✨ feat: 初步实现可视化编辑 object 配置项

✨ feat: add template of FastGPT
Merge pull request #572 from Soulter/feat-dashscope
2025-02-22 17:12:35 +08:00 · 2025-02-22 15:43:14 +08:00 · 2025-02-22 15:04:46 +08:00 · 2025-02-22 14:48:18 +08:00 · 2025-02-22 14:32:37 +08:00 · 2025-02-22 14:08:51 +08:00
132 changed files with 5738 additions and 1763 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -21,4 +21,8 @@ node_modules/
 .DS_Store
 package-lock.json
 package.json
-venv/*
+venv/*
+packages/python_interpreter/workplace
+.venv/*
+
+.conda/
--- a/4
+++ b/4
@@ -12,7 +12,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

-RUN python -m pip install -r requirements.txt
+RUN python -m pip install -r requirements.txt --no-cache-dir
+
+RUN python -m pip install socksio wechatpy cryptography --no-cache-dir

 EXPOSE 6185 
 EXPOSE 6186
--- a/README.md
+++ b/README.md
@@ -1,7 +1,6 @@
 <p align="center">
    
-![](https://github.com/user-attachments/assets/04f22f63-4dcf-4a6c-981e-b33f45c23f3e)
-
+![6e1279651f16d7fdf4727558b72bbaf1](https://github.com/user-attachments/assets/ead4c551-fc3c-48f7-a6f7-afbfdb820512)

 </p>

@@ -9,15 +8,17 @@

 _✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_

+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
 <img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
 <a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg"/></a>
-<img alt="Static Badge" src="https://img.shields.io/badge/QQ群-322154837-purple">
+<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)
-[<img src="https://api.gitsponsors.com/api/badge/img?id=575865240" height="20">](https://api.gitsponsors.com/api/badge/link?p=XEpbdGxlitw/RbcwiTX93UMzNK/jgDYC8NiSzamIPMoKvG2lBFmyXhSS/b0hFoWlBBMX2L5X5CxTDsUdyvcIEHTOfnkXz47UNOZvMwyt5CzbYpq0SEzsSV1OJF1cCo90qC/ZyYKYOWedal3MhZ3ikw==)
-</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>
@@ -27,7 +28,7 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 ## ✨ 主要功能

 1. **大语言模型对话**。支持各种大语言模型，包括 OpenAI API、Google Gemini、Llama、Deepseek、ChatGLM 等，支持接入本地部署的大模型，通过 Ollama、LLMTuner。具有多轮对话、人格情境、多模态能力，支持图片理解、语音转文字（Whisper）。
-2. **多消息平台接入**。支持接入 QQ（OneBot）、QQ 频道、微信（Gewechat、VChat）、Telegram。后续将支持钉钉、飞书、Discord、WhatsApp、小爱音响。支持速率限制、白名单、关键词过滤、百度内容审核。
+2. **多消息平台接入**。支持接入 QQ（OneBot）、QQ 频道、微信（Gewechat）、飞书、Telegram。后续将支持钉钉、Discord、WhatsApp、小爱音响。支持速率限制、白名单、关键词过滤、百度内容审核。
 3. **Agent**。原生支持部分 Agent 能力，如代码执行器、自然语言待办、网页搜索。对接 [Dify 平台](https://astrbot.app/others/dify.html)，便捷接入 Dify 智能助手、知识库和 Dify 工作流。
 4. **插件扩展**。深度优化的插件机制，支持[开发插件](https://astrbot.app/dev/plugin.html)扩展功能，极简开发。已支持安装多个插件。
 5. **可视化管理面板**。支持可视化修改配置、插件管理、日志查看等功能，降低配置难度。集成 WebChat，可在面板上与大模型对话。
@@ -36,7 +37,7 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 > [!TIP]
 > 管理面板在线体验 Demo: [https://demo.astrbot.app/](https://demo.astrbot.app/)
 > 
-> 用户名: `astrbot`, 密码: `astrbot`。此 Demo 未配置 LLM，因此无法在聊天页使用大模型。
+> 用户名: `astrbot`, 密码: `astrbot`。未配置 LLM，无法在聊天页使用大模型。（不要再修改 demo 的登录密码了 😭）

 ## ✨ 使用方式

@@ -65,19 +66,31 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用

 ## ⚡ 消息平台支持情况

-
 | 平台    | 支持性 | 详情 | 消息类型 |
 | -------- | ------- | ------- | ------ |
-| QQ      | ✔    | 私聊、群聊 | 文字、图片、语音 |
-| QQ 官方API | ✔    | 私聊、群聊，QQ 频道私聊、群聊 | 文字、图片 |
-| 微信    | ✔    | [Gewechat](https://github.com/Devo919/Gewechat)。微信个人号私聊、群聊 | 文字、图片、语音 |
+| QQ(官方机器人接口) | ✔    | 私聊、群聊，QQ 频道私聊、群聊 | 文字、图片 |
+| QQ(OneBot)      | ✔    | 私聊、群聊 | 文字、图片、语音 |
+| 微信(个人号)    | ✔    | 微信个人号私聊、群聊 | 文字、图片、语音 |
 | [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | 私聊、群聊 | 文字、图片 |
+| [微信(企业微信)](https://github.com/Soulter/astrbot_plugin_wecom)    | ✔    | 私聊 | 文字、图片、语音 |
+| 飞书   | ✔    | 群聊 | 文字、图片 |
 | 微信对话开放平台 | 🚧    | 计划内 | - |
-| 飞书   | 🚧    | 计划内 | - |
 | Discord   | 🚧    | 计划内 | - |
 | WhatsApp   | 🚧    | 计划内 | - |
 | 小爱音响   | 🚧    | 计划内 | - |

+# 🦌 接下来的路线图
+
+> [!TIP]
+> 欢迎在 Issue 提出更多建议 <3
+
+- [ ] 完善并保证目前所有平台适配器的功能一致性
+- [ ] 优化插件接口
+- [ ] 默认支持更多 TTS 服务，如 GPT-Sovits
+- [ ] 完善“聊天增强”部分，支持持久化记忆
+- [ ] 规划 i18n
+
+
 ## ❤️ 贡献

 欢迎任何 Issues/Pull Requests！只需要将你的更改提交到此项目 ：)
@@ -129,8 +142,17 @@ _✨ 内置 Web Chat，在线与机器人交互 ✨_
 > [!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

+<div align="center">
+    
 [![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)

+</div>
+
+## Disclaimer
+
+1. The project is protected under the `AGPL-v3` opensource license.
+2. The deployment of WeChat (personal account) utilizes [Gewechat](https://github.com/Devo919/Gewechat) service. AstrBot only guarantees connectivity with Gewechat and recommends using a WeChat account that is not frequently used. In the event of account risk control, the author of this project shall not bear any responsibility.
+3. Please ensure compliance with local laws and regulations when using this project.

 <!-- ## ✨ ATRI [Beta 测试]

@@ -142,5 +164,6 @@ _✨ 内置 Web Chat，在线与机器人交互 ✨_
 4. TTS
    -->

-_アトリは、高性能ですから!_
+
+_私は、高性能ですから!_

--- a/README_ja.md
+++ b/README_ja.md
@@ -0,0 +1,170 @@
+<p align="center">
+    
+![6e1279651f16d7fdf4727558b72bbaf1](https://github.com/user-attachments/assets/ead4c551-fc3c-48f7-a6f7-afbfdb820512)
+
+</p>
+
+<div align="center">
+
+_✨ 簡単に使えるマルチプラットフォーム LLM チャットボットおよび開発フレームワーク ✨_
+
+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="python">
+<a href="https://hub.docker.com/r/soulter/astrbot"><img alt="Docker pull" src="https://img.shields.io/docker/pulls/soulter/astrbot.svg"/></a>
+<img alt="Static Badge" src="https://img.shields.io/badge/QQ群-630166526-purple">
+[![wakatime](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e.svg)](https://wakatime.com/badge/user/915e5316-99c6-4563-a483-ef186cf000c9/project/018e705a-a1a7-409a-a849-3013485e6c8e)
+![Dynamic JSON Badge](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fapi.soulter.top%2Fastrbot%2Fstats&query=v&label=7%E6%97%A5%E6%B6%88%E6%81%AF%E4%B8%8A%E8%A1%8C%E9%87%8F&cacheSeconds=3600)
+[![codecov](https://codecov.io/gh/Soulter/AstrBot/graph/badge.svg?token=FF3P5967B8)](https://codecov.io/gh/Soulter/AstrBot)
+
+<a href="https://astrbot.app/">ドキュメントを見る</a> ｜
+<a href="https://github.com/Soulter/AstrBot/issues">問題を報告する</a>
+</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。
+
+## ✨ 主な機能
+
+1. **大規模言語モデルの対話**。OpenAI API、Google Gemini、Llama、Deepseek、ChatGLM など、さまざまな大規模言語モデルをサポートし、Ollama、LLMTuner を介してローカルにデプロイされた大規模モデルをサポートします。多輪対話、人格シナリオ、多モーダル機能を備え、画像理解、音声からテキストへの変換（Whisper）をサポートします。
+2. **複数のメッセージプラットフォームの接続**。QQ（OneBot）、QQ チャンネル、WeChat（Gewechat）、Feishu、Telegram への接続をサポートします。今後、DingTalk、Discord、WhatsApp、Xiaoai 音響をサポートする予定です。レート制限、ホワイトリスト、キーワードフィルタリング、Baidu コンテンツ監査をサポートします。
+3. **エージェント**。一部のエージェント機能をネイティブにサポートし、コードエグゼキューター、自然言語タスク、ウェブ検索などを提供します。[Dify プラットフォーム](https://astrbot.app/others/dify.html)と連携し、Dify スマートアシスタント、ナレッジベース、Dify ワークフローを簡単に接続できます。
+4. **プラグインの拡張**。深く最適化されたプラグインメカニズムを備え、[プラグインの開発](https://astrbot.app/dev/plugin.html)をサポートし、機能を拡張できます。複数のプラグインのインストールをサポートします。
+5. **ビジュアル管理パネル**。設定の視覚的な変更、プラグイン管理、ログの表示などをサポートし、設定の難易度を低減します。WebChat を統合し、パネル上で大規模モデルと対話できます。
+6. **高い安定性と高いモジュール性**。イベントバスとパイプラインに基づくアーキテクチャ設計により、高度にモジュール化され、低結合です。
+
+> [!TIP]
+> 管理パネルのオンラインデモを体験する: [https://demo.astrbot.app/](https://demo.astrbot.app/)
+> 
+> ユーザー名: `astrbot`, パスワード: `astrbot`。LLM が設定されていないため、チャットページで大規模モデルを使用することはできません。（デモのログインパスワードを変更しないでください 😭）
+
+## ✨ 使用方法
+
+#### Docker デプロイ
+
+公式ドキュメント [Docker を使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot) を参照してください。
+
+#### Windows ワンクリックインストーラーのデプロイ
+
+コンピュータに Python（>3.10）がインストールされている必要があります。公式ドキュメント [Windows ワンクリックインストーラーを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/windows.html) を参照してください。
+
+#### Replit デプロイ
+
+[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+
+#### CasaOS デプロイ
+
+コミュニティが提供するデプロイ方法です。
+
+公式ドキュメント [ソースコードを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/casaos.html) を参照してください。
+
+#### 手動デプロイ
+
+公式ドキュメント [ソースコードを使用して AstrBot をデプロイする](https://astrbot.app/deploy/astrbot/cli.html) を参照してください。
+
+## ⚡ メッセージプラットフォームのサポート状況
+
+| プラットフォーム    | サポート状況 | 詳細 | メッセージタイプ |
+| -------- | ------- | ------- | ------ |
+| QQ(公式ロボットインターフェース) | ✔    | プライベートチャット、グループチャット、QQ チャンネルプライベートチャット、グループチャット | テキスト、画像 |
+| QQ(OneBot)      | ✔    | プライベートチャット、グループチャット | テキスト、画像、音声 |
+| WeChat(個人アカウント)    | ✔    | WeChat 個人アカウントのプライベートチャット、グループチャット | テキスト、画像、音声 |
+| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | プライベートチャット、グループチャット | テキスト、画像 |
+| [WeChat(企業 WeChat)](https://github.com/Soulter/astrbot_plugin_wecom)    | ✔    | プライベートチャット | テキスト、画像、音声 |
+| Feishu   | ✔    | グループチャット | テキスト、画像 |
+| WeChat 対話オープンプラットフォーム | 🚧    | 計画中 | - |
+| Discord   | 🚧    | 計画中 | - |
+| WhatsApp   | 🚧    | 計画中 | - |
+| Xiaoai 音響   | 🚧    | 計画中 | - |
+
+# 🦌 今後のロードマップ
+
+> [!TIP]
+> Issue でさらに多くの提案を歓迎します <3
+
+- [ ] 現在のすべてのプラットフォームアダプターの機能の一貫性を確保し、改善する
+- [ ] プラグインインターフェースの最適化
+- [ ] GPT-Sovits などの TTS サービスをデフォルトでサポート
+- [ ] "チャット強化" 部分を完成させ、永続的な記憶をサポート
+- [ ] i18n の計画
+
+## ❤️ 貢献
+
+Issue や Pull Request を歓迎します！このプロジェクトに変更を加えるだけです :)
+
+新機能の追加については、まず Issue で議論してください。
+
+## 🌟 サポート
+
+- このプロジェクトに Star を付けてください！
+- [愛発電](https://afdian.com/a/soulter)で私をサポートしてください！
+- [WeChat](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)で私をサポートしてください~
+
+## ✨ デモ
+
+> [!NOTE]
+> コードエグゼキューターのファイル入力/出力は現在 Napcat(QQ)、Lagrange(QQ) でのみテストされています
+
+<div align='center'>
+
+<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
+
+_✨ Docker ベースのサンドボックス化されたコードエグゼキューター（ベータテスト中）✨_
+
+<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
+
+_✨ 多モーダル、ウェブ検索、長文の画像変換（設定可能）✨_
+
+<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
+
+_✨ 自然言語タスク ✨_
+
+<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>
+
+_✨ プラグインシステム - 一部のプラグインの展示 ✨_
+
+<img src="https://github.com/user-attachments/assets/592a8630-14c7-4e06-b496-9c0386e4f36c" width="600">
+
+_✨ 管理パネル ✨_
+
+![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
+
+_✨ 内蔵 Web Chat、オンラインでボットと対話 ✨_
+
+</div>
+
+## ⭐ Star History
+
+> [!TIP] 
+> このプロジェクトがあなたの生活や仕事に役立った場合、またはこのプロジェクトの将来の発展に関心がある場合は、プロジェクトに Star を付けてください。これはこのオープンソースプロジェクトを維持するためのモチベーションです <3
+
+<div align="center">
+    
+[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+
+</div>
+
+## スポンサー
+
+[<img src="https://api.gitsponsors.com/api/badge/img?id=575865240" height="20">](https://api.gitsponsors.com/api/badge/link?p=XEpbdGxlitw/RbcwiTX93UMzNK/jgDYC8NiSzamIPMoKvG2lBFmyXhSS/b0hFoWlBBMX2L5X5CxTDsUdyvcIEHTOfnkXz47UNOZvMwyt5CzbYpq0SEzsSV1OJF1cCo90qC/ZyYKYOWedal3MhZ3ikw==)
+
+## 免責事項
+
+1. このプロジェクトは `AGPL-v3` オープンソースライセンスの下で保護されています。
+2. WeChat（個人アカウント）のデプロイメントには [Gewechat](https://github.com/Devo919/Gewechat) サービスを利用しています。AstrBot は Gewechat との接続を保証するだけであり、アカウントのリスク管理に関しては、このプロジェクトの著者は一切の責任を負いません。
+3. このプロジェクトを使用する際は、現地の法律および規制を遵守してください。
+
+<!-- ## ✨ ATRI [ベータテスト]
+
+この機能はプラグインとしてロードされます。プラグインリポジトリのアドレス：[astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
+
+1. 《ATRI ~ My Dear Moments》の主人公 ATRI のキャラクターセリフを微調整データセットとして使用した `Qwen1.5-7B-Chat Lora` 微調整モデル。
+2. 長期記憶
+3. ミームの理解と返信
+4. TTS
+    -->
+
+
+_私は、高性能ですから!_
+
--- a/astrbot/api/event/filter/init.py
+++ b/astrbot/api/event/filter/init.py
@@ -5,7 +5,9 @@ from astrbot.core.star.register import (
    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_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
@@ -14,6 +16,7 @@ from astrbot.core.star.register import (
 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

 __all__ = [
    'command',
@@ -27,9 +30,12 @@ __all__ = [
    'PlatformAdapterTypeFilter',
    'PlatformAdapterType',
    'PermissionTypeFilter',
+    'CustomFilter',
+    'custom_filter',
    'PermissionType',
    'on_llm_request',
    'llm_tool',
    'on_decorating_result',
-    'after_message_sent'
+    'after_message_sent',
+    'on_llm_response'
 ]
--- a/astrbot/api/platform/init.py
+++ b/astrbot/api/platform/init.py
@@ -2,4 +2,5 @@ from astrbot.core.platform import (
    AstrMessageEvent, Platform, AstrBotMessage, MessageMember, MessageType, PlatformMetadata
 )

-from astrbot.core.platform.register import register_platform_adapter
+from astrbot.core.platform.register import register_platform_adapter
+from astrbot.core.message.components import *
--- a/astrbot/api/provider/init.py
+++ b/astrbot/api/provider/init.py
@@ -1,2 +1,2 @@
 from astrbot.core.provider import Provider, STTProvider, Personality
-from astrbot.core.provider.entites import ProviderRequest, ProviderType, ProviderMetaData
+from astrbot.core.provider.entites import ProviderRequest, ProviderType, ProviderMetaData, LLMResponse
--- a/astrbot/core/init.py
+++ b/astrbot/core/init.py
@@ -11,7 +11,8 @@ from astrbot.core.config import AstrBotConfig
 os.makedirs("data", exist_ok=True)

 astrbot_config = AstrBotConfig()
-html_renderer = HtmlRenderer()
+t2i_base_url = astrbot_config.get('t2i_endpoint', 'https://t2i.soulter.top/text2img')
+html_renderer = HtmlRenderer(t2i_base_url)
 logger = LogManager.GetLogger(log_name='astrbot')

 if os.environ.get('TESTING', ""):
--- a/astrbot/core/config/astrbot_config.py
+++ b/astrbot/core/config/astrbot_config.py
@@ -2,7 +2,7 @@ import os
 import json
 import logging
 import enum
-from .default import DEFAULT_CONFIG
+from .default import DEFAULT_CONFIG, DEFAULT_VALUE_MAP
 from typing import Dict

 ASTRBOT_CONFIG_PATH = "data/cmd_config.json"
@@ -13,29 +13,72 @@ class RateLimitStrategy(enum.Enum):
    DISCARD = "discard"

 class AstrBotConfig(dict):
-    '''从配置文件中加载的配置，支持直接通过点号操作符访问配置项'''
+    '''从配置文件中加载的配置，支持直接通过点号操作符访问根配置项。
    
-    def __init__(self):
+    - 初始化时会将传入的 default_config 与配置文件进行比对，如果配置文件中缺少配置项则会自动插入默认值并进行一次写入操作。会递归检查配置项。
+    - 如果配置文件路径对应的文件不存在，则会自动创建并写入默认配置。
+    - 如果传入了 schema，将会通过 schema 解析出 default_config，此时传入的 default_config 会被忽略。
+    '''
+    
+    def __init__(
+        self, 
+        config_path: str = ASTRBOT_CONFIG_PATH, 
+        default_config: dict = DEFAULT_CONFIG,
+        schema: dict = None
+    ):
        super().__init__()
+        
+        # 调用父类的 __setattr__ 方法，防止保存配置时将此属性写入配置文件
+        object.__setattr__(self, 'config_path', config_path)
+        object.__setattr__(self, 'default_config', default_config)
+        object.__setattr__(self, 'schema', schema)
+        
+        if schema:
+            default_config = self._config_schema_to_default_config(schema)
+        
        if not self.check_exist():
            '''不存在时载入默认配置'''
-            with open(ASTRBOT_CONFIG_PATH, "w", encoding="utf-8-sig") as f:
-                json.dump(DEFAULT_CONFIG, f, indent=4, ensure_ascii=False)
+            with open(config_path, "w", encoding="utf-8-sig") as f:
+                json.dump(default_config, f, indent=4, ensure_ascii=False)

-        with open(ASTRBOT_CONFIG_PATH, "r", encoding="utf-8-sig") as f:
+        with open(config_path, "r", encoding="utf-8-sig") as f:
            conf_str = f.read()
            if conf_str.startswith(u'/ufeff'): # remove BOM
                conf_str = conf_str.encode('utf8')[3:].decode('utf8')
            conf = json.loads(conf_str)
        
        # 检查配置完整性，并插入
-        has_new = self.check_config_integrity(DEFAULT_CONFIG, conf)
+        has_new = self.check_config_integrity(default_config, conf)
        self.update(conf)
        if has_new:
            self.save_config()
            
        self.update(conf)
-            
+
+    def _config_schema_to_default_config(self, schema: dict) -> dict:
+        '''将 Schema 转换成 Config'''
+        conf = {}
+        
+        def _parse_schema(schema: dict, conf: 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()}")
+                if 'default' in v:
+                    default = v['default']
+                else:
+                    default = DEFAULT_VALUE_MAP[v['type']]
+                
+                if v['type'] == 'object':
+                    conf[k] = {}
+                    _parse_schema(v['items'], conf[k])
+                else:
+                    conf[k] = default
+                    
+        _parse_schema(schema, conf)
+
+        return conf
+
+
    def check_config_integrity(self, refer_conf: Dict, conf: Dict, path=""):
        '''检查配置完整性，如果有新的配置项则返回 True'''
        has_new = False
@@ -61,7 +104,7 @@ class AstrBotConfig(dict):
        '''
        if replace_config:
            self.update(replace_config)
-        with open(ASTRBOT_CONFIG_PATH, "w", encoding="utf-8-sig") as f:
+        with open(self.config_path, "w", encoding="utf-8-sig") as f:
            json.dump(self, f, indent=2, ensure_ascii=False)
            
    def __getattr__(self, item):
@@ -81,4 +124,4 @@ class AstrBotConfig(dict):
        self[key] = value

    def check_exist(self) -> bool:
-        return os.path.exists(ASTRBOT_CONFIG_PATH)
+        return os.path.exists(self.config_path)
--- a/astrbot/core/config/default.py
+++ b/astrbot/core/config/default.py
@@ -2,7 +2,7 @@
 如需修改配置，请在 `data/cmd_config.json` 中修改或者在管理面板中可视化修改。
 """

-VERSION = "3.4.13"
+VERSION = "3.4.30"
 DB_PATH = "data/data_v3.db"

 # 默认配置
@@ -28,15 +28,21 @@ DEFAULT_CONFIG = {
        "segmented_reply": {
            "enable": False,
            "only_llm_result": True,
+            "interval_method": "random",
            "interval": "1.5,3.5",
-            "regex": ".*?[。？！~…]+|.+$"
-        }
+            "log_base": 2.6,
+            "words_count_threshold": 150,
+            "regex": ".*?[。？！~…]+|.+$",
+            "content_cleanup_rule": "",
+        },
+        "no_permission_reply": True,
    },
    "provider": [],
    "provider_settings": {
        "enable": True,
        "wake_prefix": "",
        "web_search": False,
+        "web_search_link": False,
        "identifier": False,
        "datetime_system_prompt": True,
        "default_personality": "default",
@@ -50,17 +56,36 @@ DEFAULT_CONFIG = {
        "enable": False,
        "provider_id": "",
    },
+    "provider_ltm_settings": {
+        "group_icl_enable": False,
+        "group_message_max_cnt": 300,
+        "image_caption": False,
+        "image_caption_provider_id": "",
+        "image_caption_prompt": "Please describe the image using Chinese.",
+        "active_reply": {
+            "enable": False,
+            "method": "possibility_reply",
+            "possibility_reply": 0.1,
+            "prompt": "",
+            "whitelist": []
+        }
+    },
    "content_safety": {
+        "also_use_in_response": False,
        "internal_keywords": {"enable": True, "extra_keywords": []},
        "baidu_aip": {"enable": False, "app_id": "", "api_key": "", "secret_key": ""},
    },
-    "admins_id": [],
+    "admins_id": [
+        "astrbot"
+    ],
    "t2i": False,
+    "t2i_word_threshold": 150,
    "http_proxy": "",
    "dashboard": {
        "enable": True,
        "username": "astrbot",
        "password": "77b90590a8945a7d36c963981a307dc9",
+        "port": 6185
    },
    "platform": [],
    "wake_prefix": ["/"],
@@ -69,14 +94,7 @@ DEFAULT_CONFIG = {
    "pip_install_arg": "",
    "plugin_repo_mirror": "",
    "knowledge_db": {},
-    "persona": [
-        {
-            "name": "default",
-            "prompt": "如果用户寻求帮助或者打招呼，请告诉他可以用 /help 查看 AstrBot 帮助。",
-            "begin_dialogs": [],
-            "mood_imitation_dialogs": [],
-        }
-    ],
+    "persona": [],
 }


@@ -98,29 +116,45 @@ CONFIG_METADATA_2 = {
                        "enable_group_c2c": True,
                        "enable_guild_direct_message": True,
                    },
+                    "qq_official_webhook(QQ)": {
+                        "id": "default",
+                        "type": "qq_official_webhook",
+                        "enable": False,
+                        "appid": "",
+                        "secret": "",
+                        "port": 6196
+                    },
                    "aiocqhtp(QQ)": {
                        "id": "default",
                        "type": "aiocqhttp",
                        "enable": False,
-                        "ws_reverse_host": "",
+                        "ws_reverse_host": "0.0.0.0",
                        "ws_reverse_port": 6199,
                    },
-                    "vchat(微信)": {"id": "default", "type": "vchat", "enable": False},
                    "gewechat(微信)": {
                        "id": "gwchat",
                        "type": "gewechat",
                        "enable": False,
                        "base_url": "http://localhost:2531",
                        "nickname": "soulter",
-                        "host": "localhost",
+                        "host": "这里填写你的局域网IP或者公网服务器IP",
                        "port": 11451,
                    },
+                    "lark(飞书)": {
+                        "id": "lark",
+                        "type": "lark",
+                        "enable": False,
+                        "lark_bot_name": "",
+                        "app_id": "",
+                        "app_secret": "",
+                        "domain": "https://open.feishu.cn"
+                    },
                },
                "items": {
                    "id": {
                        "description": "ID",
                        "type": "string",
-                        "hint": "提供商 ID 名，用于在多实例下方便管理和识别。自定义，ID 不能重复。",
+                        "hint": "用于在多实例下方便管理和识别。自定义，ID 不能重复。",
                    },
                    "type": {
                        "description": "适配器类型",
@@ -162,6 +196,12 @@ CONFIG_METADATA_2 = {
                        "type": "int",
                        "hint": "aiocqhttp 适配器的反向 Websocket 端口。",
                    },
+                    "lark_bot_name": {
+                        "description": "飞书机器人的名字",
+                        "type": "string",
+                        "hint": "请务必填对，否则 @ 机器人将无法唤醒，只能通过前缀唤醒。",
+                        "obvious_hint": True
+                    }
                },
            },
            "platform_settings": {
@@ -188,6 +228,11 @@ CONFIG_METADATA_2 = {
                            },
                        },
                    },
+                    "no_permission_reply": {
+                        "description": "无权限回复",
+                        "type": "bool",
+                        "hint": "启用后，当用户没有权限执行某个操作时，机器人会回复一条消息。",
+                    },
                    "segmented_reply": {
                        "description": "分段回复",
                        "type": "object",
@@ -200,10 +245,26 @@ CONFIG_METADATA_2 = {
                                "description": "仅对 LLM 结果分段",
                                "type": "bool",
                            },
+                            "interval_method": {
+                                "description": "间隔时间计算方法",
+                                "type": "string",
+                                "options": ["random", "log"],
+                                "hint": "分段回复的间隔时间计算方法。random 为随机时间，log 为根据消息长度计算，$y=log_{log\_base}(x)$，x为字数，y的单位为秒。",
+                            },
                            "interval": {
                                "description": "随机间隔时间(秒)",
                                "type": "string",
-                                "hint": "每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
+                                "hint": "`random` 方法用。每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
+                            },
+                            "log_base": {
+                                "description": "对数函数底数",
+                                "type": "float",
+                                "hint": "`log` 方法用。对数函数的底数。默认为 2.6",
+                            },
+                            "words_count_threshold": {
+                                "description": "字数阈值",
+                                "type": "int",
+                                "hint": "超过这个字数的消息不会被分段回复。默认为 150",
                            },
                            "regex": {
                                "description": "正则表达式",
@@ -211,6 +272,12 @@ CONFIG_METADATA_2 = {
                                "obvious_hint": True,
                                "hint": "用于分隔一段消息。默认情况下会根据句号、问号等标点符号分隔。re.findall(r'<regex>', text)",
                            },
+                            "content_cleanup_rule": {
+                                "description": "过滤分段后的内容",
+                                "type": "string",
+                                "obvious_hint": True,
+                                "hint": "移除分段后的内容中的指定的内容。支持正则表达式。如填写 `[。？！]` 将移除所有的句号、问号、感叹号。re.sub(r'<regex>', '', text)",
+                            },
                        },
                    },
                    "reply_prefix": {
@@ -230,8 +297,9 @@ CONFIG_METADATA_2 = {
                    "id_whitelist": {
                        "description": "ID 白名单",
                        "type": "list",
-                        "items": {"type": "int"},
-                        "hint": "填写后，将只处理所填写的 ID 发来的消息事件。为空时表示不启用白名单过滤。可以使用 /myid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978",
+                        "items": {"type": "string"},
+                        "obvious_hint": True,
+                        "hint": "AstrBot 只处理所填写的 ID 发来的消息事件。为空时不启用白名单过滤。可以使用 /sid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978。管理员可使用 /wl 添加白名单",
                    },
                    "id_whitelist_log": {
                        "description": "打印白名单日志",
@@ -259,15 +327,21 @@ CONFIG_METADATA_2 = {
                    "path_mapping": {
                        "description": "路径映射",
                        "type": "list",
+                        "items": {"type": "string"},
                        "obvious_hint": True,
                        "hint": "此功能解决由于文件系统不一致导致路径不存在的问题。格式为 <原路径>:<映射路径>。如 `/app/.config/QQ:/var/lib/docker/volumes/xxxx/_data`。这样，当消息平台下发的事件中图片和语音路径以 `/app/.config/QQ` 开头时，开头被替换为 `/var/lib/docker/volumes/xxxx/_data`。这在 AstrBot 或者平台协议端使用 Docker 部署时特别有用。",
-                    }
+                    },
                },
            },
            "content_safety": {
                "description": "内容安全",
                "type": "object",
                "items": {
+                    "also_use_in_response": {
+                        "description": "对大模型响应安全审核",
+                        "type": "bool",
+                        "hint": "启用后，大模型的响应也会通过内容安全审核。",
+                    },
                    "baidu_aip": {
                        "description": "百度内容审核配置",
                        "type": "object",
@@ -313,15 +387,51 @@ CONFIG_METADATA_2 = {
                "type": "list",
                "config_template": {
                    "openai": {
-                        "id": "default",
+                        "id": "openai",
                        "type": "openai_chat_completion",
                        "enable": True,
                        "key": [],
-                        "api_base": "",
+                        "api_base": "https://api.openai.com/v1",
+                        "timeout": 120,
                        "model_config": {
                            "model": "gpt-4o-mini",
                        },
                    },
+                    "azure_openai": {
+                        "id": "azure",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "api_version": "2024-05-01-preview",
+                        "key": [],
+                        "api_base": "",
+                        "timeout": 120,
+                        "model_config": {
+                            "model": "gpt-4o-mini",
+                        },
+                    },
+                    "xAI": {
+                        "id": "xai",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "api_base": "https://api.x.ai/v1",
+                        "timeout": 120,
+                        "model_config": {
+                            "model": "grok-2-latest",
+                        },
+                    },
+                    "anthropic(claude)": {
+                        "id": "claude",
+                        "type": "anthropic_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "api_base": "https://api.anthropic.com/v1",
+                        "timeout": 120,
+                        "model_config": {
+                            "model": "claude-3-5-sonnet-latest",
+                            "max_tokens": 4096,
+                        },
+                    },
                    "ollama": {
                        "id": "ollama_default",
                        "type": "openai_chat_completion",
@@ -338,6 +448,7 @@ CONFIG_METADATA_2 = {
                        "enable": True,
                        "key": [],
                        "api_base": "https://generativelanguage.googleapis.com/v1beta/openai/",
+                        "timeout": 120,
                        "model_config": {
                            "model": "gemini-1.5-flash",
                        },
@@ -348,6 +459,7 @@ CONFIG_METADATA_2 = {
                        "enable": True,
                        "key": [],
                        "api_base": "https://generativelanguage.googleapis.com/",
+                        "timeout": 120,
                        "model_config": {
                            "model": "gemini-1.5-flash",
                        },
@@ -358,6 +470,7 @@ CONFIG_METADATA_2 = {
                        "enable": True,
                        "key": [],
                        "api_base": "https://api.deepseek.com/v1",
+                        "timeout": 120,
                        "model_config": {
                            "model": "deepseek-chat",
                        },
@@ -367,11 +480,34 @@ CONFIG_METADATA_2 = {
                        "type": "zhipu_chat_completion",
                        "enable": True,
                        "key": [],
+                        "timeout": 120,
                        "api_base": "https://open.bigmodel.cn/api/paas/v4/",
                        "model_config": {
                            "model": "glm-4-flash",
                        },
                    },
+                    "siliconflow": {
+                        "id": "siliconflow",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "timeout": 120,
+                        "api_base": "https://api.siliconflow.cn/v1",
+                        "model_config": {
+                            "model": "deepseek-ai/DeepSeek-V3",
+                        },
+                    },
+                    "moonshot(kimi)": {
+                        "id": "moonshot",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "timeout": 120,
+                        "api_base": "https://api.moonshot.cn/v1",
+                        "model_config": {
+                            "model": "moonshot-v1-8k",
+                        },
+                    },
                    "llmtuner": {
                        "id": "llmtuner_default",
                        "type": "llm_tuner",
@@ -390,6 +526,27 @@ CONFIG_METADATA_2 = {
                        "dify_api_key": "",
                        "dify_api_base": "https://api.dify.ai/v1",
                        "dify_workflow_output_key": "",
+                        "dify_query_input_key": "astrbot_text_query",
+                        "variables": {},
+                        "timeout": 60,
+                    },
+                    "dashscope": {
+                        "id": "dashscope",
+                        "type": "dashscope",
+                        "enable": True,
+                        "dashscope_app_type": "agent",
+                        "dashscope_api_key": "",
+                        "dashscope_app_id": "",
+                        "variables": {},
+                        "timeout": 60,
+                    },
+                    "fastgpt": {
+                        "id": "fastgpt",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "api_base": "https://api.fastgpt.in/api/v1",
+                        "timeout": 60,
                    },
                    "whisper(API)": {
                        "id": "whisper",
@@ -413,9 +570,57 @@ CONFIG_METADATA_2 = {
                        "api_key": "",
                        "api_base": "",
                        "model": "tts-1",
+                        "openai-tts-voice": "alloy",
+                        "timeout": "20",
+                    },
+                    "fishaudio_tts(API)": {
+                        "id": "fishaudio_tts",
+                        "type": "fishaudio_tts_api",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "https://api.fish-audio.cn/v1",
+                        "fishaudio-tts-character": "可莉",
+                        "timeout": "20",
                    },
                },
                "items": {
+                    "variables": {
+                        "description": "工作流固定输入变量",
+                        "type": "object",
+                        "obvious_hint": True,
+                        "hint": "可选。工作流固定输入变量，将会作为工作流的输入。也可以在对话时使用 /set 指令动态设置变量。如果变量名冲突，优先使用动态设置的变量。",
+                    },
+                    # "fastgpt_app_type": {
+                    #     "description": "应用类型",
+                    #     "type": "string",
+                    #     "hint": "FastGPT 应用的应用类型。",
+                    #     "options": ["agent", "workflow", "plugin"],
+                    #     "obvious_hint": True,
+                    # },
+                    "dashscope_app_type": {
+                        "description": "应用类型",
+                        "type": "string",
+                        "hint": "阿里云百炼应用的应用类型。",
+                        "options": ["agent", "agent-arrange", "dialog-workflow", "task-workflow"],
+                        "obvious_hint": True,
+                    },
+                    "timeout": {
+                        "description": "超时时间",
+                        "type": "int",
+                        "hint": "超时时间，单位为秒。",
+                    },
+                    "openai-tts-voice": {
+                        "description": "voice",
+                        "type": "string",
+                        "obvious_hint": True,
+                        "hint": "OpenAI TTS 的声音。OpenAI 默认支持：'alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'",
+                    },
+                    "fishaudio-tts-character": {
+                        "description": "character",
+                        "type": "string",
+                        "obvious_hint": True,
+                        "hint": "fishaudio TTS 的角色。默认为可莉。更多角色请访问：https://fish.audio/zh-CN/discovery",
+                    },
                    "whisper_hint": {
                        "description": "本地部署 Whisper 模型须知",
                        "type": "string",
@@ -446,7 +651,7 @@ CONFIG_METADATA_2 = {
                    "api_base": {
                        "description": "API Base URL",
                        "type": "string",
-                        "hint": "API Base URL 请在在模型提供商处获得。如使用时出现了 404 报错，可以尝试在地址末尾加上 `/v1`。",
+                        "hint": "API Base URL 请在在模型提供商处获得。如出现 404 报错，尝试在地址末尾加上 /v1",
                        "obvious_hint": True,
                    },
                    "base_model_path": {
@@ -490,6 +695,7 @@ CONFIG_METADATA_2 = {
                            "temperature": {"description": "温度", "type": "float"},
                            "top_p": {"description": "Top P值", "type": "float"},
                        },
+                        "editable": True,
                    },
                    "dify_api_key": {
                        "description": "API Key",
@@ -512,6 +718,12 @@ CONFIG_METADATA_2 = {
                        "type": "string",
                        "hint": "Dify Workflow 输出变量名。当应用类型为 workflow 时才使用。默认为 astrbot_wf_output。",
                    },
+                    "dify_query_input_key": {
+                        "description": "Prompt 输入变量名",
+                        "type": "string",   
+                        "hint": "发送的消息文本内容对应的输入变量名。默认为 astrbot_text_query。",
+                        "obvious": True,
+                    }
                },
            },
            "provider_settings": {
@@ -532,16 +744,25 @@ CONFIG_METADATA_2 = {
                    "web_search": {
                        "description": "启用网页搜索",
                        "type": "bool",
-                        "hint": "能访问 Google 时效果最佳。如果 Google 访问失败，程序会依次访问 Bing, Sogo 搜索引擎。",
+                        "obvious_hint": True,
+                        "hint": "能访问 Google 时效果最佳（国内需要在 `其他配置` 开启 HTTP 代理）。如果 Google 访问失败，程序会依次访问 Bing, Sogo 搜索引擎。",
+                    },
+                    "web_search_link": {
+                        "description": "网页搜索引用链接",
+                        "type": "bool",
+                        "obvious_hint": True,
+                        "hint": "开启后，将会传入网页搜索结果的链接给模型，并引导模型输出引用链接。",
                    },
                    "identifier": {
                        "description": "启动识别群员",
                        "type": "bool",
+                        "obvious_hint": True,
                        "hint": "在 Prompt 前加上群成员的名字以让模型更好地了解群聊状态。启用将略微增加 token 开销。",
                    },
                    "datetime_system_prompt": {
                        "description": "启用日期时间系统提示",
                        "type": "bool",
+                        "obvious_hint": True,
                        "hint": "启用后，会在系统提示词中加上当前机器的日期时间。",
                    },
                    "default_personality": {
@@ -583,15 +804,15 @@ CONFIG_METADATA_2 = {
                    "begin_dialogs": {
                        "description": "预设对话",
                        "type": "list",
-                        "items": {},
-                        "hint": "可选。在每个对话前会插入这些预设对话。格式要求：第一句为用户，第二句为助手，以此类推。",
+                        "items": {"type": "string"},
+                        "hint": "可选。在每个对话前会插入这些预设对话。对话需要成对(用户和助手)，输入完一个角色的内容之后按【回车】。需要偶数个对话",
                        "obvious_hint": True,
                    },
                    "mood_imitation_dialogs": {
                        "description": "对话风格模仿",
                        "type": "list",
-                        "items": {},
-                        "hint": "旨在让模型尽可能模仿学习到所填写的对话的语气风格。格式和 `预设对话` 一样。",
+                        "items": {"type": "string"},
+                        "hint": "旨在让模型尽可能模仿学习到所填写的对话的语气风格。格式和 `预设对话` 一致。对话需要成对(用户和助手)，输入完一个角色的内容之后按【回车】。需要偶数个对话",
                        "obvious_hint": True,
                    },
                },
@@ -630,6 +851,77 @@ CONFIG_METADATA_2 = {
                    },
                },
            },
+            "provider_ltm_settings": {
+                "description": "聊天记忆增强(Beta)",
+                "type": "object",
+                "items": {
+                    "group_icl_enable": {
+                        "description": "群聊内记录各群员对话",
+                        "type": "bool",
+                        "obvious_hint": True,
+                        "hint": "启用后，会记录群聊内各群员的对话。使用 /reset 命令清除记录。推荐使用 gpt-4o-mini 模型。",
+                    },
+                    "group_message_max_cnt": {
+                        "description": "群聊消息最大数量",
+                        "type": "int",
+                        "obvious_hint": True,
+                        "hint": "群聊消息最大数量。超过此数量后，会自动清除旧消息。",
+                    },
+                    "image_caption": {
+                        "description": "启用图像转述(需要模型支持)",
+                        "type": "bool",
+                        "obvious_hint": True,
+                        "hint": "启用后，当接收到图片消息时，会使用模型先将图片转述为文字再进行后续处理。推荐使用 gpt-4o-mini 模型。",
+                    },
+                    "image_caption_provider_id": {
+                        "description": "图像转述提供商 ID",
+                        "type": "string",
+                        "obvious_hint": True,
+                        "hint": "可选。图像转述提供商 ID。如为空将选择聊天使用的提供商。",
+                    },
+                    "image_caption_prompt": {
+                        "description": "图像转述提示词",
+                        "type": "string",
+                    },
+                    "active_reply": {
+                        "description": "主动回复",
+                        "type": "object",
+                        "items": {
+                            "enable": {
+                                "description": "启用主动回复",
+                                "type": "bool",
+                                "obvious_hint": True,
+                                "hint": "启用后，会根据触发概率主动回复群聊内的对话。QQ官方API(qq_official)不可用",
+                            },
+                            "whitelist": {
+                                "description": "主动回复白名单",
+                                "type": "list",
+                                "items": {"type": "string"},
+                                "obvious_hint": True,
+                                "hint": "启用后，只有在白名单内的群聊会被主动回复。为空时不启用白名单过滤。需要通过 /sid 获取 SID 添加到这里。",
+                            },
+                            "method": {
+                                "description": "回复方法",
+                                "type": "string",
+                                "options": ["possibility_reply"],
+                                "hint": "回复方法。possibility_reply 为根据概率回复",
+                            },
+                            "possibility_reply": {
+                                "description": "回复概率",
+                                "type": "float",
+                                "obvious_hint": True,
+                                "hint": "回复概率。当回复方法为 possibility_reply 时有效。当概率 >= 1 时，每条消息都会回复。",
+                            },
+                            "prompt": {
+                                "description": "提示词",
+                                "type": "string",
+                                "obvious_hint": True,
+                                "hint": "提示词。当提示词为空时，如果触发回复，则向 LLM 请求的是触发的消息的内容；否则是提示词。此项可以和定时回复（暂未实现）配合使用。",
+                            },
+                        },
+                    },
+                },
+            },
        },
    },
    "misc_config_group": {
@@ -639,18 +931,24 @@ CONFIG_METADATA_2 = {
                "description": "机器人唤醒前缀",
                "type": "list",
                "items": {"type": "string"},
-                "hint": "在不 @ 机器人的情况下，可以通过外加消息前缀来唤醒机器人。",
+                "obvious_hint": True,
+                "hint": "在不 @ 机器人的情况下，可以通过外加消息前缀来唤醒机器人。更改此配置将影响整个 Bot 的功能唤醒，包括所有指令。如果您不保留 `/`，则内置指令（help等）将需要通过您的唤醒前缀来触发。",
            },
            "t2i": {
                "description": "文本转图像",
                "type": "bool",
                "hint": "启用后，超出一定长度的文本将会通过 AstrBot API 渲染成 Markdown 图片发送。可以缓解审核和消息过长刷屏的问题，并提高 Markdown 文本的可读性。",
            },
+            "t2i_word_threshold": {
+                "description": "文本转图像字数阈值",
+                "type": "int",
+                "hint": "超出此字符长度的文本将会被转换成图片。字数不能低于 50。",
+            },
            "admins_id": {
                "description": "管理员 ID",
                "type": "list",
-                "items": {"type": "int"},
-                "hint": "管理员 ID 列表，管理员可以使用一些特权命令，如 `update`, `plugin` 等。ID 可以通过 `/myid` 指令获得。回车添加，可添加多个。",
+                "items": {"type": "string"},
+                "hint": "管理员 ID 列表，管理员可以使用一些特权命令，如 `update`, `plugin` 等。ID 可以通过 `/sid` 指令获得。回车添加，可添加多个。",
            },
            "http_proxy": {
                "description": "HTTP 代理",
@@ -676,7 +974,8 @@ CONFIG_METADATA_2 = {
            "plugin_repo_mirror": {
                "description": "插件仓库镜像",
                "type": "string",
-                "hint": "插件仓库的镜像地址，用于加速插件的下载。",
+                "hint": "已废弃，请使用管理面板->设置页的代理地址选择",
+                "obvious_hint": True,
                "options": [
                    "default",
                    "https://ghp.ci/",
--- a/astrbot/core/conversation_mgr.py
+++ b/astrbot/core/conversation_mgr.py
@@ -0,0 +1,119 @@
+import uuid
+import json
+import asyncio
+from astrbot.core import sp
+from typing import Dict, List
+from astrbot.core.db import BaseDatabase
+from astrbot.core.db.po import Conversation
+
+class ConversationManager():
+    '''负责管理会话与 LLM 的对话，某个会话当前正在用哪个对话。'''
+    def __init__(self, db_helper: BaseDatabase):
+        self.session_conversations: Dict[str, str] = sp.get("session_conversation", {})
+        self.db = db_helper
+        self.save_interval = 60  # 每 60 秒保存一次
+        self._start_periodic_save()
+                
+    def _start_periodic_save(self):
+        asyncio.create_task(self._periodic_save())
+
+    async def _periodic_save(self):
+        while True:
+            await asyncio.sleep(self.save_interval)
+            self._save_to_storage()
+
+    def _save_to_storage(self):
+        sp.put("session_conversation", self.session_conversations)
+
+    async def new_conversation(self, unified_msg_origin: str) -> str:
+        '''新建对话，并将当前会话的对话转移到新对话'''
+        conversation_id = str(uuid.uuid4())
+        self.db.new_conversation(
+            user_id=unified_msg_origin,
+            cid=conversation_id
+        )
+        self.session_conversations[unified_msg_origin] = conversation_id
+        sp.put("session_conversation", self.session_conversations)
+        return conversation_id
+    
+    async def switch_conversation(self, unified_msg_origin: str, conversation_id: str):
+        '''切换会话的对话'''
+        self.session_conversations[unified_msg_origin] = conversation_id
+        sp.put("session_conversation", self.session_conversations)
+        
+    async def delete_conversation(self, unified_msg_origin: str, conversation_id: str=None):
+        '''删除会话的对话，当 conversation_id 为 None 时删除会话当前的对话'''
+        conversation_id = self.session_conversations.get(unified_msg_origin)
+        if conversation_id:
+            self.db.delete_conversation(
+                user_id=unified_msg_origin,
+                cid=conversation_id
+            )
+            del self.session_conversations[unified_msg_origin]
+            sp.put("session_conversation", self.session_conversations)
+            
+    async def get_curr_conversation_id(self, unified_msg_origin: str) -> str:
+        '''获取会话当前的对话 ID'''
+        return self.session_conversations.get(unified_msg_origin, None)
+    
+    async def get_conversation(self, unified_msg_origin: str, conversation_id: str) -> Conversation:
+        '''获取会话的对话'''
+        return self.db.get_conversation_by_user_id(unified_msg_origin, conversation_id)
+    
+    async def get_conversations(self, unified_msg_origin: str) -> List[Conversation]:
+        '''获取会话的所有对话'''
+        return self.db.get_conversations(unified_msg_origin)
+    
+    async def update_conversation(self, unified_msg_origin: str, conversation_id: str, history: List[Dict]):
+        '''更新会话的对话'''
+        if conversation_id:
+            self.db.update_conversation(
+                user_id=unified_msg_origin,
+                cid=conversation_id,
+                history=json.dumps(history)
+            )
+            
+    async def update_conversation_title(self, unified_msg_origin: str, title: str):
+        '''更新会话的对话标题'''
+        conversation_id = self.session_conversations.get(unified_msg_origin)
+        if conversation_id:
+            self.db.update_conversation_title(
+                user_id=unified_msg_origin,
+                cid=conversation_id,
+                title=title
+            )
+    
+    async def update_conversation_persona_id(self, unified_msg_origin: str, persona_id: str):
+        '''更新会话的对话 Persona ID'''
+        conversation_id = self.session_conversations.get(unified_msg_origin)
+        if conversation_id:
+            self.db.update_conversation_persona_id(
+                user_id=unified_msg_origin,
+                cid=conversation_id,
+                persona_id=persona_id
+            )
+            
+    async def get_human_readable_context(self, unified_msg_origin, conversation_id, page=1, page_size=10):
+        conversation = await self.get_conversation(unified_msg_origin, conversation_id)
+        history = json.loads(conversation.history)
+
+        contexts = []
+        temp_contexts = []
+        for record in history:
+            if record['role'] == "user":
+                temp_contexts.append(f"User: {record['content']}")
+            elif record['role'] == "assistant":
+                temp_contexts.append(f"Assistant: {record['content']}")
+                contexts.insert(0, temp_contexts)
+                temp_contexts = []
+
+        # 展平 contexts 列表
+        contexts = [item for sublist in contexts for item in sublist]
+
+        # 计算分页
+        paged_contexts = contexts[(page-1)*page_size:page*page_size]
+        total_pages = len(contexts) // page_size
+        if len(contexts) % page_size != 0:
+            total_pages += 1
+        
+        return paged_contexts, total_pages
--- a/astrbot/core/core_lifecycle.py
+++ b/astrbot/core/core_lifecycle.py
@@ -18,17 +18,17 @@ from astrbot.core.updator import AstrBotUpdator
 from astrbot.core import logger
 from astrbot.core.config.default import VERSION
 from astrbot.core.rag.knowledge_db_mgr import KnowledgeDBManager
-
+from astrbot.core.conversation_mgr import ConversationManager
 class AstrBotCoreLifecycle:
    def __init__(self, log_broker: LogBroker, db: BaseDatabase):
        self.log_broker = log_broker
        self.astrbot_config = astrbot_config
        self.db = db
        
-        if self.astrbot_config['http_proxy']:
-            os.environ['https_proxy'] = self.astrbot_config['http_proxy']
-            os.environ['http_proxy'] = self.astrbot_config['http_proxy']
-    
+        os.environ['https_proxy'] = self.astrbot_config['http_proxy']
+        os.environ['http_proxy'] = self.astrbot_config['http_proxy']
+        os.environ['no_proxy'] = 'localhost,127.0.0.1'
+        
    async def initialize(self):
        logger.info("AstrBot v"+ VERSION)
        if os.environ.get("TESTING", ""):
@@ -44,12 +44,15 @@ class AstrBotCoreLifecycle:
        
        self.knowledge_db_manager = KnowledgeDBManager(self.astrbot_config)
        
+        self.conversation_manager = ConversationManager(self.db)
+        
        self.star_context = Context(
            self.event_queue, 
            self.astrbot_config, 
            self.db,
            self.provider_manager,
            self.platform_manager,
+            self.conversation_manager,
            self.knowledge_db_manager
        )
        self.plugin_manager = PluginManager(self.star_context, self.astrbot_config)
--- a/astrbot/core/db/init.py
+++ b/astrbot/core/db/init.py
@@ -1,7 +1,7 @@
 import abc
 from dataclasses import dataclass
 from typing import List
-from astrbot.core.db.po import Stats, LLMHistory, ATRIVision, WebChatConversation
+from astrbot.core.db.po import Stats, LLMHistory, ATRIVision, Conversation

@dataclass
 class BaseDatabase(abc.ABC):
@@ -79,25 +79,35 @@ class BaseDatabase(abc.ABC):
        raise NotImplementedError
    
    @abc.abstractmethod
-    def get_webchat_conversation_by_user_id(self, user_id: str, cid: str) -> WebChatConversation:
-        '''通过 user_id 和 cid 获取 WebChatConversation'''
+    def get_conversation_by_user_id(self, user_id: str, cid: str) -> Conversation:
+        '''通过 user_id 和 cid 获取 Conversation'''
        raise NotImplementedError
    
    @abc.abstractmethod
-    def webchat_new_conversation(self, user_id: str, cid: str):
-        '''新建 WebChatConversation'''
+    def new_conversation(self, user_id: str, cid: str):
+        '''新建 Conversation'''
        raise NotImplementedError
    
    @abc.abstractmethod
-    def get_webchat_conversations(self, user_id: str) -> List[WebChatConversation]:
+    def get_conversations(self, user_id: str) -> List[Conversation]:
        raise NotImplementedError

    @abc.abstractmethod
-    def update_webchat_conversation(self, user_id: str, cid: str, history: str):
-        '''更新 WebChatConversation'''
+    def update_conversation(self, user_id: str, cid: str, history: str):
+        '''更新 Conversation'''
        raise NotImplementedError
    
    @abc.abstractmethod
-    def delete_webchat_conversation(self, user_id: str, cid: str):
-        '''删除 WebChatConversation'''
+    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
--- a/astrbot/core/db/po.py
+++ b/astrbot/core/db/po.py
@@ -33,16 +33,16 @@ class Stats():
    command: List[Command] = field(default_factory=list)
    llm: List[Provider] = field(default_factory=list)
    
-'''LLM 聊天时持久化的信息'''
-
@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
@@ -53,13 +53,18 @@ class ATRIVision():
    sender_nickname: str
    timestamp: int = -1
    
-    
-
@dataclass
-class WebChatConversation():
+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 = ""
--- a/astrbot/core/db/sqlite.py
+++ b/astrbot/core/db/sqlite.py
@@ -6,7 +6,7 @@ from astrbot.core.db.po import (
    Stats,
    LLMHistory,
    ATRIVision,
-    WebChatConversation
+    Conversation
 )
 from . import BaseDatabase
 from typing import Tuple
@@ -25,6 +25,37 @@ class SQLiteDatabase(BaseDatabase):
        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)
@@ -202,7 +233,7 @@ class SQLiteDatabase(BaseDatabase):
        return Stats(platform, [], [])
    
    
-    def get_webchat_conversation_by_user_id(self, user_id: str, cid: str) -> WebChatConversation:
+    def get_conversation_by_user_id(self, user_id: str, cid: str) -> Conversation:
        try:
            c = self.conn.cursor()
        except sqlite3.ProgrammingError:
@@ -216,9 +247,13 @@ class SQLiteDatabase(BaseDatabase):
        
        res = c.fetchone()
        c.close()
-        return WebChatConversation(*res)
+        
+        if not res:
+            return
+        
+        return Conversation(*res)
    
-    def webchat_new_conversation(self, user_id: str, cid: str):
+    def new_conversation(self, user_id: str, cid: str):
        history = "[]"
        updated_at = int(time.time())
        created_at = updated_at
@@ -228,7 +263,7 @@ class SQLiteDatabase(BaseDatabase):
            ''', (user_id, cid, history, updated_at, created_at)
        )
        
-    def get_webchat_conversations(self, user_id: str) -> Tuple:
+    def get_conversations(self, user_id: str) -> Tuple:
        try:
            c = self.conn.cursor()
        except sqlite3.ProgrammingError:
@@ -236,7 +271,7 @@ class SQLiteDatabase(BaseDatabase):
            
        c.execute(
            '''
-            SELECT cid, created_at, updated_at FROM webchat_conversation WHERE user_id = ? ORDER BY updated_at DESC
+            SELECT cid, created_at, updated_at, title, persona_id FROM webchat_conversation WHERE user_id = ? ORDER BY updated_at DESC
            ''', (user_id,)
        )
        
@@ -247,24 +282,42 @@ class SQLiteDatabase(BaseDatabase):
            cid = row[0]
            created_at = row[1]
            updated_at = row[2]
-            conversations.append(WebChatConversation("", cid, '[]', created_at, updated_at))
+            title = row[3]
+            persona_id = row[4]
+            conversations.append(Conversation("", cid, '[]', created_at, updated_at, title, persona_id))
        return conversations
    
-    def update_webchat_conversation(self, user_id: str, cid: str, history: str):
+    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 = ? WHERE user_id = ? AND cid = ?
-            ''', (history, user_id, cid)
+            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_webchat_conversation(self, user_id: str, cid: str):
+    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 insert_atri_vision_data(self, vision: ATRIVision):
        ts = int(time.time())
        keywords = ",".join(vision.keywords)
--- a/astrbot/core/db/sqlite_init.sql
+++ b/astrbot/core/db/sqlite_init.sql
@@ -42,5 +42,7 @@ CREATE TABLE IF NOT EXISTS webchat_conversation(
    cid TEXT,
    history TEXT,
    created_at INTEGER,
-    updated_at INTEGER
+    updated_at INTEGER,
+    title TEXT,
+    persona_id TEXT
 );
--- a/astrbot/core/message/components.py
+++ b/astrbot/core/message/components.py
@@ -306,7 +306,7 @@ class Image(BaseMessageComponent):

 class Reply(BaseMessageComponent):
    type: ComponentType = "Reply"
-    id: int
+    id: T.Union[str, int]
    text: T.Optional[str] = ""
    qq: T.Optional[int] = 0
    time: T.Optional[int] = 0
@@ -325,11 +325,13 @@ class RedBag(BaseMessageComponent):


 class Poke(BaseMessageComponent):
-    type: ComponentType = "Poke"
-    qq: int
+    type: str = ""
+    id: T.Optional[int] = 0
+    qq: T.Optional[int] = 0

-    def __init__(self, **_):
-        super().__init__(**_)
+    def __init__(self, type: str, **_):
+        type = f"Poke:{type}"
+        super().__init__(type=type, **_)


 class Forward(BaseMessageComponent):
@@ -339,14 +341,14 @@ class Forward(BaseMessageComponent):
    def __init__(self, **_):
        super().__init__(**_)

-
-class Node(BaseMessageComponent):  # 该 component 仅支持使用 sendGroupForwardMessage 发送
+class Node(BaseMessageComponent):
+    '''群合并转发消息'''
    type: ComponentType = "Node"
-    id: T.Optional[int] = 0
-    name: T.Optional[str] = ""
-    uin: T.Optional[int] = 0
-    content: T.Optional[T.Union[str, list]] = ""
-    seq: T.Optional[T.Union[str, list]] = ""  # 不清楚是什么
+    id: T.Optional[int] = 0 # 忽略
+    name: T.Optional[str] = "" # qq昵称
+    uin: T.Optional[int] = 0 # qq号
+    content: T.Optional[T.Union[str, list]] = "" # 子消息段列表
+    seq: T.Optional[T.Union[str, list]] = "" # 忽略
    time: T.Optional[int] = 0

    def __init__(self, content: T.Union[str, list], **_):
--- a/astrbot/core/message/message_event_result.py
+++ b/astrbot/core/message/message_event_result.py
@@ -140,5 +140,10 @@ class MessageEventResult(MessageChain):
        '''
        return self.result_content_type == ResultContentType.LLM_RESULT
    
+    def get_plain_text(self) -> str:
+        '''获取纯文本消息。这个方法将获取所有 Plain 组件的文本并拼接成一条消息。空格分隔。
+        '''
+        return " ".join([comp.text for comp in self.chain if isinstance(comp, Plain)])
+    
    
 CommandResult = MessageEventResult
--- a/astrbot/core/pipeline/init.py
+++ b/astrbot/core/pipeline/init.py
@@ -2,6 +2,7 @@ from astrbot.core.message.message_event_result import MessageEventResult, EventR

 from .waking_check.stage import WakingCheckStage
 from .whitelist_check.stage import WhitelistCheckStage
+from .rate_limit_check.stage import RateLimitStage
 from .content_safety_check.stage import ContentSafetyCheckStage
 from .preprocess_stage.stage import PreProcessStage
 from .process_stage.stage import ProcessStage
@@ -11,7 +12,7 @@ from .respond.stage import RespondStage
 STAGES_ORDER = [
    "WakingCheckStage", # 检查是否需要唤醒
    "WhitelistCheckStage", # 检查是否在群聊/私聊白名单
-    "RateLimitCheckStage", # 检查会话是否超过频率限制
+    "RateLimitStage", # 检查会话是否超过频率限制
    "ContentSafetyCheckStage", # 检查内容安全
    "PreProcessStage", # 预处理
    "ProcessStage", # 交由 Stars 处理（a.k.a 插件），或者 LLM 调用
@@ -22,6 +23,7 @@ STAGES_ORDER = [
 __all__ = [
    "WakingCheckStage",
    "WhitelistCheckStage",
+    "RateLimitStage",
    "ContentSafetyCheckStage",
    "PreProcessStage",
    "ProcessStage",
--- a/astrbot/core/pipeline/content_safety_check/stage.py
+++ b/astrbot/core/pipeline/content_safety_check/stage.py
@@ -17,11 +17,14 @@ class ContentSafetyCheckStage(Stage):
        config = ctx.astrbot_config['content_safety']
        self.strategy_selector = StrategySelector(config)

-    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
+    async def process(self, event: AstrMessageEvent, check_text: str = None) -> Union[None, AsyncGenerator[None, None]]:
        '''检查内容安全'''
-        ok, info = self.strategy_selector.check(event.get_message_str())
+        text = check_text if check_text else event.get_message_str()
+        ok, info = self.strategy_selector.check(text)
        if not ok:
-            event.set_result(MessageEventResult().message("你的消息中包含不适当的内容，已被屏蔽。"))
+            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。"))
+                yield 
            event.stop_event()
            logger.info(f"内容安全检查不通过，原因：{info}")
            return
--- a/astrbot/core/pipeline/process_stage/method/dify_request.py
+++ b/astrbot/core/pipeline/process_stage/method/dify_request.py
@@ -1,60 +0,0 @@
-'''
-Dify 调用 Stage
-'''
-import traceback
-from typing import Union, AsyncGenerator
-from ...context import PipelineContext
-from ..stage import Stage
-from astrbot.core.platform.astr_message_event import AstrMessageEvent
-from astrbot.core.message.message_event_result import MessageEventResult, ResultContentType
-from astrbot.core.message.components import Image
-from astrbot.core import logger
-from astrbot.core.utils.metrics import Metric
-from astrbot.core.provider.entites import ProviderRequest
-
-class DifyRequestSubStage(Stage):
-    
-    async def initialize(self, ctx: PipelineContext) -> None:
-        self.ctx = ctx
-        
-    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
-        req: ProviderRequest = None
-        
-        provider = self.ctx.plugin_manager.context.get_using_provider()
-        if provider.meta().type != "dify":
-            return
-        
-        if event.get_extra("provider_request"):
-            req = event.get_extra("provider_request")
-            assert isinstance(req, ProviderRequest), "provider_request 必须是 ProviderRequest 类型。"
-        else:
-            req = ProviderRequest(prompt="", image_urls=[])
-            if self.ctx.astrbot_config['provider_settings']['wake_prefix']:
-                if not event.message_str.startswith(self.ctx.astrbot_config['provider_settings']['wake_prefix']):
-                    return
-            req.prompt = event.message_str[len(self.ctx.astrbot_config['provider_settings']['wake_prefix']):]
-            for comp in event.message_obj.message:
-                if isinstance(comp, Image):
-                    image_url = comp.url if comp.url else comp.file
-                    req.image_urls.append(image_url)
-            req.session_id = event.session_id
-            event.set_extra("provider_request", req)
-            
-        if not req.prompt:
-            return
-            
-        try:
-            logger.debug(f"Dify 请求 Payload: {req.__dict__}")
-            llm_response = await provider.text_chat(**req.__dict__) # 请求 LLM
-            await Metric.upload(llm_tick=1, model_name=provider.get_model(), provider_type=provider.meta().type)
-
-            if llm_response.role == 'assistant':
-                # text completion
-                event.set_result(MessageEventResult().message(llm_response.completion_text)
-                                 .set_result_content_type(ResultContentType.LLM_RESULT))
-                yield # rick roll
-
-        except BaseException as e:
-            logger.error(traceback.format_exc())
-            event.set_result(MessageEventResult().message("AstrBot 请求 Dify 失败：" + str(e)))
-            return
--- a/astrbot/core/pipeline/process_stage/method/llm_request.py
+++ b/astrbot/core/pipeline/process_stage/method/llm_request.py
@@ -2,6 +2,7 @@
 本地 Agent 模式的 LLM 调用 Stage
 '''
 import traceback
+import json
 from typing import Union, AsyncGenerator
 from ...context import PipelineContext
 from ..stage import Stage
@@ -10,7 +11,7 @@ from astrbot.core.message.message_event_result import MessageEventResult, Result
 from astrbot.core.message.components import Image
 from astrbot.core import logger
 from astrbot.core.utils.metrics import Metric
-from astrbot.core.provider.entites import ProviderRequest
+from astrbot.core.provider.entites import ProviderRequest, LLMResponse
 from astrbot.core.star.star_handler import star_handlers_registry, EventType

 class LLMRequestSubStage(Stage):
@@ -24,6 +25,8 @@ class LLMRequestSubStage(Stage):
            if self.provider_wake_prefix.startswith(bwp):
                logger.info(f"识别 LLM 聊天额外唤醒前缀 {self.provider_wake_prefix} 以机器人唤醒前缀 {bwp} 开头，已自动去除。")
                self.provider_wake_prefix = self.provider_wake_prefix[len(bwp):]
+                
+        self.conv_manager = ctx.plugin_manager.context.conversation_manager
        
    async def process(self, event: AstrMessageEvent, _nested: bool = False) -> Union[None, AsyncGenerator[None, None]]:
        req: ProviderRequest = None
@@ -46,15 +49,22 @@ class LLMRequestSubStage(Stage):
                if isinstance(comp, Image):
                    image_url = comp.url if comp.url else comp.file
                    req.image_urls.append(image_url)
-            req.session_id = event.session_id
+            
+            # 获取对话上下文
+            conversation_id = await self.conv_manager.get_curr_conversation_id(event.unified_msg_origin)
+            if not conversation_id:
+                conversation_id = await self.conv_manager.new_conversation(event.unified_msg_origin)
+            req.session_id = event.unified_msg_origin
+            conversation = await self.conv_manager.get_conversation(event.unified_msg_origin, conversation_id)
+            req.conversation = conversation
+            req.contexts = json.loads(conversation.history)
+
            event.set_extra("provider_request", req)
-            session_provider_context = provider.session_memory.get(event.session_id)
-            req.contexts = session_provider_context if session_provider_context else []
            
        if not req.prompt and not req.image_urls:
            return
            
-        # 执行请求 LLM 前事件。
+        # 执行请求 LLM 前事件钩子。
        # 装饰 system_prompt 等功能
        handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnLLMRequestEvent)
        for handler in handlers:
@@ -62,18 +72,35 @@ class LLMRequestSubStage(Stage):
                await handler.handler(event, req)
            except BaseException:
                logger.error(traceback.format_exc())
+                
+        if isinstance(req.contexts, str):
+            req.contexts = json.loads(req.contexts)
        
        try:
-            logger.debug(f"提供商请求 Payload: {req.__dict__}")
+            logger.debug(f"提供商请求 Payload: {req}")
            if _nested:
                req.func_tool = None # 暂时不支持递归工具调用
            llm_response = await provider.text_chat(**req.__dict__) # 请求 LLM
+            
+            # 执行 LLM 响应后的事件。
+            handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnLLMResponseEvent)
+            for handler in handlers:
+                try:
+                    await handler.handler(event, llm_response)
+                except BaseException:
+                    logger.error(traceback.format_exc())
+            
+            # 保存到历史记录
+            await self._save_to_history(event, req, llm_response)
+            
            await Metric.upload(llm_tick=1, model_name=provider.get_model(), provider_type=provider.meta().type)

            if llm_response.role == 'assistant':
                # text completion
                event.set_result(MessageEventResult().message(llm_response.completion_text)
                                 .set_result_content_type(ResultContentType.LLM_RESULT))
+            elif llm_response.role == 'err':
+                event.set_result(MessageEventResult().message(f"AstrBot 请求失败。\n错误信息: {llm_response.completion_text}"))
            elif llm_response.role == 'tool':
                # function calling
                function_calling_result = {}
@@ -84,10 +111,10 @@ class LLMRequestSubStage(Stage):
                        # 尝试调用工具函数
                        wrapper = self._call_handler(self.ctx, event, func_tool.handler, **func_tool_args)
                        async for resp in wrapper:
-                            if resp is not None:
+                            if resp is not None: # 有 return 返回
                                function_calling_result[func_tool_name] = resp
                            else:
-                                yield
+                                yield # 有生成器返回
                        event.clear_result() # 清除上一个 handler 的结果
                    except BaseException as e:
                        logger.warning(traceback.format_exc())
@@ -102,8 +129,31 @@ class LLMRequestSubStage(Stage):
                    req.prompt += extra_prompt
                    async for _ in self.process(event, _nested=True):
                        yield
+                else:
+                    if llm_response.completion_text:
+                        event.set_result(MessageEventResult().message(llm_response.completion_text))

        except BaseException as e:
            logger.error(traceback.format_exc())
            event.set_result(MessageEventResult().message(f"AstrBot 请求失败。\n错误类型: {type(e).__name__}\n错误信息: {str(e)}"))
-            return
+            return
+        
+    async def _save_to_history(self, event: AstrMessageEvent, req: ProviderRequest, llm_response: LLMResponse):
+        if llm_response.role == "assistant":
+            # 文本回复
+            contexts = req.contexts
+            new_record = {
+                "role": "user",
+                "content": req.prompt
+            }
+            contexts.append(new_record)
+            contexts.append({
+                "role": "assistant",
+                "content": llm_response.completion_text
+            })
+            contexts_to_save = list(filter(lambda item: '_no_save' not in item, contexts))
+            await self.conv_manager.update_conversation(
+                event.unified_msg_origin, 
+                req.conversation.cid, 
+                history=contexts_to_save
+            )
--- a/astrbot/core/pipeline/process_stage/method/star_request.py
+++ b/astrbot/core/pipeline/process_stage/method/star_request.py
@@ -31,7 +31,7 @@ class StarRequestSubStage(Stage):
                    # 孤立无援的 star handler 
                    continue
                
-                logger.debug(f"执行 Star Handler {handler.handler_full_name}")
+                logger.debug(f"执行插件 handler {handler.handler_full_name}")
                wrapper = self._call_handler(self.ctx, event, handler.handler, **params)
                async for ret in wrapper:
                    yield ret
@@ -39,8 +39,11 @@ class StarRequestSubStage(Stage):
            except Exception as e:
                logger.error(traceback.format_exc())
                logger.error(f"Star {handler.handler_full_name} handle error: {e}")
-                ret = f":(\n\n在调用插件 {star_map.get(handler.handler_module_path).name} 的处理函数 {handler.handler_name} 时出现异常：{e}"
-                event.set_result(MessageEventResult().message(ret))
-                yield
-                event.clear_result()
+                
+                if event.is_at_or_wake_command:
+                    ret = f":(\n\n在调用插件 {star_map.get(handler.handler_module_path).name} 的处理函数 {handler.handler_name} 时出现异常：{e}"
+                    event.set_result(MessageEventResult().message(ret))
+                    yield
+                    event.clear_result()
+                
                event.stop_event()
--- a/astrbot/core/pipeline/process_stage/stage.py
+++ b/astrbot/core/pipeline/process_stage/stage.py
@@ -3,7 +3,6 @@ from ..stage import Stage, register_stage
 from ..context import PipelineContext
 from .method.llm_request import LLMRequestSubStage
 from .method.star_request import StarRequestSubStage
-from .method.dify_request import DifyRequestSubStage
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.star.star_handler import StarHandlerMetadata
 from astrbot.core.provider.entites import ProviderRequest
@@ -21,9 +20,6 @@ class ProcessStage(Stage):
        
        self.star_request_sub_stage = StarRequestSubStage()
        await self.star_request_sub_stage.initialize(ctx)
-        
-        self.dify_request_sub_stage = DifyRequestSubStage()
-        await self.dify_request_sub_stage.initialize(ctx)

    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
        '''处理事件
@@ -35,24 +31,29 @@ class ProcessStage(Stage):
                # 生成器返回值处理
                if isinstance(resp, ProviderRequest):
                    # Handler 的 LLM 请求
-                    logger.debug(f"llm request -> {resp.prompt}")
                    event.set_extra("provider_request", resp)
+                    _t = False
                    async for _ in self.llm_request_sub_stage.process(event):
+                        _t = True
+                        yield
+                    if not _t:
                        yield
                else:
                    yield
        
-        # 调用提供商相关请求
+        # 调用 LLM 相关请求
        if not self.ctx.astrbot_config['provider_settings'].get('enable', True):
            return
        
        if not event._has_send_oper and event.is_at_or_wake_command:
+            # 是否有过发送操作 and 是否是被 @ 或者通过唤醒前缀
            if (event.get_result() and not event.get_result().is_stopped()) or not event.get_result():
+                # 事件没有终止传播
                provider = self.ctx.plugin_manager.context.get_using_provider()
-                match provider.meta().type:
-                    case "dify":
-                        async for _ in self.dify_request_sub_stage.process(event):
-                            yield
-                    case _:
-                        async for _ in self.llm_request_sub_stage.process(event):
-                            yield
+                
+                if not provider:
+                    logger.info("未找到可用的 LLM 提供商，请先前往配置服务提供商。")
+                    return
+                
+                async for _ in self.llm_request_sub_stage.process(event):
+                    yield
--- a/astrbot/core/pipeline/rate_limit_check/stage.py
+++ b/astrbot/core/pipeline/rate_limit_check/stage.py
@@ -61,11 +61,12 @@ class RateLimitStage(Stage):
                stall_duration = (next_window_time - now).total_seconds()
                
                match self.rl_strategy:
-                    case RateLimitStrategy.STALL:
+                    case RateLimitStrategy.STALL.value:
                        logger.info(f"会话 {session_id} 被限流。根据限流策略，此会话处理将被暂停 {stall_duration:.2f} 秒。")
                        await asyncio.sleep(stall_duration)
-                    case RateLimitStrategy.DISCARD:
-                        event.set_result(MessageEventResult().message(f"会话 {session_id} 被限流。根据限流策略，此请求已被丢弃，直到您的限额于 {stall_duration:.2f} 秒后重置。"))
+                    case RateLimitStrategy.DISCARD.value:
+                        # event.set_result(MessageEventResult().message(f"会话 {session_id} 被限流。根据限流策略，此请求已被丢弃，直到您的限额于 {stall_duration:.2f} 秒后重置。"))
+                        logger.info(f"会话 {session_id} 被限流。根据限流策略，此请求已被丢弃，直到限额于 {stall_duration:.2f} 秒后重置。")
                        return event.stop_event()
                
                self._remove_expired_timestamps(timestamps, now + timedelta(seconds=stall_duration))
--- a/astrbot/core/pipeline/respond/stage.py
+++ b/astrbot/core/pipeline/respond/stage.py
@@ -1,20 +1,30 @@
 import random
 import asyncio
+import math
+import traceback
 from typing import Union, AsyncGenerator
 from ..stage import register_stage, Stage
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.message.message_event_result import MessageChain
 from astrbot.core import logger
+from astrbot.core.message.message_event_result import BaseMessageComponent
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
-
+from astrbot.core.message.components import Plain, Reply, At
@register_stage
 class RespondStage(Stage):
    async def initialize(self, ctx: PipelineContext):
        self.ctx = ctx
        
+        self.reply_with_mention = ctx.astrbot_config['platform_settings']['reply_with_mention']
+        self.reply_with_quote = ctx.astrbot_config['platform_settings']['reply_with_quote']
+        
        # 分段回复
        self.enable_seg: bool = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
+        self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
+        
+        self.interval_method = ctx.astrbot_config['platform_settings']['segmented_reply']['interval_method']
+        self.log_base = float(ctx.astrbot_config['platform_settings']['segmented_reply']['log_base'])
        interval_str: str = ctx.astrbot_config['platform_settings']['segmented_reply']['interval']
        interval_str_ls = interval_str.replace(" ", "").split(",")
        try:
@@ -22,7 +32,28 @@ class RespondStage(Stage):
        except BaseException as e:
            logger.error(f'解析分段回复的间隔时间失败。{e}')
            self.interval = [1.5, 3.5]
-
+        logger.info(f"分段回复间隔时间：{self.interval}")
+        
+    async def _word_cnt(self, text: str) -> int:
+        '''分段回复 统计字数'''
+        if all(ord(c) < 128 for c in text):
+            word_count = len(text.split())
+        else:
+            word_count = len([c for c in text if c.isalnum()])
+        return word_count
+    
+    async def _calc_comp_interval(self, comp: BaseMessageComponent) -> float:
+        '''分段回复 计算间隔时间'''
+        if self.interval_method == 'log':
+            if isinstance(comp, Plain):
+                wc = await self._word_cnt(comp.text)
+                i = math.log(wc + 1, self.log_base)
+                return random.uniform(i, i + 0.5)
+            else:
+                return random.uniform(1, 1.75)
+        else:
+            # random
+            return random.uniform(self.interval[0], self.interval[1])

    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
        result = event.get_result()
@@ -31,11 +62,26 @@ class RespondStage(Stage):

        if len(result.chain) > 0:
            await event._pre_send()
-            if self.enable_seg:
+            
+            if self.enable_seg and ((self.only_llm_result and result.is_llm_result()) or not self.only_llm_result):
+                decorated_comps = []
+                if self.reply_with_mention:
+                    for comp in result.chain:
+                        if isinstance(comp, At):
+                            decorated_comps.append(comp)
+                            result.chain.remove(comp)
+                            break
+                if self.reply_with_quote:
+                    for comp in result.chain:
+                        if isinstance(comp, Reply):
+                            decorated_comps.append(comp)
+                            result.chain.remove(comp)
+                            break
                # 分段回复
                for comp in result.chain:
-                    await event.send(MessageChain([comp]))
-                await asyncio.sleep(random.uniform(self.interval[0], self.interval[1]))
+                    i = await self._calc_comp_interval(comp)
+                    await asyncio.sleep(i)
+                    await event.send(MessageChain([*decorated_comps, comp]))
            else:
                await event.send(result)
            await event._post_send()
@@ -43,7 +89,9 @@ class RespondStage(Stage):
        
        handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnAfterMessageSentEvent)
        for handler in handlers:
-            # TODO: 如何让这里的 handler 也能使用 LLM 能力。也许需要将 LLMRequestSubStage 提取出来。
-            await handler.handler(event)
+            try:
+                await handler.handler(event)
+            except BaseException:
+                logger.error(traceback.format_exc())
            
        event.clear_result()
--- a/astrbot/core/pipeline/result_decorate/stage.py
+++ b/astrbot/core/pipeline/result_decorate/stage.py
@@ -2,39 +2,75 @@ import time
 import re
 import traceback
 from typing import Union, AsyncGenerator
-from ..stage import register_stage
+from ..stage import Stage, register_stage, registered_stages
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.platform.message_type import MessageType
 from astrbot.core import logger
-from astrbot.core.message.components import Plain, Image, At, Reply, Record
+from astrbot.core.message.components import Plain, Image, At, Reply, Record, File, Node
 from astrbot.core import html_renderer
 from astrbot.core.star.star_handler import star_handlers_registry, EventType

@register_stage
-class ResultDecorateStage:
+class ResultDecorateStage(Stage):
    async def initialize(self, ctx: PipelineContext):
        self.ctx = ctx
        self.reply_prefix = ctx.astrbot_config['platform_settings']['reply_prefix']
        self.reply_with_mention = ctx.astrbot_config['platform_settings']['reply_with_mention']
        self.reply_with_quote = ctx.astrbot_config['platform_settings']['reply_with_quote']
-        self.use_tts = ctx.astrbot_config['provider_tts_settings']['enable']
-        self.t2i = ctx.astrbot_config['t2i']
+        self.t2i_word_threshold = ctx.astrbot_config['t2i_word_threshold']
+        try:
+            self.t2i_word_threshold = int(self.t2i_word_threshold)
+            if self.t2i_word_threshold < 50:
+                self.t2i_word_threshold = 50
+        except BaseException:
+            self.t2i_word_threshold = 150
+            
+        self.forward_threshold = ctx.astrbot_config['platform_settings']['forward_threshold']
        
        # 分段回复
+        self.words_count_threshold = int(ctx.astrbot_config['platform_settings']['segmented_reply']['words_count_threshold'])
        self.enable_segmented_reply = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
        self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
        self.regex = ctx.astrbot_config['platform_settings']['segmented_reply']['regex']
+        self.content_cleanup_rule = ctx.astrbot_config['platform_settings']['segmented_reply']['content_cleanup_rule']

+        
+        # exception
+        self.content_safe_check_reply = ctx.astrbot_config['content_safety']['also_use_in_response']
+        self.content_safe_check_stage = None
+        if self.content_safe_check_reply:
+            for stage in registered_stages:
+                if stage.__class__.__name__ == "ContentSafetyCheckStage":
+                    self.content_safe_check_stage = stage
+                    
+            
    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
        result = event.get_result()
        if result is None:
            return
        
+        # 回复时检查内容安全
+        if self.content_safe_check_reply and self.content_safe_check_stage and result.is_llm_result():
+            text = ""
+            for comp in result.chain:
+                if isinstance(comp, Plain):
+                    text += comp.text
+            async for _ in self.content_safe_check_stage.process(event, check_text=text):
+                yield
+        
+        # 发送消息前事件钩子
        handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnDecoratingResultEvent)
        for handler in handlers:
-            # TODO: 如何让这里的 handler 也能使用 LLM 能力。也许需要将 LLMRequestSubStage 提取出来。
-            await handler.handler(event)
+            try:
+                await handler.handler(event)
+            except BaseException:
+                logger.error(traceback.format_exc())
+            
+        # 需要再获取一次。插件可能直接对 chain 进行了替换。
+        result = event.get_result()
+        if result is None:
+            return
        
        if len(result.chain) > 0:
            # 回复前缀
@@ -50,26 +86,35 @@ class ResultDecorateStage:
                    new_chain = []
                    for comp in result.chain:
                        if isinstance(comp, Plain):
-                            split_response = re.findall(r".*?[。？！~…]+|.+$", comp.text)
+                            if len(comp.text) > self.words_count_threshold:
+                                # 不分段回复
+                                new_chain.append(comp)
+                                continue
+                            split_response = []
+                            for line in comp.text.split("\n"):
+                                split_response.extend(re.findall(self.regex, line))
                            if not split_response:
                                new_chain.append(comp)
                                continue
                            for seg in split_response:
-                                new_chain.append(Plain(seg))
+                                if self.content_cleanup_rule:
+                                    seg = re.sub(self.content_cleanup_rule, "", seg)
+                                if seg.strip():
+                                    new_chain.append(Plain(seg))
                        else:
                            # 非 Plain 类型的消息段不分段
                            new_chain.append(comp)
                    result.chain = new_chain
                
            # TTS
-            if self.use_tts and result.is_llm_result():
+            if self.ctx.astrbot_config['provider_tts_settings']['enable'] and result.is_llm_result():
                tts_provider = self.ctx.plugin_manager.context.provider_manager.curr_tts_provider_inst
                new_chain = []
                for comp in result.chain:
                    if isinstance(comp, Plain) and len(comp.text) > 1:
                        try:
-                            logger.info("TTS 请求: " + plain_str)
-                            audio_path = await tts_provider.get_audio(plain_str)
+                            logger.info("TTS 请求: " + comp.text)
+                            audio_path = await tts_provider.get_audio(comp.text)
                            logger.info("TTS 结果: " + audio_path)
                            if audio_path:
                                new_chain.append(Record(file=audio_path, url=audio_path))
@@ -77,7 +122,7 @@ class ResultDecorateStage:
                                logger.error(f"由于 TTS 音频文件没找到，消息段转语音失败: {comp.text}")
                                new_chain.append(comp)
                        except BaseException:
-                            traceback.print_exc()
+                            logger.error(traceback.format_exc())
                            logger.error("TTS 失败，使用文本发送。")
                            new_chain.append(comp)
                    else:
@@ -85,14 +130,14 @@ class ResultDecorateStage:
                result.chain = new_chain
            
            # 文本转图片
-            elif (result.use_t2i_ is None and self.t2i) or result.use_t2i_:
+            elif (result.use_t2i_ is None and self.ctx.astrbot_config['t2i']) or result.use_t2i_:
                plain_str = ""
                for comp in result.chain:
                    if isinstance(comp, Plain):
                        plain_str += "\n\n" + comp.text
                    else:
                        break
-                if plain_str and len(plain_str) > 150:
+                if plain_str and len(plain_str) > self.t2i_word_threshold:
                    render_start = time.time()
                    try:
                        url = await html_renderer.render_t2i(plain_str, return_url=True)
@@ -104,8 +149,32 @@ class ResultDecorateStage:
                    if url:
                        result.chain = [Image.fromURL(url)]
            
-            if self.reply_with_mention and event.get_message_type() != MessageType.FRIEND_MESSAGE:
-                result.chain.insert(0, At(qq=event.get_sender_id()))
+            # 触发转发消息
+            has_forwarded = False
+            if event.get_platform_name() == 'aiocqhttp':
+                word_cnt = 0
+                for comp in result.chain:
+                    if isinstance(comp, Plain):
+                        word_cnt += len(comp.text)
+                if word_cnt > self.forward_threshold:
+                    node = Node(
+                        uin=event.get_self_id(),
+                        name="AstrBot",
+                        content=[
+                            *result.chain
+                        ]
+                    )
+                    result.chain = [node]
+                    has_forwarded = True
            
-            if self.reply_with_quote:
-                result.chain.insert(0, Reply(id=event.message_obj.message_id))
+            if not has_forwarded:
+                # at 回复
+                if self.reply_with_mention and event.get_message_type() != MessageType.FRIEND_MESSAGE:
+                    result.chain.insert(0, At(qq=event.get_sender_id(), name=event.get_sender_name()))
+                    if len(result.chain) > 1 and isinstance(result.chain[1], Plain):
+                        result.chain[1].text = "\n" + result.chain[1].text
+                
+                # 引用回复
+                if self.reply_with_quote:
+                    if not any(isinstance(item, File) for item in result.chain):
+                        result.chain.insert(0, Reply(id=event.message_obj.message_id))
--- a/astrbot/core/pipeline/scheduler.py
+++ b/astrbot/core/pipeline/scheduler.py
@@ -12,14 +12,14 @@ class PipelineScheduler():
        
    async def initialize(self):
        for stage in registered_stages:
-            logger.debug(f"初始化阶段 {stage.__class__ .__name__}")
+            # logger.debug(f"初始化阶段 {stage.__class__ .__name__}")
            
            await stage.initialize(self.ctx)
            
    async def _process_stages(self, event: AstrMessageEvent, from_stage=0):
        for i in range(from_stage, len(registered_stages)):
            stage = registered_stages[i]
-            logger.debug(f"执行阶段 {stage.__class__ .__name__}")
+            # logger.debug(f"执行阶段 {stage.__class__ .__name__}")
            coro = stage.process(event)
            if isinstance(coro, AsyncGenerator):
                async for _ in coro:
--- a/astrbot/core/pipeline/stage.py
+++ b/astrbot/core/pipeline/stage.py
@@ -1,6 +1,7 @@
 from __future__ import annotations
 import abc
 import inspect
+from astrbot.api import logger
 from typing import List, AsyncGenerator, Union, Awaitable
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from .context import PipelineContext
@@ -36,16 +37,18 @@ class Stage(abc.ABC):
        ctx: PipelineContext,
        event: AstrMessageEvent, 
        handler: Awaitable,
-        **params
+        *args,
+        **kwargs,
    ) -> AsyncGenerator[None, None]:
        '''调用 Handler。'''
        # 判断 handler 是否是类方法（通过装饰器注册的没有 __self__ 属性）
        ready_to_call = None
        try:
-            ready_to_call = handler(event, **params)
+            ready_to_call = handler(event, *args, **kwargs)
        except TypeError as e:
            # 向下兼容
-            ready_to_call = handler(event, ctx.plugin_manager.context, **params)
+            logger.debug(str(e))
+            ready_to_call = handler(event, ctx.plugin_manager.context, *args, **kwargs)
        
        if isinstance(ready_to_call, AsyncGenerator):
            async for ret in ready_to_call:
--- a/astrbot/core/pipeline/waking_check/stage.py
+++ b/astrbot/core/pipeline/waking_check/stage.py
@@ -2,11 +2,12 @@ from ..stage import Stage, register_stage
 from ..context import PipelineContext
 from typing import Union, AsyncGenerator
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
-from astrbot.core.message.message_event_result import MessageEventResult
-from astrbot.core.message.components import At
+from astrbot.core.message.message_event_result import MessageEventResult, MessageChain
+from astrbot.core.message.components import At, Reply
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
+from astrbot.core.star.star import star_map
 from astrbot.core.star.filter.command_group import CommandGroupFilter
-
+from astrbot.core.star.filter.permission import PermissionTypeFilter

@register_stage
 class WakingCheckStage(Stage):
@@ -21,6 +22,9 @@ class WakingCheckStage(Stage):

    async def initialize(self, ctx: PipelineContext) -> None:
        self.ctx = ctx
+        self.no_permission_reply = self.ctx.astrbot_config["platform_settings"].get(
+            "no_permission_reply", True
+        )

    async def process(
        self, event: AstrMessageEvent
@@ -73,44 +77,39 @@ class WakingCheckStage(Stage):
        # 检查插件的 handler filter
        activated_handlers = []
        handlers_parsed_params = {}  # 注册了指令的 handler
+        
        for handler in star_handlers_registry.get_handlers_by_event_type(EventType.AdapterMessageEvent):
-            # filter 需要满足 AND 的逻辑关系
-            passed = True
-            child_command_handler_md = None
-
+            # filter 需满足 AND 逻辑关系
+            passed = True            
+            permission_not_pass = False
            if len(handler.event_filters) == 0:
-                # 不可能有这种情况, 也不允许有这种情况
                continue

            for filter in handler.event_filters:
                try:
-                    if isinstance(filter, CommandGroupFilter):
-                        """如果指令组过滤成功, 会返回叶子指令的 StarHandlerMetadata"""
-                        ok, child_command_handler_md = filter.filter(
-                            event, self.ctx.astrbot_config
-                        )
-                        if not ok:
-                            passed = False
-                        else:
-                            handler = child_command_handler_md  # handler 覆盖
-                            break
+                    if isinstance(filter, PermissionTypeFilter):
+                        if not filter.filter(event, self.ctx.astrbot_config):
+                            permission_not_pass = True
                    else:
                        if not filter.filter(event, self.ctx.astrbot_config):
                            passed = False
                            break
                except Exception as e:
-                    # event.set_result(MessageEventResult().message(f"插件 {handler.handler_full_name} 报错：{e}"))
-                    # yield
                    await event.send(
                        MessageEventResult().message(
-                            f"插件 {handler.handler_full_name} 报错：{e}"
+                            f"插件 {star_map[handler.handler_module_path].name}: {e}"
                        )
                    )
                    event.stop_event()
                    passed = False
                    break
-
            if passed:
+                if permission_not_pass:
+                    if self.no_permission_reply:
+                        await event.send(MessageChain().message(f"ID {event.get_sender_id()} 权限不足。通过 /sid 获取 ID 并请管理员添加。"))
+                    event.stop_event()
+                    return
+                
                is_wake = True
                event.is_wake = True

@@ -119,6 +118,7 @@ class WakingCheckStage(Stage):
                    handlers_parsed_params[handler.handler_full_name] = event.get_extra(
                        "parsed_params"
                    )
+                    
            event.clear_extra()

        event.set_extra("activated_handlers", activated_handlers)
--- a/astrbot/core/pipeline/whitelist_check/stage.py
+++ b/astrbot/core/pipeline/whitelist_check/stage.py
@@ -18,6 +18,11 @@ class WhitelistCheckStage(Stage):
        
    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
        if not self.enable_whitelist_check:
+            # 白名单检查未启用
+            return
+        
+        if len(self.whitelist) == 0:
+            # 白名单为空，不检查
            return
        
        if event.get_platform_name() == 'webchat':
--- a/astrbot/core/platform/astr_message_event.py
+++ b/astrbot/core/platform/astr_message_event.py
@@ -8,7 +8,7 @@ from typing import List, Union
 from astrbot.core.message.components import Plain, Image, BaseMessageComponent, Face, At, AtAll, Forward
 from astrbot.core.utils.metrics import Metric
 from astrbot.core.provider.entites import ProviderRequest
-
+from astrbot.core.db.po import Conversation

@dataclass
 class MessageSesion:
@@ -31,12 +31,19 @@ class AstrMessageEvent(abc.ABC):
                platform_meta: PlatformMetadata,
                session_id: str,):
        self.message_str = message_str
+        '''纯文本的消息'''
        self.message_obj = message_obj
+        '''消息对象，AstrBotMessage。带有完整的消息结构。'''
        self.platform_meta = platform_meta
+        '''消息平台的信息, 其中 name 是平台的类型，如 aiocqhttp'''
        self.session_id = session_id
+        '''用户的会话 ID。可以直接使用下面的 unified_msg_origin'''
        self.role = "member"
+        '''用户是否是管理员。如果是管理员，这里是 admin'''
        self.is_wake = False # 是否通过 WakingStage
-        self.is_at_or_wake_command = False # 是否是 At 机器人或者带有唤醒词或者是私聊（事件监听器会让 is_wake 设为 True）
+        '''是否唤醒'''
+        self.is_at_or_wake_command = False
+        '''是否是 At 机器人或者带有唤醒词或者是私聊（事件监听器会让 is_wake 设为 True，但是不会让这个属性置为 True）'''
        self._extras = {}
        self.session = MessageSesion(
            platform_name=platform_meta.name,
@@ -44,7 +51,7 @@ class AstrMessageEvent(abc.ABC):
            session_id=session_id
        )
        self.unified_msg_origin = str(self.session)
-        
+        '''统一的消息来源字符串。格式为 platform_name:message_type:session_id'''
        self._result: MessageEventResult = None
        '''消息事件的结果'''
        
@@ -296,10 +303,12 @@ class AstrMessageEvent(abc.ABC):
    def request_llm(
        self,
        prompt: str,
+        func_tool_manager = None,
        session_id: str = None,
-        image_urls: List[str] = None,
-        contexts: List = None,
-        system_prompt: str = ""
+        image_urls: List[str] = [],
+        contexts: List = [],
+        system_prompt: str = "",
+        conversation: Conversation = None
    ) -> ProviderRequest:
        '''
        创建一个 LLM 请求。
@@ -308,14 +317,19 @@ class AstrMessageEvent(abc.ABC):
        ```py
        yield event.request_llm(prompt="hi")
        ```
-        
+        prompt: 提示词
+        session_id: 已经过时，留空即可
        image_urls: 可以是 base64:// 或者 http:// 开头的图片链接，也可以是本地图片路径。
-        contexts: 当指定 contexts 时，将会**只**使用 contexts 作为上下文。
+        contexts: 当指定 contexts 时，将会使用 contexts 作为上下文。
+        func_tool_manager: 函数工具管理器，用于调用函数工具。用 self.context.get_llm_tool_manager() 获取。
+        conversation: 可选。如果指定，将在指定的对话中进行 LLM 请求。对话的人格会被用于 LLM 请求，并且结果将会被记录到对话中。
        '''
        return ProviderRequest(
            prompt = prompt,
            session_id = session_id,
            image_urls = image_urls,
+            func_tool = func_tool_manager,
            contexts = contexts,
-            system_prompt = system_prompt
+            system_prompt = system_prompt,
+            conversation=conversation
        )
--- a/astrbot/core/platform/manager.py
+++ b/astrbot/core/platform/manager.py
@@ -15,19 +15,25 @@ class PlatformManager():
        self.settings = config['platform_settings']
        self.event_queue = event_queue
        
-        for platform in self.platforms_config:
-            if not platform['enable']:
-                continue
-            match platform['type']:
-                case "aiocqhttp":
-                    from .sources.aiocqhttp.aiocqhttp_platform_adapter import AiocqhttpAdapter  # noqa: F401
-                case "qq_official":
-                    from .sources.qqofficial.qqofficial_platform_adapter import QQOfficialPlatformAdapter # noqa: F401
-                case "vchat":
-                    from .sources.vchat.vchat_platform_adapter import VChatPlatformAdapter # noqa: F401
-                case "gewechat":
-                    from .sources.gewechat.gewechat_platform_adapter import GewechatPlatformAdapter # noqa: F401
-        
+        try:
+            for platform in self.platforms_config:
+                if not platform['enable']:
+                    continue
+                match platform['type']:
+                    case "aiocqhttp":
+                        from .sources.aiocqhttp.aiocqhttp_platform_adapter import AiocqhttpAdapter  # noqa: F401
+                    case "qq_official":
+                        from .sources.qqofficial.qqofficial_platform_adapter import QQOfficialPlatformAdapter # noqa: F401
+                    case "qq_official_webhook":
+                        from .sources.qqofficial_webhook.qo_webhook_adapter import QQOfficialWebhookPlatformAdapter # noqa: F401
+                    case "gewechat":
+                        from .sources.gewechat.gewechat_platform_adapter import GewechatPlatformAdapter # noqa: F401
+                    case "lark":
+                        from .sources.lark.lark_adapter import LarkPlatformAdapter # noqa: F401
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.error(f"加载平台适配器 {platform['type']} 失败，原因：{e}。请检查依赖库是否安装。提示：可以在 管理面板->控制台->安装Pip库 中安装依赖库。")
+        except Exception as e:
+            logger.error(f"加载平台适配器 {platform['type']} 失败，原因：{e}。")

    async def initialize(self):
        for platform in self.platforms_config:
@@ -37,7 +43,7 @@ class PlatformManager():
                logger.error(f"未找到适用于 {platform['type']}({platform['id']}) 平台适配器，请检查是否已经安装或者名称填写错误。已跳过。")
                continue
            cls_type = platform_cls_map[platform['type']]
-            logger.info(f"尝试实例化 {platform['type']}({platform['id']}) 平台适配器 ...")
+            logger.debug(f"尝试实例化 {platform['type']}({platform['id']}) 平台适配器 ...")
            inst = cls_type(platform, self.settings, self.event_queue)
            self.platform_insts.append(inst)
        
--- a/astrbot/core/platform/sources/aiocqhttp/aiocqhttp_message_event.py
+++ b/astrbot/core/platform/sources/aiocqhttp/aiocqhttp_message_event.py
@@ -1,9 +1,7 @@
-import os
-import random
 import asyncio

 from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.message_components import Plain, Image, Record
+from astrbot.api.message_components import Plain, Image, Record, At, Node, Music, Video
 from aiocqhttp import CQHttp
 from astrbot.core.utils.io import file_to_base64, download_image_by_url

@@ -20,7 +18,7 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
            d = segment.toDict()
            if isinstance(segment, Plain):
                d['type'] = 'text'
-            if isinstance(segment, (Image, Record)):
+            elif isinstance(segment, (Image, Record)):
                # convert to base64
                if segment.file and segment.file.startswith("file:///"):
                    bs64_data = file_to_base64(segment.file[8:])
@@ -28,17 +26,35 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
                elif segment.file and segment.file.startswith("http"):
                    image_file_path = await download_image_by_url(segment.file)
                    bs64_data = file_to_base64(image_file_path)
+                elif segment.file and segment.file.startswith("base64://"):
+                    bs64_data = segment.file
                else:
                    bs64_data = file_to_base64(segment.file)
                d['data'] = {
                    'file': bs64_data,
                }
+            elif isinstance(segment, At):
+                d['data'] = {
+                    'qq': str(segment.qq) # 转换为字符串
+                }
            ret.append(d)
        return ret

    async def send(self, message: MessageChain):
        ret = await AiocqhttpMessageEvent._parse_onebot_json(message)
-        if os.environ.get('TEST_MODE', 'off') == 'on':
-            return
-        await self.bot.send(self.message_obj.raw_message, ret)
+        
+        send_one_by_one = False
+        for seg in message.chain:
+            if isinstance(seg, (Node, Music)):
+                # 转发消息不能和普通消息混在一起发送
+                send_one_by_one = True
+                break
+        
+        if send_one_by_one:
+            for seg in message.chain:
+                await self.bot.send(self.message_obj.raw_message, await AiocqhttpMessageEvent._parse_onebot_json(MessageChain([seg])))
+                await asyncio.sleep(0.5)
+        else:
+            await self.bot.send(self.message_obj.raw_message, ret)
+        
        await super().send(message)
--- a/astrbot/core/platform/sources/aiocqhttp/aiocqhttp_platform_adapter.py
+++ b/astrbot/core/platform/sources/aiocqhttp/aiocqhttp_platform_adapter.py
@@ -2,6 +2,7 @@ import os
 import time
 import asyncio
 import logging
+import uuid
 from typing import Awaitable, Any
 from aiocqhttp import CQHttp, Event
 from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, MessageType, PlatformMetadata
@@ -46,19 +47,82 @@ class AiocqhttpAdapter(Platform):
        await super().send_by_session(session, message_chain)
        
    async def convert_message(self, event: Event) -> AstrBotMessage:
+        logger.debug(f"[aiocqhttp] RawMessage {event}")
+        
+        if event['post_type'] == 'message':
+            abm = await self._convert_handle_message_event(event)
+        elif event['post_type'] == 'notice':
+            abm = await self._convert_handle_notice_event(event)
+        elif event['post_type'] == 'request':
+            abm = await self._convert_handle_request_event(event)
+        
+        return abm
+    
+    async def _convert_handle_request_event(self, event: Event) -> AstrBotMessage:
+        '''OneBot V11 请求类事件'''
        abm = AstrBotMessage()
        abm.self_id = str(event.self_id)
-        abm.tag = "aiocqhttp"
+        abm.sender = MessageMember(
+            user_id=event.user_id,
+            nickname=event.user_id
+        )
+        abm.type = MessageType.OTHER_MESSAGE
+        if 'group_id' in event and event['group_id']:
+            abm.type = MessageType.GROUP_MESSAGE
+            abm.group_id = str(event.group_id)
+        else:
+            abm.type = MessageType.FRIEND_MESSAGE
+        if self.unique_session and abm.type == MessageType.GROUP_MESSAGE:
+            abm.session_id = abm.sender.user_id + "_" + str(event.group_id)
+        abm.message_str = ''
+        abm.message = []
+        abm.timestamp = int(time.time())
+        abm.message_id = uuid.uuid4().hex
+        abm.raw_message = event
+        return abm
+    
+    async def _convert_handle_notice_event(self, event: Event) -> AstrBotMessage:
+        '''OneBot V11 通知类事件'''
+        abm = AstrBotMessage()
+        abm.self_id = str(event.self_id)
+        abm.sender = MessageMember(
+            user_id=event.user_id,
+            nickname=event.user_id
+        )
+        abm.type = MessageType.OTHER_MESSAGE
+        if 'group_id' in event and event['group_id']:
+            abm.group_id = str(event.group_id)
+            abm.type = MessageType.GROUP_MESSAGE
+        else:
+            abm.type = MessageType.FRIEND_MESSAGE    
+        if self.unique_session and abm.type == MessageType.GROUP_MESSAGE:
+            abm.session_id = abm.sender.user_id + "_" + str(event.group_id) # 也保留群组 id
+        else:
+            abm.session_id = str(event.group_id) if abm.type == MessageType.GROUP_MESSAGE else abm.sender.user_id
+        abm.message_str = ""
+        abm.message = []
+        abm.raw_message = event
+        abm.timestamp = int(time.time())
+        abm.message_id = uuid.uuid4().hex
        
-        abm.sender = MessageMember(str(event.sender['user_id']), event.sender['nickname'])        
-
+        if 'sub_type' in event:
+            if event['sub_type'] == 'poke' and 'target_id' in event:
+                abm.message.append(Poke(qq=str(event['target_id']), type='poke')) # noqa: F405
+                
+        return abm
+    
+    
+    async def _convert_handle_message_event(self, event: Event) -> AstrBotMessage:
+        '''OneBot V11 消息类事件'''
+        abm = AstrBotMessage()
+        abm.self_id = str(event.self_id)
+        abm.sender = MessageMember(str(event.sender['user_id']), event.sender['nickname'])      
        if event['message_type'] == 'group':
            abm.type = MessageType.GROUP_MESSAGE
            abm.group_id = str(event.group_id)
        elif event['message_type'] == 'private':
            abm.type = MessageType.FRIEND_MESSAGE
-        
-        if self.unique_session:
+        if self.unique_session and abm.type == MessageType.GROUP_MESSAGE:
            abm.session_id = abm.sender.user_id + "_" + str(event.group_id) # 也保留群组 id
        else:
            abm.session_id = str(event.group_id) if abm.type == MessageType.GROUP_MESSAGE else abm.sender.user_id
@@ -75,7 +139,8 @@ class AiocqhttpAdapter(Platform):
            except BaseException as e:
                logger.error(f"回复消息失败: {e}")
            return
-        logger.debug(f"aiocqhttp: 收到消息: {event.message}")
+        
+        # 按消息段类型类型适配
        for m in event.message:
            t = m['type']
            a = None
@@ -102,7 +167,7 @@ class AiocqhttpAdapter(Platform):
                        if not ret.get('file', None):
                            raise ValueError(f"无法解析文件响应: {ret}")
                        if not os.path.exists(ret['file']):
-                            raise FileNotFoundError(f"文件不存在: {ret['file']}。如果您使用 Docker 部署了 AstrBot 或者消息协议端(Napcat等),暂时无法获取用户上传的文件。")
+                            raise FileNotFoundError(f"文件不存在或者权限问题: {ret['file']}。如果您使用 Docker 部署了 AstrBot 或者消息协议端(Napcat等),请先映射路径。如果路径在 /root 目录下，请用 sudo 打开 AstrBot")
                        
                        m['data'] = {
                            "file": ret['file'],
@@ -118,12 +183,29 @@ class AiocqhttpAdapter(Platform):
        abm.timestamp = int(time.time())
        abm.message_str = message_str
        abm.raw_message = event
+        
        return abm
    
    def run(self) -> Awaitable[Any]:
        if not self.host or not self.port:
-            return
+            logger.warning("aiocqhttp: 未配置 ws_reverse_host 或 ws_reverse_port，将使用默认值：http://0.0.0.0:6199")
+            self.host = "0.0.0.0"
+            self.port = 6199
+            
        self.bot = CQHttp(use_ws_reverse=True, import_name='aiocqhttp', api_timeout_sec=180)
+        
+        @self.bot.on_request()
+        async def request(event: Event):
+            abm = await self.convert_message(event)
+            if abm:
+                await self.handle_msg(abm)
+        
+        @self.bot.on_notice()
+        async def notice(event: Event):
+            abm = await self.convert_message(event)
+            if abm:
+                await self.handle_msg(abm)
+        
        @self.bot.on_message('group')
        async def group(event: Event):
            abm = await self.convert_message(event)
--- a/astrbot/core/platform/sources/gewechat/client.py
+++ b/astrbot/core/platform/sources/gewechat/client.py
@@ -3,7 +3,9 @@ import asyncio
 import aiohttp
 import quart
 import base64
-
+import datetime
+import re
+import os
 from astrbot.api.platform import AstrBotMessage, MessageMember, MessageType
 from astrbot.api.message_components import Plain, Image, At, Record
 from astrbot.api import logger, sp
@@ -50,6 +52,8 @@ class SimpleGewechatClient():
        self.event_queue = event_queue
        
        self.multimedia_downloader = None
+        
+        self.userrealnames = {}
    
    async def get_token_id(self):
        async with aiohttp.ClientSession() as session:
@@ -66,6 +70,18 @@ class SimpleGewechatClient():
        if type_name == "Offline":
            logger.critical("收到 gewechat 下线通知。")
            return
+        
+        if 'Data' in data and 'CreateTime' in data['Data']:
+            # 得到系统 UTF+8 的 ts
+            tz_offset = datetime.timedelta(hours=8)
+            tz = datetime.timezone(tz_offset)
+            ts = datetime.datetime.now(tz).timestamp()
+            create_time = data['Data']['CreateTime']
+            if create_time < ts - 30:
+                logger.warning(f"消息时间戳过旧: {create_time}，当前时间戳: {ts}")
+                return
+
+        
        abm = AstrBotMessage()
        d = data['Data']
    
@@ -87,13 +103,16 @@ class SimpleGewechatClient():
            content = _t[1]
            if '\u2005' in content: 
                # at
-                content = content.split('\u2005')[1]
+                # content = content.split('\u2005')[1]
+                content = re.sub(r'@[^\u2005]*\u2005', '', content)
            abm.group_id = from_user_name
            # at
            msg_source = d['MsgSource']
            if f'<atuserlist><![CDATA[,{abm.self_id}]]>' in msg_source \
                or f'<atuserlist><![CDATA[{abm.self_id}]]>' in msg_source:
                at_me = True
+            if '在群聊中@了你' in d.get('PushContent', ''):
+                at_me = True
        else:
            abm.type = MessageType.FRIEND_MESSAGE
            user_id = from_user_name
@@ -102,9 +121,25 @@ class SimpleGewechatClient():
        if at_me:
            abm.message.insert(0, At(qq=abm.self_id))
        
-        user_real_name = d['PushContent'].split(' : ')[0] \
-            .replace('在群聊中@了你', '') \
-            .replace('在群聊中发了一段语音', '') # 真实昵称
+        # 解析用户真实名字
+        user_real_name = "unknown"
+        if abm.group_id:
+            if abm.group_id not in self.userrealnames or user_id not in self.userrealnames[abm.group_id]:
+                # 获取群成员列表，并且缓存
+                if abm.group_id not in self.userrealnames:
+                    self.userrealnames[abm.group_id] = {}
+                member_list = await self.get_chatroom_member_list(abm.group_id)
+                logger.debug(f"获取到 {abm.group_id} 的群成员列表。")
+                if member_list and 'memberList' in member_list:
+                    for member in member_list['memberList']:
+                        self.userrealnames[abm.group_id][member['wxid']] = member['nickName']
+                if user_id in self.userrealnames[abm.group_id]:
+                    user_real_name = self.userrealnames[abm.group_id][user_id]
+            else:
+                user_real_name = self.userrealnames[abm.group_id][user_id]
+        else:
+            user_real_name = d.get('PushContent', 'unknown : ').split(' : ')[0]
+
        abm.sender = MessageMember(user_id, user_real_name)
        abm.raw_message = d
        abm.message_str = ""
@@ -138,12 +173,11 @@ class SimpleGewechatClient():
                    with open(file_path, "wb") as f:
                        f.write(voice_data)
                    abm.message.append(Record(file=file_path, url=file_path))
-                
            case _:
-                logger.error(f"未实现的消息类型: {d['MsgType']}")
-                return
+                logger.info(f"未实现的消息类型: {d['MsgType']}")
+                abm.raw_message = d
        
-        logger.info(f"abm: {abm}")
+        logger.debug(f"abm: {abm}")
        return abm

    async def callback(self):
@@ -153,13 +187,17 @@ class SimpleGewechatClient():
        if data.get('testMsg', None):
            return quart.jsonify({"r": "AstrBot ACK"})
        
-        abm = await self._convert(data)
-        
+        abm = None
+        try:
+            abm = await self._convert(data)
+        except BaseException as e:
+            logger.warning(f"尝试解析 GeweChat 下发的消息时遇到问题: {e}。下发消息内容: {data}。")
+            
        if abm:
            coro = getattr(self, "on_event_received")
            if coro:
                await coro(abm)
-            
+        
        return quart.jsonify({"r": "AstrBot ACK"})
    
    async def handle_file(self, file_id):
@@ -182,12 +220,12 @@ class SimpleGewechatClient():
                logger.info(f"设置回调结果: {json_blob}")
                if json_blob['ret'] != 200:
                    raise Exception(f"设置回调失败: {json_blob}")
-                logger.info(f"将在 {self.callback_url} 上接收 gewechat 下发的消息。如果一直没收到消息请先尝试重启 AstrBot。")
+                logger.info(f"将在 {self.callback_url} 上接收 gewechat 下发的消息。如果一直没收到消息请先尝试重启 AstrBot。如果仍没收到请到管理面板聊天页输入 /gewe_logout 重新登录。")
        
    async def start_polling(self):
        threading.Thread(target=asyncio.run, args=(self._set_callback_url(),)).start()
        await self.server.run_task(
-            host=self.host, 
+            host='0.0.0.0', 
            port=self.port, 
            shutdown_trigger=self.shutdown_trigger_placeholder
        )
@@ -265,8 +303,25 @@ class SimpleGewechatClient():
            "uuid": qr_uuid,
            "appId": appid
        })
+        verify_flag = False
        while retry_cnt > 0:
            retry_cnt -= 1
+
+            # 需要验证码
+            if verify_flag or os.path.exists("data/temp/gewe_code"):
+                with open("data/temp/gewe_code", "r") as f:
+                    code = f.read().strip()
+                    if not code:
+                        logger.warning("未找到验证码，请在管理面板聊天页输入 /gewe_code 验证码 来验证，如 /gewe_code 123456")
+                        await asyncio.sleep(5)
+                        continue
+                    payload['captchCode'] = code
+                    logger.info(f"使用验证码: {code}")
+                    try:
+                        os.remove("data/temp/gewe_code")
+                    except:
+                        logger.warning("删除验证码文件 data/temp/gewe_code 失败。")
+
            async with aiohttp.ClientSession() as session:
                async with session.post(
                    f"{self.base_url}/login/checkLogin",
@@ -275,30 +330,58 @@ class SimpleGewechatClient():
                ) as resp:
                    json_blob = await resp.json()
                    logger.info(f"检查登录状态: {json_blob}")
-                    status = json_blob['data']['status']
-                    nickname = json_blob['data'].get('nickName', '')
-                    if status == 1:
-                        logger.info(f"等待确认...{nickname}")
-                    elif status == 2:
-                        logger.info(f"绿泡泡平台登录成功: {nickname}")
-                        break
-                    elif status == 0:
-                        logger.info("等待扫码...")
+
+                    ret = json_blob['ret']
+                    msg = ''
+                    if json_blob['data'] and 'msg' in json_blob['data']:
+                        msg = json_blob['data']['msg']
+                    if ret == 500 and '安全验证码' in msg:
+                        logger.warning("此次登录需要安全验证码，请在管理面板聊天页输入 /gewe_code 验证码 来验证，如 /gewe_code 123456")
+                        verify_flag = True
                    else:
-                        logger.warning(f"未知状态: {status}")
+                        status = json_blob['data']['status']
+                        nickname = json_blob['data'].get('nickName', '')
+                        if status == 1: 
+                            logger.info(f"等待确认...{nickname}")
+                        elif status == 2:
+                            logger.info(f"绿泡泡平台登录成功: {nickname}")
+                            break
+                        elif status == 0:
+                            logger.info("等待扫码...")
+                        else:
+                            logger.warning(f"未知状态: {status}")
            await asyncio.sleep(5)
            
        if appid:
-            sp.put(f"gewechat-appid-{nickname}", appid)
+            sp.put(f"gewechat-appid-{self.nickname}", appid)
            self.appid = appid
            logger.info(f"已保存 APPID: {appid}")
    
-    async def post_text(self, to_wxid, content: str):
+    '''API'''
+    
+    async def get_chatroom_member_list(self, chatroom_wxid: str):
+        payload = {
+            "appId": self.appid,
+            "chatroomId": chatroom_wxid
+        }
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/group/getChatroomMemberList",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                return json_blob['data']
+    
+    async def post_text(self, to_wxid, content: str, ats: str = ""):
        payload = {
            "appId": self.appid,
            "toWxid": to_wxid,
            "content": content,
        }
+        if ats:
+            payload['ats'] = ats
        
        async with aiohttp.ClientSession() as session:
            async with session.post(
@@ -342,4 +425,21 @@ class SimpleGewechatClient():
                json=payload
            ) as resp:
                json_blob = await resp.json()
-                logger.debug(f"发送语音结果: {json_blob}")
+                logger.debug(f"发送语音结果: {json_blob}")
+                
+    async def post_file(self, to_wxid, file_url: str, file_name: str):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "fileUrl": file_url,
+            "fileName": file_name
+        }
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postFile",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送文件结果: {json_blob}")
--- a/astrbot/core/platform/sources/gewechat/gewechat_event.py
+++ b/astrbot/core/platform/sources/gewechat/gewechat_event.py
@@ -1,12 +1,13 @@
 import wave
 import uuid
+import traceback
 import os
 from astrbot.core.utils.io import save_temp_img, download_image_by_url, download_file
 from astrbot.core.utils.tencent_record_helper import wav_to_tencent_silk
 from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, MessageChain
 from astrbot.api.platform import AstrBotMessage, PlatformMetadata
-from astrbot.api.message_components import Plain, Image, Record
+from astrbot.api.message_components import Plain, Image, Record, At, File
 from .client import SimpleGewechatClient

 def get_wav_duration(file_path):
@@ -15,6 +16,8 @@ def get_wav_duration(file_path):
        n_channels, sampwidth, framerate, n_frames = wav_file.getparams()[:4]
        if n_frames == 2147483647:
            duration = (file_size - 44) / (n_channels * sampwidth * framerate)
+        elif n_frames == 0:
+            duration = (file_size - 44) / (n_channels * sampwidth * framerate)
        else:
            duration = n_frames / float(framerate)
        return duration
@@ -43,9 +46,31 @@ class GewechatPlatformEvent(AstrMessageEvent):
            logger.error("无法获取到 to_wxid。")
            return
        
+        #  检查@
+        ats = []
+        ats_names = []
+        for comp in message.chain:
+            if isinstance(comp, At):
+                ats.append(comp.qq)
+                ats_names.append(comp.name)
+        has_at = False
+        
        for comp in message.chain:
            if isinstance(comp, Plain):
-                await self.client.post_text(to_wxid, comp.text)
+                text = comp.text
+                payload = {
+                    "to_wxid": to_wxid,
+                    "content": text,
+                }
+                if not has_at and ats:
+                    ats = f"{','.join(ats)}"
+                    ats_names = f"@{' @'.join(ats_names)}"
+                    text = f"{ats_names} {text}"
+                    payload["content"] = text
+                    payload["ats"] = ats
+                    has_at = True
+                await self.client.post_text(**payload)
+                
            elif isinstance(comp, Image):
                img_url = comp.file
                img_path = ""
@@ -80,23 +105,35 @@ class GewechatPlatformEvent(AstrMessageEvent):
                    record_path = record_url
                    
                silk_path = f"data/temp/{uuid.uuid4()}.silk"
-                duration = await wav_to_tencent_silk(record_path, silk_path)
-                
-                print(f"duration: {duration}, {silk_path}")
-                
-                # 检查 record_path 是否在 data/temp 目录中, record_path 可能是绝对路径
-                # temp_directory = os.path.abspath('data/temp')
-                # record_path = os.path.abspath(record_path)
-                # if os.path.commonpath([temp_directory, record_path]) != temp_directory:
-                #     with open(record_path, "rb") as f:
-                #         record_path = f"data/temp/{uuid.uuid4()}.wav"
-                #         with open(record_path, "wb") as f2:
-                #             f2.write(f.read())
-                
+                try:
+                    duration = await wav_to_tencent_silk(record_path, silk_path)
+                except Exception as e:
+                    logger.error(traceback.format_exc())
+                    await self.send(MessageChain().message(f"语音文件转换失败。{str(e)}"))
+                logger.info("Silk 语音文件格式转换至: " + record_path)
                if duration == 0:
                    duration = get_wav_duration(record_path)
-                
                file_id = os.path.basename(silk_path)
                record_url = f"{self.client.file_server_url}/{file_id}"
+                logger.debug(f"gewe callback record url: {record_url}")
                await self.client.post_voice(to_wxid, record_url, duration*1000)
+            elif isinstance(comp, File):
+                file_path = comp.file
+                file_name = comp.name
+                if file_path.startswith("file:///"):
+                    file_path = file_path[8:]
+                elif file_path.startswith("http"):
+                    await download_file(file_path, f"data/temp/{file_name}")
+                else:
+                    file_path = file_path
+                    
+                file_id = os.path.basename(file_path)
+                file_url = f"{self.client.file_server_url}/{file_id}"
+                logger.debug(f"gewe callback file url: {file_url}")
+                await self.client.post_file(to_wxid, file_url, file_id) 
+            elif isinstance(comp, At):
+                pass
+            else:
+                logger.debug(f"gewechat 忽略: {comp.type}")   
+        
        await super().send(message)
--- a/astrbot/core/platform/sources/gewechat/gewechat_platform_adapter.py
+++ b/astrbot/core/platform/sources/gewechat/gewechat_platform_adapter.py
@@ -30,10 +30,6 @@ class GewechatPlatformAdapter(Platform):
    @override
    async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
        to_wxid = session.session_id
-        if "_" in to_wxid:
-            # 群聊，开启了独立会话
-            _, to_wxid = to_wxid.split("_")
-        
        if not to_wxid:
            logger.error("无法获取到 to_wxid。")
            return
--- a/astrbot/core/platform/sources/lark/lark_adapter.py
+++ b/astrbot/core/platform/sources/lark/lark_adapter.py
@@ -0,0 +1,175 @@
+import base64
+import time
+import asyncio
+import json
+import re
+
+from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, MessageType, PlatformMetadata
+from astrbot.api.event import MessageChain
+from typing import Union, List
+from astrbot.api.message_components import Image, Plain, At
+from astrbot.core.platform.astr_message_event import MessageSesion
+from .lark_event import LarkMessageEvent
+from ...register import register_platform_adapter
+from astrbot.core.message.components import BaseMessageComponent
+from astrbot import logger
+import lark_oapi as lark
+from lark_oapi.api.im.v1 import *
+
+@register_platform_adapter("lark", "飞书机器人官方 API 适配器")
+class LarkPlatformAdapter(Platform):
+
+    def __init__(self, platform_config: dict, platform_settings: dict, event_queue: asyncio.Queue) -> None:
+        super().__init__(event_queue)
+        
+        self.config = platform_config
+        
+        self.unique_session = platform_settings['unique_session']
+
+        self.appid = platform_config['app_id']
+        self.appsecret = platform_config['app_secret']
+        self.domain = platform_config.get('domain', lark.FEISHU_DOMAIN)
+        self.bot_name = platform_config.get('lark_bot_name', "astrbot")
+        
+        if not self.bot_name:
+            logger.warning("未设置飞书机器人名称，@ 机器人可能得不到回复。")
+        
+        async def on_msg_event_recv(event: lark.im.v1.P2ImMessageReceiveV1):
+            await self.convert_msg(event)
+        
+        def do_v2_msg_event(event: lark.im.v1.P2ImMessageReceiveV1):
+            asyncio.create_task(on_msg_event_recv(event))
+        
+        self.event_handler = lark.EventDispatcherHandler.builder("", "") \
+            .register_p2_im_message_receive_v1(do_v2_msg_event) \
+            .build()
+             
+        self.client = lark.ws.Client(
+            app_id=self.appid,
+            app_secret=self.appsecret,
+            log_level=lark.LogLevel.ERROR,
+            domain=self.domain,
+            event_handler=self.event_handler
+        )
+        
+        self.lark_api = (
+            lark.Client.builder()
+            .app_id(self.appid)
+            .app_secret(self.appsecret)
+            .build()
+        )
+        
+    async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
+        raise NotImplementedError("QQ 机器人官方 API 适配器不支持 send_by_session")
+        
+    def meta(self) -> PlatformMetadata:
+        return PlatformMetadata(
+            "lark",
+            "飞书机器人官方 API 适配器",
+        )
+        
+    async def convert_msg(self, event: lark.im.v1.P2ImMessageReceiveV1):
+        message = event.event.message
+        abm = AstrBotMessage()
+        abm.timestamp = int(message.create_time) / 1000
+        abm.message = []
+        abm.type = MessageType.GROUP_MESSAGE if message.chat_type == 'group' else MessageType.FRIEND_MESSAGE
+        if message.chat_type == 'group':
+            abm.group_id = message.chat_id
+        abm.self_id = self.bot_name
+        abm.message_str = ""
+        
+        at_list = {}
+        if message.mentions:
+            for m in message.mentions:
+                at_list[m.key] = At(qq=m.id.open_id, name=m.name)
+                if m.name == self.bot_name:
+                    abm.self_id = m.id.open_id
+                    
+        content_json_b = json.loads(message.content)
+        
+        if message.message_type == 'text':
+            message_str_raw = content_json_b['text'] # 带有 @ 的消息
+            at_pattern = r"(@_user_\d+)"  # 可以根据需求修改正则
+            at_users = re.findall(at_pattern, message_str_raw)
+            # 拆分文本，去掉AT符号部分
+            parts = re.split(at_pattern, message_str_raw)
+            for i in range(len(parts)):
+                s = parts[i].strip()
+                if not s:
+                    continue
+                if s in at_list:
+                    abm.message.append(at_list[s])
+                else:
+                    abm.message.append(Plain(parts[i].strip()))
+        elif message.message_type == 'post':
+            _ls = []
+            
+            content_ls = content_json_b.get('content', [])
+            for comp in content_ls:
+                if isinstance(comp, list):
+                    _ls.extend(comp)
+                elif isinstance(comp, dict):
+                    _ls.append(comp)
+            content_json_b = _ls
+        elif message.message_type == 'image':
+            content_json_b = [
+                {"tag": "img", "image_key": content_json_b["image_key"], "style": []}
+            ]
+            
+        if message.message_type in ('post', 'image'):    
+            for comp in content_json_b:
+                if comp['tag'] == 'at':
+                    abm.message.append(at_list[comp['user_id']])
+                elif comp['tag'] == 'text' and comp['text'].strip():
+                    abm.message.append(Plain(comp['text'].strip()))
+                elif comp['tag'] == 'img':
+                    image_key = comp['image_key']
+                    request = GetMessageResourceRequest.builder() \
+                        .message_id(message.message_id) \
+                        .file_key(image_key) \
+                        .type("image") \
+                        .build()
+                    response = await self.lark_api.im.v1.message_resource.aget(request)
+                    if not response.success():
+                        logger.error(f"无法下载飞书图片: {image_key}")
+                    image_bytes = response.file.read()
+                    image_base64 = base64.b64encode(image_bytes).decode()
+                    abm.message.append(Image.fromBase64(image_base64))
+        
+        for comp in abm.message:
+            if isinstance(comp, Plain):
+                abm.message_str += comp.text
+        abm.message_id = message.message_id
+        abm.raw_message = message
+        abm.sender = MessageMember(
+            user_id=event.event.sender.sender_id.open_id,
+            nickname=event.event.sender.sender_id.open_id[:8]
+        )
+        # 独立会话
+        if not self.unique_session:
+            if abm.type == MessageType.GROUP_MESSAGE:
+                abm.session_id = abm.group_id
+            else:
+                abm.session_id = abm.sender.user_id
+        else:
+            abm.session_id = abm.sender.user_id
+            
+        logger.debug(abm)
+        await self.handle_msg(abm)
+        
+    async def handle_msg(self, abm: AstrBotMessage):
+        event = LarkMessageEvent(
+            message_str=abm.message_str,
+            message_obj=abm,
+            platform_meta=self.meta(),
+            session_id=abm.session_id,
+            bot=self.lark_api
+        )
+        
+        self._event_queue.put_nowait(event)
+        
+    async def run(self):
+        # self.client.start()
+        await self.client._connect()
+        
--- a/astrbot/core/platform/sources/lark/lark_event.py
+++ b/astrbot/core/platform/sources/lark/lark_event.py
@@ -0,0 +1,96 @@
+import json
+import uuid
+import lark_oapi as lark
+from typing import List
+from astrbot.api.event import AstrMessageEvent, MessageChain
+from astrbot.api.message_components import Plain, Image as AstrBotImage, Record, At, Node, Music, Video
+from astrbot.core.utils.io import file_to_base64, download_image_by_url
+from lark_oapi.api.im.v1 import *
+from astrbot import logger
+
+class LarkMessageEvent(AstrMessageEvent):
+    def __init__(self, message_str, message_obj, platform_meta, session_id, bot: lark.Client):
+        super().__init__(message_str, message_obj, platform_meta, session_id)
+        self.bot = bot
+    
+    @staticmethod
+    async def _convert_to_lark(message: MessageChain, lark_client: lark.Client) -> List:
+        ret = []
+        _stage = []
+        for comp in message.chain:
+            if isinstance(comp, Plain):
+                _stage.append({
+                    "tag": "md",
+                    "text": comp.text
+                })
+            elif isinstance(comp, At):
+                _stage.append({
+                    "tag": "at",
+                    "user_id": comp.qq,
+                    "style": []
+                })
+            elif isinstance(comp, AstrBotImage):
+                file_path = ""
+                if comp.file and comp.file.startswith("file:///"):
+                    file_path = comp.file.replace('file:///', '')
+                elif comp.file and comp.file.startswith("http"):
+                    image_file_path = await download_image_by_url(comp.file)
+                    file_path = image_file_path
+                elif comp.file and comp.file.startswith("base64://"):
+                    pass
+                else:
+                    file_path = comp.file
+                
+                request = CreateImageRequest.builder() \
+                        .request_body( \
+                            CreateImageRequestBody.builder() \
+                            .image_type("message") \
+                            .image(open(file_path, 'rb')) \
+                            .build() \
+                        ) \
+                        .build()
+                response = await lark_client.im.v1.image.acreate(request)
+                if not response.success():
+                    logger.error(f"无法上传飞书图片({response.code}): {response.msg}")
+                image_key = response.data.image_key
+                print(image_key)
+                ret.append(_stage)
+                ret.append([{
+                    "tag": "img",
+                    "image_key": image_key
+                }])
+                _stage.clear()
+            else:
+                logger.warning(f"飞书 暂时不支持消息段: {comp.type}")
+
+        if _stage:
+            ret.append(_stage)            
+        return ret
+
+    async def send(self, message: MessageChain):
+        res = await LarkMessageEvent._convert_to_lark(message, self.bot)
+        wrapped = {
+            "zh_cn": {
+                "title": "",
+                "content": res,
+            }
+        }
+
+        request = ReplyMessageRequest.builder() \
+            .message_id(self.message_obj.message_id) \
+            .request_body( \
+                ReplyMessageRequestBody.builder() \
+                .content(json.dumps(wrapped)) \
+                .msg_type("post") \
+                .uuid(str(uuid.uuid4())) \
+                .reply_in_thread(False) \
+                .build() \
+            ) \
+            .build()
+
+        response = await self.bot.im.v1.message.areply(request)
+        
+        if not response.success():
+            logger.error(f"回复飞书消息失败({response.code}): {response.msg}")
+    
+        await super().send(message)
--- a/astrbot/core/platform/sources/qqofficial/qqofficial_message_event.py
+++ b/astrbot/core/platform/sources/qqofficial/qqofficial_message_event.py
@@ -8,6 +8,7 @@ from astrbot.api.platform import AstrBotMessage, PlatformMetadata
 from astrbot.api.message_components import Plain, Image
 from botpy import Client
 from botpy.http import Route
+from astrbot.api import logger


 class QQOfficialMessageEvent(AstrMessageEvent):
@@ -29,6 +30,9 @@ class QQOfficialMessageEvent(AstrMessageEvent):
        
        plain_text, image_base64, image_path = await QQOfficialMessageEvent._parse_to_qqofficial(self.send_buffer)
        
+        if not plain_text and not image_base64 and not image_path:
+            return
+        
        payload = {
            'content': plain_text,
            'msg_id': self.message_obj.message_id,
@@ -93,4 +97,6 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                else:
                    image_base64 = file_to_base64(i.file).replace("base64://", "")
                    image_file_path = i.file
+            else:
+                logger.debug(f"qq_official 忽略 {i.type}")
        return plain_text, image_base64, image_file_path
--- a/astrbot/core/platform/sources/qqofficial/qqofficial_platform_adapter.py
+++ b/astrbot/core/platform/sources/qqofficial/qqofficial_platform_adapter.py
@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import botpy
 import logging
 import time
@@ -28,25 +30,25 @@ class botClient(Client):
        
    # 收到群消息
    async def on_group_at_message_create(self, message: botpy.message.GroupMessage):
-        abm = self.platform._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
        abm.session_id = abm.sender.user_id if self.platform.unique_session else message.group_openid
        self._commit(abm)

    # 收到频道消息
    async def on_at_message_create(self, message: botpy.message.Message):
-        abm = self.platform._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
        abm.session_id = abm.sender.user_id if self.platform.unique_session else message.channel_id
        self._commit(abm)
        
    # 收到私聊消息
    async def on_direct_message_create(self, message: botpy.message.DirectMessage):
-        abm = self.platform._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
        abm.session_id = abm.sender.user_id
        self._commit(abm)
        
    # 收到 C2C 消息
    async def on_c2c_message_create(self, message: botpy.message.C2CMessage):
-        abm = self.platform._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
        abm.session_id = abm.sender.user_id
        self._commit(abm)
        
@@ -102,7 +104,8 @@ class QQOfficialPlatformAdapter(Platform):
            "QQ 机器人官方 API 适配器",
        )

-    def _parse_from_qqofficial(self, message: Union[botpy.message.Message, botpy.message.GroupMessage],
+    @staticmethod
+    def _parse_from_qqofficial(message: Union[botpy.message.Message, botpy.message.GroupMessage],
                                  message_type: MessageType):
        abm = AstrBotMessage()
        abm.type = message_type
--- a/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_adapter.py
+++ b/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_adapter.py
@@ -0,0 +1,99 @@
+import botpy
+import logging
+import asyncio
+import botpy.message
+import botpy.types
+import botpy.types.message
+
+from botpy import Client
+from astrbot.api.platform import Platform, AstrBotMessage, MessageType, PlatformMetadata
+from astrbot.api.event import MessageChain
+from astrbot.core.platform.astr_message_event import MessageSesion
+from .qo_webhook_event import QQOfficialWebhookMessageEvent
+from ...register import register_platform_adapter
+from .qo_webhook_server import QQOfficialWebhook
+from ..qqofficial.qqofficial_platform_adapter import QQOfficialPlatformAdapter
+
+# remove logger handler
+for handler in logging.root.handlers[:]:
+    logging.root.removeHandler(handler)
+    
+# QQ 机器人官方框架
+class botClient(Client):
+    def set_platform(self, platform: 'QQOfficialWebhookPlatformAdapter'):
+        self.platform = platform
+        
+    # 收到群消息
+    async def on_group_at_message_create(self, message: botpy.message.GroupMessage):
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
+        abm.session_id = abm.sender.user_id if self.platform.unique_session else message.group_openid
+        self._commit(abm)
+
+    # 收到频道消息
+    async def on_at_message_create(self, message: botpy.message.Message):
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.GROUP_MESSAGE)
+        abm.session_id = abm.sender.user_id if self.platform.unique_session else message.channel_id
+        self._commit(abm)
+        
+    # 收到私聊消息
+    async def on_direct_message_create(self, message: botpy.message.DirectMessage):
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
+        abm.session_id = abm.sender.user_id
+        self._commit(abm)
+        
+    # 收到 C2C 消息
+    async def on_c2c_message_create(self, message: botpy.message.C2CMessage):
+        abm = QQOfficialPlatformAdapter._parse_from_qqofficial(message, MessageType.FRIEND_MESSAGE)
+        abm.session_id = abm.sender.user_id
+        self._commit(abm)
+        
+    def _commit(self, abm: AstrBotMessage):
+        self.platform.commit_event(QQOfficialWebhookMessageEvent(
+            abm.message_str,
+            abm,
+            self.platform.meta(),
+            abm.session_id,
+            self
+        ))
+        
+@register_platform_adapter("qq_official_webhook", "QQ 机器人官方 API 适配器(Webhook)")
+class QQOfficialWebhookPlatformAdapter(Platform):
+
+    def __init__(self, platform_config: dict, platform_settings: dict, event_queue: asyncio.Queue) -> None:
+        super().__init__(event_queue)
+        
+        self.config = platform_config
+        
+        self.appid = platform_config['appid']
+        self.secret = platform_config['secret']
+        self.unique_session = platform_settings['unique_session']
+
+        intents = botpy.Intents(
+            public_messages=True,
+            public_guild_messages=True,
+            direct_message=True
+        )
+        self.client = botClient(
+            intents=intents, # 已经无用
+            bot_log=False,
+            timeout=20,
+        )
+        self.client.set_platform(self)
+
+    async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
+        raise NotImplementedError("QQ 机器人官方 API 适配器不支持 send_by_session")
+        
+    def meta(self) -> PlatformMetadata:
+        return PlatformMetadata(
+            "qq_official_webhook",
+            "QQ 机器人官方 API 适配器",
+        )
+
+    async def run(self):
+        self.webhook_helper = QQOfficialWebhook(
+            self.config,
+            self._event_queue,
+            self.client
+        )
+        await self.webhook_helper.initialize()
+        await self.webhook_helper.start_polling()
--- a/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_event.py
+++ b/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_event.py
@@ -0,0 +1,18 @@
+import botpy
+import botpy.message
+import botpy.types
+import botpy.types.message
+from astrbot.core.utils.io import file_to_base64, download_image_by_url
+from astrbot.api.event import AstrMessageEvent, MessageChain
+from astrbot.api.platform import AstrBotMessage, PlatformMetadata
+from astrbot.api.message_components import Plain, Image, Reply
+from botpy import Client
+from botpy.http import Route
+from astrbot.api import logger
+from ..qqofficial.qqofficial_message_event import QQOfficialMessageEvent
+
+
+class QQOfficialWebhookMessageEvent(QQOfficialMessageEvent):
+    def __init__(self, message_str: str, message_obj: AstrBotMessage, platform_meta: PlatformMetadata, session_id: str, bot: Client):
+        super().__init__(message_str, message_obj, platform_meta, session_id, bot)
+    
--- a/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_server.py
+++ b/astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_server.py
@@ -0,0 +1,108 @@
+import aiohttp
+import quart
+import json
+import logging
+import asyncio
+import typing
+from botpy import BotAPI, BotHttp, Client, Token, BotWebSocket, ConnectionSession
+from astrbot.api import logger
+import traceback
+from cryptography.hazmat.primitives.asymmetric import ed25519
+
+# remove logger handler
+for handler in logging.root.handlers[:]:
+    logging.root.removeHandler(handler)
+
+class QQOfficialWebhook():
+    def __init__(self, config: dict, event_queue: asyncio.Queue, botpy_client: Client):
+        self.appid = config['appid']
+        self.secret = config['secret']
+        self.port = config.get("port", 6196)
+        
+        if isinstance(self.port, str):
+            self.port = int(self.port)
+        
+        self.http: BotHttp = BotHttp(timeout=300)
+        self.api: BotAPI = BotAPI(http=self.http)
+        self.token = Token(self.appid, self.secret)
+        
+        self.server = quart.Quart(__name__)
+        self.server.add_url_rule('/astrbot-qo-webhook/callback', view_func=self.callback, methods=['POST'])
+        self.client = botpy_client
+        self.event_queue = event_queue
+        
+    async def initialize(self):
+        logger.info(f"正在登录到 QQ 官方机器人...")
+        self.user = await self.http.login(self.token)
+        logger.info(f"已登录 QQ 官方机器人账号: {self.user}")
+        # 直接注入到 botpy 的 Client，移花接木！
+        self.client.api = self.api
+        self.client.http = self.http
+        
+        async def bot_connect():
+            pass
+        
+        self._connection = ConnectionSession(
+            max_async=1,
+            connect=bot_connect,
+            dispatch=self.client.ws_dispatch,
+            loop=asyncio.get_event_loop(),
+            api=self.api,
+        )
+
+    async def repeat_seed(self, bot_secret: str, target_size: int = 32) -> bytes:
+        seed = bot_secret
+        while len(seed) < target_size:
+            seed *= 2
+        return seed[:target_size].encode('utf-8')
+
+        
+    async def webhook_validation(self, validation_payload: dict):
+        seed = await self.repeat_seed(self.secret)
+        private_key = ed25519.Ed25519PrivateKey.from_private_bytes(seed)
+        msg = validation_payload.get("event_ts", "") + validation_payload.get("plain_token", "")
+        # sign
+        signature = private_key.sign(msg.encode()).hex()
+        response = {
+            "plain_token": validation_payload.get("plain_token"),
+            "signature": signature
+        }
+        return response
+        
+    async def callback(self):
+        msg: dict = await quart.request.json
+        logger.debug(f"收到 qq_official_webhook 回调: {msg}")
+
+        event = msg.get("t")
+        opcode = msg.get("op")
+        data = msg.get("d")
+        
+        if opcode == 13:
+            # validation
+            signed = await self.webhook_validation(data)
+            print(signed)
+            return signed
+
+        if event and opcode == BotWebSocket.WS_DISPATCH_EVENT:
+            event = msg["t"].lower()
+            try:
+                func = self._connection.parser[event]
+            except KeyError:
+                logger.error("_parser unknown event %s.", event)
+            else:
+                func(msg)
+                
+        return {"opcode": 12}
+    
+    async def start_polling(self):
+        await self.server.run_task(
+            host='0.0.0.0', 
+            port=self.port, 
+            shutdown_trigger=self.shutdown_trigger_placeholder
+        )
+        
+    async def shutdown_trigger_placeholder(self):
+        while not self.event_queue.closed:
+            await asyncio.sleep(1)
+        logger.info("qq_official_webhook 适配器已关闭。")
+        
--- a/astrbot/core/platform/sources/vchat/vchat_message_event.py
+++ b/astrbot/core/platform/sources/vchat/vchat_message_event.py
@@ -1,44 +0,0 @@
-import random
-import asyncio
-from astrbot.core.utils.io import download_image_by_url
-from astrbot.api import logger
-from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.platform import AstrBotMessage, PlatformMetadata
-from astrbot.api.message_components import Plain, Image
-from vchat import Core
-
-class VChatPlatformEvent(AstrMessageEvent):
-    def __init__(self, message_str: str, message_obj: AstrBotMessage, platform_meta: PlatformMetadata, session_id: str, client: Core):
-        super().__init__(message_str, message_obj, platform_meta, session_id)
-        self.client = client
-        
-    @staticmethod
-    async def send_with_client(client: Core, message: MessageChain, user_name: str):
-        plain = ""
-        for comp in message.chain:
-            if isinstance(comp, Plain):
-                if message.is_split_:
-                    await client.send_msg(comp.text, user_name)
-                else:
-                    plain += comp.text
-            elif isinstance(comp, Image):
-                if comp.file and comp.file.startswith("file:///"):
-                    file_path = comp.file.replace("file:///", "")
-                    with open(file_path, "rb") as f:
-                        await client.send_image(user_name, fd=f)
-                elif comp.file and comp.file.startswith("http"):
-                    image_path = await download_image_by_url(comp.file)
-                    with open(image_path, "rb") as f:
-                        await client.send_image(user_name, fd=f)
-            else:
-                logger.error(f"不支持的 vchat(微信适配器) 消息类型: {comp}")
-            await asyncio.sleep(random.uniform(0.5, 1.5)) # 🤓
-        
-        if plain:
-            await client.send_msg(plain, user_name)
-                
-        
-    async def send(self, message: MessageChain):
-        await VChatPlatformEvent.send_with_client(self.client, message, self.message_obj.raw_message.from_.username)
-        await super().send(message)
-        
--- a/astrbot/core/platform/sources/vchat/vchat_platform_adapter.py
+++ b/astrbot/core/platform/sources/vchat/vchat_platform_adapter.py
@@ -1,120 +0,0 @@
-import sys
-import time
-import uuid
-import asyncio
-import os
-
-from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, MessageType, PlatformMetadata
-from astrbot.api.event import MessageChain
-from astrbot.api.message_components import *
-from astrbot.api import logger
-from astrbot.core.platform.astr_message_event import MessageSesion
-from .vchat_message_event import VChatPlatformEvent
-from ...register import register_platform_adapter
-
-from vchat import Core
-from vchat import model
-
-if sys.version_info >= (3, 12):
-    from typing import override
-else:
-    from typing_extensions import override
-
-@register_platform_adapter("vchat", "基于 VChat 的 Wechat 适配器")
-class VChatPlatformAdapter(Platform):
-
-    def __init__(self, platform_config: dict, platform_settings: dict, event_queue: asyncio.Queue) -> None:
-        super().__init__(event_queue)
-        self.config = platform_config
-        self.settingss = platform_settings
-        self.test_mode = os.environ.get('TEST_MODE', 'off') == 'on'
-        self.client_self_id = uuid.uuid4().hex[:8]
-    
-    @override
-    async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
-        from_username = session.session_id.split('$$')[0]
-        await VChatPlatformEvent.send_with_client(self.client, message_chain, from_username)
-        await super().send_by_session(session, message_chain)
-    
-    @override
-    def meta(self) -> PlatformMetadata:
-        return PlatformMetadata(
-            "vchat",
-            "基于 VChat 的 Wechat 适配器",
-        )
-
-    @override
-    def run(self):
-        self.client = Core()
-        @self.client.msg_register(msg_types=model.ContentTypes.TEXT, 
-                                  contact_type=model.ContactTypes.CHATROOM | model.ContactTypes.USER)
-        async def _(msg: model.Message):
-            if isinstance(msg.content, model.UselessContent):
-                return
-            if msg.create_time < self.start_time:
-                logger.debug(f"忽略旧消息: {msg}")
-                return
-            logger.debug(f"收到消息: {msg.todict()}")
-            abmsg = self.convert_message(msg)
-            # await self.handle_msg(abmsg) # 不能直接调用，否则会阻塞
-            asyncio.create_task(self.handle_msg(abmsg))
-        
-        # TODO: 对齐微信服务器时间
-        self.start_time = int(time.time())
-        return self._run()
-    
-
-    async def _run(self):
-        await self.client.init()
-        await self.client.auto_login(hot_reload=True, enable_cmd_qr=True)
-        await self.client.run()
-    
-    def convert_message(self, msg: model.Message) -> AstrBotMessage:
-        # credits: https://github.com/z2z63/astrbot_plugin_vchat/blob/master/main.py#L49
-        assert isinstance(msg.content, model.TextContent)
-        amsg = AstrBotMessage()
-        amsg.message = [Plain(msg.content.content)]
-        amsg.self_id = self.client_self_id
-        if msg.content.is_at_me:
-            amsg.message.insert(0, At(qq=amsg.self_id))
-        
-        sender = msg.chatroom_sender or msg.from_
-        amsg.sender = MessageMember(sender.username, sender.nickname)
-        
-        if msg.content.is_at_me:
-            amsg.message_str = msg.content.content.split("\u2005")[1].strip()
-        else:
-            amsg.message_str = msg.content.content
-        amsg.message_id = msg.message_id
-        if isinstance(msg.from_, model.User):
-            amsg.type = MessageType.FRIEND_MESSAGE
-        elif isinstance(msg.from_, model.Chatroom):
-            amsg.type = MessageType.GROUP_MESSAGE
-            amsg.group_id = msg.from_.username
-        else:
-            logger.error(f"不支持的 Wechat 消息类型: {msg.from_}")
-            
-        amsg.raw_message = msg
-        
-        if self.settingss['unique_session']:
-            session_id = msg.from_.username + "$$" + msg.to.username
-            if msg.chatroom_sender is not None:
-                session_id += '$$' + msg.chatroom_sender.username
-        else:
-            session_id = msg.from_.username
-                
-        amsg.session_id = session_id
-        return amsg
-    
-    async def handle_msg(self, message: AstrBotMessage):
-        message_event = VChatPlatformEvent(
-            message_str=message.message_str,
-            message_obj=message,
-            platform_meta=self.meta(),
-            session_id=message.session_id,
-            client=self.client
-        )
-        
-        logger.info(f"处理消息: {message_event}")
-        
-        self.commit_event(message_event)
--- a/astrbot/core/platform/sources/webchat/webchat_event.py
+++ b/astrbot/core/platform/sources/webchat/webchat_event.py
@@ -1,8 +1,10 @@
 import os
 import uuid
+import base64
+from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, MessageChain
 from astrbot.api.message_components import Plain, Image
-from astrbot.core.utils.io import file_to_base64, download_image_by_url
+from astrbot.core.utils.io import download_image_by_url
 from astrbot.core import web_chat_back_queue

 class WebChatMessageEvent(AstrMessageEvent):
@@ -30,6 +32,11 @@ class WebChatMessageEvent(AstrMessageEvent):
                    with open(path, "wb") as f:
                        with open(ph, "rb") as f2:
                            f.write(f2.read())
+                elif comp.file.startswith("base64://"):
+                    base64_str = comp.file[9:]
+                    image_data = base64.b64decode(base64_str)
+                    with open(path, "wb") as f:
+                        f.write(image_data)
                elif comp.file and comp.file.startswith("http"):
                    await download_image_by_url(comp.file, path=path)
                else:
@@ -37,5 +44,7 @@ class WebChatMessageEvent(AstrMessageEvent):
                        with open(comp.file, "rb") as f2:
                            f.write(f2.read())
                web_chat_back_queue.put_nowait((f"[IMAGE]{filename}", cid))
+            else:
+                logger.debug(f"webchat 忽略: {comp.type}")
        web_chat_back_queue.put_nowait(None)
        await super().send(message)
--- a/astrbot/core/provider/entites.py
+++ b/astrbot/core/provider/entites.py
@@ -2,6 +2,8 @@ import enum
 from dataclasses import dataclass, field
 from typing import List, Dict, Type
 from .func_tool_manager import FuncCall
+from openai.types.chat.chat_completion import ChatCompletion
+from astrbot.core.db.po import Conversation


 class ProviderType(enum.Enum):
@@ -37,18 +39,26 @@ class ProviderRequest():
    '''上下文。格式与 openai 的上下文格式一致：
    参考 https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages
    '''
-    
    system_prompt: str = ""
    '''系统提示词'''
+    conversation: Conversation = None
    
+    def __repr__(self):
+        return f"ProviderRequest(prompt={self.prompt}, session_id={self.session_id}, image_urls={self.image_urls}, func_tool={self.func_tool}, contexts={self.contexts}, system_prompt={self.system_prompt})"
+    
+    def __str__(self):
+        return self.__repr__()
    
@dataclass
 class LLMResponse:
    role: str
-    '''角色'''
+    '''角色, assistant, tool, err'''
    completion_text: str = ""
    '''LLM 返回的文本'''
    tools_call_args: List[Dict[str, any]] = field(default_factory=list)
    '''工具调用参数'''
    tools_call_name: List[str] = field(default_factory=list)
-    '''工具调用名称'''
+    '''工具调用名称'''
+    
+    raw_completion: ChatCompletion = None
+    _new_record: Dict[str, any] = None
--- a/astrbot/core/provider/func_tool_manager.py
+++ b/astrbot/core/provider/func_tool_manager.py
@@ -102,20 +102,50 @@ class FuncCall:
            )
        return _l
    
+    def get_func_desc_anthropic_style(self) -> list:
+        """
+        获得 Anthropic API 风格的**已经激活**的工具描述
+        """
+        tools = []
+        for f in self.func_list:
+            if not f.active:
+                continue
+
+            # Convert internal format to Anthropic style
+            tool = {
+                "name": f.name,
+                "description": f.description,
+                "input_schema": {
+                    "type": "object",
+                    "properties": f.parameters.get("properties", {}),
+                    # Keep the required field from the original parameters if it exists
+                    "required": f.parameters.get("required", [])
+                }
+            }
+            tools.append(tool)
+        return tools
+    
    def get_func_desc_google_genai_style(self) -> Dict:
        declarations = {}
        tools = []
        for f in self.func_list:
            if not f.active:
                continue
-            tools.append(
-                {
-                    "name": f.name,
-                    "parameters": f.parameters,
-                    "description": f.description,
-                }
-            )
-        declarations["function_declarations"] = tools
+
+            func_declaration = {
+                "name": f.name,
+                "description": f.description
+            }
+
+            # 检查并添加非空的properties参数
+            params = f.parameters if isinstance(f.parameters, dict) else {}
+            if params.get("properties", {}):
+                func_declaration["parameters"] = params
+
+            tools.append(func_declaration)
+
+        if tools:
+            declarations["function_declarations"] = tools
        return declarations
        

--- a/astrbot/core/provider/manager.py
+++ b/astrbot/core/provider/manager.py
@@ -1,4 +1,5 @@
 import traceback
+import uuid
 from astrbot.core.config.astrbot_config import AstrBotConfig
 from .provider import Provider, STTProvider, TTSProvider, Personality
 from .entites import ProviderType
@@ -13,8 +14,11 @@ class ProviderManager():
        self.providers_config: List = config['provider']
        self.provider_settings: dict = config['provider_settings']
        self.provider_stt_settings: dict = config.get('provider_stt_settings', {})
+        self.provider_tts_settings: dict = config.get('provider_tts_settings', {})
        self.persona_configs: list = config.get('persona', [])
        
+        # 人格情景管理
+        # 目前没有拆成独立的模块
        self.default_persona_name = self.provider_settings.get('default_personality', 'default')
        self.personas: List[Personality] = []
        self.selected_default_persona = None
@@ -26,7 +30,7 @@ class ProviderManager():
            if begin_dialogs:
                if len(begin_dialogs) % 2 != 0:
                    logger.error(f"{persona['name']} 人格情景预设对话格式不对，条数应该为偶数。")
-                    continue
+                    begin_dialogs = []
                user_turn = True
                for dialog in begin_dialogs:
                    bd_processed.append({
@@ -38,9 +42,9 @@ class ProviderManager():
            if mood_imitation_dialogs:
                if len(mood_imitation_dialogs) % 2 != 0:
                    logger.error(f"{persona['name']} 对话风格对话格式不对，条数应该为偶数。")
-                    continue
+                    mood_imitation_dialogs = []
                user_turn = True
-                for dialog in begin_dialogs:
+                for dialog in mood_imitation_dialogs:
                    role = "A" if user_turn else "B"
                    mid_processed += f"{role}: {dialog}\n"
                    if not user_turn:
@@ -59,6 +63,19 @@ class ProviderManager():
            except Exception as e:
                logger.error(f"解析 Persona 配置失败：{e}")
        
+        if not self.selected_default_persona and len(self.personas) > 0:
+            # 默认选择第一个
+            self.selected_default_persona = self.personas[0]
+            
+        if not self.selected_default_persona:
+            self.selected_default_persona = Personality(
+                prompt="You are a helpful and friendly assistant.",
+                name="default",
+                _begin_dialogs_processed=[],
+                _mood_imitation_dialogs_processed=""
+            )
+            self.personas.append(self.selected_default_persona)
+                
        
        self.provider_insts: List[Provider] = []
        '''加载的 Provider 的实例'''
@@ -82,40 +99,56 @@ class ProviderManager():
        if kdb_cfg and len(kdb_cfg):
            self.curr_kdb_name = list(kdb_cfg.keys())[0]
        
+        changed = False
        for provider_cfg in self.providers_config:
            if not provider_cfg['enable']:
                continue
            
            if provider_cfg['id'] in self.loaded_ids:
-                raise ValueError(f"Provider ID 重复：{provider_cfg['id']}。")
+                new_id = f"{provider_cfg['id']}_{str(uuid.uuid4())[:8]}"
+                logger.info(f"Provider ID 重复：{provider_cfg['id']}。已自动更改为 {new_id}。")
+                provider_cfg['id'] = new_id
+                changed = True
            self.loaded_ids[provider_cfg['id']] = True
            
            try:
                match provider_cfg['type']:
                    case "openai_chat_completion":
-                        from .sources.openai_source import ProviderOpenAIOfficial # noqa: F401
+                        from .sources.openai_source import ProviderOpenAIOfficial as ProviderOpenAIOfficial
                    case "zhipu_chat_completion":
-                        from .sources.zhipu_source import ProviderZhipu # noqa: F401
+                        from .sources.zhipu_source import ProviderZhipu as ProviderZhipu
+                    case "anthropic_chat_completion":
+                        from .sources.anthropic_source import ProviderAnthropic as ProviderAnthropic
                    case "llm_tuner":
                        logger.info("加载 LLM Tuner 工具 ...")
-                        from .sources.llmtuner_source import LLMTunerModelLoader # noqa: F401
+                        from .sources.llmtuner_source import LLMTunerModelLoader as LLMTunerModelLoader
                    case "dify":
-                        from .sources.dify_source import ProviderDify # noqa: F401
+                        from .sources.dify_source import ProviderDify as ProviderDify
+                    case "dashscope":
+                        from .sources.dashscope_source import ProviderDashscope as ProviderDashscope
                    case "googlegenai_chat_completion":
-                        from .sources.gemini_source import ProviderGoogleGenAI # noqa: F401
+                        from .sources.gemini_source import ProviderGoogleGenAI as ProviderGoogleGenAI
                    case "openai_whisper_api":
-                        from .sources.whisper_api_source import ProviderOpenAIWhisperAPI # noqa: F401
+                        from .sources.whisper_api_source import ProviderOpenAIWhisperAPI as ProviderOpenAIWhisperAPI
                    case "openai_whisper_selfhost":
-                        from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost # noqa: F401
+                        from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost as ProviderOpenAIWhisperSelfHost
                    case "openai_tts_api":
-                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI # noqa: F401
+                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI as ProviderOpenAITTSAPI
+                    case "fishaudio_tts_api":
+                        from .sources.fishaudio_tts_api_source import ProviderFishAudioTTSAPI as ProviderFishAudioTTSAPI
            except (ImportError, ModuleNotFoundError) as e:
                logger.critical(f"加载 {provider_cfg['type']}({provider_cfg['id']}) 提供商适配器失败：{e}。可能是因为有未安装的依赖。")
                continue
            except Exception as e:
                logger.critical(f"加载 {provider_cfg['type']}({provider_cfg['id']}) 提供商适配器失败：{e}。未知原因")
                continue
-            
+        
+        if changed:
+            try:
+                config.save_config()
+            except Exception as e:
+                logger.warning(f"保存配置文件失败：{e}")
+
    async def initialize(self):
        
        selected_provider_id = sp.get("curr_provider")
@@ -123,7 +156,7 @@ class ProviderManager():
        selected_tts_provider_id = self.provider_settings.get("provider_id")
        provider_enabled = self.provider_settings.get("enable", False)
        stt_enabled = self.provider_stt_settings.get("enable", False)
-        tts_enabled = self.provider_settings.get("enable", False)
+        tts_enabled = self.provider_tts_settings.get("enable", False)
            
        for provider_config in self.providers_config:
            if not provider_config['enable']:
@@ -133,7 +166,7 @@ class ProviderManager():
                continue

            provider_metadata = provider_cls_map[provider_config['type']]
-            logger.info(f"尝试实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器 ...")
+            logger.debug(f"尝试实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器 ...")
            try:
                # 按任务实例化提供商
                
--- a/astrbot/core/provider/provider.py
+++ b/astrbot/core/provider/provider.py
@@ -8,6 +8,8 @@ from typing import TypedDict
 from astrbot.core.provider.func_tool_manager import FuncCall
 from astrbot.core.provider.entites import LLMResponse
 from dataclasses import dataclass
+
+
 class Personality(TypedDict):
    prompt: str = ""
    name: str = ""
@@ -15,8 +17,8 @@ class Personality(TypedDict):
    mood_imitation_dialogs: List[str] = []
    
    # cache
-    _begin_dialogs_processed: List[dict]
-    _mood_imitation_dialogs_processed: str
+    _begin_dialogs_processed: List[dict] = []
+    _mood_imitation_dialogs_processed: str = ""
    
    
@dataclass
@@ -60,25 +62,11 @@ class Provider(AbstractProvider):
    ) -> None:
        super().__init__(provider_config)
        
-        self.session_memory = defaultdict(list)
-        '''维护了 session_id 的上下文，**不包含 system 指令**。'''
-        
        self.provider_settings = provider_settings
        
        self.curr_personality: Personality = default_persona
        '''维护了当前的使用的 persona，即人格。可能为 None'''
-        
-        self.db_helper = db_helper
-        '''用于持久化的数据库操作对象。'''

-        if persistant_history:
-            # 读取历史记录
-            try:
-                for history in db_helper.get_llm_history(provider_type=provider_config['type']):
-                    self.session_memory[history.session_id] = json.loads(history.content)
-            except BaseException as e:
-                logger.warning(f"读取 LLM 对话历史记录 失败：{e}。仍可正常使用。")
-    
    @abc.abstractmethod
    def get_current_key(self) -> str:
        raise NotImplementedError()
@@ -96,22 +84,6 @@ class Provider(AbstractProvider):
        '''获得支持的模型列表'''
        raise NotImplementedError()
    
-    @abc.abstractmethod
-    async def get_human_readable_context(self, session_id: str, page: int, page_size: int):
-        '''获取人类可读的上下文
-        
-        page 从 1 开始
-
-        Example:
-            
-            ["User: 你好", "Assistant: 你好！"]
-            
-        Return:
-            contexts: List[str]: 上下文列表
-            total_pages: int: 总页数
-        '''
-        raise NotImplementedError()
-    
    @abc.abstractmethod
    async def text_chat(self,
                        prompt: str,
@@ -125,26 +97,35 @@ class Provider(AbstractProvider):
        
        Args:
            prompt: 提示词
-            session_id: 会话 ID
+            session_id: 会话 ID(此属性已经被废弃)
            image_urls: 图片 URL 列表
            tools: Function-calling 工具
            contexts: 上下文
            kwargs: 其他参数
            
        Notes:
-            - 如果传入了 contexts，将会提前加上上下文。否则使用 session_memory 中的上下文。
-            - 可以选择性地传入 session_id，如果传入了 session_id，将会使用 session_id 对应的上下文进行对话，
-            并且也会记录相应的对话上下文，实现多轮对话。如果不传入则不会记录上下文。
            - 如果传入了 image_urls，将会在对话时附上图片。如果模型不支持图片输入，将会抛出错误。
            - 如果传入了 tools，将会使用 tools 进行 Function-calling。如果模型不支持 Function-calling，将会抛出错误。
        '''
        raise NotImplementedError()
-    
-    @abc.abstractmethod
-    async def forget(self, session_id: str) -> bool:
-        '''重置某一个 session_id 的上下文'''
-        raise NotImplementedError()

+    async def pop_record(self, context: List):
+        '''
+        弹出 context 第一条非系统提示词对话记录
+        '''
+        poped = 0
+        indexs_to_pop = []
+        for idx, record in enumerate(context):
+            if record["role"] == "system":
+                continue
+            else:
+                indexs_to_pop.append(idx)
+                poped += 1
+                if poped == 2:
+                    break
+                
+        for idx in reversed(indexs_to_pop):
+            context.pop(idx)

        
 class STTProvider(AbstractProvider):
--- a/astrbot/core/provider/sources/anthropic_source.py
+++ b/astrbot/core/provider/sources/anthropic_source.py
@@ -0,0 +1,189 @@
+from typing import List
+from mimetypes import guess_type
+
+from anthropic import AsyncAnthropic
+from anthropic.types import Message
+
+from astrbot.core.utils.io import download_image_by_url
+from astrbot.core.db import BaseDatabase
+from astrbot.api.provider import Provider, Personality
+from astrbot import logger
+from astrbot.core.provider.func_tool_manager import FuncCall
+from ..register import register_provider_adapter
+from astrbot.core.provider.entites import LLMResponse
+from .openai_source import ProviderOpenAIOfficial
+
+@register_provider_adapter("anthropic_chat_completion", "Anthropic Claude API 提供商适配器")
+class ProviderAnthropic(ProviderOpenAIOfficial):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+        db_helper: BaseDatabase,
+        persistant_history = True,
+        default_persona: Personality = None
+    ) -> None:
+        # Skip OpenAI's __init__ and call Provider's __init__ directly
+        Provider.__init__(self, provider_config, provider_settings, persistant_history, db_helper, default_persona)
+
+        self.chosen_api_key = None
+        self.api_keys: List = provider_config.get("key", [])
+        self.chosen_api_key = self.api_keys[0] if len(self.api_keys) > 0 else None
+        self.base_url = provider_config.get("api_base", "https://api.anthropic.com")
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+
+        self.client = AsyncAnthropic(
+            api_key=self.chosen_api_key,
+            timeout=self.timeout,
+            base_url=self.base_url
+        )
+        
+        self.set_model(provider_config['model_config']['model'])
+
+    async def _query(self, payloads: dict, tools: FuncCall) -> LLMResponse:
+        if tools:
+            tool_list = tools.get_func_desc_anthropic_style()
+            if tool_list:
+                payloads['tools'] = tool_list
+
+        completion = await self.client.messages.create(
+            **payloads,
+            stream=False
+        )
+
+        assert isinstance(completion, Message)
+        logger.debug(f"completion: {completion}")
+
+        if len(completion.content) == 0:
+            raise Exception("API 返回的 completion 为空。")
+        # TODO: 如果进行函数调用，思维链被截断，用户可能需要思维链的内容
+        # 选最后一条消息，如果要进行函数调用，anthropic会先返回文本消息的思维链，然后再返回函数调用请求
+        content = completion.content[-1]
+        
+        llm_response = LLMResponse("assistant")
+                
+        if content.type == "text":
+            # text completion
+            completion_text = str(content.text).strip()
+            llm_response.completion_text = completion_text
+        
+        # Anthropic每次只返回一个函数调用
+        if completion.stop_reason == "tool_use":
+            # tools call (function calling)
+            args_ls = []
+            func_name_ls = []
+            func_name_ls.append(content.name)
+            args_ls.append(content.input)
+            llm_response.role = "tool"
+            llm_response.tools_call_args = args_ls
+            llm_response.tools_call_name = func_name_ls
+
+        if not llm_response.completion_text and not llm_response.tools_call_args:
+            logger.error(f"API 返回的 completion 无法解析：{completion}。")
+            raise Exception(f"API 返回的 completion 无法解析：{completion}。")
+        
+        llm_response.raw_completion = completion
+        
+        return llm_response
+        
+    async def text_chat(
+        self,
+        prompt: str,
+        session_id: str = None,
+        image_urls: List[str] = [],
+        func_tool: FuncCall = None,
+        contexts=[],
+        system_prompt=None,
+        **kwargs
+    ) -> LLMResponse:
+        
+        if not prompt:
+            prompt = "<image>"
+    
+        new_record = await self.assemble_context(prompt, image_urls)
+        context_query = [*contexts, new_record]
+
+        for part in context_query:
+            if '_no_save' in part:
+                del part['_no_save']
+
+        model_config = self.provider_config.get("model_config", {})
+
+        payloads = {
+            "messages": context_query,
+            **model_config
+        }
+        # Anthropic has a different way of handling system prompts
+        if system_prompt:
+            payloads['system'] = system_prompt
+
+        llm_response = None
+        try:
+            llm_response = await self._query(payloads, func_tool)
+
+        except Exception as e:
+            if "maximum context length" in str(e):
+                retry_cnt = 20
+                while retry_cnt > 0:
+                    logger.warning(f"上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
+                    try:
+                        await self.pop_record(context_query)
+                        response = await self.client.messages.create(
+                            messages=context_query,
+                            **model_config
+                        )
+                        llm_response = LLMResponse("assistant")
+                        llm_response.completion_text = response.content[0].text
+                        llm_response.raw_completion = response
+                        return llm_response
+                    except Exception as e:
+                        if "maximum context length" in str(e):
+                            retry_cnt -= 1
+                        else:
+                            raise e
+                return LLMResponse("err", "err: 请尝试 /reset 清除会话记录。")
+            else:
+                logger.error(f"发生了错误。Provider 配置如下: {model_config}")
+                raise e
+            
+        return llm_response
+
+    async def assemble_context(self, text: str, image_urls: List[str] = None):
+        '''组装上下文，支持文本和图片'''
+        if not image_urls:
+            return {"role": "user", "content": text}
+            
+        content = []
+        content.append({"type": "text", "text": text})
+        
+        for image_url in image_urls:
+            if image_url.startswith("http"):
+                image_path = await download_image_by_url(image_url)
+                image_data = await self.encode_image_bs64(image_path)
+            elif image_url.startswith("file:///"):
+                image_path = image_url.replace("file:///", "")
+                image_data = await self.encode_image_bs64(image_path)
+            else:
+                image_data = await self.encode_image_bs64(image_url)
+                
+            if not image_data:
+                logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                continue
+                
+            # Get mime type for the image
+            mime_type, _ = guess_type(image_url)
+            if not mime_type:
+                mime_type = "image/jpeg"  # Default to JPEG if can't determine
+                
+            content.append({
+                "type": "image",
+                "source": {
+                    "type": "base64",
+                    "media_type": mime_type,
+                    "data": image_data.split("base64,")[1] if "base64," in image_data else image_data
+                }
+            })
+            
+        return {"role": "user", "content": content}
--- a/astrbot/core/provider/sources/dashscope_source.py
+++ b/astrbot/core/provider/sources/dashscope_source.py
@@ -0,0 +1,128 @@
+import asyncio
+import functools
+from typing import List
+from .. import Provider, Personality
+from ..entites import LLMResponse
+from ..func_tool_manager import FuncCall
+from astrbot.core.db import BaseDatabase
+from ..register import register_provider_adapter
+from .openai_source import ProviderOpenAIOfficial
+from astrbot.core import logger, sp
+from dashscope import Application
+
+
+@register_provider_adapter("dashscope", "Dashscope APP 适配器。")
+class ProviderDashscope(ProviderOpenAIOfficial):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+        db_helper: BaseDatabase,
+        persistant_history=False,
+        default_persona: Personality = None,
+    ) -> None:
+        Provider.__init__(
+            self,
+            provider_config,
+            provider_settings,
+            persistant_history,
+            db_helper,
+            default_persona,
+        )
+        self.api_key = provider_config.get("dashscope_api_key", "")
+        if not self.api_key:
+            raise Exception("阿里云百炼 API Key 不能为空。")
+        self.app_id = provider_config.get("dashscope_app_id", "")
+        if not self.app_id:
+            raise Exception("阿里云百炼 APP ID 不能为空。")
+        self.dashscope_app_type = provider_config.get("dashscope_app_type", "")
+        if not self.dashscope_app_type:
+            raise Exception("阿里云百炼 APP 类型不能为空。")
+        self.model_name = "dashscope"
+        self.variables: dict = provider_config.get("variables", {})
+
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+
+    async def text_chat(
+        self,
+        prompt: str,
+        session_id: str = None,
+        image_urls: List[str] = [],
+        func_tool: FuncCall = None,
+        contexts: List = None,
+        system_prompt: str = None,
+        **kwargs,
+    ) -> LLMResponse:
+        # 获得会话变量
+        payload_vars = self.variables.copy()
+        # 动态变量
+        session_vars = sp.get("session_variables", {})
+        session_var = session_vars.get(session_id, {})
+        payload_vars.update(session_var)
+
+        if self.dashscope_app_type in ["agent", "dialog-workflow"]:
+            # 支持多轮对话的
+            new_record = {"role": "user", "content": prompt}
+            if image_urls:
+                logger.warning("阿里云百炼暂不支持图片输入，将自动忽略图片内容。")
+            contexts_no_img = await self._remove_image_from_context(contexts)
+            context_query = [*contexts_no_img, new_record]
+            if system_prompt:
+                context_query.insert(0, {"role": "system", "content": system_prompt})
+            for part in context_query:
+                if "_no_save" in part:
+                    del part["_no_save"]
+            # 调用阿里云百炼 API
+            partial = functools.partial(
+                Application.call,
+                app_id=self.app_id,
+                api_key=self.api_key,
+                messages=context_query,
+                biz_params=payload_vars or None,
+            )
+            response = await asyncio.get_event_loop().run_in_executor(None, partial)
+        else:
+            # 不支持多轮对话的
+            # 调用阿里云百炼 API
+            partial = functools.partial(
+                Application.call,
+                app_id=self.app_id,
+                promtp=prompt,
+                api_key=self.api_key,
+                biz_params=payload_vars or None,
+            )
+            response = await asyncio.get_event_loop().run_in_executor(None, partial)
+
+        logger.debug(f"dashscope resp: {response}")
+
+        if response.status_code != 200:
+            logger.error(
+                f"阿里云百炼请求失败: request_id={response.request_id}, code={response.status_code}, message={response.message}, 请参考文档：https://help.aliyun.com/zh/model-studio/developer-reference/error-code"
+            )
+            return LLMResponse(
+                role="err",
+                completion_text=f"阿里云百炼请求失败: message={response.message} code={response.status_code}",
+            )
+
+        output_text = response.output.get("text", "")
+        return LLMResponse(role="assistant", completion_text=output_text)
+
+    async def forget(self, session_id):
+        return True
+
+    async def get_current_key(self):
+        return self.api_key
+
+    async def set_key(self, key):
+        raise Exception("阿里云百炼 适配器不支持设置 API Key。")
+
+    async def get_models(self):
+        return [self.get_model()]
+
+    async def get_human_readable_context(self, session_id, page, page_size):
+        raise Exception("暂不支持获得 阿里云百炼 的历史消息记录。")
+
+    async def terminate(self):
+        pass
--- a/astrbot/core/provider/sources/dify_source.py
+++ b/astrbot/core/provider/sources/dify_source.py
@@ -31,15 +31,22 @@ class ProviderDify(Provider):
            raise Exception("Dify API 类型不能为空。")
        self.model_name = "dify"
        self.workflow_output_key = provider_config.get("dify_workflow_output_key", "astrbot_wf_output")
-        
+        self.dify_query_input_key = provider_config.get("dify_query_input_key", "astrbot_text_query")
+        self.variables: dict = provider_config.get("variables", {})
+        if not self.dify_query_input_key:
+            self.dify_query_input_key = "astrbot_text_query"
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
        self.conversation_ids = {}
+        '''记录当前 session id 的对话 ID'''


    async def text_chat(
        self,
        prompt: str,
        session_id: str = None,
-        image_urls: List[str] = None,
+        image_urls: List[str] = [],
        func_tool: FuncCall = None,
        contexts: List = None,
        system_prompt: str = None,
@@ -64,62 +71,69 @@ class ProviderDify(Provider):
            else:
                # TODO: 处理更多情况
                logger.warning(f"未知的图片链接：{image_url}，图片将忽略。")
-            
-        logger.debug(files_payload)
        
        # 获得会话变量
+        payload_vars = self.variables.copy()
+        # 动态变量
        session_vars = sp.get("session_variables", {})
        session_var = session_vars.get(session_id, {})
+        payload_vars.update(session_var)
+        
+        try:
+            match self.api_type:
+                case "chat" | "agent":
+                    async for chunk in self.api_client.chat_messages(
+                        inputs={
+                            **payload_vars,
+                        },
+                        query=prompt,
+                        user=session_id,
+                        conversation_id=conversation_id,
+                        files=files_payload,
+                        timeout=self.timeout
+                    ):
+                        logger.debug(f"dify resp chunk: {chunk}")
+                        if chunk['event'] == "message" or \
+                            chunk['event'] == "agent_message":
+                            result += chunk['answer']
+                            if not conversation_id:
+                                self.conversation_ids[session_id] = chunk['conversation_id']
+                                conversation_id = chunk['conversation_id']
+                
+                case "workflow":
+                    async for chunk in self.api_client.workflow_run(
+                        inputs={
+                            self.dify_query_input_key: prompt,
+                            "astrbot_session_id": session_id,
+                            **payload_vars,
+                        },
+                        user=session_id,
+                        files=files_payload,
+                        timeout=self.timeout
+                    ):
+                        match chunk['event']:
+                            case "workflow_started":
+                                logger.info(f"Dify 工作流(ID: {chunk['workflow_run_id']})开始运行。")
+                            case "node_finished":
+                                logger.debug(f"Dify 工作流节点(ID: {chunk['data']['node_id']} Title: {chunk['data'].get('title', '')})运行结束。")
+                            case "workflow_finished":
+                                logger.info(f"Dify 工作流(ID: {chunk['workflow_run_id']})运行结束。")
+                                if chunk['data']['error']:
+                                    logger.error(f"Dify 工作流出现错误：{chunk['data']['error']}")
+                                    raise Exception(f"Dify 工作流出现错误：{chunk['data']['error']}")
+                                if self.workflow_output_key not in chunk['data']['outputs']:
+                                    raise Exception(f"Dify 工作流的输出不包含指定的键名：{self.workflow_output_key}")
+                                result = chunk['data']['outputs'][self.workflow_output_key]
+                case _:
+                    raise Exception(f"未知的 Dify API 类型：{self.api_type}")
+        except Exception as e:
+            logger.error(f"Dify 请求失败：{str(e)}")
+            return LLMResponse(role="err", completion_text=f"Dify 请求失败：{str(e)}")
        
-        match self.api_type:
-            case "chat" | "agent":
-                async for chunk in self.api_client.chat_messages(
-                    inputs={
-                        **session_var
-                    },
-                    query=prompt,
-                    user=session_id,
-                    conversation_id=conversation_id,
-                    files=files_payload
-                ):
-                    logger.debug(f"dify resp chunk: {chunk}")
-                    if chunk['event'] == "message" or \
-                        chunk['event'] == "agent_message":
-                        result += chunk['answer']
-                        if not conversation_id:
-                            self.conversation_ids[session_id] = chunk['conversation_id']
-                            conversation_id = chunk['conversation_id']
-            
-            case "workflow":
-                async for chunk in self.api_client.workflow_run(
-                    inputs={
-                        "astrbot_text_query": prompt,
-                        "astrbot_session_id": session_id,
-                        **session_var
-                    },
-                    user=session_id,
-                    files=files_payload
-                ):
-                    match chunk['event']:
-                        case "workflow_started":
-                            logger.info(f"Dify 工作流(ID: {chunk['workflow_run_id']})开始运行。")
-                        case "node_finished":
-                            logger.debug(f"Dify 工作流节点(ID: {chunk['data']['node_id']} Title: {chunk['data'].get('title', '')})运行结束。")
-                        case "workflow_finished":
-                            logger.info(f"Dify 工作流(ID: {chunk['workflow_run_id']})运行结束。")
-                            if chunk['data']['error']:
-                                logger.error(f"Dify 工作流出现错误：{chunk['data']['error']}")
-                                raise Exception(f"Dify 工作流出现错误：{chunk['data']['error']}")
-                            if self.workflow_output_key not in chunk['data']['outputs']:
-                                raise Exception(f"Dify 工作流的输出不包含指定的键名：{self.workflow_output_key}")
-                            result = chunk['data']['outputs'][self.workflow_output_key]
-            case _:
-                raise Exception(f"未知的 Dify API 类型：{self.api_type}")
-
        return LLMResponse(role="assistant", completion_text=result)

    async def forget(self, session_id):
-        self.conversation_ids.pop(session_id, None)
+        self.conversation_ids[session_id] = ""
        return True

    async def get_current_key(self):
--- a/astrbot/core/provider/sources/fishaudio_tts_api_source.py
+++ b/astrbot/core/provider/sources/fishaudio_tts_api_source.py
@@ -0,0 +1,105 @@
+import uuid
+import ormsgpack
+from pydantic import BaseModel, conint
+from httpx import AsyncClient
+from typing import Annotated, Literal
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+
+
+class ServeReferenceAudio(BaseModel):
+    audio: bytes
+    text: str
+
+
+class ServeTTSRequest(BaseModel):
+    text: str
+    chunk_length: Annotated[int, conint(ge=100, le=300, strict=True)] = 200
+    # 音频格式
+    format: Literal["wav", "pcm", "mp3"] = "mp3"
+    mp3_bitrate: Literal[64, 128, 192] = 128
+    # 参考音频
+    references: list[ServeReferenceAudio] = []
+    # 参考模型 ID
+    # 例如 https://fish.audio/m/7f92f8afb8ec43bf81429cc1c9199cb1/
+    # 其中reference_id为 7f92f8afb8ec43bf81429cc1c9199cb1
+    reference_id: str | None = None
+    # 对中英文文本进行标准化，这可以提高数字的稳定性
+    normalize: bool = True
+    # 平衡模式将延迟减少到300毫秒，但可能会降低稳定性
+    latency: Literal["normal", "balanced"] = "normal"
+
+
+@register_provider_adapter(
+    "fishaudio_tts_api", "FishAudio TTS API", provider_type=ProviderType.TEXT_TO_SPEECH
+)
+class ProviderFishAudioTTSAPI(TTSProvider):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key: str = provider_config.get("api_key", "")
+        self.character: str = provider_config.get("fishaudio-tts-character", "可莉")
+        self.api_base: str = provider_config.get(
+            "api_base", "https://api.fish-audio.cn/v1"
+        )
+        self.headers = {
+            "Authorization": f"Bearer {self.chosen_api_key}",
+        }
+        self.set_model(provider_config.get("model", None))
+
+    async def _get_reference_id_by_character(self, character: str) -> str:
+        """
+        获取角色的reference_id
+
+        Args:
+            character: 角色名称
+
+        Returns:
+            reference_id: 角色的reference_id
+
+        exception:
+            APIException: 获取语音角色列表为空
+        """
+        sort_options = ["score", "task_count", "created_at"]
+        async with AsyncClient(base_url=self.api_base.replace("/v1", "")) as client:
+            for sort_by in sort_options:
+                params = {"title": character, "sort_by": sort_by}
+                response = await client.get(
+                    "/model", params=params, headers=self.headers
+                )
+                resp_data = response.json()
+                if resp_data["total"] == 0:
+                    continue
+                for item in resp_data["items"]:
+                    if character in item["title"]:
+                        return item["_id"]
+            return None
+
+    async def _generate_request(self, text: str) -> dict:
+        return ServeTTSRequest(
+            text=text,
+            format="wav",
+            reference_id=await self._get_reference_id_by_character(self.character),
+        )
+
+    async def get_audio(self, text: str) -> str:
+        path = f"data/temp/fishaudio_tts_api_{uuid.uuid4()}.wav"
+        self.headers["content-type"] = "application/msgpack"
+        request = await self._generate_request(text)
+        async with AsyncClient(base_url=self.api_base).stream(
+            "POST",
+            "/tts",
+            headers=self.headers,
+            content=ormsgpack.packb(request, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
+        ) as response:
+            if response.headers["content-type"] == "audio/wav":
+                with open(path, "wb") as f:
+                    async for chunk in response.aiter_bytes():
+                        f.write(chunk)
+                return path
+            text = await response.aread()
+            raise Exception(f"Fish Audio API请求失败: {text}")
--- a/astrbot/core/provider/sources/gemini_source.py
+++ b/astrbot/core/provider/sources/gemini_source.py
@@ -1,7 +1,6 @@
-import traceback
 import base64
-import json
 import aiohttp
+import random
 from astrbot.core.utils.io import download_image_by_url
 from astrbot.core.db import BaseDatabase
 from astrbot.api.provider import Provider, Personality
@@ -12,17 +11,18 @@ from ..register import register_provider_adapter
 from astrbot.core.provider.entites import LLMResponse

 class SimpleGoogleGenAIClient():
-    def __init__(self, api_key: str, api_base: str):
+    def __init__(self, api_key: str, api_base: str, timeout: int=120) -> None:
        self.api_key = api_key
        if api_base.endswith("/"):
            self.api_base = api_base[:-1]
        else:
            self.api_base = api_base
        self.client = aiohttp.ClientSession(trust_env=True)
+        self.timeout = timeout
        
    async def models_list(self) -> List[str]:
        request_url = f"{self.api_base}/v1beta/models?key={self.api_key}"
-        async with self.client.get(request_url, timeout=10) as resp:
+        async with self.client.get(request_url, timeout=self.timeout) as resp:
            response = await resp.json()
            
            models = []
@@ -48,9 +48,19 @@ class SimpleGoogleGenAIClient():
        payload["contents"] = contents
        logger.debug(f"payload: {payload}")
        request_url = f"{self.api_base}/v1beta/models/{model}:generateContent?key={self.api_key}"
-        async with self.client.post(request_url, json=payload, timeout=10) as resp:
-            response = await resp.json()
-            return response
+        async with self.client.post(request_url, json=payload, timeout=self.timeout) as resp:
+            if "application/json" in resp.headers.get("Content-Type"):
+                try:
+                    response = await resp.json()
+                except Exception as e:
+                    text = await resp.text()
+                    logger.error(f"Gemini 返回了非 json 数据: {text}")
+                    raise e
+                return response
+            else:
+                text = await resp.text()
+                logger.error(f"Gemini 返回了非 json 数据: {text}")
+                raise Exception("Gemini 返回了非 json 数据： ")


@register_provider_adapter("googlegenai_chat_completion", "Google Gemini Chat Completion 提供商适配器")
@@ -67,66 +77,19 @@ class ProviderGoogleGenAI(Provider):
        self.chosen_api_key = None
        self.api_keys: List = provider_config.get("key", [])
        self.chosen_api_key = self.api_keys[0] if len(self.api_keys) > 0 else None
-        
+        self.timeout = provider_config.get("timeout", 180)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
        self.client = SimpleGoogleGenAIClient(
            api_key=self.chosen_api_key,
-            api_base=provider_config.get("api_base", None)
+            api_base=provider_config.get("api_base", None),
+            timeout=self.timeout
        )
        self.set_model(provider_config['model_config']['model'])
-    
-    async def get_human_readable_context(self, session_id, page, page_size):
-        if session_id not in self.session_memory:
-            raise Exception("会话 ID 不存在")
-        contexts = []
-        temp_contexts = []
-        for record in self.session_memory[session_id]:
-            if record['role'] == "user":
-                temp_contexts.append(f"User: {record['content']}")
-            elif record['role'] == "assistant":
-                temp_contexts.append(f"Assistant: {record['content']}")
-                contexts.insert(0, temp_contexts)
-                temp_contexts = []
-
-        # 展平 contexts 列表
-        contexts = [item for sublist in contexts for item in sublist]
-
-        # 计算分页
-        paged_contexts = contexts[(page-1)*page_size:page*page_size]
-        total_pages = len(contexts) // page_size
-        if len(contexts) % page_size != 0:
-            total_pages += 1
-        
-        return paged_contexts, total_pages

    async def get_models(self):
        return await self.client.models_list()
    
-    async def pop_record(self, session_id: str, pop_system_prompt: bool = False):
-        '''
-        弹出第一条记录
-        '''
-        if session_id not in self.session_memory:
-            raise Exception("会话 ID 不存在")
-
-        if len(self.session_memory[session_id]) == 0:
-            return None
-
-        for i in range(len(self.session_memory[session_id])):
-            # 检查是否是 system prompt
-            if not pop_system_prompt and self.session_memory[session_id][i]['user']['role'] == "system":
-                # 如果只有一个 system prompt，才不删掉
-                f = False
-                for j in range(i+1, len(self.session_memory[session_id])):
-                    if self.session_memory[session_id][j]['user']['role'] == "system":
-                        f = True
-                        break
-                if not f:
-                    continue
-            record = self.session_memory[session_id].pop(i)
-            break
-
-        return record
-    
    async def _query(self, payloads: dict, tools: FuncCall) -> LLMResponse:
        tool = None
        if tools:
@@ -144,6 +107,9 @@ class ProviderGoogleGenAI(Provider):
        for message in payloads["messages"]:
            if message["role"] == "user":
                if isinstance(message["content"], str):
+                    if not message['content']:
+                        message['content'] = "<empty_content>"
+                    
                    google_genai_conversation.append({
                        "role": "user",
                        "parts": [{"text": message["content"]}]
@@ -153,6 +119,8 @@ class ProviderGoogleGenAI(Provider):
                    parts = []
                    for part in message["content"]:
                        if part["type"] == "text":
+                            if not part["text"]:
+                                part["text"] = "<empty_content>"
                            parts.append({"text": part["text"]})
                        elif part["type"] == "image_url":
                            parts.append({"inline_data": {
@@ -165,12 +133,13 @@ class ProviderGoogleGenAI(Provider):
                    })
                        
            elif message["role"] == "assistant":
+                if not message["content"]:
+                    message["content"] = "<empty_content>"
                google_genai_conversation.append({
                    "role": "model",
                    "parts": [{"text": message["content"]}]
                })
-                
-        
+
        logger.debug(f"google_genai_conversation: {google_genai_conversation}")
        
        result = await self.client.generate_content(
@@ -181,6 +150,9 @@ class ProviderGoogleGenAI(Provider):
        )
        logger.debug(f"result: {result}")
        
+        if "candidates" not in result:
+            raise Exception("Gemini 返回异常结果: " + str(result))
+        
        candidates = result["candidates"][0]['content']['parts']
        llm_response = LLMResponse("assistant")
        for candidate in candidates:
@@ -190,81 +162,83 @@ class ProviderGoogleGenAI(Provider):
                llm_response.role = "tool"
                llm_response.tools_call_args.append(candidate['functionCall']['args'])
                llm_response.tools_call_name.append(candidate['functionCall']['name'])
-            
+        
+        llm_response.completion_text = llm_response.completion_text.strip()
        return llm_response

-
    async def text_chat(
        self,
        prompt: str,
-        session_id: str,
+        session_id: str = None,
        image_urls: List[str]=None,
        func_tool: FuncCall=None,
-        contexts=None,
+        contexts=[],
        system_prompt=None,
        **kwargs
    ) -> LLMResponse: 
        new_record = await self.assemble_context(prompt, image_urls)
        context_query = []
-        if not contexts:
-            context_query = [*self.session_memory[session_id], new_record]
-        else:
-            context_query = [*contexts, new_record]
+        context_query = [*contexts, new_record]
        if system_prompt:
            context_query.insert(0, {"role": "system", "content": system_prompt})
            
        for part in context_query:
            if '_no_save' in part:
                del part['_no_save']
+                
+        model_config = self.provider_config.get("model_config", {})
+        model_config['model'] = self.get_model()

        payloads = {
            "messages": context_query,
-            **self.provider_config.get("model_config", {})
+            **model_config
        }
-
-        try:
-            llm_response = await self._query(payloads, func_tool)
-            await self.save_history(contexts, new_record, session_id, llm_response)
-            return llm_response
-        except Exception as e:
-            if "maximum context length" in str(e):
-                retry_cnt = 10
-                while retry_cnt > 0:
-                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。")
-                    try:
-                        self.pop_record(session_id)
-                        llm_response = await self._query(payloads, func_tool)
-                        break
-                    except Exception as e:
-                        if "maximum context length" in str(e):
-                            retry_cnt -= 1
-                        else:
-                            raise e
-            else:
-                raise e
-    
-    async def save_history(self, contexts: List, new_record: dict, session_id: str, llm_response: LLMResponse):
-        if llm_response.role == "assistant" and session_id:
-            # 文本回复
-            if not contexts:
-                # 添加用户 record
-                self.session_memory[session_id].append(new_record)
-                # 添加 assistant record
-                self.session_memory[session_id].append({
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                })
-            else:
-                contexts_to_save = list(filter(lambda item: '_no_save' not in item, contexts))
-                self.session_memory[session_id] = [*contexts_to_save, new_record, {
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                }]
-            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['type'])
+        llm_response = None
        
-    async def forget(self, session_id: str) -> bool:
-        self.session_memory[session_id] = []
-        return True
+        retry = 10
+        keys = self.api_keys.copy()
+        chosen_key = random.choice(keys)
+        
+        for i in range(retry):
+            try:
+                self.client.api_key = chosen_key 
+                llm_response = await self._query(payloads, func_tool)
+                break
+            except Exception as e:
+                if "maximum context length" in str(e):
+                    retry_cnt = 20
+                    while retry_cnt > 0:
+                        logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
+                        try:
+                            await self.pop_record(context_query)
+                            llm_response = await self._query(payloads, func_tool)
+                            break
+                        except Exception as e:
+                            if "maximum context length" in str(e):
+                                retry_cnt -= 1
+                            else:
+                                raise e
+                    if retry_cnt == 0:
+                        llm_response = LLMResponse("err", "err: 请尝试  /reset 重置会话")
+                elif "Function calling is not enabled" in str(e):
+                    logger.info(f"{self.get_model()} 不支持函数工具调用，已自动去除，不影响使用。")
+                    if 'tools' in payloads:
+                        del payloads['tools']
+                    llm_response = await self._query(payloads, None)
+                elif "429" in str(e) or "API key not valid" in str(e):
+                    keys.remove(chosen_key)
+                    if len(keys) > 0:
+                        chosen_key = random.choice(keys)
+                        logger.info(f"检测到 Key 异常({str(e)})，正在尝试更换 API Key 重试... 当前 Key: {chosen_key[:12]}...")
+                        continue
+                    else:
+                        logger.error(f"A检测到 Key 异常({str(e)})，且已没有可用的 Key。 当前 Key: {chosen_key[:12]}...")
+                        raise Exception("API 资源已耗尽，且没有可用的 Key 重试...")
+                else:
+                    logger.error(f"发生了错误(gemini_source)。Provider 配置如下: {self.provider_config}")
+                    raise e
+
+        return llm_response

    def get_current_key(self) -> str:
        return self.client.api_key
@@ -285,8 +259,14 @@ class ProviderGoogleGenAI(Provider):
                if image_url.startswith("http"):
                    image_path = await download_image_by_url(image_url)
                    image_data = await self.encode_image_bs64(image_path)
+                elif image_url.startswith("file:///"):
+                    image_path = image_url.replace("file:///", "")
+                    image_data = await self.encode_image_bs64(image_path)
                else:
                    image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
            return user_content
        else:
--- a/astrbot/core/provider/sources/llmtuner_source.py
+++ b/astrbot/core/provider/sources/llmtuner_source.py
@@ -57,20 +57,13 @@ class LLMTunerModelLoader(Provider):
        session_id: str = None,
        image_urls: List[str] = None,
        func_tool: FuncCall = None,
-        contexts: List = None,
+        contexts: List = [],
        system_prompt: str = None,
        **kwargs,
    ) -> LLMResponse:
        system_prompt = ""
        new_record = {"role": "user", "content": prompt}
-        if not contexts:
-            query_context = [
-                *self.session_memory[session_id],
-                new_record,
-            ]
-            system_prompt = self.curr_personality["prompt"]
-        else:
-            query_context = [*contexts, new_record]
+        query_context = [*contexts, new_record]

        # 提取出系统提示
        system_idxs = []
@@ -96,33 +89,8 @@ class LLMTunerModelLoader(Provider):
        responses = await self.model.achat(**conf)

        llm_response = LLMResponse("assistant", responses[-1].response_text)
-        
-        await self.save_history(contexts, new_record, session_id, llm_response)
-        
+                
        return llm_response
-   
-    async def save_history(self, contexts: List, new_record: dict, session_id: str, llm_response: LLMResponse):
-        if llm_response.role == "assistant" and session_id:
-            # 文本回复
-            if not contexts:
-                # 添加用户 record
-                self.session_memory[session_id].append(new_record)
-                # 添加 assistant record
-                self.session_memory[session_id].append({
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                })
-            else:
-                contexts_to_save = list(filter(lambda item: '_no_save' not in item, contexts))
-                self.session_memory[session_id] = [*contexts_to_save, new_record, {
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                }]
-            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['type'])
-        
-    async def forget(self, session_id):
-        self.session_memory[session_id] = []
-        return True

    async def get_current_key(self):
        return "none"
@@ -131,28 +99,4 @@ class LLMTunerModelLoader(Provider):
        pass

    async def get_models(self):
-        return [self.get_model()]
-
-    async def get_human_readable_context(self, session_id, page, page_size):
-        if session_id not in self.session_memory:
-            raise Exception("会话 ID 不存在")
-        contexts = []
-        temp_contexts = []
-        for record in self.session_memory[session_id]:
-            if record["role"] == "user":
-                temp_contexts.append(f"User: {record['content']}")
-            elif record["role"] == "assistant":
-                temp_contexts.append(f"Assistant: {record['content']}")
-                contexts.insert(0, temp_contexts)
-                temp_contexts = []
-
-        # 展平 contexts 列表
-        contexts = [item for sublist in contexts for item in sublist]
-
-        # 计算分页
-        paged_contexts = contexts[(page - 1) * page_size : page * page_size]
-        total_pages = len(contexts) // page_size
-        if len(contexts) % page_size != 0:
-            total_pages += 1
-
-        return paged_contexts, total_pages
+        return [self.get_model()]
--- a/astrbot/core/provider/sources/openai_source.py
+++ b/astrbot/core/provider/sources/openai_source.py
@@ -1,9 +1,10 @@
 import base64
 import json
+import os

-from openai import AsyncOpenAI, NOT_GIVEN
+from openai import AsyncOpenAI, AsyncAzureOpenAI
 from openai.types.chat.chat_completion import ChatCompletion
-from openai._exceptions import NotFoundError
+from openai._exceptions import NotFoundError, UnprocessableEntityError
 from astrbot.core.utils.io import download_image_by_url

 from astrbot.core.db import BaseDatabase
@@ -28,75 +29,41 @@ class ProviderOpenAIOfficial(Provider):
        self.chosen_api_key = None
        self.api_keys: List = provider_config.get("key", [])
        self.chosen_api_key = self.api_keys[0] if len(self.api_keys) > 0 else None
-
-        self.client = AsyncOpenAI(
-            api_key=self.chosen_api_key,
-            base_url=provider_config.get("api_base", None),
-            timeout=provider_config.get("timeout", NOT_GIVEN),
-        )
-        self.set_model(provider_config['model_config']['model'])
-    
-    async def get_human_readable_context(self, session_id, page, page_size):
-        if session_id not in self.session_memory:
-            raise Exception("会话 ID 不存在")
-        contexts = []
-        temp_contexts = []
-        for record in self.session_memory[session_id]:
-            if record['role'] == "user":
-                temp_contexts.append(f"User: {record['content']}")
-            elif record['role'] == "assistant":
-                temp_contexts.append(f"Assistant: {record['content']}")
-                contexts.insert(0, temp_contexts)
-                temp_contexts = []
-
-        # 展平 contexts 列表
-        contexts = [item for sublist in contexts for item in sublist]
-
-        # 计算分页
-        paged_contexts = contexts[(page-1)*page_size:page*page_size]
-        total_pages = len(contexts) // page_size
-        if len(contexts) % page_size != 0:
-            total_pages += 1
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
+        # 适配 azure openai #332
+        if "api_version" in provider_config:
+            # 使用 azure api
+            self.client = AsyncAzureOpenAI(
+                api_key=self.chosen_api_key,
+                api_version=provider_config.get("api_version", None),
+                base_url=provider_config.get("api_base", None),
+                timeout=self.timeout
+            )
+        else:
+            # 使用 openai api
+            self.client = AsyncOpenAI(
+                api_key=self.chosen_api_key,
+                base_url=provider_config.get("api_base", None),
+                timeout=self.timeout
+            )
        
-        return paged_contexts, total_pages
+        model_config = provider_config.get("model_config", {})
+        model = model_config.get("model", "unknown")
+        self.set_model(model)

    async def get_models(self):
        try:
            models_str = []
            models = await self.client.models.list()
-            models = models.data
+            models = sorted(models.data, key=lambda x: x.id)
            for model in models:
                models_str.append(model.id)
            return models_str
        except NotFoundError as e:
            raise Exception(f"获取模型列表失败：{e}")
    
-    async def pop_record(self, session_id: str, pop_system_prompt: bool = False):
-        '''
-        弹出第一条记录
-        '''
-        if session_id not in self.session_memory:
-            raise Exception("会话 ID 不存在")
-
-        if len(self.session_memory[session_id]) == 0:
-            return None
-
-        for i in range(len(self.session_memory[session_id])):
-            # 检查是否是 system prompt
-            if not pop_system_prompt and self.session_memory[session_id][i]['user']['role'] == "system":
-                # 如果只有一个 system prompt，才不删掉
-                f = False
-                for j in range(i+1, len(self.session_memory[session_id])):
-                    if self.session_memory[session_id][j]['user']['role'] == "system":
-                        f = True
-                        break
-                if not f:
-                    continue
-            record = self.session_memory[session_id].pop(i)
-            break
-
-        return record
-    
    async def _query(self, payloads: dict, tools: FuncCall) -> LLMResponse:
        if tools:
            tool_list = tools.get_func_desc_openai_style()
@@ -107,7 +74,7 @@ class ProviderOpenAIOfficial(Provider):
            **payloads,
            stream=False
        )
-        
+
        assert isinstance(completion, ChatCompletion)
        logger.debug(f"completion: {completion}")

@@ -115,11 +82,14 @@ class ProviderOpenAIOfficial(Provider):
            raise Exception("API 返回的 completion 为空。")
        choice = completion.choices[0]
        
+        llm_response = LLMResponse("assistant")
+                
        if choice.message.content:
            # text completion
            completion_text = str(choice.message.content).strip()
-            return LLMResponse("assistant", completion_text)
-        elif choice.message.tool_calls:
+            llm_response.completion_text = completion_text
+        
+        if choice.message.tool_calls:
            # tools call (function calling)
            args_ls = []
            func_name_ls = []
@@ -129,49 +99,66 @@ class ProviderOpenAIOfficial(Provider):
                        args = json.loads(tool_call.function.arguments)
                        args_ls.append(args)
                        func_name_ls.append(tool_call.function.name)
-            return LLMResponse(role="tool", tools_call_args=args_ls, tools_call_name=func_name_ls)
-        else:
-            raise Exception("Internal Error")
+            llm_response.role = "tool"
+            llm_response.tools_call_args = args_ls
+            llm_response.tools_call_name = func_name_ls
+            
+        if choice.finish_reason == 'content_filter':
+            raise Exception("API 返回的 completion 由于内容安全过滤被拒绝(非 AstrBot)。")
+
+        if not llm_response.completion_text and not llm_response.tools_call_args:
+            logger.error(f"API 返回的 completion 无法解析：{completion}。")
+            raise Exception(f"API 返回的 completion 无法解析：{completion}。")
+        
+        llm_response.raw_completion = completion
+        
+        return llm_response

    async def text_chat(
        self,
        prompt: str,
-        session_id: str,
-        image_urls: List[str]=None,
+        session_id: str=None,
+        image_urls: List[str]=[],
        func_tool: FuncCall=None,
-        contexts=None,
+        contexts=[],
        system_prompt=None,
        **kwargs
    ) -> LLMResponse: 
        new_record = await self.assemble_context(prompt, image_urls)
-        context_query = []
-        if not contexts:
-            context_query = [*self.session_memory[session_id], new_record]
-        else:
-            context_query = [*contexts, new_record]
+        context_query = [*contexts, new_record]
        if system_prompt:
            context_query.insert(0, {"role": "system", "content": system_prompt})

        for part in context_query:
            if '_no_save' in part:
                del part['_no_save']
+                
+                
+        model_config = self.provider_config.get("model_config", {})
+        model_config['model'] = self.get_model()

        payloads = {
            "messages": context_query,
-            **self.provider_config.get("model_config", {})
+            **model_config
        }
-
+        llm_response = None
        try:
            llm_response = await self._query(payloads, func_tool)
-            await self.save_history(contexts, new_record, session_id, llm_response)
-            return llm_response
+        except UnprocessableEntityError as e:
+            logger.warning(f"不可处理的实体错误：{e}，尝试删除图片。")
+            # 尝试删除所有 image
+            new_contexts = await self._remove_image_from_context(context_query)
+            payloads['messages'] = new_contexts
+            context_query = new_contexts
+            llm_response = await self._query(payloads, func_tool)
        except Exception as e:
            if "maximum context length" in str(e):
-                retry_cnt = 10
+                # 重试 10 次
+                retry_cnt = 20
                while retry_cnt > 0:
-                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    logger.warning(f"上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
                    try:
-                        self.pop_record(session_id)
+                        await self.pop_record(context_query)
                        llm_response = await self._query(payloads, func_tool)
                        break
                    except Exception as e:
@@ -179,33 +166,69 @@ class ProviderOpenAIOfficial(Provider):
                            retry_cnt -= 1
                        else:
                            raise e
+                if retry_cnt == 0:
+                    llm_response = LLMResponse("err", "err: 请尝试 /reset 清除会话记录。")
+            elif "The model is not a VLM" in str(e): # siliconcloud
+                # 尝试删除所有 image
+                new_contexts = await self._remove_image_from_context(context_query)
+                payloads['messages'] = new_contexts
+                llm_response = await self._query(payloads, func_tool)
+
+            # openai, ollama, gemini openai, siliconcloud 的错误提示与 code 不统一，只能通过字符串匹配
+            elif 'does not support Function Calling' in str(e) \
+                or 'does not support tools' in str(e)  \
+                or 'Function call is not supported' in str(e) \
+                or 'Function calling is not enabled' in str(e) \
+                or 'Tool calling is not supported' in str(e) \
+                or 'No endpoints found that support tool use' in str(e) \
+                or 'model does not support function calling' in str(e) \
+                or ('tool' in str(e) and 'support' in str(e).lower()) \
+                or ('function' in str(e) and 'support' in str(e).lower()):
+                    logger.info(f"{self.get_model()} 不支持函数工具调用，已自动去除，不影响使用。")
+                    if 'tools' in payloads:
+                        del payloads['tools']
+                    llm_response = await self._query(payloads, None)
            else:
+                logger.error(f"发生了错误。Provider 配置如下: {self.provider_config}")
+                
+                if 'tool' in str(e).lower() and 'support' in str(e).lower():
+                    logger.error("疑似该模型不支持函数调用工具调用。请输入 /tool off_all")
+                
+                if 'Connection error.' in str(e):
+                    proxy = os.environ.get("http_proxy", None)
+                    if proxy:
+                        logger.error(f"可能为代理原因，请检查代理是否正常。当前代理: {proxy}")
+                
                raise e
-
-    
-    async def save_history(self, contexts: List, new_record: dict, session_id: str, llm_response: LLMResponse):
-        if llm_response.role == "assistant" and session_id:
-            # 文本回复
-            if not contexts:
-                # 添加用户 record
-                self.session_memory[session_id].append(new_record)
-                # 添加 assistant record
-                self.session_memory[session_id].append({
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                })
-            else:
-                contexts_to_save = list(filter(lambda item: '_no_save' not in item, contexts))
-                self.session_memory[session_id] = [*contexts_to_save, new_record, {
-                    "role": "assistant",
-                    "content": llm_response.completion_text
-                }]
-            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['type'])
        
-    async def forget(self, session_id: str) -> bool:
-        self.session_memory[session_id] = []
-        return True
-
+        return llm_response
+    
+    async def _remove_image_from_context(self, contexts: List):
+        '''
+        从上下文中删除所有带有 image 的记录
+        '''
+        new_contexts = []
+        
+        flag = False
+        for context in contexts:
+            if flag:
+                flag = False # 删除 image 后，下一条（LLM 响应）也要删除
+                continue
+            if isinstance(context['content'], list):
+                flag = True
+                # continue
+                new_content = []
+                for item in context['content']:
+                    if isinstance(item, dict) and 'image_url' in item:
+                        continue
+                    new_content.append(item)
+                if not new_content:
+                    # 用户只发了图片
+                    new_content = [{"type": "text", "text": "[图片]"}]
+                context['content'] = new_content
+            new_contexts.append(context)
+        return new_contexts
+    
    def get_current_key(self) -> str:
        return self.client.api_key

@@ -225,10 +248,14 @@ class ProviderOpenAIOfficial(Provider):
                if image_url.startswith("http"):
                    image_path = await download_image_by_url(image_url)
                    image_data = await self.encode_image_bs64(image_path)
+                elif image_url.startswith("file:///"):
+                    image_path = image_url.replace("file:///", "")
+                    image_data = await self.encode_image_bs64(image_path)
                else:
-                    if image_url.startswith("file:///"):
-                        image_url = image_url.replace("file:///", "")
                    image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
            return user_content
        else:
--- a/astrbot/core/provider/sources/openai_tts_api_source.py
+++ b/astrbot/core/provider/sources/openai_tts_api_source.py
@@ -15,7 +15,7 @@ class ProviderOpenAITTSAPI(TTSProvider):
    ) -> None:
        super().__init__(provider_config, provider_settings)
        self.chosen_api_key = provider_config.get("api_key", "")
-        self.voice = provider_config.get("voice", "alloy")
+        self.voice = provider_config.get("openai-tts-voice", "alloy")

        self.client = AsyncOpenAI(
            api_key=self.chosen_api_key,
--- a/astrbot/core/provider/sources/zhipu_source.py
+++ b/astrbot/core/provider/sources/zhipu_source.py
@@ -22,24 +22,21 @@ class ProviderZhipu(ProviderOpenAIOfficial):
    async def text_chat(
        self,
        prompt: str,
-        session_id: str,
+        session_id: str = None,
        image_urls: List[str]=None,
        func_tool: FuncCall=None,
-        contexts=None,
+        contexts=[],
        system_prompt=None,
        **kwargs
    ) -> LLMResponse: 
        new_record = await self.assemble_context(prompt, image_urls)
        context_query = []
        
-        if not contexts:
-            context_query = [*self.session_memory[session_id], new_record]
-        else:
-            context_query = [*contexts, new_record]
+        context_query = [*contexts, new_record]
        
        model_cfgs: dict = self.provider_config.get("model_config", {})
+        model = self.get_model()
        # glm-4v-flash 只支持一张图片
-        model: str = model_cfgs.get("model", "")
        if model.lower() == 'glm-4v-flash' and image_urls and len(context_query) > 1:
            logger.debug("glm-4v-flash 只支持一张图片，将只保留最后一张图片")
            logger.debug(context_query)
@@ -62,7 +59,6 @@ class ProviderZhipu(ProviderOpenAIOfficial):
        }
        try:
            llm_response = await self._query(payloads, func_tool)
-            await self.save_history(contexts, new_record, session_id, llm_response)
            return llm_response
        except Exception as e:
            if "maximum context length" in str(e):
--- a/astrbot/core/star/config.py
+++ b/astrbot/core/star/config.py
@@ -1,3 +1,7 @@
+'''
+此功能已过时，参考 https://astrbot.app/dev/plugin.html#%E6%B3%A8%E5%86%8C%E6%8F%92%E4%BB%B6%E9%85%8D%E7%BD%AE-beta
+'''
+
 from typing import Union
 import os
 import json
--- a/astrbot/core/star/context.py
+++ b/astrbot/core/star/context.py
@@ -1,8 +1,8 @@
 from asyncio import Queue
-from typing import List, TypedDict, Union
+from typing import List, Union

 from astrbot.core import sp
-from astrbot.core.provider.provider import Provider
+from astrbot.core.provider.provider import Provider, TTSProvider, STTProvider
 from astrbot.core.db import BaseDatabase
 from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot.core.provider.func_tool_manager import FuncCall
@@ -10,12 +10,13 @@ from astrbot.core.platform.astr_message_event import MessageSesion
 from astrbot.core.message.message_event_result import MessageChain
 from astrbot.core.provider.manager import ProviderManager
 from astrbot.core.platform.manager import PlatformManager
-from .star import star_registry, StarMetadata
+from .star import star_registry, StarMetadata, star_map
 from .star_handler import star_handlers_registry, StarHandlerMetadata, EventType
 from .filter.command import CommandFilter
 from .filter.regex import RegexFilter
 from typing import Awaitable
 from astrbot.core.rag.knowledge_db_mgr import KnowledgeDBManager
+from astrbot.core.conversation_mgr import ConversationManager

 class Context:
    '''
@@ -44,6 +45,7 @@ class Context:
        db: BaseDatabase, 
        provider_manager: ProviderManager = None, 
        platform_manager: PlatformManager = None,
+        conversation_manager: ConversationManager = None,
        knowledge_db_manager: KnowledgeDBManager = None
    ):
        self._event_queue = event_queue
@@ -52,48 +54,22 @@ class Context:
        self.provider_manager = provider_manager
        self.platform_manager = platform_manager
        self.knowledge_db_manager = knowledge_db_manager
+        self.conversation_manager = conversation_manager

    def get_registered_star(self, star_name: str) -> StarMetadata:
+        '''根据插件名获取插件的 Metadata'''
        for star in star_registry:
            if star.name == star_name:
                return star

    def get_all_stars(self) -> List[StarMetadata]:
+        '''获取当前载入的所有插件 Metadata 的列表'''
        return star_registry
    
    def get_llm_tool_manager(self) -> FuncCall:
-        '''
-        获取 LLM Tool Manager
-        '''
+        '''获取 LLM Tool Manager，其用于管理注册的所有的 Function-calling tools'''
        return self.provider_manager.llm_tools
        
-    def register_llm_tool(self, name: str, func_args: list, desc: str, func_obj: Awaitable) -> None:
-        '''
-        为函数调用（function-calling / tools-use）添加工具。
-        
-        @param name: 函数名
-        @param func_args: 函数参数列表，格式为 [{"type": "string", "name": "arg_name", "description": "arg_description"}, ...]
-        @param desc: 函数描述
-        @param func_obj: 异步处理函数。
-        
-        异步处理函数会接收到额外的的关键词参数：event: AstrMessageEvent, context: Context。
-        '''
-        md = StarHandlerMetadata(
-            event_type=EventType.OnLLMRequestEvent,
-            handler_full_name=func_obj.__module__ + "_" + func_obj.__name__,
-            handler_name=func_obj.__name__,
-            handler_module_path=func_obj.__module__,
-            handler=func_obj,
-            event_filters=[],
-            desc=desc
-        )
-        star_handlers_registry.append(md)
-        self.provider_manager.llm_tools.add_func(name, func_args, desc, func_obj, func_obj)
-    
-    def unregister_llm_tool(self, name: str) -> None:
-        '''删除一个函数调用工具。如果再要启用，需要重新注册。'''
-        self.provider_manager.llm_tools.remove_func(name)
-        
    def activate_llm_tool(self, name: str) -> bool:
        '''激活一个已经注册的函数调用工具。注册的工具默认是激活状态。
        
@@ -102,6 +78,11 @@ class Context:
        '''
        func_tool = self.provider_manager.llm_tools.get_func(name)
        if func_tool is not None:
+            
+            if func_tool.handler_module_path in star_map:
+                if not star_map[func_tool.handler_module_path].activated:
+                    raise ValueError(f"此函数调用工具所属的插件 {star_map[func_tool.handler_module_path].name} 已被禁用，请先在管理面板启用再激活此工具。")
+            
            func_tool.active = True
            
            inactivated_llm_tools: list = sp.get("inactivated_llm_tools", [])
@@ -129,6 +110,121 @@ class Context:
            return True
        return False
    
+    def register_provider(self, provider: Provider):
+        '''
+        注册一个 LLM Provider(Chat_Completion 类型)。
+        '''
+        self.provider_manager.provider_insts.append(provider)
+        
+    def get_provider_by_id(self, provider_id: str) -> Provider:
+        '''通过 ID 获取用于文本生成任务的 LLM Provider(Chat_Completion 类型)。'''
+        for provider in self.provider_manager.provider_insts:
+            if provider.meta().id == provider_id:
+                return provider
+        return None
+    
+    def get_all_providers(self) -> List[Provider]:
+        '''获取所有用于文本生成任务的 LLM Provider(Chat_Completion 类型)。'''
+        return self.provider_manager.provider_insts
+    
+    def get_all_tts_providers(self) -> List[TTSProvider]:
+        '''获取所有用于 TTS 任务的 Provider。'''
+        return self.provider_manager.tts_provider_insts
+    
+    def get_all_stt_providers(self) -> List[STTProvider]:
+        '''获取所有用于 STT 任务的 Provider。'''
+        return self.provider_manager.stt_provider_insts
+    
+    def get_using_provider(self) -> Provider:
+        '''
+        获取当前使用的用于文本生成任务的 LLM Provider(Chat_Completion 类型)。
+        
+        通过 /provider 指令切换。
+        '''
+        return self.provider_manager.curr_provider_inst
+    
+    def get_using_tts_provider(self) -> TTSProvider:
+        '''
+        获取当前使用的用于 TTS 任务的 Provider。
+        '''
+        return self.provider_manager.curr_tts_provider_inst
+    
+    def get_using_stt_provider(self) -> STTProvider:
+        '''
+        获取当前使用的用于 STT 任务的 Provider。
+        '''
+        return self.provider_manager.curr_stt_provider_inst
+    
+    def get_config(self) -> AstrBotConfig:
+        '''获取 AstrBot 的配置。'''
+        return self._config
+    
+    def get_db(self) -> BaseDatabase:
+        '''获取 AstrBot 数据库。'''
+        return self._db
+    
+    def get_event_queue(self) -> Queue:
+        '''
+        获取事件队列。
+        '''
+        return self._event_queue
+    
+    async def send_message(self, session: Union[str, MessageSesion], message_chain: MessageChain) -> bool:
+        '''
+        根据 session(unified_msg_origin) 发送消息。
+        
+        @param session: 消息会话。通过 event.session 或者 event.unified_msg_origin 获取。
+        @param message_chain: 消息链。
+        
+        @return: 是否找到匹配的平台。
+        
+        当 session 为字符串时，会尝试解析为 MessageSesion 对象，如果解析失败，会抛出 ValueError 异常。
+        '''
+        
+        if isinstance(session, str):
+            try:
+                session = MessageSesion.from_str(session)
+            except BaseException as e:
+                raise ValueError("不合法的 session 字符串: " + str(e))
+
+        for platform in self.platform_manager.platform_insts:
+            if platform.meta().name == session.platform_name:
+                await platform.send_by_session(session, message_chain)
+                return True
+        return False
+
+    '''
+    以下的方法已经不推荐使用。请从 AstrBot 文档查看更好的注册方式。
+    '''
+    
+    def register_llm_tool(self, name: str, func_args: list, desc: str, func_obj: Awaitable) -> None:
+        '''
+        为函数调用（function-calling / tools-use）添加工具。
+        
+        @param name: 函数名
+        @param func_args: 函数参数列表，格式为 [{"type": "string", "name": "arg_name", "description": "arg_description"}, ...]
+        @param desc: 函数描述
+        @param func_obj: 异步处理函数。
+        
+        异步处理函数会接收到额外的的关键词参数：event: AstrMessageEvent, context: Context。
+        '''
+        md = StarHandlerMetadata(
+            event_type=EventType.OnLLMRequestEvent,
+            handler_full_name=func_obj.__module__ + "_" + func_obj.__name__,
+            handler_name=func_obj.__name__,
+            handler_module_path=func_obj.__module__,
+            handler=func_obj,
+            event_filters=[],
+            desc=desc
+        )
+        star_handlers_registry.append(md)
+        self.provider_manager.llm_tools.add_func(name, func_args, desc, func_obj, func_obj)
+    
+    def unregister_llm_tool(self, name: str) -> None:
+        '''删除一个函数调用工具。如果再要启用，需要重新注册。'''
+        self.provider_manager.llm_tools.remove_func(name)
+        
+
    def register_commands(self, star_name: str, command_name: str, desc: str, priority: int, awaitable: Awaitable, use_regex=False, ignore_prefix=False):
        '''
        注册一个命令。
@@ -162,77 +258,6 @@ class Context:
            ))
        star_handlers_registry.append(md)
    
-    def register_provider(self, provider: Provider):
-        '''
-        注册一个 LLM Provider(Chat_Completion 类型)。
-        '''
-        self.provider_manager.provider_insts.append(provider)
-        
-    def get_provider_by_id(self, provider_id: str) -> Provider:
-        '''
-        通过 ID 获取 LLM Provider(Chat_Completion 类型)。
-        '''
-        for provider in self.provider_manager.provider_insts:
-            if provider.meta().id == provider_id:
-                return provider
-        return None
-    
-    def get_all_providers(self) -> List[Provider]:
-        '''
-        获取所有 LLM Provider(Chat_Completion 类型)。
-        '''
-        return self.provider_manager.provider_insts
-    
-    def get_using_provider(self) -> Provider:
-        '''
-        获取当前使用的 LLM Provider(Chat_Completion 类型)。
-        
-        通过 /provider 指令切换。
-        '''
-        return self.provider_manager.curr_provider_inst
-    
-    def get_config(self) -> AstrBotConfig:
-        '''
-        获取 AstrBot 配置信息。
-        '''
-        return self._config
-    
-    def get_db(self) -> BaseDatabase:
-        '''
-        获取 AstrBot 数据库。
-        '''
-        return self._db
-    
-    def get_event_queue(self) -> Queue:
-        '''
-        获取事件队列。
-        '''
-        return self._event_queue
-    
-    async def send_message(self, session: Union[str, MessageSesion], message_chain: MessageChain) -> bool:
-        '''
-        根据 session(unified_msg_origin) 发送消息。
-        
-        @param session: 消息会话。通过 event.session 或者 event.unified_msg_origin 获取。
-        @param message_chain: 消息链。
-        
-        @return: 是否找到匹配的平台。
-        
-        当 session 为字符串时，会尝试解析为 MessageSesion 对象，如果解析失败，会抛出 ValueError 异常。
-        '''
-        
-        if isinstance(session, str):
-            try:
-                session = MessageSesion.from_str(session)
-            except BaseException as e:
-                raise ValueError("不合法的 session 字符串: " + str(e))
-
-        for platform in self.platform_manager.platform_insts:
-            if platform.meta().name == session.platform_name:
-                await platform.send_by_session(session, message_chain)
-                return True
-        return False
-
    def register_task(self, task: Awaitable, desc: str):
        '''
        注册一个异步任务。
--- a/astrbot/core/star/filter/command.py
+++ b/astrbot/core/star/filter/command.py
@@ -1,19 +1,23 @@

 import re
 import inspect
+from typing import List, Any, Type, Dict
 from . import HandlerFilter
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.config import AstrBotConfig
-from astrbot.core.utils.param_validation_mixin import ParameterValidationMixin
+from .custom_filter import CustomFilter
 from ..star_handler import StarHandlerMetadata

 # 标准指令受到 wake_prefix 的制约。
-class CommandFilter(HandlerFilter, ParameterValidationMixin):
+class CommandFilter(HandlerFilter):
    '''标准指令过滤器'''
-    def __init__(self, command_name: str, handler_md: StarHandlerMetadata = None):
+    def __init__(self, command_name: str, alias: set = None, handler_md: StarHandlerMetadata = None, parent_command_names: List[str] = [""]):
        self.command_name = command_name
+        self.alias = alias if alias else set()
+        self.parent_command_names = parent_command_names
        if handler_md:
            self.init_handler_md(handler_md)
+        self.custom_filter_list: List[CustomFilter] = []
            
    def print_types(self):
        result = ""
@@ -22,6 +26,7 @@ class CommandFilter(HandlerFilter, ParameterValidationMixin):
                result += f"{k}({v.__name__}),"
            else:
                result += f"{k}({type(v).__name__})={v},"
+        result = result.rstrip(",")
        return result
                
    def init_handler_md(self, handle_md: StarHandlerMetadata):
@@ -42,26 +47,79 @@ class CommandFilter(HandlerFilter, ParameterValidationMixin):
    def get_handler_md(self) -> StarHandlerMetadata:
        return self.handler_md

+    def add_custom_filter(self, custom_filter: CustomFilter):
+        self.custom_filter_list.append(custom_filter)
+
+    def custom_filter_ok(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        for custom_filter in self.custom_filter_list:
+            if not custom_filter.filter(event, cfg):
+                return False
+        return True
+    
+    def validate_and_convert_params(self, params: List[Any], param_type: Dict[str, Type]) -> Dict[str, Any]:
+        '''将参数列表 params 根据 param_type 转换为参数字典。
+        '''
+        result = {}
+        for i, (param_name, param_type_or_default_val) in enumerate(param_type.items()):
+            if i >= len(params):
+                if isinstance(param_type_or_default_val, Type) or param_type_or_default_val is inspect.Parameter.empty:
+                    # 是类型
+                    raise ValueError(f"必要参数缺失。该指令完整参数: {self.print_types()}")
+                else:
+                    # 是默认值
+                    result[param_name] = param_type_or_default_val
+            else:
+                # 尝试强制转换
+                try:
+                    if param_type_or_default_val is None:
+                        if params[i].isdigit():
+                            result[param_name] = int(params[i])
+                        else:
+                            result[param_name] = params[i]
+                    elif isinstance(param_type_or_default_val, str):
+                        # 如果 param_type_or_default_val 是字符串，直接赋值
+                        result[param_name] = params[i]
+                    elif isinstance(param_type_or_default_val, int):
+                        result[param_name] = int(params[i])
+                    elif isinstance(param_type_or_default_val, float):
+                        result[param_name] = float(params[i])
+                    else:
+                        result[param_name] = param_type_or_default_val(params[i])
+                except ValueError:
+                    raise ValueError(f"参数 {param_name} 类型错误。完整参数: {self.print_types()}")
+        return result
+
    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
-        if not event.is_wake_up():
+        if not event.is_at_or_wake_command:
+            return False
+
+        if not self.custom_filter_ok(event, cfg):
            return False
        
-        message_str = event.get_message_str().strip()
-        # 分割为列表（每个参数之间可能会有多个空格）
-        ls = re.split(r"\s+", message_str)
-        if self.command_name != ls[0]:
+        # 检查是否以指令开头
+        message_str = re.sub(r"\s+", " ", event.get_message_str().strip())
+        candidates = [self.command_name] + list(self.alias)
+        ok = False
+        for candidate in candidates:
+            for parent_command_name in self.parent_command_names:
+                if parent_command_name:
+                    _full = f"{parent_command_name} {candidate}"
+                else:
+                    _full = candidate
+                if message_str.startswith(f"{_full} ") or message_str == _full:
+                    message_str = message_str[len(_full):].strip()
+                    ok = True
+                    break
+        if not ok:
            return False
-        # if len(self.handler_params) == 0 and len(ls) > 1:
-        #     # 一定程度避免 LLM 聊天时误判为指令
-        #     return False
-        # params_str = message_str[len(self.command_name):].strip()
-        ls = ls[1:]
+
+        # 分割为列表
+        ls = message_str.split(" ")
        # 去除空字符串
        ls = [param for param in ls if param]
        params = {}
        try:
            params = self.validate_and_convert_params(ls, self.handler_params)
-            
        except ValueError as e:
            raise e
        
--- a/astrbot/core/star/filter/command_group.py
+++ b/astrbot/core/star/filter/command_group.py
@@ -6,65 +6,97 @@ from . import HandlerFilter
 from .command import CommandFilter
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.config import AstrBotConfig
+from .custom_filter import CustomFilter
 from ..star_handler import StarHandlerMetadata

 # 指令组受到 wake_prefix 的制约。
 class CommandGroupFilter(HandlerFilter):
-    def __init__(self, group_name: str):
+    def __init__(self, group_name: str, alias: set = None, parent_group: CommandGroupFilter = None):
        self.group_name = group_name
+        self.alias = alias if alias else set()
        self.sub_command_filters: List[Union[CommandFilter, CommandGroupFilter]] = []
+        self.custom_filter_list: List[CustomFilter] = []
+        self.parent_group = parent_group
    
    def add_sub_command_filter(self, sub_command_filter: Union[CommandFilter, CommandGroupFilter]):
        self.sub_command_filters.append(sub_command_filter)
-    
+
+    def add_custom_filter(self, custom_filter: CustomFilter):
+        self.custom_filter_list.append(custom_filter)
+
+    def get_complete_command_names(self) -> List[str]:
+        '''遍历父节点获取完整的指令名。
+        
+        新版本 v3.4.29 采用预编译指令，不再从指令组递归遍历子指令，因此这个方法是返回包括别名在内的整个指令名列表。'''
+        parent_cmd_names = self.parent_group.get_complete_command_names() if self.parent_group else []
+        
+        if not parent_cmd_names:
+            # 根节点
+            return [self.group_name] + list(self.alias)
+        
+        result = []
+        candidates = [self.group_name] + list(self.alias)
+        for parent_cmd_name in parent_cmd_names:
+            for candidate in candidates:
+                result.append(parent_cmd_name + " " + candidate)
+        return result
+        
+
    # 以树的形式打印出来
-    def print_cmd_tree(self, sub_command_filters: List[Union[CommandFilter, CommandGroupFilter]], prefix: str = "") -> str:
+    def print_cmd_tree(self,
+        sub_command_filters: List[Union[CommandFilter, CommandGroupFilter]],
+        prefix: str = "",
+        event: AstrMessageEvent = None,
+        cfg: AstrBotConfig = None,
+    ) -> str:
        result = ""
        for sub_filter in sub_command_filters:
            if isinstance(sub_filter, CommandFilter):
-                cmd_th = sub_filter.print_types()
-                result += f"{prefix}├── {sub_filter.command_name}"
-                if cmd_th:
-                    result += f" ({cmd_th})"
-                else:
-                    result += " (无参数指令)"
-                
-                result += "\n"
+                custom_filter_pass = True
+                if event and cfg:
+                    custom_filter_pass = sub_filter.custom_filter_ok(event, cfg)
+                if custom_filter_pass:
+                    cmd_th = sub_filter.print_types()
+                    result += f"{prefix}├── {sub_filter.command_name}"
+                    if cmd_th:
+                        result += f" ({cmd_th})"
+                    else:
+                        result += " (无参数指令)"
+                    
+                    if sub_filter.handler_md and sub_filter.handler_md.desc:
+                        result += f": {sub_filter.handler_md.desc}"
+
+                    result += "\n"
            elif isinstance(sub_filter, CommandGroupFilter):
-                result += f"{prefix}├── {sub_filter.group_name}"
-                result += "\n"
-                result += sub_filter.print_cmd_tree(sub_filter.sub_command_filters, prefix+"│   ")
+                custom_filter_pass = True
+                if event and cfg:
+                    custom_filter_pass = sub_filter.custom_filter_ok(event, cfg)
+                if custom_filter_pass:
+                    result += f"{prefix}├── {sub_filter.group_name}"
+                    result += "\n"
+                    result += sub_filter.print_cmd_tree(sub_filter.sub_command_filters, prefix+"│   ", event=event, cfg=cfg)
+
        return result
-        
-    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> Tuple[bool, StarHandlerMetadata]:
-        if not event.is_wake_up():
-            return False, None
-        
-        message_str = event.get_message_str().strip()
-        ls = re.split(r"\s+", message_str)
-        
-        if ls[0] != self.group_name:
-            return False, None
-        # 改写 message_str
-        ls = ls[1:]
-        event.message_str = " ".join(ls)
-        event.message_str = event.message_str.strip()
-        
-        if event.message_str == "":
-            # 当前还是指令组
-            tree = self.group_name + "\n" + self.print_cmd_tree(self.sub_command_filters)
+
+    def custom_filter_ok(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        for custom_filter in self.custom_filter_list:
+            if not custom_filter.filter(event, cfg):
+                return False
+        return True
+
+    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        if not event.is_at_or_wake_command:
+            return False
+
+        # 判断当前指令组的自定义过滤器
+        if not self.custom_filter_ok(event, cfg):
+            return False
+
+        complete_command_names = self.get_complete_command_names()
+        if event.message_str.strip() in complete_command_names:
+            tree = self.group_name + "\n" + self.print_cmd_tree(self.sub_command_filters, event=event, cfg=cfg)
            raise ValueError(f"指令组 {self.group_name} 未填写完全。这个指令组下有如下指令：\n"+tree)
        
-        child_command_handler_md = None
-        for sub_filter in self.sub_command_filters:
-            if isinstance(sub_filter, CommandFilter):
-                if sub_filter.filter(event, cfg):
-                    child_command_handler_md = sub_filter.get_handler_md()
-                    return True, child_command_handler_md
-            elif isinstance(sub_filter, CommandGroupFilter):
-                ok, handler = sub_filter.filter(event, cfg)
-                if ok:
-                    child_command_handler_md = handler
-                    return True, child_command_handler_md
-        tree = self.group_name + "\n" + self.print_cmd_tree(self.sub_command_filters)
-        raise ValueError(f"指令组 {self.group_name} 下没有找到对应的指令。这个指令组下有如下指令：\n"+tree)
+        # complete_command_names = [name + " " for name in complete_command_names]
+        # return event.message_str.startswith(tuple(complete_command_names))
+        return False
--- a/astrbot/core/star/filter/custom_filter.py
+++ b/astrbot/core/star/filter/custom_filter.py
@@ -0,0 +1,53 @@
+from abc import abstractmethod, ABCMeta
+
+from . import HandlerFilter
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core.config import AstrBotConfig
+
+class CustomFilterMeta(ABCMeta):
+    def __and__(cls, other):
+        if not issubclass(other, CustomFilter):
+            raise TypeError("Operands must be subclasses of CustomFilter.")
+        return CustomFilterAnd(cls(), other())
+
+    def __or__(cls, other):
+        if not issubclass(other, CustomFilter):
+            raise TypeError("Operands must be subclasses of CustomFilter.")
+        return CustomFilterOr(cls(), other())
+
+class CustomFilter(HandlerFilter, metaclass=CustomFilterMeta):
+    def __init__(self,  raise_error: bool = True, **kwargs):
+        self.raise_error = raise_error
+
+    @abstractmethod
+    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        ''' 一个用于重写的自定义Filter '''
+        raise NotImplementedError
+
+    def __or__(self, other):
+        return CustomFilterOr(self, other)
+
+    def __and__(self, other):
+        return CustomFilterAnd(self, other)
+
+class CustomFilterOr(CustomFilter):
+    def __init__(self, filter1: CustomFilter, filter2: CustomFilter):
+        super().__init__()
+        if not isinstance(filter1, (CustomFilter, CustomFilterAnd, CustomFilterOr)):
+            raise ValueError("CustomFilter lass can only operate with other CustomFilter.")
+        self.filter1 = filter1
+        self.filter2 = filter2
+
+    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        return self.filter1.filter(event, cfg) or self.filter2.filter(event, cfg)
+
+class CustomFilterAnd(CustomFilter):
+    def __init__(self, filter1: CustomFilter, filter2: CustomFilter):
+        super().__init__()
+        if not isinstance(filter1, (CustomFilter, CustomFilterAnd, CustomFilterOr)):
+            raise ValueError("CustomFilter lass can only operate with other CustomFilter.")
+        self.filter1 = filter1
+        self.filter2 = filter2
+
+    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
+        return self.filter1.filter(event, cfg) and self.filter2.filter(event, cfg)
--- a/astrbot/core/star/filter/permission.py
+++ b/astrbot/core/star/filter/permission.py
@@ -19,7 +19,8 @@ class PermissionTypeFilter(HandlerFilter):
        '''
        if self.permission_type == PermissionType.ADMIN:
            if not event.is_admin():
-                event.stop_event()
-                raise ValueError(f"您 (ID: {event.get_sender_id()}) 没有权限执行此操作。")
+                # event.stop_event()
+                # raise ValueError(f"您 (ID: {event.get_sender_id()}) 没有权限操作管理员指令。")
+                return False

        return True
--- a/astrbot/core/star/filter/regex.py
+++ b/astrbot/core/star/filter/regex.py
@@ -8,6 +8,7 @@ from astrbot.core.config import AstrBotConfig
 class RegexFilter(HandlerFilter):
    '''正则表达式过滤器'''
    def __init__(self, regex: str):
+        self.regex_str = regex
        self.regex = re.compile(regex)
        
    def filter(self, event: AstrMessageEvent, cfg: AstrBotConfig) -> bool:
--- a/astrbot/core/star/register/init.py
+++ b/astrbot/core/star/register/init.py
@@ -6,7 +6,9 @@ from .star_handler import (
    register_platform_adapter_type,
    register_regex,
    register_permission_type,
+    register_custom_filter,
    register_on_llm_request,
+    register_on_llm_response,
    register_llm_tool,
    register_on_decorating_result,
    register_after_message_sent
@@ -20,7 +22,9 @@ __all__ = [
    'register_platform_adapter_type',
    'register_regex',
    'register_permission_type',
+    'register_custom_filter',
    'register_on_llm_request',
+    'register_on_llm_response',
    'register_llm_tool',
    'register_on_decorating_result',
    'register_after_message_sent'
--- a/astrbot/core/star/register/star_handler.py
+++ b/astrbot/core/star/register/star_handler.py
@@ -7,6 +7,7 @@ from ..filter.command_group import CommandGroupFilter
 from ..filter.event_message_type import EventMessageTypeFilter, EventMessageType
 from ..filter.platform_adapter_type import PlatformAdapterTypeFilter, PlatformAdapterType
 from ..filter.permission import PermissionTypeFilter, PermissionType
+from ..filter.custom_filter import CustomFilterAnd, CustomFilterOr
 from ..filter.regex import RegexFilter
 from typing import Awaitable
 from astrbot.core.provider.func_tool_manager import SUPPORTED_TYPES
@@ -17,7 +18,12 @@ def get_handler_full_name(awaitable: Awaitable) -> str:
    '''获取 Handler 的全名'''
    return f"{awaitable.__module__}_{awaitable.__name__}"

-def get_handler_or_create(handler: Awaitable, event_type: EventType, dont_add = False) -> StarHandlerMetadata:
+def get_handler_or_create(
+        handler: Awaitable, 
+        event_type: EventType, 
+        dont_add = False, 
+        **kwargs
+) -> StarHandlerMetadata:
    '''获取 Handler 或者创建一个新的 Handler'''
    handler_full_name = get_handler_full_name(handler)
    md = star_handlers_registry.get_handler_by_full_name(handler_full_name)
@@ -32,77 +38,143 @@ def get_handler_or_create(handler: Awaitable, event_type: EventType, dont_add =
            handler=handler,
            event_filters=[]
        )
+        
+        # 插件handler的附加额外信息
+        if handler.__doc__:
+            md.desc = handler.__doc__.strip()
+        if 'desc' in kwargs:
+            md.desc = kwargs['desc']
+            del kwargs['desc']
+        md.extras_configs = kwargs
+        
        if not dont_add:
            star_handlers_registry.append(md)
        return md

-def register_command(command_name: str = None, *args):
-    '''注册一个 Command'''
-    
+def register_command(command_name: str = None, sub_command: str = None, alias: set = None, **kwargs):
+    '''注册一个 Command.
+    '''
    new_command = None
    add_to_event_filters = False
    if isinstance(command_name, RegisteringCommandable):
        # 子指令
-        new_command = CommandFilter(args[0], None)
+        parent_command_names = command_name.parent_group.get_complete_command_names()
+        logger.debug(f"parent_command_names: {parent_command_names}")
+        new_command = CommandFilter(sub_command, alias, None, parent_command_names=parent_command_names)
        command_name.parent_group.add_sub_command_filter(new_command)
    else:
        # 裸指令
-        new_command = CommandFilter(command_name, None)
+        new_command = CommandFilter(command_name, alias, None)
        add_to_event_filters = True
    
    def decorator(awaitable):
-        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent)
+        if not add_to_event_filters:
+            kwargs['sub_command'] = True # 打一个标记，表示这是一个子指令，再 wakingstage 阶段这个 handler 将会直接被跳过（其父指令会接管）
+        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
        new_command.init_handler_md(handler_md)
-        if add_to_event_filters:
-            # 裸指令
-            handler_md.event_filters.append(new_command)
-        
+        handler_md.event_filters.append(new_command)
        return awaitable

    return decorator

-def register_command_group(command_group_name: str = None, *args):
-    '''注册一个 CommandGroup'''
-    
-    new_group = None
+
+def register_custom_filter(custom_type_filter, *args, **kwargs):
+    '''注册一个自定义的 CustomFilter
+
+    Args:
+        custom_type_filter: 在裸指令时为CustomFilter对象
+                                        在指令组时为父指令的RegisteringCommandable对象，即self或者command_group的返回
+        raise_error: 如果没有权限，是否抛出错误到消息平台，并且停止事件传播。默认为 True
+    '''
    add_to_event_filters = False
+    raise_error = True
+
+    # 判断是否是指令组，指令组则添加到指令组的CommandGroupFilter对象中在waking_check的时候一起判断
+    if isinstance(custom_type_filter, RegisteringCommandable):
+        # 子指令, 此时函数为RegisteringCommandable对象的方法，首位参数为RegisteringCommandable对象的self。
+        parent_register_commandable = custom_type_filter
+        custom_filter = args[0]
+        if len(args) > 1:
+            raise_error = args[1]
+    else:
+        # 裸指令
+        add_to_event_filters = True
+        custom_filter = custom_type_filter
+        if args:
+            raise_error = args[0]
+
+    if not isinstance(custom_filter, (CustomFilterAnd, CustomFilterOr)):
+        custom_filter = custom_filter(raise_error)
+
+    def decorator(awaitable):
+        # 裸指令，子指令与指令组的区分，指令组会因为标记跳过wake。
+        if not add_to_event_filters and isinstance(awaitable, RegisteringCommandable) or \
+            (add_to_event_filters and isinstance(awaitable, RegisteringCommandable)):
+            # 指令组 与 根指令组，添加到本层的grouphandle中一起判断
+            awaitable.parent_group.add_custom_filter(custom_filter)
+        else:
+            handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
+
+            if not add_to_event_filters and not isinstance(awaitable, RegisteringCommandable):
+                # 底层子指令
+                handle_full_name = get_handler_full_name(awaitable)
+                for sub_handle in parent_register_commandable.parent_group.sub_command_filters:
+                    # 所有符合fullname一致的子指令handle添加自定义过滤器。
+                    # 不确定是否会有多个子指令有一样的fullname，比如一个方法添加多个command装饰器？
+                    sub_handle_md = sub_handle.get_handler_md()
+                    if sub_handle_md and sub_handle_md.handler_full_name == handle_full_name:
+                        sub_handle.add_custom_filter(custom_filter)
+
+            else:
+                # 裸指令
+                handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
+                handler_md.event_filters.append(custom_filter)
+
+        return awaitable
+    return decorator
+
+def register_command_group(
+    command_group_name: str = None, sub_command: str = None, alias: set = None, **kwargs
+):
+    '''注册一个 CommandGroup
+    '''
+    new_group = None
    if isinstance(command_group_name, RegisteringCommandable):
        # 子指令组
-        new_group = CommandGroupFilter(args[0])
+        new_group = CommandGroupFilter(sub_command, alias, parent_group=command_group_name.parent_group)
        command_group_name.parent_group.add_sub_command_filter(new_group)
    else:
        # 根指令组
-        new_group = CommandGroupFilter(command_group_name)
-        add_to_event_filters = True
+        new_group = CommandGroupFilter(command_group_name, alias)
    
    def decorator(obj):
-        if add_to_event_filters:
-            # 根指令组
-            handler_md = get_handler_or_create(obj, EventType.AdapterMessageEvent)
-            handler_md.event_filters.append(new_group)
-        
+        # 根指令组
+        handler_md = get_handler_or_create(obj, EventType.AdapterMessageEvent, **kwargs)
+        handler_md.event_filters.append(new_group)
+            
        return RegisteringCommandable(new_group)

    return decorator

 class RegisteringCommandable():
    '''用于指令组级联注册'''
-    group = register_command_group
-    command = register_command
-    
+    group: CommandGroupFilter = register_command_group
+    command: CommandFilter = register_command
+    custom_filter = register_custom_filter
+
    def __init__(self, parent_group: CommandGroupFilter):
        self.parent_group = parent_group

-def register_event_message_type(event_message_type: EventMessageType):
+def register_event_message_type(event_message_type: EventMessageType, **kwargs):
    '''注册一个 EventMessageType'''
    def decorator(awaitable):
-        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent)
+        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
        handler_md.event_filters.append(EventMessageTypeFilter(event_message_type))
        return awaitable

    return decorator

-def register_platform_adapter_type(platform_adapter_type: PlatformAdapterType):
+def register_platform_adapter_type(platform_adapter_type: PlatformAdapterType, **kwargs):
    '''注册一个 PlatformAdapterType'''
    def decorator(awaitable):
        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent)
@@ -111,10 +183,10 @@ def register_platform_adapter_type(platform_adapter_type: PlatformAdapterType):

    return decorator

-def register_regex(regex: str):
+def register_regex(regex: str, **kwargs):
    '''注册一个 Regex'''
    def decorator(awaitable):
-        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent)
+        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
        handler_md.event_filters.append(RegexFilter(regex))
        return awaitable

@@ -134,11 +206,13 @@ def register_permission_type(permission_type: PermissionType, raise_error: bool

    return decorator

-def register_on_llm_request():
+def register_on_llm_request(**kwargs):
    '''当有 LLM 请求时的事件
    
    Examples:
    ```py
+    from astrbot.api.provider import ProviderRequest
+    
    @on_llm_request()
    async def test(self, event: AstrMessageEvent, request: ProviderRequest) -> None:
        request.system_prompt += "你是一个猫娘..."
@@ -147,11 +221,32 @@ def register_on_llm_request():
    请务必接收两个参数：event, request
    '''
    def decorator(awaitable):
-        _ = get_handler_or_create(awaitable, EventType.OnLLMRequestEvent)
+        _ = get_handler_or_create(awaitable, EventType.OnLLMRequestEvent, **kwargs)
        return awaitable
    
    return decorator

+def register_on_llm_response(**kwargs):
+    '''当有 LLM 请求后的事件
+    
+    Examples:
+    ```py
+    from astrbot.api.provider import LLMResponse
+    
+    @on_llm_response()
+    async def test(self, event: AstrMessageEvent, response: LLMResponse) -> None:
+        ...
+    ```
+    
+    请务必接收两个参数：event, request
+    '''
+    def decorator(awaitable):
+        _ = get_handler_or_create(awaitable, EventType.OnLLMResponseEvent, **kwargs)
+        return awaitable
+    
+    return decorator
+
+
 def register_llm_tool(name: str = None):
    '''为函数调用（function-calling / tools-use）添加工具。
    
@@ -159,7 +254,7 @@ def register_llm_tool(name: str = None):
    
    ```
    @llm_tool(name="get_weather") # 如果 name 不填，将使用函数名
-    async def get_weather(event: AstrMessageEvent, location: str) -> MessageEventResult:
+    async def get_weather(event: AstrMessageEvent, location: str):
        \'\'\'获取天气信息。
        
        Args:
@@ -169,7 +264,22 @@ def register_llm_tool(name: str = None):
    ```
    
    可接受的参数类型有：string, number, object, array, boolean。
+    
+    返回值：
+        - 返回 str：结果会被加入下一次 LLM 请求的 prompt 中，用于让 LLM 总结工具返回的结果
+        - 返回 None：结果不会被加入下一次 LLM 请求的 prompt 中。
+        
+    可以使用 yield 发送消息、终止事件。
+    
+    发送消息：请参考文档。
+    
+    终止事件：
+    ```
+    event.stop_event()
+    yield
+    ```
    '''
+    
    name_ = name
    
    def decorator(awaitable: Awaitable):
@@ -192,18 +302,18 @@ def register_llm_tool(name: str = None):
    
    return decorator

-def register_on_decorating_result():
+def register_on_decorating_result(**kwargs):
    '''在发送消息前的事件'''
    def decorator(awaitable):
-        _ = get_handler_or_create(awaitable, EventType.OnDecoratingResultEvent)
+        _ = get_handler_or_create(awaitable, EventType.OnDecoratingResultEvent, **kwargs)
        return awaitable
    
    return decorator

-def register_after_message_sent():
+def register_after_message_sent(**kwargs):
    '''在消息发送后的事件'''
    def decorator(awaitable):
-        _ = get_handler_or_create(awaitable, EventType.OnAfterMessageSentEvent)
+        _ = get_handler_or_create(awaitable, EventType.OnAfterMessageSentEvent, **kwargs)
        return awaitable
    
    return decorator
--- a/astrbot/core/star/star.py
+++ b/astrbot/core/star/star.py
@@ -2,7 +2,8 @@ from __future__ import annotations

 from types import ModuleType
 from typing import List, Dict
-from dataclasses import dataclass
+from dataclasses import dataclass, field
+from astrbot.core.config import AstrBotConfig

 star_registry: List[StarMetadata] = []
 star_map: Dict[str, StarMetadata] = {}
@@ -11,7 +12,7 @@ star_map: Dict[str, StarMetadata] = {}
@dataclass
 class StarMetadata:
    '''
-    Star 的元数据。
+    插件的元数据。
    '''
    name: str
    author: str  # 插件作者
@@ -20,21 +21,27 @@ class StarMetadata:
    repo: str = None  # 插件仓库地址

    star_cls_type: type = None
-    '''Star 的类对象的类型'''
+    '''插件的类对象的类型'''
    module_path: str = None
-    '''Star 的模块路径'''
+    '''插件的模块路径'''
    
    star_cls: object = None
-    '''Star 的类对象'''
+    '''插件的类对象'''
    module: ModuleType = None
-    '''Star 的模块对象'''
+    '''插件的模块对象'''
    root_dir_name: str = None
-    '''Star 的根目录名'''
+    '''插件的目录名称'''
    reserved: bool = False
-    '''是否是 AstrBot 的保留 Star'''
+    '''是否是 AstrBot 的保留插件'''
    
    activated: bool = True
    '''是否被激活'''
+    
+    config: AstrBotConfig = None
+    '''插件配置'''
+    
+    star_handler_full_names: List[str] = field(default_factory=list)
+    '''注册的 Handler 的全名列表'''

    def __str__(self) -> str:
        return f"StarMetadata({self.name}, {self.desc}, {self.version}, {self.repo})"
--- a/astrbot/core/star/star_handler.py
+++ b/astrbot/core/star/star_handler.py
@@ -1,34 +1,41 @@
 from __future__ import annotations
 import enum
-from dataclasses import dataclass
+import heapq
+from dataclasses import dataclass, field
 from typing import Awaitable, List, Dict, TypeVar, Generic
 from .filter import HandlerFilter
 from .star import star_map

 T = TypeVar('T', bound='StarHandlerMetadata')
-class StarHandlerRegistry(Generic[T], List[T]):
+class StarHandlerRegistry(Generic[T]):
    '''用于存储所有的 Star Handler'''
    
    star_handlers_map: Dict[str, StarHandlerMetadata] = {}
    '''用于快速查找。key 是 handler_full_name'''
+    _handlers = []
    
    def append(self, handler: StarHandlerMetadata):
        '''添加一个 Handler'''
-        super().append(handler)
+        if 'priority' not in handler.extras_configs:
+            handler.extras_configs['priority'] = 0
+        
+        heapq.heappush(self._handlers, (-handler.extras_configs['priority'], handler))
        self.star_handlers_map[handler.handler_full_name] = handler
        
-    def get_handlers_by_event_type(self, event_type: EventType, only_activated = True) -> List[StarHandlerMetadata]:
+    def _print_handlers(self):
+        '''打印所有的 Handler'''
+        for _, handler in self._handlers:
+            print(handler.handler_full_name)
+        
+    def get_handlers_by_event_type(self, event_type: EventType, only_activated=True) -> List[StarHandlerMetadata]:
        '''通过事件类型获取 Handler'''
-        if only_activated:
-            return [
-                handler 
-                for handler in self 
-                if handler.event_type == event_type and 
-                star_map[handler.handler_module_path] and 
-                star_map[handler.handler_module_path].activated
-            ]
-        else:
-            return [handler for handler in self if handler.event_type == event_type]
+        handlers = [
+            handler 
+            for _, handler in self._handlers 
+            if handler.event_type == event_type and 
+            (not only_activated or (star_map[handler.handler_module_path] and star_map[handler.handler_module_path].activated))
+        ]
+        return handlers
    
    def get_handler_by_full_name(self, full_name: str) -> StarHandlerMetadata:
        '''通过 Handler 的全名获取 Handler'''
@@ -36,7 +43,32 @@ class StarHandlerRegistry(Generic[T], List[T]):
    
    def get_handlers_by_module_name(self, module_name: str) -> List[StarHandlerMetadata]:
        '''通过模块名获取 Handler'''
-        return [handler for handler in self if handler.handler_module_path == module_name]
+        return [handler for _, handler in self._handlers if handler.handler_module_path == module_name]
+    
+    def clear(self):
+        '''清空所有的 Handler'''
+        self.star_handlers_map.clear()
+        self._handlers.clear()
+        
+    def remove(self, handler: StarHandlerMetadata):
+        '''删除一个 Handler'''
+        # self._handlers.remove(handler)
+        for i, h in enumerate(self._handlers):
+            if h[1] == handler:
+                self._handlers.pop(i)
+                break
+        try:
+            del self.star_handlers_map[handler.handler_full_name]
+        except KeyError:
+            pass
+    
+    def __iter__(self):
+        '''使 StarHandlerRegistry 支持迭代'''
+        return (handler for _, handler in self._handlers)
+    
+    def __len__(self):
+        '''返回 Handler 的数量'''
+        return len(self._handlers)
    
 star_handlers_registry = StarHandlerRegistry()

@@ -47,6 +79,7 @@ class EventType(enum.Enum):
    '''
    AdapterMessageEvent = enum.auto() # 收到适配器发来的消息
    OnLLMRequestEvent = enum.auto() # 收到 LLM 请求（可以是用户也可以是插件）
+    OnLLMResponseEvent = enum.auto() # LLM 响应后
    OnDecoratingResultEvent = enum.auto() # 发送消息前
    OnCallingFuncToolEvent = enum.auto() # 调用函数工具
    OnAfterMessageSentEvent = enum.auto() # 发送消息后
@@ -75,3 +108,10 @@ class StarHandlerMetadata():
    
    desc: str = ""
    '''Handler 的描述信息'''
+
+    extras_configs: dict = field(default_factory=dict)
+    '''插件注册的一些其他的信息, 如 priority 等'''
+
+    def __lt__(self, other: StarHandlerMetadata):
+        '''定义小于运算符以支持优先队列'''
+        return self.extras_configs.get('priority', 0) < other.extras_configs.get('priority', 0)
--- a/astrbot/core/star/star_manager.py
+++ b/astrbot/core/star/star_manager.py
@@ -2,6 +2,7 @@ import inspect
 import functools
 import os
 import sys
+import json
 import traceback
 import yaml
 import logging
@@ -17,6 +18,8 @@ from .star import star_registry, star_map
 from .star_handler import star_handlers_registry
 from astrbot.core.provider.register import llm_tools

+from .filter.permission import PermissionTypeFilter, PermissionType
+
 class PluginManager:
    def __init__(
        self, 
@@ -26,13 +29,22 @@ class PluginManager:
        self.updator = PluginUpdator(config['plugin_repo_mirror'])
        
        self.context = context
-        self.context._star_manager = self # 就这样吧，不想改了
+        self.context._star_manager = self
                
        self.config = config
        self.plugin_store_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), "../../../data/plugins"))
+        '''存储插件的路径。即 data/plugins'''
+        self.plugin_config_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), "../../../data/config"))
+        '''存储插件配置的路径。data/config'''
        self.reserved_plugin_path = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), "../../../packages"))
+        '''保留插件的路径。在 packages 目录下'''
+        self.conf_schema_fname = "_conf_schema.json"
+        '''插件配置 Schema 文件名'''
+        
+        self.failed_plugin_info = ""

    def _get_classes(self, arg: ModuleType):
+        '''获取指定模块（可以理解为一个 python 文件）下所有的类'''
        classes = []
        clsmembers = inspect.getmembers(arg, inspect.isclass)
        for (name, _) in clsmembers:
@@ -116,7 +128,7 @@ class PluginManager:
        
        if isinstance(metadata, dict):
            if 'name' not in metadata or 'desc' not in metadata or 'version' not in metadata or 'author' not in metadata:
-                raise Exception("插件元数据信息不完整。")
+                raise Exception("插件元数据信息不完整。name, desc, version, author 是必须的字段。")
            metadata = StarMetadata(
                name=metadata['name'],
                author=metadata['author'],
@@ -126,43 +138,69 @@ class PluginManager:
            )
            
        return metadata
-    
-    async def reload(self):
-        '''扫描并加载所有的 Star'''
-        for smd in star_registry:
-            logger.debug(f"尝试终止插件 {smd.name} ...")
-            if hasattr(smd.star_cls, "__del__"):
-                smd.star_cls.__del__()
-            
-        star_handlers_registry.clear()
-        star_handlers_registry.star_handlers_map.clear()
-        star_map.clear()
-        star_registry.clear()
-        for key in list(sys.modules.keys()):
-            if key.startswith("data.plugins") or key.startswith("packages"):
-                del sys.modules[key]
+        
+    async def reload(self, specified_plugin_name=None):
+        '''扫描并加载所有的插件 当 specified_module_path 指定时，重载指定插件'''
+        
+        specified_module_path = None
+        if specified_plugin_name:
+            for smd in star_registry:
+                if smd.name == specified_plugin_name:
+                    specified_module_path = smd.module_path
+                    break
+        
+        # 终止插件
+        if not specified_module_path:
+            for smd in star_registry:
+                logger.debug(f"尝试终止插件 {smd.name} ...")
+                if hasattr(smd.star_cls, "__del__"):
+                    smd.star_cls.__del__()
+                
+            star_handlers_registry.clear()
+            star_map.clear()
+            star_registry.clear()
+            for key in list(sys.modules.keys()):
+                if key.startswith("data.plugins") or key.startswith("packages"):
+                    del sys.modules[key]
+        else:
+            # 只重载指定插件
+            smd = star_map.get(specified_module_path)
+            if smd:
+                await self._unbind_plugin(smd.name, specified_module_path)
+                try:
+                    del sys.modules[specified_module_path]
+                except KeyError:
+                    logger.warning(f"模块 {specified_module_path} 未载入")
+
        
        plugin_modules = self._get_plugin_modules()
        if plugin_modules is None:
            return False, "未找到任何插件模块"
+        
        fail_rec = ""
        
        inactivated_plugins: list = sp.get("inactivated_plugins", [])
        inactivated_llm_tools: list = sp.get("inactivated_llm_tools", [])
        
-        # 导入 Star 模块，并尝试实例化 Star 类
+        alter_cmd = sp.get("alter_cmd", {})
+        
+        # 导入插件模块，并尝试实例化插件类
        for plugin_module in plugin_modules:
            try:
                module_str = plugin_module['module']
                # module_path = plugin_module['module_path']
-                root_dir_name = plugin_module['pname']
-                reserved = plugin_module.get('reserved', False)
+                root_dir_name = plugin_module['pname'] # 插件的目录名
+                reserved = plugin_module.get('reserved', False) # 是否是保留插件。目前在 packages/ 目录下的都是保留插件。保留插件不可以卸载。
+                
+                path = "data.plugins." if not reserved else "packages."
+                path += root_dir_name + "." + module_str
+                
+                if specified_module_path and path != specified_module_path:
+                    continue
                
                logger.info(f"正在载入插件 {root_dir_name} ...")
                
                # 尝试导入模块
-                path = "data.plugins." if not reserved else "packages."
-                path += root_dir_name + "." + module_str
                try:
                    module = __import__(path, fromlist=[module_str])
                except (ModuleNotFoundError, ImportError):
@@ -173,21 +211,54 @@ class PluginManager:
                    logger.error(traceback.format_exc())
                    logger.error(f"插件 {root_dir_name} 导入失败。原因：{str(e)}")
                    continue
+                
+                # 检查 _conf_schema.json
+                plugin_config = None
+                plugin_dir_path = os.path.join(self.plugin_store_path, root_dir_name) \
+                    if not reserved else os.path.join(self.reserved_plugin_path, root_dir_name)
+                plugin_schema_path = os.path.join(plugin_dir_path, self.conf_schema_fname)
+                if os.path.exists(plugin_schema_path):
+                    # 加载插件配置
+                    with open(plugin_schema_path, 'r', encoding='utf-8') as f:
+                        plugin_config = AstrBotConfig(
+                            config_path=os.path.join(self.plugin_config_path, f"{root_dir_name}_config.json"), 
+                            schema=json.loads(f.read())
+                        )

                if path in star_map:
                    # 通过装饰器的方式注册插件
                    metadata = star_map[path]
-                    metadata.star_cls = metadata.star_cls_type(context=self.context)
+                    
+                    try:
+                        # yaml 文件的元数据优先
+                        metadata_yaml = self._load_plugin_metadata(plugin_path=plugin_dir_path)
+                        if metadata_yaml:
+                            metadata.name = metadata_yaml.name
+                            metadata.author = metadata_yaml.author
+                            metadata.desc = metadata_yaml.desc
+                            metadata.version = metadata_yaml.version
+                            metadata.repo = metadata_yaml.repo
+                    except Exception:
+                        pass
+                    
+                    if plugin_config:
+                        metadata.config = plugin_config
+                        try:
+                            metadata.star_cls = metadata.star_cls_type(context=self.context, config=plugin_config)
+                        except TypeError as _:
+                            metadata.star_cls = metadata.star_cls_type(context=self.context)
+                    else:
+                        metadata.star_cls = metadata.star_cls_type(context=self.context)
+                            
                    metadata.module = module
                    metadata.root_dir_name = root_dir_name
                    metadata.reserved = reserved
                    
+                    # 绑定 handler
                    related_handlers = star_handlers_registry.get_handlers_by_module_name(metadata.module_path)
                    for handler in related_handlers:
-                        logger.debug(f"bind handler {handler.handler_name} to {metadata.name}")
-                        # handler.handler.__self__ = star_metadata.star_cls # 绑定 handler 的 self
                        handler.handler = functools.partial(handler.handler, metadata.star_cls)
-                    # llm_tool
+                    # 绑定 llm_tool handler
                    for func_tool in llm_tools.func_list:
                        if func_tool.handler.__module__ == metadata.module_path:
                            func_tool.handler_module_path = metadata.module_path
@@ -199,16 +270,19 @@ class PluginManager:
                    # v3.4.0 以前的方式注册插件
                    logger.debug(f"插件 {path} 未通过装饰器注册。尝试通过旧版本方式载入。")
                    classes = self._get_classes(module)
-                    try:
-                        obj = getattr(module, classes[0])(context=self.context)
-                    except BaseException as e:
-                        logger.error(f"插件 {root_dir_name} 实例化失败。")
-                        raise e
                    
+                    if plugin_config:
+                        try:
+                            obj = getattr(module, classes[0])(context=self.context, config=plugin_config) # 实例化插件类
+                        except TypeError as _:
+                            obj = getattr(module, classes[0])(context=self.context) # 实例化插件类
+                    else:
+                        obj = getattr(module, classes[0])(context=self.context) # 实例化插件类
+
                    metadata = None
-                    plugin_path = os.path.join(self.plugin_store_path, root_dir_name) if not reserved else os.path.join(self.reserved_plugin_path, root_dir_name)
-                    metadata = self._load_plugin_metadata(plugin_path=plugin_path, plugin_obj=obj)
+                    metadata = self._load_plugin_metadata(plugin_path=plugin_dir_path, plugin_obj=obj)
                    metadata.star_cls = obj
+                    metadata.config = plugin_config
                    metadata.module = module
                    metadata.root_dir_name = root_dir_name
                    metadata.reserved = reserved
@@ -216,30 +290,58 @@ class PluginManager:
                    metadata.module_path = path
                    star_map[path] = metadata
                    star_registry.append(metadata)
-                    logger.debug(f"插件 {root_dir_name} 载入成功。")
                
+                # 禁用/启用插件
                if metadata.module_path in inactivated_plugins:
                    metadata.activated = False
                    
-                # 执行 initialize 函数
+                full_names = []
+                for handler in star_handlers_registry.get_handlers_by_module_name(metadata.module_path):
+                    full_names.append(handler.handler_full_name)
+                    
+                    # 检查并且植入自定义的权限过滤器（alter_cmd）
+                    if metadata.name in alter_cmd and handler.handler_name in alter_cmd[metadata.name]:
+                        cmd_type = alter_cmd[metadata.name][handler.handler_name].get("permission", "member")
+                        found_permission_filter = False
+                        for filter_ in handler.event_filters:
+                            if isinstance(filter_, PermissionTypeFilter):
+                                if cmd_type == "admin":
+                                    filter_.permission_type = PermissionType.ADMIN
+                                else:
+                                    filter_.permission_type = PermissionType.MEMBER
+                                found_permission_filter = True
+                                break
+                        if not found_permission_filter:
+                            handler.event_filters.append(PermissionTypeFilter(PermissionType.ADMIN if cmd_type == "admin" else PermissionType.MEMBER))
+
+                        logger.debug(f"插入权限过滤器 {cmd_type} 到 {metadata.name} 的 {handler.handler_name} 方法。")
+                    
+                metadata.star_handler_full_names = full_names
+
+                # 执行 initialize() 方法
                if hasattr(metadata.star_cls, "initialize"):
                    await metadata.star_cls.initialize()
                    
            except BaseException as e:
-                traceback.print_exc()
-                fail_rec += f"加载 {path} 插件时出现问题，原因 {str(e)}\n"
+                logger.error(f"----- 插件 {root_dir_name} 载入失败 -----")
+                errors = traceback.format_exc()
+                for line in errors.split('\n'):
+                    logger.error(f"| {line}")
+                logger.error("----------------------------------")
+                fail_rec += f"加载 {root_dir_name} 插件时出现问题，原因 {str(e)}。\n"

        # 清除 pip.main 导致的多余的 logging handlers
        for handler in logging.root.handlers[:]:
            logging.root.removeHandler(handler)
-        
+
        if not fail_rec:
            return True, None
        else:
+            self.failed_plugin_info = fail_rec
            return False, fail_rec
        
-    async def install_plugin(self, repo_url: str):
-        plugin_path = await self.updator.install(repo_url)
+    async def install_plugin(self, repo_url: str, proxy=""):
+        plugin_path = await self.updator.install(repo_url, proxy)
        # reload the plugin
        await self.reload()
        return plugin_path
@@ -274,14 +376,14 @@ class PluginManager:
            logger.debug(f"unbind handler {v.handler_name} from {plugin_name} (map)")
            del star_handlers_registry.star_handlers_map[k]

-    async def update_plugin(self, plugin_name: str):
+    async def update_plugin(self, plugin_name: str, proxy = ""):
        plugin = self.context.get_registered_star(plugin_name)
        if not plugin:
            raise Exception("插件不存在。")
        if plugin.reserved:
            raise Exception("该插件是 AstrBot 保留插件，无法更新。")
        
-        await self.updator.update(plugin)
+        await self.updator.update(plugin, proxy=proxy)
        await self.reload()
    
    async def turn_off_plugin(self, plugin_name: str):
@@ -292,13 +394,14 @@ class PluginManager:
        if plugin.module_path not in inactivated_plugins:
            inactivated_plugins.append(plugin.module_path)
            
-        inactivated_llm_tools: list = sp.get("inactivated_llm_tools", [])
+        inactivated_llm_tools: list = list(set(sp.get("inactivated_llm_tools", []))) # 后向兼容
        
        # 禁用插件启用的 llm_tool
        for func_tool in llm_tools.func_list:
            if func_tool.handler_module_path == plugin.module_path:
                func_tool.active = False
-                inactivated_llm_tools.append(func_tool.name)
+                if func_tool.name not in inactivated_llm_tools:
+                    inactivated_llm_tools.append(func_tool.name)
    
        sp.put("inactivated_plugins", inactivated_plugins)
        sp.put("inactivated_llm_tools", inactivated_llm_tools)
@@ -323,8 +426,10 @@ class PluginManager:
        plugin.activated = True
        
        
-    def install_plugin_from_file(self, zip_file_path: str):
-        desti_dir = os.path.join(self.plugin_store_path, os.path.basename(zip_file_path))
+    async def install_plugin_from_file(self, zip_file_path: str):
+        dir_name = os.path.basename(zip_file_path).replace(".zip", "")
+        dir_name = dir_name.removesuffix("-master").removesuffix("-main").lower()
+        desti_dir = os.path.join(self.plugin_store_path, dir_name)
        self.updator.unzip_file(zip_file_path, desti_dir)

        # remove the zip
@@ -332,6 +437,4 @@ class PluginManager:
            os.remove(zip_file_path)
        except BaseException as e:
            logger.warning(f"删除插件压缩包失败: {str(e)}")
-        
-        self._check_plugin_dept_update()
-
+        await self.reload()
--- a/astrbot/core/star/updator.py
+++ b/astrbot/core/star/updator.py
@@ -15,20 +15,24 @@ class PluginUpdator(RepoZipUpdator):
    def get_plugin_store_path(self) -> str:
        return self.plugin_store_path
    
-    async def install(self, repo_url: str) -> str:
+    async def install(self, repo_url: str, proxy="") -> str:
        repo_name = self.format_repo_name(repo_url)
        plugin_path = os.path.join(self.plugin_store_path, repo_name)
-        await self.download_from_repo_url(plugin_path, repo_url)
+        await self.download_from_repo_url(plugin_path, repo_url, proxy)
        self.unzip_file(plugin_path + ".zip", plugin_path)
        
        return plugin_path

-    async def update(self, plugin: StarMetadata) -> str:
+    async def update(self, plugin: StarMetadata, proxy="") -> str:
        repo_url = plugin.repo
        
        if not repo_url:
            raise Exception(f"插件 {plugin.name} 没有指定仓库地址。")
        
+        if proxy:
+            proxy = proxy.removesuffix("/")
+            repo_url = f"{proxy}/{repo_url}"
+        
        plugin_path = os.path.join(self.plugin_store_path, plugin.root_dir_name)
            
        logger.info(f"正在更新插件，路径: {plugin_path}，仓库地址: {repo_url}")
--- a/astrbot/core/utils/dify_api_client.py
+++ b/astrbot/core/utils/dify_api_client.py
@@ -27,22 +27,38 @@ class DifyAPIClient:
        payload = locals()
        payload.pop("self")
        payload.pop("timeout")
+        logger.info(f"chat_messages payload: {payload}")
        async with self.session.post(
            url, json=payload, headers=self.headers, timeout=timeout
        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise Exception(f"chat_messages 请求失败：{resp.status}. {text}")
+            
+            buffer = ""
            while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                    break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                    
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
    async def workflow_run(
        self,
        inputs: Dict,
@@ -55,22 +71,38 @@ class DifyAPIClient:
        payload = locals()
        payload.pop("self")
        payload.pop("timeout")
+        logger.info(f"workflow_run payload: {payload}")
        async with self.session.post(
            url, json=payload, headers=self.headers, timeout=timeout
        ) as resp:
+            if resp.status != 200:
+                text = await resp.text()
+                raise Exception(f"workflow_run 请求失败：{resp.status}. {text}")
+            
+            buffer = ""
            while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                    break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                    
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
    async def file_upload(
        self,
        file_path: str,
@@ -87,4 +119,55 @@ class DifyAPIClient:
            return await resp.json() # {"id": "xxx", ...}
                
    async def close(self):
-        await self.session.close()
+        await self.session.close()
+        
+    async def get_chat_convs(
+        self,
+        user: str,
+        limit: int = 20
+    ):
+        # conversations. GET
+        url = f"{self.api_base}/conversations"
+        payload = {
+            "user": user,
+            "limit": limit,
+        }
+        async with self.session.get(
+            url, params=payload, headers=self.headers
+        ) as resp:
+            return await resp.json()
+        
+    async def delete_chat_conv(
+        self,
+        user: str,
+        conversation_id: str
+    ):
+        # conversation. DELETE
+        url = f"{self.api_base}/conversations/{conversation_id}"
+        payload = {
+            "user": user,
+        }
+        async with self.session.delete(
+            url, json=payload, headers=self.headers
+        ) as resp:
+            return await resp.json()
+        
+    async def rename(
+        self,
+        conversation_id: str,
+        name: str,
+        user: str,
+        auto_generate: bool = False
+    ):
+        # /conversations/:conversation_id/name
+        url = f"{self.api_base}/conversations/{conversation_id}/name"
+        payload = {
+            "user": user,
+            "name": name,
+            "auto_generate": auto_generate,
+        }
+        async with self.session.post(
+            url, json=payload, headers=self.headers
+        ) as resp:
+            return await resp.json()
+        
--- a/astrbot/core/utils/io.py
+++ b/astrbot/core/utils/io.py
@@ -7,6 +7,7 @@ import aiohttp
 import base64
 import zipfile
 import uuid
+import psutil
 from typing import Union

 from PIL import Image
@@ -109,7 +110,7 @@ async def download_file(url: str, path: str, show_progress: bool = False):
    '''
    try:
        async with aiohttp.ClientSession(trust_env=True) as session:
-            async with session.get(url, timeout=120) as resp:
+            async with session.get(url, timeout=1800) as resp:
                if resp.status != 200:
                    raise Exception(f"下载文件失败: {resp.status}")
                total_size = int(resp.headers.get('content-length', 0))
@@ -160,17 +161,17 @@ def file_to_base64(file_path: str) -> str:
        base64_str = base64.b64encode(data_bytes).decode()
    return "base64://" + base64_str

+
 def get_local_ip_addresses():
-    ip = ''
-    try:
-        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
-        s.connect(('8.8.8.8', 80))
-        ip = s.getsockname()[0]
-    except BaseException:
-        pass
-    finally:
-        s.close()
-    return ip
+    net_interfaces = psutil.net_if_addrs()
+    network_ips = []
+    
+    for interface, addrs in net_interfaces.items():
+        for addr in addrs:
+            if addr.family == socket.AF_INET:  # 使用 socket.AF_INET 代替 psutil.AF_INET
+                network_ips.append(addr.address)
+    
+    return network_ips

 async def get_dashboard_version():
    if os.path.exists("data/dist"):
--- a/astrbot/core/utils/param_validation_mixin.py
+++ b/astrbot/core/utils/param_validation_mixin.py
@@ -1,32 +0,0 @@
-import inspect
-from typing import List, Dict, Any, Type
-
-class ParameterValidationMixin:
-    def validate_and_convert_params(self, params: List[Any], param_type: Dict[str, Type]) -> Dict[str, Any]:
-        '''将参数列表 params 根据 param_type 转换为参数字典。
-        '''
-        result = {}
-        for i, (param_name, param_type_or_default_val) in enumerate(param_type.items()):
-            if i >= len(params):
-                if isinstance(param_type_or_default_val, Type) or param_type_or_default_val is inspect.Parameter.empty:
-                    # 是类型
-                    raise ValueError(f"参数 {param_name} 缺失")
-                else:
-                    # 是默认值
-                    result[param_name] = param_type_or_default_val
-            else:
-                # 尝试强制转换
-                try:
-                    if param_type_or_default_val is None:
-                        if params[i].isdigit():
-                            result[param_name] = int(params[i])
-                        else:
-                            result[param_name] = params[i]
-                    elif isinstance(param_type_or_default_val, str):
-                        # 如果 param_type_or_default_val 是字符串，直接赋值
-                        result[param_name] = params[i]
-                    else:
-                        result[param_name] = param_type_or_default_val(params[i])
-                except ValueError:
-                    raise ValueError(f"参数 {param_name} 类型错误")
-        return result
--- a/astrbot/core/utils/t2i/network_strategy.py
+++ b/astrbot/core/utils/t2i/network_strategy.py
@@ -14,11 +14,22 @@ class NetworkRenderStrategy(RenderStrategy):
            base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
        self.BASE_RENDER_URL = base_url
        self.TEMPLATE_PATH = os.path.join(os.path.dirname(__file__), "template")
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"

    def set_endpoint(self, base_url: str):
        if not base_url:
            base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
        self.BASE_RENDER_URL = base_url
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"
+

    async def render_custom_template(self, tmpl_str: str, tmpl_data: dict, return_url: bool=True) -> str:
        '''使用自定义文转图模板'''
--- a/astrbot/core/utils/t2i/renderer.py
+++ b/astrbot/core/utils/t2i/renderer.py
@@ -22,7 +22,7 @@ class HtmlRenderer:

        @return: 图片 URL 或者文件路径，取决于 return_url 参数。

-        @example: 参见 https://astrbot.soulter.top 插件开发部分。
+        @example: 参见 https://astrbot.app 插件开发部分。
        '''
        local = locals()
        local.pop('self')
--- a/astrbot/core/utils/tencent_record_helper.py
+++ b/astrbot/core/utils/tencent_record_helper.py
@@ -22,21 +22,27 @@ async def tencent_silk_to_wav(silk_path: str, output_path: str) -> str:

 async def wav_to_tencent_silk(wav_path: str, output_path: str) -> int:
    '''返回 duration'''
-    import pysilk
-
-    with wave.open(wav_path, 'rb') as wav:
-        wav_data = wav.readframes(wav.getnframes())
-        wav_data = BytesIO(wav_data)
-        output_io = BytesIO()
-        pysilk.encode(wav_data, output_io, 24000, 24000)
-        output_io.seek(0)
+    try:
+        import pilk
+    except (ImportError, ModuleNotFoundError) as _:
+        raise Exception("pilk 模块未安装，请前往管理面板->控制台->安装pip库 安装 pilk 这个库")
+    # with wave.open(wav_path, 'rb') as wav:
+    #     wav_data = wav.readframes(wav.getnframes())
+    #     wav_data = BytesIO(wav_data)
+    #     output_io = BytesIO()
+    #     pysilk.encode(wav_data, output_io, 24000, 24000)
+    #     output_io.seek(0)
        
-        # 在首字节添加 \x02,去除结尾的\xff\xff
-        silk_data = output_io.read()
-        silk_data_with_prefix = b'\x02' + silk_data[:-2]
+    #     # 在首字节添加 \x02,去除结尾的\xff\xff
+    #     silk_data = output_io.read()
+    #     silk_data_with_prefix = b'\x02' + silk_data[:-2]
        
-        # return BytesIO(silk_data_with_prefix)
-        with open(output_path, "wb") as f:
-            f.write(silk_data_with_prefix)
+    #     # return BytesIO(silk_data_with_prefix)
+    #     with open(output_path, "wb") as f:
+    #         f.write(silk_data_with_prefix)
            
-        return 0
+    #     return 0
+    with wave.open(wav_path, 'rb') as wav:
+        rate = wav.getframerate()
+        duration = pilk.encode(wav_path, output_path, pcm_rate=rate, tencent=True)
+        return duration
--- a/astrbot/core/zip_updator.py
+++ b/astrbot/core/zip_updator.py
@@ -39,7 +39,6 @@ class RepoZipUpdator():
            else:
                ret = self.github_api_release_parser(result)
        except BaseException:
-            logger.error("解析版本信息失败")
            raise Exception("解析版本信息失败")
        return ret
    
@@ -101,7 +100,7 @@ class RepoZipUpdator():
            body=update_data[0]['body']
        )
        
-    async def download_from_repo_url(self, target_path: str, repo_url: str):
+    async def download_from_repo_url(self, target_path: str, repo_url: str, proxy=""):
        repo_namespace = repo_url.split("/")[-2:]
        author = repo_namespace[0]
        repo = repo_namespace[1]
@@ -111,19 +110,23 @@ class RepoZipUpdator():
        releases = await self.fetch_release_info(url=release_url)
        if not releases:
            # download from the default branch directly. 
-            logger.info(f"未在仓库 {author}/{repo} 中找到任何发布版本，正在从默认分支下载。")
+            logger.info(f"正在从默认分支下载 {author}/{repo} ")
            release_url = f"https://github.com/{author}/{repo}/archive/refs/heads/master.zip"
        else:
            release_url = releases[0]['zipball_url']
            
        # 镜像站点
-        match self.repo_mirror:
-            case 'https://github-mirror.us.kg/':
-                release_url = self.repo_mirror + release_url
-            case "https://ghp.ci/":
-                release_url = self.repo_mirror + release_url
-            case _:
-                pass
+        # match self.repo_mirror:
+        #     case 'https://github-mirror.us.kg/':
+        #         release_url = self.repo_mirror + release_url
+        #     case "https://ghp.ci/":
+        #         release_url = self.repo_mirror + release_url
+        #     case _:
+        #         pass
+        
+        if proxy:
+            release_url = f"{proxy}/{release_url}"
+            logger.info(f"使用代理下载: {release_url}")

        await download_file(release_url, target_path + ".zip")
        
--- a/astrbot/dashboard/routes/chat.py
+++ b/astrbot/dashboard/routes/chat.py
@@ -121,7 +121,7 @@ class ChatRoute(Route):
        }))
        
        # 持久化
-        conversation = self.db.get_webchat_conversation_by_user_id(username, conversation_id)
+        conversation = self.db.get_conversation_by_user_id(username, conversation_id)
        try:
            history = json.loads(conversation.history)
        except BaseException as e:
@@ -136,7 +136,7 @@ class ChatRoute(Route):
        if audio_url:
            new_his['audio_url'] = audio_url
        history.append(new_his)
-        self.db.update_webchat_conversation(username, conversation_id, history=json.dumps(history))
+        self.db.update_conversation(username, conversation_id, history=json.dumps(history))
        
        return Response().ok().__dict__
        
@@ -168,7 +168,7 @@ class ChatRoute(Route):
                        continue
                    yield result_text + '\n'
                    
-                    conversation = self.db.get_webchat_conversation_by_user_id(username, cid)
+                    conversation = self.db.get_conversation_by_user_id(username, cid)
                    try:
                        history = json.loads(conversation.history)
                    except BaseException as e:
@@ -178,7 +178,7 @@ class ChatRoute(Route):
                        'type': 'bot',
                        'message': result_text
                    })
-                    self.db.update_webchat_conversation(username, cid, history=json.dumps(history))
+                    self.db.update_conversation(username, cid, history=json.dumps(history))
                    
                    await asyncio.sleep(0.5)
            except BaseException as e:
@@ -204,20 +204,20 @@ class ChatRoute(Route):
        if not conversation_id:
            return Response().error("Missing key: conversation_id").__dict__
        
-        self.db.delete_webchat_conversation(username, conversation_id)
+        self.db.delete_conversation(username, conversation_id)
        return Response().ok().__dict__
    
    async def new_conversation(self):
        username = g.get('username', 'guest')
        conversation_id = str(uuid.uuid4())
-        self.db.webchat_new_conversation(username, conversation_id)
+        self.db.new_conversation(username, conversation_id)
        return Response().ok(data={
            'conversation_id': conversation_id
        }).__dict__
        
    async def get_conversations(self):
        username = g.get('username', 'guest')
-        conversations = self.db.get_webchat_conversations(username)
+        conversations = self.db.get_conversations(username)
        return Response().ok(data=conversations).__dict__
    
    async def get_conversation(self):
@@ -226,7 +226,7 @@ class ChatRoute(Route):
        if not conversation_id:
            return Response().error("Missing key: conversation_id").__dict__
        
-        conversation = self.db.get_webchat_conversation_by_user_id(username, conversation_id)
+        conversation = self.db.get_conversation_by_user_id(username, conversation_id)
        
        self.curr_user_cid[username] = conversation_id
        
--- a/astrbot/dashboard/routes/config.py
+++ b/astrbot/dashboard/routes/config.py
@@ -1,14 +1,13 @@
-import os
-import json
-import traceback
+import typing
 from .route import Route, Response, RouteContext
 from quart import request
 from astrbot.core.config.default import CONFIG_METADATA_2, DEFAULT_VALUE_MAP
 from astrbot.core.config.astrbot_config import AstrBotConfig
-from astrbot.core.star.config import update_config
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.platform.register import platform_registry
 from astrbot.core.provider.register import provider_registry
+from astrbot.core.star.star import star_registry
+from astrbot.core import logger

 def try_cast(value: str, type_: str):
    if type_ == "int" and value.isdigit():
@@ -19,9 +18,9 @@ def try_cast(value: str, type_: str):
    elif type_ == "float" and isinstance(value, int):
        return float(value)

-def validate_config(data, config: AstrBotConfig):
+def validate_config(data, schema: dict, is_core: bool) -> typing.Tuple[typing.List[str], typing.Dict]:
    errors = []
-    def validate(data, metadata=CONFIG_METADATA_2, path=""):
+    def validate(data, metadata=schema, path=""):
        for key, meta in metadata.items():
            if key not in data:
                continue
@@ -56,35 +55,33 @@ def validate_config(data, config: AstrBotConfig):
            elif meta["type"] == "object" and not isinstance(value, dict):
                errors.append(f"错误的类型 {path}{key}: 期望是 dict, 得到了 {type(value).__name__}")
                validate(value, meta["items"], path=f"{path}{key}.")
-    validate(data)
-    
-    return errors

-def save_astrbot_config(post_config: dict, config: AstrBotConfig):
+    if is_core:
+        for key, group in schema.items():
+            group_meta = group.get("metadata")
+            if not group_meta:
+                continue
+            logger.info(f"验证配置: 组 {key} ...")
+            validate(data, group_meta, path=f"{key}.")
+    else:
+        validate(data, schema)
+    
+    return errors, data
+
+def save_config(post_config: dict, config: AstrBotConfig, is_core: bool = False):
    '''验证并保存配置'''
-    errors = validate_config(post_config, config)
+    errors = None
+    try:
+        if is_core:
+            errors, post_config = validate_config(post_config, CONFIG_METADATA_2, is_core)
+        else:
+            errors, post_config = validate_config(post_config, config.schema, is_core)
+    except BaseException as e:
+        logger.warning(f"验证配置时出现异常: {e}")
    if errors:
        raise ValueError(f"格式校验未通过: {errors}")
    config.save_config(post_config)
    
-def save_extension_config(post_config: dict):
-    if 'namespace' not in post_config:
-        raise ValueError("Missing key: namespace")
-    if 'config' not in post_config:
-        raise ValueError("Missing key: config")
-
-    namespace = post_config['namespace']
-    config: list = post_config['config'][0]['body']
-    for item in config:
-        key = item['path']
-        value = item['value']
-        typ = item['val_type']
-        if typ == 'int':
-            if not value.isdigit():
-                raise ValueError(f"错误的类型 {namespace}.{key}: 期望是 int, 得到了 {type(value).__name__}")
-            value = int(value)
-        update_config(namespace, key, value)
-
 class ConfigRoute(Route):
    def __init__(self, context: RouteContext, core_lifecycle: AstrBotCoreLifecycle) -> None:
        super().__init__(context)
@@ -92,17 +89,17 @@ class ConfigRoute(Route):
        self.routes = {
            '/config/get': ('GET', self.get_configs),
            '/config/astrbot/update': ('POST', self.post_astrbot_configs),
-            '/config/plugin/update': ('POST', self.post_extension_configs),
+            '/config/plugin/update': ('POST', self.post_plugin_configs),
        }
        self.register_routes()

    async def get_configs(self):
-        # namespace 为空时返回 AstrBot 配置
-        # 否则返回指定 namespace 的插件配置
-        namespace = "" if "namespace" not in request.args else request.args["namespace"]
-        if not namespace:
+        # plugin_name 为空时返回 AstrBot 配置
+        # 否则返回指定 plugin_name 的插件配置
+        plugin_name = request.args.get("plugin_name", None)
+        if not plugin_name:
            return Response().ok(await self._get_astrbot_config()).__dict__
-        return Response().ok(await self._get_extension_config(namespace)).__dict__
+        return Response().ok(await self._get_plugin_config(plugin_name)).__dict__

    async def post_astrbot_configs(self):
        post_configs = await request.json
@@ -110,14 +107,15 @@ class ConfigRoute(Route):
            await self._save_astrbot_configs(post_configs)
            return Response().ok(None, "保存成功~ 机器人正在重载配置。").__dict__
        except Exception as e:
-            traceback.print_exc()
+            logger.error(e)
            return Response().error(str(e)).__dict__
    
-    async def post_extension_configs(self):
+    async def post_plugin_configs(self):
        post_configs = await request.json
+        plugin_name = request.args.get("plugin_name", "unknown")
        try:
-            await self._save_extension_configs(post_configs)
-            return Response().ok(None, "保存成功~ 机器人正在重载配置。").__dict__
+            await self._save_plugin_configs(post_configs, plugin_name)
+            return Response().ok(None, f"保存插件 {plugin_name} 成功~ 机器人正在重载配置。").__dict__
        except Exception as e:
            return Response().error(str(e)).__dict__
            
@@ -141,28 +139,48 @@ class ConfigRoute(Route):
            "config": config
        }

-    async def _get_extension_config(self, namespace: str):
-        path = f"data/config/{namespace}.json"
-        if not os.path.exists(path):
-            return []
-        with open(path, "r", encoding="utf-8-sig") as f:
-            return [{
-                "config_type": "group",
-                "name": namespace + " 插件配置",
-                "description": "",
-                "body": list(json.load(f).values())
-            },]
-
+    async def _get_plugin_config(self, plugin_name: str):
+        ret = {
+            "metadata": None,
+            "config": None
+        }
+        
+        for plugin_md in star_registry:
+            if plugin_md.name == plugin_name:
+                if not plugin_md.config:
+                    break
+                ret['config'] = plugin_md.config # 这是自定义的 Dict 类（AstrBotConfig）
+                ret['metadata'] = {
+                    plugin_name: {
+                        "description": f"{plugin_name} 配置",
+                        "type": "object",
+                        "items": plugin_md.config.schema # 初始化时通过 __setattr__ 存入了 schema
+                    }
+                }
+                break
+            
+        return ret
+        
    async def _save_astrbot_configs(self, post_configs: dict):
        try:
-            save_astrbot_config(post_configs, self.config)
+            save_config(post_configs, self.config, is_core=True)
            self.core_lifecycle.restart()
        except Exception as e:
            raise e
-    
-    async def _save_extension_configs(self, post_configs: dict):
+        
+    async def _save_plugin_configs(self, post_configs: dict, plugin_name: str):
+        md = None
+        for plugin_md in star_registry:
+            if plugin_md.name == plugin_name:
+                md = plugin_md
+        
+        if not md:
+            raise ValueError(f"插件 {plugin_name} 不存在")
+        if not md.config:
+            raise ValueError(f"插件 {plugin_name} 没有注册配置")
+        
        try:
-            save_extension_config(post_configs)
+            save_config(post_configs, md.config)
            self.core_lifecycle.restart()
        except Exception as e:
            raise e
--- a/astrbot/dashboard/routes/plugin.py
+++ b/astrbot/dashboard/routes/plugin.py
@@ -1,11 +1,16 @@
 import traceback
 import aiohttp
-import uuid
 from .route import Route, Response, RouteContext
 from astrbot.core import logger
 from quart import request
 from astrbot.core.star.star_manager import PluginManager
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
+from astrbot.core.star.star_handler import star_handlers_registry
+from astrbot.core.star.filter.command import CommandFilter
+from astrbot.core.star.filter.command_group import CommandGroupFilter
+from astrbot.core.star.filter.permission import PermissionTypeFilter
+from astrbot.core.star.filter.regex import RegexFilter
+from astrbot.core.star.star_handler import EventType

 class PluginRoute(Route):
    def __init__(self, context: RouteContext, core_lifecycle: AstrBotCoreLifecycle, plugin_manager: PluginManager) -> None:
@@ -18,22 +23,57 @@ class PluginRoute(Route):
            '/plugin/uninstall': ('POST', self.uninstall_plugin),
            '/plugin/market_list': ('GET', self.get_online_plugins),
            '/plugin/off': ('POST', self.off_plugin),
-            '/plugin/on': ('POST', self.on_plugin)
+            '/plugin/on': ('POST', self.on_plugin),
+            '/plugin/reload': ('POST', self.reload_plugins),
        }
        self.core_lifecycle = core_lifecycle
        self.plugin_manager = plugin_manager
        self.register_routes()
+        
+        self.translated_event_type = {
+            EventType.AdapterMessageEvent: "平台消息下发时",
+            EventType.OnLLMRequestEvent: "LLM 请求时",
+            EventType.OnLLMResponseEvent: "LLM 响应后",
+            EventType.OnDecoratingResultEvent: "回复消息前",
+            EventType.OnCallingFuncToolEvent: "函数工具",
+            EventType.OnAfterMessageSentEvent: "发送消息后"
+        }
+        
+    async def reload_plugins(self):
+        data = await request.json
+        plugin_name = data.get("name", None)
+        try:
+            success, message = await self.plugin_manager.reload(plugin_name)
+            if not success:
+                return Response().error(message).__dict__
+            return Response().ok(None, "重载成功。").__dict__
+        except Exception as e:
+            logger.error(f"/api/plugin/reload: {traceback.format_exc()}")
+            return Response().error(str(e)).__dict__
    
    async def get_online_plugins(self):
-        url = "https://soulter.github.io/AstrBot_Plugins_Collection/plugins.json"
-        try:
-            async with aiohttp.ClientSession(trust_env=True) as session:
-                async with session.get(url) as response:
-                    result = await response.json()
-            return Response().ok(result).__dict__
-        except Exception as e:
-            logger.error(f"获取插件列表失败：{e}")
-            return Response().error(str(e)).__dict__
+        custom = request.args.get("custom_registry")
+        
+        if custom:
+            urls = [custom]
+        else:
+            urls = [
+                "https://api.soulter.top/astrbot/plugins"
+            ]
+            
+        for url in urls:
+            try:
+                async with aiohttp.ClientSession(trust_env=True) as session:
+                    async with session.get(url) as response:
+                        if response.status == 200:
+                            result = await response.json()
+                            return Response().ok(result).__dict__
+                        else:
+                            logger.error(f"请求 {url} 失败，状态码：{response.status}")
+            except Exception as e:
+                logger.error(f"请求 {url} 失败，错误：{e}")
+        
+        return Response().error("获取插件列表失败").__dict__
    
    async def get_plugins(self):
        _plugin_resp = []
@@ -45,17 +85,78 @@ class PluginRoute(Route):
                "desc": plugin.desc,
                "version": plugin.version,
                "reserved": plugin.reserved,
-                "activated": plugin.activated
+                "activated": plugin.activated,
+                "online_vesion": "",
+                "handlers": await self.get_plugin_handlers_info(plugin.star_handler_full_names),
            }
            _plugin_resp.append(_t)
-        return Response().ok(_plugin_resp).__dict__
+        return Response().ok(_plugin_resp, message=self.plugin_manager.failed_plugin_info).__dict__
+    
+    async def get_plugin_handlers_info(self, handler_full_names: list[str]):
+        '''解析插件行为'''
+        handlers = []
+        
+        for handler_full_name in handler_full_names:
+            info = {}
+            handler = star_handlers_registry.star_handlers_map.get(handler_full_name, None)
+            if handler is None:
+                continue
+            info["event_type"] = handler.event_type.name
+            info["event_type_h"] = self.translated_event_type.get(handler.event_type, handler.event_type.name)
+            info["handler_full_name"] = handler.handler_full_name
+            info["desc"] = handler.desc
+            info["handler_name"] = handler.handler_name
+            
+            if handler.event_type == EventType.AdapterMessageEvent:
+                # 处理平台适配器消息事件
+                has_admin = False
+                for filter in handler.event_filters: # 正常handler就只有 1~2 个 filter，因此这里时间复杂度不会太高
+                    if isinstance(filter, CommandFilter):
+                        info["type"] = "指令"
+                        info["cmd"] = f"{filter.parent_command_names[0]} {filter.command_name}"
+                        info["cmd"] = info["cmd"].strip()
+                        if self.core_lifecycle.astrbot_config['wake_prefix'] and len(self.core_lifecycle.astrbot_config['wake_prefix']) > 0:
+                            info["cmd"] = f"{self.core_lifecycle.astrbot_config['wake_prefix'][0]}{info['cmd']}"
+                    elif isinstance(filter, CommandGroupFilter):
+                        info["type"] = "指令组"
+                        info["cmd"] = filter.get_complete_command_names()[0]
+                        info["cmd"] = info["cmd"].strip()
+                        info["sub_command"] = filter.print_cmd_tree(filter.sub_command_filters)
+                        if self.core_lifecycle.astrbot_config['wake_prefix'] and len(self.core_lifecycle.astrbot_config['wake_prefix']) > 0:
+                            info["cmd"] = f"{self.core_lifecycle.astrbot_config['wake_prefix'][0]}{info['cmd']}"
+                    elif isinstance(filter, RegexFilter):
+                        info["type"] = "正则匹配"
+                        info["cmd"] = filter.regex_str
+                    elif isinstance(filter, PermissionTypeFilter):
+                        has_admin = True
+                info["has_admin"] = has_admin
+                if "cmd" not in info:
+                    info["cmd"] = "未知"
+                if "type" not in info:
+                    info["type"] = "事件监听器"
+            else:
+                info["cmd"] = "自动触发"
+                info["type"] = "无"
+                
+            if not info["desc"]:
+                info["desc"] = "无描述"
+                
+            handlers.append(info)
+                    
+        return handlers
        
    async def install_plugin(self):
        post_data = await request.json
        repo_url = post_data["url"]
+        
+        proxy: str = post_data.get("proxy", None)
+        if proxy:
+            proxy = proxy.removesuffix("/")
+        
        try:
            logger.info(f"正在安装插件 {repo_url}")
-            await self.plugin_manager.install_plugin(repo_url)
+            await self.plugin_manager.install_plugin(repo_url, proxy)
+            self.core_lifecycle.restart()
            logger.info(f"安装插件 {repo_url} 成功。")
            return Response().ok(None, "安装成功。").__dict__
        except Exception as e:
@@ -67,9 +168,10 @@ class PluginRoute(Route):
            file = await request.files
            file = file['file']
            logger.info(f"正在安装用户上传的插件 {file.filename}")
-            file_path = f"data/temp/{uuid.uuid4()}.zip"
+            file_path = f"data/temp/{file.filename}"
            await file.save(file_path)
-            self.plugin_manager.install_plugin_from_file(file_path)
+            await self.plugin_manager.install_plugin_from_file(file_path)
+            self.core_lifecycle.restart()
            logger.info(f"安装插件 {file.filename} 成功")
            return Response().ok(None, "安装成功。").__dict__
        except Exception as e:
@@ -91,13 +193,15 @@ class PluginRoute(Route):
    async def update_plugin(self):
        post_data = await request.json
        plugin_name = post_data["name"]
+        proxy: str = post_data.get("proxy", None)
        try:
            logger.info(f"正在更新插件 {plugin_name}")
-            await self.plugin_manager.update_plugin(plugin_name)
+            await self.plugin_manager.update_plugin(plugin_name, proxy)
+            self.core_lifecycle.restart()
            logger.info(f"更新插件 {plugin_name} 成功。")
            return Response().ok(None, "更新成功。").__dict__
        except Exception as e:
-            logger.error(f"/api/extensions/update: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/update: {traceback.format_exc()}")
            return Response().error(str(e)).__dict__
        
    async def off_plugin(self):
@@ -108,7 +212,7 @@ class PluginRoute(Route):
            logger.info(f"停用插件 {plugin_name} 。")
            return Response().ok(None, "停用成功。").__dict__
        except Exception as e:
-            logger.error(f"/api/extensions/off: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/off: {traceback.format_exc()}")
            return Response().error(str(e)).__dict__

    async def on_plugin(self):
@@ -119,5 +223,5 @@ class PluginRoute(Route):
            logger.info(f"启用插件 {plugin_name} 。")
            return Response().ok(None, "启用成功。").__dict__
        except Exception as e:
-            logger.error(f"/api/extensions/on: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/on: {traceback.format_exc()}")
            return Response().error(str(e)).__dict__
--- a/astrbot/dashboard/routes/static_file.py
+++ b/astrbot/dashboard/routes/static_file.py
@@ -6,6 +6,10 @@ class StaticFileRoute(Route):
        index_ = ['/', '/auth/login', '/config', '/logs', '/extension', '/dashboard/default', '/project-atri', '/console', '/chat']
        for i in index_:
            self.app.add_url_rule(i, view_func=self.index)
+            
+        @self.app.errorhandler(404)
+        async def page_not_found(e):
+            return "404 Not found。如果你初次使用打开面板发现 404，请参考文档: https://astrbot.app/deploy/dashboard-404.html"
    
    async def index(self):
        return await self.app.send_static_file('index.html')
--- a/astrbot/dashboard/routes/update.py
+++ b/astrbot/dashboard/routes/update.py
@@ -1,4 +1,5 @@
 import traceback
+import aiohttp
 from .route import Route, Response, RouteContext
 from quart import request
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
@@ -43,7 +44,7 @@ class UpdateRoute(Route):
                    }
                ).__dict__
        except Exception as e:
-            logger.error(traceback.format_exc())
+            logger.warning(f"检查更新失败: {str(e)} (不影响除项目更新外的正常使用)")
            return Response().error(e.__str__()).__dict__
    
    async def update_project(self):
--- a/astrbot/dashboard/server.py
+++ b/astrbot/dashboard/server.py
@@ -2,6 +2,7 @@ import logging
 import jwt
 import asyncio
 import os
+from astrbot.core.config.default import VERSION
 from quart import Quart, request, jsonify, g
 from quart.logging import default_handler
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
@@ -67,15 +68,21 @@ class AstrBotDashboard():
        logger.info("管理面板已关闭。")
        
    def run(self):
-        ip_addr = get_local_ip_addresses()
-        logger.info(f"""
-✨✨✨
-AstrBot 管理面板已启动，可访问
+        try:
+            ip_addr = get_local_ip_addresses()
+        except Exception as e:
+            ip_addr = []
+            
+        port = self.core_lifecycle.astrbot_config['dashboard'].get("port", 6185)
+        if isinstance(port, str):
+            port = int(port)
+    
+        display = f"\n ✨✨✨\n  AstrBot v{VERSION} 管理面板已启动，可访问\n\n"
+        display += f"   ➜  本地: http://localhost:{port}\n"
+        for ip in ip_addr:
+            display += f"   ➜  网络: http://{ip}:{port}\n"
+        display += "   ➜  默认用户名和密码: astrbot\n ✨✨✨\n"
+        logger.info(display)
+        

-1. http://{ip_addr}:6185
-2. http://localhost:6185
-
-默认用户名和密码是 astrbot。
-✨✨✨
-""")
-        return self.app.run_task(host="0.0.0.0", port=6185, shutdown_trigger=self.shutdown_trigger_placeholder)
+        return self.app.run_task(host="0.0.0.0", port=port, shutdown_trigger=self.shutdown_trigger_placeholder)
--- a/changelogs/v3.4.14.md
+++ b/changelogs/v3.4.14.md
@@ -0,0 +1,8 @@
+# What's Changed
+
+- 修复: TTS 问题
+- 新增: **支持记录非唤醒状态下群聊历史记录(beta)**
+- 优化: 自动删除 deepseek-r1 模型自带的 think 标签
+- 优化: 自动移除 ollama 不支持 tool 的模型的 tool 请求
+- 优化: /t2i 即时生效
+- 优化: gewechat 消息下发异常处理
--- a/changelogs/v3.4.15.md
+++ b/changelogs/v3.4.15.md
@@ -0,0 +1,9 @@
+# What's Changed
+
+- 修复: 配置 Validator 不起效的问题
+- 修复: DeepSeek-R1 思考标签问题
+- 修复: 分段回复间隔时间不生效
+- 修复: 修复白名单为空时依然终止事件 #259
+- 修复: 群聊增强某些参数的类型转换问题
+- 新增: 插件支持注册配置，详见 [注册插件配置](https://astrbot.app/dev/plugin.html#%E6%B3%A8%E5%86%8C%E6%8F%92%E4%BB%B6%E9%85%8D%E7%BD%AE-beta)
+- 优化: 插件的禁用/启用逻辑以及函数工具的禁用/启用逻辑
--- a/changelogs/v3.4.16.md
+++ b/changelogs/v3.4.16.md
@@ -0,0 +1,6 @@
+# What's Changed
+
+- [gewechat] [修复每次启动astrbot都需要扫码的问题](https://github.com/Soulter/AstrBot/commit/fd5d7dd37a6d74f81a148bbebef8516aa0cb5540)
+- [core] [Provider 重复时不直接报错闪退](https://github.com/Soulter/AstrBot/commit/b61f9be18db9a6b8b3c5b6b36553f66dd2b79375) https://github.com/Soulter/AstrBot/issues/265
+- [core] [弱化更新报错](https://github.com/Soulter/AstrBot/commit/0ba0150fd8ff2062dbe83889163888ba3e33bd49) https://github.com/Soulter/AstrBot/issues/267 
+- 修复 webui 无法从本地上传插件的问题
--- a/changelogs/v3.4.17.md
+++ b/changelogs/v3.4.17.md
@@ -0,0 +1,11 @@
+# What's Changed
+
+- [beta] 支持群聊内基于概率的主动回复
+- openai tts 更换模型 #300
+- 增加模型响应后的插件钩子
+- 修复 相同type的provider共享了记忆
+- 优化 人格情景在发现格式不对时仍然加载而不是跳过 #282
+- 修复 Gemini函数调用时，parameters为空对象导致的错误 by @Camreishi
+- 修复 弹出记录报错的问题 #272
+- 优化 移除默认人格
+- 优化 未启用模型提供商时的异常处理
--- a/changelogs/v3.4.18.md
+++ b/changelogs/v3.4.18.md
@@ -0,0 +1,12 @@
+# What's Changed
+
+- fix: 修复主动概率回复关闭后仍然回复的问题 #317
+- fix: 尝试修复 gewechat 群聊收不到 at 的回复 #294
+- perf: 移除了默认人格
+- fix: 修复HTTP代理删除后不生效 #319
+- fix: 调用Gemini API输出多余空行问题 #318
+- feat: 添加硅基流动模版
+- fix: 硅基流动 not a vlm 和 tool calling not supported 报错 #305 #291
+- perf: 回复时艾特发送者之后添加空格或换行 #312
+- fix: docker容器内时区不对导致 reminder 时间错误
+- perf: siliconcloud 不支持 tool 的模型
--- a/changelogs/v3.4.19.md
+++ b/changelogs/v3.4.19.md
@@ -0,0 +1,13 @@
+# What's Changed
+
+1. 支持接入企业微信（测试）
+2. 修复速率限制不可用的问题
+3. gewechat 回调接口默认暴露在所有 IP
+4. 适配 Azure OpenAI
+5. 修复请求 gemini 出现 KeyError 'candidates' 的错误
+6. 将 /reset /persona 挪入管理员指令 #308
+7. 支持通过 /alter_cmd 设置所有指令是否只能管理员操作
+8. /plugin 指令支持查看插件注册的指令和指令组
+9. 插件注册指令支持传入指令的描述以方便 /plugin 查看。需要写在函数的第一行的 docstring 中。
+10. 修复 schema 中 object hint 不显示 #290
+11. feat: 优化插件市场的访问速度
--- a/changelogs/v3.4.20.md
+++ b/changelogs/v3.4.20.md
@@ -0,0 +1,15 @@
+# What's Changed
+
+> 由于重写了会话记录部分，更新此版本后，将会造成之前的对话记录清空（但没有被删除）。
+> 关于更好的对话管理，如果有任何报错或者优化建议，请直接提交 issue~
+
+1. 更好的对话管理，支持 /ls, /del, /new, /switch, /rename 指令来操作对话。
+2. 人格情境跟随对话。每个对话支持独立设置人格情境，只需要 /persona 指令切换即可。
+3. 支持使用 LLM 辅助分段回复 #338
+4. 优化 aiocqhttp 适配器对用户非法输入的处理
+5. 优化插件页面
+6. 修复权限过滤算子导致的问题 #350
+7. 修复级联指令组时出现载入错误的问题 #366
+8. 修复代码执行器的一个typo by @eltociear
+9. 修复指令组情况下可能造成多指令出触发的问题
+10. 添加屏蔽无权限指令回复的功能 #361
--- a/changelogs/v3.4.21.md
+++ b/changelogs/v3.4.21.md
@@ -0,0 +1,19 @@
+# What's Changed
+
+> 由于重写了会话记录部分，更新此版本后，将会造成之前的对话记录清空（但没有被删除）。
+> 关于更好的对话管理，如果有任何报错或者优化建议，请直接提交 issue~
+
+1. 修复 reminder 时区问题
+2. 面板支持重载单个插件 #297
+3. 面板支持列表展示插件市场
+4. 文字转图片支持自定义字数阈值(配置->其他配置)
+5. 面板更好的列表可视化 #274
+6. 面板支持查看插件行为
+7. 支持设置 timeout 超时时间参数，防止思考模型太长达到超时时间。(需要重新配置服务提供商或者在服务提供商 config 中配置 timeout 参数) #378
+8. openrouter 报错 no endpoints found that support tool use #371
+9. 修复插件 metadata 不生效的问题
+10. 修复不支持图片的模型请求异常
+11. 修复 reminder 无法删除的问题 
+12. 修复 /model 切换不了模型的问题
+13. 插件支持设置优先级 
+14. 聊天增强图像转述支持自定义 provider id。#274
--- a/changelogs/v3.4.22.md
+++ b/changelogs/v3.4.22.md
@@ -0,0 +1,12 @@
+# What's Changed
+
+1. fix: 400 Bad Request: The browser (or proxy) sent a request that this server could not understand. #396
+2. remove: 移除了 put_history_to_prompt。当主动回复时，将群聊记录将自动放入prompt，当未主动回复但是开启群聊增强时，群聊记录将放入system prompt
+3. fix: 插件错误信息点击关闭没反应 #394
+4. fix: 自部署文转图不生效 #352
+5. fix: Google Search 报 429 错误时，放宽 Exception 至其他搜索引擎 #405
+6. fix: 使用 Google Gemini （OpenAI 兼容）的部分情况下联网搜索等函数调用工具没被调用 #342
+7. fix: 修复尝试弹出最早的记录失效的问题
+8. fix: 移除了分段回复llm提示词辅助
+9. perf: 当图片数据为空时不加入上下文 #379
+10. 修复 dify 返回的结果带有多行数据时的 json 解析异常导致返回值为空的问题 #298 by @zhaolj
--- a/changelogs/v3.4.23.md
+++ b/changelogs/v3.4.23.md
@@ -0,0 +1,11 @@
+# What's Changed
+
+0. ✨ 新增: 支持 海豚 AI（FishAudio） TTS API #433 by @Cvandia
+1. 🐛 修复: 当群聊主动回复时，不会带上人格的Prompt #419
+2. ✨ 新增: 支持展示插件是否有更新
+3. 👌 优化: 增加DIFY超时时间 #422
+4. 🐛 修复: 自部署文转图不生效 #352
+5. 🐛 修复: 修复 qq 回复别人的时候也会触发机器人, Onebot at 使用 string #330
+6. 👌 优化: 增加DIFY超时时间 #422
+7. 🐛 修复: 重启gewe的时候机器人会疯狂发消息 #421
+8. 🐛 修复: 修复子指令设置permission之后会导致其一定会被执行 #427
--- a/changelogs/v3.4.24.md
+++ b/changelogs/v3.4.24.md
@@ -0,0 +1,11 @@
+# What's Changed
+
+0. ✨ 新增: 支持正则表达式匹配触发机器人，机器人在某一段时间内持续唤醒（不用输唤醒词）。（安装 astrbot_plugin_wake_enhance 插件）
+2. ✨ 新增: 可以通过 /tts 开关TTS，通过 /provider 更换 TTS #436
+3. ✨ 新增: 管理面板支持设置 GitHub 反向代理地址以优化中国大陆地区下载 AstrBot 插件的速度。（在管理面板-设置页）
+4. 🐛 修复: 修复指令不经过唤醒前缀也能生效的问题。在引用消息的时候无法使用前缀唤醒机器人 #444
+5. 🐛 修复: 修复 Napcat 下戳一戳消息报错
+6. 👌 优化: 从压缩包上传插件时，去除仓库 -branch 尾缀
+7. 🐛 修复: gemini 报错时显示 apikey
+8. 🐛 修复: drun 不支持函数调用的报错
+9. 🐛 修复: raw_completion 没有正确传递导致部分插件无法正常运作 #439
--- a/changelogs/v3.4.25.md
+++ b/changelogs/v3.4.25.md
@@ -0,0 +1,9 @@
+# What's Changed
+
+1. ✨ 新增: 支持接入飞书（Lark）。支持飞书文字、图片。
+2. ✨ 新增: 添加月之暗面配置模板 #446
+3. ✨ 新增: Gewechat 支持文件输出
+4. 🐛 修复: 修复gewechat无法at人和发语音失败的问题 #447 #438
+5. 🐛 修复: 修复qq在@和回复开启的情况下转发消息异常的问题
+6. 🐛 修复: GitHub 加速镜像没有正确被应用
+7. 🐛 优化: 平台将显示不受支持的消息段
--- a/changelogs/v3.4.26.md
+++ b/changelogs/v3.4.26.md
@@ -0,0 +1,12 @@
+# What's Changed
+
+1. ✨ 新增: 支持 Webhook 方式接入 QQ 官方机器人接口
+2. ✨ 新增: 支持完善的 Dify Chat 模式对话管理，包括 /new /switch /del /ls /reset 均已适配 Dify Chat 模式。
+3. ✨ 新增: 支持基于对数函数的分段回复延时时间计算 #414
+4. ✨ 新增: 支持设置管理面板的端口号
+5. ✨ 新增: 支持对大模型的响应进行内容审查 #474
+6. 🐛 修复: gewechat 不能发送主动消息 #402
+7. 🐛 修复: dify Chat 模式无法重置会话 #469
+8. 🐛 修复: ensure result is retrieved again to handle potential plugin chain replacements
+9. 🐛 优化: 将 Gewechat 所有事件下发到流水线供插件开发
+10. 🐛 修复: correct dashboard update tooltip typo by @Akuma-real
--- a/Show More
+++ b/Show More