chore: release v2.6.8

Feat: 支持 Google Gemini Pro 模型

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -45,7 +45,7 @@ body:
       required: true
   - type: textarea
     attributes:
-      label: 报错信息
-      description: 请提供完整的**控制台**报错信息（若有）
+      label: 日志信息
+      description: 请提供完整的 **登录框架 和 QChatGPT控制台**的相关日志信息（若有），不提供日志信息**无法**为您排查问题
     validations:
       required: false

.gitignore

@@ -1,4 +1,4 @@
-config.py
+/config.py
 .idea/
 __pycache__/
 database.db

README.md

@@ -7,9 +7,6 @@
 
 # QChatGPT
 
-<!-- 高稳定性/持续迭代/架构清晰/支持插件/高可自定义的 ChatGPT QQ机器人框架 -->
-<!-- “当然！下面是一个使用Java编写的快速排序算法的示例代码” -->
-
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT)](https://github.com/RockChinQ/QChatGPT/releases/latest)
 <a href="https://hub.docker.com/repository/docker/rockchin/qchatgpt">
     <img src="https://img.shields.io/docker/pulls/rockchin/qchatgpt?color=blue" alt="docker pull">
@@ -35,18 +32,16 @@
 <img alt="Static Badge" src="https://img.shields.io/badge/Linux%E9%83%A8%E7%BD%B2%E8%A7%86%E9%A2%91-208647">
 </a>
 
+<blockquote> 🥳 QChatGPT 一周年啦，感谢大家的支持！欢迎前往<a href="https://github.com/RockChinQ/QChatGPT/discussions/627">讨论</a>。</blockquote>
 
-<details>
+<!-- <details>
 <summary>回复效果演示（带有联网插件）</summary>
 <img alt="联网演示GIF" src="res/webwlkr-demo.gif" width="300px">
-</details>
-</div>
+</details> -->
 
-> **NOTE**  
-> 2023/9/13 现已支持通过[One API](https://github.com/songquanpeng/one-api)接入 Azure、Anthropic Claude、Google PaLM 2、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问以及 360 智脑等模型，欢迎测试并反馈。  
-> 2023/8/29 [逆向库插件](https://github.com/RockChinQ/revLibs)已支持 gpt4free  
-> 2023/8/14 [逆向库插件](https://github.com/RockChinQ/revLibs)已支持Claude和Bard  
-> 2023/7/29 支持使用GPT的Function Calling功能实现类似ChatGPT Plugin的效果，请见[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/6-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)  
+<img alt="回复效果（带有联网插件）" src="res/QChatGPT-1211.png" width="500px"/>
+
+</div>
 
 <details>
 <summary>
@@ -66,10 +61,11 @@
 - HuggingChat, 由[插件](https://github.com/RockChinQ/revLibs)接入, 仅支持英文
 - Claude, 由[插件](https://github.com/RockChinQ/revLibs)接入
 - Google Bard, 由[插件](https://github.com/RockChinQ/revLibs)接入
+- Google Gemini Pro、Azure、Anthropic Claude、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑等官方接口, 通过[One API](https://github.com/songquanpeng/one-api)接入
 
 ### 模型聚合平台
 
-- [One API](https://github.com/songquanpeng/one-api), Azure、Anthropic Claude、Google PaLM 2、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问以及 360 智脑等模型的官方接口转换成 OpenAI API 接入，QChatGPT 原生支持，您需要先配置 One API，之后在`config.py`中设置反向代理和`One API`的密钥后使用。
+- [One API](https://github.com/songquanpeng/one-api), Azure、Anthropic Claude、Google Gemini Pro、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问以及 360 智脑等模型的官方接口转换成 OpenAI API 接入，QChatGPT 原生支持，您需要先配置 One API，之后在`config.py`中设置反向代理和`One API`的密钥后使用。
 - [gpt4free](https://github.com/xtekky/gpt4free), 破解以免费使用多个平台的各种文字模型, 由[插件](https://github.com/RockChinQ/revLibs)接入, 无需鉴权, 稳定性较差。
 - [Poe](https://poe.com), 破解免费使用Poe上多个平台的模型, 由[oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot)接入（由于 Poe 上可用的大部分模型现已通过[revLibs插件](https://github.com/RockChinQ/revLubs)或其他方式接入，此插件现已停止维护）。
 
@@ -197,7 +193,7 @@
 
 </summary>
 
-> **NOTE**  
+> **NOTE**
 > - 部署过程中遇到任何问题，请先在[QChatGPT](https://github.com/RockChinQ/QChatGPT/issues)或[qcg-installer](https://github.com/RockChinQ/qcg-installer/issues)的issue里进行搜索  
 > - QChatGPT需要Python版本>=3.9  
 > - 官方群和社区群群号请见文档顶部
@@ -346,6 +342,9 @@ python3 main.py
 - [oliverkirk-sudo/QChatWeather](https://github.com/oliverkirk-sudo/QChatWeather) - 生成好看的天气图片，基于和风天气
 - [oliverkirk-sudo/QChatMarkdown](https://github.com/oliverkirk-sudo/QChatMarkdown) - 将机器人输出的markdown转换为图片，基于[playwright](https://playwright.dev/python/docs/intro)
 - [ruuuux/WikipediaSearch](https://github.com/ruuuux/WikipediaSearch) - Wikipedia 搜索插件
+- [zuo-shi-yun/discountAssistant](https://github.com/zuo-shi-yun/discountAssistant) - 自动筛选并发送羊毛群内的优惠券
+- [zuo-shi-yun/Gatekeeper ](https://github.com/zuo-shi-yun/Gatekeeper) - QChatGPT的看门狗，包含黑白名单、临时用户机制
+- [zuo-shi-yun/AutoSwitchProxy](https://github.com/zuo-shi-yun/AutoSwitchProxy)  - 自动切换Clash代理模式以节省流量
 
 </details>
 

README_en.md

@@ -49,7 +49,7 @@ English | [简体中文](README.md)
 
 Install this [plugin](https://github.com/RockChinQ/Switcher) to switch between different models.
 
-## ✅Function Points
+## ✅Features
 
 <details>
 <summary>Details</summary>

config-template.py

@@ -254,15 +254,20 @@ auto_reset = True
 # "qwen-plus-v1",
 # "ERNIE-Bot",
 # "ERNIE-Bot-turbo",
+# "gemini-pro",
 completion_api_params = {
     "model": "gpt-3.5-turbo",
     "temperature": 0.9,  # 数值越低得到的回答越理性，取值范围[0, 1]
 }
 
 # OpenAI的Image API的参数
-# 具体请查看OpenAI的文档: https://beta.openai.com/docs/api-reference/images/create
+# 具体请查看OpenAI的文档: https://platform.openai.com/docs/api-reference/images/create
 image_api_params = {
-    "size": "256x256",  # 图片尺寸，支持256x256, 512x512, 1024x1024
+    "model": "dall-e-2", # 默认使用 dall-e-2 模型，也可以改为 dall-e-3
+    # 图片尺寸
+    # dall-e-2 模型支持 256x256, 512x512, 1024x1024
+    # dall-e-3 模型支持 1024x1024, 1792x1024, 1024x1792
+    "size": "256x256",
 }
 
 # 跟踪函数调用
@@ -322,19 +327,6 @@ retry_times = 3
 # 设置为False时，向用户及管理员发送错误详细信息
 hide_exce_info_to_user = False
 
-# 线程池相关配置
-# 该参数决定机器人可以同时处理几个人的消息，超出线程池数量的请求会被阻塞，不会被丢弃
-# 如果你不清楚该参数的意义，请不要更改
-# 程序运行本身线程池，无代码层面修改请勿更改
-sys_pool_num = 8
-
-# 执行管理员请求和指令的线程池并行线程数量，一般和管理员数量相等
-admin_pool_num = 4
-
-# 执行用户请求和指令的线程池并行线程数量
-# 如需要更高的并发，可以增大该值
-user_pool_num = 8
-
 # 每个会话的过期时间，单位为秒
 # 默认值20分钟
 session_expire_time = 1200

main.py

@@ -8,11 +8,10 @@ import time
 import logging
 import sys
 import traceback
+import asyncio
 
 sys.path.append(".")
 
-from pkg.utils.log import init_runtime_log_file, reset_logging
-
 
 def check_file():
     # 检查是否有banlist.py,如果没有就把banlist-template.py复制一份
@@ -55,6 +54,11 @@ def check_file():
 # 初始化相关文件
 check_file()
 
+from pkg.utils.log import init_runtime_log_file, reset_logging
+from pkg.config import manager as config_mgr
+from pkg.config.impls import pymodule as pymodule_cfg
+
+
 try:
     import colorlog
 except ImportError:
@@ -96,15 +100,15 @@ def ensure_dependencies():
 known_exception_caught = False
 
 
-def override_config():
-    import config
-    # 检查override.json覆盖
+def override_config_manager():
+    config = pkg.utils.context.get_config_manager().data
+
     if os.path.exists("override.json") and use_override:
         override_json = json.load(open("override.json", "r", encoding="utf-8"))
         overrided = []
         for key in override_json:
-            if hasattr(config, key):
-                setattr(config, key, override_json[key])
+            if key in config:
+                config[key] = override_json[key]
                 # logging.info("覆写配置[{}]为[{}]".format(key, override_json[key]))
                 overrided.append(key)
             else:
@@ -113,36 +117,6 @@ def override_config():
             logging.info("已根据override.json覆写配置项: {}".format(", ".join(overrided)))
 
 
-# 临时函数，用于加载config和上下文，未来统一放在config类
-def load_config():
-    logging.info("检查config模块完整性.")
-    # 完整性校验
-    non_exist_keys = []
-
-    is_integrity = True
-    config_template = importlib.import_module('config-template')
-    config = importlib.import_module('config')
-    for key in dir(config_template):
-        if not key.startswith("__") and not hasattr(config, key):
-            setattr(config, key, getattr(config_template, key))
-            # logging.warning("[{}]不存在".format(key))
-            non_exist_keys.append(key)
-            is_integrity = False
-    
-    if not is_integrity:
-        logging.warning("以下配置字段不存在: {}".format(", ".join(non_exist_keys)))
-
-    # 检查override.json覆盖
-    override_config()
-
-    if not is_integrity:
-        logging.warning("以上不存在的配置已被设为默认值，您可以依据config-template.py检查config.py，将在3秒后继续启动... ")
-        time.sleep(3)
-
-    # 存进上下文
-    pkg.utils.context.set_config(config)
-
-
 def complete_tips():
     """根据tips-custom-template模块补全tips模块的属性"""
     non_exist_keys = []
@@ -165,17 +139,29 @@ def complete_tips():
         time.sleep(3)
 
 
-def start(first_time_init=False):
+async def start_process(first_time_init=False):
     """启动流程，reload之后会被执行"""
 
     global known_exception_caught
     import pkg.utils.context
 
-    config = pkg.utils.context.get_config()
+    # 加载配置
+    cfg_inst: pymodule_cfg.PythonModuleConfigFile = pymodule_cfg.PythonModuleConfigFile(
+        'config.py',
+        'config-template.py'
+    )
+    await config_mgr.ConfigManager(cfg_inst).load_config()
+
+    override_config_manager()
+
+    # 检查tips模块
+    complete_tips()
+
+    cfg = pkg.utils.context.get_config_manager().data
     # 更新openai库到最新版本
-    if not hasattr(config, 'upgrade_dependencies') or config.upgrade_dependencies:
+    if 'upgrade_dependencies' not in cfg or cfg['upgrade_dependencies']:
         print("正在更新依赖库，请等待...")
-        if not hasattr(config, 'upgrade_dependencies'):
+        if 'upgrade_dependencies' not in cfg:
             print("这个操作不是必须的,如果不想更新,请在config.py中添加upgrade_dependencies=False")
         else:
             print("这个操作不是必须的,如果不想更新,请在config.py中将upgrade_dependencies设置为False")
@@ -184,6 +170,10 @@ def start(first_time_init=False):
         except Exception as e:
             print("更新openai库失败:{}, 请忽略或自行更新".format(e))
 
+    # 初始化文字转图片
+    from pkg.utils import text2img
+    text2img.initialize()
+
     known_exception_caught = False
     try:
         try:
@@ -192,11 +182,11 @@ def start(first_time_init=False):
             pkg.utils.context.context['logger_handler'] = sh
 
             # 检查是否设置了管理员
-            if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
+            if cfg['admin_qq'] == 0:
                 # logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
                 while True:
                     try:
-                        config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
+                        cfg['admin_qq'] = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
                         # 写入到文件
 
                         # 读取文件
@@ -204,7 +194,7 @@ def start(first_time_init=False):
                         with open("config.py", "r", encoding="utf-8") as f:
                             config_file_str = f.read()
                         # 替换
-                        config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
+                        config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(cfg['admin_qq']))
                         # 写入
                         with open("config.py", "w", encoding="utf-8") as f:
                             f.write(config_file_str)
@@ -233,23 +223,23 @@ def start(first_time_init=False):
             # 配置OpenAI proxy
             import openai
             openai.proxies = None  # 先重置，因为重载后可能需要清除proxy
-            if "http_proxy" in config.openai_config and config.openai_config["http_proxy"] is not None:
+            if "http_proxy" in cfg['openai_config'] and cfg['openai_config']["http_proxy"] is not None:
                 openai.proxies = {
-                    "http": config.openai_config["http_proxy"],
-                    "https": config.openai_config["http_proxy"]
+                    "http": cfg['openai_config']["http_proxy"],
+                    "https": cfg['openai_config']["http_proxy"]
                 }
 
             # 配置openai api_base
-            if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
-                logging.debug("设置反向代理: "+config.openai_config['reverse_proxy'])
-                openai.base_url = config.openai_config["reverse_proxy"]
+            if "reverse_proxy" in cfg['openai_config'] and cfg['openai_config']["reverse_proxy"] is not None:
+                logging.debug("设置反向代理: "+cfg['openai_config']['reverse_proxy'])
+                openai.base_url = cfg['openai_config']["reverse_proxy"]
 
             # 主启动流程
             database = pkg.database.manager.DatabaseManager()
 
             database.initialize_database()
 
-            openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
+            openai_interact = pkg.openai.manager.OpenAIInteract(cfg['openai_config']['api_key'])
 
             # 加载所有未超时的session
             pkg.openai.session.load_sessions()
@@ -338,13 +328,12 @@ def start(first_time_init=False):
         
         if first_time_init:
             if not known_exception_caught:
-                import config
-                if config.msg_source_adapter == "yirimirai":
-                    logging.info("QQ: {}, MAH: {}".format(config.mirai_http_api_config['qq'], config.mirai_http_api_config['host']+":"+str(config.mirai_http_api_config['port'])))
+                if cfg['msg_source_adapter'] == "yirimirai":
+                    logging.info("QQ: {}, MAH: {}".format(cfg['mirai_http_api_config']['qq'], cfg['mirai_http_api_config']['host']+":"+str(cfg['mirai_http_api_config']['port'])))
                     logging.critical('程序启动完成,如长时间未显示 "成功登录到账号xxxxx" ,并且不回复消息,解决办法(请勿到群里问): '
                                 'https://github.com/RockChinQ/QChatGPT/issues/37')
-                elif config.msg_source_adapter == 'nakuru':
-                    logging.info("host: {}, port: {}, http_port: {}".format(config.nakuru_config['host'], config.nakuru_config['port'], config.nakuru_config['http_port']))
+                elif cfg['msg_source_adapter'] == 'nakuru':
+                    logging.info("host: {}, port: {}, http_port: {}".format(cfg['nakuru_config']['host'], cfg['nakuru_config']['port'], cfg['nakuru_config']['http_port']))
                     logging.critical('程序启动完成,如长时间未显示 "Protocol: connected" ,并且不回复消息,请检查config.py中的nakuru_config是否正确')
             else:
                 sys.exit(1)
@@ -352,7 +341,7 @@ def start(first_time_init=False):
             logging.info('热重载完成')
 
     # 发送赞赏码
-    if config.encourage_sponsor_at_start \
+    if cfg['encourage_sponsor_at_start'] \
         and pkg.utils.context.get_openai_manager().audit_mgr.get_total_text_length() >= 2048:
 
         logging.info("发送赞赏码")
@@ -420,19 +409,12 @@ def main():
     init_runtime_log_file()
     pkg.utils.context.context['logger_handler'] = reset_logging()
 
-    # 加载配置
-    load_config()
-    config = pkg.utils.context.get_config()
-
-    # 检查tips模块
-    complete_tips()
-
     # 配置线程池
     from pkg.utils import ThreadCtl
     thread_ctl = ThreadCtl(
-        sys_pool_num=config.sys_pool_num,
-        admin_pool_num=config.admin_pool_num,
-        user_pool_num=config.user_pool_num
+        sys_pool_num=8,
+        admin_pool_num=4,
+        user_pool_num=8
     )
     # 存进上下文
     pkg.utils.context.set_thread_ctl(thread_ctl)
@@ -451,9 +433,11 @@ def main():
     # 关闭urllib的http警告
     requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
 
+    def run_wrapper():
+        asyncio.run(start_process(True))
+
     pkg.utils.context.get_thread_ctl().submit_sys_task(
-        start,
-        True
+        run_wrapper
     )
 
     # 主线程循环
@@ -463,12 +447,19 @@ def main():
         except:
             stop()
             pkg.utils.context.get_thread_ctl().shutdown()
-            import platform
-            if platform.system() == 'Windows':
-                cmd = "taskkill /F /PID {}".format(os.getpid())
-            elif platform.system() in ['Linux', 'Darwin']:
-                cmd = "kill -9 {}".format(os.getpid())
-            os.system(cmd)
+
+            launch_args = sys.argv.copy()
+
+            if "--cov-report" not in launch_args:
+                import platform
+                if platform.system() == 'Windows':
+                    cmd = "taskkill /F /PID {}".format(os.getpid())
+                elif platform.system() in ['Linux', 'Darwin']:
+                    cmd = "kill -9 {}".format(os.getpid())
+                os.system(cmd)
+            else:
+                print("正常退出以生成覆盖率报告")
+                sys.exit(0)
 
 
 if __name__ == '__main__':

override-all.json

@@ -60,6 +60,7 @@
         "temperature": 0.9
     },
     "image_api_params": {
+        "model": "dall-e-2",
         "size": "256x256"
     },
     "trace_function_calls": false,
@@ -78,9 +79,6 @@
     "font_path": "",
     "retry_times": 3,
     "hide_exce_info_to_user": false,
-    "sys_pool_num": 8,
-    "admin_pool_num": 4,
-    "user_pool_num": 8,
     "session_expire_time": 1200,
     "rate_limitation": {
         "default": 60

pkg/audit/gatherer.py

@@ -47,10 +47,10 @@ class DataGatherer:
         def thread_func():
         
             try:
-                config = context.get_config()
-                if not config.report_usage:
+                config = context.get_config_manager().data
+                if not config['report_usage']:
                     return
-                res = requests.get("http://reports.rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}&msg_source={}".format(subservice_name, self.version_str, count, config.msg_source_adapter))
+                res = requests.get("http://reports.rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}&msg_source={}".format(subservice_name, self.version_str, count, config['msg_source_adapter']))
                 if res.status_code != 200 or res.text != "ok":
                     logging.warning("report to server failed, status_code: {}, text: {}".format(res.status_code, res.text))
             except:

pkg/config/impls/pymodule.py

@@ -0,0 +1,62 @@
+import os
+import shutil
+import importlib
+import logging
+
+from .. import model as file_model
+
+
+class PythonModuleConfigFile(file_model.ConfigFile):
+    """Python模块配置文件"""
+
+    config_file_name: str = None
+    """配置文件名"""
+
+    template_file_name: str = None
+    """模板文件名"""
+
+    def __init__(self, config_file_name: str, template_file_name: str) -> None:
+        self.config_file_name = config_file_name
+        self.template_file_name = template_file_name
+
+    def exists(self) -> bool:
+        return os.path.exists(self.config_file_name)
+
+    async def create(self):
+        shutil.copyfile(self.template_file_name, self.config_file_name)
+
+    async def load(self) -> dict:
+        module_name = os.path.splitext(os.path.basename(self.config_file_name))[0]
+        module = importlib.import_module(module_name)
+        
+        cfg = {}
+
+        allowed_types = (int, float, str, bool, list, dict)
+
+        for key in dir(module):
+            if key.startswith('__'):
+                continue
+
+            if not isinstance(getattr(module, key), allowed_types):
+                continue
+
+            cfg[key] = getattr(module, key)
+
+        # 从模板模块文件中进行补全
+        module_name = os.path.splitext(os.path.basename(self.template_file_name))[0]
+        module = importlib.import_module(module_name)
+
+        for key in dir(module):
+            if key.startswith('__'):
+                continue
+
+            if not isinstance(getattr(module, key), allowed_types):
+                continue
+
+            if key not in cfg:
+                cfg[key] = getattr(module, key)
+
+        return cfg
+
+    async def save(self, data: dict):
+        logging.warning('Python模块配置文件不支持保存')

pkg/config/manager.py

@@ -0,0 +1,23 @@
+from . import model as file_model
+from ..utils import context
+
+
+class ConfigManager:
+    """配置文件管理器"""
+
+    file: file_model.ConfigFile = None
+    """配置文件实例"""
+
+    data: dict = None
+    """配置数据"""
+
+    def __init__(self, cfg_file: file_model.ConfigFile) -> None:
+        self.file = cfg_file
+        self.data = {}
+        context.set_config_manager(self)
+
+    async def load_config(self):
+        self.data = await self.file.load()
+
+    async def dump_config(self):
+        await self.file.save(self.data)

pkg/config/model.py

@@ -0,0 +1,27 @@
+import abc
+
+
+class ConfigFile(metaclass=abc.ABCMeta):
+    """配置文件抽象类"""
+
+    config_file_name: str = None
+    """配置文件名"""
+
+    template_file_name: str = None
+    """模板文件名"""
+
+    @abc.abstractmethod
+    def exists(self) -> bool:
+        pass
+
+    @abc.abstractmethod
+    async def create(self):
+        pass
+
+    @abc.abstractmethod
+    async def load(self) -> dict:
+        pass
+
+    @abc.abstractmethod
+    async def save(self, data: dict):
+        pass

pkg/database/manager.py

@@ -144,11 +144,11 @@ class DatabaseManager:
     # 从数据库加载还没过期的session数据
     def load_valid_sessions(self) -> dict:
         # 从数据库中加载所有还没过期的session
-        config = context.get_config()
+        config = context.get_config_manager().data
         self.__execute__("""
         select `name`, `type`, `number`, `create_timestamp`, `last_interact_timestamp`, `prompt`, `status`, `default_prompt`, `token_counts`
         from `sessions` where `last_interact_timestamp` > {}
-        """.format(int(time.time()) - config.session_expire_time))
+        """.format(int(time.time()) - config['session_expire_time']))
         results = self.cursor.fetchall()
         sessions = {}
         for result in results:

pkg/openai/api/model.py

@@ -3,6 +3,8 @@ import logging
 
 import openai
 
+from ...utils import context
+
 
 class RequestBase:
 
@@ -14,7 +16,6 @@ class RequestBase:
         raise NotImplementedError
 
     def _next_key(self):
-        import pkg.utils.context as context
         switched, name = context.get_openai_manager().key_mgr.auto_switch()
         logging.debug("切换api-key: switched={}, name={}".format(switched, name))
         self.client.api_key = context.get_openai_manager().key_mgr.get_using_key()
@@ -22,12 +23,12 @@ class RequestBase:
     def _req(self, **kwargs):
         """处理代理问题"""
         logging.debug("请求接口参数: %s", str(kwargs))
-        import config
+        config = context.get_config_manager().data
 
         ret = self.req_func(**kwargs)
         logging.debug("接口请求返回：%s", str(ret))
 
-        if config.switch_strategy == 'active':
+        if config['switch_strategy'] == 'active':
             self._next_key()
 
         return ret

pkg/openai/dprompt.py

@@ -1,9 +1,10 @@
 # 多情景预设值管理
 import json
 import logging
-import config
 import os
 
+from ..utils import context
+
 # __current__ = "default"
 # """当前默认使用的情景预设的名称
 
@@ -62,22 +63,24 @@ class NormalScenarioMode(ScenarioMode):
     """普通情景预设模式"""
 
     def __init__(self):
+        config = context.get_config_manager().data
+
         # 加载config中的default_prompt值
-        if type(config.default_prompt) == str:
+        if type(config['default_prompt']) == str:
             self.using_prompt_name = "default"
             self.prompts = {"default": [
                 {
                     "role": "system",
-                    "content": config.default_prompt
+                    "content": config['default_prompt']
                 }
             ]}
         
-        elif type(config.default_prompt) == dict:
-            for key in config.default_prompt:
+        elif type(config['default_prompt']) == dict:
+            for key in config['default_prompt']:
                 self.prompts[key] = [
                     {
                         "role": "system",
-                        "content": config.default_prompt[key]
+                        "content": config['default_prompt'][key]
                     }
                 ]
 
@@ -123,9 +126,9 @@ def register_all():
 
 def mode_inst() -> ScenarioMode:
     """获取指定名称的情景预设模式对象"""
-    import config
+    config = context.get_config_manager().data
 
-    if config.preset_mode == "default":
-        config.preset_mode = "normal"
+    if config['preset_mode'] == "default":
+        config['preset_mode'] = "normal"
 
-    return scenario_mode_mapping[config.preset_mode]
+    return scenario_mode_mapping[config['preset_mode']]

pkg/openai/manager.py

@@ -1,6 +1,7 @@
 import logging
 
 import openai
+from openai.types import images_response
 
 from ..openai import keymgr
 from ..utils import context
@@ -43,13 +44,13 @@ class OpenAIInteract:
         """请求补全接口回复=
         """
         # 选择接口请求类
-        config = context.get_config()
+        config = context.get_config_manager().data
 
         request: api_model.RequestBase
 
-        model: str = config.completion_api_params['model']
+        model: str = config['completion_api_params']['model']
 
-        cp_parmas = config.completion_api_params.copy()
+        cp_parmas = config['completion_api_params'].copy()
         del cp_parmas['model']
 
         request = modelmgr.select_request_cls(self.client, model, messages, cp_parmas)
@@ -65,7 +66,7 @@ class OpenAIInteract:
 
             yield resp
 
-    def request_image(self, prompt) -> dict:
+    def request_image(self, prompt) -> images_response.ImagesResponse:
         """请求图片接口回复
 
         Parameters:
@@ -74,10 +75,10 @@ class OpenAIInteract:
         Returns:
             dict: 响应
         """
-        config = context.get_config()
-        params = config.image_api_params
+        config = context.get_config_manager().data
+        params = config['image_api_params']
 
-        response = openai.Image.create(
+        response = self.client.images.generate(
             prompt=prompt,
             n=1,
             **params

pkg/openai/modelmgr.py

@@ -49,6 +49,7 @@ CHAT_COMPLETION_MODELS = {
     "qwen-plus-v1",
     "ERNIE-Bot",
     "ERNIE-Bot-turbo",
+    "gemini-pro",
 }
 
 EDIT_MODELS = {
@@ -90,6 +91,7 @@ def count_chat_completion_tokens(messages: list, model: str) -> int:
         "qwen-plus-v1",
         "ERNIE-Bot",
         "ERNIE-Bot-turbo",
+        "gemini-pro",
         }:
         tokens_per_message = 3
         tokens_per_name = 1

pkg/openai/session.py

@@ -36,11 +36,11 @@ def reset_session_prompt(session_name, prompt):
     f.write(prompt)
     f.close()
     # 生成新数据
-    config = context.get_config()
+    config = context.get_config_manager().data
     prompt = [
         {
             'role': 'system',
-            'content': config.default_prompt['default'] if type(config.default_prompt) == dict else config.default_prompt
+            'content': config['default_prompt']['default'] if type(config['default_prompt']) == dict else config['default_prompt']
         }
     ]
     # 警告
@@ -170,15 +170,15 @@ class Session:
             if self.create_timestamp != create_timestamp or self not in sessions.values():
                 return
 
-            config = context.get_config()
-            if int(time.time()) - self.last_interact_timestamp > config.session_expire_time:
+            config = context.get_config_manager().data
+            if int(time.time()) - self.last_interact_timestamp > config['session_expire_time']:
                 logging.info('session {} 已过期'.format(self.name))
 
                 # 触发插件事件
                 args = {
                     'session_name': self.name,
                     'session': self,
-                    'session_expire_time': config.session_expire_time
+                    'session_expire_time': config['session_expire_time']
                 }
                 event = plugin_host.emit(plugin_models.SessionExpired, **args)
                 if event.is_prevented_default():
@@ -216,8 +216,8 @@ class Session:
             if event.is_prevented_default():
                 return None, None, None
 
-        config = context.get_config()
-        max_length = config.prompt_submit_length
+        config = context.get_config_manager().data
+        max_length = config['prompt_submit_length']
 
         local_default_prompt = self.default_prompt.copy()
         local_prompt = self.prompt.copy()
@@ -254,7 +254,7 @@ class Session:
 
         funcs = []
 
-        trace_func_calls = config.trace_function_calls
+        trace_func_calls = config['trace_function_calls']
         botmgr = context.get_qqbot_manager()
 
         session_name_spt: list[str] = self.name.split("_")
@@ -381,7 +381,7 @@ class Session:
         # 包装目前的对话回合内容
         changable_prompts = []
 
-        use_model = context.get_config().completion_api_params['model']
+        use_model = context.get_config_manager().data['completion_api_params']['model']
 
         ptr = len(prompt) - 1
 

pkg/qqbot/adapter.py

@@ -5,6 +5,7 @@ import mirai
 
 
 class MessageSourceAdapter:
+    bot_account_id: int
     def __init__(self, config: dict):
         pass
 

pkg/qqbot/blob.py

@@ -9,7 +9,7 @@ from mirai.models.message import ForwardMessageNode
 from mirai.models.base import MiraiBaseModel
 
 from ..utils import text2img
-import config
+from ..utils import context
 
 
 class ForwardMessageDiaplay(MiraiBaseModel):
@@ -64,13 +64,16 @@ def text_to_image(text: str) -> MessageComponent:
 
 def check_text(text: str) -> list:
     """检查文本是否为长消息，并转换成该使用的消息链组件"""
-    if len(text) > config.blob_message_threshold:
+
+    config = context.get_config_manager().data
+
+    if len(text) > config['blob_message_threshold']:
 
         # logging.info("长消息: {}".format(text))
-        if config.blob_message_strategy == 'image':
+        if config['blob_message_strategy'] == 'image':
             # 转换成图片
             return [text_to_image(text)]
-        elif config.blob_message_strategy == 'forward':
+        elif config['blob_message_strategy'] == 'forward':
 
             # 包装转发消息
             display = ForwardMessageDiaplay(
@@ -82,7 +85,7 @@ def check_text(text: str) -> list:
             )
 
             node = ForwardMessageNode(
-                sender_id=config.mirai_http_api_config['qq'],
+                sender_id=config['mirai_http_api_config']['qq'],
                 sender_name='bot',
                 message_chain=MessageChain([text])
             )

pkg/qqbot/cmds/funcs/draw.py

@@ -3,7 +3,7 @@ import logging
 import mirai
 
 from .. import aamgr
-import config
+from ....utils import context
 
 
 @aamgr.AbstractCommandNode.register(
@@ -29,9 +29,9 @@ class DrawCommand(aamgr.AbstractCommandNode):
             res = session.draw_image(" ".join(ctx.params))
 
             logging.debug("draw_image result:{}".format(res))
-            reply = [mirai.Image(url=res['data'][0]['url'])]
-            if not (hasattr(config, 'include_image_description')
-                    and not config.include_image_description):
+            reply = [mirai.Image(url=res.data[0].url)]
+            config = context.get_config_manager().data
+            if config['include_image_description']:
                 reply.append(" ".join(ctx.params))
 
         return True, reply

pkg/qqbot/cmds/session/default.py

@@ -1,4 +1,6 @@
 from .. import aamgr
+from ....utils import context
+
 
 @aamgr.AbstractCommandNode.register(
     parent=None,
@@ -15,12 +17,13 @@ class DefaultCommand(aamgr.AbstractCommandNode):
         session_name = ctx.session_name
         params = ctx.params
         reply = []
-        import config
+
+        config = context.get_config_manager().data
 
         if len(params) == 0:
             # 输出目前所有情景预设
             import pkg.openai.dprompt as dprompt
-            reply_str = "[bot]当前所有情景预设({}模式):\n\n".format(config.preset_mode)
+            reply_str = "[bot]当前所有情景预设({}模式):\n\n".format(config['preset_mode'])
 
             prompts = dprompt.mode_inst().list()
 

pkg/qqbot/command.py

@@ -4,7 +4,7 @@ import logging
 from ..qqbot.cmds import aamgr as cmdmgr
 
 
-def process_command(session_name: str, text_message: str, mgr, config,
+def process_command(session_name: str, text_message: str, mgr, config: dict,
                     launcher_type: str, launcher_id: int, sender_id: int, is_admin: bool) -> list:
     reply = []
     try:

pkg/qqbot/filter.py

@@ -4,6 +4,8 @@ import requests
 import json
 import logging
 
+from ..utils import context
+
 
 class ReplyFilter:
     sensitive_words = []
@@ -20,12 +22,13 @@ class ReplyFilter:
         self.sensitive_words = sensitive_words
         self.mask = mask
         self.mask_word = mask_word
-        import config
 
-        self.baidu_check = config.baidu_check
-        self.baidu_api_key = config.baidu_api_key
-        self.baidu_secret_key = config.baidu_secret_key
-        self.inappropriate_message_tips = config.inappropriate_message_tips
+        config = context.get_config_manager().data
+
+        self.baidu_check = config['baidu_check']
+        self.baidu_api_key = config['baidu_api_key']
+        self.baidu_secret_key = config['baidu_secret_key']
+        self.inappropriate_message_tips = config['inappropriate_message_tips']
 
     def is_illegal(self, message: str) -> bool:
         processed = self.process(message)

pkg/qqbot/ignore.py

@@ -1,16 +1,18 @@
 import re
 
+from ..utils import context
+
 
 def ignore(msg: str) -> bool:
     """检查消息是否应该被忽略"""
-    import config
+    config = context.get_config_manager().data
     
-    if 'prefix' in config.ignore_rules:
-        for rule in config.ignore_rules['prefix']:
+    if 'prefix' in config['ignore_rules']:
+        for rule in config['ignore_rules']['prefix']:
             if msg.startswith(rule):
                 return True
 
-    if 'regexp' in config.ignore_rules:
-        for rule in config.ignore_rules['regexp']:
+    if 'regexp' in config['ignore_rules']:
+        for rule in config['ignore_rules']['regexp']:
             if re.search(rule, msg):
                 return True

pkg/qqbot/manager.py

@@ -2,7 +2,7 @@ import json
 import os
 import logging
 
-from mirai import At, GroupMessage, MessageEvent, Mirai, StrangerMessage, WebSocketAdapter, HTTPAdapter, \
+from mirai import At, GroupMessage, MessageEvent, StrangerMessage, \
     FriendMessage, Image, MessageChain, Plain
 import func_timeout
 
@@ -19,16 +19,16 @@ from ..qqbot import adapter as msadapter
 
 # 检查消息是否符合泛响应匹配机制
 def check_response_rule(group_id:int, text: str):
-    config = context.get_config()
+    config = context.get_config_manager().data
 
-    rules = config.response_rules
+    rules = config['response_rules']
 
     # 检查是否有特定规则
-    if 'prefix' not in config.response_rules:
-        if str(group_id) in config.response_rules:
-            rules = config.response_rules[str(group_id)]
+    if 'prefix' not in config['response_rules']:
+        if str(group_id) in config['response_rules']:
+            rules = config['response_rules'][str(group_id)]
         else:
-            rules = config.response_rules['default']
+            rules = config['response_rules']['default']
 
     # 检查前缀匹配
     if 'prefix' in rules:
@@ -48,16 +48,16 @@ def check_response_rule(group_id:int, text: str):
 
 
 def response_at(group_id: int):
-    config = context.get_config()
+    config = context.get_config_manager().data
 
-    use_response_rule = config.response_rules
+    use_response_rule = config['response_rules']
 
     # 检查是否有特定规则
-    if 'prefix' not in config.response_rules:
-        if str(group_id) in config.response_rules:
-            use_response_rule = config.response_rules[str(group_id)]
+    if 'prefix' not in config['response_rules']:
+        if str(group_id) in config['response_rules']:
+            use_response_rule = config['response_rules'][str(group_id)]
         else:
-            use_response_rule = config.response_rules['default']
+            use_response_rule = config['response_rules']['default']
 
     if 'at' not in use_response_rule:
         return True
@@ -66,16 +66,16 @@ def response_at(group_id: int):
 
 
 def random_responding(group_id):
-    config = context.get_config()
+    config = context.get_config_manager().data
 
-    use_response_rule = config.response_rules
+    use_response_rule = config['response_rules']
 
     # 检查是否有特定规则
-    if 'prefix' not in config.response_rules:
-        if str(group_id) in config.response_rules:
-            use_response_rule = config.response_rules[str(group_id)]
+    if 'prefix' not in config['response_rules']:
+        if str(group_id) in config['response_rules']:
+            use_response_rule = config['response_rules'][str(group_id)]
         else:
-            use_response_rule = config.response_rules['default']
+            use_response_rule = config['response_rules']['default']
 
     if 'random_rate' in use_response_rule:
         import random
@@ -102,25 +102,25 @@ class QQBotManager:
     ban_group = []
 
     def __init__(self, first_time_init=True):
-        import config
+        config = context.get_config_manager().data
 
-        self.timeout = config.process_message_timeout
-        self.retry = config.retry_times
+        self.timeout = config['process_message_timeout']
+        self.retry = config['retry_times']
 
         # 由于YiriMirai的bot对象是单例的，且shutdown方法暂时无法使用
         # 故只在第一次初始化时创建bot对象，重载之后使用原bot对象
         # 因此，bot的配置不支持热重载
         if first_time_init:
-            logging.debug("Use adapter:" + config.msg_source_adapter)
-            if config.msg_source_adapter == 'yirimirai':
+            logging.debug("Use adapter:" + config['msg_source_adapter'])
+            if config['msg_source_adapter'] == 'yirimirai':
                 from pkg.qqbot.sources.yirimirai import YiriMiraiAdapter
 
-                mirai_http_api_config = config.mirai_http_api_config
-                self.bot_account_id = config.mirai_http_api_config['qq']
+                mirai_http_api_config = config['mirai_http_api_config']
+                self.bot_account_id = config['mirai_http_api_config']['qq']
                 self.adapter = YiriMiraiAdapter(mirai_http_api_config)
-            elif config.msg_source_adapter == 'nakuru':
+            elif config['msg_source_adapter'] == 'nakuru':
                 from pkg.qqbot.sources.nakuru import NakuruProjectAdapter
-                self.adapter = NakuruProjectAdapter(config.nakuru_config)
+                self.adapter = NakuruProjectAdapter(config['nakuru_config'])
                 self.bot_account_id = self.adapter.bot_account_id
         else:
             self.adapter = context.get_qqbot_manager().adapter
@@ -176,7 +176,7 @@ class QQBotManager:
                 stranger_message_handler,
             )
         # nakuru不区分好友和陌生人，故仅为yirimirai注册陌生人事件
-        if config.msg_source_adapter == 'yirimirai':
+        if config['msg_source_adapter'] == 'yirimirai':
             self.adapter.register_listener(
                 StrangerMessage,
                 on_stranger_message
@@ -213,12 +213,11 @@ class QQBotManager:
 
             用于在热重载流程中卸载所有事件处理器
             """
-            import config
             self.adapter.unregister_listener(
                 FriendMessage,
                 on_friend_message
             )
-            if config.msg_source_adapter == 'yirimirai':
+            if config['msg_source_adapter'] == 'yirimirai':
                 self.adapter.unregister_listener(
                     StrangerMessage,
                     on_stranger_message
@@ -243,10 +242,10 @@ class QQBotManager:
             if hasattr(banlist, "enable_group"):
                 self.enable_group = banlist.enable_group
 
-        config = context.get_config()
+        config = context.get_config_manager().data
         if os.path.exists("sensitive.json") \
-                and config.sensitive_word_filter is not None \
-                and config.sensitive_word_filter:
+                and config['sensitive_word_filter'] is not None \
+                and config['sensitive_word_filter']:
             with open("sensitive.json", "r", encoding="utf-8") as f:
                 sensitive_json = json.load(f)
                 self.reply_filter = qqbot_filter.ReplyFilter(
@@ -258,16 +257,16 @@ class QQBotManager:
             self.reply_filter = qqbot_filter.ReplyFilter([])
 
     def send(self, event, msg, check_quote=True, check_at_sender=True):
-        config = context.get_config()
+        config = context.get_config_manager().data
         
-        if check_at_sender and config.at_sender:
+        if check_at_sender and config['at_sender']:
             msg.insert(
                 0,
                 Plain(" \n")
             )
 
             # 当回复的正文中包含换行时，quote可能会自带at，此时就不再单独添加at，只添加换行
-            if "\n" not in str(msg[1]) or config.msg_source_adapter == 'nakuru':
+            if "\n" not in str(msg[1]) or config['msg_source_adapter'] == 'nakuru':
                 msg.insert(
                     0,
                     At(
@@ -278,14 +277,15 @@ class QQBotManager:
         self.adapter.reply_message(
             event,
             msg,
-            quote_origin=True if config.quote_origin and check_quote else False
+            quote_origin=True if config['quote_origin'] and check_quote else False
         )
 
     # 私聊消息处理
     def on_person_message(self, event: MessageEvent):
-        import config
         reply = ''
 
+        config = context.get_config_manager().data
+
         if not self.enable_private:
             logging.debug("已在banlist.py中禁用所有私聊")
         elif event.sender.id == self.bot_account_id:
@@ -299,7 +299,7 @@ class QQBotManager:
                 for i in range(self.retry):
                     try:
                         
-                        @func_timeout.func_set_timeout(config.process_message_timeout)
+                        @func_timeout.func_set_timeout(config['process_message_timeout'])
                         def time_ctrl_wrapper():
                             reply = processor.process_message('person', event.sender.id, str(event.message_chain),
                                                             event.message_chain,
@@ -326,8 +326,10 @@ class QQBotManager:
 
     # 群消息处理
     def on_group_message(self, event: GroupMessage):
-        import config
         reply = ''
+
+        config = context.get_config_manager().data
+
         def process(text=None) -> str:
             replys = ""
             if At(self.bot_account_id) in event.message_chain:
@@ -337,7 +339,7 @@ class QQBotManager:
             failed = 0
             for i in range(self.retry):
                 try:
-                    @func_timeout.func_set_timeout(config.process_message_timeout)
+                    @func_timeout.func_set_timeout(config['process_message_timeout'])
                     def time_ctrl_wrapper():
                         replys = processor.process_message('group', event.group.id,
                                                         str(event.message_chain).strip() if text is None else text,
@@ -385,17 +387,17 @@ class QQBotManager:
 
     # 通知系统管理员
     def notify_admin(self, message: str):
-        config = context.get_config()
-        if config.admin_qq != 0 and config.admin_qq != []:
+        config = context.get_config_manager().data
+        if config['admin_qq'] != 0 and config['admin_qq'] != []:
             logging.info("通知管理员:{}".format(message))
-            if type(config.admin_qq) == int:
+            if type(config['admin_qq']) == int:
                 self.adapter.send_message(
                     "person",
-                    config.admin_qq,
+                    config['admin_qq'],
                     MessageChain([Plain("[bot]{}".format(message))])
                 )
             else:
-                for adm in config.admin_qq:
+                for adm in config['admin_qq']:
                     self.adapter.send_message(
                         "person",
                         adm,
@@ -403,17 +405,17 @@ class QQBotManager:
                     )
 
     def notify_admin_message_chain(self, message):
-        config = context.get_config()
-        if config.admin_qq != 0 and config.admin_qq != []:
+        config = context.get_config_manager().data
+        if config['admin_qq'] != 0 and config['admin_qq'] != []:
             logging.info("通知管理员:{}".format(message))
-            if type(config.admin_qq) == int:
+            if type(config['admin_qq']) == int:
                 self.adapter.send_message(
                     "person",
-                    config.admin_qq,
+                    config['admin_qq'],
                     message
                 )
             else:
-                for adm in config.admin_qq:
+                for adm in config['admin_qq']:
                     self.adapter.send_message(
                         "person",
                         adm,

pkg/qqbot/message.py

@@ -13,15 +13,15 @@ import tips as tips_custom
 
 def handle_exception(notify_admin: str = "", set_reply: str = "") -> list:
     """处理异常，当notify_admin不为空时，会通知管理员，返回通知用户的消息"""
-    import config
+    config = context.get_config_manager().data
     context.get_qqbot_manager().notify_admin(notify_admin)
-    if config.hide_exce_info_to_user:
+    if config['hide_exce_info_to_user']:
         return [tips_custom.alter_tip_message] if tips_custom.alter_tip_message else []
     else:
         return [set_reply]
 
 
-def process_normal_message(text_message: str, mgr, config, launcher_type: str,
+def process_normal_message(text_message: str, mgr, config: dict, launcher_type: str,
                            launcher_id: int, sender_id: int) -> list:
     session_name = f"{launcher_type}_{launcher_id}"
     logging.info("[{}]发送消息:{}".format(session_name, text_message[:min(20, len(text_message))] + (
@@ -39,7 +39,7 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
             reply = handle_exception(notify_admin=f"{session_name}，多次尝试失败。", set_reply=f"[bot]多次尝试失败，请重试或联系管理员")
             break
         try:
-            prefix = "[GPT]" if config.show_prefix else ""
+            prefix = "[GPT]" if config['show_prefix'] else ""
 
             text, finish_reason, funcs = session.query(text_message)
 
@@ -118,7 +118,7 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
                 reply = handle_exception("{}会话调用API失败:{}".format(session_name, e),
                                          "[bot]err:RateLimitError,请重试或联系作者，或等待修复")
         except openai.BadRequestError as e:
-            if config.auto_reset and "This model's maximum context length is" in str(e):
+            if config['auto_reset'] and "This model's maximum context length is" in str(e):
                 session.reset(persist=True)
                 reply = [tips_custom.session_auto_reset_message]
             else:

pkg/qqbot/process.py

@@ -1,6 +1,7 @@
 # 此模块提供了消息处理的具体逻辑的接口
 import asyncio
 import time
+import traceback
 
 import mirai
 import logging
@@ -28,11 +29,11 @@ processing = []
 
 def is_admin(qq: int) -> bool:
     """兼容list和int类型的管理员判断"""
-    import config
-    if type(config.admin_qq) == list:
-        return qq in config.admin_qq
+    config = context.get_config_manager().data
+    if type(config['admin_qq']) == list:
+        return qq in config['admin_qq']
     else:
-        return qq == config.admin_qq
+        return qq == config['admin_qq']
 
 
 def process_message(launcher_type: str, launcher_id: int, text_message: str, message_chain: mirai.MessageChain,
@@ -53,9 +54,9 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
         logging.info("根据忽略规则忽略消息: {}".format(text_message))
         return []
 
-    import config
+    config = context.get_config_manager().data
 
-    if not config.wait_last_done and session_name in processing:
+    if not config['wait_last_done'] and session_name in processing:
         return mirai.MessageChain([mirai.Plain(tips_custom.message_drop_tip)])
 
     # 检查是否被禁言
@@ -65,8 +66,7 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
             logging.info("机器人被禁言,跳过消息处理(group_{})".format(launcher_id))
             return reply
 
-    import config
-    if config.income_msg_check:
+    if config['income_msg_check']:
         if mgr.reply_filter.is_illegal(text_message):
             return mirai.MessageChain(mirai.Plain("[bot] 消息中存在不合适的内容, 请更换措辞"))
 
@@ -81,8 +81,6 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
     # 处理消息
     try:
 
-        config = context.get_config()
-
         processing.append(session_name)
         try:
             if text_message.startswith('!') or text_message.startswith("！"):  # 指令
@@ -114,7 +112,7 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
             else:  # 消息
                 # 限速丢弃检查
                 # print(ratelimit.__crt_minute_usage__[session_name])
-                if config.rate_limit_strategy == "drop":
+                if config['rate_limit_strategy'] == "drop":
                     if ratelimit.is_reach_limit(session_name):
                         logging.info("根据限速策略丢弃[{}]消息: {}".format(session_name, text_message))
 
@@ -144,7 +142,7 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
                                                                      mgr, config, launcher_type, launcher_id, sender_id)
 
                 # 限速等待时间
-                if config.rate_limit_strategy == "wait":
+                if config['rate_limit_strategy'] == "wait":
                     time.sleep(ratelimit.get_rest_wait_time(session_name, time.time() - before))
                 
                 ratelimit.add_usage(session_name)
@@ -167,13 +165,13 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
         openai_session.get_session(session_name).release_response_lock()
 
     # 检查延迟时间
-    if config.force_delay_range[1] == 0:
+    if config['force_delay_range'][1] == 0:
         delay_time = 0
     else:
         import random
 
         # 从延迟范围中随机取一个值(浮点)
-        rdm = random.uniform(config.force_delay_range[0], config.force_delay_range[1])
+        rdm = random.uniform(config['force_delay_range'][0], config['force_delay_range'][1])
 
         spent = time.time() - start_time
 

pkg/qqbot/ratelimit.py

@@ -3,6 +3,9 @@ import time
 import logging
 import threading
 
+from ..utils import context
+
+
 __crt_minute_usage__ = {}
 """当前分钟每个会话的对话次数"""
 
@@ -12,16 +15,16 @@ __timer_thr__: threading.Thread = None
 
 def get_limitation(session_name: str) -> int:
     """获取会话的限制次数"""
-    import config
+    config = context.get_config_manager().data
 
-    if type(config.rate_limitation) == dict:
+    if type(config['rate_limitation']) == dict:
         # 如果被指定了
-        if session_name in config.rate_limitation:
-            return config.rate_limitation[session_name]
+        if session_name in config['rate_limitation']:
+            return config['rate_limitation'][session_name]
         else:
-            return config.rate_limitation["default"]
-    elif type(config.rate_limitation) == int:
-        return config.rate_limitation
+            return config['rate_limitation']["default"]
+    elif type(config['rate_limitation']) == int:
+        return config['rate_limitation']
 
 
 def add_usage(session_name: str):

pkg/qqbot/sources/nakuru.py

@@ -10,6 +10,7 @@ import nakuru.entities.components as nkc
 
 from .. import adapter as adapter_model
 from ...qqbot import blob
+from ...utils import context
 
 
 class NakuruProjectMessageConverter(adapter_model.MessageConverter):
@@ -172,12 +173,14 @@ class NakuruProjectAdapter(adapter_model.MessageSourceAdapter):
         self.listener_list = []
         # nakuru库有bug，这个接口没法带access_token，会失败
         # 所以目前自行发请求
-        import config
+
+        config = context.get_config_manager().data
+
         import requests
         resp = requests.get(
-            url="http://{}:{}/get_login_info".format(config.nakuru_config['host'], config.nakuru_config['http_port']),
+            url="http://{}:{}/get_login_info".format(config['nakuru_config']['host'], config['nakuru_config']['http_port']),
             headers={
-                'Authorization': "Bearer " + config.nakuru_config['token'] if 'token' in config.nakuru_config else ""
+                'Authorization': "Bearer " + config['nakuru_config']['token'] if 'token' in config['nakuru_config']else ""
             },
             timeout=5
         )
@@ -270,7 +273,7 @@ class NakuruProjectAdapter(adapter_model.MessageSourceAdapter):
             logging.debug("注册监听器: " + str(event_type) + " -> " + str(callback))
 
             # 包装函数
-            async def listener_wrapper(app: nakuru.CQHTTP, source: self.event_converter.yiri2target(event_type)):
+            async def listener_wrapper(app: nakuru.CQHTTP, source: NakuruProjectAdapter.event_converter.yiri2target(event_type)):
                 callback(self.event_converter.target2yiri(source))
 
             # 将包装函数和原函数的对应关系存入列表

pkg/utils/context.py

@@ -1,12 +1,21 @@
+from __future__ import annotations
+
 import threading
 from . import threadctl
 
+from ..database import manager as db_mgr
+from ..openai import manager as openai_mgr
+from ..qqbot import manager as qqbot_mgr
+from ..config import  manager as config_mgr
+from ..plugin import host as plugin_host
+
 
 context = {
     'inst': {
         'database.manager.DatabaseManager': None,
         'openai.manager.OpenAIInteract': None,
         'qqbot.manager.QQBotManager': None,
+        'config.manager.ConfigManager': None,
     },
     'pool_ctl': None,
     'logger_handler': None,
@@ -29,59 +38,72 @@ def get_config():
     return t
 
 
-def set_database_manager(inst):
+def set_database_manager(inst: db_mgr.DatabaseManager):
     context_lock.acquire()
     context['inst']['database.manager.DatabaseManager'] = inst
     context_lock.release()
 
 
-def get_database_manager():
+def get_database_manager() -> db_mgr.DatabaseManager:
     context_lock.acquire()
     t = context['inst']['database.manager.DatabaseManager']
     context_lock.release()
     return t
 
 
-def set_openai_manager(inst):
+def set_openai_manager(inst: openai_mgr.OpenAIInteract):
     context_lock.acquire()
     context['inst']['openai.manager.OpenAIInteract'] = inst
     context_lock.release()
 
 
-def get_openai_manager():
+def get_openai_manager() -> openai_mgr.OpenAIInteract:
     context_lock.acquire()
     t = context['inst']['openai.manager.OpenAIInteract']
     context_lock.release()
     return t
 
 
-def set_qqbot_manager(inst):
+def set_qqbot_manager(inst: qqbot_mgr.QQBotManager):
     context_lock.acquire()
     context['inst']['qqbot.manager.QQBotManager'] = inst
     context_lock.release()
 
 
-def get_qqbot_manager():
+def get_qqbot_manager() -> qqbot_mgr.QQBotManager:
     context_lock.acquire()
     t = context['inst']['qqbot.manager.QQBotManager']
     context_lock.release()
     return t
 
 
-def set_plugin_host(inst):
+def set_config_manager(inst: config_mgr.ConfigManager):
+    context_lock.acquire()
+    context['inst']['config.manager.ConfigManager'] = inst
+    context_lock.release()
+
+
+def get_config_manager() -> config_mgr.ConfigManager:
+    context_lock.acquire()
+    t = context['inst']['config.manager.ConfigManager']
+    context_lock.release()
+    return t
+
+
+def set_plugin_host(inst: plugin_host.PluginHost):
     context_lock.acquire()
     context['plugin_host'] = inst
     context_lock.release()
 
 
-def get_plugin_host():
+def get_plugin_host() -> plugin_host.PluginHost:
     context_lock.acquire()
     t = context['plugin_host']
     context_lock.release()
     return t
 
 
-def set_thread_ctl(inst):
+def set_thread_ctl(inst: threadctl.ThreadCtl):
     context_lock.acquire()
     context['pool_ctl'] = inst
     context_lock.release()

pkg/utils/log.py

@@ -3,6 +3,8 @@ import time
 import logging
 import shutil
 
+from . import context
+
 
 log_file_name = "qchatgpt.log"
 
@@ -36,7 +38,6 @@ def init_runtime_log_file():
 def reset_logging():
     global log_file_name
 
-    import config
     import pkg.utils.context
     import colorlog
 
@@ -46,7 +47,11 @@ def reset_logging():
     for handler in logging.getLogger().handlers:
         logging.getLogger().removeHandler(handler)
 
-    logging.basicConfig(level=config.logging_level,  # 设置日志输出格式
+    config_mgr = context.get_config_manager()
+
+    logging_level = logging.INFO if config_mgr is None else config_mgr.data['logging_level']
+
+    logging.basicConfig(level=logging_level,  # 设置日志输出格式
                         filename=log_file_name,  # log日志输出的文件位置和文件名
                         format="[%(asctime)s.%(msecs)03d] %(pathname)s (%(lineno)d) - [%(levelname)s] :\n%(message)s",
                         # 日志输出的格式
@@ -54,7 +59,7 @@ def reset_logging():
                         datefmt="%Y-%m-%d %H:%M:%S"  # 时间输出的格式
                         )
     sh = logging.StreamHandler()
-    sh.setLevel(config.logging_level)
+    sh.setLevel(logging_level)
     sh.setFormatter(colorlog.ColoredFormatter(
         fmt="%(log_color)s[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : "
             "%(message)s",

pkg/utils/network.py

@@ -1,9 +1,11 @@
+from . import context
+
 
 def wrapper_proxies() -> dict:
     """获取代理"""
-    import config
+    config = context.get_config_manager().data
 
     return {
-        "http": config.openai_config['proxy'],
-        "https": config.openai_config['proxy']
-    } if 'proxy' in config.openai_config and (config.openai_config['proxy'] is not None) else None
+        "http": config['openai_config']['proxy'],
+        "https": config['openai_config']['proxy']
+    } if 'proxy' in config['openai_config'] and (config['openai_config']['proxy'] is not None) else None

pkg/utils/reloader.py

@@ -1,6 +1,7 @@
 import logging
 import importlib
 import pkgutil
+import asyncio
 
 from . import context
 from ..plugin import host as plugin_host
@@ -52,15 +53,17 @@ def reload_all(notify=True):
 
     # 执行启动流程
     logging.info("执行程序启动流程")
-    main.load_config()
-    main.complete_tips()
+
     context.get_thread_ctl().reload(
-        admin_pool_num=context.get_config().admin_pool_num,
-        user_pool_num=context.get_config().user_pool_num
+        admin_pool_num=4,
+        user_pool_num=8
     )
+
+    def run_wrapper():
+        asyncio.run(main.start_process(False))
+
     context.get_thread_ctl().submit_sys_task(
-        main.start,
-        False
+        run_wrapper
     )
 
     logging.info('程序启动完成')

pkg/utils/text2img.py

@@ -1,37 +1,42 @@
 import logging
 import re
 import os
-import config
 import traceback
 
 from PIL import Image, ImageDraw, ImageFont
 
+from ..utils import context
+
+
 text_render_font: ImageFont = None
 
-if config.blob_message_strategy == "image":  # 仅在启用了image时才加载字体
-    use_font = config.font_path
-    try:
+def initialize():
+    config = context.get_config_manager().data
 
-        # 检查是否存在
-        if not os.path.exists(use_font):
-            # 若是windows系统，使用微软雅黑
-            if os.name == "nt":
-                use_font = "C:/Windows/Fonts/msyh.ttc"
-                if not os.path.exists(use_font):
-                    logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
-                    config.blob_message_strategy = "forward"
+    if config['blob_message_strategy'] == "image":  # 仅在启用了image时才加载字体
+        use_font = config['font_path']
+        try:
+
+            # 检查是否存在
+            if not os.path.exists(use_font):
+                # 若是windows系统，使用微软雅黑
+                if os.name == "nt":
+                    use_font = "C:/Windows/Fonts/msyh.ttc"
+                    if not os.path.exists(use_font):
+                        logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
+                        config['blob_message_strategy'] = "forward"
+                    else:
+                        logging.info("使用Windows自带字体：" + use_font)
+                        text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
                 else:
-                    logging.info("使用Windows自带字体：" + use_font)
-                    text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
+                    logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
+                    config['blob_message_strategy'] = "forward"
             else:
-                logging.warn("未找到字体文件，且无法使用Windows自带字体，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。")
-                config.blob_message_strategy = "forward"
-        else:
-            text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
-    except:
-        traceback.print_exc()
-        logging.error("加载字体文件失败({})，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。".format(use_font))
-        config.blob_message_strategy = "forward"
+                text_render_font = ImageFont.truetype(use_font, 32, encoding="utf-8")
+        except:
+            traceback.print_exc()
+            logging.error("加载字体文件失败({})，更换为转发消息组件以发送长消息，您可以在config.py中调整相关设置。".format(use_font))
+            config['blob_message_strategy'] = "forward"
 
 
 def indexNumber(path=''):

res/announcement.json

@@ -16,5 +16,11 @@
         "time": "2023-11-13 18:02:39",
         "timestamp": 1699869759,
         "content": "近期 OpenAI 接口改动频繁，正在积极适配并添加新功能，请尽快更新到最新版本，更新方式：https://github.com/RockChinQ/QChatGPT/discussions/595"
+    },
+    {
+        "id": 5,
+        "time": "2023-12-07 9:20:00",
+        "timestamp": 1701912000,
+        "content": "QChatGPT 一周年啦！感谢大家的选择和支持，RockChinQ 在此衷心感谢素未谋面但又至关重要的你们每一个人，愿 AI 与我们同在！欢迎前往：https://github.com/RockChinQ/QChatGPT/discussions/627 参与讨论。"
     }
 ]

res/docs/docker_deploy.md

@@ -1,5 +1,5 @@
 
-> **Warning**
+> [!WARNING]
 > 此文档已过时，请查看[QChatGPT 容器化部署指南](docker_deployment.md)
 
 ## 操作步骤

res/docs/docker_deployment.md

@@ -1,6 +1,6 @@
 # QChatGPT 容器化部署指南
 
-> **Warning**  
+> [!WARNING]  
 > 请您确保您**确实**需要 Docker 部署，您**必须**具有以下能力：  
 > - 了解 `Docker` 和 `Docker Compose` 的使用  
 > - 了解容器间网络通信配置方式  
@@ -15,7 +15,7 @@
 
 QChatGPT 主程序需要连接`QQ登录框架`以与QQ通信，您可以选择 [Mirai](https://github.com/mamoe/mirai)（还需要配置mirai-api-http，请查看此仓库README中手动部署部分） 或 [go-cqhttp](https://github.com/Mrs4s/go-cqhttp)，我们仅发布 QChatGPT主程序 的镜像，您需要自行配置QQ登录框架（可以参考[README.md](https://github.com/RockChinQ/QChatGPT#-%E9%85%8D%E7%BD%AEqq%E7%99%BB%E5%BD%95%E6%A1%86%E6%9E%B6)中的教程，或自行寻找其镜像）并在 QChatGPT 的配置文件中设置连接地址。
 
-> **Note**
+> [!NOTE]
 > 请先确保 Docker 和 Docker Compose 已安装
 
 ## 准备文件