Fix: esp32camera pixel byte order and uart-uhci compiling error (#1728)

* Fix: uart-uhci compiling errors

* Enhance Esp32Camera functionality by adding optional byte swapping for RGB565 format. Introduce SetSwapBytes method to enable/disable byte order swapping, and update Capture method to utilize an encode buffer for improved memory management and performance during image processing.

.clang-format

@@ -0,0 +1,126 @@
+---
+Language: Cpp
+BasedOnStyle: Google
+AccessModifierOffset: -4
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlines: Left
+AlignOperands: true
+AlignTrailingComments: true
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: ExceptShortType
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: false
+  AfterNamespace: false
+  AfterObjCDeclaration: false
+  AfterStruct: false
+  AfterUnion: false
+  AfterExternBlock: false
+  BeforeCatch: false
+  BeforeElse: false
+  IndentBraces: false
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+ColumnLimit: 100
+CommentPragmas: '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat: false
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+ForEachMacros:
+  - cJSON_ArrayForEach
+IncludeBlocks: Preserve
+IncludeCategories:
+  - Regex: '^<esp_.*\.h>'
+    Priority: 1
+  - Regex: '^<driver/.*\.h>'
+    Priority: 1
+  - Regex: '^<.*\.h>'
+    Priority: 2
+  - Regex: '^<.*'
+    Priority: 3
+  - Regex: '.*'
+    Priority: 4
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IndentCaseLabels: true
+IndentPPDirectives: None
+IndentWidth: 4
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd: ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+RawStringFormats:
+  - Language: Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+    BasedOnStyle: google
+ReflowComments: true
+SortIncludes: true
+SortUsingDeclarations: true
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles: false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard: Latest
+StatementMacros:
+  - Q_UNUSED
+  - QT_REQUIRE_VERSION
+TabWidth: 4
+UseTab: Never

.github/ISSUE_TEMPLATE/01_build_install_bug.yml

@@ -0,0 +1,103 @@
+name: Installation or build bug report
+description: Report installation or build bugs
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Answers checklist.
+      description: Before submitting a new issue, please follow the checklist and try to find the answer.
+      options:
+        - label: I have read the documentation [XiaoZhi AI Programming Guide](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb) and the issue is not addressed there.
+          required: true
+        - label: I have updated my branch (master or release) to the latest version and checked that the issue is present there.
+          required: true
+        - label: I have searched the issue tracker for a similar issue and not found a similar issue.
+          required: true
+  - type: input
+    id: xiaozhi_ai_version
+    attributes:
+      label: XiaoZhi AI version.
+      description: On which XiaoZhi AI version does this issue occur on? Run `git describe --tags` to find it.
+      placeholder: ex. v1.1.0-44-g140aab8
+    validations:
+      required: true
+  - type: dropdown
+    id: operating_system
+    attributes:
+      label: Operating System used.
+      multiple: false
+      options:
+        - Windows
+        - Linux
+        - macOS
+    validations:
+      required: true
+  - type: dropdown
+    id: build
+    attributes:
+      label: How did you build your project?
+      multiple: false
+      options:
+        - Command line with CMake
+        - Command line with idf.py
+        - CLion IDE
+        - VS Code IDE/Cursor
+        - Other (please specify in More Information)
+    validations:
+      required: true
+  - type: dropdown
+    id: windows_comand_line
+    attributes:
+      label: If you are using Windows, please specify command line type.
+      multiple: false
+      options:
+        - PowerShell
+        - CMD
+    validations:
+      required: false
+  - type: textarea
+    id: expected
+    attributes:
+      label: What is the expected behavior?
+      description: Please provide a clear and concise description of the expected behavior.
+      placeholder: I expected it to...
+    validations:
+      required: true
+  - type: textarea
+    id: actual
+    attributes:
+      label: What is the actual behavior?
+      description: Please describe actual behavior.
+      placeholder: Instead it...
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce.
+      description: 'How do you trigger this bug? Please walk us through it step by step. If this is build bug, please attach sdkconfig file (from your project folder). Please attach your code here.'
+      value: |
+        1. Step
+        2. Step
+        3. Step
+        ...
+    validations:
+      required: true
+  - type: textarea
+    id: debug_logs
+    attributes:
+      label: Build or installation Logs.
+      description: Build or installation log goes here, should contain the backtrace, as well as the reset source if it is a crash.
+      placeholder: Your log goes here.
+      render: plain
+    validations:
+      required: false
+  - type: textarea
+    id: more-info
+    attributes:
+      label: More Information.
+      description: Do you have any other information from investigating this?
+      placeholder: ex. Any more.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/02_runtime_bug.yml

@@ -0,0 +1,115 @@
+name: Runtime bug report
+description: Report runtime bugs
+labels: ['bug']
+body:
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Answers checklist.
+      description: Before submitting a new issue, please follow the checklist and try to find the answer.
+      options:
+        - label: I  have read the documentation [XiaoZhi AI Programming Guide](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb) and the issue is not addressed there.
+          required: true
+        - label: I have updated my firmware to the latest version and checked that the issue is present there.
+          required: true
+        - label: I have searched the issue tracker for a similar issue and not found a similar issue.
+          required: true
+  - type: input
+    id: xiaozhi_ai_firmware_version
+    attributes:
+      label: XiaoZhi AI firmware version.
+      description: On which firmware version does this issue occur on?
+      placeholder: ex. v1.2.1_bread-compact-wifi
+    validations:
+      required: true
+  - type: dropdown
+    id: operating_system
+    attributes:
+      label: Operating System used.
+      multiple: false
+      options:
+        - Windows
+        - Linux
+        - macOS
+    validations:
+      required: true
+  - type: dropdown
+    id: build
+    attributes:
+      label: How did you build your project?
+      multiple: false
+      options:
+        - Command line with CMake
+        - Command line with idf.py
+        - CLion IDE
+        - VS Code IDE/Cursor
+        - Other (please specify in More Information)
+    validations:
+      required: true
+  - type: dropdown
+    id: windows_comand_line
+    attributes:
+      label: If you are using Windows, please specify command line type.
+      multiple: false
+      options:
+        - PowerShell
+        - CMD
+    validations:
+      required: false
+  - type: dropdown
+    id: power_supply
+    attributes:
+      label: Power Supply used.
+      multiple: false
+      options:
+        - USB
+        - External 5V
+        - External 3.3V
+        - Battery
+    validations:
+      required: true
+  - type: textarea
+    id: expected
+    attributes:
+      label: What is the expected behavior?
+      description: Please provide a clear and concise description of the expected behavior.
+      placeholder: I expected it to...
+    validations:
+      required: true
+  - type: textarea
+    id: actual
+    attributes:
+      label: What is the actual behavior?
+      description: Please describe actual behavior.
+      placeholder: Instead it...
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce.
+      description: 'How do you trigger this bug? Please walk us through it step by step. Please attach your code here.'
+      value: |
+        1. Step
+        2. Step
+        3. Step
+        ...
+    validations:
+      required: true
+  - type: textarea
+    id: debug_logs
+    attributes:
+      label: Debug Logs.
+      description: Debug log goes here, should contain the backtrace, as well as the reset source if it is a crash.
+      placeholder: Your log goes here.
+      render: plain
+    validations:
+      required: false
+  - type: textarea
+    id: more-info
+    attributes:
+      label: More Information.
+      description: Do you have any other information from investigating this?
+      placeholder: ex. Any more.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/03_feature_request.yml

@@ -0,0 +1,34 @@
+name: Feature request
+description: Suggest an idea for this project.
+labels: ['enhancement']
+body:
+  - type: markdown
+    attributes:
+      value: |
+        * We welcome any ideas or feature requests! It’s helpful if you can explain exactly why the feature would be useful.
+        * There are usually some outstanding feature requests in the [existing issues list](https://github.com/78/xiaozhi-esp32/labels/enhancement), feel free to add comments to them.
+        * If you would like to contribute, please read the [contributions guide](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb).
+  - type: textarea
+    id: problem-related
+    attributes:
+      label: Is your feature request related to a problem?
+      description: Please provide a clear and concise description of what the problem is.
+      placeholder: ex. I'm always frustrated when ...
+  - type: textarea
+    id: solution
+    attributes:
+      label: Describe the solution you'd like.
+      description: Please provide a clear and concise description of what you want to happen.
+      placeholder: ex. When using XiaoZhi ...
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Describe alternatives you've considered.
+      description: Please provide a clear and concise description of any alternative solutions or features you've considered.
+      placeholder: ex. Choosing other approach wouldn't work, because ...
+  - type: textarea
+    id: context
+    attributes:
+      label: Additional context.
+      description: Please add any other context or screenshots about the feature request here.
+      placeholder: ex. This would work only when ...

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,8 @@
+blank_issues_enabled: true
+contact_links:
+  - name: 小智 AI 官方网站
+    url: https://xiaozhi.me/
+    about: 激活设备、配置 AI、声纹识别、声音克隆等应有尽有，DIY 属于你自己的小智
+  - name: 小智 AI 聊天机器人百科全书
+    url: https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb
+    about: 开发文档、硬件制作、烧录教程、FAQ尽在小智百科

.github/workflows/build.yml

@@ -0,0 +1,111 @@
+name: Build Boards
+
+on:
+  push:
+    branches:
+      - main
+      - ci/* # for ci test
+  pull_request:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  prepare:
+    name: Determine variants to build
+    runs-on: ubuntu-latest
+    outputs:
+      variants: ${{ steps.select.outputs.variants }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Install jq
+        run: sudo apt-get update && sudo apt-get install -y jq
+
+      - id: list
+        name: Get all variant list
+        run: |
+          echo "all_variants=$(python scripts/release.py --list-boards --json)" >> $GITHUB_OUTPUT
+
+      - id: select
+        name: Select variants based on changes
+        env:
+          ALL_VARIANTS: ${{ steps.list.outputs.all_variants }}
+        run: |
+          EVENT_NAME="${{ github.event_name }}"
+
+          # push 到 main 分支，编译全部变体
+          if [[ "$EVENT_NAME" == "push" ]]; then
+            echo "variants=$ALL_VARIANTS" >> $GITHUB_OUTPUT
+            exit 0
+          fi
+
+          # pull_request 场景
+          BASE_SHA="${{ github.event.pull_request.base.sha }}"
+          HEAD_SHA="${{ github.event.pull_request.head.sha }}"
+          echo "Base: $BASE_SHA, Head: $HEAD_SHA"
+
+          CHANGED=$(git diff --name-only $BASE_SHA $HEAD_SHA || true)
+          echo -e "Changed files:\n$CHANGED"
+
+          NEED_ALL=0
+          declare -A AFFECTED
+          while IFS= read -r file; do
+            if [[ "$file" == main/* && "$file" != main/boards/* ]]; then
+              NEED_ALL=1
+            fi
+
+            if [[ "$file" == main/boards/common/* ]]; then
+              NEED_ALL=1
+            fi
+
+            if [[ "$file" == main/boards/* ]]; then
+              board=$(echo "$file" | cut -d '/' -f3)
+              AFFECTED[$board]=1
+            fi
+          done <<< "$CHANGED"
+
+          if [[ "$NEED_ALL" -eq 1 ]]; then
+            echo "variants=$ALL_VARIANTS" >> $GITHUB_OUTPUT
+          else
+            if [[ ${#AFFECTED[@]} -eq 0 ]]; then
+              echo "variants=[]" >> $GITHUB_OUTPUT
+            else
+              BOARDS_JSON=$(printf '%s\n' "${!AFFECTED[@]}" | sort -u | jq -R -s -c 'split("\n")[:-1]')
+              FILTERED=$(echo "$ALL_VARIANTS" | jq -c --argjson boards "$BOARDS_JSON" 'map(select(.board as $b | $boards | index($b)))')
+              echo "variants=$FILTERED" >> $GITHUB_OUTPUT
+            fi
+          fi
+
+  build:
+    name: Build ${{ matrix.name }}
+    needs: prepare
+    if: ${{ needs.prepare.outputs.variants != '[]' }}
+    strategy:
+      fail-fast: false  # 单个变体失败不影响其它变体
+      matrix:
+        include: ${{ fromJson(needs.prepare.outputs.variants) }}
+    runs-on: ubuntu-latest
+    container:
+      image: espressif/idf:v5.5.2
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Build current variant
+        shell: bash
+        run: |
+          source $IDF_PATH/export.sh
+          python scripts/release.py ${{ matrix.board }} --name ${{ matrix.name }}
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: xiaozhi_${{ matrix.name }}_${{ github.sha }}.bin
+          path: build/merged-binary.bin
+          if-no-files-found: error

.gitignore

@@ -2,9 +2,19 @@ tmp/
 components/
 managed_components/
 build/
+dist/
 .vscode/
 .devcontainer/
 sdkconfig.old
 sdkconfig
 dependencies.lock
 .env
+releases/
+main/assets/lang_config.h
+main/mmap_generate_emoji.h
+.DS_Store
+.cache
+*.pyc
+*.bin
+mmap_generate_*.h
+.clangd

CMakeLists.txt

@@ -1,10 +1,13 @@
-# For more information about build system see
-# https://docs.espressif.com/projects/esp-idf/en/latest/api-guides/build-system.html
-# The following five lines of boilerplate have to be in your project's
+# The following lines of boilerplate have to be in your project's
 # CMakeLists in this exact order for cmake to work correctly
 cmake_minimum_required(VERSION 3.16)
 
-set(PROJECT_VER "0.2.0")
+# Add this line to disable the specific warning
+add_compile_options(-Wno-missing-field-initializers)
 
 include($ENV{IDF_PATH}/tools/cmake/project.cmake)
+# "Trim" the build. Include the minimal set of components, main, and anything it depends on.
+idf_build_set_property(MINIMAL_BUILD ON)
+
+set(PROJECT_VER "2.2.2")
 project(xiaozhi)

LICENSE

@@ -1,6 +1,7 @@
 MIT License
 
-Copyright (c) 2024 Xiaoxia
+Copyright (c) 2025 Shenzhen Xinzhi Future Technology Co., Ltd.
+Copyright (c) 2025 Project Contributors
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,6 +1,173 @@
-# 你好，小智
+# An MCP-based Chatbot
 
-【ESP32+SenseVoice+Qwen72B打造你的AI聊天伴侣！】
+(English | [中文](README_zh.md) | [日本語](README_ja.md))
 
-https://www.bilibili.com/video/BV11msTenEH3/?share_source=copy_web&vd_source=ee1aafe19d6e60cf22e60a93881faeba
+## Introduction
 
+👉 [Human: Give AI a camera vs AI: Instantly finds out the owner hasn't washed hair for three days【bilibili】](https://www.bilibili.com/video/BV1bpjgzKEhd/)
+
+👉 [Handcraft your AI girlfriend, beginner's guide【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
+
+As a voice interaction entry, the XiaoZhi AI chatbot leverages the AI capabilities of large models like Qwen / DeepSeek, and achieves multi-terminal control via the MCP protocol.
+
+<img src="docs/mcp-based-graph.jpg" alt="Control everything via MCP" width="320">
+
+## Version Notes
+
+The current v2 version is incompatible with the v1 partition table, so it is not possible to upgrade from v1 to v2 via OTA. For partition table details, see [partitions/v2/README.md](partitions/v2/README.md).
+
+All hardware running v1 can be upgraded to v2 by manually flashing the firmware.
+
+The stable version of v1 is 1.9.2. You can switch to v1 by running `git checkout v1`. The v1 branch will be maintained until February 2026.
+
+### Features Implemented
+
+- Wi-Fi / ML307 Cat.1 4G
+- Offline voice wake-up [ESP-SR](https://github.com/espressif/esp-sr)
+- Supports two communication protocols ([Websocket](docs/websocket.md) or MQTT+UDP)
+- Uses OPUS audio codec
+- Voice interaction based on streaming ASR + LLM + TTS architecture
+- Speaker recognition, identifies the current speaker [3D Speaker](https://github.com/modelscope/3D-Speaker)
+- OLED / LCD display, supports emoji display
+- Battery display and power management
+- Multi-language support (Chinese, English, Japanese)
+- Supports ESP32-C3, ESP32-S3, ESP32-P4 chip platforms
+- Device-side MCP for device control (Speaker, LED, Servo, GPIO, etc.)
+- Cloud-side MCP to extend large model capabilities (smart home control, PC desktop operation, knowledge search, email, etc.)
+- Customizable wake words, fonts, emojis, and chat backgrounds with online web-based editing ([Custom Assets Generator](https://github.com/78/xiaozhi-assets-generator))
+
+## Hardware
+
+### Breadboard DIY Practice
+
+See the Feishu document tutorial:
+
+👉 ["XiaoZhi AI Chatbot Encyclopedia"](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)
+
+Breadboard demo:
+
+![Breadboard Demo](docs/v1/wiring2.jpg)
+
+### Supports 70+ Open Source Hardware (Partial List)
+
+- <a href="https://oshwhub.com/li-chuang-kai-fa-ban/li-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban" target="_blank" title="LiChuang ESP32-S3 Development Board">LiChuang ESP32-S3 Development Board</a>
+- <a href="https://github.com/espressif/esp-box" target="_blank" title="Espressif ESP32-S3-BOX3">Espressif ESP32-S3-BOX3</a>
+- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
+- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">M5Stack AtomS3R + Echo Base</a>
+- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="Magic Button 2.4">Magic Button 2.4</a>
+- <a href="https://www.waveshare.net/shop/ESP32-S3-Touch-AMOLED-1.8.htm" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">Waveshare ESP32-S3-Touch-AMOLED-1.8</a>
+- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
+- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="XiaGe Mini C3">XiaGe Mini C3</a>
+- <a href="https://oshwhub.com/movecall/cuican-ai-pendant-lights-up-y" target="_blank" title="Movecall CuiCan ESP32S3">CuiCan AI Pendant</a>
+- <a href="https://github.com/WMnologo/xingzhi-ai" target="_blank" title="WMnologo-Xingzhi-1.54">WMnologo-Xingzhi-1.54TFT</a>
+- <a href="https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html" target="_blank" title="SenseCAP Watcher">SenseCAP Watcher</a>
+- <a href="https://www.bilibili.com/video/BV1BHJtz6E2S/" target="_blank" title="ESP-HI Low Cost Robot Dog">ESP-HI Low Cost Robot Dog</a>
+
+<div style="display: flex; justify-content: space-between;">
+  <a href="docs/v1/lichuang-s3.jpg" target="_blank" title="LiChuang ESP32-S3 Development Board">
+    <img src="docs/v1/lichuang-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/espbox3.jpg" target="_blank" title="Espressif ESP32-S3-BOX3">
+    <img src="docs/v1/espbox3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/m5cores3.jpg" target="_blank" title="M5Stack CoreS3">
+    <img src="docs/v1/m5cores3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
+    <img src="docs/v1/atoms3r.jpg" width="240" />
+  </a>
+  <a href="docs/v1/magiclick.jpg" target="_blank" title="Magic Button 2.4">
+    <img src="docs/v1/magiclick.jpg" width="240" />
+  </a>
+  <a href="docs/v1/waveshare.jpg" target="_blank" title="Waveshare ESP32-S3-Touch-AMOLED-1.8">
+    <img src="docs/v1/waveshare.jpg" width="240" />
+  </a>
+  <a href="docs/v1/lilygo-t-circle-s3.jpg" target="_blank" title="LILYGO T-Circle-S3">
+    <img src="docs/v1/lilygo-t-circle-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/xmini-c3.jpg" target="_blank" title="XiaGe Mini C3">
+    <img src="docs/v1/xmini-c3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/movecall-cuican-esp32s3.jpg" target="_blank" title="CuiCan">
+    <img src="docs/v1/movecall-cuican-esp32s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/wmnologo_xingzhi_1.54.jpg" target="_blank" title="WMnologo-Xingzhi-1.54">
+    <img src="docs/v1/wmnologo_xingzhi_1.54.jpg" width="240" />
+  </a>
+  <a href="docs/v1/sensecap_watcher.jpg" target="_blank" title="SenseCAP Watcher">
+    <img src="docs/v1/sensecap_watcher.jpg" width="240" />
+  </a>
+  <a href="docs/v1/esp-hi.jpg" target="_blank" title="ESP-HI Low Cost Robot Dog">
+    <img src="docs/v1/esp-hi.jpg" width="240" />
+  </a>
+</div>
+
+## Software
+
+### Firmware Flashing
+
+For beginners, it is recommended to use the firmware that can be flashed without setting up a development environment.
+
+The firmware connects to the official [xiaozhi.me](https://xiaozhi.me) server by default. Personal users can register an account to use the Qwen real-time model for free.
+
+👉 [Beginner's Firmware Flashing Guide](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
+
+### Development Environment
+
+- Cursor or VSCode
+- Install ESP-IDF plugin, select SDK version 5.4 or above
+- Linux is better than Windows for faster compilation and fewer driver issues
+- This project uses Google C++ code style, please ensure compliance when submitting code
+
+### Developer Documentation
+
+- [Custom Board Guide](docs/custom-board.md) - Learn how to create custom boards for XiaoZhi AI
+- [MCP Protocol IoT Control Usage](docs/mcp-usage.md) - Learn how to control IoT devices via MCP protocol
+- [MCP Protocol Interaction Flow](docs/mcp-protocol.md) - Device-side MCP protocol implementation
+- [MQTT + UDP Hybrid Communication Protocol Document](docs/mqtt-udp.md)
+- [A detailed WebSocket communication protocol document](docs/websocket.md)
+
+## Large Model Configuration
+
+If you already have a XiaoZhi AI chatbot device and have connected to the official server, you can log in to the [xiaozhi.me](https://xiaozhi.me) console for configuration.
+
+👉 [Backend Operation Video Tutorial (Old Interface)](https://www.bilibili.com/video/BV1jUCUY2EKM/)
+
+## Related Open Source Projects
+
+For server deployment on personal computers, refer to the following open-source projects:
+
+- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python server
+- [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java server
+- [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang server
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golang server
+
+Other client projects using the XiaoZhi communication protocol:
+
+- [huangjunsen0406/py-xiaozhi](https://github.com/huangjunsen0406/py-xiaozhi) Python client
+- [TOM88812/xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) Android client
+- [100askTeam/xiaozhi-linux](http://github.com/100askTeam/xiaozhi-linux) Linux client by 100ask
+- [78/xiaozhi-sf32](https://github.com/78/xiaozhi-sf32) Bluetooth chip firmware by Sichuan
+- [QuecPython/solution-xiaozhiAI](https://github.com/QuecPython/solution-xiaozhiAI) QuecPython firmware by Quectel
+
+Custom Assets Tools:
+
+- [78/xiaozhi-assets-generator](https://github.com/78/xiaozhi-assets-generator) Custom Assets Generator (Wake words, fonts, emojis, backgrounds)
+
+## About the Project
+
+This is an open-source ESP32 project, released under the MIT license, allowing anyone to use it for free, including for commercial purposes.
+
+We hope this project helps everyone understand AI hardware development and apply rapidly evolving large language models to real hardware devices.
+
+If you have any ideas or suggestions, please feel free to raise Issues or join our [Discord](https://discord.gg/bXqgAfRm) or QQ group: 994694848
+
+## Star History
+
+<a href="https://star-history.com/#78/xiaozhi-esp32&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+ </picture>
+</a> 

README_ja.md

@@ -0,0 +1,169 @@
+# MCP ベースのチャットボット
+
+（日本語 | [中文](README_zh.md) | [English](README.md)）
+
+## はじめに
+
+👉 [人間：AIにカメラを装着 vs AI：その場で飼い主が3日間髪を洗っていないことを発見【bilibili】](https://www.bilibili.com/video/BV1bpjgzKEhd/)
+
+👉 [手作りでAIガールフレンドを作る、初心者入門チュートリアル【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
+
+シャオジーAIチャットボットは音声インタラクションの入口として、Qwen / DeepSeekなどの大規模モデルのAI能力を活用し、MCPプロトコルを通じてマルチエンド制御を実現します。
+
+<img src="docs/mcp-based-graph.jpg" alt="MCPであらゆるものを制御" width="320">
+
+## バージョンノート
+
+現在のv2バージョンはv1パーティションテーブルと互換性がないため、v1からv2へOTAでアップグレードすることはできません。パーティションテーブルの詳細については、[partitions/v2/README.md](partitions/v2/README.md)をご参照ください。
+
+v1を実行しているすべてのハードウェアは、ファームウェアを手動で書き込むことでv2にアップグレードできます。
+
+v1の安定版は1.9.2です。`git checkout v1`でv1に切り替えることができます。v1ブランチは2026年2月まで継続的にメンテナンスされます。
+
+### 実装済み機能
+
+- Wi-Fi / ML307 Cat.1 4G
+- オフライン音声ウェイクアップ [ESP-SR](https://github.com/espressif/esp-sr)
+- 2種類の通信プロトコルに対応（[Websocket](docs/websocket.md) または MQTT+UDP）
+- OPUSオーディオコーデックを採用
+- ストリーミングASR + LLM + TTSアーキテクチャに基づく音声インタラクション
+- 話者認識、現在話している人を識別 [3D Speaker](https://github.com/modelscope/3D-Speaker)
+- OLED / LCDディスプレイ、表情表示対応
+- バッテリー表示と電源管理
+- 多言語対応（中国語、英語、日本語）
+- ESP32-C3、ESP32-S3、ESP32-P4チッププラットフォーム対応
+- デバイス側MCPによるデバイス制御（音量・明るさ調整、アクション制御など）
+- クラウド側MCPで大規模モデル能力を拡張（スマートホーム制御、PCデスクトップ操作、知識検索、メール送受信など）
+- カスタマイズ可能なウェイクワード、フォント、絵文字、チャット背景、オンラインWeb編集に対応 ([カスタムアセットジェネレーター](https://github.com/78/xiaozhi-assets-generator))
+
+## ハードウェア
+
+### ブレッドボード手作り実践
+
+Feishuドキュメントチュートリアルをご覧ください：
+
+👉 [「シャオジーAIチャットボット百科事典」](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)
+
+ブレッドボードのデモ：
+
+![ブレッドボードデモ](docs/v1/wiring2.jpg)
+
+### 70種類以上のオープンソースハードウェアに対応（一部のみ表示）
+
+- <a href="https://oshwhub.com/li-chuang-kai-fa-ban/li-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban" target="_blank" title="立創・実戦派 ESP32-S3 開発ボード">立創・実戦派 ESP32-S3 開発ボード</a>
+- <a href="https://github.com/espressif/esp-box" target="_blank" title="楽鑫 ESP32-S3-BOX3">楽鑫 ESP32-S3-BOX3</a>
+- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
+- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">M5Stack AtomS3R + Echo Base</a>
+- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="マジックボタン2.4">マジックボタン2.4</a>
+- <a href="https://www.waveshare.net/shop/ESP32-S3-Touch-AMOLED-1.8.htm" target="_blank" title="微雪電子 ESP32-S3-Touch-AMOLED-1.8">微雪電子 ESP32-S3-Touch-AMOLED-1.8</a>
+- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
+- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="エビ兄さん Mini C3">エビ兄さん Mini C3</a>
+- <a href="https://oshwhub.com/movecall/cuican-ai-pendant-lights-up-y" target="_blank" title="Movecall CuiCan ESP32S3">CuiCan AIペンダント</a>
+- <a href="https://github.com/WMnologo/xingzhi-ai" target="_blank" title="無名科技Nologo-星智-1.54">無名科技Nologo-星智-1.54TFT</a>
+- <a href="https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html" target="_blank" title="SenseCAP Watcher">SenseCAP Watcher</a>
+- <a href="https://www.bilibili.com/video/BV1BHJtz6E2S/" target="_blank" title="ESP-HI 超低コストロボット犬">ESP-HI 超低コストロボット犬</a>
+
+<div style="display: flex; justify-content: space-between;">
+  <a href="docs/v1/lichuang-s3.jpg" target="_blank" title="立創・実戦派 ESP32-S3 開発ボード">
+    <img src="docs/v1/lichuang-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/espbox3.jpg" target="_blank" title="楽鑫 ESP32-S3-BOX3">
+    <img src="docs/v1/espbox3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/m5cores3.jpg" target="_blank" title="M5Stack CoreS3">
+    <img src="docs/v1/m5cores3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
+    <img src="docs/v1/atoms3r.jpg" width="240" />
+  </a>
+  <a href="docs/v1/magiclick.jpg" target="_blank" title="マジックボタン2.4">
+    <img src="docs/v1/magiclick.jpg" width="240" />
+  </a>
+  <a href="docs/v1/waveshare.jpg" target="_blank" title="微雪電子 ESP32-S3-Touch-AMOLED-1.8">
+    <img src="docs/v1/waveshare.jpg" width="240" />
+  </a>
+  <a href="docs/v1/lilygo-t-circle-s3.jpg" target="_blank" title="LILYGO T-Circle-S3">
+    <img src="docs/v1/lilygo-t-circle-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/xmini-c3.jpg" target="_blank" title="エビ兄さん Mini C3">
+    <img src="docs/v1/xmini-c3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/movecall-cuican-esp32s3.jpg" target="_blank" title="CuiCan">
+    <img src="docs/v1/movecall-cuican-esp32s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/wmnologo_xingzhi_1.54.jpg" target="_blank" title="無名科技Nologo-星智-1.54">
+    <img src="docs/v1/wmnologo_xingzhi_1.54.jpg" width="240" />
+  </a>
+  <a href="docs/v1/sensecap_watcher.jpg" target="_blank" title="SenseCAP Watcher">
+    <img src="docs/v1/sensecap_watcher.jpg" width="240" />
+  </a>
+  <a href="docs/v1/esp-hi.jpg" target="_blank" title="ESP-HI 超低コストロボット犬">
+    <img src="docs/v1/esp-hi.jpg" width="240" />
+  </a>
+</div>
+
+## ソフトウェア
+
+### ファームウェア書き込み
+
+初心者の方は、まず開発環境を構築せずに書き込み可能なファームウェアを使用することをおすすめします。
+
+ファームウェアはデフォルトで公式 [xiaozhi.me](https://xiaozhi.me) サーバーに接続します。個人ユーザーはアカウント登録でQwenリアルタイムモデルを無料で利用できます。
+
+👉 [初心者向けファームウェア書き込みガイド](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
+
+### 開発環境
+
+- Cursor または VSCode
+- ESP-IDFプラグインをインストールし、SDKバージョン5.4以上を選択
+- LinuxはWindowsよりも優れており、コンパイルが速く、ドライバの問題も少ない
+- 本プロジェクトはGoogle C++コードスタイルを採用、コード提出時は準拠を確認してください
+
+### 開発者ドキュメント
+
+- [カスタム開発ボードガイド](docs/custom-board.md) - シャオジーAI用のカスタム開発ボード作成方法
+- [MCPプロトコルIoT制御使用法](docs/mcp-usage.md) - MCPプロトコルでIoTデバイスを制御する方法
+- [MCPプロトコルインタラクションフロー](docs/mcp-protocol.md) - デバイス側MCPプロトコルの実装方法
+- [MQTT + UDP ハイブリッド通信プロトコルドキュメント](docs/mqtt-udp.md)
+- [詳細なWebSocket通信プロトコルドキュメント](docs/websocket.md)
+
+## 大規模モデル設定
+
+すでにシャオジーAIチャットボットデバイスをお持ちで、公式サーバーに接続済みの場合は、[xiaozhi.me](https://xiaozhi.me) コンソールで設定できます。
+
+👉 [バックエンド操作ビデオチュートリアル（旧インターフェース）](https://www.bilibili.com/video/BV1jUCUY2EKM/)
+
+## 関連オープンソースプロジェクト
+
+個人PCでサーバーをデプロイする場合は、以下のオープンソースプロジェクトを参照してください：
+
+- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Pythonサーバー
+- [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Javaサーバー
+- [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golangサーバー
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golangサーバー
+
+シャオジー通信プロトコルを利用した他のクライアントプロジェクト：
+
+- [huangjunsen0406/py-xiaozhi](https://github.com/huangjunsen0406/py-xiaozhi) Pythonクライアント
+- [TOM88812/xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) Androidクライアント
+- [100askTeam/xiaozhi-linux](http://github.com/100askTeam/xiaozhi-linux) 百問科技提供のLinuxクライアント
+- [78/xiaozhi-sf32](https://github.com/78/xiaozhi-sf32) 思澈科技のBluetoothチップファームウェア
+- [QuecPython/solution-xiaozhiAI](https://github.com/QuecPython/solution-xiaozhiAI) 移遠提供のQuecPythonファームウェア
+
+## プロジェクトについて
+
+これはエビ兄さんがオープンソースで公開しているESP32プロジェクトで、MITライセンスのもと、誰でも無料で、商用利用も可能です。
+
+このプロジェクトを通じて、AIハードウェア開発を理解し、急速に進化する大規模言語モデルを実際のハードウェアデバイスに応用できるようになることを目指しています。
+
+ご意見やご提案があれば、いつでもIssueを提出するか、[Discord](https://discord.gg/bXqgAfRm) または QQグループ：1011329060 にご参加ください。
+
+## スター履歴
+
+<a href="https://star-history.com/#78/xiaozhi-esp32&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+ </picture>
+</a> 

README_zh.md

@@ -0,0 +1,169 @@
+# An MCP-based Chatbot
+
+（中文 | [English](README.md) | [日本語](README_ja.md)）
+
+## 介绍
+
+👉 [人类：给 AI 装摄像头 vs AI：当场发现主人三天没洗头【bilibili】](https://www.bilibili.com/video/BV1bpjgzKEhd/)
+
+👉 [手工打造你的 AI 女友，新手入门教程【bilibili】](https://www.bilibili.com/video/BV1XnmFYLEJN/)
+
+小智 AI 聊天机器人作为一个语音交互入口，利用 Qwen / DeepSeek 等大模型的 AI 能力，通过 MCP 协议实现多端控制。
+
+<img src="docs/mcp-based-graph.jpg" alt="通过MCP控制万物" width="320">
+
+### 版本说明
+
+当前 v2 版本与 v1 版本分区表不兼容，所以无法从 v1 版本通过 OTA 升级到 v2 版本。分区表说明参见 [partitions/v2/README.md](partitions/v2/README.md)。
+
+使用 v1 版本的所有硬件，可以通过手动烧录固件来升级到 v2 版本。
+
+v1 的稳定版本为 1.9.2，可以通过 `git checkout v1` 来切换到 v1 版本，该分支会持续维护到 2026 年 2 月。
+
+### 已实现功能
+
+- Wi-Fi / ML307 Cat.1 4G
+- 离线语音唤醒 [ESP-SR](https://github.com/espressif/esp-sr)
+- 支持两种通信协议（[Websocket](docs/websocket.md) 或 MQTT+UDP）
+- 采用 OPUS 音频编解码
+- 基于流式 ASR + LLM + TTS 架构的语音交互
+- 声纹识别，识别当前说话人的身份 [3D Speaker](https://github.com/modelscope/3D-Speaker)
+- OLED / LCD 显示屏，支持表情显示
+- 电量显示与电源管理
+- 支持多语言（中文、英文、日文）
+- 支持 ESP32-C3、ESP32-S3、ESP32-P4 芯片平台
+- 通过设备端 MCP 实现设备控制（音量、灯光、电机、GPIO 等）
+- 通过云端 MCP 扩展大模型能力（智能家居控制、PC桌面操作、知识搜索、邮件收发等）
+- 自定义唤醒词、字体、表情与聊天背景，支持网页端在线修改 ([自定义Assets生成器](https://github.com/78/xiaozhi-assets-generator))
+
+## 硬件
+
+### 面包板手工制作实践
+
+详见飞书文档教程：
+
+👉 [《小智 AI 聊天机器人百科全书》](https://ccnphfhqs21z.feishu.cn/wiki/F5krwD16viZoF0kKkvDcrZNYnhb?from=from_copylink)
+
+面包板效果图如下：
+
+![面包板效果图](docs/v1/wiring2.jpg)
+
+### 支持 70 多个开源硬件（仅展示部分）
+
+- <a href="https://oshwhub.com/li-chuang-kai-fa-ban/li-chuang-shi-zhan-pai-esp32-s3-kai-fa-ban" target="_blank" title="立创·实战派 ESP32-S3 开发板">立创·实战派 ESP32-S3 开发板</a>
+- <a href="https://github.com/espressif/esp-box" target="_blank" title="乐鑫 ESP32-S3-BOX3">乐鑫 ESP32-S3-BOX3</a>
+- <a href="https://docs.m5stack.com/zh_CN/core/CoreS3" target="_blank" title="M5Stack CoreS3">M5Stack CoreS3</a>
+- <a href="https://docs.m5stack.com/en/atom/Atomic%20Echo%20Base" target="_blank" title="AtomS3R + Echo Base">M5Stack AtomS3R + Echo Base</a>
+- <a href="https://gf.bilibili.com/item/detail/1108782064" target="_blank" title="神奇按钮 2.4">神奇按钮 2.4</a>
+- <a href="https://www.waveshare.net/shop/ESP32-S3-Touch-AMOLED-1.8.htm" target="_blank" title="微雪电子 ESP32-S3-Touch-AMOLED-1.8">微雪电子 ESP32-S3-Touch-AMOLED-1.8</a>
+- <a href="https://github.com/Xinyuan-LilyGO/T-Circle-S3" target="_blank" title="LILYGO T-Circle-S3">LILYGO T-Circle-S3</a>
+- <a href="https://oshwhub.com/tenclass01/xmini_c3" target="_blank" title="虾哥 Mini C3">虾哥 Mini C3</a>
+- <a href="https://oshwhub.com/movecall/cuican-ai-pendant-lights-up-y" target="_blank" title="Movecall CuiCan ESP32S3">璀璨·AI 吊坠</a>
+- <a href="https://github.com/WMnologo/xingzhi-ai" target="_blank" title="无名科技Nologo-星智-1.54">无名科技 Nologo-星智-1.54TFT</a>
+- <a href="https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html" target="_blank" title="SenseCAP Watcher">SenseCAP Watcher</a>
+- <a href="https://www.bilibili.com/video/BV1BHJtz6E2S/" target="_blank" title="ESP-HI 超低成本机器狗">ESP-HI 超低成本机器狗</a>
+
+<div style="display: flex; justify-content: space-between;">
+  <a href="docs/v1/lichuang-s3.jpg" target="_blank" title="立创·实战派 ESP32-S3 开发板">
+    <img src="docs/v1/lichuang-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/espbox3.jpg" target="_blank" title="乐鑫 ESP32-S3-BOX3">
+    <img src="docs/v1/espbox3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/m5cores3.jpg" target="_blank" title="M5Stack CoreS3">
+    <img src="docs/v1/m5cores3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/atoms3r.jpg" target="_blank" title="AtomS3R + Echo Base">
+    <img src="docs/v1/atoms3r.jpg" width="240" />
+  </a>
+  <a href="docs/v1/magiclick.jpg" target="_blank" title="神奇按钮 2.4">
+    <img src="docs/v1/magiclick.jpg" width="240" />
+  </a>
+  <a href="docs/v1/waveshare.jpg" target="_blank" title="微雪电子 ESP32-S3-Touch-AMOLED-1.8">
+    <img src="docs/v1/waveshare.jpg" width="240" />
+  </a>
+  <a href="docs/v1/lilygo-t-circle-s3.jpg" target="_blank" title="LILYGO T-Circle-S3">
+    <img src="docs/v1/lilygo-t-circle-s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/xmini-c3.jpg" target="_blank" title="虾哥 Mini C3">
+    <img src="docs/v1/xmini-c3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/movecall-cuican-esp32s3.jpg" target="_blank" title="CuiCan">
+    <img src="docs/v1/movecall-cuican-esp32s3.jpg" width="240" />
+  </a>
+  <a href="docs/v1/wmnologo_xingzhi_1.54.jpg" target="_blank" title="无名科技Nologo-星智-1.54">
+    <img src="docs/v1/wmnologo_xingzhi_1.54.jpg" width="240" />
+  </a>
+  <a href="docs/v1/sensecap_watcher.jpg" target="_blank" title="SenseCAP Watcher">
+    <img src="docs/v1/sensecap_watcher.jpg" width="240" />
+  </a>
+  <a href="docs/v1/esp-hi.jpg" target="_blank" title="ESP-HI 超低成本机器狗">
+    <img src="docs/v1/esp-hi.jpg" width="240" />
+  </a>
+</div>
+
+## 软件
+
+### 固件烧录
+
+新手第一次操作建议先不要搭建开发环境，直接使用免开发环境烧录的固件。
+
+固件默认接入 [xiaozhi.me](https://xiaozhi.me) 官方服务器，个人用户注册账号可以免费使用 Qwen 实时模型。
+
+👉 [新手烧录固件教程](https://ccnphfhqs21z.feishu.cn/wiki/Zpz4wXBtdimBrLk25WdcXzxcnNS)
+
+### 开发环境
+
+- Cursor 或 VSCode
+- 安装 ESP-IDF 插件，选择 SDK 版本 5.4 或以上
+- Linux 比 Windows 更好，编译速度快，也免去驱动问题的困扰
+- 本项目使用 Google C++ 代码风格，提交代码时请确保符合规范
+
+### 开发者文档
+
+- [自定义开发板指南](docs/custom-board.md) - 学习如何为小智 AI 创建自定义开发板
+- [MCP 协议物联网控制用法说明](docs/mcp-usage.md) - 了解如何通过 MCP 协议控制物联网设备
+- [MCP 协议交互流程](docs/mcp-protocol.md) - 设备端 MCP 协议的实现方式
+- [MQTT + UDP 混合通信协议文档](docs/mqtt-udp.md)
+- [一份详细的 WebSocket 通信协议文档](docs/websocket.md)
+
+## 大模型配置
+
+如果你已经拥有一个小智 AI 聊天机器人设备，并且已接入官方服务器，可以登录 [xiaozhi.me](https://xiaozhi.me) 控制台进行配置。
+
+👉 [后台操作视频教程（旧版界面）](https://www.bilibili.com/video/BV1jUCUY2EKM/)
+
+## 相关开源项目
+
+在个人电脑上部署服务器，可以参考以下第三方开源的项目：
+
+- [xinnan-tech/xiaozhi-esp32-server](https://github.com/xinnan-tech/xiaozhi-esp32-server) Python 服务器
+- [joey-zhou/xiaozhi-esp32-server-java](https://github.com/joey-zhou/xiaozhi-esp32-server-java) Java 服务器
+- [AnimeAIChat/xiaozhi-server-go](https://github.com/AnimeAIChat/xiaozhi-server-go) Golang 服务器
+- [hackers365/xiaozhi-esp32-server-golang](https://github.com/hackers365/xiaozhi-esp32-server-golang) Golang 服务器
+
+使用小智通信协议的第三方客户端项目：
+
+- [huangjunsen0406/py-xiaozhi](https://github.com/huangjunsen0406/py-xiaozhi) Python 客户端
+- [TOM88812/xiaozhi-android-client](https://github.com/TOM88812/xiaozhi-android-client) Android 客户端
+- [100askTeam/xiaozhi-linux](http://github.com/100askTeam/xiaozhi-linux) 百问科技提供的 Linux 客户端
+- [78/xiaozhi-sf32](https://github.com/78/xiaozhi-sf32) 思澈科技的蓝牙芯片固件
+- [QuecPython/solution-xiaozhiAI](https://github.com/QuecPython/solution-xiaozhiAI) 移远提供的 QuecPython 固件
+
+## 关于项目
+
+这是一个由虾哥开源的 ESP32 项目，以 MIT 许可证发布，允许任何人免费使用，修改或用于商业用途。
+
+我们希望通过这个项目，能够帮助大家了解 AI 硬件开发，将当下飞速发展的大语言模型应用到实际的硬件设备中。
+
+如果你有任何想法或建议，请随时提出 Issues 或加入 [Discord](https://discord.gg/bXqgAfRm) 或 QQ 群：1011329060
+
+## Star History
+
+<a href="https://star-history.com/#78/xiaozhi-esp32&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=78/xiaozhi-esp32&type=Date" />
+ </picture>
+</a>

_codeql_detected_source_root

@@ -0,0 +1 @@
+.

docs/blufi.md

@@ -0,0 +1,37 @@
+# BluFi 配网（集成 esp-wifi-connect）
+
+本文档说明如何在小智固件中启用和使用 BluFi（BLE Wi‑Fi 配网），并结合项目内置的 `esp-wifi-connect` 组件完成 Wi‑Fi 连接与存储。官方
+BluFi
+协议说明请参考 [Espressif 文档](https://docs.espressif.com/projects/esp-idf/zh_CN/stable/esp32/api-guides/ble/blufi.html)。
+
+## 前置条件
+
+- 需要支持 BLE 的芯片与固件配置。
+- 在 `idf.py menuconfig` 中启用 `WiFi Configuration Method -> Esp Blufi`（`CONFIG_USE_ESP_BLUFI_WIFI_PROVISIONING=y`
+  ）。如果想使用 BluFi，必须关闭同一菜单下的 Hotspot 选项，否则默认使用 Hotspot 配网模式。
+
+- 保持默认的 NVS 与事件循环初始化（项目的 `app_main` 已处理）。
+- CONFIG_BT_BLUEDROID_ENABLED、CONFIG_BT_NIMBLE_ENABLED这两个宏应二选一，不能同时启用。
+## 工作流程
+
+1) 手机端通过 BluFi（如官方 EspBlufi App 或自研客户端）连接设备，发送 Wi‑Fi SSID/密码，手机端可以通过blufi协议获取设备端扫描到的WiFi列表。
+2) 设备侧在 `ESP_BLUFI_EVENT_REQ_CONNECT_TO_AP` 中将凭据写入 `SsidManager`（存储到 NVS，属于 `esp-wifi-connect` 组件）。
+3) 随后启动 `WifiStation` 扫描并连接；状态通过 BluFi 返回。
+4) 配网成功后设备会自动连接新 Wi‑Fi；失败则返回失败状态。
+
+## 使用步骤
+
+1. 配置：在 menuconfig 开启 `Esp Blufi`。编译并烧录固件。
+2. 触发配网：设备首次启动且没有已保存的 Wi‑Fi 时会自动进入配网。
+3. 手机端操作：打开 EspBlufi App（或其他 BluFi 客户端），搜索并连接设备，可以选择是否加密，按提示输入 Wi‑Fi SSID/密码并发送。
+4. 观察结果：
+    - 成功：BluFi 报告连接成功，设备自动连接 Wi‑Fi。
+    - 失败：BluFi 返回失败状态，可重新发送或检查路由器。
+
+## 注意事项
+
+- BluFi 配网不支持与热点配网同时开启。如果热点配网已经启动，则默认使用热点配网。请在 menuconfig 中只保留一种配网方式。
+- 若多次测试，建议清除或覆盖存储的 SSID（`wifi` 命名空间），避免旧配置干扰。
+- 如果使用自定义 BluFi 客户端，需遵循官方协议帧格式，参考上文官方文档链接。
+- 官方文档中已提供EspBlufi APP下载地址
+- 由于IDF5.5.2的blufi接口发生变化,5.5.2版本编译后蓝牙名称为"Xiaozhi-Blufi",5.5.1版本中蓝牙名称为"BLUFI_DEVICE"

docs/code_style.md

@@ -0,0 +1,91 @@
+# 代码风格指南
+
+## 代码格式化工具
+
+本项目使用 clang-format 工具来统一代码风格。我们已经在项目根目录下提供了 `.clang-format` 配置文件，该配置基于 Google C++ 风格指南，并做了一些自定义调整。
+
+### 安装 clang-format
+
+在使用之前，请确保你已经安装了 clang-format 工具：
+
+- **Windows**：
+  ```powershell
+  winget install LLVM
+  # 或者使用 Chocolatey
+  choco install llvm
+  ```
+
+- **Linux**：
+  ```bash
+  sudo apt install clang-format  # Ubuntu/Debian
+  sudo dnf install clang-tools-extra  # Fedora
+  ```
+
+- **macOS**：
+  ```bash
+  brew install clang-format
+  ```
+
+### 使用方法
+
+1. **格式化单个文件**：
+   ```bash
+   clang-format -i path/to/your/file.cpp
+   ```
+
+2. **格式化整个项目**：
+   ```bash
+   # 在项目根目录下执行
+   find main -iname *.h -o -iname *.cc | xargs clang-format -i
+   ```
+
+3. **在提交代码前检查格式**：
+   ```bash
+   # 检查文件格式是否符合规范（不修改文件）
+   clang-format --dry-run -Werror path/to/your/file.cpp
+   ```
+
+### IDE 集成
+
+- **Visual Studio Code**：
+  1. 安装 C/C++ 扩展
+  2. 在设置中启用 `C_Cpp.formatting` 为 `clang-format`
+  3. 可以设置保存时自动格式化：`editor.formatOnSave: true`
+
+- **CLion**：
+  1. 在设置中选择 `Editor > Code Style > C/C++`
+  2. 将 `Formatter` 设置为 `clang-format`
+  3. 选择使用项目中的 `.clang-format` 配置文件
+
+### 主要格式规则
+
+- 缩进使用 4 个空格
+- 行宽限制为 100 字符
+- 大括号采用 Attach 风格（与控制语句在同一行）
+- 指针和引用符号靠左对齐
+- 自动排序头文件包含
+- 类访问修饰符缩进为 -4 空格
+
+### 注意事项
+
+1. 提交代码前请确保代码已经过格式化
+2. 不要手动调整已格式化的代码对齐
+3. 如果某段代码不希望被格式化，可以使用以下注释包围：
+   ```cpp
+   // clang-format off
+   // 你的代码
+   // clang-format on
+   ```
+
+### 常见问题
+
+1. **格式化失败**：
+   - 检查 clang-format 版本是否过低
+   - 确认文件编码为 UTF-8
+   - 验证 .clang-format 文件语法是否正确
+
+2. **与期望格式不符**：
+   - 检查是否使用了项目根目录下的 .clang-format 配置
+   - 确认没有其他位置的 .clang-format 文件被优先使用
+
+如有任何问题或建议，欢迎提出 issue 或 pull request。

docs/custom-board.md

@@ -0,0 +1,453 @@
+# 自定义开发板指南
+
+本指南介绍如何为小智AI语音聊天机器人项目定制一个新的开发板初始化程序。小智AI支持70多种ESP32系列开发板，每个开发板的初始化代码都放在对应的目录下。
+
+## 重要提示
+
+> **警告**: 对于自定义开发板，当IO配置与原有开发板不同时，切勿直接覆盖原有开发板的配置编译固件。必须创建新的开发板类型，或者通过config.json文件中的builds配置不同的name和sdkconfig宏定义来区分。使用 `python scripts/release.py [开发板目录名字]` 来编译打包固件。
+>
+> 如果直接覆盖原有配置，将来OTA升级时，您的自定义固件可能会被原有开发板的标准固件覆盖，导致您的设备无法正常工作。每个开发板有唯一的标识和对应的固件升级通道，保持开发板标识的唯一性非常重要。
+
+## 目录结构
+
+每个开发板的目录结构通常包含以下文件：
+
+- `xxx_board.cc` - 主要的板级初始化代码，实现了板子相关的初始化和功能
+- `config.h` - 板级配置文件，定义了硬件管脚映射和其他配置项
+- `config.json` - 编译配置，指定目标芯片和特殊的编译选项
+- `README.md` - 开发板相关的说明文档
+
+## 定制开发板步骤
+
+### 1. 创建新的开发板目录
+
+首先在`boards/`目录下创建一个新的目录，命名方式应使用 `[品牌名]-[开发板类型]` 的形式，例如 `m5stack-tab5`：
+
+```bash
+mkdir main/boards/my-custom-board
+```
+
+### 2. 创建配置文件
+
+#### config.h
+
+在`config.h`中定义所有的硬件配置，包括:
+
+- 音频采样率和I2S引脚配置
+- 音频编解码芯片地址和I2C引脚配置
+- 按钮和LED引脚配置
+- 显示屏参数和引脚配置
+
+参考示例（来自lichuang-c3-dev）：
+
+```c
+#ifndef _BOARD_CONFIG_H_
+#define _BOARD_CONFIG_H_
+
+#include <driver/gpio.h>
+
+// 音频配置
+#define AUDIO_INPUT_SAMPLE_RATE  24000
+#define AUDIO_OUTPUT_SAMPLE_RATE 24000
+
+#define AUDIO_I2S_GPIO_MCLK GPIO_NUM_10
+#define AUDIO_I2S_GPIO_WS   GPIO_NUM_12
+#define AUDIO_I2S_GPIO_BCLK GPIO_NUM_8
+#define AUDIO_I2S_GPIO_DIN  GPIO_NUM_7
+#define AUDIO_I2S_GPIO_DOUT GPIO_NUM_11
+
+#define AUDIO_CODEC_PA_PIN       GPIO_NUM_13
+#define AUDIO_CODEC_I2C_SDA_PIN  GPIO_NUM_0
+#define AUDIO_CODEC_I2C_SCL_PIN  GPIO_NUM_1
+#define AUDIO_CODEC_ES8311_ADDR  ES8311_CODEC_DEFAULT_ADDR
+
+// 按钮配置
+#define BOOT_BUTTON_GPIO        GPIO_NUM_9
+
+// 显示屏配置
+#define DISPLAY_SPI_SCK_PIN     GPIO_NUM_3
+#define DISPLAY_SPI_MOSI_PIN    GPIO_NUM_5
+#define DISPLAY_DC_PIN          GPIO_NUM_6
+#define DISPLAY_SPI_CS_PIN      GPIO_NUM_4
+
+#define DISPLAY_WIDTH   320
+#define DISPLAY_HEIGHT  240
+#define DISPLAY_MIRROR_X true
+#define DISPLAY_MIRROR_Y false
+#define DISPLAY_SWAP_XY true
+
+#define DISPLAY_OFFSET_X  0
+#define DISPLAY_OFFSET_Y  0
+
+#define DISPLAY_BACKLIGHT_PIN GPIO_NUM_2
+#define DISPLAY_BACKLIGHT_OUTPUT_INVERT true
+
+#endif // _BOARD_CONFIG_H_
+```
+
+#### config.json
+
+在`config.json`中定义编译配置，这个文件用于 `scripts/release.py` 脚本自动化编译：
+
+```json
+{
+    "target": "esp32s3",  // 目标芯片型号: esp32, esp32s3, esp32c3, esp32c6, esp32p4等
+    "builds": [
+        {
+            "name": "my-custom-board",  // 开发板名称，用于生成固件包
+            "sdkconfig_append": [
+                // 特别 Flash 大小配置
+                "CONFIG_ESPTOOLPY_FLASHSIZE_8MB=y",
+                // 特别分区表配置
+                "CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\""
+            ]
+        }
+    ]
+}
+```
+
+**配置项说明：**
+- `target`: 目标芯片型号，必须与硬件匹配
+- `name`: 编译输出的固件包名称，建议与目录名一致
+- `sdkconfig_append`: 额外的 sdkconfig 配置项数组，会追加到默认配置中
+
+**常用的 sdkconfig_append 配置：**
+```json
+// Flash 大小
+"CONFIG_ESPTOOLPY_FLASHSIZE_4MB=y"   // 4MB Flash
+"CONFIG_ESPTOOLPY_FLASHSIZE_8MB=y"   // 8MB Flash
+"CONFIG_ESPTOOLPY_FLASHSIZE_16MB=y"  // 16MB Flash
+
+// 分区表
+"CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/4m.csv\""  // 4MB 分区表
+"CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/8m.csv\""  // 8MB 分区表
+"CONFIG_PARTITION_TABLE_CUSTOM_FILENAME=\"partitions/v2/16m.csv\"" // 16MB 分区表
+
+// 语言配置
+"CONFIG_LANGUAGE_EN_US=y"  // 英语
+"CONFIG_LANGUAGE_ZH_CN=y"  // 简体中文
+
+// 唤醒词配置
+"CONFIG_USE_DEVICE_AEC=y"          // 启用设备端 AEC
+"CONFIG_WAKE_WORD_DISABLED=y"      // 禁用唤醒词
+```
+
+### 3. 编写板级初始化代码
+
+创建一个`my_custom_board.cc`文件，实现开发板的所有初始化逻辑。
+
+一个基本的开发板类定义包含以下几个部分：
+
+1. **类定义**：继承自`WifiBoard`或`Ml307Board`
+2. **初始化函数**：包括I2C、显示屏、按钮、IoT等组件的初始化
+3. **虚函数重写**：如`GetAudioCodec()`、`GetDisplay()`、`GetBacklight()`等
+4. **注册开发板**：使用`DECLARE_BOARD`宏注册开发板
+
+```cpp
+#include "wifi_board.h"
+#include "codecs/es8311_audio_codec.h"
+#include "display/lcd_display.h"
+#include "application.h"
+#include "button.h"
+#include "config.h"
+#include "mcp_server.h"
+
+#include <esp_log.h>
+#include <driver/i2c_master.h>
+#include <driver/spi_common.h>
+
+#define TAG "MyCustomBoard"
+
+class MyCustomBoard : public WifiBoard {
+private:
+    i2c_master_bus_handle_t codec_i2c_bus_;
+    Button boot_button_;
+    LcdDisplay* display_;
+
+    // I2C初始化
+    void InitializeI2c() {
+        i2c_master_bus_config_t i2c_bus_cfg = {
+            .i2c_port = I2C_NUM_0,
+            .sda_io_num = AUDIO_CODEC_I2C_SDA_PIN,
+            .scl_io_num = AUDIO_CODEC_I2C_SCL_PIN,
+            .clk_source = I2C_CLK_SRC_DEFAULT,
+            .glitch_ignore_cnt = 7,
+            .intr_priority = 0,
+            .trans_queue_depth = 0,
+            .flags = {
+                .enable_internal_pullup = 1,
+            },
+        };
+        ESP_ERROR_CHECK(i2c_new_master_bus(&i2c_bus_cfg, &codec_i2c_bus_));
+    }
+
+    // SPI初始化（用于显示屏）
+    void InitializeSpi() {
+        spi_bus_config_t buscfg = {};
+        buscfg.mosi_io_num = DISPLAY_SPI_MOSI_PIN;
+        buscfg.miso_io_num = GPIO_NUM_NC;
+        buscfg.sclk_io_num = DISPLAY_SPI_SCK_PIN;
+        buscfg.quadwp_io_num = GPIO_NUM_NC;
+        buscfg.quadhd_io_num = GPIO_NUM_NC;
+        buscfg.max_transfer_sz = DISPLAY_WIDTH * DISPLAY_HEIGHT * sizeof(uint16_t);
+        ESP_ERROR_CHECK(spi_bus_initialize(SPI2_HOST, &buscfg, SPI_DMA_CH_AUTO));
+    }
+
+    // 按钮初始化
+    void InitializeButtons() {
+        boot_button_.OnClick([this]() {
+            auto& app = Application::GetInstance();
+            if (app.GetDeviceState() == kDeviceStateStarting) {
+                EnterWifiConfigMode();
+                return;
+            }
+            app.ToggleChatState();
+        });
+    }
+
+    // 显示屏初始化（以ST7789为例）
+    void InitializeDisplay() {
+        esp_lcd_panel_io_handle_t panel_io = nullptr;
+        esp_lcd_panel_handle_t panel = nullptr;
+        
+        esp_lcd_panel_io_spi_config_t io_config = {};
+        io_config.cs_gpio_num = DISPLAY_SPI_CS_PIN;
+        io_config.dc_gpio_num = DISPLAY_DC_PIN;
+        io_config.spi_mode = 2;
+        io_config.pclk_hz = 80 * 1000 * 1000;
+        io_config.trans_queue_depth = 10;
+        io_config.lcd_cmd_bits = 8;
+        io_config.lcd_param_bits = 8;
+        ESP_ERROR_CHECK(esp_lcd_new_panel_io_spi(SPI2_HOST, &io_config, &panel_io));
+
+        esp_lcd_panel_dev_config_t panel_config = {};
+        panel_config.reset_gpio_num = GPIO_NUM_NC;
+        panel_config.rgb_ele_order = LCD_RGB_ELEMENT_ORDER_RGB;
+        panel_config.bits_per_pixel = 16;
+        ESP_ERROR_CHECK(esp_lcd_new_panel_st7789(panel_io, &panel_config, &panel));
+        
+        esp_lcd_panel_reset(panel);
+        esp_lcd_panel_init(panel);
+        esp_lcd_panel_invert_color(panel, true);
+        esp_lcd_panel_swap_xy(panel, DISPLAY_SWAP_XY);
+        esp_lcd_panel_mirror(panel, DISPLAY_MIRROR_X, DISPLAY_MIRROR_Y);
+        
+        // 创建显示屏对象
+        display_ = new SpiLcdDisplay(panel_io, panel,
+                                    DISPLAY_WIDTH, DISPLAY_HEIGHT, 
+                                    DISPLAY_OFFSET_X, DISPLAY_OFFSET_Y, 
+                                    DISPLAY_MIRROR_X, DISPLAY_MIRROR_Y, DISPLAY_SWAP_XY);
+    }
+
+    // MCP Tools 初始化
+    void InitializeTools() {
+        // 参考 MCP 文档
+    }
+
+public:
+    // 构造函数
+    MyCustomBoard() : boot_button_(BOOT_BUTTON_GPIO) {
+        InitializeI2c();
+        InitializeSpi();
+        InitializeDisplay();
+        InitializeButtons();
+        InitializeTools();
+        GetBacklight()->SetBrightness(100);
+    }
+
+    // 获取音频编解码器
+    virtual AudioCodec* GetAudioCodec() override {
+        static Es8311AudioCodec audio_codec(
+            codec_i2c_bus_, 
+            I2C_NUM_0, 
+            AUDIO_INPUT_SAMPLE_RATE, 
+            AUDIO_OUTPUT_SAMPLE_RATE,
+            AUDIO_I2S_GPIO_MCLK, 
+            AUDIO_I2S_GPIO_BCLK, 
+            AUDIO_I2S_GPIO_WS, 
+            AUDIO_I2S_GPIO_DOUT, 
+            AUDIO_I2S_GPIO_DIN,
+            AUDIO_CODEC_PA_PIN, 
+            AUDIO_CODEC_ES8311_ADDR);
+        return &audio_codec;
+    }
+
+    // 获取显示屏
+    virtual Display* GetDisplay() override {
+        return display_;
+    }
+    
+    // 获取背光控制
+    virtual Backlight* GetBacklight() override {
+        static PwmBacklight backlight(DISPLAY_BACKLIGHT_PIN, DISPLAY_BACKLIGHT_OUTPUT_INVERT);
+        return &backlight;
+    }
+};
+
+// 注册开发板
+DECLARE_BOARD(MyCustomBoard);
+```
+
+### 4. 添加构建系统配置
+
+#### 在 Kconfig.projbuild 中添加开发板选项
+
+打开 `main/Kconfig.projbuild` 文件，在 `choice BOARD_TYPE` 部分添加新的开发板配置项：
+
+```kconfig
+choice BOARD_TYPE
+    prompt "Board Type"
+    default BOARD_TYPE_BREAD_COMPACT_WIFI
+    help
+        Board type. 开发板类型
+    
+    # ... 其他开发板选项 ...
+    
+    config BOARD_TYPE_MY_CUSTOM_BOARD
+        bool "My Custom Board (我的自定义开发板)"
+        depends on IDF_TARGET_ESP32S3  # 根据你的目标芯片修改
+endchoice
+```
+
+**注意事项：**
+- `BOARD_TYPE_MY_CUSTOM_BOARD` 是配置项名称，需要全大写，使用下划线分隔
+- `depends on` 指定了目标芯片类型（如 `IDF_TARGET_ESP32S3`、`IDF_TARGET_ESP32C3` 等）
+- 描述文字可以使用中英文
+
+#### 在 CMakeLists.txt 中添加开发板配置
+
+打开 `main/CMakeLists.txt` 文件，在开发板类型判断部分添加新的配置：
+
+```cmake
+# 在 elseif 链中添加你的开发板配置
+elseif(CONFIG_BOARD_TYPE_MY_CUSTOM_BOARD)
+    set(BOARD_TYPE "my-custom-board")  # 与目录名一致
+    set(BUILTIN_TEXT_FONT font_puhui_basic_20_4)  # 根据屏幕大小选择合适的字体
+    set(BUILTIN_ICON_FONT font_awesome_20_4)
+    set(DEFAULT_EMOJI_COLLECTION twemoji_64)  # 可选，如果需要表情显示
+endif()
+```
+
+**字体和表情配置说明：**
+
+根据屏幕分辨率选择合适的字体大小：
+- 小屏幕（128x64 OLED）：`font_puhui_basic_14_1` / `font_awesome_14_1`
+- 中小屏幕（240x240）：`font_puhui_basic_16_4` / `font_awesome_16_4`
+- 中等屏幕（240x320）：`font_puhui_basic_20_4` / `font_awesome_20_4`
+- 大屏幕（480x320+）：`font_puhui_basic_30_4` / `font_awesome_30_4`
+
+表情集合选项：
+- `twemoji_32` - 32x32 像素表情（小屏幕）
+- `twemoji_64` - 64x64 像素表情（大屏幕）
+
+### 5. 配置和编译
+
+#### 方法一：使用 idf.py 手动配置
+
+1. **设置目标芯片**（首次配置或更换芯片时）：
+   ```bash
+   # 对于 ESP32-S3
+   idf.py set-target esp32s3
+   
+   # 对于 ESP32-C3
+   idf.py set-target esp32c3
+   
+   # 对于 ESP32
+   idf.py set-target esp32
+   ```
+
+2. **清理旧配置**：
+   ```bash
+   idf.py fullclean
+   ```
+
+3. **进入配置菜单**：
+   ```bash
+   idf.py menuconfig
+   ```
+   
+   在菜单中导航到：`Xiaozhi Assistant` -> `Board Type`，选择你的自定义开发板。
+
+4. **编译和烧录**：
+   ```bash
+   idf.py build
+   idf.py flash monitor
+   ```
+
+#### 方法二：使用 release.py 脚本（推荐）
+
+如果你的开发板目录下有 `config.json` 文件，可以使用此脚本自动完成配置和编译：
+
+```bash
+python scripts/release.py my-custom-board
+```
+
+此脚本会自动：
+- 读取 `config.json` 中的 `target` 配置并设置目标芯片
+- 应用 `sdkconfig_append` 中的编译选项
+- 完成编译并打包固件
+
+### 6. 创建README.md
+
+在README.md中说明开发板的特性、硬件要求、编译和烧录步骤：
+
+
+## 常见开发板组件
+
+### 1. 显示屏
+
+项目支持多种显示屏驱动，包括:
+- ST7789 (SPI)
+- ILI9341 (SPI)
+- SH8601 (QSPI)
+- 等...
+
+### 2. 音频编解码器
+
+支持的编解码器包括:
+- ES8311 (常用)
+- ES7210 (麦克风阵列)
+- AW88298 (功放)
+- 等...
+
+### 3. 电源管理
+
+一些开发板使用电源管理芯片:
+- AXP2101
+- 其他可用的PMIC
+
+### 4. MCP设备控制
+
+可以添加各种MCP工具，让AI能够使用:
+- Speaker (扬声器控制)
+- Screen (屏幕亮度调节)
+- Battery (电池电量读取)
+- Light (灯光控制)
+- 等...
+
+## 开发板类继承关系
+
+- `Board` - 基础板级类
+  - `WifiBoard` - Wi-Fi连接的开发板
+  - `Ml307Board` - 使用4G模块的开发板
+  - `DualNetworkBoard` - 支持Wi-Fi与4G网络切换的开发板
+
+## 开发技巧
+
+1. **参考相似的开发板**：如果您的新开发板与现有开发板有相似之处，可以参考现有实现
+2. **分步调试**：先实现基础功能（如显示），再添加更复杂的功能（如音频）
+3. **管脚映射**：确保在config.h中正确配置所有管脚映射
+4. **检查硬件兼容性**：确认所有芯片和驱动程序的兼容性
+
+## 可能遇到的问题
+
+1. **显示屏不正常**：检查SPI配置、镜像设置和颜色反转设置
+2. **音频无输出**：检查I2S配置、PA使能引脚和编解码器地址
+3. **无法连接网络**：检查Wi-Fi凭据和网络配置
+4. **无法与服务器通信**：检查MQTT或WebSocket配置
+
+## 参考资料
+
+- ESP-IDF 文档: https://docs.espressif.com/projects/esp-idf/
+- LVGL 文档: https://docs.lvgl.io/
+- ESP-SR 文档: https://github.com/espressif/esp-sr 

docs/mcp-protocol.md

@@ -0,0 +1,269 @@
+# MCP (Model Context Protocol) 交互流程
+
+NOTICE: AI 辅助生成, 在实现后台服务时, 请参照代码确认细节!!
+
+本项目中的 MCP 协议用于后台 API（MCP 客户端）与 ESP32 设备（MCP 服务器）之间的通信，以便后台能够发现和调用设备提供的功能（工具）。
+
+## 协议格式
+
+根据代码 (`main/protocols/protocol.cc`, `main/mcp_server.cc`)，MCP 消息是封装在基础通信协议（如 WebSocket 或 MQTT）的消息体中的。其内部结构遵循 [JSON-RPC 2.0](https://www.jsonrpc.org/specification) 规范。
+
+整体消息结构示例：
+
+```json
+{
+  "session_id": "...", // 会话 ID
+  "type": "mcp",       // 消息类型，固定为 "mcp"
+  "payload": {         // JSON-RPC 2.0 负载
+    "jsonrpc": "2.0",
+    "method": "...",   // 方法名 (如 "initialize", "tools/list", "tools/call")
+    "params": { ... }, // 方法参数 (对于 request)
+    "id": ...,         // 请求 ID (对于 request 和 response)
+    "result": { ... }, // 方法执行结果 (对于 success response)
+    "error": { ... }   // 错误信息 (对于 error response)
+  }
+}
+```
+
+其中，`payload` 部分是标准的 JSON-RPC 2.0 消息：
+
+- `jsonrpc`: 固定的字符串 "2.0"。
+- `method`: 要调用的方法名称 (对于 Request)。
+- `params`: 方法的参数，一个结构化值，通常为对象 (对于 Request)。
+- `id`: 请求的标识符，客户端发送请求时提供，服务器响应时原样返回。用于匹配请求和响应。
+- `result`: 方法成功执行时的结果 (对于 Success Response)。
+- `error`: 方法执行失败时的错误信息 (对于 Error Response)。
+
+## 交互流程及发送时机
+
+MCP 的交互主要围绕客户端（后台 API）发现和调用设备上的“工具”（Tool）进行。
+
+1.  **连接建立与能力通告**
+
+    - **时机：** 设备启动并成功连接到后台 API 后。
+    - **发送方：** 设备。
+    - **消息：** 设备发送基础协议的 "hello" 消息给后台 API，消息中包含设备支持的能力列表，例如通过支持 MCP 协议 (`"mcp": true`)。
+    - **示例 (非 MCP 负载，而是基础协议消息):**
+      ```json
+      {
+        "type": "hello",
+        "version": ...,
+        "features": {
+          "mcp": true,
+          ...
+        },
+        "transport": "websocket", // 或 "mqtt"
+        "audio_params": { ... },
+        "session_id": "..." // 设备收到服务器hello后可能设置
+      }
+      ```
+
+2.  **初始化 MCP 会话**
+
+    - **时机：** 后台 API 收到设备 "hello" 消息，确认设备支持 MCP 后，通常作为 MCP 会话的第一个请求发送。
+    - **发送方：** 后台 API (客户端)。
+    - **方法：** `initialize`
+    - **消息 (MCP payload):**
+
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "method": "initialize",
+        "params": {
+          "capabilities": {
+            // 客户端能力，可选
+
+            // 摄像头视觉相关
+            "vision": {
+              "url": "...", //摄像头: 图片处理地址(必须是http地址, 不是websocket地址)
+              "token": "..." // url token
+            }
+
+            // ... 其他客户端能力
+          }
+        },
+        "id": 1 // 请求 ID
+      }
+      ```
+
+    - **设备响应时机：** 设备收到 `initialize` 请求并处理后。
+    - **设备响应消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "id": 1, // 匹配请求 ID
+        "result": {
+          "protocolVersion": "2024-11-05",
+          "capabilities": {
+            "tools": {} // 这里的 tools 似乎不列出详细信息，需要 tools/list
+          },
+          "serverInfo": {
+            "name": "...", // 设备名称 (BOARD_NAME)
+            "version": "..." // 设备固件版本
+          }
+        }
+      }
+      ```
+
+3.  **发现设备工具列表**
+
+    - **时机：** 后台 API 需要获取设备当前支持的具体功能（工具）列表及其调用方式时。
+    - **发送方：** 后台 API (客户端)。
+    - **方法：** `tools/list`
+    - **消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "method": "tools/list",
+        "params": {
+          "cursor": "" // 用于分页，首次请求为空字符串
+        },
+        "id": 2 // 请求 ID
+      }
+      ```
+    - **设备响应时机：** 设备收到 `tools/list` 请求并生成工具列表后。
+    - **设备响应消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "id": 2, // 匹配请求 ID
+        "result": {
+          "tools": [ // 工具对象列表
+            {
+              "name": "self.get_device_status",
+              "description": "...",
+              "inputSchema": { ... } // 参数 schema
+            },
+            {
+              "name": "self.audio_speaker.set_volume",
+              "description": "...",
+              "inputSchema": { ... } // 参数 schema
+            }
+            // ... 更多工具
+          ],
+          "nextCursor": "..." // 如果列表很大需要分页，这里会包含下一个请求的 cursor 值
+        }
+      }
+      ```
+    - **分页处理：** 如果 `nextCursor` 字段非空，客户端需要再次发送 `tools/list` 请求，并在 `params` 中带上这个 `cursor` 值以获取下一页工具。
+
+4.  **调用设备工具**
+
+    - **时机：** 后台 API 需要执行设备上的某个具体功能时。
+    - **发送方：** 后台 API (客户端)。
+    - **方法：** `tools/call`
+    - **消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "method": "tools/call",
+        "params": {
+          "name": "self.audio_speaker.set_volume", // 要调用的工具名称
+          "arguments": {
+            // 工具参数，对象格式
+            "volume": 50 // 参数名及其值
+          }
+        },
+        "id": 3 // 请求 ID
+      }
+      ```
+    - **设备响应时机：** 设备收到 `tools/call` 请求，执行相应的工具函数后。
+    - **设备成功响应消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "id": 3, // 匹配请求 ID
+        "result": {
+          "content": [
+            // 工具执行结果内容
+            { "type": "text", "text": "true" } // 示例：set_volume 返回 bool
+          ],
+          "isError": false // 表示成功
+        }
+      }
+      ```
+    - **设备失败响应消息 (MCP payload):**
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "id": 3, // 匹配请求 ID
+        "error": {
+          "code": -32601, // JSON-RPC 错误码，例如 Method not found (-32601)
+          "message": "Unknown tool: self.non_existent_tool" // 错误描述
+        }
+      }
+      ```
+
+5.  **设备主动发送消息 (Notifications)**
+    - **时机：** 设备内部发生需要通知后台 API 的事件时（例如，状态变化，虽然代码示例中没有明确的工具发送此类消息，但 `Application::SendMcpMessage` 的存在暗示了设备可能主动发送 MCP 消息）。
+    - **发送方：** 设备 (服务器)。
+    - **方法：** 可能是以 `notifications/` 开头的方法名，或者其他自定义方法。
+    - **消息 (MCP payload):** 遵循 JSON-RPC Notification 格式，没有 `id` 字段。
+      ```json
+      {
+        "jsonrpc": "2.0",
+        "method": "notifications/state_changed", // 示例方法名
+        "params": {
+          "newState": "idle",
+          "oldState": "connecting"
+        }
+        // 没有 id 字段
+      }
+      ```
+    - **后台 API 处理：** 接收到 Notification 后，后台 API 进行相应的处理，但不回复。
+
+## 交互图
+
+下面是一个简化的交互序列图，展示了主要的 MCP 消息流程：
+
+```mermaid
+sequenceDiagram
+    participant Device as ESP32 Device
+    participant BackendAPI as 后台 API (Client)
+
+    Note over Device, BackendAPI: 建立 WebSocket / MQTT 连接
+
+    Device->>BackendAPI: Hello Message (包含 "mcp": true)
+
+    BackendAPI->>Device: MCP Initialize Request
+    Note over BackendAPI: method: initialize
+    Note over BackendAPI: params: { capabilities: ... }
+
+    Device->>BackendAPI: MCP Initialize Response
+    Note over Device: result: { protocolVersion: ..., serverInfo: ... }
+
+    BackendAPI->>Device: MCP Get Tools List Request
+    Note over BackendAPI: method: tools/list
+    Note over BackendAPI: params: { cursor: "" }
+
+    Device->>BackendAPI: MCP Get Tools List Response
+    Note over Device: result: { tools: [...], nextCursor: ... }
+
+    loop Optional Pagination
+        BackendAPI->>Device: MCP Get Tools List Request
+        Note over BackendAPI: method: tools/list
+        Note over BackendAPI: params: { cursor: "..." }
+        Device->>BackendAPI: MCP Get Tools List Response
+        Note over Device: result: { tools: [...], nextCursor: "" }
+    end
+
+    BackendAPI->>Device: MCP Call Tool Request
+    Note over BackendAPI: method: tools/call
+    Note over BackendAPI: params: { name: "...", arguments: { ... } }
+
+    alt Tool Call Successful
+        Device->>BackendAPI: MCP Tool Call Success Response
+        Note over Device: result: { content: [...], isError: false }
+    else Tool Call Failed
+        Device->>BackendAPI: MCP Tool Call Error Response
+        Note over Device: error: { code: ..., message: ... }
+    end
+
+    opt Device Notification
+        Device->>BackendAPI: MCP Notification
+        Note over Device: method: notifications/...
+        Note over Device: params: { ... }
+    end
+```
+
+这份文档概述了该项目中 MCP 协议的主要交互流程。具体的参数细节和工具功能需要参考 `main/mcp_server.cc` 中 `McpServer::AddCommonTools` 以及各个工具的实现。

docs/mcp-usage.md

@@ -0,0 +1,115 @@
+# MCP 协议物联网控制用法说明
+
+> 本文档介绍如何基于 MCP 协议实现 ESP32 设备的物联网控制。详细协议流程请参考 [`mcp-protocol.md`](./mcp-protocol.md)。
+
+## 简介
+
+MCP（Model Context Protocol）是新一代推荐用于物联网控制的协议，通过标准 JSON-RPC 2.0 格式在后台与设备间发现和调用"工具"（Tool），实现灵活的设备控制。
+
+## 典型使用流程
+
+1. 设备启动后通过基础协议（如 WebSocket/MQTT）与后台建立连接。
+2. 后台通过 MCP 协议的 `initialize` 方法初始化会话。
+3. 后台通过 `tools/list` 获取设备支持的所有工具（功能）及参数说明。
+4. 后台通过 `tools/call` 调用具体工具，实现对设备的控制。
+
+详细协议格式与交互请见 [`mcp-protocol.md`](./mcp-protocol.md)。
+
+## 设备端工具注册方法说明
+
+设备通过 `McpServer::AddTool` 方法注册可被后台调用的"工具"。其常用函数签名如下：
+
+```cpp
+void AddTool(
+    const std::string& name,           // 工具名称，建议唯一且有层次感，如 self.dog.forward
+    const std::string& description,    // 工具描述，简明说明功能，便于大模型理解
+    const PropertyList& properties,    // 输入参数列表（可为空），支持类型：布尔、整数、字符串
+    std::function<ReturnValue(const PropertyList&)> callback // 工具被调用时的回调实现
+);
+```
+- name：工具唯一标识，建议用"模块.功能"命名风格。
+- description：自然语言描述，便于 AI/用户理解。
+- properties：参数列表，支持类型有布尔、整数、字符串，可指定范围和默认值。
+- callback：收到调用请求时的实际执行逻辑，返回值可为 bool/int/string。
+
+## 典型注册示例（以 ESP-Hi 为例）
+
+```cpp
+void InitializeTools() {
+    auto& mcp_server = McpServer::GetInstance();
+    // 例1：无参数，控制机器人前进
+    mcp_server.AddTool("self.dog.forward", "机器人向前移动", PropertyList(), [this](const PropertyList&) -> ReturnValue {
+        servo_dog_ctrl_send(DOG_STATE_FORWARD, NULL);
+        return true;
+    });
+    // 例2：带参数，设置灯光 RGB 颜色
+    mcp_server.AddTool("self.light.set_rgb", "设置RGB颜色", PropertyList({
+        Property("r", kPropertyTypeInteger, 0, 255),
+        Property("g", kPropertyTypeInteger, 0, 255),
+        Property("b", kPropertyTypeInteger, 0, 255)
+    }), [this](const PropertyList& properties) -> ReturnValue {
+        int r = properties["r"].value<int>();
+        int g = properties["g"].value<int>();
+        int b = properties["b"].value<int>();
+        led_on_ = true;
+        SetLedColor(r, g, b);
+        return true;
+    });
+}
+```
+
+## 常见工具调用 JSON-RPC 示例
+
+### 1. 获取工具列表
+```json
+{
+  "jsonrpc": "2.0",
+  "method": "tools/list",
+  "params": { "cursor": "" },
+  "id": 1
+}
+```
+
+### 2. 控制底盘前进
+```json
+{
+  "jsonrpc": "2.0",
+  "method": "tools/call",
+  "params": {
+    "name": "self.chassis.go_forward",
+    "arguments": {}
+  },
+  "id": 2
+}
+```
+
+### 3. 切换灯光模式
+```json
+{
+  "jsonrpc": "2.0",
+  "method": "tools/call",
+  "params": {
+    "name": "self.chassis.switch_light_mode",
+    "arguments": { "light_mode": 3 }
+  },
+  "id": 3
+}
+```
+
+### 4. 摄像头翻转
+```json
+{
+  "jsonrpc": "2.0",
+  "method": "tools/call",
+  "params": {
+    "name": "self.camera.set_camera_flipped",
+    "arguments": {}
+  },
+  "id": 4
+}
+```
+
+## 备注
+- 工具名称、参数及返回值请以设备端 `AddTool` 注册为准。
+- 推荐所有新项目统一采用 MCP 协议进行物联网控制。
+- 详细协议与进阶用法请查阅 [`mcp-protocol.md`](./mcp-protocol.md)。 

docs/mqtt-udp.md

@@ -0,0 +1,393 @@
+# MQTT + UDP 混合通信协议文档
+
+基于代码实现整理的 MQTT + UDP 混合通信协议文档，概述设备端与服务器之间如何通过 MQTT 进行控制消息传输，通过 UDP 进行音频数据传输的交互方式。
+
+---
+
+## 1. 协议概览
+
+本协议采用混合传输方式：
+- **MQTT**：用于控制消息、状态同步、JSON 数据交换
+- **UDP**：用于实时音频数据传输，支持加密
+
+### 1.1 协议特点
+
+- **双通道设计**：控制与数据分离，确保实时性
+- **加密传输**：UDP 音频数据使用 AES-CTR 加密
+- **序列号保护**：防止数据包重放和乱序
+- **自动重连**：MQTT 连接断开时自动重连
+
+---
+
+## 2. 总体流程概览
+
+```mermaid
+sequenceDiagram
+    participant Device as ESP32 设备
+    participant MQTT as MQTT 服务器
+    participant UDP as UDP 服务器
+
+    Note over Device, UDP: 1. 建立 MQTT 连接
+    Device->>MQTT: MQTT Connect
+    MQTT->>Device: Connected
+
+    Note over Device, UDP: 2. 请求音频通道
+    Device->>MQTT: Hello Message (type: "hello", transport: "udp")
+    MQTT->>Device: Hello Response (UDP 连接信息 + 加密密钥)
+
+    Note over Device, UDP: 3. 建立 UDP 连接
+    Device->>UDP: UDP Connect
+    UDP->>Device: Connected
+
+    Note over Device, UDP: 4. 音频数据传输
+    loop 音频流传输
+        Device->>UDP: 加密音频数据 (Opus)
+        UDP->>Device: 加密音频数据 (Opus)
+    end
+
+    Note over Device, UDP: 5. 控制消息交换
+    par 控制消息
+        Device->>MQTT: Listen/TTS/MCP 消息
+        MQTT->>Device: STT/TTS/MCP 响应
+    end
+
+    Note over Device, UDP: 6. 关闭连接
+    Device->>MQTT: Goodbye Message
+    Device->>UDP: Disconnect
+```
+
+---
+
+## 3. MQTT 控制通道
+
+### 3.1 连接建立
+
+设备通过 MQTT 连接到服务器，连接参数包括：
+- **Endpoint**：MQTT 服务器地址和端口
+- **Client ID**：设备唯一标识符
+- **Username/Password**：认证凭据
+- **Keep Alive**：心跳间隔（默认240秒）
+
+### 3.2 Hello 消息交换
+
+#### 3.2.1 设备端发送 Hello
+
+```json
+{
+  "type": "hello",
+  "version": 3,
+  "transport": "udp",
+  "features": {
+    "mcp": true
+  },
+  "audio_params": {
+    "format": "opus",
+    "sample_rate": 16000,
+    "channels": 1,
+    "frame_duration": 60
+  }
+}
+```
+
+#### 3.2.2 服务器响应 Hello
+
+```json
+{
+  "type": "hello",
+  "transport": "udp",
+  "session_id": "xxx",
+  "audio_params": {
+    "format": "opus",
+    "sample_rate": 24000,
+    "channels": 1,
+    "frame_duration": 60
+  },
+  "udp": {
+    "server": "192.168.1.100",
+    "port": 8888,
+    "key": "0123456789ABCDEF0123456789ABCDEF",
+    "nonce": "0123456789ABCDEF0123456789ABCDEF"
+  }
+}
+```
+
+**字段说明：**
+- `udp.server`：UDP 服务器地址
+- `udp.port`：UDP 服务器端口
+- `udp.key`：AES 加密密钥（十六进制字符串）
+- `udp.nonce`：AES 加密随机数（十六进制字符串）
+
+### 3.3 JSON 消息类型
+
+#### 3.3.1 设备端→服务器
+
+1. **Listen 消息**
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "listen",
+     "state": "start",
+     "mode": "manual"
+   }
+   ```
+
+2. **Abort 消息**
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "abort",
+     "reason": "wake_word_detected"
+   }
+   ```
+
+3. **MCP 消息**
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "mcp",
+     "payload": {
+       "jsonrpc": "2.0",
+       "id": 1,
+       "result": {...}
+     }
+   }
+   ```
+
+4. **Goodbye 消息**
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "goodbye"
+   }
+   ```
+
+#### 3.3.2 服务器→设备端
+
+支持的消息类型与 WebSocket 协议一致，包括：
+- **STT**：语音识别结果
+- **TTS**：语音合成控制
+- **LLM**：情感表达控制
+- **MCP**：物联网控制
+- **System**：系统控制
+- **Custom**：自定义消息（可选）
+
+---
+
+## 4. UDP 音频通道
+
+### 4.1 连接建立
+
+设备收到 MQTT Hello 响应后，使用其中的 UDP 连接信息建立音频通道：
+1. 解析 UDP 服务器地址和端口
+2. 解析加密密钥和随机数
+3. 初始化 AES-CTR 加密上下文
+4. 建立 UDP 连接
+
+### 4.2 音频数据格式
+
+#### 4.2.1 加密音频包结构
+
+```
+|type 1byte|flags 1byte|payload_len 2bytes|ssrc 4bytes|timestamp 4bytes|sequence 4bytes|
+|payload payload_len bytes|
+```
+
+**字段说明：**
+- `type`：数据包类型，固定为 0x01
+- `flags`：标志位，当前未使用
+- `payload_len`：负载长度（网络字节序）
+- `ssrc`：同步源标识符
+- `timestamp`：时间戳（网络字节序）
+- `sequence`：序列号（网络字节序）
+- `payload`：加密的 Opus 音频数据
+
+#### 4.2.2 加密算法
+
+使用 **AES-CTR** 模式加密：
+- **密钥**：128位，由服务器提供
+- **随机数**：128位，由服务器提供
+- **计数器**：包含时间戳和序列号信息
+
+### 4.3 序列号管理
+
+- **发送端**：`local_sequence_` 单调递增
+- **接收端**：`remote_sequence_` 验证连续性
+- **防重放**：拒绝序列号小于期望值的数据包
+- **容错处理**：允许轻微的序列号跳跃，记录警告
+
+### 4.4 错误处理
+
+1. **解密失败**：记录错误，丢弃数据包
+2. **序列号异常**：记录警告，但仍处理数据包
+3. **数据包格式错误**：记录错误，丢弃数据包
+
+---
+
+## 5. 状态管理
+
+### 5.1 连接状态
+
+```mermaid
+stateDiagram
+    direction TB
+    [*] --> Disconnected
+    Disconnected --> MqttConnecting: StartMqttClient()
+    MqttConnecting --> MqttConnected: MQTT Connected
+    MqttConnecting --> Disconnected: Connect Failed
+    MqttConnected --> RequestingChannel: OpenAudioChannel()
+    RequestingChannel --> ChannelOpened: Hello Exchange Success
+    RequestingChannel --> MqttConnected: Hello Timeout/Failed
+    ChannelOpened --> UdpConnected: UDP Connect Success
+    UdpConnected --> AudioStreaming: Start Audio Transfer
+    AudioStreaming --> UdpConnected: Stop Audio Transfer
+    UdpConnected --> ChannelOpened: UDP Disconnect
+    ChannelOpened --> MqttConnected: CloseAudioChannel()
+    MqttConnected --> Disconnected: MQTT Disconnect
+```
+
+### 5.2 状态检查
+
+设备通过以下条件判断音频通道是否可用：
+```cpp
+bool IsAudioChannelOpened() const {
+    return udp_ != nullptr && !error_occurred_ && !IsTimeout();
+}
+```
+
+---
+
+## 6. 配置参数
+
+### 6.1 MQTT 配置
+
+从设置中读取的配置项：
+- `endpoint`：MQTT 服务器地址
+- `client_id`：客户端标识符
+- `username`：用户名
+- `password`：密码
+- `keepalive`：心跳间隔（默认240秒）
+- `publish_topic`：发布主题
+
+### 6.2 音频参数
+
+- **格式**：Opus
+- **采样率**：16000 Hz（设备端）/ 24000 Hz（服务器端）
+- **声道数**：1（单声道）
+- **帧时长**：60ms
+
+---
+
+## 7. 错误处理与重连
+
+### 7.1 MQTT 重连机制
+
+- 连接失败时自动重试
+- 支持错误上报控制
+- 断线时触发清理流程
+
+### 7.2 UDP 连接管理
+
+- 连接失败时不自动重试
+- 依赖 MQTT 通道重新协商
+- 支持连接状态查询
+
+### 7.3 超时处理
+
+基类 `Protocol` 提供超时检测：
+- 默认超时时间：120 秒
+- 基于最后接收时间计算
+- 超时时自动标记为不可用
+
+---
+
+## 8. 安全考虑
+
+### 8.1 传输加密
+
+- **MQTT**：支持 TLS/SSL 加密（端口8883）
+- **UDP**：使用 AES-CTR 加密音频数据
+
+### 8.2 认证机制
+
+- **MQTT**：用户名/密码认证
+- **UDP**：通过 MQTT 通道分发密钥
+
+### 8.3 防重放攻击
+
+- 序列号单调递增
+- 拒绝过期数据包
+- 时间戳验证
+
+---
+
+## 9. 性能优化
+
+### 9.1 并发控制
+
+使用互斥锁保护 UDP 连接：
+```cpp
+std::lock_guard<std::mutex> lock(channel_mutex_);
+```
+
+### 9.2 内存管理
+
+- 动态创建/销毁网络对象
+- 智能指针管理音频数据包
+- 及时释放加密上下文
+
+### 9.3 网络优化
+
+- UDP 连接复用
+- 数据包大小优化
+- 序列号连续性检查
+
+---
+
+## 10. 与 WebSocket 协议的比较
+
+| 特性 | MQTT + UDP | WebSocket |
+|------|------------|-----------|
+| 控制通道 | MQTT | WebSocket |
+| 音频通道 | UDP (加密) | WebSocket (二进制) |
+| 实时性 | 高 (UDP) | 中等 |
+| 可靠性 | 中等 | 高 |
+| 复杂度 | 高 | 低 |
+| 加密 | AES-CTR | TLS |
+| 防火墙友好度 | 低 | 高 |
+
+---
+
+## 11. 部署建议
+
+### 11.1 网络环境
+
+- 确保 UDP 端口可达
+- 配置防火墙规则
+- 考虑 NAT 穿透
+
+### 11.2 服务器配置
+
+- MQTT Broker 配置
+- UDP 服务器部署
+- 密钥管理系统
+
+### 11.3 监控指标
+
+- 连接成功率
+- 音频传输延迟
+- 数据包丢失率
+- 解密失败率
+
+---
+
+## 12. 总结
+
+MQTT + UDP 混合协议通过以下设计实现高效的音视频通信：
+
+- **分离式架构**：控制与数据通道分离，各司其职
+- **加密保护**：AES-CTR 确保音频数据安全传输
+- **序列化管理**：防止重放攻击和数据乱序
+- **自动恢复**：支持连接断开后的自动重连
+- **性能优化**：UDP 传输保证音频数据的实时性
+
+该协议适用于对实时性要求较高的语音交互场景，但需要在网络复杂度和传输性能之间做出权衡。 

docs/websocket.md

@@ -0,0 +1,495 @@
+以下是一份基于代码实现整理的 WebSocket 通信协议文档，概述设备端与服务器之间如何通过 WebSocket 进行交互。
+
+该文档仅基于所提供的代码推断，实际部署时可能需要结合服务器端实现进行进一步确认或补充。
+
+---
+
+## 1. 总体流程概览
+
+1. **设备端初始化**  
+   - 设备上电、初始化 `Application`：  
+     - 初始化音频编解码器、显示屏、LED 等  
+     - 连接网络  
+     - 创建并初始化实现 `Protocol` 接口的 WebSocket 协议实例（`WebsocketProtocol`）  
+   - 进入主循环等待事件（音频输入、音频输出、调度任务等）。
+
+2. **建立 WebSocket 连接**  
+   - 当设备需要开始语音会话时（例如用户唤醒、手动按键触发等），调用 `OpenAudioChannel()`：  
+     - 根据配置获取 WebSocket URL
+     - 设置若干请求头（`Authorization`, `Protocol-Version`, `Device-Id`, `Client-Id`）  
+     - 调用 `Connect()` 与服务器建立 WebSocket 连接  
+
+3. **设备端发送 "hello" 消息**  
+   - 连接成功后，设备会发送一条 JSON 消息，示例结构如下：  
+   ```json
+   {
+     "type": "hello",
+     "version": 1,
+     "features": {
+       "mcp": true
+     },
+     "transport": "websocket",
+     "audio_params": {
+       "format": "opus",
+       "sample_rate": 16000,
+       "channels": 1,
+       "frame_duration": 60
+     }
+   }
+   ```
+   - 其中 `features` 字段为可选，内容根据设备编译配置自动生成。例如：`"mcp": true` 表示支持 MCP 协议。
+   - `frame_duration` 的值对应 `OPUS_FRAME_DURATION_MS`（例如 60ms）。
+
+4. **服务器回复 "hello"**  
+   - 设备等待服务器返回一条包含 `"type": "hello"` 的 JSON 消息，并检查 `"transport": "websocket"` 是否匹配。  
+   - 服务器可选下发 `session_id` 字段，设备端收到后会自动记录。  
+   - 示例：
+   ```json
+   {
+     "type": "hello",
+     "transport": "websocket",
+     "session_id": "xxx",
+     "audio_params": {
+       "format": "opus",
+       "sample_rate": 24000,
+       "channels": 1,
+       "frame_duration": 60
+     }
+   }
+   ```
+   - 如果匹配，则认为服务器已就绪，标记音频通道打开成功。  
+   - 如果在超时时间（默认 10 秒）内未收到正确回复，认为连接失败并触发网络错误回调。
+
+5. **后续消息交互**  
+   - 设备端和服务器端之间可发送两种主要类型的数据：  
+     1. **二进制音频数据**（Opus 编码）  
+     2. **文本 JSON 消息**（用于传输聊天状态、TTS/STT 事件、MCP 协议消息等）  
+
+   - 在代码里，接收回调主要分为：  
+     - `OnData(...)`:  
+       - 当 `binary` 为 `true` 时，认为是音频帧；设备会将其当作 Opus 数据进行解码。  
+       - 当 `binary` 为 `false` 时，认为是 JSON 文本，需要在设备端用 cJSON 进行解析并做相应业务逻辑处理（如聊天、TTS、MCP 协议消息等）。  
+
+   - 当服务器或网络出现断连，回调 `OnDisconnected()` 被触发：  
+     - 设备会调用 `on_audio_channel_closed_()`，并最终回到空闲状态。
+
+6. **关闭 WebSocket 连接**  
+   - 设备在需要结束语音会话时，会调用 `CloseAudioChannel()` 主动断开连接，并回到空闲状态。  
+   - 或者如果服务器端主动断开，也会引发同样的回调流程。
+
+---
+
+## 2. 通用请求头
+
+在建立 WebSocket 连接时，代码示例中设置了以下请求头：
+
+- `Authorization`: 用于存放访问令牌，形如 `"Bearer <token>"`  
+- `Protocol-Version`: 协议版本号，与 hello 消息体内的 `version` 字段保持一致  
+- `Device-Id`: 设备物理网卡 MAC 地址
+- `Client-Id`: 软件生成的 UUID（擦除 NVS 或重新烧录完整固件会重置）
+
+这些头会随着 WebSocket 握手一起发送到服务器，服务器可根据需求进行校验、认证等。
+
+---
+
+## 3. 二进制协议版本
+
+设备支持多种二进制协议版本，通过配置中的 `version` 字段指定：
+
+### 3.1 版本1（默认）
+直接发送 Opus 音频数据，无额外元数据。Websocket 协议会区分 text 与 binary。
+
+### 3.2 版本2
+使用 `BinaryProtocol2` 结构：
+```c
+struct BinaryProtocol2 {
+    uint16_t version;        // 协议版本
+    uint16_t type;           // 消息类型 (0: OPUS, 1: JSON)
+    uint32_t reserved;       // 保留字段
+    uint32_t timestamp;      // 时间戳（毫秒，用于服务器端AEC）
+    uint32_t payload_size;   // 负载大小（字节）
+    uint8_t payload[];       // 负载数据
+} __attribute__((packed));
+```
+
+### 3.3 版本3
+使用 `BinaryProtocol3` 结构：
+```c
+struct BinaryProtocol3 {
+    uint8_t type;            // 消息类型
+    uint8_t reserved;        // 保留字段
+    uint16_t payload_size;   // 负载大小
+    uint8_t payload[];       // 负载数据
+} __attribute__((packed));
+```
+
+---
+
+## 4. JSON 消息结构
+
+WebSocket 文本帧以 JSON 方式传输，以下为常见的 `"type"` 字段及其对应业务逻辑。若消息里包含未列出的字段，可能为可选或特定实现细节。
+
+### 4.1 设备端→服务器
+
+1. **Hello**  
+   - 连接成功后，由设备端发送，告知服务器基本参数。  
+   - 例：
+     ```json
+     {
+       "type": "hello",
+       "version": 1,
+       "features": {
+         "mcp": true
+       },
+       "transport": "websocket",
+       "audio_params": {
+         "format": "opus",
+         "sample_rate": 16000,
+         "channels": 1,
+         "frame_duration": 60
+       }
+     }
+     ```
+
+2. **Listen**  
+   - 表示设备端开始或停止录音监听。  
+   - 常见字段：  
+     - `"session_id"`：会话标识  
+     - `"type": "listen"`  
+     - `"state"`：`"start"`, `"stop"`, `"detect"`（唤醒检测已触发）  
+     - `"mode"`：`"auto"`, `"manual"` 或 `"realtime"`，表示识别模式。  
+   - 例：开始监听  
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "listen",
+       "state": "start",
+       "mode": "manual"
+     }
+     ```
+
+3. **Abort**  
+   - 终止当前说话（TTS 播放）或语音通道。  
+   - 例：
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "abort",
+       "reason": "wake_word_detected"
+     }
+     ```
+   - `reason` 值可为 `"wake_word_detected"` 或其他。
+
+4. **Wake Word Detected**  
+   - 用于设备端向服务器告知检测到唤醒词。
+   - 在发送该消息之前，可提前发送唤醒词的 Opus 音频数据，用于服务器进行声纹检测。  
+   - 例：
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "listen",
+       "state": "detect",
+       "text": "你好小明"
+     }
+     ```
+
+5. **MCP**
+   - 推荐用于物联网控制的新一代协议。所有设备能力发现、工具调用等均通过 type: "mcp" 的消息进行，payload 内部为标准 JSON-RPC 2.0（详见 [MCP 协议文档](./mcp-protocol.md)）。
+   
+   - **设备端到服务器发送 result 的例子：**
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "mcp",
+       "payload": {
+         "jsonrpc": "2.0",
+         "id": 1,
+         "result": {
+           "content": [
+             { "type": "text", "text": "true" }
+           ],
+           "isError": false
+         }
+       }
+     }
+     ```
+
+---
+
+### 4.2 服务器→设备端
+
+1. **Hello**  
+   - 服务器端返回的握手确认消息。  
+   - 必须包含 `"type": "hello"` 和 `"transport": "websocket"`。  
+   - 可能会带有 `audio_params`，表示服务器期望的音频参数，或与设备端对齐的配置。   
+   - 服务器可选下发 `session_id` 字段，设备端收到后会自动记录。  
+   - 成功接收后设备端会设置事件标志，表示 WebSocket 通道就绪。
+
+2. **STT**  
+   - `{"session_id": "xxx", "type": "stt", "text": "..."}`
+   - 表示服务器端识别到了用户语音。（例如语音转文本结果）  
+   - 设备可能将此文本显示到屏幕上，后续再进入回答等流程。
+
+3. **LLM**  
+   - `{"session_id": "xxx", "type": "llm", "emotion": "happy", "text": "😀"}`
+   - 服务器指示设备调整表情动画 / UI 表达。  
+
+4. **TTS**  
+   - `{"session_id": "xxx", "type": "tts", "state": "start"}`：服务器准备下发 TTS 音频，设备端进入 "speaking" 播放状态。  
+   - `{"session_id": "xxx", "type": "tts", "state": "stop"}`：表示本次 TTS 结束。  
+   - `{"session_id": "xxx", "type": "tts", "state": "sentence_start", "text": "..."}`
+     - 让设备在界面上显示当前要播放或朗读的文本片段（例如用于显示给用户）。  
+
+5. **MCP**
+   - 服务器通过 type: "mcp" 的消息下发物联网相关的控制指令或返回调用结果，payload 结构同上。
+   
+   - **服务器到设备端发送 tools/call 的例子：**
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "mcp",
+       "payload": {
+         "jsonrpc": "2.0",
+         "method": "tools/call",
+         "params": {
+           "name": "self.light.set_rgb",
+           "arguments": { "r": 255, "g": 0, "b": 0 }
+         },
+         "id": 1
+       }
+     }
+     ```
+
+6. **System**
+   - 系统控制命令，常用于远程升级更新。
+   - 例：
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "system",
+       "command": "reboot"
+     }
+     ```
+   - 支持的命令：
+     - `"reboot"`：重启设备
+
+7. **Custom**（可选）
+   - 自定义消息，当 `CONFIG_RECEIVE_CUSTOM_MESSAGE` 启用时支持。
+   - 例：
+     ```json
+     {
+       "session_id": "xxx",
+       "type": "custom",
+       "payload": {
+         "message": "自定义内容"
+       }
+     }
+     ```
+
+8. **音频数据：二进制帧**  
+   - 当服务器发送音频二进制帧（Opus 编码）时，设备端解码并播放。  
+   - 若设备端正在处于 "listening" （录音）状态，收到的音频帧会被忽略或清空以防冲突。
+
+---
+
+## 5. 音频编解码
+
+1. **设备端发送录音数据**  
+   - 音频输入经过可能的回声消除、降噪或音量增益后，通过 Opus 编码打包为二进制帧发送给服务器。  
+   - 根据协议版本，可能直接发送 Opus 数据（版本1）或使用带元数据的二进制协议（版本2/3）。
+
+2. **设备端播放收到的音频**  
+   - 收到服务器的二进制帧时，同样认定是 Opus 数据。  
+   - 设备端会进行解码，然后交由音频输出接口播放。  
+   - 如果服务器的音频采样率与设备不一致，会在解码后再进行重采样。
+
+---
+
+## 6. 常见状态流转
+
+以下为常见设备端关键状态流转，与 WebSocket 消息对应：
+
+1. **Idle** → **Connecting**  
+   - 用户触发或唤醒后，设备调用 `OpenAudioChannel()` → 建立 WebSocket 连接 → 发送 `"type":"hello"`。  
+
+2. **Connecting** → **Listening**  
+   - 成功建立连接后，若继续执行 `SendStartListening(...)`，则进入录音状态。此时设备会持续编码麦克风数据并发送到服务器。  
+
+3. **Listening** → **Speaking**  
+   - 收到服务器 TTS Start 消息 (`{"type":"tts","state":"start"}`) → 停止录音并播放接收到的音频。  
+
+4. **Speaking** → **Idle**  
+   - 服务器 TTS Stop (`{"type":"tts","state":"stop"}`) → 音频播放结束。若未继续进入自动监听，则返回 Idle；如果配置了自动循环，则再度进入 Listening。  
+
+5. **Listening** / **Speaking** → **Idle**（遇到异常或主动中断）  
+   - 调用 `SendAbortSpeaking(...)` 或 `CloseAudioChannel()` → 中断会话 → 关闭 WebSocket → 状态回到 Idle。  
+
+### 自动模式状态流转图
+
+```mermaid
+stateDiagram
+  direction TB
+  [*] --> kDeviceStateUnknown
+  kDeviceStateUnknown --> kDeviceStateStarting:初始化
+  kDeviceStateStarting --> kDeviceStateWifiConfiguring:配置WiFi
+  kDeviceStateStarting --> kDeviceStateActivating:激活设备
+  kDeviceStateActivating --> kDeviceStateUpgrading:检测到新版本
+  kDeviceStateActivating --> kDeviceStateIdle:激活完成
+  kDeviceStateIdle --> kDeviceStateConnecting:开始连接
+  kDeviceStateConnecting --> kDeviceStateIdle:连接失败
+  kDeviceStateConnecting --> kDeviceStateListening:连接成功
+  kDeviceStateListening --> kDeviceStateSpeaking:开始说话
+  kDeviceStateSpeaking --> kDeviceStateListening:结束说话
+  kDeviceStateListening --> kDeviceStateIdle:手动终止
+  kDeviceStateSpeaking --> kDeviceStateIdle:自动终止
+```
+
+### 手动模式状态流转图
+
+```mermaid
+stateDiagram
+  direction TB
+  [*] --> kDeviceStateUnknown
+  kDeviceStateUnknown --> kDeviceStateStarting:初始化
+  kDeviceStateStarting --> kDeviceStateWifiConfiguring:配置WiFi
+  kDeviceStateStarting --> kDeviceStateActivating:激活设备
+  kDeviceStateActivating --> kDeviceStateUpgrading:检测到新版本
+  kDeviceStateActivating --> kDeviceStateIdle:激活完成
+  kDeviceStateIdle --> kDeviceStateConnecting:开始连接
+  kDeviceStateConnecting --> kDeviceStateIdle:连接失败
+  kDeviceStateConnecting --> kDeviceStateListening:连接成功
+  kDeviceStateIdle --> kDeviceStateListening:开始监听
+  kDeviceStateListening --> kDeviceStateIdle:停止监听
+  kDeviceStateIdle --> kDeviceStateSpeaking:开始说话
+  kDeviceStateSpeaking --> kDeviceStateIdle:结束说话
+```
+
+---
+
+## 7. 错误处理
+
+1. **连接失败**  
+   - 如果 `Connect(url)` 返回失败或在等待服务器 "hello" 消息时超时，触发 `on_network_error_()` 回调。设备会提示"无法连接到服务"或类似错误信息。
+
+2. **服务器断开**  
+   - 如果 WebSocket 异常断开，回调 `OnDisconnected()`：  
+     - 设备回调 `on_audio_channel_closed_()`  
+     - 切换到 Idle 或其他重试逻辑。
+
+---
+
+## 8. 其它注意事项
+
+1. **鉴权**  
+   - 设备通过设置 `Authorization: Bearer <token>` 提供鉴权，服务器端需验证是否有效。  
+   - 如果令牌过期或无效，服务器可拒绝握手或在后续断开。
+
+2. **会话控制**  
+   - 代码中部分消息包含 `session_id`，用于区分独立的对话或操作。服务端可根据需要对不同会话做分离处理。
+
+3. **音频负载**  
+   - 代码里默认使用 Opus 格式，并设置 `sample_rate = 16000`，单声道。帧时长由 `OPUS_FRAME_DURATION_MS` 控制，一般为 60ms。可根据带宽或性能做适当调整。为了获得更好的音乐播放效果，服务器下行音频可能使用 24000 采样率。
+
+4. **协议版本配置**  
+   - 通过设置中的 `version` 字段配置二进制协议版本（1、2 或 3）
+   - 版本1：直接发送 Opus 数据
+   - 版本2：使用带时间戳的二进制协议，适用于服务器端 AEC
+   - 版本3：使用简化的二进制协议
+
+5. **物联网控制推荐 MCP 协议**  
+   - 设备与服务器之间的物联网能力发现、状态同步、控制指令等，建议全部通过 MCP 协议（type: "mcp"）实现。原有的 type: "iot" 方案已废弃。
+   - MCP 协议可在 WebSocket、MQTT 等多种底层协议上传输，具备更好的扩展性和标准化能力。
+   - 详细用法请参考 [MCP 协议文档](./mcp-protocol.md) 及 [MCP 物联网控制用法](./mcp-usage.md)。
+
+6. **错误或异常 JSON**  
+   - 当 JSON 中缺少必要字段，例如 `{"type": ...}`，设备端会记录错误日志（`ESP_LOGE(TAG, "Missing message type, data: %s", data);`），不会执行任何业务。
+
+---
+
+## 9. 消息示例
+
+下面给出一个典型的双向消息示例（流程简化示意）：
+
+1. **设备端 → 服务器**（握手）
+   ```json
+   {
+     "type": "hello",
+     "version": 1,
+     "features": {
+       "mcp": true
+     },
+     "transport": "websocket",
+     "audio_params": {
+       "format": "opus",
+       "sample_rate": 16000,
+       "channels": 1,
+       "frame_duration": 60
+     }
+   }
+   ```
+
+2. **服务器 → 设备端**（握手应答）
+   ```json
+   {
+     "type": "hello",
+     "transport": "websocket",
+     "session_id": "xxx",
+     "audio_params": {
+       "format": "opus",
+       "sample_rate": 16000
+     }
+   }
+   ```
+
+3. **设备端 → 服务器**（开始监听）
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "listen",
+     "state": "start",
+     "mode": "auto"
+   }
+   ```
+   同时设备端开始发送二进制帧（Opus 数据）。
+
+4. **服务器 → 设备端**（ASR 结果）
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "stt",
+     "text": "用户说的话"
+   }
+   ```
+
+5. **服务器 → 设备端**（TTS开始）
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "tts",
+     "state": "start"
+   }
+   ```
+   接着服务器发送二进制音频帧给设备端播放。
+
+6. **服务器 → 设备端**（TTS结束）
+   ```json
+   {
+     "session_id": "xxx",
+     "type": "tts",
+     "state": "stop"
+   }
+   ```
+   设备端停止播放音频，若无更多指令，则回到空闲状态。
+
+---
+
+## 10. 总结
+
+本协议通过在 WebSocket 上层传输 JSON 文本与二进制音频帧，完成功能包括音频流上传、TTS 音频播放、语音识别与状态管理、MCP 指令下发等。其核心特征：
+
+- **握手阶段**：发送 `"type":"hello"`，等待服务器返回。  
+- **音频通道**：采用 Opus 编码的二进制帧双向传输语音流，支持多种协议版本。  
+- **JSON 消息**：使用 `"type"` 为核心字段标识不同业务逻辑，包括 TTS、STT、MCP、WakeWord、System、Custom 等。  
+- **扩展性**：可根据实际需求在 JSON 消息中添加字段，或在 headers 里进行额外鉴权。
+
+服务器与设备端需提前约定各类消息的字段含义、时序逻辑以及错误处理规则，方能保证通信顺畅。上述信息可作为基础文档，便于后续对接、开发或扩展。

main/Application.cc

@@ -1,559 +0,0 @@
-#include "Application.h"
-#include "BuiltinLed.h"
-#include "WifiStation.h"
-#include <cstring>
-#include "esp_log.h"
-#include "model_path.h"
-#include "SystemInfo.h"
-#include "cJSON.h"
-
-#define TAG "Application"
-
-
-Application::Application() {
-    event_group_ = xEventGroupCreate();
-    audio_encode_queue_ = xQueueCreate(100, sizeof(iovec));
-    audio_decode_queue_ = xQueueCreate(100, sizeof(AudioPacket*));
-
-    srmodel_list_t *models = esp_srmodel_init("model");
-    for (int i = 0; i < models->num; i++) {
-        ESP_LOGI(TAG, "Model %d: %s", i, models->model_name[i]);
-        if (strstr(models->model_name[i], ESP_WN_PREFIX) != NULL) {
-            wakenet_model_ = models->model_name[i];
-        } else if (strstr(models->model_name[i], ESP_NSNET_PREFIX) != NULL) {
-            nsnet_model_ = models->model_name[i];
-        }
-    }
-    
-    opus_encoder_.Configure(CONFIG_AUDIO_INPUT_SAMPLE_RATE, 1);
-    opus_decoder_ = opus_decoder_create(opus_decode_sample_rate_, 1, NULL);
-    if (opus_decode_sample_rate_ != CONFIG_AUDIO_OUTPUT_SAMPLE_RATE) {
-        opus_resampler_.Configure(opus_decode_sample_rate_, CONFIG_AUDIO_OUTPUT_SAMPLE_RATE);
-    }
-}
-
-Application::~Application() {
-    if (afe_detection_data_ != nullptr) {
-        esp_afe_sr_v1.destroy(afe_detection_data_);
-    }
-
-    if (afe_communication_data_ != nullptr) {
-        esp_afe_vc_v1.destroy(afe_communication_data_);
-    }
-
-    if (wake_word_encode_task_stack_ != nullptr) {
-        free(wake_word_encode_task_stack_);
-    }
-    for (auto& pcm : wake_word_pcm_) {
-        free(pcm.iov_base);
-    }
-    for (auto& opus : wake_word_opus_) {
-        free(opus.iov_base);
-    }
-    
-    if (opus_decoder_ != nullptr) {
-        opus_decoder_destroy(opus_decoder_);
-    }
-    if (audio_encode_task_stack_ != nullptr) {
-        free(audio_encode_task_stack_);
-    }
-    if (audio_decode_task_stack_ != nullptr) {
-        free(audio_decode_task_stack_);
-    }
-    vQueueDelete(audio_decode_queue_);
-    vQueueDelete(audio_encode_queue_);
-
-    vEventGroupDelete(event_group_);
-}
-
-void Application::Start() {
-    // Initialize the audio device
-    audio_device_.Start(CONFIG_AUDIO_INPUT_SAMPLE_RATE, CONFIG_AUDIO_OUTPUT_SAMPLE_RATE);
-    audio_device_.OnStateChanged([this]() {
-        if (audio_device_.playing()) {
-            SetChatState(kChatStateSpeaking);
-        } else {
-            // Check if communication is still running
-            if (xEventGroupGetBits(event_group_) & COMMUNICATION_RUNNING) {
-                SetChatState(kChatStateListening);
-            } else {
-                SetChatState(kChatStateIdle);
-            }
-        }
-    });
-
-    // OPUS encoder / decoder use a lot of stack memory
-    const size_t opus_stack_size = 4096 * 8;
-    audio_encode_task_stack_ = (StackType_t*)malloc(opus_stack_size);
-    xTaskCreateStatic([](void* arg) {
-        Application* app = (Application*)arg;
-        app->AudioEncodeTask();
-    }, "opus_encode", opus_stack_size, this, 1, audio_encode_task_stack_, &audio_encode_task_buffer_);
-    audio_decode_task_stack_ = (StackType_t*)malloc(opus_stack_size);
-    xTaskCreateStatic([](void* arg) {
-        Application* app = (Application*)arg;
-        app->AudioDecodeTask();
-    }, "opus_decode", opus_stack_size, this, 1, audio_decode_task_stack_, &audio_decode_task_buffer_);
-
-    auto& builtin_led = BuiltinLed::GetInstance();
-    // Blink the LED to indicate the device is connecting
-    builtin_led.SetBlue();
-    builtin_led.BlinkOnce();
-    WifiStation::GetInstance().Start();
-    
-    // Check if there is a new firmware version available
-    firmware_upgrade_.CheckVersion();
-    if (firmware_upgrade_.HasNewVersion()) {
-        builtin_led.TurnOn();
-        firmware_upgrade_.StartUpgrade();
-        // If upgrade success, the device will reboot and never reach here
-        ESP_LOGI(TAG, "Firmware upgrade failed...");
-        builtin_led.TurnOff();
-    } else {
-        firmware_upgrade_.MarkValid();
-    }
-
-    StartCommunication();
-    StartDetection();
-
-    // Blink the LED to indicate the device is running
-    builtin_led.SetGreen();
-    builtin_led.BlinkOnce();
-    xEventGroupSetBits(event_group_, DETECTION_RUNNING);
-}
-
-void Application::SetChatState(ChatState state) {
-    auto& builtin_led = BuiltinLed::GetInstance();
-    chat_state_ = state;
-    switch (chat_state_) {
-        case kChatStateIdle:
-            ESP_LOGI(TAG, "Chat state: idle");
-            builtin_led.TurnOff();
-            break;
-        case kChatStateConnecting:
-            ESP_LOGI(TAG, "Chat state: connecting");
-            builtin_led.SetBlue();
-            builtin_led.TurnOn();
-            break;
-        case kChatStateListening:
-            ESP_LOGI(TAG, "Chat state: listening");
-            builtin_led.SetRed();
-            builtin_led.TurnOn();
-            break;
-        case kChatStateSpeaking:
-            ESP_LOGI(TAG, "Chat state: speaking");
-            builtin_led.SetGreen();
-            builtin_led.TurnOn();
-            break;
-        case kChatStateWakeWordDetected:
-            ESP_LOGI(TAG, "Chat state: wake word detected");
-            builtin_led.SetBlue();
-            builtin_led.TurnOn();
-            break;
-    }
-
-    const char* state_str[] = { "idle", "connecting", "listening", "speaking", "wake_word_detected", "unknown" };
-    std::lock_guard<std::recursive_mutex> lock(mutex_);
-    if (ws_client_ && ws_client_->IsConnected()) {
-        cJSON* root = cJSON_CreateObject();
-        cJSON_AddStringToObject(root, "type", "state");
-        cJSON_AddStringToObject(root, "state", state_str[chat_state_]);
-        char* json = cJSON_PrintUnformatted(root);
-        ws_client_->Send(json);
-        cJSON_Delete(root);
-        free(json);
-    }
-}
-
-void Application::StartCommunication() {
-    afe_config_t afe_config = {
-        .aec_init = false,
-        .se_init = true,
-        .vad_init = false,
-        .wakenet_init = false,
-        .voice_communication_init = true,
-        .voice_communication_agc_init = true,
-        .voice_communication_agc_gain = 10,
-        .vad_mode = VAD_MODE_3,
-        .wakenet_model_name = NULL,
-        .wakenet_model_name_2 = NULL,
-        .wakenet_mode = DET_MODE_90,
-        .afe_mode = SR_MODE_HIGH_PERF,
-        .afe_perferred_core = 0,
-        .afe_perferred_priority = 5,
-        .afe_ringbuf_size = 50,
-        .memory_alloc_mode = AFE_MEMORY_ALLOC_MORE_PSRAM,
-        .afe_linear_gain = 1.0,
-        .agc_mode = AFE_MN_PEAK_AGC_MODE_2,
-        .pcm_config = {
-            .total_ch_num = 1,
-            .mic_num = 1,
-            .ref_num = 0,
-            .sample_rate = CONFIG_AUDIO_INPUT_SAMPLE_RATE,
-        },
-        .debug_init = false,
-        .debug_hook = {{ AFE_DEBUG_HOOK_MASE_TASK_IN, NULL }, { AFE_DEBUG_HOOK_FETCH_TASK_IN, NULL }},
-        .afe_ns_mode = NS_MODE_SSP,
-        .afe_ns_model_name = NULL,
-        .fixed_first_channel = true,
-    };
-
-    afe_communication_data_ = esp_afe_vc_v1.create_from_config(&afe_config);
-    
-    xTaskCreate([](void* arg) {
-        Application* app = (Application*)arg;
-        app->AudioCommunicationTask();
-    }, "audio_communication", 4096 * 2, this, 5, NULL);
-}
-
-void Application::StartDetection() {
-    afe_config_t afe_config = {
-        .aec_init = false,
-        .se_init = true,
-        .vad_init = false,
-        .wakenet_init = true,
-        .voice_communication_init = false,
-        .voice_communication_agc_init = false,
-        .voice_communication_agc_gain = 10,
-        .vad_mode = VAD_MODE_3,
-        .wakenet_model_name = wakenet_model_,
-        .wakenet_model_name_2 = NULL,
-        .wakenet_mode = DET_MODE_90,
-        .afe_mode = SR_MODE_HIGH_PERF,
-        .afe_perferred_core = 0,
-        .afe_perferred_priority = 5,
-        .afe_ringbuf_size = 50,
-        .memory_alloc_mode = AFE_MEMORY_ALLOC_MORE_PSRAM,
-        .afe_linear_gain = 1.0,
-        .agc_mode = AFE_MN_PEAK_AGC_MODE_2,
-        .pcm_config = {
-            .total_ch_num = 1,
-            .mic_num = 1,
-            .ref_num = 0,
-            .sample_rate = CONFIG_AUDIO_INPUT_SAMPLE_RATE
-        },
-        .debug_init = false,
-        .debug_hook = {{ AFE_DEBUG_HOOK_MASE_TASK_IN, NULL }, { AFE_DEBUG_HOOK_FETCH_TASK_IN, NULL }},
-        .afe_ns_mode = NS_MODE_SSP,
-        .afe_ns_model_name = NULL,
-        .fixed_first_channel = true,
-    };
-
-    afe_detection_data_ = esp_afe_sr_v1.create_from_config(&afe_config);
-    xTaskCreate([](void* arg) {
-        Application* app = (Application*)arg;
-        app->AudioFeedTask();
-    }, "audio_feed", 4096 * 2, this, 5, NULL);
-
-    xTaskCreate([](void* arg) {
-        Application* app = (Application*)arg;
-        app->AudioDetectionTask();
-    }, "audio_detection", 4096 * 2, this, 5, NULL);
-}
-
-void Application::AudioFeedTask() {
-    int chunk_size = esp_afe_vc_v1.get_feed_chunksize(afe_detection_data_);
-    int16_t buffer[chunk_size];
-    ESP_LOGI(TAG, "Audio feed task started, chunk size: %d", chunk_size);
-
-    while (true) {
-        audio_device_.Read(buffer, chunk_size);
-
-        auto event_bits = xEventGroupGetBits(event_group_);
-        if (event_bits & DETECTION_RUNNING) {
-            esp_afe_sr_v1.feed(afe_detection_data_, buffer);
-        } else if (event_bits & COMMUNICATION_RUNNING) {
-            esp_afe_vc_v1.feed(afe_communication_data_, buffer);
-        }
-    }
-
-    vTaskDelete(NULL);
-}
-
-void Application::StoreWakeWordData(uint8_t* data, size_t size) {
-    // store audio data to detect_packets_
-    auto iov = (iovec){
-        .iov_base = heap_caps_malloc(size, MALLOC_CAP_SPIRAM),
-        .iov_len = size
-    };
-    memcpy(iov.iov_base, data, size);
-    wake_word_pcm_.push_back(iov);
-    // remove the oldest packet if the size is larger than 50, about 2 seconds
-    if (wake_word_pcm_.size() > 50) {
-        heap_caps_free(wake_word_pcm_.front().iov_base);
-        wake_word_pcm_.pop_front();
-    }
-}
-
-void Application::EncodeWakeWordData() {
-    wake_word_opus_.clear();
-    if (wake_word_encode_task_stack_ == nullptr) {
-        wake_word_encode_task_stack_ = (StackType_t*)malloc(4096 * 8);
-    }
-    wake_word_encode_task_ = xTaskCreateStatic([](void* arg) {
-        Application* app = (Application*)arg;
-        auto start_time = esp_timer_get_time();
-        // encode detect packets
-        OpusEncoder* encoder = new OpusEncoder();
-        encoder->Configure(CONFIG_AUDIO_INPUT_SAMPLE_RATE, 1, 60);
-        encoder->SetComplexity(2);
-
-        for (auto& pcm: app->wake_word_pcm_) {
-            encoder->Encode(pcm, [app](const iovec opus) {
-                iovec iov = {
-                    .iov_base = heap_caps_malloc(opus.iov_len, MALLOC_CAP_SPIRAM),
-                    .iov_len = opus.iov_len
-                };
-                memcpy(iov.iov_base, opus.iov_base, opus.iov_len);
-                app->wake_word_opus_.push_back(iov);
-            });
-            heap_caps_free(pcm.iov_base);
-        }
-        app->wake_word_pcm_.clear();
-
-        auto end_time = esp_timer_get_time();
-        ESP_LOGI(TAG, "Encode wake word data opus packets: %d in %lld ms", app->wake_word_opus_.size(), (end_time - start_time) / 1000);
-        xEventGroupSetBits(app->event_group_, DETECT_PACKETS_ENCODED);
-        delete encoder;
-        vTaskDelete(NULL);
-    }, "encode_detect_packets", 4096 * 8, this, 1, wake_word_encode_task_stack_, &wake_word_encode_task_buffer_);
-}
-
-void Application::SendWakeWordData() {
-    for (auto& opus: wake_word_opus_) {
-        ws_client_->Send(opus.iov_base, opus.iov_len, true);
-        heap_caps_free(opus.iov_base);
-    }
-    wake_word_opus_.clear();
-}
-
-void Application::AudioDetectionTask() {
-    auto chunk_size = esp_afe_sr_v1.get_fetch_chunksize(afe_detection_data_);
-    ESP_LOGI(TAG, "Audio detection task started, chunk size: %d", chunk_size);
-
-    while (true) {
-        xEventGroupWaitBits(event_group_, DETECTION_RUNNING, pdFALSE, pdTRUE, portMAX_DELAY);
-
-        auto res = esp_afe_sr_v1.fetch(afe_detection_data_);
-        if (res == nullptr || res->ret_value == ESP_FAIL) {
-            ESP_LOGE(TAG, "Error in fetch");
-            if (res != nullptr) {
-                ESP_LOGI(TAG, "Error code: %d", res->ret_value);
-            }
-            continue;;
-        }
-
-        // Store the wake word data for voice recognition, like who is speaking
-        StoreWakeWordData((uint8_t*)res->data, res->data_size);
-
-        if (res->wakeup_state == WAKENET_DETECTED) {
-            xEventGroupClearBits(event_group_, DETECTION_RUNNING);
-            SetChatState(kChatStateConnecting);
-
-            // Encode the wake word data and start websocket client at the same time
-            // They both consume a lot of time (700ms), so we can do them in parallel
-            EncodeWakeWordData();
-            StartWebSocketClient();
-
-            // Here the websocket is done, and we also wait for the wake word data to be encoded
-            xEventGroupWaitBits(event_group_, DETECT_PACKETS_ENCODED, pdTRUE, pdTRUE, portMAX_DELAY);
-
-            std::lock_guard<std::recursive_mutex> lock(mutex_);
-            if (ws_client_ && ws_client_->IsConnected()) {
-                // Send the wake word data to the server
-                SendWakeWordData();
-                // Send a ready message to indicate the server that the wake word data is sent
-                SetChatState(kChatStateWakeWordDetected);
-                opus_encoder_.ResetState();
-                // If connected, the hello message is already sent, so we can start communication
-                xEventGroupSetBits(event_group_, COMMUNICATION_RUNNING);
-                
-                ESP_LOGI(TAG, "Start communication after wake word detected");
-            } else {
-                SetChatState(kChatStateIdle);
-                xEventGroupSetBits(event_group_, DETECTION_RUNNING);
-            }
-        }
-    }
-}
-
-void Application::AudioCommunicationTask() {
-    int chunk_size = esp_afe_vc_v1.get_fetch_chunksize(afe_communication_data_);
-    ESP_LOGI(TAG, "Audio communication task started, chunk size: %d", chunk_size);
-
-    while (true) {
-        xEventGroupWaitBits(event_group_, COMMUNICATION_RUNNING, pdFALSE, pdTRUE, portMAX_DELAY);
-
-        auto res = esp_afe_vc_v1.fetch(afe_communication_data_);
-        if (res == nullptr || res->ret_value == ESP_FAIL) {
-            ESP_LOGE(TAG, "Error in fetch");
-            if (res != nullptr) {
-                ESP_LOGI(TAG, "Error code: %d", res->ret_value);
-            }
-            continue;
-        }
-
-        // Check if the websocket client is disconnected by the server
-        {
-            std::lock_guard<std::recursive_mutex> lock(mutex_);
-            if (ws_client_ == nullptr || !ws_client_->IsConnected()) {
-                if (ws_client_ != nullptr) {
-                    delete ws_client_;
-                    ws_client_ = nullptr;
-                }
-                if (audio_device_.playing()) {
-                    audio_device_.Break();
-                }
-                SetChatState(kChatStateIdle);
-                xEventGroupSetBits(event_group_, DETECTION_RUNNING);
-                xEventGroupClearBits(event_group_, COMMUNICATION_RUNNING);
-                continue;
-            }
-        }
-
-        if (chat_state_ == kChatStateListening) {
-            // Send audio data to server
-            iovec data = {
-                .iov_base = malloc(res->data_size),
-                .iov_len = (size_t)res->data_size
-            };
-            memcpy(data.iov_base, res->data, res->data_size);
-            xQueueSend(audio_encode_queue_, &data, portMAX_DELAY);
-        }
-    }
-}
-
-void Application::AudioEncodeTask() {
-    ESP_LOGI(TAG, "Audio encode task started");
-    while (true) {
-        iovec pcm;
-        xQueueReceive(audio_encode_queue_, &pcm, portMAX_DELAY);
-
-        // Encode audio data
-        opus_encoder_.Encode(pcm, [this](const iovec opus) {
-            std::lock_guard<std::recursive_mutex> lock(mutex_);
-            if (ws_client_ && ws_client_->IsConnected()) {
-                ws_client_->Send(opus.iov_base, opus.iov_len, true);
-            }
-        });
-
-        free(pcm.iov_base);
-    }
-}
-
-void Application::AudioDecodeTask() {
-    while (true) {
-        AudioPacket* packet;
-        xQueueReceive(audio_decode_queue_, &packet, portMAX_DELAY);
-
-        if (packet->type == kAudioPacketTypeData) {
-            int frame_size = opus_decode_sample_rate_ / 1000 * opus_duration_ms_;
-            packet->pcm.resize(frame_size);
-
-            int ret = opus_decode(opus_decoder_, packet->opus.data(), packet->opus.size(), packet->pcm.data(), frame_size, 0);
-            if (ret < 0) {
-                ESP_LOGE(TAG, "Failed to decode audio, error code: %d", ret);
-                delete packet;
-                continue;
-            }
-
-            if (opus_decode_sample_rate_ != CONFIG_AUDIO_OUTPUT_SAMPLE_RATE) {
-                int target_size = frame_size * CONFIG_AUDIO_OUTPUT_SAMPLE_RATE / opus_decode_sample_rate_;
-                std::vector<int16_t> resampled(target_size);
-                opus_resampler_.Process(packet->pcm.data(), frame_size, resampled.data(), target_size);
-                packet->pcm = std::move(resampled);
-            }
-        }
-
-        audio_device_.QueueAudioPacket(packet);
-    }
-}
-
-void Application::SetDecodeSampleRate(int sample_rate) {
-    if (opus_decode_sample_rate_ == sample_rate) {
-        return;
-    }
-
-    opus_decoder_destroy(opus_decoder_);
-    opus_decode_sample_rate_ = sample_rate;
-    opus_decoder_ = opus_decoder_create(opus_decode_sample_rate_, 1, NULL);
-    if (opus_decode_sample_rate_ != CONFIG_AUDIO_OUTPUT_SAMPLE_RATE) {
-        opus_resampler_.Configure(opus_decode_sample_rate_, CONFIG_AUDIO_OUTPUT_SAMPLE_RATE);
-    }
-}
-
-void Application::StartWebSocketClient() {
-    if (ws_client_ != nullptr) {
-        delete ws_client_;
-    }
-
-    std::string token = "Bearer " + std::string(CONFIG_WEBSOCKET_ACCESS_TOKEN);
-    ws_client_ = new WebSocketClient();
-    ws_client_->SetHeader("Authorization", token.c_str());
-    ws_client_->SetHeader("Device-Id", SystemInfo::GetMacAddress().c_str());
-
-    ws_client_->OnConnected([this]() {
-        ESP_LOGI(TAG, "Websocket connected");
-        
-        // Send hello message to describe the client
-        // keys: message type, version, wakeup_model, audio_params (format, sample_rate, channels)
-        std::string message = "{";
-        message += "\"type\":\"hello\", \"version\":\"1.0\",";
-        message += "\"wakeup_model\":\"" + std::string(wakenet_model_) + "\",";
-        message += "\"audio_params\":{";
-        message += "\"format\":\"opus\", \"sample_rate\":" + std::to_string(CONFIG_AUDIO_INPUT_SAMPLE_RATE) + ", \"channels\":1";
-        message += "}}";
-        ws_client_->Send(message);
-    });
-
-    ws_client_->OnData([this](const char* data, size_t len, bool binary) {
-        auto packet = new AudioPacket();
-        if (binary) {
-            auto header = (AudioDataHeader*)data;
-            packet->type = kAudioPacketTypeData;
-            packet->timestamp = ntohl(header->timestamp);
-
-            auto payload_size = ntohl(header->payload_size);
-            packet->opus.resize(payload_size);
-            memcpy(packet->opus.data(), data + sizeof(AudioDataHeader), payload_size);
-        } else {
-            // Parse JSON data
-            auto root = cJSON_Parse(data);
-            auto type = cJSON_GetObjectItem(root, "type");
-            if (type != NULL) {
-                if (strcmp(type->valuestring, "tts") == 0) {
-                    auto state = cJSON_GetObjectItem(root, "state");
-                    if (strcmp(state->valuestring, "start") == 0) {
-                        packet->type = kAudioPacketTypeStart;
-                        auto sample_rate = cJSON_GetObjectItem(root, "sample_rate");
-                        if (sample_rate != NULL) {
-                            SetDecodeSampleRate(sample_rate->valueint);
-                        }
-                    } else if (strcmp(state->valuestring, "stop") == 0) {
-                        packet->type = kAudioPacketTypeStop;
-                    } else if (strcmp(state->valuestring, "sentence_end") == 0) {
-                        packet->type = kAudioPacketTypeSentenceEnd;
-                    } else if (strcmp(state->valuestring, "sentence_start") == 0) {
-                        packet->type = kAudioPacketTypeSentenceStart;
-                        packet->text = cJSON_GetObjectItem(root, "text")->valuestring;
-                    }
-                }
-            }
-            cJSON_Delete(root);
-        }
-        xQueueSend(audio_decode_queue_, &packet, portMAX_DELAY);
-    });
-
-    ws_client_->OnError([this](int error) {
-        ESP_LOGE(TAG, "Websocket error: %d", error);
-    });
-
-    ws_client_->OnClosed([this]() {
-        ESP_LOGI(TAG, "Websocket closed");
-    });
-
-    if (!ws_client_->Connect(CONFIG_WEBSOCKET_URL)) {
-        ESP_LOGE(TAG, "Failed to connect to websocket server");
-        return;
-    }
-}

main/Application.h

@@ -1,102 +0,0 @@
-#ifndef _APPLICATION_H_
-#define _APPLICATION_H_
-
-#include "AudioDevice.h"
-#include "OpusEncoder.h"
-#include "OpusResampler.h"
-#include "WebSocketClient.h"
-#include "FirmwareUpgrade.h"
-
-#include "opus.h"
-#include "resampler_structs.h"
-#include "freertos/event_groups.h"
-#include "freertos/queue.h"
-#include "freertos/task.h"
-#include "esp_afe_sr_models.h"
-#include "esp_nsn_models.h"
-#include <mutex>
-#include <list>
-
-#define DETECTION_RUNNING 1
-#define COMMUNICATION_RUNNING 2
-#define DETECT_PACKETS_ENCODED 4
-
-
-enum ChatState {
-    kChatStateIdle,
-    kChatStateConnecting,
-    kChatStateListening,
-    kChatStateSpeaking,
-    kChatStateWakeWordDetected
-};
-
-class Application {
-public:
-    static Application& GetInstance() {
-        static Application instance;
-        return instance;
-    }
-
-    void Start();
-
-    // 删除拷贝构造函数和赋值运算符
-    Application(const Application&) = delete;
-    Application& operator=(const Application&) = delete;
-
-private:
-    Application();
-    ~Application();
-
-    AudioDevice audio_device_;
-    FirmwareUpgrade firmware_upgrade_;
-
-    std::recursive_mutex mutex_;
-    WebSocketClient* ws_client_ = nullptr;
-    esp_afe_sr_data_t* afe_detection_data_ = nullptr;
-    esp_afe_sr_data_t* afe_communication_data_ = nullptr;
-    EventGroupHandle_t event_group_;
-    char* wakenet_model_ = NULL;
-    char* nsnet_model_ = NULL;
-    volatile ChatState chat_state_ = kChatStateIdle;
-
-    // Audio encode / decode
-    TaskHandle_t audio_feed_task_ = nullptr;
-    StaticTask_t audio_encode_task_buffer_;
-    StackType_t* audio_encode_task_stack_ = nullptr;
-    QueueHandle_t audio_encode_queue_ = nullptr;
-
-    TaskHandle_t audio_decode_task_ = nullptr;
-    StaticTask_t audio_decode_task_buffer_;
-    StackType_t* audio_decode_task_stack_ = nullptr;
-    QueueHandle_t audio_decode_queue_ = nullptr;
-
-    OpusEncoder opus_encoder_;
-    OpusDecoder* opus_decoder_ = nullptr;
-
-    int opus_duration_ms_ = 60;
-    int opus_decode_sample_rate_ = CONFIG_AUDIO_OUTPUT_SAMPLE_RATE;
-    OpusResampler opus_resampler_;
-
-    TaskHandle_t wake_word_encode_task_ = nullptr;
-    StaticTask_t wake_word_encode_task_buffer_;
-    StackType_t* wake_word_encode_task_stack_ = nullptr;
-    std::list<iovec> wake_word_pcm_;
-    std::vector<iovec> wake_word_opus_;
-
-    void SetDecodeSampleRate(int sample_rate);
-    void SetChatState(ChatState state);
-    void StartDetection();
-    void StartCommunication();
-    void StartWebSocketClient();
-    void StoreWakeWordData(uint8_t* data, size_t size);
-    void EncodeWakeWordData();
-    void SendWakeWordData();
-
-    void AudioFeedTask();
-    void AudioDetectionTask();
-    void AudioCommunicationTask();
-    void AudioEncodeTask();
-    void AudioDecodeTask();
-};
-
-#endif // _APPLICATION_H_

main/AudioDevice.cc

@@ -1,236 +0,0 @@
-#include "AudioDevice.h"
-#include "esp_log.h"
-#include <cstring>
-
-#define TAG "AudioDevice"
-
-AudioDevice::AudioDevice() {
-    audio_play_queue_ = xQueueCreate(100, sizeof(AudioPacket*));
-}
-
-AudioDevice::~AudioDevice() {
-    vQueueDelete(audio_play_queue_);
-
-    if (audio_play_task_ != nullptr) {
-        vTaskDelete(audio_play_task_);
-    }
-    if (rx_handle_ != nullptr) {
-        ESP_ERROR_CHECK(i2s_channel_disable(rx_handle_));
-    }
-    if (tx_handle_ != nullptr) {
-        ESP_ERROR_CHECK(i2s_channel_disable(tx_handle_));
-    }
-}
-
-void AudioDevice::Start(int input_sample_rate, int output_sample_rate) {
-    input_sample_rate_ = input_sample_rate;
-    output_sample_rate_ = output_sample_rate;
-
-#ifdef CONFIG_AUDIO_DEVICE_I2S_SIMPLEX
-        CreateSimplexChannels();
-#else
-        CreateDuplexChannels();
-#endif
-
-    ESP_ERROR_CHECK(i2s_channel_enable(tx_handle_));
-    ESP_ERROR_CHECK(i2s_channel_enable(rx_handle_));
-
-    xTaskCreate([](void* arg) {
-        auto audio_device = (AudioDevice*)arg;
-        audio_device->AudioPlayTask();
-    }, "audio_play", 4096 * 4, this, 5, &audio_play_task_);
-}
-
-void AudioDevice::CreateDuplexChannels() {
-    duplex_ = true;
-
-    i2s_chan_config_t chan_cfg = {
-        .id = I2S_NUM_0,
-        .role = I2S_ROLE_MASTER,
-        .dma_desc_num = 6,
-        .dma_frame_num = 240,
-        .auto_clear_after_cb = false,
-        .auto_clear_before_cb = false,
-        .intr_priority = 0,
-    };
-    ESP_ERROR_CHECK(i2s_new_channel(&chan_cfg, &tx_handle_, &rx_handle_));
-
-    i2s_std_config_t std_cfg = {
-        .clk_cfg = {
-            .sample_rate_hz = (uint32_t)output_sample_rate_,
-            .clk_src = I2S_CLK_SRC_DEFAULT,
-            .ext_clk_freq_hz = 0,
-            .mclk_multiple = I2S_MCLK_MULTIPLE_256
-        },
-        .slot_cfg = {
-            .data_bit_width = I2S_DATA_BIT_WIDTH_32BIT,
-            .slot_bit_width = I2S_SLOT_BIT_WIDTH_AUTO,
-            .slot_mode = I2S_SLOT_MODE_MONO,
-            .slot_mask = I2S_STD_SLOT_LEFT,
-            .ws_width = I2S_DATA_BIT_WIDTH_32BIT,
-            .ws_pol = false,
-            .bit_shift = true,
-            .left_align = true,
-            .big_endian = false,
-            .bit_order_lsb = false
-        },
-        .gpio_cfg = {
-            .mclk = I2S_GPIO_UNUSED,
-            .bclk = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_BCLK,
-            .ws = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_WS,
-            .dout = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_DOUT,
-            .din = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_DIN,
-            .invert_flags = {
-                .mclk_inv = false,
-                .bclk_inv = false,
-                .ws_inv = false
-            }
-        }
-    };
-    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
-    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
-    ESP_LOGI(TAG, "Duplex channels created");
-}
-
-#ifdef CONFIG_AUDIO_DEVICE_I2S_SIMPLEX
-void AudioDevice::CreateSimplexChannels() {
-    // Create a new channel for speaker
-    i2s_chan_config_t chan_cfg = {
-        .id = I2S_NUM_0,
-        .role = I2S_ROLE_MASTER,
-        .dma_desc_num = 6,
-        .dma_frame_num = 240,
-        .auto_clear_after_cb = false,
-        .auto_clear_before_cb = false,
-        .intr_priority = 0,
-    };
-    ESP_ERROR_CHECK(i2s_new_channel(&chan_cfg, &tx_handle_, nullptr));
-
-    i2s_std_config_t std_cfg = {
-        .clk_cfg = {
-            .sample_rate_hz = (uint32_t)output_sample_rate_,
-            .clk_src = I2S_CLK_SRC_DEFAULT,
-            .ext_clk_freq_hz = 0,
-            .mclk_multiple = I2S_MCLK_MULTIPLE_256
-        },
-        .slot_cfg = {
-            .data_bit_width = I2S_DATA_BIT_WIDTH_32BIT,
-            .slot_bit_width = I2S_SLOT_BIT_WIDTH_AUTO,
-            .slot_mode = I2S_SLOT_MODE_MONO,
-            .slot_mask = I2S_STD_SLOT_LEFT,
-            .ws_width = I2S_DATA_BIT_WIDTH_32BIT,
-            .ws_pol = false,
-            .bit_shift = true,
-            .left_align = true,
-            .big_endian = false,
-            .bit_order_lsb = false
-        },
-        .gpio_cfg = {
-            .mclk = I2S_GPIO_UNUSED,
-            .bclk = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_BCLK,
-            .ws = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_WS,
-            .dout = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_DOUT,
-            .din = I2S_GPIO_UNUSED,
-            .invert_flags = {
-                .mclk_inv = false,
-                .bclk_inv = false,
-                .ws_inv = false
-            }
-        }
-    };
-    ESP_ERROR_CHECK(i2s_channel_init_std_mode(tx_handle_, &std_cfg));
-
-    // Create a new channel for MIC
-    chan_cfg.id = I2S_NUM_1;
-    ESP_ERROR_CHECK(i2s_new_channel(&chan_cfg, nullptr, &rx_handle_));
-    std_cfg.clk_cfg.sample_rate_hz = (uint32_t)input_sample_rate_;
-    std_cfg.gpio_cfg.bclk = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_MIC_GPIO_BCLK;
-    std_cfg.gpio_cfg.ws = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_MIC_GPIO_WS;
-    std_cfg.gpio_cfg.dout = I2S_GPIO_UNUSED;
-    std_cfg.gpio_cfg.din = (gpio_num_t)CONFIG_AUDIO_DEVICE_I2S_GPIO_DIN;
-    ESP_ERROR_CHECK(i2s_channel_init_std_mode(rx_handle_, &std_cfg));
-    ESP_LOGI(TAG, "Simplex channels created");
-}
-#endif
-
-void AudioDevice::Write(const int16_t* data, int samples) {
-    int32_t buffer[samples];
-    for (int i = 0; i < samples; i++) {
-        buffer[i] = int32_t(data[i]) << 15;
-    }
-
-    size_t bytes_written;
-    ESP_ERROR_CHECK(i2s_channel_write(tx_handle_, buffer, samples * sizeof(int32_t), &bytes_written, portMAX_DELAY));
-}
-
-int AudioDevice::Read(int16_t* dest, int samples) {
-    size_t bytes_read;
-
-    int32_t bit32_buffer_[samples];
-    if (i2s_channel_read(rx_handle_, bit32_buffer_, samples * sizeof(int32_t), &bytes_read, portMAX_DELAY) != ESP_OK) {
-        ESP_LOGE(TAG, "Read Failed!");
-        return 0;
-    }
-
-    samples = bytes_read / sizeof(int32_t);
-    for (int i = 0; i < samples; i++) {
-        int32_t value = bit32_buffer_[i] >> 12;
-        dest[i] = (value > INT16_MAX) ? INT16_MAX : (value < -INT16_MAX) ? -INT16_MAX : (int16_t)value;
-    }
-    return samples;
-}
-
-void AudioDevice::QueueAudioPacket(AudioPacket* packet) {
-    xQueueSend(audio_play_queue_, &packet, portMAX_DELAY);
-}
-
-void AudioDevice::AudioPlayTask() {
-    while (true) {
-        AudioPacket* packet;
-        xQueueReceive(audio_play_queue_, &packet, portMAX_DELAY);
-
-        switch (packet->type)
-        {
-        case kAudioPacketTypeStart:
-            playing_ = true;
-            breaked_ = false;
-            if (on_state_changed_) {
-                on_state_changed_();
-            }
-            break;
-        case kAudioPacketTypeStop:
-            playing_ = false;
-            if (on_state_changed_) {
-                on_state_changed_();
-            }
-            break;
-        case kAudioPacketTypeSentenceStart:
-            ESP_LOGI(TAG, "Playing sentence: %s", packet->text.c_str());
-            break;
-        case kAudioPacketTypeSentenceEnd:
-            if (breaked_) { // Clear the queue
-                AudioPacket* p;
-                while (xQueueReceive(audio_play_queue_, &p, 0) == pdTRUE) {
-                    delete p;
-                }
-                breaked_ = false;
-                playing_ = false;
-            }
-            break;
-        case kAudioPacketTypeData:
-            Write(packet->pcm.data(), packet->pcm.size());
-            break;
-        default:
-            ESP_LOGE(TAG, "Unknown audio packet type: %d", packet->type);
-        }
-        delete packet;
-    }
-}
-
-void AudioDevice::OnStateChanged(std::function<void()> callback) {
-    on_state_changed_ = callback;
-}
-
-void AudioDevice::Break() {
-    breaked_ = true;
-}

main/AudioDevice.h

@@ -1,76 +0,0 @@
-#ifndef _AUDIO_DEVICE_H
-#define _AUDIO_DEVICE_H
-
-#include "opus.h"
-#include "freertos/FreeRTOS.h"
-#include "freertos/queue.h"
-#include "freertos/event_groups.h"
-#include "driver/i2s_std.h"
-
-#include <vector>
-#include <string>
-#include <functional>
-
-enum AudioPacketType {
-    kAudioPacketTypeUnkonwn = 0,
-    kAudioPacketTypeStart,
-    kAudioPacketTypeStop,
-    kAudioPacketTypeData,
-    kAudioPacketTypeSentenceStart,
-    kAudioPacketTypeSentenceEnd
-};
-
-struct AudioPacket {
-    AudioPacketType type = kAudioPacketTypeUnkonwn;
-    std::string text;
-    std::vector<uint8_t> opus;
-    std::vector<int16_t> pcm;
-    uint32_t timestamp;
-};
-
-struct AudioDataHeader {
-    uint32_t version;
-    uint32_t reserved;
-    uint32_t timestamp;
-    uint32_t payload_size;
-} __attribute__((packed));
-
-class AudioDevice {
-public:
-    AudioDevice();
-    ~AudioDevice();
-
-    void Start(int input_sample_rate, int output_sample_rate);
-    int Read(int16_t* dest, int samples);
-    void Write(const int16_t* data, int samples);
-    void QueueAudioPacket(AudioPacket* packet);
-    void OnStateChanged(std::function<void()> callback);
-    void Break();
-
-    int input_sample_rate() const { return input_sample_rate_; }
-    int output_sample_rate() const { return output_sample_rate_; }
-    bool duplex() const { return duplex_; }
-    bool playing() const { return playing_; }
-
-private:
-    bool playing_ = false;
-    bool breaked_ = false;
-    bool duplex_ = false;
-    int input_sample_rate_ = 0;
-    int output_sample_rate_ = 0;
-
-    i2s_chan_handle_t tx_handle_ = nullptr;
-    i2s_chan_handle_t rx_handle_ = nullptr;
-
-    QueueHandle_t audio_play_queue_ = nullptr;
-    TaskHandle_t audio_play_task_ = nullptr;
-    
-    EventGroupHandle_t event_group_;
-    std::function<void()> on_state_changed_;
-
-    void CreateDuplexChannels();
-    void CreateSimplexChannels();
-    void AudioPlayTask();
-};
-
-#endif // _AUDIO_DEVICE_H

main/Kconfig.projbuild

@@ -1,71 +1,849 @@
 menu "Xiaozhi Assistant"
 
-config WEBSOCKET_URL
-    string "Websocket URL"
-    default "wss://"
+config OTA_URL
+    string "Default OTA URL"
+    default "https://api.tenclass.net/xiaozhi/ota/"
     help
-        Communication with the server through websocket after wake up.
+        The application will access this URL to check for new firmwares and server address.
 
-config WEBSOCKET_ACCESS_TOKEN
-    string "Websocket Access Token"
-    default ""
+choice
+    prompt "Flash Assets"
+    default FLASH_DEFAULT_ASSETS if !USE_EMOTE_MESSAGE_STYLE
+    default FLASH_EXPRESSION_ASSETS if USE_EMOTE_MESSAGE_STYLE
     help
-        Access token for websocket communication.
+        Select the assets to flash.
 
-config AUDIO_INPUT_SAMPLE_RATE
-    int "Audio Input Sample Rate"
-    default 16000
-    help
-        Audio input sample rate.
+    config FLASH_NONE_ASSETS
+        bool "Do not flash assets"
+    config FLASH_DEFAULT_ASSETS
+        bool "Flash Default Assets"
+        depends on !USE_EMOTE_MESSAGE_STYLE
+    config FLASH_CUSTOM_ASSETS
+        bool "Flash Custom Assets"
+    config FLASH_EXPRESSION_ASSETS
+        bool "Flash Emote Assets"
+        depends on USE_EMOTE_MESSAGE_STYLE
+endchoice
 
-config AUDIO_OUTPUT_SAMPLE_RATE
-    int "Audio Output Sample Rate"
-    default 24000
+config CUSTOM_ASSETS_FILE
+    depends on FLASH_CUSTOM_ASSETS
+    string "Custom Assets File"
+    default "assets.bin"
     help
-        Audio output sample rate.
+        The custom assets file to flash.
+        It can be a local file relative to the project directory or a remote url.
 
-config AUDIO_DEVICE_I2S_GPIO_BCLK
-    int "I2S GPIO BCLK"
-    default 5
+choice
+    prompt "Default Language"
+    default LANGUAGE_ZH_CN
     help
-        GPIO number of the I2S BCLK.
+        Select device display language
 
-config AUDIO_DEVICE_I2S_GPIO_WS
-    int "I2S GPIO WS"
-    default 4
-    help
-        GPIO number of the I2S WS.
+    config LANGUAGE_ZH_CN
+        bool "Chinese"
+    config LANGUAGE_ZH_TW
+        bool "Chinese Traditional"
+    config LANGUAGE_EN_US
+        bool "English"
+    config LANGUAGE_JA_JP
+        bool "Japanese"
+    config LANGUAGE_KO_KR
+        bool "Korean"
+    config LANGUAGE_VI_VN
+        bool "Vietnamese"
+    config LANGUAGE_TH_TH
+        bool "Thai"
+    config LANGUAGE_DE_DE
+        bool "German"
+    config LANGUAGE_FR_FR
+        bool "French"
+    config LANGUAGE_ES_ES
+        bool "Spanish"
+    config LANGUAGE_IT_IT
+        bool "Italian"
+    config LANGUAGE_RU_RU
+        bool "Russian"
+    config LANGUAGE_AR_SA
+        bool "Arabic"
+    config LANGUAGE_HI_IN
+        bool "Hindi"
+    config LANGUAGE_PT_PT
+        bool "Portuguese"
+    config LANGUAGE_PL_PL
+        bool "Polish"
+    config LANGUAGE_CS_CZ
+        bool "Czech"
+    config LANGUAGE_FI_FI
+        bool "Finnish"
+    config LANGUAGE_TR_TR
+        bool "Turkish"
+    config LANGUAGE_ID_ID
+        bool "Indonesian"
+    config LANGUAGE_UK_UA
+        bool "Ukrainian"
+    config LANGUAGE_RO_RO
+        bool "Romanian"
+    config LANGUAGE_BG_BG
+        bool "Bulgarian"
+    config LANGUAGE_CA_ES
+        bool "Catalan"
+    config LANGUAGE_DA_DK
+        bool "Danish"
+    config LANGUAGE_EL_GR
+        bool "Greek"
+    config LANGUAGE_FA_IR
+        bool "Persian"
+    config LANGUAGE_FIL_PH
+        bool "Filipino"
+    config LANGUAGE_HE_IL
+        bool "Hebrew"
+    config LANGUAGE_HR_HR
+        bool "Croatian"
+    config LANGUAGE_HU_HU
+        bool "Hungarian"
+    config LANGUAGE_MS_MY
+        bool "Malay"
+    config LANGUAGE_NB_NO
+        bool "Norwegian"
+    config LANGUAGE_NL_NL
+        bool "Dutch"
+    config LANGUAGE_SK_SK
+        bool "Slovak"
+    config LANGUAGE_SL_SI
+        bool "Slovenian"
+    config LANGUAGE_SV_SE
+        bool "Swedish"
+    config LANGUAGE_SR_RS
+        bool "Serbian"
+endchoice
 
-config AUDIO_DEVICE_I2S_GPIO_DOUT
-    int "I2S GPIO DOUT"
-    default 6
+choice BOARD_TYPE
+    prompt "Board Type"
+    default BOARD_TYPE_BREAD_COMPACT_WIFI
     help
-        GPIO number of the I2S DOUT.
+        Board type. 开发板类型
+    config BOARD_TYPE_BREAD_COMPACT_WIFI
+        bool "Bread Compact WiFi (面包板)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_BREAD_COMPACT_WIFI_LCD
+        bool "Bread Compact WiFi + LCD (面包板)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_BREAD_COMPACT_WIFI_CAM
+        bool "Bread Compact WiFi + LCD + Camera (面包板)"
+        depends on IDF_TARGET_ESP32S3     
+    config BOARD_TYPE_BREAD_COMPACT_ML307
+        bool "Bread Compact ML307/EC801E (面包板 4G)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_BREAD_COMPACT_NT26
+        bool "Bread Compact NT26 (面包板 4G)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_BREAD_COMPACT_ESP32
+        bool "Bread Compact ESP32 DevKit (面包板)"
+        depends on IDF_TARGET_ESP32
+    config BOARD_TYPE_BREAD_COMPACT_ESP32_LCD
+        bool "Bread Compact ESP32 DevKit + LCD (面包板)"
+        depends on IDF_TARGET_ESP32
+    config BOARD_TYPE_XMINI_C3_V3
+        bool "Xmini C3 V3"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_XMINI_C3_4G
+        bool "Xmini C3 4G"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_XMINI_C3
+        bool "Xmini C3"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_ESP_KORVO2_V3
+        bool "Espressif Korvo2 V3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_KORVO2_V3_RNDIS
+        bool "Espressif Korvo2 V3 RNDIS"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_SPARKBOT
+        bool "Espressif SparkBot"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_SENSAIRSHUTTLE
+        bool "Espressif ESP-SensairShuttle"
+        depends on IDF_TARGET_ESP32C5
+    config BOARD_TYPE_ESP_SPOT_S3
+        bool "Espressif Spot-S3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_SPOT_C5
+        bool "Espressif Spot-C5"
+        depends on IDF_TARGET_ESP32C5
+    config BOARD_TYPE_ESP_HI
+        bool "Espressif ESP-HI"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_ESP_BOX_3
+        bool "Espressif ESP-BOX-3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_BOX
+        bool "Espressif ESP-BOX"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_BOX_LITE
+        bool "Espressif ESP-BOX-Lite"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_P4_FUNCTION_EV_BOARD
+        bool "Espressif ESP-P4-Function-EV-Board"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_ECHOEAR
+        bool "EchoEar"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_KEVIN_BOX_2
+        bool "Kevin Box 2"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_KEVIN_C3
+        bool "Kevin C3"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_KEVIN_SP_V3_DEV
+        bool "Kevin SP V3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_KEVIN_SP_V4_DEV
+        bool "Kevin SP V4"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_KEVIN_YUYING_313LCD
+        bool "鱼鹰科技 3.13LCD"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_CGC
+        bool "CGC"
+        depends on IDF_TARGET_ESP32
+    config BOARD_TYPE_CGC_144
+        bool "CGC 144"
+        depends on IDF_TARGET_ESP32
+    config BOARD_TYPE_LICHUANG_DEV_S3
+        bool "立创·实战派 ESP32-S3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LICHUANG_DEV_C3
+        bool "立创·实战派 ESP32-C3"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_DF_K10
+        bool "DFRobot 行空板 k10"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_DF_S3_AI_CAM
+        bool "DFRobot ESP32-S3 AI智能摄像头模块"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MAGICLICK_S3_2P4
+        bool "神奇按钮 Magiclick_2.4"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MAGICLICK_S3_2P5
+        bool "神奇按钮 Magiclick_2.5"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MAGICLICK_C3
+        bool "神奇按钮 Magiclick_C3"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_MAGICLICK_C3_V2
+        bool "神奇按钮 Magiclick_C3_v2"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_M5STACK_CORE_S3
+        bool "M5Stack CoreS3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_CORE_TAB5
+        bool "M5Stack Tab5"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_M5STACK_ATOM_S3_ECHO_BASE
+        bool "M5Stack AtomS3 + Echo Base"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_ATOM_S3R_ECHO_BASE
+        bool "M5Stack AtomS3R + Echo Base"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_ATOM_S3R_CAM_M12_ECHO_BASE
+        bool "M5Stack AtomS3R CAM/M12 + Echo Base"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_ATOM_ECHOS3R
+        bool "M5Stack AtomEchoS3R"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_CARDPUTER_ADV
+        bool "M5Stack Cardputer Adv"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_M5STACK_ATOM_MATRIX_ECHO_BASE
+        bool "M5Stack AtomMatrix + Echo Base"
+        depends on IDF_TARGET_ESP32
+    config BOARD_TYPE_WAVESHARE_S3_AUDIO_BOARD
+        bool "Waveshare ESP32-S3-Audio-Board"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_8
+        bool "Waveshare ESP32-S3-Touch-AMOLED-1.8"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_2_06
+        bool "Waveshare ESP32-S3-Touch-AMOLED-2.06"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_2_06
+        bool "Waveshare ESP32-C6-Touch-AMOLED-2.06"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_75
+        bool "Waveshare ESP32-S3-Touch-AMOLED-1.75"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_83
+        bool "Waveshare ESP32-S3-Touch-LCD-1.83"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4B
+        bool "Waveshare ESP32-S3-Touch-LCD-4B"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4_3C
+        bool "Waveshare ESP32-S3-Touch-LCD-4.3C"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_85C
+        bool "Waveshare ESP32-S3-Touch-LCD-1.85C"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_85
+        bool "Waveshare ESP32-S3-Touch-LCD-1.85"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_46
+        bool "Waveshare ESP32-S3-Touch-LCD-1.46"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_C6_LCD_1_69
+        bool "Waveshare ESP32-C6-LCD-1.69"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_LCD_1_83
+        bool "Waveshare ESP32-C6-Touch-LCD-1.83"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_43
+        bool "Waveshare ESP32-C6-Touch-AMOLOED-1.43"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_32
+        bool "Waveshare ESP32-C6-Touch-AMOLOED-1.32"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_C6_TOUCH_AMOLED_1_8
+        bool "Waveshare ESP32-C6-Touch-AMOLED-1.8"
+        depends on IDF_TARGET_ESP32C6
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_32
+        bool "Waveshare ESP32-S3-Touch-AMOLOED-1.32"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_49
+        bool "Waveshare ESP32-S3-Touch-LCD-3.49"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_5
+        bool "Waveshare ESP32-S3-Touch-LCD-3.5"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_ePaper_1_54
+        bool "Waveshare ESP32-S3-ePaper-1.54"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_RLCD_4_2
+        bool "Waveshare ESP32-S3-RLCD-4.2"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_5B
+        bool "Waveshare ESP32-S3-Touch-LCD-3.5B"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WAVESHARE_P4_NANO
+        bool "Waveshare ESP32-P4-NANO"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_4B
+        bool "Waveshare ESP32-P4-WIFI6-Touch-LCD-4B"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_7B
+        bool "Waveshare ESP32-P4-WIFI6-Touch-LCD-7B"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_XC
+        bool "Waveshare ESP32-P4-WIFI6-Touch-LCD-3.4C or ESP32-P4-WIFI6-Touch-LCD-4C"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_TUDOUZI
+        bool "土豆子"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_CIRCLE_S3
+        bool "LILYGO T-Circle-S3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_CAMERAPLUS_S3_V1_0_V1_1
+        bool "LILYGO T-CameraPlus-S3_V1_0_V1_1"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_CAMERAPLUS_S3_V1_2
+        bool "LILYGO T-CameraPlus-S3_V1_2"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_DISPLAY_S3_PRO_MVSRLORA
+        bool "LILYGO T-Display-S3-Pro-MVSRLora"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_DISPLAY_S3_PRO_MVSRLORA_NO_BATTERY
+        bool "LILYGO T-Display-S3-Pro-MVSRLora_No_Battery"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LILYGO_T_DISPLAY_P4
+        bool "LILYGO T-Display-P4"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_MOVECALL_MOJI_ESP32S3
+        bool "Movecall Moji 小智AI衍生版"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MOVECALL_MOJI2_ESP32C5
+        bool "Movecall Moji2.0 小智AI衍生版"
+        depends on IDF_TARGET_ESP32C5
+    config BOARD_TYPE_MOVECALL_CUICAN_ESP32S3
+        bool "Movecall CuiCan 璀璨·AI吊坠"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3
+        bool "正点原子DNESP32S3开发板"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3_BOX
+        bool "正点原子DNESP32S3-BOX"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3_BOX0
+        bool "正点原子DNESP32S3-BOX0"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3_BOX2_WIFI
+        bool "正点原子DNESP32S3-BOX2-WIFI"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3_BOX2_4G
+        bool "正点原子DNESP32S3-BOX2-4G"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3M_WIFI
+        bool "正点原子DNESP32S3M-WIFI"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ATK_DNESP32S3M_4G
+        bool "正点原子DNESP32S3M-4G"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_DU_CHATX
+        bool "嘟嘟开发板CHATX(wifi)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_TAIJI_PI_S3
+        bool "太极小派esp32s3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_0_85TFT_WIFI
+        bool "无名科技星智0.85(WIFI)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_0_85TFT_ML307
+        bool "无名科技星智0.85(ML307)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_0_96OLED_WIFI
+        bool "无名科技星智0.96(WIFI)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_0_96OLED_ML307
+        bool "无名科技星智0.96(ML307)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_1_54TFT_WIFI
+        bool "无名科技星智1.54(WIFI)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_CUBE_1_54TFT_ML307
+        bool "无名科技星智1.54(ML307)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_XINGZHI_METAL_1_54_WIFI
+        bool "无名科技星智1.54 METAL(wifi)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_SEEED_STUDIO_SENSECAP_WATCHER
+        bool "Seeed Studio SenseCAP Watcher"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_DOIT_S3_AIBOX
+        bool "四博智联AI陪伴盒子"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MIXGO_NOVA
+        bool "元控·青春"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_GENJUTECH_S3_1_54TFT
+        bool "亘具科技1.54(s3)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_S3_LCD_EV_Board
+        bool "乐鑫ESP S3 LCD EV Board开发板"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ESP_S3_LCD_EV_Board_2
+        bool "乐鑫ESP S3 LCD EV Board 2开发板"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_1_54TFT_WIFI
+        bool "征辰科技1.54(WIFI)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_1_54TFT_ML307
+        bool "征辰科技1.54(ML307)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_CAM
+        bool "征辰科技AI Camera"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ZHENGCHEN_CAM_ML307
+        bool "征辰科技AI Camera(ML307)"
+	depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_MINSI_K08_DUAL
+        bool "敏思科技K08(DUAL)"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_SPOTPEAR_ESP32_S3_1_54_MUMA
+        bool "Spotpear ESP32-S3-1.54-MUMA"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_SPOTPEAR_ESP32_S3_1_28_BOX
+        bool "Spotpear ESP32-S3-1.28-BOX"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_OTTO_ROBOT
+        bool "ottoRobot"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_ELECTRON_BOT
+        bool "electronBot"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_JIUCHUAN
+        bool "九川智能"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LABPLUS_MPYTHON_V3
+        bool "labplus mpython_v3 board"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_LABPLUS_LEDONG_V2
+        bool "labplus ledong_v2 board"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_SURFER_C3_1_14TFT
+        bool "Surfer-C3-1.14TFT"
+        depends on IDF_TARGET_ESP32C3
+    config BOARD_TYPE_YUNLIAO_S3
+        bool "小智云聊-S3"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_WIRELESS_TAG_WTP4C5MP07S
+        bool "Wireless-Tag WTP4C5MP07S"
+        depends on IDF_TARGET_ESP32P4
+    config BOARD_TYPE_AIPI_LITE
+        bool "AIPI-Lite"
+        depends on IDF_TARGET_ESP32S3
+    config BOARD_TYPE_HU_087
+        bool "HU-087"
+        depends on IDF_TARGET_ESP32S3
+endchoice
 
-config AUDIO_DEVICE_I2S_GPIO_DIN
-    int "I2S GPIO DIN"
-    default 3
+choice
+    depends on BOARD_TYPE_LILYGO_T_DISPLAY_P4
+    prompt "Select the screen type"
+    default SCREEN_TYPE_HI8561
+        config SCREEN_TYPE_HI8561
+            bool "HI8561"
+        config SCREEN_TYPE_RM69A10
+            bool "RM69A10"
+endchoice
+
+choice
+    depends on BOARD_TYPE_LILYGO_T_DISPLAY_P4
+    prompt "Select the color format of the screen"
+    default SCREEN_PIXEL_FORMAT_RGB565
+        config SCREEN_PIXEL_FORMAT_RGB565
+            bool "RGB565"
+        config SCREEN_PIXEL_FORMAT_RGB888
+            bool "RGB888"
+endchoice
+
+choice ESP_S3_LCD_EV_Board_Version_TYPE
+    depends on BOARD_TYPE_ESP_S3_LCD_EV_Board
+    prompt "EV_BOARD Type"
+    default ESP_S3_LCD_EV_Board_1p4
+    config ESP_S3_LCD_EV_Board_1p4
+        bool "乐鑫ESP32_S3_LCD_EV_Board-MB_V1.4"
+    config ESP_S3_LCD_EV_Board_1p5
+        bool "乐鑫ESP32_S3_LCD_EV_Board-MB_V1.5"
+endchoice
+
+choice DISPLAY_OLED_TYPE
+    depends on BOARD_TYPE_BREAD_COMPACT_WIFI || BOARD_TYPE_BREAD_COMPACT_ML307 || BOARD_TYPE_BREAD_COMPACT_NT26 || BOARD_TYPE_BREAD_COMPACT_ESP32 || BOARD_TYPE_HU_087
+    prompt "OLED Type"
+    default OLED_SSD1306_128X32
     help
-        GPIO number of the I2S DIN.
-    
-config AUDIO_DEVICE_I2S_SIMPLEX
-    bool "I2S Simplex"
+        OLED Monochrome Display Type
+    config OLED_SSD1306_128X32
+        bool "SSD1306 128*32"
+    config OLED_SSD1306_128X64
+        bool "SSD1306 128*64"
+    config OLED_SH1106_128X64
+        bool "SH1106 128*64"
+endchoice
+
+choice DISPLAY_LCD_TYPE
+    depends on BOARD_TYPE_BREAD_COMPACT_WIFI_LCD || BOARD_TYPE_BREAD_COMPACT_ESP32_LCD || BOARD_TYPE_CGC || BOARD_TYPE_WAVESHARE_P4_NANO || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_XC || BOARD_TYPE_BREAD_COMPACT_WIFI_CAM
+    prompt "LCD Type"
+    default LCD_ST7789_240X320
+    help
+        LCD Display Type
+    config LCD_ST7789_240X320
+        bool "ST7789 240*320, IPS"
+    config LCD_ST7789_240X320_NO_IPS
+        bool "ST7789 240*320, Non-IPS"
+    config LCD_ST7789_170X320
+        bool "ST7789 170*320"
+    config LCD_ST7789_172X320
+        bool "ST7789 172*320"
+    config LCD_ST7789_240X280
+        bool "ST7789 240*280"
+    config LCD_ST7789_240X240
+        bool "ST7789 240*240"
+    config LCD_ST7789_240X240_7PIN
+        bool "ST7789 240*240, 7PIN"
+    config LCD_ST7789_240X135
+        bool "ST7789 240*135"
+    config LCD_ST7735_128X160
+        bool "ST7735 128*160"
+    config LCD_ST7735_128X128
+        bool "ST7735 128*128"
+    config LCD_ST7796_320X480
+        bool "ST7796 320*480 IPS"
+    config LCD_ST7796_320X480_NO_IPS
+        bool "ST7796 320*480, Non-IPS"
+    config LCD_ILI9341_240X320
+        bool "ILI9341 240*320"
+    config LCD_ILI9341_240X320_NO_IPS
+        bool "ILI9341 240*320, Non-IPS"
+    config LCD_GC9A01_240X240
+        bool "GC9A01 240*240 Circle"
+    config LCD_TYPE_800_1280_10_1_INCH
+        bool "Waveshare 101M-8001280-IPS-CT-K Display"
+    config LCD_TYPE_800_1280_10_1_INCH_A
+        bool "Waveshare 10.1-DSI-TOUCH-A Display"
+    config LCD_TYPE_800_800_3_4_INCH
+        bool "Waveshare ESP32-P4-WIFI6-Touch-LCD-3.4C with 800*800 3.4inch round display"
+    config LCD_TYPE_720_720_4_INCH
+        bool "Waveshare ESP32-P4-WIFI6-Touch-LCD-4C with 720*720 4inch round display"
+    config LCD_CUSTOM
+        bool "Custom LCD (自定义屏幕参数)"
+endchoice
+
+choice DISPLAY_ESP32S3_KORVO2_V3
+    depends on BOARD_TYPE_ESP_KORVO2_V3 || BOARD_TYPE_ESP_KORVO2_V3_RNDIS
+    prompt "ESP32S3_KORVO2_V3 LCD Type"
+    default ESP32S3_KORVO2_V3_LCD_ST7789
+    help
+        LCD Display Type
+    config ESP32S3_KORVO2_V3_LCD_ST7789
+        bool "ST7789 240*280"
+    config ESP32S3_KORVO2_V3_LCD_ILI9341
+        bool "ILI9341 240*320"
+endchoice
+
+choice DISPLAY_ESP32S3_AUDIO_BOARD
+    depends on BOARD_TYPE_WAVESHARE_S3_AUDIO_BOARD
+    prompt "ESP32S3_AUDIO_BOARD LCD Type"
+    default AUDIO_BOARD_LCD_JD9853
+    help
+        LCD Display Type
+    config AUDIO_BOARD_LCD_JD9853
+        bool "JD9853 320*172"
+    config AUDIO_BOARD_LCD_ST7789
+        bool "ST7789 240*320"
+endchoice
+
+choice DISPLAY_STYLE
+    prompt "Select display style"
+    default USE_DEFAULT_MESSAGE_STYLE
+    help
+        Select display style for Xiaozhi device
+
+    config USE_DEFAULT_MESSAGE_STYLE
+        bool "Enable default message style"
+
+    config USE_WECHAT_MESSAGE_STYLE
+        bool "Enable WeChat Message Style"
+
+    config USE_EMOTE_MESSAGE_STYLE
+        bool "Emote animation style"
+        depends on BOARD_TYPE_ESP_BOX || BOARD_TYPE_ESP_BOX_3 \
+            || BOARD_TYPE_ECHOEAR || BOARD_TYPE_LICHUANG_DEV_S3 \
+            || BOARD_TYPE_ESP_SENSAIRSHUTTLE
+endchoice
+
+choice WAKE_WORD_TYPE
+    prompt "Wake Word Implementation Type"
+    default USE_AFE_WAKE_WORD if (IDF_TARGET_ESP32S3 || IDF_TARGET_ESP32P4) && SPIRAM
+    default WAKE_WORD_DISABLED
+    help
+        Choose the type of wake word implementation to use
+
+    config WAKE_WORD_DISABLED
+        bool "Disabled"
+        help
+            Disable wake word detection
+
+    config USE_ESP_WAKE_WORD
+        bool "Wakenet model without AFE"
+        depends on IDF_TARGET_ESP32C3 || IDF_TARGET_ESP32C5 || IDF_TARGET_ESP32C6 || (IDF_TARGET_ESP32 && SPIRAM)
+        help
+            Support ESP32 C3、ESP32 C5 与 ESP32 C6, and (ESP32 with PSRAM)
+
+    config USE_AFE_WAKE_WORD
+        bool "Wakenet model with AFE"
+        depends on (IDF_TARGET_ESP32S3 || IDF_TARGET_ESP32P4) && SPIRAM
+        help
+            Support AEC if available, requires ESP32 S3 and PSRAM
+
+    config USE_CUSTOM_WAKE_WORD
+        bool "Multinet model (Custom Wake Word)"
+        depends on (IDF_TARGET_ESP32S3 || IDF_TARGET_ESP32P4) && SPIRAM
+        help
+            Requires ESP32 S3 and PSRAM
+
+endchoice
+
+config CUSTOM_WAKE_WORD
+    string "Custom Wake Word"
+    default "xiao tu dou"
+    depends on USE_CUSTOM_WAKE_WORD
+    help
+        Custom Wake Word, use pinyin for Chinese, separated by spaces
+
+config CUSTOM_WAKE_WORD_DISPLAY
+    string "Custom Wake Word Display"
+    default "小土豆"
+    depends on USE_CUSTOM_WAKE_WORD
+    help
+        Greeting sent to the server after wake word detection
+
+config CUSTOM_WAKE_WORD_THRESHOLD
+    int "Custom Wake Word Threshold (%)"
+    default 20
+    range 1 99
+    depends on USE_CUSTOM_WAKE_WORD
+    help
+        Custom Wake Word Threshold, range 1-99, the smaller the more sensitive, default 20
+
+config SEND_WAKE_WORD_DATA
+    bool "Send Wake Word Data"
+    default y
+    depends on USE_AFE_WAKE_WORD || USE_CUSTOM_WAKE_WORD
+    help
+        Send wake word data to the server as the first message of the conversation and wait for response
+
+config USE_AUDIO_PROCESSOR
+    bool "Enable Audio Noise Reduction"
+    default y
+    depends on (IDF_TARGET_ESP32S3 || IDF_TARGET_ESP32P4) && SPIRAM
+    help
+        Requires ESP32 S3 and PSRAM
+
+config USE_DEVICE_AEC
+    bool "Enable Device-Side AEC"
+    default n
+        depends on USE_AUDIO_PROCESSOR && (BOARD_TYPE_ESP_BOX_3 || BOARD_TYPE_ESP_BOX || BOARD_TYPE_ESP_BOX_LITE \
+        || BOARD_TYPE_LICHUANG_DEV_S3 || BOARD_TYPE_ESP_KORVO2_V3 || BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_1_75 || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_1_83\
+        || BOARD_TYPE_WAVESHARE_S3_TOUCH_AMOLED_2_06 || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4B || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_4B || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_7B \
+        || BOARD_TYPE_WAVESHARE_P4_WIFI6_TOUCH_LCD_XC || BOARD_TYPE_ESP_S3_LCD_EV_Board_2 || BOARD_TYPE_YUNLIAO_S3 \
+        || BOARD_TYPE_ECHOEAR || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_3_49 || BOARD_TYPE_WAVESHARE_S3_RLCD_4_2 || BOARD_TYPE_ZHENGCHEN_CAM || BOARD_TYPE_ZHENGCHEN_CAM_ML307 \
+        || BOARD_TYPE_WAVESHARE_S3_TOUCH_LCD_4_3C)
+    help
+        To work properly, device-side AEC requires a clean output reference path from the speaker signal and physical acoustic isolation between the microphone and speaker.
+
+config USE_SERVER_AEC
+    bool "Enable Server-Side AEC (Unstable)"
+    default n
+    depends on USE_AUDIO_PROCESSOR
+    help
+        To work perperly, server-side AEC requires server support
+
+config USE_AUDIO_DEBUGGER
+    bool "Enable Audio Debugger"
+    default n
+    help
+        Enable audio debugger, send audio data through UDP to the host machine
+
+menu "WiFi Configuration Method"
+    help
+        WiFi Configuration Method Selection
+    config USE_HOTSPOT_WIFI_PROVISIONING
+        bool "Hotspot"
+        default y
+        help
+            Use WiFi Hotspot to transmit WiFi configuration data
+    config USE_ACOUSTIC_WIFI_PROVISIONING
+        bool "Acoustic"
+        help
+            Use audio signal to transmit WiFi configuration data
+
+    config USE_ESP_BLUFI_WIFI_PROVISIONING
+        bool "Esp Blufi"
+        help
+            Use esp blufi protocol to transmit WiFi configuration data
+        select BT_ENABLED
+        select BT_BLE_42_FEATURES_SUPPORTED
+        select BT_BLE_BLUFI_ENABLE
+        select MBEDTLS_DHM_C
+endmenu
+
+config AUDIO_DEBUG_UDP_SERVER
+    string "Audio Debug UDP Server Address"
+    default "192.168.2.100:8000"
+    depends on USE_AUDIO_DEBUGGER
+    help
+        UDP server address, format: IP:PORT, used to receive audio debugging data
+
+config RECEIVE_CUSTOM_MESSAGE
+    bool "Enable Custom Message Reception"
+    default n
+    help
+        Enable custom message reception, allow the device to receive custom messages from the server (preferably through the MQTT protocol)
+
+menu "Camera Configuration"
+    depends on !IDF_TARGET_ESP32
+
+    comment "Warning: Please read the help text before modifying these settings."
+
+    config XIAOZHI_CAMERA_ALLOW_JPEG_INPUT
+        bool "Allow JPEG Input"
+        default n
+        help
+            Allow JPEG Input format for the camera.
+
+            This option may need to be enabled when using a USB camera.
+
+            Not currently supported when used simultaneously with XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE.
+
+    config XIAOZHI_ENABLE_HARDWARE_JPEG_ENCODER
+        bool "Enable Hardware JPEG Encoder"
+        default y
+        depends on SOC_JPEG_ENCODE_SUPPORTED
+        help
+            Use hardware JPEG encoder on ESP32-P4 to encode image to JPEG.
+            See https://docs.espressif.com/projects/esp-idf/en/stable/esp32p4/api-reference/peripherals/jpeg.html for more details.
+
+    config XIAOZHI_ENABLE_HARDWARE_JPEG_DECODER
+        bool "Enable Hardware JPEG Decoder"
+        default n
+        depends on SOC_JPEG_DECODE_SUPPORTED && XIAOZHI_CAMERA_ALLOW_JPEG_INPUT
+        help
+            Use hardware JPEG decoder on ESP32-P4 to decode JPEG to image.
+            See https://docs.espressif.com/projects/esp-idf/en/stable/esp32p4/api-reference/peripherals/jpeg.html for more details.
+
+    config XIAOZHI_ENABLE_CAMERA_DEBUG_MODE
+        bool "Enable Camera Debug Mode"
+        default n
+        help
+            Enable camera debug mode, print camera debug information to the console.
+            Only works on boards that support camera.
+
+    config XIAOZHI_ENABLE_CAMERA_ENDIANNESS_SWAP
+        bool "Enable software camera buffer endianness swapping"
+        default n
+        depends on !CAMERA_SENSOR_SWAP_PIXEL_BYTE_ORDER
+        help
+            This option treats the camera buffer as a uint16_t[] array and performs byte-swapping (endianness conversion) on each element.
+
+            Should only be modified by development board integration engineers.
+
+            **Incorrect usage may result in incorrect image colors!**
+
+            ATTENTION: If the option CAMERA_SENSOR_SWAP_PIXEL_BYTE_ORDER is available for your sensor, please use that instead.
+
+    menuconfig XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
+        bool "Enable Camera Image Rotation"
+        default n
+        depends on !XIAOZHI_CAMERA_ALLOW_JPEG_INPUT
+        help
+            Enable camera image rotation, rotate the camera image to the correct orientation.
+            - On ESP32-P4, rotation is handled by PPA hardware.
+            - On other chips, rotation is done in software with performance cost.
+            - For 180° rotation, use HFlip + VFlip instead of this option.
+
+            Not currently supported when used simultaneously with XIAOZHI_CAMERA_ALLOW_JPEG_INPUT.
+
+    if XIAOZHI_ENABLE_ROTATE_CAMERA_IMAGE
+        choice XIAOZHI_CAMERA_IMAGE_ROTATION_ANGLE
+            prompt "Camera Image Rotation Angle (clockwise)"
+            default XIAOZHI_CAMERA_IMAGE_ROTATION_ANGLE_90
+            help
+                Camera image rotation angle.
+            config XIAOZHI_CAMERA_IMAGE_ROTATION_ANGLE_90
+                bool "90°"
+            config XIAOZHI_CAMERA_IMAGE_ROTATION_ANGLE_270
+                bool "270°"
+            comment "For 180° rotation, use HFlip + VFlip instead of this option"
+        endchoice
+    endif
+endmenu
+
+menu "TAIJIPAI_S3_CONFIG"
+    depends on BOARD_TYPE_TAIJI_PI_S3
+    choice I2S_TYPE_TAIJIPI_S3
+        prompt "taiji-pi-S3 I2S Type"
+        default TAIJIPAI_I2S_TYPE_STD
+        help
+            I2S 类型选择
+        config TAIJIPAI_I2S_TYPE_STD
+            bool "I2S Type STD"
+        config TAIJIPAI_I2S_TYPE_PDM
+            bool "I2S Type PDM"
+    endchoice
+
+    config I2S_USE_2SLOT
+    bool "Enable I2S 2 Slot"
     default y
     help
-        Enable I2S Simplex mode.
-    
-config AUDIO_DEVICE_I2S_MIC_GPIO_BCLK
-    int "I2S MIC GPIO BCLK"
-    default 11
-    depends on AUDIO_DEVICE_I2S_SIMPLEX
-    help
-        GPIO number of the I2S MIC BCLK.
-    
-config AUDIO_DEVICE_I2S_MIC_GPIO_WS
-    int "I2S MIC GPIO WS"
-    default 10
-    depends on AUDIO_DEVICE_I2S_SIMPLEX
-    help
-        GPIO number of the I2S MIC WS.
+        启动双声道
+endmenu
 
 endmenu

main/application.h

@@ -0,0 +1,188 @@
+#ifndef _APPLICATION_H_
+#define _APPLICATION_H_
+
+#include <freertos/FreeRTOS.h>
+#include <freertos/event_groups.h>
+#include <freertos/task.h>
+#include <esp_timer.h>
+
+#include <string>
+#include <mutex>
+#include <deque>
+#include <memory>
+
+#include "protocol.h"
+#include "ota.h"
+#include "audio_service.h"
+#include "device_state.h"
+#include "device_state_machine.h"
+
+// Main event bits
+#define MAIN_EVENT_SCHEDULE             (1 << 0)
+#define MAIN_EVENT_SEND_AUDIO           (1 << 1)
+#define MAIN_EVENT_WAKE_WORD_DETECTED   (1 << 2)
+#define MAIN_EVENT_VAD_CHANGE           (1 << 3)
+#define MAIN_EVENT_ERROR                (1 << 4)
+#define MAIN_EVENT_ACTIVATION_DONE      (1 << 5)
+#define MAIN_EVENT_CLOCK_TICK           (1 << 6)
+#define MAIN_EVENT_NETWORK_CONNECTED    (1 << 7)
+#define MAIN_EVENT_NETWORK_DISCONNECTED (1 << 8)
+#define MAIN_EVENT_TOGGLE_CHAT          (1 << 9)
+#define MAIN_EVENT_START_LISTENING      (1 << 10)
+#define MAIN_EVENT_STOP_LISTENING       (1 << 11)
+#define MAIN_EVENT_STATE_CHANGED        (1 << 12)
+
+
+enum AecMode {
+    kAecOff,
+    kAecOnDeviceSide,
+    kAecOnServerSide,
+};
+
+class Application {
+public:
+    static Application& GetInstance() {
+        static Application instance;
+        return instance;
+    }
+    // Delete copy constructor and assignment operator
+    Application(const Application&) = delete;
+    Application& operator=(const Application&) = delete;
+
+    /**
+     * Initialize the application
+     * This sets up display, audio, network callbacks, etc.
+     * Network connection starts asynchronously.
+     */
+    void Initialize();
+
+    /**
+     * Run the main event loop
+     * This function runs in the main task and never returns.
+     * It handles all events including network, state changes, and user interactions.
+     */
+    void Run();
+
+    DeviceState GetDeviceState() const { return state_machine_.GetState(); }
+    bool IsVoiceDetected() const { return audio_service_.IsVoiceDetected(); }
+    
+    /**
+     * Request state transition
+     * Returns true if transition was successful
+     */
+    bool SetDeviceState(DeviceState state);
+
+    /**
+     * Schedule a callback to be executed in the main task
+     */
+    void Schedule(std::function<void()>&& callback);
+
+    /**
+     * Alert with status, message, emotion and optional sound
+     */
+    void Alert(const char* status, const char* message, const char* emotion = "", const std::string_view& sound = "");
+    void DismissAlert();
+
+    void AbortSpeaking(AbortReason reason);
+
+    /**
+     * Toggle chat state (event-based, thread-safe)
+     * Sends MAIN_EVENT_TOGGLE_CHAT to be handled in Run()
+     */
+    void ToggleChatState();
+
+    /**
+     * Start listening (event-based, thread-safe)
+     * Sends MAIN_EVENT_START_LISTENING to be handled in Run()
+     */
+    void StartListening();
+
+    /**
+     * Stop listening (event-based, thread-safe)
+     * Sends MAIN_EVENT_STOP_LISTENING to be handled in Run()
+     */
+    void StopListening();
+
+    void Reboot();
+    void WakeWordInvoke(const std::string& wake_word);
+    bool UpgradeFirmware(const std::string& url, const std::string& version = "");
+    bool CanEnterSleepMode();
+    void SendMcpMessage(const std::string& payload);
+    void SetAecMode(AecMode mode);
+    AecMode GetAecMode() const { return aec_mode_; }
+    void PlaySound(const std::string_view& sound);
+    AudioService& GetAudioService() { return audio_service_; }
+    
+    /**
+     * Reset protocol resources (thread-safe)
+     * Can be called from any task to release resources allocated after network connected
+     * This includes closing audio channel, resetting protocol and ota objects
+     */
+    void ResetProtocol();
+
+private:
+    Application();
+    ~Application();
+
+    std::mutex mutex_;
+    std::deque<std::function<void()>> main_tasks_;
+    std::unique_ptr<Protocol> protocol_;
+    EventGroupHandle_t event_group_ = nullptr;
+    esp_timer_handle_t clock_timer_handle_ = nullptr;
+    DeviceStateMachine state_machine_;
+    ListeningMode listening_mode_ = kListeningModeAutoStop;
+    AecMode aec_mode_ = kAecOff;
+    std::string last_error_message_;
+    AudioService audio_service_;
+    std::unique_ptr<Ota> ota_;
+
+    bool has_server_time_ = false;
+    bool aborted_ = false;
+    bool assets_version_checked_ = false;
+    bool play_popup_on_listening_ = false;  // Flag to play popup sound after state changes to listening
+    int clock_ticks_ = 0;
+    TaskHandle_t activation_task_handle_ = nullptr;
+
+
+    // Event handlers
+    void HandleStateChangedEvent();
+    void HandleToggleChatEvent();
+    void HandleStartListeningEvent();
+    void HandleStopListeningEvent();
+    void HandleNetworkConnectedEvent();
+    void HandleNetworkDisconnectedEvent();
+    void HandleActivationDoneEvent();
+    void HandleWakeWordDetectedEvent();
+    void ContinueOpenAudioChannel(ListeningMode mode);
+    void ContinueWakeWordInvoke(const std::string& wake_word);
+
+    // Activation task (runs in background)
+    void ActivationTask();
+
+    // Helper methods
+    void CheckAssetsVersion();
+    void CheckNewVersion();
+    void InitializeProtocol();
+    void ShowActivationCode(const std::string& code, const std::string& message);
+    void SetListeningMode(ListeningMode mode);
+    
+    // State change handler called by state machine
+    void OnStateChanged(DeviceState old_state, DeviceState new_state);
+};
+
+
+class TaskPriorityReset {
+public:
+    TaskPriorityReset(BaseType_t priority) {
+        original_priority_ = uxTaskPriorityGet(NULL);
+        vTaskPrioritySet(NULL, priority);
+    }
+    ~TaskPriorityReset() {
+        vTaskPrioritySet(NULL, original_priority_);
+    }
+
+private:
+    BaseType_t original_priority_;
+};
+
+#endif // _APPLICATION_H_

main/assets.cc

@@ -0,0 +1,560 @@
+#include "assets.h"
+#include "board.h"
+#include "display.h"
+#include "application.h"
+#include "lvgl_theme.h"
+#include "emote_display.h"
+#include "expression_emote.h"
+#if HAVE_LVGL
+#include "display/lcd_display.h"
+#include <spi_flash_mmap.h>
+#endif
+
+#include <esp_log.h>
+#include <esp_timer.h>
+#include <esp_heap_caps.h>
+#include <cbin_font.h>
+
+
+#define TAG "Assets"
+#define PARTITION_LABEL "assets"
+
+struct mmap_assets_table {
+    char asset_name[32];          /*!< Name of the asset */
+    uint32_t asset_size;          /*!< Size of the asset */
+    uint32_t asset_offset;        /*!< Offset of the asset */
+    uint16_t asset_width;         /*!< Width of the asset */
+    uint16_t asset_height;        /*!< Height of the asset */
+};
+
+Assets::Assets() {
+#if HAVE_LVGL
+    strategy_ = std::make_unique<Assets::LvglStrategy>();
+#else
+    strategy_ = std::make_unique<Assets::EmoteStrategy>();
+#endif
+    // Initialize the partition
+    InitializePartition();
+}
+
+Assets::~Assets() {
+    UnApplyPartition();
+}
+
+bool Assets::FindPartition(Assets* assets) {
+    assets->partition_ = esp_partition_find_first(ESP_PARTITION_TYPE_ANY, ESP_PARTITION_SUBTYPE_ANY, PARTITION_LABEL);
+    if (assets->partition_ == nullptr) {
+        ESP_LOGI(TAG, "No assets partition found");
+        return false;
+    }
+    return true;
+}
+
+bool Assets::Apply() {
+    return strategy_ ? strategy_->Apply(this) : false;
+}
+
+bool Assets::InitializePartition() {
+    return strategy_ ? strategy_->InitializePartition(this) : false;
+}
+
+void Assets::UnApplyPartition() {
+    if (strategy_) {
+        strategy_->UnApplyPartition(this);
+    }
+}
+
+bool Assets::GetAssetData(const std::string& name, void*& ptr, size_t& size) {
+    return strategy_ ? strategy_->GetAssetData(this, name, ptr, size) : false;
+}
+
+bool Assets::LoadSrmodelsFromIndex(Assets* assets, cJSON* root) {
+    void* ptr = nullptr;
+    size_t size = 0;
+    bool need_delete_root = false;
+
+    // If root is not provided, parse index.json
+    if (root == nullptr) {
+        if (!assets->GetAssetData("index.json", ptr, size)) {
+            ESP_LOGE(TAG, "The index.json file is not found");
+            return false;
+        }
+
+        root = cJSON_ParseWithLength(static_cast<char*>(ptr), size);
+        if (root == nullptr) {
+            ESP_LOGE(TAG, "The index.json file is not valid");
+            return false;
+        }
+        need_delete_root = true;
+    }
+
+    cJSON* srmodels = cJSON_GetObjectItem(root, "srmodels");
+    if (cJSON_IsString(srmodels)) {
+        std::string srmodels_file = srmodels->valuestring;
+        if (assets->GetAssetData(srmodels_file, ptr, size)) {
+            if (assets->models_list_ != nullptr) {
+                esp_srmodel_deinit(assets->models_list_);
+                assets->models_list_ = nullptr;
+            }
+            assets->models_list_ = srmodel_load(static_cast<uint8_t*>(ptr));
+            if (assets->models_list_ != nullptr) {
+                auto& app = Application::GetInstance();
+                app.GetAudioService().SetModelsList(assets->models_list_);
+                if (need_delete_root) {
+                    cJSON_Delete(root);
+                }
+                return true;
+            } else {
+                ESP_LOGE(TAG, "Failed to load srmodels.bin");
+            }
+        } else {
+            ESP_LOGE(TAG, "The srmodels file %s is not found", srmodels_file.c_str());
+        }
+    }
+
+    if (need_delete_root) {
+        cJSON_Delete(root);
+    }
+    return false;
+}
+
+#if HAVE_LVGL
+uint32_t Assets::LvglStrategy::CalculateChecksum(const char* data, uint32_t length) {
+    uint32_t checksum = 0;
+    for (uint32_t i = 0; i < length; i++) {
+        checksum += data[i];
+    }
+    return checksum & 0xFFFF;
+}
+
+bool Assets::LvglStrategy::InitializePartition(Assets* assets) {
+    assets->partition_valid_ = false;
+    assets_.clear();
+
+    if (!Assets::FindPartition(assets)) {
+        return false;
+    }
+
+    int free_pages = spi_flash_mmap_get_free_pages(SPI_FLASH_MMAP_DATA);
+    uint32_t storage_size = free_pages * 64 * 1024;
+    ESP_LOGI(TAG, "The storage free size is %ld KB", storage_size / 1024);
+    ESP_LOGI(TAG, "The partition size is %ld KB", assets->partition_->size / 1024);
+    if (storage_size < assets->partition_->size) {
+        ESP_LOGE(TAG, "The free size %ld KB is less than assets partition required %ld KB", storage_size / 1024, assets->partition_->size / 1024);
+        return false;
+    }
+
+    esp_err_t err = esp_partition_mmap(assets->partition_, 0, assets->partition_->size, ESP_PARTITION_MMAP_DATA, (const void**)&mmap_root_, &mmap_handle_);
+    if (err != ESP_OK) {
+        ESP_LOGE(TAG, "Failed to mmap assets partition: %s", esp_err_to_name(err));
+        return false;
+    }
+
+    assets->partition_valid_ = true;
+
+    uint32_t stored_files = *(uint32_t*)(mmap_root_ + 0);
+    uint32_t stored_chksum = *(uint32_t*)(mmap_root_ + 4);
+    uint32_t stored_len = *(uint32_t*)(mmap_root_ + 8);
+
+    if (stored_len > assets->partition_->size - 12) {
+        ESP_LOGD(TAG, "The stored_len (0x%lx) is greater than the partition size (0x%lx) - 12", stored_len, assets->partition_->size);
+        return false;
+    }
+
+    auto start_time = esp_timer_get_time();
+    uint32_t calculated_checksum = CalculateChecksum(mmap_root_ + 12, stored_len);
+    auto end_time = esp_timer_get_time();
+    ESP_LOGI(TAG, "The checksum calculation time is %d ms", int((end_time - start_time) / 1000));
+
+    if (calculated_checksum != stored_chksum) {
+        ESP_LOGE(TAG, "The calculated checksum (0x%lx) does not match the stored checksum (0x%lx)", calculated_checksum, stored_chksum);
+        return false;
+    }
+
+    checksum_valid_ = true;
+
+    for (uint32_t i = 0; i < stored_files; i++) {
+        auto item = (const mmap_assets_table*)(mmap_root_ + 12 + i * sizeof(mmap_assets_table));
+        auto asset = Asset{
+            .size = static_cast<size_t>(item->asset_size),
+            .offset = static_cast<size_t>(12 + sizeof(mmap_assets_table) * stored_files + item->asset_offset)
+        };
+        assets_[item->asset_name] = asset;
+    }
+    return checksum_valid_;
+}
+
+void Assets::LvglStrategy::UnApplyPartition(Assets* assets) {
+    if (mmap_handle_ != 0) {
+        esp_partition_munmap(mmap_handle_);
+        mmap_handle_ = 0;
+        mmap_root_ = nullptr;
+    }
+    checksum_valid_ = false;
+    assets_.clear();
+    (void)assets; // Unused parameter
+}
+
+bool Assets::LvglStrategy::GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) {
+    auto asset = assets_.find(name);
+    if (asset == assets_.end()) {
+        return false;
+    }
+    auto data = (const char*)(mmap_root_ + asset->second.offset);
+    if (data[0] != 'Z' || data[1] != 'Z') {
+        ESP_LOGE(TAG, "The asset %s is not valid with magic %02x%02x", name.c_str(), data[0], data[1]);
+        return false;
+    }
+
+    ptr = static_cast<void*>(const_cast<char*>(data + 2));
+    size = asset->second.size;
+    return true;
+}
+
+bool Assets::LvglStrategy::Apply(Assets* assets) {
+    void* ptr = nullptr;
+    size_t size = 0;
+    if (!assets->GetAssetData("index.json", ptr, size)) {
+        ESP_LOGE(TAG, "The index.json file is not found");
+        return false;
+    }
+
+    cJSON* root = cJSON_ParseWithLength(static_cast<char*>(ptr), size);
+    if (root == nullptr) {
+        ESP_LOGE(TAG, "The index.json file is not valid");
+        return false;
+    }
+
+    cJSON* version = cJSON_GetObjectItem(root, "version");
+    if (cJSON_IsNumber(version)) {
+        if (version->valuedouble > 1) {
+            ESP_LOGE(TAG, "The assets version %d is not supported, please upgrade the firmware", version->valueint);
+            return false;
+        }
+    }
+
+    Assets::LoadSrmodelsFromIndex(assets, root);
+
+    auto& theme_manager = LvglThemeManager::GetInstance();
+    auto light_theme = theme_manager.GetTheme("light");
+    auto dark_theme = theme_manager.GetTheme("dark");
+
+    cJSON* font = cJSON_GetObjectItem(root, "text_font");
+    if (cJSON_IsString(font)) {
+        std::string fonts_text_file = font->valuestring;
+        if (assets->GetAssetData(fonts_text_file, ptr, size)) {
+            auto text_font = std::make_shared<LvglCBinFont>(ptr);
+            if (text_font->font() == nullptr) {
+                ESP_LOGE(TAG, "Failed to load fonts.bin");
+                return false;
+            }
+            if (light_theme != nullptr) {
+                light_theme->set_text_font(text_font);
+            }
+            if (dark_theme != nullptr) {
+                dark_theme->set_text_font(text_font);
+            }
+        } else {
+            ESP_LOGE(TAG, "The font file %s is not found", fonts_text_file.c_str());
+        }
+    }
+
+    cJSON* emoji_collection = cJSON_GetObjectItem(root, "emoji_collection");
+    if (cJSON_IsArray(emoji_collection)) {
+        auto custom_emoji_collection = std::make_shared<EmojiCollection>();
+        int emoji_count = cJSON_GetArraySize(emoji_collection);
+        for (int i = 0; i < emoji_count; i++) {
+            cJSON* emoji = cJSON_GetArrayItem(emoji_collection, i);
+            if (cJSON_IsObject(emoji)) {
+                cJSON* name = cJSON_GetObjectItem(emoji, "name");
+                cJSON* file = cJSON_GetObjectItem(emoji, "file");
+                cJSON* eaf = cJSON_GetObjectItem(emoji, "eaf");
+                if (cJSON_IsString(name) && cJSON_IsString(file) && (NULL== eaf)) {
+                    if (!assets->GetAssetData(file->valuestring, ptr, size)) {
+                        ESP_LOGE(TAG, "Emoji %s image file %s is not found", name->valuestring, file->valuestring);
+                        continue;
+                    }
+                    custom_emoji_collection->AddEmoji(name->valuestring, new LvglRawImage(ptr, size));
+                }
+            }
+        }
+        if (light_theme != nullptr) {
+            light_theme->set_emoji_collection(custom_emoji_collection);
+        }
+        if (dark_theme != nullptr) {
+            dark_theme->set_emoji_collection(custom_emoji_collection);
+        }
+    }
+
+    cJSON* skin = cJSON_GetObjectItem(root, "skin");
+    if (cJSON_IsObject(skin)) {
+        cJSON* light_skin = cJSON_GetObjectItem(skin, "light");
+        if (cJSON_IsObject(light_skin) && light_theme != nullptr) {
+            cJSON* text_color = cJSON_GetObjectItem(light_skin, "text_color");
+            cJSON* background_color = cJSON_GetObjectItem(light_skin, "background_color");
+            cJSON* background_image = cJSON_GetObjectItem(light_skin, "background_image");
+            if (cJSON_IsString(text_color)) {
+                light_theme->set_text_color(LvglTheme::ParseColor(text_color->valuestring));
+            }
+            if (cJSON_IsString(background_color)) {
+                light_theme->set_background_color(LvglTheme::ParseColor(background_color->valuestring));
+                light_theme->set_chat_background_color(LvglTheme::ParseColor(background_color->valuestring));
+            }
+            if (cJSON_IsString(background_image)) {
+                if (!assets->GetAssetData(background_image->valuestring, ptr, size)) {
+                    ESP_LOGE(TAG, "The background image file %s is not found", background_image->valuestring);
+                    return false;
+                }
+                auto background_image = std::make_shared<LvglCBinImage>(ptr);
+                light_theme->set_background_image(background_image);
+            }
+        }
+        cJSON* dark_skin = cJSON_GetObjectItem(skin, "dark");
+        if (cJSON_IsObject(dark_skin) && dark_theme != nullptr) {
+            cJSON* text_color = cJSON_GetObjectItem(dark_skin, "text_color");
+            cJSON* background_color = cJSON_GetObjectItem(dark_skin, "background_color");
+            cJSON* background_image = cJSON_GetObjectItem(dark_skin, "background_image");
+            if (cJSON_IsString(text_color)) {
+                dark_theme->set_text_color(LvglTheme::ParseColor(text_color->valuestring));
+            }
+            if (cJSON_IsString(background_color)) {
+                dark_theme->set_background_color(LvglTheme::ParseColor(background_color->valuestring));
+                dark_theme->set_chat_background_color(LvglTheme::ParseColor(background_color->valuestring));
+            }
+            if (cJSON_IsString(background_image)) {
+                if (!assets->GetAssetData(background_image->valuestring, ptr, size)) {
+                    ESP_LOGE(TAG, "The background image file %s is not found", background_image->valuestring);
+                    return false;
+                }
+                auto background_image = std::make_shared<LvglCBinImage>(ptr);
+                dark_theme->set_background_image(background_image);
+            }
+        }
+    }
+
+    auto display = Board::GetInstance().GetDisplay();
+    ESP_LOGI(TAG, "Refreshing display theme...");
+
+    auto current_theme = display->GetTheme();
+    if (current_theme != nullptr) {
+        display->SetTheme(current_theme);
+    }
+
+    // Parse hide_subtitle configuration
+    cJSON* hide_subtitle = cJSON_GetObjectItem(root, "hide_subtitle");
+    if (cJSON_IsBool(hide_subtitle)) {
+        bool hide = cJSON_IsTrue(hide_subtitle);
+        auto lcd_display = dynamic_cast<LcdDisplay*>(display);
+        if (lcd_display != nullptr) {
+            lcd_display->SetHideSubtitle(hide);
+            ESP_LOGI(TAG, "Set hide_subtitle to %s", hide ? "true" : "false");
+        }
+    }
+    
+    cJSON_Delete(root);
+    return true;
+}
+#endif // HAVE_LVGL
+
+bool Assets::EmoteStrategy::InitializePartition(Assets* assets) {
+    assets->partition_valid_ = false;
+
+    if (!Assets::FindPartition(assets)) {
+        return false;
+    }
+
+    esp_err_t ret = ESP_ERR_INVALID_STATE;
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        const emote_data_t data = {
+            .type = EMOTE_SOURCE_PARTITION,
+            .source = {
+                .partition_label = PARTITION_LABEL,
+            },
+            .flags = {
+                .mmap_enable = true, //must be true here!!!
+            },
+        };
+        ret = emote_mount_assets(emote_display->GetEmoteHandle(), &data);
+    } else {
+        ESP_LOGE(TAG, "Emote display is not initialized");
+    }
+    assets->partition_valid_ = ((ret == ESP_OK) ? true : false);
+    return assets->partition_valid_;
+}
+
+void Assets::EmoteStrategy::UnApplyPartition(Assets* assets) {
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        emote_unmount_assets(emote_display->GetEmoteHandle());
+    }
+    (void)assets; // Unused parameter
+}
+
+bool Assets::EmoteStrategy::GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) {
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        const uint8_t* data = nullptr;
+        size_t data_size = 0;
+        if (ESP_OK == emote_get_asset_data_by_name(emote_display->GetEmoteHandle(), name.c_str(), &data, &data_size)) {
+            ptr = const_cast<void*>(static_cast<const void*>(data));
+            size = data_size;
+            return true;
+        }
+        ESP_LOGE(TAG, "Failed to get asset data by name: %s", name.c_str());
+        return false;
+    }
+    (void)assets; // Unused parameter
+    return false;
+}
+
+bool Assets::EmoteStrategy::Apply(Assets* assets) {
+    Assets::LoadSrmodelsFromIndex(assets);
+
+    auto display = Board::GetInstance().GetDisplay();
+    auto* emote_display = dynamic_cast<emote::EmoteDisplay*>(display);
+
+    if (emote_display && emote_display->GetEmoteHandle() != nullptr) {
+        emote_load_assets(emote_display->GetEmoteHandle());
+    }
+    return true;
+}
+
+bool Assets::Download(std::string url, std::function<void(int progress, size_t speed)> progress_callback) {
+    ESP_LOGI(TAG, "Downloading new version of assets from %s", url.c_str());
+
+    // 取消当前资源分区的内存映射
+    UnApplyPartition();
+
+    // 下载新的资源文件
+    auto network = Board::GetInstance().GetNetwork();
+    auto http = network->CreateHttp(0);
+    
+    if (!http->Open("GET", url)) {
+        ESP_LOGE(TAG, "Failed to open HTTP connection");
+        return false;
+    }
+
+    if (http->GetStatusCode() != 200) {
+        ESP_LOGE(TAG, "Failed to get assets, status code: %d", http->GetStatusCode());
+        return false;
+    }
+
+    size_t content_length = http->GetBodyLength();
+    if (content_length == 0) {
+        ESP_LOGE(TAG, "Failed to get content length");
+        return false;
+    }
+
+    if (content_length > partition_->size) {
+        ESP_LOGE(TAG, "Assets file size (%u) is larger than partition size (%lu)", content_length, partition_->size);
+        return false;
+    }
+
+    // 定义扇区大小为4KB（ESP32的标准扇区大小）
+    const size_t SECTOR_SIZE = esp_partition_get_main_flash_sector_size();
+    
+    // 计算需要擦除的扇区数量
+    size_t sectors_to_erase = (content_length + SECTOR_SIZE - 1) / SECTOR_SIZE; // 向上取整
+    size_t total_erase_size = sectors_to_erase * SECTOR_SIZE;
+    
+    ESP_LOGI(TAG, "Sector size: %u, content length: %u, sectors to erase: %u, total erase size: %u", 
+             SECTOR_SIZE, content_length, sectors_to_erase, total_erase_size);
+    
+    // 写入新的资源文件到分区，一边erase一边写入
+    char* buffer = (char*)heap_caps_malloc(SECTOR_SIZE, MALLOC_CAP_INTERNAL);
+    if (buffer == nullptr) {
+        ESP_LOGE(TAG, "Failed to allocate buffer");
+        return false;
+    }
+    size_t total_written = 0;
+    size_t recent_written = 0;
+    size_t current_sector = 0;
+    auto last_calc_time = esp_timer_get_time();
+    
+    while (true) {
+        int ret = http->Read(buffer, SECTOR_SIZE);
+        if (ret < 0) {
+            ESP_LOGE(TAG, "Failed to read HTTP data: %s", esp_err_to_name(ret));
+            heap_caps_free(buffer);
+            return false;
+        }
+
+        if (ret == 0) {
+            break;
+        }
+
+        // 检查是否需要擦除新的扇区
+        size_t write_end_offset = total_written + ret;
+        size_t needed_sectors = (write_end_offset + SECTOR_SIZE - 1) / SECTOR_SIZE;
+        
+        // 擦除需要的新扇区
+        while (current_sector < needed_sectors) {
+            size_t sector_start = current_sector * SECTOR_SIZE;
+            size_t sector_end = (current_sector + 1) * SECTOR_SIZE;
+            
+            // 确保擦除范围不超过分区大小
+            if (sector_end > partition_->size) {
+                ESP_LOGE(TAG, "Sector end (%u) exceeds partition size (%lu)", sector_end, partition_->size);
+                heap_caps_free(buffer);
+                return false;
+            }
+            
+            ESP_LOGD(TAG, "Erasing sector %u (offset: %u, size: %u)", current_sector, sector_start, SECTOR_SIZE);
+            esp_err_t err = esp_partition_erase_range(partition_, sector_start, SECTOR_SIZE);
+            if (err != ESP_OK) {
+                ESP_LOGE(TAG, "Failed to erase sector %u at offset %u: %s", current_sector, sector_start, esp_err_to_name(err));
+                heap_caps_free(buffer);
+                return false;
+            }
+            
+            current_sector++;
+        }
+
+        // 写入数据到分区
+        esp_err_t err = esp_partition_write(partition_, total_written, buffer, ret);
+        if (err != ESP_OK) {
+            ESP_LOGE(TAG, "Failed to write to assets partition at offset %u: %s", total_written, esp_err_to_name(err));
+            heap_caps_free(buffer);
+            return false;
+        }
+
+        total_written += ret;
+        recent_written += ret;
+
+        // 计算进度和速度
+        if (esp_timer_get_time() - last_calc_time >= 1000000 || total_written == content_length || ret == 0) {
+            size_t progress = total_written * 100 / content_length;
+            size_t speed = recent_written; // 每秒的字节数
+            ESP_LOGI(TAG, "Progress: %u%% (%u/%u), Speed: %u B/s, Sectors erased: %u", 
+                     progress, total_written, content_length, speed, current_sector);
+            if (progress_callback) {
+                progress_callback(progress, speed);
+            }
+            last_calc_time = esp_timer_get_time();
+            recent_written = 0; // 重置最近写入的字节数
+        }
+    }
+    
+    http->Close();
+    heap_caps_free(buffer);
+
+    if (total_written != content_length) {
+        ESP_LOGE(TAG, "Downloaded size (%u) does not match expected size (%u)", total_written, content_length);
+        return false;
+    }
+
+    ESP_LOGI(TAG, "Assets download completed, total written: %u bytes, total sectors erased: %u", 
+             total_written, current_sector);
+
+    // 重新初始化资源分区
+    if (!InitializePartition()) {
+        ESP_LOGE(TAG, "Failed to re-initialize assets partition");
+        return false;
+    }
+
+    return true;
+}

main/assets.h

@@ -0,0 +1,89 @@
+#ifndef ASSETS_H
+#define ASSETS_H
+
+#include <string>
+#include <functional>
+#include <memory>
+
+#include <cJSON.h>
+#include <esp_partition.h>
+#include <model_path.h>
+#include <map>
+#include <string>
+
+#if HAVE_LVGL
+#include <spi_flash_mmap.h>
+#endif
+
+struct Asset {
+    size_t size;
+    size_t offset;
+};
+
+class Assets {
+public:
+    static Assets& GetInstance() {
+        static Assets instance;
+        return instance;
+    }
+    ~Assets();
+
+    bool Download(std::string url, std::function<void(int progress, size_t speed)> progress_callback);
+    bool Apply();
+    bool GetAssetData(const std::string& name, void*& ptr, size_t& size);
+
+    inline bool partition_valid() const { return partition_valid_; }
+    inline std::string default_assets_url() const { return default_assets_url_; }
+
+private:
+    Assets();
+    Assets(const Assets&) = delete;
+    Assets& operator=(const Assets&) = delete;
+
+    bool InitializePartition();
+    void UnApplyPartition();
+    static bool FindPartition(Assets* assets);
+    static bool LoadSrmodelsFromIndex(Assets* assets, cJSON* root = nullptr);
+  
+    class AssetStrategy {
+    public:
+        virtual ~AssetStrategy() = default;
+        virtual bool Apply(Assets* assets) = 0;
+        virtual bool InitializePartition(Assets* assets) = 0;
+        virtual void UnApplyPartition(Assets* assets) = 0;
+        virtual bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) = 0;
+    };
+    
+    class LvglStrategy : public AssetStrategy {
+    public:
+        bool Apply(Assets* assets) override;
+        bool InitializePartition(Assets* assets) override;
+        void UnApplyPartition(Assets* assets) override;
+        bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) override;
+    private:
+        static uint32_t CalculateChecksum(const char* data, uint32_t length);
+        std::map<std::string, Asset> assets_;
+        esp_partition_mmap_handle_t mmap_handle_ = 0;
+        const char* mmap_root_ = nullptr;
+        bool checksum_valid_ = false;
+    };
+    
+    class EmoteStrategy : public AssetStrategy {
+    public:
+        bool Apply(Assets* assets) override;
+        bool InitializePartition(Assets* assets) override;
+        void UnApplyPartition(Assets* assets) override;
+        bool GetAssetData(Assets* assets, const std::string& name, void*& ptr, size_t& size) override;
+    };
+    
+    // Strategy instance
+    std::unique_ptr<AssetStrategy> strategy_;
+
+protected:
+    const esp_partition_t* partition_ = nullptr;
+    bool partition_valid_ = false;
+    std::string default_assets_url_;
+    srmodel_list_t* models_list_ = nullptr;
+};
+
+#endif

main/assets/locales/ar-SA/language.json

@@ -0,0 +1,59 @@
+{
+    "language": {
+        "type": "ar-SA"
+    },
+    "strings": {
+        "WARNING": "تحذير",
+        "INFO": "معلومات",
+        "ERROR": "خطأ",
+        "VERSION": "الإصدار ",
+        "LOADING_PROTOCOL": "الاتصال بالخادم...",
+        "INITIALIZING": "التهيئة...",
+        "PIN_ERROR": "يرجى إدخال بطاقة SIM",
+        "REG_ERROR": "لا يمكن الوصول إلى الشبكة، يرجى التحقق من حالة بطاقة البيانات",
+        "DETECTING_MODULE": "اكتشاف الوحدة...",
+        "REGISTERING_NETWORK": "انتظار الشبكة...",
+        "CHECKING_NEW_VERSION": "فحص الإصدار الجديد...",
+        "CHECK_NEW_VERSION_FAILED": "فشل فحص الإصدار الجديد، سيتم المحاولة خلال %d ثانية: %s",
+        "SWITCH_TO_WIFI_NETWORK": "التبديل إلى Wi-Fi...",
+        "SWITCH_TO_4G_NETWORK": "التبديل إلى 4G...",
+        "STANDBY": "في الانتظار",
+        "CONNECT_TO": "الاتصال بـ ",
+        "CONNECTING": "جاري الاتصال...",
+        "CONNECTED_TO": "متصل بـ ",
+        "LISTENING": "الاستماع...",
+        "SPEAKING": "التحدث...",
+        "SERVER_NOT_FOUND": "البحث عن خدمة متاحة",
+        "SERVER_NOT_CONNECTED": "لا يمكن الاتصال بالخدمة، يرجى المحاولة لاحقاً",
+        "SERVER_TIMEOUT": "انتهت مهلة الاستجابة",
+        "SERVER_ERROR": "فشل الإرسال، يرجى التحقق من الشبكة",
+        "CONNECT_TO_HOTSPOT": "اتصل الهاتف بنقطة الاتصال ",
+        "ACCESS_VIA_BROWSER": "،الوصول عبر المتصفح ",
+        "WIFI_CONFIG_MODE": "وضع تكوين الشبكة",
+        "ENTERING_WIFI_CONFIG_MODE": "الدخول في وضع تكوين الشبكة...",
+        "SCANNING_WIFI": "فحص Wi-Fi...",
+        "NEW_VERSION": "إصدار جديد ",
+        "OTA_UPGRADE": "تحديث OTA",
+        "UPGRADING": "تحديث النظام...",
+        "UPGRADE_FAILED": "فشل التحديث",
+        "ACTIVATION": "تفعيل الجهاز",
+        "BATTERY_LOW": "البطارية منخفضة",
+        "BATTERY_CHARGING": "جاري الشحن",
+        "BATTERY_FULL": "البطارية ممتلئة",
+        "BATTERY_NEED_CHARGE": "البطارية منخفضة، يرجى الشحن",
+        "VOLUME": "الصوت ",
+        "MUTED": "صامت",
+        "MAX_VOLUME": "أقصى صوت",
+        "RTC_MODE_OFF": "AEC مُوقف",
+        "RTC_MODE_ON": "AEC مُشغل",
+        "DOWNLOAD_ASSETS_FAILED": "فشل في تنزيل الموارد",
+        "LOADING_ASSETS": "جاري تحميل الموارد...",
+        "PLEASE_WAIT": "يرجى الانتظار...",
+        "FOUND_NEW_ASSETS": "تم العثور على موارد جديدة: %s",
+        "HELLO_MY_FRIEND": "مرحباً، صديقي!",
+        "CONNECTION_SUCCESSFUL": "تم الاتصال بنجاح",
+        "FLIGHT_MODE_OFF": "وضع الطيران معطل",
+        "FLIGHT_MODE_ON": "وضع الطيران قيد التشغيل",
+        "MODEM_INIT_ERROR": "فشل تهيئة المودم"
+    }
+}

main/assets/locales/bg-BG/language.json

@@ -0,0 +1,59 @@
+{
+    "language": {
+        "type": "bg-BG"
+    },
+    "strings": {
+        "WARNING": "Предупреждение",
+        "INFO": "Информация",
+        "ERROR": "Грешка",
+        "VERSION": "Версия ",
+        "LOADING_PROTOCOL": "Влизане в системата...",
+        "INITIALIZING": "Инициализация...",
+        "PIN_ERROR": "Моля, поставете SIM карта",
+        "REG_ERROR": "Не може да се осъществи достъп до мрежата, моля проверете статуса на SIM картата",
+        "DETECTING_MODULE": "Откриване на модул...",
+        "REGISTERING_NETWORK": "Изчакване на мрежата...",
+        "CHECKING_NEW_VERSION": "Проверка за нова версия...",
+        "CHECK_NEW_VERSION_FAILED": "Проверката за нова версия е неуспешна, ще се опита отново след %d секунди: %s",
+        "SWITCH_TO_WIFI_NETWORK": "Превключване към Wi-Fi...",
+        "SWITCH_TO_4G_NETWORK": "Превключване към 4G...",
+        "STANDBY": "Режим на готовност",
+        "CONNECT_TO": "Свързване към ",
+        "CONNECTING": "Свързване...",
+        "CONNECTION_SUCCESSFUL": "Успешно свързване",
+        "CONNECTED_TO": "Свързан към ",
+        "LISTENING": "Слушане...",
+        "SPEAKING": "Говорене...",
+        "SERVER_NOT_FOUND": "Търсене на налична услуга",
+        "SERVER_NOT_CONNECTED": "Не може да се свърже с услугата, моля опитайте по-късно",
+        "SERVER_TIMEOUT": "Времето за изчакване на отговор изтече",
+        "SERVER_ERROR": "Неуспешно изпращане, моля проверете мрежата",
+        "CONNECT_TO_HOTSPOT": "Горещa точка: ",
+        "ACCESS_VIA_BROWSER": " Конфигурационен URL: ",
+        "WIFI_CONFIG_MODE": "Режим на конфигуриране на Wi-Fi",
+        "ENTERING_WIFI_CONFIG_MODE": "Влизане в режим на конфигуриране на Wi-Fi...",
+        "SCANNING_WIFI": "Сканиране на Wi-Fi...",
+        "NEW_VERSION": "Нова версия ",
+        "OTA_UPGRADE": "OTA надстройка",
+        "UPGRADING": "Системата се надстройва...",
+        "UPGRADE_FAILED": "Надстройката е неуспешна",
+        "ACTIVATION": "Активация",
+        "BATTERY_LOW": "Слаба батерия",
+        "BATTERY_CHARGING": "Зарядна",
+        "BATTERY_FULL": "Батерията е пълна",
+        "BATTERY_NEED_CHARGE": "Слаба батерия, моля заредете",
+        "VOLUME": "Сила на звука ",
+        "MUTED": "Заглушено",
+        "MAX_VOLUME": "Максимална сила на звука",
+        "RTC_MODE_OFF": "AEC изключен",
+        "RTC_MODE_ON": "AEC включен",
+        "PLEASE_WAIT": "Моля, изчакайте...",
+        "FOUND_NEW_ASSETS": "Намерени нови ресурси: %s",
+        "DOWNLOAD_ASSETS_FAILED": "Неуспешно изтегляне на ресурси",
+        "LOADING_ASSETS": "Зареждане на ресурси...",
+        "HELLO_MY_FRIEND": "Здравей, мой приятел!",
+        "FLIGHT_MODE_OFF": "Режим на самолет е изключен",
+        "FLIGHT_MODE_ON": "Режим на самолет е включен",
+        "MODEM_INIT_ERROR": "Неуспешна инициализация на модема"
+    }
+}