chore: bump version to 4.5.4

* 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
@@ -15,7 +14,6 @@ env/
 venv*/
 ENV/
 .conda/
-README*.md
 dashboard/
 data/
 changelogs/

.github/ISSUE_TEMPLATE/PLUGIN_PUBLISH.yml

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

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -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

@@ -1,19 +1,46 @@
-<!-- 如果有的话，指定这个 PR 要解决的 ISSUE -->
+<!-- 如果有的话，请指定此 PR 旨在解决的 ISSUE 编号。 -->
-解决了 #XYZ
+<!-- 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)-->
 
-### Check
+### Modifications / 改动点
 
-<!--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-->
+<!--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?-->
 
-- [ ] 😊 我的 Commit Message 符合良好的[规范](https://www.conventionalcommits.org/en/v1.0.0/#summary)
+### Verification Steps / 验证步骤
-- [ ] 👀 我的更改经过良好的测试
+
-- [ ] 🤓 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到了 `requirements.txt` 和 `pyproject.toml` 文件相应位置。
+<!--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...）。-->
-- [ ] 😮 我的更改没有引入恶意代码
+<!--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/workflows/auto_release.yml

@@ -73,7 +73,7 @@ jobs:
         uses: actions/checkout@v5
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.10'
 

.github/workflows/code-format.yml

@@ -0,0 +1,34 @@
+name: Code Format Check
+
+on:
+  pull_request:
+    branches: [ master ]
+  push:
+    branches: [ master ]
+
+jobs:
+  format-check:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@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

@@ -60,7 +60,7 @@ jobs:
 
     # 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

@@ -22,7 +22,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
       
       - name: Install dependencies
         run: |

.github/workflows/dashboard_ci.yml

@@ -13,11 +13,18 @@ jobs:
       - 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
+          npm install pnpm -g
-          npm run build
+          pnpm install
+          pnpm i --save-dev @types/markdown-it
+          pnpm run build
 
       - name: Inject Commit SHA
         id: get_sha
@@ -29,7 +36,7 @@ jobs:
           zip -r dist.zip dist
 
       - name: Archive production artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v5
         with:
           name: dist-without-markdown
           path: |
@@ -37,6 +44,7 @@ jobs:
             !dist/**/*.md
 
       - name: Create GitHub Release
+        if: github.event_name == 'push'
         uses: ncipollo/release-action@v1
         with:
           tag: release-${{ github.sha }}

.github/workflows/docker-image.yml

@@ -27,6 +27,22 @@ jobs:
         if: github.event_name == 'workflow_dispatch'
         run: git checkout ${{ steps.get-latest-tag.outputs.latest_tag }}
 
+      - name: Check if version is pre-release
+        id: check-prerelease
+        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
@@ -64,9 +80,9 @@ jobs:
           platforms: linux/amd64,linux/arm64
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/astrbot:latest
+            ${{ 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 }}
-            ghcr.io/soulter/astrbot:latest
+            ${{ steps.check-prerelease.outputs.is_prerelease == 'false' && 'ghcr.io/soulter/astrbot:latest' || '' }}
             ghcr.io/soulter/astrbot:${{ github.event_name == 'workflow_dispatch' && steps.get-latest-tag.outputs.latest_tag || github.ref_name }}
 
       - name: Post build notifications

.github/workflows/stale.yml

@@ -18,7 +18,7 @@ jobs:
       pull-requests: write
 
     steps:
-    - uses: actions/stale@v9
+    - uses: actions/stale@v10
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: 'Stale issue message'

.gitignore

@@ -1,33 +1,49 @@
+# Python related
 __pycache__
-botpy.log
+.mypy_cache
-.vscode
 .venv*
-.idea
+.conda/
-data_v2.db
+uv.lock
-data_v3.db
-configs/session
-configs/config.yaml
-**/.DS_Store
-temp
-cmd_config.json
-data
-cookies.json
-logs/
-addons/plugins
 .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
-venv/*
+
-packages/python_interpreter/workplace
+# Operating System
-.venv/*
+**/.DS_Store
-.conda/
+.DS_Store
-.idea
+
-pytest.ini
+# AstrBot specific
 .astrbot
+astrbot.lock
+
+# Other
+chroma
+venv/*
+pytest.ini

.pre-commit-config.yaml

@@ -6,8 +6,20 @@ ci:
   autoupdate_schedule: weekly
   autoupdate_commit_msg: ":balloon: pre-commit autoupdate"
 repos:
-  - repo: https://github.com/astral-sh/ruff-pre-commit
+- repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.2
+  # Ruff version.
-    hooks:
+  rev: v0.14.1
-      - id: ruff
+  hooks:
-      - id: ruff-format
+    # 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]

Dockerfile

@@ -4,8 +4,6 @@ WORKDIR /AstrBot
 COPY . /AstrBot/
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    nodejs \
-    npm \
     gcc \
     build-essential \
     python3-dev \
@@ -13,23 +11,21 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl-dev \
     ca-certificates \
     bash \
+    ffmpeg \
+    curl \
+    gnupg \
+    git \
     && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+RUN apt-get update && apt-get install -y curl gnupg && \
+    curl -fsSL https://deb.nodesource.com/setup_lts.x | bash - && \
+    apt-get install -y nodejs && \
 
 RUN python -m pip install uv
 RUN uv pip install -r requirements.txt --no-cache-dir --system
-RUN uv pip install socksio uv pyffmpeg pilk --no-cache-dir --system
+RUN uv pip install socksio uv pilk --no-cache-dir --system
-
-# 释出 ffmpeg
-RUN python -c "from pyffmpeg import FFmpeg; ff = FFmpeg();"
-
-# add /root/.pyffmpeg/bin/ffmpeg to PATH, inorder to use ffmpeg
-RUN echo 'export PATH=$PATH:/root/.pyffmpeg/bin' >> ~/.bashrc
 
 EXPOSE 6185
-EXPOSE 6186
-
-CMD [ "python", "main.py" ]
-
-
 
+CMD ["python", "main.py"]

Dockerfile_with_node

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

README.md

@@ -1,33 +1,40 @@
-<img width="430" height="31" alt="image" src="https://github.com/user-attachments/assets/474c822c-fab7-41be-8c23-6dae252823ed" /><p align="center">
- 
 ![AstrBot-Logo-Simplified](https://github.com/user-attachments/assets/ffd99b6b-3272-4682-beaa-6fe74250f7d9)
 
 </p>
 
 <div align="center">
 
-_✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
+<br>
 
+<div>
 <a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
+<a href="https://hellogithub.com/repository/AstrBotDevs/AstrBot" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=d127d50cd5e54c5382328acc3bb25483&claim_uid=ZO9by7qCXgSd6Lp&t=1" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
-[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot?style=for-the-badge&color=76bad9)](https://github.com/Soulter/AstrBot/releases/latest)
-<img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=for-the-badge&color=76bad9" alt="python">
-<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg?style=for-the-badge&color=76bad9"/></a>
-<a  href="https://qm.qq.com/cgi-bin/qm/qr?k=wtbaNx7EioxeaqS9z7RQWVXPIxg2zYr7&jump_from=webapi&authKey=vlqnv/AV2DbJEvGIcxdlNSpfxVy+8vVqijgreRdnVKOaydpc+YSw4MctmEbr0k5"><img alt="QQ_community" src="https://img.shields.io/badge/QQ群-775869627-purple?style=for-the-badge&color=76bad9"></a>
-<a  href="https://t.me/+hAsD2Ebl5as3NmY1"><img alt="Telegram_community" src="https://img.shields.io/badge/Telegram-AstrBot-purple?style=for-the-badge&color=76bad9"></a>
-[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e.svg?style=for-the-badge&color=76bad9)](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fstats&query=v&label=7日消息量&cacheSeconds=3600&style=for-the-badge&color=3b618e)
-![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fplugin-num&query=%24.result&suffix=%E4%B8%AA&style=for-the-badge&label=%E6%8F%92%E4%BB%B6%E5%B8%82%E5%9C%BA&cacheSeconds=3600)
-
-<a href="https://github.com/Soulter/AstrBot/blob/master/README_en.md">English</a> ｜
-<a href="https://github.com/Soulter/AstrBot/blob/master/README_ja.md">日本語</a> ｜
-<a href="https://astrbot.app/">查看文档</a> ｜
-<a href="https://github.com/Soulter/AstrBot/issues">问题提交</a>
 </div>
 
-AstrBot 是一个开源的一站式 Agentic 聊天机器人平台及开发框架。
+<br>
 
-## ✨ 主要功能
+<div>
+<img src="https://img.shields.io/github/v/release/AstrBotDevs/AstrBot?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>
+
+<br>
+
+<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>
+
+AstrBot 是一个开源的一站式 Agent 聊天机器人平台及开发框架。
+
+## 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。
@@ -35,9 +42,9 @@ AstrBot 是一个开源的一站式 Agentic 聊天机器人平台及开发框架
 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。
 
-## ✨ 使用方式
+## 部署方式
 
-#### Docker 部署
+#### Docker 部署(推荐 🥳)
 
 推荐使用 Docker / Docker Compose 方式部署 AstrBot。
 
@@ -65,7 +72,7 @@ AstrBot 已由雨云官方上架至云应用平台，可一键部署。
 
 社区贡献的部署方式。
 
-[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+[![Run on Repl.it](https://repl.it/badge/github/AstrBotDevs/AstrBot)](https://repl.it/github/AstrBotDevs/AstrBot)
 
 #### Windows 一键安装器部署
 
@@ -79,9 +86,7 @@ AstrBot 已由雨云官方上架至云应用平台，可一键部署。
 
 #### 手动部署
 
-> 推荐使用 `uv`。
+首先安装 uv：
-
-首先，安装 uv：
 
 ```bash
 pip install uv
@@ -96,53 +101,91 @@ uv run main.py
 
 或者请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html) 。
 
-## ⚡ 消息平台支持情况
+## 🌍 社区
 
-| 平台    | 支持性 |
+### QQ 群组
-| -------- | ------- |
-| QQ(官方机器人接口) | ✔    |
-| QQ(OneBot)      | ✔    |
-| Telegram   | ✔    |
-| 企业微信    | ✔    |
-| 微信客服    | ✔    |
-| 微信公众号    | ✔    |
-| 飞书   | ✔    |
-| 钉钉   | ✔    |
-| Slack   | ✔    |
-| Discord   | ✔    |
-| [KOOK](https://github.com/wuyan1003/astrbot_plugin_kook_adapter)   | ✔    |
-| [VoceChat](https://github.com/HikariFroya/astrbot_plugin_vocechat)   | ✔    |
-| 微信对话开放平台 | 🚧    |
-| WhatsApp   | 🚧    |
-| 小爱音响   | 🚧    |
 
-## ⚡ 提供商支持情况
+- 1 群：322154837
+- 3 群：630166526
+- 5 群：822130018
+- 6 群：753075035
+- 开发者群：975206796
 
-| 名称    | 支持性 | 类型 | 备注 |
+### Telegram 群组
-| -------- | ------- | ------- | ------- |
-| OpenAI API | ✔    | 文本生成 | 也支持 DeepSeek、Gemini、Kimi、xAI 等兼容 OpenAI API 的服务 |
-| Claude API | ✔    | 文本生成 |  |
-| Google Gemini API | ✔    | 文本生成 |  |
-| Dify | ✔    | LLMOps |  |
-| 阿里云百炼应用 | ✔    | LLMOps |  |
-| Ollama | ✔    | 模型加载器 | 本地部署 DeepSeek、Llama 等开源语言模型 |
-| LM Studio | ✔    | 模型加载器 | 本地部署 DeepSeek、Llama 等开源语言模型 |
-| LLMTuner | ✔    | 模型加载器 | 本地加载 lora 等微调模型 |
-| [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74) | ✔    | 模型 API 及算力服务平台 |  |
-| [302.AI](https://share.302.ai/rr1M3l) | ✔    | 模型 API 服务平台 |  |
-| 硅基流动 | ✔    | 模型 API 服务平台 |  |
-| PPIO 派欧云 | ✔    | 模型 API 服务平台 |  |
-| OneAPI | ✔    | LLM 分发系统 |  |
-| Whisper | ✔    | 语音转文本 | 支持 API、本地部署 |
-| SenseVoice | ✔    | 语音转文本 | 本地部署 |
-| OpenAI TTS API | ✔    | 文本转语音 |  |
-| GSVI | ✔    | 文本转语音 | GPT-Sovits-Inference |
-| GPT-SoVITs | ✔    | 文本转语音 | GPT-Sovits-Inference |
-| FishAudio | ✔    | 文本转语音 | GPT-Sovits 作者参与的项目 |
-| Edge TTS | ✔    | 文本转语音 | Edge 浏览器的免费 TTS |
-| 阿里云百炼 TTS | ✔    | 文本转语音 |  |
-| Azure TTS | ✔    | 文本转语音 | Microsoft Azure TTS |
 
+<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>
+
+## 支持的消息平台
+
+**官方维护**
+
+- QQ (官方平台 & OneBot)
+- Telegram
+- 企微应用 & 企微智能机器人
+- 微信客服 & 微信公众号
+- 飞书
+- 钉钉
+- Slack
+- Discord
+- Satori
+- Misskey
+- Whatsapp (将支持)
+- LINE (将支持)
+
+**社区维护**
+
+- [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)
+
+## 支持的模型服务
+
+**大模型服务**
+
+- OpenAI 及兼容服务
+- Anthropic
+- Google Gemini
+- Moonshot AI
+- 智谱 AI
+- DeepSeek
+- Ollama (本地部署)
+- LM Studio (本地部署)
+- [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_astrbot&referral_code=FV7DcGowN4hB5UuXKgpE74)
+- [302.AI](https://share.302.ai/rr1M3l)
+- [小马算力](https://www.tokenpony.cn/3YPyf)
+- [硅基流动](https://docs.siliconflow.cn/cn/usercases/use-siliconcloud-in-astrbot)
+- [PPIO 派欧云](https://ppio.com/user/register?invited_by=AIOONE)
+- ModelScope
+- OneAPI
+
+**LLMOps 平台**
+
+- Dify
+- 阿里云百炼应用
+- Coze
+
+**语音转文本服务**
+
+- OpenAI Whisper
+- SenseVoice
+
+**文本转语音服务**
+
+- OpenAI TTS
+- Gemini TTS
+- GPT-Sovits-Inference
+- GPT-Sovits
+- FishAudio
+- Edge TTS
+- 阿里云百炼 TTS
+- Azure TTS
+- Minimax TTS
+- 火山引擎 TTS
 
 ## ❤️ 贡献
 
@@ -157,44 +200,11 @@ uv run main.py
 AstrBot 使用 `ruff` 进行代码格式化和检查。
 
 ```bash
-git clone https://github.com/Soulter/AstrBot
+git clone https://github.com/AstrBotDevs/AstrBot
 pip install pre-commit
 pre-commit install
 ```
 
-## 🌟 支持
-
-- Star 这个项目！
-- 在[爱发电](https://afdian.com/a/soulter)支持我！
-
-## ✨ Demo
-
-<details><summary>👉 点击展开多张 Demo 截图 👈</summary>
-
-<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）✨_
-
-<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
-
-_✨ 多模态、网页搜索、长文本转图片（可配置） ✨_
-
-<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
-<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
-
-_✨ 插件系统——部分插件展示 ✨_
-
-<img src="https://github.com/user-attachments/assets/0cdbf564-2f59-4da5-b524-ce0e7ef3d978" width=600>
-
-_✨ WebUI ✨_
-
-</div>
-
-</details>
-
-
 ## ❤️ Special Thanks
 
 特别感谢所有 Contributors 和插件开发者对 AstrBot 的贡献 ❤️
@@ -203,24 +213,21 @@ _✨ WebUI ✨_
   <img src="https://contrib.rocks/image?repo=AstrBotDevs/AstrBot" />
 </a>
 
-此外，本项目的诞生离不开以下开源项目：
+此外，本项目的诞生离不开以下开源项目的帮助：
 
 - [NapNeko/NapCatQQ](https://github.com/NapNeko/NapCatQQ) - 伟大的猫猫框架
-- [wechatpy/wechatpy](https://github.com/wechatpy/wechatpy)
 
 ## ⭐ Star History
 
 > [!TIP]
-> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我维护这个开源项目的动力 <3
+> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我们维护这个开源项目的动力 <3
 
 <div align="center">
 
-[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=astrbotdevs/astrbot&type=Date)](https://star-history.com/#astrbotdevs/astrbot&Date)
 
 </div>
 
-![10k-star-banner-credit-by-kevin](https://github.com/user-attachments/assets/c97fc5fb-20b9-4bc8-9998-c20b930ab097)
+</details>
-
 
 _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.
@@ -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        |
+| [Telegram](https://github.com/AstrBotDevs/AstrBot_plugin_telegram) | ✔      | Private/Group chats | Text, Images        |
-| [WeChat Work](https://github.com/Soulter/astrbot_plugin_wecom) | ✔      | Private chats       | Text, Images, Voice |
+| [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。
@@ -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
 

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 html_renderer, sp
-from astrbot.core import 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",
+    "AstrMessageEvent",
-    "MessageChain",
     "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",
+    "event_message_type",
-    "on_astrbot_loaded",
-    "on_llm_request",
     "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

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

astrbot/api/provider/__init__.py

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

astrbot/api/star/__init__.py

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

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/__main__.py

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

astrbot/cli/commands/__init__.py

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

astrbot/cli/commands/cmd_conf.py

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

astrbot/cli/commands/cmd_init.py

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

astrbot/cli/commands/cmd_plug.py

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

astrbot/cli/commands/cmd_run.py

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

astrbot/cli/utils/__init__.py

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

astrbot/cli/utils/basic.py

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

astrbot/cli/utils/plugin.py

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

astrbot/cli/utils/version_comparator.py

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

astrbot/core/__init__.py

@@ -1,13 +1,14 @@
 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
+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
@@ -21,7 +22,7 @@ html_renderer = HtmlRenderer(t2i_base_url)
 logger = LogManager.GetLogger(log_name="astrbot")
 db_helper = SQLiteDatabase(DB_PATH)
 # 简单的偏好设置存储, 这里后续应该存储到数据库中, 一些部分可以存储到配置中
-sp = SharedPreferences()
+sp = SharedPreferences(db_helper=db_helper)
 # 文件令牌服务
 file_token_service = FileTokenService()
 pip_installer = PipInstaller(

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 +1,12 @@
-import os
+import enum
 import json
 import logging
-import enum
+import os
-from .default import DEFAULT_CONFIG, DEFAULT_VALUE_MAP
+
-from typing import Dict
 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")
 
@@ -27,7 +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__()
 
@@ -45,7 +46,7 @@ class AstrBotConfig(dict):
                 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()
             conf = json.loads(conf_str)
 
@@ -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"]
@@ -82,7 +83,7 @@ class AstrBotConfig(dict):
 
         return conf
 
-    def check_config_integrity(self, refer_conf: Dict, conf: Dict, path=""):
+    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
 
@@ -97,27 +98,28 @@ class AstrBotConfig(dict):
                 logger.info(f"检查到配置项 {path_} 不存在，已插入默认值 {value}")
                 new_conf[key] = value
                 has_new = True
-            else:
+            elif conf[key] is None:
-                if conf[key] is None:
+                # 配置项为 None，使用默认值
-                    # 配置项为 None，使用默认值
+                new_conf[key] = value
+                has_new = True
+            elif isinstance(value, dict):
+                # 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
-                elif isinstance(value, dict):
-                    # 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
+                    # 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()):
@@ -140,7 +142,7 @@ class AstrBotConfig(dict):
 
         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

@@ -1,56 +1,109 @@
-"""
+"""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.
-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 uuid
 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):
-        # session_conversations 字典记录会话ID-对话ID 映射关系
+        self.session_conversations: dict[str, str] = {}
-        self.session_conversations: Dict[str, str] = sp.get("session_conversation", {})
         self.db = db_helper
         self.save_interval = 60  # 每 60 秒保存一次
-        self._start_periodic_save()
 
-    def _start_periodic_save(self):
+        # 会话删除回调函数列表（用于级联清理，如知识库配置）
-        """启动定时保存任务"""
+        self._on_session_deleted_callbacks: list[Callable[[str], Awaitable[None]]] = []
-        asyncio.create_task(self._periodic_save())
 
-    async def _periodic_save(self):
+    def register_on_session_deleted(
-        """定时保存会话对话映射关系到存储中"""
+        self,
-        while True:
+        callback: Callable[[str], Awaitable[None]],
-            await asyncio.sleep(self.save_interval)
+    ) -> None:
-            self._save_to_storage()
+        """注册会话删除回调函数.
 
-    def _save_to_storage(self):
+        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。
-        """保存会话对话映射关系到存储中"""
+        例如：知识库模块可以注册回调来清理会话的知识库配置。
-        sp.put("session_conversation", self.session_conversations)
 
-    async def new_conversation(self, unified_msg_origin: str) -> str:
+        Args:
-        """新建对话，并将当前会话的对话转移到新对话
+            callback: 回调函数，接收会话ID (unified_msg_origin) 作为参数
+
+        """
+        self._on_session_deleted_callbacks.append(callback)
+
+    async def _trigger_session_deleted(self, unified_msg_origin: str) -> None:
+        """触发会话删除回调.
+
+        Args:
+            unified_msg_origin: 会话ID
+
+        """
+        for callback in self._on_session_deleted_callbacks:
+            try:
+                await callback(unified_msg_origin)
+            except Exception as e:
+                from astrbot.core import logger
+
+                logger.error(
+                    f"会话删除回调执行失败 (session: {unified_msg_origin}): {e}",
+                )
+
+    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
+
         """
-        conversation_id = str(uuid.uuid4())
+        if not platform_id:
-        self.db.new_conversation(user_id=unified_msg_origin, cid=conversation_id)
+            # 如果没有提供 platform_id，则从 unified_msg_origin 中解析
-        self.session_conversations[unified_msg_origin] = conversation_id
+            parts = unified_msg_origin.split(":")
-        sp.put("session_conversation", self.session_conversations)
+            if len(parts) >= 3:
-        return conversation_id
+                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
@@ -58,147 +111,294 @@ class ConversationManager:
         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
-        sp.put("session_conversation", self.session_conversations)
+        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
+        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
-        """
-        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 get_curr_conversation_id(self, unified_msg_origin: str) -> str:
+        """
+        if not conversation_id:
+            conversation_id = self.session_conversations.get(unified_msg_origin)
+        if conversation_id:
+            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
+
         """
-        return self.session_conversations.get(unified_msg_origin, None)
+        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:
+    ) -> Conversation | None:
-        """获取会话的对话
+        """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 = self.db.get_conversation_by_user_id(unified_msg_origin, conversation_id)
+        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)
-            return self.db.get_conversation_by_user_id(
+            conv = await self.db.get_conversation_by_id(cid=conversation_id)
-                unified_msg_origin, conversation_id
+        conv_res = None
-            )
+        if conv:
-        return self.db.get_conversation_by_user_id(unified_msg_origin, conversation_id)
+            conv_res = self._convert_conv_from_v2_to_v1(conv)
+        return conv_res
 
-    async def get_conversations(self, unified_msg_origin: str) -> List[Conversation]:
+    async def get_conversations(
-        """获取会话的所有对话
+        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
+            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
+
         """
-        return self.db.get_conversations(unified_msg_origin)
+        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, history: List[Dict]
+        self,
-    ):
+        unified_msg_origin: str,
-        """更新会话的对话
+        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:
-            self.db.update_conversation(
+            await self.db.update_conversation(
-                user_id=unified_msg_origin,
                 cid=conversation_id,
-                history=json.dumps(history),
+                title=title,
+                persona_id=persona_id,
+                content=history,
             )
 
-    async def update_conversation_title(self, unified_msg_origin: str, title: str):
+    async def update_conversation_title(
-        """更新会话的对话标题
+        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.
+
         """
-        conversation_id = self.session_conversations.get(unified_msg_origin)
+        await self.update_conversation(
-        if conversation_id:
+            unified_msg_origin=unified_msg_origin,
-            self.db.update_conversation_title(
+            conversation_id=conversation_id,
-                user_id=unified_msg_origin, cid=conversation_id, title=title
+            title=title,
-            )
+        )
 
     async def update_conversation_persona_id(
-        self, unified_msg_origin: str, persona_id: str
+        self,
-    ):
+        unified_msg_origin: str,
-        """更新会话的对话 Persona ID
+        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.
+
         """
-        conversation_id = self.session_conversations.get(unified_msg_origin)
+        await self.update_conversation(
-        if conversation_id:
+            unified_msg_origin=unified_msg_origin,
-            self.db.update_conversation_persona_id(
+            conversation_id=conversation_id,
-                user_id=unified_msg_origin, cid=conversation_id, persona_id=persona_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,
-        """获取人类可读的上下文
+        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 = []
+        # contexts_groups 存放按顺序的段落（每个段落是一个 str 列表），
-        temp_contexts = []
+        # 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 "content" in record and record["content"]:
+                if record.get("content"):
                     temp_contexts.append(f"Assistant: {record['content']}")
                 elif "tool_calls" in record:
                     tool_calls_str = json.dumps(
-                        record["tool_calls"], ensure_ascii=False
+                        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.insert(0, temp_contexts)
+                contexts_groups.insert(0, temp_contexts)
                 temp_contexts = []
 
-        # 展平 contexts 列表
+        # 展平分组后的 contexts 列表为单层字符串列表
-        contexts = [item for sublist in contexts for item in sublist]
+        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

@@ -1,5 +1,5 @@
-"""
+"""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.
-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。
 
@@ -9,39 +9,44 @@ Astrbot 核心生命周期管理类, 负责管理 AstrBot 的启动、停止、
 3. 执行启动完成事件钩子
 """
 
-import traceback
 import asyncio
-import time
-import threading
 import os
-from .event_bus import EventBus
+import threading
-from . import astrbot_config
+import time
+import traceback
 from asyncio import Queue
-from typing import List
+
-from astrbot.core.pipeline.scheduler import PipelineScheduler, PipelineContext
+from astrbot.core import LogBroker, logger, sp
-from astrbot.core.star import PluginManager
+from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
-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.config.default import VERSION
 from astrbot.core.conversation_mgr import ConversationManager
-from astrbot.core.star.star_handler import star_handlers_registry, EventType
+from astrbot.core.db import BaseDatabase
-from astrbot.core.star.star_handler import star_map
+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:
-    """
+    """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.
-    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。
     """
 
-    def __init__(self, log_broker: LogBroker, db: BaseDatabase):
+    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
@@ -65,11 +70,11 @@ class AstrBotCoreLifecycle:
                 del os.environ["no_proxy"]
             logger.debug("HTTP proxy cleared")
 
-    async def initialize(self):
+    async def initialize(self) -> None:
-        """
+        """初始化 AstrBot 核心生命周期管理类.
-        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。
-        """
 
+        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", ""):
@@ -77,11 +82,40 @@ class AstrBotCoreLifecycle:
         else:
             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()
 
+        # 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, self.db)
+        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)
@@ -89,6 +123,12 @@ class AstrBotCoreLifecycle:
         # 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,
@@ -97,6 +137,10 @@ class AstrBotCoreLifecycle:
             self.provider_manager,
             self.platform_manager,
             self.conversation_manager,
+            self.platform_message_history_manager,
+            self.persona_mgr,
+            self.astrbot_config_mgr,
+            self.kb_manager,
         )
 
         # 初始化插件管理器
@@ -108,23 +152,26 @@ class AstrBotCoreLifecycle:
         # 根据配置实例化各个 Provider
         await self.provider_manager.initialize()
 
+        await self.kb_manager.initialize()
+
         # 初始化消息事件流水线调度器
-        self.pipeline_scheduler = PipelineScheduler(
+        self.pipeline_scheduler_mapping = await self.load_pipeline_scheduler()
-            PipelineContext(self.astrbot_config, self.plugin_manager)
-        )
-        await self.pipeline_scheduler.initialize()
 
         # 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)
+        self.event_bus = EventBus(
+            self.event_queue,
+            self.pipeline_scheduler_mapping,
+            self.astrbot_config_mgr,
+        )
 
         # 记录启动时间
         self.start_time = int(time.time())
 
         # 初始化当前任务列表
-        self.curr_tasks: List[asyncio.Task] = []
+        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()
@@ -132,13 +179,13 @@ class AstrBotCoreLifecycle:
         # 初始化关闭控制面板的事件
         self.dashboard_shutdown_event = asyncio.Event()
 
-    def _load(self):
+    def _load(self) -> None:
-        """加载事件总线和任务并初始化"""
+        """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
@@ -149,16 +196,17 @@ 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
+        """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
@@ -171,19 +219,22 @@ class AstrBotCoreLifecycle:
                 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"""
+        """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:
@@ -192,8 +243,8 @@ class AstrBotCoreLifecycle:
         # 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):
+    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"""
+        """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()
@@ -204,11 +255,12 @@ class AstrBotCoreLifecycle:
             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。"
+                    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
@@ -220,21 +272,59 @@ class AstrBotCoreLifecycle:
             except Exception as e:
                 logger.error(f"任务 {task.get_name()} 发生错误: {e}")
 
-    async def restart(self):
+    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

@@ -1,161 +1,315 @@
 import abc
+import datetime
+import typing as T
+from contextlib import asynccontextmanager
 from dataclasses import dataclass
-from typing import List, Dict, Any, Tuple
+
-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):
+    async def initialize(self):
-        """插入基础指标数据"""
+        """初始化数据库连接"""
-        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"])
 
-    @abc.abstractmethod
+    @asynccontextmanager
-    def insert_platform_metrics(self, metrics: dict):
+    async def get_db(self) -> T.AsyncGenerator[AsyncSession, None]:
-        """插入平台指标数据"""
+        """Get a database session."""
-        raise NotImplementedError
+        if not self.inited:
-
+            await self.initialize()
-    @abc.abstractmethod
+            self.inited = True
-    def insert_plugin_metrics(self, metrics: dict):
+        async with self.AsyncSessionLocal() as session:
-        """插入插件指标数据"""
+            yield session
-        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
 
+    @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
+    # New methods in v4.0.0
-    def insert_atri_vision_data(self, vision_data: ATRIVision):
-        """插入 ATRI 视觉数据"""
-        raise NotImplementedError
 
     @abc.abstractmethod
-    def get_atri_vision_data(self) -> List[ATRIVision]:
+    async def insert_platform_stats(
-        """获取 ATRI 视觉数据"""
+        self,
-        raise NotImplementedError
+        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(
+    async def count_platform_stats(self) -> int:
-        self, url_or_path: str, id: str
+        """Count the number of platform statistics records."""
-    ) -> ATRIVision:
+        ...
-        """通过 url 或 path 获取 ATRI 视觉数据"""
-        raise NotImplementedError
 
     @abc.abstractmethod
-    def get_conversation_by_user_id(self, user_id: str, cid: str) -> Conversation:
+    async def get_platform_stats(self, offset_sec: int = 86400) -> list[PlatformStat]:
-        """通过 user_id 和 cid 获取 Conversation"""
+        """Get platform statistics within the specified offset in seconds and group by platform_id."""
-        raise NotImplementedError
+        ...
 
     @abc.abstractmethod
-    def new_conversation(self, user_id: str, cid: str):
+    async def get_conversations(
-        """新建 Conversation"""
+        self,
-        raise NotImplementedError
+        user_id: str | None = None,
+        platform_id: str | None = None,
+    ) -> list[ConversationV2]:
+        """Get all conversations for a specific user and platform_id(optional).
 
-    @abc.abstractmethod
+        content is not included in the result.
-    def get_conversations(self, user_id: str) -> List[Conversation]:
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def update_conversation(self, user_id: str, cid: str, history: str):
-        """更新 Conversation"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def delete_conversation(self, user_id: str, cid: str):
-        """删除 Conversation"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def update_conversation_title(self, user_id: str, cid: str, title: str):
-        """更新 Conversation 标题"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    def update_conversation_persona_id(self, user_id: str, cid: str, persona_id: str):
-        """更新 Conversation Persona ID"""
-        raise NotImplementedError
-
-    @abc.abstractmethod
-    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
-
-        Args:
-            page: 页码，从1开始
-            page_size: 每页数量
-
-        Returns:
-            Tuple[List[Dict[str, Any]], int]: 返回一个元组，包含对话列表和总对话数
         """
-        raise NotImplementedError
+        ...
 
     @abc.abstractmethod
-    def get_filtered_conversations(
+    async def get_conversation_by_id(self, cid: str) -> ConversationV2:
+        """Get a specific conversation by its ID."""
+        ...
+
+    @abc.abstractmethod
+    async def get_all_conversations(
         self,
         page: int = 1,
         page_size: int = 20,
-        platforms: List[str] = None,
+    ) -> list[ConversationV2]:
-        message_types: List[str] = None,
+        """Get all conversations with pagination."""
-        search_query: str = None,
+        ...
-        exclude_ids: List[str] = None,
-        exclude_platforms: List[str] = None,
-    ) -> Tuple[List[Dict[str, Any]], int]:
-        """获取筛选后的对话列表
 
-        Args:
+    @abc.abstractmethod
-            page: 页码
+    async def get_filtered_conversations(
-            page_size: 每页数量
+        self,
-            platforms: 平台筛选列表
+        page: int = 1,
-            message_types: 消息类型筛选列表
+        page_size: int = 20,
-            search_query: 搜索关键词
+        platform_ids: list[str] | None = None,
-            exclude_ids: 排除的用户ID列表
+        search_query: str = "",
-            exclude_platforms: 排除的平台列表
+        **kwargs,
+    ) -> tuple[list[ConversationV2], int]:
+        """Get conversations filtered by platform IDs and search query."""
+        ...
 
-        Returns:
+    @abc.abstractmethod
-            Tuple[List[Dict[str, Any]], int]: 返回一个元组，包含对话列表和总对话数
+    async def create_conversation(
-        """
+        self,
-        raise NotImplementedError
+        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
+    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

@@ -1,7 +1,246 @@
-"""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
@@ -13,77 +252,6 @@ class Platform:
     timestamp: int
 
 
-@dataclass
-class Provider:
-    """供应商使用统计数据"""
-
-    name: str
-    count: int
-    timestamp: int
-
-
-@dataclass
-class Plugin:
-    """插件使用统计数据"""
-
-    name: str
-    count: int
-    timestamp: int
-
-
-@dataclass
-class Command:
-    """命令使用统计数据"""
-
-    name: str
-    count: int
-    timestamp: int
-
-
 @dataclass
 class Stats:
-    platform: List[Platform] = field(default_factory=list)
+    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 = ""

astrbot/core/db/sqlite_init.sql

@@ -1,50 +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, -- 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';

astrbot/core/db/vec_db/base.py

@@ -10,22 +10,47 @@ class Result:
 
 class BaseVecDB:
     async def initialize(self):
-        """
+        """初始化向量数据库"""
-        初始化向量数据库
-        """
-        pass
 
     @abc.abstractmethod
-    async def insert(self, content: str, metadata: dict = None, id: str = None) -> int:
+    async def insert(
-        """
+        self,
-        插入一条文本和其对应向量，自动生成 ID 并保持一致性。
+        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) -> list[Result]:
+    async def retrieve(
-        """
+        self,
-        搜索最相似的文档。
+        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
@@ -36,11 +61,13 @@ class BaseVecDB:
 
     @abc.abstractmethod
     async def delete(self, doc_id: str) -> bool:
-        """
+        """删除指定文档。
-        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/document_storage.py

@@ -1,59 +1,232 @@
-import aiosqlite
+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.connection = None
+        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"
+            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."""
-        if not os.path.exists(self.db_path):
+        await self.connect()
-            await self.connect()
+        async with self.engine.begin() as conn:  # type: ignore
-            async with self.connection.cursor() as cursor:
+            # Create tables using SQLModel
-                with open(self.sqlite_init_path, "r", encoding="utf-8") as f:
+            await conn.run_sync(BaseDocModel.metadata.create_all)
-                    sql_script = f.read()
+
-                await cursor.executescript(sql_script)
+            try:
-            await self.connection.commit()
+                await conn.execute(
-        else:
+                    text(
-            await self.connect()
+                        "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."""
-        self.connection = await aiosqlite.connect(self.db_path)
+        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
 
-    async def get_documents(self, metadata_filters: dict, ids: list = None):
+    @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 document IDs(primary key, not doc_id) that match the filters.
+            list: The list of documents that match the filters.
-        """
-        # metadata filter -> SQL WHERE clause
-        where_clauses = []
-        values = []
-        for key, val in metadata_filters.items():
-            where_clauses.append(f"json_extract(metadata, '$.{key}') = ?")
-            values.append(val)
-        if ids is not None and len(ids) > 0:
-            ids = [str(i) for i in ids if i != -1]
-            where_clauses.append("id IN ({})".format(",".join("?" * len(ids))))
-            values.extend(ids)
-        where_sql = " AND ".join(where_clauses) or "1=1"
 
-        result = []
+        """
-        async with self.connection.cursor() as cursor:
+        if self.engine is None:
-            sql = "SELECT * FROM documents WHERE " + where_sql
+            logger.warning(
-            await cursor.execute(sql, values)
+                "Database connection is not initialized, returning empty result",
-            for row in await cursor.fetchall():
+            )
-                result.append(await self.tuple_to_dict(row))
+            return []
-        return result
+
+        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.
@@ -62,40 +235,134 @@ class DocumentStorage:
             doc_id (str): The doc_id of the document to retrieve.
 
         Returns:
-            dict: The document data.
+            dict: The document data or None if not found.
+
         """
-        async with self.connection.cursor() as cursor:
+        assert self.engine is not None, "Database connection is not initialized."
-            await cursor.execute("SELECT * FROM documents WHERE doc_id = ?", (doc_id,))
+
-            row = await cursor.fetchone()
+        async with self.get_session() as session:
-            if row:
+            query = select(Document).where(col(Document.doc_id) == doc_id)
-                return await self.tuple_to_dict(row)
+            result = await session.execute(query)
-            else:
+            document = result.scalar_one_or_none()
-                return 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):
-        """Retrieve a document by its doc_id.
+        """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.
+
         """
-        async with self.connection.cursor() as cursor:
+        assert self.engine is not None, "Database connection is not initialized."
-            await cursor.execute(
+
-                "UPDATE documents SET text = ? WHERE doc_id = ?", (new_text, doc_id)
+        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",
             )
-            await self.connection.commit()
+            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.
+
         """
-        async with self.connection.cursor() as cursor:
+        assert self.engine is not None, "Database connection is not initialized."
-            await cursor.execute("SELECT DISTINCT user_id FROM documents")
+
-            rows = await cursor.fetchall()
+        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.
 
@@ -104,6 +371,9 @@ class DocumentStorage:
 
         Returns:
             dict: The converted dictionary.
+
+        Note: This method is kept for backward compatibility but is no longer used internally.
+
         """
         return {
             "id": row[0],
@@ -116,6 +386,7 @@ class DocumentStorage:
 
     async def close(self):
         """Close the connection to the SQLite database."""
-        if self.connection:
+        if self.engine:
-            await self.connection.close()
+            await self.engine.dispose()
-            self.connection = None
+            self.engine = None
+            self.async_session_maker = None

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

@@ -2,14 +2,15 @@ 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。"
+        "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):
+    def __init__(self, dimension: int, path: str | None = None):
         self.dimension = dimension
         self.path = path
         self.index = None
@@ -18,7 +19,6 @@ class EmbeddingStorage:
         else:
             base_index = faiss.IndexFlatL2(dimension)
             self.index = faiss.IndexIDMap(base_index)
-        self.storage = {}
 
     async def insert(self, vector: np.ndarray, id: int):
         """插入向量
@@ -28,13 +28,32 @@ class EmbeddingStorage:
             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]}"
+                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]))
-        self.storage[id] = vector
+        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:
@@ -45,15 +64,30 @@ class EmbeddingStorage:
             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/vec_db.py

@@ -1,89 +1,143 @@
+import time
 import uuid
-import json
+
 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
-from ..base import Result, BaseVecDB
-from astrbot.core.provider.provider import EmbeddingProvider
 
 
 class FaissVecDB(BaseVecDB):
-    """
+    """A class to represent a vector database."""
-    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
+            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, id: str = None) -> int:
+    async def insert(
-        """
+        self,
-        插入一条文本和其对应向量，自动生成 ID 并保持一致性。
+        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)
-        async with self.document_storage.connection.cursor() as cursor:
-            await cursor.execute(
-                "INSERT INTO documents (doc_id, text, metadata) VALUES (?, ?, ?)",
-                (str_id, content, json.dumps(metadata)),
-            )
-            await self.document_storage.connection.commit()
-            result = await self.document_storage.get_document_by_doc_id(str_id)
-            int_id = result["id"]
 
-            # 插入向量到 FAISS
+        # 使用 DocumentStorage 的方法插入文档
-            await self.embedding_storage.insert(vector, int_id)
+        int_id = await self.document_storage.insert_document(str_id, content, metadata)
-            return int_id
+
+        # 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, metadata_filters: dict = None
+        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。
-        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,
         )
-        # TODO: rerank
         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]
+            metadata_filters=metadata_filters or {},
+            ids=indices[0],
         )
         if not fetched_docs:
             return []
-        result_docs = []
+        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]):
@@ -93,25 +147,58 @@ class FaissVecDB(BaseVecDB):
             fetch_doc = fetched_docs[pos]
             score = scores[0][i]
             result_docs.append(Result(similarity=float(score), data=fetch_doc))
-        return result_docs[:k]
 
-    async def delete(self, doc_id: int):
+        top_k_results = result_docs[:k]
-        """
+
-        删除一条文档
+        if rerank and self.rerank_provider:
-        """
+            documents = [doc.data["text"] for doc in top_k_results]
-        await self.document_storage.connection.execute(
+            reranked_results = await self.rerank_provider.rerank(query, documents)
-            "DELETE FROM documents WHERE doc_id = ?", (doc_id,)
+            reranked_results = sorted(
-        )
+                reranked_results,
-        await self.document_storage.connection.commit()
+                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) -> int:
+    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
+
         """
-        计算文档数量
+        count = await self.document_storage.count_documents(
-        """
+            metadata_filters=metadata_filter or {},
-        async with self.document_storage.connection.cursor() as cursor:
+        )
-            await cursor.execute("SELECT COUNT(*) FROM documents")
+        return count
-            count = await cursor.fetchone()
+
-            return count[0] if count else 0
+    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

@@ -1,5 +1,4 @@
-"""
+"""事件总线, 用于处理事件的分发和处理
-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
 
@@ -13,45 +12,50 @@ class:
 
 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:
-    """事件总线: 用于处理事件的分发和处理
+    """用于处理事件的分发和处理"""
 
-    维护一个异步队列, 来接受各种消息事件
+    def __init__(
-    """
+        self,
-
+        event_queue: Queue,
-    def __init__(self, event_queue: Queue, pipeline_scheduler: PipelineScheduler):
+        pipeline_scheduler_mapping: dict[str, PipelineScheduler],
+        astrbot_config_mgr: AstrBotConfigManager = None,
+    ):
         self.event_queue = event_queue  # 事件队列
-        self.pipeline_scheduler = pipeline_scheduler  # 管道调度器
+        # abconf uuid -> scheduler
+        self.pipeline_scheduler_mapping = pipeline_scheduler_mapping
+        self.astrbot_config_mgr = astrbot_config_mgr
 
     async def dispatch(self):
-        """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"""
         while True:
-            event: AstrMessageEvent = (
+            event: AstrMessageEvent = await self.event_queue.get()
-                await self.event_queue.get()
+            conf_info = self.astrbot_config_mgr.get_conf_info(event.unified_msg_origin)
-            )  # 从事件队列中获取新的事件
+            self._print_event(event, conf_info["name"])
-            self._print_event(event)  # 打印日志
+            scheduler = self.pipeline_scheduler_mapping.get(conf_info["id"])
-            asyncio.create_task(
+            asyncio.create_task(scheduler.execute(event))
-                self.pipeline_scheduler.execute(event)
-            )  # 创建新的异步任务来执行管道调度器的处理逻辑
 
-    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

@@ -1,9 +1,9 @@
 import asyncio
 import os
-import uuid
-import time
-from urllib.parse import urlparse, unquote
 import platform
+import time
+import uuid
+from urllib.parse import unquote, urlparse
 
 
 class FileTokenService:
@@ -23,7 +23,12 @@ class FileTokenService:
         for token in expired_tokens:
             self.staged_files.pop(token, None)
 
-    async def register_file(self, file_path: str, timeout: float = None) -> str:
+    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:
@@ -35,8 +40,8 @@ class FileTokenService:
 
         Raises:
             FileNotFoundError: 当路径不存在时抛出
-        """
 
+        """
         # 处理 file:///
         try:
             parsed_uri = urlparse(file_path)
@@ -56,7 +61,7 @@ class FileTokenService:
 
             if not os.path.exists(local_path):
                 raise FileNotFoundError(
-                    f"文件不存在: {local_path} (原始输入: {file_path})"
+                    f"文件不存在: {local_path} (原始输入: {file_path})",
                 )
 
             file_token = str(uuid.uuid4())
@@ -79,6 +84,7 @@ class FileTokenService:
         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()

astrbot/core/initial_loader.py

@@ -1,5 +1,4 @@
-"""
+"""AstrBot 启动器，负责初始化和启动核心组件和仪表板服务器。
-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
@@ -8,10 +7,10 @@ AstrBot 启动器，负责初始化和启动核心组件和仪表板服务器。
 
 import asyncio
 import traceback
-from astrbot.core import logger
+
+from astrbot.core import LogBroker, logger
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.db import BaseDatabase
-from astrbot.core import LogBroker
 from astrbot.dashboard.server import AstrBotDashboard
 
 
@@ -22,6 +21,7 @@ class InitialLoader:
         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)
@@ -35,13 +35,21 @@ class InitialLoader:
 
         core_task = core_lifecycle.start()
 
-        self.dashboard_server = AstrBotDashboard(
+        webui_dir = self.webui_dir
-            core_lifecycle, self.db, core_lifecycle.dashboard_shutdown_event
-        )
-        task = asyncio.gather(
-            core_task, self.dashboard_server.run()
-        )  # 启动核心任务和仪表板服务器
 
+        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:

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

@@ -1,5 +1,4 @@
-"""
+"""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
-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
@@ -21,14 +20,14 @@ function:
 4. 订阅者可以使用 register() 方法注册到 LogBroker, 订阅日志流
 """
 
-import logging
-import colorlog
 import asyncio
+import logging
 import os
 import sys
-from collections import deque
 from asyncio import Queue
-from typing import List
+from collections import deque
+
+import colorlog
 
 # 日志缓存大小
 CACHED_SIZE = 200
@@ -52,6 +51,7 @@ def is_plugin_path(pathname):
 
     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
@@ -68,6 +68,7 @@ def get_short_level_name(level_name):
 
     Returns:
         str: 四个字母的日志级别缩写
+
     """
     level_map = {
         "DEBUG": "DBUG",
@@ -87,13 +88,14 @@ class LogBroker:
 
     def __init__(self):
         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
+        self.subscribers: list[Queue] = []  # 订阅者列表
 
     def register(self) -> Queue:
         """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)
         self.subscribers.append(q)
@@ -104,6 +106,7 @@ class LogBroker:
 
         Args:
             q (Queue): 需要取消订阅的队列
+
         """
         self.subscribers.remove(q)
 
@@ -113,6 +116,7 @@ class LogBroker:
         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:
@@ -138,6 +142,7 @@ class LogQueueHandler(logging.Handler):
 
         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(
@@ -145,7 +150,7 @@ class LogQueueHandler(logging.Handler):
                 "level": record.levelname,
                 "time": record.asctime,
                 "data": log_entry,
-            }
+            },
         )
 
 
@@ -164,6 +169,7 @@ class LogManager:
 
         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
@@ -171,10 +177,10 @@ class LogManager:
             return logger
         # 如果logger没有处理器
         console_handler = logging.StreamHandler(
-            sys.stdout
+            sys.stdout,
         )  # 创建一个StreamHandler用于控制台输出
         console_handler.setLevel(
-            logging.DEBUG
+            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
@@ -195,7 +201,8 @@ class LogManager:
 
         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"""
+            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):
@@ -231,6 +238,7 @@ class LogManager:
         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)
@@ -240,7 +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
 
@@ -26,7 +25,6 @@ import asyncio
 import base64
 import json
 import os
-import typing as T
 import uuid
 from enum import Enum
 
@@ -37,61 +35,37 @@ 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):
+class ComponentType(str, Enum):
-    Plain = "Plain"  # 纯文本消息
+    # Basic Segment Types
-    Face = "Face"  # QQ表情
+    Plain = "Plain"  # plain text message
-    Record = "Record"  # 语音
+    Image = "Image"  # image
-    Video = "Video"  # 视频
+    Record = "Record"  # audio
-    At = "At"  # At
+    Video = "Video"  # video
-    Node = "Node"  # 转发消息的一个节点
+    File = "File"  # file attachment
-    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
 
+    # 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():
@@ -108,28 +82,22 @@ class BaseMessageComponent(BaseModel):
 
 
 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, **_):
@@ -137,18 +105,18 @@ class Face(BaseMessageComponent):
 
 
 class Record(BaseMessageComponent):
-    type: ComponentType = "Record"
+    type = ComponentType.Record
-    file: T.Optional[str] = ""
+    file: str | None = ""
-    magic: T.Optional[bool] = False
+    magic: bool | None = False
-    url: T.Optional[str] = ""
+    url: str | None = ""
-    cache: T.Optional[bool] = True
+    cache: bool | None = True
-    proxy: T.Optional[bool] = True
+    proxy: bool | None = True
-    timeout: T.Optional[int] = 0
+    timeout: int | None = 0
     # 额外
-    path: T.Optional[str]
+    path: str | None
 
-    def __init__(self, file: T.Optional[str], **_):
+    def __init__(self, file: str | None, **_):
-        for k in _.keys():
+        for k in _:
             if k == "url":
                 pass
                 # Protocol.warn(f"go-cqhttp doesn't support send {self.type} by {k}")
@@ -164,19 +132,25 @@ 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 self.file and self.file.startswith("file:///"):
+        if not self.file:
-            file_path = self.file[8:]
+            raise Exception(f"not a valid file: {self.file}")
-            return file_path
+        if self.file.startswith("file:///"):
-        elif self.file and self.file.startswith("http"):
+            return self.file[8:]
+        if self.file.startswith("http"):
             file_path = await download_image_by_url(self.file)
             return os.path.abspath(file_path)
-        elif self.file and self.file.startswith("base64://"):
+        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")
@@ -184,25 +158,26 @@ class Record(BaseMessageComponent):
             with open(file_path, "wb") as f:
                 f.write(image_bytes)
             return os.path.abspath(file_path)
-        elif os.path.exists(self.file):
+        if os.path.exists(self.file):
-            file_path = self.file
+            return os.path.abspath(self.file)
-            return os.path.abspath(file_path)
+        raise Exception(f"not a valid file: {self.file}")
-        else:
-            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 self.file and self.file.startswith("file:///"):
+        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 and self.file.startswith("http"):
+        elif self.file.startswith("http"):
             file_path = await download_image_by_url(self.file)
             bs64_data = file_to_base64(file_path)
-        elif self.file and self.file.startswith("base64://"):
+        elif self.file.startswith("base64://"):
             bs64_data = self.file
         elif os.path.exists(self.file):
             bs64_data = file_to_base64(self.file)
@@ -212,14 +187,14 @@ class Record(BaseMessageComponent):
         return bs64_data
 
     async def register_to_file_service(self) -> str:
-        """
+        """将语音注册到文件服务。
-        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")
 
@@ -236,12 +211,12 @@ class Record(BaseMessageComponent):
 
 
 class Video(BaseMessageComponent):
-    type: ComponentType = "Video"
+    type = ComponentType.Video
     file: str
-    cover: T.Optional[str] = ""
+    cover: str | None = ""
-    c: T.Optional[int] = 2
+    c: int | None = 2
     # 额外
-    path: T.Optional[str] = ""
+    path: str | None = ""
 
     def __init__(self, file: str, **_):
         super().__init__(file=file, **_)
@@ -261,32 +236,31 @@ class Video(BaseMessageComponent):
 
         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:]
-        elif url and url.startswith("http"):
+        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)
-            else:
+            raise Exception(f"download failed: {url}")
-                raise Exception(f"download failed: {url}")
+        if os.path.exists(url):
-        elif os.path.exists(url):
             return os.path.abspath(url)
-        else:
+        raise Exception(f"not a valid file: {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。
-        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")
 
@@ -322,9 +296,9 @@ class Video(BaseMessageComponent):
 
 
 class At(BaseMessageComponent):
-    type: ComponentType = "At"
+    type = ComponentType.At
-    qq: T.Union[int, str]  # 此处str为all时代表所有人
+    qq: int | str  # 此处str为all时代表所有人
-    name: T.Optional[str] = ""
+    name: str | None = ""
 
     def __init__(self, **_):
         super().__init__(**_)
@@ -344,74 +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"
+    type = ComponentType.Shake
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
-class Anonymous(BaseMessageComponent):  # TODO
-    type: ComponentType = "Anonymous"
-    ignore: T.Optional[bool] = False
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Share(BaseMessageComponent):
-    type: ComponentType = "Share"
+    type = ComponentType.Share
     url: str
     title: str
-    content: T.Optional[str] = ""
+    content: str | None = ""
-    image: T.Optional[str] = ""
+    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] = ""
+    title: str | None = ""
-    content: T.Optional[str] = ""
+    content: str | None = ""
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
 class Music(BaseMessageComponent):
-    type: ComponentType = "Music"
+    type = ComponentType.Music
     _type: str
-    id: T.Optional[int] = 0
+    id: int | None = 0
-    url: T.Optional[str] = ""
+    url: str | None = ""
-    audio: T.Optional[str] = ""
+    audio: str | None = ""
-    title: T.Optional[str] = ""
+    title: str | None = ""
-    content: T.Optional[str] = ""
+    content: str | None = ""
-    image: T.Optional[str] = ""
+    image: str | None = ""
 
     def __init__(self, **_):
         # for k in _.keys():
@@ -421,19 +387,19 @@ class Music(BaseMessageComponent):
 
 
 class Image(BaseMessageComponent):
-    type: ComponentType = "Image"
+    type = ComponentType.Image
-    file: T.Optional[str] = ""
+    file: str | None = ""
-    _type: T.Optional[str] = ""
+    _type: str | None = ""
-    subType: T.Optional[int] = 0
+    subType: int | None = 0
-    url: T.Optional[str] = ""
+    url: str | None = ""
-    cache: T.Optional[bool] = True
+    cache: bool | None = True
-    id: T.Optional[int] = 40000
+    id: int | None = 40000
-    c: T.Optional[int] = 2
+    c: int | None = 2
     # 额外
-    path: T.Optional[str] = ""
+    path: str | None = ""
-    file_unique: T.Optional[str] = ""  # 某些平台可能有图片缓存的唯一标识
+    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], **_):
+    def __init__(self, file: str | None, **_):
         super().__init__(file=file, **_)
 
     @staticmethod
@@ -463,15 +429,17 @@ class Image(BaseMessageComponent):
 
         Returns:
             str: 图片的本地路径，以绝对路径表示。
+
         """
-        url = self.url if self.url else self.file
+        url = self.url or self.file
-        if url and url.startswith("file:///"):
+        if not url:
-            image_file_path = url[8:]
+            raise ValueError("No valid file or URL provided")
-            return image_file_path
+        if url.startswith("file:///"):
-        elif url and url.startswith("http"):
+            return url[8:]
+        if url.startswith("http"):
             image_file_path = await download_image_by_url(url)
             return os.path.abspath(image_file_path)
-        elif url and url.startswith("base64://"):
+        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")
@@ -479,26 +447,27 @@ class Image(BaseMessageComponent):
             with open(image_file_path, "wb") as f:
                 f.write(image_bytes)
             return os.path.abspath(image_file_path)
-        elif os.path.exists(url):
+        if os.path.exists(url):
-            image_file_path = url
+            return os.path.abspath(url)
-            return os.path.abspath(image_file_path)
+        raise Exception(f"not a valid file: {url}")
-        else:
-            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 if self.url else self.file
+        url = self.url or self.file
-        if url and url.startswith("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 and url.startswith("http"):
+        elif url.startswith("http"):
             image_file_path = await download_image_by_url(url)
             bs64_data = file_to_base64(image_file_path)
-        elif url and url.startswith("base64://"):
+        elif url.startswith("base64://"):
             bs64_data = url
         elif os.path.exists(url):
             bs64_data = file_to_base64(url)
@@ -508,14 +477,14 @@ class Image(BaseMessageComponent):
         return bs64_data
 
     async def register_to_file_service(self) -> str:
-        """
+        """将图片注册到文件服务。
-        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")
 
@@ -532,43 +501,35 @@ class Image(BaseMessageComponent):
 
 
 class Reply(BaseMessageComponent):
-    type: ComponentType = "Reply"
+    type = ComponentType.Reply
-    id: T.Union[str, int]
+    id: str | int
     """所引用的消息 ID"""
-    chain: T.Optional[T.List["BaseMessageComponent"]] = []
+    chain: list["BaseMessageComponent"] | None = []
     """被引用的消息段列表"""
-    sender_id: T.Optional[int] | T.Optional[str] = 0
+    sender_id: int | None | str = 0
     """被引用的消息对应的发送者的 ID"""
-    sender_nickname: T.Optional[str] = ""
+    sender_nickname: str | None = ""
     """被引用的消息对应的发送者的昵称"""
-    time: T.Optional[int] = 0
+    time: int | None = 0
     """被引用的消息发送时间"""
-    message_str: T.Optional[str] = ""
+    message_str: str | None = ""
     """被引用的消息解析后的纯文本消息字符串"""
 
-    text: T.Optional[str] = ""
+    text: str | None = ""
     """deprecated"""
-    qq: T.Optional[int] = 0
+    qq: int | None = 0
     """deprecated"""
-    seq: T.Optional[int] = 0
+    seq: int | None = 0
     """deprecated"""
 
     def __init__(self, **_):
         super().__init__(**_)
 
 
-class RedBag(BaseMessageComponent):
-    type: ComponentType = "RedBag"
-    title: str
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
 class Poke(BaseMessageComponent):
-    type: str = ""
+    type: str = ComponentType.Poke
-    id: T.Optional[int] = 0
+    id: int | None = 0
-    qq: T.Optional[int] = 0
+    qq: int | None = 0
 
     def __init__(self, type: str, **_):
         type = f"Poke:{type}"
@@ -576,7 +537,7 @@ class Poke(BaseMessageComponent):
 
 
 class Forward(BaseMessageComponent):
-    type: ComponentType = "Forward"
+    type = ComponentType.Forward
     id: str
 
     def __init__(self, **_):
@@ -586,13 +547,13 @@ class Forward(BaseMessageComponent):
 class Node(BaseMessageComponent):
     """群合并转发消息"""
 
-    type: ComponentType = "Node"
+    type = ComponentType.Node
-    id: T.Optional[int] = 0  # 忽略
+    id: int | None = 0  # 忽略
-    name: T.Optional[str] = ""  # qq昵称
+    name: str | None = ""  # qq昵称
-    uin: T.Optional[str] = "0"  # qq号
+    uin: str | None = "0"  # qq号
-    content: T.Optional[list[BaseMessageComponent]] = []
+    content: list[BaseMessageComponent] | None = []
-    seq: T.Optional[T.Union[str, list]] = ""  # 忽略
+    seq: str | list | None = ""  # 忽略
-    time: T.Optional[int] = 0  # 忽略
+    time: int | None = 0  # 忽略
 
     def __init__(self, content: list[BaseMessageComponent], **_):
         if isinstance(content, Node):
@@ -610,7 +571,7 @@ class Node(BaseMessageComponent):
                     {
                         "type": comp.type.lower(),
                         "data": {"file": f"base64://{bs64}"},
-                    }
+                    },
                 )
             elif isinstance(comp, Plain):
                 # For Plain segments, we need to handle the plain differently
@@ -638,10 +599,10 @@ class Node(BaseMessageComponent):
 
 
 class Nodes(BaseMessageComponent):
-    type: ComponentType = "Nodes"
+    type = ComponentType.Nodes
-    nodes: T.List[Node]
+    nodes: list[Node]
 
-    def __init__(self, nodes: T.List[Node], **_):
+    def __init__(self, nodes: list[Node], **_):
         super().__init__(nodes=nodes, **_)
 
     def toDict(self):
@@ -663,19 +624,10 @@ class Nodes(BaseMessageComponent):
         return ret
 
 
-class Xml(BaseMessageComponent):
-    type: ComponentType = "Xml"
-    data: str
-    resid: T.Optional[int] = 0
-
-    def __init__(self, **_):
-        super().__init__(**_)
-
-
 class Json(BaseMessageComponent):
-    type: ComponentType = "Json"
+    type = ComponentType.Json
-    data: T.Union[str, dict]
+    data: str | dict
-    resid: T.Optional[int] = 0
+    resid: int | None = 0
 
     def __init__(self, data, **_):
         if isinstance(data, dict):
@@ -683,50 +635,18 @@ 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):
-    """
+    """文件消息段"""
-    文件消息段
-    """
 
-    type: ComponentType = "File"
+    type = ComponentType.File
-    name: T.Optional[str] = ""  # 名字
+    name: str | None = ""  # 名字
-    file_: T.Optional[str] = ""  # 本地路径
+    file_: str | None = ""  # 本地路径
-    url: T.Optional[str] = ""  # url
+    url: str | None = ""  # url
 
     def __init__(self, name: str, file: str = "", url: str = ""):
         """文件消息段。"""
@@ -734,11 +654,11 @@ class File(BaseMessageComponent):
 
     @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
-        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_)
@@ -748,19 +668,16 @@ class File(BaseMessageComponent):
                 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! "
-                            "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。"
-                            "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",
-                            "请使用 await get_file() 代替直接获取 <File>.file 字段"
-                        )
                     )
                     return ""
-                else:
+                # 等待下载完成
-                    # 等待下载完成
+                loop.run_until_complete(self._download_file())
-                    loop.run_until_complete(self._download_file())
 
-                    if self.file_ and os.path.exists(self.file_):
+                if self.file_ and os.path.exists(self.file_):
-                        return os.path.abspath(self.file_)
+                    return os.path.abspath(self.file_)
             except Exception as e:
                 logger.error(f"文件下载失败: {e}")
 
@@ -768,11 +685,11 @@ class File(BaseMessageComponent):
 
     @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
-        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
@@ -787,6 +704,7 @@ class File(BaseMessageComponent):
             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
@@ -809,14 +727,14 @@ class File(BaseMessageComponent):
         self.file_ = os.path.abspath(file_path)
 
     async def register_to_file_service(self):
-        """
+        """将文件注册到文件服务。
-        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")
 
@@ -853,42 +771,39 @@ class File(BaseMessageComponent):
 
 
 class WechatEmoji(BaseMessageComponent):
-    type: ComponentType = "WechatEmoji"
+    type = ComponentType.WechatEmoji
-    md5: T.Optional[str] = ""
+    md5: str | None = ""
-    md5_len: T.Optional[int] = 0
+    md5_len: int | None = 0
-    cdnurl: T.Optional[str] = ""
+    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,
 }

astrbot/core/message/message_event_result.py

@@ -1,15 +1,16 @@
 import enum
-
+from collections.abc import AsyncGenerator
-from typing import List, Optional, Union, AsyncGenerator
 from dataclasses import dataclass, field
+
+from typing_extensions import deprecated
+
 from astrbot.core.message.components import (
-    BaseMessageComponent,
-    Plain,
-    Image,
     At,
     AtAll,
+    BaseMessageComponent,
+    Image,
+    Plain,
 )
-from typing_extensions import deprecated
 
 
 @dataclass
@@ -20,18 +21,18 @@ class MessageChain:
     Attributes:
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
+
     """
 
-    chain: List[BaseMessageComponent] = field(default_factory=list)
+    chain: list[BaseMessageComponent] = field(default_factory=list)
-    use_t2i_: Optional[bool] = None  # None 为跟随用户设置
+    use_t2i_: bool | None = None  # None 为跟随用户设置
-    type: Optional[str] = None
+    type: str | None = None
     """消息链承载的消息的类型。可选，用于让消息平台区分不同业务场景的消息链。"""
 
     def message(self, message: str):
         """添加一条文本消息到消息链 `chain` 中。
 
         Example:
-
             CommandResult().message("Hello ").message("world!")
             # 输出 Hello world!
 
@@ -39,11 +40,10 @@ class MessageChain:
         self.chain.append(Plain(message))
         return self
 
-    def at(self, name: str, qq: Union[str, int]):
+    def at(self, name: str, qq: str | int):
         """添加一条 At 消息到消息链 `chain` 中。
 
         Example:
-
             CommandResult().at("张三", "12345678910")
             # 输出 @张三
 
@@ -55,7 +55,6 @@ class MessageChain:
         """添加一条 AtAll 消息到消息链 `chain` 中。
 
         Example:
-
             CommandResult().at_all()
             # 输出 @所有人
 
@@ -68,7 +67,6 @@ class MessageChain:
         """添加一条错误消息到消息链 `chain` 中
 
         Example:
-
             CommandResult().error("解析失败")
 
         """
@@ -82,7 +80,6 @@ class MessageChain:
             如果需要发送本地图片，请使用 `file_image` 方法。
 
         Example:
-
             CommandResult().image("https://example.com/image.jpg")
 
         """
@@ -96,6 +93,7 @@ class MessageChain:
             如果需要发送网络图片，请使用 `url_image` 方法。
 
         CommandResult().image("image.jpg")
+
         """
         self.chain.append(Image.fromFileSystem(path))
         return self
@@ -114,6 +112,7 @@ class MessageChain:
 
         Args:
             use_t2i (bool): 是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
+
         """
         self.use_t2i_ = use_t2i
         return self
@@ -125,7 +124,7 @@ class MessageChain:
     def squash_plain(self):
         """将消息链中的所有 Plain 消息段聚合到第一个 Plain 消息段中。"""
         if not self.chain:
-            return
+            return None
 
         new_chain = []
         first_plain = None
@@ -153,6 +152,7 @@ class EventResultType(enum.Enum):
     Attributes:
         CONTINUE: 事件将会继续传播
         STOP: 事件将会终止传播
+
     """
 
     CONTINUE = enum.auto()
@@ -181,17 +181,18 @@ class MessageEventResult(MessageChain):
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
         `result_type` (EventResultType): 事件处理的结果类型。
+
     """
 
-    result_type: Optional[EventResultType] = field(
+    result_type: EventResultType | None = field(
-        default_factory=lambda: EventResultType.CONTINUE
+        default_factory=lambda: EventResultType.CONTINUE,
     )
 
-    result_content_type: Optional[ResultContentType] = field(
+    result_content_type: ResultContentType | None = field(
-        default_factory=lambda: ResultContentType.GENERAL_RESULT
+        default_factory=lambda: ResultContentType.GENERAL_RESULT,
     )
 
-    async_stream: Optional[AsyncGenerator] = None
+    async_stream: AsyncGenerator | None = None
     """异步流"""
 
     def stop_event(self) -> "MessageEventResult":
@@ -205,9 +206,7 @@ class MessageEventResult(MessageChain):
         return self
 
     def is_stopped(self) -> bool:
-        """
+        """是否终止事件传播。"""
-        是否终止事件传播。
-        """
         return self.result_type == EventResultType.STOP
 
     def set_async_stream(self, stream: AsyncGenerator) -> "MessageEventResult":
@@ -220,6 +219,7 @@ class MessageEventResult(MessageChain):
 
         Args:
             result_type (EventResultType): 事件处理的结果类型。
+
         """
         self.result_content_type = typ
         return self

astrbot/core/persona_mgr.py

@@ -0,0 +1,192 @@
+from astrbot import logger
+from astrbot.core.astrbot_config_mgr import AstrBotConfigManager
+from astrbot.core.db import BaseDatabase
+from astrbot.core.db.po import Persona, Personality
+from astrbot.core.platform.message_session import MessageSession
+
+DEFAULT_PERSONALITY = Personality(
+    prompt="You are a helpful and friendly assistant.",
+    name="default",
+    begin_dialogs=[],
+    mood_imitation_dialogs=[],
+    tools=None,
+    _begin_dialogs_processed=[],
+    _mood_imitation_dialogs_processed="",
+)
+
+
+class PersonaManager:
+    def __init__(self, db_helper: BaseDatabase, acm: AstrBotConfigManager):
+        self.db = db_helper
+        self.acm = acm
+        default_ps = acm.default_conf.get("provider_settings", {})
+        self.default_persona: str = default_ps.get("default_personality", "default")
+        self.personas: list[Persona] = []
+        self.selected_default_persona: Persona | None = None
+
+        self.personas_v3: list[Personality] = []
+        self.selected_default_persona_v3: Personality | None = None
+        self.persona_v3_config: list[dict] = []
+
+    async def initialize(self):
+        self.personas = await self.get_all_personas()
+        self.get_v3_persona_data()
+        logger.info(f"已加载 {len(self.personas)} 个人格。")
+
+    async def get_persona(self, persona_id: str):
+        """获取指定 persona 的信息"""
+        persona = await self.db.get_persona_by_id(persona_id)
+        if not persona:
+            raise ValueError(f"Persona with ID {persona_id} does not exist.")
+        return persona
+
+    async def get_default_persona_v3(
+        self,
+        umo: str | MessageSession | None = None,
+    ) -> Personality:
+        """获取默认 persona"""
+        cfg = self.acm.get_conf(umo)
+        default_persona_id = cfg.get("provider_settings", {}).get(
+            "default_personality",
+            "default",
+        )
+        if not default_persona_id or default_persona_id == "default":
+            return DEFAULT_PERSONALITY
+        try:
+            return next(p for p in self.personas_v3 if p["name"] == default_persona_id)
+        except Exception:
+            return DEFAULT_PERSONALITY
+
+    async def delete_persona(self, persona_id: str):
+        """删除指定 persona"""
+        if not await self.db.get_persona_by_id(persona_id):
+            raise ValueError(f"Persona with ID {persona_id} does not exist.")
+        await self.db.delete_persona(persona_id)
+        self.personas = [p for p in self.personas if p.persona_id != persona_id]
+        self.get_v3_persona_data()
+
+    async def update_persona(
+        self,
+        persona_id: str,
+        system_prompt: str | None = None,
+        begin_dialogs: list[str] | None = None,
+        tools: list[str] | None = None,
+    ):
+        """更新指定 persona 的信息。tools 参数为 None 时表示使用所有工具，空列表表示不使用任何工具"""
+        existing_persona = await self.db.get_persona_by_id(persona_id)
+        if not existing_persona:
+            raise ValueError(f"Persona with ID {persona_id} does not exist.")
+        persona = await self.db.update_persona(
+            persona_id,
+            system_prompt,
+            begin_dialogs,
+            tools=tools,
+        )
+        if persona:
+            for i, p in enumerate(self.personas):
+                if p.persona_id == persona_id:
+                    self.personas[i] = persona
+                    break
+        self.get_v3_persona_data()
+        return persona
+
+    async def get_all_personas(self) -> list[Persona]:
+        """获取所有 personas"""
+        return await self.db.get_personas()
+
+    async def create_persona(
+        self,
+        persona_id: str,
+        system_prompt: str,
+        begin_dialogs: list[str] = None,
+        tools: list[str] = None,
+    ) -> Persona:
+        """创建新的 persona。tools 参数为 None 时表示使用所有工具，空列表表示不使用任何工具"""
+        if await self.db.get_persona_by_id(persona_id):
+            raise ValueError(f"Persona with ID {persona_id} already exists.")
+        new_persona = await self.db.insert_persona(
+            persona_id,
+            system_prompt,
+            begin_dialogs,
+            tools=tools,
+        )
+        self.personas.append(new_persona)
+        self.get_v3_persona_data()
+        return new_persona
+
+    def get_v3_persona_data(
+        self,
+    ) -> tuple[list[dict], list[Personality], Personality]:
+        """获取 AstrBot <4.0.0 版本的 persona 数据。
+
+        Returns:
+            - list[dict]: 包含 persona 配置的字典列表。
+            - list[Personality]: 包含 Personality 对象的列表。
+            - Personality: 默认选择的 Personality 对象。
+
+        """
+        v3_persona_config = [
+            {
+                "prompt": persona.system_prompt,
+                "name": persona.persona_id,
+                "begin_dialogs": persona.begin_dialogs or [],
+                "mood_imitation_dialogs": [],  # deprecated
+                "tools": persona.tools,
+            }
+            for persona in self.personas
+        ]
+
+        personas_v3: list[Personality] = []
+        selected_default_persona: Personality | None = None
+
+        for persona_cfg in v3_persona_config:
+            begin_dialogs = persona_cfg.get("begin_dialogs", [])
+            bd_processed = []
+            if begin_dialogs:
+                if len(begin_dialogs) % 2 != 0:
+                    logger.error(
+                        f"{persona_cfg['name']} 人格情景预设对话格式不对，条数应该为偶数。",
+                    )
+                    begin_dialogs = []
+                user_turn = True
+                for dialog in begin_dialogs:
+                    bd_processed.append(
+                        {
+                            "role": "user" if user_turn else "assistant",
+                            "content": dialog,
+                            "_no_save": None,  # 不持久化到 db
+                        },
+                    )
+                    user_turn = not user_turn
+
+            try:
+                persona = Personality(
+                    **persona_cfg,
+                    _begin_dialogs_processed=bd_processed,
+                    _mood_imitation_dialogs_processed="",  # deprecated
+                )
+                if persona["name"] == self.default_persona:
+                    selected_default_persona = persona
+                personas_v3.append(persona)
+            except Exception as e:
+                logger.error(f"解析 Persona 配置失败：{e}")
+
+        if not selected_default_persona and len(personas_v3) > 0:
+            # 默认选择第一个
+            selected_default_persona = personas_v3[0]
+
+        if not selected_default_persona:
+            selected_default_persona = DEFAULT_PERSONALITY
+            personas_v3.append(selected_default_persona)
+
+        self.personas_v3 = personas_v3
+        self.selected_default_persona_v3 = selected_default_persona
+        self.persona_v3_config = v3_persona_config
+        self.selected_default_persona = Persona(
+            persona_id=selected_default_persona["name"],
+            system_prompt=selected_default_persona["prompt"],
+            begin_dialogs=selected_default_persona["begin_dialogs"],
+            tools=selected_default_persona["tools"] or None,
+        )
+
+        return v3_persona_config, personas_v3, selected_default_persona

astrbot/core/pipeline/__init__.py

@@ -4,7 +4,6 @@ from astrbot.core.message.message_event_result import (
 )
 
 from .content_safety_check.stage import ContentSafetyCheckStage
-from .platform_compatibility.stage import PlatformCompatibilityStage
 from .preprocess_stage.stage import PreProcessStage
 from .process_stage.stage import ProcessStage
 from .rate_limit_check.stage import RateLimitStage
@@ -21,7 +20,6 @@ STAGES_ORDER = [
     "SessionStatusCheckStage",  # 检查会话是否整体启用
     "RateLimitStage",  # 检查会话是否超过频率限制
     "ContentSafetyCheckStage",  # 检查内容安全
-    "PlatformCompatibilityStage",  # 检查所有处理器的平台兼容性
     "PreProcessStage",  # 预处理
     "ProcessStage",  # 交由 Stars 处理（a.k.a 插件），或者 LLM 调用
     "ResultDecorateStage",  # 处理结果，比如添加回复前缀、t2i、转换为语音 等
@@ -29,16 +27,15 @@ STAGES_ORDER = [
 ]
 
 __all__ = [
-    "WakingCheckStage",
-    "WhitelistCheckStage",
-    "SessionStatusCheckStage",
-    "RateLimitStage",
     "ContentSafetyCheckStage",
-    "PlatformCompatibilityStage",
+    "EventResultType",
+    "MessageEventResult",
     "PreProcessStage",
     "ProcessStage",
-    "ResultDecorateStage",
+    "RateLimitStage",
     "RespondStage",
-    "MessageEventResult",
+    "ResultDecorateStage",
-    "EventResultType",
+    "SessionStatusCheckStage",
+    "WakingCheckStage",
+    "WhitelistCheckStage",
 ]

astrbot/core/pipeline/content_safety_check/stage.py

@@ -1,9 +1,11 @@
-from typing import Union, AsyncGenerator
+from collections.abc import AsyncGenerator
-from ..stage import Stage, register_stage
+
-from ..context import PipelineContext
-from astrbot.core.platform.astr_message_event import AstrMessageEvent
-from astrbot.core.message.message_event_result import MessageEventResult
 from astrbot.core import logger
+from astrbot.core.message.message_event_result import MessageEventResult
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+
+from ..context import PipelineContext
+from ..stage import Stage, register_stage
 from .strategies.strategy import StrategySelector
 
 
@@ -19,8 +21,10 @@ class ContentSafetyCheckStage(Stage):
         self.strategy_selector = StrategySelector(config)
 
     async def process(
-        self, event: AstrMessageEvent, check_text: str = None
+        self,
-    ) -> Union[None, AsyncGenerator[None, None]]:
+        event: AstrMessageEvent,
+        check_text: str | None = None,
+    ) -> None | AsyncGenerator[None, None]:
         """检查内容安全"""
         text = check_text if check_text else event.get_message_str()
         ok, info = self.strategy_selector.check(text)
@@ -28,8 +32,8 @@ class ContentSafetyCheckStage(Stage):
             if event.is_at_or_wake_command:
                 event.set_result(
                     MessageEventResult().message(
-                        "你的消息或者大模型的响应中包含不适当的内容，已被屏蔽。"
+                        "你的消息或者大模型的响应中包含不适当的内容，已被屏蔽。",
-                    )
+                    ),
                 )
                 yield
             event.stop_event()

astrbot/core/pipeline/content_safety_check/strategies/__init__.py

@@ -1,8 +1,7 @@
 import abc
-from typing import Tuple
 
 
 class ContentSafetyStrategy(abc.ABC):
     @abc.abstractmethod
-    def check(self, content: str) -> Tuple[bool, str]:
+    def check(self, content: str) -> tuple[bool, str]:
         raise NotImplementedError

astrbot/core/pipeline/content_safety_check/strategies/baidu_aip.py

@@ -1,9 +1,8 @@
-"""
+"""使用此功能应该先 pip install baidu-aip"""
-使用此功能应该先 pip install baidu-aip
+
-"""
+from aip import AipContentCensor
 
 from . import ContentSafetyStrategy
-from aip import AipContentCensor
 
 
 class BaiduAipStrategy(ContentSafetyStrategy):
@@ -13,18 +12,18 @@ class BaiduAipStrategy(ContentSafetyStrategy):
         self.secret_key = sk
         self.client = AipContentCensor(self.app_id, self.api_key, self.secret_key)
 
-    def check(self, content: str):
+    def check(self, content: str) -> tuple[bool, str]:
         res = self.client.textCensorUserDefined(content)
         if "conclusionType" not in res:
             return False, ""
         if res["conclusionType"] == 1:
             return True, ""
-        else:
+        if "data" not in res:
-            if "data" not in res:
+            return False, ""
-                return False, ""
+        count = len(res["data"])
-            count = len(res["data"])
+        parts = [f"百度审核服务发现 {count} 处违规：\n"]
-            info = f"百度审核服务发现 {count} 处违规：\n"
+        for i in res["data"]:
-            for i in res["data"]:
+            parts.append(f"{i['msg']}；\n")
-                info += f"{i['msg']}；\n"
+        parts.append("\n判断结果：" + res["conclusion"])
-            info += "\n判断结果：" + res["conclusion"]
+        info = "".join(parts)
-            return False, info
+        return False, info

astrbot/core/pipeline/content_safety_check/strategies/keywords.py

@@ -1,4 +1,5 @@
 import re
+
 from . import ContentSafetyStrategy
 
 
@@ -16,7 +17,7 @@ class KeywordsStrategy(ContentSafetyStrategy):
         #             json.loads(base64.b64decode(f.read()).decode("utf-8"))["keywords"]
         #         )
 
-    def check(self, content: str) -> bool:
+    def check(self, content: str) -> tuple[bool, str]:
         for keyword in self.keywords:
             if re.search(keyword, content):
                 return False, "内容安全检查不通过，匹配到敏感词。"