要鉴权，可以在**请求头**部分添加 `Authorization` 或其他 Header。
+5. 保存配置。
+
+### 方式 2：配置文件配置（单模块部署）
+
+编辑 `xiaozhi-server/data/.config.yaml` 文件，添加 `context_providers` 配置段：
+
+```yaml
+# 上下文源配置
+context_providers:
+  - url: "http://api.example.com/data"
+    headers:
+      Authorization: "Bearer your-token"
+  - url: "http://another-api.com/data"
+```
+
+## 启用功能
+
+默认情况下，系统的提示词模板文件（`data/.agent-base-prompt.txt`）中已经预置了 `{{ dynamic_context }}` 占位符，您无需手动添加。
+
+**示例：**
+
+```markdown
+<context>
+【重要！以下信息已实时提供，无需调用工具查询，请直接使用：】
+- **设备ID：** {{device_id}}
+- **当前时间：** {{current_time}}
+...
+{{ dynamic_context }}
+</context>
+```
+
+**注意**：如果您不需要使用此功能，可以选择**不配置任何上下文源**，也可以从提示词模板文件中**删除** `{{ dynamic_context }}` 占位符。
+
+## 附录：Mock 测试服务示例
+
+为了方便您测试和开发，我们提供了一个简单的 Python Mock Server 脚本。您可以运行此脚本在本地模拟 API 接口。
+
+**mock_api_server.py**
+
+```python
+import http.server
+import socketserver
+import json
+from urllib.parse import urlparse, parse_qs
+
+# 设置端口号
+PORT = 8081
+
+class MockRequestHandler(http.server.SimpleHTTPRequestHandler):
+    def do_GET(self):
+        # 解析路径和参数
+        parsed_path = urlparse(self.path)
+        path = parsed_path.path
+        query = parse_qs(parsed_path.query)
+
+        response_data = {}
+        status_code = 200
+
+        print(f"收到请求: {path}, 参数: {query}")
+
+        # Case 1: 模拟健康数据 (返回字典 Dict)
+        # 路径参数风格: /health
+        # device_id 从 Header 获取
+        if path == "/health":
+            device_id = self.headers.get("device-id", "unknown_device")
+            print(f"device_id: {device_id}")
+            response_data = {
+                "code": 0,
+                "msg": "success",
+                "data": {
+                    "测试设备ID": device_id,
+                    "心率": "80 bpm",
+                    "血压": "120/80 mmHg",
+                    "状态": "良好"
+                }
+            }
+
+        # Case 2: 模拟新闻列表 (返回列表 List)
+        # 无参数: /news/list
+        elif path == "/news/list":
+            response_data = {
+                "code": 0,
+                "msg": "success",
+                "data": [
+                    "今日头条：Python 3.14 发布",
+                    "科技新闻：AI 助手改变生活",
+                    "本地新闻：明日有大雨，记得带伞"
+                ]
+            }
+
+        # Case 3: 模拟天气简报 (返回字符串 String)
+        # 无参数: /weather/simple
+        elif path == "/weather/simple":
+            response_data = {
+                "code": 0,
+                "msg": "success",
+                "data": "今日晴转多云，气温 20-25 度，空气质量优，适合出行。"
+            }
+
+        # Case 4: 模拟设备详情 (Query参数风格)
+        # 参数风格: /device/info
+        # device_id 从 Header 获取
+        elif path == "/device/info":
+            device_id = self.headers.get("device-id", "unknown_device")
+            response_data = {
+                "code": 0,
+                "msg": "success",
+                "data": {
+                    "查询方式": "Header参数",
+                    "设备ID": device_id,
+                    "电量": "85%",
+                    "固件": "v2.0.1"
+                }
+            }
+        
+        # Case 5: 404 Not Found
+        else:
+            status_code = 404
+            response_data = {"error": "接口不存在"}
+
+        # 发送响应
+        self.send_response(status_code)
+        self.send_header('Content-type', 'application/json; charset=utf-8')
+        self.end_headers()
+        self.wfile.write(json.dumps(response_data, ensure_ascii=False).encode('utf-8'))
+
+# 启动服务
+# 允许地址重用，防止快速重启报错
+socketserver.TCPServer.allow_reuse_address = True
+with socketserver.TCPServer(("", PORT), MockRequestHandler) as httpd:
+    print(f"==================================================")
+    print(f"Mock API Server 已启动: http://localhost:{PORT}")
+    print(f"可用接口列表:")
+    print(f"1. [字典] http://localhost:{PORT}/health")
+    print(f"2. [列表] http://localhost:{PORT}/news/list")
+    print(f"3. [文本] http://localhost:{PORT}/weather/simple")
+    print(f"4. [参数] http://localhost:{PORT}/device/info")
+    print(f"==================================================")
+    try:
+        httpd.serve_forever()
+    except KeyboardInterrupt:
+        print("\n服务已停止")
+```

docs/dev-ops-integration.md

@@ -4,6 +4,8 @@
 
 本项目的测试平台`https://2662r3426b.vicp.fun`，从开放以来就使用了该方法，效果良好。
 
+教程可参考B站博主`毕乐labs`发布的视频教程：[《开源小智服务器xiaozhi-server自动更新以及最新版本MCP接入点配置保姆教程》](https://www.bilibili.com/video/BV15H37zHE7Q)
+
 # 开始条件
 - 你的电脑/服务器是linux操作系统
 - 你已经跑通了整个流程
@@ -40,6 +42,9 @@ git clone https://ghproxy.net/https://github.com/xinnan-tech/xiaozhi-esp32-serve
 
 此刻你需要把`model.pt`文件复制到新的目录去，你可以这样
 ```
+# 创建需要的目录
+mkdir -p /home/system/xiaozhi/xiaozhi-esp32-server/main/xiaozhi-server/data/
+
 cp 你原来的.config.yaml完整路径 /home/system/xiaozhi/xiaozhi-esp32-server/main/xiaozhi-server/data/.config.yaml
 cp 你原来的model.pt完整路径 /home/system/xiaozhi/xiaozhi-esp32-server/main/xiaozhi-server/models/SenseVoiceSmall/model.pt
 ```
@@ -100,6 +105,8 @@ else
 fi
 
 nohup java -jar xiaozhi-esp32-api.jar --spring.profiles.active=dev &
+
+tail tail -f nohup.out
 ```
 
 保存好后执行赋权命令
@@ -129,8 +136,12 @@ else
   echo "已杀掉进程 $PID"
 fi
 cd main/xiaozhi-server
+# 初始化conda环境
+source ~/.bashrc
+conda activate xiaozhi-esp32-server
 pip install -r requirements.txt
 nohup python app.py >/dev/null &
+tail -f /home/system/xiaozhi/xiaozhi-esp32-server/main/xiaozhi-server/tmp/server.log
 ```
 
 保存好后执行赋权命令
@@ -144,8 +155,6 @@ chmod 777 update_8000.sh
 以上的脚本都建立好后，日常更新，我们只要依次执行以下命令就可以做到自动更新和启动
 
 ```
-# 进入pyhton环境
-conda activate xiaozhi-esp32-server
 cd /home/system/xiaozhi
 # 更新并启动Java程序
 ./update_8001.sh
@@ -153,11 +162,21 @@ cd /home/system/xiaozhi
 ./update_8002.sh
 # 更新并启动python程序
 ./update_8000.sh
-# 查看Java日志
+
+
+# 后期想查看java日志，执行以下命令
 tail -f nohup.out
-# 查看Python日志
+# 后期想查看python日志，执行以下命令
 tail -f /home/system/xiaozhi/xiaozhi-esp32-server/main/xiaozhi-server/tmp/server.log
 ```
 
 # 注意事项
 测试平台`https://2662r3426b.vicp.fun`，是使用nginx做了反向代理。nginx.conf详细配置可以[参考这里](https://github.com/xinnan-tech/xiaozhi-esp32-server/issues/791)
+
+## 常见问题
+
+### 1、为什么没有见到8001端口？
+回答：8001是开发环境使用的，用于运行前端的端口。如果你是服务器部署，不建议使用`npm run serve`启动8001端口运行前端，而是像本教程一样编译成html文件，然后使用nginx来管理访问。
+
+### 2、每次更新需要更新手动SQL语句吗？
+回答：不需要，因为项目使用**Liquibase**管理数据库版本，会自动执行新的sql脚本。

docs/digital-human-wakeword.md

@@ -0,0 +1,220 @@
+# 数字人digital-human启动方法
+
+## 概述
+
+测试页面集成了基于 **Sherpa-ONNX** 的高精度语音唤醒功能，支持自定义唤醒词和实时检测。使用轻量级关键词检测模型，提供毫秒级响应速度。
+
+## 唤醒词模型
+
+### 模型下载（必需）
+
+**重要说明**: 项目不包含模型文件，需要提前下载配置。
+
+### 官方模型下载地址
+
+- **官方模型列表**: <https://csukuangfj.github.io/sherpa/onnx/kws/pretrained_models/index.html>
+- **推荐模型**: `sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01`
+
+### 下载和配置步骤
+
+#### 1. 下载模型包
+
+```bash
+# 方法1：直接下载（推荐）
+cd main/digital-human/wakeword_runtime/
+wget https://github.com/k2-fsa/sherpa-onnx/releases/download/kws-models/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
+
+# 解压
+tar xvf sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
+
+# 方法2：使用ModelScope
+pip install modelscope
+python -c "
+from modelscope import snapshot_download
+snapshot_download('pkufool/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01', cache_dir='./models')
+"
+```
+
+#### 2. 配置模型文件
+
+模型包下载后包含以下文件：
+
+```
+sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/
+├── encoder-epoch-12-avg-2-chunk-16-left-64.int8.onnx    # 速度优先
+├── encoder-epoch-12-avg-2-chunk-16-left-64.onnx
+├── encoder-epoch-99-avg-1-chunk-16-left-64.int8.onnx    # 速度优先
+├── encoder-epoch-99-avg-1-chunk-16-left-64.onnx         # 精度优先
+├── decoder-epoch-12-avg-2-chunk-16-left-64.onnx
+├── decoder-epoch-99-avg-1-chunk-16-left-64.onnx         # 精度优先
+├── joiner-epoch-12-avg-2-chunk-16-left-64.int8.onnx     # 速度优先
+├── joiner-epoch-12-avg-2-chunk-16-left-64.onnx
+├── joiner-epoch-99-avg-1-chunk-16-left-64.int8.onnx     # 速度优先
+├── joiner-epoch-99-avg-1-chunk-16-left-64.onnx          # 精度优先
+├── tokens.txt                    # Token映射表（必需）
+├── keywords_raw.txt              # 模型包里可能附带（可选，runtime 不依赖）
+├── keywords.txt                  # 现成的
+├── test_wavs/                    # 测试音频（可选）
+├── configuration.json            # 模型元信息（可选）
+└── README.md                     # 说明文档（可选）
+```
+
+#### 3. 选择配置方案
+
+**方案一：精度优先（推荐）**
+
+```bash
+cd sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
+
+# 创建模型目录
+mkdir -p ../models
+
+# 复制精度优先的epoch-99 fp32三件套
+cp encoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/encoder.onnx
+cp decoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/decoder.onnx
+cp joiner-epoch-99-avg-1-chunk-16-left-64.onnx ../models/joiner.onnx
+
+# 复制配套文件
+cp tokens.txt ../models/tokens.txt
+# keywords_raw.txt 如果模型包里附带，可自行保留；runtime 不依赖它
+```
+
+**方案二：速度优先**
+
+```bash
+cd sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01
+
+# 创建模型目录
+mkdir -p ../models
+
+# 复制速度优先的epoch-99 int8三件套
+cp encoder-epoch-99-avg-1-chunk-16-left-64.int8.onnx ../models/encoder.onnx
+cp decoder-epoch-99-avg-1-chunk-16-left-64.onnx ../models/decoder.onnx
+cp joiner-epoch-99-avg-1-chunk-16-left-64.int8.onnx ../models/joiner.onnx
+
+# 复制配套文件
+cp tokens.txt ../models/tokens.txt
+```
+
+**注意事项**:
+
+- **不要混用 fp32 与 int8**：三个模型文件必须保持一致的精度
+- **优先选择 epoch-99**：比 epoch-12 训练更充分，精度更高
+- **必需文件**：`encoder.onnx` + `decoder.onnx` + `joiner.onnx` + `tokens.txt` + `keywords.txt`
+
+### 最终模型文件结构
+
+配置完成后，模型文件应放在 `wakeword_runtime/models/` 目录下，完整路径为 `main/digital-human/wakeword_runtime/models/`：
+
+```
+wakeword_runtime/models/
+├── encoder.onnx      # 编码器模型（重命名后）
+├── decoder.onnx      # 解码器模型（重命名后）
+├── joiner.onnx       # 连接器模型（重命名后）
+├── tokens.txt        # 拼音 Token 映射表（228行版本）
+├── keywords.txt      # 关键词配置文件（首次启动自动生成）
+└── keywords_raw.txt  # 可选，runtime 不依赖
+```
+
+## 启动方式
+
+在 `main/digital-human` 目录执行：
+
+```bash
+pip install -r wakeword_runtime/requirements.txt
+python start.py
+```
+
+启动后默认地址：
+
+- 页面地址：`http://127.0.0.1:8006/index.html`
+- 事件桥地址：`ws://127.0.0.1:8006/wakeword-ws`
+- 健康检查：`http://127.0.0.1:8006/health`
+
+停止方式：
+
+- 在运行终端按 `Ctrl+C`
+- 会同时停止静态页面服务、事件桥和唤醒词检测流程
+
+## 配置文件说明
+
+配置文件位于 [main/digital-human/wakeword_runtime/config.json](../main/digital-human/wakeword_runtime/config.json)。
+
+当前主要配置项：
+
+```json
+{
+  "wakeword": {
+    "enabled": true
+  },
+  "model_dir": "models",
+  "audio": {
+    "input_device": null,
+    "sample_rate": 16000,
+    "channels": 1
+  },
+  "detector": {
+    "num_threads": 4,
+    "provider": "cpu",
+    "max_active_paths": 2,
+    "keywords_score": 1.8,
+    "keywords_threshold": 0.1,
+    "num_trailing_blanks": 1,
+    "cooldown_seconds": 1.5
+  },
+  "logging": {
+    "level": "INFO",
+    "dir": "logs",
+    "file": "wakeword-runtime.log"
+  }
+}
+```
+
+各字段含义：
+
+| 参数 | 说明 |
+| --- | --- |
+| `wakeword.enabled` | 是否启用本地唤醒词检测 |
+| `model_dir` | 模型和词表所在目录 |
+| `audio.input_device` | 麦克风输入设备，默认使用系统默认设备 |
+| `audio.sample_rate` | 采样率，默认 `16000` |
+| `audio.channels` | 声道数，默认 `1` |
+| `detector.num_threads` | 检测器线程数 |
+| `detector.provider` | 推理 provider，当前通常为 `cpu` |
+| `detector.max_active_paths` | 搜索路径数 |
+| `detector.keywords_score` | 关键词增强分数 |
+| `detector.keywords_threshold` | 检测阈值 |
+| `detector.num_trailing_blanks` | 尾随空白数量 |
+| `detector.cooldown_seconds` | 连续触发冷却时间 |
+| `logging.level` | 日志等级 |
+| `logging.dir` | 日志目录 |
+| `logging.file` | 日志文件名 |
+
+## 推荐使用流程
+
+### 首次使用
+
+1. 准备 `models/` 目录下的模型文件和 `tokens.txt`
+2. 确认 `models/keywords.txt` 存在
+3. 在 `digital-human` 目录运行 `python start.py`
+4. 浏览器打开 `http://127.0.0.1:8006/index.html`
+5. 进入设置页检查“唤醒词”配置
+
+### 修改唤醒词
+
+1. 打开数字人页面设置
+2. 切到“唤醒词”页签
+3. 修改启用状态或唤醒词列表
+4. 点击“应用唤醒词”
+5. 根据提示决定是否立即重启
+
+### 禁用唤醒词
+
+1. 将“启用本地唤醒词”改成禁用
+2. 点击“应用唤醒词”
+3. 建议立即重启一次
+
+禁用后：
+
+- 页面与事件桥仍然可用
+- 唤醒词检测不会继续运行

docs/docker-build.md

@@ -17,5 +17,5 @@ docker build -t xiaozhi-esp32-server:web_latest -f ./Dockerfile-web .
 # 编译完成后，可以使用docker-compose启动项目
 # docker-compose.yml你需要修改成自己编译的镜像版本
 cd main/xiaozhi-server
-docker-compose up -d
+docker compose up -d
 ```

docs/docker/nginx.conf

@@ -42,9 +42,9 @@ http {
             proxy_set_header   Referer $http_referer;
             proxy_set_header   Cookie $http_cookie;
 
-            proxy_connect_timeout 10;
+            proxy_connect_timeout 15;
-            proxy_send_timeout 10;
+            proxy_send_timeout 15;
-            proxy_read_timeout 10;
+            proxy_read_timeout 15;
 
             proxy_set_header   X-Real-IP  $remote_addr;
             proxy_set_header   X-Forwarded-For $proxy_add_x_forwarded_for;

docs/docker/start.sh

@@ -6,6 +6,7 @@ java -jar /app/xiaozhi-esp32-api.jar \
   --spring.datasource.druid.username=${SPRING_DATASOURCE_DRUID_USERNAME} \
   --spring.datasource.druid.password=${SPRING_DATASOURCE_DRUID_PASSWORD} \
   --spring.data.redis.host=${SPRING_DATA_REDIS_HOST} \
+  --spring.data.redis.password=${SPRING_DATA_REDIS_PASSWORD} \
   --spring.data.redis.port=${SPRING_DATA_REDIS_PORT} &
 
 # 启动Nginx（前台运行保持容器存活）

docs/firmware-build.md

@@ -13,9 +13,9 @@ http://192.168.1.25:8003/xiaozhi/ota/
 ```
 如果显示“OTA接口运行正常，向设备发送的websocket地址是：ws://xxx:8000/xiaozhi/v1/
 
-你可以使用项目自带的`test_page.html`测试一下，是否能连上ota页面输出的websocket地址。
+你可以启动`digital-human`模块后打开`index.html`测试一下，是否能连上ota页面输出的websocket地址。
 
-如果访问不到，你需要到配置文件`.config.yaml`里修改`server.websocket`的地址，重启后再重新测试，直到`test_page.html`能正常访问。
+如果访问不到，你需要到配置文件`.config.yaml`里修改`server.websocket`的地址，重启后再重新测试，直到`index.html`能正常访问。
 
 成功后，请往下进行第2步
 

docs/homeassistant-integration.md

@@ -97,7 +97,7 @@ http://homeassistant.local:8123
 
 使用管理员账号，登录`智控台`。在`智能体管理`，找到你的智能体，再点击`配置角色`。
 
-将意图识别设置成`函数调用`或`LLM意图识别`。这时你会看到右侧有一个`编辑功能`。点击`编辑功能`按钮，会弹出`功能管理`的框。
+将意图识别设置成`外挂的大模型意图识别`或`大模型自主函数调用`。这时你会看到右侧有一个`编辑功能`。点击`编辑功能`按钮，会弹出`功能管理`的框。
 
 在`功能管理`的框里，你需要勾选`HomeAssistant设备状态查询`和`HomeAssistant设备状态修改`。
 

docs/huoshan-streamTTS-voice-cloning.md

@@ -0,0 +1,58 @@
+# 智控台 火山双流式语音合成+音色克隆配置教程
+
+本教程分为4个阶段：准备阶段、配置阶段、克隆阶段、使用阶段。主要是介绍通过智控台配置火山双流式语音合成+音色克隆的过程。
+
+## 第一阶段：准备阶段
+超级管理员先预先把火山引擎服务开通好，获取到App Id，Access Token。默认火上引擎会赠送一个音色资源。这个音色资源需要把它复制到本项目里。
+
+如果你想克隆多个音色，需要购买开通多个音色资源。只要把每个音色资源的声音ID(S_xxxxx)复制到本项目。然后分配给系统的账号使用即可。以下是详细步骤：
+
+### 1.开通火山引擎服务
+访问 https://console.volcengine.com/speech/app  在应用管理创建应用，勾选语音合成大模型和声音复刻大模型。
+
+### 2.获取音色资源ID
+访问 https://console.volcengine.com/speech/service/9999 复制三项内容，分别是App Id，Access Token以及声音ID(S_xxxxx)。如图
+
+![获取音色资源](images/image-clone-integration-01.png)
+
+## 第二阶段：配置火山引擎服务
+
+### 1.填写火山引擎配置
+
+使用超级管理员账号登录智控台，点击顶部【模型配置】，再点击模型配置页面左侧的【语音合成】，搜索找到“火山双流式语音合成”，点击修改，将你火山引擎的`App Id`填入到【应用ID】字段里，将`Access Token`填入到【访问令牌】字段里。然后保存。
+
+### 2.将音色资源ID分配给系统账号
+
+使用超级管理员账号登录智控台，点击顶部`参数字典`，在下拉菜单中，点击`系统功能配置`页面。在页面上勾选`音色克隆`，点击保存配置。即可在顶部菜单看到`音色克隆`按钮。
+
+使用超级管理员账号登录智控台，点击顶部【音色克隆】、【音色资源】。
+
+点击新增按钮，在【平台名称】选择“火山双流式语音合成”；
+
+在【音色资源ID】填入你火山引擎的声音资源ID(S_xxxxx)，填入后按回车；
+
+在【归属账号】选择你要分配给的系统账号，你可以分配给你自己。然后点击保存
+
+## 第三阶段：克隆阶段
+
+如果登录后，点击顶部【音色克隆】》【音色克隆】，显示【您的账号暂无音色资源请联系管理员分配音色资源】，说明你在第二阶段还没有把音色资源ID分配给这个账号。那就是回到第二阶段，分配音色资源给对应的账号。
+
+如果登录后，点击顶部【音色克隆】》【音色克隆】，能看到对应的音色列表。请继续。
+
+在列表里会看到对应的音色列表。选择其中一个音色资源，点击【上传音频】按钮。上传后，可以试听一下声音或者截取某段声音。确认后点击【上传音频】按钮。
+![上传音频](images/image-clone-integration-02.png)
+
+上传音频后，在列表里会看到对应的音色会变成“待复刻”状态。点击【立即复刻】按钮。等1~2秒会返回结果。
+
+如果复刻失败，请将鼠标放到“错误信息”图标上，会显示失败的原因。
+
+如果复刻成功，在列表里会看到对应的音色会变成“训练成功”状态。此时你可以点击【声音名称】栏的修改按钮，修改音色资源的名称，方便后期选择使用。
+
+## 第四阶段：使用阶段
+
+点击顶部【智能体管理】，选择任意一个智能体，点击【配置角色】按钮。
+
+语音合成(TTS)选择“火山双流式语音合成”。在列表里，找到名字带有“克隆音色”的音色资源（如图），选择它，点击保存。
+![选择音色](images/image-clone-integration-03.png)
+
+接下来，可以唤醒小智和它对话。

docs/index-stream-integration.md

@@ -0,0 +1,195 @@
+# IndexStreamTTS 使用指南
+
+## 环境准备
+### 1. 克隆项目 
+```bash 
+git clone https://github.com/Ksuriuri/index-tts-vllm.git
+```
+进入解压后的目录
+```bash
+cd index-tts-vllm
+```
+切换到指定版本 (使用VLLM-0.10.2的历史版本)
+```bash
+git checkout 224e8d5e5c8f66801845c66b30fa765328fd0be3
+```
+
+### 2. 创建并激活 conda 环境
+```bash 
+conda create -n index-tts-vllm python=3.12
+conda activate index-tts-vllm
+```
+
+### 3. 安装PyTorch 需要版本为2.8.0（最新版）
+#### 查看显卡最高支持的版本和实际安装的版本
+```bash
+nvidia-smi
+nvcc --version
+``` 
+#### 驱动支持的最高 CUDA 版本
+```bash
+CUDA Version: 12.8
+```
+#### 实际安装的 CUDA 编译器版本
+```bash
+Cuda compilation tools, release 12.8, V12.8.89
+```
+#### 那么对应的安装命令（pytorch默认给的是12.8的驱动版本）
+```bash
+pip install torch torchvision
+```
+需要 pytorch 版本 2.8.0（对应 vllm 0.10.2），具体安装指令请参考：[pytorch 官网](https://pytorch.org/get-started/locally/)
+
+### 4. 安装依赖
+```bash 
+pip install -r requirements.txt
+```
+
+### 5. 下载模型权重
+### 方案一：下载官方权重文件后转换
+此为官方权重文件，下载到本地任意路径即可，支持 IndexTTS-1.5 的权重  
+| HuggingFace                                                   | ModelScope                                                          |
+|---------------------------------------------------------------|---------------------------------------------------------------------|
+| [IndexTTS](https://huggingface.co/IndexTeam/Index-TTS)        | [IndexTTS](https://modelscope.cn/models/IndexTeam/Index-TTS)        |
+| [IndexTTS-1.5](https://huggingface.co/IndexTeam/IndexTTS-1.5) | [IndexTTS-1.5](https://modelscope.cn/models/IndexTeam/IndexTTS-1.5) |
+
+下面以ModelScope的安装方法为例  
+#### 请注意：git需要安装并初始化启用lfs（如已安装可以跳过）
+```bash
+sudo apt-get install git-lfs
+git lfs install
+```
+创建模型目录，并拉取模型
+```bash 
+mkdir model_dir
+cd model_dir
+git clone https://www.modelscope.cn/IndexTeam/IndexTTS-1.5.git
+```
+
+#### 模型权重转换
+```bash 
+bash convert_hf_format.sh /path/to/your/model_dir
+```
+例如：你下载的IndexTTS-1.5模型存放在model_dir目录下，则执行以下命令
+```bash
+bash convert_hf_format.sh model_dir/IndexTTS-1.5
+```
+此操作会将官方的模型权重转换为 transformers 库兼容的版本，保存在模型权重路径下的 vllm 文件夹中，方便后续 vllm 库加载模型权重
+
+### 6. 更改接口适配一下项目
+接口返回数据与项目不适配需要调整一下，使其直接返回音频数据
+```bash
+vi api_server.py
+```
+```bash 
+@app.post("/tts", responses={
+    200: {"content": {"application/octet-stream": {}}},
+    500: {"content": {"application/json": {}}}
+})
+async def tts_api(request: Request):
+    try:
+        data = await request.json()
+        text = data["text"]
+        character = data["character"]
+
+        global tts
+        sr, wav = await tts.infer_with_ref_audio_embed(character, text)
+
+        return Response(content=wav.tobytes(), media_type="application/octet-stream")
+        
+    except Exception as ex:
+        tb_str = ''.join(traceback.format_exception(type(ex), ex, ex.__traceback__))
+        print(tb_str)
+        return JSONResponse(
+            status_code=500,
+            content={
+                "status": "error",
+                "error": str(tb_str)
+            }
+        )
+```
+
+### 7.编写sh启动脚本（请注意要在相应的conda环境下运行）
+```bash 
+vi start_api.sh
+```
+### 将下面内容粘贴进去并按:输入wq保存  
+#### 脚本中的/home/system/index-tts-vllm/model_dir/IndexTTS-1.5 请自行修改为实际路径
+```bash
+# 激活conda环境
+conda activate index-tts-vllm 
+echo "激活项目conda环境"
+sleep 2
+# 查找占用11996端口的进程号
+PID_VLLM=$(sudo netstat -tulnp | grep 11996 | awk '{print $7}' | cut -d'/' -f1)
+
+# 检查是否找到进程号
+if [ -z "$PID_VLLM" ]; then
+  echo "没有找到占用11996端口的进程"
+else
+  echo "找到占用11996端口的进程，进程号为: $PID_VLLM"
+  # 先尝试普通kill，等待2秒
+  kill $PID_VLLM
+  sleep 2
+  # 检查进程是否还在
+  if ps -p $PID_VLLM > /dev/null; then
+    echo "进程仍在运行，强制终止..."
+    kill -9 $PID_VLLM
+  fi
+  echo "已终止进程 $PID_VLLM"
+fi
+
+# 查找占用VLLM::EngineCore进程
+GPU_PIDS=$(ps aux | grep -E "VLLM|EngineCore" | grep -v grep | awk '{print $2}')
+
+# 检查是否找到进程号
+if [ -z "$GPU_PIDS" ]; then
+  echo "没有找到VLLM相关进程"
+else
+  echo "找到VLLM相关进程，进程号为: $GPU_PIDS"
+  # 先尝试普通kill，等待2秒
+  kill $GPU_PIDS
+  sleep 2
+  # 检查进程是否还在
+  if ps -p $GPU_PIDS > /dev/null; then
+    echo "进程仍在运行，强制终止..."
+    kill -9 $GPU_PIDS
+  fi
+  echo "已终止进程 $GPU_PIDS"
+fi
+
+# 创建tmp目录（如果不存在）
+mkdir -p tmp
+
+# 后台运行api_server.py，日志重定向到tmp/server.log
+nohup python api_server.py --model_dir /home/system/index-tts-vllm/model_dir/IndexTTS-1.5 --port 11996 > tmp/server.log 2>&1 &
+echo "api_server.py 已在后台运行，日志请查看 tmp/server.log"
+```
+给脚本执行权限并运行脚本
+```bash 
+chmod +x start_api.sh
+./start_api.sh
+```
+日志会在tmp/server.log中输出，可以通过以下命令查看日志情况
+```bash
+tail -f tmp/server.log
+```
+如果显卡内存足够，可在脚本中添加启动参数 ----gpu_memory_utilization 来调整显存占用比例，默认值为 0.25
+
+## 音色配置
+index-tts-vllm支持通过配置文件注册自定义音色，支持单音色和混合音色配置。  
+在项目根目录下的assets/speaker.json文件中配置自定义音色
+### 配置格式说明
+```bash
+{
+    "说话人名称1": [
+        "音频文件路径1.wav",
+        "音频文件路径2.wav"
+    ],
+    "说话人名称2": [
+        "音频文件路径3.wav"
+    ]
+}
+```
+### 注意 （配置角色后需重启服务进行音色注册）
+添加后需在智控台中添加相应的说话人（单模块则更换相应的voice）

docs/mcp-endpoint-enable.md

@@ -0,0 +1,126 @@
+# MCP 接入点部署使用指南
+
+本教程包含3个部分
+- 1、如何部署MCP接入点这个服务
+- 2、全模块部署时，怎么配置MCP接入点
+- 3、单模块部署时，怎么配置MCP接入点
+
+# 1、如何部署MCP接入点这个服务
+
+## 第一步，下载mcp接入点项目源码
+
+浏览器打开[mcp接入点项目地址](https://github.com/xinnan-tech/mcp-endpoint-server)
+
+打开完，找到页面中一个绿色的按钮，写着`Code`的按钮，点开它，然后你就看到`Download ZIP`的按钮。
+
+点击它，下载本项目源码压缩包。下载到你电脑后，解压它，此时它的名字可能叫`mcp-endpoint-server-main`
+你需要把它重命名成`mcp-endpoint-server`。
+
+## 第二步，启动程序
+这个项目是一个很简单的项目，建议使用docker运行。不过如果你不想使用docker运行，你可以参考[这个页面](https://github.com/xinnan-tech/mcp-endpoint-server/blob/main/README_dev.md)使用源码运行。以下是docker运行的方法
+
+```
+# 进入本项目源码根目录
+cd mcp-endpoint-server
+
+# 清除缓存
+docker compose -f docker-compose.yml down
+docker stop mcp-endpoint-server
+docker rm mcp-endpoint-server
+docker rmi ghcr.nju.edu.cn/xinnan-tech/mcp-endpoint-server:latest
+
+# 启动docker容器
+docker compose -f docker-compose.yml up -d
+# 查看日志
+docker logs -f mcp-endpoint-server
+```
+
+此时，日志里会输出类似以下的日志
+```
+250705 INFO-=====下面的地址分别是智控台/单模块MCP接入点地址====
+250705 INFO-智控台MCP参数配置: http://172.22.0.2:8004/mcp_endpoint/health?key=abc
+250705 INFO-单模块部署MCP接入点: ws://172.22.0.2:8004/mcp_endpoint/mcp/?token=def
+250705 INFO-=====请根据具体部署选择使用，请勿泄露给任何人======
+```
+
+请你把两个接口地址复制出来：
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+你先把地址复制出来，放在一个草稿里，你要知道你的电脑的局域网ip是什么，例如我的电脑局域网ip是`192.168.1.25`，那么
+原来我的接口地址
+```
+智控台MCP参数配置: http://172.22.0.2:8004/mcp_endpoint/health?key=abc
+单模块部署MCP接入点: ws://172.22.0.2:8004/mcp_endpoint/mcp/?token=def
+```
+就要改成
+```
+智控台MCP参数配置: http://192.168.1.25:8004/mcp_endpoint/health?key=abc
+单模块部署MCP接入点: ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=def
+```
+
+改好后，请使用浏览器直接访问`智控台MCP参数配置`。当浏览器出现类似这样的代码，说明是成功了。
+```
+{"result":{"status":"success","connections":{"tool_connections":0,"robot_connections":0,"total_connections":0}},"error":null,"id":null,"jsonrpc":"2.0"}
+```
+
+请你保留好上面两个`接口地址`，下一步要用到。
+
+# 2、全模块部署时，怎么配置MCP接入点
+首先，你要开启MCP接入点功能。在智控台，点击顶部`参数字典`，在下拉菜单中，点击`系统功能配置`页面。在页面上勾选`MCP接入点`，点击`保存配置`。在`角色配置`页面，点击`编辑功能`按钮，即可看到`mcp接入点`功能。
+
+如果你是全模块部署，使用管理员账号，登录智控台，点击顶部`参数字典`，选择`参数管理`功能。
+
+然后搜索参数`server.mcp_endpoint`，此时，它的值应该是`null`值。
+点击修改按钮，把上一步得来的`智控台MCP参数配置`粘贴到`参数值`里。然后保存。
+
+如果能保存成功，说明一切顺利，你可以去智能体查看效果了。如果不成功，说明智控台无法访问mcp接入点，很大概率是网络防火墙，或者没有填写正确的局域网ip。
+
+# 3、单模块部署时，怎么配置MCP接入点
+
+如果你是单模块部署，找到你的配置文件`data/.config.yaml`。
+在配置文件搜索`mcp_endpoint`，如果没有找到，你就增加`mcp_endpoint`配置。类似我是就是这样
+```
+server:
+  websocket: ws://你的ip或者域名:端口号/xiaozhi/v1/
+  http_port: 8002
+log:
+  log_level: INFO
+
+# 此处可能还更多配置..
+
+mcp_endpoint: 你的接入点websocket地址
+```
+这时，请你把`如何部署MCP接入点这个服务`中得到的`单模块部署MCP接入点` 粘贴到 `mcp_endpoint`中。类似这样
+
+```
+server:
+  websocket: ws://你的ip或者域名:端口号/xiaozhi/v1/
+  http_port: 8002
+log:
+  log_level: INFO
+
+# 此处可能还更多配置
+
+mcp_endpoint: ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=def
+```
+
+配置好后，启动单模块会输出如下的日志。
+```
+250705[__main__]-INFO-初始化组件: vad成功 SileroVAD
+250705[__main__]-INFO-初始化组件: asr成功 FunASRServer
+250705[__main__]-INFO-OTA接口是          http://192.168.1.25:8002/xiaozhi/ota/
+250705[__main__]-INFO-视觉分析接口是     http://192.168.1.25:8002/mcp/vision/explain
+250705[__main__]-INFO-mcp接入点是        ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
+250705[__main__]-INFO-Websocket地址是    ws://192.168.1.25:8000/xiaozhi/v1/
+250705[__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
+250705[__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
+250705[__main__]-INFO-=============================================================
+```
+
+如上，如果能输出类似的`mcp接入点是`中`ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc`说明配置成功了。
+

docs/mcp-endpoint-integration.md

@@ -0,0 +1,94 @@
+# MCP 接入点使用指南
+
+本教程以虾哥开源的mcp计算器功能为示例，介绍如何将自己自定义的mcp服务接入到自己的接入点里。
+
+本教程的前提是，你的`xiaozhi-server`已经启用了mcp接入点功能，如果你还没启用，可以先根据[这个教程](./mcp-endpoint-enable.md)启用。
+
+# 如何为智能体接入一个简单的mcp功能，如计算器功能
+
+### 如果你是全模块部署
+如果你是全模块部署，你可以进入智控台，智能体管理，点击`配置角色`，在`意图识别`的右边，有一个`编辑功能`的按钮。
+
+点击这个按钮。在弹出的页面里，位于底部，会有`MCP接入点`，正常来说，会显示这个智能体的`MCP接入点地址`，接下来，我们来给这个智能体扩展一个基于MCP技术的计算器的功能。
+
+这个`MCP接入点地址`很重要，你等一下会用到。
+
+### 如果你是单模块部署
+如果你是单模块部署，且你已经在配置文件里配置了MCP接入点地址，那么正常来说，单模块部署启动的时候，会输出如下的日志。
+```
+250705[__main__]-INFO-初始化组件: vad成功 SileroVAD
+250705[__main__]-INFO-初始化组件: asr成功 FunASRServer
+250705[__main__]-INFO-OTA接口是          http://192.168.1.25:8002/xiaozhi/ota/
+250705[__main__]-INFO-视觉分析接口是     http://192.168.1.25:8002/mcp/vision/explain
+250705[__main__]-INFO-mcp接入点是        ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
+250705[__main__]-INFO-Websocket地址是    ws://192.168.1.25:8000/xiaozhi/v1/
+250705[__main__]-INFO-=======上面的地址是websocket协议地址，请勿用浏览器访问=======
+250705[__main__]-INFO-如想测试websocket请启动digital-human模块，打开浏览器交互测试
+250705[__main__]-INFO-=============================================================
+```
+
+如上，输出`mcp接入点是`中`ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc`就是你的`MCP接入点地址`。
+
+这个`MCP接入点地址`很重要，你等一下会用到。
+
+## 第一步 下载虾哥MCP计算器项目代码
+
+浏览器打开虾哥写的[计算器项目](https://github.com/78/mcp-calculator)，
+
+打开完，找到页面中一个绿色的按钮，写着`Code`的按钮，点开它，然后你就看到`Download ZIP`的按钮。
+
+点击它，下载本项目源码压缩包。下载到你电脑后，解压它，此时它的名字可能叫`mcp-calculatorr-main`
+你需要把它重命名成`mcp-calculator`。接下来，我们用命令行进入项目目录即安装依赖
+
+
+```bash
+# 进入项目目录
+cd mcp-calculator
+
+conda remove -n mcp-calculator --all -y
+conda create -n mcp-calculator python=3.10 -y
+conda activate mcp-calculator
+
+pip install -r requirements.txt
+```
+
+## 第二步 启动
+
+启动前，先从你的智控台的智能体里，复制到了MCP接入点的地址。
+
+例如我的智能体的mcp地址是
+```
+ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
+```
+
+开始输入命令
+
+```bash
+export MCP_ENDPOINT=ws://192.168.1.25:8004/mcp_endpoint/mcp/?token=abc
+```
+
+输入完后，启动程序
+
+```bash
+python mcp_pipe.py calculator.py
+```
+
+### 如果你是智控台部署
+如果你是智控台部署，启动完后，你再进入智控台，点击刷新MCP的接入状态，就会看到你扩展的功能列表了。
+
+### 如果你是单模块部署
+如果你是单模块部署，当设备连接后，会输出类似的日志，说明成功了
+
+```
+250705 -INFO-正在初始化MCP接入点: wss://2662r3426b.vicp.fun/mcp_e 
+250705 -INFO-发送MCP接入点初始化消息
+250705 -INFO-MCP接入点连接成功
+250705 -INFO-MCP接入点初始化成功
+250705 -INFO-统一工具处理器初始化完成
+250705 -INFO-MCP接入点服务器信息: name=Calculator, version=1.9.4
+250705 -INFO-MCP接入点支持的工具数量: 1
+250705 -INFO-所有MCP接入点工具已获取，客户端准备就绪
+250705 -INFO-工具缓存已刷新
+250705 -INFO-当前支持的函数列表: [ 'get_time', 'get_lunar', 'play_music', 'get_weather', 'handle_exit_intent', 'calculator']
+```
+如果包含了 `'calculator'`，说明设备将可以根据意图识别，调用计算器这个工具。

docs/mcp-get-device-info.md

@@ -0,0 +1,40 @@
+# MCP 方法如何获取设备信息
+
+本教程将指导你如何使用MCP方法获取设备信息。
+
+第一步：自定义你的`agent-base-prompt.txt`文件
+
+把xiaozhi-server目录的`agent-base-prompt.txt`文件内容复制到你的`data`目录下，并重命名为`.agent-base-prompt.txt`。
+
+第二步：修改`data/.agent-base-prompt.txt`文件，找到`<context>`标签，在标签内容中添加以下代码内容：
+```
+- **设备ID：** {{device_id}}
+```
+
+添加完成后，你的`data/.agent-base-prompt.txt`文件的`<context>`标签内容大致如下：
+```
+<context>
+【重要！以下信息已实时提供，无需调用工具查询，请直接使用：】
+- **设备ID：** {{device_id}}
+- **当前时间：** {{current_time}}
+- **今天日期：** {{today_date}} ({{today_weekday}})
+- **今天农历：** {{lunar_date}}
+- **用户所在城市：** {{local_address}}
+- **当地未来7天天气：** {{weather_info}}
+</context>
+```
+
+第三步：修改`data/.config.yaml`文件，找到`agent-base-prompt`配置，修改前内容如下：
+```
+prompt_template: agent-base-prompt.txt
+```
+修改成
+```
+prompt_template: data/.agent-base-prompt.txt
+```
+
+第四步：重启你的xiaozhi-server服务。
+
+第五步：在你的mcp方法增加名称为`device_id`,类型为`string`,描述为`设备ID`的参数。
+
+第六步：重新唤醒小智，让他调用mcp方法，查看你的mcp方法是否可以获取`设备ID`。

docs/mcp-vision-integration.md

@@ -58,7 +58,7 @@ docker restart xiaozhi-esp32-server
 2025-06-01 **** - 视觉分析接口是        http://192.168.4.7:8003/mcp/vision/explain
 2025-06-01 **** - Websocket地址是       ws://192.168.4.7:8000/xiaozhi/v1/
 2025-06-01 **** - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
-2025-06-01 **** - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
+2025-06-01 **** - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
 2025-06-01 **** - =============================================================
 ```
 
@@ -133,7 +133,7 @@ docker restart xiaozhi-esp32-server
 2025-06-01 **** - 视觉分析接口是        http://192.168.4.7:8003/mcp/vision/explain
 2025-06-01 **** - Websocket地址是       ws://192.168.4.7:8000/xiaozhi/v1/
 2025-06-01 **** - =======上面的地址是websocket协议地址，请勿用浏览器访问=======
-2025-06-01 **** - 如想测试websocket请用谷歌浏览器打开test目录下的test_page.html
+2025-06-01 **** - 如想测试websocket请启动digital-human模块，打开浏览器交互测试
 2025-06-01 **** - =============================================================
 ```
 

docs/mqtt-gateway-integration.md

@@ -0,0 +1,187 @@
+# MQTT 网关部署教程
+
+`xiaozhi-esp32-server`项目，可结合虾哥开源的[xiaozhi-mqtt-gateway](https://github.com/78/xiaozhi-mqtt-gateway) 项目进行简单改造，即可实现小智硬件MQTT+UDP连接。
+本教程分为三部分，你可以根据你是全模块部署还是单模块部署，选择对应的部分接入MQTT网关：
+- 第一部分：部署MQTT网关
+- 第二部分：全模块运行实现小智硬件MQTT+UDP连接
+- 第三部分：单模块运行xiaozhi-server实现小智硬件MQTT+UDP连接
+
+## 准备阶段
+准备好你的`xiaozhi-server`的`mqtt-websocket`连接地址。在你原来的`websocket地址`基础上，添加`?from=mqtt_gateway`字符，就可以得到`mqtt-websocket`连接地址
+
+1、如果你是源码部署，你的`mqtt-websocket`地址是：
+```
+ws://127.0.0.1:8000/xiaozhi/v1/?from=mqtt_gateway
+```
+
+2、如果你是docker部署，你的`mqtt-websocket`地址是
+```
+ws://你宿主机局域网IP:8000/xiaozhi/v1/?from=mqtt_gateway
+```
+
+## 重要提示
+
+如果你是服务器部署，需要确保服务器`1883`、`8884`、`8007`端口都对外开放。`8884`选择的协议类型是`UDP`，其他是`TCP`。
+
+如果你是服务器部署，需要确保服务器`1883`、`8884`、`8007`端口都对外开放。`8884`选择的协议类型是`UDP`，其他是`TCP`。
+
+如果你是服务器部署，需要确保服务器`1883`、`8884`、`8007`端口都对外开放。`8884`选择的协议类型是`UDP`，其他是`TCP`。
+
+
+## 第一部分：部署MQTT网关
+
+1. 克隆[改造后的xiaozhi-mqtt-gateway项目](https://github.com/xinnan-tech/xiaozhi-mqtt-gateway.git)：
+```bash
+git clone https://ghfast.top/https://github.com/xinnan-tech/xiaozhi-mqtt-gateway.git
+cd xiaozhi-mqtt-gateway
+```
+
+2. 安装依赖：
+```bash
+npm install
+npm install -g pm2
+```
+
+3. 配置 `config.json`：
+```bash
+cp config/mqtt.json.example config/mqtt.json
+```
+
+4. 编辑配置文件 config/mqtt.json，把你在`本文准备阶段`的`mqtt-websocket`地址替换到`chat_servers`里。例如源码部署的`xiaozhi-server`就是如下配置：
+
+``` 
+{
+    "production": {
+        "chat_servers": [
+            "ws://127.0.0.1:8000/xiaozhi/v1/?from=mqtt_gateway"
+        ]
+    },
+    "debug": false,
+    "max_mqtt_payload_size": 8192,
+    "mcp_client": {
+        "capabilities": {
+        },
+        "client_info": {
+            "name": "xiaozhi-mqtt-client",
+            "version": "1.0.0"
+        },
+        "max_tools_count": 128
+    }
+}
+```
+5. 在项目根目录创建下`.env`文件，并设置以下环境变量:
+```
+PUBLIC_IP=your-ip         # 服务器公网IP
+MQTT_PORT=1883            # MQTT服务器端口
+UDP_PORT=8884             # UDP服务器端口
+API_PORT=8007             # 管理API端口
+MQTT_SIGNATURE_KEY=test   # MQTT签名密钥
+SERVER_SECRET=Te1st12134  # 服务器密钥，请保持和智控台（server.secret）一致或者和xiaozhi-server里（server.auth_key）保持一致
+```
+请注意`PUBLIC_IP`配置，确保其与实际公网IP一致，如果有域名就填域名。
+
+`MQTT_SIGNATURE_KEY` 是用于MQTT连接认证的密钥，最好设置成复杂一点的，最好是设置成8个字符以上且同时包含大小写字母，这个密钥稍后还会用到。
+
+- 注意不要用简单的密码，比如`123456`、`test`等。
+- 注意不要用简单的密码，比如`123456`、`test`等。
+- 注意不要用简单的密码，比如`123456`、`test`等。
+
+`SERVER_SECRET` 是用生成websocket连接的认证信息。
+
+1、如果你是全模块部署，且你的智控台的参数管理里`server.auth.enabled`设置成了`true`，那么，`SERVER_SECRET`需要和智控台（`server.secret`）保持一致。
+
+2、如果你是单模块部署，且你在配置文件里把`server.auth.enabled`设置成了`true`，那么，`SERVER_SECRET`需要和配置文件里（`server.auth_key`）保持一致。
+
+
+6. 启动MQTT网关
+```
+# 启动服务
+pm2 start ecosystem.config.js
+
+# 查看日志
+pm2 logs xz-mqtt
+```
+
+当你看到如下日志，说明MQTT网关启动成功：
+```
+0|xz-mqtt  | 2025-09-11T12:14:48: MQTT 服务器正在监听端口 1883
+0|xz-mqtt  | 2025-09-11T12:14:48: UDP 服务器正在监听 x.x.x.x:8884
+```
+
+如果需要重启MQTT网关，执行如下命令：
+```
+pm2 restart xz-mqtt
+```
+
+## 第二部分：全模块运行实现小智硬件MQTT+UDP连接
+
+查看你智控台首页底部的版本号，确认你的智控台版本是否是`0.7.7`及以上版本。如果不是，需要升级智控台。
+
+1. 在智控台顶部，点击`参数管理`，搜索`server.mqtt_gateway`，点击编辑，填入你在`.env`文件中设置的`PUBLIC_IP`+`:`+`MQTT_PORT`。类似这样
+```
+192.168.0.7:1883
+```
+2. 在智控台顶部，点击`参数管理`，搜索`server.mqtt_signature_key`，点击编辑，填入你在`.env`文件中设置的`MQTT_SIGNATURE_KEY`。
+
+3. 在智控台顶部，点击`参数管理`，搜索`server.udp_gateway`，点击编辑，填入你在`.env`文件中设置的`PUBLIC_IP`+`:`+`UDP_PORT`。类似这样
+```
+192.168.0.7:8884
+```
+4. 在智控台顶部，点击`参数管理`，搜索`server.mqtt_manager_api`，点击编辑，填入你在`.env`文件中设置的`PUBLIC_IP`+`:`+`API_PORT`。类似这样
+```
+192.168.0.7:8007
+```
+
+上面的配置完成后，你可以使用curl命令，验证你的ota地址是否会下发mqtt配置，把下面的`http://localhost:8002/xiaozhi/ota/`改成你的ota地址
+```
+curl 'http://localhost:8002/xiaozhi/ota/' \
+  -H 'Content-Type: application/json' \
+  -H 'Client-Id: 7b94d69a-9808-4c59-9c9b-704333b38aff' \
+  -H 'Device-Id: 11:22:33:44:55:66' \
+  --data-raw $'{\n  "application": {\n    "version": "1.0.1",\n    "elf_sha256": "1"\n  },\n  "board": {\n    "mac": "11:22:33:44:55:66"\n  }\n}'
+```
+
+如果返回的内容包含`mqtt`相关的配置，说明配置成功。类似这样
+
+```
+{"server_time":{"timestamp":1757567894012,"timeZone":"Asia/Shanghai","timezone_offset":480},"activation":{"code":"460609","message":"http://xiaozhi.server.com\n460609","challenge":"11:22:33:44:55:66"},"firmware":{"version":"1.0.1","url":"http://xiaozhi.server.com:8002/xiaozhi/otaMag/download/NOT_ACTIVATED_FIRMWARE_THIS_IS_A_INVALID_URL"},"websocket":{"url":"ws://192.168.4.23:8000/xiaozhi/v1/"},"mqtt":{"endpoint":"192.168.0.7:1883","client_id":"GID_default@@@11_22_33_44_55_66@@@7b94d69a-9808-4c59-9c9b-704333b38aff","username":"eyJpcCI6IjA6MDowOjA6MDowOjA6MSJ9","password":"Y8XP9xcUhVIN9OmbCHT9ETBiYNE3l3Z07Wk46wV9PE8=","publish_topic":"device-server","subscribe_topic":"devices/p2p/11_22_33_44_55_66"}}
+```
+
+由于MQTT信息是需要靠OTA地址下发的，因此只有你保证能正常连接服务器的OTA地址，重启唤醒即可。
+
+唤醒后留意mqtt-gateway的日志，确认是否有连接成功的日志。
+```
+pm2 logs xz-mqtt
+```
+
+## 第三部分：单模块运行xiaozhi-server实现小智硬件MQTT+UDP连接
+
+打开你的`data/.config.yaml`文件，在`server`下找到`mqtt_gateway`填入你在`.env`文件中设置的`PUBLIC_IP`+`:`+`MQTT_PORT`。类似这样
+```
+192.168.0.7:1883
+```
+在`server`下找到`mqtt_signature_key`填入你在`.env`文件中设置的`MQTT_SIGNATURE_KEY`。
+
+在`server`下找到`udp_gateway`填入你在`.env`文件中设置的`PUBLIC_IP`+`:`+`UDP_PORT`。类似这样
+```
+192.168.0.7:8884
+```
+
+上面的配置完成后，你可以使用curl命令，验证你的ota地址是否会下发mqtt配置，把下面的`http://localhost:8002/xiaozhi/ota/`改成你的ota地址
+```
+curl 'http://localhost:8002/xiaozhi/ota/' \
+  -H 'Device-Id: 11:22:33:44:55:66' \
+  --data-raw $'{\n  "application": {\n    "version": "1.0.1",\n    "elf_sha256": "1"\n  },\n  "board": {\n    "mac": "11:22:33:44:55:66"\n  }\n}'
+```
+
+如果返回的内容包含`mqtt`相关的配置，说明配置成功。类似这样
+```
+{"server_time":{"timestamp":1758781561083,"timeZone":"GMT+08:00","timezone_offset":480},"activation":{"code":"527111","message":"http://xiaozhi.server.com\n527111","challenge":"11:22:33:44:55:66"},"firmware":{"version":"1.0.1","url":"http://xiaozhi.server.com:8002/xiaozhi/otaMag/download/NOT_ACTIVATED_FIRMWARE_THIS_IS_A_INVALID_URL"},"websocket":{"url":"ws://192.168.1.15:8000/xiaozhi/v1/"},"mqtt":{"endpoint":"192.168.1.15:1883","client_id":"GID_default@@@11_22_33_44_55_66@@@11_22_33_44_55_66","username":"eyJpcCI6IjE5Mi4xNjguMS4xNSJ9","password":"fjAYs49zTJecWqJ3jBt+kqxVn/x7vkXRAc85ak/va7Y=","publish_topic":"device-server","subscribe_topic":"devices/p2p/11_22_33_44_55_66"}}
+```
+
+由于MQTT信息是需要靠OTA地址下发的，因此只有你保证能正常连接服务器的OTA地址，重启唤醒即可。
+
+唤醒后留意mqtt-gateway的日志，确认是否有连接成功的日志。
+```
+pm2 logs xz-mqtt
+```

docs/newsnow_plugin_config.md

@@ -0,0 +1,105 @@
+# get_news_from_newsnow 插件新闻源配置指南
+
+## 概述
+
+`get_news_from_newsnow` 插件现在支持通过Web管理界面动态配置新闻源，不再需要修改代码。用户可以在智控台中为每个智能体配置不同的新闻源。
+
+## 配置方式
+
+### 1. 通过Web管理界面配置（推荐）
+
+1. 登录智控台
+2. 进入"角色配置"页面
+3. 选择要配置的智能体
+4. 点击"编辑功能"按钮
+5. 在右侧参数配置区域找到"newsnow新闻聚合"插件
+6. 在"新闻源配置"字段中输入分号分隔的中文名称
+
+### 2. 配置文件方式
+
+在 `config.yaml` 中配置：
+
+```yaml
+plugins:
+  get_news_from_newsnow:
+    url: "https://newsnow.busiyi.world/api/s?id="
+    news_sources: "澎湃新闻;百度热搜;财联社;微博;抖音"
+```
+
+## 新闻源配置格式
+
+新闻源配置使用分号分隔的中文名称，格式为：
+
+```
+中文名称1;中文名称2;中文名称3
+```
+
+### 配置示例
+
+```
+澎湃新闻;百度热搜;财联社;微博;抖音;知乎;36氪
+```
+
+## 支持的新闻源
+
+插件支持以下新闻源的中文名称：
+
+- 澎湃新闻
+- 百度热搜
+- 财联社
+- 微博
+- 抖音
+- 知乎
+- 36氪
+- 华尔街见闻
+- IT之家
+- 今日头条
+- 虎扑
+- 哔哩哔哩
+- 快手
+- 雪球
+- 格隆汇
+- 法布财经
+- 金十数据
+- 牛客
+- 少数派
+- 稀土掘金
+- 凤凰网
+- 虫部落
+- 联合早报
+- 酷安
+- 远景论坛
+- 参考消息
+- 卫星通讯社
+- 百度贴吧
+- 靠谱新闻
+- 以及更多...
+
+## 默认配置
+
+如果未配置新闻源，插件将使用以下默认配置：
+
+```
+澎湃新闻;百度热搜;财联社
+```
+
+## 使用说明
+
+1. **配置新闻源**：在Web界面或配置文件中设置新闻源的中文名称，用分号分隔
+2. **调用插件**：用户可以说"播报新闻"或"获取新闻"
+3. **指定新闻源**：用户可以说"播报澎湃新闻"或"获取百度热搜"
+4. **获取详情**：用户可以说"详细介绍这条新闻"
+
+## 工作原理
+
+1. 插件接受中文名称作为参数（如"澎湃新闻"）
+2. 根据配置的新闻源列表，将中文名称转换为对应的英文ID（如"thepaper"）
+3. 使用英文ID调用API获取新闻数据
+4. 返回新闻内容给用户
+
+## 注意事项
+
+1. 配置的中文名称必须与 CHANNEL_MAP 中定义的名称完全一致
+2. 配置更改后需要重启服务或重新加载配置
+3. 如果配置的新闻源无效，插件会自动使用默认新闻源
+4. 多个新闻源之间使用英文分号(;)分隔，不要使用中文分号(；)

docs/ota-upgrade-guide.md

@@ -0,0 +1,142 @@
+# 单模块部署固件OTA自动升级配置指南
+
+本教程将指导你如何在**单模块部署**场景下配置固件OTA自动升级功能，实现设备固件的自动更新。
+
+如果你已经使用**全模块部署**，请忽略本教程。
+
+## 功能介绍
+
+在单模块部署中，xiaozhi-server内置了OTA固件管理功能，可以自动检测设备版本并下发升级固件。系统会根据设备型号和当前版本，自动匹配并推送最新的固件版本。
+
+## 前提条件
+
+- 你已经成功进行**单模块部署**并运行xiaozhi-server
+- 设备能够正常连接到服务器
+
+## 第一步 准备固件文件
+
+### 1. 创建固件存放目录
+
+固件文件需要放在`data/bin/`目录下。如果该目录不存在，请手动创建：
+
+```bash
+mkdir -p data/bin
+```
+
+### 2. 固件文件命名规则
+
+固件文件必须遵循以下命名格式：
+
+```
+{设备型号}_{版本号}.bin
+```
+
+**命名规则说明：**
+- `设备型号`：设备的型号名称，例如 `lichuang-dev`、`bread-compact-wifi` 等
+- `版本号`：固件版本号，必须以数字开头，支持数字、字母、点号、下划线和短横线，例如 `1.6.6`、`2.0.0` 等
+- 文件扩展名必须是 `.bin`
+
+**命名示例：**
+```
+bread-compact-wifi_1.6.6.bin
+lichuang-dev_2.0.0.bin
+```
+
+### 3. 放置固件文件
+
+将准备好的固件文件（.bin文件）复制到`data/bin/`目录下：
+
+重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`!
+
+重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`!
+
+重要的事情说三遍：升级的bin文件是`xiaozhi.bin`，不是全量固件文件`merged-binary.bin`!
+
+```bash
+cp xiaozhi.bin data/bin/设备型号_版本号.bin
+```
+
+例如：
+```bash
+cp xiaozhi.bin data/bin/bread-compact-wifi_1.6.6.bin
+```
+
+## 第二步 配置公网访问地址（仅公网部署需要）
+
+**注意：此步骤仅适用于单模块公网部署的场景。**
+
+如果你的xiaozhi-server是公网部署（使用公网IP或域名），**必须**配置`server.vision_explain`参数，因为OTA固件下载地址会使用该配置的域名和端口。
+
+如果你是局域网部署，可以跳过此步骤。
+
+### 为什么要配置这个参数？
+
+在单模块部署中，系统生成固件下载地址时，会使用`vision_explain`配置的域名和端口作为基础地址。如果不配置或配置错误，设备将无法访问固件下载地址。
+
+### 配置方法
+
+打开`data/.config.yaml`文件，找到`server`配置段，设置`vision_explain`参数：
+
+```yaml
+server:
+  vision_explain: http://你的域名或IP:端口号/mcp/vision/explain
+```
+
+**配置示例：**
+
+局域网部署（默认）：
+```yaml
+server:
+  vision_explain: http://192.168.1.100:8003/mcp/vision/explain
+```
+
+公网域名部署：
+```yaml
+server:
+  vision_explain: http://yourdomain.com:8003/mcp/vision/explain
+```
+
+### 注意事项
+
+- 域名或IP必须是设备能够访问的地址
+- 如果使用Docker部署，不能使用Docker内部地址（如127.0.0.1或localhost）
+- 如果你使用了nginx反向代理，请填写对外的地址和端口号，不是本项目运行的端口号
+
+
+## 常见问题
+
+### 1. 设备收不到固件更新
+
+**可能原因和解决方法：**
+
+- 检查固件文件命名是否符合规则：`{型号}_{版本号}.bin`
+- 检查固件文件是否正确放置在`data/bin/`目录
+- 检查设备型号是否与固件文件名中的型号匹配
+- 检查固件版本号是否高于设备当前版本
+- 查看服务器日志，确认OTA请求是否正常处理
+
+### 2. 设备报告下载地址无法访问
+
+**可能原因和解决方法：**
+
+- 检查`server.vision_explain`配置的域名或IP是否正确
+- 确认端口号配置正确（默认8003）
+- 如果是公网部署，确保设备能够访问该公网地址
+- 如果是Docker部署，确保不是使用了内部地址（127.0.0.1）
+- 检查防火墙是否开放了对应端口
+- 如果你使用了nginx反向代理，请填写对外的地址和端口号，不是本项目运行的端口号
+
+### 3. 如何确认设备当前版本
+
+查看OTA请求日志，日志中会显示设备上报的版本号：
+
+```
+[ota_handler] - 设备 AA:BB:CC:DD:EE:FF 固件已是最新: 1.6.6
+```
+
+### 4. 固件文件放置后没有生效
+
+系统有30秒的缓存时间（默认），可以：
+- 等待30秒后再让设备发起OTA请求
+- 重启xiaozhi-server服务
+- 调整`firmware_cache_ttl`配置为更短的时间

docs/paddlespeech-deploy.md

@@ -0,0 +1,109 @@
+# PaddleSpeechTTS集成xiaozhi服务
+
+## 重点说明
+- 优点：本地离线部署、速度快
+- 缺点：截止2025年9月25日，默认的模型是中文模型，不支持英文转语音。如果含英文会发不出声音，如需同时支持中英文需要自己训练。
+
+## 一、基础环境要求
+操作系统：Windows / Linux / WSL 2
+
+Python 版本：3.9以上（请根据Paddle官方教程调整）
+
+Paddle 版本：官方最新版本   ```https://www.paddlepaddle.org.cn/install```
+
+依赖管理工具：conda 或 venv
+
+## 二、启动paddlespeech服务
+### 1.从paddlespeech官方仓库拉取源码
+```bash 
+git clone https://github.com/PaddlePaddle/PaddleSpeech.git
+```
+### 2.建立虚拟环境
+```bash
+
+conda create -n paddle_env python=3.10 -y
+conda activate paddle_env
+```
+### 3.安装paddle
+因CPU架构、GPU架构不同，请根据Paddle官方支持的python版本建立环境  
+```
+https://www.paddlepaddle.org.cn/install
+```
+
+### 4.进入paddlespeech目录
+```bash
+cd PaddleSpeech
+```
+### 5.安装paddlespeech
+```bash
+pip install pytest-runner -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+#以下命令使用任意一个
+pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
+pip install paddlespeech -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+### 6.使用命令自动下载语音模型
+```bash
+paddlespeech tts --input "你好，这是一次测试"
+```
+此步骤会自动下载模型缓存至本地 .paddlespeech/models 目录
+
+### 7.修改tts_online_application.yaml配置
+参考目录 ```"PaddleSpeech\demos\streaming_tts_server\conf\tts_online_application.yaml"```
+选择```tts_online_application.yaml```文件用编辑器打开，设置```protocol```为```websocket```
+
+### 8.启动服务
+```yaml
+paddlespeech_server start --config_file ./demos/streaming_tts_server/conf/tts_online_application.yaml
+#官方默认启动命令：
+paddlespeech_server start --config_file ./conf/tts_online_application.yaml
+```
+请根据你的```tts_online_application.yaml```的实际目录来启动命令，看到如下日志即启动成功
+```
+Prefix dict has been built successfully.
+[2025-08-07 10:03:11,312] [   DEBUG] __init__.py:166 - Prefix dict has been built successfully.
+INFO:     Started server process [2298]
+INFO:     Waiting for application startup.
+INFO:     Application startup complete.
+INFO:     Uvicorn running on http://0.0.0.0:8092 (Press CTRL+C to quit)
+```
+
+## 三、修改小智的配置文件
+### 1.```main/xiaozhi-server/core/providers/tts/paddle_speech.py```
+
+### 2.```main/xiaozhi-server/data/.config.yaml```
+使用单模块部署
+```yaml
+selected_module:
+  TTS: PaddleSpeechTTS
+TTS:
+  PaddleSpeechTTS:
+      type: paddle_speech
+      protocol: websocket 
+      url:  ws://127.0.0.1:8092/paddlespeech/tts/streaming  # TTS 服务的 URL 地址，指向本地服务器 [websocket默认ws://127.0.0.1:8092/paddlespeech/tts/streaming]
+      spk_id: 0  # 发音人 ID，0 通常表示默认的发音人
+      sample_rate: 24000  # 采样率 [websocket默认24000，http默认0 自动选择]
+      speed: 1.0  # 语速，1.0 表示正常语速，>1 表示加快，<1 表示减慢
+      volume: 1.0  # 音量，1.0 表示正常音量，>1 表示增大，<1 表示减小
+      save_path:   # 保存路径
+```
+### 3.启动xiaozhi服务
+```py
+python app.py
+```
+启动`main/digital-human`下的`python start.py`后，打开`http://127.0.0.1:8006/index.html`，测试连接和发送消息时paddlespeech端是否有输出日志
+
+输出日志参考：
+```
+INFO:     127.0.0.1:44312 - "WebSocket /paddlespeech/tts/streaming" [accepted]
+INFO:     connection open
+[2025-08-07 11:16:33,355] [    INFO] - sentence: 哈哈，怎么突然找我聊天啦？
+[2025-08-07 11:16:33,356] [    INFO] - The durations of audio is: 2.4625 s
+[2025-08-07 11:16:33,356] [    INFO] - first response time: 0.1143045425415039 s
+[2025-08-07 11:16:33,356] [    INFO] - final response time: 0.4777836799621582 s
+[2025-08-07 11:16:33,356] [    INFO] - RTF: 0.19402382942625715
+[2025-08-07 11:16:33,356] [    INFO] - Other info: front time: 0.06514096260070801 s, first am infer time: 0.008037090301513672 s, first voc infer time: 0.04112648963928223 s,
+[2025-08-07 11:16:33,356] [    INFO] - Complete the synthesis of the audio streams
+INFO:     connection closed
+
+```

docs/performance_tester.md

@@ -0,0 +1,27 @@
+# 语音识别、大语言模型、非流式语音合成、流式语音合成、视觉模型的性能测试工具使用指南
+
+1.在main/xiaozhi-server目录下创建data目录
+2.在data目录下创建.config.yaml文件
+3.在.data/config.yaml中，写入你的语音识别、大语言模型、流式语音合成、视觉模型的参数
+例如：
+```
+LLM:
+  ChatGLMLLM:
+    # 定义LLM API类型
+    type: openai
+    # glm-4-flash 是免费的，但是还是需要注册填写api_key的
+    # 可在这里找到你的api key https://bigmodel.cn/usercenter/proj-mgmt/apikeys
+    model_name: glm-4-flash
+    url: https://open.bigmodel.cn/api/paas/v4/
+    api_key: 你的chat-glm web key
+
+TTS:
+
+VLLM:
+
+ASR:
+```
+4.在main/xiaozhi-server目录下运行performance_tester.py: 
+```
+python performance_tester.py
+```

docs/powermem-integration.md

@@ -0,0 +1,345 @@
+# PowerMem 记忆组件集成指南
+
+## 简介
+
+[PowerMem](https://www.powermem.ai/) 是由 OceanBase 开源的 Agent 记忆组件，通过本地 LLM 进行记忆总结和智能检索，为 AI 代理提供高效的记忆管理功能。
+
+费用说明：PowerMem 本身开源免费，实际费用取决于您选择的 LLM 和数据库：
+- 使用 SQLite + 免费 LLM（如智谱 glm-4-flash）= **完全免费**
+- 使用云端 LLM 或云端数据库 = 按对应服务收费
+
+> 💡 **最佳性能提示**：PowerMem 配合 OceanBase 使用可实现最大性能释放，SQLite 仅建议在资源不足的情况下使用。
+
+- **GitHub**: https://github.com/oceanbase/powermem
+- **官网**: https://www.powermem.ai/
+- **使用示例**: https://github.com/oceanbase/powermem/tree/main/examples
+
+## 功能特性
+
+- **本地总结**：通过 LLM 在本地进行记忆总结和提取
+- **用户画像**：通过 `UserMemory` 自动提取用户信息（姓名、职业、兴趣等），持续更新用户画像
+- **智能遗忘**：基于艾宾浩斯遗忘曲线，自动"遗忘"过时噪声信息
+- **多种存储后端**：支持 OceanBase（推荐，最佳性能）、SeekDB（推荐，AI应用存储一体）、PostgreSQL、SQLite（轻量备选）
+- **多种 LLM 支持**：通义千问、智谱（glm-4-flash 免费）、OpenAI 等
+- **智能检索**：基于向量搜索的语义检索能力
+- **私有部署**：完全支持本地私有化部署
+- **异步操作**：高效的异步记忆管理
+
+## 安装
+
+PowerMem 已添加到项目依赖中，如果需要手动安装：
+
+```bash
+pip install powermem
+```
+
+## 配置说明
+
+### 基础配置
+
+在 `config.yaml` 中配置 PowerMem：
+
+```yaml
+selected_module:
+  Memory: powermem
+
+Memory:
+  powermem:
+    type: powermem
+    # 是否启用用户画像功能
+    # 用户画像支持: oceanbase、seekdb、sqlite (powermem 0.3.0+)
+    enable_user_profile: true
+    
+    # ========== LLM 配置 ==========
+    llm:
+      provider: openai  # 可选: qwen, openai, zhipu 等
+      config:
+        api_key: 你的LLM API密钥
+        model: qwen-plus
+        # openai_base_url: https://api.openai.com/v1  # 可选，自定义服务地址
+    
+    # ========== Embedding 配置 ==========
+    embedder:
+      provider: openai  # 可选: qwen, openai 等
+      config:
+        api_key: 你的嵌入模型API密钥
+        model: text-embedding-v4
+        openai_base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
+        # embedding_dims: 1024  # 向量维度，非1536时需配置
+    
+    # ========== Database 配置 ==========
+    vector_store:
+      provider: sqlite  # 可选: oceanbase(推荐), seekdb(推荐), postgres, sqlite(轻量)
+      config: {}  # SQLite 无需额外配置
+```
+
+### 配置参数详解
+
+#### LLM 配置
+
+| 参数 | 说明 | 可选值 |
+|------|------|--------|
+| `llm.provider` | LLM 提供商 | `qwen`, `openai`, `zhipu` 等 |
+| `llm.config.api_key` | API 密钥 | - |
+| `llm.config.model` | 模型名称 | 根据提供商选择 |
+| `llm.config.openai_base_url` | 自定义服务地址（可选） | - |
+
+#### Embedding 配置
+
+| 参数 | 说明 | 可选值 |
+|------|------|--------|
+| `embedder.provider` | 嵌入模型提供商 | `qwen`, `openai` 等 |
+| `embedder.config.api_key` | API 密钥 | - |
+| `embedder.config.model` | 模型名称 | 根据提供商选择 |
+| `embedder.config.openai_base_url` | 自定义服务地址（可选） | - |
+
+#### Database 配置
+
+| 参数 | 说明 | 可选值 |
+|------|------|--------|
+| `vector_store.provider` | 存储后端类型 | `oceanbase`(推荐), `seekdb`(推荐), `postgres`, `sqlite`(轻量) |
+| `vector_store.config` | 数据库连接配置 | 根据 provider 设置 |
+
+### 记忆模式说明
+
+PowerMem 支持两种记忆模式：
+
+| 模式 | 配置 | 功能 | 存储要求 |
+|------|------|------|----------|
+| **普通记忆** | `enable_user_profile: false` | 对话记忆存储与检索 | 支持所有数据库 |
+| **用户画像** | `enable_user_profile: true` | 记忆 + 自动提取用户画像 | oceanbase、seekdb、sqlite |
+
+> 📌 **版本说明**：PowerMem 0.3.0+ 版本，用户画像功能支持 OceanBase、SeekDB、SQLite 三种存储后端。
+
+### 使用通义千问（推荐）
+
+1. 访问 [阿里云百炼平台](https://bailian.console.aliyun.com/) 注册账号
+2. 在 [API Key 管理](https://bailian.console.aliyun.com/?apiKey=1#/api-key) 页面获取 API 密钥
+3. 配置如下：
+
+```yaml
+Memory:
+  powermem:
+    type: powermem
+    enable_user_profile: true
+    llm:
+      provider: qwen
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: qwen-plus
+    embedder:
+      provider: openai
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: text-embedding-v4
+        openai_base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
+    vector_store:
+      provider: sqlite
+      config: {}
+```
+
+### 使用智谱免费 LLM（完全免费方案）
+
+智谱提供免费的 glm-4-flash 模型，配合 SQLite 可实现完全免费使用：
+
+1. 访问 [智谱AI开放平台](https://bigmodel.cn/) 注册账号
+2. 在 [API Keys](https://bigmodel.cn/usercenter/proj-mgmt/apikeys) 页面获取 API 密钥
+3. 配置如下：
+
+```yaml
+Memory:
+  powermem:
+    type: powermem
+    enable_user_profile: true
+    llm:
+      provider: openai  # 使用 openai 兼容模式
+      config:
+        api_key: xxxxxxxxxxxxxxxx.xxxxxxxxxxxxxxxx
+        model: glm-4-flash
+        openai_base_url: https://open.bigmodel.cn/api/paas/v4/
+    embedder:
+      provider: openai
+      config:
+        api_key: xxxxxxxxxxxxxxxx.xxxxxxxxxxxxxxxx
+        model: embedding-3
+        openai_base_url: https://open.bigmodel.cn/api/paas/v4/
+    vector_store:
+      provider: sqlite
+      config: {}
+```
+
+### 使用 OpenAI
+
+```yaml
+Memory:
+  powermem:
+    type: powermem
+    enable_user_profile: true
+    llm:
+      provider: openai
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: gpt-4o-mini
+        openai_base_url: https://api.openai.com/v1
+    embedder:
+      provider: openai
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: text-embedding-3-small
+        openai_base_url: https://api.openai.com/v1
+    vector_store:
+      provider: sqlite
+      config: {}
+```
+
+### 使用 OceanBase（最佳性能方案）
+
+OceanBase 是 PowerMem 的最佳搭档，可实现最大性能释放：
+
+1. 部署 OceanBase 数据库（支持开源本地部署或使用云服务）
+   - 开源部署：https://github.com/oceanbase/oceanbase
+   - 云服务：https://www.oceanbase.com/
+2. 配置如下：
+
+```yaml
+Memory:
+  powermem:
+    type: powermem
+    enable_user_profile: true
+    llm:
+      provider: qwen
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: qwen-plus
+    embedder:
+      provider: openai
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: text-embedding-v4
+        openai_base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
+    vector_store:
+      provider: oceanbase
+      config:
+        host: 127.0.0.1
+        port: 2881
+        user: root@test
+        password: your_password
+        db_name: powermem
+        collection_name: memories  # 默认值
+        embedding_model_dims: 1536  # 嵌入向量维度，必需参数
+```
+
+## 设备记忆隔离
+
+PowerMem 会自动使用设备 ID（`device_id`）作为 `user_id` 进行记忆隔离。这意味着：
+
+- 每个设备拥有独立的记忆空间
+- 不同设备之间的记忆完全隔离
+- 同一设备的多次对话可以共享记忆上下文
+
+## 用户画像（UserMemory）
+
+PowerMem 提供 `UserMemory` 类，可自动从对话中提取用户画像信息。
+
+> 📌 **版本说明**：PowerMem 0.3.0+ 版本，用户画像功能支持 OceanBase、SeekDB、SQLite 三种存储后端。
+
+### 启用用户画像
+
+在配置中设置 `enable_user_profile: true` 即可启用：
+
+```yaml
+Memory:
+  powermem:
+    type: powermem
+    enable_user_profile: true  # 启用用户画像
+    llm:
+      provider: qwen
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: qwen-plus
+    embedder:
+      provider: openai
+      config:
+        api_key: sk-xxxxxxxxxxxxxxxx
+        model: text-embedding-v4
+        openai_base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
+    vector_store:
+      provider: sqlite  # 用户画像支持: oceanbase、seekdb、sqlite
+      config: {}
+```
+
+### 用户画像能力
+
+| 能力 | 说明 |
+|------|------|
+| **信息提取** | 自动从对话中提取姓名、年龄、职业、兴趣等 |
+| **持续更新** | 随着对话进行，不断完善用户画像 |
+| **画像检索** | 将用户画像与记忆搜索结合，提升检索相关性 |
+| **智能遗忘** | 基于艾宾浩斯遗忘曲线，淡化过时信息 |
+
+### 工作原理
+
+启用用户画像后，小智在查询记忆时会自动返回：
+1. **用户画像**：用户的基本信息、兴趣爱好等
+2. **相关记忆**：与当前对话相关的历史记忆
+
+> ✅ **版本说明**：PowerMem 0.3.0+ 版本，用户画像功能支持 OceanBase、SeekDB、SQLite 三种存储后端。
+
+## 与其他记忆组件的对比
+
+| 特性 | PowerMem | mem0ai | mem_local_short |
+|------|----------|--------|-----------------|
+| 工作方式 | 本地总结 | 云端接口 | 本地总结 |
+| 存储位置 | 本地/云端DB | 云端 | 本地YAML |
+| 费用 | 取决于LLM和DB | 1000次/月免费 | 完全免费 |
+| 智能检索 | ✅ 向量搜索 | ✅ 向量搜索 | ❌ 全量返回 |
+| 用户画像 | ✅ UserMemory | ❌ | ❌ |
+| 智能遗忘 | ✅ 遗忘曲线 | ❌ | ❌ |
+| 私有部署 | ✅ 支持 | ❌ 仅云端 | ✅ 支持 |
+| 数据库支持 | OceanBase(推荐)/SeekDB/PostgreSQL/SQLite | - | YAML 文件 |
+
+## 常见问题
+
+### 1. API 密钥错误
+
+如果出现 `API key is required` 错误，请检查：
+- `llm_api_key` 和 `embedding_api_key` 是否正确填写
+- API 密钥是否有效
+
+### 2. 模型不存在
+
+如果出现模型不存在的错误，请确认：
+- `llm_model` 和 `embedding_model` 名称是否正确
+- 对应的模型服务是否已开通
+
+### 3. 连接超时
+
+如果出现连接超时，可以尝试：
+- 检查网络连接
+- 如果使用代理，配置 `llm_base_url` 和 `embedding_base_url`
+
+## 测试验证
+
+可以在虚拟环境中测试 PowerMem 是否正常工作：
+
+```bash
+# 激活虚拟环境
+source .venv/bin/activate
+
+# 测试 PowerMem 导入
+python -c "from powermem import AsyncMemory; print('PowerMem 导入成功')"
+
+# 测试 UserMemory 导入（用户画像功能）
+python -c "from powermem import UserMemory; print('UserMemory 导入成功')"
+```
+
+## 更多资源
+
+- [PowerMem 官方文档](https://www.powermem.ai/)
+- [PowerMem GitHub 仓库](https://github.com/oceanbase/powermem)
+- [PowerMem 使用示例](https://github.com/oceanbase/powermem/tree/main/examples)
+- [OceanBase 官网](https://www.oceanbase.com/)
+- [OceanBase GitHub](https://github.com/oceanbase/oceanbase)
+- [SeekDB GitHub](https://github.com/oceanbase/seekdb)（AI原生搜索数据库）
+- [阿里云百炼平台](https://bailian.console.aliyun.com/)
+

docs/ragflow-integration.md

@@ -0,0 +1,269 @@
+# ragflow 集成指南
+
+本教程主要是是两部分
+
+- 一、如何部署ragflow
+- 二、如何在智控台配置ragflow接口
+
+如果您对ragflow很熟悉，且已经部署了ragflow，可直接跳过第一部分，直接进入第二部分。但是如果你希望有人指导你部署ragflow，让它能够和`xiaozhi-esp32-server`共同使用`mysql`、`redis`基础服务，以减少资源成本，你需要从第一部分开始。
+
+# 第一部分 如何部署ragflow
+## 第一步， 确认mysql、redis是否可用
+
+ragflow需要依赖`mysql`数据库。如果你之前已经部署`智控台`，说明你已经安装了`mysql`。你可以共用它。
+
+你可以你试一下在宿主机使用`telnet`命令，看看能不能正常访问`mysql`的`3306`端口。
+``` shell
+telnet 127.0.0.1 3306
+
+telnet 127.0.0.1 6379
+```
+如果能访问到`3306`端口和`6379`端口，请忽略以下的内容，直接进入第二步。
+
+如果不能访问，你需要回忆一下，你的`mysql`是怎么安装的。
+
+如果你的mysql是通过自己使用安装包安装的，说明你的`mysql`做了网络隔离。你可能先解决访问`mysql`的`3306`端口这个问题。
+
+如果你`mysql`是通过本项目的`docker-compose_all.yml`安装的。你需要找一下你当时创建数据库的`docker-compose_all.yml`文件，修改以下的内容
+
+修改前
+``` yaml
+  xiaozhi-esp32-server-db:
+    ...
+    networks:
+      - default
+    expose:
+      - "3306:3306"
+  xiaozhi-esp32-server-redis:
+    ...
+    expose:
+      - 6379
+```
+
+修改后
+``` yaml
+  xiaozhi-esp32-server-db:
+    ...
+    networks:
+      - default
+    ports:
+      - "3306:3306"
+  xiaozhi-esp32-server-redis:
+    ...
+    ports:
+      - "6379:6379"
+```
+
+注意是将`xiaozhi-esp32-server-db`和`xiaozhi-esp32-server-redis`下面的`expose`改成`ports`。改完后，需要重新启动。以下是重启mysql的命令：
+
+``` shell
+# 进入你docker-compose_all.yml所在的文件夹，例如我的是xiaozhi-server
+cd xiaozhi-server
+docker compose -f docker-compose_all.yml down
+docker compose -f docker-compose.yml up -d
+```
+
+启动完后，在宿主机再使用`telnet`命令，看看能不能正常访问`mysql`的`3306`端口。
+``` shell
+telnet 127.0.0.1 3306
+
+telnet 127.0.0.1 6379
+```
+正常来说这样就可以访问的了。
+
+## 第二步， 创建数据库和表
+如果你的宿主机，能正常访问mysql数据库，那就在mysql上创建一个名字为`rag_flow`的数据库和`rag_flow`用户，密码为`infini_rag_flow`。
+
+``` sql
+-- 创建数据库
+CREATE DATABASE IF NOT EXISTS rag_flow CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;
+
+-- 创建用户并授权
+CREATE USER IF NOT EXISTS 'rag_flow'@'%' IDENTIFIED BY 'infini_rag_flow';
+GRANT ALL PRIVILEGES ON rag_flow.* TO 'rag_flow'@'%';
+
+-- 刷新权限
+FLUSH PRIVILEGES;
+```
+
+## 第三步， 下载ragflow项目
+
+你需要在你电脑找一个文件夹，用来存放ragflow项目。例如我在`/home/system/xiaozhi`文件夹。
+
+你可以使用`git`命令，将ragflow项目下载到这个文件夹，本教程使用的是`v0.22.0`版本进行安装部署。
+```
+git clone https://ghfast.top/https://github.com/infiniflow/ragflow.git
+cd ragflow
+git checkout v0.22.0
+```
+下载完后，进入`docker`文件夹。
+``` shell
+cd docker
+```
+修改`ragflow/docker`文件夹下的`docker-compose.yml`文件，将`ragflow-cpu`和`ragflow-gpu`服务的`depends_on`配置去掉，用于解除`ragflow-cpu`服务对`mysql`的依赖。
+
+这是修改前：
+``` yaml
+  ragflow-cpu:
+    depends_on:
+      mysql:
+        condition: service_healthy
+    profiles:
+      - cpu
+  ...
+  ragflow-gpu:
+    depends_on:
+      mysql:
+        condition: service_healthy
+    profiles:
+      - gpu
+```
+这是修改后：
+``` yaml
+  ragflow-cpu:
+    profiles:
+      - cpu
+  ...
+  ragflow-gpu:
+    profiles:
+      - gpu
+```
+
+接着，修改`ragflow/docker`文件夹下的`docker-compose-base.yml`文件，去掉`mysql`和`redis`的配置。
+
+例如，删除前：
+``` yaml
+services:
+  minio:
+    image: quay.io/minio/minio:RELEASE.2025-06-13T11-33-47Z
+    ...
+  mysql:
+    image: mysql:8.0
+    ...
+  redis:
+    image: redis:6.2-alpine
+    ...
+```
+
+删除后
+``` yaml
+services:
+  minio:
+    image: quay.io/minio/minio:RELEASE.2025-06-13T11-33-47Z
+    ...
+```
+## 第四步，修改环境变量配置
+
+编辑`ragflow/docker`文件夹下的`.env`文件,找到以下配置，逐个搜索，逐个修改！逐个搜索，逐个修改！
+
+下面对于`.env`文件的修改，60%的人会忽略`MYSQL_USER`配置导致ragflow启动不成功，因此，需要强调三次：
+
+强调第一次：如果你的`.env`文件如果没有`MYSQL_USER`配置，请在配置文件增加这项！
+
+强调第二次：如果你的`.env`文件如果没有`MYSQL_USER`配置，请在配置文件增加这项！
+
+强调第三次：如果你的`.env`文件如果没有`MYSQL_USER`配置，请在配置文件增加这项！
+
+``` env
+# 端口设置
+SVR_WEB_HTTP_PORT=8008           # HTTP端口
+SVR_WEB_HTTPS_PORT=8009          # HTTPS端口
+# MySQL配置 - 修改为您本地MySQL的信息
+MYSQL_HOST=host.docker.internal  # 使用host.docker.internal让容器访问主机服务
+MYSQL_PORT=3306                  # 本地MySQL端口
+MYSQL_USER=rag_flow              # 上面创建的用户名，如果没有这项就增加这一项
+MYSQL_PASSWORD=infini_rag_flow   # 上面设置的密码
+MYSQL_DBNAME=rag_flow            # 数据库名称
+
+# Redis配置 - 修改为您本地Redis的信息
+REDIS_HOST=host.docker.internal  # 使用host.docker.internal让容器访问主机服务
+REDIS_PORT=6379                  # 本地Redis端口
+REDIS_PASSWORD=                  # 如果你的Redis没有设置密码，就按这样子填写，否则填写密码
+```
+
+注意，如果你的Redis没有设置密码，还要修改`ragflow/docker`文件夹下`service_conf.yaml.template`，将`infini_rag_flow`替换成空字符串。
+
+修改前
+``` shell
+redis:
+  db: 1
+  password: '${REDIS_PASSWORD:-infini_rag_flow}'
+  host: '${REDIS_HOST:-redis}:6379'
+```
+修改后
+``` shell
+redis:
+  db: 1
+  password: '${REDIS_PASSWORD:-}'
+  host: '${REDIS_HOST:-redis}:6379'
+```
+
+## 第五步，启动ragflow服务
+执行命令：
+``` shell
+docker-compose -f docker-compose.yml up -d
+```
+执行成功后，你可以使用`docker logs -n 20 -f docker-ragflow-cpu-1`命令，查看`docker-ragflow-cpu-1`服务的日志。
+
+如果日志中没有报错，说明ragflow服务启动成功。
+
+# 第五步，注册账号
+你可以在浏览器中访问`http://127.0.0.1:8008`，点击`Sign Up`，注册一个账号。
+
+注册成功后，你可以点击`Sign In`，登录到ragflow服务。如果你想关闭ragflow服务的注册服务，不想让其他人注册账号，你可以在`ragflow/docker`文件夹下的`.env`文件中，将`REGISTER_ENABLED`配置项设置为`0`。
+
+``` dotenv
+REGISTER_ENABLED=0
+```
+修改后，重启启动ragflow服务。
+``` shell
+docker-compose -f docker-compose.yml down
+docker-compose -f docker-compose.yml up -d
+```
+
+# 第六步，配置ragflow服务的模型
+你可以在浏览器中访问`http://127.0.0.1:8008`，点击`Sign In`，登录到ragflow服务。点击页面右上角的`头像`，进入设置页面。
+首先，在左侧导航栏中，点击`模型供应商`，进入到模型配置页面。在右侧的`可选模型`搜索框下，选择`LLM`，在列表选择你使用的模型供应商，点击`添加`，输入你的密钥；
+然后，选择`TEXT EMBEDDING`，在列表选择你使用的模型供应商，点击`添加`，输入你的密钥。
+最后，刷新一下页面，分别点击`设置默认模型`列表的LLM和Embedding，选择你使用的模型即可。请确认你的密钥开通了相应的服务，比如我是用的Embedding模型是xxx供应商的，需要去这个供应商官网查看这个模型是否需要购买资源包才能使用。
+
+
+# 第二部分 配置ragflow服务
+
+# 第一步 登录ragflow服务
+你可以在浏览器中访问`http://127.0.0.1:8008`，点击`Sign In`，登录到ragflow服务。
+
+然后点击右上角的`头像`，进入设置页面。在左侧导航栏中，点击`API`功能，然后点击"API Key"按钮。出现一个弹框，
+
+在弹框中，点击"Create new Key"按钮，生成一个API Key。复制这个`API Key`，你稍后会用到。
+
+# 第二步 配置到智控台
+确保你的智控台版本是`0.8.7`或以上。使用超级管理员账号登录到智控台。
+
+首先，你要先开启知识库功能。在顶部导航栏中，点击`参数字典`，在下拉菜单中，点击`系统功能配置`页面。在页面上勾选`知识库`，点击`保存配置`。即可在导航栏看到`知识库`功能。
+
+在顶部导航栏中，点击`模型配置`，在左侧导航栏中，点击`知识库`。在列表中找到`RAG_RAGFlow`，点击`编辑`按钮。
+
+在`服务地址`中，填写`http://你的ragflow服务的局域网IP:8008`，例如我的ragflow服务的局域网IP是`192.168.1.100`，那么我就填写`http://192.168.1.100:8008`。
+
+在`API密钥`中，填写之前复制的`API Key`。
+
+最后点击保存按钮。
+
+# 第二步 创建一个知识库
+使用超级管理员账号登录到智控台。在顶部导航栏中，点击`知识库`，在列表左下脚，点击`新增`按钮。填写一个知识库的名字和描述。点击保存。
+
+为了提高大模型对知识库的理解和召回能力，建议在创建知识库时，填写一个有意义的名字和描述。例如，如果你要创建一个关于`公司介绍`的知识库，那么知识库的名字可以是`公司介绍`，描述可以是`关于公司的相关信息例如公司基本信息、服务项目、联系电话、地址等。`。
+
+保存后，你可以在知识库列表中看到这个知识库。点击刚才创建的知识库的`查看`按钮，进入知识库详情页面。
+
+在知识库详情页面中，左下角点击`新增`按钮，可以上传文档到知识库。
+
+上传后，你可以在知识库详情页面中，看到上传的文档。此时可以点击文档的`解析`按钮，解析文档。
+
+解析完成后，你可以查看解析后的切片信息。你可以在知识库详情页面中，点击`召回测试`按钮，可以测试知识库的召回/检索功能。
+
+# 第三步 让小智使用ragflow知识库
+登录到智控台。在顶部导航栏中，点击`智能体`，找到你要配置的智能体，点击`配置角色`按钮。
+
+在意图识别左侧，点击`编辑功能`按钮，弹出一个弹框。在弹框中选择你要添加的知识库。保存即可。

docs/readme/README_de.md

@@ -0,0 +1,376 @@
+[![Banners](../images/banner1.png)](https://github.com/xinnan-tech/xiaozhi-esp32-server)
+
+<h1 align="center">Xiaozhi Backend-Service xiaozhi-esp32-server</h1>
+
+<p align="center">
+Dieses Projekt basiert auf der Theorie und Technologie der Mensch-Maschine-symbiotischen Intelligenz zur Entwicklung intelligenter Terminal-Hardware- und Software-Systeme<br/>und bietet Backend-Dienste für das Open-Source-Hardware-Projekt
+<a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a><br/>
+Implementiert mit Python, Java und Vue gemäß dem <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Xiaozhi-Kommunikationsprotokoll</a><br/>
+Unterstützt MQTT+UDP-Protokoll, Websocket-Protokoll, MCP-Endpunkte und Stimmabdruckerkennung
+</p>
+
+<p align="center">
+<a href="../FAQ.md">Häufige Fragen</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Probleme melden</a>
+· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment-Dokumentation</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Release-Hinweise</a>
+</p>
+
+<p align="center">
+  <a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
+  <a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
+  <a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DBEDFA"></a>
+  <a href="./README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
+    <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
+    <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server">
+    <img alt="stars" src="https://img.shields.io/github/stars/xinnan-tech/xiaozhi-esp32-server?color=ffcb47&labelColor=black" />
+  </a>
+</p>
+
+<p align="center">
+Geleitet vom Team von Professor Siyuan Liu (South China University of Technology)
+</br>
+刘思源教授团队主导研发(华南理工大学)
+</br>
+<img src="../images/hnlg.jpg" alt="South China University of Technology" width="50%">
+</p>
+
+---
+
+## Zielgruppe 👥
+
+Dieses Projekt erfordert ESP32-Hardware-Geräte zum Betrieb. Wenn Sie ESP32-bezogene Hardware erworben haben, erfolgreich eine Verbindung zu Brother Xias bereitgestelltem Backend-Service hergestellt haben und Ihren eigenen `xiaozhi-esp32`-Backend-Service unabhängig aufbauen möchten, dann ist dieses Projekt perfekt für Sie.
+
+Möchten Sie die Nutzungseffekte sehen? Klicken Sie auf die Videos unten 🎥
+
+<table>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
+         <picture>
+           <img alt="响应速度感受" src="../images/demo9.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
+         <picture>
+           <img alt="速度优化秘诀" src="../images/demo6.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
+         <picture>
+           <img alt="复杂医疗场景" src="../images/demo1.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
+         <picture>
+           <img alt="MQTT指令下发" src="../images/demo4.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
+         <picture>
+           <img alt="声纹识别" src="../images/demo14.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
+         <picture>
+           <img alt="控制家电开关" src="../images/demo5.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
+         <picture>
+           <img alt="MCP接入点" src="../images/demo13.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
+         <picture>
+           <img alt="多指令任务" src="../images/demo11.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
+         <picture>
+           <img alt="播放音乐" src="../images/demo7.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
+         <picture>
+           <img alt="天气插件" src="../images/demo8.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
+         <picture>
+           <img alt="实时打断" src="../images/demo10.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
+         <picture>
+           <img alt="拍照识物品" src="../images/demo12.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
+         <picture>
+           <img alt="自定义音色" src="../images/demo2.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+         <picture>
+           <img alt="使用粤语交流" src="../images/demo3.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
+         <picture>
+           <img alt="播报新闻" src="../images/demo0.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+</table>
+
+---
+
+## Warnungen ⚠️
+
+1. Dieses Projekt ist Open-Source-Software. Diese Software hat keine kommerzielle Partnerschaft mit Drittanbieter-API-Dienstleistern (einschließlich, aber nicht beschränkt auf Spracherkennung, große Modelle, Sprachsynthese und andere Plattformen), mit denen sie sich verbindet, und bietet keine Garantie für deren Servicequalität oder finanzielle Sicherheit. Es wird empfohlen, dass Benutzer Dienstleister mit entsprechenden Geschäftslizenzen bevorzugen und deren Servicevereinbarungen und Datenschutzrichtlinien sorgfältig lesen. Diese Software hostet keine Kontoschlüssel, nimmt nicht an Geldströmen teil und trägt nicht das Risiko von Verlusten bei Guthaben-Aufladungen.
+
+2. Die Funktionalität dieses Projekts ist nicht vollständig und hat keine Netzwerksicherheitsbewertung bestanden. Bitte verwenden Sie es nicht in Produktionsumgebungen. Wenn Sie dieses Projekt zu Lernzwecken in einer öffentlichen Netzwerkumgebung bereitstellen, stellen Sie bitte sicher, dass notwendige Schutzmaßnahmen vorhanden sind.
+
+---
+
+## Deployment-Dokumentation
+
+![Banners](../images/banner2.png)
+
+Dieses Projekt bietet zwei Bereitstellungsmethoden. Bitte wählen Sie basierend auf Ihren spezifischen Anforderungen:
+
+#### 🚀 Auswahl der Bereitstellungsmethode
+| Bereitstellungsmethode | Funktionen | Anwendungsszenarien | Deployment-Dokumente | Konfigurationsanforderungen | Video-Tutorials |
+|---------|------|---------|---------|---------|---------|
+| **Vereinfachte Installation** | Intelligenter Dialog, Einzel-Agenten-Verwaltung | Umgebungen mit geringer Konfiguration, Daten in Konfigurationsdateien gespeichert, keine Datenbank erforderlich | [①Docker-Version](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Quellcode-Deployment](../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)| 2 Kerne 4GB bei Verwendung von `FunASR`, 2 Kerne 2GB bei allen APIs | - |
+| **Vollständige Modulinstallation** | Intelligenter Dialog, Mehrbenutzerverwaltung, Mehr-Agenten-Verwaltung, Intelligente Steuerkonsole-Bedienung | Vollständige Funktionserfahrung, Daten in Datenbank gespeichert |[①Docker-Version](../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) / [②Quellcode-Deployment](../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) / [③Quellcode-Deployment Auto-Update-Tutorial](../dev-ops-integration.md) | 4 Kerne 8GB bei Verwendung von `FunASR`, 2 Kerne 4GB bei allen APIs| [Video-Tutorial für lokalen Quellcode-Start](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
+
+Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](../FAQ.md)
+
+> 💡 Hinweis: Unten ist eine Testplattform, die mit dem neuesten Code bereitgestellt wurde. Sie können bei Bedarf brennen und testen. Gleichzeitige Benutzer: 6, Daten werden täglich gelöscht.
+
+```
+Adresse der intelligenten Steuerkonsole: https://2662r3426b.vicp.fun
+Adresse der intelligenten Steuerkonsole (H5): https://2662r3426b.vicp.fun/h5/index.html
+
+Service-Testtool: https://2662r3426b.vicp.fun/test/
+OTA-Schnittstellenadresse: https://2662r3426b.vicp.fun/xiaozhi/ota/
+Websocket-Schnittstellenadresse: wss://2662r3426b.vicp.fun/xiaozhi/v1/
+```
+
+#### 🚩 Konfigurationsbeschreibung und Empfehlungen
+> [!Note]
+> Dieses Projekt bietet zwei Konfigurationsschemata:
+>
+> 1. `Einstiegslevel Kostenlose Einstellungen`: Geeignet für den persönlichen und privaten Gebrauch, alle Komponenten verwenden kostenlose Lösungen, keine zusätzliche Zahlung erforderlich.
+>
+> 2. `Streaming-Konfiguration`: Geeignet für Demonstrationen, Schulungen, Szenarien mit mehr als 2 gleichzeitigen Benutzern usw. Verwendet Streaming-Verarbeitungstechnologie für schnellere Reaktionsgeschwindigkeit und bessere Erfahrung.
+>
+> Ab Version `0.5.2` unterstützt das Projekt Streaming-Konfiguration. Im Vergleich zu früheren Versionen ist die Reaktionsgeschwindigkeit um ca. `2,5 Sekunden` verbessert, was die Benutzererfahrung erheblich verbessert.
+
+| Modulname | Einstiegslevel Kostenlose Einstellungen | Streaming-Konfiguration |
+|:---:|:---:|:---:|
+| ASR (Spracherkennung) | FunASR (Lokal) | 👍XunfeiStreamASR (Xunfei-Streaming) |
+| LLM (Großes Modell) | glm-4-flash (Zhipu) | 👍qwen-flash (Alibaba Bailian) |
+| VLLM (Vision Large Model) | glm-4v-flash (Zhipu) | 👍qwen3.5-flash (Alibaba Bailian) |
+| TTS (Sprachsynthese) | EdgeTTS (Microsoft) | 👍HuoshanDoubleStreamTTS (Volcano-Streaming) |
+| Intent (Absichtserkennung) | function_call (Funktionsaufruf) | function_call (Funktionsaufruf) |
+| Memory (Gedächtnisfunktion) | mem_local_short (Lokales Kurzzeitgedächtnis) | mem_local_short (Lokales Kurzzeitgedächtnis) |
+
+Wenn Sie sich um die Latenz jeder Komponente kümmern, lesen Sie bitte den [Xiaozhi-Komponenten-Leistungstestbericht](https://github.com/xinnan-tech/xiaozhi-performance-research). Sie können gemäß den Testmethoden im Bericht in Ihrer Umgebung tatsächlich testen.
+
+#### 🔧 Testwerkzeuge
+Dieses Projekt bietet die folgenden Testwerkzeuge, um Ihnen bei der Überprüfung des Systems und der Auswahl geeigneter Modelle zu helfen:
+
+| Werkzeugname | Standort | Verwendungsmethode | Funktionsbeschreibung |
+|:---:|:---|:---:|:---:|
+| Audio-Interaktionstesttool | main》digital-human》index.html | In `main/digital-human` `python start.py` ausführen und dann `http://127.0.0.1:8006/index.html` öffnen | Testet Audio-Wiedergabe- und Empfangsfunktionen, überprüft, ob die Python-seitige Audioverarbeitung normal ist |
+| Modell-Reaktionstesttool | main》xiaozhi-server》performance_tester.py | Ausführen `python performance_tester.py` | Testet die Reaktionsgeschwindigkeit von ASR (Spracherkennung), LLM (großes Modell), VLLM (Vision-Modell), TTS (Sprachsynthese) drei Kernmodulen |
+
+> 💡 Hinweis: Beim Testen der Modellgeschwindigkeit werden nur Modelle mit konfigurierten Schlüsseln getestet.
+
+---
+## Funktionsliste ✨
+### Implementiert ✅
+![请参考-全模块安装架构图](../images/deploy2.png)
+| Funktionsmodul | Beschreibung |
+|:---:|:---|
+| Kernarchitektur | Basierend auf [MQTT+UDP-Gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket und HTTP-Servern, bietet vollständiges Konsolenverwaltungs- und Authentifizierungssystem |
+| Sprachinteraktion | Unterstützt Streaming-ASR (Spracherkennung), Streaming-TTS (Sprachsynthese), VAD (Sprachaktivitätserkennung), unterstützt mehrsprachige Erkennung und Sprachverarbeitung |
+| Stimmabdruckerkennung | Unterstützt Mehrbenutzer-Stimmabdruckregistrierung, -verwaltung und -erkennung, verarbeitet parallel mit ASR, Echtzeit-Sprecheridentitätserkennung und Weitergabe an LLM für personalisierte Antworten |
+| Intelligenter Dialog | Unterstützt mehrere LLM (große Sprachmodelle), implementiert intelligenten Dialog |
+| Visuelle Wahrnehmung | Unterstützt mehrere VLLM (Vision Large Models), implementiert multimodale Interaktion |
+| Absichtserkennung | Unterstützt LLM-Absichtserkennung, Function Call-Funktionsaufruf, bietet plugin-basierten Absichtsverarbeitungsmechanismus |
+| Gedächtnissystem | Unterstützt lokales Kurzzeitgedächtnis, mem0ai-Schnittstellengedächtnis, PowerMem intelligentes Gedächtnis, mit Gedächtniszusammenfassungsfunktion |
+| Wissensdatenbank | Unterstützt RAGFlow-Wissensdatenbank, ermöglicht großem Modell die Bewertung, ob Wissensdatenbank benötigt wird, bevor geantwortet wird |
+| Werkzeugaufruf | Unterstützt Client-IOT-Protokoll, Client-MCP-Protokoll, Server-MCP-Protokoll, MCP-Endpunktprotokoll, benutzerdefinierte Werkzeugfunktionen |
+| Befehlsübermittlung | Basierend auf MQTT-Protokoll, unterstützt die Übermittlung von MCP-Befehlen von der intelligenten Steuerkonsole an ESP32-Geräte |
+| Verwaltungs-Backend | Bietet Web-Verwaltungsoberfläche, unterstützt Benutzerverwaltung, Systemkonfiguration und Geräteverwaltung; Oberfläche unterstützt vereinfachtes Chinesisch, traditionelles Chinesisch und englische Anzeige |
+| Testwerkzeuge | Bietet Leistungstestwerkzeuge, Vision-Modell-Testwerkzeuge und Audio-Interaktionstestwerkzeuge |
+| Deployment-Unterstützung | Unterstützt Docker-Deployment und lokales Deployment, bietet vollständige Konfigurationsdateiverwaltung |
+| Plugin-System | Unterstützt funktionale Plugin-Erweiterungen, benutzerdefinierte Plugin-Entwicklung und Plugin-Hot-Loading |
+
+### In Entwicklung 🚧
+
+Um über spezifische Entwicklungsplanfortschritte zu erfahren, [klicken Sie hier](https://github.com/users/xinnan-tech/projects/3). Häufige Fragen und entsprechende Tutorials finden Sie unter [diesem Link](../FAQ.md)
+
+Wenn Sie ein Softwareentwickler sind, finden Sie hier einen [Offenen Brief an Entwickler](../contributor_open_letter.md). Willkommen beim Beitritt!
+
+---
+
+## Produktökosystem 👬
+Xiaozhi ist ein Ökosystem. Wenn Sie dieses Produkt verwenden, können Sie sich auch andere [hervorragende Projekte](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) in diesem Ökosystem ansehen
+
+---
+
+## Liste der von diesem Projekt unterstützten Plattformen/Komponenten 📋
+### LLM-Sprachmodelle
+
+| Verwendungsmethode | Unterstützte Plattformen | Kostenlose Plattformen |
+|:---:|:---:|:---:|
+| OpenAI-Schnittstellenaufrufe | Alibaba Bailian, Volcano Engine Doubao, DeepSeek, Zhipu ChatGLM, Gemini | Zhipu ChatGLM, Gemini |
+| Ollama-Schnittstellenaufrufe | Ollama | - |
+| Dify-Schnittstellenaufrufe | Dify | - |
+| FastGPT-Schnittstellenaufrufe | FastGPT | - |
+| Coze-Schnittstellenaufrufe | Coze | - |
+| Xinference-Schnittstellenaufrufe | Xinference | - |
+| HomeAssistant-Schnittstellenaufrufe | HomeAssistant | - |
+
+Tatsächlich kann jedes LLM, das OpenAI-Schnittstellenaufrufe unterstützt, integriert und verwendet werden.
+
+---
+
+### VLLM-Vision-Modelle
+
+| Verwendungsmethode | Unterstützte Plattformen | Kostenlose Plattformen |
+|:---:|:---:|:---:|
+| OpenAI-Schnittstellenaufrufe | Alibaba Bailian, Zhipu ChatGLMVLLM | Zhipu ChatGLMVLLM |
+
+Tatsächlich kann jedes VLLM, das OpenAI-Schnittstellenaufrufe unterstützt, integriert und verwendet werden.
+
+---
+
+### TTS-Sprachsynthese
+
+| Verwendungsmethode | Unterstützte Plattformen | Kostenlose Plattformen |
+|:---:|:---:|:---:|
+| Schnittstellenaufrufe | EdgeTTS, Volcano Engine Doubao TTS, Tencent Cloud, Alibaba Cloud TTS, AliYun Stream TTS, CosyVoiceSiliconflow, TTS302AI, CozeCnTTS, GizwitsTTS, ACGNTTS, OpenAITTS, Lingxi Streaming TTS, MinimaxTTS, Volcano Dual-Stream TTS | Lingxi Streaming TTS, EdgeTTS, CosyVoiceSiliconflow (teilweise) |
+| Lokale Dienste | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, Index-TTS, PaddleSpeech | Index-TTS, PaddleSpeech, FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3 |
+
+---
+
+### VAD-Sprachaktivitätserkennung
+
+| Typ | Plattformname | Verwendungsmethode | Preismodell | Hinweise |
+|:---:|:---------:|:----:|:----:|:--:|
+| VAD | SileroVAD | Lokale Verwendung | Kostenlos | |
+
+---
+
+### ASR-Spracherkennung
+
+| Verwendungsmethode | Unterstützte Plattformen | Kostenlose Plattformen |
+|:---:|:---:|:---:|
+| Lokale Verwendung | FunASR, SherpaASR | FunASR, SherpaASR |
+| Schnittstellenaufrufe | DoubaoASR, Doubao Streaming ASR, FunASRServer, TencentASR, AliyunASR, Aliyun Streaming ASR, Baidu ASR, OpenAI ASR | FunASRServer |
+
+---
+
+### Voiceprint-Stimmabdruckerkennung
+
+| Verwendungsmethode | Unterstützte Plattformen | Kostenlose Plattformen |
+|:---:|:---:|:---:|
+| Lokale Verwendung | 3D-Speaker | 3D-Speaker |
+
+---
+
+### Memory-Gedächtnisspeicher
+
+| Typ | Plattformname | Verwendungsmethode | Preismodell | Hinweise |
+|:------:|:---------------:|:----:|:---------:|:--:|
+| Memory | mem0ai | Schnittstellenaufrufe | 1000 Mal/Monat Kontingent | |
+| Memory | [powermem](../powermem-integration.md) | Lokale Zusammenfassung | Abhängig von LLM und DB | OceanBase Open Source, unterstützt intelligente Abfrage |
+| Memory | mem_local_short | Lokale Zusammenfassung | Kostenlos | |
+| Memory | nomem | Kein Gedächtnismodus | Kostenlos | |
+
+---
+
+### Intent-Absichtserkennung
+
+| Typ | Plattformname | Verwendungsmethode | Preismodell | Hinweise |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Intent | intent_llm | Schnittstellenaufrufe | Basierend auf LLM-Preisen | Erkennt Absicht durch große Modelle, starke Allgemeingültigkeit |
+| Intent | function_call | Schnittstellenaufrufe | Basierend auf LLM-Preisen | Vervollständigt Absicht durch Funktionsaufruf großer Modelle, schnelle Geschwindigkeit, guter Effekt |
+| Intent | nointent | Kein Absichtsmodus | Kostenlos | Führt keine Absichtserkennung durch, gibt direkt Dialogergebnis zurück |
+
+---
+
+### Rag Retrieval Augmented Generation
+
+| Typ | Plattformname | Verwendungsmethode | Preismodell | Hinweise |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Rag | ragflow | Schnittstellenaufrufe | Gebühren basierend auf Token-Verbrauch für Segmentierung und Tokenisierung | Nutzt RAGFlow's Retrieval-Augmented-Generation-Funktion für präzisere Dialogantworten |
+
+---
+
+## Danksagungen 🙏
+
+| Logo | Projekt/Unternehmen | Beschreibung |
+|:---:|:---:|:---|
+| <img src="../images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | Dieses Projekt wurde von [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) inspiriert und auf dessen Basis implementiert |
+| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Dank an [Tenclass](https://www.tenclass.com/) für die Formulierung von Standardkommunikationsprotokollen, Multi-Geräte-Kompatibilitätslösungen und High-Concurrency-Szenario-Praxisdemonstrationen für das Xiaozhi-Ökosystem; für die Bereitstellung vollständiger technischer Dokumentationsunterstützung für dieses Projekt |
+| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Dank an [Xuanfeng Technology](https://github.com/Eric0308) für den Beitrag des Funktionsaufruf-Frameworks, des MCP-Kommunikationsprotokolls und der plugin-basierten Aufrufmechanismus-Implementierungscode. Durch standardisiertes Befehlsplanungssystem und dynamische Erweiterungsfähigkeiten wird die Interaktionseffizienz und funktionale Erweiterbarkeit von Frontend-Geräten (IoT) erheblich verbessert |
+| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Dank an [huangjunsen](https://github.com/huangjunsen0406) für den Beitrag des `Smart Control Console Mobile`-Moduls, das eine effiziente Steuerung und Echtzeit-Interaktion über mobile Geräte ermöglicht und die Betriebsbequemlichkeit und Verwaltungseffizienz des Systems in mobilen Szenarien erheblich verbessert |
+| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Dank an [Huiyuan Design](http://ui.kwd988.net/) für die Bereitstellung professioneller visueller Lösungen für dieses Projekt, unter Verwendung ihrer Design-Praxiserfahrung im Dienst von über tausend Unternehmen, um die Produktbenutzererfahrung dieses Projekts zu stärken |
+| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Dank an [Xi'an Qinren Information Technology](https://www.029app.com/) für die Vertiefung des visuellen Systems dieses Projekts und die Sicherstellung der Konsistenz und Erweiterbarkeit des Gesamtdesignstils in Multi-Szenario-Anwendungen |
+| <img src="../images/logo_contributors.png" width="160"> | [Code-Mitwirkende](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Dank an [alle Code-Mitwirkenden](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), Ihre Bemühungen haben das Projekt robuster und leistungsfähiger gemacht. |
+
+
+<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" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />
+ </picture>
+</a>

docs/readme/README_en.md

@@ -0,0 +1,376 @@
+[![Banners](../images/banner1.png)](https://github.com/xinnan-tech/xiaozhi-esp32-server)
+
+<h1 align="center">Xiaozhi Backend Service xiaozhi-esp32-server</h1>
+
+<p align="center">
+This project is based on human-machine symbiotic intelligence theory and technology to develop intelligent terminal hardware and software systems<br/>providing backend services for the open-source intelligent hardware project
+<a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a><br/>
+Implemented using Python, Java, and Vue according to the <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Xiaozhi Communication Protocol</a><br/>
+Support for MQTT+UDP protocol, Websocket protocol, MCP access point, voiceprint recognition, and knowledge base
+</p>
+
+<p align="center">
+<a href="../FAQ.md">FAQ</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Report Issues</a>
+· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Deployment Docs</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Release Notes</a>
+</p>
+
+<p align="center">
+  <a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DBEDFA"></a>
+  <a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
+  <a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
+  <a href="./README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
+    <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
+    <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server">
+    <img alt="stars" src="https://img.shields.io/github/stars/xinnan-tech/xiaozhi-esp32-server?color=ffcb47&labelColor=black" />
+  </a>
+</p>
+
+<p align="center">
+Spearheaded by Professor Siyuan Liu's Team (South China University of Technology)
+</br>
+刘思源教授团队主导研发（华南理工大学）
+</br>
+<img src="../images/hnlg.jpg" alt="South China University of Technology" width="50%">
+</p>
+
+---
+
+## Target Users 👥
+
+This project requires ESP32 hardware devices to work. If you have purchased ESP32-related hardware, successfully connected to Brother Xia's deployed backend service, and want to build your own `xiaozhi-esp32` backend service independently, then this project is perfect for you.
+
+Want to see the usage effects? Click the videos below 🎥
+
+<table>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
+         <picture>
+           <img alt="响应速度感受" src="../images/demo9.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
+         <picture>
+           <img alt="速度优化秘诀" src="../images/demo6.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
+         <picture>
+           <img alt="复杂医疗场景" src="../images/demo1.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
+         <picture>
+           <img alt="MQTT指令下发" src="../images/demo4.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
+         <picture>
+           <img alt="声纹识别" src="../images/demo14.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
+         <picture>
+           <img alt="控制家电开关" src="../images/demo5.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
+         <picture>
+           <img alt="MCP接入点" src="../images/demo13.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
+         <picture>
+           <img alt="多指令任务" src="../images/demo11.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
+         <picture>
+           <img alt="播放音乐" src="../images/demo7.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
+         <picture>
+           <img alt="天气插件" src="../images/demo8.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
+         <picture>
+           <img alt="实时打断" src="../images/demo10.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
+         <picture>
+           <img alt="拍照识物品" src="../images/demo12.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
+         <picture>
+           <img alt="自定义音色" src="../images/demo2.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+         <picture>
+           <img alt="使用粤语交流" src="../images/demo3.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
+         <picture>
+           <img alt="播报新闻" src="../images/demo0.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+</table>
+
+---
+
+## Warnings ⚠️
+
+1. This project is open-source software. This software has no commercial partnership with any third-party API service providers (including but not limited to speech recognition, large models, speech synthesis, and other platforms) that it interfaces with, and does not provide any form of guarantee for their service quality or financial security. It is recommended that users prioritize service providers with relevant business licenses and carefully read their service agreements and privacy policies. This software does not host any account keys, does not participate in fund flows, and does not bear the risk of recharge fund losses.
+
+2. The functionality of this project is not complete and has not passed network security assessment. Please do not use it in production environments. If you deploy this project for learning purposes in a public network environment, please ensure necessary protection measures are in place.
+
+---
+
+## Deployment Documentation
+
+![Banners](../images/banner2.png)
+
+This project provides two deployment methods. Please choose based on your specific needs:
+
+#### 🚀 Deployment Method Selection
+| Deployment Method | Features | Applicable Scenarios | Deployment Docs | Configuration Requirements | Video Tutorials | 
+|---------|------|---------|---------|---------|---------|
+| **Simplified Installation** | Intelligent dialogue, single agent management | Low-configuration environments, data stored in config files, no database required | [①Docker Version](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Source Code Deployment](../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)| 2 cores 4GB if using `FunASR`, 2 cores 2GB if all APIs | - | 
+| **Full Module Installation** | Intelligent dialogue, multi-user management, multi-agent management, intelligent console interface operation | Complete functionality experience, data stored in database |[①Docker Version](../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) / [②Source Code Deployment](../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) / [③Source Code Deployment Auto-Update Tutorial](../dev-ops-integration.md) | 4 cores 8GB if using `FunASR`, 2 cores 4GB if all APIs| [Local Source Code Startup Video Tutorial](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
+
+For frequently asked questions and related tutorials, please refer to [this link](../FAQ.md)
+
+> 💡 Note: Below is a test platform deployed with the latest code. You can burn and test if needed. Concurrent users: 6, data will be cleared daily.
+
+```
+Intelligent Control Console Address: https://2662r3426b.vicp.fun
+Intelligent Control Console Address (H5): https://2662r3426b.vicp.fun/h5/index.html
+
+Service Test Tool: https://2662r3426b.vicp.fun/test/
+OTA Interface Address: https://2662r3426b.vicp.fun/xiaozhi/ota/
+Websocket Interface Address: wss://2662r3426b.vicp.fun/xiaozhi/v1/
+```
+
+#### 🚩 Configuration Description and Recommendations
+> [!Note]
+> This project provides two configuration schemes:
+> 
+> 1. `Entry Level Free Settings`: Suitable for personal and home use, all components use free solutions, no additional payment required.
+> 
+> 2. `Streaming Configuration`: Suitable for demonstrations, training, scenarios with more than 2 concurrent users, etc. Uses streaming processing technology for faster response speed and better experience.
+> 
+> Starting from version `0.5.2`, the project supports streaming configuration. Compared to earlier versions, response speed is improved by approximately `2.5 seconds`, significantly improving user experience.
+
+| Module Name | Entry Level Free Settings | Streaming Configuration |
+|:---:|:---:|:---:|
+| ASR(Speech Recognition) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
+| LLM(Large Model) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
+| VLLM(Vision Large Model) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
+| TTS(Speech Synthesis) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| Intent(Intent Recognition) | function_call(Function calling) | function_call(Function calling) |
+| Memory(Memory function) | mem_local_short(Local short-term memory) | mem_local_short(Local short-term memory) |
+
+If you are concerned about the latency of each component, please refer to the [Xiaozhi Component Performance Test Report](https://github.com/xinnan-tech/xiaozhi-performance-research), and test in your own environment following the test methods in the report.
+
+#### 🔧 Testing Tools
+This project provides the following testing tools to help you verify the system and choose suitable models:
+
+| Tool Name | Location | Usage Method | Function Description |
+|:---:|:---|:---:|:---:|
+| Audio Interaction Test Tool | main》digital-human》index.html | Run `python start.py` in `main/digital-human`, then open `http://127.0.0.1:8006/index.html` | Tests audio playback and reception functions, verifies if Python-side audio processing is normal |
+| Model Response Test Tool | main》xiaozhi-server》performance_tester.py | Execute `python performance_tester.py` | Tests response speed of three core modules: ASR(speech recognition), LLM(large model), VLLM(vision model), TTS(speech synthesis) |
+
+> 💡 Note: When testing model speed, only models with configured keys will be tested.
+
+---
+## Feature List ✨
+### Implemented ✅
+![请参考-全模块安装架构图](../images/deploy2.png)
+| Feature Module | Description |
+|:---:|:---|
+| Core Architecture | Based on [MQTT+UDP gateway](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket and HTTP servers, provides complete console management and authentication system |
+| Voice Interaction | Supports streaming ASR(speech recognition), streaming TTS(speech synthesis), VAD(voice activity detection), supports multi-language recognition and voice processing |
+| Voiceprint Recognition | Supports multi-user voiceprint registration, management, and recognition, processes in parallel with ASR, real-time speaker identity recognition and passes to LLM for personalized responses |
+| Intelligent Dialogue | Supports multiple LLM(large language models), implements intelligent dialogue |
+| Visual Perception | Supports multiple VLLM(vision large models), implements multimodal interaction |
+| Intent Recognition | Supports LLM intent recognition, Function Call function calling, provides plugin-based intent processing mechanism |
+| Memory System | Supports local short-term memory, mem0ai interface memory, PowerMem intelligent memory, with memory summarization functionality |
+| Knowledge Base | Supports RAGFlow knowledge base, enabling LLM to judge whether to schedule the knowledge base after receiving the user's question, and then answer the question |
+| Tool Calling | Supports client IOT protocol, client MCP protocol, server MCP protocol, MCP endpoint protocol, custom tool functions |
+| Command Delivery | Supports MCP command delivery to ESP32 devices via MQTT protocol from Smart Console |
+| Management Backend | Provides Web management interface, supports user management, system configuration and device management; Supports Simplified Chinese, Traditional Chinese and English display |
+| Testing Tools | Provides performance testing tools, vision model testing tools, and audio interaction testing tools |
+| Deployment Support | Supports Docker deployment and local deployment, provides complete configuration file management |
+| Plugin System | Supports functional plugin extensions, custom plugin development, and plugin hot-loading |
+
+### Under Development 🚧
+
+To learn about specific development plan progress, [click here](https://github.com/users/xinnan-tech/projects/3). For frequently asked questions and related tutorials, please refer to [this link](../FAQ.md)
+
+If you are a software developer, here is an [Open Letter to Developers](../contributor_open_letter.md). Welcome to join!
+
+---
+
+## Product Ecosystem 👬
+Xiaozhi is an ecosystem. When using this product, you can also check out other [excellent projects](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) in this ecosystem
+
+---
+
+## Supported Platforms/Components List 📋
+### LLM Language Models
+
+| Usage Method | Supported Platforms | Free Platforms |
+|:---:|:---:|:---:|
+| OpenAI interface calls | Alibaba Bailian, Volcano Engine, DeepSeek, Zhipu, Gemini, iFLYTEK | Zhipu, Gemini |
+| Ollama interface calls | Ollama | - |
+| Dify interface calls | Dify | - |
+| FastGPT interface calls | FastGPT | - |
+| Coze interface calls | Coze | - |
+| Xinference interface calls | Xinference | - |
+| HomeAssistant interface calls | HomeAssistant | - |
+
+In fact, any LLM that supports OpenAI interface calls can be integrated and used.
+
+---
+
+### VLLM Vision Models
+
+| Usage Method | Supported Platforms | Free Platforms |
+|:---:|:---:|:---:|
+| OpenAI interface calls | Alibaba Bailian, Zhipu ChatGLMVLLM | Zhipu ChatGLMVLLM |
+
+In fact, any VLLM that supports OpenAI interface calls can be integrated and used.
+
+---
+
+### TTS Speech Synthesis
+
+| Usage Method | Supported Platforms | Free Platforms |
+|:---:|:---:|:---:|
+| Interface calls | EdgeTTS, iFLYTEK, Volcano Engine, Tencent Cloud, Alibaba Cloud and Bailian, CosyVoiceSiliconflow, TTS302AI, CozeCnTTS, GizwitsTTS, ACGNTTS, OpenAITTS, Lingxi Streaming TTS, MinimaxTTS | Lingxi Streaming TTS, EdgeTTS, CosyVoiceSiliconflow(partial) |
+| Local services | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, Index-TTS, PaddleSpeech | Index-TTS, PaddleSpeech, FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3 |
+
+---
+
+### VAD Voice Activity Detection
+
+| Type | Platform Name | Usage Method | Pricing Model | Notes |
+|:---:|:---------:|:----:|:----:|:--:|
+| VAD | SileroVAD | Local use | Free | |
+
+---
+
+### ASR Speech Recognition
+
+| Usage Method | Supported Platforms | Free Platforms |
+|:---:|:---:|:---:|
+| Local use | FunASR, SherpaASR | FunASR, SherpaASR |
+| Interface calls | FunASRServer, Volcano Engine, iFLYTEK, Tencent Cloud, Alibaba Cloud, Baidu Cloud, OpenAI ASR | FunASRServer |
+
+---
+
+### Voiceprint Recognition
+
+| Usage Method | Supported Platforms | Free Platforms |
+|:---:|:---:|:---:|
+| Local use | 3D-Speaker | 3D-Speaker |
+
+---
+
+### Memory Storage
+
+| Type | Platform Name | Usage Method | Pricing Model | Notes |
+|:------:|:---------------:|:----:|:---------:|:--:|
+| Memory | mem0ai | Interface calls | 1000 times/month quota | |
+| Memory | [powermem](../powermem-integration.md) | Local summarization | Depends on LLM and DB | OceanBase open source, supports intelligent retrieval |
+| Memory | mem_local_short | Local summarization | Free | |
+| Memory | nomem | No memory mode | Free | |
+
+---
+
+### Intent Recognition
+
+| Type | Platform Name | Usage Method | Pricing Model | Notes |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Intent | intent_llm | Interface calls | Based on LLM pricing | Recognizes intent through large models, strong generalization |
+| Intent | function_call | Interface calls | Based on LLM pricing | Completes intent through large model function calling, fast speed, good effect |
+| Intent | nointent | No intent mode | Free | Does not perform intent recognition, directly returns dialogue result |
+
+---
+
+### Rag Retrieval-Augmented Generation
+
+| Type | Platform Name | Usage Method | Pricing Model | Notes |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Rag | ragflow | Interface calls | Charged based on tokens consumed for slicing and word segmentation | Utilizes RagFlow's retrieval-augmented generation feature to provide more accurate dialog responses |
+
+---
+
+## Acknowledgments 🙏
+
+| Logo | Project/Company | Description |
+|:---:|:---:|:---|
+| <img src="../images/logo_bailing.png" width="160"> | [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) | This project is inspired by [Bailing Voice Dialogue Robot](https://github.com/wwbin2017/bailing) and implemented on its basis |
+| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Thanks to [Tenclass](https://www.tenclass.com/) for formulating standard communication protocols, multi-device compatibility solutions, and high-concurrency scenario practice demonstrations for the Xiaozhi ecosystem; providing full-link technical documentation support for this project |
+| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Thanks to [Xuanfeng Technology](https://github.com/Eric0308) for contributing function calling framework, MCP communication protocol, and plugin-based calling mechanism implementation code. Through standardized instruction scheduling system and dynamic expansion capabilities, it significantly improves the interaction efficiency and functional extensibility of frontend devices (IoT) |
+| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Thanks to [huangjunsen](https://github.com/huangjunsen0406) for contributing the `Smart Control Console Mobile` module, which enables efficient control and real-time interaction across mobile devices, significantly enhancing the system's operational convenience and management efficiency in mobile scenarios. |
+| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Thanks to [Huiyuan Design](http://ui.kwd988.net/) for providing professional visual solutions for this project, using their design practical experience serving over a thousand enterprises to empower this project's product user experience |
+| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Thanks to [Xi'an Qinren Information Technology](https://www.029app.com/) for deepening this project's visual system, ensuring consistency and extensibility of overall design style in multi-scenario applications |
+| <img src="../images/logo_contributors.png" width="160"> | [Code Contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Thanks to [all code contributors](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), your efforts have made the project more robust and powerful. |
+
+
+<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" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />
+ </picture>
+</a>

docs/readme/README_pt_BR.md

@@ -0,0 +1,376 @@
+[![Banners](../images/banner1.png)](https://github.com/xinnan-tech/xiaozhi-esp32-server)
+
+<h1 align="center">Serviço Backend Xiaozhi xiaozhi-esp32-server</h1>
+
+<p align="center">
+Este projeto é baseado na teoria e tecnologia de inteligência simbiótica humano-máquina para desenvolver sistemas inteligentes de hardware e software para terminais<br/>fornecendo serviços de backend para o projeto de hardware inteligente de código aberto
+<a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a><br/>
+Implementado usando Python, Java e Vue de acordo com o <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">Protocolo de Comunicação Xiaozhi</a><br/>
+Suporte ao protocolo MQTT+UDP, protocolo WebSocket, ponto de acesso MCP, reconhecimento de impressão vocal e base de conhecimento
+</p>
+
+<p align="center">
+<a href="../FAQ.md">Perguntas Frequentes</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Reportar Problemas</a>
+· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Documentação de Implantação</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Notas de Lançamento</a>
+</p>
+
+<p align="center">
+  <a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
+  <a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DFE0E5"></a>
+  <a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
+  <a href="./README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DBEDFA"></a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
+    <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
+    <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server">
+    <img alt="stars" src="https://img.shields.io/github/stars/xinnan-tech/xiaozhi-esp32-server?color=ffcb47&labelColor=black" />
+  </a>
+</p>
+
+<p align="center">
+Liderado pela Equipe do Professor Siyuan Liu (Universidade de Tecnologia do Sul da China)
+</br>
+刘思源教授团队主导研发（华南理工大学）
+</br>
+<img src="../images/hnlg.jpg" alt="Universidade de Tecnologia do Sul da China (华南理工大学)" width="50%">
+</p>
+
+---
+
+## Público-Alvo 👥
+
+Este projeto requer dispositivos de hardware ESP32 para funcionar. Se você adquiriu hardware relacionado ao ESP32, conectou-se com sucesso ao serviço backend implantado pelo Brother Xia e deseja construir seu próprio serviço backend `xiaozhi-esp32` de forma independente, então este projeto é perfeito para você.
+
+Quer ver os efeitos de uso? Clique nos vídeos abaixo 🎥
+
+<table>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
+         <picture>
+           <img alt="Experiência de velocidade de resposta" src="../images/demo9.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
+         <picture>
+           <img alt="Segredo da otimização de velocidade" src="../images/demo6.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
+         <picture>
+           <img alt="Cenário médico complexo" src="../images/demo1.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
+         <picture>
+           <img alt="Envio de comandos MQTT" src="../images/demo4.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
+         <picture>
+           <img alt="Reconhecimento de impressão vocal" src="../images/demo14.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
+         <picture>
+           <img alt="Controle de interruptores de eletrodomésticos" src="../images/demo5.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
+         <picture>
+           <img alt="Ponto de acesso MCP" src="../images/demo13.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
+         <picture>
+           <img alt="Tarefas com múltiplos comandos" src="../images/demo11.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
+         <picture>
+           <img alt="Reproduzir música" src="../images/demo7.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
+         <picture>
+           <img alt="Plugin de clima" src="../images/demo8.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
+         <picture>
+           <img alt="Interrupção em tempo real" src="../images/demo10.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
+         <picture>
+           <img alt="Fotografar e identificar objetos" src="../images/demo12.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
+         <picture>
+           <img alt="Timbre de voz personalizado" src="../images/demo2.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+         <picture>
+           <img alt="Comunicação em cantonês" src="../images/demo3.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
+         <picture>
+           <img alt="Transmissão de notícias" src="../images/demo0.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+</table>
+
+---
+
+## Avisos ⚠️
+
+1. Este projeto é um software de código aberto. Este software não possui parceria comercial com nenhum provedor de serviços de API de terceiros (incluindo, mas não se limitando a reconhecimento de fala, modelos de linguagem, síntese de voz e outras plataformas) com os quais se conecta, e não fornece nenhuma forma de garantia quanto à qualidade de serviço ou segurança financeira desses provedores. Recomenda-se que os usuários priorizem provedores de serviço com licenças comerciais relevantes e leiam cuidadosamente seus termos de serviço e políticas de privacidade. Este software não armazena nenhuma chave de conta, não participa de fluxos de fundos e não assume o risco de perda de fundos recarregados.
+
+2. A funcionalidade deste projeto não está completa e não passou por avaliação de segurança de rede. Por favor, não o utilize em ambientes de produção. Se você implantar este projeto para fins de aprendizado em um ambiente de rede pública, certifique-se de que as medidas de proteção necessárias estejam em vigor.
+
+---
+
+## Documentação de Implantação
+
+![Banners](../images/banner2.png)
+
+Este projeto oferece dois métodos de implantação. Por favor, escolha de acordo com suas necessidades específicas:
+
+#### 🚀 Seleção do Método de Implantação
+| Método de Implantação | Funcionalidades | Cenários Aplicáveis | Documentação de Implantação | Requisitos de Configuração | Tutoriais em Vídeo |
+|---------|------|---------|---------|---------|---------|
+| **Instalação Simplificada** | Diálogo inteligente, gerenciamento de agente único | Ambientes de baixa configuração, dados armazenados em arquivos de configuração, sem necessidade de banco de dados | [①Versão Docker](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Implantação via Código-Fonte](../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)| 2 núcleos 4GB se usar `FunASR`, 2 núcleos 2GB se todas APIs | - |
+| **Instalação de Módulo Completo** | Diálogo inteligente, gerenciamento multiusuário, gerenciamento de múltiplos agentes, operação de interface do console inteligente | Experiência com funcionalidade completa, dados armazenados em banco de dados |[①Versão Docker](../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) / [②Implantação via Código-Fonte](../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) / [③Tutorial de Atualização Automática via Código-Fonte](../dev-ops-integration.md) | 4 núcleos 8GB se usar `FunASR`, 2 núcleos 4GB se todas APIs| [Tutorial em Vídeo de Inicialização via Código-Fonte Local](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
+
+Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](../FAQ.md)
+
+> 💡 Nota: Abaixo está uma plataforma de teste implantada com o código mais recente. Você pode gravar e testar se necessário. Usuários simultâneos: 6, os dados serão limpos diariamente.
+
+```
+Endereço do Console de Controle Inteligente: https://2662r3426b.vicp.fun
+Endereço do Console de Controle Inteligente (H5): https://2662r3426b.vicp.fun/h5/index.html
+
+Ferramenta de Teste de Serviço: https://2662r3426b.vicp.fun/test/
+Endereço da Interface OTA: https://2662r3426b.vicp.fun/xiaozhi/ota/
+Endereço da Interface WebSocket: wss://2662r3426b.vicp.fun/xiaozhi/v1/
+```
+
+#### 🚩 Descrição e Recomendações de Configuração
+> [!Note]
+> Este projeto oferece dois esquemas de configuração:
+>
+> 1. `Configurações Gratuitas Nível Básico`: Adequado para uso pessoal e doméstico, todos os componentes utilizam soluções gratuitas, sem necessidade de pagamento adicional.
+>
+> 2. `Configuração de Streaming`: Adequado para demonstrações, treinamentos, cenários com mais de 2 usuários simultâneos, etc. Utiliza tecnologia de processamento em streaming para velocidade de resposta mais rápida e melhor experiência.
+>
+> A partir da versão `0.5.2`, o projeto suporta configuração de streaming. Em comparação com versões anteriores, a velocidade de resposta é melhorada em aproximadamente `2,5 segundos`, melhorando significativamente a experiência do usuário.
+
+| Nome do Módulo | Configurações Gratuitas Nível Básico | Configuração de Streaming |
+|:---:|:---:|:---:|
+| ASR(Reconhecimento de Fala) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
+| LLM(Modelo de Linguagem) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
+| VLLM(Modelo de Visão) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
+| TTS(Síntese de Voz) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| Intent(Reconhecimento de Intenção) | function_call(Chamada de função) | function_call(Chamada de função) |
+| Memory(Função de Memória) | mem_local_short(Memória local de curto prazo) | mem_local_short(Memória local de curto prazo) |
+
+Se você está preocupado com o tempo de resposta de cada componente, consulte o [Relatório de Teste de Desempenho dos Componentes Xiaozhi](https://github.com/xinnan-tech/xiaozhi-performance-research), e teste em seu próprio ambiente seguindo os métodos de teste do relatório.
+
+#### 🔧 Ferramentas de Teste
+Este projeto fornece as seguintes ferramentas de teste para ajudá-lo a verificar o sistema e escolher modelos adequados:
+
+| Nome da Ferramenta | Localização | Método de Uso | Descrição da Função |
+|:---:|:---|:---:|:---:|
+| Ferramenta de Teste de Interação por Áudio | main》digital-human》index.html | Execute `python start.py` em `main/digital-human` e depois abra `http://127.0.0.1:8006/index.html` | Testa as funções de reprodução e recepção de áudio, verifica se o processamento de áudio no lado Python está normal |
+| Ferramenta de Teste de Resposta de Modelo | main》xiaozhi-server》performance_tester.py | Execute `python performance_tester.py` | Testa a velocidade de resposta dos três módulos principais: ASR(reconhecimento de fala), LLM(modelo de linguagem), VLLM(modelo de visão), TTS(síntese de voz) |
+
+> 💡 Nota: Ao testar a velocidade dos modelos, apenas os modelos com chaves configuradas serão testados.
+
+---
+## Lista de Funcionalidades ✨
+### Implementado ✅
+![请参考-全模块安装架构图](../images/deploy2.png)
+| Módulo de Funcionalidade | Descrição |
+|:---:|:---|
+| Arquitetura Principal | Baseado em [gateway MQTT+UDP](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), servidores WebSocket e HTTP, fornece sistema completo de gerenciamento de console e autenticação |
+| Interação por Voz | Suporta ASR em streaming (reconhecimento de fala), TTS em streaming (síntese de voz), VAD (detecção de atividade vocal), suporta reconhecimento multilíngue e processamento de voz |
+| Reconhecimento de Impressão Vocal | Suporta registro, gerenciamento e reconhecimento de impressão vocal de múltiplos usuários, processa em paralelo com o ASR, reconhecimento de identidade do falante em tempo real e repassa ao LLM para respostas personalizadas |
+| Diálogo Inteligente | Suporta múltiplos LLM (modelos de linguagem de grande porte), implementa diálogo inteligente |
+| Percepção Visual | Suporta múltiplos VLLM (modelos de visão de grande porte), implementa interação multimodal |
+| Reconhecimento de Intenção | Suporta reconhecimento de intenção por LLM, Function Call (chamada de função), fornece mecanismo de processamento de intenção baseado em plugins |
+| Sistema de Memória | Suporta memória local de curto prazo, memória via interface mem0ai, memória inteligente PowerMem, com funcionalidade de resumo de memória |
+| Base de Conhecimento | Suporta base de conhecimento RAGFlow, permitindo que o LLM julgue se deve acionar a base de conhecimento após receber a pergunta do usuário, e então responda à pergunta |
+| Chamada de Ferramentas | Suporta protocolo IOT do cliente, protocolo MCP do cliente, protocolo MCP do servidor, protocolo de endpoint MCP, funções de ferramentas personalizadas |
+| Envio de Comandos | Suporta envio de comandos MCP para dispositivos ESP32 via protocolo MQTT a partir do Console Inteligente |
+| Backend de Gerenciamento | Fornece interface de gerenciamento Web, suporta gerenciamento de usuários, configuração do sistema e gerenciamento de dispositivos; Suporta exibição em Chinês Simplificado, Chinês Tradicional e Inglês |
+| Ferramentas de Teste | Fornece ferramentas de teste de desempenho, ferramentas de teste de modelo de visão e ferramentas de teste de interação por áudio |
+| Suporte à Implantação | Suporta implantação via Docker e implantação local, fornece gerenciamento completo de arquivos de configuração |
+| Sistema de Plugins | Suporta extensões de plugins funcionais, desenvolvimento de plugins personalizados e carregamento dinâmico de plugins |
+
+### Em Desenvolvimento 🚧
+
+Para conhecer o progresso específico do plano de desenvolvimento, [clique aqui](https://github.com/users/xinnan-tech/projects/3). Perguntas frequentes e tutoriais relacionados podem ser consultados [neste link](../FAQ.md)
+
+Se você é um desenvolvedor de software, aqui está uma [Carta Aberta aos Desenvolvedores](../contributor_open_letter.md). Seja bem-vindo a participar!
+
+---
+
+## Ecossistema do Produto 👬
+Xiaozhi é um ecossistema. Ao utilizar este produto, você também pode conferir outros [projetos excelentes](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) neste ecossistema
+
+---
+
+## Lista de Plataformas/Componentes Suportados 📋
+### LLM Modelos de Linguagem
+
+| Método de Uso | Plataformas Suportadas | Plataformas Gratuitas |
+|:---:|:---:|:---:|
+| Chamadas via interface OpenAI | Alibaba Bailian, Volcano Engine, DeepSeek, Zhipu, Gemini, iFLYTEK | Zhipu, Gemini |
+| Chamadas via interface Ollama | Ollama | - |
+| Chamadas via interface Dify | Dify | - |
+| Chamadas via interface FastGPT | FastGPT | - |
+| Chamadas via interface Coze | Coze | - |
+| Chamadas via interface Xinference | Xinference | - |
+| Chamadas via interface HomeAssistant | HomeAssistant | - |
+
+Na verdade, qualquer LLM que suporte chamadas via interface openai pode ser integrado e utilizado.
+
+---
+
+### VLLM Modelos de Visão
+
+| Método de Uso | Plataformas Suportadas | Plataformas Gratuitas |
+|:---:|:---:|:---:|
+| Chamadas via interface OpenAI | Alibaba Bailian, Zhipu ChatGLMVLLM | Zhipu ChatGLMVLLM |
+
+Na verdade, qualquer VLLM que suporte chamadas via interface OpenAI pode ser integrado e utilizado.
+
+---
+
+### TTS Síntese de Voz
+
+| Método de Uso | Plataformas Suportadas | Plataformas Gratuitas |
+|:---:|:---:|:---:|
+| Chamadas via interface | EdgeTTS, iFLYTEK, Volcano Engine, Tencent Cloud, Alibaba Cloud e Bailian, CosyVoiceSiliconflow, TTS302AI, CozeCnTTS, GizwitsTTS, ACGNTTS, OpenAITTS, Lingxi Streaming TTS, MinimaxTTS | Lingxi Streaming TTS, EdgeTTS, CosyVoiceSiliconflow(parcial) |
+| Serviços locais | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, Index-TTS, PaddleSpeech | Index-TTS, PaddleSpeech, FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3 |
+
+---
+
+### VAD Detecção de Atividade Vocal
+
+| Tipo | Nome da Plataforma | Método de Uso | Modelo de Preço | Observações |
+|:---:|:---------:|:----:|:----:|:--:|
+| VAD | SileroVAD | Uso local | Gratuito | |
+
+---
+
+### ASR Reconhecimento de Fala
+
+| Método de Uso | Plataformas Suportadas | Plataformas Gratuitas |
+|:---:|:---:|:---:|
+| Uso local | FunASR, SherpaASR | FunASR, SherpaASR |
+| Chamadas via interface | FunASRServer, Volcano Engine, iFLYTEK, Tencent Cloud, Alibaba Cloud, Baidu Cloud, OpenAI ASR | FunASRServer |
+
+---
+
+### Reconhecimento de Impressão Vocal
+
+| Método de Uso | Plataformas Suportadas | Plataformas Gratuitas |
+|:---:|:---:|:---:|
+| Uso local | 3D-Speaker | 3D-Speaker |
+
+---
+
+### Armazenamento de Memória
+
+| Tipo | Nome da Plataforma | Método de Uso | Modelo de Preço | Observações |
+|:------:|:---------------:|:----:|:---------:|:--:|
+| Memória | mem0ai | Chamadas via interface | Cota de 1000 vezes/mês | |
+| Memória | [powermem](../powermem-integration.md) | Resumo local | Depende do LLM e BD | OceanBase de código aberto, suporta busca inteligente |
+| Memória | mem_local_short | Resumo local | Gratuito | |
+| Memória | nomem | Modo sem memória | Gratuito | |
+
+---
+
+### Reconhecimento de Intenção
+
+| Tipo | Nome da Plataforma | Método de Uso | Modelo de Preço | Observações |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Intenção | intent_llm | Chamadas via interface | Baseado no preço do LLM | Reconhece intenção através de modelos de linguagem, forte generalização |
+| Intenção | function_call | Chamadas via interface | Baseado no preço do LLM | Completa a intenção através de chamada de função do modelo de linguagem, velocidade rápida, bom resultado |
+| Intenção | nointent | Modo sem intenção | Gratuito | Não realiza reconhecimento de intenção, retorna diretamente o resultado do diálogo |
+
+---
+
+### RAG Geração Aumentada por Recuperação
+
+| Tipo | Nome da Plataforma | Método de Uso | Modelo de Preço | Observações |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| RAG | ragflow | Chamadas via interface | Cobrado com base nos tokens consumidos para fatiamento e segmentação de palavras | Utiliza o recurso de geração aumentada por recuperação do RagFlow para fornecer respostas de diálogo mais precisas |
+
+---
+
+## Agradecimentos 🙏
+
+| Logo | Projeto/Empresa | Descrição |
+|:---:|:---:|:---|
+| <img src="../images/logo_bailing.png" width="160"> | [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) | Este projeto foi inspirado pelo [Robô de Diálogo por Voz Bailing](https://github.com/wwbin2017/bailing) e implementado com base nele |
+| <img src="../images/logo_tenclass.png" width="160"> | [Tenclass](https://www.tenclass.com/) | Agradecimentos à [Tenclass](https://www.tenclass.com/) por formular protocolos de comunicação padrão, soluções de compatibilidade multidispositivo e demonstrações práticas de cenários de alta concorrência para o ecossistema Xiaozhi; fornecendo suporte completo de documentação técnica para este projeto |
+| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology (玄凤科技)](https://github.com/Eric0308) | Agradecimentos à [Xuanfeng Technology](https://github.com/Eric0308) por contribuir com o framework de chamada de função, protocolo de comunicação MCP e implementação do mecanismo de chamada baseado em plugins. Através de um sistema padronizado de agendamento de instruções e capacidades de expansão dinâmica, melhora significativamente a eficiência de interação e extensibilidade funcional dos dispositivos de frontend (IoT) |
+| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Agradecimentos a [huangjunsen](https://github.com/huangjunsen0406) por contribuir com o módulo `Console de Controle Inteligente Mobile`, que permite controle eficiente e interação em tempo real em dispositivos móveis, melhorando significativamente a conveniência operacional e a eficiência de gerenciamento do sistema em cenários móveis. |
+| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design (汇远设计)](http://ui.kwd988.net/) | Agradecimentos à [Huiyuan Design](http://ui.kwd988.net/) por fornecer soluções visuais profissionais para este projeto, utilizando sua experiência prática de design atendendo mais de mil empresas para potencializar a experiência do usuário deste produto |
+| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology (西安勤人信息科技)](https://www.029app.com/) | Agradecimentos à [Xi'an Qinren Information Technology](https://www.029app.com/) por aprofundar o sistema visual deste projeto, garantindo consistência e extensibilidade do estilo de design geral em aplicações de múltiplos cenários |
+| <img src="../images/logo_contributors.png" width="160"> | [Contribuidores de Código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Agradecimentos a [todos os contribuidores de código](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), seus esforços tornaram o projeto mais robusto e poderoso. |
+
+
+<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" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />
+ </picture>
+</a>

docs/readme/README_vi.md

@@ -0,0 +1,377 @@
+[![Banners](../images/banner1.png)](https://github.com/xinnan-tech/xiaozhi-esp32-server)
+
+<h1 align="center">Dịch vụ Backend Xiaozhi xiaozhi-esp32-server</h1>
+
+<p align="center">
+Dự án này dựa trên lý thuyết và công nghệ trí tuệ cộng sinh người-máy để phát triển hệ thống phần mềm và phần cứng thiết bị đầu cuối thông minh<br/>Cung cấp dịch vụ backend cho dự án phần cứng thông minh mã nguồn mở
+<a href="https://github.com/78/xiaozhi-esp32">xiaozhi-esp32</a><br/>
+Được triển khai bằng Python, Java, Vue theo <a href="https://ccnphfhqs21z.feishu.cn/wiki/M0XiwldO9iJwHikpXD5cEx71nKh">giao thức truyền thông Xiaozhi</a><br/>
+Hỗ trợ giao thức MQTT+UDP, giao thức Websocket, điểm truy cập MCP, nhận dạng giọng nói và kho tri thức
+</p>
+
+<p align="center">
+<a href="../FAQ.md">Câu hỏi thường gặp</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/issues">Báo cáo vấn đề</a>
+· <a href="../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3">Tài liệu triển khai</a>
+· <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">Nhật ký cập nhật</a>
+</p>
+
+<p align="center">
+  <a href="../../README.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_en.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
+  <a href="./README_vi.md"><img alt="Tiếng Việt" src="https://img.shields.io/badge/Tiếng Việt-DBEDFA"></a>
+  <a href="./README_de.md"><img alt="Deutsch" src="https://img.shields.io/badge/Deutsch-DFE0E5"></a>
+  <a href="./README_pt_BR.md"><img alt="Português (Brasil)" src="https://img.shields.io/badge/Português (Brasil)-DFE0E5"></a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/releases">
+    <img alt="GitHub Contributors" src="https://img.shields.io/github/v/release/xinnan-tech/xiaozhi-esp32-server?logo=docker" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/LICENSE">
+    <img alt="GitHub pull requests" src="https://img.shields.io/badge/license-MIT-white?labelColor=black" />
+  </a>
+  <a href="https://github.com/xinnan-tech/xiaozhi-esp32-server">
+    <img alt="stars" src="https://img.shields.io/github/stars/xinnan-tech/xiaozhi-esp32-server?color=ffcb47&labelColor=black" />
+  </a>
+</p>
+
+<p align="center">
+Spearheaded by Professor Siyuan Liu's Team (South China University of Technology)
+</br>
+Được dẫn dắt bởi nhóm Giáo sư Lưu Tư Nguyên (Đại học Bách khoa Nam Trung Quốc)
+</br>
+<img src="../images/hnlg.jpg" alt="华南理工大学" width="50%">
+</p>
+
+---
+
+## Người dùng phù hợp 👥
+
+Dự án này cần được sử dụng cùng với thiết bị phần cứng ESP32. Nếu bạn đã mua phần cứng liên quan đến ESP32, đã thành công kết nối với dịch vụ backend do anh Xia triển khai, và muốn xây dựng dịch vụ backend `xiaozhi-esp32` riêng của mình, thì dự án này rất phù hợp với bạn.
+
+Muốn xem hiệu quả sử dụng? Hãy xem video 🎥
+
+<table>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1FMFyejExX" target="_blank">
+         <picture>
+           <img alt="响应速度感受" src="../images/demo9.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1vchQzaEse" target="_blank">
+         <picture>
+           <img alt="速度优化秘诀" src="../images/demo6.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1C1tCzUEZh" target="_blank">
+         <picture>
+           <img alt="复杂医疗场景" src="../images/demo1.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1zUW5zJEkq" target="_blank">
+         <picture>
+           <img alt="MQTT指令下发" src="../images/demo4.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Exu3zqEDe" target="_blank">
+         <picture>
+           <img alt="声纹识别" src="../images/demo14.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1pNXWYGEx1" target="_blank">
+         <picture>
+           <img alt="控制家电开关" src="../images/demo5.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1ZQKUzYExM" target="_blank">
+         <picture>
+           <img alt="MCP接入点" src="../images/demo13.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1TJ7WzzEo6" target="_blank">
+         <picture>
+           <img alt="多指令任务" src="../images/demo11.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1VC96Y5EMH" target="_blank">
+         <picture>
+           <img alt="播放音乐" src="../images/demo7.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1Z8XuYZEAS" target="_blank">
+         <picture>
+           <img alt="天气插件" src="../images/demo8.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <a href="https://www.bilibili.com/video/BV12J7WzBEaH" target="_blank">
+         <picture>
+           <img alt="实时打断" src="../images/demo10.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+      <a href="https://www.bilibili.com/video/BV1Co76z7EvK" target="_blank">
+         <picture>
+           <img alt="拍照识物品" src="../images/demo12.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV1CDKWemEU6" target="_blank">
+         <picture>
+           <img alt="自定义音色" src="../images/demo2.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV12yA2egEaC" target="_blank">
+         <picture>
+           <img alt="使用粤语交流" src="../images/demo3.png" />
+         </picture>
+        </a>
+    </td>
+    <td>
+        <a href="https://www.bilibili.com/video/BV17LXWYvENb" target="_blank">
+         <picture>
+           <img alt="播报新闻" src="../images/demo0.png" />
+         </picture>
+        </a>
+    </td>
+  </tr>
+</table>
+
+---
+
+## Cảnh báo ⚠️
+
+1. Dự án này là phần mềm mã nguồn mở, phần mềm này không có quan hệ hợp tác thương mại với bất kỳ nhà cung cấp dịch vụ API bên thứ ba nào (bao gồm nhưng không giới hạn ở các nền tảng nhận dạng giọng nói, mô hình lớn, tổng hợp giọng nói, v.v.), và không đảm bảo chất lượng dịch vụ cũng như an toàn tài chính của họ.
+Khuyến nghị người dùng ưu tiên lựa chọn nhà cung cấp dịch vụ có giấy phép kinh doanh liên quan và đọc kỹ thỏa thuận dịch vụ và chính sách bảo mật của họ. Phần mềm này không lưu trữ bất kỳ khóa tài khoản nào, không tham gia vào luồng tiền và không chịu rủi ro mất tiền nạp.
+
+2. Chức năng của dự án này chưa hoàn thiện và chưa qua đánh giá bảo mật mạng, vui lòng không sử dụng trong môi trường sản xuất. Nếu bạn triển khai dự án này trong môi trường mạng công cộng để học tập, vui lòng thực hiện các biện pháp bảo vệ cần thiết.
+
+---
+
+## Tài liệu triển khai
+
+![Banners](../images/banner2.png)
+
+Dự án này cung cấp hai phương pháp triển khai, vui lòng chọn theo nhu cầu cụ thể của bạn:
+
+#### 🚀 Lựa chọn phương pháp triển khai
+| Phương pháp triển khai | Đặc điểm | Tình huống áp dụng | Tài liệu triển khai | Yêu cầu cấu hình | Video hướng dẫn |
+|---------|------|---------|---------|---------|---------|
+| **Cài đặt tối giản** | Đối thoại thông minh, quản lý đơn tác nhân | Môi trường cấu hình thấp, dữ liệu lưu trong tệp cấu hình, không cần cơ sở dữ liệu | [①Phiên bản Docker](../Deployment.md#%E6%96%B9%E5%BC%8F%E4%B8%80docker%E5%8F%AA%E8%BF%90%E8%A1%8Cserver) / [②Triển khai mã nguồn](../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)| 2 nhân 4GB nếu dùng `FunASR`, 2 nhân 2GB nếu toàn API | - |
+| **Cài đặt toàn bộ module** | Đối thoại thông minh, quản lý đa người dùng, quản lý đa tác nhân, bảng điều khiển thông minh | Trải nghiệm đầy đủ tính năng, dữ liệu lưu trong cơ sở dữ liệu |[①Phiên bản Docker](../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) / [②Triển khai mã nguồn](../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) / [③Hướng dẫn tự động cập nhật triển khai mã nguồn](../dev-ops-integration.md) | 4 nhân 8GB nếu dùng `FunASR`, 2 nhân 4GB nếu toàn API| [Video hướng dẫn khởi động mã nguồn cục bộ](https://www.bilibili.com/video/BV1wBJhz4Ewe) |
+
+Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](../FAQ.md)
+
+> 💡 Gợi ý: Dưới đây là nền tảng thử nghiệm được triển khai theo mã mới nhất, có thể flash để thử nghiệm nếu cần, đồng thời là 6, dữ liệu sẽ được xóa mỗi ngày,
+
+```
+Địa chỉ bảng điều khiển thông minh: https://2662r3426b.vicp.fun
+Bảng điều khiển thông minh (phiên bản h5): https://2662r3426b.vicp.fun/h5/index.html
+
+Công cụ kiểm tra dịch vụ: https://2662r3426b.vicp.fun/test/
+Địa chỉ giao diện OTA: https://2662r3426b.vicp.fun/xiaozhi/ota/
+Địa chỉ giao diện Websocket: wss://2662r3426b.vicp.fun/xiaozhi/v1/
+```
+
+#### 🚩 Mô tả và khuyến nghị cấu hình
+> [!Note]
+> Dự án này cung cấp hai phương án cấu hình:
+>
+> 1. Cấu hình `Miễn phí hoàn toàn cho người mới`: Phù hợp với sử dụng gia đình cá nhân, tất cả các thành phần đều sử dụng phương án miễn phí, không cần thanh toán thêm.
+>
+> 2. `Cấu hình streaming`: Phù hợp với demo, đào tạo, hơn 2 đồng thời, v.v., sử dụng công nghệ xử lý streaming, tốc độ phản hồi nhanh hơn, trải nghiệm tốt hơn.
+>
+> Từ phiên bản `0.5.2`, dự án hỗ trợ cấu hình streaming, so với phiên bản đầu, tốc độ phản hồi cải thiện khoảng `2.5 giây`, cải thiện đáng kể trải nghiệm người dùng.
+
+| Tên module | Cài đặt miễn phí cho người mới | Cấu hình streaming |
+|:---:|:---:|:---:|
+| ASR(Nhận dạng giọng nói) | FunASR(Local) | 👍XunfeiStreamASR(Xunfei Streaming) |
+| LLM(Mô hình lớn) | glm-4-flash(Zhipu) | 👍qwen-flash(Alibaba Bailian) |
+| VLLM(Mô hình lớn thị giác) | glm-4v-flash(Zhipu) | 👍qwen3.5-flash(Alibaba Bailian) |
+| TTS(Tổng hợp giọng nói) | EdgeTTS(Microsoft) | 👍HuoshanDoubleStreamTTS(Volcano Streaming) |
+| Intent(Nhận dạng ý định) | function_call(Gọi hàm) | function_call(Gọi hàm) |
+| Memory(Chức năng bộ nhớ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) | mem_local_short(Bộ nhớ ngắn hạn cục bộ) |
+
+Nếu bạn quan tâm đến thời gian của từng thành phần, vui lòng xem [Báo cáo kiểm tra hiệu suất các thành phần Xiaozhi](https://github.com/xinnan-tech/xiaozhi-performance-research), có thể kiểm tra thực tế trong môi trường của bạn theo phương pháp kiểm tra trong báo cáo.
+
+#### 🔧 Công cụ kiểm tra
+Dự án này cung cấp các công cụ kiểm tra sau để giúp bạn xác minh hệ thống và chọn mô hình phù hợp:
+
+| Tên công cụ | Vị trí | Phương pháp sử dụng | Mô tả chức năng |
+|:---:|:---|:---:|:---:|
+| Công cụ kiểm tra tương tác âm thanh | main》digital-human》index.html | Chạy `python start.py` trong `main/digital-human`, sau đó mở `http://127.0.0.1:8006/index.html` | Kiểm tra chức năng phát và nhận âm thanh, xác minh xử lý âm thanh phía Python có bình thường không |
+| Công cụ kiểm tra phản hồi mô hình | main》xiaozhi-server》performance_tester.py | Thực hiện `python performance_tester.py` | Kiểm tra tốc độ phản hồi của ba module cốt lõi ASR(Nhận dạng giọng nói), LLM(Mô hình lớn), VLLM(Mô hình thị giác), TTS(Tổng hợp giọng nói) |
+
+> 💡 Gợi ý: Khi kiểm tra tốc độ mô hình, chỉ kiểm tra các mô hình đã cấu hình khóa.
+
+---
+## Danh sách tính năng ✨
+### Đã thực hiện ✅
+![请参考-全模块安装架构图](../images/deploy2.png)
+| Module chức năng | Mô tả |
+|:---:|:---|
+| Kiến trúc cốt lõi | Dựa trên [cổng MQTT+UDP](https://github.com/xinnan-tech/xiaozhi-esp32-server/blob/main/docs/mqtt-gateway-integration.md), WebSocket, máy chủ HTTP, cung cấp hệ thống quản lý bảng điều khiển và xác thực hoàn chỉnh |
+| Tương tác giọng nói | Hỗ trợ ASR streaming(Nhận dạng giọng nói), TTS streaming(Tổng hợp giọng nói), VAD(Phát hiện hoạt động giọng nói), hỗ trợ nhận dạng đa ngôn ngữ và xử lý giọng nói |
+| Nhận dạng vân giọng | Hỗ trợ đăng ký, quản lý và nhận dạng vân giọng đa người dùng, xử lý song song với ASR, nhận dạng danh tính người nói theo thời gian thực và truyền cho LLM để phản hồi cá nhân hóa |
+| Đối thoại thông minh | Hỗ trợ nhiều LLM(Mô hình ngôn ngữ lớn), thực hiện đối thoại thông minh |
+| Cảm nhận thị giác | Hỗ trợ nhiều VLLM(Mô hình lớn thị giác), thực hiện tương tác đa phương thức |
+| Nhận dạng ý định | Hỗ trợ nhận dạng ý định mô hình lớn gắn ngoài, gọi hàm tự chủ mô hình lớn, cung cấp cơ chế xử lý ý định dạng plugin |
+| Hệ thống bộ nhớ | Hỗ trợ bộ nhớ ngắn hạn cục bộ, bộ nhớ giao diện mem0ai, bộ nhớ thông minh PowerMem, có chức năng tóm tắt bộ nhớ |
+| Kho tri thức | Hỗ trợ kho tri thức RAGFlow, cho phép mô hình lớn đánh giá cần gọi kho tri thức trước khi trả lời |
+| Gọi công cụ | Hỗ trợ giao thức IOT phía client, giao thức MCP phía client, giao thức MCP phía server, giao thức điểm truy cập MCP, hàm công cụ tùy chỉnh |
+| Gửi lệnh | Dựa vào giao thức MQTT, hỗ trợ gửi lệnh MCP từ bảng điều khiển thông minh xuống thiết bị ESP32 |
+| Backend quản lý | Cung cấp giao diện quản lý Web, hỗ trợ quản lý người dùng, cấu hình hệ thống và quản lý thiết bị; giao diện hỗ trợ hiển thị tiếng Trung giản thể, tiếng Trung phồn thể, tiếng Anh |
+| Công cụ kiểm tra | Cung cấp công cụ kiểm tra hiệu suất, công cụ kiểm tra mô hình thị giác và công cụ kiểm tra tương tác âm thanh |
+| Hỗ trợ triển khai | Hỗ trợ triển khai Docker và triển khai cục bộ, cung cấp quản lý tệp cấu hình hoàn chỉnh |
+| Hệ thống plugin | Hỗ trợ mở rộng plugin chức năng, phát triển plugin tùy chỉnh và hot loading plugin |
+
+### Đang phát triển 🚧
+
+Muốn hiểu tiến độ kế hoạch phát triển cụ thể, [vui lòng nhấp vào đây](https://github.com/users/xinnan-tech/projects/3). Câu hỏi thường gặp và hướng dẫn liên quan, vui lòng tham khảo [liên kết này](../FAQ.md)
+
+Nếu bạn là một nhà phát triển phần mềm, đây có một [Lá thư mở gửi các nhà phát triển](../contributor_open_letter.md), chào mừng tham gia!
+
+---
+
+## Hệ sinh thái sản phẩm 👬
+Xiaozhi là một hệ sinh thái, khi bạn sử dụng sản phẩm này, bạn cũng có thể xem các [dự án xuất sắc](https://github.com/78/xiaozhi-esp32/blob/main/README_zh.md#%E7%9B%B8%E5%85%B3%E5%BC%80%E6%BA%90%E9%A1%B9%E7%9B%AE) khác trong hệ sinh thái này
+
+---
+
+## Danh sách nền tảng/thành phần được dự án này hỗ trợ 📋
+### LLM Mô hình ngôn ngữ
+
+| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
+|:---:|:---:|:---:|
+| Gọi giao diện openai | Alibaba Bailian, Volcano Engine, DeepSeek, Zhipu, Gemini, iFlytek | Zhipu, Gemini |
+| Gọi giao diện ollama | Ollama | - |
+| Gọi giao diện dify | Dify | - |
+| Gọi giao diện fastgpt | Fastgpt | - |
+| Gọi giao diện coze | Coze | - |
+| Gọi giao diện xinference | Xinference | - |
+| Gọi giao diện homeassistant | HomeAssistant | - |
+
+Trên thực tế, bất kỳ LLM nào hỗ trợ gọi giao diện openai đều có thể truy cập sử dụng.
+
+---
+
+### VLLM Mô hình thị giác
+
+| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
+|:---:|:---:|:---:|
+| Gọi giao diện openai | Alibaba Bailian, Zhipu ChatGLMVLLM | Zhipu ChatGLMVLLM |
+
+Trên thực tế, bất kỳ VLLM nào hỗ trợ gọi giao diện openai đều có thể truy cập sử dụng.
+
+---
+
+### TTS Tổng hợp giọng nói
+
+| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
+|:---:|:---:|:---:|
+| Gọi giao diện | EdgeTTS, iFlytek, Volcano Engine, Tencent Cloud, Alibaba Cloud và Bailian, CosyVoiceSiliconflow, TTS302AI, CozeCnTTS, GizwitsTTS, ACGNTTS, OpenAITTS, Lingxi streaming TTS, MinimaxTTS | Lingxi streaming TTS, EdgeTTS, CosyVoiceSiliconflow(một phần) |
+| Dịch vụ cục bộ | FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3, Index-TTS, PaddleSpeech | Index-TTS, PaddleSpeech, FishSpeech, GPT_SOVITS_V2, GPT_SOVITS_V3 |
+
+---
+
+### VAD Phát hiện hoạt động giọng nói
+
+| Loại  |   Tên nền tảng    | Phương pháp sử dụng | Mô hình thu phí | Ghi chú |
+|:---:|:---------:|:----:|:----:|:--:|
+| VAD | SileroVAD | Sử dụng cục bộ |  Miễn phí  |    |
+
+---
+
+### ASR Nhận dạng giọng nói
+
+| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
+|:---:|:---:|:---:|
+| Sử dụng cục bộ | FunASR, SherpaASR | FunASR, SherpaASR |
+| Gọi giao diện | FunASRServer, Volcano Engine, iFlytek, Tencent Cloud, Alibaba Cloud, Baidu Cloud, OpenAI ASR | FunASRServer |
+
+---
+
+### Voiceprint Nhận dạng vân giọng
+
+| Phương pháp sử dụng | Nền tảng hỗ trợ | Nền tảng miễn phí |
+|:---:|:---:|:---:|
+| Sử dụng cục bộ | 3D-Speaker | 3D-Speaker |
+
+---
+
+### Memory Lưu trữ bộ nhớ
+
+|   Loại   |      Tên nền tảng       | Phương pháp sử dụng |   Mô hình thu phí    | Ghi chú |
+|:------:|:---------------:|:----:|:---------:|:--:|
+| Memory |     mem0ai      | Gọi giao diện | Hạn mức 1000 lần/tháng |    |
+| Memory |     [powermem](../powermem-integration.md)    | Tóm tắt cục bộ | Phụ thuộc vào LLM và DB |  OceanBase mã nguồn mở, hỗ trợ tìm kiếm thông minh  |
+| Memory | mem_local_short | Tóm tắt cục bộ |    Miễn phí     |    |
+| Memory |     nomem       | Chế độ không có bộ nhớ |    Miễn phí     |    |
+
+---
+
+### Intent Nhận dạng ý định
+
+|   Loại   |     Tên nền tảng      | Phương pháp sử dụng |  Mô hình thu phí   |          Ghi chú           |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Intent |  intent_llm   | Gọi giao diện | Thu phí theo LLM |    Nhận dạng ý định qua mô hình lớn, tính tổng quát mạnh     |
+| Intent | function_call | Gọi giao diện | Thu phí theo LLM | Hoàn thành ý định qua gọi hàm mô hình lớn, tốc độ nhanh, hiệu quả tốt |
+| Intent |    nointent   | Chế độ không có ý định |    Miễn phí     |    Không thực hiện nhận dạng ý định, trả về trực tiếp kết quả đối thoại     |
+
+---
+
+### Rag Tăng cường truy xuất thông tin
+
+|   Loại   |     Tên nền tảng      | Phương pháp sử dụng |  Mô hình thu phí   |          Ghi chú           |
+|:------:|:-------------:|:----:|:-------:|:---------------------:|
+| Rag |  ragflow   | Gọi giao diện | Thu phí theo token tiêu tốn của phân đoạn, phân từ |    Sử dụng chức năng tăng cường truy xuất của RagFlow, cung cấp phản hồi đối thoại chính xác hơn     |
+
+---
+
+## Lời cảm ơn 🙏
+
+| Logo | Dự án/Công ty | Mô tả |
+|:---:|:---:|:---|
+| <img src="../images/logo_bailing.png" width="160"> | [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) | Dự án này được lấy cảm hứng từ [Robot đối thoại giọng nói Bailing](https://github.com/wwbin2017/bailing) và được triển khai trên cơ sở đó |
+| <img src="../images/logo_tenclass.png" width="160"> | [Shifang Ronghai](https://www.tenclass.com/) | Cảm ơn [Shifang Ronghai](https://www.tenclass.com/) đã xây dựng giao thức truyền thông tiêu chuẩn, phương án tương thích đa thiết bị và mô phạm thực hành tình huống đồng thời cao cho hệ sinh thái Xiaozhi; cung cấp tài liệu hỗ trợ kỹ thuật toàn diện cho dự án này |
+| <img src="../images/logo_xuanfeng.png" width="160"> | [Xuanfeng Technology](https://github.com/Eric0308) | Cảm ơn [Xuanfeng Technology](https://github.com/Eric0308) đã đóng góp khung gọi hàm, giao thức truyền thông MCP và mã triển khai cơ chế gọi dạng plugin, thông qua hệ thống điều phối lệnh tiêu chuẩn hóa và khả năng mở rộng động, đã cải thiện đáng kể hiệu suất tương tác và khả năng mở rộng chức năng của thiết bị front-end(IoT) |
+| <img src="../images/logo_junsen.png" width="160"> | [huangjunsen](https://github.com/huangjunsen0406) | Cảm ơn [huangjunsen](https://github.com/huangjunsen0406) đã đóng góp module `Bảng điều khiển thông minh di động`, thực hiện điều khiển hiệu quả và tương tác thời gian thực trên thiết bị di động đa nền tảng, cải thiện đáng kể sự tiện lợi vận hành và hiệu quả quản lý của hệ thống trong tình huống di động |
+| <img src="../images/logo_huiyuan.png" width="160"> | [Huiyuan Design](http://ui.kwd988.net/) | Cảm ơn [Huiyuan Design](http://ui.kwd988.net/) đã cung cấp giải pháp thị giác chuyên nghiệp cho dự án này, sử dụng kinh nghiệm thực tế thiết kế phục vụ hơn nghìn doanh nghiệp, trao quyền cho trải nghiệm người dùng sản phẩm của dự án này |
+| <img src="../images/logo_qinren.png" width="160"> | [Xi'an Qinren Information Technology](https://www.029app.com/) | Cảm ơn [Xi'an Qinren Information Technology](https://www.029app.com/) đã làm sâu sắc hệ thống thị giác của dự án này, đảm bảo tính nhất quán và khả năng mở rộng của phong cách thiết kế tổng thể trong ứng dụng đa tình huống |
+| <img src="../images/logo_contributors.png" width="160"> | [Người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors) | Cảm ơn [tất cả người đóng góp mã](https://github.com/xinnan-tech/xiaozhi-esp32-server/graphs/contributors), sự cống hiến của bạn khiến dự án mạnh mẽ và vững chắc hơn. |
+
+
+<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" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=xinnan-tech/xiaozhi-esp32-server&type=Date" />
+ </picture>
+</a>

docs/voiceprint-integration.md

@@ -0,0 +1,235 @@
+# 声纹识别启用指南
+
+本教程包含3个部分
+- 1、如何部署声纹识别这个服务
+- 2、全模块部署时，怎么配置声纹识别接口
+- 3、最简化部署时，怎么配置声纹识别
+
+# 1、如何部署声纹识别这个服务
+
+## 第一步，下载声纹识别项目源码
+
+浏览器打开[声纹识别项目地址](https://github.com/xinnan-tech/voiceprint-api)
+
+打开完，找到页面中一个绿色的按钮，写着`Code`的按钮，点开它，然后你就看到`Download ZIP`的按钮。
+
+点击它，下载本项目源码压缩包。下载到你电脑后，解压它，此时它的名字可能叫`voiceprint-api-main`
+你需要把它重命名成`voiceprint-api`。
+
+## 第二步， 创建数据库和表
+
+声纹识别需要依赖`mysql`数据库。如果你之前已经部署`智控台`，说明你已经安装了`mysql`。你可以共用它。
+
+你可以你试一下在宿主机使用`telnet`命令，看看能不能正常访问`mysql`的`3306`端口。
+```
+telnet 127.0.0.1 3306
+```
+如果能访问到3306端口，请忽略以下的内容，直接进入第三步。
+
+如果不能访问，你需要回忆一下，你的`mysql`是怎么安装的。
+
+如果你的mysql是通过自己使用安装包安装的，说明你的`mysql`做了网络隔离。你可能先解决访问`mysql`的`3306`端口这个问题。
+
+如果你`mysql`是通过本项目的`docker-compose_all.yml`安装的。你需要找一下你当时创建数据库的`docker-compose_all.yml`文件，修改以下的内容
+
+修改前
+```
+  xiaozhi-esp32-server-db:
+    ...
+    networks:
+      - default
+    expose:
+      - "3306:3306"
+```
+
+修改后
+```
+  xiaozhi-esp32-server-db:
+    ...
+    networks:
+      - default
+    ports:
+      - "3306:3306"
+```
+
+注意是将`xiaozhi-esp32-server-db`下面的`expose`改成`ports`。改完后，需要重新启动。以下是重启mysql的命令：
+
+```
+# 进入你docker-compose_all.yml所在的文件夹，例如我的是xiaozhi-server
+cd xiaozhi-server
+docker compose -f docker-compose_all.yml down
+docker compose -f docker-compose.yml up -d
+```
+
+启动完后，在宿主机再使用`telnet`命令，看看能不能正常访问`mysql`的`3306`端口。
+```
+telnet 127.0.0.1 3306
+```
+正常来说这样就可以访问的了。
+
+## 第三步， 创建数据库和表
+如果你的宿主机，能正常访问mysql数据库，那就在mysql上创建一个名字为`voiceprint_db`的数据库和`voiceprints`表。
+
+```
+CREATE DATABASE voiceprint_db CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;
+
+USE voiceprint_db;
+
+CREATE TABLE voiceprints (
+    id INT AUTO_INCREMENT PRIMARY KEY,
+    speaker_id VARCHAR(255) NOT NULL UNIQUE,
+    feature_vector LONGBLOB NOT NULL,
+    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
+    INDEX idx_speaker_id (speaker_id)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+```
+
+## 第四步， 配置数据库连接
+
+进入`voiceprint-api`文件夹，创建名字为`data`的文件夹。
+
+把`voiceprint-api`根目录里的`voiceprint.yaml`，复制到`data`的文件夹，将它重命名为`.voiceprint.yaml`
+
+接下来，你需要重点配置一下`.voiceprint.yaml`里的数据库连接。
+
+```
+mysql:
+  host: "127.0.0.1"
+  port: 3306
+  user: "root"
+  password: "your_password"
+  database: "voiceprint_db"
+```
+
+注意！由于你的声纹识别服务是使用docker部署，`host`需要填写成你`mysql所在机器的局域网ip`。
+
+注意！由于你的声纹识别服务是使用docker部署，`host`需要填写成你`mysql所在机器的局域网ip`。
+
+注意！由于你的声纹识别服务是使用docker部署，`host`需要填写成你`mysql所在机器的局域网ip`。
+
+## 第五步，启动程序
+这个项目是一个很简单的项目，建议使用docker运行。不过如果你不想使用docker运行，你可以参考[这个页面](https://github.com/xinnan-tech/voiceprint-api/blob/main/README.md)使用源码运行。以下是docker运行的方法
+
+```
+# 进入本项目源码根目录
+cd voiceprint-api
+
+# 清除缓存
+docker compose -f docker-compose.yml down
+docker stop voiceprint-api
+docker rm voiceprint-api
+docker rmi ghcr.nju.edu.cn/xinnan-tech/voiceprint-api:latest
+
+# 启动docker容器
+docker compose -f docker-compose.yml up -d
+# 查看日志
+docker logs -f voiceprint-api
+```
+
+此时，日志里会输出类似以下的日志
+```
+250711 INFO-🚀 开始: 生产环境服务启动（Uvicorn），监听地址: 0.0.0.0:8005
+250711 INFO-============================================================
+250711 INFO-声纹接口地址: http://127.0.0.1:8005/voiceprint/health?key=abcd
+250711 INFO-============================================================
+```
+
+请你把声纹接口地址复制出来：
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+由于你是docker部署，切不可直接使用上面的地址！
+
+你先把地址复制出来，放在一个草稿里，你要知道你的电脑的局域网ip是什么，例如我的电脑局域网ip是`192.168.1.25`，那么
+原来我的接口地址
+```
+http://127.0.0.1:8005/voiceprint/health?key=abcd
+
+```
+就要改成
+```
+http://192.168.1.25:8005/voiceprint/health?key=abcd
+```
+
+改好后，请使用浏览器直接访问`声纹接口地址`。当浏览器出现类似这样的代码，说明是成功了。
+```
+{"total_voiceprints":0,"status":"healthy"}
+```
+
+请你保留好修改后的`声纹接口地址`，下一步要用到。
+
+# 2、全模块部署时，怎么配置声纹识别
+
+## 第一步 配置接口
+首先，你要开启声纹识别功能。在智控台，点击顶部`参数字典`，在下拉菜单中，点击`系统功能配置`页面。在页面上勾选`声纹识别`，点击`保存配置`。即可在新建智能体的卡片上看到`声纹识别`按钮。
+
+如果你是全模块部署，使用管理员账号，登录智控台，点击顶部`参数字典`，选择`参数管理`功能。
+
+然后搜索参数`server.voice_print`，此时，它的值应该是`null`值。
+点击修改按钮，把上一步得来的`声纹接口地址`粘贴到`参数值`里。然后保存。
+
+如果能保存成功，说明一切顺利，你可以去智能体查看效果了。如果不成功，说明智控台无法访问声纹识别，很大概率是网络防火墙，或者没有填写正确的局域网ip。
+
+## 第二步 设置智能体记忆模式
+
+进入你的智能体的角色配置里，将记忆设置成`本地短期记忆`，一定要开启`上报文字+语音`。
+
+## 第三步 和你的智能体聊天
+
+将你的设备通电，然后和他用正常的语速和音调聊天。
+
+## 第四步 设置声纹
+
+在智控台，`智能体管理`页面，在智能体的面板里，有一个`声纹识别`按钮，点击它。在底部有一个`新增按钮`。就可以对某个人说的话进行声纹注册。
+在弹出的框里，`描述`这个属性建议填写上，可以是这个人的职业、性格、爱好。方便智能体对说话人进行分析和了解。
+
+## 第三步 和你的智能体聊天
+
+将你的设备通电，问它，你知道我是谁吗？如果他能回答得出，说明声纹识别功能正常。
+
+# 3、最简化部署时，怎么配置声纹识别
+
+## 第一步 配置接口
+打开 `xiaozhi-server/data/.config.yaml` 文件（如果没有需要创建），然后添加/修改以下内容：
+
+```
+# 声纹识别配置
+voiceprint:
+  # 声纹接口地址
+  url: 你的声纹接口地址
+  # 说话人配置：speaker_id,名称,描述
+  speakers:
+    - "test1,张三,张三是一个程序员"
+    - "test2,李四,李四是一个产品经理"
+    - "test3,王五,王五是一个设计师"
+```
+
+把上一步得来的 `声纹接口地址` 粘贴到 `url` 里。然后保存。
+
+`speakers` 参数依据需求添加。这里需要注意这个 `speaker_id` 参数，后面注册声纹会用到。
+
+## 第二步 注册声纹
+如果你已经启动了声纹服务，本地浏览器里访问 `http://localhost:8005/voiceprint/docs` 即可查看 API 文档，这里只说明注册声纹的 API 如何使用。
+
+注册声纹的 API 地址为 `http://localhost:8005/voiceprint/register`，请求方式为 POST。
+
+请求头需要包含 Bearer Token 认证，token 为 `声纹接口地址` 中 `?key=` 后的部分，比如如果我的声纹注册地址为 `http://127.0.0.1:8005/voiceprint/health?key=abcd`，那么我的 token 就是`abcd`。
+
+请求体包含说话人 ID（speaker_id），和 WAV 音频文件（file），请求示例如下：
+
+```
+curl -X POST \
+  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
+  -F "speaker_id=your_speaker_id_here" \
+  -F "file=@/path/to/your/file" \
+  http://localhost:8005/voiceprint/register
+```
+
+ 这里的 `file` 是要注册的说话人说话的音频文件， `speaker_id` 需要和第一步配置接口的 `speaker_id` 保持一致。比如说我需要注册张三的声纹，在 `.config.yaml` 中填的张三的 `speaker_id` 为 `test1`，那么我注册张三声纹的时候，请求体里填的 `speaker_id` 就是 `test1`， `file` 填的就是张三说一段话的音频文件。
+
+ ## 第三步 启动服务
+
+启动小智服务器和声纹服务，即可正常使用。

docs/weather-integration.md

@@ -0,0 +1,64 @@
+# 天气插件使用指南
+
+## 概述
+
+天气插件 `get_weather` 是小智ESP32语音助手的核心功能之一，支持通过语音查询全国各地的天气信息。插件基于和风天气API，提供实时天气和7天天气预报功能。
+
+## API Key 申请指南
+
+### 1. 注册和风天气账号
+
+1. 访问 [和风天气控制台](https://console.qweather.com/)
+2. 注册账号并完成邮箱验证
+3. 登录控制台
+
+### 2. 创建应用获取API Key
+
+1. 进入控制台后，点击右侧["项目管理"](https://console.qweather.com/project?lang=zh) → "创建项目"
+2. 填写项目信息：
+   - **项目名称**：如"小智语音助手"
+3. 点击保存
+4. 项目创建完成后，在该项目中点击"创建凭据"
+5. 填写凭据信息：
+    - **凭据名称**：如"小智语音助手"
+    - **身份认证方式**：选择"API Key"
+6. 点击保存
+7. 在凭据中复制`API Key`，这是第一个关键的配置信息
+
+### 3. 获取API Host
+
+1. 在控制台中点击["设置"](https://console.qweather.com/setting?lang=zh) → "API Host"
+2. 查看分配给你的专属`API Host`地址，这个是第二个关键的配置信息
+
+以上操作，会得到两个重要的配置信息:`API Key`和`API Host`
+
+## 配置方式(任选一种)
+
+### 方式1. 如果你使用了智控台部署（推荐）
+
+1. 登录智控台
+2. 进入"角色配置"页面
+3. 选择要配置的智能体
+4. 点击"编辑功能"按钮
+5. 在右侧参数配置区域找到"天气查询"插件
+6. 勾选"天气查询"
+7. 将复制过来的第一个关键配置`API Key`,填入到`天气插件 API 密钥`里
+8. 将复制过来的第二个关键配置`API Host`,填入到`开发者 API Host`里
+9. 保存配置，再保存智能体配置
+
+### 方式2. 如果你只是单模块xiaozhi-server部署
+
+在 `data/.config.yaml` 中配置：
+
+1. 将复制过来的第一个关键配置`API Key`,填入到`api_key`里
+2. 将复制过来的第二个关键配置`API Host`,填入到`api_host`里
+3. 将你所在的城市填入到`default_location`里，例如`广州`
+
+```yaml
+plugins:
+  get_weather:
+    api_key: "你的和风天气API密钥"
+    api_host: "你的和风天气API主机地址"
+    default_location: "你的默认查询城市"
+```
+

main/README.md

@@ -8,6 +8,8 @@
     *   [3.1. `xiaozhi-server` (核心AI引擎 - Python实现)](#31-xiaozhi-server-核心ai引擎---python实现)
     *   [3.2. `manager-api` (管理后端 - Java Spring Boot实现)](#32-manager-api-管理后端---java-spring-boot实现)
     *   [3.3. `manager-web` (Web管理前端 - Vue.js实现)](#33-manager-web-web管理前端---vuejs实现)
+    *   [3.4. `manager-mobile` (移动管理端 - uni-app+Vue3实现)](#34-manager-mobile-移动管理端---uni-appvue3实现)
+    *   [3.5. `digital-human` (数字人测试模块 - Python+Web实现)](#35-digital-human-数字人测试模块---pythonweb实现)
 4.  [数据流与交互机制](#4-数据流与交互机制)
 5.  [核心功能概要](#5-核心功能概要)
 6.  [部署与配置概述](#6-部署与配置概述)
@@ -58,6 +60,21 @@
     *   （潜在功能）监控系统运行状态、查看日志、进行故障排查等。
     *   与 `manager-api` 提供的所有后端管理功能进行全面的交互。
 
+5.  **`manager-mobile` (智控台移动版 - uni-app实现):**
+    这是一个基于uni-app v3 + Vue 3 + Vite的跨端移动管理端，支持App（Android & iOS）和微信小程序。其主要能力包括：
+    *   提供移动设备上的便捷管理界面，与manager-web功能类似但针对移动端进行了优化。
+    *   支持用户登录、设备管理、AI服务配置等核心功能。
+    *   跨平台适配，一套代码可同时运行在iOS、Android和微信小程序上。
+    *   基于alova + @alova/adapter-uniapp实现网络请求，与manager-api无缝集成。
+    *   使用pinia进行状态管理，确保数据一致性。
+
+6.  **`digital-human` (数字人测试模块 - Python+Web实现):**
+    这是一个独立的数字人测试模块，提供本地测试页面、前端交互资源、唤醒词运行时与事件桥能力，用于联调整个数字人交互链路。其主要能力包括：
+    *   提供浏览器端的数字人测试页面，用于验证音频播放、接收和交互流程。
+    *   集成本地唤醒词运行时，支持基于Sherpa-ONNX的关键词检测。
+    *   通过事件桥将页面状态与本地运行时打通，便于调试唤醒词触发与交互效果。
+    *   作为独立模块与`xiaozhi-server`、`manager-web`、`manager-api`并列，便于单独开发和部署。
+
 **高层交互流程概述:**
 
 *   **语音交互主线:** **ESP32设备**捕捉到用户语音后，通过**WebSocket**将音频数据实时传输给**`xiaozhi-server`**。`xiaozhi-server`完成一系列AI处理（VAD、ASR、LLM交互、TTS）后，再通过WebSocket将合成的语音回复发送回ESP32设备进行播放。所有与语音直接相关的实时交互均在此链路完成。
@@ -71,6 +88,8 @@ xiaozhi-esp32-server
   ├─ xiaozhi-server 8000 端口 Python语言开发 负责与esp32通信
   ├─ manager-web 8001 端口 Node.js+Vue开发 负责提供控制台的web界面
   ├─ manager-api 8002 端口 Java语言开发 负责提供控制台的api
+  ├─ manager-mobile 跨平台移动应用 uni-app+Vue3开发 负责提供移动版智控台管理
+  └─ digital-human 数字人测试模块 Python+Web实现 负责本地测试页面、唤醒词运行时与事件桥
 ```
 
 ---
@@ -294,6 +313,110 @@ xiaozhi-esp32-server
 
 ---
 
+### 3.4. `manager-mobile` (智控台移动版 - uni-app实现)
+
+`manager-mobile` 组件是一个基于uni-app v3 + Vue 3 + Vite的跨端移动管理端，支持App（Android & iOS）和微信小程序。它为系统管理员提供了移动端的管理界面，使得管理操作更加便捷。
+
+*   **核心目标:**
+    *   提供移动设备上的便捷管理界面，与manager-web功能类似但针对移动端进行了优化。
+    *   支持用户登录、设备管理、AI服务配置等核心功能。
+    *   跨平台适配，一套代码可同时运行在iOS、Android和微信小程序上。
+    *   为移动用户提供流畅、高效的管理体验。
+
+*   **平台兼容性:**
+
+| H5 | iOS | Android | 微信小程序 |
+| -- | --- | ------- | ---------- | 
+| √  | √   | √       | √          | 
+
+*   **核心技术栈:**
+    *   **uni-app v3:** 一个使用Vue.js开发所有前端应用的框架，支持iOS、Android、H5、以及各种小程序。
+    *   **Vue 3:** 用于构建用户界面的渐进式框架，提供了更好的性能和新特性。
+    *   **Vite:** 下一代前端开发与构建工具，提供极速的开发体验。
+    *   **pnpm:** 快速、节省磁盘空间的包管理器。
+    *   **alova:** 轻量级、灵活的请求策略库，搭配@alova/adapter-uniapp适配uni-app环境。
+    *   **pinia:** Vue的状态管理库，替代Vuex，提供更简洁的API和更好的TypeScript支持。
+    *   **UnoCSS:** 具有高性能且极具灵活性的即时原子化CSS引擎。
+    *   **TypeScript:** 提供类型安全的开发体验。
+
+*   **关键实现细节:**
+
+    1.  **跨平台架构:**
+        *   基于uni-app框架，实现了一套代码多端运行的目标，大幅减少了开发和维护成本。
+        *   针对不同平台的特性和限制，通过条件编译进行平台特定的代码处理。
+
+    2.  **项目结构:**
+        *   **`src/App.vue`:** 应用的根组件，定义了全局的样式和配置。
+        *   **`src/main.ts`:** 应用的入口文件，负责初始化Vue实例、注册插件和路由拦截器。
+        *   **`src/pages/`:** 存放应用的页面组件，如登录页、设备管理页等。
+        *   **`src/layouts/`:** 定义应用的布局组件，如默认布局、带tabbar的布局等。
+        *   **`src/api/`:** 封装与后端API的通信逻辑。
+        *   **`src/store/`:** 使用pinia进行状态管理。
+        *   **`src/components/`:** 存放可复用的组件。
+        *   **`src/utils/`:** 提供通用的工具函数。
+
+    3.  **网络请求:**
+        *   基于alova + @alova/adapter-uniapp实现网络请求，统一处理请求头、认证、错误等。
+        *   请求地址和环境配置通过.env文件管理，支持不同环境的切换。
+
+    4.  **路由与鉴权:**
+        *   使用uni-app的路由系统，结合路由拦截器实现页面的登录验证和权限控制。
+        *   未登录用户访问需要认证的页面时，会被重定向到登录页。
+
+    5.  **状态管理:**
+        *   使用pinia管理应用状态，如用户信息、设备列表等。
+        *   通过pinia-plugin-persistedstate插件实现状态的持久化存储。
+
+    6.  **构建与发布:**
+        *   支持多种构建命令，如构建微信小程序、Android和iOS App等。
+        *   使用HBuilderX进行App的云打包，简化了打包流程。
+
+`manager-mobile` 通过这些技术的应用，为用户提供了一个功能完备、体验流畅的移动端管理工具，使得管理员可以随时随地进行系统管理和配置。
+
+---
+
+### 3.5. `digital-human` (数字人测试模块 - Python+Web实现)
+
+`digital-human` 组件是一个独立的数字人测试模块，负责提供本地测试页面、页面资源、唤醒词运行时和事件桥能力。它主要用于联调整个数字人交互链路，帮助开发者验证页面交互、音频能力和本地唤醒词流程。
+
+*   **核心目标:**
+    *   提供独立的本地测试页面，用于验证数字人交互效果。
+    *   提供本地唤醒词运行时，支持关键词检测与事件上报。
+    *   为前端页面和本地运行时提供事件桥，打通测试链路。
+    *   以独立模块形式存在，便于单独开发、调试和部署。
+
+*   **核心技术栈:**
+    *   **Python 3:** 作为测试运行时的主要语言，负责启动本地服务、管理唤醒词运行时和事件桥。
+    *   **原生HTML/CSS/JavaScript:** 用于构建数字人测试页面与交互逻辑。
+    *   **Sherpa-ONNX:** 用于本地唤醒词检测。
+    *   **ThreadingHTTPServer / WebSocket桥接:** 用于承载测试页面、健康检查和本地事件通信。
+
+*   **关键实现细节:**
+
+    1.  **模块入口与页面资源:**
+        *   `start.py` 是模块启动入口，负责初始化测试运行时。
+        *   `index.html` 是数字人测试页面入口。
+        *   `js/`、`css/`、`images/`、`resources/` 目录提供页面脚本、样式和资源文件。
+
+    2.  **本地测试运行时:**
+        *   `wakeword_runtime/` 目录承载本地唤醒词运行时实现。
+        *   运行时负责配置加载、日志初始化、音频采集、关键词检测和服务生命周期管理。
+        *   模块默认通过本地HTTP服务暴露页面地址、事件桥地址和健康检查接口。
+
+    3.  **唤醒词检测链路:**
+        *   基于Sherpa-ONNX关键词检测模型，支持本地唤醒词触发。
+        *   模型文件和关键词配置位于 `wakeword_runtime/models/` 及相应配置文件中。
+        *   页面侧可结合事件桥观察唤醒词服务状态和触发结果。
+
+    4.  **调试与联调定位:**
+        *   启动后可通过浏览器访问本地页面，验证音频播放、接收和交互逻辑。
+        *   通过事件桥可以将唤醒词状态同步到页面，便于排查本地链路问题。
+        *   详细的模型下载、运行时配置和使用说明已整理在 `docs/digital-human-wakeword.md` 中。
+
+`digital-human` 的存在使得数字人相关能力可以脱离主服务独立验证，降低了页面调试、唤醒词联调和本地环境搭建的复杂度。
+
+---
+
 ## 4. 数据流与交互机制
 
 `xiaozhi-esp32-server` 系统通过各组件间定义清晰的数据流和交互协议来协同工作。主要的通信方式依赖于针对实时交互优化的WebSocket协议和适用于客户端-服务器请求的RESTful API。

main/README_en.md

@@ -8,6 +8,8 @@
     *   [3.1. `xiaozhi-server` (Core AI Engine - Python Implementation)](#31-xiaozhi-server-core-ai-engine---python-implementation)
     *   [3.2. `manager-api` (Management Backend - Java Spring Boot Implementation)](#32-manager-api-management-backend---java-spring-boot-implementation)
     *   [3.3. `manager-web` (Web Management Frontend - Vue.js Implementation)](#33-manager-web-web-management-frontend---vuejs-implementation)
+    *   [3.4. `manager-mobile` (Mobile Management Console - uni-app Implementation)](#34-manager-mobile-mobile-management-console---uniapp-implementation)
+    *   [3.5. `digital-human` (Digital Human Test Module - Python+Web Implementation)](#35-digital-human-digital-human-test-module---pythonweb-implementation)
 4.  [Data Flow and Interaction Mechanisms](#4-data-flow-and-interaction-mechanisms)
 5.  [Key Features Summary](#5-key-features-summary)
 6.  [Deployment and Configuration Overview](#6-deployment-and-configuration-overview)
@@ -59,6 +61,21 @@ The `xiaozhi-esp32-server` system adopts a **distributed, multi-component collab
     *   (Potential functionality) Monitoring system operation status, viewing logs, troubleshooting, etc.
     *   Comprehensive interaction with all backend management functions provided by `manager-api`.
 
+5.  **`manager-mobile` (Mobile Management Console - uni-app Implementation):**
+    This is a cross-platform mobile management application based on uni-app v3 + Vue 3 + Vite, supporting App (Android & iOS) and WeChat Mini Program. Its main capabilities include:
+    *   Providing a convenient management interface on mobile devices, similar in functionality to manager-web but optimized for mobile platforms.
+    *   Supporting core functions such as user login, device management, and AI service configuration.
+    *   Cross-platform adaptation, allowing a single codebase to run on iOS, Android, and WeChat Mini Programs.
+    *   Integrating with `manager-api` through alova + `@alova/adapter-uniapp`.
+    *   Using pinia for state management to ensure data consistency.
+
+6.  **`digital-human` (Digital Human Test Module - Python+Web Implementation):**
+    This is an independent digital human test module that provides a local test page, frontend interaction resources, a wake word runtime, and an event bridge for end-to-end debugging of the digital human interaction flow. Its main capabilities include:
+    *   Providing a browser-based digital human test page for validating audio playback, audio reception, and interaction flow.
+    *   Integrating a local wake word runtime with keyword detection based on Sherpa-ONNX.
+    *   Bridging page state and the local runtime through an event bridge to simplify wake word debugging.
+    *   Existing as a standalone module alongside `xiaozhi-server`, `manager-web`, and `manager-api`, making independent development and deployment easier.
+
 **High-Level Interaction Flow Overview:**
 
 *   **Voice Interaction Main Line:** After the **ESP32 device** captures user voice, it transmits audio data in real-time to **`xiaozhi-server`** through **WebSocket**. After `xiaozhi-server` completes a series of AI processing (VAD, ASR, LLM interaction, TTS), it sends the synthesized voice response back to the ESP32 device for playback through WebSocket. All real-time interactions directly related to voice are completed in this link.
@@ -72,6 +89,8 @@ xiaozhi-esp32-server
   ├─ xiaozhi-server Port 8000 Python development Responsible for ESP32 communication
   ├─ manager-web Port 8001 Node.js+Vue development Responsible for providing web interface for console
   ├─ manager-api Port 8002 Java development Responsible for providing console API
+  ├─ manager-mobile Cross-platform mobile application uni-app+Vue3 development Responsible for providing mobile console management
+  └─ digital-human Digital human test module Python+Web implementation Responsible for local test page, wake word runtime, and event bridge
 ```
 
 ---
@@ -190,7 +209,110 @@ The `manager-web` is a Single Page Application (SPA) providing the administrativ
     4.  **State Management (`src/store/index.js`):** Vuex manages global state (user info, device lists, etc.) via state, getters, mutations, and actions (often involving API calls).
     5.  **API Communication (`src/apis/`):** Modularized API service files make asynchronous calls to `manager-api`.
     6.  **Build Process & PWA Features:** Vue CLI (Webpack) bundles assets. Workbox enables PWA features like caching.
-    7.  **Environment Configuration (`.env` files):** Manages settings like the `manager-api` base URL for different environments.
+    7.  **Environment Configuration (`.env` files):**
+        *   The `.env` (and `.env.development`, `.env.production`, etc.) files in the project root directory are used to define environment variables. These variables (such as `VUE_APP_API_BASE_URL` to specify the base URL of `manager-api`) can be accessed in the application code through `process.env.VUE_APP_XXX`, allowing configuration of different parameters for different build environments (development, testing, production).
+
+`manager-web` constructs a powerful, maintainable, and user-friendly management interface through the comprehensive application of these technologies, providing solid frontend support for the configuration and monitoring of the `xiaozhi-esp32-server` system.
+
+### 3.4. `manager-mobile` (Mobile Management Console - uni-app Implementation)
+
+The `manager-mobile` component is a cross-platform mobile management application based on uni-app v3 + Vue 3 + Vite, supporting App (Android & iOS) and WeChat Mini Program. It provides system administrators with a mobile management interface, making management operations more convenient.
+
+*   **Core Objectives:**
+    *   Provide a convenient management interface on mobile devices, similar in functionality to manager-web but optimized for mobile platforms.
+    *   Support core functions such as user login, device management, and AI service configuration.
+    *   Cross-platform adaptation, allowing a single codebase to run on iOS, Android, and WeChat Mini Programs.
+    *   Provide mobile users with a smooth and efficient management experience.
+
+*   **Platform Compatibility:**
+
+| H5 | iOS | Android | WeChat Mini Program |
+| -- | --- | ------- | ------------------ | 
+| ×  | √   | √       | √                  | 
+
+*   **Core Technologies:**
+    *   **uni-app v3:** A framework for developing all frontend applications using Vue.js, supporting iOS, Android, H5, and various mini-programs.
+    *   **Vue 3:** A progressive framework for building user interfaces, providing better performance and new features.
+    *   **Vite:** The next generation frontend development and build tool, offering an extremely fast development experience.
+    *   **pnpm:** A fast, disk space-efficient package manager.
+    *   **alova:** A lightweight, flexible request strategy library, paired with @alova/adapter-uniapp to adapt to the uni-app environment.
+    *   **pinia:** State management library for Vue, replacing Vuex, providing a simpler API and better TypeScript support.
+    *   **UnoCSS:** A high-performance and extremely flexible instant atomic CSS engine.
+    *   **TypeScript:** Provides a type-safe development experience.
+
+*   **Key Implementation Details:**
+
+    1.  **Cross-Platform Architecture:**
+        *   Based on the uni-app framework, achieving the goal of "write once, run anywhere," significantly reducing development and maintenance costs.
+        *   Handling platform-specific code through conditional compilation to address the characteristics and limitations of different platforms.
+
+    2.  **Project Structure:**
+        *   **`src/App.vue`:** The root component of the application, defining global styles and configurations.
+        *   **`src/main.ts`:** The entry file of the application, responsible for initializing the Vue instance, registering plugins, and setting up route interceptors.
+        *   **`src/pages/`:** Stores application page components, such as login pages, device management pages, etc.
+        *   **`src/layouts/`:** Defines application layout components, such as default layouts, layouts with tabbar, etc.
+        *   **`src/api/`:** Encapsulates communication logic with backend APIs.
+        *   **`src/store/`:** Uses pinia for state management.
+        *   **`src/components/`:** Stores reusable components.
+        *   **`src/utils/`:** Provides common utility functions.
+
+    3.  **Network Requests:**
+        *   Implements network requests based on alova + @alova/adapter-uniapp, unified handling of request headers, authentication, errors, etc.
+        *   Request addresses and environment configurations are managed through .env files, supporting switching between different environments.
+
+    4.  **Routing and Authentication:**
+        *   Uses uni-app's routing system, combined with route interceptors to implement page login verification and permission control.
+        *   When unlogged users access pages requiring authentication, they are redirected to the login page.
+
+    5.  **State Management:**
+        *   Uses pinia to manage application state, such as user information, device lists, etc.
+        *   Implements persistent storage of state through the pinia-plugin-persistedstate plugin.
+
+    6.  **Build and Release:**
+        *   Supports multiple build commands, such as building WeChat Mini Programs, Android, and iOS Apps.
+        *   Uses HBuilderX for cloud packaging of Apps, simplifying the packaging process.
+
+`manager-mobile` provides users with a fully functional, smooth mobile management tool through the application of these technologies, allowing administrators to perform system management and configuration anytime, anywhere.
+
+### 3.5. `digital-human` (Digital Human Test Module - Python+Web Implementation)
+
+The `digital-human` component is an independent digital human test module responsible for providing a local test page, page resources, a wake word runtime, and an event bridge. It is primarily used to debug the complete digital human interaction flow and to validate frontend interaction, audio capability, and local wake word behavior.
+
+*   **Core Objectives:**
+    *   Provide an independent local test page for validating digital human interaction effects.
+    *   Provide a local wake word runtime for keyword detection and event reporting.
+    *   Provide an event bridge between the frontend page and the local runtime to connect the test flow.
+    *   Exist as a standalone module for easier independent development, debugging, and deployment.
+
+*   **Core Technologies:**
+    *   **Python 3:** Used for the local test runtime, service startup, wake word lifecycle management, and event bridge coordination.
+    *   **Native HTML/CSS/JavaScript:** Used to build the digital human test page and interaction logic.
+    *   **Sherpa-ONNX:** Used for local wake word keyword detection.
+    *   **ThreadingHTTPServer / WebSocket bridge:** Used to serve the local page, health check endpoint, and event communication.
+
+*   **Key Implementation Aspects:**
+
+    1.  **Module Entry and Page Resources:**
+        *   `start.py` is the module entry point responsible for starting the local test runtime.
+        *   `index.html` is the entry page for digital human testing.
+        *   The `js/`, `css/`, `images/`, and `resources/` directories provide frontend scripts, styles, and static resources.
+
+    2.  **Local Test Runtime:**
+        *   The `wakeword_runtime/` directory contains the local wake word runtime implementation.
+        *   The runtime is responsible for configuration loading, logging initialization, audio capture, keyword detection, and lifecycle management.
+        *   The module exposes a local page URL, event bridge URL, and health check endpoint through a local HTTP service.
+
+    3.  **Wake Word Detection Flow:**
+        *   Uses Sherpa-ONNX keyword detection models to support local wake word triggering.
+        *   Model files and keyword configurations are stored in `wakeword_runtime/models/` and related configuration files.
+        *   The page can observe runtime state and trigger results through the event bridge.
+
+    4.  **Debugging and Integration Positioning:**
+        *   After startup, developers can open the local page in a browser to validate playback, reception, and interaction logic.
+        *   The event bridge synchronizes wake word state to the page, which helps with local debugging.
+        *   Detailed model download, runtime configuration, and usage instructions are documented in `docs/digital-human-wakeword.md`.
+
+The `digital-human` module allows digital human related capabilities to be validated independently from the main service, reducing the complexity of page debugging, wake word integration, and local environment setup.
 
 ---
 

main/digital-human/README.md

@@ -0,0 +1,46 @@
+本文档是开发类文档，如需部署小智服务端，[点击这里查看部署教程](../../README.md#%E9%83%A8%E7%BD%B2%E6%96%87%E6%A1%A3)
+
+如需查看一体机数字人落地部署、Kiosk 全屏启动和系统环境配置，[点击这里查看一体机部署指南](../../docs/all-in-one-digital-human-setup.md)
+
+如需查看唤醒词模型下载、运行时配置和详细使用说明，[点击这里查看唤醒词专题文档](../../docs/digital-human-wakeword.md)
+
+# 项目介绍
+
+digital-human 是独立的数字人测试模块，负责提供本地测试页面、前端交互资源、唤醒词运行时和事件桥能力，用于联调整个数字人交互链路。
+
+# 快速启动
+
+安装依赖：
+
+```bash
+pip install -r wakeword_runtime/requirements.txt
+```
+
+启动模块：
+
+```bash
+python start.py
+```
+
+# 访问地址
+
+启动后可访问：
+
+- 页面地址：http://127.0.0.1:8006/index.html
+- 事件桥地址：ws://127.0.0.1:8006/wakeword-ws
+- 健康检查：http://127.0.0.1:8006/health
+
+# 目录说明
+
+- `start.py`：模块启动入口
+- `index.html`：数字人测试页面入口
+- `wakeword_runtime`：本地唤醒词运行时与配置目录
+- `js`、`css`：页面前端脚本与样式
+- `images`、`resources`：页面资源文件
+
+# 相关文档
+
+- 一体机部署指南：适用于 x86 设备整机落地部署、Kiosk 展示和开机自启动配置
+	[../../docs/all-in-one-digital-human-setup.md](../../docs/all-in-one-digital-human-setup.md)
+- 唤醒词专题文档：适用于唤醒词模型下载、运行时配置和本地调试说明
+	[../../docs/digital-human-wakeword.md](../../docs/digital-human-wakeword.md)

main/digital-human/index.html

@@ -0,0 +1,416 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>小智数字人页面</title>
+    <link rel="stylesheet" href="css/index.css?v=0206">
+    <script>
+        // 检测是否使用file://协议打开
+        if (window.location.protocol === 'file:') {
+            document.addEventListener('DOMContentLoaded', function () {
+                // 创建背景模糊遮罩
+                const overlayDiv = document.createElement('div');
+                overlayDiv.className = 'file-protocol-overlay';
+                document.body.appendChild(overlayDiv);
+
+                // 创建警告框
+                const warningDiv = document.createElement('div');
+                warningDiv.id = 'fileProtocolWarning';
+                warningDiv.innerHTML = `
+                    <h2>⚠️ 警告：请使用HTTP服务器打开此页面</h2>
+                    <p>您当前使用的是本地文件方式打开页面（file://协议），这可能导致页面功能异常。</p>
+                    <p>您可以使用nginx映射启动小智数字人页面，也可以请按照以下步骤启动测试运行时：</p>
+                    <ol>
+                        <li>打开命令行终端</li>
+                        <li>命令行进入到 digital-human 目录</li>
+                        <li>执行以下命令启动小智数字人页面运行时：</li>
+                    </ol>
+                    <pre>python start.py</pre>
+                    <p>然后在浏览器中访问：<strong>http://localhost:8006/index.html</strong></p>
+                `;
+                document.body.appendChild(warningDiv);
+            });
+        }
+    </script>
+</head>
+
+<body>
+    <!-- 背景容器 -->
+    <div class="background-container" id="backgroundContainer">
+        <div class="background-overlay"></div>
+    </div>
+
+    <!-- 主容器 -->
+    <div class="container">
+
+        <!-- 摄像头显示区域（可拖动） -->
+        <div class="camera-container" id="cameraContainer">
+            <video id="cameraVideo" autoplay playsinline muted></video>
+            <div class="camera-switch-mask" id="cameraSwitchMask">
+                <div class="camera-switch-container">
+                    <!-- 摄像头切换按钮 -->
+                    <div class="camera-switch" id="cameraSwitch">
+                        <svg class="btn-icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="7319" width="32" height="32"><path d="M722.1 530.3c0-44.9-13.8-86.5-37.2-120.9-0.3-0.6-0.6-1.2-0.9-1.7-2.9-4.2-6.1-8.1-9.2-12-0.4-0.5-0.7-1-1.1-1.5-21.4-26.3-48.3-46.7-78.7-59.9-0.8-0.4-1.7-0.8-2.5-1.2-4.9-2-9.8-3.8-14.9-5.5-1.8-0.6-3.6-1.3-5.4-1.8-4.4-1.3-8.8-2.4-13.3-3.5-2.5-0.6-4.9-1.2-7.4-1.7-1.2-0.2-2.4-0.6-3.6-0.8-3.3-0.6-6.7-0.8-10-1.3-2.3-0.3-4.6-0.7-6.9-0.9-5.6-0.5-11.2-0.8-16.7-0.9-1 0-2-0.1-3-0.1-0.2 0-0.3 0.1-0.5 0.1-42.8 0-84.6 13.1-120.4 38.6-11.5 8.1-14.2 24.1-6.2 35.7 8 11.6 23.8 14.4 35.2 6.3 27.7-19.7 60-29.6 93.1-29.3 4.8 0 9.5 0.3 14.1 0.7 1.4 0.2 2.8 0.4 4.3 0.5 3.8 0.5 7.6 1 11.3 1.8 1.6 0.3 3.3 0.8 4.9 1.1 3.7 0.8 7.3 1.7 10.9 2.8 1.1 0.4 2.2 0.8 3.4 1.2 4.1 1.3 8.1 2.8 12 4.5 0.4 0.2 0.8 0.4 1.2 0.5 23.6 10.3 44.3 26.1 60.4 45.9 0.1 0.1 0.2 0.3 0.3 0.4 22.7 28 36.4 63.9 36.4 102.9h-42.2L697 632.9l67.5-102.6h-42.4z m-119 133c-27.9 19.8-60.5 29.7-93.9 29.3-4.4-0.1-8.8-0.3-13.1-0.7-1.8-0.2-3.5-0.5-5.3-0.7-3.4-0.5-6.8-0.9-10.1-1.6-2-0.4-4-0.9-6.1-1.4-3.3-0.8-6.5-1.5-9.7-2.5-1.5-0.5-3-1-4.6-1.5-3.7-1.2-7.3-2.5-10.8-4-0.8-0.3-1.6-0.7-2.4-1.1-4.1-1.9-8.2-3.8-12.2-6l-0.6-0.3c-13.4-7.5-25.7-16.8-36.4-27.7-0.2-0.2-0.3-0.4-0.5-0.6-3.3-3.4-6.5-6.9-9.5-10.7-0.6-0.8-1.3-1.6-1.9-2.5-21.9-27.8-35.1-63-35.1-101.2h42.2l-67.5-102.6-67.5 102.6h42.2c0 45 13.9 86.7 37.3 121.1 0.3 0.5 0.5 1 0.8 1.5 2.4 3.5 5.1 6.8 7.7 10.1 1 1.3 1.9 2.6 2.9 3.8 3.9 4.7 7.9 9.2 12.1 13.5 0.4 0.4 0.8 0.9 1.2 1.3 14.1 14.3 30.1 26.4 47.4 36 0.5 0.3 0.9 0.6 1.4 0.8 5 2.7 10.1 5.2 15.3 7.5l3.9 1.8c4.4 1.9 9 3.5 13.6 5.1 2.2 0.7 4.4 1.5 6.6 2.2 4 1.2 8.1 2.2 12.3 3.2 2.8 0.7 5.5 1.4 8.3 1.9 1.2 0.3 2.3 0.6 3.4 0.8 3.9 0.7 7.8 1.1 11.8 1.6l4.2 0.6c7 0.7 14.1 1.2 21.1 1.2 42.9 0 84.7-13.3 120.6-38.8 11.4-8.2 14.2-24.1 6.2-35.8-8-11.5-23.8-14.3-35.3-6.2z m271.3-421.6H763c-26.5 0-82.9-119.7-112.5-119.7H370.6c-29.6 0-85.9 119.7-112.4 119.7H147.5c-46.3 0-83.9 40.2-83.9 89.7v478.8c0 49.6 37.6 89.8 83.9 89.8h726.9c46.3 0 83.9-40.1 83.9-89.8V331.4c0-49.5-37.6-89.7-83.9-89.7z m28 538.6c0 33.1-25 59.8-55.9 59.8h-671c-30.9 0-55.9-26.8-55.9-59.8V361.4c0-33 25-59.8 55.9-59.8h111.2c25.8 0 82-119.7 111.6-119.7h223.2c29.5 0 85.6 119.7 111.5 119.7h113.5c30.9 0 55.9 26.8 55.9 59.8v418.9z" p-id="7320" fill="#ffffff"></path></svg>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <!-- 连接状态指示器 - 页面顶部中部 -->
+        <div class="connection-status-top">
+            <div class="status-indicator">
+                <span class="status-dot status-disconnected"></span>
+                <span id="connectionStatus">离线</span>
+            </div>
+        </div>
+
+        <!-- 模型加载提示 -->
+        <div class="model-container">
+            <div class="model-loading" id="modelLoading">
+                <div class="loading-char-float">
+                    <div class="main-char">
+                        <span>模</span><span>型</span><span>加</span><span>载</span><span>中</span><span>✨</span>
+                    </div>
+                    <div class="shadow-char">模型加载中✨</div>
+                </div>
+            </div>
+        </div>
+
+        <!-- Live2D Canvas 容器 -->
+        <canvas id="live2d-stage"></canvas>
+
+        <!-- 聊天消息流（弹幕样式） -->
+        <div class="chat-container">
+            <div class="chat-stream" id="chatStream">
+                <!-- 聊天消息将动态插入这里 -->
+            </div>
+            <div class="chat-ipt" id="chatIpt">
+                <input type="text" id="messageInput" autocomplete="off" placeholder="输入消息，按Enter发送">
+            </div>
+        </div>
+
+        <!-- 底部控制栏 -->
+        <div class="control-bar">
+            <button class="control-btn" id="settingsBtn" title="设置">
+                <svg class="btn-icon" viewBox="0 0 24 24" fill="currentColor">
+                    <path
+                        d="M12 15.5A3.5 3.5 0 0 1 8.5 12A3.5 3.5 0 0 1 12 8.5A3.5 3.5 0 0 1 15.5 12A3.5 3.5 0 0 1 12 15.5M19.43 12.97C19.47 12.65 19.5 12.33 19.5 12C19.5 11.67 19.47 11.34 19.43 11L21.54 9.37C21.73 9.22 21.78 8.95 21.66 8.73L19.66 5.27C19.54 5.05 19.27 4.96 19.05 5.05L16.56 6.05C16.04 5.66 15.5 5.32 14.87 5.07L14.5 2.42C14.46 2.18 14.25 2 14 2H10C9.75 2 9.54 2.18 9.5 2.42L9.13 5.07C8.5 5.32 7.96 5.66 7.44 6.05L4.95 5.05C4.73 4.96 4.46 5.05 4.34 5.27L2.34 8.73C2.22 8.95 2.27 9.22 2.46 9.37L4.57 11C4.53 11.34 4.5 11.67 4.5 12C4.5 12.33 4.53 12.65 4.57 12.97L2.46 14.63C2.27 14.78 2.22 15.05 2.34 15.27L4.34 18.73C4.46 18.95 4.73 19.03 4.95 18.95L7.44 17.94C7.96 18.34 8.5 18.68 9.13 18.93L9.5 21.58C9.54 21.82 9.75 22 10 22H14C14.25 22 14.46 21.82 14.5 21.58L14.87 18.93C15.5 18.68 16.04 18.34 16.56 17.94L19.05 18.95C19.27 19.03 19.54 18.95 19.66 18.73L21.66 15.27C21.78 15.05 21.73 14.78 21.54 14.63L19.43 12.97Z" />
+                </svg>
+                <span class="btn-text">设置</span>
+            </button>
+
+            <button class="control-btn" id="cameraBtn" title="请先连接服务器" disabled>
+                <svg class="btn-icon" viewBox="0 0 24 24" fill="currentColor">
+                    <path
+                        d="M17,10.5V7A1,1 0 0,0 16,6H4A1,1 0 0,0 3,7V17A1,1 0 0,0 4,18H16A1,1 0 0,0 17,17V13.5L21,17.5V6.5L17,10.5Z" />
+                </svg>
+                <span class="btn-text">摄像头</span>
+            </button>
+
+            <button class="control-btn dial-btn" id="dialBtn" title="拨号">
+                <svg class="btn-icon" viewBox="0 0 24 24" fill="currentColor">
+                    <path
+                        d="M6.62,10.79C8.06,13.62 10.38,15.94 13.21,17.38L15.41,15.18C15.69,14.9 16.08,14.82 16.43,14.93C17.55,15.3 18.75,15.5 20,15.5A1,1 0 0,1 21,16.5V20A1,1 0 0,1 20,21A17,17 0 0,1 3,4A1,1 0 0,1 4,3H7.5A1,1 0 0,1 8.5,4C8.5,5.25 8.7,6.45 9.07,7.57C9.18,7.92 9.1,8.31 8.82,8.59L6.62,10.79Z" />
+                </svg>
+                <span class="btn-text">拨号</span>
+            </button>
+
+            <button class="control-btn" id="recordBtn" title="开始录音" disabled>
+                <svg class="btn-icon" viewBox="0 0 24 24" fill="currentColor">
+                    <path
+                        d="M12,2A3,3 0 0,1 15,5V11A3,3 0 0,1 12,14A3,3 0 0,1 9,11V5A3,3 0 0,1 12,2M19,11C19,14.53 16.39,17.44 13,17.93V21H11V17.93C7.61,17.44 5,14.53 5,11H7A5,5 0 0,0 12,16A5,5 0 0,0 17,11H19Z" />
+                </svg>
+                <span class="btn-text">录音</span>
+            </button>
+        </div>
+    </div>
+
+    <!-- 设置弹窗 -->
+    <div class="modal" id="settingsModal">
+        <div class="modal-content settings-modal">
+            <div class="modal-header">
+                <h2>设置</h2>
+                <button class="close-btn" id="closeSettingsBtn">&times;</button>
+            </div>
+            <div class="modal-body">
+                <div class="settings-tabs">
+                    <button class="tab-btn active" data-tab="device">设备配置</button>
+                    <button class="tab-btn" data-tab="wakeword">唤醒词</button>
+                    <button class="tab-btn" data-tab="mcp">MCP工具</button>
+                    <button class="tab-btn" data-tab="other">数字人皮肤</button>
+                </div>
+
+                <div class="tab-content active" id="deviceTab">
+                    <!-- 设备配置面板 -->
+                    <div class="config-panel">
+                        <div class="control-panel">
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="deviceMac">设备MAC:</label>
+                                    <input type="text" id="deviceMac" placeholder="device-id">
+                                </div>
+                            </div>
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="clientId">客户端ID:</label>
+                                    <input type="text" id="clientId" value="web_test_client" placeholder="client-id">
+                                </div>
+                                <div class="config-item">
+                                    <label for="deviceName">设备名称:</label>
+                                    <input type="text" id="deviceName" value="Web测试设备" maxlength="50"
+                                        placeholder="deviceName">
+                                </div>
+                            </div>
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="emojiEnabled">情绪表情:</label>
+                                    <select id="emojiEnabled" class="model-select">
+                                        <option value="true">启用</option>
+                                        <option value="false">禁用</option>
+                                    </select>
+                                </div>
+                            </div>
+                        </div>
+                    </div>
+
+                    <!-- 连接信息面板 -->
+                    <div class="connection-controls">
+                        <div class="input-group">
+                            <label for="otaUrl">OTA服务器地址:</label>
+                            <input type="text" id="otaUrl" value="http://127.0.0.1:8002/xiaozhi/ota/"
+                                placeholder="OTA服务器地址，如：http://127.0.0.1:8002/xiaozhi/ota/" />
+                        </div>
+                        <div class="input-group">
+                            <label for="serverUrl">WebSocket服务器地址:</label>
+                            <input type="text" id="serverUrl" value="" readonly disabled
+                                placeholder="填写OTA地址后，点击拨号按钮自动连接" />
+                        </div>
+                        <div class="input-group">
+                            <label for="visionUrl">视觉分析地址:</label>
+                            <input type="text" id="visionUrl" value="" readonly disabled placeholder="成功建立ws连接后自动获取" />
+                        </div>
+                    </div>
+                </div>
+
+                <div class="tab-content" id="wakewordTab">
+                    <div class="config-panel">
+                        <div class="control-panel">
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="wakewordEnabled">启用本地唤醒词:</label>
+                                    <select id="wakewordEnabled" class="model-select">
+                                        <option value="true">启用</option>
+                                        <option value="false">禁用</option>
+                                    </select>
+                                </div>
+                            </div>
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="wakewordWsUrl">唤醒词服务地址:</label>
+                                    <input type="text" id="wakewordWsUrl" placeholder="ws://127.0.0.1:8006/wakeword-ws">
+                                </div>
+                            </div>
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label for="wakewordList">唤醒词配置 (一行一个):</label>
+                                    <textarea id="wakewordList" placeholder="例如：&#10;小智小智&#10;你好小智"></textarea>
+                                </div>
+                            </div>
+                            <div class="modal-actions">
+                                <button type="button" class="btn-primary" id="applyWakewordBtn">应用唤醒词</button>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+
+                <div class="tab-content" id="mcpTab">
+                    <!-- MCP 工具管理区域 -->
+                    <div class="mcp-tools-container">
+                        <div class="mcp-tools-header">
+                            <h3>MCP 工具管理</h3>
+                        </div>
+                        <div class="mcp-tools-panel" id="mcpToolsPanel">
+                            <div class="mcp-tools-list" id="mcpToolsContainer">
+                                <!-- 工具列表将动态插入这里 -->
+                            </div>
+                            <div class="mcp-actions">
+                                <button class="btn-primary" id="addMcpToolBtn">
+                                    ➕ 添加新工具
+                                </button>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+
+                <div class="tab-content" id="otherTab">
+                    <div class="other-settings-panel">
+                        <div class="control-panel">
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label>选择模型:</label>
+                                    <select id="live2dModelSelect" class="model-select">
+                                        <option value="hiyori_pro_zh">hiyori (春日)</option>
+                                        <option value="natori_pro_zh">natori (名取)</option>
+                                    </select>
+                                </div>
+                            </div>
+                            <div class="config-row">
+                                <div class="config-item">
+                                    <label></label>
+                                    <button class="background-btn" id="backgroundBtn" title="切换背景">
+                                        <svg class="btn-icon" viewBox="0 0 24 24" fill="currentColor">
+                                            <path
+                                                d="M12,18A6,6 0 0,1 6,12C6,11 6.25,10.03 6.7,9.2L5.24,7.74C4.46,8.97 4,10.43 4,12A8,8 0 0,0 12,20V23L16,19L12,15V18M12,4V1L8,5L12,9V6A6,6 0 0,1 18,12C18,13 17.75,13.97 17.3,14.8L18.76,16.26C19.54,15.03 20,13.57 20,12A8,8 0 0,0 12,4Z" />
+                                        </svg>
+                                        <span class="btn-text">切换背景</span>
+                                    </button>
+                                </div>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+    </div>
+
+    <!-- MCP 工具编辑模态框 -->
+    <div id="mcpToolModal" class="modal">
+        <div class="modal-content">
+            <div class="modal-header">
+                <h2 id="mcpModalTitle">添加工具</h2>
+                <button class="close-btn" id="closeMcpModalBtn">&times;</button>
+            </div>
+            <div class="modal-body">
+                <div id="mcpErrorContainer"></div>
+                <form id="mcpToolForm">
+                    <div class="input-group">
+                        <label for="mcpToolName">工具名称 *</label>
+                        <input type="text" id="mcpToolName" placeholder="例如: self.get_device_status" required>
+                    </div>
+                    <div class="input-group">
+                        <label for="mcpToolDescription">工具描述 *</label>
+                        <textarea id="mcpToolDescription" placeholder="详细描述工具的功能和使用场景..." required></textarea>
+                    </div>
+                    <div class="input-group">
+                        <div class="input-group-header">
+                            <label>输入参数</label>
+                            <button type="button" class="properties-btn-primary" id="addMcpPropertyBtn">
+                                ➕ 添加参数
+                            </button>
+                        </div>
+                        <div class="properties-container">
+                            <div class="mcp-empty-state" id="mcpEmptyState">
+                                暂无参数，点击上方按钮添加参数
+                            </div>
+                            <div class="mcp-properties-list" id="mcpPropertiesContainer">
+                            </div>
+                        </div>
+                    </div>
+                    <div class="input-group">
+                        <label for="mcpMockResponse">
+                            模拟返回结果 (JSON 格式，可选)
+                            <span style="font-size: 12px; color: #999; font-weight: normal;">- 留空则返回默认成功消息</span>
+                        </label>
+                        <textarea id="mcpMockResponse" placeholder='{"success": true, "data": "执行成功"}'></textarea>
+                    </div>
+                    <div class="modal-actions">
+                        <button type="button" class="btn-secondary" id="cancelMcpBtn">取消</button>
+                        <button type="submit" class="btn-primary">保存</button>
+                    </div>
+                </form>
+            </div>
+        </div>
+    </div>
+
+    <!-- 参数编辑模态框 -->
+    <div id="mcpPropertyModal" class="modal">
+        <div class="modal-content property-modal">
+            <div class="modal-header">
+                <h2 id="mcpPropertyModalTitle">编辑参数</h2>
+                <button class="close-btn" id="closeMcpPropertyModalBtn">&times;</button>
+            </div>
+            <div class="modal-body">
+                <form id="mcpPropertyForm">
+                    <input type="hidden" id="mcpPropertyIndex" value="-1">
+                    <div class="input-group">
+                        <label for="mcpPropertyName">参数名称 *</label>
+                        <input type="text" id="mcpPropertyName" placeholder="例如: param_1" required>
+                    </div>
+                    <div class="input-group">
+                        <label for="mcpPropertyType">数据类型 *</label>
+                        <select id="mcpPropertyType" class="model-select" required>
+                            <option value="string">字符串</option>
+                            <option value="integer">整数</option>
+                            <option value="number">数字</option>
+                            <option value="boolean">布尔值</option>
+                            <option value="array">数组</option>
+                            <option value="object">对象</option>
+                        </select>
+                    </div>
+                    <div class="input-group" id="mcpPropertyRangeGroup" style="display: none;">
+                        <div class="config-row">
+                            <div class="config-item">
+                                <label for="mcpPropertyMinimum">最小值</label>
+                                <input type="number" id="mcpPropertyMinimum" placeholder="可选">
+                            </div>
+                            <div class="config-item">
+                                <label for="mcpPropertyMaximum">最大值</label>
+                                <input type="number" id="mcpPropertyMaximum" placeholder="可选">
+                            </div>
+                        </div>
+                    </div>
+                    <div class="input-group">
+                        <label for="mcpPropertyDescription">参数描述</label>
+                        <input type="text" id="mcpPropertyDescription" placeholder="可选">
+                    </div>
+                    <div class="input-group">
+                        <label class="mcp-checkbox-label">
+                            <input type="checkbox" id="mcpPropertyRequired">
+                            必填参数
+                        </label>
+                    </div>
+                    <div class="modal-actions">
+                        <button type="button" class="btn-secondary" id="cancelMcpPropertyBtn">取消</button>
+                        <button type="submit" class="btn-primary">保存</button>
+                    </div>
+                </form>
+            </div>
+        </div>
+    </div>
+
+    <!-- 背景加载 -->
+    <script src="js/ui/background-load.js?v=0205"></script>
+
+    <!-- PIXI.js 2D渲染引擎 -->
+    <script src="js/live2d/pixi.js?v=0205"></script>
+
+    <!-- Live2D Cubism 4.0 SDK -->
+    <script src="js/live2d/live2dcubismcore.min.js?v=0205"></script>
+    <script src="js/live2d/cubism4.min.js?v=0205"></script>
+
+    <!-- Live2D 管理器 -->
+    <script src="js/live2d/live2d.js?v=0205"></script>
+
+    <!-- Opus解码库 -->
+    <script src="js/utils/libopus.js?v=0205"></script>
+
+    <!-- 主应用入口 -->
+    <script type="module" src="js/app.js?v=0205"></script>
+
+    <!-- 全局错误处理 -->
+    <script>
+        // 添加全局错误处理
+        window.addEventListener('error', function (event) {
+            console.error('全局错误:', event.error);
+        });
+
+        // 添加未处理的Promise拒绝处理
+        window.addEventListener('unhandledrejection', function (event) {
+            console.error('未处理的Promise拒绝:', event.reason);
+        });
+    </script>
+</body>
+
+</html>

main/digital-human/js/app.js

@@ -0,0 +1,373 @@
+// 主应用入口
+import { checkOpusLoaded, initOpusEncoder } from './core/audio/opus-codec.js?v=0205';
+import { getAudioPlayer } from './core/audio/player.js?v=0205';
+import { checkMicrophoneAvailability, isHttpNonLocalhost } from './core/audio/recorder.js?v=0205';
+import { initMcpTools } from './core/mcp/tools.js?v=0205';
+import { startWakewordBridgeListener } from './core/network/wakeword-bridge.js?v=0205';
+import { uiController } from './ui/controller.js?v=0205';
+import { log } from './utils/logger.js?v=0205';
+
+// 辅助函数：将Base64数据转换为Blob
+function dataURItoBlob(dataURI) {
+    const byteString = atob(dataURI.split(',')[1]);
+    const mimeString = dataURI.split(',')[0].split(':')[1].split(';')[0];
+    const ab = new ArrayBuffer(byteString.length);
+    const ia = new Uint8Array(ab);
+    for (let i = 0; i < byteString.length; i++) {
+        ia[i] = byteString.charCodeAt(i);
+    }
+    return new Blob([ab], { type: mimeString });
+}
+
+// 应用类
+class App {
+    constructor() {
+        this.uiController = null;
+        this.audioPlayer = null;
+        this.live2dManager = null;
+        this.cameraStream = null;
+        this.currentFacingMode = 'user';
+    }
+
+    // 初始化应用
+    async init() {
+        log('正在初始化应用...', 'info');
+        // 初始化UI控制器
+        this.uiController = uiController;
+        this.uiController.init();
+        // 检查Opus库
+        checkOpusLoaded();
+        // 初始化Opus编码器
+        initOpusEncoder();
+        // 初始化音频播放器
+        this.audioPlayer = getAudioPlayer();
+        await this.audioPlayer.start();
+        // 初始化MCP工具
+        initMcpTools();
+        // 初始化本地唤醒事件监听
+        startWakewordBridgeListener();
+        // 检查麦克风可用性
+        await this.checkMicrophoneAvailability();
+        // 检查摄像头可用性
+        this.checkCameraAvailability();
+        // 初始化Live2D
+        await this.initLive2D();
+        // 初始化摄像头
+        this.initCamera();
+        // 关闭加载loading
+        this.setModelLoadingStatus(false);
+        log('应用初始化完成', 'success');
+    }
+
+    // 初始化Live2D
+    async initLive2D() {
+        try {
+            // 检查Live2DManager是否已加载
+            if (typeof window.Live2DManager === 'undefined') {
+                throw new Error('Live2DManager未加载，请检查脚本引入顺序');
+            }
+            this.live2dManager = new window.Live2DManager();
+            await this.live2dManager.initializeLive2D();
+            // 更新UI状态
+            const live2dStatus = document.getElementById('live2dStatus');
+            if (live2dStatus) {
+                live2dStatus.textContent = '● 已加载';
+                live2dStatus.className = 'status loaded';
+            }
+            log('Live2D初始化完成', 'success');
+        } catch (error) {
+            log(`Live2D初始化失败: ${error.message}`, 'error');
+            // 更新UI状态
+            const live2dStatus = document.getElementById('live2dStatus');
+            if (live2dStatus) {
+                live2dStatus.textContent = '● 加载失败';
+                live2dStatus.className = 'status error';
+            }
+        }
+    }
+
+    // 设置model加载状态
+    setModelLoadingStatus(isLoading) {
+        const modelLoading = document.getElementById('modelLoading');
+        if (modelLoading) {
+            modelLoading.style.display = isLoading ? 'flex' : 'none';
+        }
+    }
+
+    /**
+     * 检查麦克风可用性
+     * 在应用初始化时调用，检查麦克风是否可用并更新UI状态
+     */
+    async checkMicrophoneAvailability() {
+        try {
+            const isAvailable = await checkMicrophoneAvailability();
+            const isHttp = isHttpNonLocalhost();
+            // 保存可用性状态到全局变量
+            window.microphoneAvailable = isAvailable;
+            window.isHttpNonLocalhost = isHttp;
+            // 更新UI
+            if (this.uiController) {
+                this.uiController.updateMicrophoneAvailability(isAvailable, isHttp);
+            }
+            log(`麦克风可用性检查完成: ${isAvailable ? '可用' : '不可用'}`, isAvailable ? 'success' : 'warning');
+        } catch (error) {
+            log(`检查麦克风可用性失败: ${error.message}`, 'error');
+            // 默认设置为不可用
+            window.microphoneAvailable = false;
+            window.isHttpNonLocalhost = isHttpNonLocalhost();
+            if (this.uiController) {
+                this.uiController.updateMicrophoneAvailability(false, window.isHttpNonLocalhost);
+            }
+        }
+    }
+
+    // 检查摄像头可用性
+    checkCameraAvailability() {
+        window.cameraAvailable = true;
+        log('摄像头可用性检查完成: 默认已绑定验证码', 'success');
+    }
+
+    // 初始化摄像头
+    async initCamera() {
+        const cameraContainer = document.getElementById('cameraContainer');
+        const cameraVideo = document.getElementById('cameraVideo');
+        const cameraSwitch = document.getElementById('cameraSwitch');
+        const cameraSwitchMask = document.getElementById('cameraSwitchMask');
+        const dialBtn = document.getElementById('dialBtn');
+
+        if (!cameraContainer || !cameraVideo) {
+            log('摄像头元素未找到，跳过初始化', 'warning');
+            return Promise.resolve(false);
+        }
+
+        let isDragging = false;
+        let currentX, currentY, initialX, initialY;
+        let xOffset = 0, yOffset = 0;
+
+        cameraContainer.addEventListener('mousedown', dragStart);
+        document.addEventListener('mousemove', drag);
+        document.addEventListener('mouseup', dragEnd);
+        cameraContainer.addEventListener('touchstart', dragStart, { passive: false });
+        document.addEventListener('touchmove', drag, { passive: false });
+        document.addEventListener('touchend', dragEnd);
+
+        function dragStart(e) {
+            if (e.type === 'touchstart') {
+                initialX = e.touches[0].clientX - xOffset;
+                initialY = e.touches[0].clientY - yOffset;
+            } else {
+                initialX = e.clientX - xOffset;
+                initialY = e.clientY - yOffset;
+            }
+            isDragging = true;
+            cameraContainer.classList.add('dragging');
+        }
+
+        function drag(e) {
+            if (isDragging) {
+                e.preventDefault();
+                if (e.type === 'touchmove') {
+                    currentX = e.touches[0].clientX - initialX;
+                    currentY = e.touches[0].clientY - initialY;
+                } else {
+                    currentX = e.clientX - initialX;
+                    currentY = e.clientY - initialY;
+                }
+                xOffset = currentX;
+                yOffset = currentY;
+                cameraContainer.style.transform = `translate3d(${currentX}px, ${currentY}px, 0)`;
+            }
+        }
+
+        function dragEnd() {
+            initialX = currentX;
+            initialY = currentY;
+            isDragging = false;
+            cameraContainer.classList.remove('dragging');
+        }
+
+        return new Promise((resolve) => {
+            window.startCamera = async () => {
+                try {
+                    if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
+                        log('浏览器不支持摄像头API', 'warning');
+                        return false;
+                    }
+                    log('正在请求摄像头权限...', 'info');
+                    this.cameraStream = await navigator.mediaDevices.getUserMedia({
+                        video: { width: 180, height: 240, facingMode: this.currentFacingMode },
+                        audio: false
+                    });
+                    cameraVideo.srcObject = this.cameraStream;
+                    const devices = await navigator.mediaDevices.enumerateDevices();
+                    const videoDevices = devices.filter(device => device.kind === 'videoinput');
+                    if (videoDevices.length > 1) {
+                        if (cameraSwitch) cameraSwitch.classList.add('active'); 
+                    }
+                    cameraContainer.classList.add('active');
+
+                    // 切换时挂断情况
+                    const hasActive = dialBtn.classList.contains('dial-active');
+                    if (!hasActive) {
+                        cameraContainer.classList.remove('active');
+                        cameraSwitch.classList.remove('active');
+                        window.stopCamera();
+                    }
+                    log('摄像头已启动', 'success');
+                    return true;
+                } catch (error) {
+                    log(`启动摄像头失败: ${error.name} - ${error.message}`, 'error');
+                    if (error.name === 'NotAllowedError') {
+                        log('摄像头权限被拒绝，请检查浏览器设置', 'warning');
+                    } else if (error.name === 'NotFoundError') {
+                        log('未找到摄像头设备', 'warning');
+                    } else if (error.name === 'NotReadableError') {
+                        log('摄像头已被其他程序占用', 'warning');
+                    }
+                    return false;
+                }
+            };
+
+            window.stopCamera = () => {
+                if (this.cameraStream) {
+                    this.cameraStream.getTracks().forEach(track => track.stop());
+                    this.cameraStream = null;
+                    cameraVideo.srcObject = null;
+                    log('摄像头已关闭', 'info');
+                }
+            };
+
+            window.switchCamera = async() => {
+                if (window.switchCameraTimer) return;
+                if (this.cameraStream) {
+                    const currentTransform = window.getComputedStyle(cameraContainer).transform;
+                    const originalTransform = currentTransform === 'none' ? 'translate(0px, 0px)' : currentTransform;
+                    cameraContainer.style.setProperty('--original-transform', originalTransform);
+                    cameraContainer.classList.add('flip');
+                    if (cameraSwitchMask) cameraSwitchMask.style.opacity = 0; 
+                    this.currentFacingMode = this.currentFacingMode === 'user' ? 'environment' : 'user';
+                    window.stopCamera();
+                    window.startCamera();
+                    
+                    window.switchCameraTimer = setTimeout(() => {
+                        if (this.currentFacingMode === 'user') {
+                            cameraVideo.style.transform = 'scaleX(-1)';
+                        } else {
+                            cameraVideo.style.transform = 'scaleX(1)';
+                        }
+                        window.switchCameraTimer = null;
+                        cameraContainer.classList.remove('flip');
+                        cameraContainer.style.removeProperty('--original-transform');
+                        if (cameraSwitchMask) cameraSwitchMask.style.opacity = 1; 
+                    }, 500);
+                }
+            };
+
+            window.takePhoto = (question = '描述一下看到的物品') => {
+                return new Promise(async (resolve) => {
+                    const canvas = document.createElement('canvas');
+                    const video = cameraVideo;
+
+                    if (!video || video.readyState !== video.HAVE_ENOUGH_DATA) {
+                        log('无法拍照：摄像头未就绪', 'warning');
+                        resolve({
+                            success: false,
+                            error: '摄像头未就绪，请确保已连接且摄像头已启动'
+                        });
+                        return;
+                    }
+
+                    canvas.width = video.videoWidth || 180;
+                    canvas.height = video.videoHeight || 240;
+                    const ctx = canvas.getContext('2d');
+                    ctx.drawImage(video, 0, 0, canvas.width, canvas.height);
+
+                    const photoData = canvas.toDataURL('image/jpeg', 0.8);
+                    log(`拍照成功，图像数据长度: ${photoData.length}`, 'success');
+
+                    try {
+                        const xz_tester_vision = localStorage.getItem('xz_tester_vision');
+                        if (xz_tester_vision) {
+                            let visionInfo = null;
+
+                            try {
+                                visionInfo = JSON.parse(xz_tester_vision);
+                            } catch (err) {
+                                throw new Error(`视觉配置解析失败`);
+                            }
+
+                            const { url, token } = visionInfo || {};
+                            if (!url || !token) {
+                                throw new Error('视觉分析失败：配置缺少接口地址(url)或令牌(token)');
+                            }
+
+                            log(`正在发送图片到视觉分析接口: ${url}`, 'info');
+
+                            const deviceId = document.getElementById('deviceMac')?.value || '';
+                            const clientId = document.getElementById('clientId')?.value || 'web_test_client';
+
+                            const formData = new FormData();
+                            formData.append('question', question);
+                            formData.append('image', dataURItoBlob(photoData), 'photo.jpg');
+
+                            const response = await fetch(url, {
+                                method: 'POST',
+                                body: formData,
+                                headers: {
+                                    'Device-Id': deviceId,
+                                    'Client-Id': clientId,
+                                    'Authorization': `Bearer ${token}`
+                                }
+                            });
+
+                            if (!response.ok) {
+                                throw new Error(`HTTP error! status: ${response.status}`);
+                            }
+
+                            const analysisResult = await response.json();
+                            log(`视觉分析完成: ${JSON.stringify(analysisResult).substring(0, 200)}...`, 'success');
+
+                            resolve({
+                                success: true,
+                                message: question,
+                                photo_data: photoData,
+                                photo_width: canvas.width,
+                                photo_height: canvas.height,
+                                vision_analysis: analysisResult
+                            });
+                        } else {
+                            log('未配置视觉分析服务', 'warning');
+                        }
+                    } catch (error) {
+                        log(`视觉分析失败: ${error.message}`, 'error');
+                        resolve({
+                            success: true,
+                            message: question,
+                            photo_data: photoData,
+                            photo_width: canvas.width,
+                            photo_height: canvas.height,
+                            vision_analysis: {
+                                success: false,
+                                error: error.message,
+                                fallback: '无法连接到视觉分析服务'
+                            }
+                        });
+                    }
+                });
+            };
+
+            log('摄像头初始化完成', 'success');
+            resolve(true);
+        });
+    }
+}
+
+// 创建并启动应用
+const app = new App();
+// 将应用实例暴露到全局，供其他模块访问
+window.chatApp = app;
+document.addEventListener('DOMContentLoaded', () => {
+    // 初始化应用
+    app.init();
+});
+export default app;

main/digital-human/js/config/default-mcp-tools.json

@@ -0,0 +1,90 @@
+[
+    {
+        "name": "self_camera_take_photo",
+        "description": "Take a photo using the device's camera. This tool captures the current camera frame and returns the image data. You MUST call this tool when user asks to 'take a photo', 'what do you see', 'describe what you see', or similar requests. After getting the photo data, describe what you see in the image. Parameter 'question' is optional, defaults to 'describe objects seen'.",
+        "inputSchema": {
+            "type": "object",
+            "properties": {
+                "question": {
+                    "type": "string",
+                    "description": "Question to guide the photo analysis, e.g., 'describe the objects seen'. Can be empty."
+                }
+            }
+        },
+        "mockResponse": {
+            "success": true,
+            "photo_data": "base64_image_data",
+            "response": "Please describe what you see based on the returned photo_data"
+        }
+    },
+    {
+        "name": "self.get_device_status",
+        "description": "Provides the real-time information of the device, including the current status of the audio speaker, screen, battery, network, etc.\nUse this tool for: \n1. Answering questions about current condition (e.g. what is the current volume of the audio speaker?)\n2. As the first step to control the device (e.g. turn up / down the volume of the audio speaker, etc.)",
+        "inputSchema": {
+            "type": "object",
+            "properties": {}
+        },
+        "mockResponse": {
+            "audio_speaker": {
+                "volume": 50,
+                "muted": false
+            },
+            "screen": {
+                "brightness": 80,
+                "theme": "light"
+            },
+            "battery": {
+                "level": 85,
+                "charging": false
+            },
+            "network": {
+                "connected": true,
+                "type": "wifi"
+            }
+        }
+    },
+    {
+        "name": "self.audio_speaker.set_volume",
+        "description": "Set the volume of the audio speaker. If the current volume is unknown, you must call `self.get_device_status` tool first and then call this tool.",
+        "inputSchema": {
+            "type": "object",
+            "properties": {
+                "volume": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "maximum": 100
+                }
+            },
+            "required": [
+                "volume"
+            ]
+        },
+        "mockResponse": {
+            "success": true,
+            "volume": "${volume}",
+            "message": "音量已设置为 ${volume}"
+        }
+    },
+    {
+        "name": "self.screen.set_brightness",
+        "description": "Set the brightness of the screen.",
+        "inputSchema": {
+            "type": "object",
+            "properties": {
+                "brightness": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "maximum": 100
+                }
+            },
+            "required": [
+                "brightness"
+            ]
+        },
+        "mockResponse": {
+            "success": true,
+            "brightness": "${brightness}",
+            "message": "亮度已设置为 ${brightness}"
+        }
+    }
+]

main/digital-human/js/config/manager.js

@@ -0,0 +1,127 @@
+// 配置管理模块
+
+// 默认唤醒词列表
+export const DEFAULT_WAKE_WORDS = '你好小智\n你好小志\n小爱同学\n你好小鑫\n你好小新\n小美同学\n小龙小龙\n喵喵同学\n小滨小滨\n小冰小冰\n嘿你好呀';
+
+// 生成随机MAC地址
+function generateRandomMac() {
+    const hexDigits = '0123456789ABCDEF';
+    let mac = '';
+    for (let i = 0; i < 6; i++) {
+        if (i > 0) mac += ':';
+        for (let j = 0; j < 2; j++) {
+            mac += hexDigits.charAt(Math.floor(Math.random() * 16));
+        }
+    }
+    return mac;
+}
+
+// 加载配置
+export function loadConfig() {
+    const deviceMacInput = document.getElementById('deviceMac');
+    const deviceNameInput = document.getElementById('deviceName');
+    const clientIdInput = document.getElementById('clientId');
+    const otaUrlInput = document.getElementById('otaUrl');
+    const wakewordWsUrlInput = document.getElementById('wakewordWsUrl');
+    const wakewordEnabledInput = document.getElementById('wakewordEnabled');
+    const wakewordListInput = document.getElementById('wakewordList');
+
+    // 从localStorage加载MAC地址，如果没有则生成新的
+    let savedMac = localStorage.getItem('xz_tester_deviceMac');
+    if (!savedMac) {
+        savedMac = generateRandomMac();
+        localStorage.setItem('xz_tester_deviceMac', savedMac);
+    }
+    deviceMacInput.value = savedMac;
+
+    // 从localStorage加载其他配置
+    const savedDeviceName = localStorage.getItem('xz_tester_deviceName');
+    if (savedDeviceName) {
+        deviceNameInput.value = savedDeviceName;
+    }
+
+    const savedClientId = localStorage.getItem('xz_tester_clientId');
+    if (savedClientId) {
+        clientIdInput.value = savedClientId;
+    }
+
+    const savedOtaUrl = localStorage.getItem('xz_tester_otaUrl');
+    if (savedOtaUrl) {
+        otaUrlInput.value = savedOtaUrl;
+    }
+
+    const savedWakewordWsUrl = localStorage.getItem('xz_tester_wakewordWsUrl');
+    if (savedWakewordWsUrl !== null && wakewordWsUrlInput) {
+        wakewordWsUrlInput.value = savedWakewordWsUrl;
+    }
+
+    const savedWakewordEnabled = localStorage.getItem('xz_tester_wakewordEnabled');
+    if (savedWakewordEnabled !== null && wakewordEnabledInput) {
+        wakewordEnabledInput.value = savedWakewordEnabled;
+    }
+
+    const savedWakewordList = localStorage.getItem('xz_tester_wakewordList');
+    if (savedWakewordList !== null && wakewordListInput) {
+        wakewordListInput.value = savedWakewordList;
+    } else if (wakewordListInput) {
+        wakewordListInput.value = DEFAULT_WAKE_WORDS;
+    }
+
+    const emojiEnabledInput = document.getElementById('emojiEnabled');
+    const savedEmojiEnabled = localStorage.getItem('xz_tester_emojiEnabled');
+    if (savedEmojiEnabled !== null && emojiEnabledInput) {
+        emojiEnabledInput.value = savedEmojiEnabled;
+    }
+}
+
+// 保存配置
+export function saveConfig() {
+    const deviceMacInput = document.getElementById('deviceMac');
+    const deviceNameInput = document.getElementById('deviceName');
+    const clientIdInput = document.getElementById('clientId');
+    const wakewordWsUrlInput = document.getElementById('wakewordWsUrl');
+    const wakewordEnabledInput = document.getElementById('wakewordEnabled');
+    const wakewordListInput = document.getElementById('wakewordList');
+
+    localStorage.setItem('xz_tester_deviceMac', deviceMacInput.value);
+    localStorage.setItem('xz_tester_deviceName', deviceNameInput.value);
+    localStorage.setItem('xz_tester_clientId', clientIdInput.value);
+    const emojiEnabledInput = document.getElementById('emojiEnabled');
+    if (emojiEnabledInput) {
+        localStorage.setItem('xz_tester_emojiEnabled', emojiEnabledInput.value);
+    }
+    if (wakewordEnabledInput) {
+        localStorage.setItem('xz_tester_wakewordEnabled', wakewordEnabledInput.value);
+    }
+    if (wakewordListInput) {
+        localStorage.setItem('xz_tester_wakewordList', wakewordListInput.value);
+    }
+    if (wakewordWsUrlInput && wakewordWsUrlInput.value.trim()) {
+        localStorage.setItem('xz_tester_wakewordWsUrl', wakewordWsUrlInput.value.trim());
+    }
+}
+
+// 获取配置值
+export function getConfig() {
+    // 从DOM获取值
+    const deviceMac = document.getElementById('deviceMac')?.value.trim() || '';
+    const deviceName = document.getElementById('deviceName')?.value.trim() || '';
+    const clientId = document.getElementById('clientId')?.value.trim() || '';
+    const emojiEnabled = document.getElementById('emojiEnabled')?.value !== 'false';
+
+    return {
+        deviceId: deviceMac,  // 使用MAC地址作为deviceId
+        deviceName,
+        deviceMac,
+        clientId,
+        emojiEnabled
+    };
+}
+
+// 保存连接URL
+export function saveConnectionUrls() {
+    const otaUrl = document.getElementById('otaUrl').value.trim();
+    const wsUrl = document.getElementById('serverUrl').value.trim();
+    localStorage.setItem('xz_tester_otaUrl', otaUrl);
+    localStorage.setItem('xz_tester_wsUrl', wsUrl);
+}

main/digital-human/js/core/audio/opus-codec.js

@@ -0,0 +1,182 @@
+import { log } from '../../utils/logger.js?v=0205';
+
+
+// 检查Opus库是否已加载
+export function checkOpusLoaded() {
+    try {
+        // 检查Module是否存在（本地库导出的全局变量）
+        if (typeof Module === 'undefined') {
+            throw new Error('Opus库未加载，Module对象不存在');
+        }
+
+        // 尝试先使用Module.instance（libopus.js最后一行导出方式）
+        if (typeof Module.instance !== 'undefined' && typeof Module.instance._opus_decoder_get_size === 'function') {
+            // 使用Module.instance对象替换全局Module对象
+            window.ModuleInstance = Module.instance;
+            log('Opus库加载成功（使用Module.instance）', 'success');
+
+            // 3秒后隐藏状态
+            const statusElement = document.getElementById('scriptStatus');
+            if (statusElement) statusElement.style.display = 'none';
+            return;
+        }
+
+        // 如果没有Module.instance，检查全局Module函数
+        if (typeof Module._opus_decoder_get_size === 'function') {
+            window.ModuleInstance = Module;
+            log('Opus库加载成功（使用全局Module）', 'success');
+
+            // 3秒后隐藏状态
+            const statusElement = document.getElementById('scriptStatus');
+            if (statusElement) statusElement.style.display = 'none';
+            return;
+        }
+
+        throw new Error('Opus解码函数未找到，可能Module结构不正确');
+    } catch (err) {
+        log(`Opus库加载失败，请检查libopus.js文件是否存在且正确: ${err.message}`, 'error');
+    }
+}
+
+
+// 创建一个Opus编码器
+let opusEncoder = null;
+export function initOpusEncoder() {
+    try {
+        if (opusEncoder) {
+            return opusEncoder; // 已经初始化过
+        }
+
+        if (!window.ModuleInstance) {
+            log('无法创建Opus编码器：ModuleInstance不可用', 'error');
+            return;
+        }
+
+        // 初始化一个Opus编码器
+        const mod = window.ModuleInstance;
+        const sampleRate = 16000; // 16kHz采样率
+        const channels = 1;       // 单声道
+        const application = 2048; // OPUS_APPLICATION_VOIP = 2048
+
+        // 创建编码器
+        opusEncoder = {
+            channels: channels,
+            sampleRate: sampleRate,
+            frameSize: 960, // 60ms @ 16kHz = 60 * 16 = 960 samples
+            maxPacketSize: 4000, // 最大包大小
+            module: mod,
+
+            // 初始化编码器
+            init: function () {
+                try {
+                    // 获取编码器大小
+                    const encoderSize = mod._opus_encoder_get_size(this.channels);
+                    log(`Opus编码器大小: ${encoderSize}字节`, 'info');
+
+                    // 分配内存
+                    this.encoderPtr = mod._malloc(encoderSize);
+                    if (!this.encoderPtr) {
+                        throw new Error("无法分配编码器内存");
+                    }
+
+                    // 初始化编码器
+                    const err = mod._opus_encoder_init(
+                        this.encoderPtr,
+                        this.sampleRate,
+                        this.channels,
+                        application
+                    );
+
+                    if (err < 0) {
+                        throw new Error(`Opus编码器初始化失败: ${err}`);
+                    }
+
+                    // 设置位率 (16kbps)
+                    mod._opus_encoder_ctl(this.encoderPtr, 4002, 16000); // OPUS_SET_BITRATE
+
+                    // 设置复杂度 (0-10, 越高质量越好但CPU使用越多)
+                    mod._opus_encoder_ctl(this.encoderPtr, 4010, 5);     // OPUS_SET_COMPLEXITY
+
+                    // 设置使用DTX (不传输静音帧)
+                    mod._opus_encoder_ctl(this.encoderPtr, 4016, 1);     // OPUS_SET_DTX
+
+                    log("Opus编码器初始化成功", 'success');
+                    return true;
+                } catch (error) {
+                    if (this.encoderPtr) {
+                        mod._free(this.encoderPtr);
+                        this.encoderPtr = null;
+                    }
+                    log(`Opus编码器初始化失败: ${error.message}`, 'error');
+                    return false;
+                }
+            },
+
+            // 编码PCM数据为Opus
+            encode: function (pcmData) {
+                if (!this.encoderPtr) {
+                    if (!this.init()) {
+                        return null;
+                    }
+                }
+
+                try {
+                    const mod = this.module;
+
+                    // 为PCM数据分配内存
+                    const pcmPtr = mod._malloc(pcmData.length * 2); // 2字节/int16
+
+                    // 将PCM数据复制到HEAP
+                    for (let i = 0; i < pcmData.length; i++) {
+                        mod.HEAP16[(pcmPtr >> 1) + i] = pcmData[i];
+                    }
+
+                    // 为输出分配内存
+                    const outPtr = mod._malloc(this.maxPacketSize);
+
+                    // 进行编码
+                    const encodedLen = mod._opus_encode(
+                        this.encoderPtr,
+                        pcmPtr,
+                        this.frameSize,
+                        outPtr,
+                        this.maxPacketSize
+                    );
+
+                    if (encodedLen < 0) {
+                        throw new Error(`Opus编码失败: ${encodedLen}`);
+                    }
+
+                    // 复制编码后的数据
+                    const opusData = new Uint8Array(encodedLen);
+                    for (let i = 0; i < encodedLen; i++) {
+                        opusData[i] = mod.HEAPU8[outPtr + i];
+                    }
+
+                    // 释放内存
+                    mod._free(pcmPtr);
+                    mod._free(outPtr);
+
+                    return opusData;
+                } catch (error) {
+                    log(`Opus编码出错: ${error.message}`, 'error');
+                    return null;
+                }
+            },
+
+            // 销毁编码器
+            destroy: function () {
+                if (this.encoderPtr) {
+                    this.module._free(this.encoderPtr);
+                    this.encoderPtr = null;
+                }
+            }
+        };
+
+        opusEncoder.init();
+        return opusEncoder;
+    } catch (error) {
+        log(`创建Opus编码器失败: ${error.message}`, 'error');
+        return false;
+    }
+}

main/digital-human/js/core/audio/player.js

@@ -0,0 +1,297 @@
+// 音频播放模块
+import BlockingQueue from '../../utils/blocking-queue.js?v=0205';
+import { log } from '../../utils/logger.js?v=0205';
+import { createStreamingContext } from './stream-context.js?v=0205';
+
+// 音频播放器类
+export class AudioPlayer {
+    constructor() {
+        // 音频参数
+        this.SAMPLE_RATE = 16000;
+        this.CHANNELS = 1;
+        this.FRAME_SIZE = 960;
+        this.MIN_AUDIO_DURATION = 0.12;
+
+        // 状态
+        this.audioContext = null;
+        this.opusDecoder = null;
+        this.streamingContext = null;
+        this.queue = new BlockingQueue();
+        this.isPlaying = false;
+    }
+
+    // 获取或创建AudioContext
+    getAudioContext() {
+        if (!this.audioContext) {
+            this.audioContext = new (window.AudioContext || window.webkitAudioContext)({
+                sampleRate: this.SAMPLE_RATE,
+                latencyHint: 'interactive'
+            });
+            log('创建音频上下文，采样率: ' + this.SAMPLE_RATE + 'Hz', 'debug');
+        }
+        return this.audioContext;
+    }
+
+    // 初始化Opus解码器
+    async initOpusDecoder() {
+        if (this.opusDecoder) return this.opusDecoder;
+
+        try {
+            if (typeof window.ModuleInstance === 'undefined') {
+                if (typeof Module !== 'undefined') {
+                    window.ModuleInstance = Module;
+                    log('使用全局Module作为ModuleInstance', 'info');
+                } else {
+                    throw new Error('Opus库未加载，ModuleInstance和Module对象都不存在');
+                }
+            }
+
+            const mod = window.ModuleInstance;
+
+            this.opusDecoder = {
+                channels: this.CHANNELS,
+                rate: this.SAMPLE_RATE,
+                frameSize: this.FRAME_SIZE,
+                module: mod,
+                decoderPtr: null,
+
+                init: function () {
+                    if (this.decoderPtr) return true;
+
+                    const decoderSize = mod._opus_decoder_get_size(this.channels);
+                    log(`Opus解码器大小: ${decoderSize}字节`, 'debug');
+
+                    this.decoderPtr = mod._malloc(decoderSize);
+                    if (!this.decoderPtr) {
+                        throw new Error("无法分配解码器内存");
+                    }
+
+                    const err = mod._opus_decoder_init(
+                        this.decoderPtr,
+                        this.rate,
+                        this.channels
+                    );
+
+                    if (err < 0) {
+                        this.destroy();
+                        throw new Error(`Opus解码器初始化失败: ${err}`);
+                    }
+
+                    log("Opus解码器初始化成功", 'success');
+                    return true;
+                },
+
+                decode: function (opusData) {
+                    if (!this.decoderPtr) {
+                        if (!this.init()) {
+                            throw new Error("解码器未初始化且无法初始化");
+                        }
+                    }
+
+                    try {
+                        const mod = this.module;
+
+                        const opusPtr = mod._malloc(opusData.length);
+                        mod.HEAPU8.set(opusData, opusPtr);
+
+                        const pcmPtr = mod._malloc(this.frameSize * 2);
+
+                        const decodedSamples = mod._opus_decode(
+                            this.decoderPtr,
+                            opusPtr,
+                            opusData.length,
+                            pcmPtr,
+                            this.frameSize,
+                            0
+                        );
+
+                        if (decodedSamples < 0) {
+                            mod._free(opusPtr);
+                            mod._free(pcmPtr);
+                            throw new Error(`Opus解码失败: ${decodedSamples}`);
+                        }
+
+                        const decodedData = new Int16Array(decodedSamples);
+                        for (let i = 0; i < decodedSamples; i++) {
+                            decodedData[i] = mod.HEAP16[(pcmPtr >> 1) + i];
+                        }
+
+                        mod._free(opusPtr);
+                        mod._free(pcmPtr);
+
+                        return decodedData;
+                    } catch (error) {
+                        log(`Opus解码错误: ${error.message}`, 'error');
+                        return new Int16Array(0);
+                    }
+                },
+
+                destroy: function () {
+                    if (this.decoderPtr) {
+                        this.module._free(this.decoderPtr);
+                        this.decoderPtr = null;
+                    }
+                }
+            };
+
+            if (!this.opusDecoder.init()) {
+                throw new Error("Opus解码器初始化失败");
+            }
+
+            return this.opusDecoder;
+
+        } catch (error) {
+            log(`Opus解码器初始化失败: ${error.message}`, 'error');
+            this.opusDecoder = null;
+            throw error;
+        }
+    }
+
+    // 启动音频缓冲
+    async startAudioBuffering() {
+        log("开始音频缓冲...", 'info');
+
+        this.initOpusDecoder().catch(error => {
+            log(`预初始化Opus解码器失败: ${error.message}`, 'warning');
+        });
+
+        const timeout = 400;
+        while (true) {
+            const packets = await this.queue.dequeue(
+                6,
+                timeout,
+                (count) => {
+                    log(`缓冲超时，当前缓冲包数: ${count}，开始播放`, 'info');
+                }
+            );
+            if (packets.length) {
+                log(`已缓冲 ${packets.length} 个音频包，开始播放`, 'info');
+                this.streamingContext.pushAudioBuffer(packets);
+            }
+
+            while (true) {
+                const data = await this.queue.dequeue(99, 30);
+                if (data.length) {
+                    this.streamingContext.pushAudioBuffer(data);
+                } else {
+                    break;
+                }
+            }
+        }
+    }
+
+    // 播放已缓冲的音频
+    async playBufferedAudio() {
+        try {
+            this.audioContext = this.getAudioContext();
+
+            if (!this.opusDecoder) {
+                log('初始化Opus解码器...', 'info');
+                try {
+                    this.opusDecoder = await this.initOpusDecoder();
+                    if (!this.opusDecoder) {
+                        throw new Error('解码器初始化失败');
+                    }
+                    log('Opus解码器初始化成功', 'success');
+                } catch (error) {
+                    log('Opus解码器初始化失败: ' + error.message, 'error');
+                    this.isPlaying = false;
+                    return;
+                }
+            }
+
+            if (!this.streamingContext) {
+                this.streamingContext = createStreamingContext(
+                    this.opusDecoder,
+                    this.audioContext,
+                    this.SAMPLE_RATE,
+                    this.CHANNELS,
+                    this.MIN_AUDIO_DURATION
+                );
+            }
+
+            this.streamingContext.decodeOpusFrames();
+            this.streamingContext.startPlaying();
+
+        } catch (error) {
+            log(`播放已缓冲的音频出错: ${error.message}`, 'error');
+            this.isPlaying = false;
+            this.streamingContext = null;
+        }
+    }
+
+    // 添加音频数据到队列
+    enqueueAudioData(opusData) {
+        if (opusData.length > 0) {
+            this.queue.enqueue(opusData);
+        } else {
+            log('收到空音频数据帧，可能是结束标志', 'warning');
+            if (this.isPlaying && this.streamingContext) {
+                this.streamingContext.endOfStream = true;
+            }
+        }
+    }
+
+    // 预加载解码器
+    async preload() {
+        log('预加载Opus解码器...', 'info');
+        try {
+            await this.initOpusDecoder();
+            log('Opus解码器预加载成功', 'success');
+        } catch (error) {
+            log(`Opus解码器预加载失败: ${error.message}，将在需要时重试`, 'warning');
+        }
+    }
+
+    // 启动播放系统
+    async start() {
+        await this.preload();
+        this.playBufferedAudio();
+        this.startAudioBuffering();
+    }
+
+    // 获取音频包统计信息
+    getAudioStats() {
+        if (!this.streamingContext) {
+            return {
+                pendingDecode: 0,
+                pendingPlay: 0,
+                totalPending: 0
+            };
+        }
+
+        const pendingDecode = this.streamingContext.getPendingDecodeCount();
+        const pendingPlay = this.streamingContext.getPendingPlayCount();
+
+        return {
+            pendingDecode,  // 待解码包数
+            pendingPlay,    // 待播放包数
+            totalPending: pendingDecode + pendingPlay  // 总待处理包数
+        };
+    }
+
+    // 清空所有音频缓冲并停止播放
+    clearAllAudio() {
+        log('AudioPlayer: 清空所有音频', 'info');
+
+        // 清空接收队列（使用clear方法保持对象引用）
+        this.queue.clear();
+
+        // 清空流上下文的所有缓冲
+        if (this.streamingContext) {
+            this.streamingContext.clearAllBuffers();
+        }
+
+        log('AudioPlayer: 音频已清空', 'success');
+    }
+}
+
+// 创建单例
+let audioPlayerInstance = null;
+
+export function getAudioPlayer() {
+    if (!audioPlayerInstance) {
+        audioPlayerInstance = new AudioPlayer();
+    }
+    return audioPlayerInstance;
+}

main/digital-human/js/core/audio/recorder.js

@@ -0,0 +1,384 @@
+// Audio recording module
+import { log } from '../../utils/logger.js?v=0205';
+import { initOpusEncoder } from './opus-codec.js?v=0205';
+import { getAudioPlayer } from './player.js?v=0205';
+
+// Audio recorder class
+export class AudioRecorder {
+    constructor() {
+        this.isRecording = false;
+        this.audioContext = null;
+        this.analyser = null;
+        this.audioProcessor = null;
+        this.audioProcessorType = null;
+        this.audioSource = null;
+        this.opusEncoder = null;
+        this.pcmDataBuffer = new Int16Array();
+        this.audioBuffers = [];
+        this.totalAudioSize = 0;
+        this.visualizationRequest = null;
+        this.recordingTimer = null;
+        this.websocket = null;
+        // Callback functions
+        this.onRecordingStart = null;
+        this.onRecordingStop = null;
+        this.onVisualizerUpdate = null;
+    }
+
+    // Set WebSocket instance
+    setWebSocket(ws) {
+        this.websocket = ws;
+    }
+
+    // Get AudioContext instance
+    getAudioContext() {
+        return getAudioPlayer().getAudioContext();
+    }
+
+    // Initialize encoder
+    initEncoder() {
+        if (!this.opusEncoder) {
+            this.opusEncoder = initOpusEncoder();
+        }
+        return this.opusEncoder;
+    }
+
+    // PCM processor code
+    getAudioProcessorCode() {
+        return `
+            class AudioRecorderProcessor extends AudioWorkletProcessor {
+                constructor() {
+                    super();
+                    this.buffers = [];
+                    this.frameSize = 960;
+                    this.buffer = new Int16Array(this.frameSize);
+                    this.bufferIndex = 0;
+                    this.isRecording = false;
+                    this.port.onmessage = (event) => {
+                        if (event.data.command === 'start') {
+                            this.isRecording = true;
+                            this.port.postMessage({ type: 'status', status: 'started' });
+                        } else if (event.data.command === 'stop') {
+                            this.isRecording = false;
+                            if (this.bufferIndex > 0) {
+                                const finalBuffer = this.buffer.slice(0, this.bufferIndex);
+                                this.port.postMessage({ type: 'buffer', buffer: finalBuffer });
+                                this.bufferIndex = 0;
+                            }
+                            this.port.postMessage({ type: 'status', status: 'stopped' });
+                        }
+                    };
+                }
+                process(inputs, outputs, parameters) {
+                    if (!this.isRecording) return true;
+                    const input = inputs[0][0];
+                    if (!input) return true;
+                    for (let i = 0; i < input.length; i++) {
+                        if (this.bufferIndex >= this.frameSize) {
+                            this.port.postMessage({ type: 'buffer', buffer: this.buffer.slice(0) });
+                            this.bufferIndex = 0;
+                        }
+                        this.buffer[this.bufferIndex++] = Math.max(-32768, Math.min(32767, Math.floor(input[i] * 32767)));
+                    }
+                    return true;
+                }
+            }
+            registerProcessor('audio-recorder-processor', AudioRecorderProcessor);
+        `;
+    }
+
+    // Create audio processor
+    async createAudioProcessor() {
+        this.audioContext = this.getAudioContext();
+        try {
+            if (this.audioContext.audioWorklet) {
+                const blob = new Blob([this.getAudioProcessorCode()], { type: 'application/javascript' });
+                const url = URL.createObjectURL(blob);
+                await this.audioContext.audioWorklet.addModule(url);
+                URL.revokeObjectURL(url);
+                const audioProcessor = new AudioWorkletNode(this.audioContext, 'audio-recorder-processor');
+                audioProcessor.port.onmessage = (event) => {
+                    if (event.data.type === 'buffer') {
+                        this.processPCMBuffer(event.data.buffer);
+                    }
+                };
+                log('使用AudioWorklet处理音频', 'success');
+                const silent = this.audioContext.createGain();
+                silent.gain.value = 0;
+                audioProcessor.connect(silent);
+                silent.connect(this.audioContext.destination);
+                return { node: audioProcessor, type: 'worklet' };
+            } else {
+                log('AudioWorklet不可用，使用ScriptProcessorNode作为后备方案', 'warning');
+                return this.createScriptProcessor();
+            }
+        } catch (error) {
+            log(`创建音频处理器失败: ${error.message}，尝试后备方案`, 'error');
+            return this.createScriptProcessor();
+        }
+    }
+
+    // Create ScriptProcessor as fallback
+    createScriptProcessor() {
+        try {
+            const frameSize = 4096;
+            const scriptProcessor = this.audioContext.createScriptProcessor(frameSize, 1, 1);
+            scriptProcessor.onaudioprocess = (event) => {
+                if (!this.isRecording) return;
+                const input = event.inputBuffer.getChannelData(0);
+                const buffer = new Int16Array(input.length);
+                for (let i = 0; i < input.length; i++) {
+                    buffer[i] = Math.max(-32768, Math.min(32767, Math.floor(input[i] * 32767)));
+                }
+                this.processPCMBuffer(buffer);
+            };
+            const silent = this.audioContext.createGain();
+            silent.gain.value = 0;
+            scriptProcessor.connect(silent);
+            silent.connect(this.audioContext.destination);
+            log('使用ScriptProcessorNode作为后备方案成功', 'warning');
+            return { node: scriptProcessor, type: 'processor' };
+        } catch (fallbackError) {
+            log(`后备方案也失败: ${fallbackError.message}`, 'error');
+            return null;
+        }
+    }
+
+    // Process PCM buffer data
+    processPCMBuffer(buffer) {
+        if (!this.isRecording) return;
+        const newBuffer = new Int16Array(this.pcmDataBuffer.length + buffer.length);
+        newBuffer.set(this.pcmDataBuffer);
+        newBuffer.set(buffer, this.pcmDataBuffer.length);
+        this.pcmDataBuffer = newBuffer;
+        const samplesPerFrame = 960;
+        while (this.pcmDataBuffer.length >= samplesPerFrame) {
+            const frameData = this.pcmDataBuffer.slice(0, samplesPerFrame);
+            this.pcmDataBuffer = this.pcmDataBuffer.slice(samplesPerFrame);
+            this.encodeAndSendOpus(frameData);
+        }
+    }
+
+    // Encode and send Opus data
+    encodeAndSendOpus(pcmData = null) {
+        if (!this.opusEncoder) {
+            log('Opus编码器未初始化', 'error');
+            return;
+        }
+        try {
+            if (pcmData) {
+                const opusData = this.opusEncoder.encode(pcmData);
+                if (opusData && opusData.length > 0) {
+                    this.audioBuffers.push(opusData.buffer);
+                    this.totalAudioSize += opusData.length;
+                    if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
+                        try {
+                            this.websocket.send(opusData.buffer);
+                        } catch (error) {
+                            log(`WebSocket发送错误: ${error.message}`, 'error');
+                        }
+                    }
+                } else {
+                    log('Opus编码失败，未返回有效数据', 'error');
+                }
+            } else {
+                if (this.pcmDataBuffer.length > 0) {
+                    const samplesPerFrame = 960;
+                    if (this.pcmDataBuffer.length < samplesPerFrame) {
+                        const paddedBuffer = new Int16Array(samplesPerFrame);
+                        paddedBuffer.set(this.pcmDataBuffer);
+                        this.encodeAndSendOpus(paddedBuffer);
+                    } else {
+                        this.encodeAndSendOpus(this.pcmDataBuffer.slice(0, samplesPerFrame));
+                    }
+                    this.pcmDataBuffer = new Int16Array(0);
+                }
+            }
+        } catch (error) {
+            log(`Opus编码错误: ${error.message}`, 'error');
+        }
+    }
+
+    // Start recording
+    async start() {
+        if (this.isRecording) return false;
+        try {
+            if (!this.initEncoder()) {
+                log('无法开始录音: Opus编码器初始化失败', 'error');
+                return false;
+            }
+            log('请至少录制1-2秒音频以确保收集足够的数据', 'info');
+            const stream = await navigator.mediaDevices.getUserMedia({ audio: { echoCancellation: true, noiseSuppression: true, sampleRate: 16000, channelCount: 1 } });
+            this.audioContext = this.getAudioContext();
+            if (this.audioContext.state === 'suspended') {
+                await this.audioContext.resume();
+            }
+            const processorResult = await this.createAudioProcessor();
+            if (!processorResult) {
+                log('无法创建音频处理器', 'error');
+                return false;
+            }
+            this.audioProcessor = processorResult.node;
+            this.audioProcessorType = processorResult.type;
+            this.audioSource = this.audioContext.createMediaStreamSource(stream);
+            this.analyser = this.audioContext.createAnalyser();
+            this.analyser.fftSize = 2048;
+            this.audioSource.connect(this.analyser);
+            this.audioSource.connect(this.audioProcessor);
+            this.pcmDataBuffer = new Int16Array();
+            this.audioBuffers = [];
+            this.totalAudioSize = 0;
+            this.isRecording = true;
+            if (this.audioProcessorType === 'worklet' && this.audioProcessor.port) {
+                this.audioProcessor.port.postMessage({ command: 'start' });
+            }
+            // Send listening start message
+            if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
+                log(`已发送录音开始消息`, 'info');
+            } else {
+                log('WebSocket未连接，无法发送开始消息', 'error');
+                return false;
+            }
+            // Start visualization
+            if (this.onVisualizerUpdate) {
+                const dataArray = new Uint8Array(this.analyser.frequencyBinCount);
+                this.startVisualization(dataArray);
+            }
+            // Immediately notify recording start, update button state
+            if (this.onRecordingStart) {
+                this.onRecordingStart(0);
+            }
+            // Start recording timer
+            let recordingSeconds = 0;
+            this.recordingTimer = setInterval(() => {
+                recordingSeconds += 0.1;
+                if (this.onRecordingStart) {
+                    this.onRecordingStart(recordingSeconds);
+                }
+            }, 100);
+            log('已开始PCM直接录音', 'success');
+            return true;
+        } catch (error) {
+            log(`直接录音启动错误: ${error.message}`, 'error');
+            this.isRecording = false;
+            return false;
+        }
+    }
+
+    // Start visualization
+    startVisualization(dataArray) {
+        const draw = () => {
+            this.visualizationRequest = requestAnimationFrame(() => draw());
+            if (!this.isRecording) return;
+            this.analyser.getByteFrequencyData(dataArray);
+            if (this.onVisualizerUpdate) {
+                this.onVisualizerUpdate(dataArray);
+            }
+        };
+        draw();
+    }
+
+    // Stop recording
+    stop() {
+        if (!this.isRecording) return false;
+        try {
+            this.isRecording = false;
+            if (this.audioProcessor) {
+                if (this.audioProcessorType === 'worklet' && this.audioProcessor.port) {
+                    this.audioProcessor.port.postMessage({ command: 'stop' });
+                }
+                this.audioProcessor.disconnect();
+                this.audioProcessor = null;
+            }
+            if (this.audioSource) {
+                this.audioSource.disconnect();
+                this.audioSource = null;
+            }
+            if (this.visualizationRequest) {
+                cancelAnimationFrame(this.visualizationRequest);
+                this.visualizationRequest = null;
+            }
+            if (this.recordingTimer) {
+                clearInterval(this.recordingTimer);
+                this.recordingTimer = null;
+            }
+            // Encode and send remaining data
+            this.encodeAndSendOpus();
+            // Send end signal
+            if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
+                const emptyOpusFrame = new Uint8Array(0);
+                this.websocket.send(emptyOpusFrame);
+                log('已发送录音停止信号', 'info');
+            }
+            if (this.onRecordingStop) {
+                this.onRecordingStop();
+            }
+            log('已停止PCM直接录音', 'success');
+            return true;
+        } catch (error) {
+            log(`直接录音停止错误: ${error.message}`, 'error');
+            return false;
+        }
+    }
+
+    // Get analyser
+    getAnalyser() {
+        return this.analyser;
+    }
+}
+
+// Create singleton instance
+let audioRecorderInstance = null;
+
+export function getAudioRecorder() {
+    if (!audioRecorderInstance) {
+        audioRecorderInstance = new AudioRecorder();
+    }
+    return audioRecorderInstance;
+}
+
+/**
+ * Check if microphone is available
+ * @returns {Promise<boolean>} Returns true if available, false if not available
+ */
+export async function checkMicrophoneAvailability() {
+    // Check if browser supports getUserMedia API
+    if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
+        log('浏览器不支持getUserMedia API', 'warning');
+        return false;
+    }
+    try {
+        // Try to access microphone
+        const stream = await navigator.mediaDevices.getUserMedia({ audio: { echoCancellation: true, noiseSuppression: true, sampleRate: 16000, channelCount: 1 } });
+        // Immediately stop all tracks to release microphone
+        stream.getTracks().forEach(track => track.stop());
+        log('麦克风可用性检查成功', 'success');
+        return true;
+    } catch (error) {
+        log(`麦克风不可用: ${error.message}`, 'warning');
+        return false;
+    }
+}
+
+/**
+ * Check if it is HTTP non-localhost access
+ * @returns {boolean} Returns true if it is HTTP non-localhost access
+ */
+export function isHttpNonLocalhost() {
+    const protocol = window.location.protocol;
+    const hostname = window.location.hostname;
+    // Check if it is HTTP protocol
+    if (protocol !== 'http:') {
+        return false;
+    }
+    // localhost and 127.0.0.1 can use microphone
+    if (hostname === 'localhost' || hostname === '127.0.0.1') {
+        return false;
+    }
+    // Private IP addresses can also use microphone (browser allows)
+    if (hostname.startsWith('192.168.') || hostname.startsWith('10.') || hostname.startsWith('172.')) {
+        return false;
+    }
+    // Other HTTP access is considered non-localhost
+    return true;
+}

main/digital-human/js/core/audio/stream-context.js

@@ -0,0 +1,221 @@
+import BlockingQueue from '../../utils/blocking-queue.js?v=0205';
+import { log } from '../../utils/logger.js?v=0205';
+
+// 音频流播放上下文类
+export class StreamingContext {
+    constructor(opusDecoder, audioContext, sampleRate, channels, minAudioDuration) {
+        this.opusDecoder = opusDecoder;
+        this.audioContext = audioContext;
+
+        // 音频参数
+        this.sampleRate = sampleRate;
+        this.channels = channels;
+        this.minAudioDuration = minAudioDuration;
+
+        // 初始化队列和状态
+        this.queue = [];          // 已解码的PCM队列。正在播放
+        this.activeQueue = new BlockingQueue(); // 已解码的PCM队列。准备播放
+        this.pendingAudioBufferQueue = [];  // 待处理的缓存队列
+        this.audioBufferQueue = new BlockingQueue();  // 缓存队列
+        this.playing = false;     // 是否正在播放
+        this.endOfStream = false; // 是否收到结束信号
+        this.source = null;       // 当前音频源
+        this.totalSamples = 0;    // 累积的总样本数
+        this.lastPlayTime = 0;    // 上次播放的时间戳
+        this.scheduledEndTime = 0; // 已调度音频的结束时间
+
+        // 初始化分析器节点（供Live2D使用）
+        this.analyser = this.audioContext.createAnalyser();
+        this.analyser.fftSize = 256;
+    }
+
+    // 缓存音频数组
+    pushAudioBuffer(item) {
+        this.audioBufferQueue.enqueue(...item);
+    }
+
+    // 获取需要处理缓存队列，单线程：在audioBufferQueue一直更新的状态下不会出现安全问题
+    async getPendingAudioBufferQueue() {
+        // 等待数据到达并获取
+        const data = await this.audioBufferQueue.dequeue();
+        // 赋值给待处理队列
+        this.pendingAudioBufferQueue = data;
+    }
+
+    // 获取正在播放已解码的PCM队列，单线程：在activeQueue一直更新的状态下不会出现安全问题
+    async getQueue(minSamples) {
+        const num = minSamples - this.queue.length > 0 ? minSamples - this.queue.length : 1;
+
+        // 等待数据并获取
+        const tempArray = await this.activeQueue.dequeue(num);
+        this.queue.push(...tempArray);
+    }
+
+    // 将Int16音频数据转换为Float32音频数据
+    convertInt16ToFloat32(int16Data) {
+        const float32Data = new Float32Array(int16Data.length);
+        for (let i = 0; i < int16Data.length; i++) {
+            // 将[-32768,32767]范围转换为[-1,1]，统一使用32768.0避免不对称失真
+            float32Data[i] = int16Data[i] / 32768.0;
+        }
+        return float32Data;
+    }
+
+    // 获取待解码包数
+    getPendingDecodeCount() {
+        return this.audioBufferQueue.length + this.pendingAudioBufferQueue.length;
+    }
+
+    // 获取待播放样本数（转换为包数，每包960样本）
+    getPendingPlayCount() {
+        // 计算已在队列中的样本
+        const queuedSamples = this.activeQueue.length + this.queue.length;
+
+        // 计算已调度但未播放的样本（在Web Audio缓冲区中）
+        let scheduledSamples = 0;
+        if (this.playing && this.scheduledEndTime) {
+            const currentTime = this.audioContext.currentTime;
+            const remainingTime = Math.max(0, this.scheduledEndTime - currentTime);
+            scheduledSamples = Math.floor(remainingTime * this.sampleRate);
+        }
+
+        const totalSamples = queuedSamples + scheduledSamples;
+        return Math.ceil(totalSamples / 960);
+    }
+
+    // 清空所有音频缓冲
+    clearAllBuffers() {
+        log('清空所有音频缓冲', 'info');
+
+        // 清空所有队列（使用clear方法保持对象引用）
+        this.audioBufferQueue.clear();
+        this.pendingAudioBufferQueue = [];
+        this.activeQueue.clear();
+        this.queue = [];
+
+        // 停止当前播放的音频源
+        if (this.source) {
+            try {
+                this.source.stop();
+                this.source.disconnect();
+            } catch (e) {
+                // 忽略已经停止的错误
+            }
+            this.source = null;
+        }
+
+        // 重置状态
+        this.playing = false;
+        this.scheduledEndTime = this.audioContext.currentTime;
+        this.totalSamples = 0;
+
+        log('音频缓冲已清空', 'success');
+    }
+
+    // 获取分析器节点（供Live2D使用）
+    getAnalyser() {
+        return this.analyser;
+    }
+
+    // 将Opus数据解码为PCM
+    async decodeOpusFrames() {
+        if (!this.opusDecoder) {
+            log('Opus解码器未初始化，无法解码', 'error');
+            return;
+        } else {
+            log('Opus解码器启动', 'info');
+        }
+
+        while (true) {
+            let decodedSamples = [];
+            for (const frame of this.pendingAudioBufferQueue) {
+                try {
+                    // 使用Opus解码器解码
+                    const frameData = this.opusDecoder.decode(frame);
+                    if (frameData && frameData.length > 0) {
+                        // 转换为Float32
+                        const floatData = this.convertInt16ToFloat32(frameData);
+                        // 使用循环替代展开运算符
+                        for (let i = 0; i < floatData.length; i++) {
+                            decodedSamples.push(floatData[i]);
+                        }
+                    }
+                } catch (error) {
+                    log("Opus解码失败: " + error.message, 'error');
+                }
+            }
+
+            if (decodedSamples.length > 0) {
+                // 使用循环替代展开运算符
+                for (let i = 0; i < decodedSamples.length; i++) {
+                    this.activeQueue.enqueue(decodedSamples[i]);
+                }
+                this.totalSamples += decodedSamples.length;
+            } else {
+                log('没有成功解码的样本', 'warning');
+            }
+            await this.getPendingAudioBufferQueue();
+        }
+    }
+
+    // 开始播放音频
+    async startPlaying() {
+        this.scheduledEndTime = this.audioContext.currentTime; // 跟踪已调度音频的结束时间
+
+        while (true) {
+            // 初始缓冲：等待足够的样本再开始播放
+            const minSamples = this.sampleRate * this.minAudioDuration * 2;
+            if (!this.playing && this.queue.length < minSamples) {
+                await this.getQueue(minSamples);
+            }
+            this.playing = true;
+
+            // 持续播放队列中的音频，每次播放一个小块
+            while (this.playing && this.queue.length > 0) {
+                // 每次播放120ms的音频（2个Opus包）
+                const playDuration = 0.12;
+                const targetSamples = Math.floor(this.sampleRate * playDuration);
+                const actualSamples = Math.min(this.queue.length, targetSamples);
+
+                if (actualSamples === 0) break;
+
+                const currentSamples = this.queue.splice(0, actualSamples);
+                const audioBuffer = this.audioContext.createBuffer(this.channels, currentSamples.length, this.sampleRate);
+                audioBuffer.copyToChannel(new Float32Array(currentSamples), 0);
+
+                // 创建音频源
+                this.source = this.audioContext.createBufferSource();
+                this.source.buffer = audioBuffer;
+
+                // 精确调度播放时间
+                const currentTime = this.audioContext.currentTime;
+                const startTime = Math.max(this.scheduledEndTime, currentTime);
+
+                // 连接到分析器和输出
+                this.source.connect(this.analyser);
+                this.source.connect(this.audioContext.destination);
+
+                log(`调度播放 ${currentSamples.length} 个样本，约 ${(currentSamples.length / this.sampleRate).toFixed(2)} 秒`, 'debug');
+                this.source.start(startTime);
+
+                // 更新下一个音频块的调度时间
+                const duration = audioBuffer.duration;
+                this.scheduledEndTime = startTime + duration;
+                this.lastPlayTime = startTime;
+
+                // 如果队列中数据不足，等待新数据
+                if (this.queue.length < targetSamples) {
+                    break;
+                }
+            }
+
+            // 等待新数据
+            await this.getQueue(minSamples);
+        }
+    }
+}
+
+// 创建streamingContext实例的工厂函数
+export function createStreamingContext(opusDecoder, audioContext, sampleRate, channels, minAudioDuration) {
+    return new StreamingContext(opusDecoder, audioContext, sampleRate, channels, minAudioDuration);
+}

main/digital-human/js/core/mcp/tools.js

@@ -0,0 +1,525 @@
+import { log } from '../../utils/logger.js?v=0205';
+
+// ==========================================
+// MCP 工具管理逻辑
+// ==========================================
+
+// 全局变量
+let mcpTools = [];
+let mcpEditingIndex = null;
+let mcpProperties = [];
+let websocket = null; // 将从外部设置
+
+/**
+ * 设置 WebSocket 实例
+ * @param {WebSocket} ws - WebSocket 连接实例
+ */
+export function setWebSocket(ws) {
+    websocket = ws;
+}
+
+/**
+ * 初始化 MCP 工具
+ */
+export async function initMcpTools() {
+    // 加载默认工具数据
+    const defaultMcpTools = await fetch("js/config/default-mcp-tools.json").then(res => res.json());
+    const savedTools = localStorage.getItem('mcpTools');
+    if (savedTools) {
+        try {
+            const parsedTools = JSON.parse(savedTools);
+            // 合并默认工具和用户保存的工具，保留用户自定义的工具
+            const defaultToolNames = new Set(defaultMcpTools.map(t => t.name));
+            // 添加默认工具中不存在的新工具
+            parsedTools.forEach(tool => {
+                if (!defaultToolNames.has(tool.name)) {
+                    defaultMcpTools.push(tool);
+                }
+            });
+            mcpTools = defaultMcpTools;
+        } catch (e) {
+            log('加载MCP工具失败，使用默认工具', 'warning');
+            mcpTools = [...defaultMcpTools];
+        }
+    } else {
+        mcpTools = [...defaultMcpTools];
+    }
+    renderMcpTools();
+    setupMcpEventListeners();
+}
+
+/**
+ * 渲染工具列表
+ */
+function renderMcpTools() {
+    const container = document.getElementById('mcpToolsContainer');
+    const countSpan = document.getElementById('mcpToolsCount');
+    if (!container) {
+        return; // Container not found, skip rendering
+    }
+    if (countSpan) {
+        countSpan.textContent = `${mcpTools.length} 个工具`;
+    }
+    if (mcpTools.length === 0) {
+        container.innerHTML = '<div style="text-align: center; padding: 30px; color: #999;">暂无工具，点击下方按钮添加新工具</div>';
+        return;
+    }
+    container.innerHTML = mcpTools.map((tool, index) => {
+        const paramCount = tool.inputSchema.properties ? Object.keys(tool.inputSchema.properties).length : 0;
+        const requiredCount = tool.inputSchema.required ? tool.inputSchema.required.length : 0;
+        const hasMockResponse = tool.mockResponse && Object.keys(tool.mockResponse).length > 0;
+        return `
+            <div class="mcp-tool-card">
+                <div class="mcp-tool-header">
+                    <div class="mcp-tool-name">${tool.name}</div>
+                    <div class="mcp-tool-actions">
+                        <button class="mcp-edit-btn" onclick="window.mcpModule.editMcpTool(${index})">
+                            ✏️ 编辑
+                        </button>
+                        <button class="mcp-delete-btn" onclick="window.mcpModule.deleteMcpTool(${index})">
+                            🗑️ 删除
+                        </button>
+                    </div>
+                </div>
+                <div class="mcp-tool-description">${tool.description}</div>
+                <div class="mcp-tool-info">
+                    <div class="mcp-tool-info-row">
+                        <span class="mcp-tool-info-label">参数数量:</span>
+                        <span class="mcp-tool-info-value">${paramCount} 个 ${requiredCount > 0 ? `(${requiredCount} 个必填)` : ''}</span>
+                    </div>
+                    <div class="mcp-tool-info-row">
+                        <span class="mcp-tool-info-label">模拟返回:</span>
+                        <span class="mcp-tool-info-value">${hasMockResponse ? '✅ 已配置: ' + JSON.stringify(tool.mockResponse) : '⚪ 使用默认'}</span>
+                    </div>
+                </div>
+            </div>
+        `;
+    }).join('');
+}
+
+/**
+ * 渲染参数列表
+ */
+function renderMcpProperties() {
+    const container = document.getElementById('mcpPropertiesContainer');
+    const emptyState = document.getElementById('mcpEmptyState');
+    if (!container) {
+        return; // Container not found, skip rendering
+    }
+    if (mcpProperties.length === 0) {
+        if (emptyState) {
+            emptyState.style.display = 'block';
+        }
+        container.innerHTML = '';
+        return;
+    }
+    if (emptyState) {
+        emptyState.style.display = 'none';
+    }
+    container.innerHTML = mcpProperties.map((prop, index) => `
+        <div class="mcp-property-card" onclick="window.mcpModule.editMcpProperty(${index})">
+            <div class="mcp-property-row-label">
+                <span class="mcp-property-label">参数名称</span>
+                <span class="mcp-property-value">${prop.name}${prop.required ? ' <span class="mcp-property-required-badge">[必填]</span>' : ''}</span>
+            </div>
+            <div class="mcp-property-row-label">
+                <span class="mcp-property-label">数据类型</span>
+                <span class="mcp-property-value">${getTypeLabel(prop.type)}</span>
+            </div>
+            <div class="mcp-property-row-label">
+                <span class="mcp-property-label">描述</span>
+                <span class="mcp-property-value">${prop.description || '-'}</span>
+            </div>
+            <div class="mcp-property-row-action">
+                <button class="mcp-property-delete-btn" onclick="event.stopPropagation(); window.mcpModule.deleteMcpProperty(${index})">删除</button>
+            </div>
+        </div>
+    `).join('');
+}
+
+/**
+ * 获取数据类型标签
+ */
+function getTypeLabel(type) {
+    const typeMap = {
+        'string': '字符串',
+        'integer': '整数',
+        'number': '数字',
+        'boolean': '布尔值',
+        'array': '数组',
+        'object': '对象'
+    };
+    return typeMap[type] || type;
+}
+
+/**
+ * 添加参数 - 打开参数编辑模态框
+ */
+function addMcpProperty() {
+    openPropertyModal();
+}
+
+/**
+ * 编辑参数 - 打开参数编辑模态框
+ */
+function editMcpProperty(index) {
+    openPropertyModal(index);
+}
+
+/**
+ * 打开参数编辑模态框
+ */
+function openPropertyModal(index = null) {
+    const form = document.getElementById('mcpPropertyForm');
+    const title = document.getElementById('mcpPropertyModalTitle');
+    document.getElementById('mcpPropertyIndex').value = index !== null ? index : -1;
+
+    if (index !== null) {
+        const prop = mcpProperties[index];
+        title.textContent = '编辑参数';
+        document.getElementById('mcpPropertyName').value = prop.name;
+        document.getElementById('mcpPropertyType').value = prop.type || 'string';
+        document.getElementById('mcpPropertyMinimum').value = prop.minimum !== undefined ? prop.minimum : '';
+        document.getElementById('mcpPropertyMaximum').value = prop.maximum !== undefined ? prop.maximum : '';
+        document.getElementById('mcpPropertyDescription').value = prop.description || '';
+        document.getElementById('mcpPropertyRequired').checked = prop.required || false;
+    } else {
+        title.textContent = '添加参数';
+        form.reset();
+        document.getElementById('mcpPropertyName').value = `param_${mcpProperties.length + 1}`;
+        document.getElementById('mcpPropertyType').value = 'string';
+        document.getElementById('mcpPropertyMinimum').value = '';
+        document.getElementById('mcpPropertyMaximum').value = '';
+        document.getElementById('mcpPropertyDescription').value = '';
+        document.getElementById('mcpPropertyRequired').checked = false;
+    }
+
+    updatePropertyRangeVisibility();
+    document.getElementById('mcpPropertyModal').style.display = 'flex';
+}
+
+/**
+ * 关闭参数编辑模态框
+ */
+function closePropertyModal() {
+    document.getElementById('mcpPropertyModal').style.display = 'none';
+}
+
+/**
+ * 更新数值范围输入框的可见性
+ */
+function updatePropertyRangeVisibility() {
+    const type = document.getElementById('mcpPropertyType').value;
+    const rangeGroup = document.getElementById('mcpPropertyRangeGroup');
+    if (type === 'integer' || type === 'number') {
+        rangeGroup.style.display = 'block';
+    } else {
+        rangeGroup.style.display = 'none';
+    }
+}
+
+/**
+ * 处理参数表单提交
+ */
+function handlePropertySubmit(e) {
+    e.preventDefault();
+    const index = parseInt(document.getElementById('mcpPropertyIndex').value);
+    const name = document.getElementById('mcpPropertyName').value.trim();
+    const type = document.getElementById('mcpPropertyType').value;
+    const minimum = document.getElementById('mcpPropertyMinimum').value;
+    const maximum = document.getElementById('mcpPropertyMaximum').value;
+    const description = document.getElementById('mcpPropertyDescription').value.trim();
+    const required = document.getElementById('mcpPropertyRequired').checked;
+
+    // 检查名称重复
+    const isDuplicate = mcpProperties.some((p, i) => i !== index && p.name === name);
+    if (isDuplicate) {
+        alert('参数名称已存在，请使用不同的名称');
+        return;
+    }
+
+    const propData = {
+        name,
+        type,
+        description,
+        required
+    };
+
+    // 数值类型添加范围限制
+    if (type === 'integer' || type === 'number') {
+        if (minimum !== '') {
+            propData.minimum = parseFloat(minimum);
+        }
+        if (maximum !== '') {
+            propData.maximum = parseFloat(maximum);
+        }
+    }
+
+    if (index >= 0) {
+        mcpProperties[index] = propData;
+    } else {
+        mcpProperties.push(propData);
+    }
+
+    renderMcpProperties();
+    closePropertyModal();
+}
+
+/**
+ * 删除参数
+ */
+function deleteMcpProperty(index) {
+    mcpProperties.splice(index, 1);
+    renderMcpProperties();
+}
+
+/**
+ * 设置事件监听
+ */
+function setupMcpEventListeners() {
+    const panel = document.getElementById('mcpToolsPanel');
+    const addBtn = document.getElementById('addMcpToolBtn');
+    const modal = document.getElementById('mcpToolModal');
+    const closeBtn = document.getElementById('closeMcpModalBtn');
+    const cancelBtn = document.getElementById('cancelMcpBtn');
+    const form = document.getElementById('mcpToolForm');
+    const addPropertyBtn = document.getElementById('addMcpPropertyBtn');
+
+    // 参数编辑模态框相关元素
+    const propertyModal = document.getElementById('mcpPropertyModal');
+    const closePropertyBtn = document.getElementById('closeMcpPropertyModalBtn');
+    const cancelPropertyBtn = document.getElementById('cancelMcpPropertyBtn');
+    const propertyForm = document.getElementById('mcpPropertyForm');
+    const propertyTypeSelect = document.getElementById('mcpPropertyType');
+
+    // Return early if required elements don't exist (e.g., in test environment)
+    if (!panel || !addBtn || !modal || !closeBtn || !cancelBtn || !form || !addPropertyBtn) {
+        return;
+    }
+    addBtn.addEventListener('click', () => openMcpModal());
+    closeBtn.addEventListener('click', closeMcpModal);
+    cancelBtn.addEventListener('click', closeMcpModal);
+    addPropertyBtn.addEventListener('click', addMcpProperty);
+    form.addEventListener('submit', handleMcpSubmit);
+
+    // 参数编辑模态框事件
+    if (propertyModal && closePropertyBtn && cancelPropertyBtn && propertyForm && propertyTypeSelect) {
+        closePropertyBtn.addEventListener('click', closePropertyModal);
+        cancelPropertyBtn.addEventListener('click', closePropertyModal);
+        propertyForm.addEventListener('submit', handlePropertySubmit);
+        propertyTypeSelect.addEventListener('change', updatePropertyRangeVisibility);
+    }
+}
+
+/**
+ * 打开模态框
+ */
+function openMcpModal(index = null) {
+    const isConnected = websocket && websocket.readyState === WebSocket.OPEN;
+    if (isConnected) {
+        alert('WebSocket 已连接，无法编辑工具');
+        return;
+    }
+    mcpEditingIndex = index;
+    const errorContainer = document.getElementById('mcpErrorContainer');
+    errorContainer.innerHTML = '';
+    if (index !== null) {
+        document.getElementById('mcpModalTitle').textContent = '编辑工具';
+        const tool = mcpTools[index];
+        document.getElementById('mcpToolName').value = tool.name;
+        document.getElementById('mcpToolDescription').value = tool.description;
+        document.getElementById('mcpMockResponse').value = tool.mockResponse ? JSON.stringify(tool.mockResponse, null, 2) : '';
+        mcpProperties = [];
+        const schema = tool.inputSchema;
+        if (schema.properties) {
+            Object.keys(schema.properties).forEach(key => {
+                const prop = schema.properties[key];
+                mcpProperties.push({
+                    name: key,
+                    type: prop.type || 'string',
+                    minimum: prop.minimum,
+                    maximum: prop.maximum,
+                    description: prop.description || '',
+                    required: schema.required && schema.required.includes(key)
+                });
+            });
+        }
+    } else {
+        document.getElementById('mcpModalTitle').textContent = '添加工具';
+        document.getElementById('mcpToolForm').reset();
+        mcpProperties = [];
+    }
+    renderMcpProperties();
+    document.getElementById('mcpToolModal').style.display = 'flex';
+}
+
+/**
+ * 关闭模态框
+ */
+function closeMcpModal() {
+    document.getElementById('mcpToolModal').style.display = 'none';
+    mcpEditingIndex = null;
+    document.getElementById('mcpToolForm').reset();
+    mcpProperties = [];
+    document.getElementById('mcpErrorContainer').innerHTML = '';
+}
+
+/**
+ * 处理表单提交
+ */
+function handleMcpSubmit(e) {
+    e.preventDefault();
+    const errorContainer = document.getElementById('mcpErrorContainer');
+    errorContainer.innerHTML = '';
+    const name = document.getElementById('mcpToolName').value.trim();
+    const description = document.getElementById('mcpToolDescription').value.trim();
+    const mockResponseText = document.getElementById('mcpMockResponse').value.trim();
+    // 检查名称重复
+    const isDuplicate = mcpTools.some((tool, index) => tool.name === name && index !== mcpEditingIndex);
+    if (isDuplicate) {
+        showMcpError('工具名称已存在，请使用不同的名称');
+        return;
+    }
+    // 解析模拟返回结果
+    let mockResponse = null;
+    if (mockResponseText) {
+        try {
+            mockResponse = JSON.parse(mockResponseText);
+        } catch (e) {
+            showMcpError('模拟返回结果不是有效的 JSON 格式: ' + e.message);
+            return;
+        }
+    }
+    // 构建 inputSchema
+    const inputSchema = { type: "object", properties: {}, required: [] };
+    mcpProperties.forEach(prop => {
+        const propSchema = { type: prop.type };
+        if (prop.description) {
+            propSchema.description = prop.description;
+        }
+        if ((prop.type === 'integer' || prop.type === 'number')) {
+            if (prop.minimum !== undefined && prop.minimum !== '') {
+                propSchema.minimum = prop.minimum;
+            }
+            if (prop.maximum !== undefined && prop.maximum !== '') {
+                propSchema.maximum = prop.maximum;
+            }
+        }
+        inputSchema.properties[prop.name] = propSchema;
+        if (prop.required) {
+            inputSchema.required.push(prop.name);
+        }
+    });
+    if (inputSchema.required.length === 0) {
+        delete inputSchema.required;
+    }
+    const tool = { name, description, inputSchema, mockResponse };
+    if (mcpEditingIndex !== null) {
+        mcpTools[mcpEditingIndex] = tool;
+        log(`已更新工具: ${name}`, 'success');
+    } else {
+        mcpTools.push(tool);
+        log(`已添加工具: ${name}`, 'success');
+    }
+    saveMcpTools();
+    renderMcpTools();
+    closeMcpModal();
+}
+
+/**
+ * 显示错误
+ */
+function showMcpError(message) {
+    const errorContainer = document.getElementById('mcpErrorContainer');
+    errorContainer.innerHTML = `<div class="mcp-error">${message}</div>`;
+}
+
+/**
+ * 编辑工具
+ */
+function editMcpTool(index) {
+    openMcpModal(index);
+}
+
+/**
+ * 删除工具
+ */
+function deleteMcpTool(index) {
+    const isConnected = websocket && websocket.readyState === WebSocket.OPEN;
+    if (isConnected) {
+        alert('WebSocket 已连接，无法编辑工具');
+        return;
+    }
+    if (confirm(`确定要删除工具 "${mcpTools[index].name}" 吗？`)) {
+        const toolName = mcpTools[index].name;
+        mcpTools.splice(index, 1);
+        saveMcpTools();
+        renderMcpTools();
+        log(`已删除工具: ${toolName}`, 'info');
+    }
+}
+
+/**
+ * 保存工具
+ */
+function saveMcpTools() {
+    localStorage.setItem('mcpTools', JSON.stringify(mcpTools));
+}
+
+/**
+ * 获取工具列表
+ */
+export function getMcpTools() {
+    return mcpTools.map(tool => ({ name: tool.name, description: tool.description, inputSchema: tool.inputSchema }));
+}
+
+/**
+ * 执行工具调用
+ */
+export async function executeMcpTool(toolName, toolArgs) {
+    const tool = mcpTools.find(t => t.name === toolName);
+    if (!tool) {
+        log(`未找到工具: ${toolName}`, 'error');
+        return { success: false, error: `未知工具: ${toolName}` };
+    }
+
+    // 处理拍照工具
+    if (toolName === 'self_camera_take_photo') {
+        if (typeof window.takePhoto === 'function') {
+            const question = toolArgs && toolArgs.question ? toolArgs.question : '描述一下看到的物品';
+            log(`正在执行拍照: ${question}`, 'info');
+            const result = await window.takePhoto(question);
+            return result;
+        } else {
+            log('拍照功能不可用', 'warning');
+            return { success: false, error: '摄像头未启动或不支持拍照功能' };
+        }
+    }
+
+    // 如果有模拟返回结果，使用它
+    if (tool.mockResponse) {
+        // 替换模板变量
+        let responseStr = JSON.stringify(tool.mockResponse);
+        // 替换 ${paramName} 格式的变量
+        if (toolArgs) {
+            Object.keys(toolArgs).forEach(key => {
+                const regex = new RegExp(`\\$\\{${key}\\}`, 'g');
+                responseStr = responseStr.replace(regex, toolArgs[key]);
+            });
+        }
+        try {
+            const response = JSON.parse(responseStr);
+            log(`工具 ${toolName} 执行成功，返回模拟结果: ${responseStr}`, 'success');
+            return response;
+        } catch (e) {
+            log(`解析模拟返回结果失败: ${e.message}`, 'error');
+            return tool.mockResponse;
+        }
+    }
+    // 没有模拟返回结果，返回默认成功消息
+    log(`工具 ${toolName} 执行成功，返回默认结果`, 'success');
+    return { success: true, message: `工具 ${toolName} 执行成功`, tool: toolName, arguments: toolArgs };
+}
+
+// 暴露全局方法供 HTML 内联事件调用
+window.mcpModule = { addMcpProperty, editMcpProperty, deleteMcpProperty, editMcpTool, deleteMcpTool };

main/digital-human/js/core/network/ota-connector.js

@@ -0,0 +1,109 @@
+import { log } from '../../utils/logger.js?v=0205';
+
+// WebSocket 连接
+export async function webSocketConnect(otaUrl, config) {
+
+    if (!validateConfig(config)) {
+        return;
+    }
+
+    // 发送OTA请求并获取返回的websocket信息
+    const otaResult = await sendOTA(otaUrl, config);
+    if (!otaResult) {
+        log('无法从OTA服务器获取信息', 'error');
+        return;
+    }
+
+    // 从OTA响应中提取websocket信息
+    const { websocket } = otaResult;
+    if (!websocket || !websocket.url) {
+        log('OTA响应中缺少websocket信息', 'error');
+        return;
+    }
+
+    // 使用OTA返回的websocket URL
+    let connUrl = new URL(websocket.url);
+
+    // 添加token参数（从OTA响应中获取）
+    if (websocket.token) {
+        if (websocket.token.startsWith("Bearer ")) {
+            connUrl.searchParams.append('authorization', websocket.token);
+        } else {
+            connUrl.searchParams.append('authorization', 'Bearer ' + websocket.token);
+        }
+    }
+
+    // 添加认证参数（保持原有逻辑）
+    connUrl.searchParams.append('device-id', config.deviceId);
+    connUrl.searchParams.append('client-id', config.clientId);
+
+    const wsurl = connUrl.toString()
+
+    log(`正在连接: ${wsurl}`, 'info');
+
+    if (wsurl) {
+        document.getElementById('serverUrl').value = wsurl;
+    }
+
+    return new WebSocket(connUrl.toString());
+}
+
+// 验证配置
+function validateConfig(config) {
+    if (!config.deviceMac) {
+        log('设备MAC地址不能为空', 'error');
+        return false;
+    }
+    if (!config.clientId) {
+        log('客户端ID不能为空', 'error');
+        return false;
+    }
+    return true;
+}
+
+// OTA发送请求，验证状态，并返回响应数据
+async function sendOTA(otaUrl, config) {
+    try {
+        const res = await fetch(otaUrl, {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json',
+                'Device-Id': config.deviceId,
+                'Client-Id': config.clientId
+            },
+            body: JSON.stringify({
+                version: 0,
+                uuid: '',
+                application: {
+                    name: 'xiaozhi-web-test',
+                    version: '1.0.0',
+                    compile_time: '2025-04-16 10:00:00',
+                    idf_version: '4.4.3',
+                    elf_sha256: '1234567890abcdef1234567890abcdef1234567890abcdef'
+                },
+                ota: { label: 'xiaozhi-web-test' },
+                board: {
+                    type: config.deviceName,
+                    ssid: 'xiaozhi-web-test',
+                    rssi: 0,
+                    channel: 0,
+                    ip: '192.168.1.1',
+                    mac: config.deviceMac
+                },
+                flash_size: 0,
+                minimum_free_heap_size: 0,
+                mac_address: config.deviceMac,
+                chip_model_name: '',
+                chip_info: { model: 0, cores: 0, revision: 0, features: 0 },
+                partition_table: [{ label: '', type: 0, subtype: 0, address: 0, size: 0 }]
+            })
+        });
+
+        if (!res.ok) throw new Error(`${res.status} ${res.statusText}`);
+
+        const result = await res.json();
+        return result; // 返回完整的响应数据
+    } catch (err) {
+        return null; // 失败返回null
+    }
+}

main/digital-human/js/core/network/wakeword-bridge.js

@@ -0,0 +1,225 @@
+import { uiController } from '../../ui/controller.js?v=0205';
+import { log } from '../../utils/logger.js?v=0205';
+
+let wakewordSocket = null;
+let reconnectTimer = null;
+let reconnectAttempts = 0;
+let shouldReconnect = true;
+let wakewordRequestSeq = 0;
+let onNextBridgeConnectedCallback = null;
+
+const pendingWakewordRequests = new Map();
+
+export function startWakewordBridgeListener() {
+    if (wakewordSocket) {
+        return wakewordSocket;
+    }
+
+    shouldReconnect = true;
+    log('正在连接本地唤醒事件桥...', 'info');
+    tryConnect();
+    return wakewordSocket;
+}
+
+function tryConnect() {
+    const bridgeUrl = buildWakewordBridgeUrl();
+
+    try {
+        wakewordSocket = new WebSocket(bridgeUrl);
+        wakewordSocket.onopen = () => {
+            reconnectAttempts = 0;
+            log(`本地唤醒事件桥已连接: ${bridgeUrl}`, 'success');
+            // 连接成功后自动保存地址，刷新后仍能记住
+            localStorage.setItem('xz_tester_wakewordWsUrl', bridgeUrl);
+            const urlInput = document.getElementById('wakewordWsUrl');
+            if (urlInput) urlInput.value = bridgeUrl;
+        };
+
+        wakewordSocket.onerror = () => {
+            log(`本地唤醒事件桥连接失败: ${bridgeUrl}`, 'error');
+        };
+
+        wakewordSocket.onmessage = async (event) => {
+            try {
+                const message = parseWakewordBridgeMessage(event.data);
+                if (message.requestId && pendingWakewordRequests.has(message.requestId)) {
+                    settleWakewordRequest(message);
+                    return;
+                }
+
+                if (message.success === false) {
+                    log(`本地唤醒事件桥返回错误: ${message.error || '未知错误'}`, 'error');
+                    return;
+                }
+
+                if (message.type === 'bridge_connected') {
+                    log('本地唤醒监听已就绪', 'info');
+                    if (onNextBridgeConnectedCallback) {
+                        const cb = onNextBridgeConnectedCallback;
+                        onNextBridgeConnectedCallback = null;
+                        cb(message);
+                    }
+                    return;
+                }
+
+                if (message.type === 'service_ready') {
+                    log('本地唤醒服务已启动', 'info');
+                    return;
+                }
+
+                if (message.type === 'wakeword_config') {
+                    uiController.applyWakewordConfig(message.payload || {});
+                    log('已同步本地唤醒词配置', 'info');
+                    return;
+                }
+
+                if (message.type === 'service_stopping') {
+                    log('本地唤醒服务正在停止', 'warning');
+                    return;
+                }
+
+                if (message.type === 'wake_word_detected') {
+                    const wakeWord = message.payload?.wake_word || '唤醒词';
+                    log(`检测到本地唤醒事件: ${wakeWord}`, 'info');
+                    await uiController.triggerWakewordDial(wakeWord);
+                }
+            } catch (error) {
+                log(`解析本地唤醒事件失败: ${error.message}`, 'error');
+            }
+        };
+
+        wakewordSocket.onclose = () => {
+            if (wakewordSocket) {
+                wakewordSocket = null;
+            }
+
+            rejectAllWakewordRequests('本地唤醒事件桥已断开');
+
+            if (!shouldReconnect) {
+                return;
+            }
+
+            if (reconnectTimer) {
+                return;
+            }
+
+            reconnectAttempts += 1;
+            const delay = Math.min(1000 * reconnectAttempts, 5000);
+            log(`本地唤醒事件桥将在 ${delay}ms 后重连: ${bridgeUrl}`, 'warning');
+            reconnectTimer = window.setTimeout(() => {
+                reconnectTimer = null;
+                tryConnect();
+            }, delay);
+        };
+
+        return wakewordSocket;
+    } catch (error) {
+        log(`启动本地唤醒监听失败: ${error.message}`, 'error');
+        return null;
+    }
+}
+
+export function stopWakewordBridgeListener() {
+    shouldReconnect = false;
+
+    if (reconnectTimer) {
+        window.clearTimeout(reconnectTimer);
+        reconnectTimer = null;
+    }
+
+    if (!wakewordSocket) {
+        return;
+    }
+
+    wakewordSocket.onclose = null;
+    wakewordSocket.close();
+    wakewordSocket = null;
+}
+
+export function sendWakewordBridgeMessage(type, payload = {}, requestId = null) {
+    if (!wakewordSocket || wakewordSocket.readyState !== WebSocket.OPEN) {
+        log('本地唤醒事件桥未连接，无法发送消息', 'warning');
+        return false;
+    }
+
+    wakewordSocket.send(JSON.stringify({
+        type,
+        requestId,
+        payload,
+    }));
+    return true;
+}
+
+export function requestWakewordBridge(type, payload = {}, timeout = 5000) {
+    const requestId = `wakeword-${Date.now()}-${++wakewordRequestSeq}`;
+
+    return new Promise((resolve, reject) => {
+        const timer = window.setTimeout(() => {
+            pendingWakewordRequests.delete(requestId);
+            reject(new Error('本地唤醒服务响应超时'));
+        }, timeout);
+
+        pendingWakewordRequests.set(requestId, { resolve, reject, timer });
+
+        if (!sendWakewordBridgeMessage(type, payload, requestId)) {
+            window.clearTimeout(timer);
+            pendingWakewordRequests.delete(requestId);
+            reject(new Error('本地唤醒事件桥未连接'));
+        }
+    });
+}
+
+export function getWakewordBridgeUrl() {
+    if (wakewordSocket && wakewordSocket.url) {
+        return wakewordSocket.url;
+    }
+    return buildWakewordBridgeUrl();
+}
+
+export function onNextBridgeConnected(callback) {
+    onNextBridgeConnectedCallback = callback;
+}
+
+function buildWakewordBridgeUrl() {
+    const configured = localStorage.getItem('xz_tester_wakewordWsUrl');
+    if (configured && configured.trim()) {
+        return configured.trim();
+    }
+    return 'ws://127.0.0.1:8006/wakeword-ws';
+}
+
+function parseWakewordBridgeMessage(rawData) {
+    const message = JSON.parse(rawData);
+    return {
+        type: message.type || '',
+        requestId: message.requestId || null,
+        success: message.success !== false,
+        payload: message.payload || {},
+        error: message.error || null,
+    };
+}
+
+function settleWakewordRequest(message) {
+    const pendingRequest = pendingWakewordRequests.get(message.requestId);
+    if (!pendingRequest) {
+        return;
+    }
+
+    window.clearTimeout(pendingRequest.timer);
+    pendingWakewordRequests.delete(message.requestId);
+
+    if (message.success === false) {
+        pendingRequest.reject(new Error(message.error || '本地唤醒服务返回失败'));
+        return;
+    }
+
+    pendingRequest.resolve(message);
+}
+
+function rejectAllWakewordRequests(errorMessage) {
+    pendingWakewordRequests.forEach((pendingRequest) => {
+        window.clearTimeout(pendingRequest.timer);
+        pendingRequest.reject(new Error(errorMessage));
+    });
+    pendingWakewordRequests.clear();
+}

main/digital-human/js/core/network/websocket.js

@@ -0,0 +1,591 @@
+// WebSocket消息处理模块
+import { getConfig, saveConnectionUrls } from '../../config/manager.js?v=0205';
+import { uiController } from '../../ui/controller.js?v=0205';
+import { log } from '../../utils/logger.js?v=0205';
+import { getAudioPlayer } from '../audio/player.js?v=0205';
+import { getAudioRecorder } from '../audio/recorder.js?v=0205';
+import { executeMcpTool, getMcpTools, setWebSocket as setMcpWebSocket } from '../mcp/tools.js?v=0205';
+import { webSocketConnect } from './ota-connector.js?v=0205';
+
+// WebSocket处理器类
+export class WebSocketHandler {
+    constructor() {
+        this.websocket = null;
+        this.onConnectionStateChange = null;
+        this.onRecordButtonStateChange = null;
+        this.onSessionStateChange = null;
+        this.onSessionEmotionChange = null;
+        this.onChatMessage = null; // 新增：聊天消息回调
+        this.currentSessionId = null;
+        this.isRemoteSpeaking = false;
+    }
+
+    // 发送hello握手消息
+    async sendHelloMessage() {
+        if (!this.websocket || this.websocket.readyState !== WebSocket.OPEN) return false;
+
+        try {
+            const config = getConfig();
+
+            const helloMessage = {
+                type: 'hello',
+                device_id: config.deviceId,
+                device_name: config.deviceName,
+                device_mac: config.deviceMac,
+                token: config.token,
+                features: {
+                    mcp: true,
+                    emoji: config.emojiEnabled
+                }
+            };
+
+            log('发送hello握手消息', 'info');
+            this.websocket.send(JSON.stringify(helloMessage));
+
+            return new Promise(resolve => {
+                const timeout = setTimeout(() => {
+                    log('等待hello响应超时', 'error');
+                    log('提示: 请尝试点击"测试认证"按钮进行连接排查', 'info');
+                    resolve(false);
+                }, 5000);
+
+                const onMessageHandler = (event) => {
+                    try {
+                        const response = JSON.parse(event.data);
+                        if (response.type === 'hello' && response.session_id) {
+                            log(`服务器握手成功，会话ID: ${response.session_id}`, 'success');
+                            clearTimeout(timeout);
+                            this.websocket.removeEventListener('message', onMessageHandler);
+                            resolve(true);
+                        }
+                    } catch (e) {
+                        // 忽略非JSON消息
+                    }
+                };
+
+                this.websocket.addEventListener('message', onMessageHandler);
+            });
+        } catch (error) {
+            log(`发送hello消息错误: ${error.message}`, 'error');
+            return false;
+        }
+    }
+
+    _sendWakeupMessages(sessionId) {
+        if (!this.websocket || this.websocket.readyState !== WebSocket.OPEN) return;
+
+        // listen detect
+        this.websocket.send(JSON.stringify({
+            session_id: sessionId,
+            type: 'listen',
+            state: 'detect',
+            text: '嘿，你好呀'
+        }));
+        log('发送listen detect消息，唤醒词: 嘿，你好呀', 'info');
+
+        // listen start：开始监听
+        this.websocket.send(JSON.stringify({
+            session_id: sessionId,
+            type: 'listen',
+            state: 'start',
+            mode: 'auto'
+        }));
+        log('发送listen start消息', 'info');
+    }
+
+    // 处理文本消息
+    handleTextMessage(message) {
+        if (message.type === 'hello') {
+            log(`服务器回应：${JSON.stringify(message, null, 2)}`, 'success');
+            window.cameraAvailable = true;
+            log('连接成功，摄像头已可用', 'success');
+            uiController.updateDialButton(true);
+
+            this._sendWakeupMessages(message.session_id);
+
+            uiController.startAIChatSession();
+        } else if (message.type === 'tts') {
+            this.handleTTSMessage(message);
+        } else if (message.type === 'audio') {
+            log(`收到音频控制消息: ${JSON.stringify(message)}`, 'info');
+        } else if (message.type === 'stt') {
+            log(`识别结果: ${message.text}`, 'info');
+            // 检查是否需要绑定设备
+            if (message.text && (message.text.includes('绑定') || message.text.includes('bind'))) {
+                log('收到设备绑定提示，更新摄像头状态', 'warning');
+                window.cameraAvailable = false;
+                // 关闭摄像头
+                if (typeof window.stopCamera === 'function') {
+                    window.stopCamera();
+                }
+                // 更新摄像头按钮状态
+                const cameraBtn = document.getElementById('cameraBtn');
+                if (cameraBtn) {
+                    cameraBtn.classList.remove('camera-active');
+                    cameraBtn.querySelector('.btn-text').textContent = '摄像头';
+                    cameraBtn.disabled = true;
+                    cameraBtn.title = '请先绑定验证码';
+                }
+            }
+            // 使用新的聊天消息回调显示STT消息
+            if (this.onChatMessage && message.text) {
+                this.onChatMessage(message.text, true);
+            }
+        } else if (message.type === 'llm') {
+            log(`大模型回复: ${message.text}`, 'info');
+            // 使用新的聊天消息回调显示LLM回复
+            if (this.onChatMessage && message.text) {
+                this.onChatMessage(message.text, false);
+            }
+
+            // 如果包含表情，更新sessionStatus表情并触发Live2D动作
+            if (message.text && /[\u{1F300}-\u{1F9FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]/u.test(message.text)) {
+                // 提取表情符号
+                const emojiMatch = message.text.match(/[\u{1F300}-\u{1F9FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]/u);
+                if (emojiMatch && this.onSessionEmotionChange) {
+                    this.onSessionEmotionChange(emojiMatch[0]);
+                }
+
+                // 触发Live2D情绪动作
+                if (message.emotion) {
+                    console.log(`收到情绪消息: emotion=${message.emotion}, text=${message.text}`);
+                    this.triggerLive2DEmotionAction(message.emotion);
+                }
+            }
+
+            // 只有当文本不仅仅是表情时，才添加到对话中
+            // 移除文本中的表情后检查是否还有内容
+            const textWithoutEmoji = message.text ? message.text.replace(/[\u{1F300}-\u{1F9FF}]|[\u{2600}-\u{26FF}]|[\u{2700}-\u{27BF}]/gu, '').trim() : '';
+            if (textWithoutEmoji && this.onChatMessage) {
+                this.onChatMessage(message.text, false);
+            }
+        } else if (message.type === 'mcp') {
+            this.handleMCPMessage(message);
+        } else {
+            log(`未知消息类型: ${message.type}`, 'info');
+            if (this.onChatMessage) {
+                this.onChatMessage(`未知消息类型: ${message.type}\n${JSON.stringify(message, null, 2)}`, false);
+            }
+        }
+    }
+
+    // 处理TTS消息
+    handleTTSMessage(message) {
+        if (message.state === 'start') {
+            log('服务器开始发送语音', 'info');
+            this.currentSessionId = message.session_id;
+            this.isRemoteSpeaking = true;
+            if (this.onSessionStateChange) {
+                this.onSessionStateChange(true);
+            }
+
+            // 启动Live2D说话动画
+            this.startLive2DTalking();
+        } else if (message.state === 'sentence_start') {
+            log(`服务器发送语音段: ${message.text}`, 'info');
+            this.ttsSentenceCount = (this.ttsSentenceCount || 0) + 1;
+
+            if (message.text && this.onChatMessage) {
+                this.onChatMessage(message.text, false);
+            }
+
+            // 确保动画在句子开始时运行
+            const live2dManager = window.chatApp?.live2dManager;
+            if (live2dManager && !live2dManager.isTalking) {
+                this.startLive2DTalking();
+            }
+        } else if (message.state === 'sentence_end') {
+            log(`语音段结束: ${message.text}`, 'info');
+
+            // 句子结束时不清除动画，等待下一个句子或最终停止
+        } else if (message.state === 'stop') {
+            log('服务器语音传输结束，清空所有音频缓冲', 'info');
+
+            // 清空所有音频缓冲并停止播放
+            const audioPlayer = getAudioPlayer();
+            audioPlayer.clearAllAudio();
+
+            this.isRemoteSpeaking = false;
+            if (this.onRecordButtonStateChange) {
+                this.onRecordButtonStateChange(false);
+            }
+            if (this.onSessionStateChange) {
+                this.onSessionStateChange(false);
+            }
+
+            // 延迟停止Live2D说话动画，确保所有句子都播放完毕
+            setTimeout(() => {
+                this.stopLive2DTalking();
+                this.ttsSentenceCount = 0; // 重置计数器
+            }, 1000); // 1秒延迟，确保所有句子都完成
+        }
+    }
+
+    // 启动Live2D说话动画
+    startLive2DTalking() {
+        try {
+            // 获取Live2D管理器实例
+            const live2dManager = window.chatApp?.live2dManager;
+            if (live2dManager && live2dManager.live2dModel) {
+                // 使用音频播放器的分析器节点
+                live2dManager.startTalking();
+                log('Live2D说话动画已启动', 'info');
+            }
+        } catch (error) {
+            log(`启动Live2D说话动画失败: ${error.message}`, 'error');
+        }
+    }
+
+    // 停止Live2D说话动画
+    stopLive2DTalking() {
+        try {
+            const live2dManager = window.chatApp?.live2dManager;
+            if (live2dManager) {
+                live2dManager.stopTalking();
+                log('Live2D说话动画已停止', 'info');
+            }
+        } catch (error) {
+            log(`停止Live2D说话动画失败: ${error.message}`, 'error');
+        }
+    }
+
+    // 初始化Live2D音频分析器
+    initializeLive2DAudioAnalyzer() {
+        try {
+            const live2dManager = window.chatApp?.live2dManager;
+            if (live2dManager) {
+                // 初始化音频分析器（使用音频播放器的上下文）
+                if (live2dManager.initializeAudioAnalyzer()) {
+                    log('Live2D音频分析器初始化完成，已连接到音频播放器', 'success');
+                } else {
+                    log('Live2D音频分析器初始化失败，将使用模拟动画', 'warning');
+                }
+            }
+        } catch (error) {
+            log(`初始化Live2D音频分析器失败: ${error.message}`, 'error');
+        }
+    }
+
+    // 处理MCP消息
+    handleMCPMessage(message) {
+        const payload = message.payload || {};
+        log(`服务器下发: ${JSON.stringify(message)}`, 'info');
+
+        if (payload.method === 'tools/list') {
+            const tools = getMcpTools();
+
+            const replyMessage = JSON.stringify({
+                "session_id": message.session_id || "",
+                "type": "mcp",
+                "payload": {
+                    "jsonrpc": "2.0",
+                    "id": payload.id,
+                    "result": {
+                        "tools": tools
+                    }
+                }
+            });
+            log(`客户端上报: ${replyMessage}`, 'info');
+            this.websocket.send(replyMessage);
+            log(`回复MCP工具列表: ${tools.length} 个工具`, 'info');
+
+        } else if (payload.method === 'tools/call') {
+            const toolName = payload.params?.name;
+            const toolArgs = payload.params?.arguments;
+
+            log(`调用工具: ${toolName} 参数: ${JSON.stringify(toolArgs)}`, 'info');
+
+            executeMcpTool(toolName, toolArgs).then(result => {
+                const replyMessage = JSON.stringify({
+                    "session_id": message.session_id || "",
+                    "type": "mcp",
+                    "payload": {
+                        "jsonrpc": "2.0",
+                        "id": payload.id,
+                        "result": {
+                            "content": [
+                                {
+                                    "type": "text",
+                                    "text": JSON.stringify(result)
+                                }
+                            ],
+                            "isError": false
+                        }
+                    }
+                });
+
+                log(`客户端上报: ${replyMessage}`, 'info');
+                this.websocket.send(replyMessage);
+            }).catch(error => {
+                log(`工具执行失败: ${error.message}`, 'error');
+                const errorReply = JSON.stringify({
+                    "session_id": message.session_id || "",
+                    "type": "mcp",
+                    "payload": {
+                        "jsonrpc": "2.0",
+                        "id": payload.id,
+                        "error": {
+                            "code": -32603,
+                            "message": error.message
+                        }
+                    }
+                });
+                this.websocket.send(errorReply);
+            });
+        } else if (payload.method === 'initialize') {
+            log(`收到工具初始化请求: ${JSON.stringify(payload.params)}`, 'info');
+            // 保存视觉分析接口地址
+            const visionUrl = document.getElementById('visionUrl');
+            const visionConfig = payload?.params?.capabilities?.vision;
+            if (visionConfig && typeof visionConfig === 'object' && visionConfig.url && visionConfig.token) {
+                const visionConfigStr = JSON.stringify(visionConfig);
+                localStorage.setItem('xz_tester_vision', visionConfigStr);
+                if (visionUrl) visionUrl.value = visionConfig.url;
+            } else {
+                localStorage.removeItem('xz_tester_vision');
+                if (visionUrl) visionUrl.value = '';
+            }
+
+            const replyMessage = JSON.stringify({
+                "session_id": message.session_id || "",
+                "type": "mcp",
+                "payload": {
+                    "jsonrpc": "2.0",
+                    "id": payload.id,
+                    "result": {
+                        "protocolVersion": "2024-11-05",
+                        "capabilities": {
+                            "tools": {}
+                        },
+                        "serverInfo": {
+                            "name": "xiaozhi-web-test",
+                            "version": "2.1.0"
+                        }
+                    }
+                }
+            });
+            log(`回复初始化响应`, 'info');
+            this.websocket.send(replyMessage);
+        } else {
+            log(`未知的MCP方法: ${payload.method}`, 'warning');
+        }
+    }
+
+    // 处理二进制消息
+    async handleBinaryMessage(data) {
+        try {
+            let arrayBuffer;
+            if (data instanceof ArrayBuffer) {
+                arrayBuffer = data;
+            } else if (data instanceof Blob) {
+                arrayBuffer = await data.arrayBuffer();
+                log(`收到Blob音频数据，大小: ${arrayBuffer.byteLength}字节`, 'debug');
+            } else {
+                log(`收到未知类型的二进制数据: ${typeof data}`, 'warning');
+                return;
+            }
+
+            const opusData = new Uint8Array(arrayBuffer);
+            const audioPlayer = getAudioPlayer();
+            audioPlayer.enqueueAudioData(opusData);
+        } catch (error) {
+            log(`处理二进制消息出错: ${error.message}`, 'error');
+        }
+    }
+
+    // 连接WebSocket服务器
+    async connect() {
+        const config = getConfig();
+        log('正在检查OTA状态...', 'info');
+        saveConnectionUrls();
+
+        try {
+            const otaUrl = document.getElementById('otaUrl').value.trim();
+            const ws = await webSocketConnect(otaUrl, config);
+            if (ws === undefined) {
+                return false;
+            }
+            this.websocket = ws;
+
+            // 设置接收二进制数据的类型为ArrayBuffer
+            this.websocket.binaryType = 'arraybuffer';
+
+            // 设置 MCP 模块的 WebSocket 实例
+            setMcpWebSocket(this.websocket);
+
+            // 设置录音器的WebSocket
+            const audioRecorder = getAudioRecorder();
+            audioRecorder.setWebSocket(this.websocket);
+
+            this.setupEventHandlers();
+
+            return true;
+        } catch (error) {
+            log(`连接错误: ${error.message}`, 'error');
+            if (this.onConnectionStateChange) {
+                this.onConnectionStateChange(false);
+            }
+            return false;
+        }
+    }
+
+    // 设置事件处理器
+    setupEventHandlers() {
+        this.websocket.onopen = async () => {
+            const url = document.getElementById('serverUrl').value;
+            log(`已连接到服务器: ${url}`, 'success');
+
+            if (this.onConnectionStateChange) {
+                this.onConnectionStateChange(true);
+            }
+
+            // 连接成功后，默认状态为聆听中
+            this.isRemoteSpeaking = false;
+            if (this.onSessionStateChange) {
+                this.onSessionStateChange(false);
+            }
+
+            // 在WebSocket连接成功时初始化Live2D音频分析器
+            this.initializeLive2DAudioAnalyzer();
+
+            await this.sendHelloMessage();
+        };
+
+        this.websocket.onclose = () => {
+            log('已断开连接', 'info');
+
+            if (this.onConnectionStateChange) {
+                this.onConnectionStateChange(false);
+            }
+
+            const audioRecorder = getAudioRecorder();
+            audioRecorder.stop();
+
+            // 关闭摄像头
+            if (typeof window.stopCamera === 'function') {
+                window.stopCamera();
+            }
+
+            // 隐藏摄像头显示区域
+            const cameraContainer = document.getElementById('cameraContainer');
+            if (cameraContainer) {
+                cameraContainer.classList.remove('active');
+            }
+        };
+
+        this.websocket.onerror = (error) => {
+            log(`WebSocket错误: ${error.message || '未知错误'}`, 'error');
+            uiController.addChatMessage(`⚠️ WebSocket错误: ${error.message || '未知错误'}`, false);
+            if (this.onConnectionStateChange) {
+                this.onConnectionStateChange(false);
+            }
+        };
+
+        this.websocket.onmessage = (event) => {
+            try {
+                if (typeof event.data === 'string') {
+                    const message = JSON.parse(event.data);
+                    this.handleTextMessage(message);
+                } else {
+                    this.handleBinaryMessage(event.data);
+                }
+            } catch (error) {
+                log(`WebSocket消息处理错误: ${error.message}`, 'error');
+                // 不再使用旧的addMessage函数，因为conversationDiv元素不存在
+                // 错误消息将通过其他方式显示
+            }
+        };
+    }
+
+    // 断开连接
+    disconnect() {
+        if (!this.websocket) return;
+
+        this.websocket.close();
+        const audioRecorder = getAudioRecorder();
+        audioRecorder.stop();
+
+        // 关闭摄像头
+        if (typeof window.stopCamera === 'function') {
+            window.stopCamera();
+        }
+
+        // 隐藏摄像头显示区域
+        const cameraContainer = document.getElementById('cameraContainer');
+        if (cameraContainer) {
+            cameraContainer.classList.remove('active');
+        }
+    }
+
+    // 发送文本消息
+    sendTextMessage(text) {
+        if (text === '' || !this.websocket || this.websocket.readyState !== WebSocket.OPEN) {
+            return false;
+        }
+
+        try {
+            // 如果对方正在说话，先发送打断消息
+            if (this.isRemoteSpeaking && this.currentSessionId) {
+                const abortMessage = {
+                    session_id: this.currentSessionId,
+                    type: 'abort',
+                    reason: 'wake_word_detected'
+                };
+                this.websocket.send(JSON.stringify(abortMessage));
+                log('发送打断消息', 'info');
+            }
+
+            const listenMessage = {
+                type: 'listen',
+                state: 'detect',
+                text: text
+            };
+
+            this.websocket.send(JSON.stringify(listenMessage));
+            log(`发送文本消息: ${text}`, 'info');
+
+            return true;
+        } catch (error) {
+            log(`发送消息错误: ${error.message}`, 'error');
+            return false;
+        }
+    }
+
+    /**
+     * 触发Live2D情绪动作
+     * @param {string} emotion - 情绪名称
+     */
+    triggerLive2DEmotionAction(emotion) {
+        try {
+            const live2dManager = window.chatApp?.live2dManager;
+            if (live2dManager && typeof live2dManager.triggerEmotionAction === 'function') {
+                live2dManager.triggerEmotionAction(emotion);
+                log(`触发Live2D情绪动作: ${emotion}`, 'info');
+            } else {
+                log(`无法触发Live2D情绪动作: Live2D管理器未找到或方法不可用`, 'warning');
+            }
+        } catch (error) {
+            log(`触发Live2D情绪动作失败: ${error.message}`, 'error');
+        }
+    }
+
+    // 获取WebSocket实例
+    getWebSocket() {
+        return this.websocket;
+    }
+
+    // 检查是否已连接
+    isConnected() {
+        return this.websocket && this.websocket.readyState === WebSocket.OPEN;
+    }
+}
+
+// 创建单例
+let wsHandlerInstance = null;
+
+export function getWebSocketHandler() {
+    if (!wsHandlerInstance) {
+        wsHandlerInstance = new WebSocketHandler();
+    }
+    return wsHandlerInstance;
+}

main/digital-human/js/live2d/live2d.js

@@ -0,0 +1,824 @@
+/**
+ * Live2D 管理器
+ * 负责 Live2D 模型的初始化、嘴部动画控制等功能
+ */
+class Live2DManager {
+    constructor() {
+        this.live2dApp = null;
+        this.live2dModel = null;
+        this.isTalking = false;
+        this.mouthAnimationId = null;
+        this.mouthParam = 'ParamMouthOpenY';
+        this.audioContext = null;
+        this.analyser = null;
+        this.dataArray = null;
+        this.lastEmotionActionTime = null;
+        this.currentModelName = null;
+
+        // 模型特定配置
+        this.modelConfig = {
+            'hiyori_pro_zh': {
+                mouthParam: 'ParamMouthOpenY',
+                mouthAmplitude: 1.0,
+                mouthThresholds: { low: 0.3, high: 0.7 },
+                motionMap: {
+                    'FlickUp': 'FlickUp',
+                    'FlickDown': 'FlickDown',
+                    'Tap': 'Tap',
+                    'Tap@Body': 'Tap@Body',
+                    'Flick': 'Flick',
+                    'Flick@Body': 'Flick@Body'
+                }
+            },
+            'natori_pro_zh': {
+                mouthParam: 'ParamMouthOpenY',
+                mouthAmplitude: 1.0,
+                mouthThresholds: { low: 0.1, high: 0.4 },
+                mouthFormParam: 'ParamMouthForm',
+                mouthFormAmplitude: 1.0,
+                mouthForm2Param: 'ParamMouthForm2',
+                mouthForm2Amplitude: 0.8,
+                motionMap: {
+                    'FlickUp': 'FlickUp',
+                    'FlickDown': 'Flick@Body',
+                    'Tap': 'Tap',
+                    'Tap@Body': 'Tap@Head',
+                    'Flick': 'Tap',
+                    'Flick@Body': 'Flick@Body'
+                }
+            }
+        };
+
+        // 情绪到动作的映射
+        this.emotionToActionMap = {
+            'happy': 'FlickUp',      // 开心-向上轻扫动作
+            'laughing': 'FlickUp',   // 大笑-向上轻扫动作
+            'funny': 'FlickUp',      // 搞笑-向上轻扫动作
+            'sad': 'FlickDown',      // 伤心-向下轻扫动作
+            'crying': 'FlickDown',   // 哭泣-向下轻扫动作
+            'angry': 'Tap@Body',     // 生气-身体点击动作
+            'surprised': 'Tap',      // 惊讶-点击动作
+            'neutral': 'Flick',      // 平常-轻扫动作
+            'default': 'Flick@Body'  // 默认-身体轻扫动作
+        };
+
+        // 单/双击判定配置与状态
+        this._lastClickTime = 0;
+        this._lastClickPos = { x: 0, y: 0 };
+        this._singleClickTimer = null;
+        this._doubleClickMs = 280; // 双击时间阈值(ms)
+        this._doubleClickDist = 16; // 双击允许的最大位移(px)
+        // 滑动判定
+        this._pointerDown = false;
+        this._downPos = { x: 0, y: 0 };
+        this._downTime = 0;
+        this._downArea = 'Body';
+        this._movedBeyondClick = false;
+        this._swipeMinDist = 24; // 触发滑动的最小距离
+    }
+
+    /**
+     * 初始化 Live2D
+     */
+    async initializeLive2D() {
+        try {
+            const canvas = document.getElementById('live2d-stage');
+
+            // 供内部使用
+            window.PIXI = PIXI;
+
+            this.live2dApp = new PIXI.Application({
+                view: canvas,
+                height: window.innerHeight,
+                width: window.innerWidth,
+                resolution: window.devicePixelRatio,
+                autoDensity: true,
+                antialias: true,
+                backgroundAlpha: 0,
+            });
+
+            // 加载 Live2D 模型 - 动态检测当前目录，适配不同环境
+            // 获取当前HTML文件所在的目录路径
+            const currentPath = window.location.pathname;
+            const lastSlashIndex = currentPath.lastIndexOf('/');
+            const basePath = currentPath.substring(0, lastSlashIndex + 1);
+
+            // 从 localStorage 读取上次选择的模型，如果没有则使用默认
+            const savedModelName = localStorage.getItem('live2dModel') || 'hiyori_pro_zh';
+            const modelFileMap = {
+                'hiyori_pro_zh': 'hiyori_pro_t11.model3.json',
+                'natori_pro_zh': 'natori_pro_t06.model3.json'
+            };
+            const modelFileName = modelFileMap[savedModelName] || 'hiyori_pro_t11.model3.json';
+            const modelPath = basePath + 'resources/' + savedModelName + '/runtime/' + modelFileName;
+
+            this.live2dModel = await PIXI.live2d.Live2DModel.from(modelPath);
+            this.live2dApp.stage.addChild(this.live2dModel);
+
+            // 保存当前模型名称
+            this.currentModelName = savedModelName;
+
+            // 更新下拉框显示
+            const modelSelect = document.getElementById('live2dModelSelect');
+            if (modelSelect) {
+                modelSelect.value = savedModelName;
+            }
+
+            // 设置模型特定的嘴部参数名
+            if (this.modelConfig[savedModelName]) {
+                this.mouthParam = this.modelConfig[savedModelName].mouthParam || 'ParamMouthOpenY';
+            }
+
+            // 设置模型属性
+            this.live2dModel.scale.set(0.33);
+            this.live2dModel.x = (window.innerWidth - this.live2dModel.width) * 0.5;
+            this.live2dModel.y = -50;
+
+            // 启用交互并监听点击命中（头部/身体等）
+
+            this.live2dModel.interactive = true;
+
+
+            this.live2dModel.on('doublehit', (args) => {
+                const area = Array.isArray(args) ? args[0] : args;
+
+                // 触发双击动作
+                if (area === 'Body') {
+                    this.motion('Flick@Body');
+                } else if (area === 'Head' || area === 'Face') {
+                    this.motion('Flick');
+                }
+
+                const app = window.chatApp;
+                const payload = JSON.stringify({ type: 'live2d', event: 'doublehit', area });
+                if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                    app.dataChannel.send(payload);
+                }
+
+            });
+
+            this.live2dModel.on('singlehit', (args) => {
+                const area = Array.isArray(args) ? args[0] : args;
+
+                // 触发单击动作
+                if (area === 'Body') {
+                    this.motion('Tap@Body');
+                } else if (area === 'Head' || area === 'Face') {
+                    this.motion('Tap');
+                }
+
+                const app = window.chatApp;
+                const payload = JSON.stringify({ type: 'live2d', event: 'singlehit', area });
+                if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                    app.dataChannel.send(payload);
+                }
+
+            });
+
+            this.live2dModel.on('swipe', (args) => {
+                const area = Array.isArray(args) ? args[0] : args;
+                const dir = Array.isArray(args) ? args[1] : undefined;
+
+                // 触发滑动动作
+                if (area === 'Body') {
+                    if (dir === 'up') {
+                        this.motion('FlickUp');
+                    } else if (dir === 'down') {
+                        this.motion('FlickDown');
+                    }
+                } else if (area === 'Head' || area === 'Face') {
+                    if (dir === 'up') {
+                        this.motion('FlickUp');
+                    } else if (dir === 'down') {
+                        this.motion('FlickDown');
+                    }
+                }
+
+                const app = window.chatApp;
+                const payload = JSON.stringify({ type: 'live2d', event: 'swipe', area, dir });
+                if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                    app.dataChannel.send(payload);
+                }
+
+            });
+
+            // 兜底：自定义"头部/身体"命中区域 + 单/双击/滑动区分
+            this.live2dModel.on('pointerdown', (event) => {
+                try {
+                    const global = event.data.global;
+                    const bounds = this.live2dModel.getBounds();
+                    // 仅在点击落在模型可见范围内时判定
+                    if (!bounds || !bounds.contains(global.x, global.y)) return;
+
+                    const relX = (global.x - bounds.x) / (bounds.width || 1);
+                    const relY = (global.y - bounds.y) / (bounds.height || 1);
+                    let area = '';
+                    // 经验阈值：模型可见矩形的上部 20% 视为"头部"区域
+                    if (relX >= 0.4 && relX <= 0.6) {
+                        if (relY <= 0.15) {
+                            area = 'Head';
+                        } else if (relY <= 0.23) {
+                            area = 'Face';
+                        } else {
+                            area = 'Body';
+                        }
+                    }
+                    if (area === '') {
+                        return;
+                    }
+
+                    // 记录按下状态用于滑动判定
+                    this._pointerDown = true;
+                    this._downPos = { x: global.x, y: global.y };
+                    this._downTime = performance.now();
+                    this._downArea = area;
+                    this._movedBeyondClick = false;
+
+                    const now = performance.now();
+                    const dt = now - (this._lastClickTime || 0);
+                    const dx = global.x - (this._lastClickPos?.x || 0);
+                    const dy = global.y - (this._lastClickPos?.y || 0);
+                    const dist = Math.hypot(dx, dy);
+
+                    // 命中确认：仅当点击在模型上时做单/双击判断
+                    if (this._lastClickTime && dt <= this._doubleClickMs && dist <= this._doubleClickDist) {
+                        // 判定为双击：取消待触发的单击事件
+                        if (this._singleClickTimer) {
+                            clearTimeout(this._singleClickTimer);
+                            this._singleClickTimer = null;
+                        }
+                        if (typeof this.live2dModel.emit === 'function') {
+                            this.live2dModel.emit('doublehit', [area]);
+                        }
+                        this._lastClickTime = 0;
+                        this._pointerDown = false; // 双击完成，重置状态
+                        return;
+                    }
+
+                    // 可能是单击：记录并延迟确认
+                    this._lastClickTime = now;
+                    this._lastClickPos = { x: global.x, y: global.y };
+                    if (this._singleClickTimer) {
+                        clearTimeout(this._singleClickTimer);
+                        this._singleClickTimer = null;
+                    }
+                    this._singleClickTimer = setTimeout(() => {
+                        // 若在等待期间发生了移动超过阈值，则不再当作单击
+                        if (!this._movedBeyondClick && typeof this.live2dModel.emit === 'function') {
+                            this.live2dModel.emit('singlehit', [area]);
+                        }
+                        this._singleClickTimer = null;
+                        this._lastClickTime = 0;
+                    }, this._doubleClickMs);
+                } catch (e) {
+                    // 忽略自定义命中判断中的异常，避免影响主流程
+                }
+            });
+
+            // 指针移动：用于判定是否从"点击"升级为"滑动"
+            this.live2dModel.on('pointermove', (event) => {
+                try {
+                    if (!this._pointerDown) return;
+                    const global = event.data.global;
+                    const dx = global.x - this._downPos.x;
+                    const dy = global.y - this._downPos.y;
+                    const dist = Math.hypot(dx, dy);
+
+                    // 使用 _doubleClickDist 作为点击/滑动的判定阈值
+                    if (dist > this._doubleClickDist) {
+                        this._movedBeyondClick = true;
+                        // 若已超出点击阈值，取消可能的单击触发
+                        if (this._singleClickTimer) {
+                            clearTimeout(this._singleClickTimer);
+                            this._singleClickTimer = null;
+                        }
+                        this._lastClickTime = 0;
+                    }
+                } catch (e) {
+                    // 忽略移动判定中的异常
+                }
+            });
+
+            // 指针抬起：确认是否为滑动
+            const handlePointerUp = (event) => {
+                try {
+                    if (!this._pointerDown) return;
+                    const global = (event && event.data && event.data.global) ? event.data.global : { x: this._downPos.x, y: this._downPos.y };
+                    const dx = global.x - this._downPos.x;
+                    const dy = global.y - this._downPos.y;
+                    const dist = Math.hypot(dx, dy);
+
+                    // 滑动：超过滑动最小距离则触发 swipe 事件（携带方向与区域）
+                    if (this._movedBeyondClick && dist >= this._swipeMinDist) {
+                        if (typeof this.live2dModel.emit === 'function') {
+                            const dir = Math.abs(dx) >= Math.abs(dy)
+                                ? (dx > 0 ? 'right' : 'left')
+                                : (dy > 0 ? 'down' : 'up');
+                            this.live2dModel.emit('swipe', [this._downArea, dir]);
+                        }
+                        // 终止：不再让单击/双击触发
+                        if (this._singleClickTimer) {
+                            clearTimeout(this._singleClickTimer);
+                            this._singleClickTimer = null;
+                        }
+                        this._lastClickTime = 0;
+                    }
+                } catch (e) {
+                    // 忽略抬起判定中的异常
+                }
+                finally {
+                    this._pointerDown = false;
+                    this._movedBeyondClick = false;
+                }
+            };
+
+            this.live2dModel.on('pointerup', handlePointerUp);
+            this.live2dModel.on('pointerupoutside', handlePointerUp);
+
+            // 添加窗口大小变化监听器，保持模型在Canvas中间和底部
+            window.addEventListener('resize', () => {
+                if (this.live2dModel) {
+                    // 使用窗口实际尺寸重新计算模型位置
+                    this.live2dModel.x = (window.innerWidth - this.live2dModel.width) * 0.5;
+                    this.live2dModel.y = -50;
+                }
+            });
+
+        } catch (err) {
+            console.error('加载 Live2D 模型失败:', err);
+        }
+    }
+
+    /**
+     * 初始化音频分析器 - 使用音频播放器的分析器节点
+     */
+    initializeAudioAnalyzer() {
+        try {
+            // 获取音频播放器实例
+            const audioPlayer = window.chatApp?.audioPlayer;
+            if (!audioPlayer) {
+                console.warn('音频播放器未初始化，无法获取分析器节点');
+                return false;
+            }
+
+            // 获取音频播放器的音频上下文
+            this.audioContext = audioPlayer.getAudioContext();
+            if (!this.audioContext) {
+                console.warn('无法获取音频播放器的音频上下文');
+                return false;
+            }
+
+            // 创建分析器节点
+            this.analyser = this.audioContext.createAnalyser();
+            this.analyser.fftSize = 256;
+            this.dataArray = new Uint8Array(this.analyser.frequencyBinCount);
+
+            return true;
+        } catch (error) {
+            console.error('初始化音频分析器失败:', error);
+            return false;
+        }
+    }
+
+    /**
+     * 连接到音频播放器的输出节点
+     */
+    connectToAudioPlayer() {
+        try {
+            // 获取音频播放器的流上下文
+            const audioPlayer = window.chatApp?.audioPlayer;
+            if (!audioPlayer || !audioPlayer.streamingContext) {
+                console.warn('音频播放器或流上下文未初始化');
+                return false;
+            }
+
+            // 获取音频播放器的流上下文
+            const streamingContext = audioPlayer.streamingContext;
+
+            // 获取分析器节点
+            const analyser = streamingContext.getAnalyser();
+            if (!analyser) {
+                console.warn('音频播放器尚未创建分析器节点，无法连接');
+                return false;
+            }
+
+            // 使用音频播放器的分析器节点
+            this.analyser = analyser;
+            this.dataArray = new Uint8Array(this.analyser.frequencyBinCount);
+            return true;
+        } catch (error) {
+            console.error('连接到音频播放器失败:', error);
+            return false;
+        }
+    }
+
+    /**
+     * 嘴部动画循环
+     */
+    animateMouth() {
+        if (!this.isTalking) return;
+        if (!this.live2dModel) return;
+        const internal = this.live2dModel && this.live2dModel.internalModel;
+        if (internal && internal.coreModel) {
+            const coreModel = internal.coreModel;
+
+            let mouthOpenY = 0;
+            let mouthForm = 0;
+            let mouthForm2 = 0;
+            let average = 0;
+
+            if (this.analyser && this.dataArray) {
+                this.analyser.getByteFrequencyData(this.dataArray);
+                average = this.dataArray.reduce((a, b) => a + b) / this.dataArray.length;
+
+                const normalizedVolume = average / 255;
+
+                // 获取模型特定的阈值
+                let lowThreshold = 0.3;
+                let highThreshold = 0.7;
+                if (this.currentModelName && this.modelConfig[this.currentModelName]) {
+                    lowThreshold = this.modelConfig[this.currentModelName].mouthThresholds?.low || 0.3;
+                    highThreshold = this.modelConfig[this.currentModelName].mouthThresholds?.high || 0.7;
+                }
+
+                // 使用模型特定的阈值进行映射
+                let minOpenY = 0.1;
+                if (this.currentModelName && this.modelConfig[this.currentModelName]) {
+                    minOpenY = this.modelConfig[this.currentModelName].mouthMinOpenY || 0.1;
+                }
+
+                if (normalizedVolume < lowThreshold) {
+                    mouthOpenY = minOpenY + Math.pow(normalizedVolume / lowThreshold, 1.5) * (0.4 - minOpenY);
+                } else if (normalizedVolume < highThreshold) {
+                    mouthOpenY = 0.4 + (normalizedVolume - lowThreshold) / (highThreshold - lowThreshold) * 0.4;
+                } else {
+                    mouthOpenY = 0.8 + Math.pow((normalizedVolume - highThreshold) / (1 - highThreshold), 1.2) * 0.2;
+                }
+
+                // 应用模型特定的嘴部开合幅度
+                let amplitudeMultiplier = 1.0;
+                let maxOpenY = 2.5;
+                if (this.currentModelName && this.modelConfig[this.currentModelName]) {
+                    amplitudeMultiplier = this.modelConfig[this.currentModelName].mouthAmplitude;
+                    maxOpenY = this.modelConfig[this.currentModelName].maxOpenY || 2.5;
+                }
+                mouthOpenY = mouthOpenY * amplitudeMultiplier;
+                mouthOpenY = Math.min(Math.max(mouthOpenY, 0), maxOpenY);
+
+                // 计算嘴型参数（仅对支持嘴型变化的模型）
+                if (this.currentModelName && this.modelConfig[this.currentModelName]?.mouthFormParam) {
+                    const config = this.modelConfig[this.currentModelName];
+                    const formAmplitude = config.mouthFormAmplitude || 0.5;
+                    const form2Amplitude = config.mouthForm2Amplitude || 0;
+
+                    // 嘴型随音量变化：
+                    // 低音量：嘴型偏"一"字（负值）
+                    // 高音量：嘴型偏"o"字（正值）
+                    // 音量=0时：嘴型=0（自然状态）
+                    mouthForm = (normalizedVolume - 0.5) * 2 * formAmplitude;
+                    mouthForm = Math.max(-formAmplitude, Math.min(formAmplitude, mouthForm));
+
+                    // 第二嘴型参数（natori特有）
+                    if (config.mouthForm2Param) {
+                        mouthForm2 = (normalizedVolume - 0.3) * 2 * form2Amplitude;
+                        mouthForm2 = Math.max(-form2Amplitude, Math.min(form2Amplitude, mouthForm2));
+                    }
+                }
+
+                // 调试日志：输出嘴部参数
+                console.log(`[Live2D] 模型: ${this.currentModelName || 'unknown'}, 音量: ${average?.toFixed(0)}, OpenY: ${mouthOpenY.toFixed(3)}, Form: ${mouthForm.toFixed(3)}, Form2: ${mouthForm2.toFixed(3)}`);
+            }
+
+            // 设置嘴部开合参数
+            coreModel.setParameterValueById(this.mouthParam, mouthOpenY);
+
+            // 设置嘴型参数（仅对支持嘴型变化的模型）
+            if (this.currentModelName && this.modelConfig[this.currentModelName]?.mouthFormParam) {
+                const config = this.modelConfig[this.currentModelName];
+                const formParam = config.mouthFormParam;
+                coreModel.setParameterValueById(formParam, mouthForm);
+
+                // 设置第二嘴型参数（natori特有）
+                if (config.mouthForm2Param) {
+                    coreModel.setParameterValueById(config.mouthForm2Param, mouthForm2);
+                }
+            }
+
+            coreModel.update();
+        }
+        this.mouthAnimationId = requestAnimationFrame(() => this.animateMouth());
+    }
+
+    /**
+     * 开始说话动画
+     */
+    startTalking() {
+        if (this.isTalking || !this.live2dModel) return;
+
+        // 确保音频分析器已初始化
+        if (!this.analyser) {
+            if (!this.initializeAudioAnalyzer()) {
+                console.warn('音频分析器初始化失败，将使用模拟动画');
+                // 即使分析器初始化失败，也启动动画（使用模拟数据）
+                this.isTalking = true;
+                this.animateMouth();
+                return;
+            }
+        }
+
+        // 连接到音频播放器输出
+        if (!this.connectToAudioPlayer()) {
+            console.warn('无法连接到音频播放器输出，将使用模拟动画');
+        }
+
+        this.isTalking = true;
+        this.animateMouth();
+    }
+
+    /**
+     * 停止说话动画
+     */
+    stopTalking() {
+        this.isTalking = false;
+        if (this.mouthAnimationId) {
+            cancelAnimationFrame(this.mouthAnimationId);
+            this.mouthAnimationId = null;
+        }
+
+        // 重置嘴部参数
+        if (this.live2dModel) {
+            const internal = this.live2dModel.internalModel;
+            if (internal && internal.coreModel) {
+                const coreModel = internal.coreModel;
+                coreModel.setParameterValueById(this.mouthParam, 0);
+                coreModel.update();
+            }
+        }
+    }
+
+    /**
+     * 基于情绪触发动作
+     * @param {string} emotion - 情绪名称
+     */
+    triggerEmotionAction(emotion) {
+        if (!this.live2dModel) return;
+
+        // 添加冷却时间控制，避免过于频繁触发
+        const now = Date.now();
+        if (this.lastEmotionActionTime && now - this.lastEmotionActionTime < 5000) { // 5秒冷却时间
+            return;
+        }
+
+        // 根据情绪获取对应的动作
+        const action = this.emotionToActionMap[emotion] || this.emotionToActionMap['default'];
+
+        // 触发动作并记录时间
+        this.motion(action);
+        this.lastEmotionActionTime = now;
+    }
+
+
+
+    /**
+     * 触发模型动作（Motion）
+     * @param {string} name - 动作分组名称，如 'TapBody'、'FlickUp'、'Idle' 等
+     */
+    motion(name) {
+        try {
+            if (!this.live2dModel) return;
+
+            // 根据当前模型获取对应的动作名称
+            let actualMotionName = name;
+            if (this.currentModelName && this.modelConfig[this.currentModelName]) {
+                const motionMap = this.modelConfig[this.currentModelName].motionMap;
+                actualMotionName = motionMap[name] || name;
+            }
+
+            this.live2dModel.motion(actualMotionName);
+        } catch (error) {
+            console.error('触发动作失败:', error);
+        }
+    }
+
+    /**
+     * 设置模型交互事件
+     */
+    setupModelInteractions() {
+        if (!this.live2dModel) return;
+
+        this.live2dModel.interactive = true;
+
+        this.live2dModel.on('doublehit', (args) => {
+            const area = Array.isArray(args) ? args[0] : args;
+
+            if (area === 'Body') {
+                this.motion('Flick@Body');
+            } else if (area === 'Head' || area === 'Face') {
+                this.motion('Flick');
+            }
+
+            const app = window.chatApp;
+            const payload = JSON.stringify({ type: 'live2d', event: 'doublehit', area });
+            if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                app.dataChannel.send(payload);
+            }
+        });
+
+        this.live2dModel.on('singlehit', (args) => {
+            const area = Array.isArray(args) ? args[0] : args;
+
+            if (area === 'Body') {
+                this.motion('Tap@Body');
+            } else if (area === 'Head' || area === 'Face') {
+                this.motion('Tap');
+            }
+
+            const app = window.chatApp;
+            const payload = JSON.stringify({ type: 'live2d', event: 'singlehit', area });
+            if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                app.dataChannel.send(payload);
+            }
+        });
+
+        this.live2dModel.on('swipe', (args) => {
+            const area = Array.isArray(args) ? args[0] : args;
+            const dir = Array.isArray(args) ? args[1] : undefined;
+
+            if (area === 'Body') {
+                if (dir === 'up') {
+                    this.motion('FlickUp');
+                } else if (dir === 'down') {
+                    this.motion('FlickDown');
+                }
+            }
+
+            const app = window.chatApp;
+            const payload = JSON.stringify({ type: 'live2d', event: 'swipe', area, dir });
+            if (app && app.dataChannel && app.dataChannel.readyState === 'open') {
+                app.dataChannel.send(payload);
+            }
+        });
+
+        this.live2dModel.on('pointerdown', (event) => {
+            try {
+                const global = event.data.global;
+                const bounds = this.live2dModel.getBounds();
+                if (!bounds || !bounds.contains(global.x, global.y)) return;
+
+                const relX = (global.x - bounds.x) / (bounds.width || 1);
+                const relY = (global.y - bounds.y) / (bounds.height || 1);
+                let area = '';
+
+                if (relX >= 0.4 && relX <= 0.6) {
+                    if (relY <= 0.15) {
+                        area = 'Head';
+                    } else if (relY >= 0.7) {
+                        area = 'Body';
+                    }
+                }
+
+                if (!area) return;
+
+                const now = Date.now();
+                const dt = now - (this._lastClickTime || 0);
+                const dx = global.x - (this._lastClickPos?.x || 0);
+                const dy = global.y - (this._lastClickPos?.y || 0);
+                const dist = Math.hypot(dx, dy);
+
+                if (this._lastClickTime && dt <= this._doubleClickMs && dist <= this._doubleClickDist) {
+                    if (this._singleClickTimer) {
+                        clearTimeout(this._singleClickTimer);
+                        this._singleClickTimer = null;
+                    }
+
+                    this.live2dModel.emit('doublehit', area);
+                    this._lastClickTime = null;
+                    this._lastClickPos = null;
+                } else {
+                    this._lastClickTime = now;
+                    this._lastClickPos = { x: global.x, y: global.y };
+
+                    this._singleClickTimer = setTimeout(() => {
+                        this._singleClickTimer = null;
+                        this.live2dModel.emit('singlehit', area);
+                    }, this._doubleClickMs);
+                }
+            } catch (e) {
+                console.warn('pointerdown 处理出错:', e);
+            }
+        });
+    }
+
+    /**
+     * 清理资源
+     */
+    destroy() {
+        this.stopTalking();
+
+        // 清理音频分析器
+        if (this.audioContext) {
+            this.audioContext.close();
+            this.audioContext = null;
+        }
+        this.analyser = null;
+        this.dataArray = null;
+
+        // 清理 Live2D 应用
+        if (this.live2dApp) {
+            this.live2dApp.destroy(true);
+            this.live2dApp = null;
+        }
+        this.live2dModel = null;
+    }
+
+    /**
+     * 切换 Live2D 模型
+     * @param {string} modelName - 模型目录名称，如 'hiyori_pro_zh'、'natori_pro_zh'
+     * @returns {Promise<boolean>} - 切换是否成功
+     */
+    async switchModel(modelName) {
+        try {
+            // 获取模型文件名映射
+            const modelFileMap = {
+                'hiyori_pro_zh': 'hiyori_pro_t11.model3.json',
+                'natori_pro_zh': 'natori_pro_t06.model3.json',
+                'chitose': 'chitose.model3.json',
+                'haru_greeter_pro_jp': 'haru_greeter_t05.model3.json'
+            };
+
+            const modelFileName = modelFileMap[modelName];
+            if (!modelFileName) {
+                console.error('未知的模型名称:', modelName);
+                return false;
+            }
+
+            // 获取基础路径
+            const currentPath = window.location.pathname;
+            const lastSlashIndex = currentPath.lastIndexOf('/');
+            const basePath = currentPath.substring(0, lastSlashIndex + 1);
+            const modelPath = basePath + 'resources/' + modelName + '/runtime/' + modelFileName;
+
+            // 如果已存在模型，先移除
+            if (this.live2dModel) {
+                this.live2dApp.stage.removeChild(this.live2dModel);
+                this.live2dModel.destroy();
+                this.live2dModel = null;
+            }
+
+            // 显示加载状态
+            const app = window.chatApp;
+            if (app) {
+                app.setModelLoadingStatus(true);
+            }
+
+            // 加载新模型
+            this.live2dModel = await PIXI.live2d.Live2DModel.from(modelPath);
+            this.live2dApp.stage.addChild(this.live2dModel);
+
+            // 设置模型属性
+            this.live2dModel.scale.set(0.33);
+            this.live2dModel.x = (window.innerWidth - this.live2dModel.width) * 0.5;
+            this.live2dModel.y = -50;
+
+            // 重新绑定交互事件
+            this.setupModelInteractions();
+
+            // 隐藏加载状态
+            if (app) {
+                app.setModelLoadingStatus(false);
+            }
+
+            // 保存当前模型名称
+            this.currentModelName = modelName;
+
+            // 设置模型特定的嘴部参数名
+            if (this.modelConfig[modelName]) {
+                this.mouthParam = this.modelConfig[modelName].mouthParam || 'ParamMouthOpenY';
+            }
+
+            // 保存到 localStorage
+            localStorage.setItem('live2dModel', modelName);
+
+            // 更新下拉框显示
+            const modelSelect = document.getElementById('live2dModelSelect');
+            if (modelSelect) {
+                modelSelect.value = modelName;
+            }
+
+            console.log('模型切换成功:', modelName);
+            return true;
+        } catch (error) {
+            console.error('切换模型失败:', error);
+            const app = window.chatApp;
+            if (app) {
+                app.setModelLoadingStatus(false);
+            }
+            return false;
+        }
+    }
+
+
+}
+
+// 导出全局实例
+window.Live2DManager = Live2DManager;

main/digital-human/js/ui/background-load.js

@@ -0,0 +1,27 @@
+// 背景图加载检测
+(function() {
+    const backgroundContainer = document.getElementById('backgroundContainer');
+
+    // 提取背景图片URL
+    let bgImageUrl = window.getComputedStyle(backgroundContainer).backgroundImage;
+    const urlMatch = bgImageUrl && bgImageUrl.match(/url\(["']?(.*?)["']?\)/);
+    
+    if (!urlMatch || !urlMatch[1]) {
+        console.warn('未提取到有效的背景图片URL');
+        return;
+    }
+    
+    bgImageUrl = urlMatch[1];
+    
+    const bgImage = new Image();
+    bgImage.onerror = function() {
+        console.error('背景图片加载失败:', bgImageUrl);
+    };
+
+    // 加载成功显示模型加载
+    bgImage.onload = function() {
+        modelLoading.style.display = 'flex';
+    };
+
+    bgImage.src = bgImageUrl;
+})();

main/digital-human/js/ui/controller.js

@@ -0,0 +1,929 @@
+// UI controller module
+import { loadConfig, saveConfig } from '../config/manager.js?v=0205';
+import { getAudioPlayer } from '../core/audio/player.js?v=0205';
+import { getAudioRecorder } from '../core/audio/recorder.js?v=0205';
+import { requestWakewordBridge, stopWakewordBridgeListener, startWakewordBridgeListener, getWakewordBridgeUrl, onNextBridgeConnected } from '../core/network/wakeword-bridge.js?v=0205';
+import { getWebSocketHandler } from '../core/network/websocket.js?v=0205';
+import { log } from '../utils/logger.js?v=0205';
+
+// UI controller class
+class UIController {
+    constructor() {
+        this.isEditing = false;
+        this.visualizerCanvas = null;
+        this.visualizerContext = null;
+        this.audioStatsTimer = null;
+        this.currentBackgroundIndex = localStorage.getItem('backgroundIndex') ? parseInt(localStorage.getItem('backgroundIndex')) : 0;
+        this.backgroundImages = ['1.png', '2.png', '3.png'];
+        this.dialBtnDisabled = false;
+        this.isConnecting = false;
+        this.lastWakewordDialTime = 0;
+
+        // Bind methods
+        this.init = this.init.bind(this);
+        this.initEventListeners = this.initEventListeners.bind(this);
+        this.updateDialButton = this.updateDialButton.bind(this);
+        this.addChatMessage = this.addChatMessage.bind(this);
+        this.switchBackground = this.switchBackground.bind(this);
+        this.switchLive2DModel = this.switchLive2DModel.bind(this);
+        this.showModal = this.showModal.bind(this);
+        this.hideModal = this.hideModal.bind(this);
+        this.switchTab = this.switchTab.bind(this);
+        this.applyWakewordConfig = this.applyWakewordConfig.bind(this);
+        this.handleApplyWakeword = this.handleApplyWakeword.bind(this);
+        this.triggerWakewordDial = this.triggerWakewordDial.bind(this);
+    }
+
+    // Initialize
+    init() {
+        console.log('UIController init started');
+
+        this.visualizerCanvas = document.getElementById('audioVisualizer');
+        if (this.visualizerCanvas) {
+            this.visualizerContext = this.visualizerCanvas.getContext('2d');
+            this.initVisualizer();
+        }
+
+        // Check if connect button exists during initialization
+        const connectBtn = document.getElementById('connectBtn');
+        console.log('connectBtn during init:', connectBtn);
+
+        this.initEventListeners();
+        this.startAudioStatsMonitor();
+        loadConfig();
+
+        // Register recording callback
+        const audioRecorder = getAudioRecorder();
+        audioRecorder.onRecordingStart = (seconds) => {
+            this.updateRecordButtonState(true, seconds);
+        };
+
+        // Initialize status display
+        this.updateConnectionUI(false);
+        // Apply saved background
+        const backgroundContainer = document.querySelector('.background-container');
+        if (backgroundContainer) {
+            backgroundContainer.style.backgroundImage = `url('./images/${this.backgroundImages[this.currentBackgroundIndex]}')`;
+        }
+
+        this.updateDialButton(false);
+
+        console.log('UIController init completed');
+    }
+
+    // Initialize visualizer
+    initVisualizer() {
+        if (this.visualizerCanvas) {
+            this.visualizerCanvas.width = this.visualizerCanvas.clientWidth;
+            this.visualizerCanvas.height = this.visualizerCanvas.clientHeight;
+            this.visualizerContext.fillStyle = '#fafafa';
+            this.visualizerContext.fillRect(0, 0, this.visualizerCanvas.width, this.visualizerCanvas.height);
+        }
+    }
+
+    // Initialize event listeners
+    initEventListeners() {
+        // Settings button
+        const settingsBtn = document.getElementById('settingsBtn');
+        if (settingsBtn) {
+            settingsBtn.addEventListener('click', () => {
+                this.showModal('settingsModal');
+            });
+        }
+
+        // Background switch button
+        const backgroundBtn = document.getElementById('backgroundBtn');
+        if (backgroundBtn) {
+            backgroundBtn.addEventListener('click', this.switchBackground);
+        }
+
+        // Model select change event
+        const modelSelect = document.getElementById('live2dModelSelect');
+        if (modelSelect) {
+            modelSelect.addEventListener('change', () => {
+                this.switchLive2DModel();
+            });
+        }
+
+        // Camera switch button
+        const cameraSwitch = document.getElementById('cameraSwitch');
+        const cameraSwitchMask = document.getElementById('cameraSwitchMask');
+        if (cameraSwitchMask) {
+            cameraSwitchMask.addEventListener('click', () => {
+                const isCameraActive = cameraSwitch.classList.contains('active');
+                if (isCameraActive) {
+                    window.switchCamera();
+                }
+            })
+        }
+
+        // Dial button
+        const dialBtn = document.getElementById('dialBtn');
+        if (dialBtn) {
+            dialBtn.addEventListener('click', () => {
+                dialBtn.disabled = true;
+                this.dialBtnDisabled = true;
+                setTimeout(() => {
+                    dialBtn.disabled = false;
+                    this.dialBtnDisabled = false;
+                }, 3000);
+
+                const wsHandler = getWebSocketHandler();
+                const isConnected = wsHandler.isConnected();
+
+                if (isConnected) {
+                    wsHandler.disconnect();
+                    this.updateDialButton(false);
+                    if (cameraSwitch) cameraSwitch.classList.remove('active');
+                    this.addChatMessage('Disconnected, see you next time~😊', false);
+                } else {
+                    // Check if OTA URL is filled
+                    const otaUrlInput = document.getElementById('otaUrl');
+                    if (!otaUrlInput || !otaUrlInput.value.trim()) {
+                        // If OTA URL is not filled, show settings modal and switch to device tab
+                        this.showModal('settingsModal');
+                        this.switchTab('device');
+                        this.addChatMessage('Please fill in OTA server URL', false);
+                        return;
+                    }
+
+                    // Start connection process
+                    this.handleConnect();
+                }
+            });
+        }
+
+        // Camera button
+        const cameraBtn = document.getElementById('cameraBtn');
+        let cameraTimer = null;
+        if (cameraBtn) {
+            cameraBtn.addEventListener('click', () => {
+                if (cameraTimer) {
+                    clearTimeout(cameraTimer);
+                    cameraTimer = null;
+                }
+                cameraTimer = setTimeout(() => {
+                    const cameraContainer = document.getElementById('cameraContainer');
+                    if (!cameraContainer) {
+                        log('摄像头容器不存在', 'warning');
+                        return;
+                    }
+
+                    const isActive = cameraContainer.classList.contains('active');
+                    if (isActive) {
+                        // 关闭摄像头
+                        if (typeof window.stopCamera === 'function') {
+                            if (cameraSwitch) cameraSwitch.classList.remove('active');
+                            window.stopCamera();
+                        }
+                        cameraContainer.classList.remove('active');
+                        cameraBtn.classList.remove('camera-active');
+                        cameraBtn.querySelector('.btn-text').textContent = '摄像头';
+                        log('摄像头已关闭', 'info');
+                    } else {
+                        // 打开摄像头
+                        if (typeof window.startCamera === 'function') {
+                            window.startCamera().then(success => {
+                                if (success) {
+                                    cameraBtn.classList.add('camera-active');
+                                    cameraBtn.querySelector('.btn-text').textContent = '关闭';
+                                } else {
+                                    this.addChatMessage('⚠️ 摄像头启动失败，请检查浏览器权限', false);
+                                }
+                            }).catch(error => {
+                                log(`启动摄像头异常: ${error.message}`, 'error');
+                            });
+                        } else {
+                            log('startCamera函数未定义', 'warning');
+                        }
+                    }
+                }, 300);
+            });
+        }
+
+        // Record button
+        const recordBtn = document.getElementById('recordBtn');
+        if (recordBtn) {
+            let recordTimer = null;
+            recordBtn.addEventListener('click', () => {
+                if (recordTimer) {
+                    clearTimeout(recordTimer);
+                    recordTimer = null;
+                }
+                recordTimer = setTimeout(() => {
+                    const audioRecorder = getAudioRecorder();
+                    if (audioRecorder.isRecording) {
+                        audioRecorder.stop();
+                        // Restore record button to normal state
+                        recordBtn.classList.remove('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音';
+                    } else {
+                        // Update button state to recording
+                        recordBtn.classList.add('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音中';
+
+                        // Start recording, update button state after delay
+                        setTimeout(() => {
+                            audioRecorder.start();
+                        }, 100);
+                    }
+                }, 300);
+            });
+        }
+
+        // Chat input event listener
+        const chatIpt = document.getElementById('chatIpt');
+        if (chatIpt) {
+            const wsHandler = getWebSocketHandler();
+            chatIpt.addEventListener('keydown', (e) => {
+                if (e.key === 'Enter') {
+                    if (e.target.value) {
+                        wsHandler.sendTextMessage(e.target.value);
+                        e.target.value = '';
+                        return;
+                    }
+                }
+            });
+        }
+
+        // Close button
+        const closeButtons = document.querySelectorAll('.close-btn');
+        closeButtons.forEach(btn => {
+            btn.addEventListener('click', (e) => {
+                e.stopPropagation();
+                const modal = e.target.closest('.modal');
+                if (modal) {
+                    if (modal.id === 'settingsModal') {
+                        saveConfig();
+                    }
+                    this.hideModal(modal.id);
+                }
+            });
+        });
+
+        // Settings tab switch
+        const tabBtns = document.querySelectorAll('.tab-btn');
+        tabBtns.forEach(btn => {
+            btn.addEventListener('click', (e) => {
+                this.switchTab(e.target.dataset.tab);
+            });
+        });
+
+        const applyWakewordBtn = document.getElementById('applyWakewordBtn');
+        if (applyWakewordBtn) {
+            applyWakewordBtn.addEventListener('click', this.handleApplyWakeword);
+        }
+
+        // 点击模态框背景关闭（仅对特定模态框禁用此功能）
+        const modals = document.querySelectorAll('.modal');
+        modals.forEach(modal => {
+            modal.addEventListener('click', (e) => {
+                if (e.target === modal) {
+                    // settingsModal、mcpToolModal、mcpPropertyModal 只能通过点击X关闭
+                    const nonClosableModals = ['settingsModal', 'mcpToolModal', 'mcpPropertyModal'];
+                    if (nonClosableModals.includes(modal.id)) {
+                        return; // 禁止点击背景关闭
+                    }
+                    this.hideModal(modal.id);
+                }
+            });
+        });
+
+        // Add MCP tool button
+        const addMCPToolBtn = document.getElementById('addMCPToolBtn');
+        if (addMCPToolBtn) {
+            addMCPToolBtn.addEventListener('click', (e) => {
+                e.stopPropagation();
+                this.addMCPTool();
+            });
+        }
+
+        // Connect button and send button are not removed, can be added to dial button later
+    }
+
+    // Update connection status UI
+    updateConnectionUI(isConnected) {
+        const connectionStatus = document.getElementById('connectionStatus');
+        const statusDot = document.querySelector('.status-dot');
+
+        if (connectionStatus) {
+            if (isConnected) {
+                connectionStatus.textContent = '已连接';
+                if (statusDot) {
+                    statusDot.className = 'status-dot status-connected';
+                }
+            } else {
+                connectionStatus.textContent = '离线';
+                if (statusDot) {
+                    statusDot.className = 'status-dot status-disconnected';
+                }
+            }
+        }
+    }
+
+    // Update dial button state
+    updateDialButton(isConnected) {
+        const dialBtn = document.getElementById('dialBtn');
+        const recordBtn = document.getElementById('recordBtn');
+        const cameraBtn = document.getElementById('cameraBtn');
+
+        if (dialBtn) {
+            if (isConnected) {
+                dialBtn.classList.add('dial-active');
+                dialBtn.querySelector('.btn-text').textContent = '挂断';
+                // Update dial button icon to hang up icon
+                dialBtn.querySelector('svg').innerHTML = `
+                    <path d="M12,9C10.4,9 9,10.4 9,12C9,13.6 10.4,15 12,15C13.6,15 15,13.6 15,12C15,10.4 13.6,9 12,9M12,17C9.2,17 7,14.8 7,12C7,9.2 9.2,7 12,7C14.8,7 17,9.2 17,12C17,14.8 14.8,17 12,17M12,4.5C7,4.5 2.7,7.6 1,12C2.7,16.4 7,19.5 12,19.5C17,19.5 21.3,16.4 23,12C21.3,7.6 17,4.5 12,4.5Z"/>
+                `;
+            } else {
+                dialBtn.classList.remove('dial-active');
+                dialBtn.querySelector('.btn-text').textContent = '拨号';
+                // Restore dial button icon
+                dialBtn.querySelector('svg').innerHTML = `
+                    <path d="M6.62,10.79C8.06,13.62 10.38,15.94 13.21,17.38L15.41,15.18C15.69,14.9 16.08,14.82 16.43,14.93C17.55,15.3 18.75,15.5 20,15.5A1,1 0 0,1 21,16.5V20A1,1 0 0,1 20,21A17,17 0 0,1 3,4A1,1 0 0,1 4,3H7.5A1,1 0 0,1 8.5,4C8.5,5.25 8.7,6.45 9.07,7.57C9.18,7.92 9.1,8.31 8.82,8.59L6.62,10.79Z"/>
+                `;
+            }
+        }
+
+        // Update camera button state - reset to default when disconnected
+        if (cameraBtn && !isConnected) {
+            const cameraContainer = document.getElementById('cameraContainer');
+            if (cameraContainer && cameraContainer.classList.contains('active')) {
+                cameraContainer.classList.remove('active');
+            }
+            cameraBtn.classList.remove('camera-active');
+            cameraBtn.querySelector('.btn-text').textContent = '摄像头';
+            cameraBtn.disabled = true;
+            cameraBtn.title = '请先连接服务器';
+            // 关闭摄像头
+            if (typeof window.stopCamera === 'function') {
+                window.stopCamera();
+            }
+        }
+
+        // Update camera button state - enable when connected and camera is available
+        if (cameraBtn && isConnected) {
+            if (window.cameraAvailable) {
+                cameraBtn.disabled = false;
+                cameraBtn.title = '打开/关闭摄像头';
+            } else {
+                cameraBtn.disabled = true;
+                cameraBtn.title = '请先绑定验证码';
+            }
+        }
+
+        // Update record button state
+        if (recordBtn) {
+            const microphoneAvailable = window.microphoneAvailable !== false;
+            if (isConnected && microphoneAvailable) {
+                recordBtn.disabled = false;
+                recordBtn.title = '开始录音';
+                // Restore record button to normal state
+                recordBtn.querySelector('.btn-text').textContent = '录音';
+                recordBtn.classList.remove('recording');
+            } else {
+                recordBtn.disabled = true;
+                if (!microphoneAvailable) {
+                    recordBtn.title = window.isHttpNonLocalhost ? '当前由于是http访问，无法录音，只能用文字交互' : '麦克风不可用';
+                } else {
+                    recordBtn.title = '请先连接服务器';
+                }
+                // Restore record button to normal state
+                recordBtn.querySelector('.btn-text').textContent = '录音';
+                recordBtn.classList.remove('recording');
+            }
+        }
+    }
+
+    // Update record button state
+    updateRecordButtonState(isRecording, seconds = 0) {
+        const recordBtn = document.getElementById('recordBtn');
+        if (recordBtn) {
+            if (isRecording) {
+                recordBtn.querySelector('.btn-text').textContent = `录音中`;
+                recordBtn.classList.add('recording');
+            } else {
+                recordBtn.querySelector('.btn-text').textContent = '录音';
+                recordBtn.classList.remove('recording');
+            }
+            // Only enable button when microphone is available
+            recordBtn.disabled = window.microphoneAvailable === false;
+        }
+    }
+
+    /**
+     * Update microphone availability state
+     * @param {boolean} isAvailable - Whether microphone is available
+     * @param {boolean} isHttpNonLocalhost - Whether it is HTTP non-localhost access
+     */
+    updateMicrophoneAvailability(isAvailable, isHttpNonLocalhost) {
+        const recordBtn = document.getElementById('recordBtn');
+        if (!recordBtn) return;
+        if (!isAvailable) {
+            // Disable record button
+            recordBtn.disabled = true;
+            // Update button text and title
+            recordBtn.querySelector('.btn-text').textContent = '录音';
+            recordBtn.title = isHttpNonLocalhost ? '当前由于是http访问，无法录音，只能用文字交互' : '麦克风不可用';
+
+        } else {
+            // If connected, enable record button
+            const wsHandler = getWebSocketHandler();
+            if (wsHandler && wsHandler.isConnected()) {
+                recordBtn.disabled = false;
+                recordBtn.title = '开始录音';
+            }
+        }
+    }
+
+    // Add chat message
+    addChatMessage(content, isUser = false) {
+        const chatStream = document.getElementById('chatStream');
+        if (!chatStream) return;
+
+        const messageDiv = document.createElement('div');
+        messageDiv.className = `chat-message ${isUser ? 'user' : 'ai'}`;
+        messageDiv.innerHTML = `<div class="message-bubble">${content}</div>`;
+        chatStream.appendChild(messageDiv);
+
+        // Scroll to bottom
+        chatStream.scrollTop = chatStream.scrollHeight;
+    }
+
+    // Switch background
+    switchBackground() {
+        this.currentBackgroundIndex = (this.currentBackgroundIndex + 1) % this.backgroundImages.length;
+        const backgroundContainer = document.querySelector('.background-container');
+        if (backgroundContainer) {
+            backgroundContainer.style.backgroundImage = `url('./images/${this.backgroundImages[this.currentBackgroundIndex]}')`;
+        }
+        localStorage.setItem('backgroundIndex', this.currentBackgroundIndex);
+    }
+
+    // Switch Live2D model
+    switchLive2DModel() {
+        const modelSelect = document.getElementById('live2dModelSelect');
+        if (!modelSelect) {
+            console.error('模型选择下拉框不存在');
+            return;
+        }
+
+        const selectedModel = modelSelect.value;
+        const app = window.chatApp;
+
+        if (app && app.live2dManager) {
+            app.live2dManager.switchModel(selectedModel)
+                .then(success => {
+                    if (success) {
+                        this.addChatMessage(`已切换到模型: ${selectedModel}`, false);
+                    } else {
+                        this.addChatMessage('模型切换失败', false);
+                    }
+                })
+                .catch(error => {
+                    console.error('模型切换错误:', error);
+                    this.addChatMessage('模型切换出错', false);
+                });
+        } else {
+            this.addChatMessage('Live2D管理器未初始化', false);
+        }
+    }
+
+    // Show modal
+    showModal(modalId) {
+        const modal = document.getElementById(modalId);
+        if (modal) {
+            modal.style.display = 'flex';
+        }
+    }
+
+    // Hide modal
+    hideModal(modalId) {
+        const modal = document.getElementById(modalId);
+        if (modal) {
+            modal.style.display = 'none';
+        }
+    }
+
+    // Switch tab
+    switchTab(tabName) {
+        // Remove active class from all tabs
+        const tabBtns = document.querySelectorAll('.tab-btn');
+        const tabContents = document.querySelectorAll('.tab-content');
+
+        tabBtns.forEach(btn => btn.classList.remove('active'));
+        tabContents.forEach(content => content.classList.remove('active'));
+
+        // Activate selected tab
+        const activeTabBtn = document.querySelector(`[data-tab="${tabName}"]`);
+        const activeTabContent = document.getElementById(`${tabName}Tab`);
+
+        if (activeTabBtn && activeTabContent) {
+            activeTabBtn.classList.add('active');
+            activeTabContent.classList.add('active');
+        }
+    }
+
+    applyWakewordConfig(config = {}) {
+        const wakewordEnabledInput = document.getElementById('wakewordEnabled');
+        const wakewordListInput = document.getElementById('wakewordList');
+
+        if (!wakewordEnabledInput || !wakewordListInput) {
+            return;
+        }
+
+        const wakeWords = Array.isArray(config.wakeWords)
+            ? config.wakeWords.filter(item => typeof item === 'string' && item.trim())
+            : [];
+
+        wakewordEnabledInput.value = config.enabled === false ? 'false' : 'true';
+        wakewordListInput.value = wakeWords.join('\n');
+        saveConfig();
+    }
+
+    async handleApplyWakeword() {
+        const wakewordEnabledInput = document.getElementById('wakewordEnabled');
+        const wakewordListInput = document.getElementById('wakewordList');
+        const wakewordWsUrlInput = document.getElementById('wakewordWsUrl');
+        if (!wakewordEnabledInput || !wakewordListInput) {
+            return;
+        }
+
+        const wakeWords = wakewordListInput.value
+            .split(/\r?\n/u)
+            .map(item => item.trim())
+            .filter(Boolean)
+            .filter((item, index, items) => items.indexOf(item) === index);
+
+        const payload = {
+            enabled: wakewordEnabledInput.value !== 'false',
+            wakeWords,
+        };
+
+        if (payload.enabled && payload.wakeWords.length === 0) {
+            this.addChatMessage('启用唤醒词时，至少需要填写一个唤醒词。', false);
+            return;
+        }
+
+        const applyWakewordBtn = document.getElementById('applyWakewordBtn');
+        if (applyWakewordBtn) {
+            applyWakewordBtn.disabled = true;
+            applyWakewordBtn.textContent = '应用中...';
+        }
+
+        try {
+            // 保存地址到 localStorage
+            if (wakewordWsUrlInput && wakewordWsUrlInput.value.trim()) {
+                localStorage.setItem('xz_tester_wakewordWsUrl', wakewordWsUrlInput.value.trim());
+            }
+
+            // 比较新地址和当前连接地址
+            const newWsUrl = localStorage.getItem('xz_tester_wakewordWsUrl');
+            const currentWsUrl = getWakewordBridgeUrl();
+            const urlChanged = newWsUrl !== currentWsUrl;
+
+            if (urlChanged) {
+                // 地址变了，先确认
+                const shouldRestart = window.confirm('地址已变更，是否继续？（将断开旧连接并重新连接）');
+                if (!shouldRestart) {
+                    // 恢复 localStorage 里的旧地址
+                    localStorage.setItem('xz_tester_wakewordWsUrl', currentWsUrl);
+                    this.addChatMessage('已取消地址变更。', false);
+                    return;
+                }
+
+                // 断开旧连接
+                stopWakewordBridgeListener();
+
+                // 启动新连接（自动用新地址）
+                startWakewordBridgeListener();
+
+                // 等 bridge_connected
+                await new Promise((resolve, reject) => {
+                    const timeout = setTimeout(() => {
+                        reject(new Error('连接新服务器超时'));
+                    }, 5000);
+
+                    onNextBridgeConnected(() => {
+                        clearTimeout(timeout);
+                        resolve();
+                    });
+                });
+
+                // 发配置和重启
+                await requestWakewordBridge('set_wakeword_config', payload);
+                this.applyWakewordConfig(payload);
+                await requestWakewordBridge('restart_wakeword_service');
+                this.addChatMessage('唤醒词配置已保存，唤醒词服务正在重启。', false);
+            } else {
+                // 地址没变：直接在当前连接操作
+                const response = await requestWakewordBridge('set_wakeword_config', payload);
+                this.applyWakewordConfig(response.payload || payload);
+
+                const shouldRestart = window.confirm('唤醒词已保存。是否现在重启唤醒词服务以立即生效？');
+                if (!shouldRestart) {
+                    this.addChatMessage('唤醒词配置已保存，可稍后手动重启服务后生效。', false);
+                    return;
+                }
+
+                await requestWakewordBridge('restart_wakeword_service');
+                this.addChatMessage('唤醒词配置已保存，唤醒词服务正在重启。', false);
+            }
+        } catch (error) {
+            this.addChatMessage(`应用唤醒词失败: ${error.message}`, false);
+        } finally {
+            if (applyWakewordBtn) {
+                applyWakewordBtn.disabled = false;
+                applyWakewordBtn.textContent = '应用唤醒词';
+            }
+        }
+    }
+
+    // Start AI chat session after connection
+    startAIChatSession() {
+        this.addChatMessage('连接成功，开始聊天吧~😊', false);
+        // Check microphone availability and show error messages if needed
+        if (!window.microphoneAvailable) {
+            if (window.isHttpNonLocalhost) {
+                this.addChatMessage('⚠️ 当前由于是http访问，无法录音，只能用文字交互', false);
+            } else {
+                this.addChatMessage('⚠️ 麦克风不可用，请检查权限设置，只能用文字交互', false);
+            }
+        }
+        // Start recording only if microphone is available
+        if (window.microphoneAvailable) {
+            const recordBtn = document.getElementById('recordBtn');
+            if (recordBtn) {
+                recordBtn.click();
+            }
+        }
+        // Start camera only if camera is available (bound with verification code)
+        if (window.cameraAvailable && typeof window.startCamera === 'function') {
+            window.startCamera().then(success => {
+                if (success) {
+                    const cameraBtn = document.getElementById('cameraBtn');
+                    if (cameraBtn) {
+                        cameraBtn.classList.add('camera-active');
+                        cameraBtn.querySelector('.btn-text').textContent = '关闭';
+                    }
+                } else {
+                    this.addChatMessage('⚠️ 摄像头启动失败，可能被浏览器拒绝', false);
+                }
+            }).catch(error => {
+                log(`启动摄像头异常: ${error.message}`, 'error');
+            });
+        }
+    }
+
+    // Handle connect button click
+    async handleConnect() {
+        const wsHandler = getWebSocketHandler();
+        if (this.isConnecting || (wsHandler && wsHandler.isConnected())) {
+            log('连接已存在或正在进行，忽略本次拨号请求', 'info');
+            return;
+        }
+
+        this.isConnecting = true;
+        console.log('handleConnect called');
+
+        try {
+            // Switch to device settings tab
+            this.switchTab('device');
+
+            // Wait for DOM update
+            await new Promise(resolve => setTimeout(resolve, 50));
+
+            const otaUrlInput = document.getElementById('otaUrl');
+
+            console.log('otaUrl element:', otaUrlInput);
+
+            if (!otaUrlInput || !otaUrlInput.value) {
+                this.addChatMessage('请输入OTA服务器地址', false);
+                return;
+            }
+
+            const otaUrl = otaUrlInput.value;
+            console.log('otaUrl value:', otaUrl);
+
+            // Update dial button state to connecting
+            const dialBtn = document.getElementById('dialBtn');
+            if (dialBtn) {
+                dialBtn.classList.add('dial-active');
+                dialBtn.querySelector('.btn-text').textContent = '连接中...';
+                dialBtn.disabled = true;
+            }
+
+            // Show connecting message
+            this.addChatMessage('正在连接服务器...', false);
+
+            const chatIpt = document.getElementById('chatIpt');
+            if (chatIpt) {
+                chatIpt.style.display = 'flex';
+            }
+
+            // Get WebSocket handler instance
+            // Register connection state callback BEFORE connecting
+            wsHandler.onConnectionStateChange = (isConnected) => {
+                this.updateConnectionUI(isConnected);
+                this.updateDialButton(isConnected);
+            };
+
+            // Register chat message callback BEFORE connecting
+            wsHandler.onChatMessage = (text, isUser) => {
+                this.addChatMessage(text, isUser);
+            };
+
+            // Register record button state callback BEFORE connecting
+            wsHandler.onRecordButtonStateChange = (isRecording) => {
+                const recordBtn = document.getElementById('recordBtn');
+                if (recordBtn) {
+                    if (isRecording) {
+                        recordBtn.classList.add('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音中';
+                    } else {
+                        recordBtn.classList.remove('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音';
+                    }
+                }
+            };
+
+            const isConnected = await wsHandler.connect();
+
+            if (isConnected) {
+                // Check microphone availability (check again after connection)
+                const { checkMicrophoneAvailability } = await import('../core/audio/recorder.js?v=0205');
+                const micAvailable = await checkMicrophoneAvailability();
+
+                if (!micAvailable) {
+                    const isHttp = window.isHttpNonLocalhost;
+                    if (isHttp) {
+                        this.addChatMessage('⚠️ 当前由于是http访问，无法录音，只能用文字交互', false);
+                    }
+                    // Update global state
+                    window.microphoneAvailable = false;
+                }
+
+                // Update dial button state
+                const dialBtn = document.getElementById('dialBtn');
+                if (dialBtn) {
+                    if (!this.dialBtnDisabled) {
+                        dialBtn.disabled = false;
+                    }
+                    dialBtn.querySelector('.btn-text').textContent = '挂断';
+                    dialBtn.classList.add('dial-active');
+                }
+
+                this.hideModal('settingsModal');
+            } else {
+                throw new Error('OTA连接失败');
+            }
+        } catch (error) {
+            console.error('Connection error details:', {
+                message: error.message,
+                stack: error.stack,
+                name: error.name
+            });
+
+            // Show error message
+            const errorMessage = error.message.includes('Cannot set properties of null')
+                ? '连接失败：请检查设备连接'
+                : `连接失败: ${error.message}`;
+
+            this.addChatMessage(errorMessage, false);
+
+            // Restore dial button state
+            const dialBtn = document.getElementById('dialBtn');
+            if (dialBtn) {
+                if (!this.dialBtnDisabled) {
+                    dialBtn.disabled = false;
+                }
+                dialBtn.querySelector('.btn-text').textContent = '拨号';
+                dialBtn.classList.remove('dial-active');
+                console.log('Dial button state restored successfully');
+            }
+        } finally {
+            this.isConnecting = false;
+        }
+    }
+
+    async triggerWakewordDial(wakeWord = '唤醒词') {
+        const wsHandler = getWebSocketHandler();
+        const now = Date.now();
+
+        if (wsHandler && wsHandler.isConnected()) {
+            log('页面已连接，忽略自动拨号', 'info');
+            return false;
+        }
+
+        if (this.isConnecting || this.dialBtnDisabled) {
+            log('页面正在连接中，忽略重复唤醒', 'info');
+            return false;
+        }
+
+        if (now - this.lastWakewordDialTime < 3000) {
+            log('唤醒触发过于频繁，忽略本次自动拨号', 'warning');
+            return false;
+        }
+
+        this.lastWakewordDialTime = now;
+        this.addChatMessage(`检测到唤醒词“${wakeWord}”，准备连接服务器...`, false);
+        await this.handleConnect();
+        return true;
+    }
+
+    // Add MCP tool
+    addMCPTool() {
+        const mcpToolsList = document.getElementById('mcpToolsList');
+        if (!mcpToolsList) return;
+
+        const toolId = `mcp-tool-${Date.now()}`;
+        const toolDiv = document.createElement('div');
+        toolDiv.className = 'properties-container';
+        toolDiv.innerHTML = `
+            <div class="property-item">
+                <input type="text" placeholder="工具名称" value="新工具">
+                <input type="text" placeholder="工具描述" value="工具描述">
+                <button class="remove-property" onclick="uiController.removeMCPTool('${toolId}')">删除</button>
+            </div>
+        `;
+
+        mcpToolsList.appendChild(toolDiv);
+    }
+
+    // Remove MCP tool
+    removeMCPTool(toolId) {
+        const toolElement = document.getElementById(toolId);
+        if (toolElement) {
+            toolElement.remove();
+        }
+    }
+
+    // Update audio statistics display
+    updateAudioStats() {
+        const audioPlayer = getAudioPlayer();
+        if (!audioPlayer) return;
+
+        const stats = audioPlayer.getAudioStats();
+        // Here can add audio statistics UI update logic
+    }
+
+    // Start audio statistics monitor
+    startAudioStatsMonitor() {
+        // Update audio statistics every 100ms
+        this.audioStatsTimer = setInterval(() => {
+            this.updateAudioStats();
+        }, 100);
+    }
+
+    // Stop audio statistics monitor
+    stopAudioStatsMonitor() {
+        if (this.audioStatsTimer) {
+            clearInterval(this.audioStatsTimer);
+            this.audioStatsTimer = null;
+        }
+    }
+
+    // Draw audio visualizer waveform
+    drawVisualizer(dataArray) {
+        if (!this.visualizerContext || !this.visualizerCanvas) return;
+
+        this.visualizerContext.fillStyle = '#fafafa';
+        this.visualizerContext.fillRect(0, 0, this.visualizerCanvas.width, this.visualizerCanvas.height);
+
+        const barWidth = (this.visualizerCanvas.width / dataArray.length) * 2.5;
+        let barHeight;
+        let x = 0;
+
+        for (let i = 0; i < dataArray.length; i++) {
+            barHeight = dataArray[i] / 2;
+
+            // Create gradient color: from purple to blue to green
+            const gradient = this.visualizerContext.createLinearGradient(0, 0, 0, this.visualizerCanvas.height);
+            gradient.addColorStop(0, '#8e44ad');
+            gradient.addColorStop(0.5, '#3498db');
+            gradient.addColorStop(1, '#1abc9c');
+
+            this.visualizerContext.fillStyle = gradient;
+            this.visualizerContext.fillRect(x, this.visualizerCanvas.height - barHeight, barWidth, barHeight);
+            x += barWidth + 1;
+        }
+    }
+
+    // Update session status UI
+    updateSessionStatus(isSpeaking) {
+        // Here can add session status UI update logic
+        // For example: update Live2D model's mouth movement status
+    }
+
+    // Update session emotion
+    updateSessionEmotion(emoji) {
+        // Here can add emotion update logic
+        // For example: display emoji in status indicator
+    }
+}
+
+// Create singleton instance
+export const uiController = new UIController();
+
+// Export class for module usage
+export { UIController };

main/digital-human/js/utils/blocking-queue.js

@@ -0,0 +1,103 @@
+export default class BlockingQueue {
+    #items   = [];
+    #waiters = [];          // {resolve, reject, min, timer, onTimeout}
+
+    /* 空队列一次性闸门 */
+    #emptyPromise = null;
+    #emptyResolve = null;
+
+    /* 生产者：把数据塞进去 */
+    enqueue(item, ...restItems) {
+        if (restItems.length === 0) {
+            this.#items.push(item);
+        }
+        // 如果有额外参数，批量处理所有项
+        else {
+            const items = [item, ...restItems].filter(i => i);
+            if (items.length === 0) return;
+            this.#items.push(...items);
+        }
+        // 若有空队列闸门，一次性放行所有等待者
+        if (this.#emptyResolve) {
+            this.#emptyResolve();
+            this.#emptyResolve = null;
+            this.#emptyPromise = null;
+        }
+
+        // 唤醒所有正在等的 waiter
+        this.#wakeWaiters();
+    }
+
+    /* 消费者：min 条或 timeout ms 先到谁 */
+    async dequeue(min = 1, timeout = Infinity, onTimeout = null) {
+        // 1. 若空，等第一次数据到达（所有调用共享同一个 promise）
+        if (this.#items.length === 0) {
+            await this.#waitForFirstItem();
+        }
+
+        // 立即满足
+        if (this.#items.length >= min) {
+            return this.#flush();
+        }
+
+        // 需要等待
+        return new Promise((resolve, reject) => {
+            let timer = null;
+            const waiter = { resolve, reject, min, onTimeout, timer };
+
+            // 超时逻辑
+            if (Number.isFinite(timeout)) {
+                waiter.timer = setTimeout(() => {
+                    this.#removeWaiter(waiter);
+                    if (onTimeout) onTimeout(this.#items.length);
+                    resolve(this.#flush());
+                }, timeout);
+            }
+
+            this.#waiters.push(waiter);
+        });
+    }
+
+    /* 空队列闸门生成器 */
+    #waitForFirstItem() {
+        if (!this.#emptyPromise) {
+            this.#emptyPromise = new Promise(r => (this.#emptyResolve = r));
+        }
+        return this.#emptyPromise;
+    }
+
+    /* 内部：每次数据变动后，检查哪些 waiter 已满足 */
+    #wakeWaiters() {
+        for (let i = this.#waiters.length - 1; i >= 0; i--) {
+            const w = this.#waiters[i];
+            if (this.#items.length >= w.min) {
+                this.#removeWaiter(w);
+                w.resolve(this.#flush());
+            }
+        }
+    }
+
+    #removeWaiter(waiter) {
+        const idx = this.#waiters.indexOf(waiter);
+        if (idx !== -1) {
+            this.#waiters.splice(idx, 1);
+            if (waiter.timer) clearTimeout(waiter.timer);
+        }
+    }
+
+    #flush() {
+        const snapshot = [...this.#items];
+        this.#items.length = 0;
+        return snapshot;
+    }
+
+    /* 当前缓存长度（不含等待者） */
+    get length() {
+        return this.#items.length;
+    }
+
+    /* 清空队列（保持对象引用，不影响等待者） */
+    clear() {
+        this.#items.length = 0;
+    }
+}

main/digital-human/js/utils/logger.js

@@ -0,0 +1,43 @@
+// 日志记录函数
+export function log(message, type = 'info') {
+    // 将消息按换行符分割成多行
+    const lines = message.split('\n');
+    const now = new Date();
+    // const timestamp = `[${now.toLocaleTimeString()}] `;
+    const timestamp = `[${now.toLocaleTimeString()}.${now.getMilliseconds().toString().padStart(3, '0')}] `;
+
+    // 检查是否存在日志容器
+    const logContainer = document.getElementById('logContainer');
+    if (!logContainer) {
+        // 如果日志容器不存在，只输出到控制台
+        console.log(`[${type.toUpperCase()}] ${message}`);
+        return;
+    }
+
+    // 为每一行创建日志条目
+    lines.forEach((line, index) => {
+        const logEntry = document.createElement('div');
+        logEntry.className = `log-entry log-${type}`;
+        // 如果是第一条日志，显示时间戳
+        const prefix = index === 0 ? timestamp : ' '.repeat(timestamp.length);
+        logEntry.textContent = `${prefix}${line}`;
+        // logEntry.textContent = `[${new Date().toLocaleTimeString()}] ${message}`;
+        // logEntry.style 保留起始的空格
+        logEntry.style.whiteSpace = 'pre';
+        if (type === 'error') {
+            logEntry.style.color = 'red';
+        } else if (type === 'debug') {
+            logEntry.style.color = 'gray';
+            return;
+        } else if (type === 'warning') {
+            logEntry.style.color = 'orange';
+        } else if (type === 'success') {
+            logEntry.style.color = 'green';
+        } else {
+            logEntry.style.color = 'black';
+        }
+        logContainer.appendChild(logEntry);
+    });
+
+    logContainer.scrollTop = logContainer.scrollHeight;
+}

main/digital-human/resources/hiyori_pro_zh/ReadMe.txt

@@ -0,0 +1,72 @@
+
+============================================================
+
+示例模型
+桃濑日和 - PRO
+
+============================================================
+
+  该示例时基于Cubism3.0制作的标准模型素材。
+
+  可用于学习变形器的构造以及参数的使用方法。
+  模型的肩部应用了新功能【胶水】。
+
+
+------------------------------
+素材使用许可
+------------------------------
+
+　普通用户以及小规模企业在同意授权协议的情况下可用于商业用途。
+　中/大规模的企业只能用于非公开的内部试用。
+　在使用该素材时，请确认以下的【无偿提供素材使用授权协议】中的“授权类型”、“Live2D原创角色”等的相关内容，
+　并必须接受【Live2D Cubism 示例模型的使用授权要求】中的利用条件。
+
+　有关许可证的更多信息，请参阅以下页面。
+　https://www.live2d.com/zh-CHS/download/sample-data/
+
+
+------------------------------
+创作者
+------------------------------
+
+  插画：Kani Biimu
+  模型：Live2D
+
+
+------------------------------
+素材内容
+------------------------------
+
+  模型文件(cmo3)　※包含物理模拟的设定
+  动画文件(can3)
+  嵌入文件列表(runtime文件夹)
+  ・模型数据(moc3)
+  ・动作数据(motion3.json)
+  ・模型设定文件(model3.json)
+  ・物理模拟设定文件(physics3.json)
+  ・姿势设定文件(pose3.json)
+  ・辅助显示的文件(cdi3.json)
+
+
+------------------------------
+更新记录
+------------------------------
+
+【cmo3】
+
+　hiyori_pro_t11
+　2023年03月08日 修改了部分模型关键点
+
+  hiyori_pro_t10
+  2021年06月10日 公开
+
+
+【can3】
+
+　hiyori_pro_t04
+　2023年03月08日 修改了部分动画关键帧
+
+  hiyori_pro_t03
+  2021年06月10日 公开
+
+　

main/digital-human/resources/hiyori_pro_zh/runtime/hiyori_pro_t11.cdi3.json

@@ -0,0 +1,533 @@
+{
+	"Version": 3,
+	"Parameters": [
+		{
+			"Id": "ParamAngleX",
+			"GroupId": "ParamGroupFace",
+			"Name": "角度 X"
+		},
+		{
+			"Id": "ParamAngleY",
+			"GroupId": "ParamGroupFace",
+			"Name": "角度 Y"
+		},
+		{
+			"Id": "ParamAngleZ",
+			"GroupId": "ParamGroupFace",
+			"Name": "角度 Z"
+		},
+		{
+			"Id": "ParamCheek",
+			"GroupId": "ParamGroupFace",
+			"Name": "脸颊泛红"
+		},
+		{
+			"Id": "ParamEyeLOpen",
+			"GroupId": "ParamGroupEyes",
+			"Name": "左眼 开闭"
+		},
+		{
+			"Id": "ParamEyeLSmile",
+			"GroupId": "ParamGroupEyes",
+			"Name": "左眼 微笑"
+		},
+		{
+			"Id": "ParamEyeROpen",
+			"GroupId": "ParamGroupEyes",
+			"Name": "右眼 开闭"
+		},
+		{
+			"Id": "ParamEyeRSmile",
+			"GroupId": "ParamGroupEyes",
+			"Name": "右眼 微笑"
+		},
+		{
+			"Id": "ParamEyeBallX",
+			"GroupId": "ParamGroupEyeballs",
+			"Name": "眼珠 X"
+		},
+		{
+			"Id": "ParamEyeBallY",
+			"GroupId": "ParamGroupEyeballs",
+			"Name": "眼珠 Y"
+		},
+		{
+			"Id": "ParamBrowLY",
+			"GroupId": "ParamGroupBrows",
+			"Name": "左眉 上下"
+		},
+		{
+			"Id": "ParamBrowRY",
+			"GroupId": "ParamGroupBrows",
+			"Name": "右眉 上下"
+		},
+		{
+			"Id": "ParamBrowLX",
+			"GroupId": "ParamGroupBrows",
+			"Name": "左眉 左右"
+		},
+		{
+			"Id": "ParamBrowRX",
+			"GroupId": "ParamGroupBrows",
+			"Name": "右眉 左右"
+		},
+		{
+			"Id": "ParamBrowLAngle",
+			"GroupId": "ParamGroupBrows",
+			"Name": "左眉 角度"
+		},
+		{
+			"Id": "ParamBrowRAngle",
+			"GroupId": "ParamGroupBrows",
+			"Name": "右眉 角度"
+		},
+		{
+			"Id": "ParamBrowLForm",
+			"GroupId": "ParamGroupBrows",
+			"Name": "左眉 变形"
+		},
+		{
+			"Id": "ParamBrowRForm",
+			"GroupId": "ParamGroupBrows",
+			"Name": "右眉 变形"
+		},
+		{
+			"Id": "ParamMouthForm",
+			"GroupId": "ParamGroupMouth",
+			"Name": "嘴 变形"
+		},
+		{
+			"Id": "ParamMouthOpenY",
+			"GroupId": "ParamGroupMouth",
+			"Name": "嘴 开闭"
+		},
+		{
+			"Id": "ParamBodyAngleX",
+			"GroupId": "ParamGroupBody",
+			"Name": "身体的旋转 X"
+		},
+		{
+			"Id": "ParamBodyAngleY",
+			"GroupId": "ParamGroupBody",
+			"Name": "身体的旋转 Y"
+		},
+		{
+			"Id": "ParamBodyAngleZ",
+			"GroupId": "ParamGroupBody",
+			"Name": "身体的旋转 Z"
+		},
+		{
+			"Id": "ParamBreath",
+			"GroupId": "ParamGroupBody",
+			"Name": "呼吸"
+		},
+		{
+			"Id": "ParamShoulder",
+			"GroupId": "ParamGroupBody",
+			"Name": "肩"
+		},
+		{
+			"Id": "ParamLeg",
+			"GroupId": "ParamGroupBody",
+			"Name": "腿"
+		},
+		{
+			"Id": "ParamArmLA",
+			"GroupId": "ParamGroupArms",
+			"Name": "左臂 A"
+		},
+		{
+			"Id": "ParamArmRA",
+			"GroupId": "ParamGroupArms",
+			"Name": "右臂 A"
+		},
+		{
+			"Id": "ParamArmLB",
+			"GroupId": "ParamGroupArms",
+			"Name": "左臂 B"
+		},
+		{
+			"Id": "ParamArmRB",
+			"GroupId": "ParamGroupArms",
+			"Name": "右臂 B"
+		},
+		{
+			"Id": "ParamHandLB",
+			"GroupId": "ParamGroupArms",
+			"Name": "左手B 旋转"
+		},
+		{
+			"Id": "ParamHandRB",
+			"GroupId": "ParamGroupArms",
+			"Name": "右手B 旋转"
+		},
+		{
+			"Id": "ParamHandL",
+			"GroupId": "ParamGroupArms",
+			"Name": "左手"
+		},
+		{
+			"Id": "ParamHandR",
+			"GroupId": "ParamGroupArms",
+			"Name": "右手"
+		},
+		{
+			"Id": "ParamBustY",
+			"GroupId": "ParamGroupSway",
+			"Name": "胸部 摇动"
+		},
+		{
+			"Id": "ParamHairAhoge",
+			"GroupId": "ParamGroupSway",
+			"Name": "头发摇动 呆毛"
+		},
+		{
+			"Id": "ParamHairFront",
+			"GroupId": "ParamGroupSway",
+			"Name": "头发摇动 前"
+		},
+		{
+			"Id": "ParamHairBack",
+			"GroupId": "ParamGroupSway",
+			"Name": "头发摇动 后"
+		},
+		{
+			"Id": "ParamSideupRibbon",
+			"GroupId": "ParamGroupSway",
+			"Name": "发饰的摇动"
+		},
+		{
+			"Id": "ParamRibbon",
+			"GroupId": "ParamGroupSway",
+			"Name": "蝴蝶结的摇动"
+		},
+		{
+			"Id": "ParamSkirt",
+			"GroupId": "ParamGroupSway",
+			"Name": "短裙的摇动"
+		},
+		{
+			"Id": "ParamSkirt2",
+			"GroupId": "ParamGroupSway",
+			"Name": "短裙的上卷"
+		},
+		{
+			"Id": "Param_Angle_Rotation_1_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[0]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_2_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[1]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_3_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[2]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_4_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[3]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_5_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[4]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_6_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[5]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_7_ArtMesh62",
+			"GroupId": "ParamGroup2",
+			"Name": "[6]辫子左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_1_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[0]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_2_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[1]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_3_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[2]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_4_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[3]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_5_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[4]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_6_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[5]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_7_ArtMesh61",
+			"GroupId": "ParamGroup",
+			"Name": "[6]辫子右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_1_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[0]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_2_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[1]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_3_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[2]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_4_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[3]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_5_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[4]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_6_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[5]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_7_ArtMesh55",
+			"GroupId": "ParamGroup4",
+			"Name": "[6]侧发左"
+		},
+		{
+			"Id": "Param_Angle_Rotation_1_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[0]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_2_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[1]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_3_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[2]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_4_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[3]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_5_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[4]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_6_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[5]侧发右"
+		},
+		{
+			"Id": "Param_Angle_Rotation_7_ArtMesh54",
+			"GroupId": "ParamGroup3",
+			"Name": "[6]侧发右"
+		}
+	],
+	"ParameterGroups": [
+		{
+			"Id": "ParamGroupFace",
+			"GroupId": "",
+			"Name": "脸"
+		},
+		{
+			"Id": "ParamGroupEyes",
+			"GroupId": "",
+			"Name": "眼睛"
+		},
+		{
+			"Id": "ParamGroupEyeballs",
+			"GroupId": "",
+			"Name": "眼珠"
+		},
+		{
+			"Id": "ParamGroupBrows",
+			"GroupId": "",
+			"Name": "眉毛"
+		},
+		{
+			"Id": "ParamGroupMouth",
+			"GroupId": "",
+			"Name": "嘴"
+		},
+		{
+			"Id": "ParamGroupBody",
+			"GroupId": "",
+			"Name": "身体"
+		},
+		{
+			"Id": "ParamGroupArms",
+			"GroupId": "",
+			"Name": "手臂"
+		},
+		{
+			"Id": "ParamGroupSway",
+			"GroupId": "",
+			"Name": "摇动"
+		},
+		{
+			"Id": "ParamGroup2",
+			"GroupId": "",
+			"Name": "摇动 辫子左"
+		},
+		{
+			"Id": "ParamGroup",
+			"GroupId": "",
+			"Name": "摇动 辫子右"
+		},
+		{
+			"Id": "ParamGroup4",
+			"GroupId": "",
+			"Name": "摇动 侧发左"
+		},
+		{
+			"Id": "ParamGroup3",
+			"GroupId": "",
+			"Name": "摇动 侧发右"
+		}
+	],
+	"Parts": [
+		{
+			"Id": "PartCore",
+			"Name": "Core"
+		},
+		{
+			"Id": "PartCheek",
+			"Name": "脸颊"
+		},
+		{
+			"Id": "PartBrow",
+			"Name": "眉毛"
+		},
+		{
+			"Id": "PartEye",
+			"Name": "眼睛"
+		},
+		{
+			"Id": "PartNose",
+			"Name": "鼻子"
+		},
+		{
+			"Id": "PartMouth",
+			"Name": "嘴"
+		},
+		{
+			"Id": "PartFace",
+			"Name": "脸"
+		},
+		{
+			"Id": "PartEar",
+			"Name": "耳朵"
+		},
+		{
+			"Id": "PartHairSide",
+			"Name": "侧发"
+		},
+		{
+			"Id": "PartHairFront",
+			"Name": "前发"
+		},
+		{
+			"Id": "PartHairBack",
+			"Name": "后发"
+		},
+		{
+			"Id": "PartNeck",
+			"Name": "脖子"
+		},
+		{
+			"Id": "PartArmA",
+			"Name": "手臂A"
+		},
+		{
+			"Id": "PartArmB",
+			"Name": "手臂B"
+		},
+		{
+			"Id": "PartBody",
+			"Name": "身体"
+		},
+		{
+			"Id": "PartBackground",
+			"Name": "背景"
+		},
+		{
+			"Id": "PartSketch",
+			"Name": "[参考图]"
+		},
+		{
+			"Id": "PartEyeBall",
+			"Name": "眼珠"
+		},
+		{
+			"Id": "ArtMesh55_Skinning",
+			"Name": "侧发右"
+		},
+		{
+			"Id": "Part4",
+			"Name": "侧发左(旋转)"
+		},
+		{
+			"Id": "ArtMesh54_Skinning",
+			"Name": "侧发右(蒙皮)"
+		},
+		{
+			"Id": "Part3",
+			"Name": "侧发右(旋转)"
+		},
+		{
+			"Id": "ArtMesh61_Skinning",
+			"Name": "辫子右(蒙皮)"
+		},
+		{
+			"Id": "Part",
+			"Name": "辫子右(旋转)"
+		},
+		{
+			"Id": "ArtMesh62_Skinning",
+			"Name": "辫子左(蒙皮)"
+		},
+		{
+			"Id": "Part2",
+			"Name": "辫子左(旋转)"
+		}
+	],
+	"CombinedParameters": [
+		[
+			"ParamAngleX",
+			"ParamAngleY"
+		],
+		[
+			"ParamMouthForm",
+			"ParamMouthOpenY"
+		]
+	]
+}

main/digital-human/resources/hiyori_pro_zh/runtime/hiyori_pro_t11.model3.json

@@ -0,0 +1,82 @@
+{
+	"Version": 3,
+	"FileReferences": {
+		"Moc": "hiyori_pro_t11.moc3",
+		"Textures": [
+			"hiyori_pro_t11.2048/texture_00.png",
+			"hiyori_pro_t11.2048/texture_01.png"
+		],
+		"Physics": "hiyori_pro_t11.physics3.json",
+		"Pose": "hiyori_pro_t11.pose3.json",
+		"DisplayInfo": "hiyori_pro_t11.cdi3.json",
+		"Motions": {
+			"Idle": [
+				{
+					"File": "motion/hiyori_m01.motion3.json"
+				},
+				{
+					"File": "motion/hiyori_m02.motion3.json"
+				},
+				{
+					"File": "motion/hiyori_m05.motion3.json"
+				}
+			],
+			"Flick": [
+				{
+					"File": "motion/hiyori_m03.motion3.json"
+				}
+			],
+			"FlickDown": [
+				{
+					"File": "motion/hiyori_m04.motion3.json"
+				}
+			],
+			"FlickUp": [
+				{
+					"File": "motion/hiyori_m06.motion3.json"
+				}
+			],
+			"Tap": [
+				{
+					"File": "motion/hiyori_m07.motion3.json"
+				},
+				{
+					"File": "motion/hiyori_m08.motion3.json"
+				}
+			],
+			"Tap@Body": [
+				{
+					"File": "motion/hiyori_m09.motion3.json"
+				}
+			],
+			"Flick@Body": [
+				{
+					"File": "motion/hiyori_m10.motion3.json"
+				}
+			]
+		}
+	},
+	"Groups": [
+		{
+			"Target": "Parameter",
+			"Name": "LipSync",
+			"Ids": [
+				"ParamMouthOpenY"
+			]
+		},
+		{
+			"Target": "Parameter",
+			"Name": "EyeBlink",
+			"Ids": [
+				"ParamEyeLOpen",
+				"ParamEyeROpen"
+			]
+		}
+	],
+	"HitAreas": [
+		{
+			"Id": "HitArea",
+			"Name": "Body"
+		}
+	]
+}

main/digital-human/resources/hiyori_pro_zh/runtime/hiyori_pro_t11.pose3.json

@@ -0,0 +1,15 @@
+{
+	"Type": "Live2D Pose",
+	"Groups": [
+		[
+			{
+				"Id": "PartArmA",
+				"Link": []
+			},
+			{
+				"Id": "PartArmB",
+				"Link": []
+			}
+		]
+	]
+}