chore: bump version to 4.5.3

* Initial plan

* Add sidebar customization feature with drag-and-drop support

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

* Add dist/ to .gitignore to exclude build artifacts

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

* Fix memory leak and improve code quality per code review

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

* Fix i18n key format: use dot notation instead of colon notation

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

* Fix drag-and-drop to empty list issue

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

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>

.dockerignore

@@ -1,9 +1,8 @@
 # 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
 .github/
 .*ignore
-.git/
 # User-specific stuff
 .idea/
 # Byte-compiled / optimized / DLL files
@@ -15,6 +14,9 @@ env/
 venv*/
 ENV/
 .conda/
-README*.md
 dashboard/
 data/
+changelogs/
+tests/
+.ruff_cache/
+.astrbot

.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: astrbot
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: ['https://afdian.com/a/astrbot_team']

.github/ISSUE_TEMPLATE/PLUGIN_PUBLISH.yml

@@ -1,39 +1,57 @@
-name: '🥳 发布插件'
-title: "[Plugin] 插件名"
+name: 🥳 发布插件
 description: 提交插件到插件市场
+title: "[Plugin] 插件名"
 labels: ["plugin-publish"]
+assignees: []
 body:
   - type: markdown
     attributes:
       value: |
         欢迎发布插件到插件市场！
 
-  - type: textarea
+  - type: markdown
     attributes:
-      label: 插件仓库
-      description: 插件的 GitHub 仓库链接
-      placeholder: >
-        如 https://github.com/Soulter/astrbot-github-cards
-
-  - type: textarea
-    attributes:
-      label: 描述
       value: |
-        插件名: 
-        插件作者: 
-        插件简介: 
-        标签: (可选)
-        社交链接: (可选, 将会在插件市场作者名称上作为可点击的链接)
-      description: 必填。请以列表的字段按顺序将插件名、插件作者、插件简介放在这里。
+        ## 插件基本信息
 
-  - type: checkboxes
+        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 ？可以从 [此处](https://plugins.astrbot.app/submit) 生成 JSON ，生成后记得复制粘贴过来.
+
+  - type: textarea
+    id: plugin-info
     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)。
+      label: 插件信息
+      description: 请在下方代码块中填写您的插件信息，确保反引号包裹了JSON
+      value: |
+        ```json
+        {
+          "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": "",
+        }
+        ```
+    validations:
       required: true
 
   - type: markdown
     attributes:
-      value: "❤️"
+      value: |
+        ## 检查
+
+  - type: checkboxes
+    id: checks
+    attributes:
+      label: 插件检查清单
+      description: 请确认以下所有项目
+      options:
+        - label: 我的插件经过完整的测试
+          required: true
+        - label: 我的插件不包含恶意代码
+          required: true
+        - 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)。
+          required: true

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -6,13 +6,13 @@ 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）。
+        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
       placeholder: >
-        一个清晰且具体的描述这个异常是什么。
+        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
 
@@ -55,7 +55,7 @@ body:
     attributes:
       label: 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！
+        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。
     validations:

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,10 +1,46 @@
-<!-- 如果有的话，指定这个 PR 要解决的 ISSUE -->
-修复了 #XYZ
+<!-- 如果有的话，请指定此 PR 旨在解决的 ISSUE 编号。 -->
+<!-- If applicable, please specify the ISSUE number this PR aims to resolve. -->
 
-### Motivation
+fixes #XYZ
 
-<!--解释为什么要改动-->
+---
 
-### Modifications
+### Motivation / 动机
 
-<!--简单解释你的改动-->
+<!--请描述此项更改的动机：它解决了什么问题？（例如：修复了 XX 错误，添加了 YY 功能）-->
+<!--Please describe the motivation for this change: What problem does it solve? (e.g., Fixes XX bug, adds YY feature)-->
+
+### Modifications / 改动点
+
+<!--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?-->
+
+### Verification Steps / 验证步骤
+
+<!--请为审查者 (Reviewer) 提供清晰、可复现的验证步骤（例如：1. 导航到... 2. 点击...）。-->
+<!--Please provide clear and reproducible verification steps for the Reviewer (e.g., 1. Navigate to... 2. Click...).-->
+
+### Screenshots or Test Results / 运行截图或测试结果
+
+<!--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。-->
+<!--Please paste screenshots, GIFs, or test logs here as evidence of executing the "Verification Steps" to prove this change is effective.-->
+
+### Compatibility & Breaking Changes / 兼容性与破坏性变更
+
+<!--请说明此变更的兼容性：哪些是破坏性变更？哪些地方做了向后兼容处理？是否提供了数据迁移方法？-->
+<!--Please explain the compatibility of this change: What are the breaking changes? What backward-compatible measures were taken? Are data migration paths provided?-->
+
+- [ ] 这是一个破坏性变更 (Breaking Change)。/ This is a breaking change.
+- [ ] 这不是一个破坏性变更。/ This is NOT a breaking change.
+
+---
+
+### Checklist / 检查清单
+
+<!--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。-->
+<!--If merged, your code will serve tens of thousands of users! Please double-check the following items before submitting.-->
+
+- [ ] 😊 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

@@ -0,0 +1,63 @@
+# AstrBot Development Instructions
+
+AstrBot is a multi-platform LLM chatbot and development framework written in Python with a Vue.js dashboard. It supports multiple messaging platforms (QQ, Telegram, Discord, etc.) and various LLM providers (OpenAI, Anthropic, Google Gemini, etc.).
+
+Always reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
+
+## Working Effectively
+
+### Bootstrap and Install Dependencies
+- **Python 3.10+ required** - Check `.python-version` file
+- Install UV package manager: `pip install uv`
+- Install project dependencies: `uv sync` -- takes 6-7 minutes. NEVER CANCEL. Set timeout to 10+ minutes.
+- Create required directories: `mkdir -p data/plugins data/config data/temp`
+
+### 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
+- Navigate to dashboard: `cd dashboard`
+- Install dashboard dependencies: `npm install` -- takes 2-3 minutes. NEVER CANCEL. Set timeout to 5+ minutes.
+- Build dashboard: `npm run build` -- takes 25-30 seconds. NEVER CANCEL.
+- Dashboard creates optimized production build in `dashboard/dist/`
+
+### Testing
+- Do not generate test files for now.
+
+### Code Quality and Linting
+- Install ruff linter: `uv add --dev ruff`
+- Check code style: `uv run ruff check .` -- takes <1 second
+- Check formatting: `uv run ruff format --check .` -- takes <1 second
+- Fix formatting: `uv run ruff format .`
+- **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)
+- Plugin system supports function tools and message handlers
+- Key plugins: python_interpreter, web_searcher, astrbot, reminder, session_controller
+
+### Common Issues and Workarounds
+- **Dashboard download fails**: Known issue with "division by zero" error - application still works
+- **Import errors in tests**: Ensure `uv run` is used to run tests in proper environment
+=- **Build timeouts**: Always set appropriate timeouts (10+ minutes for uv sync, 5+ minutes for npm install)
+
+## CI/CD Integration
+- GitHub Actions workflows in `.github/workflows/`
+- Docker builds supported via `Dockerfile`
+- Pre-commit hooks enforce ruff formatting and linting
+
+## Docker Support
+- Primary deployment method: `docker run soulter/astrbot:latest`
+- Compose file available: `compose.yml`
+- Exposes ports: 6185 (WebUI), 6195 (WeChat), 6199 (QQ), etc.
+- Volume mount required: `./data:/AstrBot/data`
+
+## Multi-language Support
+- Documentation in Chinese (README.md), English (README_en.md), Japanese (README_ja.md)
+- UI supports internationalization
+- Default language is Chinese
+
+Remember: This is a production chatbot framework with real users. Always test thoroughly and ensure changes don't break existing functionality.

.github/dependabot.yml

@@ -0,0 +1,13 @@
+# Keep GitHub Actions up to date with GitHub's Dependabot...
+# https://docs.github.com/en/code-security/dependabot/working-with-dependabot/keeping-your-actions-up-to-date-with-dependabot
+# https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file#package-ecosystem
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    groups:
+      github-actions:
+        patterns:
+          - "*"  # Group all Actions updates into a single larger pull request
+    schedule:
+      interval: weekly

.github/workflows/auto_release.yml

@@ -7,13 +7,13 @@ on:
 name: Auto Release
 
 jobs:
-  build:
+  build-and-publish-to-github-release:
     runs-on: ubuntu-latest
     permissions:
       contents: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Dashboard Build
         run: |
@@ -24,12 +24,69 @@ jobs:
           echo ${{ github.ref_name }} > dist/assets/version
           zip -r dist.zip dist
       
+      - name: Upload to Cloudflare R2
+        env:
+          R2_ACCOUNT_ID: ${{ secrets.R2_ACCOUNT_ID }}
+          R2_ACCESS_KEY_ID: ${{ secrets.R2_ACCESS_KEY_ID }}
+          R2_SECRET_ACCESS_KEY: ${{ secrets.R2_SECRET_ACCESS_KEY }}
+          R2_BUCKET_NAME: "astrbot"
+          R2_OBJECT_NAME: "astrbot-webui-latest.zip"
+          VERSION_TAG: ${{ github.ref_name }}
+        run: |
+          echo "Installing rclone..."
+          curl https://rclone.org/install.sh | sudo bash
+
+          echo "Configuring rclone remote..."
+          mkdir -p ~/.config/rclone
+          cat <<EOF > ~/.config/rclone/rclone.conf
+          [r2]
+          type = s3
+          provider = Cloudflare
+          access_key_id = $R2_ACCESS_KEY_ID
+          secret_access_key = $R2_SECRET_ACCESS_KEY
+          endpoint = https://${R2_ACCOUNT_ID}.r2.cloudflarestorage.com
+          EOF
+
+          echo "Uploading dist.zip to R2 bucket: $R2_BUCKET_NAME/$R2_OBJECT_NAME"
+          mv dashboard/dist.zip dashboard/$R2_OBJECT_NAME
+          rclone copy dashboard/$R2_OBJECT_NAME r2:$R2_BUCKET_NAME --progress
+          mv dashboard/$R2_OBJECT_NAME dashboard/astrbot-webui-${VERSION_TAG}.zip
+          rclone copy dashboard/astrbot-webui-${VERSION_TAG}.zip r2:$R2_BUCKET_NAME --progress
+          mv dashboard/astrbot-webui-${VERSION_TAG}.zip dashboard/dist.zip
+
       - name: Fetch Changelog
         run: |
           echo "changelog=changelogs/${{github.ref_name}}.md" >> "$GITHUB_ENV"
 
-      - name: Create Release
+      - name: Create GitHub Release
         uses: ncipollo/release-action@v1
         with:
           bodyFile: ${{ env.changelog }}
           artifacts: "dashboard/dist.zip"
+      
+  build-and-publish-to-pypi:
+    # 构建并发布到 PyPI
+    runs-on: ubuntu-latest
+    needs: build-and-publish-to-github-release
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.10'
+
+      - name: Install uv
+        run: |
+          python -m pip install uv
+
+      - name: Build package
+        run: |
+          uv build
+
+      - name: Publish to PyPI
+        env:
+          UV_PUBLISH_TOKEN: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          uv publish

.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@v5
+      
+    - 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@v4
+      uses: actions/checkout@v5
 
     # 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

@@ -8,6 +8,7 @@ on:
       - 'README.md'
       - 'changelogs/**'
       - 'dashboard/**'
+  pull_request:
   workflow_dispatch:
 
 jobs:
@@ -16,30 +17,29 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
       
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install -r requirements.txt
-          pip install pytest pytest-cov pytest-asyncio
+          pip install pytest pytest-asyncio pytest-cov
+          pip install --editable .
 
       - name: Run tests
         run: |
-          mkdir data
-          mkdir data/plugins
-          mkdir data/config
-          mkdir data/temp
+          mkdir -p data/plugins
+          mkdir -p data/config
+          mkdir -p data/temp
           export TESTING=true
           export ZHIPU_API_KEY=${{ secrets.OPENAI_API_KEY }}
-          PYTHONPATH=./ pytest --cov=. tests/ -v -o log_cli=true -o log_level=DEBUG
+          pytest --cov=. -v -o log_cli=true -o log_level=DEBUG
 
       - name: Upload results to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}

.github/workflows/dashboard_ci.yml

@@ -0,0 +1,55 @@
+name: AstrBot Dashboard CI
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: 'latest'
+
+      - name: npm install, build
+        run: |
+          cd dashboard
+          npm install pnpm -g
+          pnpm install
+          pnpm i --save-dev @types/markdown-it
+          pnpm run build
+
+      - name: Inject Commit SHA
+        id: get_sha
+        run: |
+          echo "COMMIT_SHA=$(git rev-parse HEAD)" >> $GITHUB_ENV
+          mkdir -p dashboard/dist/assets
+          echo $COMMIT_SHA > dashboard/dist/assets/version
+          cd dashboard
+          zip -r dist.zip dist
+
+      - name: Archive production artifacts
+        uses: actions/upload-artifact@v5
+        with:
+          name: dist-without-markdown
+          path: |
+            dashboard/dist
+            !dist/**/*.md
+
+      - name: Create GitHub Release
+        if: github.event_name == 'push'
+        uses: ncipollo/release-action@v1
+        with:
+          tag: release-${{ github.sha }}
+          owner: AstrBotDevs
+          repo: astrbot-release-harbour
+          body: "Automated release from commit ${{ github.sha }}"
+          token: ${{ secrets.ASTRBOT_HARBOUR_TOKEN }}
+          artifacts: "dashboard/dist.zip"

.github/workflows/docker-image.yml

@@ -11,33 +11,79 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - name: 拉取源码
-        uses: actions/checkout@v3
+      - name: Pull The Codes
+        uses: actions/checkout@v5
         with:
-          fetch-depth: 1
+          fetch-depth: 0  # Must be 0 so we can fetch tags
 
-      - name: 设置 QEMU
+      - name: Get latest tag (only on manual trigger)
+        id: get-latest-tag
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          tag=$(git describe --tags --abbrev=0)
+          echo "latest_tag=$tag" >> $GITHUB_OUTPUT
+
+      - name: Checkout to latest tag (only on manual trigger)
+        if: github.event_name == 'workflow_dispatch'
+        run: git checkout ${{ steps.get-latest-tag.outputs.latest_tag }}
+
+      - name: Check if version is pre-release
+        id: check-prerelease
+        run: |
+          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+            version="${{ steps.get-latest-tag.outputs.latest_tag }}"
+          else
+            version="${{ github.ref_name }}"
+          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"
+          else
+            echo "is_prerelease=false" >> $GITHUB_OUTPUT
+            echo "Version $version is a stable release, will push latest tag"
+          fi
+
+      - 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: Set QEMU
         uses: docker/setup-qemu-action@v3
 
-      - name: 设置 Docker Buildx
+      - name: Set Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: 登录到 DockerHub
+      - name: Log in to DockerHub
         uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_PASSWORD }}
 
-      - name: 构建和推送 Docker hub
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: Soulter
+          password: ${{ secrets.GHCR_GITHUB_TOKEN }}
+
+      - name: Build and Push Docker to DockerHub and Github GHCR
         uses: docker/build-push-action@v6
         with:
           context: .
           platforms: linux/amd64,linux/arm64
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/astrbot:latest
-            ${{ secrets.DOCKER_HUB_USERNAME }}/astrbot:${{ github.ref_name }}
+            ${{ 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 }}
 
       - name: Post build notifications
         run: echo "Docker image has been built and pushed successfully"
-

.github/workflows/stale.yml

@@ -18,7 +18,7 @@ jobs:
       pull-requests: write
 
     steps:
-    - uses: actions/stale@v5
+    - uses: actions/stale@v10
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: 'Stale issue message'

.gitignore

@@ -1,28 +1,49 @@
+# Python related
 __pycache__
-botpy.log
-.vscode
-data_v2.db
-data_v3.db
-configs/session
-configs/config.yaml
-**/.DS_Store
-temp
-cmd_config.json
-data
-cookies.json
-logs/
-addons/plugins
+.mypy_cache
+.venv*
+.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 and packages
+addons/plugins
+packages/python_interpreter/workplace
 tests/astrbot_plugin_openai
-chroma
+
+# Dashboard
 dashboard/node_modules/
 dashboard/dist/
-.DS_Store
 package-lock.json
 package.json
+
+# Operating System
+**/.DS_Store
+.DS_Store
+
+# AstrBot specific
+.astrbot
+astrbot.lock
+
+# Other
+chroma
 venv/*
-packages/python_interpreter/workplace
-.venv/*
-.conda/
+pytest.ini

.pre-commit-config.yaml

@@ -7,7 +7,19 @@ ci:
   autoupdate_commit_msg: ":balloon: pre-commit autoupdate"
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+  # Ruff version.
+  rev: v0.14.1
   hooks:
-      - id: ruff
+    # 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]

.python-version

@@ -0,0 +1 @@
+3.10

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10-slim
+FROM python:3.11-slim
 WORKDIR /AstrBot
 
 COPY . /AstrBot/
@@ -9,14 +9,24 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     python3-dev \
     libffi-dev \
     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 -r requirements.txt --no-cache-dir
+RUN curl -fsSL https://deb.nodesource.com/setup_lts.x | bash - && \
+    apt-get install -y --no-install-recommends nodejs && \
+    echo "3.11" > .python-version && \
+    rm -rf /var/lib/apt/lists/*
 
-RUN python -m pip install socksio wechatpy cryptography --no-cache-dir
+RUN python -m pip install --no-cache-dir uv && \
+    uv pip install socksio pilk --no-cache-dir --system
 
 EXPOSE 6185
 EXPOSE 6186
 
-CMD [ "python", "main.py" ]
+CMD ["uv", "run", "main.py"]

Dockerfile_with_node

@@ -0,0 +1,40 @@
+FROM python:3.11-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 \
+    git \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+ENV NVM_DIR="/root/.nvm" \
+    NODE_VERSION=22
+RUN curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.2/install.sh | bash && \
+    . "$NVM_DIR/nvm.sh" && \
+    nvm install $NODE_VERSION && \
+    nvm use $NODE_VERSION && \
+    nvm alias default $NODE_VERSION && \
+    node -v && npm -v && \
+    echo "3.11" > .python-version
+ENV PATH="$NVM_DIR/versions/node/v$(node -v | cut -d 'v' -f 2)/bin:$PATH"
+
+RUN python -m pip install --no-cache-dir uv
+
+# 安装项目依赖（根据指南，使用 uv sync）
+RUN uv sync --no-cache
+
+EXPOSE 6185
+EXPOSE 6186
+
+CMD ["uv", "run", "main.py"]

README.md

@@ -1,112 +1,201 @@
-<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">
 
-_✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
+<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)
-[![star](https://gitcode.com/Soulter/AstrBot/star/badge.svg)](https://gitcode.com/Soulter/AstrBot)
-
-<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=1" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
 </div>
 
-AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用的插件系统和完善的大语言模型（LLM）接入功能的聊天机器人及开发框架。
+<br>
 
-## ✨ 主要功能
+<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=%E4%B8%AA&style=for-the-badge&label=%E6%8F%92%E4%BB%B6%E5%B8%82%E5%9C%BA&cacheSeconds=3600">
+</div>
 
-1. **大语言模型对话**。支持各种大语言模型，包括 OpenAI API、Google Gemini、Llama、Deepseek、ChatGLM 等，支持接入本地部署的大模型，通过 Ollama、LLMTuner。具有多轮对话、人格情境、多模态能力，支持图片理解、语音转文字（Whisper）。
-2. **多消息平台接入**。支持接入 QQ（OneBot）、QQ 频道、微信（Gewechat）、飞书、Telegram。后续将支持钉钉、Discord、WhatsApp、小爱音响。支持速率限制、白名单、关键词过滤、百度内容审核。
-3. **Agent**。原生支持部分 Agent 能力，如代码执行器、自然语言待办、网页搜索。对接 [Dify 平台](https://astrbot.app/others/dify.html)，便捷接入 Dify 智能助手、知识库和 Dify 工作流。
-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，极简开发。已支持安装多个插件。
-5. **可视化管理面板**。支持可视化修改配置、插件管理、日志查看等功能，降低配置难度。集成 WebChat，可在面板上与大模型对话。
-6. **高稳定性、高模块化**。基于事件总线和流水线的架构设计，高度模块化，低耦合。
+<br>
 
-> [!TIP]
-> 管理面板在线体验 Demo: [https://demo.astrbot.app/](https://demo.astrbot.app/)
-> 
-> 用户名: `astrbot`, 密码: `astrbot`。未配置 LLM，无法在聊天页使用大模型。（不要再修改 demo 的登录密码了 😭）
+<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://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>
 
-## ✨ 使用方式
+AstrBot 是一个开源的一站式 Agent 聊天机器人平台及开发框架。
 
-#### Docker 部署
+## 主要功能
+
+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。
+
+## 部署方式
+
+#### 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) 。
 
+#### 宝塔面板部署
+
+AstrBot 与宝塔面板合作，已上架至宝塔面板。
+
+请参阅官方文档 [宝塔面板部署](https://astrbot.app/deploy/astrbot/btpanel.html) 。
+
+#### 1Panel 部署
+
+AstrBot 已由 1Panel 官方上架至 1Panel 面板。
+
+请参阅官方文档 [1Panel 部署](https://astrbot.app/deploy/astrbot/1panel.html) 。
+
+#### 在 雨云 上部署
+
+AstrBot 已由雨云官方上架至云应用平台，可一键部署。
+
+[![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
+
+社区贡献的部署方式。
+
+[![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
 
-需要电脑上安装有 Python（>3.10）。请参阅官方文档 [使用 Windows 一键安装器部署 AstrBot](https://astrbot.app/deploy/astrbot/windows.html) 。
-
-#### Replit 部署
-
-[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+请参阅官方文档 [使用 Windows 一键安装器部署 AstrBot](https://astrbot.app/deploy/astrbot/windows.html) 。
 
 #### CasaOS 部署
 
 社区贡献的部署方式。
 
-请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/casaos.html) 。
+请参阅官方文档 [CasaOS 部署](https://astrbot.app/deploy/astrbot/casaos.html) 。
 
 #### 手动部署
 
-请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html) 。
+首先安装 uv：
 
-## 🚀 路线图
+```bash
+pip install uv
+```
 
-### 垂类功能
+通过 Git Clone 安装 AstrBot：
 
-1. 更好的上下文管理：限制 token 总数、对话上下文总结
-3. AstrBot in Minecraft
+```bash
+git clone https://github.com/AstrBotDevs/AstrBot && cd AstrBot
+uv run main.py
+```
 
-### 横功能
+或者请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html) 。
+
+## 🌍 社区
+
+### QQ 群组
+
+- 1 群：322154837
+- 3 群：630166526
+- 5 群：822130018
+- 6 群：753075035
+- 开发者群：975206796
+
+### Telegram 群组
+
+<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>
 
 ## ⚡ 消息平台支持情况
 
-| 平台    | 支持性 | 详情 | 消息类型 |
-| -------- | ------- | ------- | ------ |
-| QQ(官方机器人接口) | ✔    | 私聊、群聊，QQ 频道私聊、群聊 | 文字、图片 |
-| QQ(OneBot)      | ✔    | 私聊、群聊 | 文字、图片、语音 |
-| 微信(个人号)    | ✔    | 微信个人号私聊、群聊 | 文字、图片、语音 |
-| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | 私聊、群聊 | 文字、图片 |
-| [微信(企业微信)](https://github.com/Soulter/astrbot_plugin_wecom)    | ✔    | 私聊 | 文字、图片、语音 |
-| 飞书   | ✔    | 群聊 | 文字、图片 |
-| 微信对话开放平台 | 🚧    | 计划内 | - |
-| Discord   | 🚧    | 计划内 | - |
-| WhatsApp   | 🚧    | 计划内 | - |
-| 小爱音响   | 🚧    | 计划内 | - |
+**官方维护**
+
+| 平台    | 支持性 |
+| -------- | ------- |
+| QQ(官方平台) | ✔    |
+| QQ(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 |
+
+**社区维护**
+
+| 平台    | 支持性 |
+| -------- | ------- |
+| [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)   | ✔    |
+| [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)   | ✔    |
+| [Bilibili 私信](https://github.com/Hina-Chat/astrbot_plugin_bilibili_adapter)   | ✔    |
+| [wxauto](https://github.com/luosheng520qaq/wxauto-repost-onebotv11)   | ✔    |
 
 ## ⚡ 提供商支持情况
 
-| 名称    | 支持性 | 类型 | 备注 |
-| -------- | ------- | ------- | ------- |
-| OpenAI API | ✔    | 文本生成 | 同时也支持 DeepSeek、Google Gemini、GLM（智谱）、Moonshot（月之暗面）、阿里云百炼、硅基流动、xAI 等所有兼容 OpenAI API 的服务 |
-| Claude API | ✔    | 文本生成 |  |
-| Google Gemini API | ✔    | 文本生成 |  |
-| Dify | ✔    | LLMOps |  |
-| DashScope(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 |
-| 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 |  |
-| 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 |
+**大模型服务**
+
+| 名称  | 支持性 | 备注 |
+| -------- | ------- | ------- |
+| OpenAI | ✔    | 支持任何兼容 OpenAI API 的服务 |
+| Anthropic | ✔    |  |
+| Google Gemini | ✔   |  |
+| Moonshot AI | ✔   |  |
+| 智谱 AI | ✔   |  |
+| DeepSeek | ✔   |  |
+| Ollama | ✔     | 本地部署 DeepSeek 等开源语言模型 |
+| LM Studio | ✔    | 本地部署 DeepSeek 等开源语言模型 |
+| [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 | ✔    |  |
+| PPIO 派欧云 | ✔    |  |
+| ModelScope | ✔    |  |
+| OneAPI | ✔    |  |
+| Dify | ✔    |  |
+| 阿里云百炼应用 | ✔    |  |
+| Coze | ✔    |  |
+
+**语音转文本服务**
+
+| 名称  | 支持性 | 备注 |
+| -------- | ------- | ------- |
+| Whisper | ✔    | 支持 API、本地部署 |
+| SenseVoice | ✔   | 本地部署 |
+
+**文本转语音服务**
+
+| 名称  | 支持性 | 备注 |
+| -------- | ------- | ------- |
+| OpenAI TTS | ✔    |  |
+| Gemini TTS | ✔    |  |
+| GSVI | ✔    | GPT-Sovits-Inference |
+| GPT-SoVITs | ✔     | GPT-Sovits |
+| FishAudio | ✔    | |
+| Edge TTS | ✔    | Edge 浏览器的免费 TTS |
+| 阿里云百炼 TTS | ✔    |  |
+| Azure TTS | ✔   | |
+| Minimax TTS | ✔   | |
+| 火山引擎 TTS | ✔   | |
 
 ## ❤️ 贡献
 
@@ -121,78 +210,34 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 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
+## ❤️ Special Thanks
 
-- Star 这个项目！
-- 在[爱发电](https://afdian.com/a/soulter)支持我！
-- 在[微信](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)支持我~
+特别感谢所有 Contributors 和插件开发者对 AstrBot 的贡献 ❤️
 
-## ✨ Demo
+<a href="https://github.com/AstrBotDevs/AstrBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
+</a>
 
-> [!NOTE]
-> 代码执行器的文件输入/输出目前仅测试了 Napcat(QQ), Lagrange(QQ)
+此外，本项目的诞生离不开以下开源项目的帮助：
 
-<div align='center'>
-
-<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 测试中）✨_
-
-<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/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
-
-_✨ 自然语言待办事项 ✨_
-
-<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/592a8630-14c7-4e06-b496-9c0386e4f36c" width=600>
-
-_✨ 管理面板 ✨_
-
-![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
-
-_✨ 内置 Web Chat，在线与机器人交互 ✨_
-
-</div>
+- [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - 伟大的猫猫框架
 
 ## ⭐ 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
+> 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>
 
-## Disclaimer
-
-1. The project is protected under the `AGPL-v3` opensource license.
-2. The deployment of WeChat (personal account) utilizes [Gewechat](https://github.com/Devo919/Gewechat) service. AstrBot only guarantees connectivity with Gewechat and recommends using a WeChat account that is not frequently used. In the event of account risk control, the author of this project shall not bear any responsibility.
-3. Please ensure compliance with local laws and regulations when using this project.
-
-<!-- ## ✨ ATRI [Beta 测试]
-
-该功能作为插件载入。插件仓库地址：[astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
-
-1. 基于《ATRI ~ My Dear Moments》主角 ATRI 角色台词作为微调数据集的 `Qwen1.5-7B-Chat Lora` 微调模型。
-2. 长期记忆
-3. 表情包理解与回复
-4. TTS
-    -->
-
+</details>
 
 _私は、高性能ですから!_
-

README_en.md

@@ -10,16 +10,16 @@ _✨ Easy-to-use Multi-platform LLM Chatbot & Development Framework ✨_
 
 <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)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/AstrBotDevs/AstrBot)](https://github.com/AstrBotDevs/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://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot"/></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)
+[![codecov](https://codecov.io/gh/AstrBotDevs/AstrBot/graph/badge.svg?token=FF3P5967B8)](https://codecov.io/gh/AstrBotDevs/AstrBot)
 
 <a href="https://astrbot.app/">Documentation</a> ｜
-<a href="https://github.com/Soulter/AstrBot/issues">Issue Tracking</a>
+<a href="https://github.com/AstrBotDevs/AstrBot/issues">Issue Tracking</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.
@@ -28,7 +28,7 @@ AstrBot is a loosely coupled, asynchronous chatbot and development framework tha
 
 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://astrbot.app/others/dify.html) for easy access to Dify assistants/knowledge bases/workflows.
+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.
@@ -49,7 +49,7 @@ Requires Python (>3.10). See docs: [Windows Installer Guide](https://astrbot.app
 
 #### Replit Deployment
 
-[![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)
 
 #### CasaOS Deployment
 
@@ -67,8 +67,8 @@ See docs: [Source Code Deployment](https://astrbot.app/deploy/astrbot/cli.html)
 | 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 |
+| [Telegram](https://github.com/AstrBotDevs/AstrBot_plugin_telegram) | ✔      | Private/Group chats | Text, Images        |
+| [WeChat Work](https://github.com/AstrBotDevs/AstrBot_plugin_wecom) | ✔      | Private chats       | Text, Images, Voice |
 | Feishu                                                         | ✔      | Group chats         | Text, Images        |
 | WeChat Open Platform                                           | 🚧      | Planned             | -                   |
 | Discord                                                        | 🚧      | Planned             | -                   |
@@ -157,7 +157,7 @@ _✨ Built-in Web Chat Interface ✨_
 
 <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>
 
@@ -169,7 +169,7 @@ _✨ Built-in Web Chat Interface ✨_
 
 <!-- ## ✨ ATRI [Beta]
 
-Available as plugin: [astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
+Available as plugin: [astrbot_plugin_atri](https://github.com/AstrBotDevs/AstrBot_plugin_atri)
 
 1. Qwen1.5-7B-Chat Lora model fine-tuned with ATRI character data
 2. Long-term memory

README_ja.md

@@ -10,16 +10,16 @@ _✨ 簡単に使えるマルチプラットフォーム LLM チャットボッ
 
 <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)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/AstrBotDevs/AstrBot)](https://github.com/AstrBotDevs/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)
+[![codecov](https://codecov.io/gh/AstrBotDevs/AstrBot/graph/badge.svg?token=FF3P5967B8)](https://codecov.io/gh/AstrBotDevs/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://github.com/AstrBotDevs/AstrBot/issues">問題を報告する</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。
@@ -27,8 +27,8 @@ AstrBot は、疎結合、非同期、複数のメッセージプラットフォ
 ## ✨ 主な機能
 
 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、WeChat（Gewechat）、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://astrbot.app/others/dify.html)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。
+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。
@@ -50,7 +50,7 @@ AstrBot は、疎結合、非同期、複数のメッセージプラットフォ
 
 #### Replit デプロイ
 
-[![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)
 
 #### CasaOS デプロイ
 
@@ -152,8 +152,7 @@ _✨ 内蔵 Web Chat、オンラインでボットと対話 ✨_
 ## 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. WeChat（個人アカウント）のデプロイメントには [Gewechat](https://github.com/Devo919/Gewechat) サービスを利用しています。AstrBot は Gewechat との接続を保証するだけであり、アカウントのリスク管理に関しては、このプロジェクトの著者は一切の責任を負いません。
-3. 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。
+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]
 
@@ -165,6 +164,4 @@ _✨ 内蔵 Web Chat、オンラインでボットと対話 ✨_
 4. TTS
     -->
 
-
 _私は、高性能ですから!_
-

astrbot/api/__init__.py

@@ -1,7 +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 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", "html_renderer", "llm_tool", "sp"]
+__all__ = [
+    "AstrBotConfig",
+    "BaseFunctionToolExecutor",
+    "FunctionTool",
+    "ToolSet",
+    "agent",
+    "html_renderer",
+    "llm_tool",
+    "logger",
+    "sp",
+]

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 +1,52 @@
-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_platform_loaded as on_platform_loaded
+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",
+    "permission_type",
+    "platform_adapter_type",
+    "regex",
 ]

astrbot/api/platform/__init__.py

@@ -1,21 +1,22 @@
+from astrbot.core.message.components import *
 from astrbot.core.platform import (
-    AstrMessageEvent,
-    Platform,
     AstrBotMessage,
+    AstrMessageEvent,
+    Group,
     MessageMember,
     MessageType,
+    Platform,
     PlatformMetadata,
 )
-
 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",
 ]

astrbot/api/provider/__init__.py

@@ -1,17 +1,17 @@
-from astrbot.core.provider import Provider, STTProvider, Personality
-from astrbot.core.provider.entites import (
+from astrbot.core.provider import Personality, 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

@@ -1,12 +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
-from astrbot.core.star.config import *
-
-__all__ = [
-    "register",
-    "Context",
-    "Star",
-]
+__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/cli/__init__.py

@@ -0,0 +1 @@
+__version__ = "3.5.23"

astrbot/cli/__main__.py

@@ -0,0 +1,59 @@
+"""AstrBot CLI入口"""
+
+import sys
+
+import click
+
+from . import __version__
+from .commands import conf, init, plug, run
+
+logo_tmpl = r"""
+     ___           _______.___________..______      .______     ______   .___________.
+    /   \         /       |           ||   _  \     |   _  \   /  __  \  |           |
+   /  ^  \       |   (----`---|  |----`|  |_)  |    |  |_)  | |  |  |  | `---|  |----`
+  /  /_\  \       \   \       |  |     |      /     |   _  <  |  |  |  |     |  |
+ /  _____  \  .----)   |      |  |     |  |\  \----.|  |_)  | |  `--'  |     |  |
+/__/     \__\ |_______/       |__|     | _| `._____||______/   \______/      |__|
+"""
+
+
+@click.group()
+@click.version_option(__version__, prog_name="AstrBot")
+def cli() -> None:
+    """The AstrBot CLI"""
+    click.echo(logo_tmpl)
+    click.echo("Welcome to AstrBot CLI!")
+    click.echo(f"AstrBot CLI version: {__version__}")
+
+
+@click.command()
+@click.argument("command_name", required=False, type=str)
+def help(command_name: str | None) -> None:
+    """显示命令的帮助信息
+
+    如果提供了 COMMAND_NAME，则显示该命令的详细帮助信息。
+    否则，显示通用帮助信息。
+    """
+    ctx = click.get_current_context()
+    if command_name:
+        # 查找指定命令
+        command = cli.get_command(ctx, command_name)
+        if command:
+            # 显示特定命令的帮助信息
+            click.echo(command.get_help(ctx))
+        else:
+            click.echo(f"Unknown command: {command_name}")
+            sys.exit(1)
+    else:
+        # 显示通用帮助信息
+        click.echo(cli.get_help(ctx))
+
+
+cli.add_command(init)
+cli.add_command(run)
+cli.add_command(help)
+cli.add_command(plug)
+cli.add_command(conf)
+
+if __name__ == "__main__":
+    cli()

astrbot/cli/commands/__init__.py

@@ -0,0 +1,6 @@
+from .cmd_conf import conf
+from .cmd_init import init
+from .cmd_plug import plug
+from .cmd_run import run
+
+__all__ = ["conf", "init", "plug", "run"]

astrbot/cli/commands/cmd_conf.py

@@ -0,0 +1,209 @@
+import hashlib
+import json
+import zoneinfo
+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:
+    """验证日志级别"""
+    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",
+        )
+    return value
+
+
+def _validate_dashboard_port(value: str) -> int:
+    """验证 Dashboard 端口"""
+    try:
+        port = int(value)
+        if port < 1 or port > 65535:
+            raise click.ClickException("端口必须在 1-65535 范围内")
+        return port
+    except ValueError:
+        raise click.ClickException("端口必须是数字")
+
+
+def _validate_dashboard_username(value: str) -> str:
+    """验证 Dashboard 用户名"""
+    if not value:
+        raise click.ClickException("用户名不能为空")
+    return value
+
+
+def _validate_dashboard_password(value: str) -> str:
+    """验证 Dashboard 密码"""
+    if not value:
+        raise click.ClickException("密码不能为空")
+    return hashlib.md5(value.encode()).hexdigest()
+
+
+def _validate_timezone(value: str) -> str:
+    """验证时区"""
+    try:
+        zoneinfo.ZoneInfo(value)
+    except Exception:
+        raise click.ClickException(f"无效的时区: {value}，请使用有效的IANA时区名称")
+    return value
+
+
+def _validate_callback_api_base(value: str) -> str:
+    """验证回调接口基址"""
+    if not value.startswith("http://") and not value.startswith("https://"):
+        raise click.ClickException("回调接口基址必须以 http:// 或 https:// 开头")
+    return value
+
+
+# 可通过CLI设置的配置项，配置键到验证器函数的映射
+CONFIG_VALIDATORS: dict[str, Callable[[str], Any]] = {
+    "timezone": _validate_timezone,
+    "log_level": _validate_log_level,
+    "dashboard.port": _validate_dashboard_port,
+    "dashboard.username": _validate_dashboard_username,
+    "dashboard.password": _validate_dashboard_password,
+    "callback_api_base": _validate_callback_api_base,
+}
+
+
+def _load_config() -> dict[str, Any]:
+    """加载或初始化配置文件"""
+    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",
+        )
+
+    config_path = root / "data" / "cmd_config.json"
+    if not config_path.exists():
+        from astrbot.core.config.default import DEFAULT_CONFIG
+
+        config_path.write_text(
+            json.dumps(DEFAULT_CONFIG, ensure_ascii=False, indent=2),
+            encoding="utf-8-sig",
+        )
+
+    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: {e!s}")
+
+
+def _save_config(config: dict[str, Any]) -> None:
+    """保存配置文件"""
+    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",
+    )
+
+
+def _set_nested_item(obj: dict[str, Any], path: str, value: Any) -> None:
+    """设置嵌套字典中的值"""
+    parts = path.split(".")
+    for part in parts[:-1]:
+        if part not in obj:
+            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",
+            )
+        obj = obj[part]
+    obj[parts[-1]] = value
+
+
+def _get_nested_item(obj: dict[str, Any], path: str) -> Any:
+    """获取嵌套字典中的值"""
+    parts = path.split(".")
+    for part in parts:
+        obj = obj[part]
+    return obj
+
+
+@click.group(name="conf")
+def conf():
+    """配置管理命令
+
+    支持的配置项:
+
+    - timezone: 时区设置 (例如: Asia/Shanghai)
+
+    - log_level: 日志级别 (DEBUG/INFO/WARNING/ERROR/CRITICAL)
+
+    - dashboard.port: Dashboard 端口
+
+    - dashboard.username: Dashboard 用户名
+
+    - dashboard.password: Dashboard 密码
+
+    - callback_api_base: 回调接口基址
+    """
+
+
+@conf.command(name="set")
+@click.argument("key")
+@click.argument("value")
+def set_config(key: str, value: str):
+    """设置配置项的值"""
+    if key not in CONFIG_VALIDATORS:
+        raise click.ClickException(f"不支持的配置项: {key}")
+
+    config = _load_config()
+
+    try:
+        old_value = _get_nested_item(config, key)
+        validated_value = CONFIG_VALIDATORS[key](value)
+        _set_nested_item(config, key, validated_value)
+        _save_config(config)
+
+        click.echo(f"配置已更新: {key}")
+        if key == "dashboard.password":
+            click.echo("  原值: ********")
+            click.echo("  新值: ********")
+        else:
+            click.echo(f"  原值: {old_value}")
+            click.echo(f"  新值: {validated_value}")
+
+    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: {e!s}")
+
+
+@conf.command(name="get")
+@click.argument("key", required=False)
+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:
+            raise click.ClickException(f"不支持的配置项: {key}")
+
+        try:
+            value = _get_nested_item(config, key)
+            if key == "dashboard.password":
+                value = "********"
+            click.echo(f"{key}: {value}")
+        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: {e!s}")
+    else:
+        click.echo("当前配置:")
+        for key in CONFIG_VALIDATORS:
+            try:
+                value = (
+                    "********"
+                    if key == "dashboard.password"
+                    else _get_nested_item(config, key)
+                )
+                click.echo(f"  {key}: {value}")
+            except (KeyError, TypeError):
+                pass

astrbot/cli/commands/cmd_init.py

@@ -0,0 +1,56 @@
+import asyncio
+from pathlib import Path
+
+import click
+from filelock import FileLock, Timeout
+
+from ..utils import check_dashboard, get_astrbot_root
+
+
+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。",
+        )
+        if click.confirm(
+            f"请检查当前目录是否正确，确认正确请回车: {astrbot_root}",
+            default=True,
+            abort=True,
+        ):
+            dot_astrbot.touch()
+            click.echo(f"Created {dot_astrbot}")
+
+    paths = {
+        "data": astrbot_root / "data",
+        "config": astrbot_root / "data" / "config",
+        "plugins": astrbot_root / "data" / "plugins",
+        "temp": astrbot_root / "data" / "temp",
+    }
+
+    for name, path in paths.items():
+        path.mkdir(parents=True, exist_ok=True)
+        click.echo(f"{'Created' if not path.exists() else 'Directory exists'}: {path}")
+
+    await check_dashboard(astrbot_root / "data")
+
+
+@click.command()
+def init() -> None:
+    """初始化 AstrBot"""
+    click.echo("Initializing AstrBot...")
+    astrbot_root = get_astrbot_root()
+    lock_file = astrbot_root / "astrbot.lock"
+    lock = FileLock(lock_file, timeout=5)
+
+    try:
+        with lock.acquire():
+            asyncio.run(initialize_astrbot(astrbot_root))
+    except Timeout:
+        raise click.ClickException("无法获取锁文件，请检查是否有其他实例正在运行")
+
+    except Exception as e:
+        raise click.ClickException(f"初始化失败: {e!s}")

astrbot/cli/commands/cmd_plug.py

@@ -0,0 +1,245 @@
+import re
+import shutil
+from pathlib import Path
+
+import click
+
+from ..utils import (
+    PluginStatus,
+    build_plug_list,
+    check_astrbot_root,
+    get_astrbot_root,
+    get_git_repo,
+    manage_plugin,
+)
+
+
+@click.group()
+def plug():
+    """插件管理"""
+
+
+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",
+        )
+    return (base / "data").resolve()
+
+
+def display_plugins(plugins, title=None, color=None):
+    if title:
+        click.echo(click.style(title, fg=color, bold=True))
+
+    click.echo(f"{'名称':<20} {'版本':<10} {'状态':<10} {'作者':<15} {'描述':<30}")
+    click.echo("-" * 85)
+
+    for p in plugins:
+        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}",
+        )
+
+
+@plug.command()
+@click.argument("name")
+def new(name: str):
+    """创建新插件"""
+    base_path = _get_data_path()
+    plug_path = base_path / "plugins" / name
+
+    if plug_path.exists():
+        raise click.ClickException(f"插件 {name} 已存在")
+
+    author = click.prompt("请输入插件作者", type=str)
+    desc = click.prompt("请输入插件描述", type=str)
+    version = click.prompt("请输入插件版本", type=str)
+    if not re.match(r"^\d+\.\d+(\.\d+)?$", version.lower().lstrip("v")):
+        raise click.ClickException("版本号必须为 x.y 或 x.y.z 格式")
+    repo = click.prompt("请输入插件仓库：", type=str)
+    if not repo.startswith("http"):
+        raise click.ClickException("仓库地址必须以 http 开头")
+
+    click.echo("下载插件模板...")
+    get_git_repo(
+        "https://github.com/Soulter/helloworld",
+        plug_path,
+    )
+
+    click.echo("重写插件信息...")
+    # 重写 metadata.yaml
+    with open(plug_path / "metadata.yaml", "w", encoding="utf-8") as f:
+        f.write(
+            f"name: {name}\n"
+            f"desc: {desc}\n"
+            f"version: {version}\n"
+            f"author: {author}\n"
+            f"repo: {repo}\n",
+        )
+
+    # 重写 README.md
+    with open(plug_path / "README.md", "w", encoding="utf-8") as f:
+        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", encoding="utf-8") as f:
+        content = f.read()
+
+    new_content = content.replace(
+        '@register("helloworld", "YourName", "一个简单的 Hello World 插件", "1.0.0")',
+        f'@register("{name}", "{author}", "{desc}", "{version}")',
+    )
+
+    with open(plug_path / "main.py", "w", encoding="utf-8") as f:
+        f.write(new_content)
+
+    click.echo(f"插件 {name} 创建成功")
+
+
+@plug.command()
+@click.option("--all", "-a", is_flag=True, help="列出未安装的插件")
+def list(all: bool):
+    """列出插件"""
+    base_path = _get_data_path()
+    plugins = build_plug_list(base_path / "plugins")
+
+    # 未发布的插件
+    not_published_plugins = [
+        p for p in plugins if p["status"] == PluginStatus.NOT_PUBLISHED
+    ]
+    if not_published_plugins:
+        display_plugins(not_published_plugins, "未发布的插件", "red")
+
+    # 需要更新的插件
+    need_update_plugins = [
+        p for p in plugins if p["status"] == PluginStatus.NEED_UPDATE
+    ]
+    if need_update_plugins:
+        display_plugins(need_update_plugins, "需要更新的插件", "yellow")
+
+    # 已安装的插件
+    installed_plugins = [p for p in plugins if p["status"] == PluginStatus.INSTALLED]
+    if installed_plugins:
+        display_plugins(installed_plugins, "已安装的插件", "green")
+
+    # 未安装的插件
+    not_installed_plugins = [
+        p for p in plugins if p["status"] == PluginStatus.NOT_INSTALLED
+    ]
+    if not_installed_plugins and all:
+        display_plugins(not_installed_plugins, "未安装的插件", "blue")
+
+    if (
+        not any([not_published_plugins, need_update_plugins, installed_plugins])
+        and not all
+    ):
+        click.echo("未安装任何插件")
+
+
+@plug.command()
+@click.argument("name")
+@click.option("--proxy", help="代理服务器地址")
+def install(name: str, proxy: str | None):
+    """安装插件"""
+    base_path = _get_data_path()
+    plug_path = base_path / "plugins"
+    plugins = build_plug_list(base_path / "plugins")
+
+    plugin = next(
+        (
+            p
+            for p in plugins
+            if p["name"] == name and p["status"] == PluginStatus.NOT_INSTALLED
+        ),
+        None,
+    )
+
+    if not plugin:
+        raise click.ClickException(f"未找到可安装的插件 {name}，可能是不存在或已安装")
+
+    manage_plugin(plugin, plug_path, is_update=False, proxy=proxy)
+
+
+@plug.command()
+@click.argument("name")
+def remove(name: str):
+    """卸载插件"""
+    base_path = _get_data_path()
+    plugins = build_plug_list(base_path / "plugins")
+    plugin = next((p for p in plugins if p["name"] == name), None)
+
+    if not plugin or not plugin.get("local_path"):
+        raise click.ClickException(f"插件 {name} 不存在或未安装")
+
+    plugin_path = plugin["local_path"]
+
+    click.confirm(f"确定要卸载插件 {name} 吗?", default=False, abort=True)
+
+    try:
+        shutil.rmtree(plugin_path)
+        click.echo(f"插件 {name} 已卸载")
+    except Exception as e:
+        raise click.ClickException(f"卸载插件 {name} 失败: {e}")
+
+
+@plug.command()
+@click.argument("name", required=False)
+@click.option("--proxy", help="Github代理地址")
+def update(name: str, proxy: str | None):
+    """更新插件"""
+    base_path = _get_data_path()
+    plug_path = base_path / "plugins"
+    plugins = build_plug_list(base_path / "plugins")
+
+    if name:
+        plugin = next(
+            (
+                p
+                for p in plugins
+                if p["name"] == name and p["status"] == PluginStatus.NEED_UPDATE
+            ),
+            None,
+        )
+
+        if not plugin:
+            raise click.ClickException(f"插件 {name} 不需要更新或无法更新")
+
+        manage_plugin(plugin, plug_path, is_update=True, proxy=proxy)
+    else:
+        need_update_plugins = [
+            p for p in plugins if p["status"] == PluginStatus.NEED_UPDATE
+        ]
+
+        if not need_update_plugins:
+            click.echo("没有需要更新的插件")
+            return
+
+        click.echo(f"发现 {len(need_update_plugins)} 个插件需要更新")
+        for plugin in need_update_plugins:
+            plugin_name = plugin["name"]
+            click.echo(f"正在更新插件 {plugin_name}...")
+            manage_plugin(plugin, plug_path, is_update=True, proxy=proxy)
+
+
+@plug.command()
+@click.argument("query")
+def search(query: str):
+    """搜索插件"""
+    base_path = _get_data_path()
+    plugins = build_plug_list(base_path / "plugins")
+
+    matched_plugins = [
+        p
+        for p in plugins
+        if query.lower() in p["name"].lower()
+        or query.lower() in p["desc"].lower()
+        or query.lower() in p["author"].lower()
+    ]
+
+    if not matched_plugins:
+        click.echo(f"未找到匹配 '{query}' 的插件")
+        return
+
+    display_plugins(matched_plugins, f"搜索结果: '{query}'", "cyan")

astrbot/cli/commands/cmd_run.py

@@ -0,0 +1,62 @@
+import asyncio
+import os
+import sys
+import traceback
+from pathlib import Path
+
+import click
+from filelock import FileLock, Timeout
+
+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 LogBroker, LogManager, db_helper, logger
+    from astrbot.core.initial_loader import InitialLoader
+
+    await check_dashboard(astrbot_root / "data")
+
+    log_broker = LogBroker()
+    LogManager.set_queue_handler(logger, log_broker)
+    db = db_helper
+
+    core_lifecycle = InitialLoader(db, log_broker)
+
+    await core_lifecycle.start()
+
+
+@click.option("--reload", "-r", is_flag=True, help="插件自动重载")
+@click.option("--port", "-p", help="Astrbot Dashboard端口", required=False, type=str)
+@click.command()
+def run(reload: bool, port: str) -> None:
+    """运行 AstrBot"""
+    try:
+        os.environ["ASTRBOT_CLI"] = "1"
+        astrbot_root = get_astrbot_root()
+
+        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",
+            )
+
+        os.environ["ASTRBOT_ROOT"] = str(astrbot_root)
+        sys.path.insert(0, str(astrbot_root))
+
+        if port:
+            os.environ["DASHBOARD_PORT"] = port
+
+        if reload:
+            click.echo("启用插件自动重载")
+            os.environ["ASTRBOT_RELOAD"] = "1"
+
+        lock_file = astrbot_root / "astrbot.lock"
+        lock = FileLock(lock_file, timeout=5)
+        with lock.acquire():
+            asyncio.run(run_astrbot(astrbot_root))
+    except KeyboardInterrupt:
+        click.echo("AstrBot 已关闭...")
+    except Timeout:
+        raise click.ClickException("无法获取锁文件，请检查是否有其他实例正在运行")
+    except Exception as e:
+        raise click.ClickException(f"运行时出现错误: {e}\n{traceback.format_exc()}")

astrbot/cli/utils/__init__.py

@@ -0,0 +1,18 @@
+from .basic import (
+    check_astrbot_root,
+    check_dashboard,
+    get_astrbot_root,
+)
+from .plugin import PluginStatus, build_plug_list, get_git_repo, manage_plugin
+from .version_comparator import VersionComparator
+
+__all__ = [
+    "PluginStatus",
+    "VersionComparator",
+    "build_plug_list",
+    "check_astrbot_root",
+    "check_dashboard",
+    "get_astrbot_root",
+    "get_git_repo",
+    "manage_plugin",
+]

astrbot/cli/utils/basic.py

@@ -0,0 +1,76 @@
+from pathlib import Path
+
+import click
+
+
+def check_astrbot_root(path: str | Path) -> bool:
+    """检查路径是否为 AstrBot 根目录"""
+    if not isinstance(path, Path):
+        path = Path(path)
+    if not path.exists() or not path.is_dir():
+        return False
+    if not (path / ".astrbot").exists():
+        return False
+    return True
+
+
+def get_astrbot_root() -> Path:
+    """获取Astrbot根目录路径"""
+    return Path.cwd()
+
+
+async def check_dashboard(astrbot_root: Path) -> None:
+    """检查是否安装了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:
+        dashboard_version = await get_dashboard_version()
+        match dashboard_version:
+            case None:
+                click.echo("未安装管理面板")
+                if click.confirm(
+                    "是否安装管理面板？",
+                    default=True,
+                    abort=True,
+                ):
+                    click.echo("正在安装管理面板...")
+                    await download_dashboard(
+                        path="data/dashboard.zip",
+                        extract_path=str(astrbot_root),
+                        version=f"v{VERSION}",
+                        latest=False,
+                    )
+                    click.echo("管理面板安装完成")
+
+            case str():
+                if VersionComparator.compare_version(VERSION, dashboard_version) <= 0:
+                    click.echo("管理面板已是最新版本")
+                    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:
+            await download_dashboard(
+                path=str(astrbot_root / "dashboard.zip"),
+                extract_path=str(astrbot_root),
+                version=f"v{VERSION}",
+                latest=False,
+            )
+            click.echo("管理面板初始化完成")
+        except Exception as e:
+            click.echo(f"下载管理面板失败: {e}")
+            return

astrbot/cli/utils/plugin.py

@@ -0,0 +1,246 @@
+import shutil
+import tempfile
+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
+
+
+class PluginStatus(str, Enum):
+    INSTALLED = "已安装"
+    NEED_UPDATE = "需更新"
+    NOT_INSTALLED = "未安装"
+    NOT_PUBLISHED = "未发布"
+
+
+def get_git_repo(url: str, target_path: Path, proxy: str | None = None):
+    """从 Git 仓库下载代码并解压到指定路径"""
+    temp_dir = Path(tempfile.mkdtemp())
+    try:
+        # 解析仓库信息
+        repo_namespace = url.split("/")[-2:]
+        author = repo_namespace[0]
+        repo = repo_namespace[1]
+
+        # 尝试获取最新的 release
+        release_url = f"https://api.github.com/repos/{author}/{repo}/releases"
+        try:
+            with httpx.Client(
+                proxy=proxy if proxy else None,
+                follow_redirects=True,
+            ) as client:
+                resp = client.get(release_url)
+                resp.raise_for_status()
+                releases = resp.json()
+
+                if releases:
+                    # 使用最新的 release
+                    download_url = releases[0]["zipball_url"]
+                else:
+                    # 没有 release，使用默认分支
+                    click.echo(f"正在从默认分支下载 {author}/{repo}")
+                    download_url = f"https://github.com/{author}/{repo}/archive/refs/heads/master.zip"
+        except Exception as e:
+            click.echo(f"获取 release 信息失败: {e}，将直接使用提供的 URL")
+            download_url = url
+
+        # 应用代理
+        if proxy:
+            download_url = f"{proxy}/{download_url}"
+
+        # 下载并解压
+        with httpx.Client(
+            proxy=proxy if proxy else None,
+            follow_redirects=True,
+        ) as client:
+            resp = client.get(download_url)
+            if (
+                resp.status_code == 404
+                and "archive/refs/heads/master.zip" in download_url
+            ):
+                alt_url = download_url.replace("master.zip", "main.zip")
+                click.echo("master 分支不存在，尝试下载 main 分支")
+                resp = client.get(alt_url)
+                resp.raise_for_status()
+            else:
+                resp.raise_for_status()
+            zip_content = BytesIO(resp.content)
+        with ZipFile(zip_content) as z:
+            z.extractall(temp_dir)
+            namelist = z.namelist()
+            root_dir = Path(namelist[0]).parts[0] if namelist else ""
+            if target_path.exists():
+                shutil.rmtree(target_path)
+            shutil.move(temp_dir / root_dir, target_path)
+    finally:
+        if temp_dir.exists():
+            shutil.rmtree(temp_dir, ignore_errors=True)
+
+
+def load_yaml_metadata(plugin_dir: Path) -> dict:
+    """从 metadata.yaml 文件加载插件元数据
+
+    Args:
+        plugin_dir: 插件目录路径
+
+    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():
+        try:
+            return yaml.safe_load(yaml_path.read_text(encoding="utf-8")) or {}
+        except Exception as e:
+            click.echo(f"读取 {yaml_path} 失败: {e}", err=True)
+    return {}
+
+
+def build_plug_list(plugins_dir: Path) -> list:
+    """构建插件列表，包含本地和在线插件信息
+
+    Args:
+        plugins_dir (Path): 插件目录路径
+
+    Returns:
+        list: 包含插件信息的字典列表
+
+    """
+    # 获取本地插件信息
+    result = []
+    if plugins_dir.exists():
+        for plugin_name in [d.name for d in plugins_dir.glob("*") if d.is_dir()]:
+            plugin_dir = plugins_dir / plugin_name
+
+            # 从 metadata.yaml 加载元数据
+            metadata = load_yaml_metadata(plugin_dir)
+
+            if "desc" not in metadata and "description" in metadata:
+                metadata["desc"] = metadata["description"]
+
+            # 如果成功加载元数据，添加到结果列表
+            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),
+                    },
+                )
+
+    # 获取在线插件列表
+    online_plugins = []
+    try:
+        with httpx.Client() as client:
+            resp = client.get("https://api.soulter.top/astrbot/plugins")
+            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,
+                    },
+                )
+    except Exception as e:
+        click.echo(f"获取在线插件列表失败: {e}", err=True)
+
+    # 与在线插件比对，更新状态
+    online_plugin_names = {plugin["name"] for plugin in online_plugins}
+    for local_plugin in result:
+        if local_plugin["name"] in online_plugin_names:
+            # 查找对应的在线插件
+            online_plugin = next(
+                p for p in online_plugins if p["name"] == local_plugin["name"]
+            )
+            if (
+                VersionComparator.compare_version(
+                    local_plugin["version"],
+                    online_plugin["version"],
+                )
+                < 0
+            ):
+                local_plugin["status"] = PluginStatus.NEED_UPDATE
+        else:
+            # 本地插件未在线上发布
+            local_plugin["status"] = PluginStatus.NOT_PUBLISHED
+
+    # 添加未安装的在线插件
+    for online_plugin in online_plugins:
+        if not any(plugin["name"] == online_plugin["name"] for plugin in result):
+            result.append(online_plugin)
+
+    return result
+
+
+def manage_plugin(
+    plugin: dict,
+    plugins_dir: Path,
+    is_update: bool = False,
+    proxy: str | None = None,
+) -> None:
+    """安装或更新插件
+
+    Args:
+        plugin (dict): 插件信息字典
+        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"]
+
+    # 如果是更新且有本地路径，直接使用本地路径
+    if is_update and plugin.get("local_path"):
+        target_path = Path(plugin["local_path"])
+    else:
+        target_path = plugins_dir / plugin_name
+
+    backup_path = Path(f"{target_path}_backup") if is_update else None
+
+    # 检查插件是否存在
+    if is_update and not target_path.exists():
+        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 is not None and backup_path.exists():
+        shutil.rmtree(backup_path)
+    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}...",
+        )
+        get_git_repo(repo_url, target_path, proxy)
+
+        # 更新成功，删除备份
+        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 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}",
+        )

astrbot/cli/utils/version_comparator.py

@@ -0,0 +1,90 @@
+"""拷贝自 astrbot.core.utils.version_comparator"""
+
+import re
+
+
+class VersionComparator:
+    @staticmethod
+    def compare_version(v1: str, v2: str) -> int:
+        """根据 Semver 语义版本规范来比较版本号的大小。支持不仅局限于 3 个数字的版本号，并处理预发布标签。
+
+        参考: https://semver.org/lang/zh-CN/
+
+        返回 1 表示 v1 > v2，返回 -1 表示 v1 < v2，返回 0 表示 v1 = v2。
+        """
+        v1 = v1.lower().replace("v", "")
+        v2 = v2.lower().replace("v", "")
+
+        def split_version(version):
+            match = re.match(
+                r"^([0-9]+(?:\.[0-9]+)*)(?:-([0-9A-Za-z-]+(?:\.[0-9A-Za-z-]+)*))?(?:\+(.+))?$",
+                version,
+            )
+            if not match:
+                return [], None
+            major_minor_patch = match.group(1).split(".")
+            prerelease = match.group(2)
+            # buildmetadata = match.group(3) # 构建元数据在比较时忽略
+            parts = [int(x) for x in major_minor_patch]
+            prerelease = VersionComparator._split_prerelease(prerelease)
+            return parts, prerelease
+
+        v1_parts, v1_prerelease = split_version(v1)
+        v2_parts, v2_prerelease = split_version(v2)
+
+        # 比较数字部分
+        length = max(len(v1_parts), len(v2_parts))
+        v1_parts.extend([0] * (length - len(v1_parts)))
+        v2_parts.extend([0] * (length - len(v2_parts)))
+
+        for i in range(length):
+            if v1_parts[i] > v2_parts[i]:
+                return 1
+            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
+        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
+        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
+                p2 = v2_prerelease[i] if i < len(v2_prerelease) else None
+
+                if p1 is None and p2 is not None:
+                    return -1
+                if p1 is not None and p2 is None:
+                    return 1
+                if isinstance(p1, int) and isinstance(p2, str):
+                    return -1
+                if isinstance(p1, str) and isinstance(p2, int):
+                    return 1
+                if isinstance(p1, int) and isinstance(p2, int):
+                    if p1 > p2:
+                        return 1
+                    if p1 < p2:
+                        return -1
+                elif isinstance(p1, str) and isinstance(p2, str):
+                    if p1 > p2:
+                        return 1
+                    if p1 < p2:
+                        return -1
+            return 0  # 预发布标签完全相同
+
+        return 0  # 数字部分和预发布标签都相同
+
+    @staticmethod
+    def _split_prerelease(prerelease):
+        if not prerelease:
+            return None
+        parts = prerelease.split(".")
+        result = []
+        for part in parts:
+            if part.isdigit():
+                result.append(int(part))
+            else:
+                result.append(part)
+        return result

astrbot/core/__init__.py

@@ -1,26 +1,31 @@
 import os
-import asyncio
-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
 
-os.makedirs("data", exist_ok=True)
+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
+os.makedirs(get_astrbot_data_path(), exist_ok=True)
+
+DEMO_MODE = os.getenv("DEMO_MODE", False)
 
 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")
-
-if os.environ.get("TESTING", ""):
-    logger.setLevel("DEBUG")
-
 db_helper = SQLiteDatabase(DB_PATH)
-sp = SharedPreferences()  # 简单的偏好设置存储
-pip_installer = PipInstaller(astrbot_config.get("pip_install_arg", ""))
-web_chat_queue = asyncio.Queue(maxsize=32)
-web_chat_back_queue = asyncio.Queue(maxsize=32)
-WEBUI_SK = "Advanced_System_for_Text_Response_and_Bot_Operations_Tool"
+# 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)
+# 文件令牌服务
+file_token_service = FileTokenService()
+pip_installer = PipInstaller(
+    astrbot_config.get("pip_install_arg", ""),
+    astrbot_config.get("pypi_index_url", None),
+)

astrbot/core/agent/agent.py

@@ -0,0 +1,14 @@
+from dataclasses import dataclass
+from typing import 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
+    run_hooks: BaseAgentRunHooks[TContext] | None = None

astrbot/core/agent/handoff.py

@@ -0,0 +1,38 @@
+from typing import Generic
+
+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
+        super().__init__(
+            name=f"transfer_to_{agent.name}",
+            parameters=parameters or self.default_parameters(),
+            description=agent.instructions or self.default_description(agent.name),
+            **kwargs,
+        )
+
+    def default_parameters(self) -> dict:
+        return {
+            "type": "object",
+            "properties": {
+                "input": {
+                    "type": "string",
+                    "description": "The input to be handed off to another agent. This should be a clear and concise request or task.",
+                },
+            },
+        }
+
+    def default_description(self, agent_name: str | None) -> str:
+        agent_name = agent_name or "another"
+        return f"Delegate tasks to {self.name} agent to handle the request."

astrbot/core/agent/hooks.py

@@ -0,0 +1,30 @@
+from typing import Generic
+
+import mcp
+
+from astrbot.core.agent.tool import FunctionTool
+from astrbot.core.provider.entities import LLMResponse
+
+from .run_context import ContextWrapper, TContext
+
+
+class BaseAgentRunHooks(Generic[TContext]):
+    async def on_agent_begin(self, run_context: ContextWrapper[TContext]): ...
+    async def on_tool_start(
+        self,
+        run_context: ContextWrapper[TContext],
+        tool: FunctionTool,
+        tool_args: dict | None,
+    ): ...
+    async def on_tool_end(
+        self,
+        run_context: ContextWrapper[TContext],
+        tool: FunctionTool,
+        tool_args: dict | None,
+        tool_result: mcp.types.CallToolResult | None,
+    ): ...
+    async def on_agent_done(
+        self,
+        run_context: ContextWrapper[TContext],
+        llm_response: LLMResponse,
+    ): ...

astrbot/core/agent/mcp_client.py

@@ -0,0 +1,259 @@
+import asyncio
+import logging
+from contextlib import AsyncExitStack
+from datetime import timedelta
+from typing import Generic
+
+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 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。")
+
+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。",
+    )
+
+
+def _prepare_config(config: dict) -> dict:
+    """准备配置，处理嵌套格式"""
+    if config.get("mcpServers"):
+        first_key = next(iter(config["mcpServers"]))
+        config = config["mcpServers"][first_key]
+    config.pop("active", None)
+    return config
+
+
+async def _quick_test_mcp_connection(config: dict) -> tuple[bool, str]:
+    """快速测试 MCP 服务器可达性"""
+    import aiohttp
+
+    cfg = _prepare_config(config.copy())
+
+    url = cfg["url"]
+    headers = cfg.get("headers", {})
+    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 连接配置缺少 transport 或 type 字段")
+
+        async with aiohttp.ClientSession() as session:
+            if transport_type == "streamable_http":
+                test_payload = {
+                    "jsonrpc": "2.0",
+                    "method": "initialize",
+                    "id": 0,
+                    "params": {
+                        "protocolVersion": "2024-11-05",
+                        "capabilities": {},
+                        "clientInfo": {"name": "test-client", "version": "1.2.3"},
+                    },
+                }
+                async with session.post(
+                    url,
+                    headers={
+                        **headers,
+                        "Content-Type": "application/json",
+                        "Accept": "application/json, text/event-stream",
+                    },
+                    json=test_payload,
+                    timeout=aiohttp.ClientTimeout(total=timeout),
+                ) as response:
+                    if response.status == 200:
+                        return True, ""
+                    return False, f"HTTP {response.status}: {response.reason}"
+            else:
+                async with session.get(
+                    url,
+                    headers={
+                        **headers,
+                        "Accept": "application/json, text/event-stream",
+                    },
+                    timeout=aiohttp.ClientTimeout(total=timeout),
+                ) as response:
+                    if response.status == 200:
+                        return True, ""
+                    return False, f"HTTP {response.status}: {response.reason}"
+
+    except asyncio.TimeoutError:
+        return False, f"连接超时: {timeout}秒"
+    except Exception as e:
+        return False, f"{e!s}"
+
+
+class MCPClient:
+    def __init__(self):
+        # Initialize session and client objects
+        self.session: mcp.ClientSession | None = None
+        self.exit_stack = AsyncExitStack()
+
+        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
+
+        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。
+
+        Args:
+            mcp_server_config (dict): Configuration for the MCP server. See https://modelcontextprotocol.io/quickstart/server
+
+        """
+        cfg = _prepare_config(mcp_server_config.copy())
+
+        def logging_callback(msg: str):
+            # 处理 MCP 服务的错误日志
+            print(f"MCP Server {name} Error: {msg}")
+            self.server_errlogs.append(msg)
+
+        if "url" in cfg:
+            success, error_msg = await _quick_test_mcp_connection(cfg)
+            if not success:
+                raise Exception(error_msg)
+
+            if "transport" in cfg:
+                transport_type = cfg["transport"]
+            elif "type" in cfg:
+                transport_type = cfg["type"]
+            else:
+                raise Exception("MCP 连接配置缺少 transport 或 type 字段")
+
+            if transport_type != "streamable_http":
+                # SSE transport method
+                self._streams_context = sse_client(
+                    url=cfg["url"],
+                    headers=cfg.get("headers", {}),
+                    timeout=cfg.get("timeout", 5),
+                    sse_read_timeout=cfg.get("sse_read_timeout", 60 * 5),
+                )
+                streams = await self.exit_stack.enter_async_context(
+                    self._streams_context,
+                )
+
+                # Create a new client session
+                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),
+                )
+                self._streams_context = streamablehttp_client(
+                    url=cfg["url"],
+                    headers=cfg.get("headers", {}),
+                    timeout=timeout,
+                    sse_read_timeout=sse_read_timeout,
+                    terminate_on_close=cfg.get("terminate_on_close", True),
+                )
+                read_s, write_s, _ = await self.exit_stack.enter_async_context(
+                    self._streams_context,
+                )
+
+                # Create a new client session
+                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:
+            server_params = mcp.StdioServerParameters(
+                **cfg,
+            )
+
+            def callback(msg: str):
+                # 处理 MCP 服务的错误日志
+                self.server_errlogs.append(msg)
+
+            stdio_transport = await self.exit_stack.enter_async_context(
+                mcp.stdio_client(
+                    server_params,
+                    errlog=LogPipe(
+                        level=logging.ERROR,
+                        logger=logger,
+                        identifier=f"MCPServer-{name}",
+                        callback=callback,
+                    ),  # type: ignore
+                ),
+            )
+
+            # Create a new client session
+            self.session = await self.exit_stack.enter_async_context(
+                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 cleanup(self):
+        """Clean up resources"""
+        await self.exit_stack.aclose()
+        self.running_event.set()  # Set the running event to indicate cleanup is done
+
+
+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:
+        session = self.mcp_client.session
+        if not session:
+            raise ValueError("MCP session is not available for MCP function tools.")
+        res = await session.call_tool(
+            name=self.mcp_tool.name,
+            arguments=kwargs,
+            read_timeout_seconds=timedelta(
+                seconds=context.tool_call_timeout,
+            ),
+        )
+        return res

astrbot/core/agent/message.py

@@ -0,0 +1,168 @@
+# 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
+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: str
+
+    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 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: str
+
+
+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."""
+
+
+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]
+    """The content of the message."""
+
+
+class AssistantMessageSegment(Message):
+    """A message segment from the assistant."""
+
+    role: Literal["assistant"] = "assistant"
+    tool_calls: list[ToolCall] | list[dict] | None = None
+
+
+class ToolCallMessageSegment(Message):
+    """A message segment representing a tool call."""
+
+    role: Literal["tool"] = "tool"
+    tool_call_id: str
+
+
+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

@@ -0,0 +1,14 @@
+import typing as T
+from dataclasses import dataclass
+
+from astrbot.core.message.message_event_result import MessageChain
+
+
+class AgentResponseData(T.TypedDict):
+    chain: MessageChain
+
+
+@dataclass
+class AgentResponse:
+    type: str
+    data: AgentResponseData

astrbot/core/agent/run_context.py

@@ -0,0 +1,17 @@
+from dataclasses import dataclass
+from typing import Any, Generic
+
+from typing_extensions import TypeVar
+
+TContext = TypeVar("TContext", default=Any)
+
+
+@dataclass
+class ContextWrapper(Generic[TContext]):
+    """A context for running an agent, which can be used to pass additional data or state."""
+
+    context: TContext
+    tool_call_timeout: int = 60  # Default tool call timeout in seconds
+
+
+NoContext = ContextWrapper[None]

astrbot/core/agent/runners/__init__.py

@@ -0,0 +1,3 @@
+from .base import BaseAgentRunner
+
+__all__ = ["BaseAgentRunner"]

astrbot/core/agent/runners/base.py

@@ -0,0 +1,55 @@
+import abc
+import typing as T
+from enum import Enum, auto
+
+from astrbot.core.provider import Provider
+from astrbot.core.provider.entities import LLMResponse
+
+from ..hooks import BaseAgentRunHooks
+from ..response import AgentResponse
+from ..run_context import ContextWrapper, TContext
+from ..tool_executor import BaseFunctionToolExecutor
+
+
+class AgentState(Enum):
+    """Defines the state of the agent."""
+
+    IDLE = auto()  # Initial state
+    RUNNING = auto()  # Currently processing
+    DONE = auto()  # Completed
+    ERROR = auto()  # Error state
+
+
+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.
+        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."""
+        ...
+
+    @abc.abstractmethod
+    def done(self) -> bool:
+        """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.
+        This method should be called after the agent is done.
+        """
+        ...

astrbot/core/agent/runners/tool_loop_agent_runner.py

@@ -0,0 +1,358 @@
+import sys
+import traceback
+import typing as T
+
+from mcp.types import (
+    BlobResourceContents,
+    CallToolResult,
+    EmbeddedResource,
+    ImageContent,
+    TextContent,
+    TextResourceContents,
+)
+
+from astrbot import logger
+from astrbot.core.message.message_event_result import (
+    MessageChain,
+)
+from astrbot.core.provider.entities import (
+    LLMResponse,
+    ProviderRequest,
+    ToolCallsResult,
+)
+from astrbot.core.provider.provider import Provider
+
+from ..hooks import BaseAgentRunHooks
+from ..message import AssistantMessageSegment, ToolCallMessageSegment
+from ..response import AgentResponseData
+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
+else:
+    from typing_extensions import override
+
+
+class ToolLoopAgentRunner(BaseAgentRunner[TContext]):
+    @override
+    async def reset(
+        self,
+        provider: Provider,
+        request: ProviderRequest,
+        run_context: ContextWrapper[TContext],
+        tool_executor: BaseFunctionToolExecutor[TContext],
+        agent_hooks: BaseAgentRunHooks[TContext],
+        **kwargs: T.Any,
+    ) -> None:
+        self.req = request
+        self.streaming = kwargs.get("streaming", False)
+        self.provider = provider
+        self.final_llm_resp = None
+        self._state = AgentState.IDLE
+        self.tool_executor = tool_executor
+        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
+
+    async def _iter_llm_responses(self) -> T.AsyncGenerator[LLMResponse, None]:
+        """Yields chunks *and* a final LLMResponse."""
+        if self.streaming:
+            stream = self.provider.text_chat_stream(**self.req.__dict__)
+            async for resp in stream:  # type: ignore
+                yield resp
+        else:
+            yield await self.provider.text_chat(**self.req.__dict__)
+
+    @override
+    async def step(self):
+        """Process a single step of the agent.
+        This method should return the result of the step.
+        """
+        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)
+        llm_resp_result = None
+
+        async for llm_response in self._iter_llm_responses():
+            assert isinstance(llm_response, LLMResponse)
+            if llm_response.is_chunk:
+                if llm_response.result_chain:
+                    yield AgentResponse(
+                        type="streaming_delta",
+                        data=AgentResponseData(chain=llm_response.result_chain),
+                    )
+                else:
+                    yield AgentResponse(
+                        type="streaming_delta",
+                        data=AgentResponseData(
+                            chain=MessageChain().message(llm_response.completion_text),
+                        ),
+                    )
+                continue
+            llm_resp_result = llm_response
+            break  # got final response
+
+        if not llm_resp_result:
+            return
+
+        # 处理 LLM 响应
+        llm_resp = llm_resp_result
+
+        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._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'}",
+                    ),
+                ),
+            )
+
+        if not llm_resp.tools_call_name:
+            # 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)
+            try:
+                await self.agent_hooks.on_agent_done(self.run_context, llm_resp)
+            except Exception as e:
+                logger.error(f"Error in on_agent_done hook: {e}", exc_info=True)
+
+        # 返回 LLM 结果
+        if llm_resp.result_chain:
+            yield AgentResponse(
+                type="llm_result",
+                data=AgentResponseData(chain=llm_resp.result_chain),
+            )
+        elif llm_resp.completion_text:
+            yield AgentResponse(
+                type="llm_result",
+                data=AgentResponseData(
+                    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:
+            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):
+                    yield AgentResponse(
+                        type="tool_call_result",
+                        data=AgentResponseData(chain=result),
+                    )
+            # 将结果添加到上下文中
+            tool_calls_result = ToolCallsResult(
+                tool_calls_info=AssistantMessageSegment(
+                    tool_calls=llm_resp.to_openai_to_calls_model(),
+                    content=llm_resp.completion_text,
+                ),
+                tool_calls_result=tool_call_result_blocks,
+            )
+            self.req.append_tool_calls_result(tool_calls_result)
+
+    async def _handle_function_tools(
+        self,
+        req: ProviderRequest,
+        llm_response: LLMResponse,
+    ) -> T.AsyncGenerator[MessageChain | list[ToolCallMessageSegment], None]:
+        """处理函数工具调用。"""
+        tool_call_result_blocks: list[ToolCallMessageSegment] = []
+        logger.info(f"Agent 使用工具: {llm_response.tools_call_name}")
+
+        # 执行函数调用
+        for func_tool_name, func_tool_args, func_tool_id in zip(
+            llm_response.tools_call_name,
+            llm_response.tools_call_args,
+            llm_response.tools_call_ids,
+        ):
+            try:
+                if not req.func_tool:
+                    return
+                func_tool = req.func_tool.get_func(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: 未找到工具 {func_tool_name}",
+                        ),
+                    )
+                    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,
+                        valid_params,
+                    )
+                except Exception as e:
+                    logger.error(f"Error in on_tool_start hook: {e}", exc_info=True)
+
+                executor = self.tool_executor.execute(
+                    tool=func_tool,
+                    run_context=self.run_context,
+                    **valid_params,  # 只传递有效的参数
+                )
+
+                _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)",
+                                ),
+                            )
+                            yield MessageChain(type="tool_direct_result").base64_image(
+                                res.content[0].data,
+                            )
+                        elif isinstance(res.content[0], EmbeddedResource):
+                            resource = res.content[0].resource
+                            if isinstance(resource, TextResourceContents):
+                                tool_call_result_blocks.append(
+                                    ToolCallMessageSegment(
+                                        role="tool",
+                                        tool_call_id=func_tool_id,
+                                        content=resource.text,
+                                    ),
+                                )
+                                yield MessageChain().message(resource.text)
+                            elif (
+                                isinstance(resource, BlobResourceContents)
+                                and resource.mimeType
+                                and resource.mimeType.startswith("image/")
+                            ):
+                                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)",
+                                    ),
+                                )
+                                yield MessageChain(
+                                    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",
+                                    ),
+                                )
+                                yield MessageChain().message("返回的数据类型不受支持。")
+
+                    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。
+                        # 发送消息逻辑在 ToolExecutor 中处理了。
+                        logger.warning(
+                            f"{func_tool_name} 没有没有返回值或者将结果直接发送给用户，此工具调用不会被记录到历史中。"
+                        )
+                        self._transition_state(AgentState.DONE)
+                    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)}，将忽略。",
+                        )
+
+                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: {e!s}",
+                    ),
+                )
+
+        # 处理函数调用响应
+        if tool_call_result_blocks:
+            yield tool_call_result_blocks
+
+    def done(self) -> bool:
+        """检查 Agent 是否已完成工作"""
+        return self._state in (AgentState.DONE, AgentState.ERROR)
+
+    def get_final_llm_resp(self) -> LLMResponse | None:
+        return self.final_llm_resp

astrbot/core/agent/tool.py

@@ -0,0 +1,286 @@
+from collections.abc import Awaitable, Callable
+from typing import Any, Generic
+
+import jsonschema
+import mcp
+from deprecated import deprecated
+from pydantic import model_validator
+from pydantic.dataclasses import dataclass
+
+from .run_context import ContextWrapper, TContext
+
+ParametersType = dict[str, Any]
+
+
+@dataclass
+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[Any]] | None = None
+    """a callable that implements the tool's functionality. It should be an async function."""
+
+    handler_module_path: str | None = None
+    """
+    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
+    """
+    Whether the tool is active. This field is a special field for AstrBot.
+    You can ignore it when integrating with other frameworks.
+    """
+
+    def __repr__(self):
+        return f"FuncTool(name={self.name}, parameters={self.parameters}, description={self.description})"
+
+    async def call(
+        self, context: ContextWrapper[TContext], **kwargs
+    ) -> str | mcp.types.CallToolResult:
+        """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."
+        )
+
+
+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).
+    """
+
+    def __init__(self, tools: list[FunctionTool] | None = None):
+        self.tools: list[FunctionTool] = tools or []
+
+    def empty(self) -> bool:
+        """Check if the tool set is empty."""
+        return len(self.tools) == 0
+
+    def add_tool(self, tool: FunctionTool):
+        """Add a tool to the set."""
+        # 检查是否已存在同名工具
+        for i, existing_tool in enumerate(self.tools):
+            if existing_tool.name == tool.name:
+                self.tools[i] = tool
+                return
+        self.tools.append(tool)
+
+    def remove_tool(self, name: str):
+        """Remove a tool by its name."""
+        self.tools = [tool for tool in self.tools if tool.name != name]
+
+    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
+
+    @deprecated(reason="Use add_tool() instead", version="4.0.0")
+    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
+            "properties": {},
+        }
+        for param in func_args:
+            params["properties"][param["name"]] = {
+                "type": param["type"],
+                "description": param["description"],
+            }
+        _func = FunctionTool(
+            name=name,
+            parameters=params,
+            description=desc,
+            handler=handler,
+        )
+        self.add_tool(_func)
+
+    @deprecated(reason="Use remove_tool() instead", version="4.0.0")
+    def remove_func(self, name: str):
+        """Remove a function tool by its name."""
+        self.remove_tool(name)
+
+    @deprecated(reason="Use get_tool() instead", version="4.0.0")
+    def get_func(self, name: str) -> FunctionTool | None:
+        """Get all function tools."""
+        return self.get_tool(name)
+
+    @property
+    def func_list(self) -> list[FunctionTool]:
+        """Get the list of function tools."""
+        return self.tools
+
+    def openai_schema(self, omit_empty_parameter_field: bool = False) -> list[dict]:
+        """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,
+                },
+            }
+
+            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
+
+    def anthropic_schema(self) -> list[dict]:
+        """Convert tools to Anthropic API format."""
+        result = []
+        for tool in self.tools:
+            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,
+                "description": tool.description,
+                "input_schema": input_schema,
+            }
+            result.append(tool_def)
+        return result
+
+    def google_schema(self) -> dict:
+        """Convert tools to Google GenAI API format."""
+
+        def convert_schema(schema: dict) -> dict:
+            """Convert schema to Gemini API format."""
+            supported_types = {
+                "string",
+                "number",
+                "integer",
+                "boolean",
+                "array",
+                "object",
+                "null",
+            }
+            supported_formats = {
+                "string": {"enum", "date-time"},
+                "integer": {"int32", "int64"},
+                "number": {"float", "double"},
+            }
+
+            if "anyOf" in schema:
+                return {"anyOf": [convert_schema(s) for s in schema["anyOf"]]}
+
+            result = {}
+
+            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["format"] = schema["format"]
+            else:
+                result["type"] = "null"
+
+            support_fields = {
+                "title",
+                "description",
+                "enum",
+                "minimum",
+                "maximum",
+                "maxItems",
+                "minItems",
+                "nullable",
+                "required",
+            }
+            result.update({k: schema[k] for k in support_fields if k in schema})
+
+            if "properties" in schema:
+                properties = {}
+                for key, value in schema["properties"].items():
+                    prop_value = convert_schema(value)
+                    if "default" in prop_value:
+                        del prop_value["default"]
+                    properties[key] = prop_value
+
+                if properties:
+                    result["properties"] = properties
+
+            if "items" in schema:
+                result["items"] = convert_schema(schema["items"])
+
+            return result
+
+        tools = []
+        for tool in self.tools:
+            d: dict[str, Any] = {
+                "name": tool.name,
+                "description": tool.description,
+            }
+            if tool.parameters:
+                d["parameters"] = convert_schema(tool.parameters)
+            tools.append(d)
+
+        declarations = {}
+        if tools:
+            declarations["function_declarations"] = tools
+        return declarations
+
+    @deprecated(reason="Use openai_schema() instead", version="4.0.0")
+    def get_func_desc_openai_style(self, omit_empty_parameter_field: bool = False):
+        return self.openai_schema(omit_empty_parameter_field)
+
+    @deprecated(reason="Use anthropic_schema() instead", version="4.0.0")
+    def get_func_desc_anthropic_style(self):
+        return self.anthropic_schema()
+
+    @deprecated(reason="Use google_schema() instead", version="4.0.0")
+    def get_func_desc_google_genai_style(self):
+        return self.google_schema()
+
+    def names(self) -> list[str]:
+        """获取所有工具的名称列表"""
+        return [tool.name for tool in self.tools]
+
+    def __len__(self):
+        return len(self.tools)
+
+    def __bool__(self):
+        return len(self.tools) > 0
+
+    def __iter__(self):
+        return iter(self.tools)
+
+    def __repr__(self):
+        return f"ToolSet(tools={self.tools})"
+
+    def __str__(self):
+        return f"ToolSet(tools={self.tools})"

astrbot/core/agent/tool_executor.py

@@ -0,0 +1,17 @@
+from collections.abc import AsyncGenerator
+from typing import Any, Generic
+
+import mcp
+
+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,
+    ) -> AsyncGenerator[Any | mcp.types.CallToolResult, None]: ...

astrbot/core/astr_agent_context.py

@@ -0,0 +1,14 @@
+from dataclasses import dataclass
+
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core.provider import Provider
+from astrbot.core.provider.entities import ProviderRequest
+
+
+@dataclass
+class AstrAgentContext:
+    provider: Provider
+    first_provider_request: ProviderRequest
+    curr_provider_request: ProviderRequest
+    streaming: bool
+    event: AstrMessageEvent

astrbot/core/astrbot_config_mgr.py

@@ -0,0 +1,275 @@
+import os
+import uuid
+from typing import TypedDict, TypeVar
+
+from astrbot.core import AstrBotConfig, logger
+from astrbot.core.config.astrbot_config import ASTRBOT_CONFIG_PATH
+from astrbot.core.config.default import DEFAULT_CONFIG
+from astrbot.core.platform.message_session import MessageSession
+from astrbot.core.umop_config_router import UmopConfigRouter
+from astrbot.core.utils.astrbot_path import get_astrbot_config_path
+from astrbot.core.utils.shared_preferences import SharedPreferences
+
+_VT = TypeVar("_VT")
+
+
+class ConfInfo(TypedDict):
+    """Configuration information for a specific session or platform."""
+
+    id: str  # UUID of the configuration or "default"
+    name: str
+    path: str  # File name to the configuration file
+
+
+DEFAULT_CONFIG_CONF_INFO = ConfInfo(
+    id="default",
+    name="default",
+    path=ASTRBOT_CONFIG_PATH,
+)
+
+
+class AstrBotConfigManager:
+    """A class to manage the system configuration of AstrBot, aka ACM"""
+
+    def __init__(
+        self,
+        default_config: AstrBotConfig,
+        ucr: UmopConfigRouter,
+        sp: SharedPreferences,
+    ):
+        self.sp = sp
+        self.ucr = ucr
+        self.confs: dict[str, AstrBotConfig] = {}
+        """uuid / "default" -> AstrBotConfig"""
+        self.confs["default"] = default_config
+        self.abconf_data = None
+        self._load_all_configs()
+
+    def _get_abconf_data(self) -> dict:
+        """获取所有的 abconf 数据"""
+        if self.abconf_data is None:
+            self.abconf_data = self.sp.get(
+                "abconf_mapping",
+                {},
+                scope="global",
+                scope_id="global",
+            )
+        return self.abconf_data
+
+    def _load_all_configs(self):
+        """Load all configurations from the shared preferences."""
+        abconf_data = self._get_abconf_data()
+        self.abconf_data = abconf_data
+        for uuid_, meta in abconf_data.items():
+            filename = meta["path"]
+            conf_path = os.path.join(get_astrbot_config_path(), filename)
+            if os.path.exists(conf_path):
+                conf = AstrBotConfig(config_path=conf_path)
+                self.confs[uuid_] = conf
+            else:
+                logger.warning(
+                    f"Config file {conf_path} for UUID {uuid_} does not exist, skipping.",
+                )
+                continue
+
+    def _load_conf_mapping(self, umo: str | MessageSession) -> ConfInfo:
+        """获取指定 umo 的配置文件 uuid, 如果不存在则返回默认配置(返回 "default")
+
+        Returns:
+            ConfInfo: 包含配置文件的 uuid, 路径和名称等信息, 是一个 dict 类型
+
+        """
+        # uuid -> { "path": str, "name": str }
+        abconf_data = self._get_abconf_data()
+
+        if isinstance(umo, MessageSession):
+            umo = str(umo)
+        else:
+            try:
+                umo = str(MessageSession.from_str(umo))  # validate
+            except Exception:
+                return DEFAULT_CONFIG_CONF_INFO
+
+        conf_id = self.ucr.get_conf_id_for_umop(umo)
+        if conf_id:
+            meta = abconf_data.get(conf_id)
+            if meta and isinstance(meta, dict):
+                # the bind relation between umo and conf is defined in ucr now, so we remove "umop" here
+                meta.pop("umop", None)
+                return ConfInfo(**meta, id=conf_id)
+
+        return DEFAULT_CONFIG_CONF_INFO
+
+    def _save_conf_mapping(
+        self,
+        abconf_path: str,
+        abconf_id: str,
+        abconf_name: str | None = None,
+    ) -> None:
+        """保存配置文件的映射关系"""
+        abconf_data = self.sp.get(
+            "abconf_mapping",
+            {},
+            scope="global",
+            scope_id="global",
+        )
+        random_word = abconf_name or uuid.uuid4().hex[:8]
+        abconf_data[abconf_id] = {
+            "path": abconf_path,
+            "name": random_word,
+        }
+        self.sp.put("abconf_mapping", abconf_data, scope="global", scope_id="global")
+        self.abconf_data = abconf_data
+
+    def get_conf(self, umo: str | MessageSession | None) -> AstrBotConfig:
+        """获取指定 umo 的配置文件。如果不存在，则 fallback 到默认配置文件。"""
+        if not umo:
+            return self.confs["default"]
+        if isinstance(umo, MessageSession):
+            umo = f"{umo.platform_id}:{umo.message_type}:{umo.session_id}"
+
+        uuid_ = self._load_conf_mapping(umo)["id"]
+
+        conf = self.confs.get(uuid_)
+        if not conf:
+            conf = self.confs["default"]  # default MUST exists
+
+        return conf
+
+    @property
+    def default_conf(self) -> AstrBotConfig:
+        """获取默认配置文件"""
+        return self.confs["default"]
+
+    def get_conf_info(self, umo: str | MessageSession) -> ConfInfo:
+        """获取指定 umo 的配置文件元数据"""
+        if isinstance(umo, MessageSession):
+            umo = f"{umo.platform_id}:{umo.message_type}:{umo.session_id}"
+
+        return self._load_conf_mapping(umo)
+
+    def get_conf_list(self) -> list[ConfInfo]:
+        """获取所有配置文件的元数据列表"""
+        conf_list = []
+        abconf_mapping = self._get_abconf_data()
+        for uuid_, meta in abconf_mapping.items():
+            if not isinstance(meta, dict):
+                continue
+            meta.pop("umop", None)
+            conf_list.append(ConfInfo(**meta, id=uuid_))
+        conf_list.append(DEFAULT_CONFIG_CONF_INFO)
+        return conf_list
+
+    def create_conf(
+        self,
+        config: dict = DEFAULT_CONFIG,
+        name: str | None = None,
+    ) -> str:
+        conf_uuid = str(uuid.uuid4())
+        conf_file_name = f"abconf_{conf_uuid}.json"
+        conf_path = os.path.join(get_astrbot_config_path(), conf_file_name)
+        conf = AstrBotConfig(config_path=conf_path, default_config=config)
+        conf.save_config()
+        self._save_conf_mapping(conf_file_name, conf_uuid, abconf_name=name)
+        self.confs[conf_uuid] = conf
+        return conf_uuid
+
+    def delete_conf(self, conf_id: str) -> bool:
+        """删除指定配置文件
+
+        Args:
+            conf_id: 配置文件的 UUID
+
+        Returns:
+            bool: 删除是否成功
+
+        Raises:
+            ValueError: 如果试图删除默认配置文件
+
+        """
+        if conf_id == "default":
+            raise ValueError("不能删除默认配置文件")
+
+        # 从映射中移除
+        abconf_data = self.sp.get(
+            "abconf_mapping",
+            {},
+            scope="global",
+            scope_id="global",
+        )
+        if conf_id not in abconf_data:
+            logger.warning(f"配置文件 {conf_id} 不存在于映射中")
+            return False
+
+        # 获取配置文件路径
+        conf_path = os.path.join(
+            get_astrbot_config_path(),
+            abconf_data[conf_id]["path"],
+        )
+
+        # 删除配置文件
+        try:
+            if os.path.exists(conf_path):
+                os.remove(conf_path)
+                logger.info(f"已删除配置文件: {conf_path}")
+        except Exception as e:
+            logger.error(f"删除配置文件 {conf_path} 失败: {e}")
+            return False
+
+        # 从内存中移除
+        if conf_id in self.confs:
+            del self.confs[conf_id]
+
+        # 从映射中移除
+        del abconf_data[conf_id]
+        self.sp.put("abconf_mapping", abconf_data, scope="global", scope_id="global")
+        self.abconf_data = abconf_data
+
+        logger.info(f"成功删除配置文件 {conf_id}")
+        return True
+
+    def update_conf_info(self, conf_id: str, name: str | None = None) -> bool:
+        """更新配置文件信息
+
+        Args:
+            conf_id: 配置文件的 UUID
+            name: 新的配置文件名称 (可选)
+
+        Returns:
+            bool: 更新是否成功
+
+        """
+        if conf_id == "default":
+            raise ValueError("不能更新默认配置文件的信息")
+
+        abconf_data = self.sp.get(
+            "abconf_mapping",
+            {},
+            scope="global",
+            scope_id="global",
+        )
+        if conf_id not in abconf_data:
+            logger.warning(f"配置文件 {conf_id} 不存在于映射中")
+            return False
+
+        # 更新名称
+        if name is not None:
+            abconf_data[conf_id]["name"] = name
+
+        # 保存更新
+        self.sp.put("abconf_mapping", abconf_data, scope="global", scope_id="global")
+        self.abconf_data = abconf_data
+        logger.info(f"成功更新配置文件 {conf_id} 的信息")
+        return True
+
+    def g(
+        self,
+        umo: str | None = None,
+        key: str | None = None,
+        default: _VT = None,
+    ) -> _VT:
+        """获取配置项。umo 为 None 时使用默认配置"""
+        if umo is None:
+            return self.confs["default"].get(key, default)
+        conf = self.get_conf(umo)
+        return conf.get(key, default)

astrbot/core/config/__init__.py

@@ -1,9 +1,9 @@
-from .default import DEFAULT_CONFIG, VERSION, DB_PATH
 from .astrbot_config import *
+from .default import DB_PATH, DEFAULT_CONFIG, VERSION
 
 __all__ = [
+    "DB_PATH",
     "DEFAULT_CONFIG",
     "VERSION",
-    "DB_PATH",
     "AstrBotConfig",
 ]

astrbot/core/config/astrbot_config.py

@@ -1,11 +1,13 @@
-import os
+import enum
 import json
 import logging
-import enum
-from .default import DEFAULT_CONFIG, DEFAULT_VALUE_MAP
-from typing import Dict
+import os
 
-ASTRBOT_CONFIG_PATH = "data/cmd_config.json"
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
+from .default import DEFAULT_CONFIG, DEFAULT_VALUE_MAP
+
+ASTRBOT_CONFIG_PATH = os.path.join(get_astrbot_data_path(), "cmd_config.json")
 logger = logging.getLogger("astrbot")
 
 
@@ -26,7 +28,7 @@ class AstrBotConfig(dict):
         self,
         config_path: str = ASTRBOT_CONFIG_PATH,
         default_config: dict = DEFAULT_CONFIG,
-        schema: dict = None,
+        schema: dict | None = None,
     ):
         super().__init__()
 
@@ -42,11 +44,10 @@ class AstrBotConfig(dict):
             """不存在时载入默认配置"""
             with open(config_path, "w", encoding="utf-8-sig") as f:
                 json.dump(default_config, f, indent=4, ensure_ascii=False)
+                object.__setattr__(self, "first_deploy", True)  # 标记第一次部署
 
-        with open(config_path, "r", encoding="utf-8-sig") as f:
+        with open(config_path, encoding="utf-8-sig") as f:
             conf_str = f.read()
-            if conf_str.startswith("/ufeff"):  # remove BOM
-                conf_str = conf_str.encode("utf8")[3:].decode("utf8")
             conf = json.loads(conf_str)
 
         # 检查配置完整性，并插入
@@ -65,7 +66,7 @@ class AstrBotConfig(dict):
             for k, v in schema.items():
                 if v["type"] not in DEFAULT_VALUE_MAP:
                     raise TypeError(
-                        f"不受支持的配置类型 {v['type']}。支持的类型有：{DEFAULT_VALUE_MAP.keys()}"
+                        f"不受支持的配置类型 {v['type']}。支持的类型有：{DEFAULT_VALUE_MAP.keys()}",
                     )
                 if "default" in v:
                     default = v["default"]
@@ -82,27 +83,66 @@ class AstrBotConfig(dict):
 
         return conf
 
-    def check_config_integrity(self, refer_conf: Dict, conf: Dict, path=""):
-        """检查配置完整性，如果有新的配置项则返回 True"""
+    def check_config_integrity(self, refer_conf: dict, conf: dict, path=""):
+        """检查配置完整性，如果有新的配置项或顺序不一致则返回 True"""
         has_new = False
+
+        # 创建一个新的有序字典以保持参考配置的顺序
+        new_conf = {}
+
+        # 先按照参考配置的顺序添加配置项
         for key, value in refer_conf.items():
             if key not in conf:
-                # logger.info(f"检查到配置项 {path + "." + key if path else key} 不存在，已插入默认值 {value}")
+                # 配置项不存在，插入默认值
                 path_ = path + "." + key if path else key
                 logger.info(f"检查到配置项 {path_} 不存在，已插入默认值 {value}")
-                conf[key] = value
+                new_conf[key] = value
                 has_new = True
-            else:
-                if conf[key] is None:
-                    conf[key] = value
+            elif conf[key] is None:
+                # 配置项为 None，使用默认值
+                new_conf[key] = value
                 has_new = True
             elif isinstance(value, dict):
-                    has_new |= self.check_config_integrity(
-                        value, conf[key], path + "." + key if path else key
+                # 递归检查子配置项
+                if not isinstance(conf[key], dict):
+                    # 类型不匹配，使用默认值
+                    new_conf[key] = value
+                    has_new = True
+                else:
+                    # 递归检查并同步顺序
+                    child_has_new = self.check_config_integrity(
+                        value,
+                        conf[key],
+                        path + "." + key if path else key,
                     )
+                    new_conf[key] = conf[key]
+                    has_new |= child_has_new
+            else:
+                # 直接使用现有配置
+                new_conf[key] = conf[key]
+
+        # 检查是否存在参考配置中没有的配置项
+        for key in list(conf.keys()):
+            if key not in refer_conf:
+                path_ = path + "." + key if path else key
+                logger.info(f"检查到配置项 {path_} 不存在，将从当前配置中删除")
+                has_new = True
+
+        # 顺序不一致也算作变更
+        if list(conf.keys()) != list(new_conf.keys()):
+            if path:
+                logger.info(f"检查到配置项 {path} 的子项顺序不一致，已重新排序")
+            else:
+                logger.info("检查到配置项顺序不一致，已重新排序")
+            has_new = True
+
+        # 更新原始配置
+        conf.clear()
+        conf.update(new_conf)
+
         return has_new
 
-    def save_config(self, replace_config: Dict = None):
+    def save_config(self, replace_config: dict | None = None):
         """将配置写入文件
 
         如果传入 replace_config，则将配置替换为 replace_config

astrbot/core/conversation_mgr.py

@@ -1,116 +1,404 @@
-import uuid
+"""AstrBot 会话-对话管理器, 维护两个本地存储, 其中一个是 json 格式的shared_preferences, 另外一个是数据库.
+
+在 AstrBot 中, 会话和对话是独立的, 会话用于标记对话窗口, 例如群聊"123456789"可以建立一个会话,
+在一个会话中可以建立多个对话, 并且支持对话的切换和删除
+"""
+
 import json
-import asyncio
+from collections.abc import Awaitable, Callable
+
 from astrbot.core import sp
-from typing import Dict, List
+from astrbot.core.agent.message import AssistantMessageSegment, UserMessageSegment
 from astrbot.core.db import BaseDatabase
-from astrbot.core.db.po import Conversation
+from astrbot.core.db.po import Conversation, ConversationV2
 
 
 class ConversationManager:
     """负责管理会话与 LLM 的对话，某个会话当前正在用哪个对话。"""
 
     def __init__(self, db_helper: BaseDatabase):
-        self.session_conversations: Dict[str, str] = sp.get("session_conversation", {})
+        self.session_conversations: dict[str, str] = {}
         self.db = db_helper
         self.save_interval = 60  # 每 60 秒保存一次
-        self._start_periodic_save()
 
-    def _start_periodic_save(self):
-        asyncio.create_task(self._periodic_save())
+        # 会话删除回调函数列表（用于级联清理，如知识库配置）
+        self._on_session_deleted_callbacks: list[Callable[[str], Awaitable[None]]] = []
 
-    async def _periodic_save(self):
-        while True:
-            await asyncio.sleep(self.save_interval)
-            self._save_to_storage()
+    def register_on_session_deleted(
+        self,
+        callback: Callable[[str], Awaitable[None]],
+    ) -> None:
+        """注册会话删除回调函数.
 
-    def _save_to_storage(self):
-        sp.put("session_conversation", self.session_conversations)
+        其他模块可以注册回调来响应会话删除事件，实现级联清理。
+        例如：知识库模块可以注册回调来清理会话的知识库配置。
 
-    async def new_conversation(self, unified_msg_origin: str) -> str:
-        """新建对话，并将当前会话的对话转移到新对话"""
-        conversation_id = str(uuid.uuid4())
-        self.db.new_conversation(user_id=unified_msg_origin, cid=conversation_id)
-        self.session_conversations[unified_msg_origin] = conversation_id
-        sp.put("session_conversation", self.session_conversations)
-        return conversation_id
+        Args:
+            callback: 回调函数，接收会话ID (unified_msg_origin) 作为参数
 
-    async def switch_conversation(self, unified_msg_origin: str, conversation_id: str):
-        """切换会话的对话"""
-        self.session_conversations[unified_msg_origin] = conversation_id
-        sp.put("session_conversation", self.session_conversations)
+        """
+        self._on_session_deleted_callbacks.append(callback)
 
-    async def delete_conversation(
-        self, unified_msg_origin: str, conversation_id: str = None
-    ):
-        """删除会话的对话，当 conversation_id 为 None 时删除会话当前的对话"""
-        conversation_id = self.session_conversations.get(unified_msg_origin)
-        if conversation_id:
-            self.db.delete_conversation(user_id=unified_msg_origin, cid=conversation_id)
-            del self.session_conversations[unified_msg_origin]
-            sp.put("session_conversation", self.session_conversations)
+    async def _trigger_session_deleted(self, unified_msg_origin: str) -> None:
+        """触发会话删除回调.
 
-    async def get_curr_conversation_id(self, unified_msg_origin: str) -> str:
-        """获取会话当前的对话 ID"""
-        return self.session_conversations.get(unified_msg_origin, None)
+        Args:
+            unified_msg_origin: 会话ID
 
-    async def get_conversation(
-        self, unified_msg_origin: str, conversation_id: str
-    ) -> Conversation:
-        """获取会话的对话"""
-        return self.db.get_conversation_by_user_id(unified_msg_origin, conversation_id)
+        """
+        for callback in self._on_session_deleted_callbacks:
+            try:
+                await callback(unified_msg_origin)
+            except Exception as e:
+                from astrbot.core import logger
 
-    async def get_conversations(self, unified_msg_origin: str) -> List[Conversation]:
-        """获取会话的所有对话"""
-        return self.db.get_conversations(unified_msg_origin)
-
-    async def update_conversation(
-        self, unified_msg_origin: str, conversation_id: str, history: List[Dict]
-    ):
-        """更新会话的对话"""
-        if conversation_id:
-            self.db.update_conversation(
-                user_id=unified_msg_origin,
-                cid=conversation_id,
-                history=json.dumps(history),
+                logger.error(
+                    f"会话删除回调执行失败 (session: {unified_msg_origin}): {e}",
                 )
 
-    async def update_conversation_title(self, unified_msg_origin: str, title: str):
-        """更新会话的对话标题"""
+    def _convert_conv_from_v2_to_v1(self, conv_v2: ConversationV2) -> Conversation:
+        """将 ConversationV2 对象转换为 Conversation 对象"""
+        created_at = int(conv_v2.created_at.timestamp())
+        updated_at = int(conv_v2.updated_at.timestamp())
+        return Conversation(
+            platform_id=conv_v2.platform_id,
+            user_id=conv_v2.user_id,
+            cid=conv_v2.conversation_id,
+            history=json.dumps(conv_v2.content or []),
+            title=conv_v2.title,
+            persona_id=conv_v2.persona_id,
+            created_at=created_at,
+            updated_at=updated_at,
+        )
+
+    async def new_conversation(
+        self,
+        unified_msg_origin: str,
+        platform_id: str | None = None,
+        content: list[dict] | None = None,
+        title: str | None = None,
+        persona_id: str | None = None,
+    ) -> str:
+        """新建对话，并将当前会话的对话转移到新对话.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+        Returns:
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+
+        """
+        if not platform_id:
+            # 如果没有提供 platform_id，则从 unified_msg_origin 中解析
+            parts = unified_msg_origin.split(":")
+            if len(parts) >= 3:
+                platform_id = parts[0]
+        if not platform_id:
+            platform_id = "unknown"
+        conv = await self.db.create_conversation(
+            user_id=unified_msg_origin,
+            platform_id=platform_id,
+            content=content,
+            title=title,
+            persona_id=persona_id,
+        )
+        self.session_conversations[unified_msg_origin] = conv.conversation_id
+        await sp.session_put(unified_msg_origin, "sel_conv_id", conv.conversation_id)
+        return conv.conversation_id
+
+    async def switch_conversation(self, unified_msg_origin: str, conversation_id: str):
+        """切换会话的对话
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+
+        """
+        self.session_conversations[unified_msg_origin] = conversation_id
+        await sp.session_put(unified_msg_origin, "sel_conv_id", conversation_id)
+
+    async def delete_conversation(
+        self,
+        unified_msg_origin: str,
+        conversation_id: str | None = None,
+    ):
+        """删除会话的对话，当 conversation_id 为 None 时删除会话当前的对话
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+
+        """
+        if not conversation_id:
             conversation_id = self.session_conversations.get(unified_msg_origin)
         if conversation_id:
-            self.db.update_conversation_title(
-                user_id=unified_msg_origin, cid=conversation_id, title=title
+            await self.db.delete_conversation(cid=conversation_id)
+            curr_cid = await self.get_curr_conversation_id(unified_msg_origin)
+            if curr_cid == conversation_id:
+                self.session_conversations.pop(unified_msg_origin, None)
+                await sp.session_remove(unified_msg_origin, "sel_conv_id")
+
+    async def delete_conversations_by_user_id(self, unified_msg_origin: str):
+        """删除会话的所有对话
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+
+        """
+        await self.db.delete_conversations_by_user_id(user_id=unified_msg_origin)
+        self.session_conversations.pop(unified_msg_origin, None)
+        await sp.session_remove(unified_msg_origin, "sel_conv_id")
+
+        # 触发会话删除回调（级联清理）
+        await self._trigger_session_deleted(unified_msg_origin)
+
+    async def get_curr_conversation_id(self, unified_msg_origin: str) -> str | None:
+        """获取会话当前的对话 ID
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+        Returns:
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+
+        """
+        ret = self.session_conversations.get(unified_msg_origin, None)
+        if not ret:
+            ret = await sp.session_get(unified_msg_origin, "sel_conv_id", None)
+            if ret:
+                self.session_conversations[unified_msg_origin] = ret
+        return ret
+
+    async def get_conversation(
+        self,
+        unified_msg_origin: str,
+        conversation_id: str,
+        create_if_not_exists: bool = False,
+    ) -> Conversation | None:
+        """获取会话的对话.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+            create_if_not_exists (bool): 如果对话不存在,是否创建一个新的对话
+        Returns:
+            conversation (Conversation): 对话对象
+
+        """
+        conv = await self.db.get_conversation_by_id(cid=conversation_id)
+        if not conv and create_if_not_exists:
+            # 如果对话不存在且需要创建，则新建一个对话
+            conversation_id = await self.new_conversation(unified_msg_origin)
+            conv = await self.db.get_conversation_by_id(cid=conversation_id)
+        conv_res = None
+        if conv:
+            conv_res = self._convert_conv_from_v2_to_v1(conv)
+        return conv_res
+
+    async def get_conversations(
+        self,
+        unified_msg_origin: str | None = None,
+        platform_id: str | None = None,
+    ) -> list[Conversation]:
+        """获取对话列表.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id，可选
+            platform_id (str): 平台 ID, 可选参数, 用于过滤对话
+        Returns:
+            conversations (List[Conversation]): 对话对象列表
+
+        """
+        convs = await self.db.get_conversations(
+            user_id=unified_msg_origin,
+            platform_id=platform_id,
+        )
+        convs_res = []
+        for conv in convs:
+            conv_res = self._convert_conv_from_v2_to_v1(conv)
+            convs_res.append(conv_res)
+        return convs_res
+
+    async def get_filtered_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+        platform_ids: list[str] | None = None,
+        search_query: str = "",
+        **kwargs,
+    ) -> tuple[list[Conversation], int]:
+        """获取过滤后的对话列表.
+
+        Args:
+            page (int): 页码, 默认为 1
+            page_size (int): 每页大小, 默认为 20
+            platform_ids (list[str]): 平台 ID 列表, 可选
+            search_query (str): 搜索查询字符串, 可选
+        Returns:
+            conversations (list[Conversation]): 对话对象列表
+
+        """
+        convs, cnt = await self.db.get_filtered_conversations(
+            page=page,
+            page_size=page_size,
+            platform_ids=platform_ids,
+            search_query=search_query,
+            **kwargs,
+        )
+        convs_res = []
+        for conv in convs:
+            conv_res = self._convert_conv_from_v2_to_v1(conv)
+            convs_res.append(conv_res)
+        return convs_res, cnt
+
+    async def update_conversation(
+        self,
+        unified_msg_origin: str,
+        conversation_id: str | None = None,
+        history: list[dict] | None = None,
+        title: str | None = None,
+        persona_id: str | None = None,
+    ) -> None:
+        """更新会话的对话.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+            history (List[Dict]): 对话历史记录, 是一个字典列表, 每个字典包含 role 和 content 字段
+
+        """
+        if not conversation_id:
+            # 如果没有提供 conversation_id，则获取当前的
+            conversation_id = await self.get_curr_conversation_id(unified_msg_origin)
+        if conversation_id:
+            await self.db.update_conversation(
+                cid=conversation_id,
+                title=title,
+                persona_id=persona_id,
+                content=history,
+            )
+
+    async def update_conversation_title(
+        self,
+        unified_msg_origin: str,
+        title: str,
+        conversation_id: str | None = None,
+    ) -> None:
+        """更新会话的对话标题.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            title (str): 对话标题
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+        Deprecated:
+            Use `update_conversation` with `title` parameter instead.
+
+        """
+        await self.update_conversation(
+            unified_msg_origin=unified_msg_origin,
+            conversation_id=conversation_id,
+            title=title,
         )
 
     async def update_conversation_persona_id(
-        self, unified_msg_origin: str, persona_id: str
-    ):
-        """更新会话的对话 Persona ID"""
-        conversation_id = self.session_conversations.get(unified_msg_origin)
-        if conversation_id:
-            self.db.update_conversation_persona_id(
-                user_id=unified_msg_origin, cid=conversation_id, persona_id=persona_id
+        self,
+        unified_msg_origin: str,
+        persona_id: str,
+        conversation_id: str | None = None,
+    ) -> None:
+        """更新会话的对话 Persona ID.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            persona_id (str): 对话 Persona ID
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+        Deprecated:
+            Use `update_conversation` with `persona_id` parameter instead.
+
+        """
+        await self.update_conversation(
+            unified_msg_origin=unified_msg_origin,
+            conversation_id=conversation_id,
+            persona_id=persona_id,
+        )
+
+    async def add_message_pair(
+        self,
+        cid: str,
+        user_message: UserMessageSegment | dict,
+        assistant_message: AssistantMessageSegment | dict,
+    ) -> None:
+        """Add a user-assistant message pair to the conversation history.
+
+        Args:
+            cid (str): Conversation ID
+            user_message (UserMessageSegment | dict): OpenAI-format user message object or dict
+            assistant_message (AssistantMessageSegment | dict): OpenAI-format assistant message object or dict
+
+        Raises:
+            Exception: If the conversation with the given ID is not found
+        """
+        conv = await self.db.get_conversation_by_id(cid=cid)
+        if not conv:
+            raise Exception(f"Conversation with id {cid} not found")
+        history = conv.content or []
+        if isinstance(user_message, UserMessageSegment):
+            user_msg_dict = user_message.model_dump()
+        else:
+            user_msg_dict = user_message
+        if isinstance(assistant_message, AssistantMessageSegment):
+            assistant_msg_dict = assistant_message.model_dump()
+        else:
+            assistant_msg_dict = assistant_message
+        history.append(user_msg_dict)
+        history.append(assistant_msg_dict)
+        await self.db.update_conversation(
+            cid=cid,
+            content=history,
         )
 
     async def get_human_readable_context(
-        self, unified_msg_origin, conversation_id, page=1, page_size=10
-    ):
+        self,
+        unified_msg_origin: str,
+        conversation_id: str,
+        page: int = 1,
+        page_size: int = 10,
+    ) -> tuple[list[str], int]:
+        """获取人类可读的上下文.
+
+        Args:
+            unified_msg_origin (str): 统一的消息来源字符串。格式为 platform_name:message_type:session_id
+            conversation_id (str): 对话 ID, 是 uuid 格式的字符串
+            page (int): 页码
+            page_size (int): 每页大小
+
+        """
         conversation = await self.get_conversation(unified_msg_origin, conversation_id)
+        if not conversation:
+            return [], 0
         history = json.loads(conversation.history)
 
-        contexts = []
-        temp_contexts = []
+        # contexts_groups 存放按顺序的段落（每个段落是一个 str 列表），
+        # 之后会被展平成一个扁平的 str 列表返回。
+        contexts_groups: list[list[str]] = []
+        temp_contexts: list[str] = []
         for record in history:
             if record["role"] == "user":
                 temp_contexts.append(f"User: {record['content']}")
             elif record["role"] == "assistant":
+                if record.get("content"):
                     temp_contexts.append(f"Assistant: {record['content']}")
-                contexts.insert(0, temp_contexts)
+                elif "tool_calls" in record:
+                    tool_calls_str = json.dumps(
+                        record["tool_calls"],
+                        ensure_ascii=False,
+                    )
+                    temp_contexts.append(f"Assistant: [函数调用] {tool_calls_str}")
+                else:
+                    temp_contexts.append("Assistant: [未知的内容]")
+                contexts_groups.insert(0, temp_contexts)
                 temp_contexts = []
 
-        # 展平 contexts 列表
-        contexts = [item for sublist in contexts for item in sublist]
+        # 展平分组后的 contexts 列表为单层字符串列表
+        contexts = [item for sublist in contexts_groups for item in sublist]
 
         # 计算分页
         paged_contexts = contexts[(page - 1) * page_size : page * page_size]

astrbot/core/core_lifecycle.py

@@ -1,55 +1,135 @@
-import traceback
+"""Astrbot 核心生命周期管理类, 负责管理 AstrBot 的启动、停止、重启等操作.
+
+该类负责初始化各个组件, 包括 ProviderManager、PlatformManager、ConversationManager、PluginManager、PipelineScheduler、EventBus等。
+该类还负责加载和执行插件, 以及处理事件总线的分发。
+
+工作流程:
+1. 初始化所有组件
+2. 启动事件总线和任务, 所有任务都在这里运行
+3. 执行启动完成事件钩子
+"""
+
 import asyncio
-import time
-import threading
 import os
-from .event_bus import EventBus
-from . import astrbot_config
+import threading
+import time
+import traceback
 from asyncio import Queue
-from typing import List
-from astrbot.core.pipeline.scheduler import PipelineScheduler, PipelineContext
-from astrbot.core.star import PluginManager
-from astrbot.core.platform.manager import PlatformManager
-from astrbot.core.star.context import Context
-from astrbot.core.provider.manager import ProviderManager
-from astrbot.core import LogBroker
-from astrbot.core.db import BaseDatabase
-from astrbot.core.updator import AstrBotUpdator
-from astrbot.core import logger
+
+from astrbot.core import LogBroker, logger, sp
+from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
 from astrbot.core.config.default import VERSION
-from astrbot.core.rag.knowledge_db_mgr import KnowledgeDBManager
 from astrbot.core.conversation_mgr import ConversationManager
-from astrbot.core.star.star_handler import star_handlers_registry, EventType
-from astrbot.core.star.star_handler import star_map
+from astrbot.core.db import BaseDatabase
+from astrbot.core.db.migration.migra_45_to_46 import migrate_45_to_46
+from astrbot.core.knowledge_base.kb_mgr import KnowledgeBaseManager
+from astrbot.core.persona_mgr import PersonaManager
+from astrbot.core.pipeline.scheduler import PipelineContext, PipelineScheduler
+from astrbot.core.platform.manager import PlatformManager
+from astrbot.core.platform_message_history_mgr import PlatformMessageHistoryManager
+from astrbot.core.provider.manager import ProviderManager
+from astrbot.core.star import PluginManager
+from astrbot.core.star.context import Context
+from astrbot.core.star.star_handler import EventType, star_handlers_registry, star_map
+from astrbot.core.umop_config_router import UmopConfigRouter
+from astrbot.core.updator import AstrBotUpdator
+
+from . import astrbot_config, html_renderer
+from .event_bus import EventBus
 
 
 class AstrBotCoreLifecycle:
-    def __init__(self, log_broker: LogBroker, db: BaseDatabase):
-        self.log_broker = log_broker
-        self.astrbot_config = astrbot_config
-        self.db = db
+    """AstrBot 核心生命周期管理类, 负责管理 AstrBot 的启动、停止、重启等操作.
 
-        os.environ["https_proxy"] = self.astrbot_config["http_proxy"]
-        os.environ["http_proxy"] = self.astrbot_config["http_proxy"]
-        os.environ["no_proxy"] = "localhost"
+    该类负责初始化各个组件, 包括 ProviderManager、PlatformManager、ConversationManager、PluginManager、PipelineScheduler、
+    EventBus 等。
+    该类还负责加载和执行插件, 以及处理事件总线的分发。
+    """
 
-    async def initialize(self):
+    def __init__(self, log_broker: LogBroker, db: BaseDatabase) -> None:
+        self.log_broker = log_broker  # 初始化日志代理
+        self.astrbot_config = astrbot_config  # 初始化配置
+        self.db = db  # 初始化数据库
+
+        # 设置代理
+        proxy_config = self.astrbot_config.get("http_proxy", "")
+        if proxy_config != "":
+            os.environ["https_proxy"] = proxy_config
+            os.environ["http_proxy"] = proxy_config
+            logger.debug(f"Using proxy: {proxy_config}")
+            # 设置 no_proxy
+            no_proxy_list = self.astrbot_config.get("no_proxy", [])
+            os.environ["no_proxy"] = ",".join(no_proxy_list)
+        else:
+            # 清空代理环境变量
+            if "https_proxy" in os.environ:
+                del os.environ["https_proxy"]
+            if "http_proxy" in os.environ:
+                del os.environ["http_proxy"]
+            if "no_proxy" in os.environ:
+                del os.environ["no_proxy"]
+            logger.debug("HTTP proxy cleared")
+
+    async def initialize(self) -> None:
+        """初始化 AstrBot 核心生命周期管理类.
+
+        负责初始化各个组件, 包括 ProviderManager、PlatformManager、ConversationManager、PluginManager、PipelineScheduler、EventBus、AstrBotUpdator等。
+        """
+        # 初始化日志代理
         logger.info("AstrBot v" + VERSION)
         if os.environ.get("TESTING", ""):
-            logger.setLevel("DEBUG")
+            logger.setLevel("DEBUG")  # 测试模式下设置日志级别为 DEBUG
         else:
-            logger.setLevel(self.astrbot_config["log_level"])
+            logger.setLevel(self.astrbot_config["log_level"])  # 设置日志级别
+
+        await self.db.initialize()
+
+        await html_renderer.initialize()
+
+        # 初始化 UMOP 配置路由器
+        self.umop_config_router = UmopConfigRouter(sp=sp)
+
+        # 初始化 AstrBot 配置管理器
+        self.astrbot_config_mgr = AstrBotConfigManager(
+            default_config=self.astrbot_config,
+            ucr=self.umop_config_router,
+            sp=sp,
+        )
+
+        # 4.5 to 4.6 migration for umop_config_router
+        try:
+            await migrate_45_to_46(self.astrbot_config_mgr, self.umop_config_router)
+        except Exception as e:
+            logger.error(f"Migration from version 4.5 to 4.6 failed: {e!s}")
+            logger.error(traceback.format_exc())
+
+        # 初始化事件队列
         self.event_queue = Queue()
-        self.event_queue.closed = False
 
-        self.provider_manager = ProviderManager(self.astrbot_config, self.db)
+        # 初始化人格管理器
+        self.persona_mgr = PersonaManager(self.db, self.astrbot_config_mgr)
+        await self.persona_mgr.initialize()
 
+        # 初始化供应商管理器
+        self.provider_manager = ProviderManager(
+            self.astrbot_config_mgr,
+            self.db,
+            self.persona_mgr,
+        )
+
+        # 初始化平台管理器
         self.platform_manager = PlatformManager(self.astrbot_config, self.event_queue)
 
-        self.knowledge_db_manager = KnowledgeDBManager(self.astrbot_config)
-
+        # 初始化对话管理器
         self.conversation_manager = ConversationManager(self.db)
 
+        # 初始化平台消息历史管理器
+        self.platform_message_history_manager = PlatformMessageHistoryManager(self.db)
+
+        # 初始化知识库管理器
+        self.kb_manager = KnowledgeBaseManager(self.provider_manager)
+
+        # 初始化提供给插件的上下文
         self.star_context = Context(
             self.event_queue,
             self.astrbot_config,
@@ -57,35 +137,58 @@ class AstrBotCoreLifecycle:
             self.provider_manager,
             self.platform_manager,
             self.conversation_manager,
-            self.knowledge_db_manager,
+            self.platform_message_history_manager,
+            self.persona_mgr,
+            self.astrbot_config_mgr,
+            self.kb_manager,
         )
+
+        # 初始化插件管理器
         self.plugin_manager = PluginManager(self.star_context, self.astrbot_config)
 
+        # 扫描、注册插件、实例化插件类
         await self.plugin_manager.reload()
-        """扫描、注册插件、实例化插件类"""
 
+        # 根据配置实例化各个 Provider
         await self.provider_manager.initialize()
-        """根据配置实例化各个 Provider"""
 
-        self.pipeline_scheduler = PipelineScheduler(
-            PipelineContext(self.astrbot_config, self.plugin_manager)
+        await self.kb_manager.initialize()
+
+        # 初始化消息事件流水线调度器
+        self.pipeline_scheduler_mapping = await self.load_pipeline_scheduler()
+
+        # 初始化更新器
+        self.astrbot_updator = AstrBotUpdator()
+
+        # 初始化事件总线
+        self.event_bus = EventBus(
+            self.event_queue,
+            self.pipeline_scheduler_mapping,
+            self.astrbot_config_mgr,
         )
-        await self.pipeline_scheduler.initialize()
-        """初始化消息事件流水线调度器"""
 
-        self.astrbot_updator = AstrBotUpdator(self.astrbot_config["plugin_repo_mirror"])
-        self.event_bus = EventBus(self.event_queue, self.pipeline_scheduler)
+        # 记录启动时间
         self.start_time = int(time.time())
-        self.curr_tasks: List[asyncio.Task] = []
 
+        # 初始化当前任务列表
+        self.curr_tasks: list[asyncio.Task] = []
+
+        # 根据配置实例化各个平台适配器
         await self.platform_manager.initialize()
-        """根据配置实例化各个平台适配器"""
 
-    def _load(self):
+        # 初始化关闭控制面板的事件
+        self.dashboard_shutdown_event = asyncio.Event()
+
+    def _load(self) -> None:
+        """加载事件总线和任务并初始化."""
+        # 创建一个异步任务来执行事件总线的 dispatch() 方法
+        # dispatch是一个无限循环的协程, 从事件队列中获取事件并处理
         event_bus_task = asyncio.create_task(
-            self.event_bus.dispatch(), name="event_bus"
+            self.event_bus.dispatch(),
+            name="event_bus",
         )
 
+        # 把插件中注册的所有协程函数注册到事件总线中并执行
         extra_tasks = []
         for task in self.star_context._register_tasks:
             extra_tasks.append(asyncio.create_task(task, name=task.__name__))
@@ -93,48 +196,74 @@ class AstrBotCoreLifecycle:
         tasks_ = [event_bus_task, *extra_tasks]
         for task in tasks_:
             self.curr_tasks.append(
-                asyncio.create_task(self._task_wrapper(task), name=task.get_name())
+                asyncio.create_task(self._task_wrapper(task), name=task.get_name()),
             )
 
         self.start_time = int(time.time())
 
-    async def _task_wrapper(self, task: asyncio.Task):
+    async def _task_wrapper(self, task: asyncio.Task) -> None:
+        """异步任务包装器, 用于处理异步任务执行中出现的各种异常.
+
+        Args:
+            task (asyncio.Task): 要执行的异步任务
+
+        """
         try:
             await task
         except asyncio.CancelledError:
-            pass
+            pass  # 任务被取消, 静默处理
         except Exception as e:
+            # 获取完整的异常堆栈信息, 按行分割并记录到日志中
             logger.error(f"------- 任务 {task.get_name()} 发生错误: {e}")
             for line in traceback.format_exc().split("\n"):
                 logger.error(f"|    {line}")
             logger.error("-------")
 
-    async def start(self):
+    async def start(self) -> None:
+        """启动 AstrBot 核心生命周期管理类.
+
+        用load加载事件总线和任务并初始化, 执行启动完成事件钩子
+        """
         self._load()
         logger.info("AstrBot 启动完成。")
 
         # 执行启动完成事件钩子
         handlers = star_handlers_registry.get_handlers_by_event_type(
-            EventType.OnAstrBotLoadedEvent
+            EventType.OnAstrBotLoadedEvent,
         )
         for handler in handlers:
             try:
                 logger.info(
-                    f"hook(on_astrbot_loaded) -> {star_map[handler.handler_module_path].name} - {handler.handler_name}"
+                    f"hook(on_astrbot_loaded) -> {star_map[handler.handler_module_path].name} - {handler.handler_name}",
                 )
                 await handler.handler()
             except BaseException:
                 logger.error(traceback.format_exc())
 
+        # 同时运行curr_tasks中的所有任务
         await asyncio.gather(*self.curr_tasks, return_exceptions=True)
 
-    async def stop(self):
-        self.event_queue.closed = True
+    async def stop(self) -> None:
+        """停止 AstrBot 核心生命周期管理类, 取消所有当前任务并终止各个管理器."""
+        # 请求停止所有正在运行的异步任务
         for task in self.curr_tasks:
             task.cancel()
 
-        await self.provider_manager.terminate()
+        for plugin in self.plugin_manager.context.get_all_stars():
+            try:
+                await self.plugin_manager._terminate_plugin(plugin)
+            except Exception as e:
+                logger.warning(traceback.format_exc())
+                logger.warning(
+                    f"插件 {plugin.name} 未被正常终止 {e!s}, 可能会导致资源泄露等问题。",
+                )
 
+        await self.provider_manager.terminate()
+        await self.platform_manager.terminate()
+        await self.kb_manager.terminate()
+        self.dashboard_shutdown_event.set()
+
+        # 再次遍历curr_tasks等待每个任务真正结束
         for task in self.curr_tasks:
             try:
                 await task
@@ -143,17 +272,59 @@ class AstrBotCoreLifecycle:
             except Exception as e:
                 logger.error(f"任务 {task.get_name()} 发生错误: {e}")
 
-    def restart(self):
-        self.event_queue.closed = True
+    async def restart(self) -> None:
+        """重启 AstrBot 核心生命周期管理类, 终止各个管理器并重新加载平台实例"""
+        await self.provider_manager.terminate()
+        await self.platform_manager.terminate()
+        await self.kb_manager.terminate()
+        self.dashboard_shutdown_event.set()
         threading.Thread(
-            target=self.astrbot_updator._reboot, name="restart", daemon=True
+            target=self.astrbot_updator._reboot,
+            name="restart",
+            daemon=True,
         ).start()
 
-    def load_platform(self) -> List[asyncio.Task]:
+    def load_platform(self) -> list[asyncio.Task]:
+        """加载平台实例并返回所有平台实例的异步任务列表"""
         tasks = []
         platform_insts = self.platform_manager.get_insts()
         for platform_inst in platform_insts:
             tasks.append(
-                asyncio.create_task(platform_inst.run(), name=platform_inst.meta().name)
+                asyncio.create_task(
+                    platform_inst.run(),
+                    name=f"{platform_inst.meta().id}({platform_inst.meta().name})",
+                ),
             )
         return tasks
+
+    async def load_pipeline_scheduler(self) -> dict[str, PipelineScheduler]:
+        """加载消息事件流水线调度器.
+
+        Returns:
+            dict[str, PipelineScheduler]: 平台 ID 到流水线调度器的映射
+
+        """
+        mapping = {}
+        for conf_id, ab_config in self.astrbot_config_mgr.confs.items():
+            scheduler = PipelineScheduler(
+                PipelineContext(ab_config, self.plugin_manager, conf_id),
+            )
+            await scheduler.initialize()
+            mapping[conf_id] = scheduler
+        return mapping
+
+    async def reload_pipeline_scheduler(self, conf_id: str) -> None:
+        """重新加载消息事件流水线调度器.
+
+        Returns:
+            dict[str, PipelineScheduler]: 平台 ID 到流水线调度器的映射
+
+        """
+        ab_config = self.astrbot_config_mgr.confs.get(conf_id)
+        if not ab_config:
+            raise ValueError(f"配置文件 {conf_id} 不存在")
+        scheduler = PipelineScheduler(
+            PipelineContext(ab_config, self.plugin_manager, conf_id),
+        )
+        await scheduler.initialize()
+        self.pipeline_scheduler_mapping[conf_id] = scheduler

astrbot/core/db/__init__.py

@@ -1,119 +1,315 @@
 import abc
+import datetime
+import typing as T
+from contextlib import asynccontextmanager
 from dataclasses import dataclass
-from typing import List
-from astrbot.core.db.po import Stats, LLMHistory, ATRIVision, Conversation
+
+from deprecated import deprecated
+from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine
+from sqlalchemy.orm import sessionmaker
+
+from astrbot.core.db.po import (
+    Attachment,
+    ConversationV2,
+    Persona,
+    PlatformMessageHistory,
+    PlatformStat,
+    Preference,
+    Stats,
+)
 
 
 @dataclass
 class BaseDatabase(abc.ABC):
-    """
-    数据库基类
-    """
+    """数据库基类"""
+
+    DATABASE_URL = ""
 
     def __init__(self) -> None:
-        pass
+        self.engine = create_async_engine(
+            self.DATABASE_URL,
+            echo=False,
+            future=True,
+        )
+        self.AsyncSessionLocal = sessionmaker(
+            self.engine,
+            class_=AsyncSession,
+            expire_on_commit=False,
+        )
 
-    def insert_base_metrics(self, metrics: dict):
-        """插入基础指标数据"""
-        self.insert_platform_metrics(metrics["platform_stats"])
-        self.insert_plugin_metrics(metrics["plugin_stats"])
-        self.insert_command_metrics(metrics["command_stats"])
-        self.insert_llm_metrics(metrics["llm_stats"])
+    async def initialize(self):
+        """初始化数据库连接"""
 
-    @abc.abstractmethod
-    def insert_platform_metrics(self, metrics: dict):
-        """插入平台指标数据"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def insert_plugin_metrics(self, metrics: dict):
-        """插入插件指标数据"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def insert_command_metrics(self, metrics: dict):
-        """插入指令指标数据"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def insert_llm_metrics(self, metrics: dict):
-        """插入 LLM 指标数据"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def update_llm_history(self, session_id: str, content: str, provider_type: str):
-        """更新 LLM 历史记录。当不存在 session_id 时插入"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def get_llm_history(
-        self, session_id: str = None, provider_type: str = None
-    ) -> List[LLMHistory]:
-        """获取 LLM 历史记录, 如果 session_id 为 None, 返回所有"""
-        raise NotImplementedError
+    @asynccontextmanager
+    async def get_db(self) -> T.AsyncGenerator[AsyncSession, None]:
+        """Get a database session."""
+        if not self.inited:
+            await self.initialize()
+            self.inited = True
+        async with self.AsyncSessionLocal() as session:
+            yield session
 
+    @deprecated(version="4.0.0", reason="Use get_platform_stats instead")
     @abc.abstractmethod
     def get_base_stats(self, offset_sec: int = 86400) -> Stats:
         """获取基础统计数据"""
         raise NotImplementedError
 
+    @deprecated(version="4.0.0", reason="Use get_platform_stats instead")
     @abc.abstractmethod
     def get_total_message_count(self) -> int:
         """获取总消息数"""
         raise NotImplementedError
 
+    @deprecated(version="4.0.0", reason="Use get_platform_stats instead")
     @abc.abstractmethod
     def get_grouped_base_stats(self, offset_sec: int = 86400) -> Stats:
         """获取基础统计数据(合并)"""
         raise NotImplementedError
 
-    @abc.abstractmethod
-    def insert_atri_vision_data(self, vision_data: ATRIVision):
-        """插入 ATRI 视觉数据"""
-        raise NotImplementedError
+    # New methods in v4.0.0
 
     @abc.abstractmethod
-    def get_atri_vision_data(self) -> List[ATRIVision]:
-        """获取 ATRI 视觉数据"""
-        raise NotImplementedError
+    async def insert_platform_stats(
+        self,
+        platform_id: str,
+        platform_type: str,
+        count: int = 1,
+        timestamp: datetime.datetime | None = None,
+    ) -> None:
+        """Insert a new platform statistic record."""
+        ...
 
     @abc.abstractmethod
-    def get_atri_vision_data_by_path_or_id(
-        self, url_or_path: str, id: str
-    ) -> ATRIVision:
-        """通过 url 或 path 获取 ATRI 视觉数据"""
-        raise NotImplementedError
+    async def count_platform_stats(self) -> int:
+        """Count the number of platform statistics records."""
+        ...
 
     @abc.abstractmethod
-    def get_conversation_by_user_id(self, user_id: str, cid: str) -> Conversation:
-        """通过 user_id 和 cid 获取 Conversation"""
-        raise NotImplementedError
+    async def get_platform_stats(self, offset_sec: int = 86400) -> list[PlatformStat]:
+        """Get platform statistics within the specified offset in seconds and group by platform_id."""
+        ...
 
     @abc.abstractmethod
-    def new_conversation(self, user_id: str, cid: str):
-        """新建 Conversation"""
-        raise NotImplementedError
+    async def get_conversations(
+        self,
+        user_id: str | None = None,
+        platform_id: str | None = None,
+    ) -> list[ConversationV2]:
+        """Get all conversations for a specific user and platform_id(optional).
+
+        content is not included in the result.
+        """
+        ...
 
     @abc.abstractmethod
-    def get_conversations(self, user_id: str) -> List[Conversation]:
-        raise NotImplementedError
+    async def get_conversation_by_id(self, cid: str) -> ConversationV2:
+        """Get a specific conversation by its ID."""
+        ...
 
     @abc.abstractmethod
-    def update_conversation(self, user_id: str, cid: str, history: str):
-        """更新 Conversation"""
-        raise NotImplementedError
+    async def get_all_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+    ) -> list[ConversationV2]:
+        """Get all conversations with pagination."""
+        ...
 
     @abc.abstractmethod
-    def delete_conversation(self, user_id: str, cid: str):
-        """删除 Conversation"""
-        raise NotImplementedError
+    async def get_filtered_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+        platform_ids: list[str] | None = None,
+        search_query: str = "",
+        **kwargs,
+    ) -> tuple[list[ConversationV2], int]:
+        """Get conversations filtered by platform IDs and search query."""
+        ...
 
     @abc.abstractmethod
-    def update_conversation_title(self, user_id: str, cid: str, title: str):
-        """更新 Conversation 标题"""
-        raise NotImplementedError
+    async def create_conversation(
+        self,
+        user_id: str,
+        platform_id: str,
+        content: list[dict] | None = None,
+        title: str | None = None,
+        persona_id: str | None = None,
+        cid: str | None = None,
+        created_at: datetime.datetime | None = None,
+        updated_at: datetime.datetime | None = None,
+    ) -> ConversationV2:
+        """Create a new conversation."""
+        ...
 
     @abc.abstractmethod
-    def update_conversation_persona_id(self, user_id: str, cid: str, persona_id: str):
-        """更新 Conversation Persona ID"""
-        raise NotImplementedError
+    async def update_conversation(
+        self,
+        cid: str,
+        title: str | None = None,
+        persona_id: str | None = None,
+        content: list[dict] | None = None,
+    ) -> None:
+        """Update a conversation's history."""
+        ...
+
+    @abc.abstractmethod
+    async def delete_conversation(self, cid: str) -> None:
+        """Delete a conversation by its ID."""
+        ...
+
+    @abc.abstractmethod
+    async def delete_conversations_by_user_id(self, user_id: str) -> None:
+        """Delete all conversations for a specific user."""
+        ...
+
+    @abc.abstractmethod
+    async def insert_platform_message_history(
+        self,
+        platform_id: str,
+        user_id: str,
+        content: dict,
+        sender_id: str | None = None,
+        sender_name: str | None = None,
+    ) -> None:
+        """Insert a new platform message history record."""
+        ...
+
+    @abc.abstractmethod
+    async def delete_platform_message_offset(
+        self,
+        platform_id: str,
+        user_id: str,
+        offset_sec: int = 86400,
+    ) -> None:
+        """Delete platform message history records older than the specified offset."""
+        ...
+
+    @abc.abstractmethod
+    async def get_platform_message_history(
+        self,
+        platform_id: str,
+        user_id: str,
+        page: int = 1,
+        page_size: int = 20,
+    ) -> list[PlatformMessageHistory]:
+        """Get platform message history for a specific user."""
+        ...
+
+    @abc.abstractmethod
+    async def insert_attachment(
+        self,
+        path: str,
+        type: str,
+        mime_type: str,
+    ):
+        """Insert a new attachment record."""
+        ...
+
+    @abc.abstractmethod
+    async def get_attachment_by_id(self, attachment_id: str) -> Attachment:
+        """Get an attachment by its ID."""
+        ...
+
+    @abc.abstractmethod
+    async def insert_persona(
+        self,
+        persona_id: str,
+        system_prompt: str,
+        begin_dialogs: list[str] | None = None,
+        tools: list[str] | None = None,
+    ) -> Persona:
+        """Insert a new persona record."""
+        ...
+
+    @abc.abstractmethod
+    async def get_persona_by_id(self, persona_id: str) -> Persona:
+        """Get a persona by its ID."""
+        ...
+
+    @abc.abstractmethod
+    async def get_personas(self) -> list[Persona]:
+        """Get all personas for a specific bot."""
+        ...
+
+    @abc.abstractmethod
+    async def update_persona(
+        self,
+        persona_id: str,
+        system_prompt: str | None = None,
+        begin_dialogs: list[str] | None = None,
+        tools: list[str] | None = None,
+    ) -> Persona | None:
+        """Update a persona's system prompt or begin dialogs."""
+        ...
+
+    @abc.abstractmethod
+    async def delete_persona(self, persona_id: str) -> None:
+        """Delete a persona by its ID."""
+        ...
+
+    @abc.abstractmethod
+    async def insert_preference_or_update(
+        self,
+        scope: str,
+        scope_id: str,
+        key: str,
+        value: dict,
+    ) -> Preference:
+        """Insert a new preference record."""
+        ...
+
+    @abc.abstractmethod
+    async def get_preference(self, scope: str, scope_id: str, key: str) -> Preference:
+        """Get a preference by scope ID and key."""
+        ...
+
+    @abc.abstractmethod
+    async def get_preferences(
+        self,
+        scope: str,
+        scope_id: str | None = None,
+        key: str | None = None,
+    ) -> list[Preference]:
+        """Get all preferences for a specific scope ID or key."""
+        ...
+
+    @abc.abstractmethod
+    async def remove_preference(self, scope: str, scope_id: str, key: str) -> None:
+        """Remove a preference by scope ID and key."""
+        ...
+
+    @abc.abstractmethod
+    async def clear_preferences(self, scope: str, scope_id: str) -> None:
+        """Clear all preferences for a specific scope ID."""
+        ...
+
+    # @abc.abstractmethod
+    # async def insert_llm_message(
+    #     self,
+    #     cid: str,
+    #     role: str,
+    #     content: list,
+    #     tool_calls: list = None,
+    #     tool_call_id: str = None,
+    #     parent_id: str = None,
+    # ) -> LLMMessage:
+    #     """Insert a new LLM message into the conversation."""
+    #     ...
+
+    # @abc.abstractmethod
+    # async def get_llm_messages(self, cid: str) -> list[LLMMessage]:
+    #     """Get all LLM messages for a specific conversation."""
+    #     ...
+
+    @abc.abstractmethod
+    async def get_session_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+        search_query: str | None = None,
+        platform: str | None = None,
+    ) -> tuple[list[dict], int]:
+        """Get paginated session conversations with joined conversation and persona details, support search and platform filter."""
+        ...

astrbot/core/db/migration/helper.py

@@ -0,0 +1,69 @@
+import os
+
+from astrbot.api import logger, sp
+from astrbot.core.config import AstrBotConfig
+from astrbot.core.db import BaseDatabase
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
+from .migra_3_to_4 import (
+    migration_conversation_table,
+    migration_persona_data,
+    migration_platform_table,
+    migration_preferences,
+    migration_webchat_data,
+)
+
+
+async def check_migration_needed_v4(db_helper: BaseDatabase) -> bool:
+    """检查是否需要进行数据库迁移
+    如果存在 data_v3.db 并且 preference 中没有 migration_done_v4，则需要进行迁移。
+    """
+    # 仅当 data 目录下存在旧版本数据（data_v3.db 文件）时才考虑迁移
+    data_dir = get_astrbot_data_path()
+    data_v3_db = os.path.join(data_dir, "data_v3.db")
+
+    if not os.path.exists(data_v3_db):
+        return False
+    migration_done = await db_helper.get_preference(
+        "global",
+        "global",
+        "migration_done_v4",
+    )
+    if migration_done:
+        return False
+    return True
+
+
+async def do_migration_v4(
+    db_helper: BaseDatabase,
+    platform_id_map: dict[str, dict[str, str]],
+    astrbot_config: AstrBotConfig,
+) -> None:
+    """执行数据库迁移
+    迁移旧的 webchat_conversation 表到新的 conversation 表。
+    迁移旧的 platform 到新的 platform_stats 表。
+    """
+    if not await check_migration_needed_v4(db_helper):
+        return
+
+    logger.info("开始执行数据库迁移...")
+
+    # 执行会话表迁移
+    await migration_conversation_table(db_helper, platform_id_map)
+
+    # 执行人格数据迁移
+    await migration_persona_data(db_helper, astrbot_config)
+
+    # 执行 WebChat 数据迁移
+    await migration_webchat_data(db_helper, platform_id_map)
+
+    # 执行偏好设置迁移
+    await migration_preferences(db_helper, platform_id_map)
+
+    # 执行平台统计表迁移
+    await migration_platform_table(db_helper, platform_id_map)
+
+    # 标记迁移完成
+    await sp.put_async("global", "global", "migration_done_v4", True)
+
+    logger.info("数据库迁移完成。")

astrbot/core/db/migration/migra_3_to_4.py

@@ -0,0 +1,357 @@
+import datetime
+import json
+
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from astrbot.api import logger, sp
+from astrbot.core.config import AstrBotConfig
+from astrbot.core.config.default import DB_PATH
+from astrbot.core.db.po import ConversationV2, PlatformMessageHistory
+from astrbot.core.platform.astr_message_event import MessageSesion
+
+from .. import BaseDatabase
+from .shared_preferences_v3 import sp as sp_v3
+from .sqlite_v3 import SQLiteDatabase as SQLiteV3DatabaseV3
+
+"""
+1. 迁移旧的 webchat_conversation 表到新的 conversation 表。
+2. 迁移旧的 platform 到新的 platform_stats 表。
+"""
+
+
+def get_platform_id(
+    platform_id_map: dict[str, dict[str, str]],
+    old_platform_name: str,
+) -> str:
+    return platform_id_map.get(
+        old_platform_name,
+        {"platform_id": old_platform_name, "platform_type": old_platform_name},
+    ).get("platform_id", old_platform_name)
+
+
+def get_platform_type(
+    platform_id_map: dict[str, dict[str, str]],
+    old_platform_name: str,
+) -> str:
+    return platform_id_map.get(
+        old_platform_name,
+        {"platform_id": old_platform_name, "platform_type": old_platform_name},
+    ).get("platform_type", old_platform_name)
+
+
+async def migration_conversation_table(
+    db_helper: BaseDatabase,
+    platform_id_map: dict[str, dict[str, str]],
+):
+    db_helper_v3 = SQLiteV3DatabaseV3(
+        db_path=DB_PATH.replace("data_v4.db", "data_v3.db"),
+    )
+    conversations, total_cnt = db_helper_v3.get_all_conversations(
+        page=1,
+        page_size=10000000,
+    )
+    logger.info(f"迁移 {total_cnt} 条旧的会话数据到新的表中...")
+
+    async with db_helper.get_db() as dbsession:
+        dbsession: AsyncSession
+        async with dbsession.begin():
+            for idx, conversation in enumerate(conversations):
+                if total_cnt > 0 and (idx + 1) % max(1, total_cnt // 10) == 0:
+                    progress = int((idx + 1) / total_cnt * 100)
+                    if progress % 10 == 0:
+                        logger.info(f"进度: {progress}% ({idx + 1}/{total_cnt})")
+                try:
+                    conv = db_helper_v3.get_conversation_by_user_id(
+                        user_id=conversation.get("user_id", "unknown"),
+                        cid=conversation.get("cid", "unknown"),
+                    )
+                    if not conv:
+                        logger.info(
+                            f"未找到该条旧会话对应的具体数据: {conversation}, 跳过。",
+                        )
+                    if ":" not in conv.user_id:
+                        continue
+                    session = MessageSesion.from_str(session_str=conv.user_id)
+                    platform_id = get_platform_id(
+                        platform_id_map,
+                        session.platform_name,
+                    )
+                    session.platform_id = platform_id  # 更新平台名称为新的 ID
+                    conv_v2 = ConversationV2(
+                        user_id=str(session),
+                        content=json.loads(conv.history) if conv.history else [],
+                        platform_id=platform_id,
+                        title=conv.title,
+                        persona_id=conv.persona_id,
+                        conversation_id=conv.cid,
+                        created_at=datetime.datetime.fromtimestamp(conv.created_at),
+                        updated_at=datetime.datetime.fromtimestamp(conv.updated_at),
+                    )
+                    dbsession.add(conv_v2)
+                except Exception as e:
+                    logger.error(
+                        f"迁移旧会话 {conversation.get('cid', 'unknown')} 失败: {e}",
+                        exc_info=True,
+                    )
+    logger.info(f"成功迁移 {total_cnt} 条旧的会话数据到新表。")
+
+
+async def migration_platform_table(
+    db_helper: BaseDatabase,
+    platform_id_map: dict[str, dict[str, str]],
+):
+    db_helper_v3 = SQLiteV3DatabaseV3(
+        db_path=DB_PATH.replace("data_v4.db", "data_v3.db"),
+    )
+    secs_from_2023_4_10_to_now = (
+        datetime.datetime.now(datetime.timezone.utc)
+        - datetime.datetime(2023, 4, 10, tzinfo=datetime.timezone.utc)
+    ).total_seconds()
+    offset_sec = int(secs_from_2023_4_10_to_now)
+    logger.info(f"迁移旧平台数据，offset_sec: {offset_sec} 秒。")
+    stats = db_helper_v3.get_base_stats(offset_sec=offset_sec)
+    logger.info(f"迁移 {len(stats.platform)} 条旧的平台数据到新的表中...")
+    platform_stats_v3 = stats.platform
+
+    if not platform_stats_v3:
+        logger.info("没有找到旧平台数据，跳过迁移。")
+        return
+
+    first_time_stamp = platform_stats_v3[0].timestamp
+    end_time_stamp = platform_stats_v3[-1].timestamp
+    start_time = first_time_stamp - (first_time_stamp % 3600)  # 向下取整到小时
+    end_time = end_time_stamp + (3600 - (end_time_stamp % 3600))  # 向上取整到小时
+
+    idx = 0
+
+    async with db_helper.get_db() as dbsession:
+        dbsession: AsyncSession
+        async with dbsession.begin():
+            total_buckets = (end_time - start_time) // 3600
+            for bucket_idx, bucket_end in enumerate(range(start_time, end_time, 3600)):
+                if bucket_idx % 500 == 0:
+                    progress = int((bucket_idx + 1) / total_buckets * 100)
+                    logger.info(f"进度: {progress}% ({bucket_idx + 1}/{total_buckets})")
+                cnt = 0
+                while (
+                    idx < len(platform_stats_v3)
+                    and platform_stats_v3[idx].timestamp < bucket_end
+                ):
+                    cnt += platform_stats_v3[idx].count
+                    idx += 1
+                if cnt == 0:
+                    continue
+                platform_id = get_platform_id(
+                    platform_id_map,
+                    platform_stats_v3[idx].name,
+                )
+                platform_type = get_platform_type(
+                    platform_id_map,
+                    platform_stats_v3[idx].name,
+                )
+                try:
+                    await dbsession.execute(
+                        text("""
+                        INSERT INTO platform_stats (timestamp, platform_id, platform_type, count)
+                        VALUES (:timestamp, :platform_id, :platform_type, :count)
+                        ON CONFLICT(timestamp, platform_id, platform_type) DO UPDATE SET
+                            count = platform_stats.count + EXCLUDED.count
+                        """),
+                        {
+                            "timestamp": datetime.datetime.fromtimestamp(
+                                bucket_end,
+                                tz=datetime.timezone.utc,
+                            ),
+                            "platform_id": platform_id,
+                            "platform_type": platform_type,
+                            "count": cnt,
+                        },
+                    )
+                except Exception:
+                    logger.error(
+                        f"迁移平台统计数据失败: {platform_id}, {platform_type}, 时间戳: {bucket_end}",
+                        exc_info=True,
+                    )
+    logger.info(f"成功迁移 {len(platform_stats_v3)} 条旧的平台数据到新表。")
+
+
+async def migration_webchat_data(
+    db_helper: BaseDatabase,
+    platform_id_map: dict[str, dict[str, str]],
+):
+    """迁移 WebChat 的历史记录到新的 PlatformMessageHistory 表中"""
+    db_helper_v3 = SQLiteV3DatabaseV3(
+        db_path=DB_PATH.replace("data_v4.db", "data_v3.db"),
+    )
+    conversations, total_cnt = db_helper_v3.get_all_conversations(
+        page=1,
+        page_size=10000000,
+    )
+    logger.info(f"迁移 {total_cnt} 条旧的 WebChat 会话数据到新的表中...")
+
+    async with db_helper.get_db() as dbsession:
+        dbsession: AsyncSession
+        async with dbsession.begin():
+            for idx, conversation in enumerate(conversations):
+                if total_cnt > 0 and (idx + 1) % max(1, total_cnt // 10) == 0:
+                    progress = int((idx + 1) / total_cnt * 100)
+                    if progress % 10 == 0:
+                        logger.info(f"进度: {progress}% ({idx + 1}/{total_cnt})")
+                try:
+                    conv = db_helper_v3.get_conversation_by_user_id(
+                        user_id=conversation.get("user_id", "unknown"),
+                        cid=conversation.get("cid", "unknown"),
+                    )
+                    if not conv:
+                        logger.info(
+                            f"未找到该条旧会话对应的具体数据: {conversation}, 跳过。",
+                        )
+                    if ":" in conv.user_id:
+                        continue
+                    platform_id = "webchat"
+                    history = json.loads(conv.history) if conv.history else []
+                    for msg in history:
+                        type_ = msg.get("type")  # user type, "bot" or "user"
+                        new_history = PlatformMessageHistory(
+                            platform_id=platform_id,
+                            user_id=conv.cid,  # we use conv.cid as user_id for webchat
+                            content=msg,
+                            sender_id=type_,
+                            sender_name=type_,
+                        )
+                        dbsession.add(new_history)
+
+                except Exception:
+                    logger.error(
+                        f"迁移旧 WebChat 会话 {conversation.get('cid', 'unknown')} 失败",
+                        exc_info=True,
+                    )
+
+    logger.info(f"成功迁移 {total_cnt} 条旧的 WebChat 会话数据到新表。")
+
+
+async def migration_persona_data(
+    db_helper: BaseDatabase,
+    astrbot_config: AstrBotConfig,
+):
+    """迁移 Persona 数据到新的表中。
+    旧的 Persona 数据存储在 preference 中，新的 Persona 数据存储在 persona 表中。
+    """
+    v3_persona_config: list[dict] = astrbot_config.get("persona", [])
+    total_personas = len(v3_persona_config)
+    logger.info(f"迁移 {total_personas} 个 Persona 配置到新表中...")
+
+    for idx, persona in enumerate(v3_persona_config):
+        if total_personas > 0 and (idx + 1) % max(1, total_personas // 10) == 0:
+            progress = int((idx + 1) / total_personas * 100)
+            if progress % 10 == 0:
+                logger.info(f"进度: {progress}% ({idx + 1}/{total_personas})")
+        try:
+            begin_dialogs = persona.get("begin_dialogs", [])
+            mood_imitation_dialogs = persona.get("mood_imitation_dialogs", [])
+            parts = []
+            user_turn = True
+            for mood_dialog in mood_imitation_dialogs:
+                if user_turn:
+                    parts.append(f"A: {mood_dialog}\n")
+                else:
+                    parts.append(f"B: {mood_dialog}\n")
+                user_turn = not user_turn
+            mood_prompt = "".join(parts)
+            system_prompt = persona.get("prompt", "")
+            if mood_prompt:
+                system_prompt += f"Here are few shots of dialogs, you need to imitate the tone of 'B' in the following dialogs to respond:\n {mood_prompt}"
+            persona_new = await db_helper.insert_persona(
+                persona_id=persona["name"],
+                system_prompt=system_prompt,
+                begin_dialogs=begin_dialogs,
+            )
+            logger.info(
+                f"迁移 Persona {persona['name']}({persona_new.system_prompt[:30]}...) 到新表成功。",
+            )
+        except Exception as e:
+            logger.error(f"解析 Persona 配置失败：{e}")
+
+
+async def migration_preferences(
+    db_helper: BaseDatabase,
+    platform_id_map: dict[str, dict[str, str]],
+):
+    # 1. global scope migration
+    keys = [
+        "inactivated_llm_tools",
+        "inactivated_plugins",
+        "curr_provider",
+        "curr_provider_tts",
+        "curr_provider_stt",
+        "alter_cmd",
+    ]
+    for key in keys:
+        value = sp_v3.get(key)
+        if value is not None:
+            await sp.put_async("global", "global", key, value)
+            logger.info(f"迁移全局偏好设置 {key} 成功，值: {value}")
+
+    # 2. umo scope migration
+    session_conversation = sp_v3.get("session_conversation", default={})
+    for umo, conversation_id in session_conversation.items():
+        if not umo or not conversation_id:
+            continue
+        try:
+            session = MessageSesion.from_str(session_str=umo)
+            platform_id = get_platform_id(platform_id_map, session.platform_name)
+            session.platform_id = platform_id
+            await sp.put_async("umo", str(session), "sel_conv_id", conversation_id)
+            logger.info(f"迁移会话 {umo} 的对话数据到新表成功，平台 ID: {platform_id}")
+        except Exception as e:
+            logger.error(f"迁移会话 {umo} 的对话数据失败: {e}", exc_info=True)
+
+    session_service_config = sp_v3.get("session_service_config", default={})
+    for umo, config in session_service_config.items():
+        if not umo or not config:
+            continue
+        try:
+            session = MessageSesion.from_str(session_str=umo)
+            platform_id = get_platform_id(platform_id_map, session.platform_name)
+            session.platform_id = platform_id
+
+            await sp.put_async("umo", str(session), "session_service_config", config)
+
+            logger.info(f"迁移会话 {umo} 的服务配置到新表成功，平台 ID: {platform_id}")
+        except Exception as e:
+            logger.error(f"迁移会话 {umo} 的服务配置失败: {e}", exc_info=True)
+
+    session_variables = sp_v3.get("session_variables", default={})
+    for umo, variables in session_variables.items():
+        if not umo or not variables:
+            continue
+        try:
+            session = MessageSesion.from_str(session_str=umo)
+            platform_id = get_platform_id(platform_id_map, session.platform_name)
+            session.platform_id = platform_id
+            await sp.put_async("umo", str(session), "session_variables", variables)
+        except Exception as e:
+            logger.error(f"迁移会话 {umo} 的变量失败: {e}", exc_info=True)
+
+    session_provider_perf = sp_v3.get("session_provider_perf", default={})
+    for umo, perf in session_provider_perf.items():
+        if not umo or not perf:
+            continue
+        try:
+            session = MessageSesion.from_str(session_str=umo)
+            platform_id = get_platform_id(platform_id_map, session.platform_name)
+            session.platform_id = platform_id
+
+            for provider_type, provider_id in perf.items():
+                await sp.put_async(
+                    "umo",
+                    str(session),
+                    f"provider_perf_{provider_type}",
+                    provider_id,
+                )
+            logger.info(
+                f"迁移会话 {umo} 的提供商偏好到新表成功，平台 ID: {platform_id}",
+            )
+        except Exception as e:
+            logger.error(f"迁移会话 {umo} 的提供商偏好失败: {e}", exc_info=True)

astrbot/core/db/migration/migra_45_to_46.py

@@ -0,0 +1,44 @@
+from astrbot.api import logger, sp
+from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
+from astrbot.core.umop_config_router import UmopConfigRouter
+
+
+async def migrate_45_to_46(acm: AstrBotConfigManager, ucr: UmopConfigRouter):
+    abconf_data = acm.abconf_data
+
+    if not isinstance(abconf_data, dict):
+        # should be unreachable
+        logger.warning(
+            f"migrate_45_to_46: abconf_data is not a dict (type={type(abconf_data)}). Value: {abconf_data!r}",
+        )
+        return
+
+    # 如果任何一项带有 umop，则说明需要迁移
+    need_migration = False
+    for conf_id, conf_info in abconf_data.items():
+        if isinstance(conf_info, dict) and "umop" in conf_info:
+            need_migration = True
+            break
+
+    if not need_migration:
+        return
+
+    logger.info("Starting migration from version 4.5 to 4.6")
+
+    # extract umo->conf_id mapping
+    umo_to_conf_id = {}
+    for conf_id, conf_info in abconf_data.items():
+        if isinstance(conf_info, dict) and "umop" in conf_info:
+            umop_ls = conf_info.pop("umop")
+            if not isinstance(umop_ls, list):
+                continue
+            for umo in umop_ls:
+                if isinstance(umo, str) and umo not in umo_to_conf_id:
+                    umo_to_conf_id[umo] = conf_id
+
+    # update the abconf data
+    await sp.global_put("abconf_mapping", abconf_data)
+    # update the umop config router
+    await ucr.update_routing_data(umo_to_conf_id)
+
+    logger.info("Migration from version 45 to 46 completed successfully")

astrbot/core/db/migration/shared_preferences_v3.py

@@ -0,0 +1,48 @@
+import json
+import os
+from typing import TypeVar
+
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
+_VT = TypeVar("_VT")
+
+
+class SharedPreferences:
+    def __init__(self, path=None):
+        if path is None:
+            path = os.path.join(get_astrbot_data_path(), "shared_preferences.json")
+        self.path = path
+        self._data = self._load_preferences()
+
+    def _load_preferences(self):
+        if os.path.exists(self.path):
+            try:
+                with open(self.path) as f:
+                    return json.load(f)
+            except json.JSONDecodeError:
+                os.remove(self.path)
+        return {}
+
+    def _save_preferences(self):
+        with open(self.path, "w") as f:
+            json.dump(self._data, f, indent=4, ensure_ascii=False)
+            f.flush()
+
+    def get(self, key, default: _VT = None) -> _VT:
+        return self._data.get(key, default)
+
+    def put(self, key, value):
+        self._data[key] = value
+        self._save_preferences()
+
+    def remove(self, key):
+        if key in self._data:
+            del self._data[key]
+            self._save_preferences()
+
+    def clear(self):
+        self._data.clear()
+        self._save_preferences()
+
+
+sp = SharedPreferences()

astrbot/core/db/migration/sqlite_v3.py

@@ -0,0 +1,497 @@
+import sqlite3
+import time
+from dataclasses import dataclass
+from typing import Any
+
+from astrbot.core.db.po import Platform, Stats
+
+
+@dataclass
+class Conversation:
+    """LLM 对话存储
+
+    对于网页聊天，history 存储了包括指令、回复、图片等在内的所有消息。
+    对于其他平台的聊天，不存储非 LLM 的回复（因为考虑到已经存储在各自的平台上）。
+    """
+
+    user_id: str
+    cid: str
+    history: str = ""
+    """字符串格式的列表。"""
+    created_at: int = 0
+    updated_at: int = 0
+    title: str = ""
+    persona_id: str = ""
+
+
+INIT_SQL = """
+CREATE TABLE IF NOT EXISTS platform(
+    name VARCHAR(32),
+    count INTEGER,
+    timestamp INTEGER
+);
+CREATE TABLE IF NOT EXISTS llm(
+    name VARCHAR(32),
+    count INTEGER,
+    timestamp INTEGER
+);
+CREATE TABLE IF NOT EXISTS plugin(
+    name VARCHAR(32),
+    count INTEGER,
+    timestamp INTEGER
+);
+CREATE TABLE IF NOT EXISTS command(
+    name VARCHAR(32),
+    count INTEGER,
+    timestamp INTEGER
+);
+CREATE TABLE IF NOT EXISTS llm_history(
+    provider_type VARCHAR(32),
+    session_id VARCHAR(32),
+    content TEXT
+);
+
+-- ATRI
+CREATE TABLE IF NOT EXISTS atri_vision(
+    id TEXT,
+    url_or_path TEXT,
+    caption TEXT,
+    is_meme BOOLEAN,
+    keywords TEXT,
+    platform_name VARCHAR(32),
+    session_id VARCHAR(32),
+    sender_nickname VARCHAR(32),
+    timestamp INTEGER
+);
+
+CREATE TABLE IF NOT EXISTS webchat_conversation(
+    user_id TEXT, -- 会话 id
+    cid TEXT, -- 对话 id
+    history TEXT,
+    created_at INTEGER,
+    updated_at INTEGER,
+    title TEXT,
+    persona_id TEXT
+);
+
+PRAGMA encoding = 'UTF-8';
+"""
+
+
+class SQLiteDatabase:
+    def __init__(self, db_path: str) -> None:
+        super().__init__()
+        self.db_path = db_path
+
+        sql = INIT_SQL
+
+        # 初始化数据库
+        self.conn = self._get_conn(self.db_path)
+        c = self.conn.cursor()
+        c.executescript(sql)
+        self.conn.commit()
+
+        # 检查 webchat_conversation 的 title 字段是否存在
+        c.execute(
+            """
+            PRAGMA table_info(webchat_conversation)
+            """,
+        )
+        res = c.fetchall()
+        has_title = False
+        has_persona_id = False
+        for row in res:
+            if row[1] == "title":
+                has_title = True
+            if row[1] == "persona_id":
+                has_persona_id = True
+        if not has_title:
+            c.execute(
+                """
+                ALTER TABLE webchat_conversation ADD COLUMN title TEXT;
+                """,
+            )
+            self.conn.commit()
+        if not has_persona_id:
+            c.execute(
+                """
+                ALTER TABLE webchat_conversation ADD COLUMN persona_id TEXT;
+                """,
+            )
+            self.conn.commit()
+
+        c.close()
+
+    def _get_conn(self, db_path: str) -> sqlite3.Connection:
+        conn = sqlite3.connect(self.db_path)
+        conn.text_factory = str
+        return conn
+
+    def _exec_sql(self, sql: str, params: tuple = None):
+        conn = self.conn
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            conn = self._get_conn(self.db_path)
+            c = conn.cursor()
+
+        if params:
+            c.execute(sql, params)
+            c.close()
+        else:
+            c.execute(sql)
+            c.close()
+
+        conn.commit()
+
+    def insert_platform_metrics(self, metrics: dict):
+        for k, v in metrics.items():
+            self._exec_sql(
+                """
+                INSERT INTO platform(name, count, timestamp) VALUES (?, ?, ?)
+                """,
+                (k, v, int(time.time())),
+            )
+
+    def insert_llm_metrics(self, metrics: dict):
+        for k, v in metrics.items():
+            self._exec_sql(
+                """
+                INSERT INTO llm(name, count, timestamp) VALUES (?, ?, ?)
+                """,
+                (k, v, int(time.time())),
+            )
+
+    def get_base_stats(self, offset_sec: int = 86400) -> Stats:
+        """获取 offset_sec 秒前到现在的基础统计数据"""
+        where_clause = f" WHERE timestamp >= {int(time.time()) - offset_sec}"
+
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        c.execute(
+            """
+            SELECT * FROM platform
+            """
+            + where_clause,
+        )
+
+        platform = []
+        for row in c.fetchall():
+            platform.append(Platform(*row))
+
+        c.close()
+
+        return Stats(platform=platform)
+
+    def get_total_message_count(self) -> int:
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        c.execute(
+            """
+            SELECT SUM(count) FROM platform
+            """,
+        )
+        res = c.fetchone()
+        c.close()
+        return res[0]
+
+    def get_grouped_base_stats(self, offset_sec: int = 86400) -> Stats:
+        """获取 offset_sec 秒前到现在的基础统计数据(合并)"""
+        where_clause = f" WHERE timestamp >= {int(time.time()) - offset_sec}"
+
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        c.execute(
+            """
+            SELECT name, SUM(count), timestamp FROM platform
+            """
+            + where_clause
+            + " GROUP BY name",
+        )
+
+        platform = []
+        for row in c.fetchall():
+            platform.append(Platform(*row))
+
+        c.close()
+
+        return Stats(platform, [], [])
+
+    def get_conversation_by_user_id(self, user_id: str, cid: str) -> Conversation:
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        c.execute(
+            """
+            SELECT * FROM webchat_conversation WHERE user_id = ? AND cid = ?
+            """,
+            (user_id, cid),
+        )
+
+        res = c.fetchone()
+        c.close()
+
+        if not res:
+            return None
+
+        return Conversation(*res)
+
+    def new_conversation(self, user_id: str, cid: str):
+        history = "[]"
+        updated_at = int(time.time())
+        created_at = updated_at
+        self._exec_sql(
+            """
+            INSERT INTO webchat_conversation(user_id, cid, history, updated_at, created_at) VALUES (?, ?, ?, ?, ?)
+            """,
+            (user_id, cid, history, updated_at, created_at),
+        )
+
+    def get_conversations(self, user_id: str) -> tuple:
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        c.execute(
+            """
+            SELECT cid, created_at, updated_at, title, persona_id FROM webchat_conversation WHERE user_id = ? ORDER BY updated_at DESC
+            """,
+            (user_id,),
+        )
+
+        res = c.fetchall()
+        c.close()
+        conversations = []
+        for row in res:
+            cid = row[0]
+            created_at = row[1]
+            updated_at = row[2]
+            title = row[3]
+            persona_id = row[4]
+            conversations.append(
+                Conversation("", cid, "[]", created_at, updated_at, title, persona_id),
+            )
+        return conversations
+
+    def update_conversation(self, user_id: str, cid: str, history: str):
+        """更新对话，并且同时更新时间"""
+        updated_at = int(time.time())
+        self._exec_sql(
+            """
+            UPDATE webchat_conversation SET history = ?, updated_at = ? WHERE user_id = ? AND cid = ?
+            """,
+            (history, updated_at, user_id, cid),
+        )
+
+    def update_conversation_title(self, user_id: str, cid: str, title: str):
+        self._exec_sql(
+            """
+            UPDATE webchat_conversation SET title = ? WHERE user_id = ? AND cid = ?
+            """,
+            (title, user_id, cid),
+        )
+
+    def update_conversation_persona_id(self, user_id: str, cid: str, persona_id: str):
+        self._exec_sql(
+            """
+            UPDATE webchat_conversation SET persona_id = ? WHERE user_id = ? AND cid = ?
+            """,
+            (persona_id, user_id, cid),
+        )
+
+    def delete_conversation(self, user_id: str, cid: str):
+        self._exec_sql(
+            """
+            DELETE FROM webchat_conversation WHERE user_id = ? AND cid = ?
+            """,
+            (user_id, cid),
+        )
+
+    def get_all_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+    ) -> tuple[list[dict[str, Any]], int]:
+        """获取所有对话，支持分页，按更新时间降序排序"""
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        try:
+            # 获取总记录数
+            c.execute("""
+                SELECT COUNT(*) FROM webchat_conversation
+            """)
+            total_count = c.fetchone()[0]
+
+            # 计算偏移量
+            offset = (page - 1) * page_size
+
+            # 获取分页数据，按更新时间降序排序
+            c.execute(
+                """
+                SELECT user_id, cid, created_at, updated_at, title, persona_id
+                FROM webchat_conversation
+                ORDER BY updated_at DESC
+                LIMIT ? OFFSET ?
+            """,
+                (page_size, offset),
+            )
+
+            rows = c.fetchall()
+
+            conversations = []
+
+            for row in rows:
+                user_id, cid, created_at, updated_at, title, persona_id = row
+                # 确保 cid 是字符串类型且至少有8个字符，否则使用一个默认值
+                safe_cid = str(cid) if cid else "unknown"
+                display_cid = safe_cid[:8] if len(safe_cid) >= 8 else safe_cid
+
+                conversations.append(
+                    {
+                        "user_id": user_id or "",
+                        "cid": safe_cid,
+                        "title": title or f"对话 {display_cid}",
+                        "persona_id": persona_id or "",
+                        "created_at": created_at or 0,
+                        "updated_at": updated_at or 0,
+                    },
+                )
+
+            return conversations, total_count
+
+        except Exception as _:
+            # 返回空列表和0，确保即使出错也有有效的返回值
+            return [], 0
+        finally:
+            c.close()
+
+    def get_filtered_conversations(
+        self,
+        page: int = 1,
+        page_size: int = 20,
+        platforms: list[str] | None = None,
+        message_types: list[str] | None = None,
+        search_query: str | None = None,
+        exclude_ids: list[str] | None = None,
+        exclude_platforms: list[str] | None = None,
+    ) -> tuple[list[dict[str, Any]], int]:
+        """获取筛选后的对话列表"""
+        try:
+            c = self.conn.cursor()
+        except sqlite3.ProgrammingError:
+            c = self._get_conn(self.db_path).cursor()
+
+        try:
+            # 构建查询条件
+            where_clauses = []
+            params = []
+
+            # 平台筛选
+            if platforms and len(platforms) > 0:
+                platform_conditions = []
+                for platform in platforms:
+                    platform_conditions.append("user_id LIKE ?")
+                    params.append(f"{platform}:%")
+
+                if platform_conditions:
+                    where_clauses.append(f"({' OR '.join(platform_conditions)})")
+
+            # 消息类型筛选
+            if message_types and len(message_types) > 0:
+                message_type_conditions = []
+                for msg_type in message_types:
+                    message_type_conditions.append("user_id LIKE ?")
+                    params.append(f"%:{msg_type}:%")
+
+                if message_type_conditions:
+                    where_clauses.append(f"({' OR '.join(message_type_conditions)})")
+
+            # 搜索关键词
+            if search_query:
+                search_query = search_query.encode("unicode_escape").decode("utf-8")
+                where_clauses.append(
+                    "(title LIKE ? OR user_id LIKE ? OR cid LIKE ? OR history LIKE ?)",
+                )
+                search_param = f"%{search_query}%"
+                params.extend([search_param, search_param, search_param, search_param])
+
+            # 排除特定用户ID
+            if exclude_ids and len(exclude_ids) > 0:
+                for exclude_id in exclude_ids:
+                    where_clauses.append("user_id NOT LIKE ?")
+                    params.append(f"{exclude_id}%")
+
+            # 排除特定平台
+            if exclude_platforms and len(exclude_platforms) > 0:
+                for exclude_platform in exclude_platforms:
+                    where_clauses.append("user_id NOT LIKE ?")
+                    params.append(f"{exclude_platform}:%")
+
+            # 构建完整的 WHERE 子句
+            where_sql = " WHERE " + " AND ".join(where_clauses) if where_clauses else ""
+
+            # 构建计数查询
+            count_sql = f"SELECT COUNT(*) FROM webchat_conversation{where_sql}"
+
+            # 获取总记录数
+            c.execute(count_sql, params)
+            total_count = c.fetchone()[0]
+
+            # 计算偏移量
+            offset = (page - 1) * page_size
+
+            # 构建分页数据查询
+            data_sql = f"""
+                SELECT user_id, cid, created_at, updated_at, title, persona_id
+                FROM webchat_conversation
+                {where_sql}
+                ORDER BY updated_at DESC
+                LIMIT ? OFFSET ?
+            """
+            query_params = params + [page_size, offset]
+
+            # 获取分页数据
+            c.execute(data_sql, query_params)
+            rows = c.fetchall()
+
+            conversations = []
+
+            for row in rows:
+                user_id, cid, created_at, updated_at, title, persona_id = row
+                # 确保 cid 是字符串类型，否则使用一个默认值
+                safe_cid = str(cid) if cid else "unknown"
+                display_cid = safe_cid[:8] if len(safe_cid) >= 8 else safe_cid
+
+                conversations.append(
+                    {
+                        "user_id": user_id or "",
+                        "cid": safe_cid,
+                        "title": title or f"对话 {display_cid}",
+                        "persona_id": persona_id or "",
+                        "created_at": created_at or 0,
+                        "updated_at": updated_at or 0,
+                    },
+                )
+
+            return conversations, total_count
+
+        except Exception as _:
+            # 返回空列表和0，确保即使出错也有有效的返回值
+            return [], 0
+        finally:
+            c.close()

astrbot/core/db/po.py

@@ -1,32 +1,252 @@
-"""指标数据"""
-
+import uuid
 from dataclasses import dataclass, field
-from typing import List
+from datetime import datetime, timezone
+from typing import TypedDict
+
+from sqlmodel import (
+    JSON,
+    Field,
+    SQLModel,
+    Text,
+    UniqueConstraint,
+)
+
+
+class PlatformStat(SQLModel, table=True):
+    """This class represents the statistics of bot usage across different platforms.
+
+    Note: In astrbot v4, we moved `platform` table to here.
+    """
+
+    __tablename__ = "platform_stats"
+
+    id: int = Field(primary_key=True, sa_column_kwargs={"autoincrement": True})
+    timestamp: datetime = Field(nullable=False)
+    platform_id: str = Field(nullable=False)
+    platform_type: str = Field(nullable=False)  # such as "aiocqhttp", "slack", etc.
+    count: int = Field(default=0, nullable=False)
+
+    __table_args__ = (
+        UniqueConstraint(
+            "timestamp",
+            "platform_id",
+            "platform_type",
+            name="uix_platform_stats",
+        ),
+    )
+
+
+class ConversationV2(SQLModel, table=True):
+    __tablename__ = "conversations"
+
+    inner_conversation_id: int = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+    )
+    conversation_id: str = Field(
+        max_length=36,
+        nullable=False,
+        unique=True,
+        default_factory=lambda: str(uuid.uuid4()),
+    )
+    platform_id: str = Field(nullable=False)
+    user_id: str = Field(nullable=False)
+    content: list | None = Field(default=None, sa_type=JSON)
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+    title: str | None = Field(default=None, max_length=255)
+    persona_id: str | None = Field(default=None)
+
+    __table_args__ = (
+        UniqueConstraint(
+            "conversation_id",
+            name="uix_conversation_id",
+        ),
+    )
+
+
+class Persona(SQLModel, table=True):
+    """Persona is a set of instructions for LLMs to follow.
+
+    It can be used to customize the behavior of LLMs.
+    """
+
+    __tablename__ = "personas"
+
+    id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    persona_id: str = Field(max_length=255, nullable=False)
+    system_prompt: str = Field(sa_type=Text, nullable=False)
+    begin_dialogs: list | None = Field(default=None, sa_type=JSON)
+    """a list of strings, each representing a dialog to start with"""
+    tools: list | None = Field(default=None, sa_type=JSON)
+    """None means use ALL tools for default, empty list means no tools, otherwise a list of tool names."""
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+
+    __table_args__ = (
+        UniqueConstraint(
+            "persona_id",
+            name="uix_persona_id",
+        ),
+    )
+
+
+class Preference(SQLModel, table=True):
+    """This class represents preferences for bots."""
+
+    __tablename__ = "preferences"
+
+    id: int | None = Field(
+        default=None,
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+    )
+    scope: str = Field(nullable=False)
+    """Scope of the preference, such as 'global', 'umo', 'plugin'."""
+    scope_id: str = Field(nullable=False)
+    """ID of the scope, such as 'global', 'umo', 'plugin_name'."""
+    key: str = Field(nullable=False)
+    value: dict = Field(sa_type=JSON, nullable=False)
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+
+    __table_args__ = (
+        UniqueConstraint(
+            "scope",
+            "scope_id",
+            "key",
+            name="uix_preference_scope_scope_id_key",
+        ),
+    )
+
+
+class PlatformMessageHistory(SQLModel, table=True):
+    """This class represents the message history for a specific platform.
+
+    It is used to store messages that are not LLM-generated, such as user messages
+    or platform-specific messages.
+    """
+
+    __tablename__ = "platform_message_history"
+
+    id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    platform_id: str = Field(nullable=False)
+    user_id: str = Field(nullable=False)  # An id of group, user in platform
+    sender_id: str | None = Field(default=None)  # ID of the sender in the platform
+    sender_name: str | None = Field(
+        default=None,
+    )  # Name of the sender in the platform
+    content: dict = Field(sa_type=JSON, nullable=False)  # a message chain list
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+
+
+class Attachment(SQLModel, table=True):
+    """This class represents attachments for messages in AstrBot.
+
+    Attachments can be images, files, or other media types.
+    """
+
+    __tablename__ = "attachments"
+
+    inner_attachment_id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    attachment_id: str = Field(
+        max_length=36,
+        nullable=False,
+        unique=True,
+        default_factory=lambda: str(uuid.uuid4()),
+    )
+    path: str = Field(nullable=False)  # Path to the file on disk
+    type: str = Field(nullable=False)  # Type of the file (e.g., 'image', 'file')
+    mime_type: str = Field(nullable=False)  # MIME type of the file
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+
+    __table_args__ = (
+        UniqueConstraint(
+            "attachment_id",
+            name="uix_attachment_id",
+        ),
+    )
+
+
+@dataclass
+class Conversation:
+    """LLM 对话类
+
+    对于 WebChat，history 存储了包括指令、回复、图片等在内的所有消息。
+    对于其他平台的聊天，不存储非 LLM 的回复（因为考虑到已经存储在各自的平台上）。
+
+    在 v4.0.0 版本及之后，WebChat 的历史记录被迁移至 `PlatformMessageHistory` 表中，
+    """
+
+    platform_id: str
+    user_id: str
+    cid: str
+    """对话 ID, 是 uuid 格式的字符串"""
+    history: str = ""
+    """字符串格式的对话列表。"""
+    title: str | None = ""
+    persona_id: str | None = ""
+    created_at: int = 0
+    updated_at: int = 0
+
+
+class Personality(TypedDict):
+    """LLM 人格类。
+
+    在 v4.0.0 版本及之后，推荐使用上面的 Persona 类。并且， mood_imitation_dialogs 字段已被废弃。
+    """
+
+    prompt: str = ""
+    name: str = ""
+    begin_dialogs: list[str] = []
+    mood_imitation_dialogs: list[str] = []
+    """情感模拟对话预设。在 v4.0.0 版本及之后，已被废弃。"""
+    tools: list[str] | None = None
+    """工具列表。None 表示使用所有工具，空列表表示不使用任何工具"""
+
+    # cache
+    _begin_dialogs_processed: list[dict] = []
+    _mood_imitation_dialogs_processed: str = ""
+
+
+# ====
+# Deprecated, and will be removed in future versions.
+# ====
 
 
 @dataclass
 class Platform:
-    name: str
-    count: int
-    timestamp: int
+    """平台使用统计数据"""
 
-
-@dataclass
-class Provider:
-    name: str
-    count: int
-    timestamp: int
-
-
-@dataclass
-class Plugin:
-    name: str
-    count: int
-    timestamp: int
-
-
-@dataclass
-class Command:
     name: str
     count: int
     timestamp: int
@@ -34,48 +254,4 @@ class Command:
 
 @dataclass
 class Stats:
-    platform: List[Platform] = field(default_factory=list)
-    command: List[Command] = field(default_factory=list)
-    llm: List[Provider] = field(default_factory=list)
-
-
-@dataclass
-class LLMHistory:
-    """LLM 聊天时持久化的信息"""
-
-    provider_type: str
-    session_id: str
-    content: str
-
-
-@dataclass
-class ATRIVision:
-    """Deprecated"""
-
-    id: str
-    url_or_path: str
-    caption: str
-    is_meme: bool
-    keywords: List[str]
-    platform_name: str
-    session_id: str
-    sender_nickname: str
-    timestamp: int = -1
-
-
-@dataclass
-class Conversation:
-    """LLM 对话存储
-
-    对于网页聊天，history 存储了包括指令、回复、图片等在内的所有消息。
-    对于其他平台的聊天，不存储非 LLM 的回复（因为考虑到已经存储在各自的平台上）。
-    """
-
-    user_id: str
-    cid: str
-    history: str = ""
-    """字符串格式的列表。"""
-    created_at: int = 0
-    updated_at: int = 0
-    title: str = ""
-    persona_id: str = ""
+    platform: list[Platform] = field(default_factory=list)

astrbot/core/db/sqlite_init.sql

@@ -1,48 +0,0 @@
-CREATE TABLE IF NOT EXISTS platform(
-    name VARCHAR(32),
-    count INTEGER,
-    timestamp INTEGER
-);
-CREATE TABLE IF NOT EXISTS llm(
-    name VARCHAR(32),
-    count INTEGER,
-    timestamp INTEGER
-);
-CREATE TABLE IF NOT EXISTS plugin(
-    name VARCHAR(32),
-    count INTEGER,
-    timestamp INTEGER
-);
-CREATE TABLE IF NOT EXISTS command(
-    name VARCHAR(32),
-    count INTEGER,
-    timestamp INTEGER
-);
-CREATE TABLE IF NOT EXISTS llm_history(
-    provider_type VARCHAR(32),
-    session_id VARCHAR(32),
-    content TEXT
-);
-
--- ATRI
-CREATE TABLE IF NOT EXISTS atri_vision(
-    id TEXT,
-    url_or_path TEXT,
-    caption TEXT,
-    is_meme BOOLEAN,
-    keywords TEXT,
-    platform_name VARCHAR(32),
-    session_id VARCHAR(32),
-    sender_nickname VARCHAR(32),
-    timestamp INTEGER
-);
-
-CREATE TABLE IF NOT EXISTS webchat_conversation(
-    user_id TEXT,
-    cid TEXT,
-    history TEXT,
-    created_at INTEGER,
-    updated_at INTEGER,
-    title TEXT,
-    persona_id TEXT
-);

astrbot/core/db/vec_db/base.py

@@ -0,0 +1,73 @@
+import abc
+from dataclasses import dataclass
+
+
+@dataclass
+class Result:
+    similarity: float
+    data: dict
+
+
+class BaseVecDB:
+    async def initialize(self):
+        """初始化向量数据库"""
+
+    @abc.abstractmethod
+    async def insert(
+        self,
+        content: str,
+        metadata: dict | None = None,
+        id: str | None = None,
+    ) -> int:
+        """插入一条文本和其对应向量，自动生成 ID 并保持一致性。"""
+        ...
+
+    @abc.abstractmethod
+    async def insert_batch(
+        self,
+        contents: list[str],
+        metadatas: list[dict] | None = None,
+        ids: list[str] | None = None,
+        batch_size: int = 32,
+        tasks_limit: int = 3,
+        max_retries: int = 3,
+        progress_callback=None,
+    ) -> int:
+        """批量插入文本和其对应向量，自动生成 ID 并保持一致性。
+
+        Args:
+            progress_callback: 进度回调函数，接收参数 (current, total)
+
+        """
+        ...
+
+    @abc.abstractmethod
+    async def retrieve(
+        self,
+        query: str,
+        top_k: int = 5,
+        fetch_k: int = 20,
+        rerank: bool = False,
+        metadata_filters: dict | None = None,
+    ) -> list[Result]:
+        """搜索最相似的文档。
+        Args:
+            query (str): 查询文本
+            top_k (int): 返回的最相似文档的数量
+        Returns:
+            List[Result]: 查询结果
+        """
+        ...
+
+    @abc.abstractmethod
+    async def delete(self, doc_id: str) -> bool:
+        """删除指定文档。
+        Args:
+            doc_id (str): 要删除的文档 ID
+        Returns:
+            bool: 删除是否成功
+        """
+        ...
+
+    @abc.abstractmethod
+    async def close(self): ...

astrbot/core/db/vec_db/faiss_impl/__init__.py

@@ -0,0 +1,3 @@
+from .vec_db import FaissVecDB
+
+__all__ = ["FaissVecDB"]

astrbot/core/db/vec_db/faiss_impl/document_storage.py

@@ -0,0 +1,392 @@
+import json
+import os
+from contextlib import asynccontextmanager
+from datetime import datetime
+
+from sqlalchemy import Column, Text
+from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, create_async_engine
+from sqlalchemy.orm import sessionmaker
+from sqlmodel import Field, MetaData, SQLModel, col, func, select, text
+
+from astrbot.core import logger
+
+
+class BaseDocModel(SQLModel, table=False):
+    metadata = MetaData()
+
+
+class Document(BaseDocModel, table=True):
+    """SQLModel for documents table."""
+
+    __tablename__ = "documents"  # type: ignore
+
+    id: int | None = Field(
+        default=None,
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+    )
+    doc_id: str = Field(nullable=False)
+    text: str = Field(nullable=False)
+    metadata_: str | None = Field(default=None, sa_column=Column("metadata", Text))
+    created_at: datetime | None = Field(default=None)
+    updated_at: datetime | None = Field(default=None)
+
+
+class DocumentStorage:
+    def __init__(self, db_path: str):
+        self.db_path = db_path
+        self.DATABASE_URL = f"sqlite+aiosqlite:///{db_path}"
+        self.engine: AsyncEngine | None = None
+        self.async_session_maker: sessionmaker | None = None
+        self.sqlite_init_path = os.path.join(
+            os.path.dirname(__file__),
+            "sqlite_init.sql",
+        )
+
+    async def initialize(self):
+        """Initialize the SQLite database and create the documents table if it doesn't exist."""
+        await self.connect()
+        async with self.engine.begin() as conn:  # type: ignore
+            # Create tables using SQLModel
+            await conn.run_sync(BaseDocModel.metadata.create_all)
+
+            try:
+                await conn.execute(
+                    text(
+                        "ALTER TABLE documents ADD COLUMN kb_doc_id TEXT "
+                        "GENERATED ALWAYS AS (json_extract(metadata, '$.kb_doc_id')) STORED",
+                    ),
+                )
+                await conn.execute(
+                    text(
+                        "ALTER TABLE documents ADD COLUMN user_id TEXT "
+                        "GENERATED ALWAYS AS (json_extract(metadata, '$.user_id')) STORED",
+                    ),
+                )
+
+                # Create indexes
+                await conn.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_documents_kb_doc_id ON documents(kb_doc_id)",
+                    ),
+                )
+                await conn.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_documents_user_id ON documents(user_id)",
+                    ),
+                )
+            except BaseException:
+                pass
+
+            await conn.commit()
+
+    async def connect(self):
+        """Connect to the SQLite database."""
+        if self.engine is None:
+            self.engine = create_async_engine(
+                self.DATABASE_URL,
+                echo=False,
+                future=True,
+            )
+            self.async_session_maker = sessionmaker(
+                self.engine,  # type: ignore
+                class_=AsyncSession,
+                expire_on_commit=False,
+            )  # type: ignore
+
+    @asynccontextmanager
+    async def get_session(self):
+        """Context manager for database sessions."""
+        async with self.async_session_maker() as session:  # type: ignore
+            yield session
+
+    async def get_documents(
+        self,
+        metadata_filters: dict,
+        ids: list | None = None,
+        offset: int | None = 0,
+        limit: int | None = 100,
+    ) -> list[dict]:
+        """Retrieve documents by metadata filters and ids.
+
+        Args:
+            metadata_filters (dict): The metadata filters to apply.
+            ids (list | None): Optional list of document IDs to filter.
+            offset (int | None): Offset for pagination.
+            limit (int | None): Limit for pagination.
+
+        Returns:
+            list: The list of documents that match the filters.
+
+        """
+        if self.engine is None:
+            logger.warning(
+                "Database connection is not initialized, returning empty result",
+            )
+            return []
+
+        async with self.get_session() as session:
+            query = select(Document)
+
+            for key, val in metadata_filters.items():
+                query = query.where(
+                    text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                ).params(**{f"filter_{key}": val})
+
+            if ids is not None and len(ids) > 0:
+                valid_ids = [int(i) for i in ids if i != -1]
+                if valid_ids:
+                    query = query.where(col(Document.id).in_(valid_ids))
+
+            if limit is not None:
+                query = query.limit(limit)
+            if offset is not None:
+                query = query.offset(offset)
+
+            result = await session.execute(query)
+            documents = result.scalars().all()
+
+            return [self._document_to_dict(doc) for doc in documents]
+
+    async def insert_document(self, doc_id: str, text: str, metadata: dict) -> int:
+        """Insert a single document and return its integer ID.
+
+        Args:
+            doc_id (str): The document ID (UUID string).
+            text (str): The document text.
+            metadata (dict): The document metadata.
+
+        Returns:
+            int: The integer ID of the inserted document.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            document = Document(
+                doc_id=doc_id,
+                text=text,
+                metadata_=json.dumps(metadata),
+                created_at=datetime.now(),
+                updated_at=datetime.now(),
+            )
+            session.add(document)
+            await session.flush()  # Flush to get the ID
+            return document.id  # type: ignore
+
+    async def insert_documents_batch(
+        self,
+        doc_ids: list[str],
+        texts: list[str],
+        metadatas: list[dict],
+    ) -> list[int]:
+        """Batch insert documents and return their integer IDs.
+
+        Args:
+            doc_ids (list[str]): List of document IDs (UUID strings).
+            texts (list[str]): List of document texts.
+            metadatas (list[dict]): List of document metadata.
+
+        Returns:
+            list[int]: List of integer IDs of the inserted documents.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            import json
+
+            documents = []
+            for doc_id, text, metadata in zip(doc_ids, texts, metadatas):
+                document = Document(
+                    doc_id=doc_id,
+                    text=text,
+                    metadata_=json.dumps(metadata),
+                    created_at=datetime.now(),
+                    updated_at=datetime.now(),
+                )
+                documents.append(document)
+                session.add(document)
+
+            await session.flush()  # Flush to get all IDs
+            return [doc.id for doc in documents]  # type: ignore
+
+    async def delete_document_by_doc_id(self, doc_id: str):
+        """Delete a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id of the document to delete.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                await session.delete(document)
+
+    async def get_document_by_doc_id(self, doc_id: str):
+        """Retrieve a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id of the document to retrieve.
+
+        Returns:
+            dict: The document data or None if not found.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session:
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                return self._document_to_dict(document)
+            return None
+
+    async def update_document_by_doc_id(self, doc_id: str, new_text: str):
+        """Update a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id.
+            new_text (str): The new text to update the document with.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                document.text = new_text
+                document.updated_at = datetime.now()
+                session.add(document)
+
+    async def delete_documents(self, metadata_filters: dict):
+        """Delete documents by their metadata filters.
+
+        Args:
+            metadata_filters (dict): The metadata filters to apply.
+
+        """
+        if self.engine is None:
+            logger.warning(
+                "Database connection is not initialized, skipping delete operation",
+            )
+            return
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document)
+
+            for key, val in metadata_filters.items():
+                query = query.where(
+                    text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                ).params(**{f"filter_{key}": val})
+
+            result = await session.execute(query)
+            documents = result.scalars().all()
+
+            for doc in documents:
+                await session.delete(doc)
+
+    async def count_documents(self, metadata_filters: dict | None = None) -> int:
+        """Count documents in the database.
+
+        Args:
+            metadata_filters (dict | None): Metadata filters to apply.
+
+        Returns:
+            int: The count of documents.
+
+        """
+        if self.engine is None:
+            logger.warning("Database connection is not initialized, returning 0")
+            return 0
+
+        async with self.get_session() as session:
+            query = select(func.count(col(Document.id)))
+
+            if metadata_filters:
+                for key, val in metadata_filters.items():
+                    query = query.where(
+                        text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                    ).params(**{f"filter_{key}": val})
+
+            result = await session.execute(query)
+            count = result.scalar_one_or_none()
+            return count if count is not None else 0
+
+    async def get_user_ids(self) -> list[str]:
+        """Retrieve all user IDs from the documents table.
+
+        Returns:
+            list: A list of user IDs.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session:
+            query = text(
+                "SELECT DISTINCT user_id FROM documents WHERE user_id IS NOT NULL",
+            )
+            result = await session.execute(query)
+            rows = result.fetchall()
+            return [row[0] for row in rows]
+
+    def _document_to_dict(self, document: Document) -> dict:
+        """Convert a Document model to a dictionary.
+
+        Args:
+            document (Document): The document to convert.
+
+        Returns:
+            dict: The converted dictionary.
+
+        """
+        return {
+            "id": document.id,
+            "doc_id": document.doc_id,
+            "text": document.text,
+            "metadata": document.metadata_,
+            "created_at": document.created_at.isoformat()
+            if isinstance(document.created_at, datetime)
+            else document.created_at,
+            "updated_at": document.updated_at.isoformat()
+            if isinstance(document.updated_at, datetime)
+            else document.updated_at,
+        }
+
+    async def tuple_to_dict(self, row):
+        """Convert a tuple to a dictionary.
+
+        Args:
+            row (tuple): The row to convert.
+
+        Returns:
+            dict: The converted dictionary.
+
+        Note: This method is kept for backward compatibility but is no longer used internally.
+
+        """
+        return {
+            "id": row[0],
+            "doc_id": row[1],
+            "text": row[2],
+            "metadata": row[3],
+            "created_at": row[4],
+            "updated_at": row[5],
+        }
+
+    async def close(self):
+        """Close the connection to the SQLite database."""
+        if self.engine:
+            await self.engine.dispose()
+            self.engine = None
+            self.async_session_maker = None

astrbot/core/db/vec_db/faiss_impl/embedding_storage.py

@@ -0,0 +1,93 @@
+try:
+    import faiss
+except ModuleNotFoundError:
+    raise ImportError(
+        "faiss 未安装。请使用 'pip install faiss-cpu' 或 'pip install faiss-gpu' 安装。",
+    )
+import os
+
+import numpy as np
+
+
+class EmbeddingStorage:
+    def __init__(self, dimension: int, path: str | None = None):
+        self.dimension = dimension
+        self.path = path
+        self.index = None
+        if path and os.path.exists(path):
+            self.index = faiss.read_index(path)
+        else:
+            base_index = faiss.IndexFlatL2(dimension)
+            self.index = faiss.IndexIDMap(base_index)
+
+    async def insert(self, vector: np.ndarray, id: int):
+        """插入向量
+
+        Args:
+            vector (np.ndarray): 要插入的向量
+            id (int): 向量的ID
+        Raises:
+            ValueError: 如果向量的维度与存储的维度不匹配
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        if vector.shape[0] != self.dimension:
+            raise ValueError(
+                f"向量维度不匹配, 期望: {self.dimension}, 实际: {vector.shape[0]}",
+            )
+        self.index.add_with_ids(vector.reshape(1, -1), np.array([id]))
+        await self.save_index()
+
+    async def insert_batch(self, vectors: np.ndarray, ids: list[int]):
+        """批量插入向量
+
+        Args:
+            vectors (np.ndarray): 要插入的向量数组
+            ids (list[int]): 向量的ID列表
+        Raises:
+            ValueError: 如果向量的维度与存储的维度不匹配
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        if vectors.shape[1] != self.dimension:
+            raise ValueError(
+                f"向量维度不匹配, 期望: {self.dimension}, 实际: {vectors.shape[1]}",
+            )
+        self.index.add_with_ids(vectors, np.array(ids))
+        await self.save_index()
+
+    async def search(self, vector: np.ndarray, k: int) -> tuple:
+        """搜索最相似的向量
+
+        Args:
+            vector (np.ndarray): 查询向量
+            k (int): 返回的最相似向量的数量
+        Returns:
+            tuple: (距离, 索引)
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        faiss.normalize_L2(vector)
+        distances, indices = self.index.search(vector, k)
+        return distances, indices
+
+    async def delete(self, ids: list[int]):
+        """删除向量
+
+        Args:
+            ids (list[int]): 要删除的向量ID列表
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        id_array = np.array(ids, dtype=np.int64)
+        self.index.remove_ids(id_array)
+        await self.save_index()
+
+    async def save_index(self):
+        """保存索引
+
+        Args:
+            path (str): 保存索引的路径
+
+        """
+        faiss.write_index(self.index, self.path)

astrbot/core/db/vec_db/faiss_impl/sqlite_init.sql

@@ -0,0 +1,17 @@
+-- 创建文档存储表，包含 faiss 中文档的 id，文档文本，create_at，updated_at
+CREATE TABLE documents (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    doc_id TEXT NOT NULL,
+    text TEXT NOT NULL,
+    metadata TEXT,
+    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
+);
+
+ALTER TABLE documents
+ADD COLUMN group_id TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.group_id')) STORED;
+ALTER TABLE documents
+ADD COLUMN user_id TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.user_id')) STORED;
+
+CREATE INDEX idx_documents_user_id ON documents(user_id);
+CREATE INDEX idx_documents_group_id ON documents(group_id);

astrbot/core/db/vec_db/faiss_impl/vec_db.py

@@ -0,0 +1,204 @@
+import time
+import uuid
+
+import numpy as np
+
+from astrbot import logger
+from astrbot.core.provider.provider import EmbeddingProvider, RerankProvider
+
+from ..base import BaseVecDB, Result
+from .document_storage import DocumentStorage
+from .embedding_storage import EmbeddingStorage
+
+
+class FaissVecDB(BaseVecDB):
+    """A class to represent a vector database."""
+
+    def __init__(
+        self,
+        doc_store_path: str,
+        index_store_path: str,
+        embedding_provider: EmbeddingProvider,
+        rerank_provider: RerankProvider | None = None,
+    ):
+        self.doc_store_path = doc_store_path
+        self.index_store_path = index_store_path
+        self.embedding_provider = embedding_provider
+        self.document_storage = DocumentStorage(doc_store_path)
+        self.embedding_storage = EmbeddingStorage(
+            embedding_provider.get_dim(),
+            index_store_path,
+        )
+        self.embedding_provider = embedding_provider
+        self.rerank_provider = rerank_provider
+
+    async def initialize(self):
+        await self.document_storage.initialize()
+
+    async def insert(
+        self,
+        content: str,
+        metadata: dict | None = None,
+        id: str | None = None,
+    ) -> int:
+        """插入一条文本和其对应向量，自动生成 ID 并保持一致性。"""
+        metadata = metadata or {}
+        str_id = id or str(uuid.uuid4())  # 使用 UUID 作为原始 ID
+
+        vector = await self.embedding_provider.get_embedding(content)
+        vector = np.array(vector, dtype=np.float32)
+
+        # 使用 DocumentStorage 的方法插入文档
+        int_id = await self.document_storage.insert_document(str_id, content, metadata)
+
+        # 插入向量到 FAISS
+        await self.embedding_storage.insert(vector, int_id)
+        return int_id
+
+    async def insert_batch(
+        self,
+        contents: list[str],
+        metadatas: list[dict] | None = None,
+        ids: list[str] | None = None,
+        batch_size: int = 32,
+        tasks_limit: int = 3,
+        max_retries: int = 3,
+        progress_callback=None,
+    ) -> list[int]:
+        """批量插入文本和其对应向量，自动生成 ID 并保持一致性。
+
+        Args:
+            progress_callback: 进度回调函数，接收参数 (current, total)
+
+        """
+        metadatas = metadatas or [{} for _ in contents]
+        ids = ids or [str(uuid.uuid4()) for _ in contents]
+
+        start = time.time()
+        logger.debug(f"Generating embeddings for {len(contents)} contents...")
+        vectors = await self.embedding_provider.get_embeddings_batch(
+            contents,
+            batch_size=batch_size,
+            tasks_limit=tasks_limit,
+            max_retries=max_retries,
+            progress_callback=progress_callback,
+        )
+        end = time.time()
+        logger.debug(
+            f"Generated embeddings for {len(contents)} contents in {end - start:.2f} seconds.",
+        )
+
+        # 使用 DocumentStorage 的批量插入方法
+        int_ids = await self.document_storage.insert_documents_batch(
+            ids,
+            contents,
+            metadatas,
+        )
+
+        # 批量插入向量到 FAISS
+        vectors_array = np.array(vectors).astype("float32")
+        await self.embedding_storage.insert_batch(vectors_array, int_ids)
+        return int_ids
+
+    async def retrieve(
+        self,
+        query: str,
+        k: int = 5,
+        fetch_k: int = 20,
+        rerank: bool = False,
+        metadata_filters: dict | None = None,
+    ) -> list[Result]:
+        """搜索最相似的文档。
+
+        Args:
+            query (str): 查询文本
+            k (int): 返回的最相似文档的数量
+            fetch_k (int): 在根据 metadata 过滤前从 FAISS 中获取的数量
+            rerank (bool): 是否使用重排序。这需要在实例化时提供 rerank_provider, 如果未提供并且 rerank 为 True, 不会抛出异常。
+            metadata_filters (dict): 元数据过滤器
+
+        Returns:
+            List[Result]: 查询结果
+
+        """
+        embedding = await self.embedding_provider.get_embedding(query)
+        scores, indices = await self.embedding_storage.search(
+            vector=np.array([embedding]).astype("float32"),
+            k=fetch_k if metadata_filters else k,
+        )
+        if len(indices[0]) == 0 or indices[0][0] == -1:
+            return []
+        # normalize scores
+        scores[0] = 1.0 - (scores[0] / 2.0)
+        # NOTE: maybe the size is less than k.
+        fetched_docs = await self.document_storage.get_documents(
+            metadata_filters=metadata_filters or {},
+            ids=indices[0],
+        )
+        if not fetched_docs:
+            return []
+        result_docs: list[Result] = []
+
+        idx_pos = {fetch_doc["id"]: idx for idx, fetch_doc in enumerate(fetched_docs)}
+        for i, indice_idx in enumerate(indices[0]):
+            pos = idx_pos.get(indice_idx)
+            if pos is None:
+                continue
+            fetch_doc = fetched_docs[pos]
+            score = scores[0][i]
+            result_docs.append(Result(similarity=float(score), data=fetch_doc))
+
+        top_k_results = result_docs[:k]
+
+        if rerank and self.rerank_provider:
+            documents = [doc.data["text"] for doc in top_k_results]
+            reranked_results = await self.rerank_provider.rerank(query, documents)
+            reranked_results = sorted(
+                reranked_results,
+                key=lambda x: x.relevance_score,
+                reverse=True,
+            )
+            top_k_results = [
+                top_k_results[reranked_result.index]
+                for reranked_result in reranked_results
+            ]
+
+        return top_k_results
+
+    async def delete(self, doc_id: str):
+        """删除一条文档块（chunk）"""
+        # 获得对应的 int id
+        result = await self.document_storage.get_document_by_doc_id(doc_id)
+        int_id = result["id"] if result else None
+        if int_id is None:
+            return
+
+        # 使用 DocumentStorage 的删除方法
+        await self.document_storage.delete_document_by_doc_id(doc_id)
+        await self.embedding_storage.delete([int_id])
+
+    async def close(self):
+        await self.document_storage.close()
+
+    async def count_documents(self, metadata_filter: dict | None = None) -> int:
+        """计算文档数量
+
+        Args:
+            metadata_filter (dict | None): 元数据过滤器
+
+        """
+        count = await self.document_storage.count_documents(
+            metadata_filters=metadata_filter or {},
+        )
+        return count
+
+    async def delete_documents(self, metadata_filters: dict):
+        """根据元数据过滤器删除文档"""
+        docs = await self.document_storage.get_documents(
+            metadata_filters=metadata_filters,
+            offset=None,
+            limit=None,
+        )
+        doc_ids: list[int] = [doc["id"] for doc in docs]
+        await self.embedding_storage.delete(doc_ids)
+        await self.document_storage.delete_documents(metadata_filters=metadata_filters)

astrbot/core/event_bus.py

@@ -1,27 +1,61 @@
+"""事件总线, 用于处理事件的分发和处理
+事件总线是一个异步队列, 用于接收各种消息事件, 并将其发送到Scheduler调度器进行处理
+其中包含了一个无限循环的调度函数, 用于从事件队列中获取新的事件, 并创建一个新的异步任务来执行管道调度器的处理逻辑
+
+class:
+    EventBus: 事件总线, 用于处理事件的分发和处理
+
+工作流程:
+1. 维护一个异步队列, 来接受各种消息事件
+2. 无限循环的调度函数, 从事件队列中获取新的事件, 打印日志并创建一个新的异步任务来执行管道调度器的处理逻辑
+"""
+
 import asyncio
 from asyncio import Queue
-from astrbot.core.pipeline.scheduler import PipelineScheduler
+
 from astrbot.core import logger
+from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
+from astrbot.core.pipeline.scheduler import PipelineScheduler
+
 from .platform import AstrMessageEvent
 
 
 class EventBus:
-    def __init__(self, event_queue: Queue, pipeline_scheduler: PipelineScheduler):
-        self.event_queue = event_queue
-        self.pipeline_scheduler = pipeline_scheduler
+    """用于处理事件的分发和处理"""
+
+    def __init__(
+        self,
+        event_queue: Queue,
+        pipeline_scheduler_mapping: dict[str, PipelineScheduler],
+        astrbot_config_mgr: AstrBotConfigManager = None,
+    ):
+        self.event_queue = event_queue  # 事件队列
+        # abconf uuid -> scheduler
+        self.pipeline_scheduler_mapping = pipeline_scheduler_mapping
+        self.astrbot_config_mgr = astrbot_config_mgr
 
     async def dispatch(self):
         while True:
             event: AstrMessageEvent = await self.event_queue.get()
-            self._print_event(event)
-            asyncio.create_task(self.pipeline_scheduler.execute(event))
+            conf_info = self.astrbot_config_mgr.get_conf_info(event.unified_msg_origin)
+            self._print_event(event, conf_info["name"])
+            scheduler = self.pipeline_scheduler_mapping.get(conf_info["id"])
+            asyncio.create_task(scheduler.execute(event))
 
-    def _print_event(self, event: AstrMessageEvent):
+    def _print_event(self, event: AstrMessageEvent, conf_name: str):
+        """用于记录事件信息
+
+        Args:
+            event (AstrMessageEvent): 事件对象
+
+        """
+        # 如果有发送者名称: [平台名] 发送者名称/发送者ID: 消息概要
         if event.get_sender_name():
             logger.info(
-                f"[{event.get_platform_name()}] {event.get_sender_name()}/{event.get_sender_id()}: {event.get_message_outline()}"
+                f"[{conf_name}] [{event.get_platform_id()}({event.get_platform_name()})] {event.get_sender_name()}/{event.get_sender_id()}: {event.get_message_outline()}",
             )
+        # 没有发送者名称: [平台名] 发送者ID: 消息概要
         else:
             logger.info(
-                f"[{event.get_platform_name()}] {event.get_sender_id()}: {event.get_message_outline()}"
+                f"[{conf_name}] [{event.get_platform_id()}({event.get_platform_name()})] {event.get_sender_id()}: {event.get_message_outline()}",
             )

astrbot/core/file_token_service.py

@@ -0,0 +1,98 @@
+import asyncio
+import os
+import platform
+import time
+import uuid
+from urllib.parse import unquote, urlparse
+
+
+class FileTokenService:
+    """维护一个简单的基于令牌的文件下载服务，支持超时和懒清除。"""
+
+    def __init__(self, default_timeout: float = 300):
+        self.lock = asyncio.Lock()
+        self.staged_files = {}  # token: (file_path, expire_time)
+        self.default_timeout = default_timeout
+
+    async def _cleanup_expired_tokens(self):
+        """清理过期的令牌"""
+        now = time.time()
+        expired_tokens = [
+            token for token, (_, expire) in self.staged_files.items() if expire < now
+        ]
+        for token in expired_tokens:
+            self.staged_files.pop(token, None)
+
+    async def check_token_expired(self, file_token: str) -> bool:
+        async with self.lock:
+            await self._cleanup_expired_tokens()
+            return file_token not in self.staged_files
+
+    async def register_file(self, file_path: str, timeout: float | None = None) -> str:
+        """向令牌服务注册一个文件。
+
+        Args:
+            file_path(str): 文件路径
+            timeout(float): 超时时间，单位秒（可选）
+
+        Returns:
+            str: 一个单次令牌
+
+        Raises:
+            FileNotFoundError: 当路径不存在时抛出
+
+        """
+        # 处理 file:///
+        try:
+            parsed_uri = urlparse(file_path)
+            if parsed_uri.scheme == "file":
+                local_path = unquote(parsed_uri.path)
+                if platform.system() == "Windows" and local_path.startswith("/"):
+                    local_path = local_path[1:]
+            else:
+                # 如果没有 file:/// 前缀，则认为是普通路径
+                local_path = file_path
+        except Exception:
+            # 解析失败时，按原路径处理
+            local_path = file_path
+
+        async with self.lock:
+            await self._cleanup_expired_tokens()
+
+            if not os.path.exists(local_path):
+                raise FileNotFoundError(
+                    f"文件不存在: {local_path} (原始输入: {file_path})",
+                )
+
+            file_token = str(uuid.uuid4())
+            expire_time = time.time() + (
+                timeout if timeout is not None else self.default_timeout
+            )
+            # 存储转换后的真实路径
+            self.staged_files[file_token] = (local_path, expire_time)
+            return file_token
+
+    async def handle_file(self, file_token: str) -> str:
+        """根据令牌获取文件路径，使用后令牌失效。
+
+        Args:
+            file_token(str): 注册时返回的令牌
+
+        Returns:
+            str: 文件路径
+
+        Raises:
+            KeyError: 当令牌不存在或已过期时抛出
+            FileNotFoundError: 当文件本身已被删除时抛出
+
+        """
+        async with self.lock:
+            await self._cleanup_expired_tokens()
+
+            if file_token not in self.staged_files:
+                raise KeyError(f"无效或过期的文件 token: {file_token}")
+
+            file_path, _ = self.staged_files.pop(file_token)
+            if not os.path.exists(file_path):
+                raise FileNotFoundError(f"文件不存在: {file_path}")
+            return file_path

astrbot/core/initial_loader.py

@@ -0,0 +1,57 @@
+"""AstrBot 启动器，负责初始化和启动核心组件和仪表板服务器。
+
+工作流程:
+1. 初始化核心生命周期, 传递数据库和日志代理实例到核心生命周期
+2. 运行核心生命周期任务和仪表板服务器
+"""
+
+import asyncio
+import traceback
+
+from astrbot.core import LogBroker, logger
+from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
+from astrbot.core.db import BaseDatabase
+from astrbot.dashboard.server import AstrBotDashboard
+
+
+class InitialLoader:
+    """AstrBot 启动器，负责初始化和启动核心组件和仪表板服务器。"""
+
+    def __init__(self, db: BaseDatabase, log_broker: LogBroker):
+        self.db = db
+        self.logger = logger
+        self.log_broker = log_broker
+        self.webui_dir: str | None = None
+
+    async def start(self):
+        core_lifecycle = AstrBotCoreLifecycle(self.log_broker, self.db)
+
+        try:
+            await core_lifecycle.initialize()
+        except Exception as e:
+            logger.critical(traceback.format_exc())
+            logger.critical(f"😭 初始化 AstrBot 失败：{e} !!!")
+            return
+
+        core_task = core_lifecycle.start()
+
+        webui_dir = self.webui_dir
+
+        self.dashboard_server = AstrBotDashboard(
+            core_lifecycle,
+            self.db,
+            core_lifecycle.dashboard_shutdown_event,
+            webui_dir,
+        )
+
+        coro = self.dashboard_server.run()
+        if coro:
+            # 启动核心任务和仪表板服务器
+            task = asyncio.gather(core_task, coro)
+        else:
+            task = core_task
+        try:
+            await task  # 整个AstrBot在这里运行
+        except asyncio.CancelledError:
+            logger.info("🌈 正在关闭 AstrBot...")
+            await core_lifecycle.stop()

astrbot/core/knowledge_base/chunking/__init__.py

@@ -0,0 +1,9 @@
+"""文档分块模块"""
+
+from .base import BaseChunker
+from .fixed_size import FixedSizeChunker
+
+__all__ = [
+    "BaseChunker",
+    "FixedSizeChunker",
+]

astrbot/core/knowledge_base/chunking/base.py

@@ -0,0 +1,25 @@
+"""文档分块器基类
+
+定义了文档分块处理的抽象接口。
+"""
+
+from abc import ABC, abstractmethod
+
+
+class BaseChunker(ABC):
+    """分块器基类
+
+    所有分块器都应该继承此类并实现 chunk 方法。
+    """
+
+    @abstractmethod
+    async def chunk(self, text: str, **kwargs) -> list[str]:
+        """将文本分块
+
+        Args:
+            text: 输入文本
+
+        Returns:
+            list[str]: 分块后的文本列表
+
+        """

astrbot/core/knowledge_base/chunking/fixed_size.py

@@ -0,0 +1,59 @@
+"""固定大小分块器
+
+按照固定的字符数将文本分块,支持重叠区域。
+"""
+
+from .base import BaseChunker
+
+
+class FixedSizeChunker(BaseChunker):
+    """固定大小分块器
+
+    按照固定的字符数分块,并支持块之间的重叠。
+    """
+
+    def __init__(self, chunk_size: int = 512, chunk_overlap: int = 50):
+        """初始化分块器
+
+        Args:
+            chunk_size: 块的大小(字符数)
+            chunk_overlap: 块之间的重叠字符数
+
+        """
+        self.chunk_size = chunk_size
+        self.chunk_overlap = chunk_overlap
+
+    async def chunk(self, text: str, **kwargs) -> list[str]:
+        """固定大小分块
+
+        Args:
+            text: 输入文本
+            chunk_size: 每个文本块的最大大小
+            chunk_overlap: 每个文本块之间的重叠部分大小
+
+        Returns:
+            list[str]: 分块后的文本列表
+
+        """
+        chunk_size = kwargs.get("chunk_size", self.chunk_size)
+        chunk_overlap = kwargs.get("chunk_overlap", self.chunk_overlap)
+
+        chunks = []
+        start = 0
+        text_len = len(text)
+
+        while start < text_len:
+            end = start + chunk_size
+            chunk = text[start:end]
+
+            if chunk:
+                chunks.append(chunk)
+
+            # 移动窗口,保留重叠部分
+            start = end - chunk_overlap
+
+            # 防止无限循环: 如果重叠过大,直接移到end
+            if start >= end or chunk_overlap >= chunk_size:
+                start = end
+
+        return chunks

astrbot/core/knowledge_base/chunking/recursive.py

@@ -0,0 +1,161 @@
+from collections.abc import Callable
+
+from .base import BaseChunker
+
+
+class RecursiveCharacterChunker(BaseChunker):
+    def __init__(
+        self,
+        chunk_size: int = 500,
+        chunk_overlap: int = 100,
+        length_function: Callable[[str], int] = len,
+        is_separator_regex: bool = False,
+        separators: list[str] | None = None,
+    ):
+        """初始化递归字符文本分割器
+
+        Args:
+            chunk_size: 每个文本块的最大大小
+            chunk_overlap: 每个文本块之间的重叠部分大小
+            length_function: 计算文本长度的函数
+            is_separator_regex: 分隔符是否为正则表达式
+            separators: 用于分割文本的分隔符列表，按优先级排序
+
+        """
+        self.chunk_size = chunk_size
+        self.chunk_overlap = chunk_overlap
+        self.length_function = length_function
+        self.is_separator_regex = is_separator_regex
+
+        # 默认分隔符列表，按优先级从高到低
+        self.separators = separators or [
+            "\n\n",  # 段落
+            "\n",  # 换行
+            "。",  # 中文句子
+            "，",  # 中文逗号
+            ". ",  # 句子
+            ", ",  # 逗号分隔
+            " ",  # 单词
+            "",  # 字符
+        ]
+
+    async def chunk(self, text: str, **kwargs) -> list[str]:
+        """递归地将文本分割成块
+
+        Args:
+            text: 要分割的文本
+            chunk_size: 每个文本块的最大大小
+            chunk_overlap: 每个文本块之间的重叠部分大小
+
+        Returns:
+            分割后的文本块列表
+
+        """
+        if not text:
+            return []
+
+        overlap = kwargs.get("chunk_overlap", self.chunk_overlap)
+        chunk_size = kwargs.get("chunk_size", self.chunk_size)
+
+        text_length = self.length_function(text)
+        if text_length <= chunk_size:
+            return [text]
+
+        for separator in self.separators:
+            if separator == "":
+                return self._split_by_character(text, chunk_size, overlap)
+
+            if separator in text:
+                splits = text.split(separator)
+                # 重新添加分隔符（除了最后一个片段）
+                splits = [s + separator for s in splits[:-1]] + [splits[-1]]
+                splits = [s for s in splits if s]
+                if len(splits) == 1:
+                    continue
+
+                # 递归合并分割后的文本块
+                final_chunks = []
+                current_chunk = []
+                current_chunk_length = 0
+
+                for split in splits:
+                    split_length = self.length_function(split)
+
+                    # 如果单个分割部分已经超过了chunk_size，需要递归分割
+                    if split_length > chunk_size:
+                        # 先处理当前积累的块
+                        if current_chunk:
+                            combined_text = "".join(current_chunk)
+                            final_chunks.extend(
+                                await self.chunk(
+                                    combined_text,
+                                    chunk_size=chunk_size,
+                                    chunk_overlap=overlap,
+                                ),
+                            )
+                            current_chunk = []
+                            current_chunk_length = 0
+
+                        # 递归分割过大的部分
+                        final_chunks.extend(
+                            await self.chunk(
+                                split,
+                                chunk_size=chunk_size,
+                                chunk_overlap=overlap,
+                            ),
+                        )
+                    # 如果添加这部分会使当前块超过chunk_size
+                    elif current_chunk_length + split_length > chunk_size:
+                        # 合并当前块并添加到结果中
+                        combined_text = "".join(current_chunk)
+                        final_chunks.append(combined_text)
+
+                        # 处理重叠部分
+                        overlap_start = max(0, len(combined_text) - overlap)
+                        if overlap_start > 0:
+                            overlap_text = combined_text[overlap_start:]
+                            current_chunk = [overlap_text, split]
+                            current_chunk_length = (
+                                self.length_function(overlap_text) + split_length
+                            )
+                        else:
+                            current_chunk = [split]
+                            current_chunk_length = split_length
+                    else:
+                        # 添加到当前块
+                        current_chunk.append(split)
+                        current_chunk_length += split_length
+
+                # 处理剩余的块
+                if current_chunk:
+                    final_chunks.append("".join(current_chunk))
+
+                return final_chunks
+
+        return [text]
+
+    def _split_by_character(
+        self,
+        text: str,
+        chunk_size: int | None = None,
+        overlap: int | None = None,
+    ) -> list[str]:
+        """按字符级别分割文本
+
+        Args:
+            text: 要分割的文本
+
+        Returns:
+            分割后的文本块列表
+
+        """
+        chunk_size = chunk_size or self.chunk_size
+        overlap = overlap or self.chunk_overlap
+        result = []
+        for i in range(0, len(text), chunk_size - overlap):
+            end = min(i + chunk_size, len(text))
+            result.append(text[i:end])
+            if end == len(text):
+                break
+
+        return result

astrbot/core/knowledge_base/kb_db_sqlite.py

@@ -0,0 +1,301 @@
+from contextlib import asynccontextmanager
+from pathlib import Path
+
+from sqlalchemy import delete, func, select, text, update
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
+from sqlmodel import col, desc
+
+from astrbot.core import logger
+from astrbot.core.db.vec_db.faiss_impl import FaissVecDB
+from astrbot.core.knowledge_base.models import (
+    BaseKBModel,
+    KBDocument,
+    KBMedia,
+    KnowledgeBase,
+)
+
+
+class KBSQLiteDatabase:
+    def __init__(self, db_path: str = "data/knowledge_base/kb.db") -> None:
+        """初始化知识库数据库
+
+        Args:
+            db_path: 数据库文件路径, 默认为 data/knowledge_base/kb.db
+
+        """
+        self.db_path = db_path
+        self.DATABASE_URL = f"sqlite+aiosqlite:///{db_path}"
+        self.inited = False
+
+        # 确保目录存在
+        Path(db_path).parent.mkdir(parents=True, exist_ok=True)
+
+        # 创建异步引擎
+        self.engine = create_async_engine(
+            self.DATABASE_URL,
+            echo=False,
+            pool_pre_ping=True,
+            pool_recycle=3600,
+        )
+
+        # 创建会话工厂
+        self.async_session = async_sessionmaker(
+            self.engine,
+            class_=AsyncSession,
+            expire_on_commit=False,
+        )
+
+    @asynccontextmanager
+    async def get_db(self):
+        """获取数据库会话
+
+        用法:
+            async with kb_db.get_db() as session:
+                # 执行数据库操作
+                result = await session.execute(stmt)
+        """
+        async with self.async_session() as session:
+            yield session
+
+    async def initialize(self) -> None:
+        """初始化数据库,创建表并配置 SQLite 参数"""
+        async with self.engine.begin() as conn:
+            # 创建所有知识库相关表
+            await conn.run_sync(BaseKBModel.metadata.create_all)
+
+            # 配置 SQLite 性能优化参数
+            await conn.execute(text("PRAGMA journal_mode=WAL"))
+            await conn.execute(text("PRAGMA synchronous=NORMAL"))
+            await conn.execute(text("PRAGMA cache_size=20000"))
+            await conn.execute(text("PRAGMA temp_store=MEMORY"))
+            await conn.execute(text("PRAGMA mmap_size=134217728"))
+            await conn.execute(text("PRAGMA optimize"))
+            await conn.commit()
+
+        self.inited = True
+
+    async def migrate_to_v1(self) -> None:
+        """执行知识库数据库 v1 迁移
+
+        创建所有必要的索引以优化查询性能
+        """
+        async with self.get_db() as session:
+            session: AsyncSession
+            async with session.begin():
+                # 创建知识库表索引
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_kb_kb_id "
+                        "ON knowledge_bases(kb_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_kb_name "
+                        "ON knowledge_bases(kb_name)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_kb_created_at "
+                        "ON knowledge_bases(created_at)",
+                    ),
+                )
+
+                # 创建文档表索引
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_doc_doc_id "
+                        "ON kb_documents(doc_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_doc_kb_id "
+                        "ON kb_documents(kb_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_doc_name "
+                        "ON kb_documents(doc_name)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_doc_type "
+                        "ON kb_documents(file_type)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_doc_created_at "
+                        "ON kb_documents(created_at)",
+                    ),
+                )
+
+                # 创建多媒体表索引
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_media_media_id "
+                        "ON kb_media(media_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_media_doc_id "
+                        "ON kb_media(doc_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_media_kb_id ON kb_media(kb_id)",
+                    ),
+                )
+                await session.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_media_type "
+                        "ON kb_media(media_type)",
+                    ),
+                )
+
+                await session.commit()
+
+    async def close(self) -> None:
+        """关闭数据库连接"""
+        await self.engine.dispose()
+        logger.info(f"知识库数据库已关闭: {self.db_path}")
+
+    async def get_kb_by_id(self, kb_id: str) -> KnowledgeBase | None:
+        """根据 ID 获取知识库"""
+        async with self.get_db() as session:
+            stmt = select(KnowledgeBase).where(col(KnowledgeBase.kb_id) == kb_id)
+            result = await session.execute(stmt)
+            return result.scalar_one_or_none()
+
+    async def get_kb_by_name(self, kb_name: str) -> KnowledgeBase | None:
+        """根据名称获取知识库"""
+        async with self.get_db() as session:
+            stmt = select(KnowledgeBase).where(col(KnowledgeBase.kb_name) == kb_name)
+            result = await session.execute(stmt)
+            return result.scalar_one_or_none()
+
+    async def list_kbs(self, offset: int = 0, limit: int = 100) -> list[KnowledgeBase]:
+        """列出所有知识库"""
+        async with self.get_db() as session:
+            stmt = (
+                select(KnowledgeBase)
+                .offset(offset)
+                .limit(limit)
+                .order_by(desc(KnowledgeBase.created_at))
+            )
+            result = await session.execute(stmt)
+            return list(result.scalars().all())
+
+    async def count_kbs(self) -> int:
+        """统计知识库数量"""
+        async with self.get_db() as session:
+            stmt = select(func.count(col(KnowledgeBase.id)))
+            result = await session.execute(stmt)
+            return result.scalar() or 0
+
+    # ===== 文档查询 =====
+
+    async def get_document_by_id(self, doc_id: str) -> KBDocument | None:
+        """根据 ID 获取文档"""
+        async with self.get_db() as session:
+            stmt = select(KBDocument).where(col(KBDocument.doc_id) == doc_id)
+            result = await session.execute(stmt)
+            return result.scalar_one_or_none()
+
+    async def list_documents_by_kb(
+        self,
+        kb_id: str,
+        offset: int = 0,
+        limit: int = 100,
+    ) -> list[KBDocument]:
+        """列出知识库的所有文档"""
+        async with self.get_db() as session:
+            stmt = (
+                select(KBDocument)
+                .where(col(KBDocument.kb_id) == kb_id)
+                .offset(offset)
+                .limit(limit)
+                .order_by(desc(KBDocument.created_at))
+            )
+            result = await session.execute(stmt)
+            return list(result.scalars().all())
+
+    async def count_documents_by_kb(self, kb_id: str) -> int:
+        """统计知识库的文档数量"""
+        async with self.get_db() as session:
+            stmt = select(func.count(col(KBDocument.id))).where(
+                col(KBDocument.kb_id) == kb_id,
+            )
+            result = await session.execute(stmt)
+            return result.scalar() or 0
+
+    async def get_document_with_metadata(self, doc_id: str) -> dict | None:
+        async with self.get_db() as session:
+            stmt = (
+                select(KBDocument, KnowledgeBase)
+                .join(KnowledgeBase, col(KBDocument.kb_id) == col(KnowledgeBase.kb_id))
+                .where(col(KBDocument.doc_id) == doc_id)
+            )
+            result = await session.execute(stmt)
+            row = result.first()
+
+            if not row:
+                return None
+
+            return {
+                "document": row[0],
+                "knowledge_base": row[1],
+            }
+
+    async def delete_document_by_id(self, doc_id: str, vec_db: FaissVecDB):
+        """删除单个文档及其相关数据"""
+        # 在知识库表中删除
+        async with self.get_db() as session, session.begin():
+            # 删除文档记录
+            delete_stmt = delete(KBDocument).where(col(KBDocument.doc_id) == doc_id)
+            await session.execute(delete_stmt)
+            await session.commit()
+
+        # 在 vec db 中删除相关向量
+        await vec_db.delete_documents(metadata_filters={"kb_doc_id": doc_id})
+
+    # ===== 多媒体查询 =====
+
+    async def list_media_by_doc(self, doc_id: str) -> list[KBMedia]:
+        """列出文档的所有多媒体资源"""
+        async with self.get_db() as session:
+            stmt = select(KBMedia).where(col(KBMedia.doc_id) == doc_id)
+            result = await session.execute(stmt)
+            return list(result.scalars().all())
+
+    async def get_media_by_id(self, media_id: str) -> KBMedia | None:
+        """根据 ID 获取多媒体资源"""
+        async with self.get_db() as session:
+            stmt = select(KBMedia).where(col(KBMedia.media_id) == media_id)
+            result = await session.execute(stmt)
+            return result.scalar_one_or_none()
+
+    async def update_kb_stats(self, kb_id: str, vec_db: FaissVecDB) -> None:
+        """更新知识库统计信息"""
+        chunk_cnt = await vec_db.count_documents()
+
+        async with self.get_db() as session, session.begin():
+            update_stmt = (
+                update(KnowledgeBase)
+                .where(col(KnowledgeBase.kb_id) == kb_id)
+                .values(
+                    doc_count=select(func.count(col(KBDocument.id)))
+                    .where(col(KBDocument.kb_id) == kb_id)
+                    .scalar_subquery(),
+                    chunk_count=chunk_cnt,
+                )
+            )
+
+            await session.execute(update_stmt)
+            await session.commit()

astrbot/core/knowledge_base/kb_helper.py

@@ -0,0 +1,361 @@
+import json
+import uuid
+from pathlib import Path
+
+import aiofiles
+
+from astrbot.core import logger
+from astrbot.core.db.vec_db.base import BaseVecDB
+from astrbot.core.db.vec_db.faiss_impl.vec_db import FaissVecDB
+from astrbot.core.provider.manager import ProviderManager
+from astrbot.core.provider.provider import EmbeddingProvider, RerankProvider
+
+from .chunking.base import BaseChunker
+from .kb_db_sqlite import KBSQLiteDatabase
+from .models import KBDocument, KBMedia, KnowledgeBase
+from .parsers.util import select_parser
+
+
+class KBHelper:
+    vec_db: BaseVecDB
+    kb: KnowledgeBase
+
+    def __init__(
+        self,
+        kb_db: KBSQLiteDatabase,
+        kb: KnowledgeBase,
+        provider_manager: ProviderManager,
+        kb_root_dir: str,
+        chunker: BaseChunker,
+    ):
+        self.kb_db = kb_db
+        self.kb = kb
+        self.prov_mgr = provider_manager
+        self.kb_root_dir = kb_root_dir
+        self.chunker = chunker
+
+        self.kb_dir = Path(self.kb_root_dir) / self.kb.kb_id
+        self.kb_medias_dir = Path(self.kb_dir) / "medias" / self.kb.kb_id
+        self.kb_files_dir = Path(self.kb_dir) / "files" / self.kb.kb_id
+
+        self.kb_medias_dir.mkdir(parents=True, exist_ok=True)
+        self.kb_files_dir.mkdir(parents=True, exist_ok=True)
+
+    async def initialize(self):
+        await self._ensure_vec_db()
+
+    async def get_ep(self) -> EmbeddingProvider:
+        if not self.kb.embedding_provider_id:
+            raise ValueError(f"知识库 {self.kb.kb_name} 未配置 Embedding Provider")
+        ep: EmbeddingProvider = await self.prov_mgr.get_provider_by_id(
+            self.kb.embedding_provider_id,
+        )  # type: ignore
+        if not ep:
+            raise ValueError(
+                f"无法找到 ID 为 {self.kb.embedding_provider_id} 的 Embedding Provider",
+            )
+        return ep
+
+    async def get_rp(self) -> RerankProvider | None:
+        if not self.kb.rerank_provider_id:
+            return None
+        rp: RerankProvider = await self.prov_mgr.get_provider_by_id(
+            self.kb.rerank_provider_id,
+        )  # type: ignore
+        if not rp:
+            raise ValueError(
+                f"无法找到 ID 为 {self.kb.rerank_provider_id} 的 Rerank Provider",
+            )
+        return rp
+
+    async def _ensure_vec_db(self) -> FaissVecDB:
+        if not self.kb.embedding_provider_id:
+            raise ValueError(f"知识库 {self.kb.kb_name} 未配置 Embedding Provider")
+
+        ep = await self.get_ep()
+        rp = await self.get_rp()
+
+        vec_db = FaissVecDB(
+            doc_store_path=str(self.kb_dir / "doc.db"),
+            index_store_path=str(self.kb_dir / "index.faiss"),
+            embedding_provider=ep,
+            rerank_provider=rp,
+        )
+        await vec_db.initialize()
+        self.vec_db = vec_db
+        return vec_db
+
+    async def delete_vec_db(self):
+        """删除知识库的向量数据库和所有相关文件"""
+        import shutil
+
+        await self.terminate()
+        if self.kb_dir.exists():
+            shutil.rmtree(self.kb_dir)
+
+    async def terminate(self):
+        if self.vec_db:
+            await self.vec_db.close()
+
+    async def upload_document(
+        self,
+        file_name: str,
+        file_content: bytes,
+        file_type: str,
+        chunk_size: int = 512,
+        chunk_overlap: int = 50,
+        batch_size: int = 32,
+        tasks_limit: int = 3,
+        max_retries: int = 3,
+        progress_callback=None,
+    ) -> KBDocument:
+        """上传并处理文档（带原子性保证和失败清理）
+
+        流程:
+        1. 保存原始文件
+        2. 解析文档内容
+        3. 提取多媒体资源
+        4. 分块处理
+        5. 生成向量并存储
+        6. 保存元数据（事务）
+        7. 更新统计
+
+        Args:
+            progress_callback: 进度回调函数，接收参数 (stage, current, total)
+                - stage: 当前阶段 ('parsing', 'chunking', 'embedding')
+                - current: 当前进度
+                - total: 总数
+
+        """
+        await self._ensure_vec_db()
+        doc_id = str(uuid.uuid4())
+        media_paths: list[Path] = []
+
+        # file_path = self.kb_files_dir / f"{doc_id}.{file_type}"
+        # async with aiofiles.open(file_path, "wb") as f:
+        #     await f.write(file_content)
+
+        try:
+            # 阶段1: 解析文档
+            if progress_callback:
+                await progress_callback("parsing", 0, 100)
+
+            parser = await select_parser(f".{file_type}")
+            parse_result = await parser.parse(file_content, file_name)
+            text_content = parse_result.text
+            media_items = parse_result.media
+
+            if progress_callback:
+                await progress_callback("parsing", 100, 100)
+
+            # 保存媒体文件
+            saved_media = []
+            for media_item in media_items:
+                media = await self._save_media(
+                    doc_id=doc_id,
+                    media_type=media_item.media_type,
+                    file_name=media_item.file_name,
+                    content=media_item.content,
+                    mime_type=media_item.mime_type,
+                )
+                saved_media.append(media)
+                media_paths.append(Path(media.file_path))
+
+            # 阶段2: 分块
+            if progress_callback:
+                await progress_callback("chunking", 0, 100)
+
+            chunks_text = await self.chunker.chunk(
+                text_content,
+                chunk_size=chunk_size,
+                chunk_overlap=chunk_overlap,
+            )
+            contents = []
+            metadatas = []
+            for idx, chunk_text in enumerate(chunks_text):
+                contents.append(chunk_text)
+                metadatas.append(
+                    {
+                        "kb_id": self.kb.kb_id,
+                        "kb_doc_id": doc_id,
+                        "chunk_index": idx,
+                    },
+                )
+
+            if progress_callback:
+                await progress_callback("chunking", 100, 100)
+
+            # 阶段3: 生成向量（带进度回调）
+            async def embedding_progress_callback(current, total):
+                if progress_callback:
+                    await progress_callback("embedding", current, total)
+
+            await self.vec_db.insert_batch(
+                contents=contents,
+                metadatas=metadatas,
+                batch_size=batch_size,
+                tasks_limit=tasks_limit,
+                max_retries=max_retries,
+                progress_callback=embedding_progress_callback,
+            )
+
+            # 保存文档的元数据
+            doc = KBDocument(
+                doc_id=doc_id,
+                kb_id=self.kb.kb_id,
+                doc_name=file_name,
+                file_type=file_type,
+                file_size=len(file_content),
+                # file_path=str(file_path),
+                file_path="",
+                chunk_count=len(chunks_text),
+                media_count=0,
+            )
+            async with self.kb_db.get_db() as session:
+                async with session.begin():
+                    session.add(doc)
+                    for media in saved_media:
+                        session.add(media)
+                    await session.commit()
+
+                await session.refresh(doc)
+
+            vec_db: FaissVecDB = self.vec_db  # type: ignore
+            await self.kb_db.update_kb_stats(kb_id=self.kb.kb_id, vec_db=vec_db)
+            await self.refresh_kb()
+            await self.refresh_document(doc_id)
+            return doc
+        except Exception as e:
+            logger.error(f"上传文档失败: {e}")
+            # if file_path.exists():
+            #     file_path.unlink()
+
+            for media_path in media_paths:
+                try:
+                    if media_path.exists():
+                        media_path.unlink()
+                except Exception as me:
+                    logger.warning(f"清理多媒体文件失败 {media_path}: {me}")
+
+            raise e
+
+    async def list_documents(
+        self,
+        offset: int = 0,
+        limit: int = 100,
+    ) -> list[KBDocument]:
+        """列出知识库的所有文档"""
+        docs = await self.kb_db.list_documents_by_kb(self.kb.kb_id, offset, limit)
+        return docs
+
+    async def get_document(self, doc_id: str) -> KBDocument | None:
+        """获取单个文档"""
+        doc = await self.kb_db.get_document_by_id(doc_id)
+        return doc
+
+    async def delete_document(self, doc_id: str):
+        """删除单个文档及其相关数据"""
+        await self.kb_db.delete_document_by_id(
+            doc_id=doc_id,
+            vec_db=self.vec_db,  # type: ignore
+        )
+        await self.kb_db.update_kb_stats(
+            kb_id=self.kb.kb_id,
+            vec_db=self.vec_db,  # type: ignore
+        )
+        await self.refresh_kb()
+
+    async def delete_chunk(self, chunk_id: str, doc_id: str):
+        """删除单个文本块及其相关数据"""
+        vec_db: FaissVecDB = self.vec_db  # type: ignore
+        await vec_db.delete(chunk_id)
+        await self.kb_db.update_kb_stats(
+            kb_id=self.kb.kb_id,
+            vec_db=self.vec_db,  # type: ignore
+        )
+        await self.refresh_kb()
+        await self.refresh_document(doc_id)
+
+    async def refresh_kb(self):
+        if self.kb:
+            kb = await self.kb_db.get_kb_by_id(self.kb.kb_id)
+            if kb:
+                self.kb = kb
+
+    async def refresh_document(self, doc_id: str) -> None:
+        """更新文档的元数据"""
+        doc = await self.get_document(doc_id)
+        if not doc:
+            raise ValueError(f"无法找到 ID 为 {doc_id} 的文档")
+        chunk_count = await self.get_chunk_count_by_doc_id(doc_id)
+        doc.chunk_count = chunk_count
+        async with self.kb_db.get_db() as session:
+            async with session.begin():
+                session.add(doc)
+                await session.commit()
+            await session.refresh(doc)
+
+    async def get_chunks_by_doc_id(
+        self,
+        doc_id: str,
+        offset: int = 0,
+        limit: int = 100,
+    ) -> list[dict]:
+        """获取文档的所有块及其元数据"""
+        vec_db: FaissVecDB = self.vec_db  # type: ignore
+        chunks = await vec_db.document_storage.get_documents(
+            metadata_filters={"kb_doc_id": doc_id},
+            offset=offset,
+            limit=limit,
+        )
+        result = []
+        for chunk in chunks:
+            chunk_md = json.loads(chunk["metadata"])
+            result.append(
+                {
+                    "chunk_id": chunk["doc_id"],
+                    "doc_id": chunk_md["kb_doc_id"],
+                    "kb_id": chunk_md["kb_id"],
+                    "chunk_index": chunk_md["chunk_index"],
+                    "content": chunk["text"],
+                    "char_count": len(chunk["text"]),
+                },
+            )
+        return result
+
+    async def get_chunk_count_by_doc_id(self, doc_id: str) -> int:
+        """获取文档的块数量"""
+        vec_db: FaissVecDB = self.vec_db  # type: ignore
+        count = await vec_db.count_documents(metadata_filter={"kb_doc_id": doc_id})
+        return count
+
+    async def _save_media(
+        self,
+        doc_id: str,
+        media_type: str,
+        file_name: str,
+        content: bytes,
+        mime_type: str,
+    ) -> KBMedia:
+        """保存多媒体资源"""
+        media_id = str(uuid.uuid4())
+        ext = Path(file_name).suffix
+
+        # 保存文件
+        file_path = self.kb_medias_dir / doc_id / f"{media_id}{ext}"
+        file_path.parent.mkdir(parents=True, exist_ok=True)
+        async with aiofiles.open(file_path, "wb") as f:
+            await f.write(content)
+
+        media = KBMedia(
+            media_id=media_id,
+            doc_id=doc_id,
+            kb_id=self.kb.kb_id,
+            media_type=media_type,
+            file_name=file_name,
+            file_path=str(file_path),
+            file_size=len(content),
+            mime_type=mime_type,
+        )
+
+        return media

astrbot/core/knowledge_base/kb_mgr.py

@@ -0,0 +1,286 @@
+import traceback
+from pathlib import Path
+
+from astrbot.core import logger
+from astrbot.core.provider.manager import ProviderManager
+
+# from .chunking.fixed_size import FixedSizeChunker
+from .chunking.recursive import RecursiveCharacterChunker
+from .kb_db_sqlite import KBSQLiteDatabase
+from .kb_helper import KBHelper
+from .models import KnowledgeBase
+from .retrieval.manager import RetrievalManager, RetrievalResult
+from .retrieval.rank_fusion import RankFusion
+from .retrieval.sparse_retriever import SparseRetriever
+
+FILES_PATH = "data/knowledge_base"
+DB_PATH = Path(FILES_PATH) / "kb.db"
+"""Knowledge Base storage root directory"""
+CHUNKER = RecursiveCharacterChunker()
+
+
+class KnowledgeBaseManager:
+    kb_db: KBSQLiteDatabase
+    retrieval_manager: RetrievalManager
+
+    def __init__(
+        self,
+        provider_manager: ProviderManager,
+    ):
+        Path(DB_PATH).parent.mkdir(parents=True, exist_ok=True)
+        self.provider_manager = provider_manager
+        self._session_deleted_callback_registered = False
+
+        self.kb_insts: dict[str, KBHelper] = {}
+
+    async def initialize(self):
+        """初始化知识库模块"""
+        try:
+            logger.info("正在初始化知识库模块...")
+
+            # 初始化数据库
+            await self._init_kb_database()
+
+            # 初始化检索管理器
+            sparse_retriever = SparseRetriever(self.kb_db)
+            rank_fusion = RankFusion(self.kb_db)
+            self.retrieval_manager = RetrievalManager(
+                sparse_retriever=sparse_retriever,
+                rank_fusion=rank_fusion,
+                kb_db=self.kb_db,
+            )
+            await self.load_kbs()
+
+        except ImportError as e:
+            logger.error(f"知识库模块导入失败: {e}")
+            logger.warning("请确保已安装所需依赖: pypdf, aiofiles, Pillow, rank-bm25")
+        except Exception as e:
+            logger.error(f"知识库模块初始化失败: {e}")
+            logger.error(traceback.format_exc())
+
+    async def _init_kb_database(self):
+        self.kb_db = KBSQLiteDatabase(DB_PATH.as_posix())
+        await self.kb_db.initialize()
+        await self.kb_db.migrate_to_v1()
+        logger.info(f"KnowledgeBase database initialized: {DB_PATH}")
+
+    async def load_kbs(self):
+        """加载所有知识库实例"""
+        kb_records = await self.kb_db.list_kbs()
+        for record in kb_records:
+            kb_helper = KBHelper(
+                kb_db=self.kb_db,
+                kb=record,
+                provider_manager=self.provider_manager,
+                kb_root_dir=FILES_PATH,
+                chunker=CHUNKER,
+            )
+            await kb_helper.initialize()
+            self.kb_insts[record.kb_id] = kb_helper
+
+    async def create_kb(
+        self,
+        kb_name: str,
+        description: str | None = None,
+        emoji: str | None = None,
+        embedding_provider_id: str | None = None,
+        rerank_provider_id: str | None = None,
+        chunk_size: int | None = None,
+        chunk_overlap: int | None = None,
+        top_k_dense: int | None = None,
+        top_k_sparse: int | None = None,
+        top_m_final: int | None = None,
+    ) -> KBHelper:
+        """创建新的知识库实例"""
+        kb = KnowledgeBase(
+            kb_name=kb_name,
+            description=description,
+            emoji=emoji or "📚",
+            embedding_provider_id=embedding_provider_id,
+            rerank_provider_id=rerank_provider_id,
+            chunk_size=chunk_size if chunk_size is not None else 512,
+            chunk_overlap=chunk_overlap if chunk_overlap is not None else 50,
+            top_k_dense=top_k_dense if top_k_dense is not None else 50,
+            top_k_sparse=top_k_sparse if top_k_sparse is not None else 50,
+            top_m_final=top_m_final if top_m_final is not None else 5,
+        )
+        async with self.kb_db.get_db() as session:
+            session.add(kb)
+            await session.commit()
+            await session.refresh(kb)
+
+            kb_helper = KBHelper(
+                kb_db=self.kb_db,
+                kb=kb,
+                provider_manager=self.provider_manager,
+                kb_root_dir=FILES_PATH,
+                chunker=CHUNKER,
+            )
+            await kb_helper.initialize()
+        self.kb_insts[kb.kb_id] = kb_helper
+        return kb_helper
+
+    async def get_kb(self, kb_id: str) -> KBHelper | None:
+        """获取知识库实例"""
+        if kb_id in self.kb_insts:
+            return self.kb_insts[kb_id]
+
+    async def get_kb_by_name(self, kb_name: str) -> KBHelper | None:
+        """通过名称获取知识库实例"""
+        for kb_helper in self.kb_insts.values():
+            if kb_helper.kb.kb_name == kb_name:
+                return kb_helper
+        return None
+
+    async def delete_kb(self, kb_id: str) -> bool:
+        """删除知识库实例"""
+        kb_helper = await self.get_kb(kb_id)
+        if not kb_helper:
+            return False
+
+        await kb_helper.delete_vec_db()
+        async with self.kb_db.get_db() as session:
+            await session.delete(kb_helper.kb)
+            await session.commit()
+
+        self.kb_insts.pop(kb_id, None)
+        return True
+
+    async def list_kbs(self) -> list[KnowledgeBase]:
+        """列出所有知识库实例"""
+        kbs = [kb_helper.kb for kb_helper in self.kb_insts.values()]
+        return kbs
+
+    async def update_kb(
+        self,
+        kb_id: str,
+        kb_name: str,
+        description: str | None = None,
+        emoji: str | None = None,
+        embedding_provider_id: str | None = None,
+        rerank_provider_id: str | None = None,
+        chunk_size: int | None = None,
+        chunk_overlap: int | None = None,
+        top_k_dense: int | None = None,
+        top_k_sparse: int | None = None,
+        top_m_final: int | None = None,
+    ) -> KBHelper | None:
+        """更新知识库实例"""
+        kb_helper = await self.get_kb(kb_id)
+        if not kb_helper:
+            return None
+
+        kb = kb_helper.kb
+        if kb_name is not None:
+            kb.kb_name = kb_name
+        if description is not None:
+            kb.description = description
+        if emoji is not None:
+            kb.emoji = emoji
+        if embedding_provider_id is not None:
+            kb.embedding_provider_id = embedding_provider_id
+        kb.rerank_provider_id = rerank_provider_id  # 允许设置为 None
+        if chunk_size is not None:
+            kb.chunk_size = chunk_size
+        if chunk_overlap is not None:
+            kb.chunk_overlap = chunk_overlap
+        if top_k_dense is not None:
+            kb.top_k_dense = top_k_dense
+        if top_k_sparse is not None:
+            kb.top_k_sparse = top_k_sparse
+        if top_m_final is not None:
+            kb.top_m_final = top_m_final
+        async with self.kb_db.get_db() as session:
+            session.add(kb)
+            await session.commit()
+            await session.refresh(kb)
+
+        return kb_helper
+
+    async def retrieve(
+        self,
+        query: str,
+        kb_names: list[str],
+        top_k_fusion: int = 20,
+        top_m_final: int = 5,
+    ) -> dict | None:
+        """从指定知识库中检索相关内容"""
+        kb_ids = []
+        kb_id_helper_map = {}
+        for kb_name in kb_names:
+            if kb_helper := await self.get_kb_by_name(kb_name):
+                kb_ids.append(kb_helper.kb.kb_id)
+                kb_id_helper_map[kb_helper.kb.kb_id] = kb_helper
+
+        if not kb_ids:
+            return {}
+
+        results = await self.retrieval_manager.retrieve(
+            query=query,
+            kb_ids=kb_ids,
+            kb_id_helper_map=kb_id_helper_map,
+            top_k_fusion=top_k_fusion,
+            top_m_final=top_m_final,
+        )
+        if not results:
+            return None
+
+        context_text = self._format_context(results)
+
+        results_dict = [
+            {
+                "chunk_id": r.chunk_id,
+                "doc_id": r.doc_id,
+                "kb_id": r.kb_id,
+                "kb_name": r.kb_name,
+                "doc_name": r.doc_name,
+                "chunk_index": r.metadata.get("chunk_index", 0),
+                "content": r.content,
+                "score": r.score,
+                "char_count": r.metadata.get("char_count", 0),
+            }
+            for r in results
+        ]
+
+        return {
+            "context_text": context_text,
+            "results": results_dict,
+        }
+
+    def _format_context(self, results: list[RetrievalResult]) -> str:
+        """格式化知识上下文
+
+        Args:
+            results: 检索结果列表
+
+        Returns:
+            str: 格式化的上下文文本
+
+        """
+        lines = ["以下是相关的知识库内容,请参考这些信息回答用户的问题:\n"]
+
+        for i, result in enumerate(results, 1):
+            lines.append(f"【知识 {i}】")
+            lines.append(f"来源: {result.kb_name} / {result.doc_name}")
+            lines.append(f"内容: {result.content}")
+            lines.append(f"相关度: {result.score:.2f}")
+            lines.append("")
+
+        return "\n".join(lines)
+
+    async def terminate(self):
+        """终止所有知识库实例,关闭数据库连接"""
+        for kb_id, kb_helper in self.kb_insts.items():
+            try:
+                await kb_helper.terminate()
+            except Exception as e:
+                logger.error(f"关闭知识库 {kb_id} 失败: {e}")
+
+        self.kb_insts.clear()
+
+        # 关闭元数据数据库
+        if hasattr(self, "kb_db") and self.kb_db:
+            try:
+                await self.kb_db.close()
+            except Exception as e:
+                logger.error(f"关闭知识库元数据数据库失败: {e}")

astrbot/core/knowledge_base/models.py

@@ -0,0 +1,120 @@
+import uuid
+from datetime import datetime, timezone
+
+from sqlmodel import Field, MetaData, SQLModel, Text, UniqueConstraint
+
+
+class BaseKBModel(SQLModel, table=False):
+    metadata = MetaData()
+
+
+class KnowledgeBase(BaseKBModel, table=True):
+    """知识库表
+
+    存储知识库的基本信息和统计数据。
+    """
+
+    __tablename__ = "knowledge_bases"  # type: ignore
+
+    id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    kb_id: str = Field(
+        max_length=36,
+        nullable=False,
+        unique=True,
+        default_factory=lambda: str(uuid.uuid4()),
+        index=True,
+    )
+    kb_name: str = Field(max_length=100, nullable=False)
+    description: str | None = Field(default=None, sa_type=Text)
+    emoji: str | None = Field(default="📚", max_length=10)
+    embedding_provider_id: str | None = Field(default=None, max_length=100)
+    rerank_provider_id: str | None = Field(default=None, max_length=100)
+    # 分块配置参数
+    chunk_size: int | None = Field(default=512, nullable=True)
+    chunk_overlap: int | None = Field(default=50, nullable=True)
+    # 检索配置参数
+    top_k_dense: int | None = Field(default=50, nullable=True)
+    top_k_sparse: int | None = Field(default=50, nullable=True)
+    top_m_final: int | None = Field(default=5, nullable=True)
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+    doc_count: int = Field(default=0, nullable=False)
+    chunk_count: int = Field(default=0, nullable=False)
+
+    __table_args__ = (
+        UniqueConstraint(
+            "kb_name",
+            name="uix_kb_name",
+        ),
+    )
+
+
+class KBDocument(BaseKBModel, table=True):
+    """文档表
+
+    存储上传到知识库的文档元数据。
+    """
+
+    __tablename__ = "kb_documents"  # type: ignore
+
+    id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    doc_id: str = Field(
+        max_length=36,
+        nullable=False,
+        unique=True,
+        default_factory=lambda: str(uuid.uuid4()),
+        index=True,
+    )
+    kb_id: str = Field(max_length=36, nullable=False, index=True)
+    doc_name: str = Field(max_length=255, nullable=False)
+    file_type: str = Field(max_length=20, nullable=False)
+    file_size: int = Field(nullable=False)
+    file_path: str = Field(max_length=512, nullable=False)
+    chunk_count: int = Field(default=0, nullable=False)
+    media_count: int = Field(default=0, nullable=False)
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    updated_at: datetime = Field(
+        default_factory=lambda: datetime.now(timezone.utc),
+        sa_column_kwargs={"onupdate": datetime.now(timezone.utc)},
+    )
+
+
+class KBMedia(BaseKBModel, table=True):
+    """多媒体资源表
+
+    存储从文档中提取的图片、视频等多媒体资源。
+    """
+
+    __tablename__ = "kb_media"  # type: ignore
+
+    id: int | None = Field(
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+        default=None,
+    )
+    media_id: str = Field(
+        max_length=36,
+        nullable=False,
+        unique=True,
+        default_factory=lambda: str(uuid.uuid4()),
+        index=True,
+    )
+    doc_id: str = Field(max_length=36, nullable=False, index=True)
+    kb_id: str = Field(max_length=36, nullable=False, index=True)
+    media_type: str = Field(max_length=20, nullable=False)
+    file_name: str = Field(max_length=255, nullable=False)
+    file_path: str = Field(max_length=512, nullable=False)
+    file_size: int = Field(nullable=False)
+    mime_type: str = Field(max_length=100, nullable=False)
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))

astrbot/core/knowledge_base/parsers/__init__.py

@@ -0,0 +1,13 @@
+"""文档解析器模块"""
+
+from .base import BaseParser, MediaItem, ParseResult
+from .pdf_parser import PDFParser
+from .text_parser import TextParser
+
+__all__ = [
+    "BaseParser",
+    "MediaItem",
+    "PDFParser",
+    "ParseResult",
+    "TextParser",
+]

astrbot/core/knowledge_base/parsers/base.py

@@ -0,0 +1,51 @@
+"""文档解析器基类和数据结构
+
+定义了文档解析器的抽象接口和相关数据类。
+"""
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+
+
+@dataclass
+class MediaItem:
+    """多媒体项
+
+    表示从文档中提取的多媒体资源。
+    """
+
+    media_type: str  # image, video
+    file_name: str
+    content: bytes
+    mime_type: str
+
+
+@dataclass
+class ParseResult:
+    """解析结果
+
+    包含解析后的文本内容和提取的多媒体资源。
+    """
+
+    text: str
+    media: list[MediaItem]
+
+
+class BaseParser(ABC):
+    """文档解析器基类
+
+    所有文档解析器都应该继承此类并实现 parse 方法。
+    """
+
+    @abstractmethod
+    async def parse(self, file_content: bytes, file_name: str) -> ParseResult:
+        """解析文档
+
+        Args:
+            file_content: 文件内容
+            file_name: 文件名
+
+        Returns:
+            ParseResult: 解析结果
+
+        """

astrbot/core/knowledge_base/parsers/markitdown_parser.py

@@ -0,0 +1,26 @@
+import io
+import os
+
+from markitdown_no_magika import MarkItDown, StreamInfo
+
+from astrbot.core.knowledge_base.parsers.base import (
+    BaseParser,
+    ParseResult,
+)
+
+
+class MarkitdownParser(BaseParser):
+    """解析 docx, xls, xlsx 格式"""
+
+    async def parse(self, file_content: bytes, file_name: str) -> ParseResult:
+        md = MarkItDown(enable_plugins=False)
+        bio = io.BytesIO(file_content)
+        stream_info = StreamInfo(
+            extension=os.path.splitext(file_name)[1].lower(),
+            filename=file_name,
+        )
+        result = md.convert(bio, stream_info=stream_info)
+        return ParseResult(
+            text=result.markdown,
+            media=[],
+        )

astrbot/core/knowledge_base/parsers/pdf_parser.py

@@ -0,0 +1,101 @@
+"""PDF 文件解析器
+
+支持解析 PDF 文件中的文本和图片资源。
+"""
+
+import io
+
+from pypdf import PdfReader
+
+from astrbot.core.knowledge_base.parsers.base import (
+    BaseParser,
+    MediaItem,
+    ParseResult,
+)
+
+
+class PDFParser(BaseParser):
+    """PDF 文档解析器
+
+    提取 PDF 中的文本内容和嵌入的图片资源。
+    """
+
+    async def parse(self, file_content: bytes, file_name: str) -> ParseResult:
+        """解析 PDF 文件
+
+        Args:
+            file_content: 文件内容
+            file_name: 文件名
+
+        Returns:
+            ParseResult: 包含文本和图片的解析结果
+
+        """
+        pdf_file = io.BytesIO(file_content)
+        reader = PdfReader(pdf_file)
+
+        text_parts = []
+        media_items = []
+
+        # 提取文本
+        for page in reader.pages:
+            text = page.extract_text()
+            if text:
+                text_parts.append(text)
+
+        # 提取图片
+        image_counter = 0
+        for page_num, page in enumerate(reader.pages):
+            try:
+                # 安全检查 Resources
+                if "/Resources" not in page:
+                    continue
+
+                resources = page["/Resources"]
+                if not resources or "/XObject" not in resources:  # type: ignore
+                    continue
+
+                xobjects = resources["/XObject"].get_object()  # type: ignore
+                if not xobjects:
+                    continue
+
+                for obj_name in xobjects:
+                    try:
+                        obj = xobjects[obj_name]
+
+                        if obj.get("/Subtype") != "/Image":
+                            continue
+
+                        # 提取图片数据
+                        image_data = obj.get_data()
+
+                        # 确定格式
+                        filter_type = obj.get("/Filter", "")
+                        if filter_type == "/DCTDecode":
+                            ext = "jpg"
+                            mime_type = "image/jpeg"
+                        elif filter_type == "/FlateDecode":
+                            ext = "png"
+                            mime_type = "image/png"
+                        else:
+                            ext = "png"
+                            mime_type = "image/png"
+
+                        image_counter += 1
+                        media_items.append(
+                            MediaItem(
+                                media_type="image",
+                                file_name=f"page_{page_num}_img_{image_counter}.{ext}",
+                                content=image_data,
+                                mime_type=mime_type,
+                            ),
+                        )
+                    except Exception:
+                        # 单个图片提取失败不影响整体
+                        continue
+            except Exception:
+                # 页面处理失败不影响其他页面
+                continue
+
+        full_text = "\n\n".join(text_parts)
+        return ParseResult(text=full_text, media=media_items)

astrbot/core/knowledge_base/parsers/text_parser.py

@@ -0,0 +1,42 @@
+"""文本文件解析器
+
+支持解析 TXT 和 Markdown 文件。
+"""
+
+from astrbot.core.knowledge_base.parsers.base import BaseParser, ParseResult
+
+
+class TextParser(BaseParser):
+    """TXT/MD 文本解析器
+
+    支持多种字符编码的自动检测。
+    """
+
+    async def parse(self, file_content: bytes, file_name: str) -> ParseResult:
+        """解析文本文件
+
+        尝试使用多种编码解析文件内容。
+
+        Args:
+            file_content: 文件内容
+            file_name: 文件名
+
+        Returns:
+            ParseResult: 解析结果,不包含多媒体资源
+
+        Raises:
+            ValueError: 如果无法解码文件
+
+        """
+        # 尝试多种编码
+        for encoding in ["utf-8", "gbk", "gb2312", "gb18030"]:
+            try:
+                text = file_content.decode(encoding)
+                break
+            except UnicodeDecodeError:
+                continue
+        else:
+            raise ValueError(f"无法解码文件: {file_name}")
+
+        # 文本文件无多媒体资源
+        return ParseResult(text=text, media=[])

astrbot/core/knowledge_base/parsers/util.py

@@ -0,0 +1,13 @@
+from .base import BaseParser
+
+
+async def select_parser(ext: str) -> BaseParser:
+    if ext in {".md", ".txt", ".markdown", ".xlsx", ".docx", ".xls"}:
+        from .markitdown_parser import MarkitdownParser
+
+        return MarkitdownParser()
+    if ext == ".pdf":
+        from .pdf_parser import PDFParser
+
+        return PDFParser()
+    raise ValueError(f"暂时不支持的文件格式: {ext}")

astrbot/core/knowledge_base/retrieval/__init__.py

@@ -0,0 +1,14 @@
+"""检索模块"""
+
+from .manager import RetrievalManager, RetrievalResult
+from .rank_fusion import FusedResult, RankFusion
+from .sparse_retriever import SparseResult, SparseRetriever
+
+__all__ = [
+    "FusedResult",
+    "RankFusion",
+    "RetrievalManager",
+    "RetrievalResult",
+    "SparseResult",
+    "SparseRetriever",
+]

astrbot/core/knowledge_base/retrieval/hit_stopwords.txt

@@ -0,0 +1,767 @@
+———
+》），
+）÷（１－
+”，
+）、
+＝（
+:
+→
+℃ 
+&
+*
+一一
+~~~~
+’
+.
+『
+.一
+./
+-- 
+』
+＝″
+【
+［＊］
+｝＞
+［⑤］］
+［①Ｄ］
+ｃ］
+ｎｇ昉
+＊
+//
+［
+］
+［②ｅ］
+［②ｇ］
+＝｛
+}
+，也 
+‘
+Ａ
+［①⑥］
+［②Ｂ］ 
+［①ａ］
+［④ａ］
+［①③］
+［③ｈ］
+③］
+１． 
+－－ 
+［②ｂ］
+’‘ 
+××× 
+［①⑧］
+０：２ 
+＝［
+［⑤ｂ］
+［②ｃ］ 
+［④ｂ］
+［②③］
+［③ａ］
+［④ｃ］
+［①⑤］
+［①⑦］
+［①ｇ］
+∈［ 
+［①⑨］
+［①④］
+［①ｃ］
+［②ｆ］
+［②⑧］
+［②①］
+［①Ｃ］
+［③ｃ］
+［③ｇ］
+［②⑤］
+［②②］
+一.
+［①ｈ］
+.数
+［］
+［①Ｂ］
+数/
+［①ｉ］
+［③ｅ］
+［①①］
+［④ｄ］
+［④ｅ］
+［③ｂ］
+［⑤ａ］
+［①Ａ］
+［②⑧］
+［②⑦］
+［①ｄ］
+［②ｊ］
+〕〔
+］［
+://
+′∈
+［②④
+［⑤ｅ］
+１２％
+ｂ］
+...
+...................
+…………………………………………………③
+ＺＸＦＩＴＬ
+［③Ｆ］
+」
+［①ｏ］
+］∧′＝［ 
+∪φ∈
+′｜
+｛－
+②ｃ
+｝
+［③①］
+Ｒ．Ｌ．
+［①Ｅ］
+Ψ
+－［＊］－
+↑
+.日 
+［②ｄ］
+［②
+［②⑦］
+［②②］
+［③ｅ］
+［①ｉ］
+［①Ｂ］
+［①ｈ］
+［①ｄ］
+［①ｇ］
+［①②］
+［②ａ］
+ｆ］
+［⑩］
+ａ］
+［①ｅ］
+［②ｈ］
+［②⑥］
+［③ｄ］
+［②⑩］
+ｅ］
+〉
+】
+元／吨
+［②⑩］
+２．３％
+５：０  
+［①］
+::
+［②］
+［③］
+［④］
+［⑤］
+［⑥］
+［⑦］
+［⑧］
+［⑨］ 
+……
+——
+?
+、
+。
+“
+”
+《
+》
+！
+，
+：
+；
+？
+．
+,
+．
+'
+? 
+·
+———
+──
+? 
+—
+<
+>
+（
+）
+〔
+〕
+[
+]
+(
+)
+-
++
+～
+×
+／
+/
+①
+②
+③
+④
+⑤
+⑥
+⑦
+⑧
+⑨
+⑩
+Ⅲ
+В
+"
+;
+#
+@
+γ
+μ
+φ
+φ．
+× 
+Δ
+■
+▲
+sub
+exp 
+sup
+sub
+Lex 
+＃
+％
+＆
+＇
+＋
+＋ξ
+＋＋
+－
+－β
+＜
+＜±
+＜Δ
+＜λ
+＜φ
+＜＜
+=
+＝
+＝☆
+＝－
+＞
+＞λ
+＿
+～±
+～＋
+［⑤ｆ］
+［⑤ｄ］
+［②ｉ］
+≈ 
+［②Ｇ］
+［①ｆ］
+ＬＩ
+㈧ 
+［－
+......
+〉
+［③⑩］
+第二
+一番
+一直
+一个
+一些
+许多
+种
+有的是
+也就是说
+末##末
+啊
+阿
+哎
+哎呀
+哎哟
+唉
+俺
+俺们
+按
+按照
+吧
+吧哒
+把
+罢了
+被
+本
+本着
+比
+比方
+比如
+鄙人
+彼
+彼此
+边
+别
+别的
+别说
+并
+并且
+不比
+不成
+不单
+不但
+不独
+不管
+不光
+不过
+不仅
+不拘
+不论
+不怕
+不然
+不如
+不特
+不惟
+不问
+不只
+朝
+朝着
+趁
+趁着
+乘
+冲
+除
+除此之外
+除非
+除了
+此
+此间
+此外
+从
+从而
+打
+待
+但
+但是
+当
+当着
+到
+得
+的
+的话
+等
+等等
+地
+第
+叮咚
+对
+对于
+多
+多少
+而
+而况
+而且
+而是
+而外
+而言
+而已
+尔后
+反过来
+反过来说
+反之
+非但
+非徒
+否则
+嘎
+嘎登
+该
+赶
+个
+各
+各个
+各位
+各种
+各自
+给
+根据
+跟
+故
+故此
+固然
+关于
+管
+归
+果然
+果真
+过
+哈
+哈哈
+呵
+和
+何
+何处
+何况
+何时
+嘿
+哼
+哼唷
+呼哧
+乎
+哗
+还是
+还有
+换句话说
+换言之
+或
+或是
+或者
+极了
+及
+及其
+及至
+即
+即便
+即或
+即令
+即若
+即使
+几
+几时
+己
+既
+既然
+既是
+继而
+加之
+假如
+假若
+假使
+鉴于
+将
+较
+较之
+叫
+接着
+结果
+借
+紧接着
+进而
+尽
+尽管
+经
+经过
+就
+就是
+就是说
+据
+具体地说
+具体说来
+开始
+开外
+靠
+咳
+可
+可见
+可是
+可以
+况且
+啦
+来
+来着
+离
+例如
+哩
+连
+连同
+两者
+了
+临
+另
+另外
+另一方面
+论
+嘛
+吗
+慢说
+漫说
+冒
+么
+每
+每当
+们
+莫若
+某
+某个
+某些
+拿
+哪
+哪边
+哪儿
+哪个
+哪里
+哪年
+哪怕
+哪天
+哪些
+哪样
+那
+那边
+那儿
+那个
+那会儿
+那里
+那么
+那么些
+那么样
+那时
+那些
+那样
+乃
+乃至
+呢
+能
+你
+你们
+您
+宁
+宁可
+宁肯
+宁愿
+哦
+呕
+啪达
+旁人
+呸
+凭
+凭借
+其
+其次
+其二
+其他
+其它
+其一
+其余
+其中
+起
+起见
+起见
+岂但
+恰恰相反
+前后
+前者
+且
+然而
+然后
+然则
+让
+人家
+任
+任何
+任凭
+如
+如此
+如果
+如何
+如其
+如若
+如上所述
+若
+若非
+若是
+啥
+上下
+尚且
+设若
+设使
+甚而
+甚么
+甚至
+省得
+时候
+什么
+什么样
+使得
+是
+是的
+首先
+谁
+谁知
+顺
+顺着
+似的
+虽
+虽然
+虽说
+虽则
+随
+随着
+所
+所以
+他
+他们
+他人
+它
+它们
+她
+她们
+倘
+倘或
+倘然
+倘若
+倘使
+腾
+替
+通过
+同
+同时
+哇
+万一
+往
+望
+为
+为何
+为了
+为什么
+为着
+喂
+嗡嗡
+我
+我们
+呜
+呜呼
+乌乎
+无论
+无宁
+毋宁
+嘻
+吓
+相对而言
+像
+向
+向着
+嘘
+呀
+焉
+沿
+沿着
+要
+要不
+要不然
+要不是
+要么
+要是
+也
+也罢
+也好
+一
+一般
+一旦
+一方面
+一来
+一切
+一样
+一则
+依
+依照
+矣
+以
+以便
+以及
+以免
+以至
+以至于
+以致
+抑或
+因
+因此
+因而
+因为
+哟
+用
+由
+由此可见
+由于
+有
+有的
+有关
+有些
+又
+于
+于是
+于是乎
+与
+与此同时
+与否
+与其
+越是
+云云
+哉
+再说
+再者
+在
+在下
+咱
+咱们
+则
+怎
+怎么
+怎么办
+怎么样
+怎样
+咋
+照
+照着
+者
+这
+这边
+这儿
+这个
+这会儿
+这就是说
+这里
+这么
+这么点儿
+这么些
+这么样
+这时
+这些
+这样
+正如
+吱
+之
+之类
+之所以
+之一
+只是
+只限
+只要
+只有
+至
+至于
+诸位
+着
+着呢
+自
+自从
+自个儿
+自各儿
+自己
+自家
+自身
+综上所述
+总的来看
+总的来说
+总的说来
+总而言之
+总之
+纵
+纵令
+纵然
+纵使
+遵照
+作为
+兮
+呃
+呗
+咚
+咦
+喏
+啐
+喔唷
+嗬
+嗯
+嗳

astrbot/core/knowledge_base/retrieval/manager.py

@@ -0,0 +1,276 @@
+"""检索管理器
+
+协调稠密检索、稀疏检索和 Rerank,提供统一的检索接口
+"""
+
+import time
+from dataclasses import dataclass
+
+from astrbot import logger
+from astrbot.core.db.vec_db.base import Result
+from astrbot.core.db.vec_db.faiss_impl import FaissVecDB
+from astrbot.core.knowledge_base.kb_db_sqlite import KBSQLiteDatabase
+from astrbot.core.knowledge_base.retrieval.rank_fusion import RankFusion
+from astrbot.core.knowledge_base.retrieval.sparse_retriever import SparseRetriever
+from astrbot.core.provider.provider import RerankProvider
+
+from ..kb_helper import KBHelper
+
+
+@dataclass
+class RetrievalResult:
+    """检索结果"""
+
+    chunk_id: str
+    doc_id: str
+    doc_name: str
+    kb_id: str
+    kb_name: str
+    content: str
+    score: float
+    metadata: dict
+
+
+class RetrievalManager:
+    """检索管理器
+
+    职责:
+    - 协调稠密检索、稀疏检索和 Rerank
+    - 结果融合和排序
+    """
+
+    def __init__(
+        self,
+        sparse_retriever: SparseRetriever,
+        rank_fusion: RankFusion,
+        kb_db: KBSQLiteDatabase,
+    ):
+        """初始化检索管理器
+
+        Args:
+            vec_db_factory: 向量数据库工厂
+            sparse_retriever: 稀疏检索器
+            rank_fusion: 结果融合器
+            kb_db: 知识库数据库实例
+
+        """
+        self.sparse_retriever = sparse_retriever
+        self.rank_fusion = rank_fusion
+        self.kb_db = kb_db
+
+    async def retrieve(
+        self,
+        query: str,
+        kb_ids: list[str],
+        kb_id_helper_map: dict[str, KBHelper],
+        top_k_fusion: int = 20,
+        top_m_final: int = 5,
+    ) -> list[RetrievalResult]:
+        """混合检索
+
+        流程:
+        1. 稠密检索 (向量相似度)
+        2. 稀疏检索 (BM25)
+        3. 结果融合 (RRF)
+        4. Rerank 重排序
+
+        Args:
+            query: 查询文本
+            kb_ids: 知识库 ID 列表
+            top_m_final: 最终返回数量
+            enable_rerank: 是否启用 Rerank
+
+        Returns:
+            List[RetrievalResult]: 检索结果列表
+
+        """
+        if not kb_ids:
+            return []
+
+        kb_options: dict = {}
+        new_kb_ids = []
+        for kb_id in kb_ids:
+            kb_helper = kb_id_helper_map.get(kb_id)
+            if kb_helper:
+                kb = kb_helper.kb
+                kb_options[kb_id] = {
+                    "top_k_dense": kb.top_k_dense or 50,
+                    "top_k_sparse": kb.top_k_sparse or 50,
+                    "top_m_final": kb.top_m_final or 5,
+                    "vec_db": kb_helper.vec_db,
+                    "rerank_provider_id": kb.rerank_provider_id,
+                }
+                new_kb_ids.append(kb_id)
+            else:
+                logger.warning(f"知识库 ID {kb_id} 实例未找到, 已跳过该知识库的检索")
+
+        kb_ids = new_kb_ids
+
+        # 1. 稠密检索
+        time_start = time.time()
+        dense_results = await self._dense_retrieve(
+            query=query,
+            kb_ids=kb_ids,
+            kb_options=kb_options,
+        )
+        time_end = time.time()
+        logger.debug(
+            f"Dense retrieval across {len(kb_ids)} bases took {time_end - time_start:.2f}s and returned {len(dense_results)} results.",
+        )
+
+        # 2. 稀疏检索
+        time_start = time.time()
+        sparse_results = await self.sparse_retriever.retrieve(
+            query=query,
+            kb_ids=kb_ids,
+            kb_options=kb_options,
+        )
+        time_end = time.time()
+        logger.debug(
+            f"Sparse retrieval across {len(kb_ids)} bases took {time_end - time_start:.2f}s and returned {len(sparse_results)} results.",
+        )
+
+        # 3. 结果融合
+        time_start = time.time()
+        fused_results = await self.rank_fusion.fuse(
+            dense_results=dense_results,
+            sparse_results=sparse_results,
+            top_k=top_k_fusion,
+        )
+        time_end = time.time()
+        logger.debug(
+            f"Rank fusion took {time_end - time_start:.2f}s and returned {len(fused_results)} results.",
+        )
+
+        # 4. 转换为 RetrievalResult (获取元数据)
+        retrieval_results = []
+        for fr in fused_results:
+            metadata_dict = await self.kb_db.get_document_with_metadata(fr.doc_id)
+            if metadata_dict:
+                retrieval_results.append(
+                    RetrievalResult(
+                        chunk_id=fr.chunk_id,
+                        doc_id=fr.doc_id,
+                        doc_name=metadata_dict["document"].doc_name,
+                        kb_id=fr.kb_id,
+                        kb_name=metadata_dict["knowledge_base"].kb_name,
+                        content=fr.content,
+                        score=fr.score,
+                        metadata={
+                            "chunk_index": fr.chunk_index,
+                            "char_count": len(fr.content),
+                        },
+                    ),
+                )
+
+        # 5. Rerank
+        first_rerank = None
+        for kb_id in kb_ids:
+            vec_db: FaissVecDB = kb_options[kb_id]["vec_db"]
+            rerank_pi = kb_options[kb_id]["rerank_provider_id"]
+            if (
+                vec_db
+                and vec_db.rerank_provider
+                and rerank_pi
+                and rerank_pi == vec_db.rerank_provider.meta().id
+            ):
+                first_rerank = vec_db.rerank_provider
+                break
+        if first_rerank and retrieval_results:
+            retrieval_results = await self._rerank(
+                query=query,
+                results=retrieval_results,
+                top_k=top_m_final,
+                rerank_provider=first_rerank,
+            )
+
+        return retrieval_results[:top_m_final]
+
+    async def _dense_retrieve(
+        self,
+        query: str,
+        kb_ids: list[str],
+        kb_options: dict,
+    ):
+        """稠密检索 (向量相似度)
+
+        为每个知识库使用独立的向量数据库进行检索,然后合并结果。
+
+        Args:
+            query: 查询文本
+            kb_ids: 知识库 ID 列表
+            top_k: 返回结果数量
+
+        Returns:
+            List[Result]: 检索结果列表
+
+        """
+        all_results: list[Result] = []
+        for kb_id in kb_ids:
+            if kb_id not in kb_options:
+                continue
+            try:
+                vec_db: FaissVecDB = kb_options[kb_id]["vec_db"]
+                dense_k = int(kb_options[kb_id]["top_k_dense"])
+                vec_results = await vec_db.retrieve(
+                    query=query,
+                    k=dense_k,
+                    fetch_k=dense_k * 2,
+                    rerank=False,  # 稠密检索阶段不进行 rerank
+                    metadata_filters={"kb_id": kb_id},
+                )
+
+                all_results.extend(vec_results)
+            except Exception as e:
+                from astrbot.core import logger
+
+                logger.warning(f"知识库 {kb_id} 稠密检索失败: {e}")
+                continue
+
+        # 按相似度排序并返回 top_k
+        all_results.sort(key=lambda x: x.similarity, reverse=True)
+        # return all_results[: len(all_results) // len(kb_ids)]
+        return all_results
+
+    async def _rerank(
+        self,
+        query: str,
+        results: list[RetrievalResult],
+        top_k: int,
+        rerank_provider: RerankProvider,
+    ) -> list[RetrievalResult]:
+        """Rerank 重排序
+
+        Args:
+            query: 查询文本
+            results: 检索结果列表
+            top_k: 返回结果数量
+
+        Returns:
+            List[RetrievalResult]: 重排序后的结果列表
+
+        """
+        if not results:
+            return []
+
+        # 准备文档列表
+        docs = [r.content for r in results]
+
+        # 调用 Rerank Provider
+        rerank_results = await rerank_provider.rerank(
+            query=query,
+            documents=docs,
+        )
+
+        # 更新分数并重新排序
+        reranked_list = []
+        for rerank_result in rerank_results:
+            idx = rerank_result.index
+            if idx < len(results):
+                result = results[idx]
+                result.score = rerank_result.relevance_score
+                reranked_list.append(result)
+
+        reranked_list.sort(key=lambda x: x.score, reverse=True)
+
+        return reranked_list[:top_k]

astrbot/core/knowledge_base/retrieval/rank_fusion.py

@@ -0,0 +1,142 @@
+"""检索结果融合器
+
+使用 Reciprocal Rank Fusion (RRF) 算法融合稠密检索和稀疏检索的结果
+"""
+
+import json
+from dataclasses import dataclass
+
+from astrbot.core.db.vec_db.base import Result
+from astrbot.core.knowledge_base.kb_db_sqlite import KBSQLiteDatabase
+from astrbot.core.knowledge_base.retrieval.sparse_retriever import SparseResult
+
+
+@dataclass
+class FusedResult:
+    """融合后的检索结果"""
+
+    chunk_id: str
+    chunk_index: int
+    doc_id: str
+    kb_id: str
+    content: str
+    score: float
+
+
+class RankFusion:
+    """检索结果融合器
+
+    职责:
+    - 融合稠密检索和稀疏检索的结果
+    - 使用 Reciprocal Rank Fusion (RRF) 算法
+    """
+
+    def __init__(self, kb_db: KBSQLiteDatabase, k: int = 60):
+        """初始化结果融合器
+
+        Args:
+            kb_db: 知识库数据库实例
+            k: RRF 参数,用于平滑排名
+
+        """
+        self.kb_db = kb_db
+        self.k = k
+
+    async def fuse(
+        self,
+        dense_results: list[Result],
+        sparse_results: list[SparseResult],
+        top_k: int = 20,
+    ) -> list[FusedResult]:
+        """融合稠密和稀疏检索结果
+
+        RRF 公式:
+        score(doc) = sum(1 / (k + rank_i))
+
+        Args:
+            dense_results: 稠密检索结果
+            sparse_results: 稀疏检索结果
+            top_k: 返回结果数量
+
+        Returns:
+            List[FusedResult]: 融合后的结果列表
+
+        """
+        # 1. 构建排名映射
+        dense_ranks = {
+            r.data["doc_id"]: (idx + 1) for idx, r in enumerate(dense_results)
+        }  # 这里的 doc_id 实际上是 chunk_id
+        sparse_ranks = {r.chunk_id: (idx + 1) for idx, r in enumerate(sparse_results)}
+
+        # 2. 收集所有唯一的 ID
+        # 需要统一为 chunk_id
+        all_chunk_ids = set()
+        vec_doc_id_to_dense: dict[str, Result] = {}  # vec_doc_id -> Result
+        chunk_id_to_sparse: dict[str, SparseResult] = {}  # chunk_id -> SparseResult
+
+        # 处理稀疏检索结果
+        for r in sparse_results:
+            all_chunk_ids.add(r.chunk_id)
+            chunk_id_to_sparse[r.chunk_id] = r
+
+        # 处理稠密检索结果 (需要转换 vec_doc_id 到 chunk_id)
+        for r in dense_results:
+            vec_doc_id = r.data["doc_id"]
+            all_chunk_ids.add(vec_doc_id)
+            vec_doc_id_to_dense[vec_doc_id] = r
+
+        # 3. 计算 RRF 分数
+        rrf_scores: dict[str, float] = {}
+
+        for identifier in all_chunk_ids:
+            score = 0.0
+
+            # 来自稠密检索的贡献
+            if identifier in dense_ranks:
+                score += 1.0 / (self.k + dense_ranks[identifier])
+
+            # 来自稀疏检索的贡献
+            if identifier in sparse_ranks:
+                score += 1.0 / (self.k + sparse_ranks[identifier])
+
+            rrf_scores[identifier] = score
+
+        # 4. 排序
+        sorted_ids = sorted(
+            rrf_scores.keys(),
+            key=lambda cid: rrf_scores[cid],
+            reverse=True,
+        )[:top_k]
+
+        # 5. 构建融合结果
+        fused_results = []
+        for identifier in sorted_ids:
+            # 优先从稀疏检索获取完整信息
+            if identifier in chunk_id_to_sparse:
+                sr = chunk_id_to_sparse[identifier]
+                fused_results.append(
+                    FusedResult(
+                        chunk_id=sr.chunk_id,
+                        chunk_index=sr.chunk_index,
+                        doc_id=sr.doc_id,
+                        kb_id=sr.kb_id,
+                        content=sr.content,
+                        score=rrf_scores[identifier],
+                    ),
+                )
+            elif identifier in vec_doc_id_to_dense:
+                # 从向量检索获取信息,需要从数据库获取块的详细信息
+                vec_result = vec_doc_id_to_dense[identifier]
+                chunk_md = json.loads(vec_result.data["metadata"])
+                fused_results.append(
+                    FusedResult(
+                        chunk_id=identifier,
+                        chunk_index=chunk_md["chunk_index"],
+                        doc_id=chunk_md["kb_doc_id"],
+                        kb_id=chunk_md["kb_id"],
+                        content=vec_result.data["text"],
+                        score=rrf_scores[identifier],
+                    ),
+                )
+
+        return fused_results

astrbot/core/knowledge_base/retrieval/sparse_retriever.py

@@ -0,0 +1,136 @@
+"""稀疏检索器
+
+使用 BM25 算法进行基于关键词的文档检索
+"""
+
+import json
+import os
+from dataclasses import dataclass
+
+import jieba
+from rank_bm25 import BM25Okapi
+
+from astrbot.core.db.vec_db.faiss_impl import FaissVecDB
+from astrbot.core.knowledge_base.kb_db_sqlite import KBSQLiteDatabase
+
+
+@dataclass
+class SparseResult:
+    """稀疏检索结果"""
+
+    chunk_index: int
+    chunk_id: str
+    doc_id: str
+    kb_id: str
+    content: str
+    score: float
+
+
+class SparseRetriever:
+    """BM25 稀疏检索器
+
+    职责:
+    - 基于关键词的文档检索
+    - 使用 BM25 算法计算相关度
+    """
+
+    def __init__(self, kb_db: KBSQLiteDatabase):
+        """初始化稀疏检索器
+
+        Args:
+            kb_db: 知识库数据库实例
+
+        """
+        self.kb_db = kb_db
+        self._index_cache = {}  # 缓存 BM25 索引
+
+        with open(
+            os.path.join(os.path.dirname(__file__), "hit_stopwords.txt"),
+            encoding="utf-8",
+        ) as f:
+            self.hit_stopwords = {
+                word.strip() for word in set(f.read().splitlines()) if word.strip()
+            }
+
+    async def retrieve(
+        self,
+        query: str,
+        kb_ids: list[str],
+        kb_options: dict,
+    ) -> list[SparseResult]:
+        """执行稀疏检索
+
+        Args:
+            query: 查询文本
+            kb_ids: 知识库 ID 列表
+            kb_options: 每个知识库的检索选项
+
+        Returns:
+            List[SparseResult]: 检索结果列表
+
+        """
+        # 1. 获取所有相关块
+        top_k_sparse = 0
+        chunks = []
+        for kb_id in kb_ids:
+            vec_db: FaissVecDB = kb_options.get(kb_id, {}).get("vec_db")
+            if not vec_db:
+                continue
+            result = await vec_db.document_storage.get_documents(
+                metadata_filters={},
+                limit=None,
+                offset=None,
+            )
+            chunk_mds = [json.loads(doc["metadata"]) for doc in result]
+            result = [
+                {
+                    "chunk_id": doc["doc_id"],
+                    "chunk_index": chunk_md["chunk_index"],
+                    "doc_id": chunk_md["kb_doc_id"],
+                    "kb_id": kb_id,
+                    "text": doc["text"],
+                }
+                for doc, chunk_md in zip(result, chunk_mds)
+            ]
+            chunks.extend(result)
+            top_k_sparse += kb_options.get(kb_id, {}).get("top_k_sparse", 50)
+
+        if not chunks:
+            return []
+
+        # 2. 准备文档和索引
+        corpus = [chunk["text"] for chunk in chunks]
+        tokenized_corpus = [list(jieba.cut(doc)) for doc in corpus]
+        tokenized_corpus = [
+            [word for word in doc if word not in self.hit_stopwords]
+            for doc in tokenized_corpus
+        ]
+
+        # 3. 构建 BM25 索引
+        bm25 = BM25Okapi(tokenized_corpus)
+
+        # 4. 执行检索
+        tokenized_query = list(jieba.cut(query))
+        tokenized_query = [
+            word for word in tokenized_query if word not in self.hit_stopwords
+        ]
+        scores = bm25.get_scores(tokenized_query)
+
+        # 5. 排序并返回 Top-K
+        results = []
+        for idx, score in enumerate(scores):
+            chunk = chunks[idx]
+            results.append(
+                SparseResult(
+                    chunk_id=chunk["chunk_id"],
+                    chunk_index=chunk["chunk_index"],
+                    doc_id=chunk["doc_id"],
+                    kb_id=chunk["kb_id"],
+                    content=chunk["text"],
+                    score=float(score),
+                ),
+            )
+
+        results.sort(key=lambda x: x.score, reverse=True)
+        # return results[: len(results) // len(kb_ids)]
+        return results[:top_k_sparse]

astrbot/core/log.py

@@ -1,12 +1,37 @@
-import logging
-import colorlog
-import asyncio
-import os
-from collections import deque
-from asyncio import Queue
-from typing import List
+"""日志系统, 用于支持核心组件和插件的日志记录, 提供了日志订阅功能
 
+const:
+    CACHED_SIZE: 日志缓存大小, 用于限制缓存的日志数量
+    log_color_config: 日志颜色配置, 定义了不同日志级别的颜色
+
+class:
+    LogBroker: 日志代理类, 用于缓存和分发日志消息
+    LogQueueHandler: 日志处理器, 用于将日志消息发送到 LogBroker
+    LogManager: 日志管理器, 用于创建和配置日志记录器
+
+function:
+    is_plugin_path: 检查文件路径是否来自插件目录
+    get_short_level_name: 将日志级别名称转换为四个字母的缩写
+
+工作流程:
+1. 通过 LogManager.GetLogger() 获取日志器, 配置了控制台输出和多个格式化过滤器
+2. 通过 set_queue_handler() 设置日志处理器, 将日志消息发送到 LogBroker
+3. logBroker 维护一个订阅者列表, 负责将日志分发给所有订阅者
+4. 订阅者可以使用 register() 方法注册到 LogBroker, 订阅日志流
+"""
+
+import asyncio
+import logging
+import os
+import sys
+from asyncio import Queue
+from collections import deque
+
+import colorlog
+
+# 日志缓存大小
 CACHED_SIZE = 200
+# 日志颜色配置
 log_color_config = {
     "DEBUG": "green",
     "INFO": "bold_cyan",
@@ -19,8 +44,14 @@ log_color_config = {
 
 
 def is_plugin_path(pathname):
-    """
-    检查文件路径是否来自插件目录
+    """检查文件路径是否来自插件目录
+
+    Args:
+        pathname (str): 文件路径
+
+    Returns:
+        bool: 如果路径来自插件目录，则返回 True，否则返回 False
+
     """
     if not pathname:
         return False
@@ -30,8 +61,14 @@ def is_plugin_path(pathname):
 
 
 def get_short_level_name(level_name):
-    """
-    将日志级别名称转换为四个字母的缩写
+    """将日志级别名称转换为四个字母的缩写
+
+    Args:
+        level_name (str): 日志级别名称, 如 "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"
+
+    Returns:
+        str: 四个字母的日志级别缩写
+
     """
     level_map = {
         "DEBUG": "DBUG",
@@ -44,24 +81,43 @@ def get_short_level_name(level_name):
 
 
 class LogBroker:
+    """日志代理类, 用于缓存和分发日志消息
+
+    发布-订阅模式
+    """
+
     def __init__(self):
-        self.log_cache = deque(maxlen=CACHED_SIZE)
-        self.subscribers: List[Queue] = []
+        self.log_cache = deque(maxlen=CACHED_SIZE)  # 环形缓冲区, 保存最近的日志
+        self.subscribers: list[Queue] = []  # 订阅者列表
 
     def register(self) -> Queue:
-        """给每个订阅者返回一个带有日志缓存的队列"""
+        """注册新的订阅者, 并给每个订阅者返回一个带有日志缓存的队列
+
+        Returns:
+            Queue: 订阅者的队列, 可用于接收日志消息
+
+        """
         q = Queue(maxsize=CACHED_SIZE + 10)
-        for log in self.log_cache:
-            q.put_nowait(log)
         self.subscribers.append(q)
         return q
 
     def unregister(self, q: Queue):
-        """取消订阅"""
+        """取消订阅
+
+        Args:
+            q (Queue): 需要取消订阅的队列
+
+        """
         self.subscribers.remove(q)
 
-    def publish(self, log_entry: str):
-        """发布消息"""
+    def publish(self, log_entry: dict):
+        """发布新日志到所有订阅者, 使用非阻塞方式投递, 避免一个订阅者阻塞整个系统
+
+        Args:
+            log_entry (dict): 日志消息, 包含日志级别和日志内容.
+                example: {"level": "INFO", "data": "This is a log message.", "time": "2023-10-01 12:00:00"}
+
+        """
         self.log_cache.append(log_entry)
         for q in self.subscribers:
             try:
@@ -71,24 +127,63 @@ class LogBroker:
 
 
 class LogQueueHandler(logging.Handler):
+    """日志处理器, 用于将日志消息发送到 LogBroker
+
+    继承自 logging.Handler
+    """
+
     def __init__(self, log_broker: LogBroker):
         super().__init__()
         self.log_broker = log_broker
 
     def emit(self, record):
+        """日志处理的入口方法, 接受一个日志记录, 转换为字符串后由 LogBroker 发布
+        这个方法会在每次日志记录时被调用
+
+        Args:
+            record (logging.LogRecord): 日志记录对象, 包含日志信息
+
+        """
         log_entry = self.format(record)
-        self.log_broker.publish(log_entry)
+        self.log_broker.publish(
+            {
+                "level": record.levelname,
+                "time": record.asctime,
+                "data": log_entry,
+            },
+        )
 
 
 class LogManager:
+    """日志管理器, 用于创建和配置日志记录器
+
+    提供了获取默认日志记录器logger和设置队列处理器的方法
+    """
+
     @classmethod
     def GetLogger(cls, log_name: str = "default"):
+        """获取指定名称的日志记录器logger
+
+        Args:
+            log_name (str): 日志记录器的名称, 默认为 "default"
+
+        Returns:
+            logging.Logger: 返回配置好的日志记录器
+
+        """
         logger = logging.getLogger(log_name)
+        # 检查该logger或父级logger是否已经有处理器, 如果已经有处理器, 直接返回该logger, 避免重复配置
         if logger.hasHandlers():
             return logger
-        console_handler = logging.StreamHandler()
-        console_handler.setLevel(logging.DEBUG)
+        # 如果logger没有处理器
+        console_handler = logging.StreamHandler(
+            sys.stdout,
+        )  # 创建一个StreamHandler用于控制台输出
+        console_handler.setLevel(
+            logging.DEBUG,
+        )  # 将日志级别设置为DEBUG(最低级别, 显示所有日志), *如果插件没有设置级别, 默认为DEBUG
 
+        # 创建彩色日志格式化器, 输出日志格式为: [时间] [插件标签] [日志级别] [文件名:行号]: 日志消息
         console_formatter = colorlog.ColoredFormatter(
             fmt="%(log_color)s [%(asctime)s] %(plugin_tag)s [%(short_levelname)-4s] [%(filename)s:%(lineno)d]: %(message)s %(reset)s",
             datefmt="%H:%M:%S",
@@ -96,6 +191,8 @@ class LogManager:
         )
 
         class PluginFilter(logging.Filter):
+            """插件过滤器类, 用于标记日志来源是插件还是核心组件"""
+
             def filter(self, record):
                 record.plugin_tag = (
                     "[Plug]" if is_plugin_path(record.pathname) else "[Core]"
@@ -103,6 +200,10 @@ class LogManager:
                 return True
 
         class FileNameFilter(logging.Filter):
+            """文件名过滤器类, 用于修改日志记录的文件名格式
+            例如: 将文件路径 /path/to/file.py 转换为 file.<file> 格式
+            """
+
             # 获取这个文件和父文件夹的名字：<folder>.<file> 并且去除 .py
             def filter(self, record):
                 dirname = os.path.dirname(record.pathname)
@@ -114,22 +215,31 @@ class LogManager:
                 return True
 
         class LevelNameFilter(logging.Filter):
+            """短日志级别名称过滤器类, 用于将日志级别名称转换为四个字母的缩写"""
+
             # 添加短日志级别名称
             def filter(self, record):
                 record.short_levelname = get_short_level_name(record.levelname)
                 return True
 
-        console_handler.setFormatter(console_formatter)
-        logger.addFilter(PluginFilter())
-        logger.addFilter(FileNameFilter())
+        console_handler.setFormatter(console_formatter)  # 设置处理器的格式化器
+        logger.addFilter(PluginFilter())  # 添加插件过滤器
+        logger.addFilter(FileNameFilter())  # 添加文件名过滤器
         logger.addFilter(LevelNameFilter())  # 添加级别名称过滤器
-        logger.setLevel(logging.DEBUG)
-        logger.addHandler(console_handler)
+        logger.setLevel(logging.DEBUG)  # 设置日志级别为DEBUG
+        logger.addHandler(console_handler)  # 添加处理器到logger
 
         return logger
 
     @classmethod
     def set_queue_handler(cls, logger: logging.Logger, log_broker: LogBroker):
+        """设置队列处理器, 用于将日志消息发送到 LogBroker
+
+        Args:
+            logger (logging.Logger): 日志记录器
+            log_broker (LogBroker): 日志代理类, 用于缓存和分发日志消息
+
+        """
         handler = LogQueueHandler(log_broker)
         handler.setLevel(logging.DEBUG)
         if logger.handlers:
@@ -138,7 +248,7 @@ class LogManager:
             # 为队列处理器设置相同格式的formatter
             handler.setFormatter(
                 logging.Formatter(
-                    "[%(asctime)s] [%(short_levelname)s] %(plugin_tag)s[%(filename)s:%(lineno)d]: %(message)s"
-                )
+                    "[%(asctime)s] [%(short_levelname)s] %(plugin_tag)s[%(filename)s:%(lineno)d]: %(message)s",
+                ),
             )
         logger.addHandler(handler)

astrbot/core/message/components.py

@@ -1,5 +1,4 @@
-"""
-MIT License
+"""MIT License
 
 Copyright (c) 2021 Lxns-Network
 
@@ -22,67 +21,51 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 """
 
+import asyncio
 import base64
 import json
 import os
-import typing as T
+import uuid
 from enum import Enum
+
 from pydantic.v1 import BaseModel
 
+from astrbot.core import astrbot_config, file_token_service, logger
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+from astrbot.core.utils.io import download_file, download_image_by_url, file_to_base64
 
-class ComponentType(Enum):
-    Plain = "Plain"  # 纯文本消息
-    Face = "Face"  # QQ表情
-    Record = "Record"  # 语音
-    Video = "Video"  # 视频
-    At = "At"  # At
-    Node = "Node"  # 转发消息的一个节点
-    Nodes = "Nodes"  # 转发消息的多个节点
-    Poke = "Poke"  # QQ 戳一戳
-    Image = "Image"  # 图片
-    Reply = "Reply"  # 回复
-    Forward = "Forward"  # 转发消息
-    File = "File"  # 文件
 
+class ComponentType(str, Enum):
+    # Basic Segment Types
+    Plain = "Plain"  # plain text message
+    Image = "Image"  # image
+    Record = "Record"  # audio
+    Video = "Video"  # video
+    File = "File"  # file attachment
+
+    # IM-specific Segment Types
+    Face = "Face"  # Emoji segment for Tencent QQ platform
+    At = "At"  # mention a user in IM apps
+    Node = "Node"  # a node in a forwarded message
+    Nodes = "Nodes"  # a forwarded message consisting of multiple nodes
+    Poke = "Poke"  # a poke message for Tencent QQ platform
+    Reply = "Reply"  # a reply message segment
+    Forward = "Forward"  # a forwarded message segment
     RPS = "RPS"  # TODO
     Dice = "Dice"  # TODO
     Shake = "Shake"  # TODO
-    Anonymous = "Anonymous"  # TODO
     Share = "Share"
     Contact = "Contact"  # TODO
     Location = "Location"  # TODO
     Music = "Music"
-    RedBag = "RedBag"
-    Xml = "Xml"
     Json = "Json"
-    CardImage = "CardImage"
-    TTS = "TTS"
     Unknown = "Unknown"
+    WechatEmoji = "WechatEmoji"  # Wechat 下的 emoji 表情包
 
 
 class BaseMessageComponent(BaseModel):
     type: ComponentType
 
-    def toString(self):
-        output = f"[CQ:{self.type.lower()}"
-        for k, v in self.__dict__.items():
-            if k == "type" or v is None:
-                continue
-            if k == "_type":
-                k = "type"
-            if isinstance(v, bool):
-                v = 1 if v else 0
-            output += ",%s=%s" % (
-                k,
-                str(v)
-                .replace("&", "&")
-                .replace(",", ",")
-                .replace("[", "[")
-                .replace("]", "]"),
-            )
-        output += "]"
-        return output
-
     def toDict(self):
         data = {}
         for k, v in self.__dict__.items():
@@ -93,25 +76,28 @@ class BaseMessageComponent(BaseModel):
             data[k] = v
         return {"type": self.type.lower(), "data": data}
 
+    async def to_dict(self) -> dict:
+        # 默认情况下，回退到旧的同步 toDict()
+        return self.toDict()
+
 
 class Plain(BaseMessageComponent):
-    type: ComponentType = "Plain"
+    type = ComponentType.Plain
     text: str
-    convert: T.Optional[bool] = True  # 若为 False 则直接发送未转换 CQ 码的消息
+    convert: bool | None = True
 
     def __init__(self, text: str, convert: bool = True, **_):
         super().__init__(text=text, convert=convert, **_)
 
-    def toString(self):  # 没有 [CQ:plain] 这种东西，所以直接导出纯文本
-        if not self.convert:
-            return self.text
-        return (
-            self.text.replace("&", "&").replace("[", "[").replace("]", "]")
-        )
+    def toDict(self):
+        return {"type": "text", "data": {"text": self.text.strip()}}
+
+    async def to_dict(self):
+        return {"type": "text", "data": {"text": self.text}}
 
 
 class Face(BaseMessageComponent):
-    type: ComponentType = "Face"
+    type = ComponentType.Face
     id: int
 
     def __init__(self, **_):
@@ -119,18 +105,18 @@ class Face(BaseMessageComponent):
 
 
 class Record(BaseMessageComponent):
-    type: ComponentType = "Record"
-    file: T.Optional[str] = ""
-    magic: T.Optional[bool] = False
-    url: T.Optional[str] = ""
-    cache: T.Optional[bool] = True
-    proxy: T.Optional[bool] = True
-    timeout: T.Optional[int] = 0
+    type = ComponentType.Record
+    file: str | None = ""
+    magic: bool | None = False
+    url: str | None = ""
+    cache: bool | None = True
+    proxy: bool | None = True
+    timeout: int | None = 0
     # 额外
-    path: T.Optional[str]
+    path: str | None
 
-    def __init__(self, file: T.Optional[str], **_):
-        for k in _.keys():
+    def __init__(self, file: str | None, **_):
+        for k in _:
             if k == "url":
                 pass
                 # Protocol.warn(f"go-cqhttp doesn't support send {self.type} by {k}")
@@ -146,19 +132,93 @@ class Record(BaseMessageComponent):
             return Record(file=url, **_)
         raise Exception("not a valid url")
 
+    @staticmethod
+    def fromBase64(bs64_data: str, **_):
+        return Record(file=f"base64://{bs64_data}", **_)
+
+    async def convert_to_file_path(self) -> str:
+        """将这个语音统一转换为本地文件路径。这个方法避免了手动判断语音数据类型，直接返回语音数据的本地路径（如果是网络 URL, 则会自动进行下载）。
+
+        Returns:
+            str: 语音的本地路径，以绝对路径表示。
+
+        """
+        if not self.file:
+            raise Exception(f"not a valid file: {self.file}")
+        if self.file.startswith("file:///"):
+            return self.file[8:]
+        if self.file.startswith("http"):
+            file_path = await download_image_by_url(self.file)
+            return os.path.abspath(file_path)
+        if self.file.startswith("base64://"):
+            bs64_data = self.file.removeprefix("base64://")
+            image_bytes = base64.b64decode(bs64_data)
+            temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+            file_path = os.path.join(temp_dir, f"{uuid.uuid4()}.jpg")
+            with open(file_path, "wb") as f:
+                f.write(image_bytes)
+            return os.path.abspath(file_path)
+        if os.path.exists(self.file):
+            return os.path.abspath(self.file)
+        raise Exception(f"not a valid file: {self.file}")
+
+    async def convert_to_base64(self) -> str:
+        """将语音统一转换为 base64 编码。这个方法避免了手动判断语音数据类型，直接返回语音数据的 base64 编码。
+
+        Returns:
+            str: 语音的 base64 编码，不以 base64:// 或者 data:image/jpeg;base64, 开头。
+
+        """
+        # convert to base64
+        if not self.file:
+            raise Exception(f"not a valid file: {self.file}")
+        if self.file.startswith("file:///"):
+            bs64_data = file_to_base64(self.file[8:])
+        elif self.file.startswith("http"):
+            file_path = await download_image_by_url(self.file)
+            bs64_data = file_to_base64(file_path)
+        elif self.file.startswith("base64://"):
+            bs64_data = self.file
+        elif os.path.exists(self.file):
+            bs64_data = file_to_base64(self.file)
+        else:
+            raise Exception(f"not a valid file: {self.file}")
+        bs64_data = bs64_data.removeprefix("base64://")
+        return bs64_data
+
+    async def register_to_file_service(self) -> str:
+        """将语音注册到文件服务。
+
+        Returns:
+            str: 注册后的URL
+
+        Raises:
+            Exception: 如果未配置 callback_api_base
+
+        """
+        callback_host = astrbot_config.get("callback_api_base")
+
+        if not callback_host:
+            raise Exception("未配置 callback_api_base，文件服务不可用")
+
+        file_path = await self.convert_to_file_path()
+
+        token = await file_token_service.register_file(file_path)
+
+        logger.debug(f"已注册：{callback_host}/api/file/{token}")
+
+        return f"{callback_host}/api/file/{token}"
+
 
 class Video(BaseMessageComponent):
-    type: ComponentType = "Video"
+    type = ComponentType.Video
     file: str
-    cover: T.Optional[str] = ""
-    c: T.Optional[int] = 2
+    cover: str | None = ""
+    c: int | None = 2
     # 额外
-    path: T.Optional[str] = ""
+    path: str | None = ""
 
     def __init__(self, file: str, **_):
-        # for k in _.keys():
-        #     if k == "c" and _[k] not in [2, 3]:
-        #         logger.warn(f"Protocol: {k}={_[k]} doesn't match values")
         super().__init__(file=file, **_)
 
     @staticmethod
@@ -171,15 +231,84 @@ class Video(BaseMessageComponent):
             return Video(file=url, **_)
         raise Exception("not a valid url")
 
+    async def convert_to_file_path(self) -> str:
+        """将这个视频统一转换为本地文件路径。这个方法避免了手动判断视频数据类型，直接返回视频数据的本地路径（如果是网络 URL，则会自动进行下载）。
+
+        Returns:
+            str: 视频的本地路径，以绝对路径表示。
+
+        """
+        url = self.file
+        if url and url.startswith("file:///"):
+            return url[8:]
+        if url and url.startswith("http"):
+            download_dir = os.path.join(get_astrbot_data_path(), "temp")
+            video_file_path = os.path.join(download_dir, f"{uuid.uuid4().hex}")
+            await download_file(url, video_file_path)
+            if os.path.exists(video_file_path):
+                return os.path.abspath(video_file_path)
+            raise Exception(f"download failed: {url}")
+        if os.path.exists(url):
+            return os.path.abspath(url)
+        raise Exception(f"not a valid file: {url}")
+
+    async def register_to_file_service(self):
+        """将视频注册到文件服务。
+
+        Returns:
+            str: 注册后的URL
+
+        Raises:
+            Exception: 如果未配置 callback_api_base
+
+        """
+        callback_host = astrbot_config.get("callback_api_base")
+
+        if not callback_host:
+            raise Exception("未配置 callback_api_base，文件服务不可用")
+
+        file_path = await self.convert_to_file_path()
+
+        token = await file_token_service.register_file(file_path)
+
+        logger.debug(f"已注册：{callback_host}/api/file/{token}")
+
+        return f"{callback_host}/api/file/{token}"
+
+    async def to_dict(self):
+        """需要和 toDict 区分开，toDict 是同步方法"""
+        url_or_path = self.file
+        if url_or_path.startswith("http"):
+            payload_file = url_or_path
+        elif callback_host := astrbot_config.get("callback_api_base"):
+            callback_host = str(callback_host).removesuffix("/")
+            token = await file_token_service.register_file(url_or_path)
+            payload_file = f"{callback_host}/api/file/{token}"
+            logger.debug(f"Generated video file callback link: {payload_file}")
+        else:
+            payload_file = url_or_path
+        return {
+            "type": "video",
+            "data": {
+                "file": payload_file,
+            },
+        }
+
 
 class At(BaseMessageComponent):
-    type: ComponentType = "At"
-    qq: T.Union[int, str]  # 此处str为all时代表所有人
-    name: T.Optional[str] = ""
+    type = ComponentType.At
+    qq: int | str  # 此处str为all时代表所有人
+    name: str | None = ""
 
     def __init__(self, **_):
         super().__init__(**_)
 
+    def toDict(self):
+        return {
+            "type": "at",
+            "data": {"qq": str(self.qq)},
+        }
+
 
 class AtAll(At):
     qq: str = "all"
@@ -189,74 +318,66 @@ class AtAll(At):
 
 
 class RPS(BaseMessageComponent):  # TODO
-    type: ComponentType = "RPS"
+    type = ComponentType.RPS
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Dice(BaseMessageComponent):  # TODO
-    type: ComponentType = "Dice"
+    type = ComponentType.Dice
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Shake(BaseMessageComponent):  # TODO
-    type: ComponentType = "Shake"
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
-class Anonymous(BaseMessageComponent):  # TODO
-    type: ComponentType = "Anonymous"
-    ignore: T.Optional[bool] = False
+    type = ComponentType.Shake
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Share(BaseMessageComponent):
-    type: ComponentType = "Share"
+    type = ComponentType.Share
     url: str
     title: str
-    content: T.Optional[str] = ""
-    image: T.Optional[str] = ""
+    content: str | None = ""
+    image: str | None = ""
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Contact(BaseMessageComponent):  # TODO
-    type: ComponentType = "Contact"
+    type = ComponentType.Contact
     _type: str  # type 字段冲突
-    id: T.Optional[int] = 0
+    id: int | None = 0
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Location(BaseMessageComponent):  # TODO
-    type: ComponentType = "Location"
+    type = ComponentType.Location
     lat: float
     lon: float
-    title: T.Optional[str] = ""
-    content: T.Optional[str] = ""
+    title: str | None = ""
+    content: str | None = ""
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Music(BaseMessageComponent):
-    type: ComponentType = "Music"
+    type = ComponentType.Music
     _type: str
-    id: T.Optional[int] = 0
-    url: T.Optional[str] = ""
-    audio: T.Optional[str] = ""
-    title: T.Optional[str] = ""
-    content: T.Optional[str] = ""
-    image: T.Optional[str] = ""
+    id: int | None = 0
+    url: str | None = ""
+    audio: str | None = ""
+    title: str | None = ""
+    content: str | None = ""
+    image: str | None = ""
 
     def __init__(self, **_):
         # for k in _.keys():
@@ -266,23 +387,19 @@ class Music(BaseMessageComponent):
 
 
 class Image(BaseMessageComponent):
-    type: ComponentType = "Image"
-    file: T.Optional[str] = ""
-    _type: T.Optional[str] = ""
-    subType: T.Optional[int] = 0
-    url: T.Optional[str] = ""
-    cache: T.Optional[bool] = True
-    id: T.Optional[int] = 40000
-    c: T.Optional[int] = 2
+    type = ComponentType.Image
+    file: str | None = ""
+    _type: str | None = ""
+    subType: int | None = 0
+    url: str | None = ""
+    cache: bool | None = True
+    id: int | None = 40000
+    c: int | None = 2
     # 额外
-    path: T.Optional[str] = ""
-    file_unique: T.Optional[str] = ""  # 某些平台可能有图片缓存的唯一标识
+    path: str | None = ""
+    file_unique: str | None = ""  # 某些平台可能有图片缓存的唯一标识
 
-    def __init__(self, file: T.Optional[str], **_):
-        # for k in _.keys():
-        #     if (k == "_type" and _[k] not in ["flash", "show", None]) or \
-        #             (k == "c" and _[k] not in [2, 3]):
-        #         logger.warn(f"Protocol: {k}={_[k]} doesn't match values")
+    def __init__(self, file: str | None, **_):
         super().__init__(file=file, **_)
 
     @staticmethod
@@ -307,31 +424,112 @@ class Image(BaseMessageComponent):
     def fromIO(IO):
         return Image.fromBytes(IO.read())
 
+    async def convert_to_file_path(self) -> str:
+        """将这个图片统一转换为本地文件路径。这个方法避免了手动判断图片数据类型，直接返回图片数据的本地路径（如果是网络 URL, 则会自动进行下载）。
+
+        Returns:
+            str: 图片的本地路径，以绝对路径表示。
+
+        """
+        url = self.url or self.file
+        if not url:
+            raise ValueError("No valid file or URL provided")
+        if url.startswith("file:///"):
+            return url[8:]
+        if url.startswith("http"):
+            image_file_path = await download_image_by_url(url)
+            return os.path.abspath(image_file_path)
+        if url.startswith("base64://"):
+            bs64_data = url.removeprefix("base64://")
+            image_bytes = base64.b64decode(bs64_data)
+            temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+            image_file_path = os.path.join(temp_dir, f"{uuid.uuid4()}.jpg")
+            with open(image_file_path, "wb") as f:
+                f.write(image_bytes)
+            return os.path.abspath(image_file_path)
+        if os.path.exists(url):
+            return os.path.abspath(url)
+        raise Exception(f"not a valid file: {url}")
+
+    async def convert_to_base64(self) -> str:
+        """将这个图片统一转换为 base64 编码。这个方法避免了手动判断图片数据类型，直接返回图片数据的 base64 编码。
+
+        Returns:
+            str: 图片的 base64 编码，不以 base64:// 或者 data:image/jpeg;base64, 开头。
+
+        """
+        # convert to base64
+        url = self.url or self.file
+        if not url:
+            raise ValueError("No valid file or URL provided")
+        if url.startswith("file:///"):
+            bs64_data = file_to_base64(url[8:])
+        elif url.startswith("http"):
+            image_file_path = await download_image_by_url(url)
+            bs64_data = file_to_base64(image_file_path)
+        elif url.startswith("base64://"):
+            bs64_data = url
+        elif os.path.exists(url):
+            bs64_data = file_to_base64(url)
+        else:
+            raise Exception(f"not a valid file: {url}")
+        bs64_data = bs64_data.removeprefix("base64://")
+        return bs64_data
+
+    async def register_to_file_service(self) -> str:
+        """将图片注册到文件服务。
+
+        Returns:
+            str: 注册后的URL
+
+        Raises:
+            Exception: 如果未配置 callback_api_base
+
+        """
+        callback_host = astrbot_config.get("callback_api_base")
+
+        if not callback_host:
+            raise Exception("未配置 callback_api_base，文件服务不可用")
+
+        file_path = await self.convert_to_file_path()
+
+        token = await file_token_service.register_file(file_path)
+
+        logger.debug(f"已注册：{callback_host}/api/file/{token}")
+
+        return f"{callback_host}/api/file/{token}"
+
 
 class Reply(BaseMessageComponent):
-    type: ComponentType = "Reply"
-    id: T.Union[str, int]
-    text: T.Optional[str] = ""
-    qq: T.Optional[int] = 0
-    time: T.Optional[int] = 0
-    seq: T.Optional[int] = 0
+    type = ComponentType.Reply
+    id: str | int
+    """所引用的消息 ID"""
+    chain: list["BaseMessageComponent"] | None = []
+    """被引用的消息段列表"""
+    sender_id: int | None | str = 0
+    """被引用的消息对应的发送者的 ID"""
+    sender_nickname: str | None = ""
+    """被引用的消息对应的发送者的昵称"""
+    time: int | None = 0
+    """被引用的消息发送时间"""
+    message_str: str | None = ""
+    """被引用的消息解析后的纯文本消息字符串"""
 
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
-class RedBag(BaseMessageComponent):
-    type: ComponentType = "RedBag"
-    title: str
+    text: str | None = ""
+    """deprecated"""
+    qq: int | None = 0
+    """deprecated"""
+    seq: int | None = 0
+    """deprecated"""
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Poke(BaseMessageComponent):
-    type: str = ""
-    id: T.Optional[int] = 0
-    qq: T.Optional[int] = 0
+    type: str = ComponentType.Poke
+    id: int | None = 0
+    qq: int | None = 0
 
     def __init__(self, type: str, **_):
         type = f"Poke:{type}"
@@ -339,7 +537,7 @@ class Poke(BaseMessageComponent):
 
 
 class Forward(BaseMessageComponent):
-    type: ComponentType = "Forward"
+    type = ComponentType.Forward
     id: str
 
     def __init__(self, **_):
@@ -349,51 +547,87 @@ class Forward(BaseMessageComponent):
 class Node(BaseMessageComponent):
     """群合并转发消息"""
 
-    type: ComponentType = "Node"
-    id: T.Optional[int] = 0  # 忽略
-    name: T.Optional[str] = ""  # qq昵称
-    uin: T.Optional[int] = 0  # qq号
-    content: T.Optional[T.Union[str, list]] = ""  # 子消息段列表
-    seq: T.Optional[T.Union[str, list]] = ""  # 忽略
-    time: T.Optional[int] = 0
+    type = ComponentType.Node
+    id: int | None = 0  # 忽略
+    name: str | None = ""  # qq昵称
+    uin: str | None = "0"  # qq号
+    content: list[BaseMessageComponent] | None = []
+    seq: str | list | None = ""  # 忽略
+    time: int | None = 0  # 忽略
 
-    def __init__(self, content: T.Union[str, list], **_):
-        if isinstance(content, list):
-            _content = ""
-            for chain in content:
-                _content += chain.toString()
-            content = _content
+    def __init__(self, content: list[BaseMessageComponent], **_):
+        if isinstance(content, Node):
+            # back
+            content = [content]
         super().__init__(content=content, **_)
 
-    def toString(self):
-        # logger.warn("Protocol: node doesn't support stringify")
-        return ""
+    async def to_dict(self):
+        data_content = []
+        for comp in self.content:
+            if isinstance(comp, (Image, Record)):
+                # For Image and Record segments, we convert them to base64
+                bs64 = await comp.convert_to_base64()
+                data_content.append(
+                    {
+                        "type": comp.type.lower(),
+                        "data": {"file": f"base64://{bs64}"},
+                    },
+                )
+            elif isinstance(comp, Plain):
+                # For Plain segments, we need to handle the plain differently
+                d = await comp.to_dict()
+                data_content.append(d)
+            elif isinstance(comp, File):
+                # For File segments, we need to handle the file differently
+                d = await comp.to_dict()
+                data_content.append(d)
+            elif isinstance(comp, (Node, Nodes)):
+                # For Node segments, we recursively convert them to dict
+                d = await comp.to_dict()
+                data_content.append(d)
+            else:
+                d = comp.toDict()
+                data_content.append(d)
+        return {
+            "type": "node",
+            "data": {
+                "user_id": str(self.uin),
+                "nickname": self.name,
+                "content": data_content,
+            },
+        }
 
 
 class Nodes(BaseMessageComponent):
-    type: ComponentType = "Nodes"
-    nodes: T.List[Node]
+    type = ComponentType.Nodes
+    nodes: list[Node]
 
-    def __init__(self, nodes: T.List[Node], **_):
+    def __init__(self, nodes: list[Node], **_):
         super().__init__(nodes=nodes, **_)
 
     def toDict(self):
-        return {"messages": [node.toDict() for node in self.nodes]}
+        """Deprecated. Use to_dict instead"""
+        ret = {
+            "messages": [],
+        }
+        for node in self.nodes:
+            d = node.toDict()
+            ret["messages"].append(d)
+        return ret
 
-
-class Xml(BaseMessageComponent):
-    type: ComponentType = "Xml"
-    data: str
-    resid: T.Optional[int] = 0
-
-    def __init__(self, **_):
-        super().__init__(**_)
+    async def to_dict(self):
+        """将 Nodes 转换为字典格式，适用于 OneBot JSON 格式"""
+        ret = {"messages": []}
+        for node in self.nodes:
+            d = await node.to_dict()
+            ret["messages"].append(d)
+        return ret
 
 
 class Json(BaseMessageComponent):
-    type: ComponentType = "Json"
-    data: T.Union[str, dict]
-    resid: T.Optional[int] = 0
+    type = ComponentType.Json
+    data: str | dict
+    resid: int | None = 0
 
     def __init__(self, data, **_):
         if isinstance(data, dict):
@@ -401,80 +635,175 @@ class Json(BaseMessageComponent):
         super().__init__(data=data, **_)
 
 
-class CardImage(BaseMessageComponent):
-    type: ComponentType = "CardImage"
-    file: str
-    cache: T.Optional[bool] = True
-    minwidth: T.Optional[int] = 400
-    minheight: T.Optional[int] = 400
-    maxwidth: T.Optional[int] = 500
-    maxheight: T.Optional[int] = 500
-    source: T.Optional[str] = ""
-    icon: T.Optional[str] = ""
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-    @staticmethod
-    def fromFileSystem(path, **_):
-        return CardImage(file=f"file:///{os.path.abspath(path)}", **_)
-
-
-class TTS(BaseMessageComponent):
-    type: ComponentType = "TTS"
-    text: str
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
 class Unknown(BaseMessageComponent):
-    type: ComponentType = "Unknown"
+    type = ComponentType.Unknown
     text: str
 
-    def toString(self):
-        return ""
-
 
 class File(BaseMessageComponent):
-    """
-    目前此消息段只适配了 Napcat。
-    """
+    """文件消息段"""
 
-    type: ComponentType = "File"
-    name: T.Optional[str] = ""  # 名字
-    file: T.Optional[str] = ""  # url（本地路径）
+    type = ComponentType.File
+    name: str | None = ""  # 名字
+    file_: str | None = ""  # 本地路径
+    url: str | None = ""  # url
 
-    def __init__(self, name: str, file: str):
-        super().__init__(name=name, file=file)
+    def __init__(self, name: str, file: str = "", url: str = ""):
+        """文件消息段。"""
+        super().__init__(name=name, file_=file, url=url)
+
+    @property
+    def file(self) -> str:
+        """获取文件路径，如果文件不存在但有URL，则同步下载文件
+
+        Returns:
+            str: 文件路径
+
+        """
+        if self.file_ and os.path.exists(self.file_):
+            return os.path.abspath(self.file_)
+
+        if self.url:
+            try:
+                loop = asyncio.get_event_loop()
+                if loop.is_running():
+                    logger.warning(
+                        "不可以在异步上下文中同步等待下载! "
+                        "这个警告通常发生于某些逻辑试图通过 <File>.file 获取文件消息段的文件内容。"
+                        "请使用 await get_file() 代替直接获取 <File>.file 字段",
+                    )
+                    return ""
+                # 等待下载完成
+                loop.run_until_complete(self._download_file())
+
+                if self.file_ and os.path.exists(self.file_):
+                    return os.path.abspath(self.file_)
+            except Exception as e:
+                logger.error(f"文件下载失败: {e}")
+
+        return ""
+
+    @file.setter
+    def file(self, value: str):
+        """向前兼容, 设置file属性, 传入的参数可能是文件路径或URL
+
+        Args:
+            value (str): 文件路径或URL
+
+        """
+        if value.startswith("http://") or value.startswith("https://"):
+            self.url = value
+        else:
+            self.file_ = value
+
+    async def get_file(self, allow_return_url: bool = False) -> str:
+        """异步获取文件。请注意在使用后清理下载的文件, 以免占用过多空间
+
+        Args:
+            allow_return_url: 是否允许以文件 http 下载链接的形式返回，这允许您自行控制是否需要下载文件。
+            注意，如果为 True，也可能返回文件路径。
+        Returns:
+            str: 文件路径或者 http 下载链接
+
+        """
+        if allow_return_url and self.url:
+            return self.url
+
+        if self.file_ and os.path.exists(self.file_):
+            return os.path.abspath(self.file_)
+
+        if self.url:
+            await self._download_file()
+            return os.path.abspath(self.file_)
+
+        return ""
+
+    async def _download_file(self):
+        """下载文件"""
+        download_dir = os.path.join(get_astrbot_data_path(), "temp")
+        os.makedirs(download_dir, exist_ok=True)
+        file_path = os.path.join(download_dir, f"{uuid.uuid4().hex}")
+        await download_file(self.url, file_path)
+        self.file_ = os.path.abspath(file_path)
+
+    async def register_to_file_service(self):
+        """将文件注册到文件服务。
+
+        Returns:
+            str: 注册后的URL
+
+        Raises:
+            Exception: 如果未配置 callback_api_base
+
+        """
+        callback_host = astrbot_config.get("callback_api_base")
+
+        if not callback_host:
+            raise Exception("未配置 callback_api_base，文件服务不可用")
+
+        file_path = await self.get_file()
+
+        token = await file_token_service.register_file(file_path)
+
+        logger.debug(f"已注册：{callback_host}/api/file/{token}")
+
+        return f"{callback_host}/api/file/{token}"
+
+    async def to_dict(self):
+        """需要和 toDict 区分开，toDict 是同步方法"""
+        url_or_path = await self.get_file(allow_return_url=True)
+        if url_or_path.startswith("http"):
+            payload_file = url_or_path
+        elif callback_host := astrbot_config.get("callback_api_base"):
+            callback_host = str(callback_host).removesuffix("/")
+            token = await file_token_service.register_file(url_or_path)
+            payload_file = f"{callback_host}/api/file/{token}"
+            logger.debug(f"Generated file callback link: {payload_file}")
+        else:
+            payload_file = url_or_path
+        return {
+            "type": "file",
+            "data": {
+                "name": self.name,
+                "file": payload_file,
+            },
+        }
+
+
+class WechatEmoji(BaseMessageComponent):
+    type = ComponentType.WechatEmoji
+    md5: str | None = ""
+    md5_len: int | None = 0
+    cdnurl: str | None = ""
+
+    def __init__(self, **_):
+        super().__init__(**_)
 
 
 ComponentTypes = {
+    # Basic Message Segments
     "plain": Plain,
     "text": Plain,
-    "face": Face,
+    "image": Image,
     "record": Record,
     "video": Video,
+    "file": File,
+    # IM-specific Message Segments
+    "face": Face,
     "at": At,
     "rps": RPS,
     "dice": Dice,
     "shake": Shake,
-    "anonymous": Anonymous,
     "share": Share,
     "contact": Contact,
     "location": Location,
     "music": Music,
-    "image": Image,
     "reply": Reply,
-    "redbag": RedBag,
     "poke": Poke,
     "forward": Forward,
     "node": Node,
     "nodes": Nodes,
-    "xml": Xml,
     "json": Json,
-    "cardimage": CardImage,
-    "tts": TTS,
     "unknown": Unknown,
-    "file": File,
+    "WechatEmoji": WechatEmoji,
 }