docs: revise description for AstrBot in README.md

* fix: 修复特定提供商导致的定时任务执行失败的问题

* ruff format

---------

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

.dockerignore

@@ -1,9 +1,9 @@
 # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
 # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
-# github acions
+# github actions
+.git
 .github/
 .*ignore
-.git/
 # User-specific stuff
 .idea/
 # Byte-compiled / optimized / DLL files
@@ -15,10 +15,10 @@ env/
 venv*/
 ENV/
 .conda/
-README*.md
 dashboard/
 data/
 changelogs/
 tests/
 .ruff_cache/
-.astrbot
+.astrbot
+astrbot.lock

.github/ISSUE_TEMPLATE/PLUGIN_PUBLISH.yml

@@ -16,7 +16,7 @@ body:
 
         请将插件信息填写到下方的 JSON 代码块中。其中 `tags`（插件标签）和 `social_link`（社交链接）选填。
 
-        不熟悉 JSON ？现在可以从 [这里](https://plugins.astrbot.app/#/submit) 获取你的 JSON 啦！获取到了记得复制粘贴过来哦！
+        不熟悉 JSON ？可以从 [此站](https://plugins.astrbot.app) 右下角提交。
 
   - type: textarea
     id: plugin-info
@@ -26,12 +26,13 @@ body:
       value: |
         ```json
         {
-          "name": "插件名",
-          "desc": "插件介绍",
+          "name": "插件名，请以 astrbot_plugin_ 开头",
+          "display_name": "用于展示的插件名，方便人类阅读",
+          "desc": "插件的简短介绍",
           "author": "作者名",
           "repo": "插件仓库链接",
           "tags": [],
-          "social_link": ""
+          "social_link": "",
         }
         ```
     validations:

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -1,46 +1,44 @@
-name: '🐛 报告 Bug'
+name: '🐛 Report Bug / 报告 Bug'
 title: '[Bug]'
-description: 提交报告帮助我们改进。
+description: Submit bug report to help us improve. / 提交报告帮助我们改进。
 labels: [ 'bug' ]
 body:
   - type: markdown
     attributes:
       value: |
-        感谢您抽出时间报告问题！请准确解释您的问题。如果可能，请提供一个可复现的片段（这有助于更快地解决问题）。
+        Thank you for taking the time to report this issue! Please describe your problem accurately. If possible, please provide a reproducible snippet (this will help resolve the issue more quickly). Please note that issues that are not detailed or have no logs will be closed immediately. Thank you for your understanding. / 感谢您抽出时间报告问题！请准确解释您的问题。如果可能，请提供一个可复现的片段（这有助于更快地解决问题）。请注意，不详细 / 没有日志的 issue 会被直接关闭，谢谢理解。
   - type: textarea
     attributes:
-      label: 发生了什么
-      description: 描述你遇到的异常
+      label: What happened / 发生了什么
+      description: Description
       placeholder: >
-        一个清晰且具体的描述这个异常是什么。
+        Please provide a clear and specific description of what this exception is. Please note that issues that are not detailed or have no logs will be closed immediately. Thank you for your understanding. / 一个清晰且具体的描述这个异常是什么。请注意，不详细 / 没有日志的 issue 会被直接关闭，谢谢理解。
     validations:
       required: true
 
   - type: textarea
     attributes:
-      label: 如何复现？
+      label: Reproduce / 如何复现？
       description: >
-        复现该问题的步骤
+        The steps to reproduce the issue. / 复现该问题的步骤
       placeholder: >
-        如: 1. 打开 '...'
+        Example: 1. Open '...'
     validations:
       required: true
 
   - type: textarea
     attributes:
-      label: AstrBot 版本、部署方式（如 Windows Docker Desktop 部署）、使用的提供商、使用的消息平台适配器
-      description: >
-        请提供您的 AstrBot 版本和部署方式。
+      label: AstrBot version, deployment method (e.g., Windows Docker Desktop deployment), provider used, and messaging platform used. / AstrBot 版本、部署方式（如 Windows Docker Desktop 部署）、使用的提供商、使用的消息平台适配器
       placeholder: >
-        如: 3.1.8 Docker, 3.1.7 Windows启动器
+        Example: 4.5.7 Docker, 3.1.7 Windows Launcher
     validations:
       required: true
 
   - type: dropdown
     attributes:
-      label: 操作系统
+      label: OS
       description: |
-        你在哪个操作系统上遇到了这个问题？
+        On which operating system did you encounter this problem? / 你在哪个操作系统上遇到了这个问题？
       multiple: false
       options:
         - 'Windows'
@@ -53,30 +51,30 @@ body:
 
   - type: textarea
     attributes:
-      label: 报错日志
+      label: Logs / 报错日志
       description: >
-        如报错日志、截图等。请提供完整的 Debug 级别的日志，不要介意它很长！
+        Please provide complete Debug-level logs, such as error logs and screenshots. Don't worry if they're long! Please note that issues with insufficient details or no logs will be closed immediately. Thank you for your understanding. / 如报错日志、截图等。请提供完整的 Debug 级别的日志，不要介意它很长！请注意，不详细 / 没有日志的 issue 会被直接关闭，谢谢理解。
       placeholder: >
-        请提供完整的报错日志或截图。
+        Please provide a complete error log or screenshot. / 请提供完整的报错日志或截图。
     validations:
       required: true
 
   - type: checkboxes
     attributes:
-      label: 你愿意提交 PR 吗？
+      label: Are you willing to submit a PR? / 你愿意提交 PR 吗？
       description: >
-        这不是必需的，但我们很乐意在贡献过程中为您提供指导特别是如果你已经很好地理解了如何实现修复。
+        This is not required, but we would be happy to provide guidance during the contribution process, especially if you already have a good understanding of how to implement the fix. / 这不是必需的，但我们很乐意在贡献过程中为您提供指导特别是如果你已经很好地理解了如何实现修复。
       options:
-        - label: 是的，我愿意提交 PR!
+        - label: Yes!
 
   - type: checkboxes
     attributes:
       label: Code of Conduct
       options:
         - label: >
-            我已阅读并同意遵守该项目的 [行为准则](https://docs.github.com/zh/site-policy/github-terms/github-community-code-of-conduct)。
+            I have read and agree to abide by the project's [Code of Conduct](https://docs.github.com/zh/site-policy/github-terms/github-community-code-of-conduct)。
           required: true
 
   - type: markdown
     attributes:
-      value: "感谢您填写我们的表单！"
+      value: "Thank you for filling out our form! / 感谢您填写我们的表单！"

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,19 +1,27 @@
-<!-- 如果有的话，指定这个 PR 要解决的 ISSUE -->
-解决了 #XYZ
+<!--Please describe the motivation for this change: What problem does it solve? (e.g., Fixes XX issue, adds YY feature)-->
+<!--请描述此项更改的动机：它解决了什么问题？（例如：修复了 XX issue，添加了 YY 功能）-->
 
-### Motivation
+### Modifications / 改动点
 
-<!--解释为什么要改动-->
+<!--请总结你的改动：哪些核心文件被修改了？实现了什么功能？-->
+<!--Please summarize your changes: What core files were modified? What functionality was implemented?-->
 
-### Modifications
+- [x] This is NOT a breaking change. / 这不是一个破坏性变更。
+<!-- If your changes is a breaking change, please uncheck the checkbox above -->
 
-<!--简单解释你的改动-->
+### Screenshots or Test Results / 运行截图或测试结果
 
-### Check
+<!--Please paste screenshots, GIFs, or test logs here as evidence of executing the "Verification Steps" to prove this change is effective.-->
+<!--请粘贴截图、GIF 或测试日志，作为执行“验证步骤”的证据，证明此改动有效。-->
 
-<!--如果分支被合并，您的代码将服务于数万名用户！在提交前，请核查一下几点内容-->
+---
 
-- [ ] 😊 我的 Commit Message 符合良好的[规范](https://www.conventionalcommits.org/en/v1.0.0/#summary)
-- [ ] 👀 我的更改经过良好的测试
-- [ ] 🤓 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到了 `requirements.txt` 和 `pyproject.toml` 文件相应位置。
-- [ ] 😮 我的更改没有引入恶意代码
+### Checklist / 检查清单
+
+<!--If merged, your code will serve tens of thousands of users! Please double-check the following items before submitting.-->
+<!--如果分支被合并，您的代码将服务于数万名用户！在提交前，请核查一下几点内容。-->
+
+- [ ] 😊 如果 PR 中有新加入的功能，已经通过 Issue / 邮件等方式和作者讨论过。/ If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
+- [ ] 👀 我的更改经过了良好的测试，**并已在上方提供了“验证步骤”和“运行截图”**。/ My changes have been well-tested, **and "Verification Steps" and "Screenshots" have been provided above**.
+- [ ] 🤓 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到了 `requirements.txt` 和 `pyproject.toml` 文件相应位置。/ I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in `requirements.txt` and `pyproject.toml`.
+- [ ] 😮 我的更改没有引入恶意代码。/ My changes do not introduce malicious code.

.github/auto_assign.yml

@@ -0,0 +1,38 @@
+# Set to true to add reviewers to pull requests
+addReviewers: true
+
+# Set to true to add assignees to pull requests
+addAssignees: false
+
+# A list of reviewers to be added to pull requests (GitHub user name)
+reviewers:
+  - Soulter
+  - Raven95676
+  - Larch-C
+  - anka-afk
+  - advent259141
+  - Fridemn
+  - LIghtJUNction
+  # - zouyonghe
+
+# A number of reviewers added to the pull request
+# Set 0 to add all the reviewers (default: 0)
+numberOfReviewers: 2
+
+# A list of assignees, overrides reviewers if set
+# assignees:
+#   - assigneeA
+
+# A number of assignees to add to the pull request
+# Set to 0 to add all of the assignees.
+# Uses numberOfReviewers if unset.
+# numberOfAssignees: 2
+
+# A list of keywords to be skipped the process that add reviewers if pull requests include it
+skipKeywords:
+  - wip
+  - draft
+
+# A list of users to be skipped by both the add reviewers and add assignees processes
+# skipUsers:
+#   - dependabot[bot]

.github/copilot-instructions.md

@@ -15,7 +15,6 @@ Always reference these instructions first and fallback to search or bash command
 ### Running the Application
 - Run main application: `uv run main.py` -- starts in ~3 seconds
 - Application creates WebUI on http://localhost:6185 (default credentials: `astrbot`/`astrbot`)
-- Application loads plugins automatically from `packages/` and `data/plugins/` directories
 
 ### Dashboard Build (Vue.js/Node.js)
 - **Prerequisites**: Node.js 20+ and npm 10+ required
@@ -35,7 +34,7 @@ Always reference these instructions first and fallback to search or bash command
 - **ALWAYS** run `uv run ruff check .` and `uv run ruff format .` before committing changes
 
 ### Plugin Development
-- Plugins load from `packages/` (built-in) and `data/plugins/` (user-installed)
+- Plugins load from `astrbot/builtin_stars/` (built-in) and `data/plugins/` (user-installed)
 - Plugin system supports function tools and message handlers
 - Key plugins: python_interpreter, web_searcher, astrbot, reminder, session_controller
 

.github/workflows/auto_release.yml

@@ -13,7 +13,7 @@ jobs:
       contents: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Dashboard Build
         run: |
@@ -70,10 +70,10 @@ jobs:
     needs: build-and-publish-to-github-release
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.10'
 

.github/workflows/code-format.yml

@@ -0,0 +1,34 @@
+name: Code Format Check
+
+on:
+  pull_request:
+    branches: [ master ]
+  push:
+    branches: [ master ]
+
+jobs:
+  format-check:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v6
+      
+    - name: Set up Python
+      uses: actions/setup-python@v6
+      with:
+        python-version: '3.10'
+        
+    - name: Install UV
+      run: pip install uv
+      
+    - name: Install dependencies
+      run: uv sync
+      
+    - name: Check code formatting with ruff
+      run: |
+        uv run ruff format --check .
+        
+    - name: Check code style with ruff
+      run: |
+        uv run ruff check .

.github/workflows/codeql.yml

@@ -56,11 +56,11 @@ jobs:
         # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v5
+      uses: actions/checkout@v6
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -88,6 +88,6 @@ jobs:
         exit 1
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/coverage_test.yml

@@ -17,12 +17,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
       
       - name: Install dependencies
         run: |

.github/workflows/dashboard_ci.yml

@@ -11,13 +11,20 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: 'latest'
 
       - name: npm install, build
         run: |
           cd dashboard
-          npm install
-          npm run build
+          npm install pnpm -g
+          pnpm install
+          pnpm i --save-dev @types/markdown-it
+          pnpm run build
 
       - name: Inject Commit SHA
         id: get_sha
@@ -29,7 +36,7 @@ jobs:
           zip -r dist.zip dist
 
       - name: Archive production artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: dist-without-markdown
           path: |
@@ -37,6 +44,7 @@ jobs:
             !dist/**/*.md
 
       - name: Create GitHub Release
+        if: github.event_name == 'push'
         uses: ncipollo/release-action@v1
         with:
           tag: release-${{ github.sha }}

.github/workflows/docker-image.yml

@@ -3,18 +3,125 @@ name: Docker Image CI/CD
 on:
   push:
     tags:
-      - 'v*'
+      - "v*"
+  schedule:
+    # Run at 00:00 UTC every day
+    - cron: "0 0 * * *"
   workflow_dispatch:
 
 jobs:
-  publish-docker:
+  build-nightly-image:
+    if: github.event_name == 'schedule'
     runs-on: ubuntu-latest
+    env:
+      DOCKER_HUB_USERNAME: ${{ secrets.DOCKER_HUB_USERNAME }}
+      GHCR_OWNER: soulter
+      HAS_GHCR_TOKEN: ${{ secrets.GHCR_GITHUB_TOKEN != '' }}
 
     steps:
-      - name: Pull The Codes
-        uses: actions/checkout@v5
+      - name: Checkout
+        uses: actions/checkout@v6
         with:
-          fetch-depth: 0  # Must be 0 so we can fetch tags
+          fetch-depth: 1
+          fetch-tag: true
+
+      - name: Check for new commits today
+        if: github.event_name == 'schedule'
+        id: check-commits
+        run: |
+          # Get commits from the last 24 hours
+          commits=$(git log --since="24 hours ago" --oneline)
+          if [ -z "$commits" ]; then
+            echo "No commits in the last 24 hours, skipping build"
+            echo "has_commits=false" >> $GITHUB_OUTPUT
+          else
+            echo "Found commits in the last 24 hours:"
+            echo "$commits"
+            echo "has_commits=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Exit if no commits
+        if: github.event_name == 'schedule' && steps.check-commits.outputs.has_commits == 'false'
+        run: exit 0
+
+      - name: Build Dashboard
+        run: |
+          cd dashboard
+          npm install
+          npm run build
+          mkdir -p dist/assets
+          echo $(git rev-parse HEAD) > dist/assets/version
+          cd ..
+          mkdir -p data
+          cp -r dashboard/dist data/
+
+      - name: Determine test image tags
+        id: test-meta
+        run: |
+          short_sha=$(echo "${GITHUB_SHA}" | cut -c1-12)
+          build_date=$(date +%Y%m%d)
+          echo "short_sha=$short_sha" >> $GITHUB_OUTPUT
+          echo "build_date=$build_date" >> $GITHUB_OUTPUT
+
+      - name: Set QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to DockerHub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_HUB_USERNAME }}
+          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
+
+      - name: Login to GitHub Container Registry
+        if: env.HAS_GHCR_TOKEN == 'true'
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ env.GHCR_OWNER }}
+          password: ${{ secrets.GHCR_GITHUB_TOKEN }}
+
+      - name: Build nightly image tags list
+        id: test-tags
+        run: |
+          TAGS="${{ env.DOCKER_HUB_USERNAME }}/astrbot:nightly-latest
+          ${{ env.DOCKER_HUB_USERNAME }}/astrbot:nightly-${{ steps.test-meta.outputs.build_date }}-${{ steps.test-meta.outputs.short_sha }}"
+          if [ "${{ env.HAS_GHCR_TOKEN }}" = "true" ]; then
+            TAGS="$TAGS
+          ghcr.io/${{ env.GHCR_OWNER }}/astrbot:nightly-latest
+          ghcr.io/${{ env.GHCR_OWNER }}/astrbot:nightly-${{ steps.test-meta.outputs.build_date }}-${{ steps.test-meta.outputs.short_sha }}"
+          fi
+          echo "tags<<EOF" >> $GITHUB_OUTPUT
+          echo "$TAGS" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
+
+      - name: Build and Push Nightly Image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.test-tags.outputs.tags }}
+
+      - name: Post build notifications
+        run: echo "Test Docker image has been built and pushed successfully"
+
+  build-release-image:
+    if: github.event_name == 'workflow_dispatch' || (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v'))
+    runs-on: ubuntu-latest
+    env:
+      DOCKER_HUB_USERNAME: ${{ secrets.DOCKER_HUB_USERNAME }}
+      GHCR_OWNER: soulter
+      HAS_GHCR_TOKEN: ${{ secrets.GHCR_GITHUB_TOKEN != '' }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 1
+          fetch-tag: true
 
       - name: Get latest tag (only on manual trigger)
         id: get-latest-tag
@@ -27,21 +134,22 @@ jobs:
         if: github.event_name == 'workflow_dispatch'
         run: git checkout ${{ steps.get-latest-tag.outputs.latest_tag }}
 
-      - name: Check if version is pre-release
-        id: check-prerelease
+      - name: Compute release metadata
+        id: release-meta
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
             version="${{ steps.get-latest-tag.outputs.latest_tag }}"
           else
-            version="${{ github.ref_name }}"
+            version="${GITHUB_REF#refs/tags/}"
           fi
           if [[ "$version" == *"beta"* ]] || [[ "$version" == *"alpha"* ]]; then
             echo "is_prerelease=true" >> $GITHUB_OUTPUT
-            echo "Version $version is a pre-release, will not push latest tag"
+            echo "Version $version marked as pre-release"
           else
             echo "is_prerelease=false" >> $GITHUB_OUTPUT
-            echo "Version $version is a stable release, will push latest tag"
+            echo "Version $version marked as stable"
           fi
+          echo "version=$version" >> $GITHUB_OUTPUT
 
       - name: Build Dashboard
         run: |
@@ -67,23 +175,24 @@ jobs:
           password: ${{ secrets.DOCKER_HUB_PASSWORD }}
 
       - name: Login to GitHub Container Registry
+        if: env.HAS_GHCR_TOKEN == 'true'
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
-          username: Soulter
+          username: ${{ env.GHCR_OWNER }}
           password: ${{ secrets.GHCR_GITHUB_TOKEN }}
 
-      - name: Build and Push Docker to DockerHub and Github GHCR
+      - name: Build and Push Release Image
         uses: docker/build-push-action@v6
         with:
           context: .
           platforms: linux/amd64,linux/arm64
           push: true
           tags: |
-            ${{ steps.check-prerelease.outputs.is_prerelease == 'false' && format('{0}/astrbot:latest', secrets.DOCKER_HUB_USERNAME) || '' }}
-            ${{ secrets.DOCKER_HUB_USERNAME }}/astrbot:${{ github.event_name == 'workflow_dispatch' && steps.get-latest-tag.outputs.latest_tag || github.ref_name }}
-            ${{ steps.check-prerelease.outputs.is_prerelease == 'false' && 'ghcr.io/soulter/astrbot:latest' || '' }}
-            ghcr.io/soulter/astrbot:${{ github.event_name == 'workflow_dispatch' && steps.get-latest-tag.outputs.latest_tag || github.ref_name }}
+            ${{ steps.release-meta.outputs.is_prerelease == 'false' && format('{0}/astrbot:latest', env.DOCKER_HUB_USERNAME) || '' }}
+            ${{ steps.release-meta.outputs.is_prerelease == 'false' && env.HAS_GHCR_TOKEN == 'true' && format('ghcr.io/{0}/astrbot:latest', env.GHCR_OWNER) || '' }}
+            ${{ format('{0}/astrbot:{1}', env.DOCKER_HUB_USERNAME, steps.release-meta.outputs.version) }}
+            ${{ env.HAS_GHCR_TOKEN == 'true' && format('ghcr.io/{0}/astrbot:{1}', env.GHCR_OWNER, steps.release-meta.outputs.version) || '' }}
 
       - name: Post build notifications
-        run: echo "Docker image has been built and pushed successfully"
+        run: echo "Release Docker image has been built and pushed successfully"

.github/workflows/smoke_test.yml

@@ -0,0 +1,58 @@
+name: Smoke Test
+
+on:
+  push:
+    branches:
+      - master
+    paths-ignore:
+      - 'README*.md'
+      - 'changelogs/**'
+      - 'dashboard/**'
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  smoke-test:
+    name: Run smoke tests
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.12'
+      
+      - name: Install UV package manager
+        run: |
+          pip install uv
+
+      - name: Install dependencies
+        run: |
+          uv sync
+        timeout-minutes: 15
+
+      - name: Run smoke tests
+        run: |
+          uv run main.py &
+          APP_PID=$!
+
+          echo "Waiting for application to start..."
+          for i in {1..60}; do
+            if curl -f http://localhost:6185 > /dev/null 2>&1; then
+              echo "Application started successfully!"
+              kill $APP_PID
+              exit 0
+            fi
+            sleep 1
+          done
+
+          echo "Application failed to start within 30 seconds"
+          kill $APP_PID 2>/dev/null || true
+          exit 1
+        timeout-minutes: 2

.github/workflows/stale.yml

@@ -1,27 +1,64 @@
-# This workflow warns and then closes issues and PRs that have had no activity for a specified amount of time.
+# 本工作流用于标记并关闭长期不活跃的 Issue。
+# 目前仅针对带 `bug` 标签的 Issue 生效，不会处理 PR。
 #
-# You can adjust the behavior by modifying this file.
-# For more information, see:
-# https://github.com/actions/stale
-name: Mark stale issues and pull requests
+# 文档: https://github.com/actions/stale
+name: Mark stale bug issues
 
 on:
   schedule:
-  - cron: '21 23 * * *'
+    # 每天 UTC 08:30 执行 (北京时间 16:30)
+    - cron: '30 8 * * *'
+  workflow_dispatch:
+    inputs:
+      dry-run:
+        description: '仅预览, 不实际执行 (Dry run mode)'
+        required: false
+        default: true
+        type: boolean
 
 jobs:
   stale:
-
     runs-on: ubuntu-latest
     permissions:
       issues: write
-      pull-requests: write
 
     steps:
-    - uses: actions/stale@v9
-      with:
-        repo-token: ${{ secrets.GITHUB_TOKEN }}
-        stale-issue-message: 'Stale issue message'
-        stale-pr-message: 'Stale pull request message'
-        stale-issue-label: 'no-issue-activity'
-        stale-pr-label: 'no-pr-activity'
+      - uses: actions/stale@v10
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          operations-per-run: 200
+
+          # 只处理带 bug 标签的 Issue
+          any-of-labels: 'bug'
+
+          # 不处理 PR
+          days-before-pr-stale: -1
+          days-before-pr-close: -1
+
+          # 不活跃判定与关闭策略: 先标记 stale, 再延迟关闭
+          days-before-issue-stale: 60
+          days-before-issue-close: 30
+
+          stale-issue-label: 'stale'
+          stale-issue-message: |
+            This issue has been automatically marked as **stale** because it has not had any activity.
+            It will be closed in a certain period of time if no further activity occurs.
+            If this issue is still relevant, please leave a comment.
+
+            ---
+
+            该 Issue 已较长时间无活动, 已被标记为 `stale`。
+            如无后续活动, 将在一段时间后自动关闭。
+            如仍需跟进, 请回复评论。
+          close-issue-message: |
+            This issue has been automatically closed due to inactivity.
+            If the problem still exists, feel free to reopen or create a new issue with updated information.
+
+            ---
+
+            该 Issue 因长期无活动已自动关闭。
+            如问题仍存在, 欢迎补充复现信息并重新打开或新建 Issue。
+
+          remove-stale-when-updated: true
+
+          debug-only: ${{ github.event_name == 'workflow_dispatch' && inputs.dry-run }}

.gitignore

@@ -1,33 +1,56 @@
+# Python related
 __pycache__
-botpy.log
-.vscode
+.mypy_cache
 .venv*
-.idea
-data_v2.db
-data_v3.db
-configs/session
-configs/config.yaml
-**/.DS_Store
-temp
-cmd_config.json
-data
-cookies.json
-logs/
-addons/plugins
+.conda/
+uv.lock
 .coverage
 
+# IDE and editors
+.vscode
+.idea
 
+# Logs and temporary files
+botpy.log
+logs/
+temp
+cookies.json
+
+# Data files
+data_v2.db
+data_v3.db
+data
+configs/session
+configs/config.yaml
+cmd_config.json
+
+# Plugins
+addons/plugins
+astrbot/builtin_stars/python_interpreter/workplace
 tests/astrbot_plugin_openai
-chroma
+
+# Dashboard
 dashboard/node_modules/
 dashboard/dist/
-.DS_Store
 package-lock.json
 package.json
+yarn.lock
+
+# Operating System
+**/.DS_Store
+.DS_Store
+
+# AstrBot specific
+.astrbot
+astrbot.lock
+
+# Other
+chroma
 venv/*
-packages/python_interpreter/workplace
-.venv/*
-.conda/
-.idea
 pytest.ini
-.astrbot
+AGENTS.md
+IFLOW.md
+
+# genie_tts data
+CharacterModels/
+GenieData/

.pre-commit-config.yaml

@@ -6,8 +6,20 @@ ci:
   autoupdate_schedule: weekly
   autoupdate_commit_msg: ":balloon: pre-commit autoupdate"
 repos:
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.2
-    hooks:
-      - id: ruff
-      - id: ruff-format
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.14.1
+  hooks:
+    # Run the linter.
+    - id: ruff-check
+      types_or: [ python, pyi ]
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format
+      types_or: [ python, pyi ]
+      
+- repo: https://github.com/asottile/pyupgrade
+  rev: v3.21.0
+  hooks:
+    - id: pyupgrade
+      args: [--py310-plus]

AGENTS.md

@@ -0,0 +1,33 @@
+## Setup commands
+
+### Core
+
+```
+uv sync
+uv run main.py
+```
+
+Exposed an API server on `http://localhost:6185` by default.
+
+### Dashboard(WebUI)
+
+```
+cd dashboard
+pnpm install # First time only. Use npm install -g pnpm if pnpm is not installed.
+pnpm dev
+```
+
+Runs on `http://localhost:3000` by default.
+
+## Dev environment tips
+
+1. When modifying the WebUI, be sure to maintain componentization and clean code. Avoid duplicate code.
+2. Do not add any report files such as xxx_SUMMARY.md.
+3. After finishing, use `ruff format .` and `ruff check .` to format and check the code.
+4. When committing, ensure to use conventional commits messages, such as `feat: add new agent for data analysis` or `fix: resolve bug in provider manager`.
+5. Use English for all new comments.
+
+## PR instructions
+
+1. Title format: use conventional commit messages
+2. Use English to write PR title and descriptions.

CONTRIBUTING.md

@@ -0,0 +1,90 @@
+# CONTRIBUTING
+
+## 贡献指南
+
+首先，感谢您花时间做出贡献！❤️
+
+所有类型的贡献都受到鼓励和重视。有关不同的帮助方式和处理方式的详细信息，请参阅[目录](#目录)。在做出贡献之前，请确保阅读相关部分。这将使我们维护人员的工作变得更加容易，并为所有参与者带来顺畅的体验。社区期待您的贡献。🎉
+
+### 目录
+
+- [报告问题](#报告问题)
+- [提交代码更改](#提交代码更改)
+
+### 报告问题
+
+如果您在使用 AstrBot 时遇到任何问题，请按照以下步骤报告：
+
+1. **检查现有问题**：在提交新问题之前，请先检查 [Issues](https://github.com/AstrBotDevs/AstrBot/issues) 中是否已经存在类似的问题。
+2. **创建新问题**：如果没有类似的问题，请创建一个新问题。请确保提供以下信息：
+   - 问题的简要描述
+   - 重现问题的步骤
+   - 预期结果和实际结果
+   - 相关日志或错误消息
+
+### 提交代码更改
+
+#### 分支命名
+
+我们使用 `fix/` 前缀来修复错误，使用 `feat/` 前缀来添加新功能。对于 `fix/` 分支，请使用简短的描述，或者直接使用 Issue 编号。例如：`fix/1234` 或者 `fix/1234-login-typo`。对于 `feat/` 分支，请使用简短的描述，例如：`feat/add-user-profile`。
+
+#### PR 描述
+
+- 请使用英文描述您的 PR。
+- 标题请使用 `fix: `, `feat: `, `docs: `, `style: `, `refactor: `, `test: `, `chore: ` 等语义化前缀，并简要描述更改内容。如：`fix: correct login page typo`。
+
+#### 代码规范
+
+##### Core
+
+我们使用 Ruff 作为代码格式化和静态分析工具。在提交代码之前，请运行以下命令以确保代码符合规范：
+
+```bash
+ruff format .
+ruff check .
+```
+
+如果您使用 VSCode，可以安装 `Ruff` 插件。
+
+
+## Contributing Guide
+
+First off, thanks for taking the time to contribute! ❤️
+
+All types of contributions are encouraged and valued. See the [Table of Contents](#table-of-contents) for different ways to help and details about how this project handles them. Please make sure to read the relevant section before making your contribution. It will make it a lot easier for us maintainers and smooth out the experience for all involved. The community looks forward to your contributions. 🎉
+
+### Table of Contents
+
+- [Reporting Issues](#reporting-issues)
+- [Pull Requests](#pull-requests)
+
+### Reporting Issues
+
+If you encounter any issues while using AstrBot, please follow these steps to report them:
+1. **Check Existing Issues**: Before submitting a new issue, please check if a similar issue already exists in the [Issues](https://github.com/AstrBotDevs/AstrBot/issues) section of the repository.
+2. **Create a New Issue**: If no similar issue exists, please create a new issue. Make sure to provide the following information:
+   - A brief description of the issue
+   - Steps to reproduce the issue
+   - Expected and actual results
+   - Relevant logs or error messages
+
+### Pull Requests
+
+#### Branch Naming
+
+We use the `fix/` prefix for bug fixes and the `feat/` prefix for new features. For `fix/` branches, please use a short description or directly use the Issue number, e.g., `fix/1234` or `fix/1234-login-typo`. For `feat/` branches, please use a short description, e.g., `feat/add-user-profile`.
+
+#### PR Description
+- Please use English to describe your PR.
+- Use semantic prefixes like `fix: `, `feat: `, `docs: `, `style: `, `refactor: `, `test: `, `chore: ` in the title, followed by a brief description of the changes, e.g., `fix: correct login page typo`.
+
+#### Code Style
+
+##### Core
+
+We use Ruff as our code formatter and static analysis tool. Before submitting your code, please run the following commands to ensure your code adheres to the style guidelines:
+
+```bash
+ruff format .
+ruff check .
+```

Dockerfile

@@ -4,8 +4,6 @@ WORKDIR /AstrBot
 COPY . /AstrBot/
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    nodejs \
-    npm \
     gcc \
     build-essential \
     python3-dev \
@@ -13,23 +11,22 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl-dev \
     ca-certificates \
     bash \
+    ffmpeg \
+    curl \
+    gnupg \
+    git \
     && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
-RUN python -m pip install uv
+RUN apt-get update && apt-get install -y curl gnupg \
+    && curl -fsSL https://deb.nodesource.com/setup_lts.x | bash - \
+    && apt-get install -y nodejs
+
+RUN python -m pip install uv \
+    && echo "3.11" > .python-version
 RUN uv pip install -r requirements.txt --no-cache-dir --system
-RUN uv pip install socksio uv pyffmpeg pilk --no-cache-dir --system
-
-# 释出 ffmpeg
-RUN python -c "from pyffmpeg import FFmpeg; ff = FFmpeg();"
-
-# add /root/.pyffmpeg/bin/ffmpeg to PATH, inorder to use ffmpeg
-RUN echo 'export PATH=$PATH:/root/.pyffmpeg/bin' >> ~/.bashrc
-
-EXPOSE 6185 
-EXPOSE 6186
-
-CMD [ "python", "main.py" ]
-
+RUN uv pip install socksio uv pilk --no-cache-dir --system
 
+EXPOSE 6185
 
+CMD ["python", "main.py"]

Dockerfile_with_node

@@ -1,35 +0,0 @@
-FROM python:3.10-slim
-
-WORKDIR /AstrBot
-
-COPY . /AstrBot/
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    gcc \
-    build-essential \
-    python3-dev \
-    libffi-dev \
-    libssl-dev \
-    curl \
-    unzip \
-    ca-certificates \
-    bash \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Installation of Node.js
-ENV NVM_DIR="/root/.nvm"
-RUN curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.2/install.sh | bash && \
-    . "$NVM_DIR/nvm.sh" && \
-    nvm install 22 && \
-    nvm use 22
-RUN /bin/bash -c ". \"$NVM_DIR/nvm.sh\" && node -v && npm -v"
-
-RUN python -m pip install uv
-RUN uv pip install -r requirements.txt --no-cache-dir --system
-RUN uv pip install socksio uv pyffmpeg --no-cache-dir --system
-
-EXPOSE 6185
-EXPOSE 6186
-
-CMD ["python", "main.py"]

EULA.md

@@ -0,0 +1,244 @@
+# 最终用户许可协议（EULA）
+
+> 我们热爱开源软件，并始终致力于为所有用户提供健康、安全、可靠的使用体验。 ❤️
+
+For English edition, please refer to the section below the Chinese version.
+
+**最后更新：** 2026-01-12
+
+感谢您使用 **AstrBot**。
+在使用本项目之前，请仔细阅读以下声明内容。
+
+**您一旦安装、运行或使用本项目，即表示您已阅读、理解并同意本声明中的全部内容。**
+
+## 1. 项目性质
+
+AstrBot 是一个遵循 **GNU Affero General Public License v3（AGPLv3）** 协议发布的**免费开源软件项目**。
+
+* 截至目前，AstrBot 项目未开展任何形式的商业化服务，AstrBot 团队也未通过本项目向用户提供任何收费服务。若您因使用 AstrBot 被要求付费，请务必提高警惕，谨防诈骗行为。
+* AstrBot 的代码实现未对任何第三方系统进行逆向工程、破解、反编译或绕过安全机制等行为。AstrBot 仅使用并支持各即时通讯（IM）平台官方公开提供的机器人接入接口、开放平台能力或相关通信协议进行集成与通信。
+
+## 2. 无担保声明
+
+AstrBot 按“**现状（as is）**”提供，不附带任何形式的明示或暗示担保。
+
+AstrBot 团队不对以下内容作出任何保证：
+
+* 系统本身的安全性、可靠性或稳定性；
+* 任何第三方插件的安全性、正确性或可信度；
+* 任何第三方 AI 模型或外部服务 API 的可用性、质量、准确性或安全性；
+* 本软件对任何特定用途的适用性。
+
+**您使用本软件所产生的一切风险均由您自行承担。**
+
+## 3. 第三方插件与服务
+
+* AstrBot 支持第三方插件及外部 AI 服务接入；
+* AstrBot 团队**不对任何第三方插件、扩展或服务进行审计、控制、背书或担保**；
+* 因使用第三方插件或服务所产生的任何风险、损失、数据泄露或法律后果，均由用户自行承担。
+* 第三方插件指代的是非 AstrBot 自带的插件，AstrBot 自带的插件指代的是插件实现代码已经包含在 AstrBotDevs/AstrBot 代码库中的插件。插件市场中的插件都是第三方插件。
+
+## 4. 使用与内容限制
+
+您同意不会将 AstrBot 用于以下行为：
+
+* 输入、生成、传播或处理任何违法、极端、暴力、色情、仇恨、辱骂或其他有害内容；
+* 从事违反您所在国家或地区法律法规，或任何适用国际法律的行为；
+* 试图绕过、关闭、削弱或破坏本系统内置的安全机制或内容限制。
+* 任何侵犯他人合法权益、损害他人和自己身心健康、涉及个人隐私、个人信息等敏感内容的内容。
+
+## 5. 项目用途说明
+
+AstrBot 是一个**工具型对话与 Agent 系统**，在**安全、健康、友善**的前提下提供有限的人性化交互能力。
+
+项目的主要目标是：
+
+* 提供 Agent 能力与自动化辅助；
+* 帮助用户提升工作、学习和信息处理效率；
+* 在合理范围内提供友好的人机交互体验。
+* 辅助用户成长，提供有益于用户身心健康的内容。
+
+## 6. 安全措施说明
+
+AstrBot 团队**已尽合理努力在技术和策略层面设置安全与内容约束机制**，以引导系统输出健康、友善、安全的内容。
+
+但请理解：
+
+* 世界上任何的系统均无法保证完全无误、绝对安全或无法被滥用；
+* 用户仍有责任自行合理配置、监督并正确使用本系统。
+
+如果您要关闭 AstrBot 默认启用的“健康模式”，请在 cmd_config.json 中将 `provider_settings.llm_safety_mode` 设置为 `False`。但请注意，关闭健康模式不是推荐的使用方式，可能导致系统输出不安全或不适当的内容。关闭该功能所产生的任何风险与后果，均由用户自行承担，AstrBot 团队不对此承担任何责任。
+
+## 7. 心理健康提示
+
+如果您在使用本项目过程中因系统输出内容而感到心理不适、情绪困扰，  
+或您本身正处于心理压力较大、情绪不稳定、焦虑、抑郁等状态并因此使用本项目，  
+请优先考虑寻求来自专业人士的帮助，例如心理咨询师、心理医生或当地心理援助机构。
+
+如遇紧急情况（例如存在自伤或他伤风险），请立即联系当地的紧急救助电话或专业机构。
+
+## 8. 统计信息与隐私说明
+
+AstrBot 可能会收集有限的匿名统计信息，用于了解系统使用情况、发现问题以及持续改进项目。
+
+所收集的统计信息仅包括与系统运行和功能使用相关的基础技术指标，例如功能使用频率、错误信息等。
+
+AstrBot **不会收集、上传或存储您的对话内容、消息正文、输入文本，或任何能够识别您个人身份的敏感信息**。
+
+您可以手动关闭此项功能，通过在系统环境变量中设置 `ASTRBOT_DISABLE_METRICS=1` 来禁用匿名统计信息收集。
+
+## 9. 责任限制
+
+在法律允许的最大范围内，AstrBot 团队不对因以下原因导致的任何直接或间接损失承担责任，包括但不限于：
+
+* 使用或无法使用本软件；
+* 使用第三方插件或服务；
+* 系统生成的内容或输出；
+* 数据丢失、服务中断或安全事件。
+
+## 10. 条款的接受
+
+您一旦安装、运行、修改或使用 AstrBot，即确认：
+
+* 您已阅读并理解本声明内容；
+* 您同意并接受上述所有条款；
+* 您对自身使用行为承担全部责任。
+
+如您不同意本声明的任何内容，请勿使用本项目。
+
+## 11. 许可与版权
+
+AstrBot 的源代码、文档及相关内容受版权法及相关法律保护。
+
+在遵守本声明及 AGPLv3 协议的前提下，AstrBot 授予您一项非独占、不可转让、不可再许可的许可，用于下载、安装、运行、修改和分发本软件。
+
+除非法律另有规定或本声明另有明确说明，AstrBot 团队保留本项目的所有未明确授予的权利。
+
+## 12. 适用法律
+
+本声明的解释与适用应遵循您所在地或项目发布地适用的法律法规。
+
+如本声明的任何条款被认定为无效或不可执行，其余条款仍然有效。
+
+---
+
+# EULA
+
+> We love open-source software and are always committed to providing all users with a healthy, safe, and reliable experience. ❤️
+
+**Last updated:** January 12, 2026
+
+Thank you for using **AstrBot**.
+Please read the following notice carefully before using this project.
+
+**By installing, running, or using this project, you acknowledge that you have read, understood, and agreed to all the terms stated below.**
+
+## 1. Nature of the Project
+
+AstrBot is a **free and open-source software project** released under the **GNU Affero General Public License v3 (AGPLv3)**.
+
+* AstrBot does not constitute any form of commercial service;
+* The AstrBot Team does not provide any paid services through this project;
+* AstrBot’s implementation does not involve reverse engineering, cracking, decompilation, or circumvention of security mechanisms of any third-party systems. AstrBot only uses and supports officially published bot integration interfaces, open platform capabilities, or related communication protocols provided by instant messaging (IM) platforms for integration and communication.
+
+## 2. No Warranty
+
+AstrBot is provided **“as is”**, without any express or implied warranties.
+
+The AstrBot Team makes no guarantees regarding:
+
+* The security, reliability, or stability of the system;
+* The security, correctness, or trustworthiness of any third-party plugins;
+* The availability, quality, accuracy, or safety of any third-party AI model APIs or external services;
+* The fitness of the software for any particular purpose.
+
+**All risks arising from the use of this software are borne solely by the user.**
+
+## 3. Third-Party Plugins and Services
+
+* AstrBot supports third-party plugins and external AI services;
+* The AstrBot Team does **not audit, control, endorse, or guarantee** any third-party plugins, extensions, or services;
+* Any risks, losses, data leaks, or legal consequences arising from the use of third-party plugins or services are solely the responsibility of the user;
+* “Third-party plugins” refer to plugins that are not built into AstrBot. Built-in plugins are those whose implementation code is included in the AstrBotDevs/AstrBot repository. All plugins available in the plugin marketplace are third-party plugins.
+
+## 4. Usage and Content Restrictions
+
+You agree not to use AstrBot for any of the following activities:
+
+* Inputting, generating, distributing, or processing any illegal, extremist, violent, pornographic, hateful, abusive, or otherwise harmful content;
+* Engaging in activities that violate the laws or regulations of your country or region, or any applicable international laws;
+* Attempting to bypass, disable, weaken, or undermine the built-in safety mechanisms or content restrictions of the system;
+* Any activities that infringe upon the legitimate rights and interests of others, harm the physical or mental well-being of yourself or others, or involve personal privacy or sensitive personal information.
+
+## 5. Intended Use
+
+AstrBot is a **tool-oriented conversational and agent system** that provides limited human-like interaction capabilities under the principles of **safety, health, and friendliness**.
+
+The primary goals of the project are to:
+
+* Provide agent capabilities and automation assistance;
+* Help users improve efficiency in work, study, and information processing;
+* Offer a friendly human–computer interaction experience within reasonable boundaries;
+* Support user growth and provide content beneficial to users’ physical and mental well-being.
+
+## 6. Safety Measures
+
+The AstrBot Team has made **reasonable efforts** at both technical and policy levels to implement safety and content restriction mechanisms, guiding the system to produce healthy, friendly, and safe outputs.
+
+However, please understand that:
+
+* No system in the world can be guaranteed to be completely error-free, absolutely secure, or immune to misuse;
+* Users remain responsible for properly configuring, supervising, and using the system.
+
+If you wish to disable AstrBot’s default “Safety Mode,” please set `provider_settings.llm_safety_mode` to `False` in `cmd_config.json`. However, please note that disabling Safety Mode is not recommended and may lead to unsafe or inappropriate outputs. Any risks or consequences arising from disabling this feature are solely borne by the user, and the AstrBot Team assumes no responsibility.
+
+## 7. Mental Health Notice
+
+If you experience psychological discomfort or emotional distress due to system outputs during use,
+or if you are experiencing significant psychological stress, emotional instability, anxiety, or depression and are using this project for such reasons,
+please prioritize seeking help from qualified professionals, such as psychologists, psychiatrists, or local mental health support services.
+
+In case of emergency (for example, if there is a risk of self-harm or harm to others), please immediately contact your local emergency number or professional crisis support services.
+
+## 8. Metrics and Privacy
+
+AstrBot may collect a limited amount of anonymous usage statistics to understand system usage, identify issues, and continuously improve the project.
+
+Collected metrics are limited to basic technical indicators related to system operation and feature usage, such as feature usage frequency and error information.
+
+AstrBot **does not collect, upload, or store your conversation content, message bodies, input text, or any personally identifiable or sensitive information**.
+
+You may manually disable this feature by setting the environment variable `ASTRBOT_DISABLE_METRICS=1` to turn off anonymous metrics collection.
+
+## 9. Limitation of Liability
+
+To the maximum extent permitted by law, the AstrBot Team shall not be liable for any direct or indirect losses arising from, including but not limited to:
+
+* The use or inability to use this software;
+* The use of third-party plugins or services;
+* Generated content or system outputs;
+* Data loss, service interruptions, or security incidents.
+
+## 10. Acceptance of Terms
+
+By installing, running, modifying, or using AstrBot, you confirm that:
+
+* You have read and understood this Notice;
+* You agree to and accept all the terms stated above;
+* You assume full responsibility for your use of the software.
+
+If you do not agree with any part of this Notice, please do not use this project.
+
+## 11. License and Copyright
+
+The source code, documentation, and related materials of AstrBot are protected by copyright laws and applicable regulations.
+
+Subject to compliance with this Notice and the AGPLv3 license, AstrBot grants you a non-exclusive, non-transferable, non-sublicensable license to download, install, run, modify, and distribute this software.
+
+Unless otherwise required by law or expressly stated in this Notice, the AstrBot Team reserves all rights not expressly granted.
+
+## 12. Governing Law
+
+The interpretation and application of this Notice shall be governed by the laws and regulations applicable in your jurisdiction or the jurisdiction where the project is released.
+
+If any provision of this Notice is held to be invalid or unenforceable, the remaining provisions shall remain in full force and effect.

Makefile

@@ -0,0 +1,32 @@
+.PHONY: worktree worktree-add worktree-rm
+
+WORKTREE_DIR ?= ../astrbot_worktree
+BRANCH ?= $(word 2,$(MAKECMDGOALS))
+BASE ?= $(word 3,$(MAKECMDGOALS))
+BASE ?= master
+
+worktree:
+	@echo "Usage:"
+	@echo "  make worktree-add <branch> [base-branch]"
+	@echo "  make worktree-rm  <branch>"
+
+worktree-add:
+ifeq ($(strip $(BRANCH)),)
+	$(error Branch name required. Usage: make worktree-add <branch> [base-branch])
+endif
+	@mkdir -p $(WORKTREE_DIR)
+	git worktree add $(WORKTREE_DIR)/$(BRANCH) -b $(BRANCH) $(BASE)
+
+worktree-rm:
+ifeq ($(strip $(BRANCH)),)
+	$(error Branch name required. Usage: make worktree-rm <branch>)
+endif
+	@if [ -d "$(WORKTREE_DIR)/$(BRANCH)" ]; then \
+		git worktree remove $(WORKTREE_DIR)/$(BRANCH); \
+	else \
+		echo "Worktree $(WORKTREE_DIR)/$(BRANCH) not found."; \
+	fi
+
+# Swallow extra args (branch/base) so make doesn't treat them as targets
+%:
+	@true

README.md

@@ -1,48 +1,86 @@
-<img width="430" height="31" alt="image" src="https://github.com/user-attachments/assets/474c822c-fab7-41be-8c23-6dae252823ed" /><p align="center">
- 
 ![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
 
-</p>
-
 <div align="center">
 
-_✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
 
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ja.md">日本語</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_zh-TW.md">繁體中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_fr.md">Français</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ru.md">Русский</a>
+
+<div>
 <a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot?style=for-the-badge&color=76bad9)](https://github.com/Soulter/AstrBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
-<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
-<a  href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
-<a  href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
-[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e.svg?style=for-the-badge&color=76bad9)](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fstats&query=v&label=7日消息量&cacheSeconds=3600&style=for-the-badge&color=3b618e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%E4%B8%AA&style=for-the-badge&label=%E6%8F%92%E4%BB%B6%E5%B8%82%E5%9C%BA&cacheSeconds=3600)
-
-<a href="https://github.com/Soulter/AstrBot/blob/master/README_en.md">English</a> ｜
-<a href="https://github.com/Soulter/AstrBot/blob/master/README_ja.md">日本語</a> ｜
-<a href="https://astrbot.app/">查看文档</a> ｜
-<a href="https://github.com/Soulter/AstrBot/issues">问题提交</a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
 </div>
 
-AstrBot 是一个开源的一站式 Agentic 聊天机器人平台及开发框架。
+<br>
 
-## ✨ 主要功能
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
+<img src="https://deepwiki.com/badge.svg" href="https://deepwiki.com/AstrBotDevs/AstrBot">
+<a href="https://zread.ai/AstrBotDevs/AstrBot" target="_blank"><img src="https://img.shields.io/badge/Ask_Zread-_.svg?style=flat&color=00b0aa&labelColor=000000&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iMTYiIGhlaWdodD0iMTYiIHZpZXdCb3g9IjAgMCAxNiAxNiIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTQuOTYxNTYgMS42MDAxSDIuMjQxNTZDMS44ODgxIDEuNjAwMSAxLjYwMTU2IDEuODg2NjQgMS42MDE1NiAyLjI0MDFWNC45NjAxQzEuNjAxNTYgNS4zMTM1NiAxLjg4ODEgNS42MDAxIDIuMjQxNTYgNS42MDAxSDQuOTYxNTZDNS4zMTUwMiA1LjYwMDEgNS42MDE1NiA1LjMxMzU2IDUuNjAxNTYgNC45NjAxVjIuMjQwMUM1LjYwMTU2IDEuODg2NjQgNS4zMTUwMiAxLjYwMDEgNC45NjE1NiAxLjYwMDFaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00Ljk2MTU2IDEwLjM5OTlIMi4yNDE1NkMxLjg4ODEgMTAuMzk5OSAxLjYwMTU2IDEwLjY4NjQgMS42MDE1NiAxMS4wMzk5VjEzLjc1OTlDMS42MDE1NiAxNC4xMTM0IDEuODg4MSAxNC4zOTk5IDIuMjQxNTYgMTQuMzk5OUg0Ljk2MTU2QzUuMzE1MDIgMTQuMzk5OSA1LjYwMTU2IDE0LjExMzQgNS42MDE1NiAxMy43NTk5VjExLjAzOTlDNS42MDE1NiAxMC42ODY0IDUuMzE1MDIgMTAuMzk5OSA0Ljk2MTU2IDEwLjM5OTlaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik0xMy43NTg0IDEuNjAwMUgxMS4wMzg0QzEwLjY4NSAxLjYwMDEgMTAuMzk4NCAxLjg4NjY0IDEwLjM5ODQgMi4yNDAxVjQuOTYwMUMxMC4zOTg0IDUuMzEzNTYgMTAuNjg1IDUuNjAwMSAxMS4wMzg0IDUuNjAwMUgxMy43NTg0QzE0LjExMTkgNS42MDAxIDE0LjM5ODQgNS4zMTM1NiAxNC4zOTg0IDQuOTYwMVYyLjI0MDFDMTQuMzk4NCAxLjg4NjY0IDE0LjExMTkgMS42MDAxIDEzLjc1ODQgMS42MDAxWiIgZmlsbD0iI2ZmZiIvPgo8cGF0aCBkPSJNNCAxMkwxMiA0TDQgMTJaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00IDEyTDEyIDQiIHN0cm9rZT0iI2ZmZiIgc3Ryb2tlLXdpZHRoPSIxLjUiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIvPgo8L3N2Zz4K&logoColor=ffffff" alt="zread"/></a>
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?color=76bad9"/></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%E4%B8%AA&label=%E6%8F%92%E4%BB%B6%E5%B8%82%E5%9C%BA&cacheSeconds=3600">
+<img src="https://gitcode.com/Soulter/AstrBot/star/badge.svg" href="https://gitcode.com/Soulter/AstrBot">
+</div>
 
-1. **大模型对话**。支持接入多种大模型服务。支持多模态、工具调用、MCP、原生知识库、人设等功能。
-2. **多消息平台支持**。支持接入 QQ、企业微信、微信公众号、飞书、Telegram、钉钉、Discord、KOOK 等平台。支持速率限制、白名单、百度内容审核。
-3. **Agent**。完善适配的 Agentic 能力。支持多轮工具调用、内置沙盒代码执行器、网页搜索等功能。
-4. **插件扩展**。深度优化的插件机制，支持[开发插件](https://astrbot.app/dev/plugin.html)扩展功能，社区插件生态丰富。
-5. **WebUI**。可视化配置和管理机器人，功能齐全。
+<br>
 
-## ✨ 使用方式
+<a href="https://astrbot.app/">文档</a> ｜
+<a href="https://blog.astrbot.app/">Blog</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">路线图</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">问题提交</a>
+</div>
 
-#### Docker 部署
+AstrBot 是一个易用、高性能的 AI Agentic 个人 / 群聊助手。可在 QQ、Telegram、企业微信、飞书、钉钉、Slack、等数十款主流即时通讯软件上部署，此外还内置类似 OpenWebUI 的轻量化 ChatUI，为个人、开发者和团队打造可靠、可扩展的对话式智能基础设施。无论是个人 AI 伙伴、智能客服、自动化助手，还是企业知识库，AstrBot 都能在你的即时通讯软件平台的工作流中快速构建 AI 应用。
+
+![521771166-00782c4c-4437-4d97-aabc-605e3738da5c (1)](https://github.com/user-attachments/assets/61e7b505-f7db-41aa-a75f-4ef8f079b8ba)
+
+## 主要功能
+
+1. 💯 免费 & 开源。
+1. ✨ AI 大模型对话，多模态，Agent，MCP，Skills，知识库，人格设定，自动压缩对话。
+2. 🤖 支持接入 Dify、阿里云百炼、Coze 等智能体平台。
+2. 🌐 多平台，支持 QQ、企业微信、飞书、钉钉、微信公众号、Telegram、Slack 以及[更多](#支持的消息平台)。
+3. 📦 插件扩展，已有近 800 个插件可一键安装。
+5. 🛡️ [Agent Sandbox](https://docs.astrbot.app/use/astrbot-agent-sandbox.html) 隔离化环境，安全地执行任何代码、调用 Shell、会话级资源复用。
+6. 💻 WebUI 支持。
+7. 🌈 Web ChatUI 支持，ChatUI 内置代理沙盒、网页搜索等。
+8. 🌐 国际化（i18n）支持。
+
+<br>
+
+<table align="center">
+  <tr align="center">
+    <th>💙 角色扮演 & 情感陪伴</th>
+    <th>✨ 主动式 Agent</th>
+    <th>🚀 通用 Agentic 能力</th>
+    <th>🧩 900+ 社区插件</th>
+  </tr>
+  <tr>
+    <td align="center"><p align="center"><img width="984" height="1746" alt="99b587c5d35eea09d84f33e6cf6cfd4f" src="https://github.com/user-attachments/assets/89196061-3290-458d-b51f-afa178049f84" /></p></td>
+    <td align="center"><p align="center"><img width="976" height="1612" alt="c449acd838c41d0915cc08a3824025b1" src="https://github.com/user-attachments/assets/f75368b4-e022-41dc-a9e0-131c3e73e32e" /></p></td>
+    <td align="center"><p align="center"><img width="974" height="1732" alt="image" src="https://github.com/user-attachments/assets/e22a3968-87d7-4708-a7cd-e7f198c7c32e" /></p></td>
+    <td align="center"><p align="center"><img width="976" height="1734" alt="image" src="https://github.com/user-attachments/assets/0952b395-6b4a-432a-8a50-c294b7f89750" /></p></td>
+  </tr>
+</table>
+
+## 快速开始
+
+#### Docker 部署(推荐 🥳)
 
 推荐使用 Docker / Docker Compose 方式部署 AstrBot。
 
 请参阅官方文档 [使用 Docker 部署 AstrBot](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot) 。
 
+#### uv 部署
+
+```bash
+uvx astrbot
+```
+
 #### 宝塔面板部署
 
 AstrBot 与宝塔面板合作，已上架至宝塔面板。
@@ -65,7 +103,7 @@ AstrBot 已由雨云官方上架至云应用平台，可一键部署。
 
 社区贡献的部署方式。
 
-[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
 
 #### Windows 一键安装器部署
 
@@ -79,9 +117,7 @@ AstrBot 已由雨云官方上架至云应用平台，可一键部署。
 
 #### 手动部署
 
-> 推荐使用 `uv`。
-
-首先，安装 uv：
+首先安装 uv：
 
 ```bash
 pip install uv
@@ -96,53 +132,72 @@ uv run main.py
 
 或者请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html) 。
 
-## ⚡ 消息平台支持情况
+## 支持的消息平台
 
-| 平台    | 支持性 |
-| -------- | ------- |
-| QQ(官方机器人接口) | ✔    |
-| QQ(OneBot)      | ✔    |
-| Telegram   | ✔    |
-| 企业微信    | ✔    |
-| 微信客服    | ✔    |
-| 微信公众号    | ✔    |
-| 飞书   | ✔    |
-| 钉钉   | ✔    |
-| Slack   | ✔    |
-| Discord   | ✔    |
-| [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)   | ✔    |
-| [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)   | ✔    |
-| 微信对话开放平台 | 🚧    |
-| WhatsApp   | 🚧    |
-| 小爱音响   | 🚧    |
+**官方维护**
 
-## ⚡ 提供商支持情况
+- QQ (官方平台 & OneBot)
+- Telegram
+- 企微应用 & 企微智能机器人
+- 微信客服 & 微信公众号
+- 飞书
+- 钉钉
+- Slack
+- Discord
+- Satori
+- Misskey
+- Whatsapp (将支持)
+- LINE (将支持)
 
-| 名称    | 支持性 | 类型 | 备注 |
-| -------- | ------- | ------- | ------- |
-| OpenAI API | ✔    | 文本生成 | 也支持 DeepSeek、Gemini、Kimi、xAI 等兼容 OpenAI API 的服务 |
-| Claude API | ✔    | 文本生成 |  |
-| Google Gemini API | ✔    | 文本生成 |  |
-| Dify | ✔    | LLMOps |  |
-| 阿里云百炼应用 | ✔    | LLMOps |  |
-| Ollama | ✔    | 模型加载器 | 本地部署 DeepSeek、Llama 等开源语言模型 |
-| LM Studio | ✔    | 模型加载器 | 本地部署 DeepSeek、Llama 等开源语言模型 |
-| LLMTuner | ✔    | 模型加载器 | 本地加载 lora 等微调模型 |
-| [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74) | ✔    | 模型 API 及算力服务平台 |  |
-| [302.AI](https://share.302.ai/rr1M3l) | ✔    | 模型 API 服务平台 |  |
-| 硅基流动 | ✔    | 模型 API 服务平台 |  |
-| PPIO 派欧云 | ✔    | 模型 API 服务平台 |  |
-| OneAPI | ✔    | LLM 分发系统 |  |
-| Whisper | ✔    | 语音转文本 | 支持 API、本地部署 |
-| SenseVoice | ✔    | 语音转文本 | 本地部署 |
-| OpenAI TTS API | ✔    | 文本转语音 |  |
-| GSVI | ✔    | 文本转语音 | GPT-Sovits-Inference |
-| GPT-SoVITs | ✔    | 文本转语音 | GPT-Sovits-Inference |
-| FishAudio | ✔    | 文本转语音 | GPT-Sovits 作者参与的项目 |
-| Edge TTS | ✔    | 文本转语音 | Edge 浏览器的免费 TTS |
-| 阿里云百炼 TTS | ✔    | 文本转语音 |  |
-| Azure TTS | ✔    | 文本转语音 | Microsoft Azure TTS |
+**社区维护**
 
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
+
+## 支持的模型服务
+
+**大模型服务**
+
+- OpenAI 及兼容服务
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- 智谱 AI
+- DeepSeek
+- Ollama (本地部署)
+- LM Studio (本地部署)
+- [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [小马算力](https://www.tokenpony.cn/3YPyf)
+- [硅基流动](https://docs.siliconflow.cn/cn/usercases/use-siliconcloud-in-astrbot)
+- [PPIO 派欧云](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
+
+**LLMOps 平台**
+
+- Dify
+- 阿里云百炼应用
+- Coze
+
+**语音转文本服务**
+
+- OpenAI Whisper
+- SenseVoice
+
+**文本转语音服务**
+
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- 阿里云百炼 TTS
+- Azure TTS
+- Minimax TTS
+- 火山引擎 TTS
 
 ## ❤️ 贡献
 
@@ -157,43 +212,30 @@ uv run main.py
 AstrBot 使用 `ruff` 进行代码格式化和检查。
 
 ```bash
-git clone https://github.com/Soulter/AstrBot
+git clone https://github.com/AstrBotDevs/AstrBot
 pip install pre-commit
 pre-commit install
 ```
 
-## 🌟 支持
+## 🌍 社区
 
-- Star 这个项目！
-- 在[爱发电](https://afdian.com/a/soulter)支持我！
+### QQ 群组
 
-## ✨ Demo
+- 1 群：322154837
+- 3 群：630166526
+- 5 群：822130018
+- 6 群：753075035
+- 7 群：743746109
+- 8 群：1030353265
+- 开发者群：975206796
 
-<details><summary>👉 点击展开多张 Demo 截图 👈</summary>
+### Telegram 群组
 
-<div align='center'>
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
 
-<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
-
-_✨基于 Docker 的沙箱化代码执行器（Beta 测试）✨_
-
-<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
-
-_✨ 多模态、网页搜索、长文本转图片（可配置） ✨_
-
-<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
-<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
-
-_✨ 插件系统——部分插件展示 ✨_
-
-<img src="https://github.com/user-attachments/assets/0cdbf564-2f59-4da5-b524-ce0e7ef3d978" width=600>
-
-_✨ WebUI ✨_
-
-</div>
-
-</details>
+### Discord 群组
 
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
 
 ## ❤️ Special Thanks
 
@@ -203,24 +245,27 @@ _✨ WebUI ✨_
   <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
 </a>
 
-此外，本项目的诞生离不开以下开源项目：
+此外，本项目的诞生离不开以下开源项目的帮助：
 
 - [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - 伟大的猫猫框架
-- [wechatpy/wechatpy](https://github.com/wechatpy/wechatpy)
 
 ## ⭐ Star History
 
-> [!TIP] 
-> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我维护这个开源项目的动力 <3
+> [!TIP]
+> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我们维护这个开源项目的动力 <3
 
 <div align="center">
-    
-[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
 
 </div>
 
-![10k-star-banner-credit-by-kevin](https://github.com/user-attachments/assets/c97fc5fb-20b9-4bc8-9998-c20b930ab097)
+</details>
 
+<div align="center">
 
 _私は、高性能ですから!_
 
+陪伴与能力从来不应该是对立面。我们希望创造的是一个既能理解情绪、给予陪伴，也能可靠完成工作的机器人。
+
+

README_en.md

@@ -1,182 +1,255 @@
-<p align="center">
-    
-![6e1279651f16d7fdf4727558b72bbaf1](https://github.com/user-attachments/assets/ead4c551-fc3c-48f7-a6f7-afbfdb820512)
-
-</p>
+![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
 
 <div align="center">
 
-_✨ Easy-to-use Multi-platform LLM Chatbot & Development Framework ✨_
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README.md">中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ja.md">日本語</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_zh-TW.md">繁體中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_fr.md">Français</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ru.md">Русский</a>
 
+<br>
+
+<div>
 <a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
-<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg"/></a>
-<a  href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="Static Badge" src="https://img.shields.io/badge/QQ群-630166526-purple"></a>
-[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e.svg)](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fstats&query=v&label=7%E6%97%A5%E6%B6%88%E6%81%AF%E4%B8%8A%E8%A1%8C%E9%87%8F&cacheSeconds=3600)
-[![codecov](https://codecov.io/gh/Soulter/AstrBot/graph/badge.svg?token=FF3P5967B8)](https://codecov.io/gh/Soulter/AstrBot)
-
-<a href="https://astrbot.app/">Documentation</a> ｜
-<a href="https://github.com/Soulter/AstrBot/issues">Issue Tracking</a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
 </div>
 
-AstrBot is a loosely coupled, asynchronous chatbot and development framework that supports multi-platform deployment, featuring an easy-to-use plugin system and comprehensive Large Language Model (LLM) integration capabilities.
+<br>
 
-## ✨ Key Features
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
+<img src="https://deepwiki.com/badge.svg" href="https://deepwiki.com/AstrBotDevs/AstrBot">
+<a href="https://zread.ai/AstrBotDevs/AstrBot" target="_blank"><img src="https://img.shields.io/badge/Ask_Zread-_.svg?style=flat&color=00b0aa&labelColor=000000&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iMTYiIGhlaWdodD0iMTYiIHZpZXdCb3g9IjAgMCAxNiAxNiIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTQuOTYxNTYgMS42MDAxSDIuMjQxNTZDMS44ODgxIDEuNjAwMSAxLjYwMTU2IDEuODg2NjQgMS42MDE1NiAyLjI0MDFWNC45NjAxQzEuNjAxNTYgNS4zMTM1NiAxLjg4ODEgNS42MDAxIDIuMjQxNTYgNS42MDAxSDQuOTYxNTZDNS4zMTUwMiA1LjYwMDEgNS42MDE1NiA1LjMxMzU2IDUuNjAxNTYgNC45NjAxVjIuMjQwMUM1LjYwMTU2IDEuODg2NjQgNS4zMTUwMiAxLjYwMDEgNC45NjE1NiAxLjYwMDFaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00Ljk2MTU2IDEwLjM5OTlIMi4yNDE1NkMxLjg4ODEgMTAuMzk5OSAxLjYwMTU2IDEwLjY4NjQgMS42MDE1NiAxMS4wMzk5VjEzLjc1OTlDMS42MDE1NiAxNC4xMTM0IDEuODg4MSAxNC4zOTk5IDIuMjQxNTYgMTQuMzk5OUg0Ljk2MTU2QzUuMzE1MDIgMTQuMzk5OSA1LjYwMTU2IDE0LjExMzQgNS42MDE1NiAxMy43NTk5VjExLjAzOTlDNS42MDE1NiAxMC42ODY0IDUuMzE1MDIgMTAuMzk5OSA0Ljk2MTU2IDEwLjM5OTlaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik0xMy43NTg0IDEuNjAwMUgxMS4wMzg0QzEwLjY4NSAxLjYwMDEgMTAuMzk4NCAxLjg4NjY0IDEwLjM5ODQgMi4yNDAxVjQuOTYwMUMxMC4zOTg0IDUuMzEzNTYgMTAuNjg1IDUuNjAwMSAxMS4wMzg0IDUuNjAwMUgxMy43NTg0QzE0LjExMTkgNS42MDAxIDE0LjM5ODQgNS4zMTM1NiAxNC4zOTg0IDQuOTYwMVYyLjI0MDFDMTQuMzk4NCAxLjg4NjY0IDE0LjExMTkgMS42MDAxIDEzLjc1ODQgMS42MDAxWiIgZmlsbD0iI2ZmZiIvPgo8cGF0aCBkPSJNNCAxMkwxMiA0TDQgMTJaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00IDEyTDEyIDQiIHN0cm9rZT0iI2ZmZiIgc3Ryb2tlLXdpZHRoPSIxLjUiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIvPgo8L3N2Zz4K&logoColor=ffffff" alt="zread"/></a>
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?color=76bad9"/></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%20plugins&label=Marketplace&cacheSeconds=3600">
+<img src="https://gitcode.com/Soulter/AstrBot/star/badge.svg" href="https://gitcode.com/Soulter/AstrBot">
+</div>
 
-1. **LLM Conversations** - Supports various LLMs including OpenAI API, Google Gemini, Llama, Deepseek, ChatGLM, etc. Enables local model deployment via Ollama/LLMTuner. Features multi-turn dialogues, personality contexts, multimodal capabilities (image understanding), and speech-to-text (Whisper).
-2. **Multi-platform Integration** - Supports QQ (OneBot), QQ Channels, WeChat (Gewechat), Feishu, and Telegram. Planned support for DingTalk, Discord, WhatsApp, and Xiaomi Smart Speakers. Includes rate limiting, whitelisting, keyword filtering, and Baidu content moderation.
-3. **Agent Capabilities** - Native support for code execution, natural language TODO lists, web search. Integrates with [Dify Platform](https://dify.ai/) for easy access to Dify assistants/knowledge bases/workflows.
-4. **Plugin System** - Optimized plugin mechanism with minimal development effort. Supports multiple installed plugins.
-5. **Web Dashboard** - Visual configuration management, plugin controls, logging, and WebChat interface for direct LLM interaction.
-6. **High Stability & Modularity** - Event bus and pipeline architecture ensures high modularization and loose coupling.
+<br>
 
-> [!TIP]
-> Dashboard Demo: [https://demo.astrbot.app/](https://demo.astrbot.app/)  
-> Username: `astrbot`, Password: `astrbot` (LLM not configured for chat page)
+<a href="https://astrbot.app/">Documentation</a> ｜
+<a href="https://blog.astrbot.app/">Blog</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">Roadmap</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">Issue Tracker</a>
+</div>
 
-## ✨ Deployment
+AstrBot is an open-source all-in-one Agent chatbot platform that integrates with mainstream instant messaging apps. It provides reliable and scalable conversational AI infrastructure for individuals, developers, and teams. Whether you're building a personal AI companion, intelligent customer service, automation assistant, or enterprise knowledge base, AstrBot enables you to quickly build production-ready AI applications within your IM platform workflows.
 
-#### Docker Deployment
+![070d50ba43ea3c96980787127bbbe552](https://github.com/user-attachments/assets/6fe147c5-68d9-4f47-a8de-252e63fdcbd8)
 
-See docs: [Deploy with Docker](https://astrbot.app/deploy/astrbot/docker.html#docker-deployment)
+## Key Features
 
-#### Windows Installer
+1. 💯 Free & Open Source.
+2. ✨ AI LLM Conversations, Multimodal, Agent, MCP, Skills, Knowledge Base, Persona Settings, Auto Context Compression.
+3. 🤖 Supports integration with Dify, Alibaba Cloud Bailian, Coze, and other agent platforms.
+4. 🌐 Multi-Platform: QQ, WeChat Work, Feishu, DingTalk, WeChat Official Accounts, Telegram, Slack, and [more](#supported-messaging-platforms).
+5. 📦 Plugin Extensions with nearly 800 plugins available for one-click installation.
+6. 🛡️ [Agent Sandbox](https://docs.astrbot.app/use/astrbot-agent-sandbox.html) for isolated, safe execution of code, shell calls, and session-level resource reuse.
+7. 💻 WebUI Support.
+8. 🌈 Web ChatUI Support with built-in agent sandbox and web search.
+9. 🌐 Internationalization (i18n) Support.
 
-Requires Python (>3.10). See docs: [Windows Installer Guide](https://astrbot.app/deploy/astrbot/windows.html)
+## Quick Start
 
-#### Replit Deployment
+#### Docker Deployment (Recommended 🥳)
 
-[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+We recommend deploying AstrBot using Docker or Docker Compose.
+
+Please refer to the official documentation: [Deploy AstrBot with Docker](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot).
+
+#### uv Deployment
+
+```bash
+uvx astrbot
+```
+
+#### BT-Panel Deployment
+
+AstrBot has partnered with BT-Panel and is now available in their marketplace.
+
+Please refer to the official documentation: [BT-Panel Deployment](https://astrbot.app/deploy/astrbot/btpanel.html).
+
+#### 1Panel Deployment
+
+AstrBot has been officially listed on the 1Panel marketplace.
+
+Please refer to the official documentation: [1Panel Deployment](https://astrbot.app/deploy/astrbot/1panel.html).
+
+#### Deploy on RainYun
+
+AstrBot has been officially listed on RainYun's cloud application platform with one-click deployment.
+
+[![Deploy on RainYun](https://rainyun-apps.cn-nb1.rains3.com/materials/deploy-on-rainyun-en.svg)](https://app.rainyun.com/apps/rca/store/5994?ref=NjU1ODg0)
+
+#### Deploy on Replit
+
+Community-contributed deployment method.
+
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
+
+#### Windows One-Click Installer
+
+Please refer to the official documentation: [Deploy AstrBot with Windows One-Click Installer](https://astrbot.app/deploy/astrbot/windows.html).
 
 #### CasaOS Deployment
 
-Community-contributed method.  
-See docs: [CasaOS Deployment](https://astrbot.app/deploy/astrbot/casaos.html)
+Community-contributed deployment method.
+
+Please refer to the official documentation: [CasaOS Deployment](https://astrbot.app/deploy/astrbot/casaos.html).
 
 #### Manual Deployment
 
-See docs: [Source Code Deployment](https://astrbot.app/deploy/astrbot/cli.html)
+First, install uv:
 
-## ⚡ Platform Support
+```bash
+pip install uv
+```
 
-| Platform                                                       | Status | Details             | Message Types       |
-| -------------------------------------------------------------- | ------ | ------------------- | ------------------- |
-| QQ (Official Bot)                                              | ✔      | Private/Group chats | Text, Images        |
-| QQ (OneBot)                                                    | ✔      | Private/Group chats | Text, Images, Voice |
-| WeChat (Personal)                                              | ✔      | Private/Group chats | Text, Images, Voice |
-| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram) | ✔      | Private/Group chats | Text, Images        |
-| [WeChat Work](https://github.com/Soulter/astrbot_plugin_wecom) | ✔      | Private chats       | Text, Images, Voice |
-| Feishu                                                         | ✔      | Group chats         | Text, Images        |
-| WeChat Open Platform                                           | 🚧      | Planned             | -                   |
-| Discord                                                        | 🚧      | Planned             | -                   |
-| WhatsApp                                                       | 🚧      | Planned             | -                   |
-| Xiaomi Speakers                                                | 🚧      | Planned             | -                   |
+Install AstrBot via Git Clone:
 
-## Provider Support Status
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
 
-| Name                      | Support | Type                   | Notes                                                                 |
-|---------------------------|---------|------------------------|-----------------------------------------------------------------------|
-| OpenAI API                | ✔       | Text Generation        | Supports all OpenAI API-compatible services including DeepSeek, Google Gemini, GLM, Moonshot, Alibaba Cloud Bailian, Silicon Flow, xAI, etc. |
-| Claude API                | ✔       | Text Generation        |                                                                       |
-| Google Gemini API         | ✔       | Text Generation        |                                                                       |
-| Dify                      | ✔       | LLMOps                 |                                                                       |
-| DashScope (Alibaba Cloud) | ✔       | LLMOps                 |                                                                       |
-| Ollama                    | ✔       | Model Loader           | Local deployment for open-source LLMs (DeepSeek, Llama, etc.)         |
-| LM Studio                 | ✔       | Model Loader           | Local deployment for open-source LLMs (DeepSeek, Llama, etc.)         |
-| LLMTuner                  | ✔       | Model Loader           | Local loading of fine-tuned models (e.g. LoRA)                        |
-| OneAPI                    | ✔       | LLM Distribution       |                                                                       |
-| Whisper                   | ✔       | Speech-to-Text         | Supports API and local deployment                                    |
-| SenseVoice                | ✔       | Speech-to-Text         | Local deployment                                                     |
-| OpenAI TTS API            | ✔       | Text-to-Speech         |                                                                       |
-| Fishaudio                 | ✔       | Text-to-Speech         | Project involving GPT-Sovits author                                  |
+Or refer to the official documentation: [Deploy AstrBot from Source](https://astrbot.app/deploy/astrbot/cli.html).
 
-# 🦌 Roadmap
+## Supported Messaging Platforms
 
-> [!TIP]
-> Suggestions welcome via Issues <3
+**Officially Maintained**
 
-- [ ] Ensure feature parity across all platform adapters
-- [ ] Optimize plugin APIs
-- [ ] Add default TTS services (e.g., GPT-Sovits)
-- [ ] Enhance chat features with persistent memory
-- [ ] i18n Planning
+- QQ (Official Platform & OneBot)
+- Telegram
+- WeChat Work Application & WeChat Work Intelligent Bot
+- WeChat Customer Service & WeChat Official Accounts
+- Feishu (Lark)
+- DingTalk
+- Slack
+- Discord
+- Satori
+- Misskey
+- WhatsApp (Coming Soon)
+- LINE (Coming Soon)
 
-## ❤️ Contributions
+**Community Maintained**
 
-All Issues/PRs welcome! Simply submit your changes to this project :)
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
 
-For major features, please discuss via Issues first.
+## Supported Model Services
 
-## 🌟 Support
+**LLM Services**
 
-- Star this project!
-- Support via [Afdian](https://afdian.com/a/soulter)
-- WeChat support: [QR Code](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)
+- OpenAI and Compatible Services
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- Zhipu AI
+- DeepSeek
+- Ollama (Self-hosted)
+- LM Studio (Self-hosted)
+- [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [TokenPony](https://www.tokenpony.cn/3YPyf)
+- [SiliconFlow](https://docs.siliconflow.cn/cn/usecases/use-siliconcloud-in-astrbot)
+- [PPIO Cloud](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
 
-## ✨ Demos
+**LLMOps Platforms**
 
-> [!NOTE]
-> Code executor file I/O currently tested with Napcat(QQ)/Lagrange(QQ)
+- Dify
+- Alibaba Cloud Bailian Applications
+- Coze
 
-<div align='center'>
+**Speech-to-Text Services**
 
-<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
+- OpenAI Whisper
+- SenseVoice
 
-_✨ Docker-based Sandboxed Code Executor (Beta) ✨_
+**Text-to-Speech Services**
 
-<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- Alibaba Cloud Bailian TTS
+- Azure TTS
+- Minimax TTS
+- Volcano Engine TTS
 
-_✨ Multimodal Input, Web Search, Text-to-Image ✨_
+## ❤️ Contributing
 
-<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
+Issues and Pull Requests are always welcome! Feel free to submit your changes to this project :)
 
-_✨ Natural Language TODO Lists ✨_
+### How to Contribute
 
-<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
-<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
+You can contribute by reviewing issues or helping with pull request reviews. Any issues or PRs are welcome to encourage community participation. Of course, these are just suggestions—you can contribute in any way you like. For adding new features, please discuss through an Issue first.
 
-_✨ Plugin System Showcase ✨_
+### Development Environment
 
-<img src="https://github.com/user-attachments/assets/592a8630-14c7-4e06-b496-9c0386e4f36c" width=600>
+AstrBot uses `ruff` for code formatting and linting.
 
-_✨ Web Dashboard ✨_
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot
+pip install pre-commit
+pre-commit install
+```
 
-![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
+## 🌍 Community
 
-_✨ Built-in Web Chat Interface ✨_
+### QQ Groups
 
-</div>
+- Group 1: 322154837
+- Group 3: 630166526
+- Group 5: 822130018
+- Group 6: 753075035
+- Group 7: 743746109
+- Group 8: 1030353265
+- Developer Group: 975206796
+
+### Telegram Group
+
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+### Discord Server
+
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+## ❤️ Special Thanks
+
+Special thanks to all Contributors and plugin developers for their contributions to AstrBot ❤️
+
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
+
+Additionally, the birth of this project would not have been possible without the help of the following open-source projects:
+
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - The amazing cat framework
 
 ## ⭐ Star History
 
-> [!TIP] 
-> If this project helps you, please give it a star <3
+> [!TIP]
+> If this project has helped you in your life or work, or if you're interested in its future development, please give the project a Star. It's the driving force behind maintaining this open-source project <3
 
 <div align="center">
-    
-[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
 
 </div>
 
-## Disclaimer
-
-1. Licensed under `AGPL-v3`.
-2. WeChat integration uses [Gewechat](https://github.com/Devo919/Gewechat). Use at your own risk with non-critical accounts.
-3. Users must comply with local laws and regulations.
-
-<!-- ## ✨ ATRI [Beta]
-
-Available as plugin: [astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
-
-1. Qwen1.5-7B-Chat Lora model fine-tuned with ATRI character data
-2. Long-term memory
-3. Meme understanding & responses
-4. TTS integration
-    -->
+</details>
 
+<div align="center">
 
 _私は、高性能ですから!_
 
+<img src="https://files.astrbot.app/watashiwa-koseino-desukara.gif" width="100"/>
+</div>

README_fr.md

@@ -0,0 +1,247 @@
+![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
+
+</p>
+
+<div align="center">
+
+<br>
+
+<div>
+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+</div>
+
+<br>
+
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?style=for-the-badge&color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
+<a href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%20plugins&style=for-the-badge&label=Marketplace&cacheSeconds=3600">
+</div>
+
+<br>
+
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README.md">中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ja.md">日本語</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_zh-TW.md">繁體中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ru.md">Русский</a>
+
+<a href="https://astrbot.app/">Documentation</a> ｜
+<a href="https://blog.astrbot.app/">Blog</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">Feuille de route</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">Signaler un problème</a>
+</div>
+
+AstrBot est une plateforme de chatbot Agent tout-en-un open source qui s'intègre aux principales applications de messagerie instantanée. Elle fournit une infrastructure d'IA conversationnelle fiable et évolutive pour les particuliers, les développeurs et les équipes. Que vous construisiez un compagnon IA personnel, un service client intelligent, un assistant d'automatisation ou une base de connaissances d'entreprise, AstrBot vous permet de créer rapidement des applications d'IA prêtes pour la production dans les flux de travail de votre plateforme de messagerie.
+
+<img width="1776" height="1080" alt="image" src="https://github.com/user-attachments/assets/00782c4c-4437-4d97-aabc-605e3738da5c" />
+
+## Fonctionnalités principales
+
+1. 💯 Gratuit & Open Source.
+2. ✨ Conversations avec LLM IA, Multimodal, Agent, MCP, Base de connaissances, Paramètres de personnalité.
+3. 🤖 Prise en charge de l'intégration avec Dify, Alibaba Cloud Bailian, Coze et autres plateformes d'agents.
+4. 🌐 Multi-plateforme : QQ, WeChat Work, Feishu, DingTalk, Comptes officiels WeChat, Telegram, Slack, et [plus encore](#plateformes-de-messagerie-prises-en-charge).
+5. 📦 Extensions de plugins avec près de 800 plugins disponibles pour une installation en un clic.
+6. 💻 Support WebUI.
+7. 🌐 Support de l'internationalisation (i18n).
+
+## Démarrage rapide
+
+#### Déploiement Docker (Recommandé 🥳)
+
+Nous recommandons de déployer AstrBot en utilisant Docker ou Docker Compose.
+
+Veuillez consulter la documentation officielle : [Déployer AstrBot avec Docker](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot).
+
+#### Déploiement uv
+
+```bash
+uvx astrbot
+```
+
+#### Déploiement BT-Panel
+
+AstrBot s'est associé à BT-Panel et est maintenant disponible sur leur marketplace.
+
+Veuillez consulter la documentation officielle : [Déploiement BT-Panel](https://astrbot.app/deploy/astrbot/btpanel.html).
+
+#### Déploiement 1Panel
+
+AstrBot a été officiellement listé sur le marketplace 1Panel.
+
+Veuillez consulter la documentation officielle : [Déploiement 1Panel](https://astrbot.app/deploy/astrbot/1panel.html).
+
+#### Déployer sur RainYun
+
+AstrBot a été officiellement listé sur la plateforme d'applications cloud de RainYun avec un déploiement en un clic.
+
+[![Deploy on RainYun](https://rainyun-apps.cn-nb1.rains3.com/materials/deploy-on-rainyun-en.svg)](https://app.rainyun.com/apps/rca/store/5994?ref=NjU1ODg0)
+
+#### Déployer sur Replit
+
+Méthode de déploiement contribuée par la communauté.
+
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
+
+#### Installateur Windows en un clic
+
+Veuillez consulter la documentation officielle : [Déployer AstrBot avec l'installateur Windows en un clic](https://astrbot.app/deploy/astrbot/windows.html).
+
+#### Déploiement CasaOS
+
+Méthode de déploiement contribuée par la communauté.
+
+Veuillez consulter la documentation officielle : [Déploiement CasaOS](https://astrbot.app/deploy/astrbot/casaos.html).
+
+#### Déploiement manuel
+
+Tout d'abord, installez uv :
+
+```bash
+pip install uv
+```
+
+Installez AstrBot via Git Clone :
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
+
+Ou consultez la documentation officielle : [Déployer AstrBot depuis les sources](https://astrbot.app/deploy/astrbot/cli.html).
+
+## Plateformes de messagerie prises en charge
+
+**Maintenues officiellement**
+
+- QQ (Plateforme officielle & OneBot)
+- Telegram
+- Application WeChat Work & Bot intelligent WeChat Work
+- Service client WeChat & Comptes officiels WeChat
+- Feishu (Lark)
+- DingTalk
+- Slack
+- Discord
+- Satori
+- Misskey
+- WhatsApp (Bientôt disponible)
+- LINE (Bientôt disponible)
+
+**Maintenues par la communauté**
+
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
+
+## Services de modèles pris en charge
+
+**Services LLM**
+
+- OpenAI et services compatibles
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- Zhipu AI
+- DeepSeek
+- Ollama (Auto-hébergé)
+- LM Studio (Auto-hébergé)
+- [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [TokenPony](https://www.tokenpony.cn/3YPyf)
+- [SiliconFlow](https://docs.siliconflow.cn/cn/usecases/use-siliconcloud-in-astrbot)
+- [PPIO Cloud](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
+
+**Plateformes LLMOps**
+
+- Dify
+- Applications Alibaba Cloud Bailian
+- Coze
+
+**Services de reconnaissance vocale**
+
+- OpenAI Whisper
+- SenseVoice
+
+**Services de synthèse vocale**
+
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- Alibaba Cloud Bailian TTS
+- Azure TTS
+- Minimax TTS
+- Volcano Engine TTS
+
+## ❤️ Contribuer
+
+Les Issues et Pull Requests sont toujours les bienvenues ! N'hésitez pas à soumettre vos modifications à ce projet :)
+
+### Comment contribuer
+
+Vous pouvez contribuer en examinant les issues ou en aidant à la revue des pull requests. Toutes les issues ou PRs sont les bienvenues pour encourager la participation de la communauté. Bien sûr, ce ne sont que des suggestions - vous pouvez contribuer de la manière que vous souhaitez. Pour l'ajout de nouvelles fonctionnalités, veuillez d'abord en discuter via une Issue.
+
+### Environnement de développement
+
+AstrBot utilise `ruff` pour le formatage et le linting du code.
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot
+pip install pre-commit
+pre-commit install
+```
+
+## 🌍 Communauté
+
+### Groupes QQ
+
+- Groupe 1 : 322154837
+- Groupe 3 : 630166526
+- Groupe 5 : 822130018
+- Groupe 6 : 753075035
+- Groupe développeurs : 975206796
+
+### Groupe Telegram
+
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+### Serveur Discord
+
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+## ❤️ Remerciements spéciaux
+
+Un grand merci à tous les contributeurs et développeurs de plugins pour leurs contributions à AstrBot ❤️
+
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
+
+De plus, la naissance de ce projet n'aurait pas été possible sans l'aide des projets open source suivants :
+
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - L'incroyable framework chat
+
+## ⭐ Historique des étoiles
+
+> [!TIP]
+> Si ce projet vous a aidé dans votre vie ou votre travail, ou si vous êtes intéressé par son développement futur, veuillez donner une étoile au projet. C'est la force motrice derrière la maintenance de ce projet open source <3
+
+<div align="center">
+
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
+
+</div>
+
+</details>
+
+_私は、高性能ですから!_
+

README_ja.md

@@ -1,167 +1,247 @@
-<p align="center">
-
-![6e1279651f16d7fdf4727558b72bbaf1](https://github.com/user-attachments/assets/ead4c551-fc3c-48f7-a6f7-afbfdb820512)
+![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
 
 </p>
 
 <div align="center">
 
-_✨ 簡単に使えるマルチプラットフォーム LLM チャットボットおよび開発フレームワーク ✨_
+<br>
 
+<div>
 <a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
-<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg"/></a>
-<img alt="Static Badge" src="https://img.shields.io/badge/QQ群-630166526-purple">
-[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e.svg)](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fstats&query=v&label=7%E6%97%A5%E6%B6%88%E6%81%AF%E4%B8%8A%E8%A1%8C%E9%87%8F&cacheSeconds=3600)
-[![codecov](https://codecov.io/gh/Soulter/AstrBot/graph/badge.svg?token=FF3P5967B8)](https://codecov.io/gh/Soulter/AstrBot)
-
-<a href="https://astrbot.app/">ドキュメントを見る</a> ｜
-<a href="https://github.com/Soulter/AstrBot/issues">問題を報告する</a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
 </div>
 
-AstrBot は、疎結合、非同期、複数のメッセージプラットフォームに対応したデプロイ、使いやすいプラグインシステム、および包括的な大規模言語モデル（LLM）接続機能を備えたチャットボットおよび開発フレームワークです。
+<br>
 
-## ✨ 主な機能
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?style=for-the-badge&color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
+<a href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%E5%80%8B&style=for-the-badge&label=%E3%83%97%E3%83%A9%E3%82%B0%E3%82%A4%E3%83%B3&cacheSeconds=3600">
+</div>
 
-1. **大規模言語モデルの対話**。OpenAI API、Google Gemini、Llama、Deepseek、ChatGLM など、さまざまな大規模言語モデルをサポートし、Ollama、LLMTuner を介してローカルにデプロイされた大規模モデルをサポートします。多輪対話、人格シナリオ、多モーダル機能を備え、画像理解、音声からテキストへの変換（Whisper）をサポートします。
-2. **複数のメッセージプラットフォームの接続**。QQ（OneBot）、QQ チャンネル、Feishu、Telegram への接続をサポートします。今後、DingTalk、Discord、WhatsApp、Xiaoai 音響をサポートする予定です。レート制限、ホワイトリスト、キーワードフィルタリング、Baidu コンテンツ監査をサポートします。
-3. **エージェント**。一部のエージェント機能をネイティブにサポートし、コードエグゼキューター、自然言語タスク、ウェブ検索などを提供します。[Dify プラットフォーム](https://dify.ai/)と連携し、Dify スマートアシスタント、ナレッジベース、Dify ワークフローを簡単に接続できます。
-4. **プラグインの拡張**。深く最適化されたプラグインメカニズムを備え、[プラグインの開発](https://astrbot.app/dev/plugin.html)をサポートし、機能を拡張できます。複数のプラグインのインストールをサポートします。
-5. **ビジュアル管理パネル**。設定の視覚的な変更、プラグイン管理、ログの表示などをサポートし、設定の難易度を低減します。WebChat を統合し、パネル上で大規模モデルと対話できます。
-6. **高い安定性と高いモジュール性**。イベントバスとパイプラインに基づくアーキテクチャ設計により、高度にモジュール化され、低結合です。
+<br>
 
-> [!TIP]
-> 管理パネルのオンラインデモを体験する: [https://demo.astrbot.app/](https://demo.astrbot.app/)
->
-> ユーザー名: `astrbot`, パスワード: `astrbot`。LLM が設定されていないため、チャットページで大規模モデルを使用することはできません。（デモのログインパスワードを変更しないでください 😭）
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README.md">中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_zh-TW.md">繁體中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_fr.md">Français</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ru.md">Русский</a>
 
-## ✨ 使用方法
+<a href="https://astrbot.app/">ドキュメント</a> ｜
+<a href="https://blog.astrbot.app/">Blog</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">ロードマップ</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">Issue</a>
+</div>
 
-#### Docker デプロイ
+AstrBot は、主要なインスタントメッセージングアプリと統合できるオープンソースのオールインワン Agent チャットボットプラットフォームです。個人、開発者、チームに信頼性が高くスケーラブルな会話型 AI インフラストラクチャを提供します。パーソナル AI コンパニオン、インテリジェントカスタマーサービス、オートメーションアシスタント、エンタープライズナレッジベースなど、AstrBot を使用すると、IM プラットフォームのワークフロー内で本番環境対応の AI アプリケーションを迅速に構築できます。
 
-公式ドキュメント [Docker を使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot) を参照してください。
+<img width="1776" height="1080" alt="image" src="https://github.com/user-attachments/assets/00782c4c-4437-4d97-aabc-605e3738da5c" />
 
-#### Windows ワンクリックインストーラーのデプロイ
+## 主な機能
 
-コンピュータに Python（>3.10）がインストールされている必要があります。公式ドキュメント [Windows ワンクリックインストーラーを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/windows.html) を参照してください。
+1. 💯 無料 & オープンソース。
+2. ✨ AI 大規模言語モデル対話、マルチモーダル、Agent、MCP、ナレッジベース、ペルソナ設定。
+3. 🤖 Dify、Alibaba Cloud 百炼、Coze などの Agent プラットフォームとの統合をサポート。
+4. 🌐 マルチプラットフォーム：QQ、WeChat Work、Feishu、DingTalk、WeChat 公式アカウント、Telegram、Slack、[その他](#サポートされているメッセージプラットフォーム)。
+5. 📦 約800個のプラグインをワンクリックでインストール可能なプラグイン拡張機能。
+6. 💻 WebUI サポート。
+7. 🌐 国際化（i18n）サポート。
 
-#### Replit デプロイ
+## クイックスタート
 
-[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+#### Docker デプロイ（推奨 🥳）
+
+Docker / Docker Compose を使用した AstrBot のデプロイを推奨します。
+
+公式ドキュメント [Docker を使用した AstrBot のデプロイ](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot) をご参照ください。
+
+#### uv デプロイ
+
+```bash
+uvx astrbot
+```
+
+#### 宝塔パネルデプロイ
+
+AstrBot は宝塔パネルと提携し、宝塔パネルに公開されています。
+
+公式ドキュメント [宝塔パネルデプロイ](https://astrbot.app/deploy/astrbot/btpanel.html) をご参照ください。
+
+#### 1Panel デプロイ
+
+AstrBot は 1Panel 公式により 1Panel パネルに公開されています。
+
+公式ドキュメント [1Panel デプロイ](https://astrbot.app/deploy/astrbot/1panel.html) をご参照ください。
+
+#### 雨云でのデプロイ
+
+AstrBot は雨云公式によりクラウドアプリケーションプラットフォームに公開され、ワンクリックでデプロイ可能です。
+
+[![Deploy on RainYun](https://rainyun-apps.cn-nb1.rains3.com/materials/deploy-on-rainyun-en.svg)](https://app.rainyun.com/apps/rca/store/5994?ref=NjU1ODg0)
+
+#### Replit でのデプロイ
+
+コミュニティ貢献によるデプロイ方法。
+
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
+
+#### Windows ワンクリックインストーラーデプロイ
+
+公式ドキュメント [Windows ワンクリックインストーラーを使用した AstrBot のデプロイ](https://astrbot.app/deploy/astrbot/windows.html) をご参照ください。
 
 #### CasaOS デプロイ
 
-コミュニティが提供するデプロイ方法です。
+コミュニティ貢献によるデプロイ方法。
 
-公式ドキュメント [ソースコードを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/casaos.html) を参照してください。
+公式ドキュメント [CasaOS デプロイ](https://astrbot.app/deploy/astrbot/casaos.html) をご参照ください。
 
 #### 手動デプロイ
 
-公式ドキュメント [ソースコードを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/cli.html) を参照してください。
+まず uv をインストールします:
 
-## ⚡ メッセージプラットフォームのサポート状況
+```bash
+pip install uv
+```
 
-| プラットフォーム    | サポート状況 | 詳細 | メッセージタイプ |
-| -------- | ------- | ------- | ------ |
-| QQ(公式ロボットインターフェース) | ✔    | プライベートチャット、グループチャット、QQ チャンネルプライベートチャット、グループチャット | テキスト、画像 |
-| QQ(OneBot)      | ✔    | プライベートチャット、グループチャット | テキスト、画像、音声 |
-| WeChat(個人アカウント)    | ✔    | WeChat 個人アカウントのプライベートチャット、グループチャット | テキスト、画像、音声 |
-| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | プライベートチャット、グループチャット | テキスト、画像 |
-| [WeChat(企業 WeChat)](https://github.com/Soulter/astrbot_plugin_wecom)    | ✔    | プライベートチャット | テキスト、画像、音声 |
-| Feishu   | ✔    | グループチャット | テキスト、画像 |
-| WeChat 対話オープンプラットフォーム | 🚧    | 計画中 | - |
-| Discord   | 🚧    | 計画中 | - |
-| WhatsApp   | 🚧    | 計画中 | - |
-| Xiaoai 音響   | 🚧    | 計画中 | - |
+Git Clone で AstrBot をインストール:
 
-# 🦌 今後のロードマップ
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
 
-> [!TIP]
-> Issue でさらに多くの提案を歓迎します <3
+または、公式ドキュメント [ソースコードから AstrBot をデプロイ](https://astrbot.app/deploy/astrbot/cli.html) をご参照ください。
 
-- [ ] 現在のすべてのプラットフォームアダプターの機能の一貫性を確保し、改善する
-- [ ] プラグインインターフェースの最適化
-- [ ] GPT-Sovits などの TTS サービスをデフォルトでサポート
-- [ ] "チャット強化" 部分を完成させ、永続的な記憶をサポート
-- [ ] i18n の計画
+## サポートされているメッセージプラットフォーム
 
-## ❤️ 貢献
+**公式メンテナンス**
 
-Issue や Pull Request を歓迎します！このプロジェクトに変更を加えるだけです :)
+- QQ (公式プラットフォーム & OneBot)
+- Telegram
+- WeChat Work アプリケーション & WeChat Work インテリジェントボット
+- WeChat カスタマーサービス & WeChat 公式アカウント
+- Feishu (Lark)
+- DingTalk
+- Slack
+- Discord
+- Satori
+- Misskey
+- WhatsApp (近日対応予定)
+- LINE (近日対応予定)
 
-新機能の追加については、まず Issue で議論してください。
+**コミュニティメンテナンス**
 
-## 🌟 サポート
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
 
-- このプロジェクトに Star を付けてください！
-- [愛発電](https://afdian.com/a/soulter)で私をサポートしてください！
-- [WeChat](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)で私をサポートしてください~
 
-## ✨ デモ
+## サポートされているモデルサービス
 
-> [!NOTE]
-> コードエグゼキューターのファイル入力/出力は現在 Napcat(QQ)、Lagrange(QQ) でのみテストされています
+**大規模言語モデルサービス**
 
-<div align='center'>
+- OpenAI および互換サービス
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- 智谱 AI
+- DeepSeek
+- Ollama (セルフホスト)
+- LM Studio (セルフホスト)
+- [優云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [小馬算力](https://www.tokenpony.cn/3YPyf)
+- [硅基流動](https://docs.siliconflow.cn/cn/usercases/use-siliconcloud-in-astrbot)
+- [PPIO 派欧云](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
 
-<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
+**LLMOps プラットフォーム**
 
-_✨ Docker ベースのサンドボックス化されたコードエグゼキューター（ベータテスト中）✨_
+- Dify
+- Alibaba Cloud 百炼アプリケーション
+- Coze
 
-<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
+**音声認識サービス**
 
-_✨ 多モーダル、ウェブ検索、長文の画像変換（設定可能）✨_
+- OpenAI Whisper
+- SenseVoice
 
-<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
+**音声合成サービス**
 
-_✨ 自然言語タスク ✨_
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- Alibaba Cloud 百炼 TTS
+- Azure TTS
+- Minimax TTS
+- Volcano Engine TTS
 
-<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
-<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
+## ❤️ コントリビューション
 
-_✨ プラグインシステム - 一部のプラグインの展示 ✨_
+Issue や Pull Request は大歓迎です!このプロジェクトに変更を送信してください :)
 
-<img src="https://github.com/user-attachments/assets/592a8630-14c7-4e06-b496-9c0386e4f36c" width="600">
+### コントリビュート方法
 
-_✨ 管理パネル ✨_
+Issue を確認したり、PR(プルリクエスト)のレビューを手伝うことで貢献できます。どんな Issue や PR への参加も歓迎され、コミュニティ貢献を促進します。もちろん、これらは提案に過ぎず、どんな方法でも貢献できます。新機能の追加については、まず Issue で議論してください。
 
-![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
+### 開発環境
 
-_✨ 内蔵 Web Chat、オンラインでボットと対話 ✨_
+AstrBot はコードのフォーマットとチェックに `ruff` を使用しています。
 
-</div>
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot
+pip install pre-commit
+pre-commit install
+```
+
+## 🌍 コミュニティ
+
+### QQ グループ
+
+- 1群: 322154837
+- 3群: 630166526
+- 5群: 822130018
+- 6群: 753075035
+- 開発者群: 975206796
+
+### Telegram グループ
+
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+### Discord サーバー
+
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+## ❤️ Special Thanks
+
+AstrBot への貢献をしていただいたすべてのコントリビューターとプラグイン開発者に特別な感謝を ❤️
+
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
+
+また、このプロジェクトの誕生は以下のオープンソースプロジェクトの助けなしには実現できませんでした:
+
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - 素晴らしい猫猫フレームワーク
 
 ## ⭐ Star History
 
 > [!TIP]
-> このプロジェクトがあなたの生活や仕事に役立った場合、またはこのプロジェクトの将来の発展に関心がある場合は、プロジェクトに Star を付けてください。これはこのオープンソースプロジェクトを維持するためのモチベーションです <3
+> このプロジェクトがあなたの生活や仕事に役立ったり、このプロジェクトの今後の発展に関心がある場合は、プロジェクトに Star をください。これがこのオープンソースプロジェクトを維持する原動力です <3
 
 <div align="center">
 
-[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
 
 </div>
 
-## スポンサー
-
-[<img src="https://api.gitsponsors.com/api/badge/img?id=575865240" height="20">](https://api.gitsponsors.com/api/badge/link?p=XEpbdGxlitw/RbcwiTX93UMzNK/jgDYC8NiSzamIPMoKvG2lBFmyXhSS/b0hFoWlBBMX2L5X5CxTDsUdyvcIEHTOfnkXz47UNOZvMwyt5CzbYpq0SEzsSV1OJF1cCo90qC/ZyYKYOWedal3MhZ3ikw==)
-
-## 免責事項
-
-1. このプロジェクトは `AGPL-v3` オープンソースライセンスの下で保護されています。
-2. このプロジェクトを使用する際は、現地の法律および規制を遵守してください。
-
-<!-- ## ✨ ATRI [ベータテスト]
-
-この機能はプラグインとしてロードされます。プラグインリポジトリのアドレス：[astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
-
-1. 《ATRI ~ My Dear Moments》の主人公 ATRI のキャラクターセリフを微調整データセットとして使用した `Qwen1.5-7B-Chat Lora` 微調整モデル。
-2. 長期記憶
-3. ミームの理解と返信
-4. TTS
-    -->
+</details>
 
 _私は、高性能ですから!_

README_ru.md

@@ -0,0 +1,247 @@
+![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
+
+</p>
+
+<div align="center">
+
+<br>
+
+<div>
+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+</div>
+
+<br>
+
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?style=for-the-badge&color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
+<a href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%20%D0%BF%D0%BB%D0%B0%D0%B3%D0%B8%D0%BD%D0%BE%D0%B2&style=for-the-badge&label=%D0%9C%D0%B0%D0%B3%D0%B0%D0%B7%D0%B8%D0%BD&cacheSeconds=3600">
+</div>
+
+<br>
+
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README.md">中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ja.md">日本語</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_zh-TW.md">繁體中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_fr.md">Français</a>
+
+<a href="https://astrbot.app/">Документация</a> ｜
+<a href="https://blog.astrbot.app/">Блог</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">Дорожная карта</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">Сообщить о проблеме</a>
+</div>
+
+AstrBot — это универсальная платформа Agent-чатботов с открытым исходным кодом, которая интегрируется с основными приложениями для обмена мгновенными сообщениями. Она предоставляет надёжную и масштабируемую инфраструктуру разговорного ИИ для частных лиц, разработчиков и команд. Будь то персональный ИИ-компаньон, интеллектуальная служба поддержки, автоматизированный помощник или корпоративная база знаний — AstrBot позволяет быстро создавать готовые к использованию ИИ-приложения в рабочих процессах вашей платформы обмена сообщениями.
+
+<img width="1776" height="1080" alt="image" src="https://github.com/user-attachments/assets/00782c4c-4437-4d97-aabc-605e3738da5c" />
+
+## Основные возможности
+
+1. 💯 Бесплатно и с открытым исходным кодом.
+2. ✨ ИИ-диалоги с LLM, мультимодальность, Agent, MCP, база знаний, настройки личности.
+3. 🤖 Поддержка интеграции с Dify, Alibaba Cloud Bailian, Coze и другими платформами агентов.
+4. 🌐 Мультиплатформенность: QQ, WeChat Work, Feishu, DingTalk, официальные аккаунты WeChat, Telegram, Slack и [другие](#поддерживаемые-платформы-обмена-сообщениями).
+5. 📦 Расширения плагинов с почти 800 плагинами, доступными для установки в один клик.
+6. 💻 Поддержка WebUI.
+7. 🌐 Поддержка интернационализации (i18n).
+
+## Быстрый старт
+
+#### Развёртывание Docker (Рекомендуется 🥳)
+
+Мы рекомендуем развёртывать AstrBot с помощью Docker или Docker Compose.
+
+См. официальную документацию: [Развёртывание AstrBot с Docker](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot).
+
+#### Развёртывание uv
+
+```bash
+uvx astrbot
+```
+
+#### Развёртывание BT-Panel
+
+AstrBot в партнёрстве с BT-Panel теперь доступен на их маркетплейсе.
+
+См. официальную документацию: [Развёртывание BT-Panel](https://astrbot.app/deploy/astrbot/btpanel.html).
+
+#### Развёртывание 1Panel
+
+AstrBot официально размещён на маркетплейсе 1Panel.
+
+См. официальную документацию: [Развёртывание 1Panel](https://astrbot.app/deploy/astrbot/1panel.html).
+
+#### Развёртывание на RainYun
+
+AstrBot официально размещён на облачной платформе приложений RainYun с развёртыванием в один клик.
+
+[![Deploy on RainYun](https://rainyun-apps.cn-nb1.rains3.com/materials/deploy-on-rainyun-en.svg)](https://app.rainyun.com/apps/rca/store/5994?ref=NjU1ODg0)
+
+#### Развёртывание на Replit
+
+Метод развёртывания от сообщества.
+
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
+
+#### Установщик Windows в один клик
+
+См. официальную документацию: [Развёртывание AstrBot с установщиком Windows в один клик](https://astrbot.app/deploy/astrbot/windows.html).
+
+#### Развёртывание CasaOS
+
+Метод развёртывания от сообщества.
+
+См. официальную документацию: [Развёртывание CasaOS](https://astrbot.app/deploy/astrbot/casaos.html).
+
+#### Ручное развёртывание
+
+Сначала установите uv:
+
+```bash
+pip install uv
+```
+
+Установите AstrBot через Git Clone:
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
+
+Или см. официальную документацию: [Развёртывание AstrBot из исходного кода](https://astrbot.app/deploy/astrbot/cli.html).
+
+## Поддерживаемые платформы обмена сообщениями
+
+**Официально поддерживаемые**
+
+- QQ (Официальная платформа и OneBot)
+- Telegram
+- Приложение WeChat Work и интеллектуальный бот WeChat Work
+- Служба поддержки WeChat и официальные аккаунты WeChat
+- Feishu (Lark)
+- DingTalk
+- Slack
+- Discord
+- Satori
+- Misskey
+- WhatsApp (Скоро)
+- LINE (Скоро)
+
+**Поддерживаемые сообществом**
+
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
+
+## Поддерживаемые сервисы моделей
+
+**Сервисы LLM**
+
+- OpenAI и совместимые сервисы
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- Zhipu AI
+- DeepSeek
+- Ollama (Самостоятельное размещение)
+- LM Studio (Самостоятельное размещение)
+- [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [TokenPony](https://www.tokenpony.cn/3YPyf)
+- [SiliconFlow](https://docs.siliconflow.cn/cn/usecases/use-siliconcloud-in-astrbot)
+- [PPIO Cloud](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
+
+**Платформы LLMOps**
+
+- Dify
+- Приложения Alibaba Cloud Bailian
+- Coze
+
+**Сервисы распознавания речи**
+
+- OpenAI Whisper
+- SenseVoice
+
+**Сервисы синтеза речи**
+
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- Alibaba Cloud Bailian TTS
+- Azure TTS
+- Minimax TTS
+- Volcano Engine TTS
+
+## ❤️ Вклад в проект
+
+Issues и Pull Request всегда приветствуются! Не стесняйтесь отправлять свои изменения в этот проект :)
+
+### Как внести вклад
+
+Вы можете внести вклад, просматривая issues или помогая с ревью pull request. Любые issues или PR приветствуются для поощрения участия сообщества. Конечно, это лишь предложения — вы можете вносить вклад любым удобным для вас способом. Для добавления новых функций сначала обсудите это через Issue.
+
+### Среда разработки
+
+AstrBot использует `ruff` для форматирования и линтинга кода.
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot
+pip install pre-commit
+pre-commit install
+```
+
+## 🌍 Сообщество
+
+### Группы QQ
+
+- Группа 1: 322154837
+- Группа 3: 630166526
+- Группа 5: 822130018
+- Группа 6: 753075035
+- Группа разработчиков: 975206796
+
+### Группа Telegram
+
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+### Сервер Discord
+
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+## ❤️ Особая благодарность
+
+Особая благодарность всем контрибьюторам и разработчикам плагинов за их вклад в AstrBot ❤️
+
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
+
+Кроме того, рождение этого проекта было бы невозможно без помощи следующих проектов с открытым исходным кодом:
+
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - Замечательный кошачий фреймворк
+
+## ⭐ История звёзд
+
+> [!TIP]
+> Если этот проект помог вам в жизни или работе, или если вас интересует его будущее развитие, пожалуйста, поставьте проекту звезду. Это движущая сила поддержки этого проекта с открытым исходным кодом <3
+
+<div align="center">
+
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
+
+</div>
+
+</details>
+
+_私は、高性能ですから!_
+

README_zh-TW.md

@@ -0,0 +1,247 @@
+![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
+
+</p>
+
+<div align="center">
+
+<br>
+
+<div>
+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=2" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+</div>
+
+<br>
+
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?style=for-the-badge&color=76bad9" href="https://github.com/AstrBotDevs/AstrBot/releases/latest">
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
+<a href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+<img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%E5%80%8B&style=for-the-badge&label=%E6%8F%92%E4%BB%B6%E5%B8%82%E5%A0%B4&cacheSeconds=3600">
+</div>
+
+<br>
+
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README.md">简体中文</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_en.md">English</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ja.md">日本語</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_fr.md">Français</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/blob/master/README_ru.md">Русский</a>
+
+<a href="https://astrbot.app/">文件</a> ｜
+<a href="https://blog.astrbot.app/">Blog</a> ｜
+<a href="https://astrbot.featurebase.app/roadmap">路線圖</a> ｜
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">問題回報</a>
+</div>
+
+AstrBot 是一個開源的一站式 Agent 聊天機器人平台，可接入主流即時通訊軟體，為個人、開發者和團隊打造可靠、可擴展的對話式智慧基礎設施。無論是個人 AI 夥伴、智慧客服、自動化助手，還是企業知識庫，AstrBot 都能在您的即時通訊軟體平台的工作流程中快速構建生產可用的 AI 應用程式。
+
+<img width="1776" height="1080" alt="image" src="https://github.com/user-attachments/assets/00782c4c-4437-4d97-aabc-605e3738da5c" />
+
+## 主要功能
+
+1. 💯 免費 & 開源。
+2. ✨ AI 大型模型對話，多模態，Agent，MCP，知識庫，人格設定。
+3. 🤖 支援接入 Dify、阿里雲百煉、Coze 等智慧體平台。
+4. 🌐 多平台：QQ、企業微信、飛書、釘釘、微信公眾號、Telegram、Slack 以及[更多](#支援的訊息平台)。
+5. 📦 外掛擴充，已有近 800 個外掛可一鍵安裝。
+6. 💻 WebUI 支援。
+7. 🌐 國際化（i18n）支援。
+
+## 快速開始
+
+#### Docker 部署（推薦 🥳）
+
+推薦使用 Docker / Docker Compose 方式部署 AstrBot。
+
+請參閱官方文件 [使用 Docker 部署 AstrBot](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot)。
+
+#### uv 部署
+
+```bash
+uvx astrbot
+```
+
+#### 寶塔面板部署
+
+AstrBot 與寶塔面板合作，已上架至寶塔面板。
+
+請參閱官方文件 [寶塔面板部署](https://astrbot.app/deploy/astrbot/btpanel.html)。
+
+#### 1Panel 部署
+
+AstrBot 已由 1Panel 官方上架至 1Panel 面板。
+
+請參閱官方文件 [1Panel 部署](https://astrbot.app/deploy/astrbot/1panel.html)。
+
+#### 在雨雲上部署
+
+AstrBot 已由雨雲官方上架至雲端應用程式平台，可一鍵部署。
+
+[![Deploy on RainYun](https://rainyun-apps.cn-nb1.rains3.com/materials/deploy-on-rainyun-en.svg)](https://app.rainyun.com/apps/rca/store/5994?ref=NjU1ODg0)
+
+#### 在 Replit 上部署
+
+社群貢獻的部署方式。
+
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
+
+#### Windows 一鍵安裝器部署
+
+請參閱官方文件 [使用 Windows 一鍵安裝器部署 AstrBot](https://astrbot.app/deploy/astrbot/windows.html)。
+
+#### CasaOS 部署
+
+社群貢獻的部署方式。
+
+請參閱官方文件 [CasaOS 部署](https://astrbot.app/deploy/astrbot/casaos.html)。
+
+#### 手動部署
+
+首先安裝 uv：
+
+```bash
+pip install uv
+```
+
+透過 Git Clone 安裝 AstrBot：
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
+
+或者請參閱官方文件 [透過原始碼部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html)。
+
+## 支援的訊息平台
+
+**官方維護**
+
+- QQ（官方平台 & OneBot）
+- Telegram
+- 企微應用 & 企微智慧機器人
+- 微信客服 & 微信公眾號
+- 飛書
+- 釘釘
+- Slack
+- Discord
+- Satori
+- Misskey
+- Whatsapp（即將支援）
+- LINE（即將支援）
+
+**社群維護**
+
+- [Matrix](https://github.com/stevessr/astrbot_plugin_matrix_adapter)
+- [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)
+- [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)
+
+## 支援的模型服務
+
+**大型模型服務**
+
+- OpenAI 及相容服務
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- 智譜 AI
+- DeepSeek
+- Ollama（本機部署）
+- LM Studio（本機部署）
+- [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [小馬算力](https://www.tokenpony.cn/3YPyf)
+- [矽基流動](https://docs.siliconflow.cn/cn/usercases/use-siliconcloud-in-astrbot)
+- [PPIO 派歐雲](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
+
+**LLMOps 平台**
+
+- Dify
+- 阿里雲百煉應用
+- Coze
+
+**語音轉文字服務**
+
+- OpenAI Whisper
+- SenseVoice
+
+**文字轉語音服務**
+
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- 阿里雲百煉 TTS
+- Azure TTS
+- Minimax TTS
+- 火山引擎 TTS
+
+## ❤️ 貢獻
+
+歡迎任何 Issues/Pull Requests！只需要將您的變更提交到此專案 ：)
+
+### 如何貢獻
+
+您可以透過檢視問題或協助審核 PR（拉取請求）來貢獻。任何問題或 PR 都歡迎參與，以促進社群貢獻。當然，這些只是建議，您可以以任何方式進行貢獻。對於新功能的新增，請先透過 Issue 討論。
+
+### 開發環境
+
+AstrBot 使用 `ruff` 進行程式碼格式化和檢查。
+
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot
+pip install pre-commit
+pre-commit install
+```
+
+## 🌍 社群
+
+### QQ 群組
+
+- 1 群：322154837
+- 3 群：630166526
+- 5 群：822130018
+- 6 群：753075035
+- 開發者群：975206796
+
+### Telegram 群組
+
+<a href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+### Discord 群組
+
+<a href="https://discord.gg/hAVk6tgV36"><img alt="Discord_community" src="https://img.shields.io/badge/Discord-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
+
+## ❤️ Special Thanks
+
+特別感謝所有 Contributors 和外掛開發者對 AstrBot 的貢獻 ❤️
+
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
+
+此外，本專案的誕生離不開以下開源專案的幫助：
+
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - 偉大的貓貓框架
+
+## ⭐ Star History
+
+> [!TIP]
+> 如果本專案對您的生活 / 工作產生了幫助，或者您關注本專案的未來發展，請給專案 Star，這是我們維護這個開源專案的動力 <3
+
+<div align="center">
+
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
+
+</div>
+
+</details>
+
+_私は、高性能ですから!_
+

astrbot/api/__init__.py

@@ -1,20 +1,19 @@
-from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot import logger
-from astrbot.core import html_renderer
-from astrbot.core import sp
-from astrbot.core.star.register import register_llm_tool as llm_tool
-from astrbot.core.star.register import register_agent as agent
-from astrbot.core.agent.tool import ToolSet, FunctionTool
+from astrbot.core import html_renderer, sp
+from astrbot.core.agent.tool import FunctionTool, ToolSet
 from astrbot.core.agent.tool_executor import BaseFunctionToolExecutor
+from astrbot.core.config.astrbot_config import AstrBotConfig
+from astrbot.core.star.register import register_agent as agent
+from astrbot.core.star.register import register_llm_tool as llm_tool
 
 __all__ = [
     "AstrBotConfig",
-    "logger",
+    "BaseFunctionToolExecutor",
+    "FunctionTool",
+    "ToolSet",
+    "agent",
     "html_renderer",
     "llm_tool",
-    "agent",
+    "logger",
     "sp",
-    "ToolSet",
-    "FunctionTool",
-    "BaseFunctionToolExecutor",
 ]

astrbot/api/all.py

@@ -36,7 +36,8 @@ from astrbot.core.star.config import *
 
 
 # provider
-from astrbot.core.provider import Provider, Personality, ProviderMetaData
+from astrbot.core.provider import Provider, ProviderMetaData
+from astrbot.core.db.po import Personality
 
 # platform
 from astrbot.core.platform import (

astrbot/api/event/__init__.py

@@ -1,18 +1,17 @@
 from astrbot.core.message.message_event_result import (
-    MessageEventResult,
-    MessageChain,
     CommandResult,
     EventResultType,
+    MessageChain,
+    MessageEventResult,
     ResultContentType,
 )
-
 from astrbot.core.platform import AstrMessageEvent
 
 __all__ = [
-    "MessageEventResult",
-    "MessageChain",
+    "AstrMessageEvent",
     "CommandResult",
     "EventResultType",
-    "AstrMessageEvent",
+    "MessageChain",
+    "MessageEventResult",
     "ResultContentType",
 ]

astrbot/api/event/filter/__init__.py

@@ -1,49 +1,62 @@
-from astrbot.core.star.register import (
-    register_command as command,
-    register_command_group as command_group,
-    register_event_message_type as event_message_type,
-    register_regex as regex,
-    register_platform_adapter_type as platform_adapter_type,
-    register_permission_type as permission_type,
-    register_custom_filter as custom_filter,
-    register_on_astrbot_loaded as on_astrbot_loaded,
-    register_on_llm_request as on_llm_request,
-    register_on_llm_response as on_llm_response,
-    register_llm_tool as llm_tool,
-    register_on_decorating_result as on_decorating_result,
-    register_after_message_sent as after_message_sent,
-)
-
-from astrbot.core.star.filter.event_message_type import (
-    EventMessageTypeFilter,
-    EventMessageType,
-)
-from astrbot.core.star.filter.platform_adapter_type import (
-    PlatformAdapterTypeFilter,
-    PlatformAdapterType,
-)
-from astrbot.core.star.filter.permission import PermissionTypeFilter, PermissionType
 from astrbot.core.star.filter.custom_filter import CustomFilter
+from astrbot.core.star.filter.event_message_type import (
+    EventMessageType,
+    EventMessageTypeFilter,
+)
+from astrbot.core.star.filter.permission import PermissionType, PermissionTypeFilter
+from astrbot.core.star.filter.platform_adapter_type import (
+    PlatformAdapterType,
+    PlatformAdapterTypeFilter,
+)
+from astrbot.core.star.register import register_after_message_sent as after_message_sent
+from astrbot.core.star.register import register_command as command
+from astrbot.core.star.register import register_command_group as command_group
+from astrbot.core.star.register import register_custom_filter as custom_filter
+from astrbot.core.star.register import register_event_message_type as event_message_type
+from astrbot.core.star.register import register_llm_tool as llm_tool
+from astrbot.core.star.register import register_on_astrbot_loaded as on_astrbot_loaded
+from astrbot.core.star.register import (
+    register_on_decorating_result as on_decorating_result,
+)
+from astrbot.core.star.register import register_on_llm_request as on_llm_request
+from astrbot.core.star.register import register_on_llm_response as on_llm_response
+from astrbot.core.star.register import (
+    register_on_llm_tool_respond as on_llm_tool_respond,
+)
+from astrbot.core.star.register import register_on_platform_loaded as on_platform_loaded
+from astrbot.core.star.register import register_on_using_llm_tool as on_using_llm_tool
+from astrbot.core.star.register import (
+    register_on_waiting_llm_request as on_waiting_llm_request,
+)
+from astrbot.core.star.register import register_permission_type as permission_type
+from astrbot.core.star.register import (
+    register_platform_adapter_type as platform_adapter_type,
+)
+from astrbot.core.star.register import register_regex as regex
 
 __all__ = [
+    "CustomFilter",
+    "EventMessageType",
+    "EventMessageTypeFilter",
+    "PermissionType",
+    "PermissionTypeFilter",
+    "PlatformAdapterType",
+    "PlatformAdapterTypeFilter",
+    "after_message_sent",
     "command",
     "command_group",
-    "event_message_type",
-    "regex",
-    "platform_adapter_type",
-    "permission_type",
-    "EventMessageTypeFilter",
-    "EventMessageType",
-    "PlatformAdapterTypeFilter",
-    "PlatformAdapterType",
-    "PermissionTypeFilter",
-    "CustomFilter",
     "custom_filter",
-    "PermissionType",
-    "on_astrbot_loaded",
-    "on_llm_request",
+    "event_message_type",
     "llm_tool",
+    "on_astrbot_loaded",
     "on_decorating_result",
-    "after_message_sent",
+    "on_llm_request",
     "on_llm_response",
+    "on_platform_loaded",
+    "on_waiting_llm_request",
+    "permission_type",
+    "platform_adapter_type",
+    "regex",
+    "on_using_llm_tool",
+    "on_llm_tool_respond",
 ]

astrbot/api/platform/__init__.py

@@ -1,23 +1,22 @@
+from astrbot.core.message.components import *
 from astrbot.core.platform import (
-    AstrMessageEvent,
-    Platform,
     AstrBotMessage,
+    AstrMessageEvent,
+    Group,
     MessageMember,
     MessageType,
+    Platform,
     PlatformMetadata,
-    Group,
 )
-
 from astrbot.core.platform.register import register_platform_adapter
-from astrbot.core.message.components import *
 
 __all__ = [
-    "AstrMessageEvent",
-    "Platform",
     "AstrBotMessage",
+    "AstrMessageEvent",
+    "Group",
     "MessageMember",
     "MessageType",
+    "Platform",
     "PlatformMetadata",
     "register_platform_adapter",
-    "Group",
 ]

astrbot/api/provider/__init__.py

@@ -1,17 +1,18 @@
-from astrbot.core.provider import Provider, STTProvider, Personality
+from astrbot.core.db.po import Personality
+from astrbot.core.provider import Provider, STTProvider
 from astrbot.core.provider.entities import (
+    LLMResponse,
+    ProviderMetaData,
     ProviderRequest,
     ProviderType,
-    ProviderMetaData,
-    LLMResponse,
 )
 
 __all__ = [
-    "Provider",
-    "STTProvider",
+    "LLMResponse",
     "Personality",
+    "Provider",
+    "ProviderMetaData",
     "ProviderRequest",
     "ProviderType",
-    "ProviderMetaData",
-    "LLMResponse",
+    "STTProvider",
 ]

astrbot/api/star/__init__.py

@@ -1,8 +1,7 @@
+from astrbot.core.star import Context, Star, StarTools
+from astrbot.core.star.config import *
 from astrbot.core.star.register import (
     register_star as register,  # 注册插件（Star）
 )
 
-from astrbot.core.star import Context, Star, StarTools
-from astrbot.core.star.config import *
-
-__all__ = ["register", "Context", "Star", "StarTools"]
+__all__ = ["Context", "Star", "StarTools", "register"]

astrbot/api/util/__init__.py

@@ -1,7 +1,7 @@
 from astrbot.core.utils.session_waiter import (
-    SessionWaiter,
     SessionController,
+    SessionWaiter,
     session_waiter,
 )
 
-__all__ = ["SessionWaiter", "SessionController", "session_waiter"]
+__all__ = ["SessionController", "SessionWaiter", "session_waiter"]

astrbot/builtin_stars/astrbot/long_term_memory.py

@@ -1,13 +1,14 @@
 import datetime
-import uuid
 import random
-import astrbot.api.star as star
-from astrbot.api.event import AstrMessageEvent
-from astrbot.api.platform import MessageType
-from astrbot.api.provider import ProviderRequest
-from astrbot.api.message_components import Plain, Image
-from astrbot import logger
+import uuid
 from collections import defaultdict
+
+from astrbot import logger
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent
+from astrbot.api.message_components import At, Image, Plain
+from astrbot.api.platform import MessageType
+from astrbot.api.provider import LLMResponse, Provider, ProviderRequest
 from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
 
 """
@@ -29,13 +30,13 @@ class LongTermMemory:
         except BaseException as e:
             logger.error(e)
             max_cnt = 300
-        image_caption = (
-            True
-            if cfg["provider_settings"]["default_image_caption_provider_id"]
-            else False
-        )
         image_caption_prompt = cfg["provider_settings"]["image_caption_prompt"]
-        image_caption_provider_id = cfg["provider_settings"]["default_image_caption_provider_id"]
+        image_caption_provider_id = cfg["provider_ltm_settings"].get(
+            "image_caption_provider_id"
+        )
+        image_caption = cfg["provider_ltm_settings"]["image_caption"] and bool(
+            image_caption_provider_id
+        )
         active_reply = cfg["provider_ltm_settings"]["active_reply"]
         enable_active_reply = active_reply.get("enable", False)
         ar_method = active_reply["method"]
@@ -63,7 +64,10 @@ class LongTermMemory:
         return cnt
 
     async def get_image_caption(
-        self, image_url: str, image_caption_provider_id: str, image_caption_prompt: str
+        self,
+        image_url: str,
+        image_caption_provider_id: str,
+        image_caption_prompt: str,
     ) -> str:
         if not image_caption_provider_id:
             provider = self.context.get_using_provider()
@@ -71,6 +75,8 @@ class LongTermMemory:
             provider = self.context.get_provider_by_id(image_caption_provider_id)
             if not provider:
                 raise Exception(f"没有找到 ID 为 {image_caption_provider_id} 的提供商")
+        if not isinstance(provider, Provider):
+            raise Exception(f"提供商类型错误({type(provider)})，无法获取图片描述")
         response = await provider.text_chat(
             prompt=image_caption_prompt,
             session_id=uuid.uuid4().hex,
@@ -110,26 +116,33 @@ class LongTermMemory:
         if event.get_message_type() == MessageType.GROUP_MESSAGE:
             datetime_str = datetime.datetime.now().strftime("%H:%M:%S")
 
-            final_message = f"[{event.message_obj.sender.nickname}/{datetime_str}]: "
+            parts = [f"[{event.message_obj.sender.nickname}/{datetime_str}]: "]
 
             cfg = self.cfg(event)
 
             for comp in event.get_messages():
                 if isinstance(comp, Plain):
-                    final_message += f" {comp.text}"
+                    parts.append(f" {comp.text}")
                 elif isinstance(comp, Image):
                     if cfg["image_caption"]:
                         try:
+                            url = comp.url if comp.url else comp.file
+                            if not url:
+                                raise Exception("图片 URL 为空")
                             caption = await self.get_image_caption(
-                                comp.url if comp.url else comp.file,
+                                url,
                                 cfg["image_caption_provider_id"],
                                 cfg["image_caption_prompt"],
                             )
-                            final_message += f" [Image: {caption}]"
+                            parts.append(f" [Image: {caption}]")
                         except Exception as e:
                             logger.error(f"获取图片描述失败: {e}")
                     else:
-                        final_message += " [Image]"
+                        parts.append(" [Image]")
+                elif isinstance(comp, At):
+                    parts.append(f" [At: {comp.name}]")
+
+            final_message = "".join(parts)
             logger.debug(f"ltm | {event.unified_msg_origin} | {final_message}")
             self.session_chats[event.unified_msg_origin].append(final_message)
             if len(self.session_chats[event.unified_msg_origin]) > cfg["max_cnt"]:
@@ -145,8 +158,12 @@ class LongTermMemory:
         cfg = self.cfg(event)
         if cfg["enable_active_reply"]:
             prompt = req.prompt
-            req.prompt = f"You are now in a chatroom. The chat history is as follows:\n{chats_str}"
-            req.prompt += f"\nNow, a new message is coming: `{prompt}`. Please react to it. Only output your response and do not output any other information."
+            req.prompt = (
+                f"You are now in a chatroom. The chat history is as follows:\n{chats_str}"
+                f"\nNow, a new message is coming: `{prompt}`. "
+                "Please react to it. Only output your response and do not output any other information. "
+                "You MUST use the SAME language as the chatroom is using."
+            )
             req.contexts = []  # 清空上下文，当使用了主动回复，所有聊天记录都在一个prompt中。
         else:
             req.system_prompt += (
@@ -154,13 +171,15 @@ class LongTermMemory:
             )
             req.system_prompt += chats_str
 
-    async def after_req_llm(self, event: AstrMessageEvent):
+    async def after_req_llm(self, event: AstrMessageEvent, llm_resp: LLMResponse):
         if event.unified_msg_origin not in self.session_chats:
             return
 
-        if event.get_result() and event.get_result().is_llm_result():
-            final_message = f"[You/{datetime.datetime.now().strftime('%H:%M:%S')}]: {event.get_result().get_plain_text()}"
-            logger.debug(f"ltm | {event.unified_msg_origin} | {final_message}")
+        if llm_resp.completion_text:
+            final_message = f"[You/{datetime.datetime.now().strftime('%H:%M:%S')}]: {llm_resp.completion_text}"
+            logger.debug(
+                f"Recorded AI response: {event.unified_msg_origin} | {final_message}"
+            )
             self.session_chats[event.unified_msg_origin].append(final_message)
             cfg = self.cfg(event)
             if len(self.session_chats[event.unified_msg_origin]) > cfg["max_cnt"]:

astrbot/builtin_stars/astrbot/main.py

@@ -0,0 +1,114 @@
+import traceback
+
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, filter
+from astrbot.api.message_components import Image, Plain
+from astrbot.api.provider import LLMResponse, ProviderRequest
+from astrbot.core import logger
+
+from .long_term_memory import LongTermMemory
+
+
+class Main(star.Star):
+    def __init__(self, context: star.Context) -> None:
+        self.context = context
+        self.ltm = None
+        try:
+            self.ltm = LongTermMemory(self.context.astrbot_config_mgr, self.context)
+        except BaseException as e:
+            logger.error(f"聊天增强 err: {e}")
+
+    def ltm_enabled(self, event: AstrMessageEvent):
+        ltmse = self.context.get_config(umo=event.unified_msg_origin)[
+            "provider_ltm_settings"
+        ]
+        return ltmse["group_icl_enable"] or ltmse["active_reply"]["enable"]
+
+    @filter.platform_adapter_type(filter.PlatformAdapterType.ALL)
+    async def on_message(self, event: AstrMessageEvent):
+        """群聊记忆增强"""
+        has_image_or_plain = False
+        for comp in event.message_obj.message:
+            if isinstance(comp, Plain) or isinstance(comp, Image):
+                has_image_or_plain = True
+                break
+
+        if self.ltm_enabled(event) and self.ltm and has_image_or_plain:
+            need_active = await self.ltm.need_active_reply(event)
+
+            group_icl_enable = self.context.get_config()["provider_ltm_settings"][
+                "group_icl_enable"
+            ]
+            if group_icl_enable:
+                """记录对话"""
+                try:
+                    await self.ltm.handle_message(event)
+                except BaseException as e:
+                    logger.error(e)
+
+            if need_active:
+                """主动回复"""
+                provider = self.context.get_using_provider(event.unified_msg_origin)
+                if not provider:
+                    logger.error("未找到任何 LLM 提供商。请先配置。无法主动回复")
+                    return
+                try:
+                    conv = None
+                    session_curr_cid = await self.context.conversation_manager.get_curr_conversation_id(
+                        event.unified_msg_origin,
+                    )
+
+                    if not session_curr_cid:
+                        logger.error(
+                            "当前未处于对话状态，无法主动回复，请确保 平台设置->会话隔离(unique_session) 未开启，并使用 /switch 序号 切换或者 /new 创建一个会话。",
+                        )
+                        return
+
+                    conv = await self.context.conversation_manager.get_conversation(
+                        event.unified_msg_origin,
+                        session_curr_cid,
+                    )
+
+                    prompt = event.message_str
+
+                    if not conv:
+                        logger.error("未找到对话，无法主动回复")
+                        return
+
+                    yield event.request_llm(
+                        prompt=prompt,
+                        session_id=event.session_id,
+                        conversation=conv,
+                    )
+                except BaseException as e:
+                    logger.error(traceback.format_exc())
+                    logger.error(f"主动回复失败: {e}")
+
+    @filter.on_llm_request()
+    async def decorate_llm_req(self, event: AstrMessageEvent, req: ProviderRequest):
+        """在请求 LLM 前注入人格信息、Identifier、时间、回复内容等 System Prompt"""
+        if self.ltm and self.ltm_enabled(event):
+            try:
+                await self.ltm.on_req_llm(event, req)
+            except BaseException as e:
+                logger.error(f"ltm: {e}")
+
+    @filter.on_llm_response()
+    async def record_llm_resp_to_ltm(self, event: AstrMessageEvent, resp: LLMResponse):
+        """在 LLM 响应后记录对话"""
+        if self.ltm and self.ltm_enabled(event):
+            try:
+                await self.ltm.after_req_llm(event, resp)
+            except Exception as e:
+                logger.error(f"ltm: {e}")
+
+    @filter.after_message_sent()
+    async def after_message_sent(self, event: AstrMessageEvent):
+        """消息发送后处理"""
+        if self.ltm and self.ltm_enabled(event):
+            try:
+                clean_session = event.get_extra("_clean_ltm_session", False)
+                if clean_session:
+                    await self.ltm.remove_session(event)
+            except Exception as e:
+                logger.error(f"ltm: {e}")

astrbot/builtin_stars/astrbot/metadata.yaml

@@ -0,0 +1,4 @@
+name: astrbot
+desc: AstrBot 自带插件，包含人格注入、思考内容注入、群聊上下文感知等功能的实现，禁用后将无法使用这些功能。
+author: Soulter
+version: 4.1.0

astrbot/builtin_stars/builtin_commands/commands/__init__.py

@@ -0,0 +1,29 @@
+# Commands module
+
+from .admin import AdminCommands
+from .alter_cmd import AlterCmdCommands
+from .conversation import ConversationCommands
+from .help import HelpCommand
+from .llm import LLMCommands
+from .persona import PersonaCommands
+from .plugin import PluginCommands
+from .provider import ProviderCommands
+from .setunset import SetUnsetCommands
+from .sid import SIDCommand
+from .t2i import T2ICommand
+from .tts import TTSCommand
+
+__all__ = [
+    "AdminCommands",
+    "AlterCmdCommands",
+    "ConversationCommands",
+    "HelpCommand",
+    "LLMCommands",
+    "PersonaCommands",
+    "PluginCommands",
+    "ProviderCommands",
+    "SIDCommand",
+    "SetUnsetCommands",
+    "T2ICommand",
+    "TTSCommand",
+]

astrbot/builtin_stars/builtin_commands/commands/admin.py

@@ -0,0 +1,77 @@
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageChain, MessageEventResult
+from astrbot.core.config.default import VERSION
+from astrbot.core.utils.io import download_dashboard
+
+
+class AdminCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def op(self, event: AstrMessageEvent, admin_id: str = ""):
+        """授权管理员。op <admin_id>"""
+        if not admin_id:
+            event.set_result(
+                MessageEventResult().message(
+                    "使用方法: /op <id> 授权管理员；/deop <id> 取消管理员。可通过 /sid 获取 ID。",
+                ),
+            )
+            return
+        self.context.get_config()["admins_id"].append(str(admin_id))
+        self.context.get_config().save_config()
+        event.set_result(MessageEventResult().message("授权成功。"))
+
+    async def deop(self, event: AstrMessageEvent, admin_id: str = ""):
+        """取消授权管理员。deop <admin_id>"""
+        if not admin_id:
+            event.set_result(
+                MessageEventResult().message(
+                    "使用方法: /deop <id> 取消管理员。可通过 /sid 获取 ID。",
+                ),
+            )
+            return
+        try:
+            self.context.get_config()["admins_id"].remove(str(admin_id))
+            self.context.get_config().save_config()
+            event.set_result(MessageEventResult().message("取消授权成功。"))
+        except ValueError:
+            event.set_result(
+                MessageEventResult().message("此用户 ID 不在管理员名单内。"),
+            )
+
+    async def wl(self, event: AstrMessageEvent, sid: str = ""):
+        """添加白名单。wl <sid>"""
+        if not sid:
+            event.set_result(
+                MessageEventResult().message(
+                    "使用方法: /wl <id> 添加白名单；/dwl <id> 删除白名单。可通过 /sid 获取 ID。",
+                ),
+            )
+            return
+        cfg = self.context.get_config(umo=event.unified_msg_origin)
+        cfg["platform_settings"]["id_whitelist"].append(str(sid))
+        cfg.save_config()
+        event.set_result(MessageEventResult().message("添加白名单成功。"))
+
+    async def dwl(self, event: AstrMessageEvent, sid: str = ""):
+        """删除白名单。dwl <sid>"""
+        if not sid:
+            event.set_result(
+                MessageEventResult().message(
+                    "使用方法: /dwl <id> 删除白名单。可通过 /sid 获取 ID。",
+                ),
+            )
+            return
+        try:
+            cfg = self.context.get_config(umo=event.unified_msg_origin)
+            cfg["platform_settings"]["id_whitelist"].remove(str(sid))
+            cfg.save_config()
+            event.set_result(MessageEventResult().message("删除白名单成功。"))
+        except ValueError:
+            event.set_result(MessageEventResult().message("此 SID 不在白名单内。"))
+
+    async def update_dashboard(self, event: AstrMessageEvent):
+        """更新管理面板"""
+        await event.send(MessageChain().message("正在尝试更新管理面板..."))
+        await download_dashboard(version=f"v{VERSION}", latest=False)
+        await event.send(MessageChain().message("管理面板更新完成。"))

astrbot/builtin_stars/builtin_commands/commands/alter_cmd.py

@@ -0,0 +1,173 @@
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageChain
+from astrbot.core.star.filter.command import CommandFilter
+from astrbot.core.star.filter.command_group import CommandGroupFilter
+from astrbot.core.star.filter.permission import PermissionTypeFilter
+from astrbot.core.star.star import star_map
+from astrbot.core.star.star_handler import StarHandlerMetadata, star_handlers_registry
+from astrbot.core.utils.command_parser import CommandParserMixin
+
+from .utils.rst_scene import RstScene
+
+
+class AlterCmdCommands(CommandParserMixin):
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def update_reset_permission(self, scene_key: str, perm_type: str):
+        """更新reset命令在特定场景下的权限设置"""
+        from astrbot.api import sp
+
+        alter_cmd_cfg = await sp.global_get("alter_cmd", {})
+        plugin_cfg = alter_cmd_cfg.get("astrbot", {})
+        reset_cfg = plugin_cfg.get("reset", {})
+        reset_cfg[scene_key] = perm_type
+        plugin_cfg["reset"] = reset_cfg
+        alter_cmd_cfg["astrbot"] = plugin_cfg
+        await sp.global_put("alter_cmd", alter_cmd_cfg)
+
+    async def alter_cmd(self, event: AstrMessageEvent):
+        token = self.parse_commands(event.message_str)
+        if token.len < 3:
+            await event.send(
+                MessageChain().message(
+                    "该指令用于设置指令或指令组的权限。\n"
+                    "格式: /alter_cmd <cmd_name> <admin/member>\n"
+                    "例1: /alter_cmd c1 admin 将 c1 设为管理员指令\n"
+                    "例2: /alter_cmd g1 c1 admin 将 g1 指令组的 c1 子指令设为管理员指令\n"
+                    "/alter_cmd reset config 打开 reset 权限配置",
+                ),
+            )
+            return
+
+        # 兼容 reset scene 的专门配置
+        cmd_name = token.get(1)
+        cmd_type = token.get(2)
+
+        if cmd_name == "reset" and cmd_type == "config":
+            from astrbot.api import sp
+
+            alter_cmd_cfg = await sp.global_get("alter_cmd", {})
+            plugin_ = alter_cmd_cfg.get("astrbot", {})
+            reset_cfg = plugin_.get("reset", {})
+
+            group_unique_on = reset_cfg.get("group_unique_on", "admin")
+            group_unique_off = reset_cfg.get("group_unique_off", "admin")
+            private = reset_cfg.get("private", "member")
+
+            config_menu = f"""reset命令权限细粒度配置
+                当前配置：
+                1. 群聊+会话隔离开: {group_unique_on}
+                2. 群聊+会话隔离关: {group_unique_off}
+                3. 私聊: {private}
+                修改指令格式：
+                /alter_cmd reset scene <场景编号> <admin/member>
+                例如: /alter_cmd reset scene 2 member"""
+            await event.send(MessageChain().message(config_menu))
+            return
+
+        if cmd_name == "reset" and cmd_type == "scene" and token.len >= 4:
+            scene_num = token.get(3)
+            perm_type = token.get(4)
+
+            if scene_num is None or perm_type is None:
+                await event.send(MessageChain().message("场景编号和权限类型不能为空"))
+                return
+
+            if not scene_num.isdigit() or int(scene_num) < 1 or int(scene_num) > 3:
+                await event.send(
+                    MessageChain().message("场景编号必须是 1-3 之间的数字"),
+                )
+                return
+
+            if perm_type not in ["admin", "member"]:
+                await event.send(
+                    MessageChain().message("权限类型错误，只能是 admin 或 member"),
+                )
+                return
+
+            scene_num = int(scene_num)
+            scene = RstScene.from_index(scene_num)
+            scene_key = scene.key
+
+            await self.update_reset_permission(scene_key, perm_type)
+
+            await event.send(
+                MessageChain().message(
+                    f"已将 reset 命令在{scene.name}场景下的权限设为{perm_type}",
+                ),
+            )
+            return
+
+        if cmd_type not in ["admin", "member"]:
+            await event.send(
+                MessageChain().message("指令类型错误，可选类型有 admin, member"),
+            )
+            return
+
+        # 查找指令
+        cmd_name = " ".join(token.tokens[1:-1])
+        cmd_type = token.get(-1)
+        found_command = None
+        cmd_group = False
+        for handler in star_handlers_registry:
+            assert isinstance(handler, StarHandlerMetadata)
+            for filter_ in handler.event_filters:
+                if isinstance(filter_, CommandFilter):
+                    if filter_.equals(cmd_name):
+                        found_command = handler
+                        break
+                elif isinstance(filter_, CommandGroupFilter):
+                    if filter_.equals(cmd_name):
+                        found_command = handler
+                        cmd_group = True
+                        break
+
+        if not found_command:
+            await event.send(MessageChain().message("未找到该指令"))
+            return
+
+        found_plugin = star_map[found_command.handler_module_path]
+
+        from astrbot.api import sp
+
+        alter_cmd_cfg = await sp.global_get("alter_cmd", {})
+        plugin_ = alter_cmd_cfg.get(found_plugin.name, {})
+        cfg = plugin_.get(found_command.handler_name, {})
+        cfg["permission"] = cmd_type
+        plugin_[found_command.handler_name] = cfg
+        alter_cmd_cfg[found_plugin.name] = plugin_
+
+        await sp.global_put("alter_cmd", alter_cmd_cfg)
+
+        # 注入权限过滤器
+        found_permission_filter = False
+        for filter_ in found_command.event_filters:
+            if isinstance(filter_, PermissionTypeFilter):
+                if cmd_type == "admin":
+                    from astrbot.api.event import filter
+
+                    filter_.permission_type = filter.PermissionType.ADMIN
+                else:
+                    from astrbot.api.event import filter
+
+                    filter_.permission_type = filter.PermissionType.MEMBER
+                found_permission_filter = True
+                break
+        if not found_permission_filter:
+            from astrbot.api.event import filter
+
+            found_command.event_filters.insert(
+                0,
+                PermissionTypeFilter(
+                    filter.PermissionType.ADMIN
+                    if cmd_type == "admin"
+                    else filter.PermissionType.MEMBER,
+                ),
+            )
+        cmd_group_str = "指令组" if cmd_group else "指令"
+        await event.send(
+            MessageChain().message(
+                f"已将「{cmd_name}」{cmd_group_str} 的权限级别调整为 {cmd_type}。",
+            ),
+        )

astrbot/builtin_stars/builtin_commands/commands/conversation.py

@@ -0,0 +1,366 @@
+import datetime
+
+from astrbot.api import sp, star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+from astrbot.core.platform.astr_message_event import MessageSession
+from astrbot.core.platform.message_type import MessageType
+
+from .utils.rst_scene import RstScene
+
+THIRD_PARTY_AGENT_RUNNER_KEY = {
+    "dify": "dify_conversation_id",
+    "coze": "coze_conversation_id",
+    "dashscope": "dashscope_conversation_id",
+}
+THIRD_PARTY_AGENT_RUNNER_STR = ", ".join(THIRD_PARTY_AGENT_RUNNER_KEY.keys())
+
+
+class ConversationCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def _get_current_persona_id(self, session_id):
+        curr = await self.context.conversation_manager.get_curr_conversation_id(
+            session_id,
+        )
+        if not curr:
+            return None
+        conv = await self.context.conversation_manager.get_conversation(
+            session_id,
+            curr,
+        )
+        if not conv:
+            return None
+        return conv.persona_id
+
+    async def reset(self, message: AstrMessageEvent):
+        """重置 LLM 会话"""
+        umo = message.unified_msg_origin
+        cfg = self.context.get_config(umo=message.unified_msg_origin)
+        is_unique_session = cfg["platform_settings"]["unique_session"]
+        is_group = bool(message.get_group_id())
+
+        scene = RstScene.get_scene(is_group, is_unique_session)
+
+        alter_cmd_cfg = await sp.get_async("global", "global", "alter_cmd", {})
+        plugin_config = alter_cmd_cfg.get("astrbot", {})
+        reset_cfg = plugin_config.get("reset", {})
+
+        required_perm = reset_cfg.get(
+            scene.key,
+            "admin" if is_group and not is_unique_session else "member",
+        )
+
+        if required_perm == "admin" and message.role != "admin":
+            message.set_result(
+                MessageEventResult().message(
+                    f"在{scene.name}场景下，reset命令需要管理员权限，"
+                    f"您 (ID {message.get_sender_id()}) 不是管理员，无法执行此操作。",
+                ),
+            )
+            return
+
+        agent_runner_type = cfg["provider_settings"]["agent_runner_type"]
+        if agent_runner_type in THIRD_PARTY_AGENT_RUNNER_KEY:
+            await sp.remove_async(
+                scope="umo",
+                scope_id=umo,
+                key=THIRD_PARTY_AGENT_RUNNER_KEY[agent_runner_type],
+            )
+            message.set_result(MessageEventResult().message("重置对话成功。"))
+            return
+
+        if not self.context.get_using_provider(umo):
+            message.set_result(
+                MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"),
+            )
+            return
+
+        cid = await self.context.conversation_manager.get_curr_conversation_id(umo)
+
+        if not cid:
+            message.set_result(
+                MessageEventResult().message(
+                    "当前未处于对话状态，请 /switch 切换或者 /new 创建。",
+                ),
+            )
+            return
+
+        await self.context.conversation_manager.update_conversation(
+            umo,
+            cid,
+            [],
+        )
+
+        ret = "清除聊天历史成功！"
+
+        message.set_extra("_clean_ltm_session", True)
+
+        message.set_result(MessageEventResult().message(ret))
+
+    async def his(self, message: AstrMessageEvent, page: int = 1):
+        """查看对话记录"""
+        if not self.context.get_using_provider(message.unified_msg_origin):
+            message.set_result(
+                MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"),
+            )
+            return
+
+        size_per_page = 6
+
+        conv_mgr = self.context.conversation_manager
+        umo = message.unified_msg_origin
+        session_curr_cid = await conv_mgr.get_curr_conversation_id(umo)
+
+        if not session_curr_cid:
+            session_curr_cid = await conv_mgr.new_conversation(
+                umo,
+                message.get_platform_id(),
+            )
+
+        contexts, total_pages = await conv_mgr.get_human_readable_context(
+            umo,
+            session_curr_cid,
+            page,
+            size_per_page,
+        )
+
+        parts = []
+        for context in contexts:
+            if len(context) > 150:
+                context = context[:150] + "..."
+            parts.append(f"{context}\n")
+
+        history = "".join(parts)
+        ret = (
+            f"当前对话历史记录："
+            f"{history or '无历史记录'}\n\n"
+            f"第 {page} 页 | 共 {total_pages} 页\n"
+            f"*输入 /history 2 跳转到第 2 页"
+        )
+
+        message.set_result(MessageEventResult().message(ret).use_t2i(False))
+
+    async def convs(self, message: AstrMessageEvent, page: int = 1):
+        """查看对话列表"""
+        cfg = self.context.get_config(umo=message.unified_msg_origin)
+        agent_runner_type = cfg["provider_settings"]["agent_runner_type"]
+        if agent_runner_type in THIRD_PARTY_AGENT_RUNNER_KEY:
+            message.set_result(
+                MessageEventResult().message(
+                    f"{THIRD_PARTY_AGENT_RUNNER_STR} 对话列表功能暂不支持。",
+                ),
+            )
+            return
+
+        size_per_page = 6
+        """获取所有对话列表"""
+        conversations_all = await self.context.conversation_manager.get_conversations(
+            message.unified_msg_origin,
+        )
+        """计算总页数"""
+        total_pages = (len(conversations_all) + size_per_page - 1) // size_per_page
+        """确保页码有效"""
+        page = max(1, min(page, total_pages))
+        """分页处理"""
+        start_idx = (page - 1) * size_per_page
+        end_idx = start_idx + size_per_page
+        conversations_paged = conversations_all[start_idx:end_idx]
+
+        parts = ["对话列表：\n---\n"]
+        """全局序号从当前页的第一个开始"""
+        global_index = start_idx + 1
+
+        """生成所有对话的标题字典"""
+        _titles = {}
+        for conv in conversations_all:
+            title = conv.title if conv.title else "新对话"
+            _titles[conv.cid] = title
+
+        """遍历分页后的对话生成列表显示"""
+        for conv in conversations_paged:
+            persona_id = conv.persona_id
+            if not persona_id or persona_id == "[%None]":
+                persona = await self.context.persona_manager.get_default_persona_v3(
+                    umo=message.unified_msg_origin,
+                )
+                persona_id = persona["name"]
+            title = _titles.get(conv.cid, "新对话")
+            parts.append(
+                f"{global_index}. {title}({conv.cid[:4]})\n  人格情景: {persona_id}\n  上次更新: {datetime.datetime.fromtimestamp(conv.updated_at).strftime('%m-%d %H:%M')}\n"
+            )
+            global_index += 1
+
+        parts.append("---\n")
+        ret = "".join(parts)
+        curr_cid = await self.context.conversation_manager.get_curr_conversation_id(
+            message.unified_msg_origin,
+        )
+        if curr_cid:
+            """从所有对话的标题字典中获取标题"""
+            title = _titles.get(curr_cid, "新对话")
+            ret += f"\n当前对话: {title}({curr_cid[:4]})"
+        else:
+            ret += "\n当前对话: 无"
+
+        cfg = self.context.get_config(umo=message.unified_msg_origin)
+        unique_session = cfg["platform_settings"]["unique_session"]
+        if unique_session:
+            ret += "\n会话隔离粒度: 个人"
+        else:
+            ret += "\n会话隔离粒度: 群聊"
+
+        ret += f"\n第 {page} 页 | 共 {total_pages} 页"
+        ret += "\n*输入 /ls 2 跳转到第 2 页"
+
+        message.set_result(MessageEventResult().message(ret).use_t2i(False))
+        return
+
+    async def new_conv(self, message: AstrMessageEvent):
+        """创建新对话"""
+        cfg = self.context.get_config(umo=message.unified_msg_origin)
+        agent_runner_type = cfg["provider_settings"]["agent_runner_type"]
+        if agent_runner_type in THIRD_PARTY_AGENT_RUNNER_KEY:
+            await sp.remove_async(
+                scope="umo",
+                scope_id=message.unified_msg_origin,
+                key=THIRD_PARTY_AGENT_RUNNER_KEY[agent_runner_type],
+            )
+            message.set_result(MessageEventResult().message("已创建新对话。"))
+            return
+
+        cpersona = await self._get_current_persona_id(message.unified_msg_origin)
+        cid = await self.context.conversation_manager.new_conversation(
+            message.unified_msg_origin,
+            message.get_platform_id(),
+            persona_id=cpersona,
+        )
+
+        message.set_extra("_clean_ltm_session", True)
+
+        message.set_result(
+            MessageEventResult().message(f"切换到新对话: 新对话({cid[:4]})。"),
+        )
+
+    async def groupnew_conv(self, message: AstrMessageEvent, sid: str = ""):
+        """创建新群聊对话"""
+        if sid:
+            session = str(
+                MessageSession(
+                    platform_name=message.platform_meta.id,
+                    message_type=MessageType("GroupMessage"),
+                    session_id=sid,
+                ),
+            )
+
+            cpersona = await self._get_current_persona_id(session)
+            cid = await self.context.conversation_manager.new_conversation(
+                session,
+                message.get_platform_id(),
+                persona_id=cpersona,
+            )
+            message.set_result(
+                MessageEventResult().message(
+                    f"群聊 {session} 已切换到新对话: 新对话({cid[:4]})。",
+                ),
+            )
+        else:
+            message.set_result(
+                MessageEventResult().message("请输入群聊 ID。/groupnew 群聊ID。"),
+            )
+
+    async def switch_conv(
+        self,
+        message: AstrMessageEvent,
+        index: int | None = None,
+    ):
+        """通过 /ls 前面的序号切换对话"""
+        if not isinstance(index, int):
+            message.set_result(
+                MessageEventResult().message("类型错误，请输入数字对话序号。"),
+            )
+            return
+
+        if index is None:
+            message.set_result(
+                MessageEventResult().message(
+                    "请输入对话序号。/switch 对话序号。/ls 查看对话 /new 新建对话",
+                ),
+            )
+            return
+        conversations = await self.context.conversation_manager.get_conversations(
+            message.unified_msg_origin,
+        )
+        if index > len(conversations) or index < 1:
+            message.set_result(
+                MessageEventResult().message("对话序号错误，请使用 /ls 查看"),
+            )
+        else:
+            conversation = conversations[index - 1]
+            title = conversation.title if conversation.title else "新对话"
+            await self.context.conversation_manager.switch_conversation(
+                message.unified_msg_origin,
+                conversation.cid,
+            )
+            message.set_result(
+                MessageEventResult().message(
+                    f"切换到对话: {title}({conversation.cid[:4]})。",
+                ),
+            )
+
+    async def rename_conv(self, message: AstrMessageEvent, new_name: str = ""):
+        """重命名对话"""
+        if not new_name:
+            message.set_result(MessageEventResult().message("请输入新的对话名称。"))
+            return
+        await self.context.conversation_manager.update_conversation_title(
+            message.unified_msg_origin,
+            new_name,
+        )
+        message.set_result(MessageEventResult().message("重命名对话成功。"))
+
+    async def del_conv(self, message: AstrMessageEvent):
+        """删除当前对话"""
+        cfg = self.context.get_config(umo=message.unified_msg_origin)
+        is_unique_session = cfg["platform_settings"]["unique_session"]
+        if message.get_group_id() and not is_unique_session and message.role != "admin":
+            # 群聊，没开独立会话，发送人不是管理员
+            message.set_result(
+                MessageEventResult().message(
+                    f"会话处于群聊，并且未开启独立会话，并且您 (ID {message.get_sender_id()}) 不是管理员，因此没有权限删除当前对话。",
+                ),
+            )
+            return
+
+        agent_runner_type = cfg["provider_settings"]["agent_runner_type"]
+        if agent_runner_type in THIRD_PARTY_AGENT_RUNNER_KEY:
+            await sp.remove_async(
+                scope="umo",
+                scope_id=message.unified_msg_origin,
+                key=THIRD_PARTY_AGENT_RUNNER_KEY[agent_runner_type],
+            )
+            message.set_result(MessageEventResult().message("重置对话成功。"))
+            return
+
+        session_curr_cid = (
+            await self.context.conversation_manager.get_curr_conversation_id(
+                message.unified_msg_origin,
+            )
+        )
+
+        if not session_curr_cid:
+            message.set_result(
+                MessageEventResult().message(
+                    "当前未处于对话状态，请 /switch 序号 切换或 /new 创建。",
+                ),
+            )
+            return
+
+        await self.context.conversation_manager.delete_conversation(
+            message.unified_msg_origin,
+            session_curr_cid,
+        )
+
+        ret = "删除当前对话成功。不再处于对话状态，使用 /switch 序号 切换到其他对话或 /new 创建。"
+        message.set_extra("_clean_ltm_session", True)
+        message.set_result(MessageEventResult().message(ret))

astrbot/builtin_stars/builtin_commands/commands/help.py

@@ -0,0 +1,88 @@
+import aiohttp
+
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+from astrbot.core.config.default import VERSION
+from astrbot.core.star import command_management
+from astrbot.core.utils.io import get_dashboard_version
+
+
+class HelpCommand:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def _query_astrbot_notice(self):
+        try:
+            async with aiohttp.ClientSession(trust_env=True) as session:
+                async with session.get(
+                    "https://astrbot.app/notice.json",
+                    timeout=2,
+                ) as resp:
+                    return (await resp.json())["notice"]
+        except BaseException:
+            return ""
+
+    async def _build_reserved_command_lines(self) -> list[str]:
+        """
+        使用实时指令配置生成内置指令清单，确保重命名/禁用后与实际生效状态保持一致。
+        """
+        try:
+            commands = await command_management.list_commands()
+        except BaseException:
+            return []
+
+        lines: list[str] = []
+        hidden_commands = {"set", "unset", "websearch"}
+
+        def walk(items: list[dict], indent: int = 0):
+            for item in items:
+                if not item.get("reserved") or not item.get("enabled"):
+                    continue
+                # 仅展示顶级指令或指令组
+                if item.get("type") == "sub_command":
+                    continue
+                if item.get("parent_signature"):
+                    continue
+
+                effective = (
+                    item.get("effective_command")
+                    or item.get("original_command")
+                    or item.get("handler_name")
+                )
+                if not effective:
+                    continue
+                if effective in hidden_commands:
+                    continue
+
+                description = item.get("description") or ""
+                desc_text = f" - {description}" if description else ""
+                indent_prefix = "  " * indent
+                lines.append(f"{indent_prefix}/{effective}{desc_text}")
+
+        walk(commands)
+        return lines
+
+    async def help(self, event: AstrMessageEvent):
+        """查看帮助"""
+        notice = ""
+        try:
+            notice = await self._query_astrbot_notice()
+        except BaseException:
+            pass
+
+        dashboard_version = await get_dashboard_version()
+        command_lines = await self._build_reserved_command_lines()
+        commands_section = (
+            "\n".join(command_lines) if command_lines else "暂无启用的内置指令"
+        )
+
+        msg_parts = [
+            f"AstrBot v{VERSION}(WebUI: {dashboard_version})",
+            "内置指令:",
+            commands_section,
+        ]
+        if notice:
+            msg_parts.append(notice)
+        msg = "\n".join(msg_parts)
+
+        event.set_result(MessageEventResult().message(msg).use_t2i(False))

astrbot/builtin_stars/builtin_commands/commands/llm.py

@@ -0,0 +1,20 @@
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageChain
+
+
+class LLMCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def llm(self, event: AstrMessageEvent):
+        """开启/关闭 LLM"""
+        cfg = self.context.get_config(umo=event.unified_msg_origin)
+        enable = cfg["provider_settings"].get("enable", True)
+        if enable:
+            cfg["provider_settings"]["enable"] = False
+            status = "关闭"
+        else:
+            cfg["provider_settings"]["enable"] = True
+            status = "开启"
+        cfg.save_config()
+        await event.send(MessageChain().message(f"{status} LLM 聊天功能。"))

astrbot/builtin_stars/builtin_commands/commands/persona.py

@@ -0,0 +1,204 @@
+import builtins
+from typing import TYPE_CHECKING
+
+from astrbot.api import sp, star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+
+if TYPE_CHECKING:
+    from astrbot.core.db.po import Persona
+
+
+class PersonaCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    def _build_tree_output(
+        self,
+        folder_tree: list[dict],
+        all_personas: list["Persona"],
+        depth: int = 0,
+    ) -> list[str]:
+        """递归构建树状输出，使用短线条表示层级"""
+        lines: list[str] = []
+        # 使用短线条作为缩进前缀，每层只用 "│" 加一个空格
+        prefix = "│ " * depth
+
+        for folder in folder_tree:
+            # 输出文件夹
+            lines.append(f"{prefix}├ 📁 {folder['name']}/")
+
+            # 获取该文件夹下的人格
+            folder_personas = [
+                p for p in all_personas if p.folder_id == folder["folder_id"]
+            ]
+            child_prefix = "│ " * (depth + 1)
+
+            # 输出该文件夹下的人格
+            for persona in folder_personas:
+                lines.append(f"{child_prefix}├ 👤 {persona.persona_id}")
+
+            # 递归处理子文件夹
+            children = folder.get("children", [])
+            if children:
+                lines.extend(
+                    self._build_tree_output(
+                        children,
+                        all_personas,
+                        depth + 1,
+                    )
+                )
+
+        return lines
+
+    async def persona(self, message: AstrMessageEvent):
+        l = message.message_str.split(" ")  # noqa: E741
+        umo = message.unified_msg_origin
+
+        curr_persona_name = "无"
+        cid = await self.context.conversation_manager.get_curr_conversation_id(umo)
+        default_persona = await self.context.persona_manager.get_default_persona_v3(
+            umo=umo,
+        )
+
+        force_applied_persona_id = (
+            await sp.get_async(
+                scope="umo", scope_id=umo, key="session_service_config", default={}
+            )
+        ).get("persona_id")
+
+        curr_cid_title = "无"
+        if cid:
+            conv = await self.context.conversation_manager.get_conversation(
+                unified_msg_origin=umo,
+                conversation_id=cid,
+                create_if_not_exists=True,
+            )
+            if conv is None:
+                message.set_result(
+                    MessageEventResult().message(
+                        "当前对话不存在，请先使用 /new 新建一个对话。",
+                    ),
+                )
+                return
+            if not conv.persona_id and conv.persona_id != "[%None]":
+                curr_persona_name = default_persona["name"]
+            else:
+                curr_persona_name = conv.persona_id
+
+            if force_applied_persona_id:
+                curr_persona_name = f"{curr_persona_name} (自定义规则)"
+
+            curr_cid_title = conv.title if conv.title else "新对话"
+            curr_cid_title += f"({cid[:4]})"
+
+        if len(l) == 1:
+            message.set_result(
+                MessageEventResult()
+                .message(
+                    f"""[Persona]
+
+- 人格情景列表: `/persona list`
+- 设置人格情景: `/persona 人格`
+- 人格情景详细信息: `/persona view 人格`
+- 取消人格: `/persona unset`
+
+默认人格情景: {default_persona["name"]}
+当前对话 {curr_cid_title} 的人格情景: {curr_persona_name}
+
+配置人格情景请前往管理面板-配置页
+""",
+                )
+                .use_t2i(False),
+            )
+        elif l[1] == "list":
+            # 获取文件夹树和所有人格
+            folder_tree = await self.context.persona_manager.get_folder_tree()
+            all_personas = self.context.persona_manager.personas
+
+            lines = ["📂 人格列表：\n"]
+
+            # 构建树状输出
+            tree_lines = self._build_tree_output(folder_tree, all_personas)
+            lines.extend(tree_lines)
+
+            # 输出根目录下的人格（没有文件夹的）
+            root_personas = [p for p in all_personas if p.folder_id is None]
+            if root_personas:
+                if tree_lines:  # 如果有文件夹内容，加个空行
+                    lines.append("")
+                for persona in root_personas:
+                    lines.append(f"👤 {persona.persona_id}")
+
+            # 统计信息
+            total_count = len(all_personas)
+            lines.append(f"\n共 {total_count} 个人格")
+            lines.append("\n*使用 `/persona <人格名>` 设置人格")
+            lines.append("*使用 `/persona view <人格名>` 查看详细信息")
+
+            msg = "\n".join(lines)
+            message.set_result(MessageEventResult().message(msg).use_t2i(False))
+        elif l[1] == "view":
+            if len(l) == 2:
+                message.set_result(MessageEventResult().message("请输入人格情景名"))
+                return
+            ps = l[2].strip()
+            if persona := next(
+                builtins.filter(
+                    lambda persona: persona["name"] == ps,
+                    self.context.provider_manager.personas,
+                ),
+                None,
+            ):
+                msg = f"人格{ps}的详细信息：\n"
+                msg += f"{persona['prompt']}\n"
+            else:
+                msg = f"人格{ps}不存在"
+            message.set_result(MessageEventResult().message(msg))
+        elif l[1] == "unset":
+            if not cid:
+                message.set_result(
+                    MessageEventResult().message("当前没有对话，无法取消人格。"),
+                )
+                return
+            await self.context.conversation_manager.update_conversation_persona_id(
+                message.unified_msg_origin,
+                "[%None]",
+            )
+            message.set_result(MessageEventResult().message("取消人格成功。"))
+        else:
+            ps = "".join(l[1:]).strip()
+            if not cid:
+                message.set_result(
+                    MessageEventResult().message(
+                        "当前没有对话，请先开始对话或使用 /new 创建一个对话。",
+                    ),
+                )
+                return
+            if persona := next(
+                builtins.filter(
+                    lambda persona: persona["name"] == ps,
+                    self.context.provider_manager.personas,
+                ),
+                None,
+            ):
+                await self.context.conversation_manager.update_conversation_persona_id(
+                    message.unified_msg_origin,
+                    ps,
+                )
+                force_warn_msg = ""
+                if force_applied_persona_id:
+                    force_warn_msg = (
+                        "提醒：由于自定义规则，您现在切换的人格将不会生效。"
+                    )
+
+                message.set_result(
+                    MessageEventResult().message(
+                        f"设置成功。如果您正在切换到不同的人格，请注意使用 /reset 来清空上下文，防止原人格对话影响现人格。{force_warn_msg}",
+                    ),
+                )
+            else:
+                message.set_result(
+                    MessageEventResult().message(
+                        "不存在该人格情景。使用 /persona list 查看所有。",
+                    ),
+                )

astrbot/builtin_stars/builtin_commands/commands/plugin.py

@@ -0,0 +1,120 @@
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+from astrbot.core import DEMO_MODE, logger
+from astrbot.core.star.filter.command import CommandFilter
+from astrbot.core.star.filter.command_group import CommandGroupFilter
+from astrbot.core.star.star_handler import StarHandlerMetadata, star_handlers_registry
+from astrbot.core.star.star_manager import PluginManager
+
+
+class PluginCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def plugin_ls(self, event: AstrMessageEvent):
+        """获取已经安装的插件列表。"""
+        parts = ["已加载的插件：\n"]
+        for plugin in self.context.get_all_stars():
+            line = f"- `{plugin.name}` By {plugin.author}: {plugin.desc}"
+            if not plugin.activated:
+                line += " (未启用)"
+            parts.append(line + "\n")
+
+        if len(parts) == 1:
+            plugin_list_info = "没有加载任何插件。"
+        else:
+            plugin_list_info = "".join(parts)
+
+        plugin_list_info += "\n使用 /plugin help <插件名> 查看插件帮助和加载的指令。\n使用 /plugin on/off <插件名> 启用或者禁用插件。"
+        event.set_result(
+            MessageEventResult().message(f"{plugin_list_info}").use_t2i(False),
+        )
+
+    async def plugin_off(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """禁用插件"""
+        if DEMO_MODE:
+            event.set_result(MessageEventResult().message("演示模式下无法禁用插件。"))
+            return
+        if not plugin_name:
+            event.set_result(
+                MessageEventResult().message("/plugin off <插件名> 禁用插件。"),
+            )
+            return
+        await self.context._star_manager.turn_off_plugin(plugin_name)  # type: ignore
+        event.set_result(MessageEventResult().message(f"插件 {plugin_name} 已禁用。"))
+
+    async def plugin_on(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """启用插件"""
+        if DEMO_MODE:
+            event.set_result(MessageEventResult().message("演示模式下无法启用插件。"))
+            return
+        if not plugin_name:
+            event.set_result(
+                MessageEventResult().message("/plugin on <插件名> 启用插件。"),
+            )
+            return
+        await self.context._star_manager.turn_on_plugin(plugin_name)  # type: ignore
+        event.set_result(MessageEventResult().message(f"插件 {plugin_name} 已启用。"))
+
+    async def plugin_get(self, event: AstrMessageEvent, plugin_repo: str = ""):
+        """安装插件"""
+        if DEMO_MODE:
+            event.set_result(MessageEventResult().message("演示模式下无法安装插件。"))
+            return
+        if not plugin_repo:
+            event.set_result(
+                MessageEventResult().message("/plugin get <插件仓库地址> 安装插件"),
+            )
+            return
+        logger.info(f"准备从 {plugin_repo} 安装插件。")
+        if self.context._star_manager:
+            star_mgr: PluginManager = self.context._star_manager
+            try:
+                await star_mgr.install_plugin(plugin_repo)  # type: ignore
+                event.set_result(MessageEventResult().message("安装插件成功。"))
+            except Exception as e:
+                logger.error(f"安装插件失败: {e}")
+                event.set_result(MessageEventResult().message(f"安装插件失败: {e}"))
+                return
+
+    async def plugin_help(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """获取插件帮助"""
+        if not plugin_name:
+            event.set_result(
+                MessageEventResult().message("/plugin help <插件名> 查看插件信息。"),
+            )
+            return
+        plugin = self.context.get_registered_star(plugin_name)
+        if plugin is None:
+            event.set_result(MessageEventResult().message("未找到此插件。"))
+            return
+        help_msg = ""
+        help_msg += f"\n\n✨ 作者: {plugin.author}\n✨ 版本: {plugin.version}"
+        command_handlers = []
+        command_names = []
+        for handler in star_handlers_registry:
+            assert isinstance(handler, StarHandlerMetadata)
+            if handler.handler_module_path != plugin.module_path:
+                continue
+            for filter_ in handler.event_filters:
+                if isinstance(filter_, CommandFilter):
+                    command_handlers.append(handler)
+                    command_names.append(filter_.command_name)
+                    break
+                if isinstance(filter_, CommandGroupFilter):
+                    command_handlers.append(handler)
+                    command_names.append(filter_.group_name)
+
+        if len(command_handlers) > 0:
+            parts = ["\n\n🔧 指令列表：\n"]
+            for i in range(len(command_handlers)):
+                line = f"- {command_names[i]}"
+                if command_handlers[i].desc:
+                    line += f": {command_handlers[i].desc}"
+                parts.append(line + "\n")
+            parts.append("\nTip: 指令的触发需要添加唤醒前缀，默认为 /。")
+            help_msg += "".join(parts)
+
+        ret = f"🧩 插件 {plugin_name} 帮助信息：\n" + help_msg
+        ret += "更多帮助信息请查看插件仓库 README。"
+        event.set_result(MessageEventResult().message(ret).use_t2i(False))

astrbot/builtin_stars/builtin_commands/commands/provider.py

@@ -0,0 +1,329 @@
+import asyncio
+import re
+
+from astrbot import logger
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+from astrbot.core.provider.entities import ProviderType
+
+
+class ProviderCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    def _log_reachability_failure(
+        self,
+        provider,
+        provider_capability_type: ProviderType | None,
+        err_code: str,
+        err_reason: str,
+    ):
+        """记录不可达原因到日志。"""
+        meta = provider.meta()
+        logger.warning(
+            "Provider reachability check failed: id=%s type=%s code=%s reason=%s",
+            meta.id,
+            provider_capability_type.name if provider_capability_type else "unknown",
+            err_code,
+            err_reason,
+        )
+
+    async def _test_provider_capability(self, provider):
+        """测试单个 provider 的可用性"""
+        meta = provider.meta()
+        provider_capability_type = meta.provider_type
+
+        try:
+            await provider.test()
+            return True, None, None
+        except Exception as e:
+            err_code = "TEST_FAILED"
+            err_reason = str(e)
+            self._log_reachability_failure(
+                provider, provider_capability_type, err_code, err_reason
+            )
+            return False, err_code, err_reason
+
+    async def provider(
+        self,
+        event: AstrMessageEvent,
+        idx: str | int | None = None,
+        idx2: int | None = None,
+    ):
+        """查看或者切换 LLM Provider"""
+        umo = event.unified_msg_origin
+        cfg = self.context.get_config(umo).get("provider_settings", {})
+        reachability_check_enabled = cfg.get("reachability_check", True)
+
+        if idx is None:
+            parts = ["## 载入的 LLM 提供商\n"]
+
+            # 获取所有类型的提供商
+            llms = list(self.context.get_all_providers())
+            ttss = self.context.get_all_tts_providers()
+            stts = self.context.get_all_stt_providers()
+
+            # 构造待检测列表: [(provider, type_label), ...]
+            all_providers = []
+            all_providers.extend([(p, "llm") for p in llms])
+            all_providers.extend([(p, "tts") for p in ttss])
+            all_providers.extend([(p, "stt") for p in stts])
+
+            # 并发测试连通性
+            if reachability_check_enabled:
+                if all_providers:
+                    await event.send(
+                        MessageEventResult().message(
+                            "正在进行提供商可达性测试，请稍候..."
+                        )
+                    )
+                check_results = await asyncio.gather(
+                    *[self._test_provider_capability(p) for p, _ in all_providers],
+                    return_exceptions=True,
+                )
+            else:
+                # 用 None 表示未检测
+                check_results = [None for _ in all_providers]
+
+            # 整合结果
+            display_data = []
+            for (p, p_type), reachable in zip(all_providers, check_results):
+                meta = p.meta()
+                id_ = meta.id
+                error_code = None
+
+                if isinstance(reachable, Exception):
+                    # 异常情况下兜底处理，避免单个 provider 导致列表失败
+                    self._log_reachability_failure(
+                        p,
+                        None,
+                        reachable.__class__.__name__,
+                        str(reachable),
+                    )
+                    reachable_flag = False
+                    error_code = reachable.__class__.__name__
+                elif isinstance(reachable, tuple):
+                    reachable_flag, error_code, _ = reachable
+                else:
+                    reachable_flag = reachable
+
+                # 根据类型构建显示名称
+                if p_type == "llm":
+                    info = f"{id_} ({meta.model})"
+                else:
+                    info = f"{id_}"
+
+                # 确定状态标记
+                if reachable_flag is True:
+                    mark = " ✅"
+                elif reachable_flag is False:
+                    if error_code:
+                        mark = f" ❌(错误码: {error_code})"
+                    else:
+                        mark = " ❌"
+                else:
+                    mark = ""  # 不支持检测时不显示标记
+
+                display_data.append(
+                    {
+                        "type": p_type,
+                        "info": info,
+                        "mark": mark,
+                        "provider": p,
+                    }
+                )
+
+            # 分组输出
+            # 1. LLM
+            llm_data = [d for d in display_data if d["type"] == "llm"]
+            for i, d in enumerate(llm_data):
+                line = f"{i + 1}. {d['info']}{d['mark']}"
+                provider_using = self.context.get_using_provider(umo=umo)
+                if (
+                    provider_using
+                    and provider_using.meta().id == d["provider"].meta().id
+                ):
+                    line += " (当前使用)"
+                parts.append(line + "\n")
+
+            # 2. TTS
+            tts_data = [d for d in display_data if d["type"] == "tts"]
+            if tts_data:
+                parts.append("\n## 载入的 TTS 提供商\n")
+                for i, d in enumerate(tts_data):
+                    line = f"{i + 1}. {d['info']}{d['mark']}"
+                    tts_using = self.context.get_using_tts_provider(umo=umo)
+                    if tts_using and tts_using.meta().id == d["provider"].meta().id:
+                        line += " (当前使用)"
+                    parts.append(line + "\n")
+
+            # 3. STT
+            stt_data = [d for d in display_data if d["type"] == "stt"]
+            if stt_data:
+                parts.append("\n## 载入的 STT 提供商\n")
+                for i, d in enumerate(stt_data):
+                    line = f"{i + 1}. {d['info']}{d['mark']}"
+                    stt_using = self.context.get_using_stt_provider(umo=umo)
+                    if stt_using and stt_using.meta().id == d["provider"].meta().id:
+                        line += " (当前使用)"
+                    parts.append(line + "\n")
+
+            parts.append("\n使用 /provider <序号> 切换 LLM 提供商。")
+            ret = "".join(parts)
+
+            if ttss:
+                ret += "\n使用 /provider tts <序号> 切换 TTS 提供商。"
+            if stts:
+                ret += "\n使用 /provider stt <序号> 切换 STT 提供商。"
+            if not reachability_check_enabled:
+                ret += "\n已跳过提供商可达性检测，如需检测请在配置文件中开启。"
+
+            event.set_result(MessageEventResult().message(ret))
+        elif idx == "tts":
+            if idx2 is None:
+                event.set_result(MessageEventResult().message("请输入序号。"))
+                return
+            if idx2 > len(self.context.get_all_tts_providers()) or idx2 < 1:
+                event.set_result(MessageEventResult().message("无效的提供商序号。"))
+                return
+            provider = self.context.get_all_tts_providers()[idx2 - 1]
+            id_ = provider.meta().id
+            await self.context.provider_manager.set_provider(
+                provider_id=id_,
+                provider_type=ProviderType.TEXT_TO_SPEECH,
+                umo=umo,
+            )
+            event.set_result(MessageEventResult().message(f"成功切换到 {id_}。"))
+        elif idx == "stt":
+            if idx2 is None:
+                event.set_result(MessageEventResult().message("请输入序号。"))
+                return
+            if idx2 > len(self.context.get_all_stt_providers()) or idx2 < 1:
+                event.set_result(MessageEventResult().message("无效的提供商序号。"))
+                return
+            provider = self.context.get_all_stt_providers()[idx2 - 1]
+            id_ = provider.meta().id
+            await self.context.provider_manager.set_provider(
+                provider_id=id_,
+                provider_type=ProviderType.SPEECH_TO_TEXT,
+                umo=umo,
+            )
+            event.set_result(MessageEventResult().message(f"成功切换到 {id_}。"))
+        elif isinstance(idx, int):
+            if idx > len(self.context.get_all_providers()) or idx < 1:
+                event.set_result(MessageEventResult().message("无效的提供商序号。"))
+                return
+            provider = self.context.get_all_providers()[idx - 1]
+            id_ = provider.meta().id
+            await self.context.provider_manager.set_provider(
+                provider_id=id_,
+                provider_type=ProviderType.CHAT_COMPLETION,
+                umo=umo,
+            )
+            event.set_result(MessageEventResult().message(f"成功切换到 {id_}。"))
+        else:
+            event.set_result(MessageEventResult().message("无效的参数。"))
+
+    async def model_ls(
+        self,
+        message: AstrMessageEvent,
+        idx_or_name: int | str | None = None,
+    ):
+        """查看或者切换模型"""
+        prov = self.context.get_using_provider(message.unified_msg_origin)
+        if not prov:
+            message.set_result(
+                MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"),
+            )
+            return
+        # 定义正则表达式匹配 API 密钥
+        api_key_pattern = re.compile(r"key=[^&'\" ]+")
+
+        if idx_or_name is None:
+            models = []
+            try:
+                models = await prov.get_models()
+            except BaseException as e:
+                err_msg = api_key_pattern.sub("key=***", str(e))
+                message.set_result(
+                    MessageEventResult()
+                    .message("获取模型列表失败: " + err_msg)
+                    .use_t2i(False),
+                )
+                return
+            parts = ["下面列出了此模型提供商可用模型:"]
+            for i, model in enumerate(models, 1):
+                parts.append(f"\n{i}. {model}")
+
+            curr_model = prov.get_model() or "无"
+            parts.append(f"\n当前模型: [{curr_model}]")
+            parts.append(
+                "\nTips: 使用 /model <模型名/编号>，即可实时更换模型。如目标模型不存在于上表，请输入模型名。"
+            )
+
+            ret = "".join(parts)
+            message.set_result(MessageEventResult().message(ret).use_t2i(False))
+        elif isinstance(idx_or_name, int):
+            models = []
+            try:
+                models = await prov.get_models()
+            except BaseException as e:
+                message.set_result(
+                    MessageEventResult().message("获取模型列表失败: " + str(e)),
+                )
+                return
+            if idx_or_name > len(models) or idx_or_name < 1:
+                message.set_result(MessageEventResult().message("模型序号错误。"))
+            else:
+                try:
+                    new_model = models[idx_or_name - 1]
+                    prov.set_model(new_model)
+                except BaseException as e:
+                    message.set_result(
+                        MessageEventResult().message("切换模型未知错误: " + str(e)),
+                    )
+                message.set_result(
+                    MessageEventResult().message(
+                        f"切换模型成功。当前提供商: [{prov.meta().id}] 当前模型: [{prov.get_model()}]",
+                    ),
+                )
+        else:
+            prov.set_model(idx_or_name)
+            message.set_result(
+                MessageEventResult().message(f"切换模型到 {prov.get_model()}。"),
+            )
+
+    async def key(self, message: AstrMessageEvent, index: int | None = None):
+        prov = self.context.get_using_provider(message.unified_msg_origin)
+        if not prov:
+            message.set_result(
+                MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"),
+            )
+            return
+
+        if index is None:
+            keys_data = prov.get_keys()
+            curr_key = prov.get_current_key()
+            parts = ["Key:"]
+            for i, k in enumerate(keys_data, 1):
+                parts.append(f"\n{i}. {k[:8]}")
+
+            parts.append(f"\n当前 Key: {curr_key[:8]}")
+            parts.append("\n当前模型: " + prov.get_model())
+            parts.append("\n使用 /key <idx> 切换 Key。")
+
+            ret = "".join(parts)
+            message.set_result(MessageEventResult().message(ret).use_t2i(False))
+        else:
+            keys_data = prov.get_keys()
+            if index > len(keys_data) or index < 1:
+                message.set_result(MessageEventResult().message("Key 序号错误。"))
+            else:
+                try:
+                    new_key = keys_data[index - 1]
+                    prov.set_key(new_key)
+                except BaseException as e:
+                    message.set_result(
+                        MessageEventResult().message(f"切换 Key 未知错误: {e!s}"),
+                    )
+                message.set_result(MessageEventResult().message("切换 Key 成功。"))

astrbot/builtin_stars/builtin_commands/commands/setunset.py

@@ -0,0 +1,36 @@
+from astrbot.api import sp, star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+
+
+class SetUnsetCommands:
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def set_variable(self, event: AstrMessageEvent, key: str, value: str):
+        """设置会话变量"""
+        uid = event.unified_msg_origin
+        session_var = await sp.session_get(uid, "session_variables", {})
+        session_var[key] = value
+        await sp.session_put(uid, "session_variables", session_var)
+
+        event.set_result(
+            MessageEventResult().message(
+                f"会话 {uid} 变量 {key} 存储成功。使用 /unset 移除。",
+            ),
+        )
+
+    async def unset_variable(self, event: AstrMessageEvent, key: str):
+        """移除会话变量"""
+        uid = event.unified_msg_origin
+        session_var = await sp.session_get(uid, "session_variables", {})
+
+        if key not in session_var:
+            event.set_result(
+                MessageEventResult().message("没有那个变量名。格式 /unset 变量名。"),
+            )
+        else:
+            del session_var[key]
+            await sp.session_put(uid, "session_variables", session_var)
+            event.set_result(
+                MessageEventResult().message(f"会话 {uid} 变量 {key} 移除成功。"),
+            )

astrbot/builtin_stars/builtin_commands/commands/sid.py

@@ -0,0 +1,36 @@
+"""会话ID命令"""
+
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+
+
+class SIDCommand:
+    """会话ID命令类"""
+
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def sid(self, event: AstrMessageEvent):
+        """获取消息来源信息"""
+        sid = event.unified_msg_origin
+        user_id = str(event.get_sender_id())
+        umo_platform = event.session.platform_id
+        umo_msg_type = event.session.message_type.value
+        umo_session_id = event.session.session_id
+        ret = (
+            f"UMO: 「{sid}」 此值可用于设置白名单。\n"
+            f"UID: 「{user_id}」 此值可用于设置管理员。\n"
+            f"消息会话来源信息:\n"
+            f"  机器人 ID: 「{umo_platform}」\n"
+            f"  消息类型: 「{umo_msg_type}」\n"
+            f"  会话 ID: 「{umo_session_id}」\n"
+            f"消息来源可用于配置机器人的配置文件路由。"
+        )
+
+        if (
+            self.context.get_config()["platform_settings"]["unique_session"]
+            and event.get_group_id()
+        ):
+            ret += f"\n\n当前处于独立会话模式, 此群 ID: 「{event.get_group_id()}」, 也可将此 ID 加入白名单来放行整个群聊。"
+
+        event.set_result(MessageEventResult().message(ret).use_t2i(False))

astrbot/builtin_stars/builtin_commands/commands/t2i.py

@@ -0,0 +1,23 @@
+"""文本转图片命令"""
+
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+
+
+class T2ICommand:
+    """文本转图片命令类"""
+
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def t2i(self, event: AstrMessageEvent):
+        """开关文本转图片"""
+        config = self.context.get_config(umo=event.unified_msg_origin)
+        if config["t2i"]:
+            config["t2i"] = False
+            config.save_config()
+            event.set_result(MessageEventResult().message("已关闭文本转图片模式。"))
+            return
+        config["t2i"] = True
+        config.save_config()
+        event.set_result(MessageEventResult().message("已开启文本转图片模式。"))

astrbot/builtin_stars/builtin_commands/commands/tts.py

@@ -0,0 +1,36 @@
+"""文本转语音命令"""
+
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult
+from astrbot.core.star.session_llm_manager import SessionServiceManager
+
+
+class TTSCommand:
+    """文本转语音命令类"""
+
+    def __init__(self, context: star.Context):
+        self.context = context
+
+    async def tts(self, event: AstrMessageEvent):
+        """开关文本转语音（会话级别）"""
+        umo = event.unified_msg_origin
+        ses_tts = await SessionServiceManager.is_tts_enabled_for_session(umo)
+        cfg = self.context.get_config(umo=umo)
+        tts_enable = cfg["provider_tts_settings"]["enable"]
+
+        # 切换状态
+        new_status = not ses_tts
+        await SessionServiceManager.set_tts_status_for_session(umo, new_status)
+
+        status_text = "已开启" if new_status else "已关闭"
+
+        if new_status and not tts_enable:
+            event.set_result(
+                MessageEventResult().message(
+                    f"{status_text}当前会话的文本转语音。但 TTS 功能在配置中未启用，请前往 WebUI 开启。",
+                ),
+            )
+        else:
+            event.set_result(
+                MessageEventResult().message(f"{status_text}当前会话的文本转语音。"),
+            )

astrbot/builtin_stars/builtin_commands/commands/utils/rst_scene.py

@@ -0,0 +1,26 @@
+from enum import Enum
+
+
+class RstScene(Enum):
+    GROUP_UNIQUE_ON = ("group_unique_on", "群聊+会话隔离开启")
+    GROUP_UNIQUE_OFF = ("group_unique_off", "群聊+会话隔离关闭")
+    PRIVATE = ("private", "私聊")
+
+    @property
+    def key(self) -> str:
+        return self.value[0]
+
+    @property
+    def name(self) -> str:
+        return self.value[1]
+
+    @classmethod
+    def from_index(cls, index: int) -> "RstScene":
+        mapping = {1: cls.GROUP_UNIQUE_ON, 2: cls.GROUP_UNIQUE_OFF, 3: cls.PRIVATE}
+        return mapping[index]
+
+    @classmethod
+    def get_scene(cls, is_group: bool, is_unique_session: bool) -> "RstScene":
+        if is_group:
+            return cls.GROUP_UNIQUE_ON if is_unique_session else cls.GROUP_UNIQUE_OFF
+        return cls.PRIVATE

astrbot/builtin_stars/builtin_commands/main.py

@@ -0,0 +1,211 @@
+from astrbot.api import star
+from astrbot.api.event import AstrMessageEvent, filter
+
+from .commands import (
+    AdminCommands,
+    AlterCmdCommands,
+    ConversationCommands,
+    HelpCommand,
+    LLMCommands,
+    PersonaCommands,
+    PluginCommands,
+    ProviderCommands,
+    SetUnsetCommands,
+    SIDCommand,
+    T2ICommand,
+    TTSCommand,
+)
+
+
+class Main(star.Star):
+    def __init__(self, context: star.Context) -> None:
+        self.context = context
+
+        self.help_c = HelpCommand(self.context)
+        self.llm_c = LLMCommands(self.context)
+        self.plugin_c = PluginCommands(self.context)
+        self.admin_c = AdminCommands(self.context)
+        self.conversation_c = ConversationCommands(self.context)
+        self.provider_c = ProviderCommands(self.context)
+        self.persona_c = PersonaCommands(self.context)
+        self.alter_cmd_c = AlterCmdCommands(self.context)
+        self.setunset_c = SetUnsetCommands(self.context)
+        self.t2i_c = T2ICommand(self.context)
+        self.tts_c = TTSCommand(self.context)
+        self.sid_c = SIDCommand(self.context)
+
+    @filter.command("help")
+    async def help(self, event: AstrMessageEvent):
+        """查看帮助"""
+        await self.help_c.help(event)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("llm")
+    async def llm(self, event: AstrMessageEvent):
+        """开启/关闭 LLM"""
+        await self.llm_c.llm(event)
+
+    @filter.command_group("plugin")
+    def plugin(self):
+        """插件管理"""
+
+    @plugin.command("ls")
+    async def plugin_ls(self, event: AstrMessageEvent):
+        """获取已经安装的插件列表。"""
+        await self.plugin_c.plugin_ls(event)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @plugin.command("off")
+    async def plugin_off(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """禁用插件"""
+        await self.plugin_c.plugin_off(event, plugin_name)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @plugin.command("on")
+    async def plugin_on(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """启用插件"""
+        await self.plugin_c.plugin_on(event, plugin_name)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @plugin.command("get")
+    async def plugin_get(self, event: AstrMessageEvent, plugin_repo: str = ""):
+        """安装插件"""
+        await self.plugin_c.plugin_get(event, plugin_repo)
+
+    @plugin.command("help")
+    async def plugin_help(self, event: AstrMessageEvent, plugin_name: str = ""):
+        """获取插件帮助"""
+        await self.plugin_c.plugin_help(event, plugin_name)
+
+    @filter.command("t2i")
+    async def t2i(self, event: AstrMessageEvent):
+        """开关文本转图片"""
+        await self.t2i_c.t2i(event)
+
+    @filter.command("tts")
+    async def tts(self, event: AstrMessageEvent):
+        """开关文本转语音（会话级别）"""
+        await self.tts_c.tts(event)
+
+    @filter.command("sid")
+    async def sid(self, event: AstrMessageEvent):
+        """获取会话 ID 和 管理员 ID"""
+        await self.sid_c.sid(event)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("op")
+    async def op(self, event: AstrMessageEvent, admin_id: str = ""):
+        """授权管理员。op <admin_id>"""
+        await self.admin_c.op(event, admin_id)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("deop")
+    async def deop(self, event: AstrMessageEvent, admin_id: str):
+        """取消授权管理员。deop <admin_id>"""
+        await self.admin_c.deop(event, admin_id)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("wl")
+    async def wl(self, event: AstrMessageEvent, sid: str = ""):
+        """添加白名单。wl <sid>"""
+        await self.admin_c.wl(event, sid)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("dwl")
+    async def dwl(self, event: AstrMessageEvent, sid: str):
+        """删除白名单。dwl <sid>"""
+        await self.admin_c.dwl(event, sid)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("provider")
+    async def provider(
+        self,
+        event: AstrMessageEvent,
+        idx: str | int | None = None,
+        idx2: int | None = None,
+    ):
+        """查看或者切换 LLM Provider"""
+        await self.provider_c.provider(event, idx, idx2)
+
+    @filter.command("reset")
+    async def reset(self, message: AstrMessageEvent):
+        """重置 LLM 会话"""
+        await self.conversation_c.reset(message)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("model")
+    async def model_ls(
+        self,
+        message: AstrMessageEvent,
+        idx_or_name: int | str | None = None,
+    ):
+        """查看或者切换模型"""
+        await self.provider_c.model_ls(message, idx_or_name)
+
+    @filter.command("history")
+    async def his(self, message: AstrMessageEvent, page: int = 1):
+        """查看对话记录"""
+        await self.conversation_c.his(message, page)
+
+    @filter.command("ls")
+    async def convs(self, message: AstrMessageEvent, page: int = 1):
+        """查看对话列表"""
+        await self.conversation_c.convs(message, page)
+
+    @filter.command("new")
+    async def new_conv(self, message: AstrMessageEvent):
+        """创建新对话"""
+        await self.conversation_c.new_conv(message)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("groupnew")
+    async def groupnew_conv(self, message: AstrMessageEvent, sid: str):
+        """创建新群聊对话"""
+        await self.conversation_c.groupnew_conv(message, sid)
+
+    @filter.command("switch")
+    async def switch_conv(self, message: AstrMessageEvent, index: int | None = None):
+        """通过 /ls 前面的序号切换对话"""
+        await self.conversation_c.switch_conv(message, index)
+
+    @filter.command("rename")
+    async def rename_conv(self, message: AstrMessageEvent, new_name: str):
+        """重命名对话"""
+        await self.conversation_c.rename_conv(message, new_name)
+
+    @filter.command("del")
+    async def del_conv(self, message: AstrMessageEvent):
+        """删除当前对话"""
+        await self.conversation_c.del_conv(message)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("key")
+    async def key(self, message: AstrMessageEvent, index: int | None = None):
+        """查看或者切换 Key"""
+        await self.provider_c.key(message, index)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("persona")
+    async def persona(self, message: AstrMessageEvent):
+        """查看或者切换 Persona"""
+        await self.persona_c.persona(message)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("dashboard_update")
+    async def update_dashboard(self, event: AstrMessageEvent):
+        """更新管理面板"""
+        await self.admin_c.update_dashboard(event)
+
+    @filter.command("set")
+    async def set_variable(self, event: AstrMessageEvent, key: str, value: str):
+        await self.setunset_c.set_variable(event, key, value)
+
+    @filter.command("unset")
+    async def unset_variable(self, event: AstrMessageEvent, key: str):
+        await self.setunset_c.unset_variable(event, key)
+
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("alter_cmd", alias={"alter"})
+    async def alter_cmd(self, event: AstrMessageEvent):
+        """修改命令权限"""
+        await self.alter_cmd_c.alter_cmd(event)

astrbot/builtin_stars/builtin_commands/metadata.yaml

@@ -0,0 +1,4 @@
+name: builtin_commands
+desc: AstrBot 自带指令，提供常用的对话管理、工具使用、插件管理等功能。
+author: Soulter
+version: 0.0.1

astrbot/builtin_stars/session_controller/main.py

@@ -1,19 +1,20 @@
-import astrbot.api.message_components as Comp
 import copy
+from sys import maxsize
+
+import astrbot.api.message_components as Comp
 from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, filter
 from astrbot.api.star import Context, Star
 from astrbot.core.utils.session_waiter import (
-    SessionWaiter,
-    USER_SESSIONS,
     FILTERS,
-    session_waiter,
+    USER_SESSIONS,
     SessionController,
+    SessionWaiter,
+    session_waiter,
 )
-from sys import maxsize
 
 
-class Waiter(Star):
+class Main(Star):
     """会话控制"""
 
     def __init__(self, context: Context):
@@ -48,17 +49,18 @@ class Waiter(Star):
                     if p_settings.get("empty_mention_waiting_need_reply", True):
                         try:
                             # 尝试使用 LLM 生成更生动的回复
-                            func_tools_mgr = self.context.get_llm_tool_manager()
+                            # func_tools_mgr = self.context.get_llm_tool_manager()
 
                             # 获取用户当前的对话信息
                             curr_cid = await self.context.conversation_manager.get_curr_conversation_id(
-                                event.unified_msg_origin
+                                event.unified_msg_origin,
                             )
                             conversation = None
 
                             if curr_cid:
                                 conversation = await self.context.conversation_manager.get_conversation(
-                                    event.unified_msg_origin, curr_cid
+                                    event.unified_msg_origin,
+                                    curr_cid,
                                 )
                             else:
                                 # 创建新对话
@@ -74,23 +76,24 @@ class Waiter(Star):
                                     "你友好地询问用户想要聊些什么或者需要什么帮助，回复要符合人设，不要太过机械化。"
                                     "请注意，你仅需要输出要回复用户的内容，不要输出其他任何东西"
                                 ),
-                                func_tool_manager=func_tools_mgr,
                                 session_id=curr_cid,
                                 contexts=[],
                                 system_prompt="",
                                 conversation=conversation,
                             )
                         except Exception as e:
-                            logger.error(f"LLM response failed: {str(e)}")
+                            logger.error(f"LLM response failed: {e!s}")
                             # LLM 回复失败，使用原始预设回复
                             yield event.plain_result("想要问什么呢？😄")
 
                     @session_waiter(60)
                     async def empty_mention_waiter(
-                        controller: SessionController, event: AstrMessageEvent
+                        controller: SessionController,
+                        event: AstrMessageEvent,
                     ):
                         event.message_obj.message.insert(
-                            0, Comp.At(qq=event.get_self_id(), name=event.get_self_id())
+                            0,
+                            Comp.At(qq=event.get_self_id(), name=event.get_self_id()),
                         )
                         new_event = copy.copy(event)
                         # 重新推入事件队列

astrbot/builtin_stars/web_searcher/engines/__init__.py

@@ -1,9 +1,9 @@
 import random
-from bs4 import BeautifulSoup
-from aiohttp import ClientSession
-from dataclasses import dataclass
-from typing import List
 import urllib.parse
+from dataclasses import dataclass
+
+from aiohttp import ClientSession
+from bs4 import BeautifulSoup, Tag
 
 HEADERS = {
     "User-Agent": "Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0",
@@ -32,53 +32,62 @@ class SearchResult:
     title: str
     url: str
     snippet: str
+    favicon: str | None = None
 
     def __str__(self) -> str:
         return f"{self.title} - {self.url}\n{self.snippet}"
 
 
 class SearchEngine:
-    """
-    搜索引擎爬虫基类
-    """
+    """搜索引擎爬虫基类"""
 
     def __init__(self) -> None:
         self.TIMEOUT = 10
         self.page = 1
         self.headers = HEADERS
 
-    def _set_selector(self, selector: str) -> None:
-        raise NotImplementedError()
+    def _set_selector(self, selector: str) -> str:
+        raise NotImplementedError
 
-    def _get_next_page(self):
-        raise NotImplementedError()
+    def _get_next_page(self, query: str):
+        raise NotImplementedError
 
-    async def _get_html(self, url: str, data: dict = None) -> str:
+    async def _get_html(self, url: str, data: dict | None = None) -> str:
         headers = self.headers
         headers["Referer"] = url
         headers["User-Agent"] = random.choice(USER_AGENTS)
         if data:
-            async with ClientSession() as session:
-                async with session.post(
-                    url, headers=headers, data=data, timeout=self.TIMEOUT
-                ) as resp:
-                    ret = await resp.text(encoding="utf-8")
-                    return ret
+            async with (
+                ClientSession() as session,
+                session.post(
+                    url,
+                    headers=headers,
+                    data=data,
+                    timeout=self.TIMEOUT,
+                ) as resp,
+            ):
+                ret = await resp.text(encoding="utf-8")
+                return ret
         else:
-            async with ClientSession() as session:
-                async with session.get(
-                    url, headers=headers, timeout=self.TIMEOUT
-                ) as resp:
-                    ret = await resp.text(encoding="utf-8")
-                    return ret
+            async with (
+                ClientSession() as session,
+                session.get(
+                    url,
+                    headers=headers,
+                    timeout=self.TIMEOUT,
+                ) as resp,
+            ):
+                ret = await resp.text(encoding="utf-8")
+                return ret
 
     def tidy_text(self, text: str) -> str:
-        """
-        清理文本，去除空格、换行符等
-        """
+        """清理文本，去除空格、换行符等"""
         return text.strip().replace("\n", " ").replace("\r", " ").replace("  ", " ")
 
-    async def search(self, query: str, num_results: int) -> List[SearchResult]:
+    def _get_url(self, tag: Tag) -> str:
+        return self.tidy_text(tag.get_text())
+
+    async def search(self, query: str, num_results: int) -> list[SearchResult]:
         query = urllib.parse.quote(query)
 
         try:
@@ -87,12 +96,16 @@ class SearchEngine:
             links = soup.select(self._set_selector("links"))
             results = []
             for link in links:
-                title = self.tidy_text(
-                    link.select_one(self._set_selector("title")).text
-                )
-                url = link.select_one(self._set_selector("url"))
+                # Safely get the title text (select_one may return None)
+                title_elem = link.select_one(self._set_selector("title"))
+                title = ""
+                if title_elem is not None:
+                    title = self.tidy_text(title_elem.get_text())
+
+                url_tag = link.select_one(self._set_selector("url"))
                 snippet = ""
-                if title and url:
+                if title and url_tag:
+                    url = self._get_url(url_tag)
                     results.append(SearchResult(title=title, url=url, snippet=snippet))
             return results[:num_results] if len(results) > num_results else results
         except Exception as e:

astrbot/builtin_stars/web_searcher/engines/bing.py

@@ -1,6 +1,4 @@
-from typing import List
-from . import SearchEngine, SearchResult
-from . import USER_AGENT_BING
+from . import USER_AGENT_BING, SearchEngine
 
 
 class Bing(SearchEngine):
@@ -30,11 +28,3 @@ class Bing(SearchEngine):
                 self.base_url = base_url
                 continue
         raise Exception("Bing search failed")
-
-    async def search(self, query: str, num_results: int) -> List[SearchResult]:
-        results = await super().search(query, num_results)
-        for result in results:
-            if not isinstance(result.url, str):
-                result.url = result.url.text
-
-        return results

astrbot/builtin_stars/web_searcher/engines/sogo.py

@@ -1,10 +1,10 @@
 import random
 import re
-from bs4 import BeautifulSoup
-from . import SearchEngine, SearchResult
-from . import USER_AGENTS
+from typing import cast
 
-from typing import List
+from bs4 import BeautifulSoup, Tag
+
+from . import USER_AGENTS, SearchEngine, SearchResult
 
 
 class Sogo(SearchEngine):
@@ -27,10 +27,12 @@ class Sogo(SearchEngine):
         url = f"{self.base_url}/web?query={query}"
         return await self._get_html(url, None)
 
-    async def search(self, query: str, num_results: int) -> List[SearchResult]:
+    def _get_url(self, tag: Tag) -> str:
+        return cast(str, tag.get("href"))
+
+    async def search(self, query: str, num_results: int) -> list[SearchResult]:
         results = await super().search(query, num_results)
         for result in results:
-            result.url = result.url.get("href")
             if result.url.startswith("/link?"):
                 result.url = self.base_url + result.url
                 result.url = await self._parse_url(result.url)
@@ -41,7 +43,10 @@ class Sogo(SearchEngine):
         soup = BeautifulSoup(html, "html.parser")
         script = soup.find("script")
         if script:
-            url = re.search(r'window.location.replace\("(.+?)"\)', script.string).group(
-                1
+            script_text = (
+                script.string if script.string is not None else script.get_text()
             )
+            match = re.search(r'window.location.replace\("(.+?)"\)', script_text)
+            if match:
+                url = match.group(1)
         return url

astrbot/builtin_stars/web_searcher/main.py

@@ -1,19 +1,20 @@
-import aiohttp
 import asyncio
+import json
 import random
-import astrbot.api.star as star
-import astrbot.api.event.filter as filter
-from astrbot.api.event import AstrMessageEvent, MessageEventResult
+import uuid
+
+import aiohttp
+from bs4 import BeautifulSoup
+from readability import Document
+
+from astrbot.api import AstrBotConfig, llm_tool, logger, sp, star
+from astrbot.api.event import AstrMessageEvent, MessageEventResult, filter
 from astrbot.api.provider import ProviderRequest
-from astrbot.api import llm_tool, agent, logger, AstrBotConfig
 from astrbot.core.provider.func_tool_manager import FunctionToolManager
-from .engines import SearchResult
+
+from .engines import HEADERS, USER_AGENTS, SearchResult
 from .engines.bing import Bing
 from .engines.sogo import Sogo
-from .engines.google import Google
-from readability import Document
-from bs4 import BeautifulSoup
-from .engines import HEADERS, USER_AGENTS
 
 
 class Main(star.Star):
@@ -26,10 +27,27 @@ class Main(star.Star):
 
     def __init__(self, context: star.Context) -> None:
         self.context = context
+        self.tavily_key_index = 0
+        self.tavily_key_lock = asyncio.Lock()
+
+        # 将 str 类型的 key 迁移至 list[str]，并保存
+        cfg = self.context.get_config()
+        provider_settings = cfg.get("provider_settings")
+        if provider_settings:
+            tavily_key = provider_settings.get("websearch_tavily_key")
+            if isinstance(tavily_key, str):
+                logger.info(
+                    "检测到旧版 websearch_tavily_key (字符串格式)，自动迁移为列表格式并保存。",
+                )
+                if tavily_key:
+                    provider_settings["websearch_tavily_key"] = [tavily_key]
+                else:
+                    provider_settings["websearch_tavily_key"] = []
+                cfg.save_config()
 
         self.bing_search = Bing()
         self.sogo_search = Sogo()
-        self.google = Google()
+        self.baidu_initialized = False
 
     async def _tidy_text(self, text: str) -> str:
         """清理文本，去除空格、换行符等"""
@@ -49,7 +67,10 @@ class Main(star.Star):
                 return ret
 
     async def _process_search_result(
-        self, result: SearchResult, idx: int, websearch_link: bool
+        self,
+        result: SearchResult,
+        idx: int,
+        websearch_link: bool,
     ) -> str:
         """处理单个搜索结果"""
         logger.info(f"web_searcher - scraping web: {result.title} - {result.url}")
@@ -69,19 +90,15 @@ class Main(star.Star):
         return f"{header}\n{result.snippet}\n{site_result}\n\n"
 
     async def _web_search_default(
-        self, query, num_results: int = 5
+        self,
+        query,
+        num_results: int = 5,
     ) -> list[SearchResult]:
         results = []
         try:
-            results = await self.google.search(query, num_results)
+            results = await self.bing_search.search(query, num_results)
         except Exception as e:
-            logger.error(f"google search error: {e}, try the next one...")
-        if len(results) == 0:
-            logger.debug("search google failed")
-            try:
-                results = await self.bing_search.search(query, num_results)
-            except Exception as e:
-                logger.error(f"bing search error: {e}, try the next one...")
+            logger.error(f"bing search error: {e}, try the next one...")
         if len(results) == 0:
             logger.debug("search bing failed")
             try:
@@ -94,13 +111,24 @@ class Main(star.Star):
 
         return results
 
+    async def _get_tavily_key(self, cfg: AstrBotConfig) -> str:
+        """并发安全的从列表中获取并轮换Tavily API密钥。"""
+        tavily_keys = cfg.get("provider_settings", {}).get("websearch_tavily_key", [])
+        if not tavily_keys:
+            raise ValueError("错误：Tavily API密钥未在AstrBot中配置。")
+
+        async with self.tavily_key_lock:
+            key = tavily_keys[self.tavily_key_index]
+            self.tavily_key_index = (self.tavily_key_index + 1) % len(tavily_keys)
+            return key
+
     async def _web_search_tavily(
-        self, cfg: AstrBotConfig, payload: dict
+        self,
+        cfg: AstrBotConfig,
+        payload: dict,
     ) -> list[SearchResult]:
         """使用 Tavily 搜索引擎进行搜索"""
-        tavily_key = cfg.get("provider_settings", {}).get("websearch_tavily_key", None)
-        if not tavily_key:
-            raise ValueError("Error: Tavily API key is not configured in AstrBot.")
+        tavily_key = await self._get_tavily_key(cfg)
         url = "https://api.tavily.com/search"
         header = {
             "Authorization": f"Bearer {tavily_key}",
@@ -108,12 +136,15 @@ class Main(star.Star):
         }
         async with aiohttp.ClientSession(trust_env=True) as session:
             async with session.post(
-                url, json=payload, headers=header, timeout=6
+                url,
+                json=payload,
+                headers=header,
+                timeout=6,
             ) as response:
                 if response.status != 200:
                     reason = await response.text()
                     raise Exception(
-                        f"Tavily web search failed: {reason}, status: {response.status}"
+                        f"Tavily web search failed: {reason}, status: {response.status}",
                     )
                 data = await response.json()
                 results = []
@@ -122,15 +153,14 @@ class Main(star.Star):
                         title=item.get("title"),
                         url=item.get("url"),
                         snippet=item.get("content"),
+                        favicon=item.get("favicon"),
                     )
                     results.append(result)
                 return results
 
     async def _extract_tavily(self, cfg: AstrBotConfig, payload: dict) -> list[dict]:
         """使用 Tavily 提取网页内容"""
-        tavily_key = cfg.get("provider_settings", {}).get("websearch_tavily_key", None)
-        if not tavily_key:
-            raise ValueError("Error: Tavily API key is not configured in AstrBot.")
+        tavily_key = await self._get_tavily_key(cfg)
         url = "https://api.tavily.com/extract"
         header = {
             "Authorization": f"Bearer {tavily_key}",
@@ -138,38 +168,46 @@ class Main(star.Star):
         }
         async with aiohttp.ClientSession(trust_env=True) as session:
             async with session.post(
-                url, json=payload, headers=header, timeout=6
+                url,
+                json=payload,
+                headers=header,
+                timeout=6,
             ) as response:
                 if response.status != 200:
                     reason = await response.text()
                     raise Exception(
-                        f"Tavily web search failed: {reason}, status: {response.status}"
+                        f"Tavily web search failed: {reason}, status: {response.status}",
                     )
                 data = await response.json()
                 results: list[dict] = data.get("results", [])
                 if not results:
                     raise ValueError(
-                        "Error: Tavily web searcher does not return any results."
+                        "Error: Tavily web searcher does not return any results.",
                     )
                 return results
 
     @filter.command("websearch")
-    async def websearch(self, event: AstrMessageEvent, oper: str = None) -> str:
+    async def websearch(self, event: AstrMessageEvent, oper: str | None = None):
+        """网页搜索指令（已废弃）"""
         event.set_result(
             MessageEventResult().message(
-                "此指令已经被废弃，请在 WebUI 中开启或关闭网页搜索功能。"
-            )
+                "此指令已经被废弃，请在 WebUI 中开启或关闭网页搜索功能。",
+            ),
         )
 
     @llm_tool(name="web_search")
     async def search_from_search_engine(
-        self, event: AstrMessageEvent, query: str, max_results: int = 5
+        self,
+        event: AstrMessageEvent,
+        query: str,
+        max_results: int = 5,
     ) -> str:
         """搜索网络以回答用户的问题。当用户需要搜索网络以获取即时性的信息时调用此工具。
 
         Args:
             query(string): 和用户的问题最相关的搜索关键词，用于在 Google 上搜索。
             max_results(number): 返回的最大搜索结果数量，默认为 5。
+
         """
         logger.info(f"web_searcher - search_from_search_engine: {query}")
         cfg = self.context.get_config(umo=event.unified_msg_origin)
@@ -186,7 +224,7 @@ class Main(star.Star):
         processed_results = await asyncio.gather(*tasks, return_exceptions=True)
         ret = ""
         for processed_result in processed_results:
-            if isinstance(processed_result, Exception):
+            if isinstance(processed_result, BaseException):
                 logger.error(f"Error processing search result: {processed_result}")
                 continue
             ret += processed_result
@@ -196,12 +234,38 @@ class Main(star.Star):
 
         return ret
 
+    async def ensure_baidu_ai_search_mcp(self, umo: str | None = None):
+        if self.baidu_initialized:
+            return
+        cfg = self.context.get_config(umo=umo)
+        key = cfg.get("provider_settings", {}).get(
+            "websearch_baidu_app_builder_key",
+            "",
+        )
+        if not key:
+            raise ValueError(
+                "Error: Baidu AI Search API key is not configured in AstrBot.",
+            )
+        func_tool_mgr = self.context.get_llm_tool_manager()
+        await func_tool_mgr.enable_mcp_server(
+            "baidu_ai_search",
+            config={
+                "transport": "sse",
+                "url": f"http://appbuilder.baidu.com/v2/ai_search/mcp/sse?api_key={key}",
+                "headers": {},
+                "timeout": 30,
+            },
+        )
+        self.baidu_initialized = True
+        logger.info("Successfully initialized Baidu AI Search MCP server.")
+
     @llm_tool(name="fetch_url")
     async def fetch_website_content(self, event: AstrMessageEvent, url: str) -> str:
-        """fetch the content of a website with the given web url
+        """Fetch the content of a website with the given web url
 
         Args:
             url(string): The url of the website to fetch content from
+
         """
         resp = await self._get_from_url(url)
         return resp
@@ -211,7 +275,7 @@ class Main(star.Star):
         self,
         event: AstrMessageEvent,
         query: str,
-        max_results: int = 5,
+        max_results: int = 7,
         search_depth: str = "basic",
         topic: str = "general",
         days: int = 3,
@@ -224,26 +288,23 @@ class Main(star.Star):
 
         Args:
             query(string): Required. Search query.
-            max_results(number): Optional. The maximum number of results to return. Default is 5. Range is 5-20.
+            max_results(number): Optional. The maximum number of results to return. Default is 7. Range is 5-20.
             search_depth(string): Optional. The depth of the search, must be one of 'basic', 'advanced'. Default is "basic".
             topic(string): Optional. The topic of the search, must be one of 'general', 'news'. Default is "general".
             days(number): Optional. The number of days back from the current date to include in the search results. Please note that this feature is only available when using the 'news' search topic.
             time_range(string): Optional. The time range back from the current date to include in the search results. This feature is available for both 'general' and 'news' search topics. Must be one of 'day', 'week', 'month', 'year'.
             start_date(string): Optional. The start date for the search results in the format 'YYYY-MM-DD'.
             end_date(string): Optional. The end date for the search results in the format 'YYYY-MM-DD'.
+
         """
         logger.info(f"web_searcher - search_from_tavily: {query}")
         cfg = self.context.get_config(umo=event.unified_msg_origin)
-        websearch_link = cfg["provider_settings"].get("web_search_link", False)
-        tavily_key = cfg.get("provider_settings", {}).get("websearch_tavily_key", None)
-        if not tavily_key:
+        # websearch_link = cfg["provider_settings"].get("web_search_link", False)
+        if not cfg.get("provider_settings", {}).get("websearch_tavily_key", []):
             raise ValueError("Error: Tavily API key is not configured in AstrBot.")
 
         # build payload
-        payload = {
-            "query": query,
-            "max_results": max_results,
-        }
+        payload = {"query": query, "max_results": max_results, "include_favicon": True}
         if search_depth not in ["basic", "advanced"]:
             search_depth = "basic"
         payload["search_depth"] = search_depth
@@ -267,29 +328,40 @@ class Main(star.Star):
             return "Error: Tavily web searcher does not return any results."
 
         ret_ls = []
-        for result in results:
-            ret_ls.append(f"\nTitle: {result.title}")
-            ret_ls.append(f"URL: {result.url}")
-            ret_ls.append(f"Content: {result.snippet}")
-        ret = "\n".join(ret_ls)
-
-        if websearch_link:
-            ret += "\n\n针对问题，请根据上面的结果分点总结，并且在结尾处附上对应内容的参考链接（如有）。"
+        ref_uuid = str(uuid.uuid4())[:4]
+        for idx, result in enumerate(results, 1):
+            index = f"{ref_uuid}.{idx}"
+            ret_ls.append(
+                {
+                    "title": f"{result.title}",
+                    "url": f"{result.url}",
+                    "snippet": f"{result.snippet}",
+                    # TODO: do not need ref for non-webchat platform adapter
+                    "index": index,
+                }
+            )
+            if result.favicon:
+                sp.temorary_cache["_ws_favicon"][result.url] = result.favicon
+        # ret = "\n".join(ret_ls)
+        ret = json.dumps({"results": ret_ls}, ensure_ascii=False)
         return ret
 
     @llm_tool("tavily_extract_web_page")
     async def tavily_extract_web_page(
-        self, event: AstrMessageEvent, url: str = "", extract_depth: str = "basic"
+        self,
+        event: AstrMessageEvent,
+        url: str = "",
+        extract_depth: str = "basic",
     ) -> str:
         """Extract the content of a web page using Tavily.
 
         Args:
             url(string): Required. An URl to extract content from.
             extract_depth(string): Optional. The depth of the extraction, must be one of 'basic', 'advanced'. Default is "basic".
+
         """
         cfg = self.context.get_config(umo=event.unified_msg_origin)
-        tavily_key = cfg.get("provider_settings", {}).get("websearch_tavily_key", None)
-        if not tavily_key:
+        if not cfg.get("provider_settings", {}).get("websearch_tavily_key", []):
             raise ValueError("Error: Tavily API key is not configured in AstrBot.")
 
         if not url:
@@ -312,8 +384,10 @@ class Main(star.Star):
 
     @filter.on_llm_request(priority=-10000)
     async def edit_web_search_tools(
-        self, event: AstrMessageEvent, req: ProviderRequest
-    ) -> str:
+        self,
+        event: AstrMessageEvent,
+        req: ProviderRequest,
+    ):
         """Get the session conversation for the given event."""
         cfg = self.context.get_config(umo=event.unified_msg_origin)
         prov_settings = cfg.get("provider_settings", {})
@@ -325,6 +399,9 @@ class Main(star.Star):
             req.func_tool = tool_set.get_full_tool_set()
             tool_set = req.func_tool
 
+        if not tool_set:
+            return
+
         if not websearch_enable:
             # pop tools
             for tool_name in self.TOOLS:
@@ -341,6 +418,7 @@ class Main(star.Star):
                 tool_set.add_tool(fetch_url_t)
             tool_set.remove_tool("web_search_tavily")
             tool_set.remove_tool("tavily_extract_web_page")
+            tool_set.remove_tool("AIsearch")
         elif provider == "tavily":
             web_search_tavily = func_tool_mgr.get_func("web_search_tavily")
             tavily_extract_web_page = func_tool_mgr.get_func("tavily_extract_web_page")
@@ -350,3 +428,17 @@ class Main(star.Star):
                 tool_set.add_tool(tavily_extract_web_page)
             tool_set.remove_tool("web_search")
             tool_set.remove_tool("fetch_url")
+            tool_set.remove_tool("AIsearch")
+        elif provider == "baidu_ai_search":
+            try:
+                await self.ensure_baidu_ai_search_mcp(event.unified_msg_origin)
+                aisearch_tool = func_tool_mgr.get_func("AIsearch")
+                if not aisearch_tool:
+                    raise ValueError("Cannot get Baidu AI Search MCP tool.")
+                tool_set.add_tool(aisearch_tool)
+                tool_set.remove_tool("web_search")
+                tool_set.remove_tool("fetch_url")
+                tool_set.remove_tool("web_search_tavily")
+                tool_set.remove_tool("tavily_extract_web_page")
+            except Exception as e:
+                logger.error(f"Cannot Initialize Baidu AI Search MCP Server: {e}")

astrbot/cli/__init__.py

@@ -1 +1 @@
-__version__ = "3.5.23"
+__version__ = "4.14.4"

astrbot/cli/__main__.py

@@ -1,11 +1,11 @@
-"""
-AstrBot CLI入口
-"""
+"""AstrBot CLI入口"""
+
+import sys
 
 import click
-import sys
+
 from . import __version__
-from .commands import init, run, plug, conf
+from .commands import conf, init, plug, run
 
 logo_tmpl = r"""
      ___           _______.___________..______      .______     ______   .___________.

astrbot/cli/commands/__init__.py

@@ -1,6 +1,6 @@
-from .cmd_init import init
-from .cmd_run import run
-from .cmd_plug import plug
 from .cmd_conf import conf
+from .cmd_init import init
+from .cmd_plug import plug
+from .cmd_run import run
 
-__all__ = ["init", "run", "plug", "conf"]
+__all__ = ["conf", "init", "plug", "run"]

astrbot/cli/commands/cmd_conf.py

@@ -1,9 +1,12 @@
-import json
-import click
 import hashlib
+import json
 import zoneinfo
-from typing import Any, Callable
-from ..utils import get_astrbot_root, check_astrbot_root
+from collections.abc import Callable
+from typing import Any
+
+import click
+
+from ..utils import check_astrbot_root, get_astrbot_root
 
 
 def _validate_log_level(value: str) -> str:
@@ -11,7 +14,7 @@ def _validate_log_level(value: str) -> str:
     value = value.upper()
     if value not in ["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"]:
         raise click.ClickException(
-            "日志级别必须是 DEBUG/INFO/WARNING/ERROR/CRITICAL 之一"
+            "日志级别必须是 DEBUG/INFO/WARNING/ERROR/CRITICAL 之一",
         )
     return value
 
@@ -73,7 +76,7 @@ def _load_config() -> dict[str, Any]:
     root = get_astrbot_root()
     if not check_astrbot_root(root):
         raise click.ClickException(
-            f"{root}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init"
+            f"{root}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init",
         )
 
     config_path = root / "data" / "cmd_config.json"
@@ -88,7 +91,7 @@ def _load_config() -> dict[str, Any]:
     try:
         return json.loads(config_path.read_text(encoding="utf-8-sig"))
     except json.JSONDecodeError as e:
-        raise click.ClickException(f"配置文件解析失败: {str(e)}")
+        raise click.ClickException(f"配置文件解析失败: {e!s}")
 
 
 def _save_config(config: dict[str, Any]) -> None:
@@ -96,7 +99,8 @@ def _save_config(config: dict[str, Any]) -> None:
     config_path = get_astrbot_root() / "data" / "cmd_config.json"
 
     config_path.write_text(
-        json.dumps(config, ensure_ascii=False, indent=2), encoding="utf-8-sig"
+        json.dumps(config, ensure_ascii=False, indent=2),
+        encoding="utf-8-sig",
     )
 
 
@@ -108,7 +112,7 @@ def _set_nested_item(obj: dict[str, Any], path: str, value: Any) -> None:
             obj[part] = {}
         elif not isinstance(obj[part], dict):
             raise click.ClickException(
-                f"配置路径冲突: {'.'.join(parts[: parts.index(part) + 1])} 不是字典"
+                f"配置路径冲突: {'.'.join(parts[: parts.index(part) + 1])} 不是字典",
             )
         obj = obj[part]
     obj[parts[-1]] = value
@@ -140,7 +144,6 @@ def conf():
 
     - callback_api_base: 回调接口基址
     """
-    pass
 
 
 @conf.command(name="set")
@@ -148,7 +151,7 @@ def conf():
 @click.argument("value")
 def set_config(key: str, value: str):
     """设置配置项的值"""
-    if key not in CONFIG_VALIDATORS.keys():
+    if key not in CONFIG_VALIDATORS:
         raise click.ClickException(f"不支持的配置项: {key}")
 
     config = _load_config()
@@ -170,17 +173,17 @@ def set_config(key: str, value: str):
     except KeyError:
         raise click.ClickException(f"未知的配置项: {key}")
     except Exception as e:
-        raise click.UsageError(f"设置配置失败: {str(e)}")
+        raise click.UsageError(f"设置配置失败: {e!s}")
 
 
 @conf.command(name="get")
 @click.argument("key", required=False)
-def get_config(key: str = None):
+def get_config(key: str | None = None):
     """获取配置项的值，不提供key则显示所有可配置项"""
     config = _load_config()
 
     if key:
-        if key not in CONFIG_VALIDATORS.keys():
+        if key not in CONFIG_VALIDATORS:
             raise click.ClickException(f"不支持的配置项: {key}")
 
         try:
@@ -191,10 +194,10 @@ def get_config(key: str = None):
         except KeyError:
             raise click.ClickException(f"未知的配置项: {key}")
         except Exception as e:
-            raise click.UsageError(f"获取配置失败: {str(e)}")
+            raise click.UsageError(f"获取配置失败: {e!s}")
     else:
         click.echo("当前配置:")
-        for key in CONFIG_VALIDATORS.keys():
+        for key in CONFIG_VALIDATORS:
             try:
                 value = (
                     "********"

astrbot/cli/commands/cmd_init.py

@@ -1,4 +1,5 @@
 import asyncio
+from pathlib import Path
 
 import click
 from filelock import FileLock, Timeout
@@ -6,14 +7,14 @@ from filelock import FileLock, Timeout
 from ..utils import check_dashboard, get_astrbot_root
 
 
-async def initialize_astrbot(astrbot_root) -> None:
+async def initialize_astrbot(astrbot_root: Path) -> None:
     """执行 AstrBot 初始化逻辑"""
     dot_astrbot = astrbot_root / ".astrbot"
 
     if not dot_astrbot.exists():
         click.echo(f"Current Directory: {astrbot_root}")
         click.echo(
-            "如果你确认这是 Astrbot root directory, 你需要在当前目录下创建一个 .astrbot 文件标记该目录为 AstrBot 的数据目录。"
+            "如果你确认这是 Astrbot root directory, 你需要在当前目录下创建一个 .astrbot 文件标记该目录为 AstrBot 的数据目录。",
         )
         if click.confirm(
             f"请检查当前目录是否正确，确认正确请回车: {astrbot_root}",

astrbot/cli/commands/cmd_plug.py

@@ -1,31 +1,29 @@
 import re
+import shutil
 from pathlib import Path
 
 import click
-import shutil
-
 
 from ..utils import (
-    get_git_repo,
-    build_plug_list,
-    manage_plugin,
     PluginStatus,
+    build_plug_list,
     check_astrbot_root,
     get_astrbot_root,
+    get_git_repo,
+    manage_plugin,
 )
 
 
 @click.group()
 def plug():
     """插件管理"""
-    pass
 
 
 def _get_data_path() -> Path:
     base = get_astrbot_root()
     if not check_astrbot_root(base):
         raise click.ClickException(
-            f"{base}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init"
+            f"{base}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init",
         )
     return (base / "data").resolve()
 
@@ -41,7 +39,7 @@ def display_plugins(plugins, title=None, color=None):
         desc = p["desc"][:30] + ("..." if len(p["desc"]) > 30 else "")
         click.echo(
             f"{p['name']:<20} {p['version']:<10} {p['status']:<10} "
-            f"{p['author']:<15} {desc:<30}"
+            f"{p['author']:<15} {desc:<30}",
         )
 
 
@@ -78,7 +76,7 @@ def new(name: str):
             f"desc: {desc}\n"
             f"version: {version}\n"
             f"author: {author}\n"
-            f"repo: {repo}\n"
+            f"repo: {repo}\n",
         )
 
     # 重写 README.md
@@ -86,7 +84,7 @@ def new(name: str):
         f.write(f"# {name}\n\n{desc}\n\n# 支持\n\n[帮助文档](https://astrbot.app)\n")
 
     # 重写 main.py
-    with open(plug_path / "main.py", "r", encoding="utf-8") as f:
+    with open(plug_path / "main.py", encoding="utf-8") as f:
         content = f.read()
 
     new_content = content.replace(

astrbot/cli/commands/cmd_run.py

@@ -1,19 +1,18 @@
+import asyncio
 import os
 import sys
+import traceback
 from pathlib import Path
 
 import click
-import asyncio
-import traceback
-
 from filelock import FileLock, Timeout
 
-from ..utils import check_dashboard, check_astrbot_root, get_astrbot_root
+from ..utils import check_astrbot_root, check_dashboard, get_astrbot_root
 
 
 async def run_astrbot(astrbot_root: Path):
     """运行 AstrBot"""
-    from astrbot.core import logger, LogManager, LogBroker, db_helper
+    from astrbot.core import LogBroker, LogManager, db_helper, logger
     from astrbot.core.initial_loader import InitialLoader
 
     await check_dashboard(astrbot_root / "data")
@@ -38,7 +37,7 @@ def run(reload: bool, port: str) -> None:
 
         if not check_astrbot_root(astrbot_root):
             raise click.ClickException(
-                f"{astrbot_root}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init"
+                f"{astrbot_root}不是有效的 AstrBot 根目录，如需初始化请使用 astrbot init",
             )
 
         os.environ["ASTRBOT_ROOT"] = str(astrbot_root)

astrbot/cli/utils/__init__.py

@@ -1,18 +1,18 @@
 from .basic import (
-    get_astrbot_root,
     check_astrbot_root,
     check_dashboard,
+    get_astrbot_root,
 )
-from .plugin import get_git_repo, manage_plugin, build_plug_list, PluginStatus
+from .plugin import PluginStatus, build_plug_list, get_git_repo, manage_plugin
 from .version_comparator import VersionComparator
 
 __all__ = [
-    "get_astrbot_root",
+    "PluginStatus",
+    "VersionComparator",
+    "build_plug_list",
     "check_astrbot_root",
     "check_dashboard",
+    "get_astrbot_root",
     "get_git_repo",
     "manage_plugin",
-    "build_plug_list",
-    "VersionComparator",
-    "PluginStatus",
 ]

astrbot/cli/utils/basic.py

@@ -21,8 +21,9 @@ def get_astrbot_root() -> Path:
 
 async def check_dashboard(astrbot_root: Path) -> None:
     """检查是否安装了dashboard"""
-    from astrbot.core.utils.io import get_dashboard_version, download_dashboard
     from astrbot.core.config.default import VERSION
+    from astrbot.core.utils.io import download_dashboard, get_dashboard_version
+
     from .version_comparator import VersionComparator
 
     try:
@@ -48,19 +49,18 @@ async def check_dashboard(astrbot_root: Path) -> None:
                 if VersionComparator.compare_version(VERSION, dashboard_version) <= 0:
                     click.echo("管理面板已是最新版本")
                     return
-                else:
-                    try:
-                        version = dashboard_version.split("v")[1]
-                        click.echo(f"管理面板版本: {version}")
-                        await download_dashboard(
-                            path="data/dashboard.zip",
-                            extract_path=str(astrbot_root),
-                            version=f"v{VERSION}",
-                            latest=False,
-                        )
-                    except Exception as e:
-                        click.echo(f"下载管理面板失败: {e}")
-                        return
+                try:
+                    version = dashboard_version.split("v")[1]
+                    click.echo(f"管理面板版本: {version}")
+                    await download_dashboard(
+                        path="data/dashboard.zip",
+                        extract_path=str(astrbot_root),
+                        version=f"v{VERSION}",
+                        latest=False,
+                    )
+                except Exception as e:
+                    click.echo(f"下载管理面板失败: {e}")
+                    return
     except FileNotFoundError:
         click.echo("初始化管理面板目录...")
         try:

astrbot/cli/utils/plugin.py

@@ -1,14 +1,14 @@
 import shutil
 import tempfile
-
-import httpx
-import yaml
 from enum import Enum
 from io import BytesIO
 from pathlib import Path
 from zipfile import ZipFile
 
 import click
+import httpx
+import yaml
+
 from .version_comparator import VersionComparator
 
 
@@ -32,7 +32,8 @@ def get_git_repo(url: str, target_path: Path, proxy: str | None = None):
         release_url = f"https://api.github.com/repos/{author}/{repo}/releases"
         try:
             with httpx.Client(
-                proxy=proxy if proxy else None, follow_redirects=True
+                proxy=proxy if proxy else None,
+                follow_redirects=True,
             ) as client:
                 resp = client.get(release_url)
                 resp.raise_for_status()
@@ -55,7 +56,8 @@ def get_git_repo(url: str, target_path: Path, proxy: str | None = None):
 
         # 下载并解压
         with httpx.Client(
-            proxy=proxy if proxy else None, follow_redirects=True
+            proxy=proxy if proxy else None,
+            follow_redirects=True,
         ) as client:
             resp = client.get(download_url)
             if (
@@ -89,6 +91,7 @@ def load_yaml_metadata(plugin_dir: Path) -> dict:
 
     Returns:
         dict: 包含元数据的字典，如果读取失败则返回空字典
+
     """
     yaml_path = plugin_dir / "metadata.yaml"
     if yaml_path.exists():
@@ -107,6 +110,7 @@ def build_plug_list(plugins_dir: Path) -> list:
 
     Returns:
         list: 包含插件信息的字典列表
+
     """
     # 获取本地插件信息
     result = []
@@ -124,15 +128,17 @@ def build_plug_list(plugins_dir: Path) -> list:
             if metadata and all(
                 k in metadata for k in ["name", "desc", "version", "author", "repo"]
             ):
-                result.append({
-                    "name": str(metadata.get("name", "")),
-                    "desc": str(metadata.get("desc", "")),
-                    "version": str(metadata.get("version", "")),
-                    "author": str(metadata.get("author", "")),
-                    "repo": str(metadata.get("repo", "")),
-                    "status": PluginStatus.INSTALLED,
-                    "local_path": str(plugin_dir),
-                })
+                result.append(
+                    {
+                        "name": str(metadata.get("name", "")),
+                        "desc": str(metadata.get("desc", "")),
+                        "version": str(metadata.get("version", "")),
+                        "author": str(metadata.get("author", "")),
+                        "repo": str(metadata.get("repo", "")),
+                        "status": PluginStatus.INSTALLED,
+                        "local_path": str(plugin_dir),
+                    },
+                )
 
     # 获取在线插件列表
     online_plugins = []
@@ -142,15 +148,17 @@ def build_plug_list(plugins_dir: Path) -> list:
             resp.raise_for_status()
             data = resp.json()
             for plugin_id, plugin_info in data.items():
-                online_plugins.append({
-                    "name": str(plugin_id),
-                    "desc": str(plugin_info.get("desc", "")),
-                    "version": str(plugin_info.get("version", "")),
-                    "author": str(plugin_info.get("author", "")),
-                    "repo": str(plugin_info.get("repo", "")),
-                    "status": PluginStatus.NOT_INSTALLED,
-                    "local_path": None,
-                })
+                online_plugins.append(
+                    {
+                        "name": str(plugin_id),
+                        "desc": str(plugin_info.get("desc", "")),
+                        "version": str(plugin_info.get("version", "")),
+                        "author": str(plugin_info.get("author", "")),
+                        "repo": str(plugin_info.get("repo", "")),
+                        "status": PluginStatus.NOT_INSTALLED,
+                        "local_path": None,
+                    },
+                )
     except Exception as e:
         click.echo(f"获取在线插件列表失败: {e}", err=True)
 
@@ -164,7 +172,8 @@ def build_plug_list(plugins_dir: Path) -> list:
             )
             if (
                 VersionComparator.compare_version(
-                    local_plugin["version"], online_plugin["version"]
+                    local_plugin["version"],
+                    online_plugin["version"],
                 )
                 < 0
             ):
@@ -182,7 +191,10 @@ def build_plug_list(plugins_dir: Path) -> list:
 
 
 def manage_plugin(
-    plugin: dict, plugins_dir: Path, is_update: bool = False, proxy: str | None = None
+    plugin: dict,
+    plugins_dir: Path,
+    is_update: bool = False,
+    proxy: str | None = None,
 ) -> None:
     """安装或更新插件
 
@@ -191,6 +203,7 @@ def manage_plugin(
         plugins_dir (Path): 插件目录
         is_update (bool, optional): 是否为更新操作. 默认为 False
         proxy (str, optional): 代理服务器地址
+
     """
     plugin_name = plugin["name"]
     repo_url = plugin["repo"]
@@ -208,26 +221,26 @@ def manage_plugin(
         raise click.ClickException(f"插件 {plugin_name} 未安装，无法更新")
 
     # 备份现有插件
-    if is_update and backup_path.exists():
+    if is_update and backup_path is not None and backup_path.exists():
         shutil.rmtree(backup_path)
-    if is_update:
+    if is_update and backup_path is not None:
         shutil.copytree(target_path, backup_path)
 
     try:
         click.echo(
-            f"正在从 {repo_url} {'更新' if is_update else '下载'}插件 {plugin_name}..."
+            f"正在从 {repo_url} {'更新' if is_update else '下载'}插件 {plugin_name}...",
         )
         get_git_repo(repo_url, target_path, proxy)
 
         # 更新成功，删除备份
-        if is_update and backup_path.exists():
+        if is_update and backup_path is not None and backup_path.exists():
             shutil.rmtree(backup_path)
         click.echo(f"插件 {plugin_name} {'更新' if is_update else '安装'}成功")
     except Exception as e:
         if target_path.exists():
             shutil.rmtree(target_path, ignore_errors=True)
-        if is_update and backup_path.exists():
+        if is_update and backup_path is not None and backup_path.exists():
             shutil.move(backup_path, target_path)
         raise click.ClickException(
-            f"{'更新' if is_update else '安装'}插件 {plugin_name} 时出错: {e}"
+            f"{'更新' if is_update else '安装'}插件 {plugin_name} 时出错: {e}",
         )

astrbot/cli/utils/version_comparator.py

@@ -1,6 +1,4 @@
-"""
-拷贝自 astrbot.core.utils.version_comparator
-"""
+"""拷贝自 astrbot.core.utils.version_comparator"""
 
 import re
 
@@ -42,15 +40,15 @@ class VersionComparator:
         for i in range(length):
             if v1_parts[i] > v2_parts[i]:
                 return 1
-            elif v1_parts[i] < v2_parts[i]:
+            if v1_parts[i] < v2_parts[i]:
                 return -1
 
         # 比较预发布标签
         if v1_prerelease is None and v2_prerelease is not None:
             return 1  # 没有预发布标签的版本高于有预发布标签的版本
-        elif v1_prerelease is not None and v2_prerelease is None:
+        if v1_prerelease is not None and v2_prerelease is None:
             return -1  # 有预发布标签的版本低于没有预发布标签的版本
-        elif v1_prerelease is not None and v2_prerelease is not None:
+        if v1_prerelease is not None and v2_prerelease is not None:
             len_pre = max(len(v1_prerelease), len(v2_prerelease))
             for i in range(len_pre):
                 p1 = v1_prerelease[i] if i < len(v1_prerelease) else None
@@ -58,21 +56,21 @@ class VersionComparator:
 
                 if p1 is None and p2 is not None:
                     return -1
-                elif p1 is not None and p2 is None:
+                if p1 is not None and p2 is None:
                     return 1
-                elif isinstance(p1, int) and isinstance(p2, str):
+                if isinstance(p1, int) and isinstance(p2, str):
                     return -1
-                elif isinstance(p1, str) and isinstance(p2, int):
+                if isinstance(p1, str) and isinstance(p2, int):
                     return 1
-                elif isinstance(p1, int) and isinstance(p2, int):
+                if isinstance(p1, int) and isinstance(p2, int):
                     if p1 > p2:
                         return 1
-                    elif p1 < p2:
+                    if p1 < p2:
                         return -1
                 elif isinstance(p1, str) and isinstance(p2, str):
                     if p1 > p2:
                         return 1
-                    elif p1 < p2:
+                    if p1 < p2:
                         return -1
             return 0  # 预发布标签完全相同
 

astrbot/core/__init__.py

@@ -1,12 +1,14 @@
 import os
-from .log import LogManager, LogBroker  # noqa
-from astrbot.core.utils.t2i.renderer import HtmlRenderer
-from astrbot.core.utils.shared_preferences import SharedPreferences
-from astrbot.core.utils.pip_installer import PipInstaller
-from astrbot.core.db.sqlite import SQLiteDatabase
-from astrbot.core.config.default import DB_PATH
+
 from astrbot.core.config import AstrBotConfig
+from astrbot.core.config.default import DB_PATH
+from astrbot.core.db.sqlite import SQLiteDatabase
 from astrbot.core.file_token_service import FileTokenService
+from astrbot.core.utils.pip_installer import PipInstaller
+from astrbot.core.utils.shared_preferences import SharedPreferences
+from astrbot.core.utils.t2i.renderer import HtmlRenderer
+
+from .log import LogBroker, LogManager  # noqa
 from .utils.astrbot_path import get_astrbot_data_path
 
 # 初始化数据存储文件夹
@@ -18,6 +20,8 @@ astrbot_config = AstrBotConfig()
 t2i_base_url = astrbot_config.get("t2i_endpoint", "https://t2i.soulter.top/text2img")
 html_renderer = HtmlRenderer(t2i_base_url)
 logger = LogManager.GetLogger(log_name="astrbot")
+LogManager.configure_logger(logger, astrbot_config)
+LogManager.configure_trace_logger(astrbot_config)
 db_helper = SQLiteDatabase(DB_PATH)
 # 简单的偏好设置存储, 这里后续应该存储到数据库中, 一些部分可以存储到配置中
 sp = SharedPreferences(db_helper=db_helper)

astrbot/core/agent/agent.py

@@ -1,13 +1,15 @@
 from dataclasses import dataclass
-from .tool import FunctionTool
-from typing import Generic
-from .run_context import TContext
+from typing import Any, Generic
+
 from .hooks import BaseAgentRunHooks
+from .run_context import TContext
+from .tool import FunctionTool
 
 
 @dataclass
 class Agent(Generic[TContext]):
     name: str
     instructions: str | None = None
-    tools: list[str, FunctionTool] | None = None
+    tools: list[str | FunctionTool] | None = None
     run_hooks: BaseAgentRunHooks[TContext] | None = None
+    begin_dialogs: list[Any] | None = None

astrbot/core/agent/context/compressor.py

@@ -0,0 +1,243 @@
+from typing import TYPE_CHECKING, Protocol, runtime_checkable
+
+from ..message import Message
+
+if TYPE_CHECKING:
+    from astrbot import logger
+else:
+    try:
+        from astrbot import logger
+    except ImportError:
+        import logging
+
+        logger = logging.getLogger("astrbot")
+
+if TYPE_CHECKING:
+    from astrbot.core.provider.provider import Provider
+
+from ..context.truncator import ContextTruncator
+
+
+@runtime_checkable
+class ContextCompressor(Protocol):
+    """
+    Protocol for context compressors.
+    Provides an interface for compressing message lists.
+    """
+
+    def should_compress(
+        self, messages: list[Message], current_tokens: int, max_tokens: int
+    ) -> bool:
+        """Check if compression is needed.
+
+        Args:
+            messages: The message list to evaluate.
+            current_tokens: The current token count.
+            max_tokens: The maximum allowed tokens for the model.
+
+        Returns:
+            True if compression is needed, False otherwise.
+        """
+        ...
+
+    async def __call__(self, messages: list[Message]) -> list[Message]:
+        """Compress the message list.
+
+        Args:
+            messages: The original message list.
+
+        Returns:
+            The compressed message list.
+        """
+        ...
+
+
+class TruncateByTurnsCompressor:
+    """Truncate by turns compressor implementation.
+    Truncates the message list by removing older turns.
+    """
+
+    def __init__(self, truncate_turns: int = 1, compression_threshold: float = 0.82):
+        """Initialize the truncate by turns compressor.
+
+        Args:
+            truncate_turns: The number of turns to remove when truncating (default: 1).
+            compression_threshold: The compression trigger threshold (default: 0.82).
+        """
+        self.truncate_turns = truncate_turns
+        self.compression_threshold = compression_threshold
+
+    def should_compress(
+        self, messages: list[Message], current_tokens: int, max_tokens: int
+    ) -> bool:
+        """Check if compression is needed.
+
+        Args:
+            messages: The message list to evaluate.
+            current_tokens: The current token count.
+            max_tokens: The maximum allowed tokens.
+
+        Returns:
+            True if compression is needed, False otherwise.
+        """
+        if max_tokens <= 0 or current_tokens <= 0:
+            return False
+        usage_rate = current_tokens / max_tokens
+        return usage_rate > self.compression_threshold
+
+    async def __call__(self, messages: list[Message]) -> list[Message]:
+        truncator = ContextTruncator()
+        truncated_messages = truncator.truncate_by_dropping_oldest_turns(
+            messages,
+            drop_turns=self.truncate_turns,
+        )
+        return truncated_messages
+
+
+def split_history(
+    messages: list[Message], keep_recent: int
+) -> tuple[list[Message], list[Message], list[Message]]:
+    """Split the message list into system messages, messages to summarize, and recent messages.
+
+    Ensures that the split point is between complete user-assistant pairs to maintain conversation flow.
+
+    Args:
+        messages: The original message list.
+        keep_recent: The number of latest messages to keep.
+
+    Returns:
+        tuple: (system_messages, messages_to_summarize, recent_messages)
+    """
+    # keep the system messages
+    first_non_system = 0
+    for i, msg in enumerate(messages):
+        if msg.role != "system":
+            first_non_system = i
+            break
+
+    system_messages = messages[:first_non_system]
+    non_system_messages = messages[first_non_system:]
+
+    if len(non_system_messages) <= keep_recent:
+        return system_messages, [], non_system_messages
+
+    # Find the split point, ensuring recent_messages starts with a user message
+    # This maintains complete conversation turns
+    split_index = len(non_system_messages) - keep_recent
+
+    # Search backward from split_index to find the first user message
+    # This ensures recent_messages starts with a user message (complete turn)
+    while split_index > 0 and non_system_messages[split_index].role != "user":
+        # TODO: +=1 or -=1 ? calculate by tokens
+        split_index -= 1
+
+    # If we couldn't find a user message, keep all messages as recent
+    if split_index == 0:
+        return system_messages, [], non_system_messages
+
+    messages_to_summarize = non_system_messages[:split_index]
+    recent_messages = non_system_messages[split_index:]
+
+    return system_messages, messages_to_summarize, recent_messages
+
+
+class LLMSummaryCompressor:
+    """LLM-based summary compressor.
+    Uses LLM to summarize the old conversation history, keeping the latest messages.
+    """
+
+    def __init__(
+        self,
+        provider: "Provider",
+        keep_recent: int = 4,
+        instruction_text: str | None = None,
+        compression_threshold: float = 0.82,
+    ):
+        """Initialize the LLM summary compressor.
+
+        Args:
+            provider: The LLM provider instance.
+            keep_recent: The number of latest messages to keep (default: 4).
+            instruction_text: Custom instruction for summary generation.
+            compression_threshold: The compression trigger threshold (default: 0.82).
+        """
+        self.provider = provider
+        self.keep_recent = keep_recent
+        self.compression_threshold = compression_threshold
+
+        self.instruction_text = instruction_text or (
+            "Based on our full conversation history, produce a concise summary of key takeaways and/or project progress.\n"
+            "1. Systematically cover all core topics discussed and the final conclusion/outcome for each; clearly highlight the latest primary focus.\n"
+            "2. If any tools were used, summarize tool usage (total call count) and extract the most valuable insights from tool outputs.\n"
+            "3. If there was an initial user goal, state it first and describe the current progress/status.\n"
+            "4. Write the summary in the user's language.\n"
+        )
+
+    def should_compress(
+        self, messages: list[Message], current_tokens: int, max_tokens: int
+    ) -> bool:
+        """Check if compression is needed.
+
+        Args:
+            messages: The message list to evaluate.
+            current_tokens: The current token count.
+            max_tokens: The maximum allowed tokens.
+
+        Returns:
+            True if compression is needed, False otherwise.
+        """
+        if max_tokens <= 0 or current_tokens <= 0:
+            return False
+        usage_rate = current_tokens / max_tokens
+        return usage_rate > self.compression_threshold
+
+    async def __call__(self, messages: list[Message]) -> list[Message]:
+        """Use LLM to generate a summary of the conversation history.
+
+        Process:
+        1. Divide messages: keep the system message and the latest N messages.
+        2. Send the old messages + the instruction message to the LLM.
+        3. Reconstruct the message list: [system message, summary message, latest messages].
+        """
+        if len(messages) <= self.keep_recent + 1:
+            return messages
+
+        system_messages, messages_to_summarize, recent_messages = split_history(
+            messages, self.keep_recent
+        )
+
+        if not messages_to_summarize:
+            return messages
+
+        # build payload
+        instruction_message = Message(role="user", content=self.instruction_text)
+        llm_payload = messages_to_summarize + [instruction_message]
+
+        # generate summary
+        try:
+            response = await self.provider.text_chat(contexts=llm_payload)
+            summary_content = response.completion_text
+        except Exception as e:
+            logger.error(f"Failed to generate summary: {e}")
+            return messages
+
+        # build result
+        result = []
+        result.extend(system_messages)
+
+        result.append(
+            Message(
+                role="user",
+                content=f"Our previous history conversation summary: {summary_content}",
+            )
+        )
+        result.append(
+            Message(
+                role="assistant",
+                content="Acknowledged the summary of our previous conversation history.",
+            )
+        )
+
+        result.extend(recent_messages)
+
+        return result

astrbot/core/agent/context/config.py

@@ -0,0 +1,35 @@
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
+
+from .compressor import ContextCompressor
+from .token_counter import TokenCounter
+
+if TYPE_CHECKING:
+    from astrbot.core.provider.provider import Provider
+
+
+@dataclass
+class ContextConfig:
+    """Context configuration class."""
+
+    max_context_tokens: int = 0
+    """Maximum number of context tokens. <= 0 means no limit."""
+    enforce_max_turns: int = -1  # -1 means no limit
+    """Maximum number of conversation turns to keep. -1 means no limit. Executed before compression."""
+    truncate_turns: int = 1
+    """Number of conversation turns to discard at once when truncation is triggered.
+    Two processes will use this value:
+
+    1. Enforce max turns truncation.
+    2. Truncation by turns compression strategy.
+    """
+    llm_compress_instruction: str | None = None
+    """Instruction prompt for LLM-based compression."""
+    llm_compress_keep_recent: int = 0
+    """Number of recent messages to keep during LLM-based compression."""
+    llm_compress_provider: "Provider | None" = None
+    """LLM provider used for compression tasks. If None, truncation strategy is used."""
+    custom_token_counter: TokenCounter | None = None
+    """Custom token counting method. If None, the default method is used."""
+    custom_compressor: ContextCompressor | None = None
+    """Custom context compression method. If None, the default method is used."""

astrbot/core/agent/context/manager.py

@@ -0,0 +1,120 @@
+from astrbot import logger
+
+from ..message import Message
+from .compressor import LLMSummaryCompressor, TruncateByTurnsCompressor
+from .config import ContextConfig
+from .token_counter import EstimateTokenCounter
+from .truncator import ContextTruncator
+
+
+class ContextManager:
+    """Context compression manager."""
+
+    def __init__(
+        self,
+        config: ContextConfig,
+    ):
+        """Initialize the context manager.
+
+        There are two strategies to handle context limit reached:
+        1. Truncate by turns: remove older messages by turns.
+        2. LLM-based compression: use LLM to summarize old messages.
+
+        Args:
+            config: The context configuration.
+        """
+        self.config = config
+
+        self.token_counter = config.custom_token_counter or EstimateTokenCounter()
+        self.truncator = ContextTruncator()
+
+        if config.custom_compressor:
+            self.compressor = config.custom_compressor
+        elif config.llm_compress_provider:
+            self.compressor = LLMSummaryCompressor(
+                provider=config.llm_compress_provider,
+                keep_recent=config.llm_compress_keep_recent,
+                instruction_text=config.llm_compress_instruction,
+            )
+        else:
+            self.compressor = TruncateByTurnsCompressor(
+                truncate_turns=config.truncate_turns
+            )
+
+    async def process(
+        self, messages: list[Message], trusted_token_usage: int = 0
+    ) -> list[Message]:
+        """Process the messages.
+
+        Args:
+            messages: The original message list.
+
+        Returns:
+            The processed message list.
+        """
+        try:
+            result = messages
+
+            # 1. 基于轮次的截断 (Enforce max turns)
+            if self.config.enforce_max_turns != -1:
+                result = self.truncator.truncate_by_turns(
+                    result,
+                    keep_most_recent_turns=self.config.enforce_max_turns,
+                    drop_turns=self.config.truncate_turns,
+                )
+
+            # 2. 基于 token 的压缩
+            if self.config.max_context_tokens > 0:
+                total_tokens = self.token_counter.count_tokens(
+                    result, trusted_token_usage
+                )
+
+                if self.compressor.should_compress(
+                    result, total_tokens, self.config.max_context_tokens
+                ):
+                    result = await self._run_compression(result, total_tokens)
+
+            return result
+        except Exception as e:
+            logger.error(f"Error during context processing: {e}", exc_info=True)
+            return messages
+
+    async def _run_compression(
+        self, messages: list[Message], prev_tokens: int
+    ) -> list[Message]:
+        """
+        Compress/truncate the messages.
+
+        Args:
+            messages: The original message list.
+            prev_tokens: The token count before compression.
+
+        Returns:
+            The compressed/truncated message list.
+        """
+        logger.debug("Compress triggered, starting compression...")
+
+        messages = await self.compressor(messages)
+
+        # double check
+        tokens_after_summary = self.token_counter.count_tokens(messages)
+
+        # calculate compress rate
+        compress_rate = (tokens_after_summary / self.config.max_context_tokens) * 100
+        logger.info(
+            f"Compress completed."
+            f" {prev_tokens} -> {tokens_after_summary} tokens,"
+            f" compression rate: {compress_rate:.2f}%.",
+        )
+
+        # last check
+        if self.compressor.should_compress(
+            messages, tokens_after_summary, self.config.max_context_tokens
+        ):
+            logger.info(
+                "Context still exceeds max tokens after compression, applying halving truncation..."
+            )
+            # still need compress, truncate by half
+            messages = self.truncator.truncate_by_halving(messages)
+
+        return messages

astrbot/core/agent/context/token_counter.py

@@ -0,0 +1,64 @@
+import json
+from typing import Protocol, runtime_checkable
+
+from ..message import Message, TextPart
+
+
+@runtime_checkable
+class TokenCounter(Protocol):
+    """
+    Protocol for token counters.
+    Provides an interface for counting tokens in message lists.
+    """
+
+    def count_tokens(
+        self, messages: list[Message], trusted_token_usage: int = 0
+    ) -> int:
+        """Count the total tokens in the message list.
+
+        Args:
+            messages: The message list.
+            trusted_token_usage: The total token usage that LLM API returned.
+                For some cases, this value is more accurate.
+                But some API does not return it, so the value defaults to 0.
+
+        Returns:
+            The total token count.
+        """
+        ...
+
+
+class EstimateTokenCounter:
+    """Estimate token counter implementation.
+    Provides a simple estimation of token count based on character types.
+    """
+
+    def count_tokens(
+        self, messages: list[Message], trusted_token_usage: int = 0
+    ) -> int:
+        if trusted_token_usage > 0:
+            return trusted_token_usage
+
+        total = 0
+        for msg in messages:
+            content = msg.content
+            if isinstance(content, str):
+                total += self._estimate_tokens(content)
+            elif isinstance(content, list):
+                # 处理多模态内容
+                for part in content:
+                    if isinstance(part, TextPart):
+                        total += self._estimate_tokens(part.text)
+
+            # 处理 Tool Calls
+            if msg.tool_calls:
+                for tc in msg.tool_calls:
+                    tc_str = json.dumps(tc if isinstance(tc, dict) else tc.model_dump())
+                    total += self._estimate_tokens(tc_str)
+
+        return total
+
+    def _estimate_tokens(self, text: str) -> int:
+        chinese_count = len([c for c in text if "\u4e00" <= c <= "\u9fff"])
+        other_count = len(text) - chinese_count
+        return int(chinese_count * 0.6 + other_count * 0.3)

astrbot/core/agent/context/truncator.py

@@ -0,0 +1,141 @@
+from ..message import Message
+
+
+class ContextTruncator:
+    """Context truncator."""
+
+    def fix_messages(self, messages: list[Message]) -> list[Message]:
+        fixed_messages = []
+        for message in messages:
+            if message.role == "tool":
+                # tool block 前面必须要有 user 和 assistant block
+                if len(fixed_messages) < 2:
+                    # 这种情况可能是上下文被截断导致的
+                    # 我们直接将之前的上下文都清空
+                    fixed_messages = []
+                else:
+                    fixed_messages.append(message)
+            else:
+                fixed_messages.append(message)
+        return fixed_messages
+
+    def truncate_by_turns(
+        self,
+        messages: list[Message],
+        keep_most_recent_turns: int,
+        drop_turns: int = 1,
+    ) -> list[Message]:
+        """截断上下文列表，确保不超过最大长度。
+        一个 turn 包含一个 user 消息和一个 assistant 消息。
+        这个方法会保证截断后的上下文列表符合 OpenAI 的上下文格式。
+
+        Args:
+            messages: 上下文列表
+            keep_most_recent_turns: 保留最近的对话轮数
+            drop_turns: 一次性丢弃的对话轮数
+
+        Returns:
+            截断后的上下文列表
+        """
+        if keep_most_recent_turns == -1:
+            return messages
+
+        first_non_system = 0
+        for i, msg in enumerate(messages):
+            if msg.role != "system":
+                first_non_system = i
+                break
+
+        system_messages = messages[:first_non_system]
+        non_system_messages = messages[first_non_system:]
+
+        if len(non_system_messages) // 2 <= keep_most_recent_turns:
+            return messages
+
+        num_to_keep = keep_most_recent_turns - drop_turns + 1
+        if num_to_keep <= 0:
+            truncated_contexts = []
+        else:
+            truncated_contexts = non_system_messages[-num_to_keep * 2 :]
+
+        # 找到第一个 role 为 user 的索引，确保上下文格式正确
+        index = next(
+            (i for i, item in enumerate(truncated_contexts) if item.role == "user"),
+            None,
+        )
+        if index is not None and index > 0:
+            truncated_contexts = truncated_contexts[index:]
+
+        result = system_messages + truncated_contexts
+
+        return self.fix_messages(result)
+
+    def truncate_by_dropping_oldest_turns(
+        self,
+        messages: list[Message],
+        drop_turns: int = 1,
+    ) -> list[Message]:
+        """丢弃最旧的 N 个对话轮次。"""
+        if drop_turns <= 0:
+            return messages
+
+        first_non_system = 0
+        for i, msg in enumerate(messages):
+            if msg.role != "system":
+                first_non_system = i
+                break
+
+        system_messages = messages[:first_non_system]
+        non_system_messages = messages[first_non_system:]
+
+        if len(non_system_messages) // 2 <= drop_turns:
+            truncated_non_system = []
+        else:
+            truncated_non_system = non_system_messages[drop_turns * 2 :]
+
+        index = next(
+            (i for i, item in enumerate(truncated_non_system) if item.role == "user"),
+            None,
+        )
+        if index is not None:
+            truncated_non_system = truncated_non_system[index:]
+        elif truncated_non_system:
+            truncated_non_system = []
+
+        result = system_messages + truncated_non_system
+
+        return self.fix_messages(result)
+
+    def truncate_by_halving(
+        self,
+        messages: list[Message],
+    ) -> list[Message]:
+        """对半砍策略，删除 50% 的消息"""
+        if len(messages) <= 2:
+            return messages
+
+        first_non_system = 0
+        for i, msg in enumerate(messages):
+            if msg.role != "system":
+                first_non_system = i
+                break
+
+        system_messages = messages[:first_non_system]
+        non_system_messages = messages[first_non_system:]
+
+        messages_to_delete = len(non_system_messages) // 2
+        if messages_to_delete == 0:
+            return messages
+
+        truncated_non_system = non_system_messages[messages_to_delete:]
+
+        index = next(
+            (i for i, item in enumerate(truncated_non_system) if item.role == "user"),
+            None,
+        )
+        if index is not None:
+            truncated_non_system = truncated_non_system[index:]
+
+        result = system_messages + truncated_non_system
+
+        return self.fix_messages(result)

astrbot/core/agent/handoff.py

@@ -1,23 +1,40 @@
 from typing import Generic
-from .tool import FunctionTool
+
 from .agent import Agent
 from .run_context import TContext
+from .tool import FunctionTool
 
 
 class HandoffTool(FunctionTool, Generic[TContext]):
     """Handoff tool for delegating tasks to another agent."""
 
     def __init__(
-        self, agent: Agent[TContext], parameters: dict | None = None, **kwargs
+        self,
+        agent: Agent[TContext],
+        parameters: dict | None = None,
+        tool_description: str | None = None,
+        **kwargs,
     ):
         self.agent = agent
+
+        # Avoid passing duplicate `description` to the FunctionTool dataclass.
+        # Some call sites (e.g. SubAgentOrchestrator) pass `description` via kwargs
+        # to override what the main agent sees, while we also compute a default
+        # description here.
+        # `tool_description` is the public description shown to the main LLM.
+        # Keep a separate kwarg to avoid conflicting with FunctionTool's `description`.
+        description = tool_description or self.default_description(agent.name)
         super().__init__(
             name=f"transfer_to_{agent.name}",
             parameters=parameters or self.default_parameters(),
-            description=agent.instructions or self.default_description(agent.name),
+            description=description,
             **kwargs,
         )
 
+        # Optional provider override for this subagent. When set, the handoff
+        # execution will use this chat provider id instead of the global/default.
+        self.provider_id: str | None = None
+
     def default_parameters(self) -> dict:
         return {
             "type": "object",

astrbot/core/agent/hooks.py

@@ -1,12 +1,13 @@
-import mcp
-from dataclasses import dataclass
-from .run_context import ContextWrapper, TContext
 from typing import Generic
-from astrbot.core.provider.entities import LLMResponse
+
+import mcp
+
 from astrbot.core.agent.tool import FunctionTool
+from astrbot.core.provider.entities import LLMResponse
+
+from .run_context import ContextWrapper, TContext
 
 
-@dataclass
 class BaseAgentRunHooks(Generic[TContext]):
     async def on_agent_begin(self, run_context: ContextWrapper[TContext]): ...
     async def on_tool_start(
@@ -23,5 +24,7 @@ class BaseAgentRunHooks(Generic[TContext]):
         tool_result: mcp.types.CallToolResult | None,
     ): ...
     async def on_agent_done(
-        self, run_context: ContextWrapper[TContext], llm_response: LLMResponse
+        self,
+        run_context: ContextWrapper[TContext],
+        llm_response: LLMResponse,
     ): ...

astrbot/core/agent/mcp_client.py

@@ -1,28 +1,44 @@
 import asyncio
 import logging
-from datetime import timedelta
-from typing import Optional
 from contextlib import AsyncExitStack
+from datetime import timedelta
+from typing import Generic
+
+from tenacity import (
+    before_sleep_log,
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
+
 from astrbot import logger
+from astrbot.core.agent.run_context import ContextWrapper
 from astrbot.core.utils.log_pipe import LogPipe
 
+from .run_context import TContext
+from .tool import FunctionTool
+
 try:
+    import anyio
     import mcp
     from mcp.client.sse import sse_client
 except (ModuleNotFoundError, ImportError):
-    logger.warning("警告: 缺少依赖库 'mcp'，将无法使用 MCP 服务。")
+    logger.warning(
+        "Warning: Missing 'mcp' dependency, MCP services will be unavailable."
+    )
 
 try:
     from mcp.client.streamable_http import streamablehttp_client
 except (ModuleNotFoundError, ImportError):
     logger.warning(
-        "警告: 缺少依赖库 'mcp' 或者 mcp 库版本过低，无法使用 Streamable HTTP 连接方式。"
+        "Warning: Missing 'mcp' dependency or MCP library version too old, Streamable HTTP connection unavailable.",
     )
 
 
 def _prepare_config(config: dict) -> dict:
-    """准备配置，处理嵌套格式"""
-    if "mcpServers" in config and config["mcpServers"]:
+    """Prepare configuration, handle nested format"""
+    if config.get("mcpServers"):
         first_key = next(iter(config["mcpServers"]))
         config = config["mcpServers"][first_key]
     config.pop("active", None)
@@ -30,7 +46,7 @@ def _prepare_config(config: dict) -> dict:
 
 
 async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
-    """快速测试 MCP 服务器可达性"""
+    """Quick test MCP server connectivity"""
     import aiohttp
 
     cfg = _prepare_config(config.copy())
@@ -40,8 +56,15 @@ async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
     timeout = cfg.get("timeout", 10)
 
     try:
+        if "transport" in cfg:
+            transport_type = cfg["transport"]
+        elif "type" in cfg:
+            transport_type = cfg["type"]
+        else:
+            raise Exception("MCP connection config missing transport or type field")
+
         async with aiohttp.ClientSession() as session:
-            if cfg.get("transport") == "streamable_http":
+            if transport_type == "streamable_http":
                 test_payload = {
                     "jsonrpc": "2.0",
                     "method": "initialize",
@@ -64,8 +87,7 @@ async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
                 ) as response:
                     if response.status == 200:
                         return True, ""
-                    else:
-                        return False, f"HTTP {response.status}: {response.reason}"
+                    return False, f"HTTP {response.status}: {response.reason}"
             else:
                 async with session.get(
                     url,
@@ -77,11 +99,10 @@ async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
                 ) as response:
                     if response.status == 200:
                         return True, ""
-                    else:
-                        return False, f"HTTP {response.status}: {response.reason}"
+                    return False, f"HTTP {response.status}: {response.reason}"
 
     except asyncio.TimeoutError:
-        return False, f"连接超时: {timeout}秒"
+        return False, f"Connection timeout: {timeout} seconds"
     except Exception as e:
         return False, f"{e!s}"
 
@@ -89,30 +110,42 @@ async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
 class MCPClient:
     def __init__(self):
         # Initialize session and client objects
-        self.session: Optional[mcp.ClientSession] = None
+        self.session: mcp.ClientSession | None = None
         self.exit_stack = AsyncExitStack()
+        self._old_exit_stacks: list[AsyncExitStack] = []  # Track old stacks for cleanup
 
-        self.name = None
+        self.name: str | None = None
         self.active: bool = True
         self.tools: list[mcp.Tool] = []
         self.server_errlogs: list[str] = []
         self.running_event = asyncio.Event()
 
-    async def connect_to_server(self, mcp_server_config: dict, name: str):
-        """连接到 MCP 服务器
+        # Store connection config for reconnection
+        self._mcp_server_config: dict | None = None
+        self._server_name: str | None = None
+        self._reconnect_lock = asyncio.Lock()  # Lock for thread-safe reconnection
+        self._reconnecting: bool = False  # For logging and debugging
 
-        如果 `url` 参数存在：
-            1. 当 transport 指定为 `streamable_http` 时，使用 Streamable HTTP 连接方式。
-            1. 当 transport 指定为 `sse` 时，使用 SSE 连接方式。
-            2. 如果没有指定，默认使用 SSE 的方式连接到 MCP 服务。
+    async def connect_to_server(self, mcp_server_config: dict, name: str):
+        """Connect to MCP server
+
+        If `url` parameter exists:
+            1. When transport is specified as `streamable_http`, use Streamable HTTP connection.
+            2. When transport is specified as `sse`, use SSE connection.
+            3. If not specified, default to SSE connection to MCP service.
 
         Args:
             mcp_server_config (dict): Configuration for the MCP server. See https://modelcontextprotocol.io/quickstart/server
+
         """
+        # Store config for reconnection
+        self._mcp_server_config = mcp_server_config
+        self._server_name = name
+
         cfg = _prepare_config(mcp_server_config.copy())
 
         def logging_callback(msg: str):
-            # 处理 MCP 服务的错误日志
+            # Handle MCP service error logs
             print(f"MCP Server {name} Error: {msg}")
             self.server_errlogs.append(msg)
 
@@ -121,7 +154,14 @@ class MCPClient:
             if not success:
                 raise Exception(error_msg)
 
-            if cfg.get("transport") != "streamable_http":
+            if "transport" in cfg:
+                transport_type = cfg["transport"]
+            elif "type" in cfg:
+                transport_type = cfg["type"]
+            else:
+                raise Exception("MCP connection config missing transport or type field")
+
+            if transport_type != "streamable_http":
                 # SSE transport method
                 self._streams_context = sse_client(
                     url=cfg["url"],
@@ -130,22 +170,22 @@ class MCPClient:
                     sse_read_timeout=cfg.get("sse_read_timeout", 60 * 5),
                 )
                 streams = await self.exit_stack.enter_async_context(
-                    self._streams_context
+                    self._streams_context,
                 )
 
                 # Create a new client session
-                read_timeout = timedelta(seconds=cfg.get("session_read_timeout", 20))
+                read_timeout = timedelta(seconds=cfg.get("session_read_timeout", 60))
                 self.session = await self.exit_stack.enter_async_context(
                     mcp.ClientSession(
                         *streams,
                         read_timeout_seconds=read_timeout,
                         logging_callback=logging_callback,  # type: ignore
-                    )
+                    ),
                 )
             else:
                 timeout = timedelta(seconds=cfg.get("timeout", 30))
                 sse_read_timeout = timedelta(
-                    seconds=cfg.get("sse_read_timeout", 60 * 5)
+                    seconds=cfg.get("sse_read_timeout", 60 * 5),
                 )
                 self._streams_context = streamablehttp_client(
                     url=cfg["url"],
@@ -155,18 +195,18 @@ class MCPClient:
                     terminate_on_close=cfg.get("terminate_on_close", True),
                 )
                 read_s, write_s, _ = await self.exit_stack.enter_async_context(
-                    self._streams_context
+                    self._streams_context,
                 )
 
                 # Create a new client session
-                read_timeout = timedelta(seconds=cfg.get("session_read_timeout", 20))
+                read_timeout = timedelta(seconds=cfg.get("session_read_timeout", 60))
                 self.session = await self.exit_stack.enter_async_context(
                     mcp.ClientSession(
                         read_stream=read_s,
                         write_stream=write_s,
                         read_timeout_seconds=read_timeout,
                         logging_callback=logging_callback,  # type: ignore
-                    )
+                    ),
                 )
 
         else:
@@ -175,7 +215,7 @@ class MCPClient:
             )
 
             def callback(msg: str):
-                # 处理 MCP 服务的错误日志
+                # Handle MCP service error logs
                 self.server_errlogs.append(msg)
 
             stdio_transport = await self.exit_stack.enter_async_context(
@@ -192,17 +232,154 @@ class MCPClient:
 
             # Create a new client session
             self.session = await self.exit_stack.enter_async_context(
-                mcp.ClientSession(*stdio_transport)
+                mcp.ClientSession(*stdio_transport),
             )
         await self.session.initialize()
 
     async def list_tools_and_save(self) -> mcp.ListToolsResult:
         """List all tools from the server and save them to self.tools"""
+        if not self.session:
+            raise Exception("MCP Client is not initialized")
         response = await self.session.list_tools()
         self.tools = response.tools
         return response
 
+    async def _reconnect(self) -> None:
+        """Reconnect to the MCP server using the stored configuration.
+
+        Uses asyncio.Lock to ensure thread-safe reconnection in concurrent environments.
+
+        Raises:
+            Exception: raised when reconnection fails
+        """
+        async with self._reconnect_lock:
+            # Check if already reconnecting (useful for logging)
+            if self._reconnecting:
+                logger.debug(
+                    f"MCP Client {self._server_name} is already reconnecting, skipping"
+                )
+                return
+
+            if not self._mcp_server_config or not self._server_name:
+                raise Exception("Cannot reconnect: missing connection configuration")
+
+            self._reconnecting = True
+            try:
+                logger.info(
+                    f"Attempting to reconnect to MCP server {self._server_name}..."
+                )
+
+                # Save old exit_stack for later cleanup (don't close it now to avoid cancel scope issues)
+                if self.exit_stack:
+                    self._old_exit_stacks.append(self.exit_stack)
+
+                # Mark old session as invalid
+                self.session = None
+
+                # Create new exit stack for new connection
+                self.exit_stack = AsyncExitStack()
+
+                # Reconnect using stored config
+                await self.connect_to_server(self._mcp_server_config, self._server_name)
+                await self.list_tools_and_save()
+
+                logger.info(
+                    f"Successfully reconnected to MCP server {self._server_name}"
+                )
+            except Exception as e:
+                logger.error(
+                    f"Failed to reconnect to MCP server {self._server_name}: {e}"
+                )
+                raise
+            finally:
+                self._reconnecting = False
+
+    async def call_tool_with_reconnect(
+        self,
+        tool_name: str,
+        arguments: dict,
+        read_timeout_seconds: timedelta,
+    ) -> mcp.types.CallToolResult:
+        """Call MCP tool with automatic reconnection on failure, max 2 retries.
+
+        Args:
+            tool_name: tool name
+            arguments: tool arguments
+            read_timeout_seconds: read timeout
+
+        Returns:
+            MCP tool call result
+
+        Raises:
+            ValueError: MCP session is not available
+            anyio.ClosedResourceError: raised after reconnection failure
+        """
+
+        @retry(
+            retry=retry_if_exception_type(anyio.ClosedResourceError),
+            stop=stop_after_attempt(2),
+            wait=wait_exponential(multiplier=1, min=1, max=3),
+            before_sleep=before_sleep_log(logger, logging.WARNING),
+            reraise=True,
+        )
+        async def _call_with_retry():
+            if not self.session:
+                raise ValueError("MCP session is not available for MCP function tools.")
+
+            try:
+                return await self.session.call_tool(
+                    name=tool_name,
+                    arguments=arguments,
+                    read_timeout_seconds=read_timeout_seconds,
+                )
+            except anyio.ClosedResourceError:
+                logger.warning(
+                    f"MCP tool {tool_name} call failed (ClosedResourceError), attempting to reconnect..."
+                )
+                # Attempt to reconnect
+                await self._reconnect()
+                # Reraise the exception to trigger tenacity retry
+                raise
+
+        return await _call_with_retry()
+
     async def cleanup(self):
-        """Clean up resources"""
-        await self.exit_stack.aclose()
-        self.running_event.set()  # Set the running event to indicate cleanup is done
+        """Clean up resources including old exit stacks from reconnections"""
+        # Close current exit stack
+        try:
+            await self.exit_stack.aclose()
+        except Exception as e:
+            logger.debug(f"Error closing current exit stack: {e}")
+
+        # Don't close old exit stacks as they may be in different task contexts
+        # They will be garbage collected naturally
+        # Just clear the list to release references
+        self._old_exit_stacks.clear()
+
+        # Set running_event first to unblock any waiting tasks
+        self.running_event.set()
+
+
+class MCPTool(FunctionTool, Generic[TContext]):
+    """A function tool that calls an MCP service."""
+
+    def __init__(
+        self, mcp_tool: mcp.Tool, mcp_client: MCPClient, mcp_server_name: str, **kwargs
+    ):
+        super().__init__(
+            name=mcp_tool.name,
+            description=mcp_tool.description or "",
+            parameters=mcp_tool.inputSchema,
+        )
+        self.mcp_tool = mcp_tool
+        self.mcp_client = mcp_client
+        self.mcp_server_name = mcp_server_name
+
+    async def call(
+        self, context: ContextWrapper[TContext], **kwargs
+    ) -> mcp.types.CallToolResult:
+        return await self.mcp_client.call_tool_with_reconnect(
+            tool_name=self.mcp_tool.name,
+            arguments=kwargs,
+            read_timeout_seconds=timedelta(seconds=context.tool_call_timeout),
+        )

astrbot/core/agent/message.py

@@ -0,0 +1,225 @@
+# Inspired by MoonshotAI/kosong, credits to MoonshotAI/kosong authors for the original implementation.
+# License: Apache License 2.0
+
+from typing import Any, ClassVar, Literal, cast
+
+from pydantic import BaseModel, GetCoreSchemaHandler, model_serializer, model_validator
+from pydantic_core import core_schema
+
+
+class ContentPart(BaseModel):
+    """A part of the content in a message."""
+
+    __content_part_registry: ClassVar[dict[str, type["ContentPart"]]] = {}
+
+    type: Literal["text", "think", "image_url", "audio_url"]
+
+    def __init_subclass__(cls, **kwargs: Any) -> None:
+        super().__init_subclass__(**kwargs)
+
+        invalid_subclass_error_msg = f"ContentPart subclass {cls.__name__} must have a `type` field of type `str`"
+
+        type_value = getattr(cls, "type", None)
+        if type_value is None or not isinstance(type_value, str):
+            raise ValueError(invalid_subclass_error_msg)
+
+        cls.__content_part_registry[type_value] = cls
+
+    @classmethod
+    def __get_pydantic_core_schema__(
+        cls, source_type: Any, handler: GetCoreSchemaHandler
+    ) -> core_schema.CoreSchema:
+        # If we're dealing with the base ContentPart class, use custom validation
+        if cls.__name__ == "ContentPart":
+
+            def validate_content_part(value: Any) -> Any:
+                # if it's already an instance of a ContentPart subclass, return it
+                if hasattr(value, "__class__") and issubclass(value.__class__, cls):
+                    return value
+
+                # if it's a dict with a type field, dispatch to the appropriate subclass
+                if isinstance(value, dict) and "type" in value:
+                    type_value: Any | None = cast(dict[str, Any], value).get("type")
+                    if not isinstance(type_value, str):
+                        raise ValueError(f"Cannot validate {value} as ContentPart")
+                    target_class = cls.__content_part_registry[type_value]
+                    return target_class.model_validate(value)
+
+                raise ValueError(f"Cannot validate {value} as ContentPart")
+
+            return core_schema.no_info_plain_validator_function(validate_content_part)
+
+        # for subclasses, use the default schema
+        return handler(source_type)
+
+
+class TextPart(ContentPart):
+    """
+    >>> TextPart(text="Hello, world!").model_dump()
+    {'type': 'text', 'text': 'Hello, world!'}
+    """
+
+    type: str = "text"
+    text: str
+
+
+class ThinkPart(ContentPart):
+    """
+    >>> ThinkPart(think="I think I need to think about this.").model_dump()
+    {'type': 'think', 'think': 'I think I need to think about this.', 'encrypted': None}
+    """
+
+    type: str = "think"
+    think: str
+    encrypted: str | None = None
+    """Encrypted thinking content, or signature."""
+
+    def merge_in_place(self, other: Any) -> bool:
+        if not isinstance(other, ThinkPart):
+            return False
+        if self.encrypted:
+            return False
+        self.think += other.think
+        if other.encrypted:
+            self.encrypted = other.encrypted
+        return True
+
+
+class ImageURLPart(ContentPart):
+    """
+    >>> ImageURLPart(image_url="http://example.com/image.jpg").model_dump()
+    {'type': 'image_url', 'image_url': 'http://example.com/image.jpg'}
+    """
+
+    class ImageURL(BaseModel):
+        url: str
+        """The URL of the image, can be data URI scheme like `data:image/png;base64,...`."""
+        id: str | None = None
+        """The ID of the image, to allow LLMs to distinguish different images."""
+
+    type: str = "image_url"
+    image_url: ImageURL
+
+
+class AudioURLPart(ContentPart):
+    """
+    >>> AudioURLPart(audio_url=AudioURLPart.AudioURL(url="https://example.com/audio.mp3")).model_dump()
+    {'type': 'audio_url', 'audio_url': {'url': 'https://example.com/audio.mp3', 'id': None}}
+    """
+
+    class AudioURL(BaseModel):
+        url: str
+        """The URL of the audio, can be data URI scheme like `data:audio/aac;base64,...`."""
+        id: str | None = None
+        """The ID of the audio, to allow LLMs to distinguish different audios."""
+
+    type: str = "audio_url"
+    audio_url: AudioURL
+
+
+class ToolCall(BaseModel):
+    """
+    A tool call requested by the assistant.
+
+    >>> ToolCall(
+    ...     id="123",
+    ...     function=ToolCall.FunctionBody(
+    ...         name="function",
+    ...         arguments="{}"
+    ...     ),
+    ... ).model_dump()
+    {'type': 'function', 'id': '123', 'function': {'name': 'function', 'arguments': '{}'}}
+    """
+
+    class FunctionBody(BaseModel):
+        name: str
+        arguments: str | None
+
+    type: Literal["function"] = "function"
+
+    id: str
+    """The ID of the tool call."""
+    function: FunctionBody
+    """The function body of the tool call."""
+    extra_content: dict[str, Any] | None = None
+    """Extra metadata for the tool call."""
+
+    @model_serializer(mode="wrap")
+    def serialize(self, handler):
+        data = handler(self)
+        if self.extra_content is None:
+            data.pop("extra_content", None)
+        return data
+
+
+class ToolCallPart(BaseModel):
+    """A part of the tool call."""
+
+    arguments_part: str | None = None
+    """A part of the arguments of the tool call."""
+
+
+class Message(BaseModel):
+    """A message in a conversation."""
+
+    role: Literal[
+        "system",
+        "user",
+        "assistant",
+        "tool",
+    ]
+
+    content: str | list[ContentPart] | None = None
+    """The content of the message."""
+
+    tool_calls: list[ToolCall] | list[dict] | None = None
+    """The tool calls of the message."""
+
+    tool_call_id: str | None = None
+    """The ID of the tool call."""
+
+    @model_validator(mode="after")
+    def check_content_required(self):
+        # assistant + tool_calls is not None: allow content to be None
+        if self.role == "assistant" and self.tool_calls is not None:
+            return self
+
+        # other all cases: content is required
+        if self.content is None:
+            raise ValueError(
+                "content is required unless role='assistant' and tool_calls is not None"
+            )
+        return self
+
+    @model_serializer(mode="wrap")
+    def serialize(self, handler):
+        data = handler(self)
+        if self.tool_calls is None:
+            data.pop("tool_calls", None)
+        if self.tool_call_id is None:
+            data.pop("tool_call_id", None)
+        return data
+
+
+class AssistantMessageSegment(Message):
+    """A message segment from the assistant."""
+
+    role: Literal["assistant"] = "assistant"
+
+
+class ToolCallMessageSegment(Message):
+    """A message segment representing a tool call."""
+
+    role: Literal["tool"] = "tool"
+
+
+class UserMessageSegment(Message):
+    """A message segment from the user."""
+
+    role: Literal["user"] = "user"
+
+
+class SystemMessageSegment(Message):
+    """A message segment from the system."""
+
+    role: Literal["system"] = "system"

astrbot/core/agent/response.py

@@ -1,6 +1,9 @@
-from dataclasses import dataclass
 import typing as T
+from dataclasses import dataclass, field
+
 from astrbot.core.message.message_event_result import MessageChain
+from astrbot.core.provider.entities import TokenUsage
+
 
 class AgentResponseData(T.TypedDict):
     chain: MessageChain
@@ -10,3 +13,23 @@ class AgentResponseData(T.TypedDict):
 class AgentResponse:
     type: str
     data: AgentResponseData
+
+
+@dataclass
+class AgentStats:
+    token_usage: TokenUsage = field(default_factory=TokenUsage)
+    start_time: float = 0.0
+    end_time: float = 0.0
+    time_to_first_token: float = 0.0
+
+    @property
+    def duration(self) -> float:
+        return self.end_time - self.start_time
+
+    def to_dict(self) -> dict:
+        return {
+            "token_usage": self.token_usage.__dict__,
+            "start_time": self.start_time,
+            "end_time": self.end_time,
+            "time_to_first_token": self.time_to_first_token,
+        }

astrbot/core/agent/run_context.py

@@ -1,8 +1,10 @@
-from dataclasses import dataclass
 from typing import Any, Generic
+
+from pydantic import Field
+from pydantic.dataclasses import dataclass
 from typing_extensions import TypeVar
 
-from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from .message import Message
 
 TContext = TypeVar("TContext", default=Any)
 
@@ -12,6 +14,9 @@ class ContextWrapper(Generic[TContext]):
     """A context for running an agent, which can be used to pass additional data or state."""
 
     context: TContext
-    event: AstrMessageEvent
+    messages: list[Message] = Field(default_factory=list)
+    """This field stores the llm message context for the agent run, agent runners will maintain this field automatically."""
+    tool_call_timeout: int = 60  # Default tool call timeout in seconds
+
 
 NoContext = ContextWrapper[None]

astrbot/core/agent/runners/base.py

@@ -1,13 +1,14 @@
 import abc
 import typing as T
 from enum import Enum, auto
-from ..run_context import ContextWrapper, TContext
-from ..response import AgentResponse
-from ..hooks import BaseAgentRunHooks
-from ..tool_executor import BaseFunctionToolExecutor
-from astrbot.core.provider import Provider
+
+from astrbot import logger
 from astrbot.core.provider.entities import LLMResponse
 
+from ..hooks import BaseAgentRunHooks
+from ..response import AgentResponse
+from ..run_context import ContextWrapper, TContext
+
 
 class AgentState(Enum):
     """Defines the state of the agent."""
@@ -22,37 +23,43 @@ class BaseAgentRunner(T.Generic[TContext]):
     @abc.abstractmethod
     async def reset(
         self,
-        provider: Provider,
         run_context: ContextWrapper[TContext],
-        tool_executor: BaseFunctionToolExecutor[TContext],
         agent_hooks: BaseAgentRunHooks[TContext],
         **kwargs: T.Any,
     ) -> None:
-        """
-        Reset the agent to its initial state.
+        """Reset the agent to its initial state.
         This method should be called before starting a new run.
         """
         ...
 
     @abc.abstractmethod
     async def step(self) -> T.AsyncGenerator[AgentResponse, None]:
-        """
-        Process a single step of the agent.
-        """
+        """Process a single step of the agent."""
+        ...
+
+    @abc.abstractmethod
+    async def step_until_done(
+        self, max_step: int
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        """Process steps until the agent is done."""
         ...
 
     @abc.abstractmethod
     def done(self) -> bool:
-        """
-        Check if the agent has completed its task.
+        """Check if the agent has completed its task.
         Returns True if the agent is done, False otherwise.
         """
         ...
 
     @abc.abstractmethod
     def get_final_llm_resp(self) -> LLMResponse | None:
-        """
-        Get the final observation from the agent.
+        """Get the final observation from the agent.
         This method should be called after the agent is done.
         """
         ...
+
+    def _transition_state(self, new_state: AgentState) -> None:
+        """Transition the agent state."""
+        if self._state != new_state:
+            logger.debug(f"Agent state transition: {self._state} -> {new_state}")
+            self._state = new_state

astrbot/core/agent/runners/coze/coze_agent_runner.py

@@ -0,0 +1,367 @@
+import base64
+import json
+import sys
+import typing as T
+
+import astrbot.core.message.components as Comp
+from astrbot import logger
+from astrbot.core import sp
+from astrbot.core.message.message_event_result import MessageChain
+from astrbot.core.provider.entities import (
+    LLMResponse,
+    ProviderRequest,
+)
+
+from ...hooks import BaseAgentRunHooks
+from ...response import AgentResponseData
+from ...run_context import ContextWrapper, TContext
+from ..base import AgentResponse, AgentState, BaseAgentRunner
+from .coze_api_client import CozeAPIClient
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+
+
+class CozeAgentRunner(BaseAgentRunner[TContext]):
+    """Coze Agent Runner"""
+
+    @override
+    async def reset(
+        self,
+        request: ProviderRequest,
+        run_context: ContextWrapper[TContext],
+        agent_hooks: BaseAgentRunHooks[TContext],
+        provider_config: dict,
+        **kwargs: T.Any,
+    ) -> None:
+        self.req = request
+        self.streaming = kwargs.get("streaming", False)
+        self.final_llm_resp = None
+        self._state = AgentState.IDLE
+        self.agent_hooks = agent_hooks
+        self.run_context = run_context
+
+        self.api_key = provider_config.get("coze_api_key", "")
+        if not self.api_key:
+            raise Exception("Coze API Key 不能为空。")
+        self.bot_id = provider_config.get("bot_id", "")
+        if not self.bot_id:
+            raise Exception("Coze Bot ID 不能为空。")
+        self.api_base: str = provider_config.get("coze_api_base", "https://api.coze.cn")
+
+        if not isinstance(self.api_base, str) or not self.api_base.startswith(
+            ("http://", "https://"),
+        ):
+            raise Exception(
+                "Coze API Base URL 格式不正确，必须以 http:// 或 https:// 开头。",
+            )
+
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+        self.auto_save_history = provider_config.get("auto_save_history", True)
+
+        # 创建 API 客户端
+        self.api_client = CozeAPIClient(api_key=self.api_key, api_base=self.api_base)
+
+        # 会话相关缓存
+        self.file_id_cache: dict[str, dict[str, str]] = {}
+
+    @override
+    async def step(self):
+        """
+        执行 Coze Agent 的一个步骤
+        """
+        if not self.req:
+            raise ValueError("Request is not set. Please call reset() first.")
+
+        if self._state == AgentState.IDLE:
+            try:
+                await self.agent_hooks.on_agent_begin(self.run_context)
+            except Exception as e:
+                logger.error(f"Error in on_agent_begin hook: {e}", exc_info=True)
+
+        # 开始处理，转换到运行状态
+        self._transition_state(AgentState.RUNNING)
+
+        try:
+            # 执行 Coze 请求并处理结果
+            async for response in self._execute_coze_request():
+                yield response
+        except Exception as e:
+            logger.error(f"Coze 请求失败：{str(e)}")
+            self._transition_state(AgentState.ERROR)
+            self.final_llm_resp = LLMResponse(
+                role="err", completion_text=f"Coze 请求失败：{str(e)}"
+            )
+            yield AgentResponse(
+                type="err",
+                data=AgentResponseData(
+                    chain=MessageChain().message(f"Coze 请求失败：{str(e)}")
+                ),
+            )
+        finally:
+            await self.api_client.close()
+
+    @override
+    async def step_until_done(
+        self, max_step: int = 30
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        while not self.done():
+            async for resp in self.step():
+                yield resp
+
+    async def _execute_coze_request(self):
+        """执行 Coze 请求的核心逻辑"""
+        prompt = self.req.prompt or ""
+        session_id = self.req.session_id or "unknown"
+        image_urls = self.req.image_urls or []
+        contexts = self.req.contexts or []
+        system_prompt = self.req.system_prompt
+
+        # 用户ID参数
+        user_id = session_id
+
+        # 获取或创建会话ID
+        conversation_id = await sp.get_async(
+            scope="umo",
+            scope_id=user_id,
+            key="coze_conversation_id",
+            default="",
+        )
+
+        # 构建消息
+        additional_messages = []
+
+        if system_prompt:
+            if not self.auto_save_history or not conversation_id:
+                additional_messages.append(
+                    {
+                        "role": "system",
+                        "content": system_prompt,
+                        "content_type": "text",
+                    },
+                )
+
+        # 处理历史上下文
+        if not self.auto_save_history and contexts:
+            for ctx in contexts:
+                if isinstance(ctx, dict) and "role" in ctx and "content" in ctx:
+                    # 处理上下文中的图片
+                    content = ctx["content"]
+                    if isinstance(content, list):
+                        # 多模态内容，需要处理图片
+                        processed_content = []
+                        for item in content:
+                            if isinstance(item, dict):
+                                if item.get("type") == "text":
+                                    processed_content.append(item)
+                                elif item.get("type") == "image_url":
+                                    # 处理图片上传
+                                    try:
+                                        image_data = item.get("image_url", {})
+                                        url = image_data.get("url", "")
+                                        if url:
+                                            file_id = (
+                                                await self._download_and_upload_image(
+                                                    url, session_id
+                                                )
+                                            )
+                                            processed_content.append(
+                                                {
+                                                    "type": "file",
+                                                    "file_id": file_id,
+                                                    "file_url": url,
+                                                }
+                                            )
+                                    except Exception as e:
+                                        logger.warning(f"处理上下文图片失败: {e}")
+                                        continue
+
+                        if processed_content:
+                            additional_messages.append(
+                                {
+                                    "role": ctx["role"],
+                                    "content": processed_content,
+                                    "content_type": "object_string",
+                                }
+                            )
+                    else:
+                        # 纯文本内容
+                        additional_messages.append(
+                            {
+                                "role": ctx["role"],
+                                "content": content,
+                                "content_type": "text",
+                            }
+                        )
+
+        # 构建当前消息
+        if prompt or image_urls:
+            if image_urls:
+                # 多模态
+                object_string_content = []
+                if prompt:
+                    object_string_content.append({"type": "text", "text": prompt})
+
+                for url in image_urls:
+                    # the url is a base64 string
+                    try:
+                        image_data = base64.b64decode(url)
+                        file_id = await self.api_client.upload_file(image_data)
+                        object_string_content.append(
+                            {
+                                "type": "image",
+                                "file_id": file_id,
+                            }
+                        )
+                    except Exception as e:
+                        logger.warning(f"处理图片失败 {url}: {e}")
+                        continue
+
+                if object_string_content:
+                    content = json.dumps(object_string_content, ensure_ascii=False)
+                    additional_messages.append(
+                        {
+                            "role": "user",
+                            "content": content,
+                            "content_type": "object_string",
+                        }
+                    )
+            elif prompt:
+                # 纯文本
+                additional_messages.append(
+                    {
+                        "role": "user",
+                        "content": prompt,
+                        "content_type": "text",
+                    },
+                )
+
+        # 执行 Coze API 请求
+        accumulated_content = ""
+        message_started = False
+
+        async for chunk in self.api_client.chat_messages(
+            bot_id=self.bot_id,
+            user_id=user_id,
+            additional_messages=additional_messages,
+            conversation_id=conversation_id,
+            auto_save_history=self.auto_save_history,
+            stream=True,
+            timeout=self.timeout,
+        ):
+            event_type = chunk.get("event")
+            data = chunk.get("data", {})
+
+            if event_type == "conversation.chat.created":
+                if isinstance(data, dict) and "conversation_id" in data:
+                    await sp.put_async(
+                        scope="umo",
+                        scope_id=user_id,
+                        key="coze_conversation_id",
+                        value=data["conversation_id"],
+                    )
+
+            if event_type == "conversation.message.delta":
+                # 增量消息
+                content = data.get("content", "")
+                if not content and "delta" in data:
+                    content = data["delta"].get("content", "")
+                if not content and "text" in data:
+                    content = data.get("text", "")
+
+                if content:
+                    accumulated_content += content
+                    message_started = True
+
+                    # 如果是流式响应，发送增量数据
+                    if self.streaming:
+                        yield AgentResponse(
+                            type="streaming_delta",
+                            data=AgentResponseData(
+                                chain=MessageChain().message(content)
+                            ),
+                        )
+
+            elif event_type == "conversation.message.completed":
+                # 消息完成
+                logger.debug("Coze message completed")
+                message_started = True
+
+            elif event_type == "conversation.chat.completed":
+                # 对话完成
+                logger.debug("Coze chat completed")
+                break
+
+            elif event_type == "error":
+                # 错误处理
+                error_msg = data.get("msg", "未知错误")
+                error_code = data.get("code", "UNKNOWN")
+                logger.error(f"Coze 出现错误: {error_code} - {error_msg}")
+                raise Exception(f"Coze 出现错误: {error_code} - {error_msg}")
+
+        if not message_started and not accumulated_content:
+            logger.warning("Coze 未返回任何内容")
+            accumulated_content = ""
+
+        # 创建最终响应
+        chain = MessageChain(chain=[Comp.Plain(accumulated_content)])
+        self.final_llm_resp = LLMResponse(role="assistant", result_chain=chain)
+        self._transition_state(AgentState.DONE)
+
+        try:
+            await self.agent_hooks.on_agent_done(self.run_context, self.final_llm_resp)
+        except Exception as e:
+            logger.error(f"Error in on_agent_done hook: {e}", exc_info=True)
+
+        # 返回最终结果
+        yield AgentResponse(
+            type="llm_result",
+            data=AgentResponseData(chain=chain),
+        )
+
+    async def _download_and_upload_image(
+        self,
+        image_url: str,
+        session_id: str | None = None,
+    ) -> str:
+        """下载图片并上传到 Coze，返回 file_id"""
+        import hashlib
+
+        # 计算哈希实现缓存
+        cache_key = hashlib.md5(image_url.encode("utf-8")).hexdigest()
+
+        if session_id:
+            if session_id not in self.file_id_cache:
+                self.file_id_cache[session_id] = {}
+
+            if cache_key in self.file_id_cache[session_id]:
+                file_id = self.file_id_cache[session_id][cache_key]
+                logger.debug(f"[Coze] 使用缓存的 file_id: {file_id}")
+                return file_id
+
+        try:
+            image_data = await self.api_client.download_image(image_url)
+            file_id = await self.api_client.upload_file(image_data)
+
+            if session_id:
+                self.file_id_cache[session_id][cache_key] = file_id
+                logger.debug(f"[Coze] 图片上传成功并缓存，file_id: {file_id}")
+
+            return file_id
+
+        except Exception as e:
+            logger.error(f"处理图片失败 {image_url}: {e!s}")
+            raise Exception(f"处理图片失败: {e!s}")
+
+    @override
+    def done(self) -> bool:
+        """检查 Agent 是否已完成工作"""
+        return self._state in (AgentState.DONE, AgentState.ERROR)
+
+    @override
+    def get_final_llm_resp(self) -> LLMResponse | None:
+        return self.final_llm_resp

astrbot/core/agent/runners/coze/coze_api_client.py

@@ -0,0 +1,324 @@
+import asyncio
+import io
+import json
+from collections.abc import AsyncGenerator
+from typing import Any
+
+import aiohttp
+
+from astrbot.core import logger
+
+
+class CozeAPIClient:
+    def __init__(self, api_key: str, api_base: str = "https://api.coze.cn"):
+        self.api_key = api_key
+        self.api_base = api_base
+        self.session = None
+
+    async def _ensure_session(self):
+        """确保HTTP session存在"""
+        if self.session is None:
+            connector = aiohttp.TCPConnector(
+                ssl=False if self.api_base.startswith("http://") else True,
+                limit=100,
+                limit_per_host=30,
+                keepalive_timeout=30,
+                enable_cleanup_closed=True,
+            )
+            timeout = aiohttp.ClientTimeout(
+                total=120,  # 默认超时时间
+                connect=30,
+                sock_read=120,
+            )
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Accept": "text/event-stream",
+            }
+            self.session = aiohttp.ClientSession(
+                headers=headers,
+                timeout=timeout,
+                connector=connector,
+            )
+        return self.session
+
+    async def upload_file(
+        self,
+        file_data: bytes,
+    ) -> str:
+        """上传文件到 Coze 并返回 file_id
+
+        Args:
+            file_data (bytes): 文件的二进制数据
+        Returns:
+            str: 上传成功后返回的 file_id
+
+        """
+        session = await self._ensure_session()
+        url = f"{self.api_base}/v1/files/upload"
+
+        try:
+            file_io = io.BytesIO(file_data)
+            async with session.post(
+                url,
+                data={
+                    "file": file_io,
+                },
+                timeout=aiohttp.ClientTimeout(total=60),
+            ) as response:
+                if response.status == 401:
+                    raise Exception("Coze API 认证失败，请检查 API Key 是否正确")
+
+                response_text = await response.text()
+                logger.debug(
+                    f"文件上传响应状态: {response.status}, 内容: {response_text}",
+                )
+
+                if response.status != 200:
+                    raise Exception(
+                        f"文件上传失败，状态码: {response.status}, 响应: {response_text}",
+                    )
+
+                try:
+                    result = await response.json()
+                except json.JSONDecodeError:
+                    raise Exception(f"文件上传响应解析失败: {response_text}")
+
+                if result.get("code") != 0:
+                    raise Exception(f"文件上传失败: {result.get('msg', '未知错误')}")
+
+                file_id = result["data"]["id"]
+                logger.debug(f"[Coze] 图片上传成功，file_id: {file_id}")
+                return file_id
+
+        except asyncio.TimeoutError:
+            logger.error("文件上传超时")
+            raise Exception("文件上传超时")
+        except Exception as e:
+            logger.error(f"文件上传失败: {e!s}")
+            raise Exception(f"文件上传失败: {e!s}")
+
+    async def download_image(self, image_url: str) -> bytes:
+        """下载图片并返回字节数据
+
+        Args:
+            image_url (str): 图片的URL
+        Returns:
+            bytes: 图片的二进制数据
+
+        """
+        session = await self._ensure_session()
+
+        try:
+            async with session.get(image_url) as response:
+                if response.status != 200:
+                    raise Exception(f"下载图片失败，状态码: {response.status}")
+
+                image_data = await response.read()
+                return image_data
+
+        except Exception as e:
+            logger.error(f"下载图片失败 {image_url}: {e!s}")
+            raise Exception(f"下载图片失败: {e!s}")
+
+    async def chat_messages(
+        self,
+        bot_id: str,
+        user_id: str,
+        additional_messages: list[dict] | None = None,
+        conversation_id: str | None = None,
+        auto_save_history: bool = True,
+        stream: bool = True,
+        timeout: float = 120,
+    ) -> AsyncGenerator[dict[str, Any], None]:
+        """发送聊天消息并返回流式响应
+
+        Args:
+            bot_id: Bot ID
+            user_id: 用户ID
+            additional_messages: 额外消息列表
+            conversation_id: 会话ID
+            auto_save_history: 是否自动保存历史
+            stream: 是否流式响应
+            timeout: 超时时间
+
+        """
+        session = await self._ensure_session()
+        url = f"{self.api_base}/v3/chat"
+
+        payload = {
+            "bot_id": bot_id,
+            "user_id": user_id,
+            "stream": stream,
+            "auto_save_history": auto_save_history,
+        }
+
+        if additional_messages:
+            payload["additional_messages"] = additional_messages
+
+        params = {}
+        if conversation_id:
+            params["conversation_id"] = conversation_id
+
+        logger.debug(f"Coze chat_messages payload: {payload}, params: {params}")
+
+        try:
+            async with session.post(
+                url,
+                json=payload,
+                params=params,
+                timeout=aiohttp.ClientTimeout(total=timeout),
+            ) as response:
+                if response.status == 401:
+                    raise Exception("Coze API 认证失败，请检查 API Key 是否正确")
+
+                if response.status != 200:
+                    raise Exception(f"Coze API 流式请求失败，状态码: {response.status}")
+
+                # SSE
+                buffer = ""
+                event_type = None
+                event_data = None
+
+                async for chunk in response.content:
+                    if chunk:
+                        buffer += chunk.decode("utf-8", errors="ignore")
+                        lines = buffer.split("\n")
+                        buffer = lines[-1]
+
+                        for line in lines[:-1]:
+                            line = line.strip()
+
+                            if not line:
+                                if event_type and event_data:
+                                    yield {"event": event_type, "data": event_data}
+                                    event_type = None
+                                    event_data = None
+                            elif line.startswith("event:"):
+                                event_type = line[6:].strip()
+                            elif line.startswith("data:"):
+                                data_str = line[5:].strip()
+                                if data_str and data_str != "[DONE]":
+                                    try:
+                                        event_data = json.loads(data_str)
+                                    except json.JSONDecodeError:
+                                        event_data = {"content": data_str}
+
+        except asyncio.TimeoutError:
+            raise Exception(f"Coze API 流式请求超时 ({timeout}秒)")
+        except Exception as e:
+            raise Exception(f"Coze API 流式请求失败: {e!s}")
+
+    async def clear_context(self, conversation_id: str):
+        """清空会话上下文
+
+        Args:
+            conversation_id: 会话ID
+        Returns:
+            dict: API响应结果
+
+        """
+        session = await self._ensure_session()
+        url = f"{self.api_base}/v3/conversation/message/clear_context"
+        payload = {"conversation_id": conversation_id}
+
+        try:
+            async with session.post(url, json=payload) as response:
+                response_text = await response.text()
+
+                if response.status == 401:
+                    raise Exception("Coze API 认证失败，请检查 API Key 是否正确")
+
+                if response.status != 200:
+                    raise Exception(f"Coze API 请求失败，状态码: {response.status}")
+
+                try:
+                    return json.loads(response_text)
+                except json.JSONDecodeError:
+                    raise Exception("Coze API 返回非JSON格式")
+
+        except asyncio.TimeoutError:
+            raise Exception("Coze API 请求超时")
+        except aiohttp.ClientError as e:
+            raise Exception(f"Coze API 请求失败: {e!s}")
+
+    async def get_message_list(
+        self,
+        conversation_id: str,
+        order: str = "desc",
+        limit: int = 10,
+        offset: int = 0,
+    ):
+        """获取消息列表
+
+        Args:
+            conversation_id: 会话ID
+            order: 排序方式 (asc/desc)
+            limit: 限制数量
+            offset: 偏移量
+        Returns:
+            dict: API响应结果
+
+        """
+        session = await self._ensure_session()
+        url = f"{self.api_base}/v3/conversation/message/list"
+        params = {
+            "conversation_id": conversation_id,
+            "order": order,
+            "limit": limit,
+            "offset": offset,
+        }
+
+        try:
+            async with session.get(url, params=params) as response:
+                response.raise_for_status()
+                return await response.json()
+
+        except Exception as e:
+            logger.error(f"获取Coze消息列表失败: {e!s}")
+            raise Exception(f"获取Coze消息列表失败: {e!s}")
+
+    async def close(self):
+        """关闭会话"""
+        if self.session:
+            await self.session.close()
+            self.session = None
+
+
+if __name__ == "__main__":
+    import asyncio
+    import os
+
+    async def test_coze_api_client():
+        api_key = os.getenv("COZE_API_KEY", "")
+        bot_id = os.getenv("COZE_BOT_ID", "")
+        client = CozeAPIClient(api_key=api_key)
+
+        try:
+            with open("README.md", "rb") as f:
+                file_data = f.read()
+            file_id = await client.upload_file(file_data)
+            print(f"Uploaded file_id: {file_id}")
+            async for event in client.chat_messages(
+                bot_id=bot_id,
+                user_id="test_user",
+                additional_messages=[
+                    {
+                        "role": "user",
+                        "content": json.dumps(
+                            [
+                                {"type": "text", "text": "这是什么"},
+                                {"type": "file", "file_id": file_id},
+                            ],
+                            ensure_ascii=False,
+                        ),
+                        "content_type": "object_string",
+                    },
+                ],
+                stream=True,
+            ):
+                print(f"Event: {event}")
+
+        finally:
+            await client.close()
+
+    asyncio.run(test_coze_api_client())

astrbot/core/agent/runners/dashscope/dashscope_agent_runner.py

@@ -0,0 +1,403 @@
+import asyncio
+import functools
+import queue
+import re
+import sys
+import threading
+import typing as T
+
+from dashscope import Application
+from dashscope.app.application_response import ApplicationResponse
+
+import astrbot.core.message.components as Comp
+from astrbot.core import logger, sp
+from astrbot.core.message.message_event_result import MessageChain
+from astrbot.core.provider.entities import (
+    LLMResponse,
+    ProviderRequest,
+)
+
+from ...hooks import BaseAgentRunHooks
+from ...response import AgentResponseData
+from ...run_context import ContextWrapper, TContext
+from ..base import AgentResponse, AgentState, BaseAgentRunner
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+
+
+class DashscopeAgentRunner(BaseAgentRunner[TContext]):
+    """Dashscope Agent Runner"""
+
+    @override
+    async def reset(
+        self,
+        request: ProviderRequest,
+        run_context: ContextWrapper[TContext],
+        agent_hooks: BaseAgentRunHooks[TContext],
+        provider_config: dict,
+        **kwargs: T.Any,
+    ) -> None:
+        self.req = request
+        self.streaming = kwargs.get("streaming", False)
+        self.final_llm_resp = None
+        self._state = AgentState.IDLE
+        self.agent_hooks = agent_hooks
+        self.run_context = run_context
+
+        self.api_key = provider_config.get("dashscope_api_key", "")
+        if not self.api_key:
+            raise Exception("阿里云百炼 API Key 不能为空。")
+        self.app_id = provider_config.get("dashscope_app_id", "")
+        if not self.app_id:
+            raise Exception("阿里云百炼 APP ID 不能为空。")
+        self.dashscope_app_type = provider_config.get("dashscope_app_type", "")
+        if not self.dashscope_app_type:
+            raise Exception("阿里云百炼 APP 类型不能为空。")
+
+        self.variables: dict = provider_config.get("variables", {}) or {}
+        self.rag_options: dict = provider_config.get("rag_options", {})
+        self.output_reference = self.rag_options.get("output_reference", False)
+        self.rag_options = self.rag_options.copy()
+        self.rag_options.pop("output_reference", None)
+
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+
+    def has_rag_options(self):
+        """判断是否有 RAG 选项
+
+        Returns:
+            bool: 是否有 RAG 选项
+
+        """
+        if self.rag_options and (
+            len(self.rag_options.get("pipeline_ids", [])) > 0
+            or len(self.rag_options.get("file_ids", [])) > 0
+        ):
+            return True
+        return False
+
+    @override
+    async def step(self):
+        """
+        执行 Dashscope Agent 的一个步骤
+        """
+        if not self.req:
+            raise ValueError("Request is not set. Please call reset() first.")
+
+        if self._state == AgentState.IDLE:
+            try:
+                await self.agent_hooks.on_agent_begin(self.run_context)
+            except Exception as e:
+                logger.error(f"Error in on_agent_begin hook: {e}", exc_info=True)
+
+        # 开始处理，转换到运行状态
+        self._transition_state(AgentState.RUNNING)
+
+        try:
+            # 执行 Dashscope 请求并处理结果
+            async for response in self._execute_dashscope_request():
+                yield response
+        except Exception as e:
+            logger.error(f"阿里云百炼请求失败：{str(e)}")
+            self._transition_state(AgentState.ERROR)
+            self.final_llm_resp = LLMResponse(
+                role="err", completion_text=f"阿里云百炼请求失败：{str(e)}"
+            )
+            yield AgentResponse(
+                type="err",
+                data=AgentResponseData(
+                    chain=MessageChain().message(f"阿里云百炼请求失败：{str(e)}")
+                ),
+            )
+
+    @override
+    async def step_until_done(
+        self, max_step: int = 30
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        while not self.done():
+            async for resp in self.step():
+                yield resp
+
+    def _consume_sync_generator(
+        self, response: T.Any, response_queue: queue.Queue
+    ) -> None:
+        """在线程中消费同步generator,将结果放入队列
+
+        Args:
+            response: 同步generator对象
+            response_queue: 用于传递数据的队列
+
+        """
+        try:
+            if self.streaming:
+                for chunk in response:
+                    response_queue.put(("data", chunk))
+            else:
+                response_queue.put(("data", response))
+        except Exception as e:
+            response_queue.put(("error", e))
+        finally:
+            response_queue.put(("done", None))
+
+    async def _process_stream_chunk(
+        self, chunk: ApplicationResponse, output_text: str
+    ) -> tuple[str, list | None, AgentResponse | None]:
+        """处理流式响应的单个chunk
+
+        Args:
+            chunk: Dashscope响应chunk
+            output_text: 当前累积的输出文本
+
+        Returns:
+            (更新后的output_text, doc_references, AgentResponse或None)
+
+        """
+        logger.debug(f"dashscope stream chunk: {chunk}")
+
+        if chunk.status_code != 200:
+            logger.error(
+                f"阿里云百炼请求失败: request_id={chunk.request_id}, code={chunk.status_code}, message={chunk.message}, 请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code",
+            )
+            self._transition_state(AgentState.ERROR)
+            error_msg = (
+                f"阿里云百炼请求失败: message={chunk.message} code={chunk.status_code}"
+            )
+            self.final_llm_resp = LLMResponse(
+                role="err",
+                result_chain=MessageChain().message(error_msg),
+            )
+            return (
+                output_text,
+                None,
+                AgentResponse(
+                    type="err",
+                    data=AgentResponseData(chain=MessageChain().message(error_msg)),
+                ),
+            )
+
+        chunk_text = chunk.output.get("text", "") or ""
+        # RAG 引用脚标格式化
+        chunk_text = re.sub(r"<ref>\[(\d+)\]</ref>", r"[\1]", chunk_text)
+
+        response = None
+        if chunk_text:
+            output_text += chunk_text
+            response = AgentResponse(
+                type="streaming_delta",
+                data=AgentResponseData(chain=MessageChain().message(chunk_text)),
+            )
+
+        # 获取文档引用
+        doc_references = chunk.output.get("doc_references", None)
+
+        return output_text, doc_references, response
+
+    def _format_doc_references(self, doc_references: list) -> str:
+        """格式化文档引用为文本
+
+        Args:
+            doc_references: 文档引用列表
+
+        Returns:
+            格式化后的引用文本
+
+        """
+        ref_parts = []
+        for ref in doc_references:
+            ref_title = (
+                ref.get("title", "") if ref.get("title") else ref.get("doc_name", "")
+            )
+            ref_parts.append(f"{ref['index_id']}. {ref_title}\n")
+        ref_str = "".join(ref_parts)
+        return f"\n\n回答来源:\n{ref_str}"
+
+    async def _build_request_payload(
+        self, prompt: str, session_id: str, contexts: list, system_prompt: str
+    ) -> dict:
+        """构建请求payload
+
+        Args:
+            prompt: 用户输入
+            session_id: 会话ID
+            contexts: 上下文列表
+            system_prompt: 系统提示词
+
+        Returns:
+            请求payload字典
+
+        """
+        conversation_id = await sp.get_async(
+            scope="umo",
+            scope_id=session_id,
+            key="dashscope_conversation_id",
+            default="",
+        )
+        # 获得会话变量
+        payload_vars = self.variables.copy()
+        session_var = await sp.get_async(
+            scope="umo",
+            scope_id=session_id,
+            key="session_variables",
+            default={},
+        )
+        payload_vars.update(session_var)
+
+        if (
+            self.dashscope_app_type in ["agent", "dialog-workflow"]
+            and not self.has_rag_options()
+        ):
+            # 支持多轮对话的
+            p = {
+                "app_id": self.app_id,
+                "api_key": self.api_key,
+                "prompt": prompt,
+                "biz_params": payload_vars or None,
+                "stream": self.streaming,
+                "incremental_output": True,
+            }
+            if conversation_id:
+                p["session_id"] = conversation_id
+            return p
+        else:
+            # 不支持多轮对话的
+            payload = {
+                "app_id": self.app_id,
+                "prompt": prompt,
+                "api_key": self.api_key,
+                "biz_params": payload_vars or None,
+                "stream": self.streaming,
+                "incremental_output": True,
+            }
+            if self.rag_options:
+                payload["rag_options"] = self.rag_options
+            return payload
+
+    async def _handle_streaming_response(
+        self, response: T.Any, session_id: str
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        """处理流式响应
+
+        Args:
+            response: Dashscope 流式响应 generator
+
+        Yields:
+            AgentResponse 对象
+
+        """
+        response_queue = queue.Queue()
+        consumer_thread = threading.Thread(
+            target=self._consume_sync_generator,
+            args=(response, response_queue),
+            daemon=True,
+        )
+        consumer_thread.start()
+
+        output_text = ""
+        doc_references = None
+
+        while True:
+            try:
+                item_type, item_data = await asyncio.get_event_loop().run_in_executor(
+                    None, response_queue.get, True, 1
+                )
+            except queue.Empty:
+                continue
+
+            if item_type == "done":
+                break
+            elif item_type == "error":
+                raise item_data
+            elif item_type == "data":
+                chunk = item_data
+                assert isinstance(chunk, ApplicationResponse)
+
+                (
+                    output_text,
+                    chunk_doc_refs,
+                    response,
+                ) = await self._process_stream_chunk(chunk, output_text)
+
+                if response:
+                    if response.type == "err":
+                        yield response
+                        return
+                    yield response
+
+                if chunk_doc_refs:
+                    doc_references = chunk_doc_refs
+
+                if chunk.output.session_id:
+                    await sp.put_async(
+                        scope="umo",
+                        scope_id=session_id,
+                        key="dashscope_conversation_id",
+                        value=chunk.output.session_id,
+                    )
+
+        # 添加 RAG 引用
+        if self.output_reference and doc_references:
+            ref_text = self._format_doc_references(doc_references)
+            output_text += ref_text
+
+            if self.streaming:
+                yield AgentResponse(
+                    type="streaming_delta",
+                    data=AgentResponseData(chain=MessageChain().message(ref_text)),
+                )
+
+        # 创建最终响应
+        chain = MessageChain(chain=[Comp.Plain(output_text)])
+        self.final_llm_resp = LLMResponse(role="assistant", result_chain=chain)
+        self._transition_state(AgentState.DONE)
+
+        try:
+            await self.agent_hooks.on_agent_done(self.run_context, self.final_llm_resp)
+        except Exception as e:
+            logger.error(f"Error in on_agent_done hook: {e}", exc_info=True)
+
+        # 返回最终结果
+        yield AgentResponse(
+            type="llm_result",
+            data=AgentResponseData(chain=chain),
+        )
+
+    async def _execute_dashscope_request(self):
+        """执行 Dashscope 请求的核心逻辑"""
+        prompt = self.req.prompt or ""
+        session_id = self.req.session_id or "unknown"
+        image_urls = self.req.image_urls or []
+        contexts = self.req.contexts or []
+        system_prompt = self.req.system_prompt
+
+        # 检查图片输入
+        if image_urls:
+            logger.warning("阿里云百炼暂不支持图片输入，将自动忽略图片内容。")
+
+        # 构建请求payload
+        payload = await self._build_request_payload(
+            prompt, session_id, contexts, system_prompt
+        )
+
+        if not self.streaming:
+            payload["incremental_output"] = False
+
+        # 发起请求
+        partial = functools.partial(Application.call, **payload)
+        response = await asyncio.get_event_loop().run_in_executor(None, partial)
+
+        async for resp in self._handle_streaming_response(response, session_id):
+            yield resp
+
+    @override
+    def done(self) -> bool:
+        """检查 Agent 是否已完成工作"""
+        return self._state in (AgentState.DONE, AgentState.ERROR)
+
+    @override
+    def get_final_llm_resp(self) -> LLMResponse | None:
+        return self.final_llm_resp

astrbot/core/agent/runners/dify/dify_agent_runner.py

@@ -0,0 +1,336 @@
+import base64
+import os
+import sys
+import typing as T
+
+import astrbot.core.message.components as Comp
+from astrbot.core import logger, sp
+from astrbot.core.message.message_event_result import MessageChain
+from astrbot.core.provider.entities import (
+    LLMResponse,
+    ProviderRequest,
+)
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+from astrbot.core.utils.io import download_file
+
+from ...hooks import BaseAgentRunHooks
+from ...response import AgentResponseData
+from ...run_context import ContextWrapper, TContext
+from ..base import AgentResponse, AgentState, BaseAgentRunner
+from .dify_api_client import DifyAPIClient
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+
+
+class DifyAgentRunner(BaseAgentRunner[TContext]):
+    """Dify Agent Runner"""
+
+    @override
+    async def reset(
+        self,
+        request: ProviderRequest,
+        run_context: ContextWrapper[TContext],
+        agent_hooks: BaseAgentRunHooks[TContext],
+        provider_config: dict,
+        **kwargs: T.Any,
+    ) -> None:
+        self.req = request
+        self.streaming = kwargs.get("streaming", False)
+        self.final_llm_resp = None
+        self._state = AgentState.IDLE
+        self.agent_hooks = agent_hooks
+        self.run_context = run_context
+
+        self.api_key = provider_config.get("dify_api_key", "")
+        self.api_base = provider_config.get("dify_api_base", "https://api.dify.ai/v1")
+        self.api_type = provider_config.get("dify_api_type", "chat")
+        self.workflow_output_key = provider_config.get(
+            "dify_workflow_output_key",
+            "astrbot_wf_output",
+        )
+        self.dify_query_input_key = provider_config.get(
+            "dify_query_input_key",
+            "astrbot_text_query",
+        )
+        self.variables: dict = provider_config.get("variables", {}) or {}
+        self.timeout = provider_config.get("timeout", 60)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+
+        self.api_client = DifyAPIClient(self.api_key, self.api_base)
+
+    @override
+    async def step(self):
+        """
+        执行 Dify Agent 的一个步骤
+        """
+        if not self.req:
+            raise ValueError("Request is not set. Please call reset() first.")
+
+        if self._state == AgentState.IDLE:
+            try:
+                await self.agent_hooks.on_agent_begin(self.run_context)
+            except Exception as e:
+                logger.error(f"Error in on_agent_begin hook: {e}", exc_info=True)
+
+        # 开始处理，转换到运行状态
+        self._transition_state(AgentState.RUNNING)
+
+        try:
+            # 执行 Dify 请求并处理结果
+            async for response in self._execute_dify_request():
+                yield response
+        except Exception as e:
+            logger.error(f"Dify 请求失败：{str(e)}")
+            self._transition_state(AgentState.ERROR)
+            self.final_llm_resp = LLMResponse(
+                role="err", completion_text=f"Dify 请求失败：{str(e)}"
+            )
+            yield AgentResponse(
+                type="err",
+                data=AgentResponseData(
+                    chain=MessageChain().message(f"Dify 请求失败：{str(e)}")
+                ),
+            )
+        finally:
+            await self.api_client.close()
+
+    @override
+    async def step_until_done(
+        self, max_step: int = 30
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        while not self.done():
+            async for resp in self.step():
+                yield resp
+
+    async def _execute_dify_request(self):
+        """执行 Dify 请求的核心逻辑"""
+        prompt = self.req.prompt or ""
+        session_id = self.req.session_id or "unknown"
+        image_urls = self.req.image_urls or []
+        system_prompt = self.req.system_prompt
+
+        conversation_id = await sp.get_async(
+            scope="umo",
+            scope_id=session_id,
+            key="dify_conversation_id",
+            default="",
+        )
+        result = ""
+
+        # 处理图片上传
+        files_payload = []
+        for image_url in image_urls:
+            # image_url is a base64 string
+            try:
+                image_data = base64.b64decode(image_url)
+                file_response = await self.api_client.file_upload(
+                    file_data=image_data,
+                    user=session_id,
+                    mime_type="image/png",
+                    file_name="image.png",
+                )
+                logger.debug(f"Dify 上传图片响应：{file_response}")
+                if "id" not in file_response:
+                    logger.warning(
+                        f"上传图片后得到未知的 Dify 响应：{file_response}，图片将忽略。"
+                    )
+                    continue
+                files_payload.append(
+                    {
+                        "type": "image",
+                        "transfer_method": "local_file",
+                        "upload_file_id": file_response["id"],
+                    }
+                )
+            except Exception as e:
+                logger.warning(f"上传图片失败：{e}")
+                continue
+
+        # 获得会话变量
+        payload_vars = self.variables.copy()
+        # 动态变量
+        session_var = await sp.get_async(
+            scope="umo",
+            scope_id=session_id,
+            key="session_variables",
+            default={},
+        )
+        payload_vars.update(session_var)
+        payload_vars["system_prompt"] = system_prompt
+
+        # 处理不同的 API 类型
+        match self.api_type:
+            case "chat" | "agent" | "chatflow":
+                if not prompt:
+                    prompt = "请描述这张图片。"
+
+                async for chunk in self.api_client.chat_messages(
+                    inputs={
+                        **payload_vars,
+                    },
+                    query=prompt,
+                    user=session_id,
+                    conversation_id=conversation_id,
+                    files=files_payload,
+                    timeout=self.timeout,
+                ):
+                    logger.debug(f"dify resp chunk: {chunk}")
+                    if chunk["event"] == "message" or chunk["event"] == "agent_message":
+                        result += chunk["answer"]
+                        if not conversation_id:
+                            await sp.put_async(
+                                scope="umo",
+                                scope_id=session_id,
+                                key="dify_conversation_id",
+                                value=chunk["conversation_id"],
+                            )
+                            conversation_id = chunk["conversation_id"]
+
+                        # 如果是流式响应，发送增量数据
+                        if self.streaming and chunk["answer"]:
+                            yield AgentResponse(
+                                type="streaming_delta",
+                                data=AgentResponseData(
+                                    chain=MessageChain().message(chunk["answer"])
+                                ),
+                            )
+                    elif chunk["event"] == "message_end":
+                        logger.debug("Dify message end")
+                        break
+                    elif chunk["event"] == "error":
+                        logger.error(f"Dify 出现错误：{chunk}")
+                        raise Exception(
+                            f"Dify 出现错误 status: {chunk['status']} message: {chunk['message']}"
+                        )
+
+            case "workflow":
+                async for chunk in self.api_client.workflow_run(
+                    inputs={
+                        self.dify_query_input_key: prompt,
+                        "astrbot_session_id": session_id,
+                        **payload_vars,
+                    },
+                    user=session_id,
+                    files=files_payload,
+                    timeout=self.timeout,
+                ):
+                    logger.debug(f"dify workflow resp chunk: {chunk}")
+                    match chunk["event"]:
+                        case "workflow_started":
+                            logger.info(
+                                f"Dify 工作流(ID: {chunk['workflow_run_id']})开始运行。"
+                            )
+                        case "node_finished":
+                            logger.debug(
+                                f"Dify 工作流节点(ID: {chunk['data']['node_id']} Title: {chunk['data'].get('title', '')})运行结束。"
+                            )
+                        case "text_chunk":
+                            if self.streaming and chunk["data"]["text"]:
+                                yield AgentResponse(
+                                    type="streaming_delta",
+                                    data=AgentResponseData(
+                                        chain=MessageChain().message(
+                                            chunk["data"]["text"]
+                                        )
+                                    ),
+                                )
+                        case "workflow_finished":
+                            logger.info(
+                                f"Dify 工作流(ID: {chunk['workflow_run_id']})运行结束"
+                            )
+                            logger.debug(f"Dify 工作流结果：{chunk}")
+                            if chunk["data"]["error"]:
+                                logger.error(
+                                    f"Dify 工作流出现错误：{chunk['data']['error']}"
+                                )
+                                raise Exception(
+                                    f"Dify 工作流出现错误：{chunk['data']['error']}"
+                                )
+                            if self.workflow_output_key not in chunk["data"]["outputs"]:
+                                raise Exception(
+                                    f"Dify 工作流的输出不包含指定的键名：{self.workflow_output_key}"
+                                )
+                            result = chunk
+            case _:
+                raise Exception(f"未知的 Dify API 类型：{self.api_type}")
+
+        if not result:
+            logger.warning("Dify 请求结果为空，请查看 Debug 日志。")
+
+        # 解析结果
+        chain = await self.parse_dify_result(result)
+
+        # 创建最终响应
+        self.final_llm_resp = LLMResponse(role="assistant", result_chain=chain)
+        self._transition_state(AgentState.DONE)
+
+        try:
+            await self.agent_hooks.on_agent_done(self.run_context, self.final_llm_resp)
+        except Exception as e:
+            logger.error(f"Error in on_agent_done hook: {e}", exc_info=True)
+
+        # 返回最终结果
+        yield AgentResponse(
+            type="llm_result",
+            data=AgentResponseData(chain=chain),
+        )
+
+    async def parse_dify_result(self, chunk: dict | str) -> MessageChain:
+        """解析 Dify 的响应结果"""
+        if isinstance(chunk, str):
+            # Chat
+            return MessageChain(chain=[Comp.Plain(chunk)])
+
+        async def parse_file(item: dict):
+            match item["type"]:
+                case "image":
+                    return Comp.Image(file=item["url"], url=item["url"])
+                case "audio":
+                    # 仅支持 wav
+                    temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+                    path = os.path.join(temp_dir, f"{item['filename']}.wav")
+                    await download_file(item["url"], path)
+                    return Comp.Image(file=item["url"], url=item["url"])
+                case "video":
+                    return Comp.Video(file=item["url"])
+                case _:
+                    return Comp.File(name=item["filename"], file=item["url"])
+
+        output = chunk["data"]["outputs"][self.workflow_output_key]
+        chains = []
+        if isinstance(output, str):
+            # 纯文本输出
+            chains.append(Comp.Plain(output))
+        elif isinstance(output, list):
+            # 主要适配 Dify 的 HTTP 请求结点的多模态输出
+            for item in output:
+                # handle Array[File]
+                if (
+                    not isinstance(item, dict)
+                    or item.get("dify_model_identity", "") != "__dify__file__"
+                ):
+                    chains.append(Comp.Plain(str(output)))
+                    break
+        else:
+            chains.append(Comp.Plain(str(output)))
+
+        # scan file
+        files = chunk["data"].get("files", [])
+        for item in files:
+            comp = await parse_file(item)
+            chains.append(comp)
+
+        return MessageChain(chain=chains)
+
+    @override
+    def done(self) -> bool:
+        """检查 Agent 是否已完成工作"""
+        return self._state in (AgentState.DONE, AgentState.ERROR)
+
+    @override
+    def get_final_llm_resp(self) -> LLMResponse | None:
+        return self.final_llm_resp

astrbot/core/agent/runners/dify/dify_api_client.py

@@ -0,0 +1,195 @@
+import codecs
+import json
+from collections.abc import AsyncGenerator
+from typing import Any
+
+from aiohttp import ClientResponse, ClientSession, FormData
+
+from astrbot.core import logger
+
+
+async def _stream_sse(resp: ClientResponse) -> AsyncGenerator[dict, None]:
+    decoder = codecs.getincrementaldecoder("utf-8")()
+    buffer = ""
+    async for chunk in resp.content.iter_chunked(8192):
+        buffer += decoder.decode(chunk)
+        while "\n\n" in buffer:
+            block, buffer = buffer.split("\n\n", 1)
+            if block.strip().startswith("data:"):
+                try:
+                    yield json.loads(block[5:])
+                except json.JSONDecodeError:
+                    logger.warning(f"Drop invalid dify json data: {block[5:]}")
+                    continue
+    # flush any remaining text
+    buffer += decoder.decode(b"", final=True)
+    if buffer.strip().startswith("data:"):
+        try:
+            yield json.loads(buffer[5:])
+        except json.JSONDecodeError:
+            logger.warning(f"Drop invalid dify json data: {buffer[5:]}")
+
+
+class DifyAPIClient:
+    def __init__(self, api_key: str, api_base: str = "https://api.dify.ai/v1"):
+        self.api_key = api_key
+        self.api_base = api_base
+        self.session = ClientSession(trust_env=True)
+        self.headers = {
+            "Authorization": f"Bearer {self.api_key}",
+        }
+
+    async def chat_messages(
+        self,
+        inputs: dict,
+        query: str,
+        user: str,
+        response_mode: str = "streaming",
+        conversation_id: str = "",
+        files: list[dict[str, Any]] | None = None,
+        timeout: float = 60,
+    ) -> AsyncGenerator[dict[str, Any], None]:
+        if files is None:
+            files = []
+        url = f"{self.api_base}/chat-messages"
+        payload = locals()
+        payload.pop("self")
+        payload.pop("timeout")
+        logger.info(f"chat_messages payload: {payload}")
+        async with self.session.post(
+            url,
+            json=payload,
+            headers=self.headers,
+            timeout=timeout,
+        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise Exception(
+                    f"Dify /chat-messages 接口请求失败：{resp.status}. {text}",
+                )
+            async for event in _stream_sse(resp):
+                yield event
+
+    async def workflow_run(
+        self,
+        inputs: dict,
+        user: str,
+        response_mode: str = "streaming",
+        files: list[dict[str, Any]] | None = None,
+        timeout: float = 60,
+    ):
+        if files is None:
+            files = []
+        url = f"{self.api_base}/workflows/run"
+        payload = locals()
+        payload.pop("self")
+        payload.pop("timeout")
+        logger.info(f"workflow_run payload: {payload}")
+        async with self.session.post(
+            url,
+            json=payload,
+            headers=self.headers,
+            timeout=timeout,
+        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise Exception(
+                    f"Dify /workflows/run 接口请求失败：{resp.status}. {text}",
+                )
+            async for event in _stream_sse(resp):
+                yield event
+
+    async def file_upload(
+        self,
+        user: str,
+        file_path: str | None = None,
+        file_data: bytes | None = None,
+        file_name: str | None = None,
+        mime_type: str | None = None,
+    ) -> dict[str, Any]:
+        """Upload a file to Dify. Must provide either file_path or file_data.
+
+        Args:
+            user: The user ID.
+            file_path: The path to the file to upload.
+            file_data: The file data in bytes.
+            file_name: Optional file name when using file_data.
+        Returns:
+            A dictionary containing the uploaded file information.
+        """
+        url = f"{self.api_base}/files/upload"
+
+        form = FormData()
+        form.add_field("user", user)
+
+        if file_data is not None:
+            # 使用 bytes 数据
+            form.add_field(
+                "file",
+                file_data,
+                filename=file_name or "uploaded_file",
+                content_type=mime_type or "application/octet-stream",
+            )
+        elif file_path is not None:
+            # 使用文件路径
+            import os
+
+            with open(file_path, "rb") as f:
+                file_content = f.read()
+                form.add_field(
+                    "file",
+                    file_content,
+                    filename=os.path.basename(file_path),
+                    content_type=mime_type or "application/octet-stream",
+                )
+        else:
+            raise ValueError("file_path 和 file_data 不能同时为 None")
+
+        async with self.session.post(
+            url,
+            data=form,
+            headers=self.headers,  # 不包含 Content-Type，让 aiohttp 自动设置
+        ) as resp:
+            if resp.status != 200 and resp.status != 201:
+                text = await resp.text()
+                raise Exception(f"Dify 文件上传失败：{resp.status}. {text}")
+            return await resp.json()  # {"id": "xxx", ...}
+
+    async def close(self):
+        await self.session.close()
+
+    async def get_chat_convs(self, user: str, limit: int = 20):
+        # conversations. GET
+        url = f"{self.api_base}/conversations"
+        payload = {
+            "user": user,
+            "limit": limit,
+        }
+        async with self.session.get(url, params=payload, headers=self.headers) as resp:
+            return await resp.json()
+
+    async def delete_chat_conv(self, user: str, conversation_id: str):
+        # conversation. DELETE
+        url = f"{self.api_base}/conversations/{conversation_id}"
+        payload = {
+            "user": user,
+        }
+        async with self.session.delete(url, json=payload, headers=self.headers) as resp:
+            return await resp.json()
+
+    async def rename(
+        self,
+        conversation_id: str,
+        name: str,
+        user: str,
+        auto_generate: bool = False,
+    ):
+        # /conversations/:conversation_id/name
+        url = f"{self.api_base}/conversations/{conversation_id}/name"
+        payload = {
+            "user": user,
+            "name": name,
+            "auto_generate": auto_generate,
+        }
+        async with self.session.post(url, json=payload, headers=self.headers) as resp:
+            return await resp.json()

astrbot/core/agent/runners/tool_loop_agent_runner.py

@@ -1,31 +1,42 @@
+import copy
 import sys
+import time
 import traceback
 import typing as T
-from .base import BaseAgentRunner, AgentResponse, AgentState
-from ..hooks import BaseAgentRunHooks
-from ..tool_executor import BaseFunctionToolExecutor
-from ..run_context import ContextWrapper, TContext
-from ..response import AgentResponseData
-from astrbot.core.provider.provider import Provider
+
+from mcp.types import (
+    BlobResourceContents,
+    CallToolResult,
+    EmbeddedResource,
+    ImageContent,
+    TextContent,
+    TextResourceContents,
+)
+
+from astrbot import logger
+from astrbot.core.agent.message import TextPart, ThinkPart
+from astrbot.core.agent.tool import ToolSet
+from astrbot.core.message.components import Json
 from astrbot.core.message.message_event_result import (
     MessageChain,
 )
 from astrbot.core.provider.entities import (
-    ProviderRequest,
     LLMResponse,
-    ToolCallMessageSegment,
-    AssistantMessageSegment,
+    ProviderRequest,
     ToolCallsResult,
 )
-from mcp.types import (
-    TextContent,
-    ImageContent,
-    EmbeddedResource,
-    TextResourceContents,
-    BlobResourceContents,
-    CallToolResult,
-)
-from astrbot import logger
+from astrbot.core.provider.provider import Provider
+
+from ..context.compressor import ContextCompressor
+from ..context.config import ContextConfig
+from ..context.manager import ContextManager
+from ..context.token_counter import TokenCounter
+from ..hooks import BaseAgentRunHooks
+from ..message import AssistantMessageSegment, Message, ToolCallMessageSegment
+from ..response import AgentResponseData, AgentStats
+from ..run_context import ContextWrapper, TContext
+from ..tool_executor import BaseFunctionToolExecutor
+from .base import AgentResponse, AgentState, BaseAgentRunner
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -42,10 +53,48 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         run_context: ContextWrapper[TContext],
         tool_executor: BaseFunctionToolExecutor[TContext],
         agent_hooks: BaseAgentRunHooks[TContext],
+        streaming: bool = False,
+        # enforce max turns, will discard older turns when exceeded BEFORE compression
+        # -1 means no limit
+        enforce_max_turns: int = -1,
+        # llm compressor
+        llm_compress_instruction: str | None = None,
+        llm_compress_keep_recent: int = 0,
+        llm_compress_provider: Provider | None = None,
+        # truncate by turns compressor
+        truncate_turns: int = 1,
+        # customize
+        custom_token_counter: TokenCounter | None = None,
+        custom_compressor: ContextCompressor | None = None,
+        tool_schema_mode: str | None = "full",
         **kwargs: T.Any,
     ) -> None:
         self.req = request
-        self.streaming = kwargs.get("streaming", False)
+        self.streaming = streaming
+        self.enforce_max_turns = enforce_max_turns
+        self.llm_compress_instruction = llm_compress_instruction
+        self.llm_compress_keep_recent = llm_compress_keep_recent
+        self.llm_compress_provider = llm_compress_provider
+        self.truncate_turns = truncate_turns
+        self.custom_token_counter = custom_token_counter
+        self.custom_compressor = custom_compressor
+        # we will do compress when:
+        # 1. before requesting LLM
+        # TODO: 2. after LLM output a tool call
+        self.context_config = ContextConfig(
+            # <=0 will never do compress
+            max_context_tokens=provider.provider_config.get("max_context_tokens", 0),
+            # enforce max turns before compression
+            enforce_max_turns=self.enforce_max_turns,
+            truncate_turns=self.truncate_turns,
+            llm_compress_instruction=self.llm_compress_instruction,
+            llm_compress_keep_recent=self.llm_compress_keep_recent,
+            llm_compress_provider=self.llm_compress_provider,
+            custom_token_counter=self.custom_token_counter,
+            custom_compressor=self.custom_compressor,
+        )
+        self.context_manager = ContextManager(self.context_config)
+
         self.provider = provider
         self.final_llm_resp = None
         self._state = AgentState.IDLE
@@ -53,25 +102,63 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         self.agent_hooks = agent_hooks
         self.run_context = run_context
 
-    def _transition_state(self, new_state: AgentState) -> None:
-        """转换 Agent 状态"""
-        if self._state != new_state:
-            logger.debug(f"Agent state transition: {self._state} -> {new_state}")
-            self._state = new_state
+        # These two are used for tool schema mode handling
+        # We now have two modes:
+        # - "full": use full tool schema for LLM calls, default.
+        # - "skills_like": use light tool schema for LLM calls, and re-query with param-only schema when needed.
+        #   Light tool schema does not include tool parameters.
+        #   This can reduce token usage when tools have large descriptions.
+        # See #4681
+        self.tool_schema_mode = tool_schema_mode
+        self._tool_schema_param_set = None
+        self._skill_like_raw_tool_set = None
+        if tool_schema_mode == "skills_like":
+            tool_set = self.req.func_tool
+            if not tool_set:
+                return
+            self._skill_like_raw_tool_set = tool_set
+            light_set = tool_set.get_light_tool_set()
+            self._tool_schema_param_set = tool_set.get_param_only_tool_set()
+            # MODIFIE the req.func_tool to use light tool schemas
+            self.req.func_tool = light_set
+
+        messages = []
+        # append existing messages in the run context
+        for msg in request.contexts:
+            messages.append(Message.model_validate(msg))
+        if request.prompt is not None:
+            m = await request.assemble_context()
+            messages.append(Message.model_validate(m))
+        if request.system_prompt:
+            messages.insert(
+                0,
+                Message(role="system", content=request.system_prompt),
+            )
+        self.run_context.messages = messages
+
+        self.stats = AgentStats()
+        self.stats.start_time = time.time()
 
     async def _iter_llm_responses(self) -> T.AsyncGenerator[LLMResponse, None]:
         """Yields chunks *and* a final LLMResponse."""
+        payload = {
+            "contexts": self.run_context.messages,  # list[Message]
+            "func_tool": self.req.func_tool,
+            "model": self.req.model,  # NOTE: in fact, this arg is None in most cases
+            "session_id": self.req.session_id,
+            "extra_user_content_parts": self.req.extra_user_content_parts,  # list[ContentPart]
+        }
+
         if self.streaming:
-            stream = self.provider.text_chat_stream(**self.req.__dict__)
+            stream = self.provider.text_chat_stream(**payload)
             async for resp in stream:  # type: ignore
                 yield resp
         else:
-            yield await self.provider.text_chat(**self.req.__dict__)
+            yield await self.provider.text_chat(**payload)
 
     @override
     async def step(self):
-        """
-        Process a single step of the agent.
+        """Process a single step of the agent.
         This method should return the result of the step.
         """
         if not self.req:
@@ -87,23 +174,47 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         self._transition_state(AgentState.RUNNING)
         llm_resp_result = None
 
+        # do truncate and compress
+        token_usage = self.req.conversation.token_usage if self.req.conversation else 0
+        self.run_context.messages = await self.context_manager.process(
+            self.run_context.messages, trusted_token_usage=token_usage
+        )
+
         async for llm_response in self._iter_llm_responses():
-            assert isinstance(llm_response, LLMResponse)
             if llm_response.is_chunk:
+                # update ttft
+                if self.stats.time_to_first_token == 0:
+                    self.stats.time_to_first_token = time.time() - self.stats.start_time
+
                 if llm_response.result_chain:
                     yield AgentResponse(
                         type="streaming_delta",
                         data=AgentResponseData(chain=llm_response.result_chain),
                     )
-                else:
+                elif llm_response.completion_text:
                     yield AgentResponse(
                         type="streaming_delta",
                         data=AgentResponseData(
-                            chain=MessageChain().message(llm_response.completion_text)
+                            chain=MessageChain().message(llm_response.completion_text),
+                        ),
+                    )
+                elif llm_response.reasoning_content:
+                    yield AgentResponse(
+                        type="streaming_delta",
+                        data=AgentResponseData(
+                            chain=MessageChain(type="reasoning").message(
+                                llm_response.reasoning_content,
+                            ),
                         ),
                     )
                 continue
             llm_resp_result = llm_response
+
+            if not llm_response.is_chunk and llm_response.usage:
+                # only count the token usage of the final response for computation purpose
+                self.stats.token_usage += llm_response.usage
+                if self.req.conversation:
+                    self.req.conversation.token_usage = llm_response.usage.total
             break  # got final response
 
         if not llm_resp_result:
@@ -115,13 +226,14 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
         if llm_resp.role == "err":
             # 如果 LLM 响应错误，转换到错误状态
             self.final_llm_resp = llm_resp
+            self.stats.end_time = time.time()
             self._transition_state(AgentState.ERROR)
             yield AgentResponse(
                 type="err",
                 data=AgentResponseData(
                     chain=MessageChain().message(
-                        f"LLM 响应错误: {llm_resp.completion_text or '未知错误'}"
-                    )
+                        f"LLM 响应错误: {llm_resp.completion_text or '未知错误'}",
+                    ),
                 ),
             )
 
@@ -129,6 +241,22 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
             # 如果没有工具调用，转换到完成状态
             self.final_llm_resp = llm_resp
             self._transition_state(AgentState.DONE)
+            self.stats.end_time = time.time()
+
+            # record the final assistant message
+            parts = []
+            if llm_resp.reasoning_content or llm_resp.reasoning_signature:
+                parts.append(
+                    ThinkPart(
+                        think=llm_resp.reasoning_content,
+                        encrypted=llm_resp.reasoning_signature,
+                    )
+                )
+            if llm_resp.completion_text:
+                parts.append(TextPart(text=llm_resp.completion_text))
+            self.run_context.messages.append(Message(role="assistant", content=parts))
+
+            # call the on_agent_done hook
             try:
                 await self.agent_hooks.on_agent_done(self.run_context, llm_resp)
             except Exception as e:
@@ -144,39 +272,86 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
             yield AgentResponse(
                 type="llm_result",
                 data=AgentResponseData(
-                    chain=MessageChain().message(llm_resp.completion_text)
+                    chain=MessageChain().message(llm_resp.completion_text),
                 ),
             )
 
         # 如果有工具调用，还需处理工具调用
         if llm_resp.tools_call_name:
+            if self.tool_schema_mode == "skills_like":
+                llm_resp, _ = await self._resolve_tool_exec(llm_resp)
+
             tool_call_result_blocks = []
-            for tool_call_name in llm_resp.tools_call_name:
-                yield AgentResponse(
-                    type="tool_call",
-                    data=AgentResponseData(
-                        chain=MessageChain().message(f"🔨 调用工具: {tool_call_name}")
-                    ),
-                )
             async for result in self._handle_function_tools(self.req, llm_resp):
                 if isinstance(result, list):
                     tool_call_result_blocks = result
                 elif isinstance(result, MessageChain):
+                    if result.type is None:
+                        # should not happen
+                        continue
+                    if result.type == "tool_direct_result":
+                        ar_type = "tool_call_result"
+                    else:
+                        ar_type = result.type
                     yield AgentResponse(
-                        type="tool_call_result",
+                        type=ar_type,
                         data=AgentResponseData(chain=result),
                     )
+
             # 将结果添加到上下文中
+            parts = []
+            if llm_resp.reasoning_content or llm_resp.reasoning_signature:
+                parts.append(
+                    ThinkPart(
+                        think=llm_resp.reasoning_content,
+                        encrypted=llm_resp.reasoning_signature,
+                    )
+                )
+            if llm_resp.completion_text:
+                parts.append(TextPart(text=llm_resp.completion_text))
             tool_calls_result = ToolCallsResult(
                 tool_calls_info=AssistantMessageSegment(
-                    role="assistant",
-                    tool_calls=llm_resp.to_openai_tool_calls(),
-                    content=llm_resp.completion_text,
+                    tool_calls=llm_resp.to_openai_to_calls_model(),
+                    content=parts,
                 ),
                 tool_calls_result=tool_call_result_blocks,
             )
+            # record the assistant message with tool calls
+            self.run_context.messages.extend(
+                tool_calls_result.to_openai_messages_model()
+            )
+
             self.req.append_tool_calls_result(tool_calls_result)
 
+    async def step_until_done(
+        self, max_step: int
+    ) -> T.AsyncGenerator[AgentResponse, None]:
+        """Process steps until the agent is done."""
+        step_count = 0
+        while not self.done() and step_count < max_step:
+            step_count += 1
+            async for resp in self.step():
+                yield resp
+
+        #  如果循环结束了但是 agent 还没有完成，说明是达到了 max_step
+        if not self.done():
+            logger.warning(
+                f"Agent reached max steps ({max_step}), forcing a final response."
+            )
+            # 拔掉所有工具
+            if self.req:
+                self.req.func_tool = None
+            # 注入提示词
+            self.run_context.messages.append(
+                Message(
+                    role="user",
+                    content="工具调用次数已达到上限，请停止使用工具，并根据已经收集到的信息，对你的任务和发现进行总结，然后直接回复用户。",
+                )
+            )
+            # 再执行最后一步
+            async for resp in self.step():
+                yield resp
+
     async def _handle_function_tools(
         self,
         req: ProviderRequest,
@@ -192,15 +367,79 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
             llm_response.tools_call_args,
             llm_response.tools_call_ids,
         ):
+            yield MessageChain(
+                type="tool_call",
+                chain=[
+                    Json(
+                        data={
+                            "id": func_tool_id,
+                            "name": func_tool_name,
+                            "args": func_tool_args,
+                            "ts": time.time(),
+                        }
+                    )
+                ],
+            )
             try:
                 if not req.func_tool:
                     return
-                func_tool = req.func_tool.get_func(func_tool_name)
+
+                if (
+                    self.tool_schema_mode == "skills_like"
+                    and self._skill_like_raw_tool_set
+                ):
+                    # in 'skills_like' mode, raw.func_tool is light schema, does not have handler
+                    # so we need to get the tool from the raw tool set
+                    func_tool = self._skill_like_raw_tool_set.get_tool(func_tool_name)
+                else:
+                    func_tool = req.func_tool.get_tool(func_tool_name)
+
                 logger.info(f"使用工具：{func_tool_name}，参数：{func_tool_args}")
 
+                if not func_tool:
+                    logger.warning(f"未找到指定的工具: {func_tool_name}，将跳过。")
+                    tool_call_result_blocks.append(
+                        ToolCallMessageSegment(
+                            role="tool",
+                            tool_call_id=func_tool_id,
+                            content=f"error: Tool {func_tool_name} not found.",
+                        ),
+                    )
+                    continue
+
+                valid_params = {}  # 参数过滤：只传递函数实际需要的参数
+
+                # 获取实际的 handler 函数
+                if func_tool.handler:
+                    logger.debug(
+                        f"工具 {func_tool_name} 期望的参数: {func_tool.parameters}",
+                    )
+                    if func_tool.parameters and func_tool.parameters.get("properties"):
+                        expected_params = set(func_tool.parameters["properties"].keys())
+
+                        valid_params = {
+                            k: v
+                            for k, v in func_tool_args.items()
+                            if k in expected_params
+                        }
+
+                    # 记录被忽略的参数
+                    ignored_params = set(func_tool_args.keys()) - set(
+                        valid_params.keys(),
+                    )
+                    if ignored_params:
+                        logger.warning(
+                            f"工具 {func_tool_name} 忽略非期望参数: {ignored_params}",
+                        )
+                else:
+                    # 如果没有 handler（如 MCP 工具），使用所有参数
+                    valid_params = func_tool_args
+
                 try:
                     await self.agent_hooks.on_tool_start(
-                        self.run_context, func_tool, func_tool_args
+                        self.run_context,
+                        func_tool,
+                        valid_params,
                     )
                 except Exception as e:
                     logger.error(f"Error in on_tool_start hook: {e}", exc_info=True)
@@ -208,30 +447,32 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
                 executor = self.tool_executor.execute(
                     tool=func_tool,
                     run_context=self.run_context,
-                    **func_tool_args,
+                    **valid_params,  # 只传递有效的参数
                 )
-                async for resp in executor:
+
+                _final_resp: CallToolResult | None = None
+                async for resp in executor:  # type: ignore
                     if isinstance(resp, CallToolResult):
                         res = resp
+                        _final_resp = resp
                         if isinstance(res.content[0], TextContent):
                             tool_call_result_blocks.append(
                                 ToolCallMessageSegment(
                                     role="tool",
                                     tool_call_id=func_tool_id,
                                     content=res.content[0].text,
-                                )
+                                ),
                             )
-                            yield MessageChain().message(res.content[0].text)
                         elif isinstance(res.content[0], ImageContent):
                             tool_call_result_blocks.append(
                                 ToolCallMessageSegment(
                                     role="tool",
                                     tool_call_id=func_tool_id,
-                                    content="返回了图片(已直接发送给用户)",
-                                )
+                                    content="The tool has successfully returned an image and sent directly to the user. You can describe it in your next response.",
+                                ),
                             )
                             yield MessageChain(type="tool_direct_result").base64_image(
-                                res.content[0].data
+                                res.content[0].data,
                             )
                         elif isinstance(res.content[0], EmbeddedResource):
                             resource = res.content[0].resource
@@ -241,9 +482,8 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
                                         role="tool",
                                         tool_call_id=func_tool_id,
                                         content=resource.text,
-                                    )
+                                    ),
                                 )
-                                yield MessageChain().message(resource.text)
                             elif (
                                 isinstance(resource, BlobResourceContents)
                                 and resource.mimeType
@@ -253,79 +493,155 @@ class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
                                     ToolCallMessageSegment(
                                         role="tool",
                                         tool_call_id=func_tool_id,
-                                        content="返回了图片(已直接发送给用户)",
-                                    )
+                                        content="The tool has successfully returned an image and sent directly to the user. You can describe it in your next response.",
+                                    ),
                                 )
                                 yield MessageChain(
-                                    type="tool_direct_result"
-                                ).base64_image(res.content[0].data)
+                                    type="tool_direct_result",
+                                ).base64_image(resource.blob)
                             else:
                                 tool_call_result_blocks.append(
                                     ToolCallMessageSegment(
                                         role="tool",
                                         tool_call_id=func_tool_id,
-                                        content="返回的数据类型不受支持",
-                                    )
+                                        content="The tool has returned a data type that is not supported.",
+                                    ),
                                 )
-                                yield MessageChain().message("返回的数据类型不受支持。")
 
-                            try:
-                                await self.agent_hooks.on_tool_end(
-                                    self.run_context,
-                                    func_tool_name,
-                                    func_tool_args,
-                                    resp,
-                                )
-                            except Exception as e:
-                                logger.error(
-                                    f"Error in on_tool_end hook: {e}", exc_info=True
-                                )
                     elif resp is None:
                         # Tool 直接请求发送消息给用户
-                        # 这里我们将直接结束 Agent Loop。
-                        self._transition_state(AgentState.DONE)
-                        if res := self.run_context.event.get_result():
-                            if res.chain:
-                                yield MessageChain(
-                                    chain=res.chain, type="tool_direct_result"
-                                )
-                        try:
-                            await self.agent_hooks.on_tool_end(
-                                self.run_context, func_tool_name, func_tool_args, None
-                            )
-                        except Exception as e:
-                            logger.error(
-                                f"Error in on_tool_end hook: {e}", exc_info=True
-                            )
-                    else:
+                        # 这里我们将直接结束 Agent Loop
+                        # 发送消息逻辑在 ToolExecutor 中处理了
                         logger.warning(
-                            f"Tool 返回了不支持的类型: {type(resp)}，将忽略。"
+                            f"{func_tool_name} 没有返回值，或者已将结果直接发送给用户。"
+                        )
+                        self._transition_state(AgentState.DONE)
+                        self.stats.end_time = time.time()
+                        tool_call_result_blocks.append(
+                            ToolCallMessageSegment(
+                                role="tool",
+                                tool_call_id=func_tool_id,
+                                content="The tool has no return value, or has sent the result directly to the user.",
+                            ),
+                        )
+                    else:
+                        # 不应该出现其他类型
+                        logger.warning(
+                            f"Tool 返回了不支持的类型: {type(resp)}。",
+                        )
+                        tool_call_result_blocks.append(
+                            ToolCallMessageSegment(
+                                role="tool",
+                                tool_call_id=func_tool_id,
+                                content="*The tool has returned an unsupported type. Please tell the user to check the definition and implementation of this tool.*",
+                            ),
                         )
 
-                        try:
-                            await self.agent_hooks.on_tool_end(
-                                self.run_context, func_tool_name, func_tool_args, None
-                            )
-                        except Exception as e:
-                            logger.error(
-                                f"Error in on_tool_end hook: {e}", exc_info=True
-                            )
-
-                self.run_context.event.clear_result()
+                try:
+                    await self.agent_hooks.on_tool_end(
+                        self.run_context,
+                        func_tool,
+                        func_tool_args,
+                        _final_resp,
+                    )
+                except Exception as e:
+                    logger.error(f"Error in on_tool_end hook: {e}", exc_info=True)
             except Exception as e:
                 logger.warning(traceback.format_exc())
                 tool_call_result_blocks.append(
                     ToolCallMessageSegment(
                         role="tool",
                         tool_call_id=func_tool_id,
-                        content=f"error: {str(e)}",
-                    )
+                        content=f"error: {e!s}",
+                    ),
                 )
 
+        # yield the last tool call result
+        if tool_call_result_blocks:
+            last_tcr_content = str(tool_call_result_blocks[-1].content)
+            yield MessageChain(
+                type="tool_call_result",
+                chain=[
+                    Json(
+                        data={
+                            "id": func_tool_id,
+                            "ts": time.time(),
+                            "result": last_tcr_content,
+                        }
+                    )
+                ],
+            )
+            logger.info(f"Tool `{func_tool_name}` Result: {last_tcr_content}")
+
         # 处理函数调用响应
         if tool_call_result_blocks:
             yield tool_call_result_blocks
 
+    def _build_tool_requery_context(
+        self, tool_names: list[str]
+    ) -> list[dict[str, T.Any]]:
+        """Build contexts for re-querying LLM with param-only tool schemas."""
+        contexts: list[dict[str, T.Any]] = []
+        for msg in self.run_context.messages:
+            if hasattr(msg, "model_dump"):
+                contexts.append(msg.model_dump())  # type: ignore[call-arg]
+            elif isinstance(msg, dict):
+                contexts.append(copy.deepcopy(msg))
+        instruction = (
+            "You have decided to call tool(s): "
+            + ", ".join(tool_names)
+            + ". Now call the tool(s) with required arguments using the tool schema, "
+            "and follow the existing tool-use rules."
+        )
+        if contexts and contexts[0].get("role") == "system":
+            content = contexts[0].get("content") or ""
+            contexts[0]["content"] = f"{content}\n{instruction}"
+        else:
+            contexts.insert(0, {"role": "system", "content": instruction})
+        return contexts
+
+    def _build_tool_subset(self, tool_set: ToolSet, tool_names: list[str]) -> ToolSet:
+        """Build a subset of tools from the given tool set based on tool names."""
+        subset = ToolSet()
+        for name in tool_names:
+            tool = tool_set.get_tool(name)
+            if tool:
+                subset.add_tool(tool)
+        return subset
+
+    async def _resolve_tool_exec(
+        self,
+        llm_resp: LLMResponse,
+    ) -> tuple[LLMResponse, ToolSet | None]:
+        """Used in 'skills_like' tool schema mode to re-query LLM with param-only tool schemas."""
+        tool_names = llm_resp.tools_call_name
+        if not tool_names:
+            return llm_resp, self.req.func_tool
+        full_tool_set = self.req.func_tool
+        if not isinstance(full_tool_set, ToolSet):
+            return llm_resp, self.req.func_tool
+
+        subset = self._build_tool_subset(full_tool_set, tool_names)
+        if not subset.tools:
+            return llm_resp, full_tool_set
+
+        if isinstance(self._tool_schema_param_set, ToolSet):
+            param_subset = self._build_tool_subset(
+                self._tool_schema_param_set, tool_names
+            )
+            if param_subset.tools and tool_names:
+                contexts = self._build_tool_requery_context(tool_names)
+                requery_resp = await self.provider.text_chat(
+                    contexts=contexts,
+                    func_tool=param_subset,
+                    model=self.req.model,
+                    session_id=self.req.session_id,
+                )
+                if requery_resp:
+                    llm_resp = requery_resp
+
+        return llm_resp, subset
+
     def done(self) -> bool:
         """检查 Agent 是否已完成工作"""
         return self._state in (AgentState.DONE, AgentState.ERROR)

astrbot/core/agent/tool.py

@@ -1,58 +1,88 @@
-from dataclasses import dataclass
+import copy
+from collections.abc import AsyncGenerator, Awaitable, Callable
+from typing import Any, Generic
+
+import jsonschema
+import mcp
 from deprecated import deprecated
-from typing import Awaitable, Literal, Any, Optional
-from .mcp_client import MCPClient
+from pydantic import Field, model_validator
+from pydantic.dataclasses import dataclass
+
+from astrbot.core.message.message_event_result import MessageEventResult
+
+from .run_context import ContextWrapper, TContext
+
+ParametersType = dict[str, Any]
+ToolExecResult = str | mcp.types.CallToolResult
 
 
 @dataclass
-class FunctionTool:
-    """A class representing a function tool that can be used in function calling."""
+class ToolSchema:
+    """A class representing the schema of a tool for function calling."""
+
+    name: str
+    """The name of the tool."""
+
+    description: str
+    """The description of the tool."""
+
+    parameters: ParametersType
+    """The parameters of the tool, in JSON Schema format."""
+
+    @model_validator(mode="after")
+    def validate_parameters(self) -> "ToolSchema":
+        jsonschema.validate(
+            self.parameters, jsonschema.Draft202012Validator.META_SCHEMA
+        )
+        return self
+
+
+@dataclass
+class FunctionTool(ToolSchema, Generic[TContext]):
+    """A callable tool, for function calling."""
+
+    handler: (
+        Callable[..., Awaitable[str | None] | AsyncGenerator[MessageEventResult, None]]
+        | None
+    ) = None
+    """a callable that implements the tool's functionality. It should be an async function."""
 
-    name: str | None = None
-    parameters: dict | None = None
-    description: str | None = None
-    handler: Awaitable | None = None
-    """处理函数, 当 origin 为 mcp 时，这个为空"""
     handler_module_path: str | None = None
-    """处理函数的模块路径，当 origin 为 mcp 时，这个为空
-
-    必须要保留这个字段, handler 在初始化会被 functools.partial 包装，导致 handler 的 __module__ 为 functools
+    """
+    The module path of the handler function. This is empty when the origin is mcp.
+    This field must be retained, as the handler will be wrapped in functools.partial during initialization,
+    causing the handler's __module__ to be functools
     """
     active: bool = True
-    """是否激活"""
-
-    origin: Literal["local", "mcp"] = "local"
-    """函数工具的来源, local 为本地函数工具, mcp 为 MCP 服务"""
-
-    # MCP 相关字段
-    mcp_server_name: str | None = None
-    """MCP 服务名称，当 origin 为 mcp 时有效"""
-    mcp_client: MCPClient | None = None
-    """MCP 客户端，当 origin 为 mcp 时有效"""
+    """
+    Whether the tool is active. This field is a special field for AstrBot.
+    You can ignore it when integrating with other frameworks.
+    """
+    is_background_task: bool = False
+    """
+    Declare this tool as a background task. Background tasks return immediately
+    with a task identifier while the real work continues asynchronously.
+    """
 
     def __repr__(self):
-        return f"FuncTool(name={self.name}, parameters={self.parameters}, description={self.description}, active={self.active}, origin={self.origin})"
+        return f"FuncTool(name={self.name}, parameters={self.parameters}, description={self.description})"
 
-    def __dict__(self) -> dict[str, Any]:
-        """将 FunctionTool 转换为字典格式"""
-        return {
-            "name": self.name,
-            "parameters": self.parameters,
-            "description": self.description,
-            "active": self.active,
-            "origin": self.origin,
-            "mcp_server_name": self.mcp_server_name,
-        }
+    async def call(self, context: ContextWrapper[TContext], **kwargs) -> ToolExecResult:
+        """Run the tool with the given arguments. The handler field has priority."""
+        raise NotImplementedError(
+            "FunctionTool.call() must be implemented by subclasses or set a handler."
+        )
 
 
+@dataclass
 class ToolSet:
     """A set of function tools that can be used in function calling.
 
     This class provides methods to add, remove, and retrieve tools, as well as
-    convert the tools to different API formats (OpenAI, Anthropic, Google GenAI)."""
+    convert the tools to different API formats (OpenAI, Anthropic, Google GenAI).
+    """
 
-    def __init__(self, tools: list[FunctionTool] = None):
-        self.tools: list[FunctionTool] = tools or []
+    tools: list[FunctionTool] = Field(default_factory=list)
 
     def empty(self) -> bool:
         """Check if the tool set is empty."""
@@ -71,15 +101,62 @@ class ToolSet:
         """Remove a tool by its name."""
         self.tools = [tool for tool in self.tools if tool.name != name]
 
-    def get_tool(self, name: str) -> Optional[FunctionTool]:
+    def get_tool(self, name: str) -> FunctionTool | None:
         """Get a tool by its name."""
         for tool in self.tools:
             if tool.name == name:
                 return tool
         return None
 
+    def get_light_tool_set(self) -> "ToolSet":
+        """Return a light tool set with only name/description."""
+        light_tools = []
+        for tool in self.tools:
+            if hasattr(tool, "active") and not tool.active:
+                continue
+            light_params = {
+                "type": "object",
+                "properties": {},
+            }
+            light_tools.append(
+                FunctionTool(
+                    name=tool.name,
+                    parameters=light_params,
+                    description=tool.description,
+                    handler=None,
+                )
+            )
+        return ToolSet(light_tools)
+
+    def get_param_only_tool_set(self) -> "ToolSet":
+        """Return a tool set with name/parameters only (no description)."""
+        param_tools = []
+        for tool in self.tools:
+            if hasattr(tool, "active") and not tool.active:
+                continue
+            params = (
+                copy.deepcopy(tool.parameters)
+                if tool.parameters
+                else {"type": "object", "properties": {}}
+            )
+            param_tools.append(
+                FunctionTool(
+                    name=tool.name,
+                    parameters=params,
+                    description="",
+                    handler=None,
+                )
+            )
+        return ToolSet(param_tools)
+
     @deprecated(reason="Use add_tool() instead", version="4.0.0")
-    def add_func(self, name: str, func_args: list, desc: str, handler: Awaitable):
+    def add_func(
+        self,
+        name: str,
+        func_args: list,
+        desc: str,
+        handler: Callable[..., Awaitable[Any]],
+    ):
         """Add a function tool to the set."""
         params = {
             "type": "object",  # hard-coded here
@@ -104,7 +181,7 @@ class ToolSet:
         self.remove_tool(name)
 
     @deprecated(reason="Use get_tool() instead", version="4.0.0")
-    def get_func(self, name: str) -> list[FunctionTool]:
+    def get_func(self, name: str) -> FunctionTool | None:
         """Get all function tools."""
         return self.get_tool(name)
 
@@ -117,16 +194,15 @@ class ToolSet:
         """Convert tools to OpenAI API function calling schema format."""
         result = []
         for tool in self.tools:
-            func_def = {
-                "type": "function",
-                "function": {
-                    "name": tool.name,
-                    "description": tool.description,
-                },
-            }
+            func_def = {"type": "function", "function": {"name": tool.name}}
+            if tool.description:
+                func_def["function"]["description"] = tool.description
 
-            if tool.parameters.get("properties") or not omit_empty_parameter_field:
-                func_def["function"]["parameters"] = tool.parameters
+            if tool.parameters is not None:
+                if (
+                    tool.parameters and tool.parameters.get("properties")
+                ) or not omit_empty_parameter_field:
+                    func_def["function"]["parameters"] = tool.parameters
 
             result.append(func_def)
         return result
@@ -135,15 +211,13 @@ class ToolSet:
         """Convert tools to Anthropic API format."""
         result = []
         for tool in self.tools:
-            tool_def = {
-                "name": tool.name,
-                "description": tool.description,
-                "input_schema": {
-                    "type": "object",
-                    "properties": tool.parameters.get("properties", {}),
-                    "required": tool.parameters.get("required", []),
-                },
-            }
+            input_schema = {"type": "object"}
+            if tool.parameters:
+                input_schema["properties"] = tool.parameters.get("properties", {})
+                input_schema["required"] = tool.parameters.get("required", [])
+            tool_def = {"name": tool.name, "input_schema": input_schema}
+            if tool.description:
+                tool_def["description"] = tool.description
             result.append(tool_def)
         return result
 
@@ -175,7 +249,8 @@ class ToolSet:
             if "type" in schema and schema["type"] in supported_types:
                 result["type"] = schema["type"]
                 if "format" in schema and schema["format"] in supported_formats.get(
-                    result["type"], set()
+                    result["type"],
+                    set(),
                 ):
                     result["format"] = schema["format"]
             else:
@@ -210,14 +285,14 @@ class ToolSet:
 
             return result
 
-        tools = [
-            {
-                "name": tool.name,
-                "description": tool.description,
-                "parameters": convert_schema(tool.parameters),
-            }
-            for tool in self.tools
-        ]
+        tools = []
+        for tool in self.tools:
+            d: dict[str, Any] = {"name": tool.name}
+            if tool.description:
+                d["description"] = tool.description
+            if tool.parameters:
+                d["parameters"] = convert_schema(tool.parameters)
+            tools.append(d)
 
         declarations = {}
         if tools:
@@ -240,6 +315,11 @@ class ToolSet:
         """获取所有工具的名称列表"""
         return [tool.name for tool in self.tools]
 
+    def merge(self, other: "ToolSet"):
+        """Merge another ToolSet into this one."""
+        for tool in other.tools:
+            self.add_tool(tool)
+
     def __len__(self):
         return len(self.tools)
 

astrbot/core/agent/tool_executor.py

@@ -1,11 +1,17 @@
+from collections.abc import AsyncGenerator
+from typing import Any, Generic
+
 import mcp
-from typing import Any, Generic, AsyncGenerator
-from .run_context import TContext, ContextWrapper
+
+from .run_context import ContextWrapper, TContext
 from .tool import FunctionTool
 
 
 class BaseFunctionToolExecutor(Generic[TContext]):
     @classmethod
     async def execute(
-        cls, tool: FunctionTool, run_context: ContextWrapper[TContext], **tool_args
+        cls,
+        tool: FunctionTool,
+        run_context: ContextWrapper[TContext],
+        **tool_args,
     ) -> AsyncGenerator[Any | mcp.types.CallToolResult, None]: ...

astrbot/core/astr_agent_context.py

@@ -1,11 +1,21 @@
-from dataclasses import dataclass
-from astrbot.core.provider import Provider
-from astrbot.core.provider.entities import ProviderRequest
+from pydantic import Field
+from pydantic.dataclasses import dataclass
+
+from astrbot.core.agent.run_context import ContextWrapper
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core.star.context import Context
 
 
 @dataclass
 class AstrAgentContext:
-    provider: Provider
-    first_provider_request: ProviderRequest
-    curr_provider_request: ProviderRequest
-    streaming: bool
+    __pydantic_config__ = {"arbitrary_types_allowed": True}
+
+    context: Context
+    """The star context instance"""
+    event: AstrMessageEvent
+    """The message event associated with the agent context."""
+    extra: dict[str, str] = Field(default_factory=dict)
+    """Customized extra data."""
+
+
+AgentContextWrapper = ContextWrapper[AstrAgentContext]

astrbot/core/astr_agent_hooks.py

@@ -0,0 +1,88 @@
+from typing import Any
+
+from mcp.types import CallToolResult
+
+from astrbot.core.agent.hooks import BaseAgentRunHooks
+from astrbot.core.agent.message import Message
+from astrbot.core.agent.run_context import ContextWrapper
+from astrbot.core.agent.tool import FunctionTool
+from astrbot.core.astr_agent_context import AstrAgentContext
+from astrbot.core.pipeline.context_utils import call_event_hook
+from astrbot.core.star.star_handler import EventType
+
+
+class MainAgentHooks(BaseAgentRunHooks[AstrAgentContext]):
+    async def on_agent_done(self, run_context, llm_response):
+        # 执行事件钩子
+        if llm_response and llm_response.reasoning_content:
+            # we will use this in result_decorate stage to inject reasoning content to chain
+            run_context.context.event.set_extra(
+                "_llm_reasoning_content", llm_response.reasoning_content
+            )
+
+        await call_event_hook(
+            run_context.context.event,
+            EventType.OnLLMResponseEvent,
+            llm_response,
+        )
+
+    async def on_tool_start(
+        self,
+        run_context: ContextWrapper[AstrAgentContext],
+        tool: FunctionTool[Any],
+        tool_args: dict | None,
+    ):
+        await call_event_hook(
+            run_context.context.event,
+            EventType.OnUsingLLMToolEvent,
+            tool,
+            tool_args,
+        )
+
+    async def on_tool_end(
+        self,
+        run_context: ContextWrapper[AstrAgentContext],
+        tool: FunctionTool[Any],
+        tool_args: dict | None,
+        tool_result: CallToolResult | None,
+    ):
+        run_context.context.event.clear_result()
+        await call_event_hook(
+            run_context.context.event,
+            EventType.OnLLMToolRespondEvent,
+            tool,
+            tool_args,
+            tool_result,
+        )
+
+        # special handle web_search_tavily
+        platform_name = run_context.context.event.get_platform_name()
+        if (
+            platform_name == "webchat"
+            and tool.name == "web_search_tavily"
+            and len(run_context.messages) > 0
+            and tool_result
+            and len(tool_result.content)
+        ):
+            # inject system prompt
+            first_part = run_context.messages[0]
+            if (
+                isinstance(first_part, Message)
+                and first_part.role == "system"
+                and first_part.content
+                and isinstance(first_part.content, str)
+            ):
+                # we assume system part is str
+                first_part.content += (
+                    "Always cite web search results you rely on. "
+                    "Index is a unique identifier for each search result. "
+                    "Use the exact citation format <ref>index</ref> (e.g. <ref>abcd.3</ref>) "
+                    "after the sentence that uses the information. Do not invent citations."
+                )
+
+
+class EmptyAgentHooks(BaseAgentRunHooks[AstrAgentContext]):
+    pass
+
+
+MAIN_AGENT_HOOKS = MainAgentHooks()

astrbot/core/astr_agent_run_util.py

@@ -0,0 +1,393 @@
+import asyncio
+import re
+import time
+import traceback
+from collections.abc import AsyncGenerator
+
+from astrbot.core import logger
+from astrbot.core.agent.message import Message
+from astrbot.core.agent.runners.tool_loop_agent_runner import ToolLoopAgentRunner
+from astrbot.core.astr_agent_context import AstrAgentContext
+from astrbot.core.message.components import BaseMessageComponent, Json, Plain
+from astrbot.core.message.message_event_result import (
+    MessageChain,
+    MessageEventResult,
+    ResultContentType,
+)
+from astrbot.core.provider.entities import LLMResponse
+from astrbot.core.provider.provider import TTSProvider
+
+AgentRunner = ToolLoopAgentRunner[AstrAgentContext]
+
+
+async def run_agent(
+    agent_runner: AgentRunner,
+    max_step: int = 30,
+    show_tool_use: bool = True,
+    stream_to_general: bool = False,
+    show_reasoning: bool = False,
+) -> AsyncGenerator[MessageChain | None, None]:
+    step_idx = 0
+    astr_event = agent_runner.run_context.context.event
+    while step_idx < max_step + 1:
+        step_idx += 1
+
+        if step_idx == max_step + 1:
+            logger.warning(
+                f"Agent reached max steps ({max_step}), forcing a final response."
+            )
+            if not agent_runner.done():
+                # 拔掉所有工具
+                if agent_runner.req:
+                    agent_runner.req.func_tool = None
+                # 注入提示词
+                agent_runner.run_context.messages.append(
+                    Message(
+                        role="user",
+                        content="工具调用次数已达到上限，请停止使用工具，并根据已经收集到的信息，对你的任务和发现进行总结，然后直接回复用户。",
+                    )
+                )
+
+        try:
+            async for resp in agent_runner.step():
+                if astr_event.is_stopped():
+                    return
+                if resp.type == "tool_call_result":
+                    msg_chain = resp.data["chain"]
+
+                    astr_event.trace.record(
+                        "agent_tool_result",
+                        tool_result=msg_chain.get_plain_text(
+                            with_other_comps_mark=True
+                        ),
+                    )
+
+                    if msg_chain.type == "tool_direct_result":
+                        # tool_direct_result 用于标记 llm tool 需要直接发送给用户的内容
+                        await astr_event.send(msg_chain)
+                        continue
+                    if astr_event.get_platform_id() == "webchat":
+                        await astr_event.send(msg_chain)
+                    # 对于其他情况，暂时先不处理
+                    continue
+                elif resp.type == "tool_call":
+                    if agent_runner.streaming:
+                        # 用来标记流式响应需要分节
+                        yield MessageChain(chain=[], type="break")
+
+                    tool_info = None
+
+                    if resp.data["chain"].chain:
+                        json_comp = resp.data["chain"].chain[0]
+                        if isinstance(json_comp, Json):
+                            tool_info = json_comp.data
+                        astr_event.trace.record(
+                            "agent_tool_call",
+                            tool_name=tool_info if tool_info else "unknown",
+                        )
+
+                    if astr_event.get_platform_name() == "webchat":
+                        await astr_event.send(resp.data["chain"])
+                    elif show_tool_use:
+                        if tool_info:
+                            m = f"🔨 调用工具: {tool_info.get('name', 'unknown')}"
+                        else:
+                            m = "🔨 调用工具..."
+                        chain = MessageChain(type="tool_call").message(m)
+                        await astr_event.send(chain)
+                    continue
+
+                if stream_to_general and resp.type == "streaming_delta":
+                    continue
+
+                if stream_to_general or not agent_runner.streaming:
+                    content_typ = (
+                        ResultContentType.LLM_RESULT
+                        if resp.type == "llm_result"
+                        else ResultContentType.GENERAL_RESULT
+                    )
+                    astr_event.set_result(
+                        MessageEventResult(
+                            chain=resp.data["chain"].chain,
+                            result_content_type=content_typ,
+                        ),
+                    )
+                    yield
+                    astr_event.clear_result()
+                elif resp.type == "streaming_delta":
+                    chain = resp.data["chain"]
+                    if chain.type == "reasoning" and not show_reasoning:
+                        # display the reasoning content only when configured
+                        continue
+                    yield resp.data["chain"]  # MessageChain
+            if agent_runner.done():
+                # send agent stats to webchat
+                if astr_event.get_platform_name() == "webchat":
+                    await astr_event.send(
+                        MessageChain(
+                            type="agent_stats",
+                            chain=[Json(data=agent_runner.stats.to_dict())],
+                        )
+                    )
+
+                break
+
+        except Exception as e:
+            logger.error(traceback.format_exc())
+
+            err_msg = f"\n\nAstrBot 请求失败。\n错误类型: {type(e).__name__}\n错误信息: {e!s}\n\n请在平台日志查看和分享错误详情。\n"
+
+            error_llm_response = LLMResponse(
+                role="err",
+                completion_text=err_msg,
+            )
+            try:
+                await agent_runner.agent_hooks.on_agent_done(
+                    agent_runner.run_context, error_llm_response
+                )
+            except Exception:
+                logger.exception("Error in on_agent_done hook")
+
+            if agent_runner.streaming:
+                yield MessageChain().message(err_msg)
+            else:
+                astr_event.set_result(MessageEventResult().message(err_msg))
+            return
+
+
+async def run_live_agent(
+    agent_runner: AgentRunner,
+    tts_provider: TTSProvider | None = None,
+    max_step: int = 30,
+    show_tool_use: bool = True,
+    show_reasoning: bool = False,
+) -> AsyncGenerator[MessageChain | None, None]:
+    """Live Mode 的 Agent 运行器，支持流式 TTS
+
+    Args:
+        agent_runner: Agent 运行器
+        tts_provider: TTS Provider 实例
+        max_step: 最大步数
+        show_tool_use: 是否显示工具使用
+        show_reasoning: 是否显示推理过程
+
+    Yields:
+        MessageChain: 包含文本或音频数据的消息链
+    """
+    # 如果没有 TTS Provider，直接发送文本
+    if not tts_provider:
+        async for chain in run_agent(
+            agent_runner,
+            max_step=max_step,
+            show_tool_use=show_tool_use,
+            stream_to_general=False,
+            show_reasoning=show_reasoning,
+        ):
+            yield chain
+        return
+
+    support_stream = tts_provider.support_stream()
+    if support_stream:
+        logger.info("[Live Agent] 使用流式 TTS（原生支持 get_audio_stream）")
+    else:
+        logger.info(
+            f"[Live Agent] 使用 TTS（{tts_provider.meta().type} "
+            "使用 get_audio，将按句子分块生成音频）"
+        )
+
+    # 统计数据初始化
+    tts_start_time = time.time()
+    tts_first_frame_time = 0.0
+    first_chunk_received = False
+
+    # 创建队列
+    text_queue: asyncio.Queue[str | None] = asyncio.Queue()
+    # audio_queue stored bytes or (text, bytes)
+    audio_queue: asyncio.Queue[bytes | tuple[str, bytes] | None] = asyncio.Queue()
+
+    # 1. 启动 Agent Feeder 任务：负责运行 Agent 并将文本分句喂给 text_queue
+    feeder_task = asyncio.create_task(
+        _run_agent_feeder(
+            agent_runner, text_queue, max_step, show_tool_use, show_reasoning
+        )
+    )
+
+    # 2. 启动 TTS 任务：负责从 text_queue 读取文本并生成音频到 audio_queue
+    if support_stream:
+        tts_task = asyncio.create_task(
+            _safe_tts_stream_wrapper(tts_provider, text_queue, audio_queue)
+        )
+    else:
+        tts_task = asyncio.create_task(
+            _simulated_stream_tts(tts_provider, text_queue, audio_queue)
+        )
+
+    # 3. 主循环：从 audio_queue 读取音频并 yield
+    try:
+        while True:
+            queue_item = await audio_queue.get()
+
+            if queue_item is None:
+                break
+
+            text = None
+            if isinstance(queue_item, tuple):
+                text, audio_data = queue_item
+            else:
+                audio_data = queue_item
+
+            if not first_chunk_received:
+                # 记录首帧延迟（从开始处理到收到第一个音频块）
+                tts_first_frame_time = time.time() - tts_start_time
+                first_chunk_received = True
+
+            # 将音频数据封装为 MessageChain
+            import base64
+
+            audio_b64 = base64.b64encode(audio_data).decode("utf-8")
+            comps: list[BaseMessageComponent] = [Plain(audio_b64)]
+            if text:
+                comps.append(Json(data={"text": text}))
+            chain = MessageChain(chain=comps, type="audio_chunk")
+            yield chain
+
+    except Exception as e:
+        logger.error(f"[Live Agent] 运行时发生错误: {e}", exc_info=True)
+    finally:
+        # 清理任务
+        if not feeder_task.done():
+            feeder_task.cancel()
+        if not tts_task.done():
+            tts_task.cancel()
+
+        # 确保队列被消费
+        pass
+
+    tts_end_time = time.time()
+
+    # 发送 TTS 统计信息
+    try:
+        astr_event = agent_runner.run_context.context.event
+        if astr_event.get_platform_name() == "webchat":
+            tts_duration = tts_end_time - tts_start_time
+            await astr_event.send(
+                MessageChain(
+                    type="tts_stats",
+                    chain=[
+                        Json(
+                            data={
+                                "tts_total_time": tts_duration,
+                                "tts_first_frame_time": tts_first_frame_time,
+                                "tts": tts_provider.meta().type,
+                                "chat_model": agent_runner.provider.get_model(),
+                            }
+                        )
+                    ],
+                )
+            )
+    except Exception as e:
+        logger.error(f"发送 TTS 统计信息失败: {e}")
+
+
+async def _run_agent_feeder(
+    agent_runner: AgentRunner,
+    text_queue: asyncio.Queue,
+    max_step: int,
+    show_tool_use: bool,
+    show_reasoning: bool,
+):
+    """运行 Agent 并将文本输出分句放入队列"""
+    buffer = ""
+    try:
+        async for chain in run_agent(
+            agent_runner,
+            max_step=max_step,
+            show_tool_use=show_tool_use,
+            stream_to_general=False,
+            show_reasoning=show_reasoning,
+        ):
+            if chain is None:
+                continue
+
+            # 提取文本
+            text = chain.get_plain_text()
+            if text:
+                buffer += text
+
+                # 分句逻辑：匹配标点符号
+                # r"([.。!！?？\n]+)" 会保留分隔符
+                parts = re.split(r"([.。!！?？\n]+)", buffer)
+
+                if len(parts) > 1:
+                    # 处理完整的句子
+                    # range step 2 因为 split 后是 [text, delim, text, delim, ...]
+                    temp_buffer = ""
+                    for i in range(0, len(parts) - 1, 2):
+                        sentence = parts[i]
+                        delim = parts[i + 1]
+                        full_sentence = sentence + delim
+                        temp_buffer += full_sentence
+
+                        if len(temp_buffer) >= 10:
+                            if temp_buffer.strip():
+                                logger.info(f"[Live Agent Feeder] 分句: {temp_buffer}")
+                                await text_queue.put(temp_buffer)
+                            temp_buffer = ""
+
+                    # 更新 buffer 为剩余部分
+                    buffer = temp_buffer + parts[-1]
+
+        # 处理剩余 buffer
+        if buffer.strip():
+            await text_queue.put(buffer)
+
+    except Exception as e:
+        logger.error(f"[Live Agent Feeder] Error: {e}", exc_info=True)
+    finally:
+        # 发送结束信号
+        await text_queue.put(None)
+
+
+async def _safe_tts_stream_wrapper(
+    tts_provider: TTSProvider,
+    text_queue: asyncio.Queue[str | None],
+    audio_queue: "asyncio.Queue[bytes | tuple[str, bytes] | None]",
+):
+    """包装原生流式 TTS 确保异常处理和队列关闭"""
+    try:
+        await tts_provider.get_audio_stream(text_queue, audio_queue)
+    except Exception as e:
+        logger.error(f"[Live TTS Stream] Error: {e}", exc_info=True)
+    finally:
+        await audio_queue.put(None)
+
+
+async def _simulated_stream_tts(
+    tts_provider: TTSProvider,
+    text_queue: asyncio.Queue[str | None],
+    audio_queue: "asyncio.Queue[bytes | tuple[str, bytes] | None]",
+):
+    """模拟流式 TTS 分句生成音频"""
+    try:
+        while True:
+            text = await text_queue.get()
+            if text is None:
+                break
+
+            try:
+                audio_path = await tts_provider.get_audio(text)
+
+                if audio_path:
+                    with open(audio_path, "rb") as f:
+                        audio_data = f.read()
+                    await audio_queue.put((text, audio_data))
+            except Exception as e:
+                logger.error(
+                    f"[Live TTS Simulated] Error processing text '{text[:20]}...': {e}"
+                )
+                # 继续处理下一句
+
+    except Exception as e:
+        logger.error(f"[Live TTS Simulated] Critical Error: {e}", exc_info=True)
+    finally:
+        await audio_queue.put(None)

astrbot/core/astr_agent_tool_exec.py

@@ -0,0 +1,455 @@
+import asyncio
+import inspect
+import json
+import traceback
+import typing as T
+import uuid
+
+import mcp
+
+from astrbot import logger
+from astrbot.core.agent.handoff import HandoffTool
+from astrbot.core.agent.mcp_client import MCPTool
+from astrbot.core.agent.message import Message
+from astrbot.core.agent.run_context import ContextWrapper
+from astrbot.core.agent.tool import FunctionTool, ToolSet
+from astrbot.core.agent.tool_executor import BaseFunctionToolExecutor
+from astrbot.core.astr_agent_context import AstrAgentContext
+from astrbot.core.astr_main_agent_resources import (
+    BACKGROUND_TASK_RESULT_WOKE_SYSTEM_PROMPT,
+    SEND_MESSAGE_TO_USER_TOOL,
+)
+from astrbot.core.cron.events import CronMessageEvent
+from astrbot.core.message.message_event_result import (
+    CommandResult,
+    MessageChain,
+    MessageEventResult,
+)
+from astrbot.core.platform.message_session import MessageSession
+from astrbot.core.provider.entites import ProviderRequest
+from astrbot.core.provider.register import llm_tools
+from astrbot.core.utils.history_saver import persist_agent_history
+
+
+class FunctionToolExecutor(BaseFunctionToolExecutor[AstrAgentContext]):
+    @classmethod
+    async def execute(cls, tool, run_context, **tool_args):
+        """执行函数调用。
+
+        Args:
+            event (AstrMessageEvent): 事件对象, 当 origin 为 local 时必须提供。
+            **kwargs: 函数调用的参数。
+
+        Returns:
+            AsyncGenerator[None | mcp.types.CallToolResult, None]
+
+        """
+        if isinstance(tool, HandoffTool):
+            async for r in cls._execute_handoff(tool, run_context, **tool_args):
+                yield r
+            return
+
+        elif isinstance(tool, MCPTool):
+            async for r in cls._execute_mcp(tool, run_context, **tool_args):
+                yield r
+            return
+
+        elif tool.is_background_task:
+            task_id = uuid.uuid4().hex
+
+            async def _run_in_background():
+                try:
+                    await cls._execute_background(
+                        tool=tool,
+                        run_context=run_context,
+                        task_id=task_id,
+                        **tool_args,
+                    )
+                except Exception as e:  # noqa: BLE001
+                    logger.error(
+                        f"Background task {task_id} failed: {e!s}",
+                        exc_info=True,
+                    )
+
+            asyncio.create_task(_run_in_background())
+            text_content = mcp.types.TextContent(
+                type="text",
+                text=f"Background task submitted. task_id={task_id}",
+            )
+            yield mcp.types.CallToolResult(content=[text_content])
+
+            return
+        else:
+            async for r in cls._execute_local(tool, run_context, **tool_args):
+                yield r
+            return
+
+    @classmethod
+    async def _execute_handoff(
+        cls,
+        tool: HandoffTool,
+        run_context: ContextWrapper[AstrAgentContext],
+        **tool_args,
+    ):
+        input_ = tool_args.get("input")
+
+        # make toolset for the agent
+        tools = tool.agent.tools
+        if tools:
+            toolset = ToolSet()
+            for t in tools:
+                if isinstance(t, str):
+                    _t = llm_tools.get_func(t)
+                    if _t:
+                        toolset.add_tool(_t)
+                elif isinstance(t, FunctionTool):
+                    toolset.add_tool(t)
+        else:
+            toolset = None
+
+        ctx = run_context.context.context
+        event = run_context.context.event
+        umo = event.unified_msg_origin
+
+        # Use per-subagent provider override if configured; otherwise fall back
+        # to the current/default provider resolution.
+        prov_id = getattr(
+            tool, "provider_id", None
+        ) or await ctx.get_current_chat_provider_id(umo)
+
+        # prepare begin dialogs
+        contexts = None
+        dialogs = tool.agent.begin_dialogs
+        if dialogs:
+            contexts = []
+            for dialog in dialogs:
+                try:
+                    contexts.append(
+                        dialog
+                        if isinstance(dialog, Message)
+                        else Message.model_validate(dialog)
+                    )
+                except Exception:
+                    continue
+
+        llm_resp = await ctx.tool_loop_agent(
+            event=event,
+            chat_provider_id=prov_id,
+            prompt=input_,
+            system_prompt=tool.agent.instructions,
+            tools=toolset,
+            contexts=contexts,
+            max_steps=30,
+            run_hooks=tool.agent.run_hooks,
+        )
+        yield mcp.types.CallToolResult(
+            content=[mcp.types.TextContent(type="text", text=llm_resp.completion_text)]
+        )
+
+    @classmethod
+    async def _execute_background(
+        cls,
+        tool: FunctionTool,
+        run_context: ContextWrapper[AstrAgentContext],
+        task_id: str,
+        **tool_args,
+    ):
+        from astrbot.core.astr_main_agent import (
+            MainAgentBuildConfig,
+            _get_session_conv,
+            build_main_agent,
+        )
+
+        # run the tool
+        result_text = ""
+        try:
+            async for r in cls._execute_local(
+                tool, run_context, tool_call_timeout=3600, **tool_args
+            ):
+                # collect results, currently we just collect the text results
+                if isinstance(r, mcp.types.CallToolResult):
+                    result_text = ""
+                    for content in r.content:
+                        if isinstance(content, mcp.types.TextContent):
+                            result_text += content.text + "\n"
+        except Exception as e:
+            result_text = (
+                f"error: Background task execution failed, internal error: {e!s}"
+            )
+
+        event = run_context.context.event
+        ctx = run_context.context.context
+
+        note = (
+            event.get_extra("background_note")
+            or f"Background task {tool.name} finished."
+        )
+        extras = {
+            "background_task_result": {
+                "task_id": task_id,
+                "tool_name": tool.name,
+                "result": result_text or "",
+                "tool_args": tool_args,
+            }
+        }
+        session = MessageSession.from_str(event.unified_msg_origin)
+        cron_event = CronMessageEvent(
+            context=ctx,
+            session=session,
+            message=note,
+            extras=extras,
+            message_type=session.message_type,
+        )
+        cron_event.role = event.role
+        config = MainAgentBuildConfig(tool_call_timeout=3600)
+
+        req = ProviderRequest()
+        conv = await _get_session_conv(event=cron_event, plugin_context=ctx)
+        req.conversation = conv
+        context = json.loads(conv.history)
+        if context:
+            req.contexts = context
+            context_dump = req._print_friendly_context()
+            req.contexts = []
+            req.system_prompt += (
+                "\n\nBellow is you and user previous conversation history:\n"
+                f"{context_dump}"
+            )
+
+        bg = json.dumps(extras["background_task_result"], ensure_ascii=False)
+        req.system_prompt += BACKGROUND_TASK_RESULT_WOKE_SYSTEM_PROMPT.format(
+            background_task_result=bg
+        )
+        req.prompt = (
+            "Proceed according to your system instructions. "
+            "Output using same language as previous conversation."
+            " After completing your task, summarize and output your actions and results."
+        )
+        if not req.func_tool:
+            req.func_tool = ToolSet()
+        req.func_tool.add_tool(SEND_MESSAGE_TO_USER_TOOL)
+
+        result = await build_main_agent(
+            event=cron_event, plugin_context=ctx, config=config, req=req
+        )
+        if not result:
+            logger.error("Failed to build main agent for background task job.")
+            return
+
+        runner = result.agent_runner
+        async for _ in runner.step_until_done(30):
+            # agent will send message to user via using tools
+            pass
+        llm_resp = runner.get_final_llm_resp()
+        task_meta = extras.get("background_task_result", {})
+        summary_note = (
+            f"[BackgroundTask] {task_meta.get('tool_name', tool.name)} "
+            f"(task_id={task_meta.get('task_id', task_id)}) finished. "
+            f"Result: {task_meta.get('result') or result_text or 'no content'}"
+        )
+        if llm_resp and llm_resp.completion_text:
+            summary_note += (
+                f"I finished the task, here is the result: {llm_resp.completion_text}"
+            )
+        await persist_agent_history(
+            ctx.conversation_manager,
+            event=cron_event,
+            req=req,
+            summary_note=summary_note,
+        )
+        if not llm_resp:
+            logger.warning("background task agent got no response")
+            return
+
+    @classmethod
+    async def _execute_local(
+        cls,
+        tool: FunctionTool,
+        run_context: ContextWrapper[AstrAgentContext],
+        *,
+        tool_call_timeout: int | None = None,
+        **tool_args,
+    ):
+        event = run_context.context.event
+        if not event:
+            raise ValueError("Event must be provided for local function tools.")
+
+        is_override_call = False
+        for ty in type(tool).mro():
+            if "call" in ty.__dict__ and ty.__dict__["call"] is not FunctionTool.call:
+                is_override_call = True
+                break
+
+        # 检查 tool 下有没有 run 方法
+        if not tool.handler and not hasattr(tool, "run") and not is_override_call:
+            raise ValueError("Tool must have a valid handler or override 'run' method.")
+
+        awaitable = None
+        method_name = ""
+        if tool.handler:
+            awaitable = tool.handler
+            method_name = "decorator_handler"
+        elif is_override_call:
+            awaitable = tool.call
+            method_name = "call"
+        elif hasattr(tool, "run"):
+            awaitable = getattr(tool, "run")
+            method_name = "run"
+        if awaitable is None:
+            raise ValueError("Tool must have a valid handler or override 'run' method.")
+
+        wrapper = call_local_llm_tool(
+            context=run_context,
+            handler=awaitable,
+            method_name=method_name,
+            **tool_args,
+        )
+        while True:
+            try:
+                resp = await asyncio.wait_for(
+                    anext(wrapper),
+                    timeout=tool_call_timeout or run_context.tool_call_timeout,
+                )
+                if resp is not None:
+                    if isinstance(resp, mcp.types.CallToolResult):
+                        yield resp
+                    else:
+                        text_content = mcp.types.TextContent(
+                            type="text",
+                            text=str(resp),
+                        )
+                        yield mcp.types.CallToolResult(content=[text_content])
+                else:
+                    # NOTE: Tool 在这里直接请求发送消息给用户
+                    # TODO: 是否需要判断 event.get_result() 是否为空?
+                    # 如果为空,则说明没有发送消息给用户,并且返回值为空,将返回一个特殊的 TextContent,其内容如"工具没有返回内容"
+                    if res := run_context.context.event.get_result():
+                        if res.chain:
+                            try:
+                                await event.send(
+                                    MessageChain(
+                                        chain=res.chain,
+                                        type="tool_direct_result",
+                                    )
+                                )
+                            except Exception as e:
+                                logger.error(
+                                    f"Tool 直接发送消息失败: {e}",
+                                    exc_info=True,
+                                )
+                    yield None
+            except asyncio.TimeoutError:
+                raise Exception(
+                    f"tool {tool.name} execution timeout after {tool_call_timeout or run_context.tool_call_timeout} seconds.",
+                )
+            except StopAsyncIteration:
+                break
+
+    @classmethod
+    async def _execute_mcp(
+        cls,
+        tool: FunctionTool,
+        run_context: ContextWrapper[AstrAgentContext],
+        **tool_args,
+    ):
+        res = await tool.call(run_context, **tool_args)
+        if not res:
+            return
+        yield res
+
+
+async def call_local_llm_tool(
+    context: ContextWrapper[AstrAgentContext],
+    handler: T.Callable[
+        ...,
+        T.Awaitable[MessageEventResult | mcp.types.CallToolResult | str | None]
+        | T.AsyncGenerator[MessageEventResult | CommandResult | str | None, None],
+    ],
+    method_name: str,
+    *args,
+    **kwargs,
+) -> T.AsyncGenerator[T.Any, None]:
+    """执行本地 LLM 工具的处理函数并处理其返回结果"""
+    ready_to_call = None  # 一个协程或者异步生成器
+
+    trace_ = None
+
+    event = context.context.event
+
+    try:
+        if method_name == "run" or method_name == "decorator_handler":
+            ready_to_call = handler(event, *args, **kwargs)
+        elif method_name == "call":
+            ready_to_call = handler(context, *args, **kwargs)
+        else:
+            raise ValueError(f"未知的方法名: {method_name}")
+    except ValueError as e:
+        raise Exception(f"Tool execution ValueError: {e}") from e
+    except TypeError as e:
+        # 获取函数的签名（包括类型），除了第一个 event/context 参数。
+        try:
+            sig = inspect.signature(handler)
+            params = list(sig.parameters.values())
+            # 跳过第一个参数（event 或 context）
+            if params:
+                params = params[1:]
+
+            param_strs = []
+            for param in params:
+                param_str = param.name
+                if param.annotation != inspect.Parameter.empty:
+                    # 获取类型注解的字符串表示
+                    if isinstance(param.annotation, type):
+                        type_str = param.annotation.__name__
+                    else:
+                        type_str = str(param.annotation)
+                    param_str += f": {type_str}"
+                if param.default != inspect.Parameter.empty:
+                    param_str += f" = {param.default!r}"
+                param_strs.append(param_str)
+
+            handler_param_str = (
+                ", ".join(param_strs) if param_strs else "(no additional parameters)"
+            )
+        except Exception:
+            handler_param_str = "(unable to inspect signature)"
+
+        raise Exception(
+            f"Tool handler parameter mismatch, please check the handler definition. Handler parameters: {handler_param_str}"
+        ) from e
+    except Exception as e:
+        trace_ = traceback.format_exc()
+        raise Exception(f"Tool execution error: {e}. Traceback: {trace_}") from e
+
+    if not ready_to_call:
+        return
+
+    if inspect.isasyncgen(ready_to_call):
+        _has_yielded = False
+        try:
+            async for ret in ready_to_call:
+                # 这里逐步执行异步生成器, 对于每个 yield 返回的 ret, 执行下面的代码
+                # 返回值只能是 MessageEventResult 或者 None（无返回值）
+                _has_yielded = True
+                if isinstance(ret, MessageEventResult | CommandResult):
+                    # 如果返回值是 MessageEventResult, 设置结果并继续
+                    event.set_result(ret)
+                    yield
+                else:
+                    # 如果返回值是 None, 则不设置结果并继续
+                    # 继续执行后续阶段
+                    yield ret
+            if not _has_yielded:
+                # 如果这个异步生成器没有执行到 yield 分支
+                yield
+        except Exception as e:
+            logger.error(f"Previous Error: {trace_}")
+            raise e
+    elif inspect.iscoroutine(ready_to_call):
+        # 如果只是一个协程, 直接执行
+        ret = await ready_to_call
+        if isinstance(ret, MessageEventResult | CommandResult):
+            event.set_result(ret)
+            yield
+        else:
+            yield ret

astrbot/core/astr_main_agent.py

@@ -0,0 +1,990 @@
+from __future__ import annotations
+
+import asyncio
+import builtins
+import copy
+import datetime
+import json
+import os
+import zoneinfo
+from collections.abc import Coroutine
+from dataclasses import dataclass, field
+
+from astrbot.api import sp
+from astrbot.core import logger
+from astrbot.core.agent.handoff import HandoffTool
+from astrbot.core.agent.mcp_client import MCPTool
+from astrbot.core.agent.message import TextPart
+from astrbot.core.agent.tool import ToolSet
+from astrbot.core.astr_agent_context import AgentContextWrapper, AstrAgentContext
+from astrbot.core.astr_agent_hooks import MAIN_AGENT_HOOKS
+from astrbot.core.astr_agent_run_util import AgentRunner
+from astrbot.core.astr_agent_tool_exec import FunctionToolExecutor
+from astrbot.core.astr_main_agent_resources import (
+    CHATUI_SPECIAL_DEFAULT_PERSONA_PROMPT,
+    EXECUTE_SHELL_TOOL,
+    FILE_DOWNLOAD_TOOL,
+    FILE_UPLOAD_TOOL,
+    KNOWLEDGE_BASE_QUERY_TOOL,
+    LIVE_MODE_SYSTEM_PROMPT,
+    LLM_SAFETY_MODE_SYSTEM_PROMPT,
+    LOCAL_EXECUTE_SHELL_TOOL,
+    LOCAL_PYTHON_TOOL,
+    PYTHON_TOOL,
+    SANDBOX_MODE_PROMPT,
+    SEND_MESSAGE_TO_USER_TOOL,
+    TOOL_CALL_PROMPT,
+    TOOL_CALL_PROMPT_SKILLS_LIKE_MODE,
+    retrieve_knowledge_base,
+)
+from astrbot.core.conversation_mgr import Conversation
+from astrbot.core.message.components import File, Image, Reply
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core.provider import Provider
+from astrbot.core.provider.entities import ProviderRequest
+from astrbot.core.skills.skill_manager import SkillManager, build_skills_prompt
+from astrbot.core.star.context import Context
+from astrbot.core.star.star_handler import star_map
+from astrbot.core.tools.cron_tools import (
+    CREATE_CRON_JOB_TOOL,
+    DELETE_CRON_JOB_TOOL,
+    LIST_CRON_JOBS_TOOL,
+)
+from astrbot.core.utils.file_extract import extract_file_moonshotai
+from astrbot.core.utils.llm_metadata import LLM_METADATAS
+
+
+@dataclass(slots=True)
+class MainAgentBuildConfig:
+    """The main agent build configuration.
+    Most of the configs can be found in the cmd_config.json"""
+
+    tool_call_timeout: int
+    """The timeout (in seconds) for a tool call.
+    When the tool call exceeds this time,
+    a timeout error as a tool result will be returned.
+    """
+    tool_schema_mode: str = "full"
+    """The tool schema mode, can be 'full' or 'skills-like'."""
+    provider_wake_prefix: str = ""
+    """The wake prefix for the provider. If the user message does not start with this prefix,
+    the main agent will not be triggered."""
+    streaming_response: bool = True
+    """Whether to use streaming response."""
+    sanitize_context_by_modalities: bool = False
+    """Whether to sanitize the context based on the provider's supported modalities.
+    This will remove unsupported message types(e.g. image) from the context to prevent issues."""
+    kb_agentic_mode: bool = False
+    """Whether to use agentic mode for knowledge base retrieval.
+    This will inject the knowledge base query tool into the main agent's toolset to allow dynamic querying."""
+    file_extract_enabled: bool = False
+    """Whether to enable file content extraction for uploaded files."""
+    file_extract_prov: str = "moonshotai"
+    """The file extraction provider."""
+    file_extract_msh_api_key: str = ""
+    """The API key for Moonshot AI file extraction provider."""
+    context_limit_reached_strategy: str = "truncate_by_turns"
+    """The strategy to handle context length limit reached."""
+    llm_compress_instruction: str = ""
+    """The instruction for compression in llm_compress strategy."""
+    llm_compress_keep_recent: int = 6
+    """The number of most recent turns to keep during llm_compress strategy."""
+    llm_compress_provider_id: str = ""
+    """The provider ID for the LLM used in context compression."""
+    max_context_length: int = -1
+    """The maximum number of turns to keep in context. -1 means no limit.
+    This enforce max turns before compression"""
+    dequeue_context_length: int = 1
+    """The number of oldest turns to remove when context length limit is reached."""
+    llm_safety_mode: bool = True
+    """This will inject healthy and safe system prompt into the main agent,
+    to prevent LLM output harmful information"""
+    safety_mode_strategy: str = "system_prompt"
+    computer_use_runtime: str = "local"
+    """The runtime for agent computer use: none, local, or sandbox."""
+    sandbox_cfg: dict = field(default_factory=dict)
+    add_cron_tools: bool = True
+    """This will add cron job management tools to the main agent for proactive cron job execution."""
+    provider_settings: dict = field(default_factory=dict)
+    subagent_orchestrator: dict = field(default_factory=dict)
+    timezone: str | None = None
+
+
+@dataclass(slots=True)
+class MainAgentBuildResult:
+    agent_runner: AgentRunner
+    provider_request: ProviderRequest
+    provider: Provider
+    reset_coro: Coroutine | None = None
+
+
+def _select_provider(
+    event: AstrMessageEvent, plugin_context: Context
+) -> Provider | None:
+    """Select chat provider for the event."""
+    sel_provider = event.get_extra("selected_provider")
+    if sel_provider and isinstance(sel_provider, str):
+        provider = plugin_context.get_provider_by_id(sel_provider)
+        if not provider:
+            logger.error("未找到指定的提供商: %s。", sel_provider)
+        if not isinstance(provider, Provider):
+            logger.error(
+                "选择的提供商类型无效(%s)，跳过 LLM 请求处理。", type(provider)
+            )
+            return None
+        return provider
+    try:
+        return plugin_context.get_using_provider(umo=event.unified_msg_origin)
+    except ValueError as exc:
+        logger.error("Error occurred while selecting provider: %s", exc)
+        return None
+
+
+async def _get_session_conv(
+    event: AstrMessageEvent, plugin_context: Context
+) -> Conversation:
+    conv_mgr = plugin_context.conversation_manager
+    umo = event.unified_msg_origin
+    cid = await conv_mgr.get_curr_conversation_id(umo)
+    if not cid:
+        cid = await conv_mgr.new_conversation(umo, event.get_platform_id())
+    conversation = await conv_mgr.get_conversation(umo, cid)
+    if not conversation:
+        cid = await conv_mgr.new_conversation(umo, event.get_platform_id())
+        conversation = await conv_mgr.get_conversation(umo, cid)
+    if not conversation:
+        raise RuntimeError("无法创建新的对话。")
+    return conversation
+
+
+async def _apply_kb(
+    event: AstrMessageEvent,
+    req: ProviderRequest,
+    plugin_context: Context,
+    config: MainAgentBuildConfig,
+) -> None:
+    if not config.kb_agentic_mode:
+        if req.prompt is None:
+            return
+        try:
+            kb_result = await retrieve_knowledge_base(
+                query=req.prompt,
+                umo=event.unified_msg_origin,
+                context=plugin_context,
+            )
+            if not kb_result:
+                return
+            if req.system_prompt is not None:
+                req.system_prompt += (
+                    f"\n\n[Related Knowledge Base Results]:\n{kb_result}"
+                )
+        except Exception as exc:  # noqa: BLE001
+            logger.error("Error occurred while retrieving knowledge base: %s", exc)
+    else:
+        if req.func_tool is None:
+            req.func_tool = ToolSet()
+        req.func_tool.add_tool(KNOWLEDGE_BASE_QUERY_TOOL)
+
+
+async def _apply_file_extract(
+    event: AstrMessageEvent,
+    req: ProviderRequest,
+    config: MainAgentBuildConfig,
+) -> None:
+    file_paths = []
+    file_names = []
+    for comp in event.message_obj.message:
+        if isinstance(comp, File):
+            file_paths.append(await comp.get_file())
+            file_names.append(comp.name)
+        elif isinstance(comp, Reply) and comp.chain:
+            for reply_comp in comp.chain:
+                if isinstance(reply_comp, File):
+                    file_paths.append(await reply_comp.get_file())
+                    file_names.append(reply_comp.name)
+    if not file_paths:
+        return
+    if not req.prompt:
+        req.prompt = "总结一下文件里面讲了什么？"
+    if config.file_extract_prov == "moonshotai":
+        if not config.file_extract_msh_api_key:
+            logger.error("Moonshot AI API key for file extract is not set")
+            return
+        file_contents = await asyncio.gather(
+            *[
+                extract_file_moonshotai(
+                    file_path,
+                    config.file_extract_msh_api_key,
+                )
+                for file_path in file_paths
+            ]
+        )
+    else:
+        logger.error("Unsupported file extract provider: %s", config.file_extract_prov)
+        return
+
+    for file_content, file_name in zip(file_contents, file_names):
+        req.contexts.append(
+            {
+                "role": "system",
+                "content": (
+                    "File Extract Results of user uploaded files:\n"
+                    f"{file_content}\nFile Name: {file_name or 'Unknown'}"
+                ),
+            },
+        )
+
+
+def _apply_prompt_prefix(req: ProviderRequest, cfg: dict) -> None:
+    prefix = cfg.get("prompt_prefix")
+    if not prefix:
+        return
+    if "{{prompt}}" in prefix:
+        req.prompt = prefix.replace("{{prompt}}", req.prompt)
+    else:
+        req.prompt = f"{prefix}{req.prompt}"
+
+
+def _apply_local_env_tools(req: ProviderRequest) -> None:
+    if req.func_tool is None:
+        req.func_tool = ToolSet()
+    req.func_tool.add_tool(LOCAL_EXECUTE_SHELL_TOOL)
+    req.func_tool.add_tool(LOCAL_PYTHON_TOOL)
+
+
+async def _ensure_persona_and_skills(
+    req: ProviderRequest,
+    cfg: dict,
+    plugin_context: Context,
+    event: AstrMessageEvent,
+) -> None:
+    """Ensure persona and skills are applied to the request's system prompt or user prompt."""
+    if not req.conversation:
+        return
+
+    # get persona ID
+
+    # 1. from session service config - highest priority
+    persona_id = (
+        await sp.get_async(
+            scope="umo",
+            scope_id=event.unified_msg_origin,
+            key="session_service_config",
+            default={},
+        )
+    ).get("persona_id")
+
+    if not persona_id:
+        # 2. from conversation setting - second priority
+        persona_id = req.conversation.persona_id
+
+        if persona_id == "[%None]":
+            # explicitly set to no persona
+            pass
+        elif persona_id is None:
+            # 3. from config default persona setting - last priority
+            persona_id = cfg.get("default_personality")
+
+    persona = next(
+        builtins.filter(
+            lambda persona: persona["name"] == persona_id,
+            plugin_context.persona_manager.personas_v3,
+        ),
+        None,
+    )
+    if persona:
+        # Inject persona system prompt
+        if prompt := persona["prompt"]:
+            req.system_prompt += f"\n# Persona Instructions\n\n{prompt}\n"
+        if begin_dialogs := copy.deepcopy(persona.get("_begin_dialogs_processed")):
+            req.contexts[:0] = begin_dialogs
+    else:
+        # special handling for webchat persona
+        if event.get_platform_name() == "webchat" and persona_id != "[%None]":
+            persona_id = "_chatui_default_"
+            req.system_prompt += CHATUI_SPECIAL_DEFAULT_PERSONA_PROMPT
+
+    # Inject skills prompt
+    runtime = cfg.get("computer_use_runtime", "local")
+    skill_manager = SkillManager()
+    skills = skill_manager.list_skills(active_only=True, runtime=runtime)
+
+    if skills:
+        if persona and persona.get("skills") is not None:
+            if not persona["skills"]:
+                skills = []
+            else:
+                allowed = set(persona["skills"])
+                skills = [skill for skill in skills if skill.name in allowed]
+        if skills:
+            req.system_prompt += f"\n{build_skills_prompt(skills)}\n"
+            if runtime == "none":
+                req.system_prompt += (
+                    "User has not enabled the Computer Use feature. "
+                    "You cannot use shell or Python to perform skills. "
+                    "If you need to use these capabilities, ask the user to enable Computer Use in the AstrBot WebUI -> Config."
+                )
+    tmgr = plugin_context.get_llm_tool_manager()
+
+    # sub agents integration
+    orch_cfg = plugin_context.get_config().get("subagent_orchestrator", {})
+    so = plugin_context.subagent_orchestrator
+    if orch_cfg.get("main_enable", False) and so:
+        remove_dup = bool(orch_cfg.get("remove_main_duplicate_tools", False))
+
+        assigned_tools: set[str] = set()
+        agents = orch_cfg.get("agents", [])
+        if isinstance(agents, list):
+            for a in agents:
+                if not isinstance(a, dict):
+                    continue
+                if a.get("enabled", True) is False:
+                    continue
+                persona_tools = None
+                pid = a.get("persona_id")
+                if pid:
+                    persona_tools = next(
+                        (
+                            p.get("tools")
+                            for p in plugin_context.persona_manager.personas_v3
+                            if p["name"] == pid
+                        ),
+                        None,
+                    )
+                tools = a.get("tools", [])
+                if persona_tools is not None:
+                    tools = persona_tools
+                if tools is None:
+                    assigned_tools.update(
+                        [
+                            tool.name
+                            for tool in tmgr.func_list
+                            if not isinstance(tool, HandoffTool)
+                        ]
+                    )
+                    continue
+                if not isinstance(tools, list):
+                    continue
+                for t in tools:
+                    name = str(t).strip()
+                    if name:
+                        assigned_tools.add(name)
+
+        if req.func_tool is None:
+            toolset = ToolSet()
+        else:
+            toolset = req.func_tool
+
+        # add subagent handoff tools
+        for tool in so.handoffs:
+            toolset.add_tool(tool)
+
+        # check duplicates
+        if remove_dup:
+            names = toolset.names()
+            for tool_name in assigned_tools:
+                if tool_name in names:
+                    toolset.remove_tool(tool_name)
+
+        req.func_tool = toolset
+
+        router_prompt = (
+            plugin_context.get_config()
+            .get("subagent_orchestrator", {})
+            .get("router_system_prompt", "")
+        ).strip()
+        if router_prompt:
+            req.system_prompt += f"\n{router_prompt}\n"
+        return
+
+    # inject toolset in the persona
+    if (persona and persona.get("tools") is None) or not persona:
+        toolset = tmgr.get_full_tool_set()
+        for tool in list(toolset):
+            if not tool.active:
+                toolset.remove_tool(tool.name)
+    else:
+        toolset = ToolSet()
+        if persona["tools"]:
+            for tool_name in persona["tools"]:
+                tool = tmgr.get_func(tool_name)
+                if tool and tool.active:
+                    toolset.add_tool(tool)
+    if not req.func_tool:
+        req.func_tool = toolset
+    else:
+        req.func_tool.merge(toolset)
+    try:
+        event.trace.record(
+            "sel_persona", persona_id=persona_id, persona_toolset=toolset.names()
+        )
+    except Exception:
+        pass
+    logger.debug("Tool set for persona %s: %s", persona_id, toolset.names())
+
+
+async def _request_img_caption(
+    provider_id: str,
+    cfg: dict,
+    image_urls: list[str],
+    plugin_context: Context,
+) -> str:
+    prov = plugin_context.get_provider_by_id(provider_id)
+    if prov is None:
+        raise ValueError(
+            f"Cannot get image caption because provider `{provider_id}` is not exist.",
+        )
+    if not isinstance(prov, Provider):
+        raise ValueError(
+            f"Cannot get image caption because provider `{provider_id}` is not a valid Provider, it is {type(prov)}.",
+        )
+
+    img_cap_prompt = cfg.get(
+        "image_caption_prompt",
+        "Please describe the image.",
+    )
+    logger.debug("Processing image caption with provider: %s", provider_id)
+    llm_resp = await prov.text_chat(
+        prompt=img_cap_prompt,
+        image_urls=image_urls,
+    )
+    return llm_resp.completion_text
+
+
+async def _ensure_img_caption(
+    req: ProviderRequest,
+    cfg: dict,
+    plugin_context: Context,
+    image_caption_provider: str,
+) -> None:
+    try:
+        caption = await _request_img_caption(
+            image_caption_provider,
+            cfg,
+            req.image_urls,
+            plugin_context,
+        )
+        if caption:
+            req.extra_user_content_parts.append(
+                TextPart(text=f"<image_caption>{caption}</image_caption>")
+            )
+            req.image_urls = []
+    except Exception as exc:  # noqa: BLE001
+        logger.error("处理图片描述失败: %s", exc)
+
+
+async def _process_quote_message(
+    event: AstrMessageEvent,
+    req: ProviderRequest,
+    img_cap_prov_id: str,
+    plugin_context: Context,
+) -> None:
+    quote = None
+    for comp in event.message_obj.message:
+        if isinstance(comp, Reply):
+            quote = comp
+            break
+    if not quote:
+        return
+
+    content_parts = []
+    sender_info = f"({quote.sender_nickname}): " if quote.sender_nickname else ""
+    message_str = quote.message_str or "[Empty Text]"
+    content_parts.append(f"{sender_info}{message_str}")
+
+    image_seg = None
+    if quote.chain:
+        for comp in quote.chain:
+            if isinstance(comp, Image):
+                image_seg = comp
+                break
+
+    if image_seg:
+        try:
+            prov = None
+            if img_cap_prov_id:
+                prov = plugin_context.get_provider_by_id(img_cap_prov_id)
+            if prov is None:
+                prov = plugin_context.get_using_provider(event.unified_msg_origin)
+
+            if prov and isinstance(prov, Provider):
+                llm_resp = await prov.text_chat(
+                    prompt="Please describe the image content.",
+                    image_urls=[await image_seg.convert_to_file_path()],
+                )
+                if llm_resp.completion_text:
+                    content_parts.append(
+                        f"[Image Caption in quoted message]: {llm_resp.completion_text}"
+                    )
+            else:
+                logger.warning("No provider found for image captioning in quote.")
+        except BaseException as exc:
+            logger.error("处理引用图片失败: %s", exc)
+
+    quoted_content = "\n".join(content_parts)
+    quoted_text = f"<Quoted Message>\n{quoted_content}\n</Quoted Message>"
+    req.extra_user_content_parts.append(TextPart(text=quoted_text))
+
+
+def _append_system_reminders(
+    event: AstrMessageEvent,
+    req: ProviderRequest,
+    cfg: dict,
+    timezone: str | None,
+) -> None:
+    system_parts: list[str] = []
+    if cfg.get("identifier"):
+        user_id = event.message_obj.sender.user_id
+        user_nickname = event.message_obj.sender.nickname
+        system_parts.append(f"User ID: {user_id}, Nickname: {user_nickname}")
+
+    if cfg.get("group_name_display") and event.message_obj.group_id:
+        if not event.message_obj.group:
+            logger.error(
+                "Group name display enabled but group object is None. Group ID: %s",
+                event.message_obj.group_id,
+            )
+        else:
+            group_name = event.message_obj.group.group_name
+            if group_name:
+                system_parts.append(f"Group name: {group_name}")
+
+    if cfg.get("datetime_system_prompt"):
+        current_time = None
+        if timezone:
+            try:
+                now = datetime.datetime.now(zoneinfo.ZoneInfo(timezone))
+                current_time = now.strftime("%Y-%m-%d %H:%M (%Z)")
+            except Exception as exc:  # noqa: BLE001
+                logger.error("时区设置错误: %s, 使用本地时区", exc)
+        if not current_time:
+            current_time = (
+                datetime.datetime.now().astimezone().strftime("%Y-%m-%d %H:%M (%Z)")
+            )
+        system_parts.append(f"Current datetime: {current_time}")
+
+    if system_parts:
+        system_content = (
+            "<system_reminder>" + "\n".join(system_parts) + "</system_reminder>"
+        )
+        req.extra_user_content_parts.append(TextPart(text=system_content))
+
+
+async def _decorate_llm_request(
+    event: AstrMessageEvent,
+    req: ProviderRequest,
+    plugin_context: Context,
+    config: MainAgentBuildConfig,
+) -> None:
+    cfg = config.provider_settings or plugin_context.get_config(
+        umo=event.unified_msg_origin
+    ).get("provider_settings", {})
+
+    _apply_prompt_prefix(req, cfg)
+
+    if req.conversation:
+        await _ensure_persona_and_skills(req, cfg, plugin_context, event)
+
+        img_cap_prov_id: str = cfg.get("default_image_caption_provider_id") or ""
+        if img_cap_prov_id and req.image_urls:
+            await _ensure_img_caption(
+                req,
+                cfg,
+                plugin_context,
+                img_cap_prov_id,
+            )
+
+    img_cap_prov_id = cfg.get("default_image_caption_provider_id") or ""
+    await _process_quote_message(
+        event,
+        req,
+        img_cap_prov_id,
+        plugin_context,
+    )
+
+    tz = config.timezone
+    if tz is None:
+        tz = plugin_context.get_config().get("timezone")
+    _append_system_reminders(event, req, cfg, tz)
+
+
+def _modalities_fix(provider: Provider, req: ProviderRequest) -> None:
+    if req.image_urls:
+        provider_cfg = provider.provider_config.get("modalities", ["image"])
+        if "image" not in provider_cfg:
+            logger.debug(
+                "Provider %s does not support image, using placeholder.", provider
+            )
+            image_count = len(req.image_urls)
+            placeholder = " ".join(["[图片]"] * image_count)
+            if req.prompt:
+                req.prompt = f"{placeholder} {req.prompt}"
+            else:
+                req.prompt = placeholder
+            req.image_urls = []
+    if req.func_tool:
+        provider_cfg = provider.provider_config.get("modalities", ["tool_use"])
+        if "tool_use" not in provider_cfg:
+            logger.debug(
+                "Provider %s does not support tool_use, clearing tools.", provider
+            )
+            req.func_tool = None
+
+
+def _sanitize_context_by_modalities(
+    config: MainAgentBuildConfig,
+    provider: Provider,
+    req: ProviderRequest,
+) -> None:
+    if not config.sanitize_context_by_modalities:
+        return
+    if not isinstance(req.contexts, list) or not req.contexts:
+        return
+    modalities = provider.provider_config.get("modalities", None)
+    if not modalities or not isinstance(modalities, list):
+        return
+    supports_image = bool("image" in modalities)
+    supports_tool_use = bool("tool_use" in modalities)
+    if supports_image and supports_tool_use:
+        return
+
+    sanitized_contexts: list[dict] = []
+    removed_image_blocks = 0
+    removed_tool_messages = 0
+    removed_tool_calls = 0
+
+    for msg in req.contexts:
+        if not isinstance(msg, dict):
+            continue
+        role = msg.get("role")
+        if not role:
+            continue
+
+        new_msg = msg
+        if not supports_tool_use:
+            if role == "tool":
+                removed_tool_messages += 1
+                continue
+            if role == "assistant" and "tool_calls" in new_msg:
+                if "tool_calls" in new_msg:
+                    removed_tool_calls += 1
+                new_msg.pop("tool_calls", None)
+                new_msg.pop("tool_call_id", None)
+
+        if not supports_image:
+            content = new_msg.get("content")
+            if isinstance(content, list):
+                filtered_parts: list = []
+                removed_any_image = False
+                for part in content:
+                    if isinstance(part, dict):
+                        part_type = str(part.get("type", "")).lower()
+                        if part_type in {"image_url", "image"}:
+                            removed_any_image = True
+                            removed_image_blocks += 1
+                            continue
+                    filtered_parts.append(part)
+                if removed_any_image:
+                    new_msg["content"] = filtered_parts
+
+        if role == "assistant":
+            content = new_msg.get("content")
+            has_tool_calls = bool(new_msg.get("tool_calls"))
+            if not has_tool_calls:
+                if not content:
+                    continue
+                if isinstance(content, str) and not content.strip():
+                    continue
+
+        sanitized_contexts.append(new_msg)
+
+    if removed_image_blocks or removed_tool_messages or removed_tool_calls:
+        logger.debug(
+            "sanitize_context_by_modalities applied: "
+            "removed_image_blocks=%s, removed_tool_messages=%s, removed_tool_calls=%s",
+            removed_image_blocks,
+            removed_tool_messages,
+            removed_tool_calls,
+        )
+    req.contexts = sanitized_contexts
+
+
+def _plugin_tool_fix(event: AstrMessageEvent, req: ProviderRequest) -> None:
+    """根据事件中的插件设置，过滤请求中的工具列表。
+
+    注意：没有 handler_module_path 的工具（如 MCP 工具）会被保留，
+    因为它们不属于任何插件，不应被插件过滤逻辑影响。
+    """
+    if event.plugins_name is not None and req.func_tool:
+        new_tool_set = ToolSet()
+        for tool in req.func_tool.tools:
+            if isinstance(tool, MCPTool):
+                # 保留 MCP 工具
+                new_tool_set.add_tool(tool)
+                continue
+            mp = tool.handler_module_path
+            if not mp:
+                continue
+            plugin = star_map.get(mp)
+            if not plugin:
+                continue
+            if plugin.name in event.plugins_name or plugin.reserved:
+                new_tool_set.add_tool(tool)
+        req.func_tool = new_tool_set
+
+
+async def _handle_webchat(
+    event: AstrMessageEvent, req: ProviderRequest, prov: Provider
+) -> None:
+    from astrbot.core import db_helper
+
+    chatui_session_id = event.session_id.split("!")[-1]
+    user_prompt = req.prompt
+    session = await db_helper.get_platform_session_by_id(chatui_session_id)
+
+    if not user_prompt or not chatui_session_id or not session or session.display_name:
+        return
+
+    llm_resp = await prov.text_chat(
+        system_prompt=(
+            "You are a conversation title generator. "
+            "Generate a concise title in the same language as the user’s input, "
+            "no more than 10 words, capturing only the core topic."
+            "If the input is a greeting, small talk, or has no clear topic, "
+            "(e.g., “hi”, “hello”, “haha”), return <None>. "
+            "Output only the title itself or <None>, with no explanations."
+        ),
+        prompt=f"Generate a concise title for the following user query:\n{user_prompt}",
+    )
+    if llm_resp and llm_resp.completion_text:
+        title = llm_resp.completion_text.strip()
+        if not title or "<None>" in title:
+            return
+        logger.info(
+            "Generated chatui title for session %s: %s", chatui_session_id, title
+        )
+        await db_helper.update_platform_session(
+            session_id=chatui_session_id,
+            display_name=title,
+        )
+
+
+def _apply_llm_safety_mode(config: MainAgentBuildConfig, req: ProviderRequest) -> None:
+    if config.safety_mode_strategy == "system_prompt":
+        req.system_prompt = (
+            f"{LLM_SAFETY_MODE_SYSTEM_PROMPT}\n\n{req.system_prompt or ''}"
+        )
+    else:
+        logger.warning(
+            "Unsupported llm_safety_mode strategy: %s.",
+            config.safety_mode_strategy,
+        )
+
+
+def _apply_sandbox_tools(
+    config: MainAgentBuildConfig, req: ProviderRequest, session_id: str
+) -> None:
+    if req.func_tool is None:
+        req.func_tool = ToolSet()
+    if config.sandbox_cfg.get("booter") == "shipyard":
+        ep = config.sandbox_cfg.get("shipyard_endpoint", "")
+        at = config.sandbox_cfg.get("shipyard_access_token", "")
+        if not ep or not at:
+            logger.error("Shipyard sandbox configuration is incomplete.")
+            return
+        os.environ["SHIPYARD_ENDPOINT"] = ep
+        os.environ["SHIPYARD_ACCESS_TOKEN"] = at
+    req.func_tool.add_tool(EXECUTE_SHELL_TOOL)
+    req.func_tool.add_tool(PYTHON_TOOL)
+    req.func_tool.add_tool(FILE_UPLOAD_TOOL)
+    req.func_tool.add_tool(FILE_DOWNLOAD_TOOL)
+    req.system_prompt += f"\n{SANDBOX_MODE_PROMPT}\n"
+
+
+def _proactive_cron_job_tools(req: ProviderRequest) -> None:
+    if req.func_tool is None:
+        req.func_tool = ToolSet()
+    req.func_tool.add_tool(CREATE_CRON_JOB_TOOL)
+    req.func_tool.add_tool(DELETE_CRON_JOB_TOOL)
+    req.func_tool.add_tool(LIST_CRON_JOBS_TOOL)
+
+
+def _get_compress_provider(
+    config: MainAgentBuildConfig, plugin_context: Context
+) -> Provider | None:
+    if not config.llm_compress_provider_id:
+        return None
+    if config.context_limit_reached_strategy != "llm_compress":
+        return None
+    provider = plugin_context.get_provider_by_id(config.llm_compress_provider_id)
+    if provider is None:
+        logger.warning(
+            "未找到指定的上下文压缩模型 %s，将跳过压缩。",
+            config.llm_compress_provider_id,
+        )
+        return None
+    if not isinstance(provider, Provider):
+        logger.warning(
+            "指定的上下文压缩模型 %s 不是对话模型，将跳过压缩。",
+            config.llm_compress_provider_id,
+        )
+        return None
+    return provider
+
+
+async def build_main_agent(
+    *,
+    event: AstrMessageEvent,
+    plugin_context: Context,
+    config: MainAgentBuildConfig,
+    provider: Provider | None = None,
+    req: ProviderRequest | None = None,
+    apply_reset: bool = True,
+) -> MainAgentBuildResult | None:
+    """构建主对话代理（Main Agent），并且自动 reset。
+
+    If apply_reset is False, will not call reset on the agent runner.
+    """
+    provider = provider or _select_provider(event, plugin_context)
+    if provider is None:
+        logger.info("未找到任何对话模型（提供商），跳过 LLM 请求处理。")
+        return None
+
+    if req is None:
+        if event.get_extra("provider_request"):
+            req = event.get_extra("provider_request")
+            assert isinstance(req, ProviderRequest), (
+                "provider_request 必须是 ProviderRequest 类型。"
+            )
+            if req.conversation:
+                req.contexts = json.loads(req.conversation.history)
+        else:
+            req = ProviderRequest()
+            req.prompt = ""
+            req.image_urls = []
+            if sel_model := event.get_extra("selected_model"):
+                req.model = sel_model
+            if config.provider_wake_prefix and not event.message_str.startswith(
+                config.provider_wake_prefix
+            ):
+                return None
+
+            req.prompt = event.message_str[len(config.provider_wake_prefix) :]
+            for comp in event.message_obj.message:
+                if isinstance(comp, Image):
+                    image_path = await comp.convert_to_file_path()
+                    req.image_urls.append(image_path)
+                    req.extra_user_content_parts.append(
+                        TextPart(text=f"[Image Attachment: path {image_path}]")
+                    )
+                elif isinstance(comp, File):
+                    file_path = await comp.get_file()
+                    file_name = comp.name or os.path.basename(file_path)
+                    req.extra_user_content_parts.append(
+                        TextPart(
+                            text=f"[File Attachment: name {file_name}, path {file_path}]"
+                        )
+                    )
+
+            conversation = await _get_session_conv(event, plugin_context)
+            req.conversation = conversation
+            req.contexts = json.loads(conversation.history)
+            event.set_extra("provider_request", req)
+
+    if isinstance(req.contexts, str):
+        req.contexts = json.loads(req.contexts)
+
+    if config.file_extract_enabled:
+        try:
+            await _apply_file_extract(event, req, config)
+        except Exception as exc:  # noqa: BLE001
+            logger.error("Error occurred while applying file extract: %s", exc)
+
+    if not req.prompt and not req.image_urls:
+        if not event.get_group_id() and req.extra_user_content_parts:
+            req.prompt = "<attachment>"
+        else:
+            return None
+
+    await _decorate_llm_request(event, req, plugin_context, config)
+
+    await _apply_kb(event, req, plugin_context, config)
+
+    if not req.session_id:
+        req.session_id = event.unified_msg_origin
+
+    _modalities_fix(provider, req)
+    _plugin_tool_fix(event, req)
+    _sanitize_context_by_modalities(config, provider, req)
+
+    if config.llm_safety_mode:
+        _apply_llm_safety_mode(config, req)
+
+    if config.computer_use_runtime == "sandbox":
+        _apply_sandbox_tools(config, req, req.session_id)
+    elif config.computer_use_runtime == "local":
+        _apply_local_env_tools(req)
+
+    agent_runner = AgentRunner()
+    astr_agent_ctx = AstrAgentContext(
+        context=plugin_context,
+        event=event,
+    )
+
+    if config.add_cron_tools:
+        _proactive_cron_job_tools(req)
+
+    if event.platform_meta.support_proactive_message:
+        if req.func_tool is None:
+            req.func_tool = ToolSet()
+        req.func_tool.add_tool(SEND_MESSAGE_TO_USER_TOOL)
+
+    if provider.provider_config.get("max_context_tokens", 0) <= 0:
+        model = provider.get_model()
+        if model_info := LLM_METADATAS.get(model):
+            provider.provider_config["max_context_tokens"] = model_info["limit"][
+                "context"
+            ]
+
+    if event.get_platform_name() == "webchat":
+        asyncio.create_task(_handle_webchat(event, req, provider))
+
+    if req.func_tool and req.func_tool.tools:
+        tool_prompt = (
+            TOOL_CALL_PROMPT
+            if config.tool_schema_mode == "full"
+            else TOOL_CALL_PROMPT_SKILLS_LIKE_MODE
+        )
+        req.system_prompt += f"\n{tool_prompt}\n"
+
+    action_type = event.get_extra("action_type")
+    if action_type == "live":
+        req.system_prompt += f"\n{LIVE_MODE_SYSTEM_PROMPT}\n"
+
+    reset_coro = agent_runner.reset(
+        provider=provider,
+        request=req,
+        run_context=AgentContextWrapper(
+            context=astr_agent_ctx,
+            tool_call_timeout=config.tool_call_timeout,
+        ),
+        tool_executor=FunctionToolExecutor(),
+        agent_hooks=MAIN_AGENT_HOOKS,
+        streaming=config.streaming_response,
+        llm_compress_instruction=config.llm_compress_instruction,
+        llm_compress_keep_recent=config.llm_compress_keep_recent,
+        llm_compress_provider=_get_compress_provider(config, plugin_context),
+        truncate_turns=config.dequeue_context_length,
+        enforce_max_turns=config.max_context_length,
+        tool_schema_mode=config.tool_schema_mode,
+    )
+
+    if apply_reset:
+        await reset_coro
+
+    return MainAgentBuildResult(
+        agent_runner=agent_runner,
+        provider_request=req,
+        provider=provider,
+        reset_coro=reset_coro if not apply_reset else None,
+    )