v3.4.33

fix: 不记忆历史的会话 #630
Merge pull request #648 from Soulter/feat-edge-tts
2025-02-28 22:13:08 +08:00 · 2025-02-28 22:00:49 +08:00 · 2025-02-28 21:46:50 +08:00 · 2025-02-28 21:33:03 +08:00 · 2025-02-28 21:24:54 +08:00 · 2025-02-28 21:12:37 +08:00
37 changed files with 1328 additions and 121 deletions
@@ -25,5 +25,4 @@ package.json
 venv/*
 packages/python_interpreter/workplace
 .venv/*
-
-.conda/
+.conda/
@@ -629,8 +629,8 @@ to attach them to the start of each source file to most effectively
 state the exclusion of warranty; and each file should have at least
 the "copyright" line and a pointer to where the full notice is found.

-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
+    AstrBot is a llm-powered chatbot and develop framework.
+    Copyright (C) 2022-2099 Soulter

    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU Affero General Public License as published
@@ -18,6 +18,7 @@ _✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
 ![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://github.com/Soulter/AstrBot/blob/master/README_en.md">English</a> ｜
 <a href="https://github.com/Soulter/AstrBot/blob/master/README_ja.md">日本語</a> ｜
 <a href="https://astrbot.app/">查看文档</a> ｜
 <a href="https://github.com/Soulter/AstrBot/issues">问题提交</a>
@@ -0,0 +1,164 @@
+<p align="center">
+    
+![6e1279651f16d7fdf4727558b72bbaf1](https://github.com/user-attachments/assets/ead4c551-fc3c-48f7-a6f7-afbfdb820512)
+
+</p>
+
+<div align="center">
+
+_✨ Easy-to-use Multi-platform LLM Chatbot & Development Framework ✨_
+
+<a href="https://trendshift.io/repositories/12875" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12875" alt="Soulter%2FAstrBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
+<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/">Documentation</a> ｜
+<a href="https://github.com/Soulter/AstrBot/issues">Issue Tracking</a>
+</div>
+
+AstrBot is a loosely coupled, asynchronous chatbot and development framework that supports multi-platform deployment, featuring an easy-to-use plugin system and comprehensive Large Language Model (LLM) integration capabilities.
+
+## ✨ Key Features
+
+1. **LLM Conversations** - Supports various LLMs including OpenAI API, Google Gemini, Llama, Deepseek, ChatGLM, etc. Enables local model deployment via Ollama/LLMTuner. Features multi-turn dialogues, personality contexts, multimodal capabilities (image understanding), and speech-to-text (Whisper).
+2. **Multi-platform Integration** - Supports QQ (OneBot), QQ Channels, WeChat (Gewechat), Feishu, and Telegram. Planned support for DingTalk, Discord, WhatsApp, and Xiaomi Smart Speakers. Includes rate limiting, whitelisting, keyword filtering, and Baidu content moderation.
+3. **Agent Capabilities** - Native support for code execution, natural language TODO lists, web search. Integrates with [Dify Platform](https://astrbot.app/others/dify.html) for easy access to Dify assistants/knowledge bases/workflows.
+4. **Plugin System** - Optimized plugin mechanism with minimal development effort. Supports multiple installed plugins.
+5. **Web Dashboard** - Visual configuration management, plugin controls, logging, and WebChat interface for direct LLM interaction.
+6. **High Stability & Modularity** - Event bus and pipeline architecture ensures high modularization and loose coupling.
+
+> [!TIP]
+> Dashboard Demo: [https://demo.astrbot.app/](https://demo.astrbot.app/)  
+> Username: `astrbot`, Password: `astrbot` (LLM not configured for chat page)
+
+## ✨ Deployment
+
+#### Docker Deployment
+
+See docs: [Deploy with Docker](https://astrbot.app/deploy/astrbot/docker.html#docker-deployment)
+
+#### Windows Installer
+
+Requires Python (>3.10). See docs: [Windows Installer Guide](https://astrbot.app/deploy/astrbot/windows.html)
+
+#### Replit Deployment
+
+[![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
+
+#### CasaOS Deployment
+
+Community-contributed method.  
+See docs: [CasaOS Deployment](https://astrbot.app/deploy/astrbot/casaos.html)
+
+#### Manual Deployment
+
+See docs: [Source Code Deployment](https://astrbot.app/deploy/astrbot/cli.html)
+
+## ⚡ Platform Support
+
+| Platform                                                       | Status | Details             | Message Types       |
+| -------------------------------------------------------------- | ------ | ------------------- | ------------------- |
+| QQ (Official Bot)                                              | ✔      | Private/Group chats | Text, Images        |
+| QQ (OneBot)                                                    | ✔      | Private/Group chats | Text, Images, Voice |
+| WeChat (Personal)                                              | ✔      | Private/Group chats | Text, Images, Voice |
+| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram) | ✔      | Private/Group chats | Text, Images        |
+| [WeChat Work](https://github.com/Soulter/astrbot_plugin_wecom) | ✔      | Private chats       | Text, Images, Voice |
+| Feishu                                                         | ✔      | Group chats         | Text, Images        |
+| WeChat Open Platform                                           | 🚧      | Planned             | -                   |
+| Discord                                                        | 🚧      | Planned             | -                   |
+| WhatsApp                                                       | 🚧      | Planned             | -                   |
+| Xiaomi Speakers                                                | 🚧      | Planned             | -                   |
+
+# 🦌 Roadmap
+
+> [!TIP]
+> Suggestions welcome via Issues <3
+
+- [ ] Ensure feature parity across all platform adapters
+- [ ] Optimize plugin APIs
+- [ ] Add default TTS services (e.g., GPT-Sovits)
+- [ ] Enhance chat features with persistent memory
+- [ ] i18n Planning
+
+## ❤️ Contributions
+
+All Issues/PRs welcome! Simply submit your changes to this project :)
+
+For major features, please discuss via Issues first.
+
+## 🌟 Support
+
+- Star this project!
+- Support via [Afdian](https://afdian.com/a/soulter)
+- WeChat support: [QR Code](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)
+
+## ✨ Demos
+
+> [!NOTE]
+> Code executor file I/O currently tested with Napcat(QQ)/Lagrange(QQ)
+
+<div align='center'>
+
+<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
+
+_✨ Docker-based Sandboxed Code Executor (Beta) ✨_
+
+<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
+
+_✨ Multimodal Input, Web Search, Text-to-Image ✨_
+
+<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
+
+_✨ Natural Language TODO Lists ✨_
+
+<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>
+
+_✨ Plugin System Showcase ✨_
+
+<img src="https://github.com/user-attachments/assets/592a8630-14c7-4e06-b496-9c0386e4f36c" width=600>
+
+_✨ Web Dashboard ✨_
+
+![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
+
+_✨ Built-in Web Chat Interface ✨_
+
+</div>
+
+## ⭐ Star History
+
+> [!TIP] 
+> If this project helps you, please give it a star <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. Licensed under `AGPL-v3`.
+2. WeChat integration uses [Gewechat](https://github.com/Devo919/Gewechat). Use at your own risk with non-critical accounts.
+3. Users must comply with local laws and regulations.
+
+<!-- ## ✨ ATRI [Beta]
+
+Available as plugin: [astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
+
+1. Qwen1.5-7B-Chat Lora model fine-tuned with ATRI character data
+2. Long-term memory
+3. Meme understanding & responses
+4. TTS integration
+    -->
+
+
+_私は、高性能ですから!_
+
@@ -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 = "3.4.31"
+VERSION = "3.4.33"
 DB_PATH = "data/data_v3.db"

 # 默认配置
@@ -16,7 +16,7 @@ DEFAULT_CONFIG = {
            "strategy": "stall",  # stall, discard
        },
        "reply_prefix": "",
-        "forward_threshold": 200,
+        "forward_threshold": 1500,
        "enable_id_white_list": True,
        "id_whitelist": [],
        "id_whitelist_log": True,
@@ -67,17 +67,15 @@ DEFAULT_CONFIG = {
            "method": "possibility_reply",
            "possibility_reply": 0.1,
            "prompt": "",
-            "whitelist": []
-        }
+            "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": [
-        "astrbot"
-    ],
+    "admins_id": ["astrbot"],
    "t2i": False,
    "t2i_word_threshold": 150,
    "http_proxy": "",
@@ -85,7 +83,7 @@ DEFAULT_CONFIG = {
        "enable": True,
        "username": "astrbot",
        "password": "77b90590a8945a7d36c963981a307dc9",
-        "port": 6185
+        "port": 6185,
    },
    "platform": [],
    "wake_prefix": ["/"],
@@ -122,9 +120,9 @@ CONFIG_METADATA_2 = {
                        "enable": False,
                        "appid": "",
                        "secret": "",
-                        "port": 6196
+                        "port": 6196,
                    },
-                    "aiocqhtp(QQ)": {
+                    "aiocqhttp(OneBotv11)": {
                        "id": "default",
                        "type": "aiocqhttp",
                        "enable": False,
@@ -140,6 +138,14 @@ CONFIG_METADATA_2 = {
                        "host": "这里填写你的局域网IP或者公网服务器IP",
                        "port": 11451,
                    },
+                    "wecom(企业微信)": {
+                        "corpid": "",
+                        "secret": "",
+                        "port": 6195,
+                        "token": "",
+                        "encoding_aes_key": "",
+                        "api_base_url": "https://qyapi.weixin.qq.com/cgi-bin/",
+                    },
                    "lark(飞书)": {
                        "id": "lark",
                        "type": "lark",
@@ -147,10 +153,23 @@ CONFIG_METADATA_2 = {
                        "lark_bot_name": "",
                        "app_id": "",
                        "app_secret": "",
-                        "domain": "https://open.feishu.cn"
+                        "domain": "https://open.feishu.cn",
+                    },
+                    "telegram": {
+                        "id": "telegram",
+                        "type": "telegram",
+                        "enable": False,
+                        "telegram_token": "your_bot_token",
+                        "start_message": "Hello, I'm AstrBot!",
+                        "telegram_api_base_url": "https://api.telegram.org/bot",
                    },
                },
                "items": {
+                    "telegram_token": {
+                        "description": "Bot Token",
+                        "type": "string",
+                        "hint": "如果你的网络环境为中国大陆，请在 `其他配置` 处设置代理或更改 api_base。",
+                    },
                    "id": {
                        "description": "ID",
                        "type": "string",
@@ -201,8 +220,8 @@ CONFIG_METADATA_2 = {
                        "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
-                    }
+                        "obvious_hint": True,
+                    },
                },
            },
            "platform_settings": {
@@ -250,7 +269,7 @@ CONFIG_METADATA_2 = {
                                "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。",
+                                "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)",
@@ -387,7 +406,7 @@ CONFIG_METADATA_2 = {
                "description": "服务提供商配置",
                "type": "list",
                "config_template": {
-                    "openai": {
+                    "OpenAI": {
                        "id": "openai",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -398,7 +417,7 @@ CONFIG_METADATA_2 = {
                            "model": "gpt-4o-mini",
                        },
                    },
-                    "azure_openai": {
+                    "Azure_OpenAI": {
                        "id": "azure",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -410,7 +429,7 @@ CONFIG_METADATA_2 = {
                            "model": "gpt-4o-mini",
                        },
                    },
-                    "xAI": {
+                    "xAI(grok)": {
                        "id": "xai",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -421,7 +440,7 @@ CONFIG_METADATA_2 = {
                            "model": "grok-2-latest",
                        },
                    },
-                    "anthropic(claude)": {
+                    "Anthropic(claude)": {
                        "id": "claude",
                        "type": "anthropic_chat_completion",
                        "enable": True,
@@ -433,7 +452,7 @@ CONFIG_METADATA_2 = {
                            "max_tokens": 4096,
                        },
                    },
-                    "ollama": {
+                    "Ollama": {
                        "id": "ollama_default",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -443,7 +462,7 @@ CONFIG_METADATA_2 = {
                            "model": "llama3.1-8b",
                        },
                    },
-                    "gemini(OpenAI兼容)": {
+                    "Gemini(OpenAI兼容)": {
                        "id": "gemini_default",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -454,7 +473,7 @@ CONFIG_METADATA_2 = {
                            "model": "gemini-1.5-flash",
                        },
                    },
-                    "gemini(googlegenai原生)": {
+                    "Gemini(googlegenai原生)": {
                        "id": "gemini_default",
                        "type": "googlegenai_chat_completion",
                        "enable": True,
@@ -465,7 +484,7 @@ CONFIG_METADATA_2 = {
                            "model": "gemini-1.5-flash",
                        },
                    },
-                    "deepseek": {
+                    "DeepSeek": {
                        "id": "deepseek_default",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -476,7 +495,7 @@ CONFIG_METADATA_2 = {
                            "model": "deepseek-chat",
                        },
                    },
-                    "zhipu": {
+                    "Zhipu(智谱)": {
                        "id": "zhipu_default",
                        "type": "zhipu_chat_completion",
                        "enable": True,
@@ -487,7 +506,7 @@ CONFIG_METADATA_2 = {
                            "model": "glm-4-flash",
                        },
                    },
-                    "siliconflow": {
+                    "SiliconFlow(硅基流动)": {
                        "id": "siliconflow",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -498,7 +517,7 @@ CONFIG_METADATA_2 = {
                            "model": "deepseek-ai/DeepSeek-V3",
                        },
                    },
-                    "moonshot(kimi)": {
+                    "MoonShot(Kimi)": {
                        "id": "moonshot",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -509,7 +528,7 @@ CONFIG_METADATA_2 = {
                            "model": "moonshot-v1-8k",
                        },
                    },
-                    "llmtuner": {
+                    "LLMTuner": {
                        "id": "llmtuner_default",
                        "type": "llm_tuner",
                        "enable": True,
@@ -519,7 +538,7 @@ CONFIG_METADATA_2 = {
                        "finetuning_type": "lora",
                        "quantization_bit": 4,
                    },
-                    "dify": {
+                    "Dify": {
                        "id": "dify_app_default",
                        "type": "dify",
                        "enable": True,
@@ -531,7 +550,7 @@ CONFIG_METADATA_2 = {
                        "variables": {},
                        "timeout": 60,
                    },
-                    "dashscope": {
+                    "Dashscope(阿里云百炼应用)": {
                        "id": "dashscope",
                        "type": "dashscope",
                        "enable": True,
@@ -541,7 +560,7 @@ CONFIG_METADATA_2 = {
                        "variables": {},
                        "timeout": 60,
                    },
-                    "fastgpt": {
+                    "FastGPT": {
                        "id": "fastgpt",
                        "type": "openai_chat_completion",
                        "enable": True,
@@ -549,7 +568,7 @@ CONFIG_METADATA_2 = {
                        "api_base": "https://api.fastgpt.in/api/v1",
                        "timeout": 60,
                    },
-                    "whisper(API)": {
+                    "Whisper(API)": {
                        "id": "whisper",
                        "type": "openai_whisper_api",
                        "enable": False,
@@ -557,14 +576,22 @@ CONFIG_METADATA_2 = {
                        "api_base": "",
                        "model": "whisper-1",
                    },
-                    "whisper(本地加载)": {
+                    "Whisper(本地加载)": {
                        "whisper_hint": "(不用修改我)",
                        "enable": False,
                        "id": "whisper",
                        "type": "openai_whisper_selfhost",
                        "model": "tiny",
                    },
-                    "openai_tts(API)": {
+                    "sensevoice(本地加载)": {
+                        "sensevoice_hint": "(不用修改我)",
+                        "enable": False,
+                        "id": "sensevoice",
+                        "type": "sensevoice_stt_selfhost",
+                        "stt_model": "iic/SenseVoiceSmall",
+                        "is_emotion": False,
+                    },
+                    "OpenAI_TTS(API)": {
                        "id": "openai_tts",
                        "type": "openai_tts_api",
                        "enable": False,
@@ -574,7 +601,14 @@ CONFIG_METADATA_2 = {
                        "openai-tts-voice": "alloy",
                        "timeout": "20",
                    },
-                    "fishaudio_tts(API)": {
+                    "Edge_TTS": {
+                        "id": "edge_tts",
+                        "type": "edge_tts",
+                        "enable": False,
+                        "edge-tts-voice": "zh-CN-XiaoxiaoNeural",
+                        "timeout": 20,
+                    },
+                    "FishAudio_TTS(API)": {
                        "id": "fishaudio_tts",
                        "type": "fishaudio_tts_api",
                        "enable": False,
@@ -585,6 +619,22 @@ CONFIG_METADATA_2 = {
                    },
                },
                "items": {
+                    "sensevoice_hint": {
+                        "description": "部署SenseVoice",
+                        "type": "string",
+                        "hint": "启用前请 pip 安装 funasr、funasr_onnx、torchaudio、torch、modelscope、jieba 库（默认使用CPU，大约下载 1 GB），并且安装 ffmpeg。否则将无法正常转文字。",
+                        "obvious_hint": True,
+                    },
+                    "is_emotion": {
+                        "description": "情绪识别",
+                        "type": "bool",
+                        "hint": "是否开启情绪识别。happy｜sad｜angry｜neutral｜fearful｜disgusted｜surprised｜unknown",
+                    },
+                    "stt_model": {
+                        "description": "模型名称",
+                        "type": "string",
+                        "hint": "modelscope 上的模型名称。默认：iic/SenseVoiceSmall。",
+                    },
                    # "variables": {
                    #     "description": "工作流固定输入变量",
                    #     "type": "object",
@@ -602,7 +652,12 @@ CONFIG_METADATA_2 = {
                        "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"],
+                        "options": [
+                            "agent",
+                            "agent-arrange",
+                            "dialog-workflow",
+                            "task-workflow",
+                        ],
                        "obvious_hint": True,
                    },
                    "timeout": {
@@ -721,10 +776,10 @@ CONFIG_METADATA_2 = {
                    },
                    "dify_query_input_key": {
                        "description": "Prompt 输入变量名",
-                        "type": "string",   
+                        "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": {
@@ -27,7 +27,7 @@ class AstrBotCoreLifecycle:
        
        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'
+        os.environ['no_proxy'] = 'localhost'
        
    async def initialize(self):
        logger.info("AstrBot v"+ VERSION)
@@ -7,7 +7,7 @@ from typing import List

 CACHED_SIZE = 200
 log_color_config = {
-    'DEBUG': 'bold_blue', 'INFO': 'bold_cyan',
+    'DEBUG': 'green', 'INFO': 'bold_cyan',
    'WARNING': 'bold_yellow', 'ERROR': 'red',
    'CRITICAL': 'bold_red', 'RESET': 'reset',
    'asctime': 'green'
@@ -75,6 +75,10 @@ class LLMRequestSubStage(Stage):
            except BaseException:
                logger.error(traceback.format_exc())
                
+            if event.is_stopped():
+                logger.info(f"{star_map[handler.handler_module_path].name} - {handler.handler_name} 终止了事件传播。")
+                return
+                
        if isinstance(req.contexts, str):
            req.contexts = json.loads(req.contexts)
        
@@ -92,6 +96,11 @@ class LLMRequestSubStage(Stage):
                    await handler.handler(event, llm_response)
                except BaseException:
                    logger.error(traceback.format_exc())
+                    
+                if event.is_stopped():
+                    logger.info(f"{star_map[handler.handler_module_path].name} - {handler.handler_name} 终止了事件传播。")
+                    return
+               
            
            # 保存到历史记录
            await self._save_to_history(event, req, llm_response)
@@ -142,6 +151,9 @@ class LLMRequestSubStage(Stage):
            return
        
    async def _save_to_history(self, event: AstrMessageEvent, req: ProviderRequest, llm_response: LLMResponse):
+        if not req or not req.conversation or not llm_response:
+            return
+        
        if llm_response.role == "assistant":
            # 文本回复
            contexts = req.contexts
@@ -95,5 +95,9 @@ class RespondStage(Stage):
                await handler.handler(event)
            except BaseException:
                logger.error(traceback.format_exc())
+                
+            if event.is_stopped():
+                logger.info(f"{star_map[handler.handler_module_path].name} - {handler.handler_name} 终止了事件传播。")
+                return
            
        event.clear_result()
@@ -70,6 +70,10 @@ class ResultDecorateStage(Stage):
                    logger.debug(f"hook(on_decorating_result) -> {star_map[handler.handler_module_path].name} - {handler.handler_name} 将消息结果清空。")
            except BaseException:
                logger.error(traceback.format_exc())
+                
+            if event.is_stopped():
+                logger.info(f"{star_map[handler.handler_module_path].name} - {handler.handler_name} 终止了事件传播。")
+                return
            
        # 需要再获取一次。插件可能直接对 chain 进行了替换。
        result = event.get_result()
@@ -27,6 +27,9 @@ class PipelineScheduler():
                        logger.debug(f"阶段 {stage.__class__ .__name__} 已终止事件传播。")
                        break
                    await self._process_stages(event, i + 1)
+                    if event.is_stopped():
+                        logger.debug(f"阶段 {stage.__class__ .__name__} 已终止事件传播。")
+                        break
            else:
                await coro

@@ -49,6 +49,8 @@ class PlatformManager():
                    from .sources.gewechat.gewechat_platform_adapter import GewechatPlatformAdapter # noqa: F401
                case "lark":
                    from .sources.lark.lark_adapter import LarkPlatformAdapter # noqa: F401
+                case "telegram":    
+                    from .sources.telegram.tg_adapter import TelegramPlatformAdapter # noqa: F401
        except (ImportError, ModuleNotFoundError) as e:
            logger.error(f"加载平台适配器 {platform_config['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:
@@ -56,7 +58,7 @@ class PlatformManager():
            
            
        if platform_config['type'] not in platform_cls_map:
-            logger.error(f"未找到适用于 {platform_config['type']}({platform_config['id']}) 平台适配器，请检查是否已经安装或者名称填写错误。")
+            logger.error(f"未找到适用于 {platform_config['type']}({platform_config['id']}) 平台适配器，请检查是否已经安装或者名称填写错误")
            return
        cls_type = platform_cls_map[platform_config['type']]
        inst = cls_type(platform_config, self.settings, self.event_queue)
@@ -75,7 +75,7 @@ class AiocqhttpAdapter(Platform):
        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.session_id = str(abm.sender.user_id) + "_" + str(event.group_id)
        abm.message_str = ''
        abm.message = []
        abm.timestamp = int(time.time())
@@ -231,7 +231,7 @@ class AiocqhttpAdapter(Platform):
                
        @self.bot.on_websocket_connection
        def on_websocket_connection(_):
-            logger.info("aiocqhttp 适配器已连接。")
+            logger.info("aiocqhttp(OneBot v11) 适配器已连接。")
        
        bot = self.bot.run_task(host=self.host, port=int(self.port), shutdown_trigger=self.shutdown_trigger_placeholder)
        
@@ -305,12 +305,11 @@ 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"):
+            if os.path.exists("data/temp/gewe_code"):
                with open("data/temp/gewe_code", "r") as f:
                    code = f.read().strip()
                    if not code:
@@ -339,7 +338,6 @@ class SimpleGewechatClient():
                        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:
                        status = json_blob['data']['status']
                        nickname = json_blob['data'].get('nickName', '')
@@ -0,0 +1,128 @@
+import sys
+import uuid
+import asyncio
+
+from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, PlatformMetadata, MessageType
+from astrbot.api.event import MessageChain
+from astrbot.api.message_components import Plain, Image, Record, File as AstrBotFile, Video, At
+from astrbot.core.platform.astr_message_event import MessageSesion
+from astrbot.api.platform import register_platform_adapter
+
+from telegram import Update
+from telegram.ext import ApplicationBuilder, ContextTypes, filters
+from telegram.constants import ChatType
+from telegram.ext import MessageHandler as TelegramMessageHandler
+from .tg_event import TelegramPlatformEvent
+from astrbot.api import logger
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+
+@register_platform_adapter("telegram", "telegram 适配器")
+class TelegramPlatformAdapter(Platform):
+
+    def __init__(self, platform_config: dict, platform_settings: dict, event_queue: asyncio.Queue) -> None:
+        super().__init__(event_queue)
+        self.config = platform_config
+        self.settings = platform_settings
+        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
+        await TelegramPlatformEvent.send_with_client(self.client, message_chain, from_username)
+        await super().send_by_session(session, message_chain)
+    
+    @override
+    def meta(self) -> PlatformMetadata:
+        return PlatformMetadata(
+            "telegram",
+            "telegram 适配器",
+        )
+
+    @override
+    async def run(self):
+        base_url = self.config.get("telegram_api_base_url", "https://api.telegram.org/bot")
+        if not base_url:
+            base_url = "https://api.telegram.org/bot"
+        
+        self.application = ApplicationBuilder().token(self.config['telegram_token']).base_url(base_url).build()
+        message_handler = TelegramMessageHandler(
+            filters=filters.ALL,  # receive all messages
+            callback=self.convert_message
+        )
+        self.application.add_handler(message_handler)
+        await self.application.initialize()
+        await self.application.start()
+        queue = self.application.updater.start_polling()
+        self.client = self.application.bot
+        logger.info("Telegram Platform Adapter is running.")
+
+        await queue
+
+    async def start(self, update: Update, context: ContextTypes.DEFAULT_TYPE):
+        await context.bot.send_message(chat_id=update.effective_chat.id, text=self.config["start_message"])
+
+    async def convert_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> AstrBotMessage:
+        message = AstrBotMessage()
+        # 获得是群聊还是私聊
+        if update.effective_chat.type == ChatType.PRIVATE:
+            message.type = MessageType.FRIEND_MESSAGE
+        else:
+            message.type = MessageType.GROUP_MESSAGE
+            message.group_id = update.effective_chat.id
+        message.message_id = str(update.message.message_id)
+        message.session_id = str(update.effective_chat.id)
+        message.sender = MessageMember(str(update.effective_user.id), update.effective_user.username)
+        message.self_id = str(context.bot.id)
+        message.raw_message = update
+        message.message_str = ""
+        message.message = []
+        
+        logger.debug(f"Telegram message: {update.message}")
+        
+        if update.message.text:
+            plain_text = update.message.text
+
+            if update.message.entities:
+                for entity in update.message.entities:
+                    if entity.type == "mention":
+                        name = plain_text[entity.offset:entity.offset+entity.length]
+                        message.message.append(At(qq=message.self_id, name=name))
+                        plain_text = plain_text[:entity.offset] + plain_text[entity.offset+entity.length:]
+            
+            message.message.append(Plain(plain_text))
+            message.message_str = plain_text
+                        
+            
+        elif update.message.voice:
+            file = await update.message.voice.get_file()
+            message.message = [Record(file=file.file_path, url=file.file_path),]
+            
+        elif update.message.photo:
+            for photo in update.message.photo:
+                file = await photo.get_file()
+                message.message.append(Image(file=file.file_path, url=file.file_path))
+            
+        elif update.message.document:
+            file = await update.message.document.get_file()
+            message.message = [AstrBotFile(file=file.file_path, name="file"),]
+        
+        elif update.message.video:
+            file = await update.message.video.get_file()
+            message.message = [Video(file=file.file_path, path=file.file_path),]
+            
+        
+        await self.handle_msg(message)
+    
+    async def handle_msg(self, message: AstrBotMessage):
+        message_event = TelegramPlatformEvent(
+            message_str=message.message_str,
+            message_obj=message,
+            platform_meta=self.meta(),
+            session_id=message.session_id,
+            client=self.client
+        )
+        self.commit_event(message_event)
@@ -0,0 +1,57 @@
+from astrbot.api.event import AstrMessageEvent, MessageChain
+from astrbot.api.platform import AstrBotMessage, PlatformMetadata, MessageType
+from astrbot.api.message_components import Plain, Image, Reply, At
+from telegram.ext import ExtBot
+
+class TelegramPlatformEvent(AstrMessageEvent):
+    def __init__(self, message_str: str, message_obj: AstrBotMessage, platform_meta: PlatformMetadata, session_id: str, client: ExtBot):
+        super().__init__(message_str, message_obj, platform_meta, session_id)
+        self.client = client
+        
+    @staticmethod
+    async def send_with_client(client: ExtBot, message: MessageChain, user_name: str):
+        image_path = None
+        
+        has_reply = False
+        reply_message_id = None
+        at_user_id = None
+        for i in message.chain:
+            if isinstance(i, Reply):
+                has_reply = True
+                reply_message_id = i.id
+            if isinstance(i, At):
+                at_user_id = i.name
+        
+        at_flag = False
+        for i in message.chain:
+            payload = {
+                "chat_id": user_name,
+            }
+            if has_reply:
+                payload["reply_to_message_id"] = reply_message_id
+            
+            if isinstance(i, Plain):
+                if at_user_id and not at_flag:
+                    i.text = f"@{at_user_id} " + i.text
+                    at_flag = True
+                await client.send_message(text=i.text, **payload)
+            elif isinstance(i, Image):
+                if i.path:
+                    image_path = i.path
+                else:
+                    image_path = i.file
+
+                if image_path.startswith("base64://"):
+                    import base64
+                    base64_data = image_path[9:]
+                    image_bytes = base64.b64decode(base64_data)
+                    await client.send_photo(photo=image_bytes, **payload)
+                else:
+                    await client.send_photo(photo=image_path, **payload)
+
+    async def send(self, message: MessageChain):
+        if self.get_message_type() == MessageType.GROUP_MESSAGE:
+            await self.send_with_client(self.client, message, self.message_obj.group_id)
+        else:
+            await self.send_with_client(self.client, message, self.get_sender_id())
+        await super().send(message)
@@ -0,0 +1,230 @@
+import sys
+import uuid
+import asyncio
+import quart
+
+from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, PlatformMetadata, MessageType
+from astrbot.api.event import MessageChain
+from astrbot.api.message_components import Plain, Image, Record
+from astrbot.core.platform.astr_message_event import MessageSesion
+from astrbot.api.platform import register_platform_adapter
+from astrbot.core import logger
+from requests import Response
+
+from wechatpy.enterprise.crypto import WeChatCrypto
+from wechatpy.enterprise import WeChatClient
+from wechatpy.enterprise.messages import TextMessage, ImageMessage, VoiceMessage
+from wechatpy.exceptions import InvalidSignatureException
+from wechatpy.enterprise import parse_message
+from .wecom_event import WecomPlatformEvent
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+    
+class WecomServer():
+    def __init__(
+            self, 
+            event_queue: asyncio.Queue,
+            config: dict
+        ):
+        self.server = quart.Quart(__name__)
+        self.port = int(config.get("port"))
+        self.server.add_url_rule('/callback/command', view_func=self.verify, methods=['GET'])
+        self.server.add_url_rule('/callback/command', view_func=self.callback_command, methods=['POST'])
+        self.event_queue = event_queue
+        
+        self.crypto = WeChatCrypto(
+            config['token'].strip(),
+            config['encoding_aes_key'].strip(),
+            config['corpid'].strip()
+        )
+
+        self.callback = None
+        
+    async def verify(self):
+        logger.info(f"验证请求有效性: {quart.request.args}")
+        args = quart.request.args
+        try:
+            echo_str = self.crypto.check_signature(
+                args.get('msg_signature'),
+                args.get('timestamp'),
+                args.get('nonce'),
+                args.get('echostr')   
+            )
+            logger.info("验证请求有效性成功。")
+            return echo_str
+        except InvalidSignatureException:
+            logger.error("验证请求有效性失败，签名异常，请检查配置。")
+            raise 
+        
+    async def callback_command(self):
+        data = await quart.request.get_data()
+        msg_signature = quart.request.args.get('msg_signature')
+        timestamp = quart.request.args.get('timestamp')
+        nonce = quart.request.args.get('nonce')
+        try:
+            xml = self.crypto.decrypt_message(
+                data,
+                msg_signature,
+                timestamp,
+                nonce
+            )
+        except InvalidSignatureException:
+            logger.error("解密失败，签名异常，请检查配置。")
+            raise
+        else:
+            msg = parse_message(xml)
+            logger.info(f"解析成功: {msg}")
+            
+            if self.callback:
+                await self.callback(msg)
+            
+        return "success"
+    
+    async def start_polling(self):
+        logger.info(f"将在 0.0.0.0:{self.port} 端口启动 企业微信 适配器。")
+        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("企业微信 适配器已关闭。")
+        
+
+@register_platform_adapter("wecom", "wecom 适配器")
+class WecomPlatformAdapter(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.client_self_id = uuid.uuid4().hex[:8]
+        self.api_base_url = platform_config.get("api_base_url", "https://qyapi.weixin.qq.com/cgi-bin/")
+        
+        if not self.api_base_url:
+            self.api_base_url = "https://qyapi.weixin.qq.com/cgi-bin/"
+            
+        if self.api_base_url.endswith("/"):
+            self.api_base_url = self.api_base_url[:-1]
+        if not self.api_base_url.endswith("/cgi-bin"):
+            self.api_base_url += "/cgi-bin"
+            
+        if not self.api_base_url.endswith("/"):
+            self.api_base_url += "/"
+        
+    @override
+    async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
+        await super().send_by_session(session, message_chain)
+
+    @override
+    def meta(self) -> PlatformMetadata:
+        return PlatformMetadata(
+            "wecom",
+            "wecom 适配器",
+        )
+
+    @override
+    async def run(self):
+        self.server = WecomServer(
+            self._event_queue,
+            self.config
+        )
+        
+        self.client = WeChatClient(
+            self.config['corpid'].strip(),
+            self.config['secret'].strip(),
+        )
+        self.client.API_BASE_URL = self.api_base_url
+        
+        async def callback(msg):
+            await self.convert_message(msg)
+            
+        self.server.callback = callback
+        
+        await self.server.start_polling()
+        
+    async def convert_message(self, msg):
+        abm = AstrBotMessage()
+        if msg.type == 'text':
+            assert isinstance(msg, TextMessage)
+            abm.message_str = msg.content
+            abm.self_id = str(msg.agent)
+            abm.message = [Plain(msg.content)]
+            abm.type = MessageType.FRIEND_MESSAGE
+            abm.sender = MessageMember(
+                msg.source,
+                msg.source,
+            )
+            abm.message_id = msg.id
+            abm.timestamp = msg.time
+            abm.session_id = abm.sender.user_id
+            abm.raw_message = msg
+        elif msg.type == 'image':
+            assert isinstance(msg, ImageMessage)
+            abm.message_str = "[图片]"
+            abm.self_id = str(msg.agent)
+            abm.message = [Image(file=msg.image, url=msg.image)]
+            abm.type = MessageType.FRIEND_MESSAGE
+            abm.sender = MessageMember(
+                msg.source,
+                msg.source,
+            )
+            abm.message_id = msg.id
+            abm.timestamp = msg.time
+            abm.session_id = abm.sender.user_id
+            abm.raw_message = msg
+        elif msg.type == 'voice':
+            assert isinstance(msg, VoiceMessage)
+            
+            resp: Response = await asyncio.get_event_loop().run_in_executor(
+                None, 
+                self.client.media.download,
+                msg.media_id
+            )
+            path = f"data/temp/wecom_{msg.media_id}.amr"
+            with open(path, 'wb') as f:
+                f.write(resp.content)
+            
+            try:
+                from pydub import AudioSegment
+
+                path_wav = f"data/temp/wecom_{msg.media_id}.wav"
+                audio = AudioSegment.from_file(path)
+                audio.export(path_wav, format="wav")
+            except Exception as e:
+                logger.error(f"转换音频失败: {e}。如果没有安装 ffmpeg 请先安装。")
+                path_wav = path
+                return
+            
+            abm.message_str = ""
+            abm.self_id = str(msg.agent)
+            abm.message = [Record(file=path_wav, url=path_wav)]
+            abm.type = MessageType.FRIEND_MESSAGE
+            abm.sender = MessageMember(
+                msg.source,
+                msg.source,
+            )
+            abm.message_id = msg.id
+            abm.timestamp = msg.time
+            abm.session_id = abm.sender.user_id
+            abm.raw_message = msg
+            
+            
+        
+        logger.info(f"abm: {abm}")
+        await self.handle_msg(abm)
+
+    async def handle_msg(self, message: AstrBotMessage):
+        message_event = WecomPlatformEvent(
+            message_str=message.message_str,
+            message_obj=message,
+            platform_meta=self.meta(),
+            session_id=message.session_id,
+            client=self.client
+        )
+        self.commit_event(message_event)
@@ -0,0 +1,103 @@
+import uuid
+from astrbot.api.event import AstrMessageEvent, MessageChain
+from astrbot.api.platform import AstrBotMessage, PlatformMetadata
+from astrbot.api.message_components import Plain, Image, Record
+from wechatpy.enterprise import WeChatClient
+from astrbot.core.utils.io import download_image_by_url, download_file
+
+from astrbot.api import logger
+
+try:
+    import pydub
+except Exception:
+    logger.warning(
+        "检测到 pydub 库未安装，企业微信将无法语音收发。如需使用语音，请前往管理面板 -> 控制台 -> 安装 Pip 库安装 pydub。"
+    )
+    pass
+
+
+class WecomPlatformEvent(AstrMessageEvent):
+    def __init__(
+        self,
+        message_str: str,
+        message_obj: AstrBotMessage,
+        platform_meta: PlatformMetadata,
+        session_id: str,
+        client: WeChatClient,
+    ):
+        super().__init__(message_str, message_obj, platform_meta, session_id)
+        self.client = client
+
+    @staticmethod
+    async def send_with_client(
+        client: WeChatClient, message: MessageChain, user_name: str
+    ):
+        pass
+
+    async def send(self, message: MessageChain):
+        message_obj = self.message_obj
+
+        for comp in message.chain:
+            if isinstance(comp, Plain):
+                self.client.message.send_text(
+                    message_obj.self_id, message_obj.session_id, comp.text
+                )
+            elif isinstance(comp, Image):
+                img_url = comp.file
+                img_path = ""
+                if img_url.startswith("file:///"):
+                    img_path = img_url[8:]
+                elif comp.file and comp.file.startswith("http"):
+                    img_path = await download_image_by_url(comp.file)
+                else:
+                    img_path = img_url
+
+                with open(img_path, "rb") as f:
+                    try:
+                        response = self.client.media.upload("image", f)
+                    except Exception as e:
+                        logger.error(f"企业微信上传图片失败: {e}")
+                        await self.send(
+                            MessageChain().message(f"企业微信上传图片失败: {e}")
+                        )
+                        return
+                    logger.info(f"企业微信上传图片返回: {response}")
+                    self.client.message.send_image(
+                        message_obj.self_id,
+                        message_obj.session_id,
+                        response["media_id"],
+                    )
+            elif isinstance(comp, Record):
+                record_url = comp.file
+                record_path = ""
+
+                if record_url.startswith("file:///"):
+                    record_path = record_url[8:]
+                elif record_url.startswith("http"):
+                    await download_file(record_url, f"data/temp/{uuid.uuid4()}.wav")
+                else:
+                    record_path = record_url
+
+                # 转成amr
+                record_path_amr = f"data/temp/{uuid.uuid4()}.amr"
+                pydub.AudioSegment.from_wav(record_path).export(
+                    record_path_amr, format="amr"
+                )
+
+                with open(record_path_amr, "rb") as f:
+                    try:
+                        response = self.client.media.upload("voice", f)
+                    except Exception as e:
+                        logger.error(f"企业微信上传语音失败: {e}")
+                        await self.send(
+                            MessageChain().message(f"企业微信上传语音失败: {e}")
+                        )
+                        return
+                    logger.info(f"企业微信上传语音返回: {response}")
+                    self.client.message.send_voice(
+                        message_obj.self_id,
+                        message_obj.session_id,
+                        response["media_id"],
+                    )
+
+        await super().send(message)
@@ -104,7 +104,8 @@ class ProviderManager():
        kdb_cfg = config.get("knowledge_db", {})
        if kdb_cfg and len(kdb_cfg):
            self.curr_kdb_name = list(kdb_cfg.keys())[0]
-        
+    
+
    async def initialize(self):
        for provider_config in self.providers_config:
            await self.load_provider(provider_config)
@@ -123,6 +124,7 @@ class ProviderManager():
            return
        
        logger.info(f"载入 {provider_config['type']}({provider_config['id']}) 服务提供商适配器 ...")
+        logger.debug(f"Provider Config: {provider_config}")
        
        # 动态导入
        try:
@@ -142,12 +144,16 @@ class ProviderManager():
                    from .sources.dashscope_source import ProviderDashscope as ProviderDashscope
                case "googlegenai_chat_completion":
                    from .sources.gemini_source import ProviderGoogleGenAI as ProviderGoogleGenAI
+                case "sensevoice_stt_selfhost":
+                    from .sources.sensevoice_selfhosted_source import ProviderSenseVoiceSTTSelfHost as ProviderSenseVoiceSTTSelfHost
                case "openai_whisper_api":
                    from .sources.whisper_api_source import ProviderOpenAIWhisperAPI as ProviderOpenAIWhisperAPI
                case "openai_whisper_selfhost":
                    from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost as ProviderOpenAIWhisperSelfHost
                case "openai_tts_api":
                    from .sources.openai_tts_api_source import ProviderOpenAITTSAPI as ProviderOpenAITTSAPI
+                case "edge_tts":
+                    from .sources.edge_tts_source import ProviderEdgeTTS as ProviderEdgeTTS
                case "fishaudio_tts_api":
                    from .sources.fishaudio_tts_api_source import ProviderFishAudioTTSAPI as ProviderFishAudioTTSAPI
        except (ImportError, ModuleNotFoundError) as e:
@@ -215,7 +221,7 @@ class ProviderManager():
            
            self.inst_map[provider_config['id']] = inst
        except Exception as e:
-            traceback.print_exc()
+            logger.error(traceback.format_exc())
            logger.error(f"实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器失败：{e}")

    async def reload(self, provider_config: dict):
@@ -242,7 +248,7 @@ class ProviderManager():
    async def terminate_provider(self, provider_id: str):
        if provider_id in self.inst_map:
            
-            logger.info(f"终止 {provider_id} 提供商适配器 ...")
+            logger.info(f"终止 {provider_id} 提供商适配器({len(self.provider_insts)}, {len(self.stt_provider_insts)}, {len(self.tts_provider_insts)}) ...")
            
            if self.inst_map[provider_id] in self.provider_insts:
                self.provider_insts.remove(self.inst_map[provider_id])
@@ -250,11 +256,19 @@ class ProviderManager():
                self.stt_provider_insts.remove(self.inst_map[provider_id])
            if self.inst_map[provider_id] in self.tts_provider_insts:
                self.tts_provider_insts.remove(self.inst_map[provider_id])
+
+            if self.inst_map[provider_id] == self.curr_provider_inst:
+                self.curr_provider_inst = None
+            if self.inst_map[provider_id] == self.curr_stt_provider_inst:
+                self.curr_stt_provider_inst = None
+            if self.inst_map[provider_id] == self.curr_tts_provider_inst:
+                self.curr_tts_provider_inst = None
                
            if getattr(self.inst_map[provider_id], 'terminate', None):
                await self.inst_map[provider_id].terminate()
-                logger.info(f"{provider_id} 提供商适配器已终止。")
-                del self.inst_map[provider_id]
+            
+            logger.info(f"{provider_id} 提供商适配器已终止({len(self.provider_insts)}, {len(self.stt_provider_insts)}, {len(self.tts_provider_insts)})")
+            del self.inst_map[provider_id]
                        
    async def terminate(self):
        for provider_inst in self.provider_insts:
@@ -99,6 +99,12 @@ class ProviderDify(Provider):
                            if not conversation_id:
                                self.conversation_ids[session_id] = chunk['conversation_id']
                                conversation_id = chunk['conversation_id']
+                        elif chunk['event'] == 'message_end':
+                            logger.debug("Dify message end")
+                            break
+                        elif chunk['event'] == 'error':
+                            logger.error(f"Dify 出现错误：{chunk}")
+                            raise Exception(f"Dify 出现错误 status: {chunk['status']} message: {chunk['message']}")
                
                case "workflow":
                    async for chunk in self.api_client.workflow_run(
@@ -130,6 +136,9 @@ class ProviderDify(Provider):
            logger.error(f"Dify 请求失败：{str(e)}")
            return LLMResponse(role="err", completion_text=f"Dify 请求失败：{str(e)}")
        
+        if not result:
+            logger.warning("Dify 请求结果为空，请查看 Debug 日志。")
+        
        return LLMResponse(role="assistant", completion_text=result)

    async def forget(self, session_id):
@@ -0,0 +1,90 @@
+import uuid
+import os
+import edge_tts
+import subprocess
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+from astrbot.core import logger
+
+"""
+edge_tts 方式，能够免费、快速生成语音，使用需要先安装edge-tts库
+```
+pip install edge_tts
+```
+Windows 如果提示找不到指定文件，以管理员身份运行命令行窗口，然后再次运行 AstrBot
+"""
+
+@register_provider_adapter("edge_tts", "Microsoft Edge TTS", provider_type=ProviderType.TEXT_TO_SPEECH)
+class ProviderEdgeTTS(TTSProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        
+        # 设置默认语音，如果没有指定则使用中文小萱
+        self.voice = provider_config.get("edge-tts-voice", "zh-CN-XiaoxiaoNeural")
+        self.rate = provider_config.get("rate", None)
+        self.volume = provider_config.get("volume", None)
+        self.pitch = provider_config.get("pitch", None)
+        self.timeout = provider_config.get("timeout", 30)
+        
+        self.set_model("edge_tts")
+        
+    async def get_audio(self, text: str) -> str:
+        os.makedirs("data/temp", exist_ok=True)
+        mp3_path = f'data/temp/edge_tts_temp_{uuid.uuid4()}.mp3'
+        wav_path = f'data/temp/edge_tts_{uuid.uuid4()}.wav'
+        
+        # 构建Edge TTS参数
+        kwargs = {"text": text, "voice": self.voice}
+        if self.rate:
+            kwargs["rate"] = self.rate
+        if self.volume:
+            kwargs["volume"] = self.volume
+        if self.pitch:
+            kwargs["pitch"] = self.pitch
+        
+        try:
+            communicate = edge_tts.Communicate(**kwargs)
+            await communicate.save(mp3_path)
+            
+            # 使用ffmpeg将MP3转换为标准WAV格式
+            _ = subprocess.run([
+                "ffmpeg",
+                "-y",                   # 覆盖输出文件
+                "-i", mp3_path,         # 输入文件
+                "-acodec", "pcm_s16le", # 16位PCM编码
+                "-ar", "24000",         # 采样率24kHz (适合微信语音)
+                "-ac", "1",             # 单声道
+                wav_path                # 输出文件
+            ], capture_output=True, check=True)
+            
+
+            os.remove(mp3_path)
+            if os.path.exists(wav_path) and os.path.getsize(wav_path) > 0:
+                return wav_path
+            else:
+                logger.error("生成的WAV文件不存在或为空")
+                raise RuntimeError("生成的WAV文件不存在或为空")
+                
+        except subprocess.CalledProcessError as e:
+            logger.error(f"FFmpeg转换失败: {e.stderr.decode() if e.stderr else str(e)}")
+            try:
+                if os.path.exists(mp3_path):
+                    os.remove(mp3_path)
+            except:
+                pass
+            raise RuntimeError(f"FFmpeg转换失败: {str(e)}")
+            
+        except Exception as e:
+            logger.error(f"音频生成失败: {str(e)}")
+            try:
+                if os.path.exists(mp3_path):
+                    os.remove(mp3_path)
+            except:
+                pass
+            raise RuntimeError(f"音频生成失败: {str(e)}")
+    
@@ -1,6 +1,7 @@
 import base64
 import json
 import os
+import inspect

 from openai import AsyncOpenAI, AsyncAzureOpenAI
 from openai.types.chat.chat_completion import ChatCompletion
@@ -49,6 +50,8 @@ class ProviderOpenAIOfficial(Provider):
                timeout=self.timeout
            )
        
+        self.default_params = inspect.signature(self.client.chat.completions.create).parameters.keys()
+        
        model_config = provider_config.get("model_config", {})
        model = model_config.get("model", "unknown")
        self.set_model(model)
@@ -69,13 +72,26 @@ class ProviderOpenAIOfficial(Provider):
            tool_list = tools.get_func_desc_openai_style()
            if tool_list:
                payloads['tools'] = tool_list
-        
+
+        # 不在默认参数中的参数放在 extra_body 中
+        extra_body = {}
+        to_del = []
+        for key in payloads.keys():
+            if key not in self.default_params:
+                extra_body[key] = payloads[key]
+                to_del.append(key)
+        for key in to_del:
+            del payloads[key]
+
        completion = await self.client.chat.completions.create(
            **payloads,
-            stream=False
+            stream=False,
+            extra_body=extra_body
        )

-        assert isinstance(completion, ChatCompletion)
+        if not isinstance(completion, ChatCompletion):
+            raise Exception(f"API 返回的 completion 类型错误：{type(completion)}: {completion}。")
+
        logger.debug(f"completion: {completion}")

        if len(completion.choices) == 0:
@@ -0,0 +1,105 @@
+'''
+Author: diudiu62
+Date: 2025-02-24 18:04:18
+LastEditTime: 2025-02-25 14:06:30
+'''
+import asyncio
+from datetime import datetime
+import os
+import re
+from funasr_onnx import SenseVoiceSmall
+from funasr_onnx.utils.postprocess_utils import rich_transcription_postprocess
+from ..provider import STTProvider
+from ..entites import ProviderType
+from astrbot.core.utils.io import download_file
+from ..register import register_provider_adapter
+from astrbot.core import logger
+from astrbot.core.utils.tencent_record_helper import tencent_silk_to_wav
+
+@register_provider_adapter("sensevoice_stt_selfhost", "SenseVoice 自托管语音识别 模型部署", provider_type=ProviderType.SPEECH_TO_TEXT)
+class ProviderSenseVoiceSTTSelfHost(STTProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.set_model(provider_config.get("stt_model", None))
+        self.model = None
+        self.is_emotion = provider_config.get("is_emotion", False)
+    
+    async def initialize(self):
+        logger.info("下载或者加载 SenseVoice 模型中，这可能需要一些时间 ...")
+      
+
+        # 将模型加载放到线程池中执行
+        self.model = await asyncio.get_event_loop().run_in_executor(
+            None,
+            lambda: SenseVoiceSmall(self.model_name, quantize=True, batch_size=16)
+        )
+
+        logger.info("SenseVoice 模型加载完成。")
+    
+    async def get_timestamped_path(self) -> str:
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        return os.path.join("data", "temp", f"{timestamp}")
+ 
+    async def _convert_audio(self, path: str) -> str:
+        from pyffmpeg import FFmpeg
+        filename = await self.get_timestamped_path() + '.mp3'
+        ff = FFmpeg()
+        output_path = ff.convert(path, os.path.join('data","temp', filename))
+        return output_path
+    
+    async def _is_silk_file(self, file_path):
+        silk_header = b"SILK"
+        with open(file_path, "rb") as f:
+            file_header = f.read(8)
+
+        if silk_header in file_header:
+            return True
+        else:
+            return False
+
+    async def get_text(self, audio_url: str) -> str:
+        try:
+            is_tencent = audio_url.startswith("http") and "multimedia.nt.qq.com.cn" in audio_url
+            
+            if is_tencent:
+                path = await self.get_timestamped_path()
+                await download_file(audio_url, path)
+                audio_url = path
+                
+            if not os.path.isfile(audio_url):
+                raise FileNotFoundError(f"文件不存在: {audio_url}")
+
+            if audio_url.endswith((".amr", ".silk")) or is_tencent:
+                is_silk = await self._is_silk_file(audio_url)
+                if is_silk:
+                    logger.info("Converting silk file to wav ...")
+                    output_path = await self.get_timestamped_path()+'.wav'
+                    await tencent_silk_to_wav(audio_url, output_path)
+                    audio_url = output_path
+
+            # 使用 run_in_executor 来调用模型进行识别
+            loop = asyncio.get_event_loop()
+            res = await loop.run_in_executor(
+                None,  # 使用默认的线程池
+                lambda: self.model(audio_url, language="auto", use_itn=True)
+            )
+
+            # res = self.model(audio_url, language="auto", use_itn=True)
+            logger.debug(f"SenseVoice识别到的文案：{res}")
+            text = rich_transcription_postprocess(res[0])
+            if self.is_emotion:
+                # 提取第二个匹配的值
+                matches = re.findall(r'<\|([^|]+)\|>', res[0])
+                if len(matches) >= 2:
+                    emotion = matches[1]
+                    text = f"(当前的情绪：{emotion}) {text}"
+                else:
+                    logger.warning("未能提取到情绪信息")
+            return text
+        except Exception as e:
+            logger.error(f"处理音频文件时出错: {e}")
+            raise
@@ -9,13 +9,19 @@ class PlatformAdapterType(enum.Flag):
    QQOFFICIAL = enum.auto()
    VCHAT = enum.auto()
    GEWECHAT = enum.auto()
-    ALL = AIOCQHTTP | QQOFFICIAL | VCHAT | GEWECHAT
+    TELEGRAM = enum.auto()
+    WECOM = enum.auto()
+    LARK = enum.auto()
+    ALL = AIOCQHTTP | QQOFFICIAL | VCHAT | GEWECHAT | TELEGRAM | WECOM | LARK
    
 ADAPTER_NAME_2_TYPE = {
    "aiocqhttp": PlatformAdapterType.AIOCQHTTP,
    "qq_official": PlatformAdapterType.QQOFFICIAL,
    "vchat": PlatformAdapterType.VCHAT,
-    "gewechat": PlatformAdapterType.GEWECHAT
+    "gewechat": PlatformAdapterType.GEWECHAT,
+    "telegram": PlatformAdapterType.TELEGRAM,
+    "wecom": PlatformAdapterType.WECOM,
+    "lark": PlatformAdapterType.LARK
 }

 class PlatformAdapterTypeFilter(HandlerFilter):
@@ -1,6 +1,7 @@
 import logging
 from pip import main as pip_main

+logger = logging.getLogger("astrbot")
 class PipInstaller():
    def __init__(self, pip_install_arg: str):
        self.pip_install_arg = pip_install_arg
@@ -20,7 +21,7 @@ class PipInstaller():
        if self.pip_install_arg:
            args.extend(self.pip_install_arg.split())
            
-        print(f"Pip 包管理器: {' '.join(args)}")
+        logger.info(f"Pip 包管理器: pip {' '.join(args)}")
        
        result_code = pip_main(args)
        
@@ -181,8 +181,8 @@ class ChatRoute(Route):
                    self.db.update_conversation(username, cid, history=json.dumps(history))
                    
                    await asyncio.sleep(0.5)
-            except BaseException as e:
-                logger.debug(f"用户 {username} 断开聊天长连接: {str(e)}。")
+            except BaseException as _:
+                logger.debug(f"用户 {username} 断开聊天长连接。")
                self.curr_chat_sse.pop(username)
                return

@@ -1,15 +1,31 @@
 from .route import Route, RouteContext
+
+
 class StaticFileRoute(Route):
    def __init__(self, context: RouteContext) -> None:
        super().__init__(context)
-        
-        index_ = ['/', '/auth/login', '/config', '/logs', '/extension', '/dashboard/default', '/project-atri', '/console', '/chat']
+
+        index_ = [
+            "/",
+            "/auth/login",
+            "/config",
+            "/logs",
+            "/extension",
+            "/dashboard/default",
+            "/project-atri",
+            "/console",
+            "/chat",
+            "/settings",
+            "/platforms",
+            "/providers",
+            "/about",
+        ]
        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"
-    
+            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/faq.html。"
+
    async def index(self):
-        return await self.app.send_static_file('index.html')
+        return await self.app.send_static_file("index.html")
@@ -0,0 +1,15 @@
+# What's Changed
+
+
+1. ✨ 新增: Add a draggable iframe for tutorial links and enhance platform configuration UI
+2. ✨ 新增: 集成 astrbot_plugin_telegram/企业微信 至 astrbot
+3. ✨ 新增: openai_source 支持传入任何自定义参数以适配 Ollama 和 FastGPT 等 provider
+4. ✨ 新增: Telegram 适配器中支持 @ 唤醒
+5. ✨ 新增: 添加面板下载按钮置灰 by @Fridemn
+6. ✨ 新增: 添加 SenseVoice 语音转文本（STT）服务 by @diudiu62
+7. ⚡ 优化: Increase forward threshold from 200 to 1500 in default configuration
+8. ⚡ 优化: 添加控制台关闭自动滚动按钮 by @Fridemn
+9.  🐛 修复: 修复前端面板部分页面刷新后的 404 错误
+10. 🐛 修复: 修复某些情况下热重载 服务提供商 时可能没有正确应用的问题
+11. 🐛 修复: 修复 Telegram 适配器中未处理 base64 的问题 @Raven95676
+12. 🐛 修复: 修复 Dify 主动回复报错的问题 #616
@@ -0,0 +1,13 @@
+# What's Changed
+
+1. ✨ 新增: add English README by @CAICAIIs
+2. ✨ 新增: perf: 优化网页录音 [#283](https://github.com/Soulter/AstrBot/issues/283) by @Fridemn
+3. ✨ 新增: 添加对于 Edge-TTS 的支持 [#471](https://github.com/Soulter/AstrBot/issues/471) by @Fridemn
+4. ⚡ 优化: 为防止输入一大堆 k，改 k 键为 Ctrl 键；改为长按录音，松手结束；为防止误触改为只有点击输入框之后才会生效 by @Fridemn
+5. ⚡ 优化: 插件市场非列表视图能够正常搜索 [#640](https://github.com/Soulter/AstrBot/issues/640) by @Fridemn
+6. ⚡ 优化: 插件市场帮助按钮 tooltip 移入时会消失无法点击其中链接，更改为按钮触发 by @Quirrel-zh
+7. ‼️‼️ 🐛 修复: v3.4.32 无法记忆历史的会话 [#630](https://github.com/Soulter/AstrBot/issues/630)
+8. ‼️🐛 修复: 钩子函数无法终止事件传播的问题；修复某些情况下终止事件传播后仍然会请求 LLM 的问题
+9. ‼️🐛 修复: OneBot V11 通知类事件某些情况无法回复问题 by @CAICAIIs
+10. 🐛 修复: Correct STT model path and improve logging in provider manager and pip installer
+11. 🐛 修复: 由于已安装插件与插件市场中 name 不一致或 repo 链接大小写不一致导致的检测不到是否安装或有更新 by @Quirrel-zh
@@ -300,7 +300,7 @@ commonStore.getStartTime();
                </p>
              </div>

-              <v-btn color="primary" style="border-radius: 10px;" @click="updateDashboard()">
+              <v-btn color="primary" style="border-radius: 10px;" @click="updateDashboard()" :disabled="!dashboardHasNewVersion">
                下载并更新
              </v-btn>
            </div>
@@ -1,16 +1,58 @@
-<script setup lang="ts">
-import { shallowRef } from 'vue';
+<script setup>
+import { ref, shallowRef } from 'vue';
 import { useCustomizerStore } from '../../../stores/customizer';
 import sidebarItems from './sidebarItem';
 import NavItem from './NavItem.vue';

 const customizer = useCustomizerStore();
 const sidebarMenu = shallowRef(sidebarItems);
+
+const showIframe = ref(false);
+
+const dragButtonStyle = {
+  width: '100%',
+  padding: '4px',
+  cursor: 'move',
+  background: '#f0f0f0',
+  borderBottom: '1px solid #ccc',
+  borderTopLeftRadius: '8px',
+  borderTopRightRadius: '8px'
+};
+
+function toggleIframe() {
+  showIframe.value = !showIframe.value;
+}
+
+let offsetX = 0;
+let offsetY = 0;
+let isDragging = false;
+
+// @ts-ignore
+function onMouseDown(event) {
+  isDragging = true;
+  offsetX = event.clientX - event.target.parentElement.getBoundingClientRect().left;
+  offsetY = event.clientY - event.target.parentElement.getBoundingClientRect().top;
+}
+// @ts-ignore
+function onMouseMove(event) {
+  if (isDragging) {
+    const dm = document.getElementById('draggable-iframe');
+    // @ts-ignore
+    dm.style.left = (event.clientX - offsetX) + 'px';
+    // @ts-ignore
+    dm.style.top = (event.clientY - offsetY) + 'px';
+  }
+}
+
+function onMouseUp() {
+  isDragging = false;
+}
+
 </script>

 <template>
-  <v-navigation-drawer left v-model="customizer.Sidebar_drawer" elevation="0" rail-width="80"
-    app class="leftSidebar" :rail="customizer.mini_sidebar">
+  <v-navigation-drawer left v-model="customizer.Sidebar_drawer" elevation="0" rail-width="80" app class="leftSidebar"
+    :rail="customizer.mini_sidebar">
    <v-list class="pa-4 listitem" style="height: auto">
      <template v-for="(item, i) in sidebarMenu" :key="i">
        <NavItem :item="item" class="leftPadding" />
@@ -21,9 +63,9 @@ const sidebarMenu = shallowRef(sidebarItems);
    </div>

    <div style="position: absolute; bottom: 32px; width: 100%" class="text-center">
-      <v-list-item v-if="!customizer.mini_sidebar" href="https://astrbot.app/">
+      <v-list-item v-if="!customizer.mini_sidebar" @click="toggleIframe">
        <v-btn variant="plain" size="small">
-          🤔 初次使用？点击查看文档！
+          🤔 点击查看悬浮文档！
        </v-btn>
      </v-list-item>
      <small style="display: block;" v-if="buildVer">构建: {{ buildVer }}</small>
@@ -34,14 +76,25 @@ const sidebarMenu = shallowRef(sidebarItems);
        </template>
      </v-tooltip>

-      
+
      <small style="display: block; margin-top: 8px;">© 2025 AstrBot</small>
    </div>

  </v-navigation-drawer>
+  <div v-if="showIframe"
+    id="draggable-iframe"
+    style="position: fixed; bottom: 16px; right: 16px; width: 500px; height: 400px; border: 1px solid #ccc; background: white; resize: both; overflow: auto; z-index: 10000000; border-radius: 8px;"
+    @mousemove="onMouseMove"
+    @mouseup="onMouseUp"
+    @mouseleave="onMouseUp">
+    <div :style="dragButtonStyle" @mousedown="onMouseDown">
+      <v-icon icon="mdi-cursor-move" />
+    </div>
+    <iframe src="https://astrbot.app" style="width: 100%; height: calc(100% - 24px); border: none; border-bottom-left-radius: 8px; border-bottom-right-radius: 8px;"></iframe>
+  </div>
 </template>

-<script lang="ts">
+<script>
 import axios from 'axios';
 export default {
  name: 'VerticalSidebar',
@@ -9,6 +9,17 @@ export const useCommonStore = defineStore({
    log_cache: [],
    log_cache_max_len: 1000,
    startTime: -1,
+
+    tutorial_map: {
+      "qq_official_webhook": "https://astrbot.app/deploy/platform/qqofficial/webhook.html",
+      "qq_official": "https://astrbot.app/deploy/platform/qqofficial/websockets.html",
+      "aiocqhttp": "https://astrbot.app/deploy/platform/aiocqhttp/napcat.html",
+      "wecom": "https://astrbot.app/deploy/platform/wecom.html",
+      "gewechat": "https://astrbot.app/deploy/platform/gewechat.html",
+      "lark": "https://astrbot.app/deploy/platform/lark.html",
+      "telegram": "https://astrbot.app/deploy/platform/telegram.html",
+    }
+
  }),
  actions: {
    createWebSocket() {
@@ -39,5 +50,8 @@ export const useCommonStore = defineStore({
          this.startTime = res.data.data.start_time
      })
    },
+    getTutorialLink(platform) {
+      return this.tutorial_map[platform]
+    }
  }
 });
@@ -60,10 +60,10 @@ marked.setOptions({
                                <span>获取帮助 😊</span>
                            </div>
                            <div style="margin-top: 8px; color: #aaa;">
-                                <span>按</span>
+                                <span>长按</span>
                                <span
-                                    style="background-color: #eee; padding-left: 4px; padding-right: 4px; margin: 2px; border-radius: 4px;">K</span>
-                                <span>开始语音 🎤</span>
+                                    style="background-color: #eee; padding-left: 4px; padding-right: 4px; margin: 2px; border-radius: 4px;">Ctrl</span>
+                                <span>录制语音 🎤</span>
                            </div>
                            <div style="margin-top: 8px; color: #aaa;">
                                <span>按</span>
@@ -112,7 +112,8 @@ marked.setOptions({

                            <v-text-field id="input-field" variant="outlined" v-model="prompt" :label="inputFieldLabel"
                                placeholder="Start typing..." loading clear-icon="mdi-close-circle" clearable
-                                @click:clear="clearMessage" style="width: 100%; max-width: 850px;">
+                                @click:clear="clearMessage" style="width: 100%; max-width: 850px;"
+                                @keydown="handleInputKeyDown">
                                <template v-slot:loader>
                                    <v-progress-linear :active="loadingChat" height="6"
                                        indeterminate></v-progress-linear>
@@ -189,7 +190,12 @@ export default {
            status: {},
            statusText: '',
            
-            eventSource: null
+            eventSource: null,
+            
+            // 添加Ctrl键长按相关变量
+            ctrlKeyDown: false,
+            ctrlKeyTimer: null,
+            ctrlKeyLongPressThreshold: 300 // 长按阈值，单位毫秒
        }
    },

@@ -205,11 +211,9 @@ export default {
                this.sendMessage();
            }
        }.bind(this));
-        document.addEventListener('keydown', function (e) {
-            if (e.keyCode == 75) {
-                this.isRecording ? this.stopRecording() : this.startRecording();
-            }
-        }.bind(this));
+        
+        // 添加keyup事件监听
+        document.addEventListener('keyup', this.handleInputKeyUp);
    },

    beforeUnmount() {
@@ -218,6 +222,9 @@ export default {
            this.eventSource.cancel();
            console.log('SSE连接已断开');
        }
+        
+        // 移除keyup事件监听
+        document.removeEventListener('keyup', this.handleInputKeyUp);
    },

    methods: {
@@ -531,7 +538,40 @@ export default {
                const container = this.$refs.messageContainer;
                container.scrollTop = container.scrollHeight;
            });
-        }
+        },
+
+        handleInputKeyDown(e) {
+            if (e.keyCode === 17) { // Ctrl键
+                // 防止重复触发
+                if (this.ctrlKeyDown) return;
+                
+                this.ctrlKeyDown = true;
+                
+                // 设置定时器识别长按
+                this.ctrlKeyTimer = setTimeout(() => {
+                    if (this.ctrlKeyDown && !this.isRecording) {
+                        this.startRecording();
+                    }
+                }, this.ctrlKeyLongPressThreshold);
+            }
+        },
+        
+        handleInputKeyUp(e) {
+            if (e.keyCode === 17) { // Ctrl键
+                this.ctrlKeyDown = false;
+                
+                // 清除定时器
+                if (this.ctrlKeyTimer) {
+                    clearTimeout(this.ctrlKeyTimer);
+                    this.ctrlKeyTimer = null;
+                }
+                
+                // 如果正在录音，停止录音
+                if (this.isRecording) {
+                    this.stopRecording();
+                }
+            }
+        },
    },
 }

@@ -4,7 +4,6 @@ import WaitingForRestart from '@/components/shared/WaitingForRestart.vue';
 import AstrBotConfig from '@/components/shared/AstrBotConfig.vue';
 import ConsoleDisplayer from '@/components/shared/ConsoleDisplayer.vue';
 import axios from 'axios';
-import { max } from 'date-fns';

 </script>

@@ -94,12 +93,15 @@ import { max } from 'date-fns';

          🧩 插件市场

-          <v-btn icon size="small" style="margin-left: 8px" variant="plain">
+          <v-btn icon size="small" style="margin-left: 8px" variant="plain" @click="jumpToPluginMarket()">
            <v-icon size="small">mdi-help</v-icon>
            <v-tooltip activator="parent" location="start">
-              如无法显示，请打开 <a href="https://soulter.github.io/AstrBot_Plugins_Collection/plugins.json">链接</a> 复制想安装插件对应的
+              <span>
+                如无法显示，请单击此按钮跳转至插件市场，复制想安装插件对应的
              `repo`
              链接然后点击右下角 + 号安装，或打开链接下载压缩包安装。
+            </span>
+              
            </v-tooltip>
          </v-btn>

@@ -141,7 +143,7 @@ import { max } from 'date-fns';
        </template>
        <template v-else>
          <v-row style="margin: 8px;">
-            <v-col cols="12" md="6" lg="3" v-for="plugin in pluginMarketData">
+            <v-col cols="12" md="6" lg="3" v-for="plugin in filteredPluginMarketData">
              <ExtensionCard :key="plugin.name" :title="plugin.name" :link="plugin.repo" style="margin-bottom: 4px;">
                <div style="min-height: 130px; max-height: 130px; overflow: hidden;">
                  <p style="font-weight: bold;">By @{{ plugin.author }}</p>
@@ -380,6 +382,17 @@ export default {
      alreadyCheckUpdate: false
    }
  },
+  computed: {
+    filteredPluginMarketData() {
+      if (!this.marketSearch) {
+        return this.pluginMarketData;
+      }
+      const search = this.marketSearch.toLowerCase();
+      return this.pluginMarketData.filter(plugin => 
+        plugin.name.toLowerCase().includes(search)
+      );
+    }
+  },
  mounted() {
    this.getExtensions();
    this.fetchPluginCollection();
@@ -390,6 +403,9 @@ export default {
    });
  },
  methods: {
+    jumpToPluginMarket() {
+      window.open('https://soulter.github.io/AstrBot_Plugins_Collection/plugins.json', '_blank');
+    },
    toast(message, success) {
      this.snack_message = message;
      this.snack_show = true;
@@ -422,21 +438,34 @@ export default {
    },

    checkUpdate() {
-      // 遍历 extension_data 和 pluginMarketData，检查是否有更新\
-      for (let i = 0; i < this.extension_data.data.length; i++) {
-        for (let j = 0; j < this.pluginMarketData.length; j++) {
-          console.log(this.extension_data.data[i].repo, this.pluginMarketData[j].repo);
-          if (this.extension_data.data[i].repo === this.pluginMarketData[j].repo ||
-            this.extension_data.data[i].name === this.pluginMarketData[j].name) {
-            this.extension_data.data[i].online_version = this.pluginMarketData[j].version;
-            if (this.extension_data.data[i].version !== this.pluginMarketData[j].version && this.pluginMarketData[j].version !== "未知") {
-              this.extension_data.data[i].has_update = true;
-            } else {
-              this.extension_data.data[i].has_update = false;
-            }
-          }
+      // 创建在线插件的map
+      const onlinePluginsMap = new Map();
+      const onlinePluginsNameMap = new Map();
+      
+      // 将在线插件信息存储到map中
+      this.pluginMarketData.forEach(plugin => {
+        if (plugin.repo) {
+          onlinePluginsMap.set(plugin.repo.toLowerCase(), plugin);
        }
-      }
+        onlinePluginsNameMap.set(plugin.name, plugin);
+      });
+      
+      // 遍历本地插件列表
+      this.extension_data.data.forEach(extension => {
+        // 通过repo或name查找在线版本
+        const repoKey = extension.repo?.toLowerCase();
+        const onlinePlugin = repoKey ? onlinePluginsMap.get(repoKey) : null;
+        const onlinePluginByName = onlinePluginsNameMap.get(extension.name);
+        const matchedPlugin = onlinePlugin || onlinePluginByName;
+        
+        if (matchedPlugin) {
+          extension.online_version = matchedPlugin.version;
+          extension.has_update = extension.version !== matchedPlugin.version && 
+                                matchedPlugin.version !== "未知";
+        } else {
+          extension.has_update = false;
+        }
+      });
    },

    newExtension() {
@@ -613,15 +642,14 @@ export default {
      });
    },
    checkAlreadyInstalled() {
+      // 创建已安装插件的仓库和名称集合 统一格式
+      const installedRepos = new Set(this.extension_data.data.map(ext => ext.repo?.toLowerCase()));
+      const installedNames = new Set(this.extension_data.data.map(ext => ext.name));
+      
+      // 遍历检查安装状态
      for (let i = 0; i < this.pluginMarketData.length; i++) {
-        this.pluginMarketData[i].installed = false;
-      }
-      for (let i = 0; i < this.pluginMarketData.length; i++) {
-        for (let j = 0; j < this.extension_data.data.length; j++) {
-          if (this.pluginMarketData[i].repo === this.extension_data.data[j].repo || this.pluginMarketData[i].name === this.extension_data.data[j].name) {
-            this.pluginMarketData[i].installed = true;
-          }
-        }
+        const plugin = this.pluginMarketData[i];
+        plugin.installed = installedRepos.has(plugin.repo?.toLowerCase()) || installedNames.has(plugin.name);
      }

      // 将已安装的插件移动到最后面
@@ -47,14 +47,29 @@
                    </v-card>
                </v-col>
            </v-row>
-            <v-dialog v-model="showPlatformCfg" width="700">
+            <v-dialog v-model="showPlatformCfg">
                <v-card>
                    <v-card-title>
                        <span class="text-h4">{{ newSelectedPlatformName }} 配置</span>
                    </v-card-title>
                    <v-card-text>
-                        <AstrBotConfig :iterable="newSelectedPlatformConfig"
-                            :metadata="metadata['platform_group']['metadata']" metadataKey="platform" />
+                        <v-row>
+                            <v-col cols="12" md="6">
+                                <AstrBotConfig :iterable="newSelectedPlatformConfig"
+                                    :metadata="metadata['platform_group']['metadata']" metadataKey="platform" />
+                            </v-col>
+                            <v-col cols="12" md="6">
+                                <v-btn :loading="iframeLoading" @click="refreshIframe" variant="tonal" color="primary" style="float: right;">
+                                    <v-icon>mdi-refresh</v-icon>
+                                    刷新
+                                </v-btn>
+                                <iframe v-show="!iframeLoading"
+                                    :src="store.getTutorialLink(newSelectedPlatformConfig.type)"
+                                    @load="iframeLoading = false" style="width: 100%; border: none; height: 100%;">
+                                </iframe>
+                            </v-col>
+                        </v-row>
+
                    </v-card-text>
                    <v-card-actions>
                        <v-spacer></v-spacer>
@@ -66,7 +81,8 @@
            </v-dialog>


-            <v-btn style="margin-top: 16px" class="flex-grow-1" variant="tonal"  size="large" rounded="lg" color="gray" @click="showConsole = !showConsole">
+            <v-btn style="margin-top: 16px" class="flex-grow-1" variant="tonal" size="large" rounded="lg" color="gray"
+                @click="showConsole = !showConsole">
                <template v-slot:default>
                    <v-icon>mdi-console-line</v-icon>
                    {{ showConsole ? '隐藏' : '显示' }}日志
@@ -91,6 +107,7 @@ import axios from 'axios';
 import AstrBotConfig from '@/components/shared/AstrBotConfig.vue';
 import WaitingForRestart from '@/components/shared/WaitingForRestart.vue';
 import ConsoleDisplayer from '@/components/shared/ConsoleDisplayer.vue';
+import { useCommonStore } from '@/stores/common';

 export default {
    name: 'PlatformPage',
@@ -117,6 +134,9 @@ export default {
            save_message_success: "",

            showConsole: false,
+            iframeLoading: true,
+
+            store: useCommonStore()
        }
    },

@@ -125,6 +145,12 @@ export default {
    },

    methods: {
+        refreshIframe() {
+            this.iframeLoading = true;
+            const iframe = document.querySelector('iframe');
+            console.log(iframe.src);
+            iframe.src = iframe.src + '?t=' + new Date().getTime();
+        },
        getConfig() {
            // 获取配置
            axios.get('/api/config/get').then((res) => {
@@ -146,6 +146,7 @@ class Main(star.Star):
        try:
            docker = aiodocker.Docker()
            await docker.version()
+            await docker.close()
            return True
        except BaseException as e:
            logger.info(f"检查 Docker 可用性: {e}")
@@ -310,6 +311,7 @@ class Main(star.Star):
            # 启动容器
            docker = aiodocker.Docker()
            
+            
            # 检查有没有image
            image_name = await self.get_image_name()
            try:
@@ -9,7 +9,6 @@ beautifulsoup4
 googlesearch-python
 readability-lxml
 quart
-psutil
 lxml_html_clean
 colorlog
 aiocqhttp
@@ -19,9 +18,9 @@ docstring_parser
 aiodocker
 silk-python
 psutil>=5.8.0
-
 lark-oapi
 ormsgpack
 cryptography
-
-dashscope
+dashscope
+python-telegram-bot
+wechatpy
Author	SHA1	Message	Date
Soulter	bcebd0fb62	v3.4.33	2025-02-28 22:13:08 +08:00
Soulter	3817d3ca87	fix: 不记忆历史的会话 #630	2025-02-28 22:00:49 +08:00
Soulter	4dd714e814	Merge pull request #648 from Soulter/feat-edge-tts feat: 添加对于 edge-tts 支持 #471	2025-02-28 21:46:50 +08:00
Soulter	61e8bb49ec	chore: Cleanup	2025-02-28 21:33:03 +08:00
Soulter	103dcd3761	Merge pull request #645 from Quirrel-zh/master 修复&优化	2025-02-28 21:24:54 +08:00
Soulter	54ac135fc8	Merge pull request #642 from CAICAIIs/fix_bug fix bug #621	2025-02-28 21:12:37 +08:00
Soulter	86582809fc	Merge pull request #641 from Soulter/perf-plugin-search perf: 插件市场非列表视图能够正常搜索 #640	2025-02-28 21:11:43 +08:00
Soulter	974d648f19	Merge pull request #638 from Soulter/perf-record perf: 优化网页录音 #283	2025-02-28 21:10:09 +08:00
崔永亮	a79afc9597	feat: 添加对于 edge-tts 支持 #471	2025-02-28 16:57:44 +08:00
quirrel-zh	e4883241d9	🐛fixed： 1、由于tooltip移入时会消失无法点击其中链接，更改为按钮出发 2、修复了由于已安装插件与插件市场中name不一致或repo链接大小写不一致导致的检测不到是否安装或有更新的bug	2025-02-28 15:58:57 +08:00
yxw	babf223745	fix bug #621	2025-02-28 14:22:59 +08:00
崔永亮	c7d91730b6	perf: 插件市场非列表视图能够正常搜索 #640	2025-02-28 14:18:10 +08:00
Soulter	71246b65c9	Update README.md	2025-02-28 14:06:31 +08:00
Soulter	50076b647e	Merge pull request #639 from CAICAIIs/master docs: add English README	2025-02-28 14:06:00 +08:00
yxw	a1a788dce8	docs: add English README	2025-02-28 13:39:45 +08:00
崔永亮	a611b4f346	perf: 优化网页录音 #283 1. 为防止输入一大堆 k，改 k 键为 Ctrl 键； 2. 改为长按录音，松手结束； 3. 为防止误触改为只有点击输入框之后才会生效	2025-02-28 13:22:55 +08:00
Soulter	7f6ed674b4	‼️🐛 fix: 修复钩子函数无法终止事件传播的问题；修复某些情况下终止事件传播后仍然会请求 LLM 的问题	2025-02-28 00:02:17 +08:00
Soulter	aa3cfd887a	fix: correct STT model path and improve logging in provider manager and pip installer	2025-02-27 11:33:53 +08:00
Soulter	2649d46d8d	chore: remove ts	2025-02-27 01:01:28 +08:00
Soulter	e23ffe6f02	chore: remove ts	2025-02-27 00:57:55 +08:00
Soulter	96f3c3729a	v3.4.32	2025-02-27 00:44:23 +08:00
Soulter	11e9d47ce2	fix: dify active message error #616	2025-02-27 00:26:04 +08:00
Soulter	efbc8e4383	Merge pull request #614 from Raven95676/master 🐛 fix: 修复telegram适配器中未处理base64的问题	2025-02-27 00:03:38 +08:00
Soulter	bc7404409f	Merge pull request #612 from diudiu62/feat-sensevoice 新增sensevoice语言识别能力	2025-02-26 23:56:03 +08:00
Soulter	8677d70baf	feat: add sensevoice adapter	2025-02-26 23:55:00 +08:00
Soulter	f39253f0e1	Merge branch 'master' into feat-sensevoice	2025-02-26 23:27:04 +08:00
Soulter	68c1957267	chore: update gitignore	2025-02-26 23:21:28 +08:00
Raven95676	a275aa2e4d	🐛 fix: 修复telegram适配器中未处理base64的问题	2025-02-26 16:35:44 +08:00
Soulter	cadbac9948	🐛 fix: update 404 error message to reference FAQ for better user guidance	2025-02-26 11:56:40 +08:00
diudiu62	82673e8ddd	依赖放到了参数配置地方提醒，docker提前自行打包依赖	2025-02-26 09:46:30 +08:00
Soulter	bee51024b3	perf: 修复 wecom 配置项的空格问题，确保正确传递 #599	2025-02-26 00:57:54 +08:00
Soulter	3437cb73ec	Merge pull request #605 from Soulter/feat-update-btn feat: 添加面板下载按钮置灰	2025-02-25 22:26:12 +08:00
diudiu62	d01d1a8520	增加依赖	2025-02-25 18:03:29 +08:00
diudiu62	5aa842cf66	增加sensevoice配置	2025-02-25 14:15:22 +08:00
Soulter	03282dee0f	🐛 fix: handle message end and error events in Dify provider, improve logging and error reporting	2025-02-25 14:09:12 +08:00
Soulter	98e8ecb8e2	🐛 fix: add type check for completion response from API to ensure correct handling	2025-02-25 11:46:44 +08:00
Soulter	9451dc3fd4	🐛 fix: 修复某些情况下热重载 provider 时可能没有正确应用的问题	2025-02-25 11:46:44 +08:00
崔永亮	e1d3759f55	feat: 添加面板下载按钮置灰	2025-02-25 10:13:34 +08:00
diudiu62	0ec382c86b	尝试集成sensevoice	2025-02-25 09:05:24 +08:00
Soulter	756087c9f1	✨ feat: 扩展 PlatformAdapterType，支持 Telegram、WeCom 和 Lark 适配器 #601	2025-02-25 01:39:34 +08:00
Soulter	3e7c47e873	✨ feat: 在 Telegram 适配器中支持@功能，增强消息处理能力	2025-02-25 01:32:44 +08:00
Soulter	e3ffdbc308	✨ feat: openai_source 支持传入任何自定义参数以适配 Ollama 和 FastGPT 等	2025-02-25 00:51:09 +08:00
Soulter	645cace4d6	✨ feat: 添加企业微信适配器配置并优化默认配置格式	2025-02-24 23:00:41 +08:00
Soulter	0959d5986b	✨ feat: 将 astrbot_plugin_wecom 集成至 astrbot	2025-02-24 22:43:43 +08:00
Soulter	89605c29a7	🐛 fix: ping docker 后关闭 Docker 连接以避免资源泄漏	2025-02-24 22:26:46 +08:00
Soulter	e527f31213	✨ feat: 集成 astrbot_plugin_telegram 至 astrbot	2025-02-24 22:26:23 +08:00
Soulter	a0dbd99928	✨ feat: 在静态文件路由中添加新的URL路径以增强功能	2025-02-24 22:09:42 +08:00
Soulter	17d39c7a4a	🐛 fix: increase forward threshold from 200 to 1500 in default configuration	2025-02-24 15:38:22 +08:00
Soulter	54edaebbd9	🐛 fix: remove unnecessary verification flag for captcha handling in SimpleGewechatClient	2025-02-24 15:36:37 +08:00
Soulter	d587a6f64c	✨ feat: add draggable iframe for tutorial links and enhance platform configuration UI	2025-02-24 13:50:07 +08:00
Soulter	2371c32be5	Update LICENSE	2025-02-24 00:31:57 +08:00
Soulter	c9abb8352c	Update LICENSE	2025-02-24 00:29:27 +08:00