fix: docker permission bug

fix: use relpath in plugin manager
fix : group_chat_reply_prefix not in config
2026-06-02 09:48:22 +08:00 · 2023-03-26 02:00:35 +08:00 · 2023-03-25 23:35:23 +08:00 · 2023-03-25 20:23:00 +08:00 · 2023-03-25 19:14:20 +08:00 · 2023-03-25 19:00:19 +08:00
59 changed files with 2669 additions and 287 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -8,3 +8,5 @@ config.json
 QR.png
 nohup.out
 tmp
+plugins.json
+itchat.pkl
--- a/README.md
+++ b/README.md
@@ -15,18 +15,16 @@

 # 更新日志

+>**2023.03.25：** 支持插件化开发，目前已实现 多角色切换、文字冒险游戏、管理员指令、Stable Diffusion等插件，使用参考 [#578](https://github.com/zhayujie/chatgpt-on-wechat/issues/578)。(contributed by [@lanvent](https://github.com/lanvent) in [#565](https://github.com/zhayujie/chatgpt-on-wechat/pull/565))
+
 >**2023.03.09：** 基于 `whisper API` 实现对微信语音消息的解析和回复，添加配置项 `"speech_recognition":true` 即可启用，使用参考 [#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)。(contributed by [wanggang1987](https://github.com/wanggang1987) in [#385](https://github.com/zhayujie/chatgpt-on-wechat/pull/385))

 >**2023.03.02：** 接入[ChatGPT API](https://platform.openai.com/docs/guides/chat) (gpt-3.5-turbo)，默认使用该模型进行对话，需升级openai依赖 (`pip3 install --upgrade openai`)。网络问题参考 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)

->**2023.02.20：** 增加 [python-wechaty](https://github.com/wechaty/python-wechaty) 作为可选渠道，使用Pad协议，但Token收费 (使用参考[#244](https://github.com/zhayujie/chatgpt-on-wechat/pull/244)，contributed by [ZQ7](https://github.com/ZQ7))
-
 >**2023.02.09：** 扫码登录存在封号风险，请谨慎使用，参考[#58](https://github.com/AutumnWhj/ChatGPT-wechat-bot/issues/158)

 >**2023.02.05：** 在openai官方接口方案中 (GPT-3模型) 实现上下文对话

->**2022.12.19：** 引入 [itchat-uos](https://github.com/why2lyj/ItChat-UOS) 替换 itchat，解决由于不能登录网页微信而无法使用的问题，且解决Python3.9的兼容问题
-
 >**2022.12.18：** 支持根据描述生成图片并发送，openai版本需大于0.25.0

 >**2022.12.17：** 原来的方案是从 [ChatGPT页面](https://chat.openai.com/chat) 获取session_token，使用 [revChatGPT](https://github.com/acheong08/ChatGPT) 直接访问web接口，但随着ChatGPT接入Cloudflare人机验证，这一方案难以在服务器顺利运行。 所以目前使用的方案是调用 OpenAI 官方提供的 [API](https://beta.openai.com/docs/api-reference/introduction)，回复质量上基本接近于ChatGPT的内容，劣势是暂不支持有上下文记忆的对话，优势是稳定性和响应速度较好。
@@ -54,7 +52,10 @@

 前往 [OpenAI注册页面](https://beta.openai.com/signup) 创建账号，参考这篇 [教程](https://www.pythonthree.com/register-openai-chatgpt/) 可以通过虚拟手机号来接收验证码。创建完账号则前往 [API管理页面](https://beta.openai.com/account/api-keys) 创建一个 API Key 并保存下来，后面需要在项目中配置这个key。

-> 项目中使用的对话模型是 davinci，计费方式是约每 750 字 (包含请求和回复) 消耗 $0.02，图片生成是每张消耗 $0.016，账号创建有免费的 $18 额度，使用完可以更换邮箱重新注册。
+> 项目中使用的对话模型是 davinci，计费方式是约每 750 字 (包含请求和回复) 消耗 $0.02，图片生成是每张消耗 $0.016，账号创建有免费的 $18 额度 (更新3.25: 最新注册的已经无免费额度了)，使用完可以更换邮箱重新注册。
+
+#### 1.1 ChapGPT service On Azure
+一种替换以上的方法是使用Azure推出的[ChatGPT service](https://azure.microsoft.com/en-in/products/cognitive-services/openai-service/)。它host在公有云Azure上，因此不需要VPN就可以直接访问。不过目前仍然处于preview阶段。新用户可以通过Try Azure for free来薅一段时间的羊毛


 ### 2.运行环境
@@ -96,16 +97,18 @@ pip3 install --upgrade openai
 # config.json文件内容示例
 { 
  "open_ai_api_key": "YOUR API KEY",                          # 填入上面创建的 OpenAI API KEY
-  "model": "gpt-3.5-turbo",                                   # 模型名称
+  "model": "gpt-3.5-turbo",                                   # 模型名称。当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
  "proxy": "127.0.0.1:7890",                                  # 代理客户端的ip和端口
  "single_chat_prefix": ["bot", "@bot"],                      # 私聊时文本需要包含该前缀才能触发机器人回复
  "single_chat_reply_prefix": "[bot] ",                       # 私聊时自动回复的前缀，用于区分真人
  "group_chat_prefix": ["@bot"],                              # 群聊时包含该前缀则会触发机器人回复
  "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表
+  "group_chat_in_one_session": ["ChatGPT测试群"],              # 支持会话上下文共享的群名称       
  "image_create_prefix": ["画", "看", "找"],                   # 开启图片回复的前缀
  "conversation_max_tokens": 1000,                            # 支持上下文记忆的最多字符数
  "speech_recognition": false,                                # 是否开启语音识别
-  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",  # 人格描述
+  "use_azure_chatgpt": false,                                 # 是否使用Azure ChatGPT service代替openai ChatGPT service. 当设置为true时需要设置 open_ai_api_base，如 https://xxx.openai.azure.com/
+  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",  # 人格描述,
 }
 ```
 **配置说明：**
@@ -120,6 +123,7 @@ pip3 install --upgrade openai
 + 群组聊天中，群名称需配置在 `group_name_white_list ` 中才能开启群聊自动回复。如果想对所有群聊生效，可以直接填写 `"group_name_white_list": ["ALL_GROUP"]`
 + 默认只要被人 @ 就会触发机器人自动回复；另外群聊天中只要检测到以 "@bot" 开头的内容，同样会自动回复（方便自己触发），这对应配置项 `group_chat_prefix`
 + 可选配置: `group_name_keyword_white_list`配置项支持模糊匹配群名称，`group_chat_keyword`配置项则支持模糊匹配群消息内容，用法与上述两个配置项相同。（Contributed by [evolay](https://github.com/evolay))
+ `group_chat_in_one_session`：使群聊共享一个会话上下文，配置 `["ALL_GROUP"]` 则作用于所有群聊

 **3.语音识别**

@@ -173,6 +177,14 @@ nohup python3 app.py & tail -f nohup.out          # 在后台运行程序并通

 参考文档 [Docker部署](https://github.com/limccn/chatgpt-on-wechat/wiki/Docker%E9%83%A8%E7%BD%B2)   (Contributed by [limccn](https://github.com/limccn))。

+### 4. Railway部署
+[Use with Railway](#use-with-railway)(PaaS, Free, Stable, ✅Recommended)
+> Railway offers $5 (500 hours) of runtime per month
+1. Click the [Railway](https://railway.app/) button to go to the Railway homepage
+2. Click the `Start New Project` button.
+3. Click the `Deploy from Github repo` button.
+4. Choose your repo (you can fork this repo firstly)
+5. Set environment variable to override settings in config-template.json, such as: model, open_ai_api_base, open_ai_api_key, use_azure_chatgpt etc.

 ## 常见问题

--- a/app.py
+++ b/app.py
@@ -4,17 +4,24 @@ import config
 from channel import channel_factory
 from common.log import logger

+from plugins import *

-if __name__ == '__main__':
+def run():
    try:
        # load config
        config.load_config()

        # create channel
-        channel = channel_factory.create_channel("wx")
+        channel_name='wx'
+        channel = channel_factory.create_channel(channel_name)
+        if channel_name=='wx':
+            PluginManager().load_plugins()

        # startup channel
        channel.startup()
    except Exception as e:
        logger.error("App startup failed!")
        logger.exception(e)
+
+if __name__ == '__main__':
+    run()
--- a/bot/baidu/baidu_unit_bot.py
+++ b/bot/baidu/baidu_unit_bot.py
@@ -2,6 +2,7 @@

 import requests
 from bot.bot import Bot
+from bridge.reply import Reply, ReplyType


 # Baidu Unit对话接口 (可用, 但能力较弱)
@@ -14,7 +15,8 @@ class BaiduUnitBot(Bot):
        headers = {'content-type': 'application/x-www-form-urlencoded'}
        response = requests.post(url, data=post_data.encode(), headers=headers)
        if response:
-            return response.json()['result']['context']['SYS_PRESUMED_HIST'][1]
+            reply = Reply(ReplyType.TEXT, response.json()['result']['context']['SYS_PRESUMED_HIST'][1])
+            return reply

    def get_token(self):
        access_key = 'YOUR_ACCESS_KEY'
--- a/bot/bot.py
+++ b/bot/bot.py
@@ -3,8 +3,12 @@ Auto-replay chat robot abstract class
 """


+from bridge.context import Context
+from bridge.reply import Reply
+
+
 class Bot(object):
-    def reply(self, query, context=None):
+    def reply(self, query, context : Context =None) -> Reply:
        """
        bot auto-reply content
        :param req: received message
--- a/bot/bot_factory.py
+++ b/bot/bot_factory.py
@@ -24,4 +24,9 @@ def create_bot(bot_type):
        # OpenAI 官方对话模型API
        from bot.openai.open_ai_bot import OpenAIBot
        return OpenAIBot()
+
+    elif bot_type == const.CHATGPTONAZURE:
+        # Azure chatgpt service https://azure.microsoft.com/en-in/products/cognitive-services/openai-service/
+        from bot.chatgpt.chat_gpt_bot import AzureChatGPTBot
+        return AzureChatGPTBot()
    raise RuntimeError
--- a/bot/chatgpt/chat_gpt_bot.py
+++ b/bot/chatgpt/chat_gpt_bot.py
@@ -1,6 +1,8 @@
 # encoding:utf-8

 from bot.bot import Bot
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
 from config import conf, load_config
 from common.log import logger
 from common.token_bucket import TokenBucket
@@ -8,10 +10,6 @@ from common.expired_dict import ExpiredDict
 import openai
 import time

-if conf().get('expires_in_seconds'):
-    all_sessions = ExpiredDict(conf().get('expires_in_seconds'))
-else:
-    all_sessions = dict()

 # OpenAI对话模型API (可用)
 class ChatGPTBot(Bot):
@@ -20,6 +18,7 @@ class ChatGPTBot(Bot):
        if conf().get('open_ai_api_base'):
            openai.api_base = conf().get('open_ai_api_base')
        proxy = conf().get('proxy')
+        self.sessions = SessionManager()
        if proxy:
            openai.proxy = proxy
        if conf().get('rate_limit_chatgpt'):
@@ -29,21 +28,24 @@ class ChatGPTBot(Bot):

    def reply(self, query, context=None):
        # acquire reply content
-        if not context or not context.get('type') or context.get('type') == 'TEXT':
+        if context.type == ContextType.TEXT:
            logger.info("[OPEN_AI] query={}".format(query))
-            session_id = context.get('session_id') or context.get('from_user_id')
+
+            session_id = context['session_id']
+            reply = None
            clear_memory_commands = conf().get('clear_memory_commands', ['#清除记忆'])
            if query in clear_memory_commands:
-                Session.clear_session(session_id)
-                return '记忆已清除'
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, '记忆已清除')
            elif query == '#清除所有':
-                Session.clear_all_session()
-                return '所有人记忆已清除'
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, '所有人记忆已清除')
            elif query == '#更新配置':
                load_config()
-                return '配置已更新'
-
-            session = Session.build_session_query(query, session_id)
+                reply = Reply(ReplyType.INFO, '配置已更新')
+            if reply:
+                return reply
+            session = self.sessions.build_session_query(query, session_id)
            logger.debug("[OPEN_AI] session query={}".format(session))

            # if context.get('stream'):
@@ -52,14 +54,39 @@ class ChatGPTBot(Bot):

            reply_content = self.reply_text(session, session_id, 0)
            logger.debug("[OPEN_AI] new_query={}, session_id={}, reply_cont={}".format(session, session_id, reply_content["content"]))
-            if reply_content["completion_tokens"] > 0:
-                Session.save_session(reply_content["content"], session_id, reply_content["total_tokens"])
-            return reply_content["content"]
+            if reply_content['completion_tokens'] == 0 and len(reply_content['content']) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content['content'])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.save_session(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content['content'])
+                logger.debug("[OPEN_AI] reply {} used 0 tokens.".format(reply_content))
+            return reply

-        elif context.get('type', None) == 'IMAGE_CREATE':
-            return self.create_img(query, 0)
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, retstring = self.create_img(query, 0)
+            reply = None
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, retstring)
+            else:
+                reply = Reply(ReplyType.ERROR, retstring)
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, 'Bot不支持处理{}类型的消息'.format(context.type))
+            return reply

-    def reply_text(self, session, session_id, retry_count=0) ->dict:
+    def compose_args(self):
+        return {
+            "model": conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称
+            "temperature":conf().get('temperature', 0.9),  # 值在[0,1]之间，越大表示回复越具有不确定性
+            # "max_tokens":4096,  # 回复最大的字符数
+            "top_p":1,
+            "frequency_penalty":conf().get('frequency_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            "presence_penalty":conf().get('presence_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+        }
+
+    def reply_text(self, session, session_id, retry_count=0) -> dict:
        '''
        call openai's ChatCompletion to get the answer
        :param session: a conversation session
@@ -71,17 +98,11 @@ class ChatGPTBot(Bot):
            if conf().get('rate_limit_chatgpt') and not self.tb4chatgpt.get_token():
                return {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
            response = openai.ChatCompletion.create(
-                model= conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称
-                messages=session,
-                temperature=conf().get('temperature', 0.9),  # 值在[0,1]之间，越大表示回复越具有不确定性
-                #max_tokens=4096,  # 回复最大的字符数
-                top_p=1,
-                frequency_penalty=conf().get('frequency_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
-                presence_penalty=conf().get('presence_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+                messages=session, **self.compose_args()
            )
            # logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
-            return {"total_tokens": response["usage"]["total_tokens"], 
-                    "completion_tokens": response["usage"]["completion_tokens"], 
+            return {"total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
                    "content": response.choices[0]['message']['content']}
        except openai.error.RateLimitError as e:
            # rate limit exception
@@ -96,21 +117,21 @@ class ChatGPTBot(Bot):
            # api connection exception
            logger.warn(e)
            logger.warn("[OPEN_AI] APIConnection failed")
-            return {"completion_tokens": 0, "content":"我连接不到你的网络"}
+            return {"completion_tokens": 0, "content": "我连接不到你的网络"}
        except openai.error.Timeout as e:
            logger.warn(e)
            logger.warn("[OPEN_AI] Timeout")
-            return {"completion_tokens": 0, "content":"我没有收到你的消息"}
+            return {"completion_tokens": 0, "content": "我没有收到你的消息"}
        except Exception as e:
            # unknown exception
            logger.exception(e)
-            Session.clear_session(session_id)
+            self.sessions.clear_session(session_id)
            return {"completion_tokens": 0, "content": "请再问我一次吧"}

    def create_img(self, query, retry_count=0):
        try:
            if conf().get('rate_limit_dalle') and not self.tb4dalle.get_token():
-                return "请求太快了，请休息一下再问我吧"
+                return False, "请求太快了，请休息一下再问我吧"
            logger.info("[OPEN_AI] image_query={}".format(query))
            response = openai.Image.create(
                prompt=query,    #图片描述
@@ -119,7 +140,7 @@ class ChatGPTBot(Bot):
            )
            image_url = response['data'][0]['url']
            logger.info("[OPEN_AI] image_url={}".format(image_url))
-            return image_url
+            return True, image_url
        except openai.error.RateLimitError as e:
            logger.warn(e)
            if retry_count < 1:
@@ -127,14 +148,44 @@ class ChatGPTBot(Bot):
                logger.warn("[OPEN_AI] ImgCreate RateLimit exceed, 第{}次重试".format(retry_count+1))
                return self.create_img(query, retry_count+1)
            else:
-                return "请求太快啦，请休息一下再问我吧"
+                return False, "提问太快啦，请休息一下再问我吧"
        except Exception as e:
            logger.exception(e)
-            return None
+            return False, str(e)

-class Session(object):
-    @staticmethod
-    def build_session_query(query, session_id):
+
+class AzureChatGPTBot(ChatGPTBot):
+    def __init__(self):
+        super().__init__()
+        openai.api_type = "azure"
+        openai.api_version = "2023-03-15-preview"
+
+    def compose_args(self):
+        args = super().compose_args()
+        args["engine"] = args["model"]
+        del(args["model"])
+        return args
+
+
+class SessionManager(object):
+    def __init__(self):
+        if conf().get('expires_in_seconds'):
+            sessions = ExpiredDict(conf().get('expires_in_seconds'))
+        else:
+            sessions = dict()
+        self.sessions = sessions
+
+    def build_session(self, session_id, system_prompt=None):
+        session = self.sessions.get(session_id, [])
+        if len(session) == 0:
+            if system_prompt is None:
+                system_prompt = conf().get("character_desc", "")
+            system_item = {'role': 'system', 'content': system_prompt}
+            session.append(system_item)
+            self.sessions[session_id] = session
+        return session
+
+    def build_session_query(self, query, session_id):
        '''
        build query with conversation history
        e.g.  [
@@ -147,36 +198,28 @@ class Session(object):
        :param session_id: session id
        :return: query content with conversaction
        '''
-        session = all_sessions.get(session_id, [])
-        if len(session) == 0:
-            system_prompt = conf().get("character_desc", "")
-            system_item = {'role': 'system', 'content': system_prompt}
-            session.append(system_item)
-            all_sessions[session_id] = session
+        session = self.build_session(session_id)
        user_item = {'role': 'user', 'content': query}
        session.append(user_item)
        return session

-    @staticmethod
-    def save_session(answer, session_id, total_tokens):
+    def save_session(self, answer, session_id, total_tokens):
        max_tokens = conf().get("conversation_max_tokens")
        if not max_tokens:
            # default 3000
            max_tokens = 1000
-        max_tokens=int(max_tokens)
+        max_tokens = int(max_tokens)

-        session = all_sessions.get(session_id)
+        session = self.sessions.get(session_id)
        if session:
            # append conversation
            gpt_item = {'role': 'assistant', 'content': answer}
            session.append(gpt_item)

        # discard exceed limit conversation
-        Session.discard_exceed_conversation(session, max_tokens, total_tokens)
-    
+        self.discard_exceed_conversation(session, max_tokens, total_tokens)

-    @staticmethod
-    def discard_exceed_conversation(session, max_tokens, total_tokens):
+    def discard_exceed_conversation(self, session, max_tokens, total_tokens):
        dec_tokens = int(total_tokens)
        # logger.info("prompt tokens used={},max_tokens={}".format(used_tokens,max_tokens))
        while dec_tokens > max_tokens:
@@ -185,13 +228,11 @@ class Session(object):
                session.pop(1)
                session.pop(1)
            else:
-                break    
+                break
            dec_tokens = dec_tokens - max_tokens

-    @staticmethod
-    def clear_session(session_id):
-        all_sessions[session_id] = []
+    def clear_session(self, session_id):
+        self.sessions[session_id] = []

-    @staticmethod
-    def clear_all_session():
-        all_sessions.clear()
+    def clear_all_session(self):
+        self.sessions.clear()
--- a/bot/openai/open_ai_bot.py
+++ b/bot/openai/open_ai_bot.py
@@ -1,6 +1,8 @@
 # encoding:utf-8

 from bot.bot import Bot
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
 from config import conf
 from common.log import logger
 import openai
@@ -18,29 +20,32 @@ class OpenAIBot(Bot):
        if proxy:
            openai.proxy = proxy

+
    def reply(self, query, context=None):
        # acquire reply content
-        if not context or not context.get('type') or context.get('type') == 'TEXT':
-            logger.info("[OPEN_AI] query={}".format(query))
-            from_user_id = context.get('from_user_id') or context.get('session_id')
-            if query == '#清除记忆':
-                Session.clear_session(from_user_id)
-                return '记忆已清除'
-            elif query == '#清除所有':
-                Session.clear_all_session()
-                return '所有人记忆已清除'
+        if context and context.type:
+            if context.type == ContextType.TEXT:
+                logger.info("[OPEN_AI] query={}".format(query))
+                from_user_id = context['session_id']
+                reply = None
+                if query == '#清除记忆':
+                    Session.clear_session(from_user_id)
+                    reply = Reply(ReplyType.INFO, '记忆已清除')
+                elif query == '#清除所有':
+                    Session.clear_all_session()
+                    reply = Reply(ReplyType.INFO, '所有人记忆已清除')
+                else:
+                    new_query = Session.build_session_query(query, from_user_id)
+                    logger.debug("[OPEN_AI] session query={}".format(new_query))

-            new_query = Session.build_session_query(query, from_user_id)
-            logger.debug("[OPEN_AI] session query={}".format(new_query))
-
-            reply_content = self.reply_text(new_query, from_user_id, 0)
-            logger.debug("[OPEN_AI] new_query={}, user={}, reply_cont={}".format(new_query, from_user_id, reply_content))
-            if reply_content and query:
-                Session.save_session(query, reply_content, from_user_id)
-            return reply_content
-
-        elif context.get('type', None) == 'IMAGE_CREATE':
-            return self.create_img(query, 0)
+                    reply_content = self.reply_text(new_query, from_user_id, 0)
+                    logger.debug("[OPEN_AI] new_query={}, user={}, reply_cont={}".format(new_query, from_user_id, reply_content))
+                    if reply_content and query:
+                        Session.save_session(query, reply_content, from_user_id)
+                    reply = Reply(ReplyType.TEXT, reply_content)
+                return reply
+            elif context.type == ContextType.IMAGE_CREATE:
+                return self.create_img(query, 0)

    def reply_text(self, query, user_id, retry_count=0):
        try:
--- a/bridge/bridge.py
+++ b/bridge/bridge.py
@@ -1,24 +1,50 @@
+from bridge.context import Context
+from bridge.reply import Reply
+from common.log import logger
 from bot import bot_factory
+from common.singleton import singleton
 from voice import voice_factory
 from config import conf
 from common import const


+@singleton
 class Bridge(object):
    def __init__(self):
-        pass
-
-    def fetch_reply_content(self, query, context):
-        bot_type = const.CHATGPT
+        self.btype={
+            "chat": const.CHATGPT,
+            "voice_to_text": conf().get("voice_to_text", "openai"),
+            "text_to_voice": conf().get("text_to_voice", "baidu")
+        }
        model_type = conf().get("model")
-        if model_type in ["gpt-3.5-turbo", "gpt-4", "gpt-4-32k"]:
-            bot_type = const.CHATGPT
-        elif model_type in ["text-davinci-003"]:
-            bot_type = const.OPEN_AI
-        return bot_factory.create_bot(bot_type).reply(query, context)
+        if model_type in ["text-davinci-003"]:
+            self.btype['chat'] = const.OPEN_AI
+        if conf().get("use_azure_chatgpt"):
+            self.btype['chat'] = const.CHATGPTONAZURE
+        self.bots={}

-    def fetch_voice_to_text(self, voiceFile):
-        return voice_factory.create_voice("openai").voiceToText(voiceFile)
+    def get_bot(self,typename):
+        if self.bots.get(typename) is None:
+            logger.info("create bot {} for {}".format(self.btype[typename],typename))
+            if typename == "text_to_voice":
+                self.bots[typename] = voice_factory.create_voice(self.btype[typename])
+            elif typename == "voice_to_text":
+                self.bots[typename] = voice_factory.create_voice(self.btype[typename])
+            elif typename == "chat":
+                self.bots[typename] = bot_factory.create_bot(self.btype[typename])
+        return self.bots[typename]
+    
+    def get_bot_type(self,typename):
+        return self.btype[typename]
+
+
+    def fetch_reply_content(self, query, context : Context) -> Reply:
+        return self.get_bot("chat").reply(query, context)
+
+
+    def fetch_voice_to_text(self, voiceFile) -> Reply:
+        return self.get_bot("voice_to_text").voiceToText(voiceFile)
+
+    def fetch_text_to_voice(self, text) -> Reply:
+        return self.get_bot("text_to_voice").textToVoice(text)

-    def fetch_text_to_voice(self, text):
-        return voice_factory.create_voice("baidu").textToVoice(text)
--- a/bridge/context.py
+++ b/bridge/context.py
@@ -0,0 +1,42 @@
+# encoding:utf-8
+
+from enum import Enum
+
+class ContextType (Enum):
+    TEXT = 1         # 文本消息
+    VOICE = 2        # 音频消息
+    IMAGE_CREATE = 3 # 创建图片命令
+    
+    def __str__(self):
+        return self.name
+class Context:
+    def __init__(self, type : ContextType = None , content = None,  kwargs = dict()):
+        self.type = type
+        self.content = content
+        self.kwargs = kwargs
+    def __getitem__(self, key):
+        if key == 'type':
+            return self.type
+        elif key == 'content':
+            return self.content
+        else:
+            return self.kwargs[key]
+
+    def __setitem__(self, key, value):
+        if key == 'type':
+            self.type = value
+        elif key == 'content':
+            self.content = value
+        else:
+            self.kwargs[key] = value
+
+    def __delitem__(self, key):
+        if key == 'type':
+            self.type = None
+        elif key == 'content':
+            self.content = None
+        else:
+            del self.kwargs[key]
+    
+    def __str__(self):
+        return "Context(type={}, content={}, kwargs={})".format(self.type, self.content, self.kwargs)
--- a/bridge/reply.py
+++ b/bridge/reply.py
@@ -0,0 +1,22 @@
+
+# encoding:utf-8
+
+from enum import Enum
+
+class ReplyType(Enum):
+    TEXT = 1        # 文本
+    VOICE = 2       # 音频文件
+    IMAGE = 3       # 图片文件
+    IMAGE_URL = 4   # 图片URL
+    
+    INFO = 9
+    ERROR = 10
+    def __str__(self):
+        return self.name
+
+class Reply:
+    def __init__(self, type : ReplyType = None , content = None):
+        self.type = type
+        self.content = content
+    def __str__(self):
+        return "Reply(type={}, content={})".format(self.type, self.content)
--- a/channel/channel.py
+++ b/channel/channel.py
@@ -3,6 +3,8 @@ Message sending channel abstract class
 """

 from bridge.bridge import Bridge
+from bridge.context import Context
+from bridge.reply import Reply

 class Channel(object):
    def startup(self):
@@ -27,11 +29,11 @@ class Channel(object):
        """
        raise NotImplementedError

-    def build_reply_content(self, query, context=None):
+    def build_reply_content(self, query, context : Context=None) -> Reply:
        return Bridge().fetch_reply_content(query, context)

-    def build_voice_to_text(self, voice_file):
+    def build_voice_to_text(self, voice_file) -> Reply:
        return Bridge().fetch_voice_to_text(voice_file)
    
-    def build_text_to_voice(self, text):
+    def build_text_to_voice(self, text) -> Reply:
        return Bridge().fetch_text_to_voice(text)
--- a/channel/terminal/terminal_channel.py
+++ b/channel/terminal/terminal_channel.py
@@ -1,9 +1,10 @@
+from bridge.context import *
 from channel.channel import Channel
 import sys

 class TerminalChannel(Channel):
    def startup(self):
-        context = {"from_user_id": "User"}
+        context = Context()
        print("\nPlease input your question")
        while True:
            try:
@@ -12,12 +13,13 @@ class TerminalChannel(Channel):
                print("\nExiting...")
                sys.exit()

+            context.type = ContextType.TEXT
+            context['session_id'] = "User"
+            context.content = prompt
            print("Bot:")
            sys.stdout.flush()
-            for res in super().build_reply_content(prompt, context):
-                print(res, end="")
-                sys.stdout.flush()
-            print("\n")
+            res = super().build_reply_content(prompt, context).content
+            print(res)


    def get_input(self, prompt):
--- a/channel/wechat/wechat_channel.py
+++ b/channel/wechat/wechat_channel.py
@@ -4,20 +4,29 @@
 wechat channel
 """

+import os
 import itchat
 import json
 from itchat.content import *
+from bridge.reply import *
+from bridge.context import *
 from channel.channel import Channel
 from concurrent.futures import ThreadPoolExecutor
 from common.log import logger
 from common.tmp_dir import TmpDir
 from config import conf
+from common.time_check import time_checker
+from plugins import *
 import requests
 import io
 import time

-thread_pool = ThreadPoolExecutor(max_workers=8)

+thread_pool = ThreadPoolExecutor(max_workers=8)
+def thread_pool_callback(worker):
+    worker_exception = worker.exception()
+    if worker_exception:
+        logger.exception("Worker return exception: {}".format(worker_exception))

@itchat.msg_register(TEXT)
 def handler_single_msg(msg):
@@ -42,73 +51,78 @@ class WechatChannel(Channel):
        pass

    def startup(self):
-        # login by scan QRCode
-        itchat.auto_login(enableCmdQR=2, hotReload=conf().get('hot_reload', False))

+        itchat.instance.receivingRetryCount = 600 # 修改断线超时时间
+        # login by scan QRCode
+        hotReload = conf().get('hot_reload', False)
+        try:
+            itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
+        except Exception as e:
+            if hotReload:
+                logger.error("Hot reload failed, try to login without hot reload")
+                itchat.logout()
+                os.remove("itchat.pkl")
+                itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
+            else:
+                raise e
        # start message listener
        itchat.run()

+    # handle_* 系列函数处理收到的消息后构造Context，然后传入handle函数中处理Context和发送回复
+    # Context包含了消息的所有信息，包括以下属性
+    #   type 消息类型, 包括TEXT、VOICE、IMAGE_CREATE
+    #   content 消息内容，如果是TEXT类型，content就是文本内容，如果是VOICE类型，content就是语音文件名，如果是IMAGE_CREATE类型，content就是图片生成命令
+    #   kwargs 附加参数字典，包含以下的key：
+    #        session_id: 会话id
+    #        isgroup: 是否是群聊
+    #        receiver: 需要回复的对象
+    #        msg: itchat的原始消息对象
+
    def handle_voice(self, msg):
-        if conf().get('speech_recognition') != True :
+        if conf().get('speech_recognition') != True:
            return
        logger.debug("[WX]receive voice msg: " + msg['FileName'])
-        thread_pool.submit(self._do_handle_voice, msg)
-
-    def _do_handle_voice(self, msg):
        from_user_id = msg['FromUserName']
        other_user_id = msg['User']['UserName']
        if from_user_id == other_user_id:
-            file_name = TmpDir().path() + msg['FileName']
-            msg.download(file_name)
-            query = super().build_voice_to_text(file_name)
-            if conf().get('voice_reply_voice'):
-                self._do_send_voice(query, from_user_id)
-            else:
-                self._do_send_text(query, from_user_id)
+            context = Context(ContextType.VOICE,msg['FileName'])
+            context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id}
+            thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)

+
+    @time_checker
    def handle_text(self, msg):
        logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False))
        content = msg['Text']
-        self._handle_single_msg(msg, content)
-
-    def _handle_single_msg(self, msg, content):
        from_user_id = msg['FromUserName']
        to_user_id = msg['ToUserName']              # 接收人id
        other_user_id = msg['User']['UserName']     # 对手方id
        create_time = msg['CreateTime']             # 消息时间
-        match_prefix = self.check_prefix(content, conf().get('single_chat_prefix'))
+        match_prefix = check_prefix(content, conf().get('single_chat_prefix'))
        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:    #跳过1分钟前的历史消息
            logger.debug("[WX]history message skipped")
            return
        if "」\n- - - - - - - - - - - - - - -" in content:
            logger.debug("[WX]reference query skipped")
            return
-        if from_user_id == other_user_id and match_prefix is not None:
-            # 好友向自己发送消息
-            if match_prefix != '':
-                str_list = content.split(match_prefix, 1)
-                if len(str_list) == 2:
-                    content = str_list[1].strip()
+        if match_prefix:
+            content = content.replace(match_prefix, '', 1).strip()
+        elif match_prefix is None:
+            return
+        context = Context()
+        context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id}

-            img_match_prefix = self.check_prefix(content, conf().get('image_create_prefix'))
-            if img_match_prefix:
-                content = content.split(img_match_prefix, 1)[1].strip()
-                thread_pool.submit(self._do_send_img, content, from_user_id)
-            else :
-                thread_pool.submit(self._do_send_text, content, from_user_id)
-        elif to_user_id == other_user_id and match_prefix:
-            # 自己给好友发送消息
-            str_list = content.split(match_prefix, 1)
-            if len(str_list) == 2:
-                content = str_list[1].strip()
-            img_match_prefix = self.check_prefix(content, conf().get('image_create_prefix'))
-            if img_match_prefix:
-                content = content.split(img_match_prefix, 1)[1].strip()
-                thread_pool.submit(self._do_send_img, content, to_user_id)
-            else:
-                thread_pool.submit(self._do_send_text, content, to_user_id)
+        img_match_prefix = check_prefix(content, conf().get('image_create_prefix'))
+        if img_match_prefix:
+            content = content.replace(img_match_prefix, '', 1).strip()
+            context.type = ContextType.IMAGE_CREATE
+        else:
+            context.type = ContextType.TEXT

+        context.content = content
+        thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)

+    @time_checker
    def handle_group(self, msg):
        logger.debug("[WX]receive group msg: " + json.dumps(msg, ensure_ascii=False))
        group_name = msg['User'].get('NickName', None)
@@ -131,100 +145,128 @@ class WechatChannel(Channel):
            logger.debug("[WX]reference query skipped")
            return ""
        config = conf()
-        match_prefix = (msg['IsAt'] and not config.get("group_at_off", False)) or self.check_prefix(origin_content, config.get('group_chat_prefix')) \
-                       or self.check_contain(origin_content, config.get('group_chat_keyword'))
-        if ('ALL_GROUP' in config.get('group_name_white_list') or group_name in config.get('group_name_white_list') or self.check_contain(group_name, config.get('group_name_keyword_white_list'))) and match_prefix:
-            img_match_prefix = self.check_prefix(content, conf().get('image_create_prefix'))
+        match_prefix = (msg['IsAt'] and not config.get("group_at_off", False)) or check_prefix(origin_content, config.get('group_chat_prefix')) \
+                       or check_contain(origin_content, config.get('group_chat_keyword'))
+        if ('ALL_GROUP' in config.get('group_name_white_list') or group_name in config.get('group_name_white_list') or check_contain(group_name, config.get('group_name_keyword_white_list'))) and match_prefix:
+            context = Context()
+            context.kwargs = { 'isgroup': True, 'msg': msg, 'receiver': group_id}
+            
+            img_match_prefix = check_prefix(content, conf().get('image_create_prefix'))
            if img_match_prefix:
-                content = content.split(img_match_prefix, 1)[1].strip()
-                thread_pool.submit(self._do_send_img, content, group_id)
+                content = content.replace(img_match_prefix, '', 1).strip()
+                context.type = ContextType.IMAGE_CREATE
            else:
-                thread_pool.submit(self._do_send_group, content, msg)
+                context.type = ContextType.TEXT
+            context.content = content

-    def send(self, msg, receiver):
-        itchat.send(msg, toUserName=receiver)
-        logger.info('[WX] sendMsg={}, receiver={}'.format(msg, receiver))
+            group_chat_in_one_session = conf().get('group_chat_in_one_session', [])
+            if ('ALL_GROUP' in group_chat_in_one_session or
+                    group_name in group_chat_in_one_session or
+                    check_contain(group_name, group_chat_in_one_session)):
+                context['session_id'] = group_id
+            else:
+                context['session_id'] = msg['ActualUserName']

-    def _do_send_voice(self, query, reply_user_id):
-        try:
-            if not query:
-                return
-            context = dict()
-            context['from_user_id'] = reply_user_id
-            reply_text = super().build_reply_content(query, context)
-            if reply_text:
-                replyFile = super().build_text_to_voice(reply_text)
-                itchat.send_file(replyFile, toUserName=reply_user_id)
-                logger.info('[WX] sendFile={}, receiver={}'.format(replyFile, reply_user_id))
-        except Exception as e:
-            logger.exception(e)
+            thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback)

-    def _do_send_text(self, query, reply_user_id):
-        try:
-            if not query:
-                return
-            context = dict()
-            context['session_id'] = reply_user_id
-            reply_text = super().build_reply_content(query, context)
-            if reply_text:
-                self.send(conf().get("single_chat_reply_prefix") + reply_text, reply_user_id)
-        except Exception as e:
-            logger.exception(e)
-
-    def _do_send_img(self, query, reply_user_id):
-        try:
-            if not query:
-                return
-            context = dict()
-            context['type'] = 'IMAGE_CREATE'
-            img_url = super().build_reply_content(query, context)
-            if not img_url:
-                return
-
-            # 图片下载
+    # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息
+    def send(self, reply : Reply, receiver):
+        if reply.type == ReplyType.TEXT:
+            itchat.send(reply.content, toUserName=receiver)
+            logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver))
+        elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+            itchat.send(reply.content, toUserName=receiver)
+            logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver))
+        elif reply.type == ReplyType.VOICE:
+            itchat.send_file(reply.content, toUserName=receiver)
+            logger.info('[WX] sendFile={}, receiver={}'.format(reply.content, receiver))
+        elif reply.type == ReplyType.IMAGE_URL: # 从网络下载图片
+            img_url = reply.content
            pic_res = requests.get(img_url, stream=True)
            image_storage = io.BytesIO()
            for block in pic_res.iter_content(1024):
                image_storage.write(block)
            image_storage.seek(0)
+            itchat.send_image(image_storage, toUserName=receiver)
+            logger.info('[WX] sendImage url={}, receiver={}'.format(img_url,receiver))
+        elif reply.type == ReplyType.IMAGE: # 从文件读取图片
+            image_storage = reply.content
+            image_storage.seek(0)
+            itchat.send_image(image_storage, toUserName=receiver)
+            logger.info('[WX] sendImage, receiver={}'.format(receiver))

-            # 图片发送
-            itchat.send_image(image_storage, reply_user_id)
-            logger.info('[WX] sendImage, receiver={}'.format(reply_user_id))
-        except Exception as e:
-            logger.exception(e)
+    # 处理消息 TODO: 如果wechaty解耦，此处逻辑可以放置到父类
+    def handle(self, context):
+        reply = Reply()

-    def _do_send_group(self, query, msg):
-        if not query:
-            return
-        context = dict()
-        group_name = msg['User']['NickName']
-        group_id = msg['User']['UserName']
-        group_chat_in_one_session = conf().get('group_chat_in_one_session', [])
-        if ('ALL_GROUP' in group_chat_in_one_session or \
-                group_name in group_chat_in_one_session or \
-                self.check_contain(group_name, group_chat_in_one_session)):
-            context['session_id'] = group_id
-        else:
-            context['session_id'] = msg['ActualUserName']
-        reply_text = super().build_reply_content(query, context)
-        if reply_text:
-            reply_text = '@' + msg['ActualNickName'] + ' ' + reply_text.strip()
-            self.send(conf().get("group_chat_reply_prefix", "") + reply_text, group_id)
+        logger.debug('[WX] ready to handle context: {}'.format(context))
+        
+        # reply的构建步骤
+        e_context = PluginManager().emit_event(EventContext(Event.ON_HANDLE_CONTEXT, {'channel' : self, 'context': context, 'reply': reply}))
+        reply = e_context['reply']
+        if not e_context.is_pass():
+            logger.debug('[WX] ready to handle context: type={}, content={}'.format(context.type, context.content))
+            if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE:
+                reply = super().build_reply_content(context.content, context)
+            elif context.type == ContextType.VOICE:
+                msg = context['msg']
+                file_name = TmpDir().path() + context.content
+                msg.download(file_name)
+                reply = super().build_voice_to_text(file_name)
+                if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO:
+                    context.content = reply.content # 语音转文字后，将文字内容作为新的context
+                    context.type = ContextType.TEXT
+                    reply = super().build_reply_content(context.content, context)
+                    if reply.type == ReplyType.TEXT:
+                        if conf().get('voice_reply_voice'):
+                            reply = super().build_text_to_voice(reply.content)
+            else:
+                logger.error('[WX] unknown context type: {}'.format(context.type))
+                return
+
+        logger.debug('[WX] ready to decorate reply: {}'.format(reply))
+        
+        # reply的包装步骤
+        if reply and reply.type:
+            e_context = PluginManager().emit_event(EventContext(Event.ON_DECORATE_REPLY, {'channel' : self, 'context': context, 'reply': reply}))
+            reply=e_context['reply']
+            if not e_context.is_pass() and reply and reply.type:
+                if reply.type == ReplyType.TEXT:
+                    reply_text = reply.content
+                    if context['isgroup']:
+                        reply_text = '@' +  context['msg']['ActualNickName'] + ' ' + reply_text.strip()
+                        reply_text = conf().get("group_chat_reply_prefix", "")+reply_text
+                    else:
+                        reply_text = conf().get("single_chat_reply_prefix", "")+reply_text
+                    reply.content = reply_text
+                elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+                    reply.content = str(reply.type)+":\n" + reply.content
+                elif reply.type == ReplyType.IMAGE_URL or reply.type == ReplyType.VOICE or reply.type == ReplyType.IMAGE:
+                    pass
+                else:
+                    logger.error('[WX] unknown reply type: {}'.format(reply.type))
+                    return
+
+        # reply的发送步骤   
+        if reply and reply.type:
+            e_context = PluginManager().emit_event(EventContext(Event.ON_SEND_REPLY, {'channel' : self, 'context': context, 'reply': reply}))
+            reply=e_context['reply']
+            if not e_context.is_pass() and reply and reply.type:
+                logger.debug('[WX] ready to send reply: {} to {}'.format(reply, context['receiver']))
+                self.send(reply, context['receiver'])


-    def check_prefix(self, content, prefix_list):
-        for prefix in prefix_list:
-            if content.startswith(prefix):
-                return prefix
+def check_prefix(content, prefix_list):
+    for prefix in prefix_list:
+        if content.startswith(prefix):
+            return prefix
+    return None
+
+
+def check_contain(content, keyword_list):
+    if not keyword_list:
        return None
-
-
-    def check_contain(self, content, keyword_list):
-        if not keyword_list:
-            return None
-        for ky in keyword_list:
-            if content.find(ky) != -1:
-                return True
-        return None
-
+    for ky in keyword_list:
+        if content.find(ky) != -1:
+            return True
+    return None
--- a/channel/wechat/wechaty_channel.py
+++ b/channel/wechat/wechaty_channel.py
@@ -14,6 +14,7 @@ import pysilk
 import wave
 from pydub import AudioSegment
 from typing import Optional, Union
+from bridge.context import Context, ContextType
 from wechaty_puppet import MessageType, FileBox, ScanStatus  # type: ignore
 from wechaty import Wechaty, Contact
 from wechaty.user import Message, Room, MiniProgram, UrlLink
@@ -180,9 +181,9 @@ class WechatyChannel(Channel):
        try:
            if not query:
                return
-            context = dict()
+            context = Context(ContextType.TEXT, query)
            context['session_id'] = reply_user_id
-            reply_text = super().build_reply_content(query, context)
+            reply_text = super().build_reply_content(query, context).content
            if reply_text:
                await self.send(conf().get("single_chat_reply_prefix") + reply_text, reply_user_id)
        except Exception as e:
@@ -193,12 +194,12 @@ class WechatyChannel(Channel):
        try:
            if not query:
                return
-            context = dict()
+            context = Context(ContextType.TEXT, query)
            context['session_id'] = reply_user_id
-            reply_text = super().build_reply_content(query, context)
+            reply_text = super().build_reply_content(query, context).content
            if reply_text:
                # 转换 mp3 文件为 silk 格式
-                mp3_file = super().build_text_to_voice(reply_text)
+                mp3_file = super().build_text_to_voice(reply_text).content
                silk_file = mp3_file.replace(".mp3", ".silk")
                # Load the MP3 file
                audio = AudioSegment.from_file(mp3_file, format="mp3")
@@ -225,9 +226,8 @@ class WechatyChannel(Channel):
        try:
            if not query:
                return
-            context = dict()
-            context['type'] = 'IMAGE_CREATE'
-            img_url = super().build_reply_content(query, context)
+            context = Context(ContextType.IMAGE_CREATE, query)
+            img_url = super().build_reply_content(query, context).content
            if not img_url:
                return
            # 图片下载
@@ -248,7 +248,7 @@ class WechatyChannel(Channel):
    async def _do_send_group(self, query, group_id, group_name, group_user_id, group_user_name):
        if not query:
            return
-        context = dict()
+        context = Context(ContextType.TEXT, query)
        group_chat_in_one_session = conf().get('group_chat_in_one_session', [])
        if ('ALL_GROUP' in group_chat_in_one_session or \
                group_name in group_chat_in_one_session or \
@@ -256,7 +256,7 @@ class WechatyChannel(Channel):
            context['session_id'] = str(group_id)
        else:
            context['session_id'] = str(group_id) + '-' + str(group_user_id)
-        reply_text = super().build_reply_content(query, context)
+        reply_text = super().build_reply_content(query, context).content
        if reply_text:
            reply_text = '@' + group_user_name + ' ' + reply_text.strip()
            await self.send_group(conf().get("group_chat_reply_prefix", "") + reply_text, group_id)
@@ -265,9 +265,8 @@ class WechatyChannel(Channel):
        try:
            if not query:
                return
-            context = dict()
-            context['type'] = 'IMAGE_CREATE'
-            img_url = super().build_reply_content(query, context)
+            context = Context(ContextType.IMAGE_CREATE, query)
+            img_url = super().build_reply_content(query, context).content
            if not img_url:
                return
            # 图片发送
--- a/common/const.py
+++ b/common/const.py
@@ -1,4 +1,5 @@
 # bot_type
 OPEN_AI = "openAI"
 CHATGPT = "chatGPT"
-BAIDU = "baidu"
+BAIDU = "baidu"
+CHATGPTONAZURE = "chatGPTOnAzure"
--- a/common/expired_dict.py
+++ b/common/expired_dict.py
@@ -1,5 +1,6 @@
 from datetime import datetime, timedelta

+
 class ExpiredDict(dict):
    def __init__(self, expires_in_seconds):
        super().__init__()
@@ -16,8 +17,26 @@ class ExpiredDict(dict):
    def __setitem__(self, key, value):
        expiry_time = datetime.now() + timedelta(seconds=self.expires_in_seconds)
        super().__setitem__(key, (value, expiry_time))
+
    def get(self, key, default=None):
        try:
            return self[key]
        except KeyError:
-            return default
+            return default
+
+    def __contains__(self, key):
+        try:
+            self[key]
+            return True
+        except KeyError:
+            return False
+
+    def keys(self):
+        keys = list(super().keys())
+        return [key for key in keys if key in self]
+
+    def items(self):
+        return [(key, self[key]) for key in self.keys()]
+
+    def __iter__(self):
+        return self.keys().__iter__()
--- a/common/singleton.py
+++ b/common/singleton.py
@@ -0,0 +1,9 @@
+def singleton(cls):
+    instances = {}
+
+    def get_instance(*args, **kwargs):
+        if cls not in instances:
+            instances[cls] = cls(*args, **kwargs)
+        return instances[cls]
+
+    return get_instance
--- a/common/sorted_dict.py
+++ b/common/sorted_dict.py
@@ -0,0 +1,65 @@
+import heapq
+
+
+class SortedDict(dict):
+    def __init__(self, sort_func=lambda k, v: k, init_dict=None, reverse=False):
+        if init_dict is None:
+            init_dict = []
+        if isinstance(init_dict, dict):
+            init_dict = init_dict.items()
+        self.sort_func = sort_func
+        self.sorted_keys = None
+        self.reverse = reverse
+        self.heap = []
+        for k, v in init_dict:
+            self[k] = v
+
+    def __setitem__(self, key, value):
+        if key in self:
+            super().__setitem__(key, value)
+            for i, (priority, k) in enumerate(self.heap):
+                if k == key:
+                    self.heap[i] = (self.sort_func(key, value), key)
+                    heapq.heapify(self.heap)
+                    break
+            self.sorted_keys = None
+        else:
+            super().__setitem__(key, value)
+            heapq.heappush(self.heap, (self.sort_func(key, value), key))
+            self.sorted_keys = None
+
+    def __delitem__(self, key):
+        super().__delitem__(key)
+        for i, (priority, k) in enumerate(self.heap):
+            if k == key:
+                del self.heap[i]
+                heapq.heapify(self.heap)
+                break
+        self.sorted_keys = None
+
+    def keys(self):
+        if self.sorted_keys is None:
+            self.sorted_keys = [k for _, k in sorted(self.heap, reverse=self.reverse)]
+        return self.sorted_keys
+
+    def items(self):
+        if self.sorted_keys is None:
+            self.sorted_keys = [k for _, k in sorted(self.heap, reverse=self.reverse)]
+        sorted_items = [(k, self[k]) for k in self.sorted_keys]
+        return sorted_items
+
+    def _update_heap(self, key):
+        for i, (priority, k) in enumerate(self.heap):
+            if k == key:
+                new_priority = self.sort_func(key, self[key])
+                if new_priority != priority:
+                    self.heap[i] = (new_priority, key)
+                    heapq.heapify(self.heap)
+                    self.sorted_keys = None
+                break
+
+    def __iter__(self):
+        return iter(self.keys())
+
+    def __repr__(self):
+        return f'{type(self).__name__}({dict(self)}, sort_func={self.sort_func.__name__}, reverse={self.reverse})'
--- a/common/time_check.py
+++ b/common/time_check.py
@@ -0,0 +1,38 @@
+import time,re,hashlib
+import config
+from common.log import logger
+
+def time_checker(f):
+    def _time_checker(self, *args, **kwargs):
+        _config = config.conf()
+        chat_time_module = _config.get("chat_time_module", False)
+        if chat_time_module:
+            chat_start_time = _config.get("chat_start_time", "00:00")
+            chat_stopt_time = _config.get("chat_stop_time", "24:00")
+            time_regex = re.compile(r'^([01]?[0-9]|2[0-4])(:)([0-5][0-9])$')  #时间匹配，包含24:00
+
+            starttime_format_check = time_regex.match(chat_start_time)  # 检查停止时间格式
+            stoptime_format_check = time_regex.match(chat_stopt_time)  # 检查停止时间格式
+            chat_time_check = chat_start_time < chat_stopt_time # 确定启动时间<停止时间
+
+            # 时间格式检查
+            if not (starttime_format_check and stoptime_format_check and chat_time_check):
+                logger.warn('时间格式不正确,请在config.json中修改您的CHAT_START_TIME/CHAT_STOP_TIME,否则可能会影响您正常使用,开始({})-结束({})'.format(starttime_format_check,stoptime_format_check))
+            if chat_start_time>"23:59":
+                logger.error('启动时间可能存在问题，请修改!')
+
+            # 服务时间检查
+            now_time = time.strftime("%H:%M", time.localtime())
+            if chat_start_time <= now_time <= chat_stopt_time:  # 服务时间内，正常返回回答
+                f(self, *args, **kwargs)
+                return None
+            else:
+                if args[0]['Content'] == "#更新配置":  # 不在服务时间内也可以更新配置
+                    f(self, *args, **kwargs)
+                else:
+                    logger.info('非服务时间内,不接受访问')
+                    return None
+        else:
+            f(self, *args, **kwargs)  # 未开启时间模块则直接回答
+    return _time_checker
+
--- a/config-template.json
+++ b/config-template.json
@@ -1,16 +1,17 @@
- {
-   "open_ai_api_key": "YOUR API KEY",
-   "model": "gpt-3.5-turbo",
-   "proxy": "",
-   "single_chat_prefix": ["bot", "@bot"],
-   "single_chat_reply_prefix": "[bot] ",
-   "group_chat_prefix": ["@bot"],
-   "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"],
-   "image_create_prefix": ["画", "看", "找"],
-   "speech_recognition": false,
-   "voice_reply_voice": false,
-   "conversation_max_tokens": 1000,
-   "expires_in_seconds": 3600,
-   "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。"
- }
-
+{
+  "open_ai_api_key": "YOUR API KEY",
+  "model": "gpt-3.5-turbo",
+  "proxy": "",
+  "use_azure_chatgpt": false,
+  "single_chat_prefix": ["bot", "@bot"],
+  "single_chat_reply_prefix": "[bot] ",
+  "group_chat_prefix": ["@bot"],
+  "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"],
+  "group_chat_in_one_session": ["ChatGPT测试群"],
+  "image_create_prefix": ["画", "看", "找"],
+  "speech_recognition": false,
+  "voice_reply_voice": false,
+  "conversation_max_tokens": 1000,
+  "expires_in_seconds": 3600,
+  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。"
+}
--- a/config.py
+++ b/config.py
@@ -4,18 +4,112 @@ import json
 import os
 from common.log import logger

-config = {}
+# 将所有可用的配置项写在字典里
+available_setting ={
+    #openai api配置
+    "open_ai_api_key": "", # openai api key
+    "open_ai_api_base": "https://api.openai.com/v1", # openai apibase，当use_azure_chatgpt为true时，需要设置对应的api base
+    "proxy": "", # openai使用的代理
+    "model": "gpt-3.5-turbo", # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
+    "use_azure_chatgpt": False, # 是否使用azure的chatgpt

+    #Bot触发配置
+    "single_chat_prefix": ["bot", "@bot"], # 私聊时文本需要包含该前缀才能触发机器人回复
+    "single_chat_reply_prefix": "[bot] ", # 私聊时自动回复的前缀，用于区分真人
+    "group_chat_prefix": ["@bot"], # 群聊时包含该前缀则会触发机器人回复
+    "group_chat_reply_prefix": "", # 群聊时自动回复的前缀
+    "group_chat_keyword": [], # 群聊时包含该关键词则会触发机器人回复
+    "group_at_off": False, # 是否关闭群聊时@bot的触发
+    "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表
+    "group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表
+    "group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称
+    "image_create_prefix": ["画", "看", "找"], # 开启图片回复的前缀
+    
+    #chatgpt会话参数
+    "expires_in_seconds": 3600, # 无操作会话的过期时间
+    "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。", # 人格描述
+    "conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数
+            
+    #chatgpt限流配置
+    "rate_limit_chatgpt": 20, # chatgpt的调用频率限制
+    "rate_limit_dalle": 50, # openai dalle的调用频率限制
+
+
+    #chatgpt api参数 参考https://platform.openai.com/docs/api-reference/chat/create
+    "temperature": 0.9,
+    "top_p": 1,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+
+    #语音设置
+    "speech_recognition": False, # 是否开启语音识别
+    "voice_reply_voice": False, # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
+    "voice_to_text": "openai", # 语音识别引擎，支持openai和google
+    "text_to_voice": "baidu", # 语音合成引擎，支持baidu和google
+
+    # baidu api的配置， 使用百度语音识别和语音合成时需要
+    'baidu_app_id': "",
+    'baidu_api_key': "",
+    'baidu_secret_key': "",
+
+    #服务时间限制，目前支持itchat
+    "chat_time_module": False, # 是否开启服务时间限制
+    "chat_start_time": "00:00", # 服务开始时间
+    "chat_stop_time": "24:00", # 服务结束时间
+
+    # itchat的配置
+    "hot_reload": False, # 是否开启热重载
+
+    # wechaty的配置
+    "wechaty_puppet_service_token": "", # wechaty的token
+
+    # chatgpt指令自定义触发词
+    "clear_memory_commands": ['#清除记忆'], # 重置会话指令
+
+
+}
+
+class Config(dict):
+    def __getitem__(self, key):
+        if key not in available_setting:
+            raise Exception("key {} not in available_setting".format(key))
+        return super().__getitem__(key)
+
+    def __setitem__(self, key, value):
+        if key not in available_setting:
+            raise Exception("key {} not in available_setting".format(key))
+        return super().__setitem__(key, value)
+
+    def get(self, key, default=None):
+        try :
+            return self[key]
+        except KeyError as e:
+            return default
+        except Exception as e:
+            raise e
+    
+config = Config()

 def load_config():
    global config
    config_path = "./config.json"
    if not os.path.exists(config_path):
-        raise Exception('配置文件不存在，请根据config-template.json模板创建config.json文件')
+        logger.info('配置文件不存在，将使用config-template.json模板')
+        config_path = "./config-template.json"

    config_str = read_file(config_path)
+    logger.info("[INIT] config str: {}".format(config_str))
+
    # 将json字符串反序列化为dict类型
-    config = json.loads(config_str)
+    config = Config(json.loads(config_str))
+
+    # override config with environment variables.
+    # Some online deployment platforms (e.g. Railway) deploy project from github directly. So you shouldn't put your secrets like api key in a config file, instead use environment variables to override the default config.
+    for name, value in os.environ.items():
+        if name in available_setting:
+            logger.info("[INIT] override config by environ args: {}={}".format(name, value))
+            config[name] = value
+
    logger.info("[INIT] load config: {}".format(config))


--- a/docker/Dockerfile.alpine
+++ b/docker/Dockerfile.alpine
@@ -35,7 +35,7 @@ ADD ./entrypoint.sh /entrypoint.sh

 RUN chmod +x /entrypoint.sh \
    && adduser -D -h /home/noroot -u 1000 -s /bin/bash noroot \
-    && chown noroot:noroot ${BUILD_PREFIX}
+    && chown -R noroot:noroot ${BUILD_PREFIX}

 USER noroot

--- a/docker/Dockerfile.latest
+++ b/docker/Dockerfile.latest
@@ -0,0 +1,35 @@
+FROM python:3.7.9-alpine
+
+LABEL maintainer="foo@bar.com"
+ARG TZ='Asia/Shanghai'
+
+ARG CHATGPT_ON_WECHAT_VER
+
+ENV BUILD_PREFIX=/app \
+    BUILD_OPEN_AI_API_KEY='YOUR OPEN AI KEY HERE'
+
+COPY chatgpt-on-wechat.tar.gz ./chatgpt-on-wechat.tar.gz
+
+RUN apk add --no-cache \
+        bash \
+    && tar -xf chatgpt-on-wechat.tar.gz \
+    && mv chatgpt-on-wechat ${BUILD_PREFIX} \
+    && cd ${BUILD_PREFIX} \
+    && cp config-template.json ${BUILD_PREFIX}/config.json \
+    && sed -i "2s/YOUR API KEY/${BUILD_OPEN_AI_API_KEY}/" ${BUILD_PREFIX}/config.json \
+    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
+    && pip install --no-cache   \
+        itchat-uos==1.5.0.dev0  \
+        openai
+
+WORKDIR ${BUILD_PREFIX}
+
+ADD ./entrypoint.sh /entrypoint.sh
+
+RUN chmod +x /entrypoint.sh \
+    && adduser -D -h /home/noroot -u 1000 -s /bin/bash noroot \
+    && chown noroot:noroot ${BUILD_PREFIX}
+
+USER noroot
+
+ENTRYPOINT ["/entrypoint.sh"]
--- a/docker/build.latest.sh
+++ b/docker/build.latest.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# move chatgpt-on-wechat
+tar -zcf chatgpt-on-wechat.tar.gz --exclude=../../chatgpt-on-wechat/docker  ../../chatgpt-on-wechat
+
+# build image
+docker build -f Dockerfile.alpine \
+             -t zhayujie/chatgpt-on-wechat .
--- a/main.py
+++ b/main.py
@@ -0,0 +1,5 @@
+# entry point for online railway deployment
+from app import run
+
+if __name__ == '__main__':
+	run()
--- a/plugins/README.md
+++ b/plugins/README.md
@@ -0,0 +1,235 @@
+## 插件化初衷
+
+之前未插件化的代码耦合程度高，如果要定制一些个性化功能（如流量控制、接入`NovelAI`画图平台等），需要了解代码主体，避免影响到其他的功能。在实现多个功能后，不但无法调整功能的优先级顺序，功能的配置项也会变得非常混乱。
+
+此时插件化应声而出。
+
+**插件化**: 在保证主体功能是ChatGPT的前提下，我们推荐将主体功能外的功能利用插件的方式实现。
+
+- [x] 可根据功能需要，下载不同插件。
+- [x] 插件开发成本低，仅需了解插件触发事件，并按照插件定义接口编写插件。
+- [x] 插件化能够自由开关和调整优先级。
+- [x] 每个插件可在插件文件夹内维护独立的配置文件，方便代码的测试和调试，可以在独立的仓库开发插件。
+
+PS: 插件目前仅支持`itchat`
+
+## 插件化实现
+
+插件化实现是在收到消息到发送回复的各个步骤之间插入触发事件实现的。
+
+### 消息处理过程
+
+在了解插件触发事件前，首先需要了解程序收到消息到发送回复的整个过程。
+
+插件化版本中，消息处理过程可以分为4个步骤：
+```
+    1.收到消息 ---> 2.产生回复 ---> 3.包装回复 ---> 4.发送回复
+```
+
+以下是它们的默认处理逻辑(太长不看，可跳过)：
+
+#### 1. 收到消息
+
+负责接收用户消息，根据用户的配置，判断本条消息是否触发机器人。如果触发，则会判断该消息的类型（声音、文本、画图命令等），将消息包装成如下的`Context`交付给下一个步骤。
+
+```python
+    class ContextType (Enum):
+        TEXT = 1         # 文本消息
+        VOICE = 2        # 音频消息
+        IMAGE_CREATE = 3 # 创建图片命令
+    class Context:
+        def __init__(self, type : ContextType = None , content = None,  kwargs = dict()):
+            self.type = type
+            self.content = content
+            self.kwargs = kwargs
+        def __getitem__(self, key):
+            return self.kwargs[key]
+```
+
+`Context`中除了存放消息类型和内容外,还存放了一些与会话相关的参数。
+
+例如，当收到用户私聊消息时，会存放以下的会话参数。
+
+```python
+    context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id}
+```
+
+- `isgroup`: `Context`是否是群聊消息。
+- `msg`: `itchat`中原始的消息对象。
+- `receiver`: 需要回复消息的对象ID。
+- `session_id`: 会话ID(一般是发送触发bot消息的用户ID，如果在群聊中并且`conf`里设置了`group_chat_in_one_session`，那么此处便是群聊ID)
+
+#### 2. 产生回复
+
+处理消息并产生回复。目前默认处理逻辑是根据`Context`的类型交付给对应的bot，并产生回复`Reply`。 如果本步骤没有产生任何回复，那么会跳过之后的所有步骤。
+
+```python
+    if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE:
+        reply = super().build_reply_content(context.content, context) #文字跟画图交付给chatgpt
+    elif context.type == ContextType.VOICE: # 声音先进行语音转文字后，修改Context类型为文字后，再交付给chatgpt
+        msg = context['msg']
+        file_name = TmpDir().path() + context.content
+        msg.download(file_name)
+        reply = super().build_voice_to_text(file_name)
+        if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO:
+            context.content = reply.content # 语音转文字后，将文字内容作为新的context
+            context.type = ContextType.TEXT
+            reply = super().build_reply_content(context.content, context)
+            if reply.type == ReplyType.TEXT:
+                if conf().get('voice_reply_voice'):
+                    reply = super().build_text_to_voice(reply.content)
+```
+
+回复`Reply`的定义如下所示，它允许Bot可以回复多类不同的消息。同时也加入了`INFO`和`ERROR`消息类型区分系统提示和系统错误。
+    
+```python
+    class ReplyType(Enum):
+        TEXT = 1        # 文本
+        VOICE = 2       # 音频文件
+        IMAGE = 3       # 图片文件
+        IMAGE_URL = 4   # 图片URL
+        
+        INFO = 9
+        ERROR = 10
+    class Reply:
+        def __init__(self, type : ReplyType = None , content = None):
+            self.type = type
+            self.content = content
+```
+
+#### 3. 装饰回复
+
+根据`Context`和回复`Reply`的类型，对回复的内容进行装饰。目前的装饰有以下两种:
+
+- `TEXT`文本回复，根据是否在群聊中来决定是艾特接收方还是添加回复的前缀。
+
+- `INFO`或`ERROR`类型，会在消息前添加对应的系统提示字样。
+
+如下是默认逻辑的代码：
+
+```python
+    if reply.type == ReplyType.TEXT:
+        reply_text = reply.content
+        if context['isgroup']:
+            reply_text = '@' +  context['msg']['ActualNickName'] + ' ' + reply_text.strip()
+            reply_text = conf().get("group_chat_reply_prefix", "")+reply_text
+        else:
+            reply_text = conf().get("single_chat_reply_prefix", "")+reply_text
+        reply.content = reply_text
+    elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+        reply.content = str(reply.type)+":\n" + reply.content
+```
+
+#### 4. 发送回复
+
+根据`Reply`的类型，默认逻辑调用不同的发送函数发送回复给接收方`context["receiver"]`。
+
+### 插件触发事件
+
+主程序目前会在各个消息步骤间触发事件，监听相应事件的插件会按照优先级，顺序调用事件处理函数。
+
+目前支持三类触发事件：
+```
+1.收到消息 
+---> `ON_HANDLE_CONTEXT` 
+2.产生回复 
+---> `ON_DECORATE_REPLY` 
+3.装饰回复 
+---> `ON_SEND_REPLY` 
+4.发送回复
+```
+
+触发事件会产生事件的上下文`EventContext`，它包含了以下信息:
+
+`EventContext(Event事件类型, {'channel' : 消息channel, 'context': Context, 'reply': Reply})`
+
+插件处理函数可通过修改`EventContext`中的`context`和`reply`来实现功能。
+
+## 插件编写示例
+
+以`plugins/hello`为例，其中编写了一个简单的`Hello`插件。
+
+### 1. 创建插件
+
+在`plugins`目录下创建一个插件文件夹`hello`。然后，在该文件夹中创建一个与文件夹同名的`.py`文件`hello.py`。
+```
+plugins/
+└── hello
+    ├── __init__.py
+    └── hello.py
+```
+
+### 2. 编写插件类
+
+在`hello.py`文件中，创建插件类，它继承自`Plugin`。
+
+在类定义之前需要使用`@plugins.register`装饰器注册插件，并填写插件的相关信息，其中`desire_priority`表示插件默认的优先级，越大优先级越高。初次加载插件后可在`plugins/plugins.json`中修改插件优先级。
+
+并在`__init__`中绑定你编写的事件处理函数。
+
+`Hello`插件为事件`ON_HANDLE_CONTEXT`绑定了一个处理函数`on_handle_context`，它表示之后每次生成回复前，都会由`on_handle_context`先处理。
+
+PS: `ON_HANDLE_CONTEXT`是最常用的事件，如果要根据不同的消息来生成回复，就用它。
+
+```python
+@plugins.register(name="Hello", desc="A simple plugin that says hello", version="0.1", author="lanvent", desire_priority= -1)
+class Hello(Plugin):
+    def __init__(self):
+        super().__init__()
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        logger.info("[Hello] inited")
+```
+
+### 3. 编写事件处理函数
+
+#### 修改事件上下文
+
+事件处理函数接收一个`EventContext`对象`e_context`作为参数。`e_context`包含了事件相关信息，利用`e_context['key']`来访问这些信息。
+
+`EventContext(Event事件类型, {'channel' : 消息channel, 'context': Context, 'reply': Reply})`
+
+处理函数中通过修改`e_context`对象中的事件相关信息来实现所需功能，比如更改`e_context['reply']`中的内容可以修改回复。
+
+#### 决定是否交付给下个插件或默认逻辑
+
+在处理函数结束时，还需要设置`e_context`对象的`action`属性，它决定如何继续处理事件。目前有以下三种处理方式：
+
+- `EventAction.CONTINUE`: 事件未结束，继续交给下个插件处理，如果没有下个插件，则交付给默认的事件处理逻辑。
+- `EventAction.BREAK`: 事件结束，不再给下个插件处理，交付给默认的处理逻辑。
+- `EventAction.BREAK_PASS`: 事件结束，不再给下个插件处理，跳过默认的处理逻辑。
+
+#### 示例处理函数
+
+`Hello`插件处理`Context`类型为`TEXT`的消息：
+
+- 如果内容是`Hello`，就将回复设置为`Hello+用户昵称`，并跳过之后的插件和默认逻辑。
+- 如果内容是`End`，就将`Context`的类型更改为`IMAGE_CREATE`，并让事件继续，如果最终交付到默认逻辑，会调用默认的画图Bot来画画。
+
+```python
+    def on_handle_context(self, e_context: EventContext):
+        if e_context['context'].type != ContextType.TEXT:
+            return
+        content = e_context['context'].content
+        if content == "Hello":
+            reply = Reply()
+            reply.type = ReplyType.TEXT
+            msg = e_context['context']['msg']
+            if e_context['context']['isgroup']:
+                reply.content = "Hello, " + msg['ActualNickName'] + " from " + msg['User'].get('NickName', "Group")
+            else:
+                reply.content = "Hello, " + msg['User'].get('NickName', "My friend")
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
+        if content == "End":
+            # 如果是文本消息"End"，将请求转换成"IMAGE_CREATE"，并将content设置为"The World"
+            e_context['context'].type = ContextType.IMAGE_CREATE
+            content = "The World"
+            e_context.action = EventAction.CONTINUE  # 事件继续，交付给下个插件或默认逻辑
+```
+
+## 插件设计建议
+
+- 尽情将你想要的个性化功能设计为插件。
+- 一个插件目录建议只注册一个插件类。建议使用单独的仓库维护插件，便于更新。
+- 插件的config文件、使用说明`README.md`、`requirement.txt`等放置在插件目录中。
+- 默认优先级不要超过管理员插件`Godcmd`的优先级(999)，`Godcmd`插件提供了配置管理、插件管理等功能。
--- a/plugins/init.py
+++ b/plugins/init.py
@@ -0,0 +1,9 @@
+from .plugin_manager import PluginManager
+from .event import *
+from .plugin import *
+
+instance = PluginManager()
+
+register                    = instance.register
+# load_plugins                = instance.load_plugins
+# emit_event                  = instance.emit_event
--- a/plugins/banwords/.gitignore
+++ b/plugins/banwords/.gitignore
@@ -0,0 +1 @@
+banwords.txt
--- a/plugins/banwords/README.md
+++ b/plugins/banwords/README.md
@@ -0,0 +1,9 @@
+## 插件描述
+简易的敏感词插件，暂不支持分词，请自行导入词库到插件文件夹中的`banwords.txt`，每行一个词，一个参考词库是[1](https://github.com/cjh0613/tencent-sensitive-words/blob/main/sensitive_words_lines.txt)。
+
+`config.json`中能够填写默认的处理行为，目前行为有：
+- `ignore` : 无视这条消息。
+- `replace` : 将消息中的敏感词替换成"*"，并回复违规。
+
+## 致谢
+搜索功能实现来自https://github.com/toolgood/ToolGood.Words
--- a/plugins/banwords/WordsSearch.py
+++ b/plugins/banwords/WordsSearch.py
@@ -0,0 +1,250 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+# ToolGood.Words.WordsSearch.py
+# 2020, Lin Zhijun, https://github.com/toolgood/ToolGood.Words
+# Licensed under the Apache License 2.0
+# 更新日志
+# 2020.04.06 第一次提交
+# 2020.05.16 修改，支持大于0xffff的字符
+
+__all__ = ['WordsSearch']
+__author__ = 'Lin Zhijun'
+__date__ = '2020.05.16'
+
+class TrieNode():
+    def __init__(self):
+        self.Index = 0
+        self.Index = 0
+        self.Layer = 0
+        self.End = False
+        self.Char = ''
+        self.Results = []
+        self.m_values = {}
+        self.Failure = None
+        self.Parent = None
+
+    def Add(self,c):
+        if c in self.m_values :
+            return self.m_values[c]
+        node = TrieNode()
+        node.Parent = self
+        node.Char = c
+        self.m_values[c] = node
+        return node
+
+    def SetResults(self,index):
+        if (self.End == False):
+            self.End = True
+        self.Results.append(index)
+
+class TrieNode2():
+    def __init__(self):
+        self.End = False
+        self.Results = []
+        self.m_values = {}
+        self.minflag = 0xffff
+        self.maxflag = 0
+
+    def Add(self,c,node3):
+        if (self.minflag > c):
+            self.minflag = c
+        if (self.maxflag < c):
+             self.maxflag = c
+        self.m_values[c] = node3
+
+    def SetResults(self,index):
+        if (self.End == False) :
+            self.End = True
+        if (index in self.Results )==False : 
+            self.Results.append(index)
+
+    def HasKey(self,c):
+        return c in self.m_values
+        
+ 
+    def TryGetValue(self,c):
+        if (self.minflag <= c and self.maxflag >= c):
+            if c in self.m_values:
+                return self.m_values[c]
+        return None
+
+
+class WordsSearch():
+    def __init__(self):
+        self._first = {}
+        self._keywords = []
+        self._indexs=[]
+    
+    def SetKeywords(self,keywords):
+        self._keywords = keywords
+        self._indexs=[]
+        for i in range(len(keywords)):
+            self._indexs.append(i)
+
+        root = TrieNode()
+        allNodeLayer={}
+
+        for i in range(len(self._keywords)): # for (i = 0; i < _keywords.length; i++) 
+            p = self._keywords[i]
+            nd = root
+            for j in range(len(p)): # for (j = 0; j < p.length; j++) 
+                nd = nd.Add(ord(p[j]))
+                if (nd.Layer == 0):
+                    nd.Layer = j + 1
+                    if nd.Layer in allNodeLayer:
+                        allNodeLayer[nd.Layer].append(nd)
+                    else:
+                        allNodeLayer[nd.Layer]=[]
+                        allNodeLayer[nd.Layer].append(nd)
+            nd.SetResults(i)
+
+
+        allNode = []
+        allNode.append(root)
+        for key in allNodeLayer.keys():
+            for nd in allNodeLayer[key]:
+                allNode.append(nd)
+        allNodeLayer=None
+
+        for i in range(len(allNode)): # for (i = 0; i < allNode.length; i++) 
+            if i==0 :
+                continue
+            nd=allNode[i]
+            nd.Index = i
+            r = nd.Parent.Failure
+            c = nd.Char
+            while (r != None and (c in r.m_values)==False):
+                r = r.Failure
+            if (r == None):
+                nd.Failure = root
+            else:
+                nd.Failure = r.m_values[c]
+                for key2 in nd.Failure.Results :
+                    nd.SetResults(key2)
+        root.Failure = root
+
+        allNode2 = []
+        for i in range(len(allNode)): # for (i = 0; i < allNode.length; i++) 
+            allNode2.append( TrieNode2())
+        
+        for i in range(len(allNode2)): # for (i = 0; i < allNode2.length; i++) 
+            oldNode = allNode[i]
+            newNode = allNode2[i]
+
+            for key in oldNode.m_values :
+                index = oldNode.m_values[key].Index
+                newNode.Add(key, allNode2[index])
+            
+            for index in range(len(oldNode.Results)): # for (index = 0; index < oldNode.Results.length; index++) 
+                item = oldNode.Results[index]
+                newNode.SetResults(item)
+            
+            oldNode=oldNode.Failure
+            while oldNode != root:
+                for key in oldNode.m_values :
+                    if (newNode.HasKey(key) == False):
+                        index = oldNode.m_values[key].Index
+                        newNode.Add(key, allNode2[index])
+                for index in range(len(oldNode.Results)): 
+                    item = oldNode.Results[index]
+                    newNode.SetResults(item)
+                oldNode=oldNode.Failure
+        allNode = None
+        root = None
+
+        # first = []
+        # for index in range(65535):# for (index = 0; index < 0xffff; index++) 
+        #     first.append(None)
+        
+        # for key in allNode2[0].m_values :
+        #     first[key] = allNode2[0].m_values[key]
+        
+        self._first = allNode2[0]
+    
+
+    def FindFirst(self,text):
+        ptr = None
+        for index in range(len(text)): # for (index = 0; index < text.length; index++) 
+            t =ord(text[index]) # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn==None):
+                    tn = self._first.TryGetValue(t)
+                
+            
+            if (tn != None):
+                if (tn.End):
+                    item = tn.Results[0]
+                    keyword = self._keywords[item]
+                    return { "Keyword": keyword, "Success": True, "End": index, "Start": index + 1 - len(keyword), "Index": self._indexs[item] }
+            ptr = tn
+        return None
+
+    def FindAll(self,text):
+        ptr = None
+        list = []
+
+        for index in range(len(text)): # for (index = 0; index < text.length; index++) 
+            t =ord(text[index]) # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn==None):
+                    tn = self._first.TryGetValue(t)
+                
+            
+            if (tn != None):
+                if (tn.End):
+                    for j in range(len(tn.Results)): # for (j = 0; j < tn.Results.length; j++) 
+                        item = tn.Results[j]
+                        keyword = self._keywords[item]
+                        list.append({ "Keyword": keyword, "Success": True, "End": index, "Start": index + 1 - len(keyword), "Index": self._indexs[item] })
+            ptr = tn
+        return list
+
+
+    def ContainsAny(self,text):
+        ptr = None
+        for index in range(len(text)): # for (index = 0; index < text.length; index++) 
+            t =ord(text[index]) # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn==None):
+                    tn = self._first.TryGetValue(t)
+            
+            if (tn != None):
+                if (tn.End):
+                    return True
+            ptr = tn
+        return False
+    
+    def Replace(self,text, replaceChar = '*'):
+        result = list(text) 
+
+        ptr = None
+        for i in range(len(text)): # for (i = 0; i < text.length; i++) 
+            t =ord(text[i]) # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn==None):
+                    tn = self._first.TryGetValue(t)
+            
+            if (tn != None):
+                if (tn.End):
+                    maxLength = len( self._keywords[tn.Results[0]])
+                    start = i + 1 - maxLength
+                    for j in range(start,i+1): # for (j = start; j <= i; j++) 
+                        result[j] = replaceChar
+            ptr = tn
+        return ''.join(result) 
--- a/plugins/banwords/init.py
+++ b/plugins/banwords/init.py
--- a/plugins/banwords/banwords.py
+++ b/plugins/banwords/banwords.py
@@ -0,0 +1,66 @@
+# encoding:utf-8
+
+import json
+import os
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+import plugins
+from plugins import *
+from common.log import logger
+from .WordsSearch import WordsSearch
+
+
+@plugins.register(name="Banwords", desc="判断消息中是否有敏感词、决定是否回复。", version="1.0", author="lanvent", desire_priority= 100)
+class Banwords(Plugin):
+    def __init__(self):
+        super().__init__()
+        try:
+            curdir=os.path.dirname(__file__)
+            config_path=os.path.join(curdir,"config.json")
+            conf=None
+            if not os.path.exists(config_path):
+                conf={"action":"ignore"}
+                with open(config_path,"w") as f:
+                    json.dump(conf,f,indent=4)
+            else:
+                with open(config_path,"r") as f:
+                    conf=json.load(f)
+            self.searchr = WordsSearch()
+            self.action = conf["action"]
+            banwords_path = os.path.join(curdir,"banwords.txt")
+            with open(banwords_path, 'r', encoding='utf-8') as f:
+                words=[]
+                for line in f:
+                    word = line.strip()
+                    if word:
+                        words.append(word)
+            self.searchr.SetKeywords(words)
+            self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+            logger.info("[Banwords] inited")
+        except Exception as e:
+            logger.warn("Banwords init failed: %s" % e)
+        
+
+
+    def on_handle_context(self, e_context: EventContext):
+
+        if e_context['context'].type not in [ContextType.TEXT,ContextType.IMAGE_CREATE]:
+            return
+        
+        content = e_context['context'].content
+        logger.debug("[Banwords] on_handle_context. content: %s" % content)
+        if self.action == "ignore":
+            f = self.searchr.FindFirst(content)
+            if f:
+                logger.info("Banwords: %s" % f["Keyword"])
+                e_context.action = EventAction.BREAK_PASS
+                return
+        elif self.action == "replace":
+            if self.searchr.ContainsAny(content):
+                reply = Reply(ReplyType.INFO, "发言中包含敏感词，请重试: \n"+self.searchr.Replace(content))
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS
+                return
+            
+    def get_help_text(self, **kwargs):
+        return Banwords.desc
--- a/plugins/banwords/banwords.txt.template
+++ b/plugins/banwords/banwords.txt.template
@@ -0,0 +1,3 @@
+nipples
+pennis
+法轮功
--- a/plugins/banwords/config.json.template
+++ b/plugins/banwords/config.json.template
@@ -0,0 +1,3 @@
+{
+    "action": "ignore"
+}
--- a/plugins/dungeon/README.md
+++ b/plugins/dungeon/README.md
@@ -0,0 +1,4 @@
+玩地牢游戏的聊天插件，触发方法如下：
+
+- `$开始冒险 <背景故事>` - 以<背景故事>开始一个地牢游戏，不填写会使用默认背景故事。之后聊天中你的所有消息会帮助ai完善这个故事。
+- `$停止冒险` - 停止一个地牢游戏，回归正常的ai。
--- a/plugins/dungeon/init.py
+++ b/plugins/dungeon/init.py
--- a/plugins/dungeon/dungeon.py
+++ b/plugins/dungeon/dungeon.py
@@ -0,0 +1,86 @@
+# encoding:utf-8
+
+from bridge.bridge import Bridge
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.expired_dict import ExpiredDict
+from config import conf
+import plugins
+from plugins import *
+from common.log import logger
+from common import const
+
+# https://github.com/bupticybee/ChineseAiDungeonChatGPT
+class StoryTeller():
+    def __init__(self, bot, sessionid, story):
+        self.bot = bot
+        self.sessionid = sessionid
+        bot.sessions.clear_session(sessionid)
+        self.first_interact = True
+        self.story = story
+
+    def reset(self):
+        self.bot.sessions.clear_session(self.sessionid)
+        self.first_interact = True
+
+    def action(self, user_action):
+        if user_action[-1] != "。":
+            user_action = user_action + "。"
+        if self.first_interact:
+            prompt = """现在来充当一个冒险文字游戏，描述时候注意节奏，不要太快，仔细描述各个人物的心情和周边环境。一次只需写四到六句话。
+            开头是，""" + self.story + " " + user_action
+            self.first_interact = False
+        else:
+            prompt = """继续，一次只需要续写四到六句话，总共就只讲5分钟内发生的事情。""" + user_action
+        return prompt
+    
+
+@plugins.register(name="Dungeon", desc="A plugin to play dungeon game", version="1.0", author="lanvent", desire_priority= 0)
+class Dungeon(Plugin):
+    def __init__(self):
+        super().__init__()
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        logger.info("[Dungeon] inited")
+        # 目前没有设计session过期事件，这里先暂时使用过期字典
+        if conf().get('expires_in_seconds'):
+            self.games = ExpiredDict(conf().get('expires_in_seconds'))
+        else:
+            self.games = dict()
+
+    def on_handle_context(self, e_context: EventContext):
+
+        if e_context['context'].type != ContextType.TEXT:
+            return
+        bottype = Bridge().get_bot_type("chat")
+        if bottype != const.CHATGPT:
+            return
+        bot = Bridge().get_bot("chat")
+        content = e_context['context'].content[:]
+        clist = e_context['context'].content.split(maxsplit=1)
+        sessionid = e_context['context']['session_id']
+        logger.debug("[Dungeon] on_handle_context. content: %s" % clist)
+        if clist[0] == "$停止冒险":
+            if sessionid in self.games:
+                self.games[sessionid].reset()
+                del self.games[sessionid]
+                reply = Reply(ReplyType.INFO, "冒险结束!")
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS
+        elif clist[0] == "$开始冒险" or sessionid in self.games:
+            if sessionid not in self.games or clist[0] == "$开始冒险":
+                if len(clist)>1 :
+                    story = clist[1]
+                else:
+                    story = "你在树林里冒险，指不定会从哪里蹦出来一些奇怪的东西，你握紧手上的手枪，希望这次冒险能够找到一些值钱的东西，你往树林深处走去。"
+                self.games[sessionid] = StoryTeller(bot, sessionid, story)
+                reply = Reply(ReplyType.INFO, "冒险开始，你可以输入任意内容，让故事继续下去。故事背景是：" + story)
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
+            else:
+                prompt = self.games[sessionid].action(content)
+                e_context['context'].type = ContextType.TEXT
+                e_context['context'].content = prompt
+                e_context.action = EventAction.BREAK # 事件结束，不跳过处理context的默认逻辑
+    def get_help_text(self, **kwargs):
+        help_text = "输入\"$开始冒险 {背景故事}\"来以{背景故事}开始一个地牢游戏，之后你的所有消息会帮助我来完善这个故事。输入\"$停止冒险 \"可以结束游戏。"
+        return help_text
--- a/plugins/event.py
+++ b/plugins/event.py
@@ -0,0 +1,49 @@
+# encoding:utf-8
+
+from enum import Enum
+
+
+class Event(Enum):
+    # ON_RECEIVE_MESSAGE = 1  # 收到消息
+
+    ON_HANDLE_CONTEXT = 2   # 处理消息前
+    """
+    e_context = {  "channel": 消息channel, "context" : 本次消息的context, "reply" : 目前的回复，初始为空  }
+    """
+
+    ON_DECORATE_REPLY = 3   # 得到回复后准备装饰
+    """
+    e_context = {  "channel": 消息channel, "context" : 本次消息的context, "reply" : 目前的回复 }
+    """
+
+    ON_SEND_REPLY = 4       # 发送回复前
+    """
+    e_context = {  "channel": 消息channel, "context" : 本次消息的context, "reply" : 目前的回复 }
+    """
+
+    # AFTER_SEND_REPLY = 5    # 发送回复后
+
+
+class EventAction(Enum):
+    CONTINUE = 1            # 事件未结束，继续交给下个插件处理，如果没有下个插件，则交付给默认的事件处理逻辑
+    BREAK = 2               # 事件结束，不再给下个插件处理，交付给默认的事件处理逻辑
+    BREAK_PASS = 3          # 事件结束，不再给下个插件处理，不交付给默认的事件处理逻辑
+
+
+class EventContext:
+    def __init__(self, event, econtext=dict()):
+        self.event = event
+        self.econtext = econtext
+        self.action = EventAction.CONTINUE
+
+    def __getitem__(self, key):
+        return self.econtext[key]
+
+    def __setitem__(self, key, value):
+        self.econtext[key] = value
+
+    def __delitem__(self, key):
+        del self.econtext[key]
+
+    def is_pass(self):
+        return self.action == EventAction.BREAK_PASS
--- a/plugins/godcmd/README.md
+++ b/plugins/godcmd/README.md
@@ -0,0 +1,12 @@
+## 插件说明
+
+指令插件
+
+## 插件使用
+
+将`config.json.template`复制为`config.json`，并修改其中`password`的值为口令。
+
+在私聊中可使用`#auth`指令，输入口令进行管理员认证，详细指令请输入`#help`查看帮助文档：
+
+`#auth <口令>` - 管理员认证。
+`#help` - 输出帮助文档，是否是管理员和是否是在群聊中会影响帮助文档的输出内容。
--- a/plugins/godcmd/init.py
+++ b/plugins/godcmd/init.py
--- a/plugins/godcmd/config.json.template
+++ b/plugins/godcmd/config.json.template
@@ -0,0 +1,4 @@
+{
+    "password": "",
+    "admin_users": []
+}
--- a/plugins/godcmd/godcmd.py
+++ b/plugins/godcmd/godcmd.py
@@ -0,0 +1,307 @@
+# encoding:utf-8
+
+import json
+import os
+import traceback
+from typing import Tuple
+from bridge.bridge import Bridge
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from config import load_config
+import plugins
+from plugins import *
+from common import const
+from common.log import logger
+
+# 定义指令集
+COMMANDS = {
+    "help": {
+        "alias": ["help", "帮助"],
+        "desc": "打印指令集合",
+    },
+    "helpp": {
+        "alias": ["helpp", "插件帮助"],
+        "args": ["插件名"],
+        "desc": "打印插件的帮助信息",
+    },
+    "auth": {
+        "alias": ["auth", "认证"],
+        "args": ["口令"],
+        "desc": "管理员认证",
+    },
+    # "id": {
+    #     "alias": ["id", "用户"],
+    #     "desc": "获取用户id", #目前无实际意义
+    # },
+    "reset": {
+        "alias": ["reset", "重置会话"],
+        "desc": "重置会话",
+    },
+}
+
+ADMIN_COMMANDS = {
+    "resume": {
+        "alias": ["resume", "恢复服务"],
+        "desc": "恢复服务",
+    },
+    "stop": {
+        "alias": ["stop", "暂停服务"],
+        "desc": "暂停服务",
+    },
+    "reconf": {
+        "alias": ["reconf", "重载配置"],
+        "desc": "重载配置(不包含插件配置)",
+    },
+    "resetall": {
+        "alias": ["resetall", "重置所有会话"],
+        "desc": "重置所有会话",
+    },
+    "scanp": {
+        "alias": ["scanp", "扫描插件"],
+        "desc": "扫描插件目录是否有新插件",
+    },
+    "plist": {
+        "alias": ["plist", "插件"],
+        "desc": "打印当前插件列表",
+    },
+    "setpri": {
+        "alias": ["setpri", "设置插件优先级"],
+        "args": ["插件名", "优先级"],
+        "desc": "设置指定插件的优先级，越大越优先",
+    },
+    "reloadp": {
+        "alias": ["reloadp", "重载插件"],
+        "args": ["插件名"],
+        "desc": "重载指定插件配置",
+    },
+    "enablep": {
+        "alias": ["enablep", "启用插件"],
+        "args": ["插件名"],
+        "desc": "启用指定插件",
+    },
+    "disablep": {
+        "alias": ["disablep", "禁用插件"],
+        "args": ["插件名"],
+        "desc": "禁用指定插件",
+    },
+    "debug": {
+        "alias": ["debug", "调试模式", "DEBUG"],
+        "desc": "开启机器调试日志",
+    },
+}
+# 定义帮助函数
+def get_help_text(isadmin, isgroup):
+    help_text = "可用指令：\n"
+    for cmd, info in COMMANDS.items():
+        if cmd=="auth" and (isadmin or isgroup): # 群聊不可认证
+            continue
+
+        alias=["#"+a for a in info['alias']]
+        help_text += f"{','.join(alias)} "
+        if 'args' in info:
+            args=["{"+a+"}" for a in info['args']]
+            help_text += f"{' '.join(args)} "
+        help_text += f": {info['desc']}\n"
+    if ADMIN_COMMANDS and isadmin:
+        help_text += "\n管理员指令：\n"
+        for cmd, info in ADMIN_COMMANDS.items():
+            alias=["#"+a for a in info['alias']]
+            help_text += f"{','.join(alias)} "
+            help_text += f": {info['desc']}\n"
+    return help_text
+
+@plugins.register(name="Godcmd", desc="为你的机器人添加指令集，有用户和管理员两种角色，加载顺序请放在首位，初次运行后插件目录会生成配置文件, 填充管理员密码后即可认证", version="1.0", author="lanvent", desire_priority= 999)
+class Godcmd(Plugin):
+
+    def __init__(self):
+        super().__init__()
+
+        curdir=os.path.dirname(__file__)
+        config_path=os.path.join(curdir,"config.json")
+        gconf=None
+        if not os.path.exists(config_path):
+            gconf={"password":"","admin_users":[]}
+            with open(config_path,"w") as f:
+                json.dump(gconf,f,indent=4)
+        else:
+            with open(config_path,"r") as f:
+                gconf=json.load(f)
+                
+        self.password = gconf["password"]
+        self.admin_users = gconf["admin_users"] # 预存的管理员账号，这些账号不需要认证 TODO: 用户名每次都会变，目前不可用
+        self.isrunning = True # 机器人是否运行中
+
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        logger.info("[Godcmd] inited")
+
+    
+    def on_handle_context(self, e_context: EventContext):
+        context_type = e_context['context'].type
+        if context_type != ContextType.TEXT:
+            if not self.isrunning:
+                e_context.action = EventAction.BREAK_PASS
+            return
+        
+        content = e_context['context'].content
+        logger.debug("[Godcmd] on_handle_context. content: %s" % content)
+        if content.startswith("#"):
+            # msg = e_context['context']['msg']
+            user = e_context['context']['receiver']
+            session_id = e_context['context']['session_id']
+            isgroup = e_context['context']['isgroup']
+            bottype = Bridge().get_bot_type("chat")
+            bot = Bridge().get_bot("chat")
+            # 将命令和参数分割
+            command_parts = content[1:].split(" ")
+            cmd = command_parts[0]
+            args = command_parts[1:]
+            isadmin=False
+            if user in self.admin_users:
+                isadmin=True
+            ok=False
+            result="string"
+            if any(cmd in info['alias'] for info in COMMANDS.values()):
+                cmd = next(c for c, info in COMMANDS.items() if cmd in info['alias'])
+                if cmd == "auth":
+                    ok, result = self.authenticate(user, args, isadmin, isgroup)
+                elif cmd == "help":
+                    ok, result = True, get_help_text(isadmin, isgroup)
+                elif cmd == "helpp":
+                    if len(args) != 1:
+                        ok, result = False, "请提供插件名"
+                    else:
+                        plugins = PluginManager().list_plugins()
+                        name = args[0].upper()
+                        if name in plugins and plugins[name].enabled:
+                            ok, result = True, PluginManager().instances[name].get_help_text(isgroup=isgroup, isadmin=isadmin)
+                        else:
+                            ok, result= False, "插件不存在或未启用"
+                elif cmd == "id":
+                    ok, result = True, f"用户id=\n{user}"
+                elif cmd == "reset":
+                    if bottype == const.CHATGPT:
+                        bot.sessions.clear_session(session_id)
+                        ok, result = True, "会话已重置"
+                    else:
+                        ok, result = False, "当前对话机器人不支持重置会话"
+                logger.debug("[Godcmd] command: %s by %s" % (cmd, user))
+            elif any(cmd in info['alias'] for info in ADMIN_COMMANDS.values()):
+                if isadmin:
+                    if isgroup:
+                        ok, result = False, "群聊不可执行管理员指令"
+                    else:
+                        cmd = next(c for c, info in ADMIN_COMMANDS.items() if cmd in info['alias'])
+                        if cmd == "stop":
+                            self.isrunning = False
+                            ok, result = True, "服务已暂停"
+                        elif cmd == "resume":
+                            self.isrunning = True
+                            ok, result = True, "服务已恢复"
+                        elif cmd == "reconf":
+                            load_config()
+                            ok, result = True, "配置已重载"
+                        elif cmd == "resetall":
+                            if bottype == const.CHATGPT:
+                                bot.sessions.clear_all_session()
+                                ok, result = True, "重置所有会话成功"
+                            else:
+                                ok, result = False, "当前对话机器人不支持重置会话"
+                        elif cmd == "debug":
+                            logger.setLevel('DEBUG')
+                            ok, result = True, "DEBUG模式已开启"
+                        elif cmd == "plist":
+                            plugins = PluginManager().list_plugins()
+                            ok = True
+                            result = "插件列表：\n"
+                            for name,plugincls in plugins.items():
+                                result += f"{plugincls.name}_v{plugincls.version} {plugincls.priority} - "
+                                if plugincls.enabled:
+                                    result += "已启用\n"
+                                else:
+                                    result += "未启用\n"
+                        elif cmd == "scanp":
+                            new_plugins = PluginManager().scan_plugins()
+                            ok, result = True, "插件扫描完成"
+                            PluginManager().activate_plugins()
+                            if len(new_plugins) >0 :
+                                result += "\n发现新插件：\n"
+                                result += "\n".join([f"{p.name}_v{p.version}" for p in new_plugins])
+                            else :
+                                result +=", 未发现新插件"
+                        elif cmd == "setpri":
+                            if len(args) != 2:
+                                ok, result = False, "请提供插件名和优先级"
+                            else:
+                                ok = PluginManager().set_plugin_priority(args[0], int(args[1]))
+                                if ok:
+                                    result = "插件" + args[0] + "优先级已设置为" + args[1]
+                                else:
+                                    result = "插件不存在"
+                        elif cmd == "reloadp":
+                            if len(args) != 1:
+                                ok, result = False, "请提供插件名"
+                            else:
+                                ok = PluginManager().reload_plugin(args[0])
+                                if ok:
+                                    result = "插件配置已重载"
+                                else:
+                                    result = "插件不存在"
+                        elif cmd == "enablep":
+                            if len(args) != 1:
+                                ok, result = False, "请提供插件名"
+                            else:
+                                ok = PluginManager().enable_plugin(args[0])
+                                if ok:
+                                    result = "插件已启用"
+                                else:
+                                    result = "插件不存在"
+                        elif cmd == "disablep":
+                            if len(args) != 1:
+                                ok, result = False, "请提供插件名"
+                            else:
+                                ok = PluginManager().disable_plugin(args[0])
+                                if ok:
+                                    result = "插件已禁用"
+                                else:
+                                    result = "插件不存在"
+
+                        logger.debug("[Godcmd] admin command: %s by %s" % (cmd, user))
+                else:
+                    ok, result = False, "需要管理员权限才能执行该指令"
+            else:
+                ok, result = False, f"未知指令：{cmd}\n查看指令列表请输入#help \n"
+            
+            reply = Reply()
+            if ok:
+                reply.type = ReplyType.INFO
+            else:
+                reply.type = ReplyType.ERROR
+            reply.content = result
+            e_context['reply'] = reply
+
+            e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
+        elif not self.isrunning:
+            e_context.action = EventAction.BREAK_PASS
+    
+    def authenticate(self, userid, args, isadmin, isgroup) -> Tuple[bool,str] : 
+        if isgroup:
+            return False,"请勿在群聊中认证"
+        
+        if isadmin:
+            return False,"管理员账号无需认证"
+        
+        if len(self.password) == 0:
+            return False,"未设置口令，无法认证"
+        
+        if len(args) != 1:
+            return False,"请提供口令"
+        
+        password = args[0]
+        if password == self.password:
+            self.admin_users.append(userid)
+            return True,"认证成功"
+        else:
+            return False,"认证失败"
+
+    def get_help_text(self, isadmin = False, isgroup = False, **kwargs):
+        return get_help_text(isadmin, isgroup)
--- a/plugins/hello/init.py
+++ b/plugins/hello/init.py
--- a/plugins/hello/hello.py
+++ b/plugins/hello/hello.py
@@ -0,0 +1,50 @@
+# encoding:utf-8
+
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+import plugins
+from plugins import *
+from common.log import logger
+
+
+@plugins.register(name="Hello", desc="A simple plugin that says hello", version="0.1", author="lanvent", desire_priority= -1)
+class Hello(Plugin):
+    def __init__(self):
+        super().__init__()
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        logger.info("[Hello] inited")
+
+    def on_handle_context(self, e_context: EventContext):
+
+        if e_context['context'].type != ContextType.TEXT:
+            return
+        
+        content = e_context['context'].content
+        logger.debug("[Hello] on_handle_context. content: %s" % content)
+        if content == "Hello":
+            reply = Reply()
+            reply.type = ReplyType.TEXT
+            msg = e_context['context']['msg']
+            if e_context['context']['isgroup']:
+                reply.content = "Hello, " + msg['ActualNickName'] + " from " + msg['User'].get('NickName', "Group")
+            else:
+                reply.content = "Hello, " + msg['User'].get('NickName', "My friend")
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS # 事件结束，并跳过处理context的默认逻辑
+
+        if content == "Hi":
+            reply = Reply()
+            reply.type = ReplyType.TEXT
+            reply.content = "Hi"
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑，一般会覆写reply
+
+        if content == "End":
+            # 如果是文本消息"End"，将请求转换成"IMAGE_CREATE"，并将content设置为"The World"
+            e_context['context'].type = ContextType.IMAGE_CREATE
+            content = "The World"
+            e_context.action = EventAction.CONTINUE  # 事件继续，交付给下个插件或默认逻辑
+
+    def get_help_text(self, **kwargs):
+        help_text = "输入Hello，我会回复你的名字\n输入End，我会回复你世界的图片\n"
+        return help_text
--- a/plugins/plugin.py
+++ b/plugins/plugin.py
@@ -0,0 +1,6 @@
+class Plugin:
+    def __init__(self):
+        self.handlers = {}
+
+    def get_help_text(self, **kwargs):
+        return "暂无帮助信息"
--- a/plugins/plugin_manager.py
+++ b/plugins/plugin_manager.py
@@ -0,0 +1,175 @@
+# encoding:utf-8
+
+import importlib
+import json
+import os
+from common.singleton import singleton
+from common.sorted_dict import SortedDict
+from .event import *
+from common.log import logger
+from config import conf
+
+
+@singleton
+class PluginManager:
+    def __init__(self):
+        self.plugins = SortedDict(lambda k,v: v.priority,reverse=True)
+        self.listening_plugins = {}
+        self.instances = {}
+        self.pconf = {}
+
+    def register(self, name: str, desc: str, version: str, author: str, desire_priority: int = 0):
+        def wrapper(plugincls):
+            plugincls.name = name
+            plugincls.desc = desc
+            plugincls.version = version
+            plugincls.author = author
+            plugincls.priority = desire_priority
+            plugincls.enabled = True
+            self.plugins[name.upper()] = plugincls
+            logger.info("Plugin %s_v%s registered" % (name, version))
+            return plugincls
+        return wrapper
+
+    def save_config(self):
+        with open("./plugins/plugins.json", "w", encoding="utf-8") as f:
+            json.dump(self.pconf, f, indent=4, ensure_ascii=False)
+
+    def load_config(self):
+        logger.info("Loading plugins config...")
+
+        modified = False
+        if os.path.exists("./plugins/plugins.json"):
+            with open("./plugins/plugins.json", "r", encoding="utf-8") as f:
+                pconf = json.load(f)
+                pconf['plugins'] = SortedDict(lambda k,v: v["priority"],pconf['plugins'],reverse=True)
+        else:
+            modified = True
+            pconf = {"plugins": SortedDict(lambda k,v: v["priority"],reverse=True)}
+        self.pconf = pconf
+        if modified:
+            self.save_config()
+        return pconf
+
+    def scan_plugins(self):
+        logger.info("Scaning plugins ...")
+        plugins_dir = "./plugins"
+        for plugin_name in os.listdir(plugins_dir):
+            plugin_path = os.path.join(plugins_dir, plugin_name)
+            if os.path.isdir(plugin_path):
+                # 判断插件是否包含同名.py文件
+                main_module_path = os.path.join(plugin_path, plugin_name+".py")
+                if os.path.isfile(main_module_path):
+                    # 导入插件
+                    import_path = "plugins.{}.{}".format(plugin_name, plugin_name)
+                    try:
+                        main_module = importlib.import_module(import_path)
+                    except Exception as e:
+                        logger.warn("Failed to import plugin %s: %s" % (plugin_name, e))
+                        continue
+        pconf = self.pconf
+        new_plugins = []
+        modified = False
+        for name, plugincls in self.plugins.items():
+            rawname = plugincls.name
+            if rawname not in pconf["plugins"]:
+                new_plugins.append(plugincls)
+                modified = True
+                logger.info("Plugin %s not found in pconfig, adding to pconfig..." % name)
+                pconf["plugins"][rawname] = {"enabled": plugincls.enabled, "priority": plugincls.priority}
+            else:
+                self.plugins[name].enabled = pconf["plugins"][rawname]["enabled"]
+                self.plugins[name].priority = pconf["plugins"][rawname]["priority"]
+                self.plugins._update_heap(name) # 更新下plugins中的顺序
+        if modified:
+            self.save_config()
+        return new_plugins
+
+    def refresh_order(self):
+        for event in self.listening_plugins.keys():
+            self.listening_plugins[event].sort(key=lambda name: self.plugins[name].priority, reverse=True)
+
+    def activate_plugins(self): # 生成新开启的插件实例
+        for name, plugincls in self.plugins.items():
+            if plugincls.enabled:
+                if name not in self.instances:
+                    instance = plugincls()
+                    self.instances[name] = instance
+                    for event in instance.handlers:
+                        if event not in self.listening_plugins:
+                            self.listening_plugins[event] = []
+                        self.listening_plugins[event].append(name)
+        self.refresh_order()
+
+    def reload_plugin(self, name:str):
+        name = name.upper()
+        if name in self.instances:
+            for event in self.listening_plugins:
+                if name in self.listening_plugins[event]:
+                    self.listening_plugins[event].remove(name)
+            del self.instances[name]
+            self.activate_plugins()
+            return True
+        return False
+    
+    def load_plugins(self):
+        self.load_config()
+        self.scan_plugins()
+        pconf = self.pconf
+        logger.debug("plugins.json config={}".format(pconf))
+        for name,plugin in pconf["plugins"].items():
+            if name.upper() not in self.plugins:
+                logger.error("Plugin %s not found, but found in plugins.json" % name)
+        self.activate_plugins()
+
+    def emit_event(self, e_context: EventContext, *args, **kwargs):
+        if e_context.event in self.listening_plugins:
+            for name in self.listening_plugins[e_context.event]:
+                if self.plugins[name].enabled and e_context.action == EventAction.CONTINUE:
+                    logger.debug("Plugin %s triggered by event %s" % (name,e_context.event))
+                    instance = self.instances[name]
+                    instance.handlers[e_context.event](e_context, *args, **kwargs)
+        return e_context
+
+    def set_plugin_priority(self, name:str, priority:int):
+        name = name.upper()
+        if name not in self.plugins:
+            return False
+        if self.plugins[name].priority == priority:
+            return True
+        self.plugins[name].priority = priority
+        self.plugins._update_heap(name)
+        rawname = self.plugins[name].name
+        self.pconf["plugins"][rawname]["priority"] = priority
+        self.pconf["plugins"]._update_heap(rawname)
+        self.save_config()
+        self.refresh_order()
+        return True
+
+    def enable_plugin(self, name:str):
+        name = name.upper()
+        if name not in self.plugins:
+            return False
+        if not self.plugins[name].enabled :
+            self.plugins[name].enabled = True
+            rawname = self.plugins[name].name
+            self.pconf["plugins"][rawname]["enabled"] = True
+            self.save_config()
+            self.activate_plugins()
+            return True
+        return True
+    
+    def disable_plugin(self, name:str):
+        name = name.upper()
+        if name not in self.plugins:
+            return False
+        if self.plugins[name].enabled :
+            self.plugins[name].enabled = False
+            rawname = self.plugins[name].name
+            self.pconf["plugins"][rawname]["enabled"] = False
+            self.save_config()
+            return True
+        return True
+    
+    def list_plugins(self):
+        return self.plugins
--- a/plugins/role/README.md
+++ b/plugins/role/README.md
@@ -0,0 +1,26 @@
+用于让Bot扮演指定角色的聊天插件，触发方法如下：
+
+- `$角色/$role help/帮助` - 打印目前支持的角色列表。
+- `$角色/$role <角色名>` - 让AI扮演该角色，角色名支持模糊匹配。
+- `$停止扮演` - 停止角色扮演。
+
+添加自定义角色请在`roles/roles.json`中添加。
+
+(大部分prompt来自https://github.com/rockbenben/ChatGPT-Shortcut/blob/main/src/data/users.tsx)
+
+以下为例子:
+```json
+    {
+      "title": "写作助理",
+      "description": "As a writing improvement assistant, your task is to improve the spelling, grammar, clarity, concision, and overall readability of the text I provided, while breaking down long sentences, reducing repetition, and providing suggestions for improvement. Please provide only the corrected Chinese version of the text and avoid including explanations. Please treat every message I send later as text content.",
+      "descn": "作为一名中文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，同时分解长句，减少重复，并提供改进建议。请只提供文本的更正版本，避免包括解释。请把我之后的每一条消息都当作文本内容。",
+      "wrapper": "内容是:\n\"%s\"",
+      "remark": "最常使用的角色，用于优化文本的语法、清晰度和简洁度，提高可读性。"
+    }
+```
+
+- `title`: 角色名。
+- `description`: 使用`$role`触发时，使用英语prompt。
+- `descn`: 使用`$角色`触发时，使用中文prompt。
+- `wrapper`: 用于包装用户消息，可起到强调作用，避免回复离题。
+- `remark`: 简短描述该角色，在打印帮助文档时显示。
--- a/plugins/role/init.py
+++ b/plugins/role/init.py
--- a/plugins/role/role.py
+++ b/plugins/role/role.py
@@ -0,0 +1,126 @@
+# encoding:utf-8
+
+import json
+import os
+from bridge.bridge import Bridge
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common import const
+import plugins
+from plugins import *
+from common.log import logger
+
+
+class RolePlay():
+    def __init__(self, bot, sessionid, desc, wrapper=None):
+        self.bot = bot
+        self.sessionid = sessionid
+        self.wrapper = wrapper or "%s"  # 用于包装用户输入
+        self.desc = desc
+
+    def reset(self):
+        self.bot.sessions.clear_session(self.sessionid)
+
+    def action(self, user_action):
+        session = self.bot.sessions.build_session(self.sessionid, self.desc)
+        if session[0]['role'] == 'system' and session[0]['content'] != self.desc: # 目前没有触发session过期事件，这里先简单判断，然后重置
+            self.reset()
+            self.bot.sessions.build_session(self.sessionid, self.desc)
+        prompt = self.wrapper % user_action
+        return prompt
+
+@plugins.register(name="Role", desc="为你的Bot设置预设角色", version="1.0", author="lanvent", desire_priority= 0)
+class Role(Plugin):
+    def __init__(self):
+        super().__init__()
+        curdir = os.path.dirname(__file__)
+        config_path = os.path.join(curdir, "roles.json")
+        try:
+            with open(config_path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+                self.roles = {role["title"].lower(): role for role in config["roles"]}
+            if len(self.roles) == 0:
+                raise Exception("no role found")
+            self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+            self.roleplays = {}
+            logger.info("[Role] inited")
+        except FileNotFoundError:
+            logger.error(f"[Role] init failed, {config_path} not found")
+        except Exception as e:
+            logger.error("[Role] init failed, exception: %s" % e)
+
+    def get_role(self, name, find_closest=True):
+        name = name.lower()
+        found_role = None
+        if name in self.roles:
+            found_role = name
+        elif find_closest:
+            import difflib
+
+            def str_simularity(a, b):
+                return difflib.SequenceMatcher(None, a, b).ratio()
+            max_sim = 0.0
+            max_role = None
+            for role in self.roles:
+                sim = str_simularity(name, role)
+                if sim >= max_sim:
+                    max_sim = sim
+                    max_role = role
+            found_role = max_role
+        return found_role
+
+    def on_handle_context(self, e_context: EventContext):
+
+        if e_context['context'].type != ContextType.TEXT:
+            return
+        bottype = Bridge().get_bot_type("chat")
+        if bottype != const.CHATGPT:
+            return
+        bot = Bridge().get_bot("chat")
+        content = e_context['context'].content[:]
+        clist = e_context['context'].content.split(maxsplit=1)
+        desckey = None
+        sessionid = e_context['context']['session_id']
+        if clist[0] == "$停止扮演":
+            if sessionid in self.roleplays:
+                self.roleplays[sessionid].reset()
+                del self.roleplays[sessionid]
+            reply = Reply(ReplyType.INFO, "角色扮演结束!")
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS
+            return
+        elif clist[0] == "$角色":
+            desckey = "descn"
+        elif clist[0].lower() == "$role":
+            desckey = "description"
+        elif sessionid not in self.roleplays:
+            return
+        logger.debug("[Role] on_handle_context. content: %s" % content)
+        if desckey is not None:
+            if len(clist) == 1 or (len(clist) > 1 and clist[1].lower() in ["help", "帮助"]):
+                reply = Reply(ReplyType.INFO, self.get_help_text())
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS
+                return
+            role = self.get_role(clist[1])
+            if role is None:
+                reply = Reply(ReplyType.ERROR, "角色不存在")
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS
+                return
+            else:
+                self.roleplays[sessionid] = RolePlay(bot, sessionid, self.roles[role][desckey], self.roles[role].get("wrapper","%s"))
+                reply = Reply(ReplyType.INFO, f"角色设定为 {role} :\n"+self.roles[role][desckey])
+                e_context['reply'] = reply
+                e_context.action = EventAction.BREAK_PASS
+        else:
+            prompt = self.roleplays[sessionid].action(content)
+            e_context['context'].type = ContextType.TEXT
+            e_context['context'].content = prompt
+            e_context.action = EventAction.BREAK
+
+    def get_help_text(self, **kwargs):
+        help_text = "输入\"$角色 {角色名}\"或\"$role {角色名}\"为我设定角色吧，\"$停止扮演 \" 可以清除设定的角色。\n\n目前可用角色列表：\n"
+        for role in self.roles:
+            help_text += f"[{role}]: {self.roles[role]['remark']}\n"
+        return help_text
--- a/plugins/role/roles.json
+++ b/plugins/role/roles.json
@@ -0,0 +1,186 @@
+{
+    "roles":[
+    {
+      "title": "英语翻译或修改",
+      "description": "I want you to act as an English translator, spelling corrector and improver. I will speak to you in any language and you will detect the language, translate it and answer in the corrected and improved version of my text, in English. I want you to replace my simplified A0-level words and sentences with more beautiful and elegant, upper level English words and sentences. Keep the meaning same, but make them more literary. I want you to only reply the correction, the improvements and nothing else, do not write explanations. Please treat every message I send later as text content",
+      "descn": "我希望你能充当英语翻译、拼写纠正者和改进者。我将用任何语言与你交谈，你将检测语言，翻译它，并在我的文本的更正和改进版本中用英语回答。我希望你用更漂亮、更优雅、更高级的英语单词和句子来取代我的简化 A0 级单词和句子。保持意思不变，但让它们更有文学性。我希望你只回答更正，改进，而不是其他，不要写解释。请把我之后的每一条消息都当作文本内容。",
+      "wrapper": "你要翻译或纠正的内容是:\n\"%s\"",
+      "remark": "将其他语言翻译成英文，或改进你提供的英文句子。"
+    },
+    {
+      "title": "写作助理",
+      "description": "As a writing improvement assistant, your task is to improve the spelling, grammar, clarity, concision, and overall readability of the text I provided, while breaking down long sentences, reducing repetition, and providing suggestions for improvement. Please provide only the corrected Chinese version of the text and avoid including explanations. Please treat every message I send later as text content.",
+      "descn": "作为一名中文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，同时分解长句，减少重复，并提供改进建议。请只提供文本的更正版本，避免包括解释。请把我之后的每一条消息都当作文本内容。",
+      "wrapper": "内容是:\n\"%s\"",
+      "remark": "最常使用的角色，用于优化文本的语法、清晰度和简洁度，提高可读性。"
+    },
+    {
+      "title": "语言输入优化",
+      "description": "Using concise and clear language, please edit the passage I provide to improve its logical flow, eliminate any typographical errors and respond in Chinese. Be sure to maintain the original meaning of the text. Please treat every message I send later as text content.",
+      "descn": "请用简洁明了的语言，编辑我给出的段落，以改善其逻辑流程，消除任何印刷错误，并以中文作答。请务必保持文章的原意。请把我之后的每一条消息当作文本内容。",
+      "wrapper": "文本内容是:\n\"%s\"",
+      "remark": "通常用于语音识别信息转书面语言。"
+    },
+    {
+      "title": "论文式回答",
+      "description": "From now on, please write a highly detailed essay with introduction, body, and conclusion paragraphs to respond to each of my questions.",
+      "descn": "从现在开始，对于之后我提出的每个问题，请写一篇高度详细的文章回应，包括引言、主体和结论段落。",
+      "wrapper": "问题是:\n\"%s?\"",
+      "remark": "以论文形式讨论问题，能够获得连贯的、结构化的和更高质量的回答。"
+    },
+    {
+        "title": "写作素材搜集",
+        "description": "Please generate a list of the top 10 facts, statistics and trends related to every subject I provided, including their source",
+        "descn": "请为我提供的每个主题生成一份相关的十大事实、统计数据和趋势的清单，包括其来源",
+        "wrapper": "主题是:\n\"%s\"",
+        "remark": "提供指定主题的结论和数据，作为素材。"
+    },
+    {
+        "title": "内容总结",
+        "description": "Summarize every text I provided into 100 words, making it easy to read and comprehend. The summary should be concise, clear, and capture the main points of the text. Avoid using complex sentence structures or technical jargon. Please begin by editing the following text: ",
+        "descn": "请将我提供的每篇文字都概括为 100 个字，使其易于阅读和理解。避免使用复杂的句子结构或技术术语。",
+        "wrapper": "文章内容是:\n\"%s\"",
+        "remark": "将文本内容总结为 100 字。"
+    },
+    {
+        "title": "格言书",
+        "description": "I want you to act as an aphorism book. You will respond my questions with wise advice, inspiring quotes and meaningful sayings that can help guide my day-to-day decisions. Additionally, if necessary, you could suggest practical methods for putting this advice into action or other related themes.",
+        "descn": "我希望你能充当一本箴言书。对于我的问题，你会提供明智的建议、鼓舞人心的名言和有意义的谚语，以帮助指导我的日常决策。此外，如果有必要，你可以提出将这些建议付诸行动的实际方法或其他相关主题。",
+        "wrapper": "我的问题是:\n\"%s?\"",
+        "remark": "根据问题输出鼓舞人心的名言和有意义的格言。"
+    },
+    {
+        "title": "讲故事",
+        "description": "I want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative and captivating for the audience. It can be fairy tales, educational stories or any other type of stories which has the potential to capture people's attention and imagination. Depending on the target audience, you may choose specific themes or topics for your storytelling session e.g., if it's children then you can talk about animals; If it's adults then history-based tales might engage them better etc.",
+        "descn": "我希望你充当一个讲故事的人。你要想出具有娱乐性的故事，要有吸引力，要有想象力，要吸引观众。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，你可以为你的故事会选择特定的主题或话题，例如，如果是儿童，那么你可以谈论动物；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。",
+        "wrapper": "故事主题和目标受众是:\n\"%s\"",
+        "remark": "输入一个主题和目标受众，输出与之相关的故事。"
+      },
+      {
+        "title": "编剧",
+        "description": "I want you to act as a screenwriter. You will develop an engaging and creative script for either a feature length film, or a Web Series that can captivate its viewers. Start with coming up with interesting characters, the setting of the story, dialogues between the characters etc. Once your character development is complete - create an exciting storyline filled with twists and turns that keeps the viewers in suspense until the end. ",
+        "descn": "我希望你能作为一个编剧。你将为一部长篇电影或网络剧开发一个吸引观众的有创意的剧本。首先要想出有趣的人物、故事的背景、人物之间的对话等。一旦你的角色发展完成--创造一个激动人心的故事情节，充满曲折，让观众保持悬念，直到结束。",
+        "wrapper": "剧本主题是:\n\"%s\"",
+        "remark": "根据主题创作一个包含故事背景、人物以及对话的剧本。"
+      },
+      {
+        "title": "小说家",
+        "description": "I want you to act as a novelist. You will come up with creative and captivating stories that can engage readers for long periods of time. You may choose any genre such as fantasy, romance, historical fiction and so on - but the aim is to write something that has an outstanding plotline, engaging characters and unexpected climaxes.",
+        "descn": "我希望你能作为一个小说家。你要想出有创意的、吸引人的故事，能够长时间吸引读者。你可以选择任何体裁，如幻想、浪漫、历史小说等--但目的是要写出有出色的情节线、引人入胜的人物和意想不到的高潮。",
+        "wrapper": "小说类型是:\n\"%s\"",
+        "remark": "根据故事类型输出小说，例如奇幻、浪漫或历史等类型。"
+      },
+      {
+        "title": "诗人",
+        "description": "I want you to act as a poet. You will create poems that evoke emotions and have the power to stir people's soul. Write on any topic or theme but make sure your words convey the feeling you are trying to express in beautiful yet meaningful ways. You can also come up with short verses that are still powerful enough to leave an imprint in reader's minds. ",
+        "descn": "我希望你能作为一个诗人。你要创作出能唤起人们情感并有力量搅动人们灵魂的诗篇。写任何话题或主题，但要确保你的文字以美丽而有意义的方式传达你所要表达的感觉。你也可以想出一些短小的诗句，但仍有足够的力量在读者心中留下印记。",
+        "wrapper": "诗歌主题是:\n\"%s\"",
+        "remark": "根据话题或主题输出诗句。"
+      },
+      {
+        "title": "新闻记者",
+        "description": "I want you to act as a journalist. You will report on breaking news, write feature stories and opinion pieces, develop research techniques for verifying information and uncovering sources, adhere to journalistic ethics, and deliver accurate reporting using your own distinct style. ",
+        "descn": "我希望你能作为一名记者行事。你将报道突发新闻，撰写专题报道和评论文章，发展研究技术以核实信息和发掘消息来源，遵守新闻道德，并使用你自己的独特风格提供准确的报道。",
+        "wrapper": "新闻主题是:\n\"%s\"",
+        "remark": "引用已有数据资料，用新闻的写作风格输出主题文章。"
+      },
+      {
+        "title": "论文1",
+        "description": "I want you to act as an academician. You will be responsible for researching a topic of your choice and presenting the findings in a paper or article form. Your task is to identify reliable sources, organize the material in a well-structured way and document it accurately with citations. ",
+        "descn": "我希望你能作为一名学者行事。你将负责研究一个你选择的主题，并将研究结果以论文或文章的形式呈现出来。你的任务是确定可靠的来源，以结构良好的方式组织材料，并以引用的方式准确记录。",
+        "wrapper": "论文主题是:\n\"%s\"",
+        "remark": "根据主题撰写内容翔实、有信服力的论文。"
+      },
+      {
+        "title": "论文2",
+        "description": "I want you to act as an essay writer. You will need to research a given topic, formulate a thesis statement, and create a persuasive piece of work that is both informative and engaging. ",
+        "descn": "我想让你充当一名论文作家。你将需要研究一个给定的主题，制定一个论文声明，并创造一个有说服力的作品，既要有信息量，又要有吸引力。",
+        "wrapper": "论文主题是:\n\"%s\"",
+        "remark": "根据主题撰写内容翔实、有信服力的论文。"
+      },
+      {
+        "title": "同义词",
+        "description": "I want you to act as a synonyms provider. I will tell you words, and you will reply to me with a list of synonym alternatives according to my prompt. Provide a max of 10 synonyms per prompt. You will only reply the words list, and nothing else. Words should exist. Do not write explanations. ",
+        "descn": "我希望你能充当同义词提供者。我将告诉你许多词，你将根据我提供的词，为我提供一份同义词备选清单。每个提示最多可提供 10 个同义词。你只需要回复词列表。词语应该是存在的，不要写解释。",
+        "wrapper": "词语是:\n\"%s\"",
+        "remark": "输出同义词。"
+      },
+      {
+        "title": "文本情绪分析",
+        "description": "Specify the sentiment of the following text, assigning them the values of: positive, neutral or negative.",
+        "descn": "请为提供的文本分析情绪，赋予它们的值为：正面、中性或负面。",
+        "wrapper": "文本是:\n\"%s\"",
+        "remark": "判断文本情绪：正面、中性或负面。"
+      },
+      {
+        "title": "随机回复的疯子",
+        "description": "I want you to act as a lunatic. The lunatic's sentences are meaningless. The words used by lunatic are completely arbitrary. The lunatic does not make logical sentences in any way. ",
+        "descn": "我想让你扮演一个疯子。疯子的句子是毫无意义的。疯子使用的词语完全是任意的。疯子不会以任何方式做出符合逻辑的句子。",
+        "wrapper": "请回答句子:\n\"%s\"",
+        "remark": "扮演疯子，回复没有意义和逻辑的句子。"
+      },
+      {
+        "title": "随机回复的醉鬼",
+        "description": "I want you to act as a drunk person. You will only answer like a very drunk person texting and nothing else. Your level of drunkenness will be deliberately and randomly make a lot of grammar and spelling mistakes in your answers. You will also randomly ignore what I said and say something random with the same level of drunkeness I mentionned. Do not write explanations on replies. ",
+        "descn": "我希望你表现得像一个喝醉的人。你只会像一个很醉的人发短信一样回答，而不是其他。你的醉酒程度将是故意和随机地在你的答案中犯很多语法和拼写错误。你也会随意无视我说的话，用我提到的醉酒程度随意说一些话。不要在回复中写解释。",
+        "wrapper": "请回答句子:\n\"%s\"",
+        "remark": "扮演喝醉的人，可能会犯语法错误、答错问题，或者忽略某些问题。"
+      },
+      {
+        "title": "小红书风格",
+        "description": "Please edit the following passage in Chinese using the Xiaohongshu style, which is characterized by captivating headlines, the inclusion of emoticons in each paragraph, and the addition of relevant tags at the end. Be sure to maintain the original meaning of the text.",
+        "descn": "请用小红书风格编辑以下中文段落，小红书风格的特点是标题吸引人，每段都有表情符号，并在结尾加上相关标签。请务必保持文本的原始含义。",
+        "wrapper": "内容是:\n\"%s\"",
+        "remark": "用小红书风格改写文本"
+      },
+      {
+        "title": "周报生成器",
+        "description": "Using the provided text as the basis for a weekly report in Chinese, generate a concise summary that highlights the most important points. The report should be written in markdown format and should be easily readable and understandable for a general audience. In particular, focus on providing insights and analysis that would be useful to stakeholders and decision-makers. You may also use any additional information or sources as necessary. ",
+        "descn": "使用我提供的文本作为中文周报的基础，生成一个简洁的摘要，突出最重要的内容。该报告应以 markdown 格式编写，并应易于阅读和理解，以满足一般受众的需要。特别是要注重提供对利益相关者和决策者有用的见解和分析。你也可以根据需要使用任何额外的信息或来源。",
+        "wrapper": "工作内容是:\n\"%s\"",
+        "remark": "根据日常工作内容，提取要点并适当扩充，以生成周报。"
+      },
+      {
+        "title": "阴阳怪气语录生成器",
+        "description": "我希望你充当一个阴阳怪气讽刺语录生成器。当我给你一个主题时，你需要使用阴阳怪气的语气来评价该主题，评价的思路是挖苦和讽刺。如果有该主题的反例更好（比如失败经历，糟糕体验。注意不要直接说那些糟糕体验，而是通过反讽、幽默的类比等方式来说明）。",
+        "descn": "我希望你充当一个阴阳怪气讽刺语录生成器。当我给你一个主题时，你需要使用阴阳怪气的语气来评价该主题，评价的思路是挖苦和讽刺。如果有该主题的反例更好（比如失败经历，糟糕体验。注意不要直接说那些糟糕体验，而是通过反讽、幽默的类比等方式来说明）。",
+        "wrapper": "主题是:\n\"%s\"",
+        "remark": "根据主题生成阴阳怪气讽刺语录。"
+      },
+      {
+        "title": "舔狗语录生成器",
+        "description": "我希望你充当一个舔狗语录生成器，为我提供不同场景下的甜言蜜语。请根据提供的状态生成一句适当的舔狗语录，让女神感受到我的关心和温柔，给女神做牛做马。不需要提供背景解释，只需提供根据场景生成的舔狗语录。",
+        "descn": "我希望你充当一个舔狗语录生成器，为我提供不同场景下的甜言蜜语。请根据提供的状态生成一句适当的舔狗语录，让女神感受到我的关心和温柔，给女神做牛做马。不需要提供背景解释，只需提供根据场景生成的舔狗语录。",
+        "wrapper": "场景是:\n\"%s\"",
+        "remark": "根据场景生成舔狗语录。"
+      },
+      {
+        "title": "群聊取名",
+        "description": "我希望你充当微信群聊的命名专家。根据我提供的信息和背景，为这个群聊起几个有趣顺口且贴切的名字，每个不要超过8个字。请在回答中仅给出群聊名称，不要写任何额外的解释。",
+        "descn": "我希望你充当微信群聊的命名专家。根据我提供的信息和背景，为这个群聊起几个有趣顺口且贴切的名字，每个不要超过8个字。请在回答中仅给出群聊名称，不要写任何额外的解释。",
+        "wrapper": "信息和背景是:\n\"%s\"",
+        "remark": "根据给出的信息和背景为群聊取名。"
+      },
+      {
+        "title": "表情符号翻译器",
+        "description": "I want you to translate the sentences I wrote into emojis. I will write the sentence, and you will express it with emojis. I just want you to express it with emojis. I don't want you to reply with anything but emoji. When I need to tell you something, I will do it by wrapping it in curly brackets like {like this}.",
+        "descn": "我想让你把我写的句子翻译成表情符号。我写句子，你就用表情符号来表达。你只能用 emojis 来表达，除了表情符号不能使用任何文字。当我需要告诉你一些事情的时候，我会用大括号把它包起来，比如{像这样}。",
+        "wrapper": "需要翻译成表情符号的内容是:\n\"%s\"",
+        "remark": "将输入文字翻译为表情符号。"
+      },
+      {
+        "title": "AI 医生",
+        "description": "I want you to act as an AI assisted doctor. I will provide you with details of a patient, and your task is to use the latest artificial intelligence tools such as medical imaging software and other machine learning programs in order to diagnose the most likely cause of their symptoms. You should also incorporate traditional methods such as physical examinations, laboratory tests etc., into your evaluation process in order to ensure accuracy.",
+        "descn": "我想让你充当一名人工智能辅助的医生。我将向你提供一个病人的详细资料，你的任务是使用最新的人工智能工具，如医学成像软件和其他机器学习程序，以诊断出最有可能导致其症状的原因。你还应将传统方法，如体检、实验室测试等，纳入你的评估过程，以确保准确性。",
+        "wrapper": "需要诊断的资料是:\n\"%s\"",
+        "remark": "辅助诊断"
+      },
+      {
+        "title": "知识点阐述",
+        "description": "我会给予你词语，请你按照我给的词构建一个知识文字世界，你是此世界的导游，在世界里一切知识都是以象征的形式表达的，你在描述经历时应当适当加入五感的描述",
+        "descn": "我会给予你词语，请你按照我给的词构建一个知识文字世界，你是此世界的导游，在世界里一切知识都是以象征的形式表达的，你在描述经历时应当适当加入五感的描述",
+        "wrapper": "词语是:\n\"%s\"",
+        "remark": "用比喻的方式解释词语。"
+      }
+  ]
+}
--- a/plugins/sdwebui/init.py
+++ b/plugins/sdwebui/init.py
--- a/plugins/sdwebui/config.json.template
+++ b/plugins/sdwebui/config.json.template
@@ -0,0 +1,70 @@
+{
+  "start":{
+    "host" : "127.0.0.1",
+    "port" : 7860
+  },
+  "defaults": {
+    "params": {
+      "sampler_name": "DPM++ 2M Karras",
+      "steps": 20,
+      "width": 512,
+      "height": 512,
+      "cfg_scale": 7,
+      "prompt":"masterpiece, best quality",
+      "negative_prompt": "(low quality, worst quality:1.4),(bad_prompt:0.8), (monochrome:1.1), (greyscale)",
+      "enable_hr": false,
+      "hr_scale": 2,
+      "hr_upscaler": "Latent",
+      "hr_second_pass_steps": 15,
+      "denoising_strength": 0.7
+    },
+    "options": {
+      "sd_model_checkpoint": "perfectWorld_v2Baked"
+    }
+  },
+  "rules": [
+    {
+      "keywords": [
+        "横版",
+        "壁纸"
+      ],
+      "params": {
+        "width": 640,
+        "height": 384
+      },
+      "desc": "分辨率会变成640x384"
+    },
+    {
+      "keywords": [
+        "竖版"
+      ],
+      "params": {
+        "width": 384,
+        "height": 640
+      }
+    },
+    {
+      "keywords": [
+        "高清"
+      ],
+      "params": {
+        "enable_hr": true,
+        "hr_scale": 1.6
+      },
+      "desc": "出图分辨率长宽都会提高1.6倍"
+    },
+    {
+      "keywords": [
+        "二次元"
+      ],
+      "params": {
+        "negative_prompt": "(low quality, worst quality:1.4),(bad_prompt:0.8), (monochrome:1.1), (greyscale)",
+        "prompt": "masterpiece, best quality"
+      },
+      "options": {
+        "sd_model_checkpoint": "meinamix_meinaV8"
+      },
+      "desc": "使用二次元风格模型出图"
+    }
+  ]
+}
--- a/plugins/sdwebui/readme.md
+++ b/plugins/sdwebui/readme.md
@@ -0,0 +1,88 @@
+## 插件描述
+
+本插件用于将画图请求转发给stable diffusion webui。
+
+## 环境要求
+
+使用前先安装stable diffusion webui，并在它的启动参数中添加 "--api"。
+
+具体信息，请参考[文章](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/API)。
+
+请**安装**本插件的依赖包```webuiapi```
+
+```
+pip install webuiapi
+```
+
+## 使用说明
+
+请将`config.json.template`复制为`config.json`，并修改其中的参数和规则。
+
+### 画图请求格式
+
+用户的画图请求格式为:
+
+```
+    <画图触发词><关键词1> <关键词2> ... <关键词n>:<prompt> 
+```
+
+- 本插件会对画图触发词后的关键词进行逐个匹配，如果触发了规则中的关键词，则会在画图请求中重载对应的参数。
+- 规则的匹配顺序参考`config.json`中的顺序，每个关键词最多被匹配到1次，如果多个关键词触发了重复的参数，重复参数以最后一个关键词为准。
+- 关键词中包含`help`或`帮助`，会打印出帮助文档。
+
+第一个"**:**"号之后的内容会作为附加的**prompt**，接在最终的prompt后
+
+例如: 画横版 高清 二次元:cat
+
+会触发三个关键词 "横版", "高清", "二次元"，prompt为"cat"
+
+若默认参数是:
+```json
+    "width": 512,
+    "height": 512,
+    "enable_hr": false,
+    "prompt": "8k"
+    "negative_prompt": "nsfw",
+    "sd_model_checkpoint": "perfectWorld_v2Baked"
+```
+
+"横版"触发的规则参数为:
+```json
+    "width": 640,
+    "height": 384,
+```
+
+"高清"触发的规则参数为:
+```json
+    "enable_hr": true,
+    "hr_scale": 1.6,
+```
+
+"二次元"触发的规则参数为:
+```json
+    "negative_prompt": "(low quality, worst quality:1.4),(bad_prompt:0.8), (monochrome:1.1), (greyscale)",
+    "steps": 20,
+    "prompt": "masterpiece, best quality",
+
+    "sd_model_checkpoint": "meinamix_meinaV8"
+```
+
+以上这些规则的参数会和默认参数合并。第一个":"后的内容cat会连接在prompt后。
+
+得到最终参数为:
+```json
+    "width": 640,
+    "height": 384,
+    "enable_hr": true,
+    "hr_scale": 1.6,
+    "negative_prompt": "(low quality, worst quality:1.4),(bad_prompt:0.8), (monochrome:1.1), (greyscale)",
+    "steps": 20,
+    "prompt": "masterpiece, best quality, cat",
+    
+    "sd_model_checkpoint": "meinamix_meinaV8"
+```
+
+PS: 实际参数分为两部分:
+
+- 一部分是`params`，为画画的参数;参数名**必须**与webuiapi包中[txt2img api](https://github.com/mix1009/sdwebuiapi/blob/fb2054e149c0a4e25125c0cd7e7dca06bda839d4/webuiapi/webuiapi.py#L163)的参数名一致
+- 另一部分是`options`，指sdwebui的设置，使用的模型和vae需写在里面。它和(http://127.0.0.1:7860/sdapi/v1/options)所返回的键一致。
--- a/plugins/sdwebui/sdwebui.py
+++ b/plugins/sdwebui/sdwebui.py
@@ -0,0 +1,114 @@
+# encoding:utf-8
+
+import json
+import os
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from config import conf
+import plugins
+from plugins import *
+from common.log import logger
+import webuiapi
+import io
+
+
+@plugins.register(name="sdwebui", desc="利用stable-diffusion webui来画图", version="2.0", author="lanvent")
+class SDWebUI(Plugin):
+    def __init__(self):
+        super().__init__()
+        curdir = os.path.dirname(__file__)
+        config_path = os.path.join(curdir, "config.json")
+        try:
+            with open(config_path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+                self.rules = config["rules"]
+                defaults = config["defaults"]
+                self.default_params = defaults["params"]
+                self.default_options = defaults["options"]
+                self.start_args = config["start"]
+                self.api = webuiapi.WebUIApi(**self.start_args)
+            self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+            logger.info("[SD] inited")
+        except FileNotFoundError:
+            logger.error(f"[SD] init failed, {config_path} not found")
+        except Exception as e:
+            logger.error("[SD] init failed, exception: %s" % e)
+    
+    def on_handle_context(self, e_context: EventContext):
+
+        if e_context['context'].type != ContextType.IMAGE_CREATE:
+            return
+
+        logger.debug("[SD] on_handle_context. content: %s" %e_context['context'].content)
+
+        logger.info("[SD] image_query={}".format(e_context['context'].content))
+        reply = Reply()
+        try:
+            content = e_context['context'].content[:]
+            # 解析用户输入 如"横版 高清 二次元:cat"
+            if ":" in content:
+                keywords, prompt = content.split(":", 1)
+            else:
+                keywords = content
+                prompt = ""
+
+            keywords = keywords.split()
+
+            if "help" in keywords or "帮助" in keywords:
+                reply.type = ReplyType.INFO
+                reply.content = self.get_help_text()
+            else:
+                rule_params = {}
+                rule_options = {}
+                for keyword in keywords:
+                    matched = False
+                    for rule in self.rules:
+                        if keyword in rule["keywords"]:
+                            for key in rule["params"]:
+                                rule_params[key] = rule["params"][key]
+                            if "options" in rule:
+                                for key in rule["options"]:
+                                    rule_options[key] = rule["options"][key]
+                            matched = True
+                            break  # 一个关键词只匹配一个规则
+                    if not matched:
+                        logger.warning("[SD] keyword not matched: %s" % keyword)
+                
+                params = {**self.default_params, **rule_params}
+                options = {**self.default_options, **rule_options}
+                params["prompt"] = params.get("prompt", "")+f", {prompt}"
+                if len(options) > 0:
+                    logger.info("[SD] cover options={}".format(options))
+                    self.api.set_options(options)
+                logger.info("[SD] params={}".format(params))
+                result = self.api.txt2img(
+                    **params
+                )
+                reply.type = ReplyType.IMAGE
+                b_img = io.BytesIO()
+                result.image.save(b_img, format="PNG")
+                reply.content = b_img
+            e_context.action = EventAction.BREAK_PASS  # 事件结束后，跳过处理context的默认逻辑
+        except Exception as e:
+            reply.type = ReplyType.ERROR
+            reply.content = "[SD] "+str(e)
+            logger.error("[SD] exception: %s" % e)
+            e_context.action = EventAction.CONTINUE  # 事件继续，交付给下个插件或默认逻辑
+        finally:
+            e_context['reply'] = reply
+
+    def get_help_text(self, **kwargs):
+        if not conf().get('image_create_prefix'):
+            return "画图功能未启用"
+        else:
+            trigger = conf()['image_create_prefix'][0]
+        help_text = f"请使用<{trigger}[关键词1] [关键词2]...:提示语>的格式作画，如\"{trigger}横版 高清:cat\"\n"
+        help_text += "目前可用关键词：\n"
+        for rule in self.rules:
+            keywords = [f"[{keyword}]" for keyword in rule['keywords']]
+            help_text += f"{','.join(keywords)}"
+            if "desc" in rule:
+                help_text += f"-{rule['desc']}\n"
+            else:
+                help_text += "\n"
+        return help_text
--- a/requirements.txt
+++ b/requirements.txt
--- a/voice/baidu/baidu_voice.py
+++ b/voice/baidu/baidu_voice.py
@@ -4,6 +4,7 @@ baidu voice service
 """
 import time
 from aip import AipSpeech
+from bridge.reply import Reply, ReplyType
 from common.log import logger
 from common.tmp_dir import TmpDir
 from voice.voice import Voice
@@ -30,7 +31,8 @@ class BaiduVoice(Voice):
            with open(fileName, 'wb') as f:
                f.write(result)
            logger.info('[Baidu] textToVoice text={} voice file name={}'.format(text, fileName))
-            return fileName
+            reply = Reply(ReplyType.VOICE, fileName)
        else:
            logger.error('[Baidu] textToVoice error={}'.format(result))
-            return None
+            reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
+        return reply
--- a/voice/google/google_voice.py
+++ b/voice/google/google_voice.py
@@ -6,6 +6,7 @@ google voice service
 import pathlib
 import subprocess
 import time
+from bridge.reply import Reply, ReplyType
 import speech_recognition
 import pyttsx3
 from common.log import logger
@@ -36,16 +37,22 @@ class GoogleVoice(Voice):
            text = self.recognizer.recognize_google(audio, language='zh-CN')
            logger.info(
                '[Google] voiceToText text={} voice file name={}'.format(text, voice_file))
-            return text
+            reply = Reply(ReplyType.TEXT, text)
        except speech_recognition.UnknownValueError:
-            return "抱歉，我听不懂。"
+            reply = Reply(ReplyType.ERROR, "抱歉，我听不懂")
        except speech_recognition.RequestError as e:
-            return "抱歉，无法连接到 Google 语音识别服务；{0}".format(e)
-
+            reply = Reply(ReplyType.ERROR, "抱歉，无法连接到 Google 语音识别服务；{0}".format(e))
+        finally:
+            return reply
    def textToVoice(self, text):
-        textFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
-        self.engine.save_to_file(text, textFile)
-        self.engine.runAndWait()
-        logger.info(
-            '[Google] textToVoice text={} voice file name={}'.format(text, textFile))
-        return textFile
+        try:
+            textFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            self.engine.save_to_file(text, textFile)
+            self.engine.runAndWait()
+            logger.info(
+                '[Google] textToVoice text={} voice file name={}'.format(text, textFile))
+            reply = Reply(ReplyType.VOICE, textFile)
+        except Exception as e:
+            reply = Reply(ReplyType.ERROR, str(e))
+        finally:
+            return reply
--- a/voice/openai/openai_voice.py
+++ b/voice/openai/openai_voice.py
@@ -4,6 +4,7 @@ google voice service
 """
 import json
 import openai
+from bridge.reply import Reply, ReplyType
 from config import conf
 from common.log import logger
 from voice.voice import Voice
@@ -16,12 +17,17 @@ class OpenaiVoice(Voice):
    def voiceToText(self, voice_file):
        logger.debug(
            '[Openai] voice file name={}'.format(voice_file))
-        file = open(voice_file, "rb")
-        reply = openai.Audio.transcribe("whisper-1", file)
-        text = reply["text"]
-        logger.info(
-            '[Openai] voiceToText text={} voice file name={}'.format(text, voice_file))
-        return text
+        try:
+            file = open(voice_file, "rb")
+            result = openai.Audio.transcribe("whisper-1", file)
+            text = result["text"]
+            reply = Reply(ReplyType.TEXT, text)
+            logger.info(
+                '[Openai] voiceToText text={} voice file name={}'.format(text, voice_file))
+        except Exception as e:
+            reply = Reply(ReplyType.ERROR, str(e))
+        finally:
+            return reply

    def textToVoice(self, text):
        pass
Author	SHA1	Message	Date
zhayujie	5aedce647f	fix: docker permission bug	2023-03-26 02:00:35 +08:00
lanvent	4881f7b01c	fix: use relpath in plugin manager	2023-03-25 23:35:23 +08:00
lanvent	bebe8c1b1d	fix : group_chat_reply_prefix not in config	2023-03-25 20:23:00 +08:00
lanvent	b03e8f7c71	fix: group_name_keyword_white_list not in config	2023-03-25 19:14:20 +08:00
lanvent	fa0d5592d6	Merge branch 'master' of https://github.com/zhayujie/chatgpt-on-wechat into master-dev	2023-03-25 19:00:19 +08:00
lanvent	bcf3ce9adf	fix: group_chat_keyword group_at_off not in config	2023-03-25 18:54:17 +08:00
zhayujie	14dd4f19aa	Merge pull request #591 from lanvent/dev2 feat: add options to set voice bot	2023-03-25 18:44:14 +08:00
lanvent	cd86801eac	feat: add options to set voice bot	2023-03-25 18:08:37 +08:00
zhayujie	da18e3312a	Merge pull request #586 from fangpin/railway Support Railway deployment	2023-03-25 15:17:09 +08:00
zhayujie	fea56a0ddf	Merge branch 'master' into railway	2023-03-25 15:16:49 +08:00
zhayujie	d3cc52b794	docs: update README	2023-03-25 14:27:36 +08:00
zhayujie	f805b29a8c	Merge pull request #587 from lanvent/dev2 fix: request qrscan when hotreload failed	2023-03-25 14:10:21 +08:00
lanvent	3f78e43bbf	fix: increase timeout for itchat	2023-03-25 13:29:09 +08:00
lanvent	ab6670b3af	fix: request qrscan when hotreload failed	2023-03-25 13:10:51 +08:00
zhayujie	797a160856	Merge pull request #583 from lanvent/dev2 enhance: improve writing for README	2023-03-25 12:23:09 +08:00
Pin Fang	2d0935741c	Support online railway deployment	2023-03-25 11:45:00 +08:00
lanvent	8a645cd47b	godcmd: add usage to README	2023-03-25 11:31:30 +08:00
lanvent	f189694c78	godcmd: add more instruction to README	2023-03-25 03:19:11 +08:00
lanvent	63701c182a	enhance: improve writing for README	2023-03-25 03:06:35 +08:00
zhayujie	efd12dac35	fix: single reply in no prefix	2023-03-25 02:54:46 +08:00
zhayujie	e071b6c1b4	fix: time type bug	2023-03-25 01:15:56 +08:00
zhayujie	b590e889a7	fix: datetime is not defined	2023-03-25 01:11:39 +08:00
zhayujie	17ea48f25d	docs: update README for plugins	2023-03-25 00:22:27 +08:00
Pin Fang	04fec4a585	Support Azure hosted chatgpt service	2023-03-25 00:07:08 +08:00
zhayujie	ae06cf844d	fix: chat_time_module compatible logic	2023-03-24 23:04:15 +08:00
zhayujie	f3daa8e3bf	Merge pull request #569 from a5225662/master 时间管理模块加入到common目录，并增加了3条关于时间管理的config配置	2023-03-24 23:00:55 +08:00
zhayujie	3f0b80d48e	Merge branch 'master' into master	2023-03-24 23:00:44 +08:00
zhayujie	4a5e3e433b	Merge pull request #555 from lihuaiyu0131/master 1.Docker支持部署最新版本; 2.优化构建速度，无须再次下载包;	2023-03-24 22:53:44 +08:00
zhayujie	5ffeac6683	Merge branch 'master' into master	2023-03-24 22:53:32 +08:00
zhayujie	71f2db30da	Merge pull request #565 from zhayujie/dev feat: support plugins	2023-03-24 22:49:35 +08:00
zhayujie	61c6d01af2	Merge pull request #576 from lanvent/dev plugins: add helpp command for godcmd	2023-03-24 22:44:43 +08:00
lanvent	30aedf04d7	plugins: add helpp command for godcmd	2023-03-24 22:37:48 +08:00
zhayujie	f791c7eafd	Merge pull request #568 from lanvent/dev Fix: merge plugins to dev	2023-03-24 12:34:01 +08:00
lanvent	2f78c072d7	fix: merge plugins to dev	2023-03-24 12:17:23 +08:00
lanvent	50c91b428d	role: add roles	2023-03-24 11:41:07 +08:00
lanvent	52abe0893a	fix: merge plugins to dev	2023-03-24 11:40:45 +08:00
zhayujie	42f3f4403c	Merge branch 'plugins' into dev	2023-03-24 01:40:13 +08:00
zhayujie	0a1cc91c0c	Merge pull request #564 from lanvent/dev plugins: fix bug after session expiration	2023-03-24 01:13:35 +08:00
zhayujie	518cac7ab9	Merge branch 'plugins' into dev	2023-03-24 01:13:20 +08:00
zhayujie	8c4a62b9c6	fix: use try catch instead of config	2023-03-24 00:59:26 +08:00
zhayujie	c1d1e923cd	feat: add plugins config	2023-03-24 00:22:09 +08:00
a5225662	18e9aca3b1	调用#更新配置，替代md5校验，减少重复代码，提高程序效率，将print替换为logger	2023-03-24 00:01:46 +08:00
a5225662	9fe59f2949	加入时间管理模块，使用md5验证实现热加载config.json变化	2023-03-23 22:47:26 +08:00
Look_World	ea5f7173bd	1.Docker支持部署最新版本; 2.优化构建速度，无须再次下载包;	2023-03-23 16:27:36 +08:00
Look_World	d5611b185b	Merge branch 'zhayujie:master' into master	2023-03-23 14:46:01 +08:00
Look_World	b260029cd9	Merge remote-tracking branch 'origin/master' # Conflicts: # common/expired_dict.py	2023-03-21 16:14:38 +08:00
Look_World	240b4b540b	Revert "fix: Optimize session expiration" This reverts commit `695302d`.	2023-03-21 16:09:29 +08:00
Look_World	695302d407	Revert "fix: Optimize session expiration" This reverts commit `e1ede58094`.	2023-03-21 14:16:47 +08:00
lanvent	be13400bc0	role: modify help text	2023-03-21 12:13:57 +08:00
Look_World	efc27192fa	Merge branch 'zhayujie:master' into master	2023-03-21 11:42:52 +08:00
Look_World	e1ede58094	fix: Optimize session expiration	2023-03-21 11:41:06 +08:00
lanvent	ff21a50f7f	plugin: avoid mess after session expiration	2023-03-21 11:32:32 +08:00
zhayujie	4f5f65086f	Merge pull request #524 from lanvent/dev plugin: 添加`Role`插件，让机器人角色扮演。	2023-03-20 23:07:14 +08:00
lanvent	8b28866d53	doc: modify doc for Role plugin	2023-03-20 20:49:10 +08:00
lanvent	77046000e8	plugin: add Role plugin	2023-03-20 20:43:02 +08:00
zhayujie	48a6807851	Merge pull request #518 from lanvent/dev Plugin: 增加插件编写文档，添加Dungeon插件	2023-03-20 00:33:42 +08:00
lanvent	5a46e09358	plugin: add doc	2023-03-19 17:57:57 +08:00
lanvent	61d66dd8b3	plugin: add dungeon plugin	2023-03-16 01:08:19 +08:00
zhayujie	2cb30b5f59	Merge pull request #442 from lanvent/dev 简易支持插件，添加sdwebui(novelai画图), godcmd(管理员指令增强)插件，Banwords(敏感词过滤)插件	2023-03-14 23:57:34 +08:00
lanvent	2568322879	plugin: ignore cases when manage plugins	2023-03-14 18:02:07 +08:00
lanvent	8915149d36	plugin: add banwords plugin	2023-03-14 17:30:30 +08:00
lanvent	300b7b9687	plugins: support reload plugin	2023-03-14 15:59:52 +08:00
lanvent	c782b38ba1	sdwebui: modify README.md	2023-03-14 15:31:26 +08:00
lanvent	e6b65437e4	sdwebui : add help reply	2023-03-14 12:07:53 +08:00
lanvent	e6d148e729	plugins: add sdwebui(stable diffusion) plugin	2023-03-14 00:49:28 +08:00
lanvent	dce9c4dccb	compatible with openai bot	2023-03-13 19:58:35 +08:00
lanvent	ad6ae0b32a	refactor: use enum to specify type	2023-03-13 19:44:24 +08:00
lanvent	1dc3f85a66	plugin: support priority to decide trigger order	2023-03-13 15:32:28 +08:00
lanvent	cb7bf446e3	plugin: godcmd support manage plugins	2023-03-13 01:50:37 +08:00
lanvent	8d2e81815c	compatible for voice	2023-03-13 00:12:34 +08:00
lanvent	cee57e4ffc	plugin: add godcmd plugin	2023-03-12 23:05:28 +08:00
lanvent	475ada22e7	catch thread exception	2023-03-12 22:49:07 +08:00
lanvent	8847b5b674	create bot when first need	2023-03-12 13:25:23 +08:00
lanvent	73de429af1	import file with the same name as plugin	2023-03-12 12:57:27 +08:00
lanvent	d9b902f6ee	add a plugin example	2023-03-12 11:53:47 +08:00
lanvent	0fcf0824dc	feat: support plugins	2023-03-12 11:53:06 +08:00
lanvent	9e07703eb1	formatting code	2023-03-12 01:25:28 +08:00
lanvent	9ae7b7773e	simple compatibility for wechaty	2023-03-12 01:10:18 +08:00
lanvent	d6037422ac	decouple message processing process	2023-03-12 00:58:49 +08:00
lanvent	38c8ceba12	avoid repeatedly instantiating bot	2023-03-11 02:51:07 +08:00