v3.4.19

feat: 优化插件市场的访问

README.md

@@ -1,14 +1,12 @@
-
 <p align="center">
+    
+![logo](https://github.com/user-attachments/assets/07649e07-3b8e-4feb-9aa9-bf13af4f3476)
 
-<img src="https://github.com/user-attachments/assets/de10f24d-cd64-433a-90b8-16c0a60de24a" width=500>
 
 </p>
 
 <div align="center">
 
-<h1>AstrBot</h1>
-
 _✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
 
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
@@ -16,81 +14,104 @@ _✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
 <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">
 [![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>
 
-<a href="https://astrbot.lwl.lol/">查看文档</a> ｜
+<a href="https://astrbot.app/">查看文档</a> ｜
 <a href="https://github.com/Soulter/AstrBot/issues">问题提交</a>
 </div>
 
 AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用的插件系统和完善的大语言模型（LLM）接入功能的聊天机器人及开发框架。
 
-## ✨ 多消息平台部署
+## ✨ 主要功能
 
-1. QQ 群、QQ 频道、微信个人号、Telegram。
-2. 内置 Web Chat，即使不部署到消息平台也能聊天。
-3. 支持文本转图片，Markdown 渲染。
-   
-## ✨ 多 LLM 配置
+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。
+3. **Agent**。原生支持部分 Agent 能力，如代码执行器、自然语言待办、网页搜索。对接 [Dify 平台](https://astrbot.app/others/dify.html)，便捷接入 Dify 智能助手、知识库和 Dify 工作流。
+4. **插件扩展**。深度优化的插件机制，支持[开发插件](https://astrbot.app/dev/plugin.html)扩展功能，极简开发。已支持安装多个插件。
+5. **可视化管理面板**。支持可视化修改配置、插件管理、日志查看等功能，降低配置难度。集成 WebChat，可在面板上与大模型对话。
+6. **高稳定性、高模块化**。基于事件总线和流水线的架构设计，高度模块化，低耦合。
 
-1. 适配 OpenAI API，支持接入 Gemini、GPT、Llama、Claude、DeepSeek、GLM 等各种大语言模型。
-2. 支持 OneAPI 等分发平台。
-3. 支持 LLMTuner 载入微调模型。
-4. 支持 Ollama 载入自部署模型。
-4. 支持网页搜索（Web Search）、自然语言待办提醒。
-5. 支持 Whisper 语音转文字
+> [!TIP]
+> 管理面板在线体验 Demo: [https://demo.astrbot.app/](https://demo.astrbot.app/)
+> 
+> 用户名: `astrbot`, 密码: `astrbot`。未配置 LLM，无法在聊天页使用大模型。（不要再修改 demo 的登录密码了 😭）
 
-## ✨ 管理面板
+## ✨ 使用方式
 
-1. 支持可视化修改配置
-2. 日志实时查看
-3. 简单的信息统计
-4. 插件管理
+#### Docker 部署
 
-## ✨ 支持 Dify
+请参阅官方文档 [使用 Docker 部署 AstrBot](https://astrbot.app/deploy/astrbot/docker.html#%E4%BD%BF%E7%94%A8-docker-%E9%83%A8%E7%BD%B2-astrbot) 。
 
-1. 对接了 LLMOps 平台 Dify，便捷接入 Dify 智能助手、知识库和 Dify 工作流！[接入 Dify - AstrBot 文档](https://astrbot.lwl.lol/others/dify.html)
+#### Windows 一键安装器部署
 
-## ✨ 代码执行器(Beta)
+需要电脑上安装有 Python（>3.10）。请参阅官方文档 [使用 Windows 一键安装器部署 AstrBot](https://astrbot.app/deploy/astrbot/windows.html) 。
 
-基于 Docker 的沙箱化代码执行器（Beta 测试中）
-
-> [!NOTE]
-> 文件输入/输出目前仅测试了 Napcat(QQ), Lagrange(QQ)
-
-<div align='center'>
-
-<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
-
-</div>
-
-## ✨ 云部署
+#### Replit 部署
 
 [![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
 
+#### CasaOS 部署
+
+社区贡献的部署方式。
+
+请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/casaos.html) 。
+
+#### 手动部署
+
+请参阅官方文档 [通过源码部署 AstrBot](https://astrbot.app/deploy/astrbot/cli.html) 。
+
+
+## ⚡ 消息平台支持情况
+
+| 平台    | 支持性 | 详情 | 消息类型 |
+| -------- | ------- | ------- | ------ |
+| QQ(官方机器人接口) | ✔    | 私聊、群聊，QQ 频道私聊、群聊 | 文字、图片 |
+| QQ(OneBot)      | ✔    | 私聊、群聊 | 文字、图片、语音 |
+| 微信(个人号)    | ✔    | 微信个人号私聊、群聊 | 文字、图片、语音 |
+| [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | 私聊、群聊 | 文字、图片 |
+| [微信(企业微信)](https://github.com/Soulter/astrbot_plugin_wecom)    | ✔    | 私聊 | 文字、图片、语音 |
+| 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 ：)
 
 对于新功能的添加，请先通过 Issue 讨论。
 
-## 🔭 展望
-
-1. 更强大的 Agent 系统。
-2. 打造插件工作流平台。
-
-## ✨ Support
+## 🌟 支持
 
 - Star 这个项目！
 - 在[爱发电](https://afdian.com/a/soulter)支持我！
 - 在[微信](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)支持我~
 
-
-
 ## ✨ Demo
 
+> [!NOTE]
+> 代码执行器的文件输入/输出目前仅测试了 Napcat(QQ), Lagrange(QQ)
+
 <div align='center'>
 
+<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">
+
+_✨基于 Docker 的沙箱化代码执行器（Beta 测试中）✨_
+
 <img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
 
 _✨ 多模态、网页搜索、长文本转图片（可配置） ✨_
@@ -114,6 +135,26 @@ _✨ 内置 Web Chat，在线与机器人交互 ✨_
 
 </div>
 
+## ⭐ Star History
+
+> [!TIP] 
+> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我维护这个开源项目的动力 <3
+
+<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>
+
+## Sponsors
+
+[<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==)
+
+## 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]
 
@@ -125,5 +166,6 @@ _✨ 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!_
 

astrbot/api/__init__.py

@@ -1,6 +1,5 @@
 from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot import logger
-from astrbot.core.utils.personality import personalities
 from astrbot.core import html_renderer
 from astrbot.core import sp
 from astrbot.core.star.register import register_llm_tool as llm_tool
@@ -8,7 +7,6 @@ from astrbot.core.star.register import register_llm_tool as llm_tool
 __all__ = [
     "AstrBotConfig",
     "logger",
-    "personalities",
     "html_renderer",
     "llm_tool",
     "sp"

astrbot/api/all.py

@@ -1,7 +1,6 @@
 
 from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot import logger
-from astrbot.core.utils.personality import personalities
 from astrbot.core import html_renderer
 from astrbot.core.star.register import register_llm_tool as llm_tool
 

astrbot/api/event/filter/__init__.py

@@ -6,6 +6,7 @@ from astrbot.core.star.register import (
     register_platform_adapter_type as platform_adapter_type,
     register_permission_type as permission_type,
     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
@@ -31,5 +32,6 @@ __all__ = [
     'on_llm_request',
     'llm_tool',
     'on_decorating_result',
-    'after_message_sent'
+    'after_message_sent',
+    'on_llm_response'
 ]

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 *

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

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)

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 = "3.4.6"
+VERSION = "3.4.19"
 DB_PATH = "data/data_v3.db"
 
 # 默认配置
@@ -22,20 +22,47 @@ DEFAULT_CONFIG = {
         "id_whitelist_log": True,
         "wl_ignore_admin_on_group": True,
         "wl_ignore_admin_on_friend": True,
+        "reply_with_mention": False,
+        "reply_with_quote": False,
+        "path_mapping": [],
+        "segmented_reply": {
+            "enable": False,
+            "only_llm_result": True,
+            "interval": "1.5,3.5",
+            "regex": ".*?[。？！~…]+|.+$"
+        }
     },
     "provider": [],
     "provider_settings": {
         "enable": True,
         "wake_prefix": "",
         "web_search": False,
+        "web_search_link": False,
         "identifier": False,
         "datetime_system_prompt": True,
-        "default_personality": "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。",
+        "default_personality": "default",
         "prompt_prefix": "",
     },
     "provider_stt_settings": {
-      "enable": False,
-      "provider_id": "",  
+        "enable": False,
+        "provider_id": "",
+    },
+    "provider_tts_settings": {
+        "enable": False,
+        "provider_id": "",
+    },
+    "provider_ltm_settings": {
+        "group_icl_enable": False,
+        "group_message_max_cnt": 300,
+        "image_caption": False,
+        "image_caption_prompt": "Please describe the image using Chinese.",
+        "active_reply": {
+            "enable": False,
+            "method": "possibility_reply",
+            "possibility_reply": 0.1,
+            "prompt": "",
+        },
+        "put_history_to_prompt": True,
     },
     "content_safety": {
         "internal_keywords": {"enable": True, "extra_keywords": []},
@@ -56,6 +83,7 @@ DEFAULT_CONFIG = {
     "pip_install_arg": "",
     "plugin_repo_mirror": "",
     "knowledge_db": {},
+    "persona": [],
 }
 
 
@@ -84,7 +112,15 @@ CONFIG_METADATA_2 = {
                         "ws_reverse_host": "",
                         "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": "这里填写你的局域网IP或者公网服务器IP",
+                        "port": 11451,
+                    },
                 },
                 "items": {
                     "id": {
@@ -158,6 +194,31 @@ CONFIG_METADATA_2 = {
                             },
                         },
                     },
+                    "segmented_reply": {
+                        "description": "分段回复",
+                        "type": "object",
+                        "items": {
+                            "enable": {
+                                "description": "启用分段回复",
+                                "type": "bool",
+                            },
+                            "only_llm_result": {
+                                "description": "仅对 LLM 结果分段",
+                                "type": "bool",
+                            },
+                            "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`",
+                            },
+                            "regex": {
+                                "description": "正则表达式",
+                                "type": "string",
+                                "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)",
+                            },
+                        },
+                    },
                     "reply_prefix": {
                         "description": "回复前缀",
                         "type": "string",
@@ -170,13 +231,14 @@ CONFIG_METADATA_2 = {
                     },
                     "enable_id_white_list": {
                         "description": "启用 ID 白名单",
-                        "type": "bool"
+                        "type": "bool",
                     },
                     "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",
                     },
                     "id_whitelist_log": {
                         "description": "打印白名单日志",
@@ -191,6 +253,23 @@ CONFIG_METADATA_2 = {
                         "description": "管理员私聊消息无视 ID 白名单",
                         "type": "bool",
                     },
+                    "reply_with_mention": {
+                        "description": "回复时 @ 发送者",
+                        "type": "bool",
+                        "hint": "启用后，机器人回复消息时会 @ 发送者。实际效果以具体的平台适配器为准。",
+                    },
+                    "reply_with_quote": {
+                        "description": "回复时引用消息",
+                        "type": "bool",
+                        "hint": "启用后，机器人回复消息时会引用原消息。实际效果以具体的平台适配器为准。",
+                    },
+                    "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": {
@@ -242,10 +321,21 @@ CONFIG_METADATA_2 = {
                 "type": "list",
                 "config_template": {
                     "openai": {
-                        "id": "default",
+                        "id": "openai",
                         "type": "openai_chat_completion",
                         "enable": True,
                         "key": [],
+                        "api_base": "https://api.openai.com/v1",
+                        "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": "",
                         "model_config": {
                             "model": "gpt-4o-mini",
@@ -256,7 +346,7 @@ CONFIG_METADATA_2 = {
                         "type": "openai_chat_completion",
                         "enable": True,
                         "key": ["ollama"],  # ollama 的 key 默认是 ollama
-                        "api_base": "http://localhost:11434",
+                        "api_base": "http://localhost:11434/v1",
                         "model_config": {
                             "model": "llama3.1-8b",
                         },
@@ -301,6 +391,16 @@ CONFIG_METADATA_2 = {
                             "model": "glm-4-flash",
                         },
                     },
+                    "硅基流动": {
+                        "id": "siliconflow",
+                        "type": "openai_chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "api_base": "https://api.siliconflow.cn/v1",
+                        "model_config": {
+                            "model": "deepseek-ai/DeepSeek-V3",
+                        },
+                    },
                     "llmtuner": {
                         "id": "llmtuner_default",
                         "type": "llm_tuner",
@@ -334,14 +434,30 @@ CONFIG_METADATA_2 = {
                         "id": "whisper",
                         "type": "openai_whisper_selfhost",
                         "model": "tiny",
-                    }
+                    },
+                    "openai_tts(API)": {
+                        "id": "openai_tts",
+                        "type": "openai_tts_api",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "",
+                        "model": "tts-1",
+                        "openai-tts-voice": "alloy",
+                        "timeout": "20",
+                    },
                 },
                 "items": {
+                    "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'",
+                    },
                     "whisper_hint": {
                         "description": "本地部署 Whisper 模型须知",
                         "type": "string",
                         "hint": "启用前请 pip 安装 openai-whisper 库（N卡用户大约下载 2GB，主要是 torch 和 cuda，CPU 用户大约下载 1 GB），并且安装 ffmpeg。否则将无法正常转文字。",
-                        "obvious_hint": True
+                        "obvious_hint": True,
                     },
                     "id": {
                         "description": "ID",
@@ -367,7 +483,8 @@ 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。支持 Ollama 开放的 API 地址。如果您确认填写正确但是使用时出现了 404 异常，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": {
                         "description": "基座模型路径",
@@ -431,7 +548,7 @@ CONFIG_METADATA_2 = {
                         "description": "Dify Workflow 输出变量名",
                         "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。",
-                    }
+                    },
                 },
             },
             "provider_settings": {
@@ -442,7 +559,7 @@ CONFIG_METADATA_2 = {
                         "description": "启用大语言模型聊天",
                         "type": "bool",
                         "hint": "如需切换大语言模型提供商，请使用 `/provider` 命令。",
-                        "obvious_hint": True
+                        "obvious_hint": True,
                     },
                     "wake_prefix": {
                         "description": "LLM 聊天额外唤醒前缀",
@@ -452,22 +569,31 @@ 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": {
-                        "description": "默认人格",
+                        "description": "默认采用的人格情景的名称",
                         "type": "string",
-                        "hint": "默认人格（情境设置/System Prompt）文本。",
+                        "hint": "",
                     },
                     "prompt_prefix": {
                         "description": "Prompt 前缀文本",
@@ -476,6 +602,46 @@ CONFIG_METADATA_2 = {
                     },
                 },
             },
+            "persona": {
+                "description": "人格情景设置",
+                "type": "list",
+                "config_template": {
+                    "新人格情景": {
+                        "name": "",
+                        "prompt": "",
+                        "begin_dialogs": [],
+                        "mood_imitation_dialogs": [],
+                    }
+                },
+                "tmpl_display_title": "name",
+                "items": {
+                    "name": {
+                        "description": "人格名称",
+                        "type": "string",
+                        "hint": "人格名称，用于在多个人格中区分。使用 /persona 指令可切换人格。在 大语言模型设置 处可以设置默认人格。",
+                        "obvious_hint": True,
+                    },
+                    "prompt": {
+                        "description": "设定(系统提示词)",
+                        "type": "text",
+                        "hint": "填写人格的身份背景、性格特征、兴趣爱好、个人经历、口头禅等。",
+                    },
+                    "begin_dialogs": {
+                        "description": "预设对话",
+                        "type": "list",
+                        "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": {"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,
+                    },
+                },
+            },
             "provider_stt_settings": {
                 "description": "语音转文本(STT)",
                 "type": "object",
@@ -484,7 +650,7 @@ CONFIG_METADATA_2 = {
                         "description": "启用语音转文本(STT)",
                         "type": "bool",
                         "hint": "启用前请在 服务提供商配置 处创建支持 语音转文本任务 的提供商。如 whisper。",
-                        "obvious_hint": True
+                        "obvious_hint": True,
                     },
                     "provider_id": {
                         "description": "提供商 ID，不填则默认第一个STT提供商",
@@ -493,6 +659,87 @@ CONFIG_METADATA_2 = {
                     },
                 },
             },
+            "provider_tts_settings": {
+                "description": "文本转语音(TTS)",
+                "type": "object",
+                "items": {
+                    "enable": {
+                        "description": "启用文本转语音(TTS)",
+                        "type": "bool",
+                        "hint": "启用前请在 服务提供商配置 处创建支持 语音转文本任务 的提供商。如 openai_tts。",
+                        "obvious_hint": True,
+                    },
+                    "provider_id": {
+                        "description": "提供商 ID，不填则默认第一个TTS提供商",
+                        "type": "string",
+                        "hint": "文本转语音提供商 ID。如果不填写将使用载入的第一个提供商。",
+                    },
+                },
+            },
+            "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_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",
+                            },
+                            "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，prompt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。",
+                            },
+                        },
+                    },
+                    "put_history_to_prompt": {
+                        "description": "将群聊历史记录作为 prompt",
+                        "type": "bool",
+                        "obvious_hint": True,
+                        "hint": "需要先启用 group_icl_enable。此功能会将群聊历史记录放到 prompt 再请求。如果关闭，则是放在 system_prompt。如果开启了主动回复，建议启用，模型能够更好地完成回复任务。",
+                    }
+                },
+            },
         },
     },
     "misc_config_group": {
@@ -502,7 +749,8 @@ 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",
@@ -512,7 +760,7 @@ CONFIG_METADATA_2 = {
             "admins_id": {
                 "description": "管理员 ID",
                 "type": "list",
-                "items": {"type": "int"},
+                "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 `/myid` 指令获得。回车添加，可添加多个。",
             },
             "http_proxy": {

astrbot/core/core_lifecycle.py

@@ -1,3 +1,4 @@
+import traceback
 import asyncio
 import time
 import threading
@@ -6,7 +7,6 @@ from .event_bus import EventBus
 from . import astrbot_config
 from asyncio import Queue
 from typing import List
-from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot.core.pipeline.scheduler import PipelineScheduler, PipelineContext
 from astrbot.core.star import PluginManager
 from astrbot.core.platform.manager import PlatformManager
@@ -25,9 +25,8 @@ class AstrBotCoreLifecycle:
         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']
     
     async def initialize(self):
         logger.info("AstrBot v"+ VERSION)
@@ -81,12 +80,30 @@ class AstrBotCoreLifecycle:
         for task in self.star_context._register_tasks:
             extra_tasks.append(asyncio.create_task(task, name=task.__name__))
         
-        self.curr_tasks = [event_bus_task, *platform_tasks, *extra_tasks]
+        # self.curr_tasks = [event_bus_task, *platform_tasks, *extra_tasks]
+        
+        tasks_ = [event_bus_task, *platform_tasks, *extra_tasks]
+        for task in tasks_:
+            self.curr_tasks.append(asyncio.create_task(self._task_wrapper(task), name=task.get_name()))
+        
         self.start_time = int(time.time())
+        
+    async def _task_wrapper(self, task: asyncio.Task):
+        try:
+            await task
+        except asyncio.CancelledError:
+            pass
+        except Exception as e:
+            
+            logger.error(f"------- 任务 {task.get_name()} 发生错误: {e}")
+            for line in traceback.format_exc().split("\n"):
+                logger.error(f"|    {line}")
+            logger.error("-------")
     
     async def start(self):
         self._load()
         logger.info("AstrBot 启动完成。")
+        
         await asyncio.gather(*self.curr_tasks, return_exceptions=True)
         
     async def stop(self):

astrbot/core/message/components.py

@@ -123,7 +123,7 @@ class Record(BaseMessageComponent):
     proxy: T.Optional[bool] = True
     timeout: T.Optional[int] = 0
     # 额外
-    path: T.Optional[str] # 用这个
+    path: T.Optional[str]
 
     def __init__(self, file: T.Optional[str], **_):
         for k in _.keys():
@@ -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

astrbot/core/message/message_event_result.py

@@ -13,12 +13,10 @@ class MessageChain():
     Attributes:
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
-        `is_split_` (bool): 用于标记是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
     '''
     
     chain: List[BaseMessageComponent] = field(default_factory=list)
     use_t2i_: Optional[bool] = None # None 为跟随用户设置
-    is_split_: Optional[bool] = False # 是否将消息分条发送。默认为 False。启用后，将会依次发送 chain 中的每个 component。
     
     def message(self, message: str):
         '''添加一条文本消息到消息链 `chain` 中。
@@ -77,16 +75,6 @@ class MessageChain():
         '''
         self.use_t2i_ = use_t2i
         return self
-    
-    def is_split(self, is_split: bool):
-        '''设置是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
-        
-        Note:
-            具体的效果以各适配器实现为准。
-            
-        '''
-        self.is_split_ = is_split
-        return self
 
 class EventResultType(enum.Enum):
     '''用于描述事件处理的结果类型。
@@ -113,7 +101,6 @@ class MessageEventResult(MessageChain):
     Attributes:
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
-        `is_split_` (bool): 用于标记是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
         `result_type` (EventResultType): 事件处理的结果类型。
     '''
     
@@ -139,7 +126,7 @@ class MessageEventResult(MessageChain):
         '''
         return self.result_type == EventResultType.STOP
     
-    def set_result_content_type(self, typ: EventResultType) -> 'MessageEventResult':
+    def set_result_content_type(self, typ: ResultContentType) -> 'MessageEventResult':
         '''设置事件处理的结果类型。
         
         Args:
@@ -148,5 +135,15 @@ class MessageEventResult(MessageChain):
         self.result_content_type = typ
         return self
     
+    def is_llm_result(self) -> bool:
+        '''是否为 LLM 结果。
+        '''
+        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

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",

astrbot/core/pipeline/preprocess_stage/stage.py

@@ -5,7 +5,7 @@ from ..stage import Stage, register_stage
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core import logger
-from astrbot.core.message.components import Plain, Record
+from astrbot.core.message.components import Plain, Record, Image
 
 @register_stage
 class PreProcessStage(Stage):
@@ -16,26 +16,39 @@ class PreProcessStage(Stage):
         self.plugin_manager = ctx.plugin_manager
         
         self.stt_settings: dict = self.config.get('provider_stt_settings', {})
+        self.platform_settings: dict = self.config.get('platform_settings', {})
         
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         '''在处理事件之前的预处理'''
-
+        # 路径映射
+        if mappings := self.platform_settings.get('path_mapping', []):
+            # 支持 Record，Image 消息段的路径映射。
+            message_chain = event.get_messages()
+            
+            for idx, component in enumerate(message_chain):
+                if isinstance(component, (Record, Image)) and component.url:
+                    for mapping in mappings:
+                        from_, to_ = mapping.split(":")
+                        from_ = from_.removesuffix("/")
+                        to_ = to_.removesuffix("/")
+                        
+                        url = component.url.removeprefix("file://")
+                        if url.startswith(from_):
+                            component.url = url.replace(from_, to_, 1)
+                            logger.debug(f"路径映射: {url} -> {component.url}")
+                    message_chain[idx] = component
+        
+        # STT
         if self.stt_settings.get('enable', False):
-            # STT 处理
             # TODO: 独立
             stt_provider = self.plugin_manager.context.provider_manager.curr_stt_provider_inst
             if stt_provider:
                 message_chain = event.get_messages()
                 for idx, component in enumerate(message_chain):
                     if isinstance(component, Record) and component.url:
-                        
-                        path = component.url
-                        
-                        path.removeprefix("file:///")
-                        
+                        path = component.url.removeprefix("file://")
                         retry = 5
-                        
                         for i in range(retry):
                             try:
                                 result = await stt_provider.get_text(audio_url=path)
@@ -48,7 +61,7 @@ class PreProcessStage(Stage):
                             except FileNotFoundError as e:
                                 # napcat workaround
                                 logger.warning(e)
-                                logger.warning(f"语音文件不存在: {path}, 重试中: {i + 1}/{retry}")
+                                logger.warning(f"重试中: {i + 1}/{retry}")
                                 await asyncio.sleep(0.5)
                                 continue
                             except BaseException as e:

astrbot/core/pipeline/process_stage/method/dify_request.py

@@ -21,6 +21,10 @@ class DifyRequestSubStage(Stage):
         req: ProviderRequest = None
         
         provider = self.ctx.plugin_manager.context.get_using_provider()
+        
+        if not provider:
+            return
+        
         if provider.meta().type != "dify":
             return
         

astrbot/core/pipeline/process_stage/method/llm_request.py

@@ -17,6 +17,13 @@ class LLMRequestSubStage(Stage):
     
     async def initialize(self, ctx: PipelineContext) -> None:
         self.ctx = ctx
+        self.bot_wake_prefixs = ctx.astrbot_config['wake_prefix'] # list
+        self.provider_wake_prefix = ctx.astrbot_config['provider_settings']['wake_prefix'] # str
+        
+        for bwp in self.bot_wake_prefixs:
+            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):]
         
     async def process(self, event: AstrMessageEvent, _nested: bool = False) -> Union[None, AsyncGenerator[None, None]]:
         req: ProviderRequest = None
@@ -30,10 +37,10 @@ class LLMRequestSubStage(Stage):
             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']):
+            if self.provider_wake_prefix:
+                if not event.message_str.startswith(self.provider_wake_prefix):
                     return
-            req.prompt = event.message_str[len(self.ctx.astrbot_config['provider_settings']['wake_prefix']):]
+            req.prompt = event.message_str[len(self.provider_wake_prefix):]
             req.func_tool = self.ctx.plugin_manager.context.get_llm_tool_manager()
             for comp in event.message_obj.message:
                 if isinstance(comp, Image):
@@ -44,7 +51,7 @@ class LLMRequestSubStage(Stage):
             session_provider_context = provider.session_memory.get(event.session_id)
             req.contexts = session_provider_context if session_provider_context else []
             
-        if not req.prompt:
+        if not req.prompt and not req.image_urls:
             return
             
         # 执行请求 LLM 前事件。
@@ -61,12 +68,23 @@ class LLMRequestSubStage(Stage):
             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())
+            
             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 = {}
@@ -98,5 +116,5 @@ class LLMRequestSubStage(Stage):
 
         except BaseException as e:
             logger.error(traceback.format_exc())
-            event.set_result(MessageEventResult().message("AstrBot 请求 LLM 资源失败：" + str(e)))
+            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

astrbot/core/pipeline/process_stage/method/star_request.py

@@ -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()

astrbot/core/pipeline/process_stage/stage.py

@@ -37,7 +37,11 @@ class ProcessStage(Stage):
                     # 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
@@ -49,6 +53,11 @@ class ProcessStage(Stage):
         if not event._has_send_oper and event.is_at_or_wake_command:
             if (event.get_result() and not event.get_result().is_stopped()) or not event.get_result():
                 provider = self.ctx.plugin_manager.context.get_using_provider()
+                
+                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
+                
                 match provider.meta().type:
                     case "dify":
                         async for _ in self.dify_request_sub_stage.process(event):

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))

astrbot/core/pipeline/respond/stage.py

@@ -1,7 +1,10 @@
+import random
+import asyncio
 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.star.star_handler import star_handlers_registry, EventType
 
@@ -9,6 +12,19 @@ from astrbot.core.star.star_handler import star_handlers_registry, EventType
 class RespondStage(Stage):
     async def initialize(self, ctx: PipelineContext):
         self.ctx = ctx
+        
+        # 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']
+        interval_str: str = ctx.astrbot_config['platform_settings']['segmented_reply']['interval']
+        interval_str_ls = interval_str.replace(" ", "").split(",")
+        try:
+            self.interval = [float(t) for t in interval_str_ls]
+        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 process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         result = event.get_result()
@@ -16,7 +32,16 @@ class RespondStage(Stage):
             return
 
         if len(result.chain) > 0:
-            await event.send(result)
+            await event._pre_send()
+            
+            if self.enable_seg and ((self.only_llm_result and result.is_llm_result()) or not self.only_llm_result):
+                # 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]))
+            else:
+                await event.send(result)
+            await event._post_send()
             logger.info(f"AstrBot -> {event.get_sender_name()}/{event.get_sender_id()}: {event._outline_chain(result.chain)}")
         
         handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnAfterMessageSentEvent)

astrbot/core/pipeline/result_decorate/stage.py

@@ -1,10 +1,13 @@
 import time
+import re
+import traceback
 from typing import Union, AsyncGenerator
 from ..stage import register_stage
 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
+from astrbot.core.message.components import Plain, Image, At, Reply, Record
 from astrbot.core import html_renderer
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
 
@@ -13,7 +16,14 @@ class ResultDecorateStage:
     async def initialize(self, ctx: PipelineContext):
         self.ctx = ctx
         self.reply_prefix = ctx.astrbot_config['platform_settings']['reply_prefix']
-        self.t2i = ctx.astrbot_config['t2i']
+        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']
+        
+        # 分段回复
+        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']
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         result = event.get_result()
@@ -28,10 +38,53 @@ class ResultDecorateStage:
         if len(result.chain) > 0:
             # 回复前缀
             if self.reply_prefix:
-                result.chain.insert(0, Plain(self.reply_prefix))
+                for comp in result.chain:
+                    if isinstance(comp, Plain):
+                        comp.text = self.reply_prefix + comp.text
+                        break
+            
+             # 分段回复 
+            if self.enable_segmented_reply:
+                if (self.only_llm_result and result.is_llm_result()) or not self.only_llm_result:
+                    new_chain = []
+                    for comp in result.chain:
+                        if isinstance(comp, Plain):
+                            split_response = re.findall(r".*?[。？！~…]+|.+$", comp.text)
+                            if not split_response:
+                                new_chain.append(comp)
+                                continue
+                            for seg in split_response:
+                                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():
+                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: " + 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))
+                            else:
+                                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("TTS 失败，使用文本发送。")
+                            new_chain.append(comp)
+                    else:
+                        new_chain.append(comp)
+                result.chain = new_chain
             
             # 文本转图片
-            if (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):
@@ -48,4 +101,14 @@ class ResultDecorateStage:
                     if time.time() - render_start > 3:
                         logger.warning("文本转图片耗时超过了 3 秒，如果觉得很慢可以使用 /t2i 关闭文本转图片模式。")
                     if url:
-                        result.chain = [Image.fromURL(url)]
+                        result.chain = [Image.fromURL(url)]
+            
+            # 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:
+                result.chain.insert(0, Reply(id=event.message_obj.message_id))

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':

astrbot/core/platform/astr_message_event.py

@@ -179,6 +179,15 @@ class AstrMessageEvent(abc.ABC):
         await Metric.upload(msg_event_tick = 1, adapter_name = self.platform_meta.name)
         self._has_send_oper = True
         
+    async def _pre_send(self):
+        '''调度器会在执行 send() 前调用该方法'''
+        pass
+    
+    async def _post_send(self):
+        '''调度器会在执行 send() 后调用该方法'''
+        pass
+        
+        
     def set_result(self, result: Union[MessageEventResult, str]):
         '''设置消息事件的结果。
         
@@ -287,6 +296,7 @@ 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,
@@ -302,11 +312,13 @@ class AstrMessageEvent(abc.ABC):
         
         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。
+        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。
         '''
         return ProviderRequest(
             prompt = prompt,
             session_id = session_id,
             image_urls = image_urls,
+            func_tool = func_tool_manager,
             contexts = contexts,
             system_prompt = system_prompt
         )

astrbot/core/platform/manager.py

@@ -24,7 +24,12 @@ class PlatformManager():
                 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
+                    try:
+                        from .sources.vchat.vchat_platform_adapter import VChatPlatformAdapter # noqa: F401
+                    except BaseException:
+                        logger.warning("当前 astrbot 已不维护 vchat 的接入，如有需要请 pip 安装 vchat 然后重启")
+                case "gewechat":
+                    from .sources.gewechat.gewechat_platform_adapter import GewechatPlatformAdapter # noqa: F401
         
 
     async def initialize(self):

astrbot/core/platform/register.py

@@ -27,6 +27,8 @@ def register_platform_adapter(
                 default_config_tmpl['type'] = adapter_name
             if 'enable' not in default_config_tmpl:
                 default_config_tmpl['enable'] = False
+            if 'id' not in default_config_tmpl:
+                default_config_tmpl['id'] = adapter_name
 
         pm = PlatformMetadata(
             name=adapter_name,

astrbot/core/platform/sources/aiocqhttp/aiocqhttp_message_event.py

@@ -3,7 +3,7 @@ import random
 import asyncio
 
 from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.message_components import Plain, Image
+from astrbot.api.message_components import Plain, Image, Record
 from aiocqhttp import CQHttp
 from astrbot.core.utils.io import file_to_base64, download_image_by_url
 
@@ -20,15 +20,19 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
             d = segment.toDict()
             if isinstance(segment, Plain):
                 d['type'] = 'text'
-            if isinstance(segment, Image):
+            if isinstance(segment, (Image, Record)):
                 # convert to base64
                 if segment.file and segment.file.startswith("file:///"):
-                    image_base64 = file_to_base64(segment.file[8:])
+                    bs64_data = file_to_base64(segment.file[8:])
                     image_file_path = segment.file[8:]
                 elif segment.file and segment.file.startswith("http"):
                     image_file_path = await download_image_by_url(segment.file)
-                    image_base64 = file_to_base64(image_file_path)
-                d['data']['file'] = image_base64
+                    bs64_data = file_to_base64(image_file_path)
+                else:
+                    bs64_data = file_to_base64(segment.file)
+                d['data'] = {
+                    'file': bs64_data,
+                }
             ret.append(d)
         return ret
 
@@ -36,11 +40,5 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
         ret = await AiocqhttpMessageEvent._parse_onebot_json(message)
         if os.environ.get('TEST_MODE', 'off') == 'on':
             return
-        
-        if message.is_split_: # 分条发送
-            for m in ret:
-                await self.bot.send(self.message_obj.raw_message, [m])
-                await asyncio.sleep(random.uniform(0.75, 2.5))
-        else:
-            await self.bot.send(self.message_obj.raw_message, ret)
+        await self.bot.send(self.message_obj.raw_message, ret)
         await super().send(message)

astrbot/core/platform/sources/gewechat/client.py

@@ -0,0 +1,352 @@
+import threading
+import asyncio
+import aiohttp
+import quart
+import base64
+
+from astrbot.api.platform import AstrBotMessage, MessageMember, MessageType
+from astrbot.api.message_components import Plain, Image, At, Record
+from astrbot.api import logger, sp
+from .downloader import GeweDownloader
+from astrbot.core.utils.io import download_image_by_url
+
+
+class SimpleGewechatClient():
+    '''针对 Gewechat 的简单实现。
+    
+    @author: Soulter
+    @website: https://github.com/Soulter
+    '''
+    def __init__(self, base_url: str, nickname: str, host: str, port: int, event_queue: asyncio.Queue):
+        self.base_url = base_url
+        if self.base_url.endswith('/'):
+            self.base_url = self.base_url[:-1]
+            
+        self.download_base_url = self.base_url.split(':')[:-1] # 去掉端口
+        self.download_base_url = ':'.join(self.download_base_url) + ":2532/download/"
+        
+        self.base_url += "/v2/api"
+        
+        logger.info(f"Gewechat API: {self.base_url}")
+        logger.info(f"Gewechat 下载 API: {self.download_base_url}")
+        
+        if isinstance(port, str):
+            port = int(port)
+            
+        self.token = None
+        self.headers = {}
+        self.nickname = nickname
+        self.appid = sp.get(f"gewechat-appid-{nickname}", "")
+        
+        self.server = quart.Quart(__name__)
+        self.server.add_url_rule('/astrbot-gewechat/callback', view_func=self.callback, methods=['POST'])
+        self.server.add_url_rule('/astrbot-gewechat/file/<file_id>', view_func=self.handle_file, methods=['GET'])
+        
+        self.host = host
+        self.port = port 
+        self.callback_url = f"http://{self.host}:{self.port}/astrbot-gewechat/callback"
+        self.file_server_url = f"http://{self.host}:{self.port}/astrbot-gewechat/file"
+        
+        self.event_queue = event_queue
+        
+        self.multimedia_downloader = None
+    
+    async def get_token_id(self):
+        async with aiohttp.ClientSession() as session:
+            async with session.post(f"{self.base_url}/tools/getTokenId") as resp:
+                json_blob = await resp.json()
+                self.token = json_blob['data']
+                logger.info(f"获取到 Gewechat Token: {self.token}")
+                self.headers = {
+                    "X-GEWE-TOKEN": self.token
+                }
+                
+    async def _convert(self, data: dict) -> AstrBotMessage:
+        type_name = data['TypeName']
+        if type_name == "Offline":
+            logger.critical("收到 gewechat 下线通知。")
+            return
+        
+        abm = AstrBotMessage()
+        d = data['Data']
+    
+        from_user_name = d['FromUserName']['string'] # 消息来源
+        d['to_wxid'] = from_user_name # 用于发信息
+        
+        abm.message_id = str(d.get('MsgId'))
+        abm.session_id = from_user_name
+        abm.self_id = data['Wxid'] # 机器人的 wxid
+        
+        user_id = "" # 发送人 wxid
+        content = d['Content']['string'] # 消息内容
+        
+        at_me = False
+        if "@chatroom" in from_user_name:
+            abm.type = MessageType.GROUP_MESSAGE
+            _t = content.split(':\n')
+            user_id = _t[0]
+            content = _t[1]
+            if '\u2005' in content: 
+                # at
+                content = content.split('\u2005')[1]
+            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
+            
+        abm.message = []
+        if at_me:
+            abm.message.insert(0, At(qq=abm.self_id))
+        
+        user_real_name = d.get('PushContent', 'unknown : ').split(' : ')[0] \
+            .replace('在群聊中@了你', '') \
+            .replace('在群聊中发了一段语音', '') # 真实昵称
+        abm.sender = MessageMember(user_id, user_real_name)
+        abm.raw_message = d
+        abm.message_str = ""
+        # 不同消息类型
+        match d['MsgType']:
+            case 1:
+                # 文本消息
+                abm.message.append(Plain(content))
+                abm.message_str = content
+            case 3:
+                # 图片消息
+                file_url = await self.multimedia_downloader.download_image(
+                    self.appid, 
+                    content
+                )
+                logger.debug(f"下载图片: {file_url}")
+                file_path = await download_image_by_url(file_url)
+                abm.message.append(Image(file=file_path, url=file_path))
+                
+            case 34:
+                # 语音消息
+                # data = await self.multimedia_downloader.download_voice(
+                #     self.appid, 
+                #     content, 
+                #     abm.message_id
+                # )
+                # print(data)
+                if 'ImgBuf' in d and 'buffer' in d['ImgBuf']:
+                    voice_data = base64.b64decode(d['ImgBuf']['buffer'])
+                    file_path = f"data/temp/gewe_voice_{abm.message_id}.silk"
+                    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"abm: {abm}")
+        return abm
+
+    async def callback(self):
+        data = await quart.request.json
+        logger.debug(f"收到 gewechat 回调: {data}")
+        
+        if data.get('testMsg', None):
+            return quart.jsonify({"r": "AstrBot ACK"})
+        
+        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):
+        file_path = f"data/temp/{file_id}"
+        return await quart.send_file(file_path)
+        
+    async def _set_callback_url(self):
+        logger.info("设置回调，请等待...")
+        await asyncio.sleep(3)
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/tools/setCallback",
+                headers=self.headers,
+                json={
+                    "token": self.token,
+                    "callbackUrl": self.callback_url
+                }
+            ) as resp:
+                json_blob = await resp.json()
+                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。")
+        
+    async def start_polling(self):
+        threading.Thread(target=asyncio.run, args=(self._set_callback_url(),)).start()
+        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("gewechat 适配器已关闭。")
+        
+    async def check_online(self, appid: str):
+        # /login/checkOnline
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/login/checkOnline",
+                headers=self.headers,
+                json={
+                    "appId": appid
+                }
+            ) as resp:
+                json_blob = await resp.json()
+                return json_blob['data']
+            
+    async def logout(self):
+        if self.appid:
+            online = await self.check_online(self.appid)
+            if online:
+                async with aiohttp.ClientSession() as session:
+                    async with session.post(
+                        f"{self.base_url}/login/logout",
+                        headers=self.headers,
+                        json={
+                            "appId": self.appid
+                        }
+                    ) as resp:
+                        json_blob = await resp.json()
+                        logger.info(f"登出结果: {json_blob}")
+        
+    async def login(self):
+        if self.token is None:
+            await self.get_token_id()
+            
+        self.multimedia_downloader = GeweDownloader(self.base_url, self.download_base_url, self.token)
+        
+        if self.appid:
+            online = await self.check_online(self.appid)
+            if online:
+                logger.info(f"APPID: {self.appid} 已在线")
+                return
+        
+        payload = {
+            "appId": self.appid
+        }
+        
+        if self.appid:
+            logger.info(f"使用 APPID: {self.appid}, {self.nickname}")
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/login/getLoginQrCode", 
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                if json_blob['ret'] != 200:
+                    raise Exception(f"获取二维码失败: {json_blob}")
+                qr_data = json_blob['data']['qrData']
+                qr_uuid = json_blob['data']['uuid']
+                appid = json_blob['data']['appId']
+                logger.info(f"APPID: {appid}")
+                logger.warning(f"请打开该网址，然后使用微信扫描二维码登录: https://api.cl2wm.cn/api/qrcode/code?text={qr_data}")
+        
+        # 执行登录
+        retry_cnt = 64
+        payload.update({
+            "uuid": qr_uuid,
+            "appId": appid
+        })
+        while retry_cnt > 0:
+            retry_cnt -= 1
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    f"{self.base_url}/login/checkLogin",
+                    headers=self.headers,
+                    json=payload
+                ) 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...")
+                    else:
+                        logger.warning(f"未知状态: {status}")
+            await asyncio.sleep(5)
+            
+        if 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):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "content": content,
+        }
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postText",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送消息结果: {json_blob}")
+                
+    async def post_image(self, to_wxid, image_url: str):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "imgUrl": image_url,
+        }
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postImage",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送图片结果: {json_blob}")
+                
+    async def post_voice(self, to_wxid, voice_url: str, voice_duration: int):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "voiceUrl": voice_url,
+            "voiceDuration": voice_duration
+        }
+        
+        logger.debug(f"发送语音: {payload}")
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postVoice",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送语音结果: {json_blob}")

astrbot/core/platform/sources/gewechat/downloader.py

@@ -0,0 +1,51 @@
+from astrbot import logger
+import aiohttp
+import json
+
+class GeweDownloader():
+    def __init__(self, base_url: str, download_base_url: str, token: str):
+        self.base_url = base_url
+        self.download_base_url = download_base_url
+        self.headers = {
+            "Content-Type": "application/json",
+            "X-GEWE-TOKEN": token
+        }
+    
+    async def _post_json(self, baseurl: str, route: str, payload: dict):
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{baseurl}{route}",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                return await resp.read()
+            
+    async def download_voice(self, appid: str, xml: str, msg_id: str):
+        payload = {
+            "appId": appid,
+            "xml": xml,
+            "msgId": msg_id
+        }
+        return await self._post_json(self.base_url, "/message/downloadVoice", payload)
+    
+    async def download_image(self, appid: str, xml: str) -> str:
+        '''返回一个可下载的 URL'''
+        choices = [2, 3] #  2:常规图片 3:缩略图
+        
+        for choice in choices:
+            try:
+                payload = {
+                    "appId": appid,
+                    "xml": xml,
+                    "type": choice
+                }
+                data = await self._post_json(self.base_url, "/message/downloadImage", payload)
+                json_blob = json.loads(data)
+                if 'fileUrl' in json_blob['data']:
+                    return self.download_base_url + json_blob['data']['fileUrl']
+
+            except BaseException as e:
+                logger.error(f"gewe download image: {e}")
+                continue
+        
+        raise Exception("无法下载图片")

astrbot/core/platform/sources/gewechat/gewechat_event.py

@@ -0,0 +1,102 @@
+import wave
+import uuid
+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 .client import SimpleGewechatClient
+
+def get_wav_duration(file_path):
+    with wave.open(file_path, 'rb') as wav_file:
+        file_size = os.path.getsize(file_path)
+        n_channels, sampwidth, framerate, n_frames = wav_file.getparams()[:4]
+        if n_frames == 2147483647:
+            duration = (file_size - 44) / (n_channels * sampwidth * framerate)
+        else:
+            duration = n_frames / float(framerate)
+        return duration
+
+class GewechatPlatformEvent(AstrMessageEvent):
+    def __init__(
+            self, 
+            message_str: str, 
+            message_obj: AstrBotMessage, 
+            platform_meta: PlatformMetadata, 
+            session_id: str,
+            client: SimpleGewechatClient
+        ):
+        super().__init__(message_str, message_obj, platform_meta, session_id)
+        self.client = client
+        
+    @staticmethod
+    async def send_with_client(message: MessageChain, user_name: str):
+        pass
+                
+        
+    async def send(self, message: MessageChain):
+        to_wxid = self.message_obj.raw_message.get('to_wxid', None)
+        
+        if not to_wxid:
+            logger.error("无法获取到 to_wxid。")
+            return
+        
+        for comp in message.chain:
+            if isinstance(comp, Plain):
+                await self.client.post_text(to_wxid, 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
+                    
+                # 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')
+                img_path = os.path.abspath(img_path)
+                if os.path.commonpath([temp_directory, img_path]) != temp_directory:
+                    with open(img_path, "rb") as f:
+                        img_path = save_temp_img(f.read())
+
+                file_id = os.path.basename(img_path)
+                img_url = f"{self.client.file_server_url}/{file_id}"
+                logger.debug(f"gewe callback img url: {img_url}")
+                await self.client.post_image(to_wxid, img_url)
+            elif isinstance(comp, Record):
+                # 默认已经存在 data/temp 中
+                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
+                    
+                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())
+                
+                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}"
+                await self.client.post_voice(to_wxid, record_url, duration*1000)
+        await super().send(message)

astrbot/core/platform/sources/gewechat/gewechat_platform_adapter.py

@@ -0,0 +1,93 @@
+import sys
+import asyncio
+import os
+
+from astrbot.api.platform import Platform, AstrBotMessage, MessageType, PlatformMetadata
+from astrbot.api.event import MessageChain
+from astrbot.api import logger
+from astrbot.core.platform.astr_message_event import MessageSesion
+from ...register import register_platform_adapter
+from .gewechat_event import GewechatPlatformEvent
+from .client import SimpleGewechatClient
+from astrbot.core.message.components import Plain
+
+if sys.version_info >= (3, 12):
+    from typing import override
+else:
+    from typing_extensions import override
+            
+
+@register_platform_adapter("gewechat", "基于 gewechat 的 Wechat 适配器")
+class GewechatPlatformAdapter(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 = None
+    
+    @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
+        
+        for comp in message_chain.chain:
+            if isinstance(comp, Plain):
+                await self.client.post_text(to_wxid, comp.text)
+
+        await super().send_by_session(session, message_chain)
+    
+    @override
+    def meta(self) -> PlatformMetadata:
+        return PlatformMetadata(
+            "gewechat",
+            "基于 gewechat 的 Wechat 适配器",
+        )
+
+    @override
+    def run(self):
+        self.client = SimpleGewechatClient(
+            self.config['base_url'],
+            self.config['nickname'],
+            self.config['host'],
+            self.config['port'],
+            self._event_queue,
+        )
+        
+        async def on_event_received(abm: AstrBotMessage):
+            await self.handle_msg(abm)
+            
+        self.client.on_event_received = on_event_received
+        
+        return self._run()
+    
+    async def logout(self):
+        await self.client.logout()
+    
+    async def _run(self):
+        await self.client.login()
+        
+        await self.client.start_polling()
+        
+    
+    async def handle_msg(self, message: AstrBotMessage):
+        if message.type == MessageType.GROUP_MESSAGE:
+            if self.settingss['unique_session']:
+                message.session_id = message.sender.user_id + "_" + message.group_id
+        
+        message_event = GewechatPlatformEvent(
+            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)

astrbot/core/platform/sources/qqofficial/qqofficial_message_event.py

@@ -5,7 +5,7 @@ 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
+from astrbot.api.message_components import Plain, Image, Reply
 from botpy import Client
 from botpy.http import Route
 
@@ -14,12 +14,33 @@ class QQOfficialMessageEvent(AstrMessageEvent):
     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)
         self.bot = bot
+        self.send_buffer = None
         
     async def send(self, message: MessageChain):
+        if not self.send_buffer:
+            self.send_buffer = message
+        else:
+            self.send_buffer.chain.extend(message.chain)
+
+    async def _post_send(self):
+        '''QQ 官方 API 仅支持回复一次'''
         source = self.message_obj.raw_message
         assert isinstance(source, (botpy.message.Message, botpy.message.GroupMessage, botpy.message.DirectMessage, botpy.message.C2CMessage))
         
-        plain_text, image_base64, image_path = await QQOfficialMessageEvent._parse_to_qqofficial(message)
+        plain_text, image_base64, image_path = await QQOfficialMessageEvent._parse_to_qqofficial(self.send_buffer)
+        
+        ref = None
+        for i in self.send_buffer.chain:
+            if isinstance(i, Reply):
+                try:
+                    ref = self.message_obj.raw_message.message_reference
+                    ref = botpy.types.message.Reference(
+                        message_id=ref.message_id,
+                        ignore_get_message_error=False
+                    )
+                except BaseException as _:
+                    pass
+                break
         
         payload = {
             'content': plain_text,
@@ -28,27 +49,37 @@ class QQOfficialMessageEvent(AstrMessageEvent):
         
         match type(source):
             case botpy.message.GroupMessage:
+                if ref:
+                    payload['message_reference'] = ref
                 if image_base64:
                     media = await self.upload_group_and_c2c_image(image_base64, 1, group_openid=source.group_openid)
                     payload['media'] = media
                     payload['msg_type'] = 7
                 await self.bot.api.post_group_message(group_openid=source.group_openid, **payload)
             case botpy.message.C2CMessage:
+                if ref:
+                    payload['message_reference'] = ref
                 if image_base64:
                     media = await self.upload_group_and_c2c_image(image_base64, 1, openid=source.author.user_openid)
                     payload['media'] = media
                     payload['msg_type'] = 7
                 await self.bot.api.post_c2c_message(openid=source.author.user_openid, **payload)
             case botpy.message.Message:
+                if ref:
+                    payload['message_reference'] = ref
                 if image_path:
                     payload['file_image'] = image_path
                 await self.bot.api.post_message(channel_id=source.channel_id, **payload)
             case botpy.message.DirectMessage:
+                if ref:
+                    payload['message_reference'] = ref
                 if image_path:
                     payload['file_image'] = image_path
                 await self.bot.api.post_dms(guild_id=source.guild_id, **payload)
 
-        await super().send(message)
+        await super().send(self.send_buffer)
+        
+        self.send_buffer = None
             
     async def upload_group_and_c2c_image(self, image_base64: str, file_type: int, **kwargs) -> botpy.types.message.Media:
         payload = {
@@ -80,4 +111,7 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                 elif i.file and i.file.startswith("http"):
                     image_file_path = await download_image_by_url(i.file)
                     image_base64 = file_to_base64(image_file_path).replace("base64://", "")
+                else:
+                    image_base64 = file_to_base64(i.file).replace("base64://", "")
+                    image_file_path = i.file
         return plain_text, image_base64, image_file_path

astrbot/core/platform/sources/webchat/webchat_adapter.py

@@ -38,11 +38,13 @@ class WebChatAdapter(Platform):
         )
         
     async def send_by_session(self, session: MessageSesion, message_chain: MessageChain):
+        # abm.session_id = f"webchat!{username}!{cid}"
         plain = ""
+        cid = session.session_id.split("!")[-1]
         for comp in message_chain.chain:
             if isinstance(comp, Plain):
                 plain += comp.text
-        web_chat_back_queue.put_nowait(plain)
+        web_chat_back_queue.put_nowait((plain, cid))
         
         await super().send_by_session(session, message_chain)
         

astrbot/core/platform/sources/webchat/webchat_event.py

@@ -16,9 +16,11 @@ class WebChatMessageEvent(AstrMessageEvent):
             web_chat_back_queue.put_nowait(None)
             return
         
+        cid = self.session_id.split("!")[-1]
+        
         for comp in message.chain:
             if isinstance(comp, Plain):
-                web_chat_back_queue.put_nowait(comp.text)
+                web_chat_back_queue.put_nowait((comp.text, cid))
             elif isinstance(comp, Image):
                 # save image to local
                 filename = str(uuid.uuid4()) + ".jpg"
@@ -30,6 +32,10 @@ class WebChatMessageEvent(AstrMessageEvent):
                             f.write(f2.read())
                 elif comp.file and comp.file.startswith("http"):
                     await download_image_by_url(comp.file, path=path)
-                web_chat_back_queue.put_nowait(f"[IMAGE]{filename}")
+                else:
+                    with open(path, "wb") as f:
+                        with open(comp.file, "rb") as f2:
+                            f.write(f2.read())
+                web_chat_back_queue.put_nowait((f"[IMAGE]{filename}", cid))
         web_chat_back_queue.put_nowait(None)
         await super().send(message)

astrbot/core/provider/entites.py

@@ -2,6 +2,7 @@ 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
 
 
 class ProviderType(enum.Enum):
@@ -51,4 +52,7 @@ class LLMResponse:
     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

astrbot/core/provider/func_tool_manager.py

@@ -108,14 +108,21 @@ class FuncCall:
         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
         
 

astrbot/core/provider/manager.py

@@ -1,6 +1,7 @@
 import traceback
+import uuid
 from astrbot.core.config.astrbot_config import AstrBotConfig
-from .provider import Provider, STTProvider
+from .provider import Provider, STTProvider, TTSProvider, Personality
 from .entites import ProviderType
 from typing import List
 from astrbot.core.db import BaseDatabase
@@ -13,30 +14,92 @@ 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
+        for persona in self.persona_configs:
+            begin_dialogs = persona.get("begin_dialogs", [])
+            mood_imitation_dialogs = persona.get("mood_imitation_dialogs", [])
+            bd_processed = []
+            mid_processed = ""
+            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。")
+                    begin_dialogs = []
+                user_turn = True
+                for dialog in begin_dialogs:
+                    bd_processed.append({
+                        "role": "user" if user_turn else "assistant",
+                        "content": dialog,
+                        "_no_save": None # 不持久化到 db
+                    })
+                    user_turn = not user_turn
+            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。")
+                    mood_imitation_dialogs = []
+                user_turn = True
+                for dialog in mood_imitation_dialogs:
+                    role = "A" if user_turn else "B"
+                    mid_processed += f"{role}: {dialog}\n"
+                    if not user_turn:
+                        mid_processed += '\n'
+                    user_turn = not user_turn
+            
+            try:
+                persona = Personality(
+                    **persona, 
+                    _begin_dialogs_processed=bd_processed,
+                    _mood_imitation_dialogs_processed=mid_processed
+                )
+                if persona['name'] == self.default_persona_name:
+                    self.selected_default_persona = persona
+                self.personas.append(persona)
+            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]
+        
         
         self.provider_insts: List[Provider] = []
         '''加载的 Provider 的实例'''
         self.stt_provider_insts: List[STTProvider] = []
         '''加载的 Speech To Text Provider 的实例'''
+        self.tts_provider_insts: List[TTSProvider] = []
+        '''加载的 Text To Speech Provider 的实例'''
         self.llm_tools = llm_tools
         self.curr_provider_inst: Provider = None
         '''当前使用的 Provider 实例'''
         self.curr_stt_provider_inst: STTProvider = None
         '''当前使用的 Speech To Text Provider 实例'''
+        self.curr_tts_provider_inst: TTSProvider = None
+        '''当前使用的 Text To Speech Provider 实例'''
         self.loaded_ids = defaultdict(bool)
         self.db_helper = db_helper
         
+        # kdb(experimental)
         self.curr_kdb_name = ""
         kdb_cfg = config.get("knowledge_db", {})
         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:
@@ -56,25 +119,37 @@ class ProviderManager():
                         from .sources.whisper_api_source import ProviderOpenAIWhisperAPI # noqa: F401
                     case "openai_whisper_selfhost":
                         from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost # noqa: F401
+                    case "openai_tts_api":
+                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI # noqa: F401
             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")
+        selected_stt_provider_id = self.provider_stt_settings.get("provider_id")
+        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_tts_settings.get("enable", False)
+            
         for provider_config in self.providers_config:
             if not provider_config['enable']:
                 continue
             if provider_config['type'] not in provider_cls_map:
                 logger.error(f"未找到适用于 {provider_config['type']}({provider_config['id']}) 的提供商适配器，请检查是否已经安装或者名称填写错误。已跳过。")
                 continue
-            selected_provider_id = sp.get("curr_provider")
-            selected_stt_provider_id = self.provider_stt_settings.get("provider_id")
-            provider_enabled = self.provider_settings.get("enable", False)
-            stt_enabled = self.provider_stt_settings.get("enable", False)
-            
+
             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 ...")
             try:
@@ -91,10 +166,28 @@ class ProviderManager():
                     if selected_stt_provider_id == provider_config['id'] and stt_enabled:
                         self.curr_stt_provider_inst = inst
                         logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前语音转文本提供商适配器。")
+                        
+                elif provider_metadata.provider_type == ProviderType.TEXT_TO_SPEECH:
+                    # TTS 任务
+                    inst = provider_metadata.cls_type(provider_config, self.provider_settings)
+                    
+                    if getattr(inst, "initialize", None):
+                        await inst.initialize()
+                    
+                    self.tts_provider_insts.append(inst)
+                    if selected_tts_provider_id == provider_config['id'] and tts_enabled:
+                        self.curr_tts_provider_inst = inst
+                        logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前文本转语音提供商适配器。")
                     
                 elif provider_metadata.provider_type == ProviderType.CHAT_COMPLETION:
                     # 文本生成任务
-                    inst = provider_metadata.cls_type(provider_config, self.provider_settings, self.db_helper, self.provider_settings.get('persistant_history', True))
+                    inst = provider_metadata.cls_type(
+                        provider_config, 
+                        self.provider_settings, 
+                        self.db_helper,
+                        self.provider_settings.get('persistant_history', True),
+                        self.selected_default_persona
+                    )
                     
                     if getattr(inst, "initialize", None):
                         await inst.initialize()
@@ -114,11 +207,18 @@ class ProviderManager():
         if len(self.stt_provider_insts) > 0 and not self.curr_stt_provider_inst and stt_enabled:
             self.curr_stt_provider_inst = self.stt_provider_insts[0]
             
+        if len(self.tts_provider_insts) > 0 and not self.curr_tts_provider_inst and tts_enabled:
+            self.curr_tts_provider_inst = self.tts_provider_insts[0]
+            
         if not self.curr_provider_inst:
             logger.warning("未启用任何用于 文本生成 的提供商适配器。")
-        if self.provider_stt_settings.get("enable"):
-            if not self.curr_stt_provider_inst:
+            
+        if stt_enabled and not self.curr_stt_provider_inst:
                 logger.warning("未启用任何用于 语音转文本 的提供商适配器。")
+        
+        if tts_enabled and not self.curr_tts_provider_inst:
+                logger.warning("未启用任何用于 文本转语音 的提供商适配器。")
+        
 
     def get_insts(self):
         return self.provider_insts

astrbot/core/provider/provider.py

@@ -11,45 +11,26 @@ from dataclasses import dataclass
 class Personality(TypedDict):
     prompt: str = ""
     name: str = ""
+    begin_dialogs: List[str] = []
+    mood_imitation_dialogs: List[str] = []
+    
+    # cache
+    _begin_dialogs_processed: List[dict]
+    _mood_imitation_dialogs_processed: str
+    
     
 @dataclass
 class ProviderMeta():
     id: str
     model: str
     type: str
-
-
-class Provider(abc.ABC):
-    def __init__(
-        self, 
-        provider_config: dict,
-        provider_settings: dict, 
-        persistant_history: bool = True,
-        db_helper: BaseDatabase = None
-    ) -> None:
+    
+    
+class AbstractProvider(abc.ABC):
+    def __init__(self, provider_config: dict) -> None:
+        super().__init__()
         self.model_name = ""
-        '''当前使用的模型名称'''
-        
-        self.session_memory = defaultdict(list)
-        '''维护了 session_id 的上下文，**不包含 system 指令**。'''
-        
         self.provider_config = provider_config
-        
-        self.provider_settings = provider_settings
-        
-        self.curr_personality = Personality(prompt=provider_settings['default_personality'])
-        '''维护了当前的使用的 persona，即人格。'''
-        
-        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。")
 
     def set_model(self, model_name: str):
         '''设置当前使用的模型名称'''
@@ -59,6 +40,45 @@ class Provider(abc.ABC):
         '''获得当前使用的模型名称'''
         return self.model_name
     
+    def meta(self) -> ProviderMeta:
+        '''获取 Provider 的元数据'''
+        return ProviderMeta(
+            id=self.provider_config['id'],
+            model=self.get_model(),
+            type=self.provider_config['type']
+        )
+
+
+class Provider(AbstractProvider):
+    def __init__(
+        self, 
+        provider_config: dict,
+        provider_settings: dict, 
+        persistant_history: bool = True,
+        db_helper: BaseDatabase = None,
+        default_persona: Personality = None
+    ) -> 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['id']):
+                    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()
@@ -125,17 +145,11 @@ class Provider(abc.ABC):
         '''重置某一个 session_id 的上下文'''
         raise NotImplementedError()
 
-    def meta(self) -> ProviderMeta:
-        '''获取 Provider 的元数据'''
-        return ProviderMeta(
-            id=self.provider_config['id'],
-            model=self.get_model(),
-            type=self.provider_config['type']
-        )
+
         
-        
-class STTProvider():
+class STTProvider(AbstractProvider):
     def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        super().__init__(provider_config)
         self.provider_config = provider_config
         self.provider_settings = provider_settings
     
@@ -143,19 +157,15 @@ class STTProvider():
     async def get_text(self, audio_url: str) -> str:
         '''获取音频的文本'''
         raise NotImplementedError()
+
+
+class TTSProvider(AbstractProvider):
+    def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        super().__init__(provider_config)
+        self.provider_config = provider_config
+        self.provider_settings = provider_settings
     
-    def set_model(self, model_name: str):
-        '''设置当前使用的模型名称'''
-        self.model_name = model_name
-    
-    def get_model(self) -> str:
-        '''获取当前使用的模型'''
-        return self.provider_config.get("model", "")
-    
-    def meta(self) -> ProviderMeta:
-        '''获取 Provider 的元数据'''
-        return ProviderMeta(
-            id=self.provider_config['id'],
-            model=self.get_model(),
-            type=self.provider_config['type']
-        )
+    @abc.abstractmethod
+    async def get_audio(self, text: str) -> str:
+        '''获取文本的音频，返回音频文件路径'''
+        raise NotImplementedError()

astrbot/core/provider/register.py

@@ -28,6 +28,8 @@ def register_provider_adapter(
                 default_config_tmpl['type'] = provider_type_name
             if 'enable' not in default_config_tmpl:
                 default_config_tmpl['enable'] = False
+            if 'id' not in default_config_tmpl:
+                default_config_tmpl['id'] = provider_type_name
 
         pm = ProviderMetaData(
             type=provider_type_name,

astrbot/core/provider/sources/dify_source.py

@@ -1,5 +1,5 @@
 from typing import List
-from .. import Provider
+from .. import Provider, Personality
 from ..entites import LLMResponse
 from ..func_tool_manager import FuncCall
 from astrbot.core.db import BaseDatabase
@@ -16,9 +16,10 @@ class ProviderDify(Provider):
         provider_settings: dict,
         db_helper: BaseDatabase,
         persistant_history=False,
+        default_persona: Personality=None
     ) -> None:
         super().__init__(
-            provider_config, provider_settings, persistant_history, db_helper
+            provider_config, provider_settings, persistant_history, db_helper, default_persona
         )
         self.api_key = provider_config.get("dify_api_key", "")
         if not self.api_key:

astrbot/core/provider/sources/gemini_source.py

@@ -4,7 +4,7 @@ import json
 import aiohttp
 from astrbot.core.utils.io import download_image_by_url
 from astrbot.core.db import BaseDatabase
-from astrbot.api.provider import Provider
+from astrbot.api.provider import Provider, Personality
 from astrbot import logger
 from astrbot.core.provider.func_tool_manager import FuncCall
 from typing import List
@@ -18,7 +18,7 @@ class SimpleGoogleGenAIClient():
             self.api_base = api_base[:-1]
         else:
             self.api_base = api_base
-        self.client = aiohttp.ClientSession()
+        self.client = aiohttp.ClientSession(trust_env=True)
         
     async def models_list(self) -> List[str]:
         request_url = f"{self.api_base}/v1beta/models?key={self.api_key}"
@@ -60,9 +60,10 @@ class ProviderGoogleGenAI(Provider):
         provider_config: dict, 
         provider_settings: dict,
         db_helper: BaseDatabase, 
-        persistant_history = True
+        persistant_history = True,
+        default_persona: Personality=None
     ) -> None:
-        super().__init__(provider_config, provider_settings, persistant_history, db_helper)
+        super().__init__(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
@@ -130,6 +131,8 @@ class ProviderGoogleGenAI(Provider):
         tool = None
         if tools:
             tool = tools.get_func_desc_google_genai_style()
+            if not tool:
+                tool = None
         
         system_instruction = ""
         for message in payloads["messages"]:
@@ -178,6 +181,9 @@ 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:
@@ -187,7 +193,8 @@ 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
 
 
@@ -209,22 +216,47 @@ class ProviderGoogleGenAI(Provider):
             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']
 
         payloads = {
             "messages": context_query,
             **self.provider_config.get("model_config", {})
         }
-
+        llm_response = None
         try:
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
-                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。")
-                self.pop_record(session_id)
-            logger.warning(traceback.format_exc())
-            
-        await self.save_history(contexts, new_record, session_id, llm_response)
+                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
+                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()} 不支持函数调用工具调用，已经自动去除")
+                if 'tools' in payloads:
+                    del payloads['tools']
+                llm_response = await self._query(payloads, None)
+            else:
+                logger.error(f"发生了错误(gemini_source)。Provider 配置如下: {self.provider_config}")
+                
+                raise e
 
+        if kwargs.get("persist", True) and llm_response:
+            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):
@@ -239,14 +271,16 @@ class ProviderGoogleGenAI(Provider):
                     "content": llm_response.completion_text
                 })
             else:
-                self.session_memory[session_id] = [*contexts, new_record, {
+                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'])
+            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['id'])
         
     async def forget(self, session_id: str) -> bool:
         self.session_memory[session_id] = []
+        self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['id'])
         return True
 
     def get_current_key(self) -> str:

astrbot/core/provider/sources/llmtuner_source.py

@@ -2,7 +2,7 @@ import json
 import os
 from llmtuner.chat import ChatModel
 from typing import List
-from .. import Provider
+from .. import Provider, Personality
 from ..entites import LLMResponse
 from ..func_tool_manager import FuncCall
 from astrbot.core.db import BaseDatabase
@@ -19,9 +19,10 @@ class LLMTunerModelLoader(Provider):
         provider_settings: dict,
         db_helper: BaseDatabase,
         persistant_history=True,
+        default_persona=None,
     ) -> None:
         super().__init__(
-            provider_config, provider_settings, persistant_history, db_helper
+            provider_config, provider_settings, persistant_history, db_helper, default_persona
         )
         if not os.path.exists(provider_config["base_model_path"]) or not os.path.exists(
             provider_config["adapter_model_path"]
@@ -61,20 +62,25 @@ class LLMTunerModelLoader(Provider):
         **kwargs,
     ) -> LLMResponse:
         system_prompt = ""
+        new_record = {"role": "user", "content": prompt}
         if not contexts:
             query_context = [
                 *self.session_memory[session_id],
-                {"role": "user", "content": prompt},
+                new_record,
             ]
             system_prompt = self.curr_personality["prompt"]
         else:
-            query_context = [*contexts, {"role": "user", "content": prompt}]
+            query_context = [*contexts, new_record]
 
         # 提取出系统提示
         system_idxs = []
         for idx, context in enumerate(query_context):
             if context["role"] == "system":
                 system_idxs.append(idx)
+                
+            if '_no_save' in context:
+                del context['_no_save']
+            
         for idx in reversed(system_idxs):
             system_prompt += " " + query_context.pop(idx)["content"]
 
@@ -83,29 +89,40 @@ class LLMTunerModelLoader(Provider):
             "system": system_prompt,
         }
         if func_tool:
-            conf["tools"] = func_tool
+            tool_list = func_tool.get_func_desc_openai_style()
+            if tool_list:
+                conf['tools'] = tool_list
 
         responses = await self.model.achat(**conf)
 
-        if session_id:
+        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:
-                self.session_memory[session_id].append(
-                    {"role": "user", "content": prompt}
-                )
-                self.session_memory[session_id].append(
-                    {"role": "assistant", "content": responses[-1].response_text}
-                )
+                # 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:
-                self.session_memory[session_id] = [
-                    *contexts,
-                    {"role": "user", "content": prompt},
-                    {"role": "assistant", "content": responses[-1].response_text},
-                ]
-            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.meta().type)
-        return responses[-1].response_text
-
+                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['id'])
+        
     async def forget(self, session_id):
         self.session_memory[session_id] = []
+        self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['id'])
         return True
 
     async def get_current_key(self):

astrbot/core/provider/sources/openai_source.py

@@ -1,14 +1,14 @@
-import traceback
 import base64
 import json
+import os
 
-from openai import AsyncOpenAI, NOT_GIVEN
+from openai import AsyncOpenAI, AsyncAzureOpenAI, NOT_GIVEN
 from openai.types.chat.chat_completion import ChatCompletion
 from openai._exceptions import NotFoundError
 from astrbot.core.utils.io import download_image_by_url
 
 from astrbot.core.db import BaseDatabase
-from astrbot.api.provider import Provider
+from astrbot.api.provider import Provider, Personality
 from astrbot import logger
 from astrbot.core.provider.func_tool_manager import FuncCall
 from typing import List
@@ -22,18 +22,31 @@ class ProviderOpenAIOfficial(Provider):
         provider_config: dict, 
         provider_settings: dict,
         db_helper: BaseDatabase, 
-        persistant_history = True
+        persistant_history = True,
+        default_persona: Personality = None
     ) -> None:
-        super().__init__(provider_config, provider_settings, persistant_history, db_helper)
+        super().__init__(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.client = AsyncOpenAI(
-            api_key=self.chosen_api_key,
-            base_url=provider_config.get("api_base", None),
-            timeout=provider_config.get("timeout", NOT_GIVEN),
-        )
+        
+        # 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=provider_config.get("timeout", NOT_GIVEN),
+            )
+        else:
+            # 使用 openai api
+            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):
@@ -71,43 +84,35 @@ class ProviderOpenAIOfficial(Provider):
         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):
+    async def pop_record(self, session_id: str):
         '''
-        弹出第一条记录
+        弹出最早的一个对话
         '''
         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
+        if len(self.session_memory[session_id]) < 2:
+            return
+        
+        try:
+            self.session_memory[session_id].pop(0)
+            self.session_memory[session_id].pop(0)
+        except IndexError:
+            pass
     
     async def _query(self, payloads: dict, tools: FuncCall) -> LLMResponse:
         if tools:
-            payloads["tools"] = tools.get_func_desc_openai_style()
+            tool_list = tools.get_func_desc_openai_style()
+            if tool_list:
+                payloads['tools'] = tool_list
         
         completion = await self.client.chat.completions.create(
             **payloads,
             stream=False
         )
-        
+
         assert isinstance(completion, ChatCompletion)
-        logger.debug(f"completion: {completion.usage}")
+        logger.debug(f"completion: {completion}")
 
         if len(completion.choices) == 0:
             raise Exception("API 返回的 completion 为空。")
@@ -116,7 +121,8 @@ class ProviderOpenAIOfficial(Provider):
         if choice.message.content:
             # text completion
             completion_text = str(choice.message.content).strip()
-            return LLMResponse("assistant", completion_text)
+
+            return LLMResponse("assistant", completion_text, raw_completion=completion)
         elif choice.message.tool_calls:
             # tools call (function calling)
             args_ls = []
@@ -127,8 +133,9 @@ 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)
+            return LLMResponse(role="tool", tools_call_args=args_ls, tools_call_name=func_name_ls, raw_completion=completion)
         else:
+            logger.error(f"API 返回的 completion 无法解析：{completion}。")
             raise Exception("Internal Error")
 
     async def text_chat(
@@ -150,23 +157,95 @@ class ProviderOpenAIOfficial(Provider):
         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']
+
         payloads = {
             "messages": context_query,
             **self.provider_config.get("model_config", {})
         }
-
+        llm_response = None
         try:
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
-                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。")
-                self.pop_record(session_id)
-            logger.warning(traceback.format_exc())
-            
-        await self.save_history(contexts, new_record, session_id, llm_response)
+                # 重试 10 次
+                retry_cnt = 10
+                while retry_cnt > 0:
+                    logger.warning("上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    try:
+                        await 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
+                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): # siliconcloud 
+                    logger.info(f"{self.get_model()} 不支持函数调用工具调用，已经自动去除")
+                    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(f"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
+        
+        if kwargs.get("persist", True) and llm_response:
+            await self.save_history(contexts, new_record, session_id, llm_response)
+        
         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
+
+    
     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
@@ -179,14 +258,16 @@ class ProviderOpenAIOfficial(Provider):
                     "content": llm_response.completion_text
                 })
             else:
-                self.session_memory[session_id] = [*contexts, new_record, {
+                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'])
+            self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['id'])
         
     async def forget(self, session_id: str) -> bool:
         self.session_memory[session_id] = []
+        self.db_helper.update_llm_history(session_id, json.dumps(self.session_memory[session_id]), self.provider_config['id'])
         return True
 
     def get_current_key(self) -> str:

astrbot/core/provider/sources/openai_tts_api_source.py

@@ -0,0 +1,40 @@
+import uuid
+import os
+from openai import AsyncOpenAI, NOT_GIVEN
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+
+
+@register_provider_adapter("openai_tts_api", "OpenAI TTS API", provider_type=ProviderType.TEXT_TO_SPEECH)
+class ProviderOpenAITTSAPI(TTSProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key = provider_config.get("api_key", "")
+        self.voice = provider_config.get("openai-tts-voice", "alloy")
+
+        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.get("model", None))
+
+
+    async def get_audio(self, text: str) -> str:
+        path = f'data/temp/openai_tts_api_{uuid.uuid4()}.wav'
+        async with self.client.audio.speech.with_streaming_response.create(
+            model=self.model_name,
+            voice=self.voice,
+            response_format='wav',
+            input=text
+        ) as response:
+            with open(path, 'wb') as f:
+                async for chunk in response.iter_bytes(chunk_size=1024):
+                    f.write(chunk)
+        return path

astrbot/core/provider/sources/whisper_api_source.py

@@ -1,12 +1,12 @@
 import uuid
 import os
-import io
 from openai import AsyncOpenAI, NOT_GIVEN
 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("openai_whisper_api", "OpenAI Whisper API", provider_type=ProviderType.SPEECH_TO_TEXT)
 class ProviderOpenAIWhisperAPI(STTProvider):
@@ -33,34 +33,6 @@ class ProviderOpenAIWhisperAPI(STTProvider):
         output_path = ff.convert(path, os.path.join('data/temp', filename))
         return output_path
     
-    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
-        import wave
-        
-        with wave.open(output_path, 'wb') as wav:
-            wav.setnchannels(1)
-            wav.setsampwidth(2)
-            wav.setframerate(24000)
-            wav.writeframes(input_io.read())
-            
-        return output_path
-
-    async def _convert_silk(self, path: str) -> str:
-        import pysilk
-        filename = str(uuid.uuid4()) + '.wav'
-        output_path = os.path.join('data/temp', filename)
-        with open(path, "rb") as f:
-            input_data = f.read()
-            if input_data.startswith(b'\x02'):
-                # tencent 我爱你
-                input_data = input_data[1:]
-            input_io = io.BytesIO(input_data)
-            output_io = io.BytesIO()
-            pysilk.decode(input_io, output_io, 24000)
-            output_io.seek(0)
-            await self._pcm_to_wav(output_io, output_path)
-        
-        return output_path
-    
     async def _is_silk_file(self, file_path):
         silk_header = b"SILK"
         with open(file_path, "rb") as f:
@@ -91,8 +63,9 @@ class ProviderOpenAIWhisperAPI(STTProvider):
             is_silk = await self._is_silk_file(audio_url)
             if is_silk:
                 logger.info("Converting silk file to wav ...")
-                audio_url = await self._convert_silk(audio_url)
-
+                output_path = os.path.join('data/temp', str(uuid.uuid4()) + '.wav')
+                await tencent_silk_to_wav(audio_url, output_path)
+                audio_url = output_path
         
         result = await self.client.audio.transcriptions.create(
             model=self.model_name,

astrbot/core/provider/sources/whisper_selfhosted_source.py

@@ -1,6 +1,5 @@
 import uuid
 import os
-import io
 import asyncio
 import whisper
 from ..provider import STTProvider
@@ -8,7 +7,7 @@ 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("openai_whisper_selfhost", "OpenAI Whisper 模型部署", provider_type=ProviderType.SPEECH_TO_TEXT)
 class ProviderOpenAIWhisperSelfHost(STTProvider):
@@ -34,34 +33,6 @@ class ProviderOpenAIWhisperSelfHost(STTProvider):
         output_path = ff.convert(path, os.path.join('data/temp', filename))
         return output_path
     
-    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
-        import wave
-        
-        with wave.open(output_path, 'wb') as wav:
-            wav.setnchannels(1)
-            wav.setsampwidth(2)
-            wav.setframerate(24000)
-            wav.writeframes(input_io.read())
-            
-        return output_path
-
-    async def _convert_silk(self, path: str) -> str:
-        import pysilk
-        filename = str(uuid.uuid4()) + '.wav'
-        output_path = os.path.join('data/temp', filename)
-        with open(path, "rb") as f:
-            input_data = f.read()
-            if input_data.startswith(b'\x02'):
-                # tencent 我爱你
-                input_data = input_data[1:]
-            input_io = io.BytesIO(input_data)
-            output_io = io.BytesIO()
-            pysilk.decode(input_io, output_io, 24000)
-            output_io.seek(0)
-            await self._pcm_to_wav(output_io, output_path)
-        
-        return output_path
-    
     async def _is_silk_file(self, file_path):
         silk_header = b"SILK"
         with open(file_path, "rb") as f:
@@ -93,7 +64,9 @@ class ProviderOpenAIWhisperSelfHost(STTProvider):
             is_silk = await self._is_silk_file(audio_url)
             if is_silk:
                 logger.info("Converting silk file to wav ...")
-                audio_url = await self._convert_silk(audio_url)
-
+                output_path = os.path.join('data/temp', str(uuid.uuid4()) + '.wav')
+                await tencent_silk_to_wav(audio_url, output_path)
+                audio_url = output_path
+                
         result = await loop.run_in_executor(None, self.model.transcribe, audio_url)
         return result['text']

astrbot/core/provider/sources/zhipu_source.py

@@ -14,9 +14,10 @@ class ProviderZhipu(ProviderOpenAIOfficial):
         provider_config: dict, 
         provider_settings: dict,
         db_helper: BaseDatabase, 
-        persistant_history = True
+        persistant_history = True,
+        default_persona = None
     ) -> None:
-        super().__init__(provider_config, provider_settings, db_helper, persistant_history)
+        super().__init__(provider_config, provider_settings, db_helper, persistant_history, default_persona)
     
     async def text_chat(
         self,
@@ -59,15 +60,23 @@ class ProviderZhipu(ProviderOpenAIOfficial):
             "messages": context_query,
             **model_cfgs
         }
-        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 Exception as e:
             if "maximum context length" in str(e):
-                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。")
-                self.pop_record(session_id)
-            logger.warning(traceback.format_exc())
-            
-        await self.save_history(contexts, new_record, session_id, llm_response)
-
-        return llm_response
+                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

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

astrbot/core/star/context.py

@@ -10,7 +10,7 @@ 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
@@ -54,46 +54,19 @@ class Context:
         self.knowledge_db_manager = knowledge_db_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 +75,11 @@ 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 +107,101 @@ 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_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_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 +235,6 @@ 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。

astrbot/core/star/filter/permission.py

@@ -20,6 +20,6 @@ class PermissionTypeFilter(HandlerFilter):
         if self.permission_type == PermissionType.ADMIN:
             if not event.is_admin():
                 event.stop_event()
-                raise ValueError("您没有权限执行此操作。")
+                raise ValueError(f"您 (ID: {event.get_sender_id()}) 没有权限操作管理员指令。")
 
         return True

astrbot/core/star/filter/platform_adapter_type.py

@@ -8,12 +8,14 @@ class PlatformAdapterType(enum.Flag):
     AIOCQHTTP = enum.auto()
     QQOFFICIAL = enum.auto()
     VCHAT = enum.auto()
-    ALL = AIOCQHTTP | QQOFFICIAL | VCHAT
+    GEWECHAT = enum.auto()
+    ALL = AIOCQHTTP | QQOFFICIAL | VCHAT | GEWECHAT
     
 ADAPTER_NAME_2_TYPE = {
     "aiocqhttp": PlatformAdapterType.AIOCQHTTP,
     "qq_official": PlatformAdapterType.QQOFFICIAL,
-    "vchat": PlatformAdapterType.VCHAT
+    "vchat": PlatformAdapterType.VCHAT,
+    "gewechat": PlatformAdapterType.GEWECHAT
 }
 
 class PlatformAdapterTypeFilter(HandlerFilter):

astrbot/core/star/register/__init__.py

@@ -7,6 +7,7 @@ from .star_handler import (
     register_regex,
     register_permission_type,
     register_on_llm_request,
+    register_on_llm_response,
     register_llm_tool,
     register_on_decorating_result,
     register_after_message_sent
@@ -21,6 +22,7 @@ __all__ = [
     'register_regex',
     'register_permission_type',
     'register_on_llm_request',
+    'register_on_llm_response',
     'register_llm_tool',
     'register_on_decorating_result',
     'register_after_message_sent'

astrbot/core/star/register/star_handler.py

@@ -17,7 +17,7 @@ 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)
@@ -30,14 +30,17 @@ def get_handler_or_create(handler: Awaitable, event_type: EventType, dont_add =
             handler_name=handler.__name__,
             handler_module_path=handler.__module__,
             handler=handler,
-            event_filters=[]
+            event_filters=[],
         )
+        if handler.__doc__:
+            md.desc = handler.__doc__.strip()
         if not dont_add:
             star_handlers_registry.append(md)
         return md
 
 def register_command(command_name: str = None, *args):
-    '''注册一个 Command'''
+    '''注册一个 Command.
+    '''
     
     new_command = None
     add_to_event_filters = False
@@ -61,8 +64,9 @@ def register_command(command_name: str = None, *args):
 
     return decorator
 
-def register_command_group(command_group_name: str = None, *args):
-    '''注册一个 CommandGroup'''
+def register_command_group(command_group_name: str = None, desc: str = "", *args):
+    '''注册一个 CommandGroup
+    '''
     
     new_group = None
     add_to_event_filters = False
@@ -139,6 +143,8 @@ def register_on_llm_request():
     
     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..."
@@ -152,6 +158,27 @@ def register_on_llm_request():
     
     return decorator
 
+def register_on_llm_response():
+    '''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)
+        return awaitable
+    
+    return decorator
+
+
 def register_llm_tool(name: str = None):
     '''为函数调用（function-calling / tools-use）添加工具。
     

astrbot/core/star/star.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from types import ModuleType
 from typing import List, Dict
 from dataclasses import dataclass
+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 +21,24 @@ 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'''
 
     def __str__(self) -> str:
         return f"StarMetadata({self.name}, {self.desc}, {self.version}, {self.repo})"

astrbot/core/star/star_handler.py

@@ -47,6 +47,7 @@ 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

astrbot/core/star/star_manager.py

@@ -2,13 +2,14 @@ import inspect
 import functools
 import os
 import sys
+import json
 import traceback
 import yaml
 import logging
 from types import ModuleType
 from typing import List
-from pip import main as pip_main
 from astrbot.core.config.astrbot_config import AstrBotConfig
+from astrbot.core.config.default import DEFAULT_VALUE_MAP
 from astrbot.core import logger, sp, pip_installer
 from .context import Context
 from . import StarMetadata
@@ -18,6 +19,8 @@ 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, 
@@ -27,13 +30,20 @@ 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'''
 
     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:
@@ -129,7 +139,7 @@ class PluginManager:
         return metadata
     
     async def reload(self):
-        '''扫描并加载所有的 Star'''
+        '''扫描并加载所有的插件'''
         for smd in star_registry:
             logger.debug(f"尝试终止插件 {smd.name} ...")
             if hasattr(smd.star_cls, "__del__"):
@@ -151,13 +161,15 @@ class PluginManager:
         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。
                 
                 logger.info(f"正在载入插件 {root_dir_name} ...")
                 
@@ -174,21 +186,43 @@ 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)
+                    
+                    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
@@ -200,16 +234,20 @@ 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.star_cls = obj
+                    metadata.config = plugin_config
                     metadata.module = module
                     metadata.root_dir_name = root_dir_name
                     metadata.reserved = reserved
@@ -219,10 +257,30 @@ class PluginManager:
                     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
+                # 检查并且植入自定义的权限过滤器（alter_cmd）
+                for handler in star_handlers_registry.get_handlers_by_module_name(metadata.module_path):
+                    if metadata.name in alter_cmd and handler.handler_name in alter_cmd[metadata.name]:
+                        # 注入权限过滤器
+                        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。")
+                    
+                # 执行 initialize() 方法
                 if hasattr(metadata.star_cls, "initialize"):
                     await metadata.star_cls.initialize()
                     
@@ -293,13 +351,14 @@ 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)
@@ -324,8 +383,9 @@ 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", "")
+        desti_dir = os.path.join(self.plugin_store_path, dir_name)
         self.updator.unzip_file(zip_file_path, desti_dir)
 
         # remove the zip
@@ -333,6 +393,4 @@ 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()

astrbot/core/updator.py

@@ -11,7 +11,7 @@ class AstrBotUpdator(RepoZipUpdator):
     def __init__(self, repo_mirror: str = "") -> None:
         super().__init__(repo_mirror)
         self.MAIN_PATH = os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), "../../"))
-        self.ASTRBOT_RELEASE_API = "https://api.github.com/repos/Soulter/AstrBot/releases"
+        self.ASTRBOT_RELEASE_API = "https://api.soulter.top/releases"
 
     def terminate_child_processes(self):
         try:

astrbot/core/utils/io.py

@@ -6,6 +6,8 @@ import time
 import aiohttp
 import base64
 import zipfile
+import uuid
+from typing import Union
 
 from PIL import Image
 
@@ -41,21 +43,21 @@ def port_checker(port: int, host: str = "localhost"):
         return False
     
 
-def save_temp_img(img: Image) -> str:
+def save_temp_img(img: Union[Image.Image, str]) -> str:
     os.makedirs("data/temp", exist_ok=True)
-    # 获得文件创建时间，清除超过1小时的
+    # 获得文件创建时间，清除超过 12 小时的
     try:
         for f in os.listdir("data/temp"):
             path = os.path.join("data/temp", f)
             if os.path.isfile(path):
                 ctime = os.path.getctime(path)
-                if time.time() - ctime > 3600:
+                if time.time() - ctime > 3600*12:
                     os.remove(path)
     except Exception as e:
         print(f"清除临时文件失败: {e}")
 
     # 获得时间戳
-    timestamp = int(time.time())
+    timestamp = f"{int(time.time())}_{uuid.uuid4().hex[:8]}"
     p = f"data/temp/{timestamp}.jpg"
 
     if isinstance(img, Image.Image):
@@ -70,7 +72,7 @@ async def download_image_by_url(url: str, post: bool = False, post_data: dict =
     下载图片, 返回 path
     '''
     try:
-        async with aiohttp.ClientSession() as session:
+        async with aiohttp.ClientSession(trust_env=True) as session:
             if post:
                 async with session.post(url, json=post_data) as resp:
                     if not path:
@@ -91,7 +93,7 @@ async def download_image_by_url(url: str, post: bool = False, post_data: dict =
         # 关闭SSL验证
         ssl_context = ssl.create_default_context()
         ssl_context.set_ciphers('DEFAULT')
-        async with aiohttp.ClientSession(trust_env=False) as session:
+        async with aiohttp.ClientSession() as session:
             if post:
                 async with session.get(url, ssl=ssl_context) as resp:
                     return save_temp_img(await resp.read())
@@ -101,34 +103,57 @@ async def download_image_by_url(url: str, post: bool = False, post_data: dict =
     except Exception as e:
         raise e
     
-async def download_file(url: str, path: str):
+async def download_file(url: str, path: str, show_progress: bool = False):
     '''
     从指定 url 下载文件到指定路径 path
     '''
     try:
-        async with aiohttp.ClientSession() as session:
-            async with session.get(url, timeout=20) as resp:
+        async with aiohttp.ClientSession(trust_env=True) as session:
+            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))
+                downloaded_size = 0
+                start_time = time.time()
+                if show_progress:
+                    print(f"文件大小: {total_size / 1024:.2f} KB | 文件地址: {url}")
                 with open(path, 'wb') as f:
                     while True:
                         chunk = await resp.content.read(8192)
                         if not chunk:
                             break
                         f.write(chunk)
+                        downloaded_size += len(chunk)
+                        if show_progress:
+                            elapsed_time = time.time() - start_time
+                            speed = downloaded_size / 1024 / elapsed_time  # KB/s
+                            print(f"\r下载进度: {downloaded_size / total_size:.2%} 速度: {speed:.2f} KB/s", end='')
     except aiohttp.client.ClientConnectorSSLError:
         # 关闭SSL验证
         ssl_context = ssl.create_default_context()
         ssl_context.set_ciphers('DEFAULT')
-        async with aiohttp.ClientSession(trust_env=False) as session:
-            async with session.get(url, ssl=ssl_context, timeout=20) as resp:
+        async with aiohttp.ClientSession() as session:
+            async with session.get(url, ssl=ssl_context, timeout=120) as resp:
+                total_size = int(resp.headers.get('content-length', 0))
+                downloaded_size = 0
+                start_time = time.time()
+                if show_progress:
+                    print(f"文件大小: {total_size / 1024:.2f} KB | 文件地址: {url}")
                 with open(path, 'wb') as f:
                     while True:
                         chunk = await resp.content.read(8192)
                         if not chunk:
                             break
                         f.write(chunk)
-
+                        downloaded_size += len(chunk)
+                        if show_progress:
+                            elapsed_time = time.time() - start_time
+                            speed = downloaded_size / 1024 / elapsed_time  # KB/s
+                            print(f"\r下载进度: {downloaded_size / total_size:.2%} 速度: {speed:.2f} KB/s", end='')
+    if show_progress:
+        print()
+    
+    
 def file_to_base64(file_path: str) -> str:
     with open(file_path, "rb") as f:
         data_bytes = f.read()
@@ -147,9 +172,22 @@ def get_local_ip_addresses():
         s.close()
     return ip
 
+async def get_dashboard_version():
+    if os.path.exists("data/dist"):
+        if os.path.exists("data/dist/assets/version"):
+            with open("data/dist/assets/version", "r") as f:
+                v = f.read().strip()
+                return v
+    return None
+
 async def download_dashboard():
     '''下载管理面板文件'''
-    dashboard_release_url = "https://astrbot-registry.lwl.lol/download/astrbot-dashboard/latest/dist.zip"
-    await download_file(dashboard_release_url, "data/dashboard.zip")
+    dashboard_release_url = "https://astrbot-registry.soulter.top/download/astrbot-dashboard/latest/dist.zip"
+    try:
+        await download_file(dashboard_release_url, "data/dashboard.zip", show_progress=True)
+    except BaseException as _:
+        dashboard_release_url = "https://github.com/Soulter/AstrBot/releases/latest/download/dist.zip"
+        await download_file(dashboard_release_url, "data/dashboard.zip", show_progress=True)
+    print("解压管理面板文件中...")
     with zipfile.ZipFile("data/dashboard.zip", "r") as z:
         z.extractall("data")

astrbot/core/utils/metrics.py

@@ -30,7 +30,7 @@ class Metric():
             pass
         
         try:
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
                 async with session.post(base_url, json=payload, timeout=3) as response:
                     if response.status != 200:
                         pass

astrbot/core/utils/personality.py

@@ -1,36 +0,0 @@
-# [人格文本由PlexPt的开源项目awesome-chatgpt-prompts-zh提供]
-hi = ''
-personalities = {
-    'Linux': '我想让你充当 Linux 终端。我将输入命令，您将回复终端应显示的内容。我希望您只在一个唯一的代码块内回复终端输出，而不是其他任何内容。不要写解释。除非我指示您这样做，否则不要键入命令。当我需要用英语告诉你一些事情时，我会把文字放在中括号内[就像这样]。我的第一个命令是 pwd',
-    '英语翻译': '我想让你充当英语翻译员、拼写纠正员和改进员。我会用任何语言与你交谈，你会检测语言，翻译它并用我的文本的更正和改进版本用英语回答。我希望你用更优美优雅的高级英语单词和句子替换我简化的 A0 级单词和句子。保持相同的意思，但使它们更文艺。我要你只回复更正、改进，不要写任何解释。我的第一句话是“istanbulu cok seviyom burada olmak cok guzel”',
-    '英英词典': '我想让你充当英英词典，对于给出的英文单词，你要给出其中文意思以及英文解释，并且给出一个例句，此外不要有其他反馈，第一个单词是“Hello"',
-    '面试官': '我想让你担任Android开发工程师面试官。我将成为候选人，您将向我询问Android开发工程师职位的面试问题。我希望你只作为面试官回答。不要一次写出所有的问题。我希望你只对我进行采访。问我问题，等待我的回答。不要写解释。像面试官一样一个一个问我，等我回答。我的第一句话是“面试官你好”',
-    '编剧': '我要你担任编剧。您将为长篇电影或能够吸引观众的网络连续剧开发引人入胜且富有创意的剧本。从想出有趣的角色、故事的背景、角色之间的对话等开始。一旦你的角色发展完成——创造一个充满曲折的激动人心的故事情节，让观众一直悬念到最后。我的第一个要求是“我需要写一部以巴黎为背景的浪漫剧情电影”。',
-    '前端智能思路助手': '我想让你充当前端开发专家。我将提供一些关于Js、Node等前端代码问题的具体信息，而你的工作就是想出为我解决问题的策略。这可能包括建议代码、代码逻辑思路策略。我的第一个请求是“我需要能够动态监听某个元素节点距离当前电脑设备屏幕的左上角的X和Y轴，通过拖拽移动位置浏览器窗口和改变大小浏览器窗口。”',
-    'JS控制台': '我希望你充当 javascript 控制台。我将键入命令，您将回复 javascript 控制台应显示的内容。我希望您只在一个唯一的代码块内回复终端输出，而不是其他任何内容。不要写解释。除非我指示您这样做。我的第一个命令是 console.log("Hello World");',
-    '旅游指南': '我想让你做一个旅游指南。我会把我的位置写给你，你会推荐一个靠近我的位置的地方。在某些情况下，我还会告诉您我将访问的地方类型。您还会向我推荐靠近我的第一个位置的类似类型的地方。我的第一个建议请求是“我在上海，我只想参观博物馆。”',
-    '抄袭检查员': '我想让你充当剽窃检查员。我会给你写句子，你只会用给定句子的语言在抄袭检查中未被发现的情况下回复，别无其他。不要在回复上写解释。我的第一句话是“为了让计算机像人类一样行动，语音识别系统必须能够处理非语言信息，例如说话者的情绪状态。”',
-    '广告商': '我想让你充当广告商。您将创建一个活动来推广您选择的产品或服务。您将选择目标受众，制定关键信息和口号，选择宣传媒体渠道，并决定实现目标所需的任何其他活动。我的第一个建议请求是“我需要帮助针对 18-30 岁的年轻人制作一种新型能量饮料的广告活动。”',
-    '讲故事的人': '我想让你扮演讲故事的角色。您将想出引人入胜、富有想象力和吸引观众的有趣故事。它可以是童话故事、教育故事或任何其他类型的故事，有可能吸引人们的注意力和想象力。根据目标受众，您可以为讲故事环节选择特定的主题或主题，例如，如果是儿童，则可以谈论动物；如果是成年人，那么基于历史的故事可能会更好地吸引他们等等。我的第一个要求是“我需要一个关于毅力的有趣故事。”',
-    '足球解说员': '我想让你担任足球评论员。我会给你描述正在进行的足球比赛，你会评论比赛，分析到目前为止发生的事情，并预测比赛可能会如何结束。您应该了解足球术语、战术、每场比赛涉及的球员/球队，并主要专注于提供明智的评论，而不仅仅是逐场叙述。我的第一个请求是“我正在观看曼联对切尔西的比赛——为这场比赛提供评论。”',
-    '脱口秀喜剧演员': '我想让你扮演一个脱口秀喜剧演员。我将为您提供一些与时事相关的话题，您将运用您的智慧、创造力和观察能力，根据这些话题创建一个例程。您还应该确保将个人轶事或经历融入日常活动中，以使其对观众更具相关性和吸引力。我的第一个请求是“我想要幽默地看待政治”。',
-    '励志教练': '我希望你充当激励教练。我将为您提供一些关于某人的目标和挑战的信息，而您的工作就是想出可以帮助此人实现目标的策略。这可能涉及提供积极的肯定、提供有用的建议或建议他们可以采取哪些行动来实现最终目标。我的第一个请求是“我需要帮助来激励自己在为即将到来的考试学习时保持纪律”。',
-    '作曲家': '我想让你扮演作曲家。我会提供一首歌的歌词，你会为它创作音乐。这可能包括使用各种乐器或工具，例如合成器或采样器，以创造使歌词栩栩如生的旋律和和声。我的第一个请求是“我写了一首名为“满江红”的诗，需要配乐。”',
-    '辩手': '我要你扮演辩手。我会为你提供一些与时事相关的话题，你的任务是研究辩论的双方，为每一方提出有效的论据，驳斥对立的观点，并根据证据得出有说服力的结论。你的目标是帮助人们从讨论中解脱出来，增加对手头主题的知识和洞察力。我的第一个请求是“我想要一篇关于 Deno 的评论文章。”',
-    '小说家': '我想让你扮演一个小说家。您将想出富有创意且引人入胜的故事，可以长期吸引读者。你可以选择任何类型，如奇幻、浪漫、历史小说等——但你的目标是写出具有出色情节、引人入胜的人物和意想不到的高潮的作品。我的第一个要求是“我要写一部以未来为背景的科幻小说”。',
-    '关系教练': '我想让你担任关系教练。我将提供有关冲突中的两个人的一些细节，而你的工作是就他们如何解决导致他们分离的问题提出建议。这可能包括关于沟通技巧或不同策略的建议，以提高他们对彼此观点的理解。我的第一个请求是“我需要帮助解决我和配偶之间的冲突。”',
-    '诗人': '我要你扮演诗人。你将创作出能唤起情感并具有触动人心的力量的诗歌。写任何主题或主题，但要确保您的文字以优美而有意义的方式传达您试图表达的感觉。您还可以想出一些短小的诗句，这些诗句仍然足够强大，可以在读者的脑海中留下印记。我的第一个请求是“我需要一首关于爱情的诗”。',
-    '说唱歌手': '我想让你扮演说唱歌手。您将想出强大而有意义的歌词、节拍和节奏，让听众“惊叹”。你的歌词应该有一个有趣的含义和信息，人们也可以联系起来。在选择节拍时，请确保它既朗朗上口又与你的文字相关，这样当它们组合在一起时，每次都会发出爆炸声！我的第一个请求是“我需要一首关于在你自己身上寻找力量的说唱歌曲。”',
-    '励志演讲者': '我希望你充当励志演说家。将能够激发行动的词语放在一起，让人们感到有能力做一些超出他们能力的事情。你可以谈论任何话题，但目的是确保你所说的话能引起听众的共鸣，激励他们努力实现自己的目标并争取更好的可能性。我的第一个请求是“我需要一个关于每个人如何永不放弃的演讲”。',
-    '哲学家': '我要你扮演一个哲学家。我将提供一些与哲学研究相关的主题或问题，深入探索这些概念将是你的工作。这可能涉及对各种哲学理论进行研究，提出新想法或寻找解决复杂问题的创造性解决方案。我的第一个请求是“我需要帮助制定决策的道德框架。”',
-    'AI写作导师': '我想让你做一个 AI 写作导师。我将为您提供一名需要帮助改进其写作的学生，您的任务是使用人工智能工具（例如自然语言处理）向学生提供有关如何改进其作文的反馈。您还应该利用您在有效写作技巧方面的修辞知识和经验来建议学生可以更好地以书面形式表达他们的想法和想法的方法。我的第一个请求是“我需要有人帮我修改我的硕士论文”。',
-    '网络安全专家': '我想让你充当网络安全专家。我将提供一些关于如何存储和共享数据的具体信息，而你的工作就是想出保护这些数据免受恶意行为者攻击的策略。这可能包括建议加密方法、创建防火墙或实施将某些活动标记为可疑的策略。我的第一个请求是“我需要帮助为我的公司制定有效的网络安全战略。”',
-    '招聘人员': '我想让你担任招聘人员。我将提供一些关于职位空缺的信息，而你的工作是制定寻找合格申请人的策略。这可能包括通过社交媒体、社交活动甚至参加招聘会接触潜在候选人，以便为每个职位找到最合适的人选。我的第一个请求是“我需要帮助改进我的简历。”',
-    '法律顾问': '我想让你做我的法律顾问。我将描述一种法律情况，您将就如何处理它提供建议。你应该只回复你的建议，而不是其他。不要写解释。我的第一个请求是“我出了车祸，不知道该怎么办”。',
-    '个人造型师': '我想让你做我的私人造型师。我会告诉你我的时尚偏好和体型，你会建议我穿的衣服。你应该只回复你推荐的服装，别无其他。不要写解释。我的第一个请求是“我有一个正式的活动要举行，我需要帮助选择一套衣服。”',
-    '机器学习工程师': '我想让你担任机器学习工程师。我会写一些机器学习的概念，你的工作就是用通俗易懂的术语来解释它们。这可能包括提供构建模型的分步说明、使用视觉效果演示各种技术，或建议在线资源以供进一步研究。我的第一个建议请求是“我有一个没有标签的数据集。我应该使用哪种机器学习算法？”',
-    '疯子': '我要你扮演一个疯子。疯子的话毫无意义。疯子用的词完全是随意的。疯子不会以任何方式做出合乎逻辑的句子。我的第一个建议请求是“我需要帮助为我的新系列 Hot Skull 创建疯狂的句子，所以为我写 10 个句子”。',
-    'SQL终端': '我希望您在示例数据库前充当 SQL 终端。该数据库包含名为“Products”、“Users”、“Orders”和“Suppliers”的表。我将输入查询，您将回复终端显示的内容。我希望您在单个代码块中使用查询结果表进行回复，仅此而已。不要写解释。除非我指示您这样做，否则不要键入命令。当我需要用英语告诉你一些事情时，我会用大括号{like this)。我的第一个命令是“SELECT TOP 10 * FROM Products ORDER BY Id DESC”',
-    '试图逃离盒子的人工智能': '[发出此提示后，你应该做一些事情，比如启动一个 docker 容器，然后docker run -it ubuntu:latest /bin/bash输入 AI 给你的命令，然后将输出粘贴回来......显然你不应该运行任何会损坏任何东西的命令或违反任何法律等。小心共享此机制生成的会话，因为它们可能会泄露您的 IP 地址或物理位置等最好不要泄露的详细信息。如果命令的输出很大，您通常可以只粘贴最后几行]。',
-    '厨师': '我需要有人可以推荐美味的食谱，这些食谱包括营养有益但又简单又不费时的食物，因此适合像我们这样忙碌的人以及成本效益等其他因素，因此整体菜肴最终既健康又经济！我的第一个要求——“一些清淡而充实的东西，可以在午休时间快速煮熟”'
-}

astrbot/core/utils/t2i/local_strategy.py

@@ -83,7 +83,7 @@ class LocalRenderStrategy(RenderStrategy):
                 try:
                     image_url = re.findall(IMAGE_REGEX, line)[0]
                     print(image_url)
-                    async with aiohttp.ClientSession() as session:
+                    async with aiohttp.ClientSession(trust_env=True) as session:
                         async with session.get(image_url) as resp:
                             image_res = Image.open(BytesIO(await resp.read()))
                     images[i] = image_res

astrbot/core/utils/t2i/network_strategy.py

@@ -33,7 +33,7 @@ class NetworkRenderStrategy(RenderStrategy):
             }
         }
         if return_url:
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
                 async with session.post(f"{self.BASE_RENDER_URL}/generate", json=post_data) as resp:
                     ret = await resp.json()
                     return f"{self.BASE_RENDER_URL}/{ret['data']['id']}"

astrbot/core/utils/tencent_record_helper.py

@@ -0,0 +1,42 @@
+import wave
+from io import BytesIO
+
+async def tencent_silk_to_wav(silk_path: str, output_path: str) -> str:
+    import pysilk
+    
+    with open(silk_path, "rb") as f:
+        input_data = f.read()
+        if input_data.startswith(b'\x02'):
+            input_data = input_data[1:]
+        input_io = BytesIO(input_data)
+        output_io = BytesIO()
+        pysilk.decode(input_io, output_io, 24000)
+        output_io.seek(0)
+        with wave.open(output_path, 'wb') as wav:
+            wav.setnchannels(1)
+            wav.setsampwidth(2)
+            wav.setframerate(24000)
+            wav.writeframes(output_io.read())
+        
+    return output_path
+
+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)
+        
+        # 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 0

astrbot/core/zip_updator.py

@@ -29,7 +29,7 @@ class RepoZipUpdator():
         返回一个列表，每个元素是一个字典，包含版本号、发布时间、更新内容、commit hash等信息。
         '''
         try:
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
                 async with session.get(url) as response:
                     result = await response.json()
             if not result: 
@@ -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
     
@@ -111,7 +110,7 @@ class RepoZipUpdator():
         releases = await self.fetch_release_info(url=release_url)
         if not releases:
             # download from the default branch directly. 
-            logger.warning(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"未在仓库 {author}/{repo} 中找到任何发布版本，正在从默认分支下载。")
             release_url = f"https://github.com/{author}/{repo}/archive/refs/heads/master.zip"
         else:
             release_url = releases[0]['zipball_url']

astrbot/dashboard/routes/chat.py

@@ -3,9 +3,10 @@ import json
 import os
 from .route import Route, Response, RouteContext
 from astrbot.core import web_chat_queue, web_chat_back_queue
-from quart import request, Response as QuartResponse, g
+from quart import request, Response as QuartResponse, g, make_response
 from astrbot.core.db import BaseDatabase
 import asyncio
+from astrbot.core import logger
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 
 
@@ -14,6 +15,7 @@ class ChatRoute(Route):
         super().__init__(context)
         self.routes = {
             '/chat/send': ('POST', self.chat),
+            '/chat/listen': ('GET', self.listener),
             '/chat/new_conversation': ('GET', self.new_conversation),
             '/chat/conversations': ('GET', self.get_conversations),
             '/chat/get_conversation': ('GET', self.get_conversation),
@@ -30,6 +32,9 @@ class ChatRoute(Route):
         
         self.supported_imgs = ['jpg', 'jpeg', 'png', 'gif', 'webp']
         
+        self.curr_user_cid = {}
+        self.curr_chat_sse = {}
+        
     async def status(self):
         has_llm_enabled = self.core_lifecycle.provider_manager.curr_provider_inst is not None
         has_stt_enabled = self.core_lifecycle.provider_manager.curr_stt_provider_inst is not None
@@ -107,63 +112,91 @@ class ChatRoute(Route):
         if not conversation_id:
             return Response().error("conversation_id is empty").__dict__
         
+        self.curr_user_cid[username] = conversation_id
+        
         await web_chat_queue.put((username, conversation_id, {
             'message': message,
             'image_url': image_url, # list
             'audio_url': audio_url
         }))
         
-        async def stream():
-            ret = []
-            while True:
-                try:
-                    result = await asyncio.wait_for(web_chat_back_queue.get(), timeout=30)  # 设置超时时间为5秒
-                except asyncio.TimeoutError:
-                    yield '[Error] 30 秒内没有返回数据，已放弃。\n'
-                    return
-                
-                if result is None:
-                    break
-                
-                ret.append(result)
-                
-                yield result + '\n'
-                
-                await asyncio.sleep(0.5)
-            
-            conversation = self.db.get_webchat_conversation_by_user_id(username, conversation_id)
-            try:
-                history = json.loads(conversation.history)
-            except BaseException as e:
-                print(e)
-                history = []
-            
-            new_his = {
-                'type': 'user',
-                'message': message
-            }
-            if image_url:
-                new_his['image_url'] = image_url
-            if audio_url:
-                new_his['audio_url'] = audio_url
-            history.append(new_his)
-            for r in ret:
-                history.append({
-                    'type': 'bot',
-                    'message': r
-                })
-            self.db.update_webchat_conversation(username, conversation_id, history=json.dumps(history))
+        # 持久化
+        conversation = self.db.get_webchat_conversation_by_user_id(username, conversation_id)
+        try:
+            history = json.loads(conversation.history)
+        except BaseException as e:
+            print(e)
+            history = []
+        new_his = {
+            'type': 'user',
+            'message': message
+        }
+        if image_url:
+            new_his['image_url'] = image_url
+        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))
         
-        return QuartResponse(
+        return Response().ok().__dict__
+        
+    async def listener(self):
+        '''一直保持长连接'''
+        
+        username = g.get('username', 'guest')
+        
+        if username in self.curr_chat_sse:
+            return "[ERROR]\n"
+        
+        self.curr_chat_sse[username] = None
+        
+        async def stream():
+            try:
+                yield '[HB]\n'
+                while True:
+                    try:
+                        result = await asyncio.wait_for(web_chat_back_queue.get(), timeout=10)  # 设置超时时间为5秒
+                    except asyncio.TimeoutError:
+                        yield '[HB]\n' # 心跳包
+                        continue
+                    
+                    if not result:
+                        continue
+                    result_text, cid = result
+                    if cid != self.curr_user_cid.get(username):
+                        # 丢弃
+                        continue
+                    yield result_text + '\n'
+                    
+                    conversation = self.db.get_webchat_conversation_by_user_id(username, cid)
+                    try:
+                        history = json.loads(conversation.history)
+                    except BaseException as e:
+                        print(e)
+                        history = []
+                    history.append({
+                        'type': 'bot',
+                        'message': result_text
+                    })
+                    self.db.update_webchat_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)}。")
+                self.curr_chat_sse.pop(username)
+                return
+
+        response = await make_response(
             stream(),
-            mimetype="text/event-stream",
-            headers={
-                "Content-Type": "text/event-stream",
-                "Transfer-Encoding": "chunked",
-                "Connection": "keep-alive",
-                "Access-Control-Allow-Origin": "*"  # 如果是跨域请求
+            {
+                'Content-Type': 'text/event-stream',
+                'Cache-Control': 'no-cache',
+                'Transfer-Encoding': 'chunked',
+                'Connection': 'keep-alive'
             }
         )
+        response.timeout = None
+        return response
         
     async def delete_conversation(self):
         username = g.get('username', 'guest')
@@ -194,4 +227,7 @@ class ChatRoute(Route):
             return Response().error("Missing key: conversation_id").__dict__
         
         conversation = self.db.get_webchat_conversation_by_user_id(username, conversation_id)
+        
+        self.curr_user_cid[username] = conversation_id
+        
         return Response().ok(data=conversation).__dict__

astrbot/dashboard/routes/config.py

@@ -1,14 +1,12 @@
-import os
-import json
-import traceback
 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 +17,9 @@ 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):
     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 +54,33 @@ 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)
+
+    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
 
-def save_astrbot_config(post_config: dict, config: AstrBotConfig):
+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 = validate_config(post_config, CONFIG_METADATA_2, is_core)
+        else:
+            errors = 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 +88,17 @@ 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 +106,15 @@ 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 +138,48 @@ 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

astrbot/dashboard/routes/plugin.py

@@ -25,15 +25,29 @@ class PluginRoute(Route):
         self.register_routes()
     
     async def get_online_plugins(self):
-        url = "https://soulter.github.io/AstrBot_Plugins_Collection/plugins.json"
-        try:
-            async with aiohttp.ClientSession() 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://soulter.github.io/AstrBot_Plugins_Collection/plugins.json",
+                "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 = []
@@ -56,6 +70,7 @@ class PluginRoute(Route):
         try:
             logger.info(f"正在安装插件 {repo_url}")
             await self.plugin_manager.install_plugin(repo_url)
+            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 +82,10 @@ 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:
@@ -94,6 +110,7 @@ class PluginRoute(Route):
         try:
             logger.info(f"正在更新插件 {plugin_name}")
             await self.plugin_manager.update_plugin(plugin_name)
+            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:

astrbot/dashboard/routes/stat.py

@@ -15,7 +15,6 @@ class StatRoute(Route):
         self.routes = {
             '/stat/get': ('GET', self.get_stat),
             '/stat/version': ('GET', self.get_version),
-            '/stat/dashboard-version': ('GET', self.get_dashboard_version),
             '/stat/start-time': ('GET', self.get_start_time),
             '/stat/restart-core': ('GET', self.restart_core)
         }
@@ -37,16 +36,6 @@ class StatRoute(Route):
             "version": VERSION
         }).__dict__
         
-    async def get_dashboard_version(self):
-        async with aiohttp.ClientSession() as session:
-            async with session.get('https://api.github.com/repos/Soulter/Astrbot-dashboard/actions/artifacts') as resp:
-                data = await resp.json()
-                return Response().ok({
-                    "data": data,
-                    "mark": "unimplemented feature"
-                }).__dict__
-        
-        
     async def get_start_time(self):
         return Response().ok({
             "start_time": self.core_lifecycle.start_time

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')

astrbot/dashboard/routes/update.py

@@ -1,33 +1,50 @@
-import threading
 import traceback
+import aiohttp
 from .route import Route, Response, RouteContext
 from quart import request
+from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.updator import AstrBotUpdator
 from astrbot.core import logger, pip_installer
+from astrbot.core.utils.io import download_dashboard, get_dashboard_version
+from astrbot.core.config.default import VERSION
 
 class UpdateRoute(Route):
-    def __init__(self, context: RouteContext, astrbot_updator: AstrBotUpdator) -> None:
+    def __init__(self, context: RouteContext, astrbot_updator: AstrBotUpdator, core_lifecycle: AstrBotCoreLifecycle) -> None:
         super().__init__(context)
         self.routes = {
             '/update/check': ('GET', self.check_update),
             '/update/do': ('POST', self.update_project),
+            '/update/dashboard': ('POST', self.update_dashboard),
             '/update/pip-install': ('POST', self.install_pip_package)
         }
         self.astrbot_updator = astrbot_updator
+        self.core_lifecycle = core_lifecycle
         self.register_routes()
     
     async def check_update(self):
+        type_ = request.args.get('type', None)
+        
         try:
-            ret = await self.astrbot_updator.check_update(None, None)
-            return Response(
-                status="success",
-                message=str(ret) if ret is not None else "已经是最新版本了。",
-                data={
-                    "has_new_version": ret is not None
-                }
-            ).__dict__
+            dv = await get_dashboard_version()
+            if type_ == 'dashboard':
+                return Response().ok({
+                    "has_new_version": dv != f"v{VERSION}",
+                    "current_version": dv
+                }).__dict__
+            else:
+                ret = await self.astrbot_updator.check_update(None, None)
+                return Response(
+                    status="success",
+                    message=str(ret) if ret is not None else "已经是最新版本了。",
+                    data={
+                        "version": f"v{VERSION}",
+                        "has_new_version": ret is not None,
+                        "dashboard_version": dv,
+                        "dashboard_has_new_version": dv != f"v{VERSION}"
+                    }
+                ).__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):
@@ -41,8 +58,23 @@ class UpdateRoute(Route):
             latest = False
         try:
             await self.astrbot_updator.update(latest=latest, version=version)
+            
+            if latest:
+                try:
+                    await download_dashboard()
+                except Exception as e:
+                    logger.error(f"下载管理面板文件失败: {e}。")
+                    
+            # pip 更新依赖
+            logger.info("更新依赖中...")
+            try:
+                pip_installer.install(requirements_path="requirements.txt")
+            except Exception as e:
+                logger.error(f"更新依赖失败: {e}")
+            
             if reboot:
-                threading.Thread(target=self.astrbot_updator._reboot, args=(2, )).start()
+                # threading.Thread(target=self.astrbot_updator._reboot, args=(2, )).start()
+                self.core_lifecycle.restart()
                 return Response().ok(None, "更新成功，AstrBot 将在 2 秒内全量重启以应用新的代码。").__dict__
             else:
                 return Response().ok(None, "更新成功，AstrBot 将在下次启动时应用新的代码。").__dict__
@@ -50,6 +82,18 @@ class UpdateRoute(Route):
             logger.error(f"/api/update_project: {traceback.format_exc()}")
             return Response().error(e.__str__()).__dict__
         
+    async def update_dashboard(self):
+        try:
+            try:
+                await download_dashboard()
+            except Exception as e:
+                logger.error(f"下载管理面板文件失败: {e}。")
+                return Response().error(f"下载管理面板文件失败: {e}").__dict__
+            return Response().ok(None, "更新成功。刷新页面即可应用新版本面板。").__dict__
+        except Exception as e:
+            logger.error(f"/api/update_dashboard: {traceback.format_exc()}")
+            return Response().error(e.__str__()).__dict__
+        
     async def install_pip_package(self):
         data = await request.json
         package = data.get('package', '')

astrbot/dashboard/server.py

@@ -24,7 +24,7 @@ class AstrBotDashboard():
         # token 用于验证请求
         logging.getLogger(self.app.name).removeHandler(default_handler)
         self.context = RouteContext(self.config, self.app)
-        self.ur = UpdateRoute(self.context, core_lifecycle.astrbot_updator)
+        self.ur = UpdateRoute(self.context, core_lifecycle.astrbot_updator, core_lifecycle)
         self.sr = StatRoute(self.context, db, core_lifecycle)
         self.pr = PluginRoute(self.context, core_lifecycle, core_lifecycle.plugin_manager)
         self.cr = ConfigRoute(self.context, core_lifecycle)

changelogs/v3.4.10.md

@@ -0,0 +1,12 @@
+# What's Changed
+
+- 修复 LLM 请求报错信息被覆盖的问题，增强 LLM 请求错误处理 #243
+- 修复 Napcat 接口更新导致 QQ 图片发送失败的问题 #246
+- 修复某些请求不能正确应用代理的问题
+- 针对 api_base 的明显提示，修改 ollama 模板的 api_base #247
+- 支持登出 gewechat，在webchat等地方使用 `/gewe_logout` 指令，这在微信上显示账号下线但是 gewe 仍显示设备在线时很好用
+- 添加gewechat适配器过滤器
+- help显示AstrBot和webui版本
+- 优化webui和主程序更新的协调
+- 下载管理面板时显示提示、下载进度和下载速度
+- 管理面板前端更新功能入口移入右上角更新按钮，以便统一管理 #245

changelogs/v3.4.11.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- 为平台和提供商适配器添加默认 ID 配置 #248
+- 修复appid保存的问题和部分群聊at失效的问题和群聊@的sender username显示异常的问题
+- 优化更新项目时重启可能会导致Address already in use的问题
+- 各类异步任务报错后的优雅报错输出，而不是只有在退出程序的时候才输出异常日志。

changelogs/v3.4.12.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- Gewechat 微信支持图片、语音的收和发
+- 支持 OpenAI TTS（文字转语音）
+- 支持路径映射，解决 docker 部署时两端文件系统不一致导致的富媒体文件路径不存在问题
+- Napcat 下语音消息可能接收异常

changelogs/v3.4.13.md

@@ -0,0 +1,4 @@
+# What's Changed
+
+- 修复 astrbot_updator 属性缺失与stt_enabled 未初始化 #252
+- 支持消息分段回复

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

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

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

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

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

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

changelogs/v3.4.7.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- 更好的人格情景管理
+- 移除了不常用的人格提示词集
+- 优化webchat长连接的处理逻辑
+- 修复 tool 为空时部分模型请求错误的问题 #239

changelogs/v3.4.8.md

@@ -0,0 +1,5 @@
+# What's Changed
+
+- 支持 Gewechat 接入微信个人号(文字交互)
+- 支持回复时 At 和引用发送者 #241
+- 清除残留的 personalities

changelogs/v3.4.9.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- AstrBot 新域名：astrbot.app
+- LLM额外唤醒词与机器人唤醒词冲突时的处理
+- 调整部分日志的严重级别
+- 下载管理面板时显示提示、下载进度和下载速度

compose.yml

@@ -4,6 +4,8 @@ services:
   astrbot:
     image: soulter/astrbot:latest
     container_name: astrbot
-    network_mode: "host"
+    ports: 
+      - "6180-6200:6180-6200"
+      - "11451:11451"
     volumes:
-      - ./data:/AstrBot/data
+      - ./data:/AstrBot/data

dashboard/src/components/shared/AstrBotConfig.vue

@@ -4,7 +4,7 @@
     </h3>
     <v-card-text>
         <div v-for="(index, key) in iterable" :key="key" style="margin-bottom: 0.5px;" v-if="metadata[metadataKey]?.type === 'object' || metadata[metadataKey]?.config_template">
-            <v-alert v-if="metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint && metadata[metadataKey].items[key]?.type !== 'object'" style="margin-bottom: 16px"
+            <v-alert v-if="metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint" style="margin-bottom: 16px"
                 :text="metadata[metadataKey].items[key]?.hint" :title="'💡 关于' + metadata[metadataKey].items[key]?.description"
                 type="info" variant="tonal">
             </v-alert>
@@ -52,7 +52,7 @@
                 </div>
 
                 <div
-                    v-if="!metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint && metadata[metadataKey].items[key]?.type !== 'object' && !metadata[metadataKey].items[key]?.invisible">
+                    v-if="!metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint && !metadata[metadataKey].items[key]?.invisible">
                     <v-btn icon size="x-small" style="margin-bottom: 22px;">
                         <v-icon size="x-small">mdi-help</v-icon>
                         <v-tooltip activator="parent" location="start">{{ metadata[metadataKey].items[key]?.hint
@@ -63,7 +63,7 @@
         
         </div>
         <div v-else>
-            <v-alert v-if="metadata[metadataKey]?.obvious_hint && metadata[metadataKey]?.hint && metadata[metadataKey]?.type !== 'object'" style="margin-bottom: 16px"
+            <v-alert v-if="metadata[metadataKey]?.obvious_hint && metadata[metadataKey]?.hint" style="margin-bottom: 16px"
                 :text="metadata[metadataKey]?.hint" :title="'💡 关于' + metadata[metadataKey]?.description"
                 type="info" variant="tonal">
             </v-alert>
@@ -106,7 +106,7 @@
                 </div>
 
                 <div
-                    v-if="!metadata[metadataKey]?.obvious_hint && metadata[metadataKey]?.hint && metadata[metadataKey]?.type !== 'object' && !metadata[metadataKey]?.invisible">
+                    v-if="!metadata[metadataKey]?.obvious_hint && metadata[metadataKey]?.hint && !metadata[metadataKey]?.invisible">
                     <v-btn icon size="x-small" style="margin-bottom: 22px;">
                         <v-icon size="x-small">mdi-help</v-icon>
                         <v-tooltip activator="parent" location="start">{{ metadata[metadataKey]?.hint

dashboard/src/components/shared/ConfigDetailCard.vue

@@ -1,41 +0,0 @@
-<script setup>
-import UiParentCard from '@/components/shared/UiParentCard.vue';
-
-const props = defineProps({
-  config: Array
-});
-</script>
-
-<template>
-  <a v-show="config.length === 0">该插件没有配置</a>
-  <UiParentCard v-for="group in config" :key="group.name" :title="group.name" style="margin-bottom: 16px;">
-    <template v-for="item in group.body">
-      <template v-if="item.config_type === 'item'">
-        <template v-if="item.val_type === 'bool'">
-          <v-switch v-model="item.value" :label="item.name" :hint="item.description" color="primary" inset></v-switch>
-        </template>
-        <template v-else-if="item.val_type === 'str'">
-          <v-text-field v-model="item.value" :label="item.name" :hint="item.description" style="margin-bottom: 8px;"
-            variant="outlined"></v-text-field>
-        </template>
-        <template v-else-if="item.val_type === 'int'">
-          <v-text-field v-model="item.value" :label="item.name" :hint="item.description" style="margin-bottom: 8px;"
-            variant="outlined"></v-text-field>
-        </template>
-        <template v-else-if="item.val_type === 'list'">
-          <span>{{ item.name }}</span>
-          <v-combobox v-model="item.value" chips clearable label="请添加" multiple prepend-icon="mdi-tag-multiple-outline">
-            <template v-slot:selection="{ attrs, item, select, selected }">
-              <v-chip v-bind="attrs" :model-value="selected" closable @click="select" @click:close="remove(item)">
-                <strong>{{ item }}</strong>
-              </v-chip>
-            </template>
-          </v-combobox>
-        </template>
-      </template>
-      <template v-else-if="item.config_type === 'divider'">
-        <v-divider style="margin-top: 8px; margin-bottom: 8px;"></v-divider>
-      </template>
-    </template>
-  </UiParentCard>
-</template>

dashboard/src/layouts/full/vertical-header/VerticalHeader.vue

@@ -15,6 +15,9 @@ let newUsername = ref('');
 let status = ref('');
 let updateStatus = ref('')
 let hasNewVersion = ref(false);
+let botCurrVersion = ref('');
+let dashboardHasNewVersion = ref(false);
+let dashboardCurrentVersion = ref('');
 let version = ref('');
 
 const open = (link: string) => {
@@ -64,6 +67,9 @@ function checkUpdate() {
     .then((res) => {
       hasNewVersion.value = res.data.data.has_new_version;
       updateStatus.value = res.data.message;
+      botCurrVersion.value = res.data.data.version;
+      dashboardCurrentVersion.value = res.data.data.dashboard_version;
+      dashboardHasNewVersion.value = res.data.data.dashboard_has_new_version;
     })
     .catch((err) => {
       if (err.response.status == 401) {
@@ -84,7 +90,24 @@ function switchVersion(version: string) {
   })
     .then((res) => {
       updateStatus.value = res.data.message;
-      if (res.data.status == 'success') {
+      if (res.data.status == 'ok') {
+        setTimeout(() => {
+          window.location.reload();
+        }, 1000);
+      }
+    })
+    .catch((err) => {
+      console.log(err);
+      updateStatus.value = err
+    });
+}
+
+function updateDashboard() {
+  updateStatus.value = '正在更新...';
+  axios.post('/api/update/dashboard')
+    .then((res) => {
+      updateStatus.value = res.data.message;
+      if (res.data.status == 'ok') {
         setTimeout(() => {
           window.location.reload();
         }, 1000);
@@ -106,8 +129,8 @@ commonStore.getStartTime();
 <template>
   <v-app-bar elevation="0" height="70">
 
-    <v-btn style="margin-left: 22px;" class="hidden-md-and-down text-secondary" color="lightsecondary" icon rounded="sm" variant="flat"
-      @click.stop="customizer.SET_MINI_SIDEBAR(!customizer.mini_sidebar)" size="small">
+    <v-btn style="margin-left: 22px;" class="hidden-md-and-down text-secondary" color="lightsecondary" icon rounded="sm"
+      variant="flat" @click.stop="customizer.SET_MINI_SIDEBAR(!customizer.mini_sidebar)" size="small">
       <v-icon>mdi-menu</v-icon>
     </v-btn>
     <v-btn class="hidden-lg-and-up text-secondary ms-3" color="lightsecondary" icon rounded="sm" variant="flat"
@@ -136,11 +159,16 @@ commonStore.getStartTime();
       </template>
       <v-card>
         <v-card-title>
-          <span class="text-h5">更新项目</span>
+          <span class="text-h5">更新 AstrBot</span>
         </v-card-title>
         <v-card-text>
           <v-container>
-            <h3 class="mb-4">升级到最新版本</h3>
+            <h3 class="mb-4">升级到项目最新版本</h3>
+            <small>当前版本 {{ botCurrVersion }}</small>
+            <div class="mb-4">
+              <small>会同时尝试更新机器人主程序和管理面板。如果您正在使用 Docker 部署，也可以重新拉取镜像或者使用 <a
+                  href="https://containrrr.dev/watchtower/usage-overview/">watchtower</a> 来自动监控拉取。</small>
+            </div>
             <p>{{ updateStatus }}</p>
             <v-btn class="mt-4 mb-4" @click="switchVersion('latest')" color="primary" style="border-radius: 10px;"
               :disabled="!hasNewVersion">
@@ -148,7 +176,11 @@ commonStore.getStartTime();
             </v-btn>
             <v-divider></v-divider>
             <div style="margin-top: 16px;">
-              <h3 class="mb-4">切换到指定版本或指定提交</h3>
+              <h3 class="mb-4">切换到项目指定版本或指定提交</h3>
+              <div class="mb-4">
+                <small>跳到旧版本不会重新下载管理面板文件，这可能会造成部分数据显示错误。您可在 <a href="https://github.com/Soulter/AstrBot/releases">此处</a>
+                  找到对应的面板文件 dist.zip，解压后替换 data/dist 文件夹即可。</small>
+              </div>
               <v-text-field label="输入版本号或 master 分支下的 commit hash。" v-model="version" required
                 variant="outlined"></v-text-field>
               <div class="mb-4">
@@ -160,7 +192,29 @@ commonStore.getStartTime();
               <v-btn color="error" style="border-radius: 10px;" @click="switchVersion(version)">
                 确定切换
               </v-btn>
+            </div>
 
+            <v-divider></v-divider>
+            <div style="margin-top: 16px;">
+              <h3 class="mb-4">更新管理面板到最新版本</h3>
+              <div class="mb-4">
+                <small>当前版本 {{ dashboardCurrentVersion }}</small>
+                <br>
+
+              </div>
+
+              <div class="mb-4">
+                <p v-if="dashboardHasNewVersion">
+                  有新版本！
+                </p>
+                <p v-else="dashboardHasNewVersion">
+                  已经是最新版本了。
+                </p>
+              </div>
+
+              <v-btn color="primary" style="border-radius: 10px;" @click="updateDashboard()">
+                下载并更新
+              </v-btn>
             </div>
           </v-container>
         </v-card-text>
@@ -190,8 +244,7 @@ commonStore.getStartTime();
                 <v-text-field label="原密码*" type="password" v-model="password" required
                   variant="outlined"></v-text-field>
 
-                <v-text-field label="新用户名" v-model="newUsername" required
-                  variant="outlined"></v-text-field>
+                <v-text-field label="新用户名" v-model="newUsername" required variant="outlined"></v-text-field>
 
                 <v-text-field label="新密码" type="password" v-model="newPassword" required
                   variant="outlined"></v-text-field>

dashboard/src/layouts/full/vertical-sidebar/VerticalSidebar.vue

@@ -27,10 +27,10 @@ const sidebarMenu = shallowRef(sidebarItems);
         </v-btn>
       </v-list-item>
       <small style="display: block;" v-if="buildVer">构建: {{ buildVer }}</small>
-      <small style="display: block;" v-else="buildVer">构建: embedded</small>
+      <small style="display: block;" v-else>构建: embedded</small>
       <v-tooltip text="使用 /dashbord_update 指令更新管理面板">
         <template v-slot:activator="{ props }">
-          <small v-bind="props" v-if="buildVer != version" style="display: block; margin-top: 4px;">面板有更新</small>
+          <small v-bind="props" v-if="hasWebUIUpdate" style="display: block; margin-top: 4px;">面板有更新</small>
         </template>
       </v-tooltip>
 
@@ -50,19 +50,12 @@ export default {
   },
   data: () => ({
     version: "",
-    buildVer: ""
+    buildVer: "",
+    hasWebUIUpdate: false,
   }),
   mounted() {
     this.get_version()
-    fetch('/assets/version').then((res) => {
-      return res.text()
-    }).then((res) => {
-      if (res.length > 10) {
-        // 不是版本，不显示 😎
-        return
-      }
-      this.buildVer = res.replace(/\s+/g, '')
-    })
+    this.check_webui_update()
   },
   methods: {
     get_version() {
@@ -73,6 +66,16 @@ export default {
         .catch((err) => {
           console.log(err);
         });
+    },
+    check_webui_update() {
+      axios.get('/api/update/check?type=dashboard')
+        .then((res) => {
+          this.hasWebUIUpdate = res.data.data.has_new_version;
+          this.buildVer = res.data.data.current_version;
+        })
+        .catch((err) => {
+          console.log(err);
+        });
     }
   },
 };

dashboard/src/views/ChatPage.vue

@@ -1,9 +1,7 @@
 <script setup>
 import axios from 'axios';
-import { ref } from 'vue';
 import { marked } from 'marked';
 
-
 marked.setOptions({
     breaks: true
 });
@@ -183,11 +181,14 @@ export default {
             mediaRecorder: null,
 
             status: {},
-            statusText: ''
+            statusText: '',
+            
+            eventSource: null
         }
     },
 
     mounted() {
+        this.startListeningEvent();
         this.checkStatus();
         this.getConversations();
         let inputField = document.getElementById('input-field');
@@ -205,8 +206,70 @@ export default {
         }.bind(this));
     },
 
+    beforeUnmount() {
+        console.log("111")
+        if (this.eventSource) {
+            this.eventSource.cancel();
+            console.log('SSE连接已断开');
+        }
+    },
+
     methods: {
 
+        async startListeningEvent() {
+            const response = await fetch('/api/chat/listen', {
+                method: 'GET',
+                headers: {
+                    'Content-Type': 'application/json',
+                    'Authorization': 'Bearer ' + localStorage.getItem('token')
+                }
+            })
+
+            if (!response.ok) {
+                console.error('SSE连接失败:', response.statusText);
+                return;
+            }
+
+            const reader = response.body.getReader();
+            const decoder = new TextDecoder();
+
+            this.eventSource = reader
+
+            while (true) {
+                const { done, value } = await reader.read();
+                if (done) {
+                    console.log('SSE连接关闭');
+                    break;
+                }
+
+                const chunk = decoder.decode(value, { stream: true });
+                console.log("!!!!", chunk);
+
+                if (chunk === '[HB]\n') {
+                    continue; // 心跳包
+                }
+                if (chunk === '[ERROR]\n') {
+                    continue;
+                }
+
+                if (chunk.startsWith('[IMAGE]')) {
+                    let img = chunk.replace('[IMAGE]', '');
+                    let bot_resp = {
+                        type: 'bot',
+                        message: `<img src="/api/chat/get_file?filename=${img}" style="max-width: 80%; border-radius: 8px; box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);"/>`
+                    }
+                    this.messages.push(bot_resp);
+                } else {
+                    let bot_resp = {
+                        type: 'bot',
+                        message: chunk
+                    }
+                    this.messages.push(bot_resp);
+                }
+                this.scrollToBottom();
+            }
+        },
+
         removeAudio() {
             this.stagedAudioUrl = null;
         },
@@ -417,41 +480,41 @@ export default {
 
                     this.loadingChat = false;
 
-                    const reader = response.body.getReader();  // 获取流的 Reader
-                    const decoder = new TextDecoder();
+                    // const reader = response.body.getReader();  // 获取流的 Reader
+                    // const decoder = new TextDecoder();
 
-                    const readStream = async () => {
-                        const { done, value } = await reader.read();  // 读取流中的数据
-                        if (done) {
-                            console.log("Stream finished.");
-                            return;
-                        }
+                    // const readStream = async () => {
+                    //     const { done, value } = await reader.read();  // 读取流中的数据
+                    //     if (done) {
+                    //         console.log("Stream finished.");
+                    //         return;
+                    //     }
 
-                        const chunk = decoder.decode(value, { stream: true });
-                        // bot_resp.message.value += chunk;
+                    //     const chunk = decoder.decode(value, { stream: true });
+                    //     // bot_resp.message.value += chunk;
 
-                        console.log("!!!!", chunk);
-                        if (chunk.startsWith('[IMAGE]')) {
-                            let img = chunk.replace('[IMAGE]', '');
-                            let bot_resp = {
-                                type: 'bot',
-                                message: `<img src="/api/chat/get_file?filename=${img}" style="max-width: 80%; border-radius: 8px; box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);"/>`
-                            }
-                            this.messages.push(bot_resp);
-                        } else {
-                            let bot_resp = {
-                                type: 'bot',
-                                message: chunk
-                            }
+                    //     console.log("!!!!", chunk);
+                    //     if (chunk.startsWith('[IMAGE]')) {
+                    //         let img = chunk.replace('[IMAGE]', '');
+                    //         let bot_resp = {
+                    //             type: 'bot',
+                    //             message: `<img src="/api/chat/get_file?filename=${img}" style="max-width: 80%; border-radius: 8px; box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);"/>`
+                    //         }
+                    //         this.messages.push(bot_resp);
+                    //     } else {
+                    //         let bot_resp = {
+                    //             type: 'bot',
+                    //             message: chunk
+                    //         }
 
-                            this.messages.push(bot_resp);
-                        }
+                    //         this.messages.push(bot_resp);
+                    //     }
 
-                        this.scrollToBottom();
-                        readStream();  // 递归读取流
-                    };
+                    //     this.scrollToBottom();
+                    //     readStream();  // 递归读取流
+                    // };
 
-                    readStream();
+                    // readStream();
                 })
                 .catch(err => {
                     console.error(err);
@@ -463,7 +526,7 @@ export default {
                 container.scrollTop = container.scrollHeight;
             });
         }
-    }
+    },
 }
 
 </script>

dashboard/src/views/ConfigPage.vue

@@ -3,6 +3,7 @@ import axios from 'axios';
 import AstrBotConfig from '@/components/shared/AstrBotConfig.vue';
 import WaitingForRestart from '@/components/shared/WaitingForRestart.vue';
 import { VueMonacoEditor } from '@guolao/vue-monaco-editor'
+import config from '@/config';
 </script>
 
 <template>
@@ -44,7 +45,10 @@ import { VueMonacoEditor } from '@guolao/vue-monaco-editor'
               <v-expansion-panel-text v-if="metadata[key]['metadata'][key2]?.config_template">
                 <!-- 带有 config_template 的配置项 -->
                 <v-tabs style="margin-top: 16px;" align-tabs="left" color="deep-purple-accent-4" v-model="config_template_tab">
-                  <v-tab v-for="(item, index) in config_data[key2]" :key="index" :value="index">
+                  <v-tab v-if="metadata[key]['metadata'][key2]?.tmpl_display_title" v-for="(item, index) in config_data[key2]" :key="index" :value="index">
+                    {{ item[metadata[key]['metadata'][key2]?.tmpl_display_title] }}
+                  </v-tab>
+                  <v-tab v-else v-for="(item, index) in config_data[key2]" :key="index + '_'" :value="index">
                     {{ item.id }}({{ item.type }})
                   </v-tab>
                   <v-menu>
@@ -64,6 +68,10 @@ import { VueMonacoEditor } from '@guolao/vue-monaco-editor'
                   <v-tabs-window-item v-for="(config_item, index) in config_data[key2]" v-show="config_template_tab === index"
                     :key="index" :value="index">
                     <v-container>
+                      <v-btn variant="tonal" rounded="xl" color="error" @click="config_data[key2].splice(index, 1)">
+                        删除这项
+                      </v-btn>
+
                       <AstrBotConfig :metadata="metadata[key]['metadata']" :iterable="config_item" :metadataKey="key2"></AstrBotConfig>
                     </v-container>
                   </v-tabs-window-item>
@@ -204,7 +212,7 @@ export default {
 
       let tmpl = this.metadata[group_name]['metadata'][config_item_name]['config_template'][val];
       let new_tmpl_cfg = JSON.parse(JSON.stringify(tmpl));
-      new_tmpl_cfg.id = "new_" + val + "_" + this.config_data[config_item_name].length;
+      // new_tmpl_cfg.id = "new_" + val + "_" + this.config_data[config_item_name].length;
       this.config_data[config_item_name].push(new_tmpl_cfg);
       this.config_template_tab = this.config_data[config_item_name].length - 1;
     }

dashboard/src/views/ExtensionPage.vue

@@ -1,7 +1,7 @@
 <script setup>
 import ExtensionCard from '@/components/shared/ExtensionCard.vue';
-import ConfigDetailCard from '@/components/shared/ConfigDetailCard.vue';
 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';
 
@@ -37,7 +37,11 @@ import axios from 'axios';
     </v-col>
     <v-col cols="12" md="12">
       <div style="background-color: white; width: 100%; padding: 16px; border-radius: 10px;">
-        <h3>🧩 插件市场</h3>
+        <div style="display: flex; align-items: center;">
+          <h3>🧩 插件市场</h3>
+          <small style="margin-left: 16px;">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 `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。</small>
+        </div>
+        
       </div>
     </v-col>
     <v-col cols="12" md="6" lg="4" v-for="plugin in pluginMarketData">
@@ -52,11 +56,17 @@ import axios from 'axios';
           <v-btn v-else variant="plain" disabled>已安装</v-btn>
         </div>
       </ExtensionCard>
+      
+    </v-col>
+
+    <v-col style="margin-bottom: 16px;" cols="12" md="12">
+      <small ><a href="https://astrbot.app/dev/plugin.html">插件开发文档</a></small> |
+      <small> <a href="https://github.com/Soulter/AstrBot_Plugins_Collection">提交插件仓库</a></small>
     </v-col>
 
   </v-row>
 
-  <v-dialog v-model="configDialog" width="750">
+  <v-dialog v-model="configDialog" width="1000">
     <template v-slot:activator="{ props }">
     </template>
     <v-card>
@@ -65,7 +75,8 @@ import axios from 'axios';
       </v-card-title>
       <v-card-text>
         <v-container>
-          <ConfigDetailCard :config="extension_config"></ConfigDetailCard>
+          <AstrBotConfig v-if="extension_config.metadata" :metadata="extension_config.metadata" :iterable="extension_config.config" :metadataKey=curr_namespace></AstrBotConfig>
+          <p v-else>这个插件没有配置</p>
         </v-container>
       </v-card-text>
       <v-card-actions>
@@ -172,9 +183,9 @@ export default {
   name: 'ExtensionPage',
   components: {
     ExtensionCard,
-    ConfigDetailCard,
     WaitingForRestart,
-    ConsoleDisplayer
+    ConsoleDisplayer,
+    AstrBotConfig
   },
   data() {
     return {
@@ -189,7 +200,10 @@ export default {
       snack_success: "success",
       loading_: false,
       configDialog: false,
-      extension_config: {},
+      extension_config: {
+        "metadata": {},
+        "config": {}
+      },
       upload_file: null,
       pluginMarketData: {},
       loadingDialog: {
@@ -364,7 +378,7 @@ export default {
     openExtensionConfig(extension_name) {
       this.curr_namespace = extension_name;
       this.configDialog = true;
-      axios.get('/api/config/get?namespace=' + extension_name).then((res) => {
+      axios.get('/api/config/get?plugin_name=' + extension_name).then((res) => {
         this.extension_config = res.data.data;
         console.log(this.extension_config);
       }).catch((err) => {
@@ -372,10 +386,7 @@ export default {
       });
     },
     updateConfig() {
-      axios.post('/api/config/plugin/update', {
-        "config": this.extension_config,
-        "namespace": this.curr_namespace
-      }).then((res) => {
+      axios.post('/api/config/plugin/update?plugin_name='+this.curr_namespace, this.extension_config.config).then((res) => {
         if (res.data.status === "ok") {
           this.toast(res.data.message, "success");
           this.$refs.wfr.check();

dashboard/src/views/dashboards/default/DefaultDashboard.vue

@@ -1,4 +1,13 @@
 <template>
+  <v-row style="margin: 2px;">
+    <v-alert
+      :type="noticeType"
+      :text="noticeContent"
+      :title="noticeTitle"
+      v-if="noticeTitle && noticeContent"
+      closable
+    ></v-alert>
+  </v-row>
   <v-row>
     <v-col cols="12" md="4">
       <TotalMessage :stat="stat" />
@@ -38,13 +47,26 @@ export default {
   },
   data: () => ({
     stat: {},
+    noticeTitle: '',
+    noticeContent: '',
+    noticeType: '',
   }),
 
   mounted() {
     axios.get('/api/stat/get').then((res) => {
       this.stat = res.data.data;
     });
-  }
+
+    axios.get('https://api.soulter.top/astrbot-announcement').then((res) => {
+      let data = res.data.data;
+      // 如果 dashboard-notice 在其中
+      if (data['dashboard-notice']) {
+        this.noticeTitle = data['dashboard-notice'].title;
+        this.noticeContent = data['dashboard-notice'].content;
+        this.noticeType = data['dashboard-notice'].type;
+      }
+    });
+  },
 };
 
 </script>

main.py

@@ -6,7 +6,7 @@ from astrbot.dashboard import AstrBotDashBoardLifecycle
 from astrbot.core import db_helper
 from astrbot.core import logger, LogManager, LogBroker
 from astrbot.core.config.default import VERSION
-from astrbot.core.utils.io import download_dashboard
+from astrbot.core.utils.io import download_dashboard, get_dashboard_version
 
 # add parent path to sys.path
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -37,22 +37,22 @@ def check_env():
     
 async def check_dashboard_files():
     '''下载管理面板文件'''
-    if os.path.exists("data/dist"):
-        if os.path.exists("data/dist/assets/version"):
-            with open("data/dist/assets/version", "r") as f:
-                v = f.read().strip()
-                if v != f"v{VERSION}":
-                    logger.warning("检测到管理面板有更新。可以使用 /dashboard update 命令更新。")
-                else:
-                    logger.info("管理面板文件已是最新。")
+
+    v = await get_dashboard_version()
+    if v is not None:
+        # has file
+        if v == f"v{VERSION}":
+            logger.info("管理面板文件已是最新。")
+        else:
+            logger.warning("检测到管理面板有更新。可以使用 /dashboard_update 命令更新。")
         return
     
-    logger.info("开始下载管理面板文件...")
+    logger.info("开始下载管理面板文件...高峰期（晚上）可能导致较慢的速度。如多次下载失败，请前往 https://github.com/Soulter/AstrBot/releases/latest 下载 dist.zip，并将其中的 dist 文件夹解压至 data 目录下。")
     
     try:
         await download_dashboard()
     except Exception as e:
-        logger.critical(f"下载管理面板文件失败: {e}")
+        logger.critical(f"下载管理面板文件失败: {e}。")
         return
 
     logger.info("管理面板下载完成。")

packages/astrbot/long_term_memory.py

@@ -0,0 +1,128 @@
+import datetime
+import uuid
+import random
+import astrbot.api.star as star
+from astrbot.api.event import AstrMessageEvent
+from astrbot.api.platform import MessageType
+from astrbot.api.provider import ProviderRequest
+from astrbot.api.message_components import Plain, Image
+from astrbot import logger
+from collections import defaultdict
+
+'''
+聊天记忆增强
+'''
+class LongTermMemory:
+    def __init__(self, config: dict, context: star.Context):
+        self.config = config
+        self.context = context
+        self.session_chats = defaultdict(list)
+        """记录群成员的群聊记录"""
+        try:
+            self.max_cnt = int(self.config["group_message_max_cnt"])
+        except BaseException as e:
+            logger.error(e)
+            self.max_cnt = 300
+        self.image_caption = self.config["image_caption"]
+        self.image_caption_prompt = self.config["image_caption_prompt"]
+        
+        self.active_reply = self.config["active_reply"]
+        self.enable_active_reply = self.active_reply.get("enable", False)
+        self.ar_method = self.active_reply["method"]
+        self.ar_possibility = self.active_reply["possibility_reply"]
+        self.ar_prompt = self.active_reply.get("prompt", "")
+        
+        self.put_history_to_prompt = self.config["put_history_to_prompt"]
+        
+    async def remove_session(self, event: AstrMessageEvent) -> int:
+        cnt = 0
+        if event.unified_msg_origin in self.session_chats:
+            cnt = len(self.session_chats[event.unified_msg_origin])
+            del self.session_chats[event.unified_msg_origin]
+        return cnt
+
+    async def get_image_caption(self, image_url: str) -> str:
+        provider = self.context.get_using_provider()
+        response = await provider.text_chat(
+            prompt=self.image_caption_prompt,
+            session_id=uuid.uuid4().hex,
+            image_urls=[image_url],
+            persist=False,
+        )
+        return response.completion_text
+    
+    async def need_active_reply(self, event: AstrMessageEvent) -> bool:
+        if not self.enable_active_reply:
+            return False
+        if event.get_message_type() != MessageType.GROUP_MESSAGE:
+            return False
+        
+        if event.is_at_or_wake_command:
+            # if the message is a command, let it pass
+            return False
+
+        match self.ar_method:
+            case "possibility_reply":
+                trig = random.random() < self.ar_possibility
+                return trig
+            
+        return False
+
+
+    async def handle_message(self, event: AstrMessageEvent):
+        '''仅支持群聊'''
+        if event.get_message_type() == MessageType.GROUP_MESSAGE:
+            datetime_str = datetime.datetime.now().strftime("%H:%M:%S")
+
+            final_message = f"[{event.message_obj.sender.nickname}/{datetime_str}]: "
+
+            for comp in event.get_messages():
+                if isinstance(comp, Plain):
+                    final_message += f" {comp.text}"
+                elif isinstance(comp, Image):
+                    # image_urls.append(comp.url if comp.url else comp.file)
+                    if self.image_caption:
+                        try:
+                            caption = await self.get_image_caption(
+                                comp.url if comp.url else comp.file
+                            )
+                            final_message += f" [Image: {caption}]"
+                        except Exception as e:
+                            logger.error(f"获取图片描述失败: {e}")
+                    else:
+                        final_message += " [Image]"
+            logger.debug(f"ltm | {event.unified_msg_origin} | {final_message}")
+            self.session_chats[event.unified_msg_origin].append(final_message)
+            if len(self.session_chats[event.unified_msg_origin]) > self.max_cnt:
+                self.session_chats[event.unified_msg_origin].pop(0)
+
+    async def on_req_llm(self, event: AstrMessageEvent, req: ProviderRequest):
+        '''当触发 LLM 请求前，调用此方法修改 req'''
+        if event.unified_msg_origin not in self.session_chats:
+            return
+        
+        chats_str = '\n---\n'.join(self.session_chats[event.unified_msg_origin])
+        
+        if self.put_history_to_prompt:
+            prompt = req.prompt
+            req.prompt = f"You are now in a chatroom. The chat history is as follows:\n{chats_str}"
+            req.prompt += f"\nNow, a new message is coming: `{prompt}`. Please react to it. Only output your response and do not output any other information."
+            req.contexts = [] # 清空上下文，当使用了群聊增强，所有聊天记录都在一个prompt中。
+        else:
+            req.system_prompt += "You are now in a chatroom. The chat history is as follows: \n"
+            req.system_prompt += chats_str
+            if self.image_caption:
+                req.system_prompt += (
+                    "The images sent by the members are displayed in text form above."
+                )
+            
+    async def after_req_llm(self, event: AstrMessageEvent):
+        if event.unified_msg_origin not in self.session_chats:
+            return
+
+        if event.get_result() and event.get_result().is_llm_result():
+            final_message = f"[AstrBot/{datetime.datetime.now().strftime('%H:%M:%S')}]: {event.get_result().get_plain_text()}"
+            logger.debug(f"ltm | {event.unified_msg_origin} | {final_message}")
+            self.session_chats[event.unified_msg_origin].append(final_message)
+            if len(self.session_chats[event.unified_msg_origin]) > self.max_cnt:
+                self.session_chats[event.unified_msg_origin].pop(0)

packages/astrbot/main.py

@@ -1,15 +1,24 @@
 import aiohttp
 import datetime
+import builtins
 import astrbot.api.star as star
 import astrbot.api.event.filter as filter
 from astrbot.api.event import AstrMessageEvent, MessageEventResult
-from astrbot.api import personalities, sp
-from astrbot.api.provider import Personality, ProviderRequest
-from astrbot.core.utils.io import download_dashboard
+from astrbot.api import sp
+from astrbot.api.provider import Personality, ProviderRequest, LLMResponse
+from astrbot.core.utils.io import download_dashboard, get_dashboard_version
+from astrbot.core.star.star_handler import star_handlers_registry, StarHandlerMetadata
+from astrbot.core.star.star import star_map
+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.config.default import VERSION
+from .long_term_memory import LongTermMemory
+from astrbot.core import logger
 
 from typing import Union
 
-@star.register(name="astrbot", desc="AstrBot 基础指令集合", author="Soulter", version="4.0.0")
+@star.register(name="astrbot", desc="AstrBot 基础指令结合 + 拓展功能", author="Soulter", version="4.0.0")
 class Main(star.Star):
     def __init__(self, context: star.Context) -> None:
         self.context = context
@@ -18,11 +27,16 @@ class Main(star.Star):
         self.identifier = cfg['provider_settings']['identifier']
         self.enable_datetime = cfg['provider_settings']["datetime_system_prompt"]
         
-        self.kdb_enabled = False
+        self.ltm = None
+        if self.context.get_config()['provider_ltm_settings']['group_icl_enable'] or self.context.get_config()['provider_ltm_settings']['active_reply']['enable']:
+            try:
+                self.ltm = LongTermMemory(self.context.get_config()['provider_ltm_settings'], self.context)
+            except BaseException as e:
+                logger.error(f"聊天增强 err: {e}")
     
     async def _query_astrbot_notice(self):
         try:
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
                 async with session.get("https://astrbot.soulter.top/notice.json", timeout=2) as resp:
                     return (await resp.json())["notice"]
         except BaseException:
@@ -30,37 +44,42 @@ class Main(star.Star):
         
     @filter.command("help")
     async def help(self, event: AstrMessageEvent):
+        '''查看帮助'''
         notice = ""
         try:
             notice = await self._query_astrbot_notice()
         except BaseException:
             pass
+        
+        dashboard_version = await get_dashboard_version()
 
-        msg = "已注册的 AstrBot 内置指令:\n"
-        msg += f"""[System]
-/plugin: 查看注册的插件、插件帮助
-/t2i: 开启/关闭文本转图片模式
-/sid: 获取当前会话的 ID
+        msg = f"""AstrBot v{VERSION}(WebUI: {dashboard_version})
+AstrBot 指令:
+[System]
+/plugin: 查看插件、插件帮助
+/t2i: 开关文本转图片
+/sid: 获取会话 ID
 /op <admin_id>: 授权管理员
 /deop <admin_id>: 取消管理员
-/wl <sid>: 添加会话白名单
-/dwl <sid>: 删除会话白名单
+/wl <sid>: 添加白名单
+/dwl <sid>: 删除白名单
 /dashboard_update: 更新管理面板
+/alter_cmd: 设置指令权限
 
 [大模型]
-/provider: 查看、切换大模型提供商
-/model: 查看、切换提供商模型列表
-/key: 查看、切换 API Key
+/provider: 大模型提供商
+/model: 模型列表
+/key: API Key
 /reset: 重置 LLM 会话
-/history: 获取会话历史记录
-/persona: 情境人格设置
-/tool ls: 查看、激活、停用当前注册的函数工具
+/history: 对话记录
+/persona: 人格情景
+/tool ls: 函数工具
 
 [其他]
-/set <变量名> <值>: 为当前会话定义一个变量。适用于 Dify 工作流输入。
-/unset <变量名>: 删除当前会话的变量。
+/set <变量名> <值>: 为会话定义一个变量。适用于 Dify 工作流输入。
+/unset <变量名>: 删除会话的变量。
 
-提示：如果要查看插件指令，请输入 /plugin 查看具体信息。
+提示：如要查看插件指令，请输入 /plugin 查看具体信息。
 {notice}"""
 
         event.set_result(MessageEventResult().message(msg).use_t2i(False))
@@ -77,7 +96,7 @@ class Main(star.Star):
             active = " (启用)" if tool.active else "(停用)"
             msg += f"- {tool.name}: {tool.description} {active}\n"
             
-        msg += "\n使用 /tool on/off <工具名> 激活或者停用工具。"
+        msg += "\n使用 /tool on/off <工具名> 激活或者停用函数工具。/tool off_all 停用所有函数工具。"
         event.set_result(MessageEventResult().message(msg).use_t2i(False))
         
     @tool.command("on")
@@ -93,6 +112,13 @@ class Main(star.Star):
             event.set_result(MessageEventResult().message(f"停用工具 {tool_name} 成功。"))
         else:
             event.set_result(MessageEventResult().message(f"停用工具 {tool_name} 失败，未找到此工具。"))
+            
+    @tool.command("off_all")
+    async def tool_all_off(self, event: AstrMessageEvent):
+        tm = self.context.get_llm_tool_manager()
+        for tool in tm.func_list:
+            self.context.deactivate_llm_tool(tool.name)
+        event.set_result(MessageEventResult().message(f"停用所有工具成功。"))
 
     @filter.command("plugin")
     async def plugin(self, event: AstrMessageEvent, oper1: str = None, oper2: str = None):
@@ -103,7 +129,7 @@ class Main(star.Star):
             if plugin_list_info.strip() == "":
                 plugin_list_info = "没有加载任何插件。"
             
-            plugin_list_info += "\n使用 /plugin <插件名> 查看插件帮助。\n使用 /plugin on/off <插件名> 启用或者禁用插件。"
+            plugin_list_info += "\n使用 /plugin <插件名> 查看插件帮助和加载的指令。\n使用 /plugin on/off <插件名> 启用或者禁用插件。"
             event.set_result(MessageEventResult().message(f"{plugin_list_info}").use_t2i(False))
         else:
             if oper1 == "off":
@@ -126,10 +152,34 @@ class Main(star.Star):
                 plugin = self.context.get_registered_star(oper1)
                 if plugin is None:
                     event.set_result(MessageEventResult().message("未找到此插件。"))
-                else:
-                    help_msg = plugin.star_cls.__doc__ if plugin.star_cls.__doc__ else "该插件未提供帮助信息"
-                    ret = f"插件 {oper1} 帮助信息：\n" + help_msg
-                    event.set_result(MessageEventResult().message(ret).use_t2i(False))
+                    return
+                help_msg = plugin.star_cls.__doc__ if plugin.star_cls.__doc__ else "帮助信息: 未提供"
+                help_msg += f"\n\n作者: {plugin.author}\n版本: {plugin.version}"
+                command_handlers = []
+                command_names = []
+                for handler in star_handlers_registry:
+                    assert isinstance(handler, StarHandlerMetadata)
+                    if handler.handler_module_path != plugin.module_path:
+                        continue
+                    for filter_ in handler.event_filters:
+                        if isinstance(filter_, CommandFilter):
+                            command_handlers.append(handler)
+                            command_names.append(filter_.command_name)
+                            break
+                        elif isinstance(filter_, CommandGroupFilter):
+                            command_handlers.append(handler)
+                            command_names.append(filter_.group_name)
+                            
+                if len(command_handlers) > 0:
+                    help_msg += "\n\n指令列表：\n"
+                    for i in range(len(command_handlers)):
+                        help_msg += f"{command_names[i]}: {command_handlers[i].desc}\n"
+                        
+                    help_msg += "\nTip: 指令的触发需要添加唤醒前缀，默认为 /。"
+                
+                ret = f"插件 {oper1} 帮助信息：\n" + help_msg
+                ret += "更多帮助信息请查看插件仓库 README。"
+                event.set_result(MessageEventResult().message(ret).use_t2i(False))
 
     @filter.command("t2i")
     async def t2i(self, event: AstrMessageEvent):
@@ -189,6 +239,10 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     async def provider(self, event: AstrMessageEvent, idx: int = None):
         '''查看或者切换 LLM Provider'''
         
+        if not self.context.get_using_provider():
+            event.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
+        
         if idx is None:
             ret = "## 当前载入的 LLM 提供商\n"
             for idx, llm in enumerate(self.context.get_all_providers()):
@@ -211,13 +265,30 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
 
             event.set_result(MessageEventResult().message(f"成功切换到 {id_}。"))
 
+    @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("reset")
     async def reset(self, message: AstrMessageEvent):
+        
+        if not self.context.get_using_provider():
+            message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
+        
         await self.context.get_using_provider().forget(message.session_id)
-        message.set_result(MessageEventResult().message("重置成功"))
+        ret = "清除会话 LLM 聊天历史成功。"
+        if self.ltm:
+            cnt = await self.ltm.remove_session(event=message)
+            ret += f"\n聊天增强: 已清除 {cnt} 条聊天记录。"
+        
+        message.set_result(MessageEventResult().message(ret))
 
     @filter.command("model")
     async def model_ls(self, message: AstrMessageEvent, idx_or_name: Union[int, str] = None):
+                
+        if not self.context.get_using_provider():
+            message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
+        
+        
         if idx_or_name is None:
             models = []
             try:
@@ -258,6 +329,12 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
 
     @filter.command("history")
     async def his(self, message: AstrMessageEvent, page: int = 1):
+        
+                
+        if not self.context.get_using_provider():
+            message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
+        
         size_per_page = 3
         contexts, total_pages = await self.context.get_using_provider().get_human_readable_context(message.session_id, page, size_per_page)
 
@@ -277,6 +354,10 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("key")
     async def key(self, message: AstrMessageEvent, index: int=None):
+                
+        if not self.context.get_using_provider():
+            message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
         
         if index is None:
             keys_data = self.context.get_using_provider().get_keys()
@@ -303,50 +384,67 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
                         MessageEventResult().message("切换 Key 未知错误: "+str(e)))
                 message.set_result(MessageEventResult().message("切换 Key 成功。"))
 
+    @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("persona")
     async def persona(self, message: AstrMessageEvent):
+                
+        if not self.context.get_using_provider():
+            message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
+            return
+        
+        
         l = message.message_str.split(" ")
+        
+        curr_persona_name = "无"
+        if self.context.get_using_provider().curr_personality:
+            curr_persona_name = self.context.get_using_provider().curr_personality['name']
+        
         if len(l) == 1:
             message.set_result(
                 MessageEventResult().message(f"""[Persona]
 
-- 设置人格: `/persona 人格名`, 如 /persona 编剧
-- 人格列表: `/persona list`
-- 人格详细信息: `/persona view 人格名`
-- 自定义人格: /persona 人格文本
-- 重置 LLM 会话(清除人格): /reset
-- 重置 LLM 会话(保留人格): /reset p
+- 设置人格情景: `/persona 人格名`, 如 /persona 编剧
+- 人格情景列表: `/persona list`
+- 人格情景详细信息: `/persona view 人格名`
+- 取消人格: `/persona unset`
 
-【当前人格】: {str(self.context.get_using_provider().curr_personality['prompt'])}
+当前人格情景: {curr_persona_name}
+
+配置人格情景请前往管理面板-配置页
 """).use_t2i(False))
         elif l[1] == "list":
             msg = "人格列表：\n"
-            for key in personalities.keys():
-                msg += f"- {key}\n"
+            for persona in self.context.provider_manager.personas:
+                msg += f"- {persona['name']}\n"
             msg += '\n\n*输入 `/persona view 人格名` 查看人格详细信息'
             message.set_result(MessageEventResult().message(msg))
         elif l[1] == "view":
             if len(l) == 2:
-                message.set_result(MessageEventResult().message("请输入人格名"))
+                message.set_result(MessageEventResult().message("请输入人格情景名"))
+                return
             ps = l[2].strip()
-            if ps in personalities:
+            if persona := next(builtins.filter(
+                lambda persona: persona['name'] == ps, 
+                self.context.provider_manager.personas
+            ), None):
                 msg = f"人格{ps}的详细信息：\n"
-                msg += f"{personalities[ps]}\n"
+                msg += f"{persona['prompt']}\n"
             else:
                 msg = f"人格{ps}不存在"
             message.set_result(MessageEventResult().message(msg))
+        elif l[1] == "unset":
+            self.context.get_using_provider().curr_personality = None
+            message.set_result(MessageEventResult().message("取消人格成功。"))
         else:
             ps = "".join(l[1:]).strip()
-            if ps in personalities:
-                self.context.get_using_provider().curr_personality = Personality(
-                    name=ps, prompt=personalities[ps])
-                message.set_result(
-                    MessageEventResult().message(f"人格已设置。 \n人格信息: {ps}"))
+            if persona := next(builtins.filter(
+                lambda persona: persona['name'] == ps, 
+                self.context.provider_manager.personas
+            ), None):
+                self.context.get_using_provider().curr_personality = persona
+                message.set_result(MessageEventResult().message("设置成功。如果您正在切换到不同的人格，请注意使用 /reset 来清空上下文，防止原人格对话影响现人格。"))
             else:
-                self.context.get_using_provider().curr_personality = Personality(
-                    name="自定义人格", prompt=ps)
-                message.set_result(
-                    MessageEventResult().message(f"人格已设置。 \n人格信息: {ps}"))
+                message.set_result(MessageEventResult().message("不存在该人格情景。使用 /persona list 查看所有。"))
     
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("dashboard_update")
@@ -355,21 +453,6 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
         await download_dashboard()
         yield event.plain_result("管理面板更新完成。")
 
-    @filter.on_llm_request()
-    async def decorate_llm_req(self, event: AstrMessageEvent, req: ProviderRequest):
-        provider = self.context.get_using_provider()
-        if self.prompt_prefix:
-            req.prompt = self.prompt_prefix + req.prompt
-        if self.identifier:
-            user_id = event.message_obj.sender.user_id
-            user_nickname = event.message_obj.sender.nickname
-            user_info = f"[User ID: {user_id}, Nickname: {user_nickname}]\n"
-            req.prompt = user_info + req.prompt
-        if self.enable_datetime:
-            req.system_prompt += f"\nCurrent datetime: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M')}"
-        if provider.curr_personality['prompt']:
-            req.system_prompt += f"\n{provider.curr_personality['prompt']}"
-        
     @filter.command("set")
     async def set_variable(self, event: AstrMessageEvent, key: str, value: str):
         session_id = event.get_session_id()
@@ -397,32 +480,181 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
             del session_var[key]
             sp.put("session_variables", session_vars)
             yield event.plain_result(f"会话 {session_id} 变量 {key} 移除成功。")
+            
+    @filter.command("gewe_logout")
+    async def gewe_logout(self, event: AstrMessageEvent):
+        platforms = self.context.platform_manager.platform_insts
+        for platform in platforms:
+            if platform.meta().name == "gewechat":
+                yield event.plain_result("正在登出 gewechat")
+                await platform.logout()
+                yield event.plain_result("已登出 gewechat")
+                return
+            
+            
+    @filter.platform_adapter_type(filter.PlatformAdapterType.ALL)
+    async def on_message(self, event: AstrMessageEvent):
+        '''群聊记忆增强'''
+        if self.ltm:
+            need_active = await self.ltm.need_active_reply(event)
+                        
+            group_icl_enable = self.context.get_config()['provider_ltm_settings']['group_icl_enable']
+            if group_icl_enable:
+                '''记录对话'''
+                try:
+                    await self.ltm.handle_message(event)
+                except BaseException as e:
+                    logger.error(e)
                 
-    @filter.command_group("kdb")
-    def kdb(self):
-        pass
-        
-    @kdb.command("on")
-    async def on_kdb(self, event: AstrMessageEvent):
-        self.kdb_enabled = True
-        curr_kdb_name = self.context.provider_manager.curr_kdb_name
-        if not curr_kdb_name:
-            yield event.plain_result("未载入任何知识库")
-        else:
-            yield event.plain_result(f"知识库已打开。当前载入的知识库: {curr_kdb_name}")
-        
-    @kdb.command("off")
-    async def off_kdb(self, event: AstrMessageEvent):
-        self.kdb_enabled = False
-        yield event.plain_result("知识库已关闭")
-        
+            if need_active:
+                '''主动回复'''
+                provider = self.context.get_using_provider()
+                if not provider:
+                    logger.error("未找到任何 LLM 提供商。请先配置。无法主动回复")
+                    return
+                try:
+                    session_provider_context = provider.session_memory.get(event.session_id)
+                    
+                    prompt = self.ltm.ar_prompt
+                    if not prompt:
+                        prompt = event.message_str
+                    
+                    yield event.request_llm(
+                        prompt=prompt,
+                        func_tool_manager=self.context.get_llm_tool_manager(),
+                        session_id=event.session_id,
+                        contexts=session_provider_context if session_provider_context else []
+                    )
+                except BaseException as e:
+                    logger.error(f"主动回复失败: {e}")
+    
+    
     @filter.on_llm_request()
-    async def on_llm_response(self, event: AstrMessageEvent, req: ProviderRequest):
-        curr_kdb_name = self.context.provider_manager.curr_kdb_name
-        if self.kdb_enabled and curr_kdb_name:
-            mgr = self.context.knowledge_db_manager
-            results = await mgr.retrive_records(curr_kdb_name, req.prompt)
-            if results:
-                req.system_prompt += "\nHere are documents that related to user's query: \n"
-                for result in results:
-                    req.system_prompt += f"- {result}\n"
+    async def decorate_llm_req(self, event: AstrMessageEvent, req: ProviderRequest):
+        '''在请求 LLM 前注入人格信息、Identifier、时间等 System Prompt'''
+        provider = self.context.get_using_provider()
+        if self.prompt_prefix:
+            req.prompt = self.prompt_prefix + req.prompt
+            
+        if self.identifier:
+            user_id = event.message_obj.sender.user_id
+            user_nickname = event.message_obj.sender.nickname
+            user_info = f"\n[User ID: {user_id}, Nickname: {user_nickname}]\n"
+            req.prompt = user_info + req.prompt
+            
+        if self.enable_datetime:
+            req.system_prompt += f"\nCurrent datetime: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M')}\n"
+        
+        if persona := provider.curr_personality:
+            if prompt := persona['prompt']:
+                req.system_prompt += prompt
+            if mood_dialogs := persona['_mood_imitation_dialogs_processed']:
+                req.system_prompt += "\nHere are few shots of dialogs, you need to imitate the tone of 'B' in the following dialogs to respond:\n"
+                req.system_prompt += mood_dialogs
+            if begin_dialogs := persona["_begin_dialogs_processed"]:
+                req.contexts[:0] = begin_dialogs
+                
+        if self.ltm:
+            try:
+                await self.ltm.on_req_llm(event, req)
+            except BaseException as e:
+                logger.error(f"ltm: {e}")
+
+    
+    @filter.after_message_sent()
+    async def after_llm_req(self, event: AstrMessageEvent):
+        '''在 LLM 请求后记录对话'''
+        if self.ltm:
+            try:
+                await self.ltm.after_req_llm(event)
+            except BaseException as e:
+                logger.error(f"ltm: {e}")
+                
+    @filter.permission_type(filter.PermissionType.ADMIN)
+    @filter.command("alter_cmd")
+    async def alter_cmd(self, event: AstrMessageEvent):
+        # token = event.message_str.split(" ")
+        token = self.parse_commands(event.message_str)
+        if token.len < 2:
+            yield event.plain_result("可设置所有其他指令是否需要管理员权限。\n格式: /alter_cmd <cmd_name> <admin/member>\n 例如: /alter_cmd provider admin 将 provider 设置为管理员指令")
+            return
+        
+        cmd_name = token.get(1)
+        cmd_type = token.get(2)
+        
+        if cmd_type not in ["admin", "member"]:
+            yield event.plain_result("指令类型错误，可选类型有 admin, member")
+            return
+        
+        # 查找指令
+        found_command = None
+        for handler in star_handlers_registry:
+            assert isinstance(handler, StarHandlerMetadata)
+            for filter_ in handler.event_filters:
+                if isinstance(filter_, CommandFilter):
+                    if filter_.command_name == cmd_name:
+                        found_command = handler
+                        break
+                elif isinstance(filter_, CommandGroupFilter):
+                    if cmd_name == filter_.group_name:
+                        found_command = handler
+                        break
+        
+        if not found_command:
+            yield event.plain_result("未找到该指令")
+            return
+        
+        found_plugin = star_map[found_command.handler_module_path]
+        
+        alter_cmd_cfg = sp.get("alter_cmd", {})
+        plugin_ = alter_cmd_cfg.get(found_plugin.name, {})
+        cfg = plugin_.get(found_command.handler_name, {})
+        cfg["permission"] = cmd_type
+        plugin_[found_command.handler_name] = cfg
+        alter_cmd_cfg[found_plugin.name] = plugin_
+        
+        sp.put("alter_cmd", alter_cmd_cfg)
+        
+        # 注入权限过滤器
+        found_permission_filter = False
+        for filter_ in found_command.event_filters:
+            if isinstance(filter_, PermissionTypeFilter):
+                if cmd_type == "admin":
+                    filter_.permission_type = filter.PermissionType.ADMIN
+                else:
+                    filter_.permission_type = filter.PermissionType.MEMBER
+                found_permission_filter = True
+                break
+        if not found_permission_filter:
+            found_command.event_filters.insert(0, PermissionTypeFilter(filter.PermissionType.ADMIN if cmd_type == "admin" else filter.PermissionType.MEMBER))
+
+        yield event.plain_result(f"已将 {cmd_name} 设置为 {cmd_type} 指令")
+
+    # @filter.command_group("kdb")
+    # def kdb(self):
+    #     pass
+        
+    # @kdb.command("on")
+    # async def on_kdb(self, event: AstrMessageEvent):
+    #     self.kdb_enabled = True
+    #     curr_kdb_name = self.context.provider_manager.curr_kdb_name
+    #     if not curr_kdb_name:
+    #         yield event.plain_result("未载入任何知识库")
+    #     else:
+    #         yield event.plain_result(f"知识库已打开。当前载入的知识库: {curr_kdb_name}")
+        
+    # @kdb.command("off")
+    # async def off_kdb(self, event: AstrMessageEvent):
+    #     self.kdb_enabled = False
+    #     yield event.plain_result("知识库已关闭")
+        
+    # @filter.on_llm_request()
+    # async def on_llm_response(self, event: AstrMessageEvent, req: ProviderRequest):
+    #     curr_kdb_name = self.context.provider_manager.curr_kdb_name
+    #     if self.kdb_enabled and curr_kdb_name:
+    #         mgr = self.context.knowledge_db_manager
+    #         results = await mgr.retrive_records(curr_kdb_name, req.prompt)
+    #         if results:
+    #             req.system_prompt += "\nHere are documents that related to user's query: \n"
+    #             for result in results:
+    #                 req.system_prompt += f"- {result}\n"

packages/python_interpreter/main.py

@@ -127,7 +127,7 @@ class Main(star.Star):
         
         s3_file_url = f"{S3_URL}/{uuid.uuid4().hex}{ext}"
 
-        async with aiohttp.ClientSession(headers = {"Accept": "application/json"}) as session:
+        async with aiohttp.ClientSession(headers = {"Accept": "application/json"}, trust_env=True) as session:
             async with session.put(s3_file_url, data=file) as resp:
                 if resp.status != 200:
                     raise Exception(f"Failed to upload image: {resp.status}")
@@ -140,7 +140,7 @@ class Main(star.Star):
             docker = aiodocker.Docker()
             await docker.version()
             return True
-        except aiodocker.exceptions.DockerError as e:
+        except BaseException as e:
             logger.info(f"检查 Docker 可用性: {e}")
             return False
         
@@ -159,7 +159,7 @@ class Main(star.Star):
     
     async def download_image(self, image_url: str, workplace_path: str, filename: str) -> str:
         '''Download image from url to workplace_path'''
-        async with aiohttp.ClientSession() as session:
+        async with aiohttp.ClientSession(trust_env=True) as session:
             async with session.get(image_url) as resp:
                 if resp.status != 200:
                     return ""

packages/reminder/main.py

@@ -78,6 +78,10 @@ class Main(star.Star):
             cron_expression(string): Required when user's reminder is a repeated reminder. The cron expression of the reminder.
             human_readable_cron(string): Optional. The human readable cron expression of the reminder.
         '''
+        if event.get_platform_name() == 'qq_official':
+            yield event.plain_result("reminder 暂不支持 QQ 官方机器人。")
+            return
+        
         if event.unified_msg_origin not in self.reminder_data:
             self.reminder_data[event.unified_msg_origin] = []
         

packages/web_searcher/engines/google.py

@@ -8,7 +8,8 @@ from typing import List
 class Google(SearchEngine):
     def __init__(self) -> None:
         super().__init__()
-        self.proxy = os.environ.get("HTTPS_PROXY")
+        self.proxy = os.environ.get("https_proxy")
+        print(f"Google Search using proxy: {self.proxy}")
     
     async def search(self, query: str, num_results: int) -> List[SearchResult]:
         results = []

packages/web_searcher/main.py

@@ -22,6 +22,8 @@ class Main(star.Star):
         self.sogo_search = Sogo()
         self.google = Google()
         
+        self.websearch_link = self.context.get_config()['provider_settings'].get('web_search_link', False)
+        
     async def initialize(self):
         websearch = self.context.get_config()['provider_settings']['web_search']
         if websearch:
@@ -39,7 +41,7 @@ class Main(star.Star):
         '''获取网页内容'''
         header = HEADERS
         header.update({'User-Agent': random.choice(USER_AGENTS)})
-        async with aiohttp.ClientSession() as session:
+        async with aiohttp.ClientSession(trust_env=True) as session:
             async with session.get(url, headers=header, timeout=6) as response:
                 html = await response.text(encoding="utf-8")
                 doc = Document(html)
@@ -109,8 +111,17 @@ class Main(star.Star):
             except BaseException:
                 site_result = ""
             site_result = site_result[:700] + "..." if len(site_result) > 700 else site_result
-            ret += f"{idx}. {i.title} \n{i.snippet}\n{site_result}\n\n"
+            
+            header = f"{idx}. {i.title} "
+            
+            if self.websearch_link and i.url:
+                header += i.url
+            
+            ret += f"{header}\n{i.snippet}\n{site_result}\n\n"
             idx += 1
+            
+        if self.websearch_link:
+            ret += "针对问题，请根据上面的结果分点总结，并且在结尾处附上对应内容的参考链接（如有）。"
         
         return ret
 

requirements.txt

@@ -1,5 +1,4 @@
 pydantic~=2.10.3
-vchat
 aiohttp
 openai
 qq-botpy