fix: default to fast mode

Merge pull request #1334 from zyqfork/master
azure api add api-version https://learn.microsoft.com/zh-cn/azure/ai-serv…
2026-05-17 18:08:57 +08:00 · 2023-07-31 21:40:50 +08:00 · 2023-07-31 18:40:06 +08:00 · 2023-07-31 18:02:41 +08:00 · 2023-07-31 17:58:06 +08:00 · 2023-07-31 17:53:46 +08:00
43 changed files with 926 additions and 484 deletions
@@ -28,6 +28,12 @@ jobs:
      - name: Checkout repository
        uses: actions/checkout@v3

+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
      - name: Log in to the Container registry
        uses: docker/login-action@v2
        with:
@@ -39,7 +45,9 @@ jobs:
        id: meta
        uses: docker/metadata-action@v4
        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          images: |
+            ${{ env.IMAGE_NAME }}
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}

      - name: Build and push Docker image
        uses: docker/build-push-action@v3
@@ -24,4 +24,5 @@ plugins/**/
 !plugins/banwords/**/
 !plugins/hello
 !plugins/role
-!plugins/keyword
+!plugins/keyword
+!plugins/linkai
@@ -13,11 +13,6 @@

 > 欢迎接入更多应用，参考 [Terminal代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/terminal/terminal_channel.py)实现接收和发送消息逻辑即可接入。 同时欢迎增加新的插件，参考 [插件说明文档](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)。

-**一键部署:**
- 个人微信
-  
-  [![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/qApznZ?referralCode=RC3znh)
-
 # 演示

 https://user-images.githubusercontent.com/26161723/233777277-e3b9928e-b88f-43e2-b0e0-3cbc923bc799.mp4
@@ -26,13 +21,13 @@ Demo made by [Visionn](https://www.wangpc.cc/)

 # 交流群

-添加小助手微信进群：
+添加小助手微信进群，请备注 "wechat"：

 <img width="240" src="./docs/images/contact.jpg">

 # 更新日志

->**2023.06.12：** 接入 [LinkAI](https://chat.link-ai.tech/console) 平台，可在线创建 个人知识库，并接入微信中。Beta版本欢迎体验，使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。
+>**2023.06.12：** 接入 [LinkAI](https://chat.link-ai.tech/console) 平台，可在线创建 个人知识库，并接入微信、公众号及企业微信中。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。

 >**2023.04.26：** 支持企业微信应用号部署，兼容插件，并支持语音图片交互，私人助理理想选择，[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatcom/README.md)。(contributed by [@lanvent](https://github.com/lanvent) in [#944](https://github.com/zhayujie/chatgpt-on-wechat/pull/944))

@@ -63,6 +58,8 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 支持 Linux、MacOS、Windows 系统（可在Linux服务器上长期运行)，同时需安装 `Python`。
 > 建议Python版本在 3.7.1~3.9.X 之间，推荐3.8版本，3.10及以上版本在 MacOS 可用，其他系统上不确定能否正常运行。

+> 注意：Docker 或 Railway 部署无需安装python环境和下载源码，可直接快进到下一节。
+
 **(1) 克隆项目代码：**

 ```bash
@@ -114,7 +111,7 @@ pip3 install azure-cognitiveservices-speech
 {
  "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。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
+  "proxy": "",                                                # 代理客户端的ip和端口，国内环境开启代理的需要填写该项，如 "127.0.0.1:7890"
  "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
@@ -126,6 +123,7 @@ pip3 install azure-cognitiveservices-speech
  "group_speech_recognition": false,                          # 是否开启群组语音识别
  "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/
  "azure_deployment_id": "",                                  # 采用Azure ChatGPT时，模型部署名称
+  "azure_api_version": "",                                    # 采用Azure ChatGPT时，API版本
  "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
  # 订阅消息，公众号和企业微信channel中请填写，当被订阅时会自动回复，可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成bot的触发词。
  "subscribe_msg": "感谢您的关注！\n这里是ChatGPT，可以自由对话。\n支持语音对话。\n支持图片输出，画字开头的消息将按要求创作图片。\n支持角色扮演和文字冒险等丰富插件。\n输入{trigger_prefix}#help 查看详细指令。"
@@ -196,14 +194,61 @@ nohup python3 app.py & tail -f nohup.out          # 在后台运行程序并通

 ### 3.Docker部署

-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))。
+> 使用docker部署无需下载源码和安装依赖，只需要获取 docker-compose.yml 配置文件并启动容器即可。

-### 4. Railway部署 (✅推荐)
-> Railway每月提供5刀和最多500小时的免费额度。
-1. 进入 [Railway](https://railway.app/template/qApznZ?referralCode=RC3znh)。
+> 前提是需要安装好 `docker` 及 `docker-compose`，安装成功的表现是执行 `docker -v` 和 `docker-compose version` (或 docker compose version) 可以查看到版本号，可前往 [docker官网](https://docs.docker.com/engine/install/) 进行下载。
+
+#### (1) 下载 docker-compose.yml 文件
+
+```bash
+wget https://open-1317903499.cos.ap-guangzhou.myqcloud.com/docker-compose.yml
+```
+
+下载完成后打开 `docker-compose.yml` 修改所需配置，如 `OPEN_AI_API_KEY` 和 `GROUP_NAME_WHITE_LIST` 等。
+
+#### (2) 启动容器
+
+在 `docker-compose.yml` 所在目录下执行以下命令启动容器：
+
+```bash
+sudo docker compose up -d
+```
+
+运行 `sudo docker ps` 能查看到 NAMES 为 chatgpt-on-wechat 的容器即表示运行成功。
+
+注意：
+
+ - 如果 `docker-compose` 是 1.X 版本 则需要执行 `sudo  docker-compose up -d` 来启动容器
+ - 该命令会自动去 [docker hub](https://hub.docker.com/r/zhayujie/chatgpt-on-wechat) 拉取 latest 版本的镜像，latest 镜像会在每次项目 release 新的版本时生成
+
+最后运行以下命令可查看容器运行日志，扫描日志中的二维码即可完成登录：
+
+```bash
+sudo docker logs -f chatgpt-on-wechat
+```
+
+#### (3) 插件使用
+
+如果需要在docker容器中修改插件配置，可通过挂载的方式完成，将 [插件配置文件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/config.json.template)
+重命名为 `config.json`，放置于 `docker-compose.yml` 相同目录下，并在 `docker-compose.yml` 中的 `chatgpt-on-wechat` 部分下添加 `volumes` 映射:
+
+```
+volumes:
+  - ./config.json:/app/plugins/config.json
+```
+
+### 4. Railway部署
+
+> Railway 每月提供5刀和最多500小时的免费额度。 (07.11更新: 目前大部分账号已无法免费部署)
+
+1. 进入 [Railway](https://railway.app/template/qApznZ?referralCode=RC3znh)
 2. 点击 `Deploy Now` 按钮。
 3. 设置环境变量来重载程序运行的参数，例如`open_ai_api_key`, `character_desc`。

+**一键部署:**
+  
+  [![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/qApznZ?referralCode=RC3znh)
+
 ## 常见问题

 FAQs： <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
@@ -121,6 +121,7 @@ class ChatGPTBot(Bot, OpenAIImage):
            if args is None:
                args = self.args
            response = openai.ChatCompletion.create(api_key=api_key, messages=session.messages, **args)
+            # logger.debug("[CHATGPT] response={}".format(response))
            # logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
            return {
                "total_tokens": response["usage"]["total_tokens"],
@@ -165,7 +166,7 @@ class AzureChatGPTBot(ChatGPTBot):
    def __init__(self):
        super().__init__()
        openai.api_type = "azure"
-        openai.api_version = "2023-03-15-preview"
+        openai.api_version = conf().get("azure_api_version", "2023-06-01-preview")
        self.args["deployment_id"] = conf().get("azure_deployment_id")

    def create_img(self, query, retry_count=0, api_key=None):
@@ -57,25 +57,25 @@ def num_tokens_from_messages(messages, model):
    """Returns the number of tokens used by a list of messages."""
    import tiktoken

-    if model == "gpt-3.5-turbo" or model == "gpt-35-turbo":
-        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0301")
-    elif model == "gpt-4":
-        return num_tokens_from_messages(messages, model="gpt-4-0314")
+    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo"]:
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
+    elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k"]:
+        return num_tokens_from_messages(messages, model="gpt-4")

    try:
        encoding = tiktoken.encoding_for_model(model)
    except KeyError:
        logger.debug("Warning: model not found. Using cl100k_base encoding.")
        encoding = tiktoken.get_encoding("cl100k_base")
-    if model == "gpt-3.5-turbo-0301":
+    if model == "gpt-3.5-turbo":
        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
        tokens_per_name = -1  # if there's a name, the role is omitted
-    elif model == "gpt-4-0314":
+    elif model == "gpt-4":
        tokens_per_message = 3
        tokens_per_name = 1
    else:
-        logger.warn(f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo-0301.")
-        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0301")
+        logger.warn(f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo.")
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
    num_tokens = 0
    for message in messages:
        num_tokens += tokens_per_message
@@ -29,18 +29,24 @@ class LinkAIBot(Bot, OpenAIImage):
        if context.type == ContextType.TEXT:
            return self._chat(query, context)
        elif context.type == ContextType.IMAGE_CREATE:
-            ok, retstring = self.create_img(query, 0)
-            reply = None
+            ok, res = self.create_img(query, 0)
            if ok:
-                reply = Reply(ReplyType.IMAGE_URL, retstring)
+                reply = Reply(ReplyType.IMAGE_URL, res)
            else:
-                reply = Reply(ReplyType.ERROR, retstring)
+                reply = Reply(ReplyType.ERROR, res)
            return reply
        else:
            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
            return reply

-    def _chat(self, query, context, retry_count=0):
+    def _chat(self, query, context, retry_count=0) -> Reply:
+        """
+        发起对话请求
+        :param query: 请求提示词
+        :param context: 对话上下文
+        :param retry_count: 当前递归重试次数
+        :return: 回复
+        """
        if retry_count >= 2:
            # exit from retry 2 times
            logger.warn("[LINKAI] failed after maximum number of retry times")
@@ -52,7 +58,7 @@ class LinkAIBot(Bot, OpenAIImage):
                logger.info(f"[LINKAI] won't set appcode because a plugin ({context['generate_breaked_by']}) affected the context")
                app_code = None
            else:
-                app_code = conf().get("linkai_app_code")
+                app_code = context.kwargs.get("app_code") or conf().get("linkai_app_code")
            linkai_api_key = conf().get("linkai_api_key")

            session_id = context["session_id"]
@@ -63,10 +69,8 @@ class LinkAIBot(Bot, OpenAIImage):
            if app_code and session.messages[0].get("role") == "system":
                session.messages.pop(0)

-            logger.info(f"[LINKAI] query={query}, app_code={app_code}")
-
            body = {
-                "appCode": app_code,
+                "app_code": app_code,
                "messages": session.messages,
                "model": conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称
                "temperature": conf().get("temperature"),
@@ -74,31 +78,34 @@ class LinkAIBot(Bot, OpenAIImage):
                "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
            }
+            logger.info(f"[LINKAI] query={query}, app_code={app_code}, mode={body.get('model')}")
            headers = {"Authorization": "Bearer " + linkai_api_key}

            # do http request
-            res = requests.post(url=self.base_url + "/chat/completion", json=body, headers=headers).json()
+            res = requests.post(url=self.base_url + "/chat/completions", json=body, headers=headers,
+                                timeout=conf().get("request_timeout", 180))
+            if res.status_code == 200:
+                # execute success
+                response = res.json()
+                reply_content = response["choices"][0]["message"]["content"]
+                total_tokens = response["usage"]["total_tokens"]
+                logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}")
+                self.sessions.session_reply(reply_content, session_id, total_tokens)
+                return Reply(ReplyType.TEXT, reply_content)

-            if not res or not res["success"]:
-                if res.get("code") == self.AUTH_FAILED_CODE:
-                    logger.exception(f"[LINKAI] please check your linkai_api_key, res={res}")
-                    return Reply(ReplyType.ERROR, "请再问我一次吧")
+            else:
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[LINKAI] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}")

-                elif res.get("code") == self.NO_QUOTA_CODE:
-                    logger.exception(f"[LINKAI] please check your account quota, https://chat.link-ai.tech/console/account")
-                    return Reply(ReplyType.ERROR, "提问太快啦，请休息一下再问我吧")
-
-                else:
-                    # retry
+                if res.status_code >= 500:
+                    # server error, need retry
                    time.sleep(2)
                    logger.warn(f"[LINKAI] do retry, times={retry_count}")
                    return self._chat(query, context, retry_count + 1)

-            # execute success
-            reply_content = res["data"]["content"]
-            logger.info(f"[LINKAI] reply={reply_content}")
-            self.sessions.session_reply(reply_content, session_id)
-            return Reply(ReplyType.TEXT, reply_content)
+                return Reply(ReplyType.ERROR, "提问太快啦，请休息一下再问我吧")

        except Exception as e:
            logger.exception(e)
@@ -223,9 +223,9 @@ class ChatChannel(Channel):
                        return self._decorate_reply(context, reply)
                    if context.get("isgroup", False):
                        reply_text = "@" + context["msg"].actual_user_nickname + "\n" + reply_text.strip()
-                        reply_text = conf().get("group_chat_reply_prefix", "") + reply_text
+                        reply_text = conf().get("group_chat_reply_prefix", "") + reply_text + conf().get("group_chat_reply_suffix", "")
                    else:
-                        reply_text = conf().get("single_chat_reply_prefix", "") + reply_text
+                        reply_text = conf().get("single_chat_reply_prefix", "") + reply_text + conf().get("single_chat_reply_suffix", "")
                    reply.content = reply_text
                elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
                    reply.content = "[" + str(reply.type) + "]\n" + reply.content
@@ -48,6 +48,7 @@ class ChatMessage(object):
    to_user_nickname = None
    other_user_id = None
    other_user_nickname = None
+    my_msg = False

    is_group = False
    is_at = False
@@ -53,11 +53,14 @@ def _check(func):
        if msgId in self.receivedMsgs:
            logger.info("Wechat message {} already received, ignore".format(msgId))
            return
-        self.receivedMsgs[msgId] = cmsg
+        self.receivedMsgs[msgId] = True
        create_time = cmsg.create_time  # 消息时间戳
        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".format(msgId))
            return
+        if cmsg.my_msg:
+            logger.debug("[WX]my message {} skipped".format(msgId))
+            return
        return func(self, cmsg)

    return wrapper
@@ -105,7 +108,7 @@ class WechatChannel(ChatChannel):

    def __init__(self):
        super().__init__()
-        self.receivedMsgs = ExpiredDict(60 * 60 * 24)
+        self.receivedMsgs = ExpiredDict(60 * 60)

    def startup(self):
        itchat.instance.receivingRetryCount = 600  # 修改断线超时时间
@@ -159,7 +162,7 @@ class WechatChannel(ChatChannel):
    @_check
    def handle_group(self, cmsg: ChatMessage):
        if cmsg.ctype == ContextType.VOICE:
-            if conf().get("speech_recognition") != True:
+            if conf().get("group_speech_recognition") != True:
                return
            logger.debug("[WX]receive voice for group msg: {}".format(cmsg.content))
        elif cmsg.ctype == ContextType.IMAGE:
@@ -58,6 +58,8 @@ class WechatMessage(ChatMessage):
        if self.to_user_id == user_id:
            self.to_user_nickname = nickname
        try:  # 陌生人时候, 'User'字段可能不存在
+            self.my_msg = itchat_msg["ToUserName"] == itchat_msg["User"]["UserName"] and \
+                          itchat_msg["ToUserName"] != itchat_msg["FromUserName"]
            self.other_user_id = itchat_msg["User"]["UserName"]
            self.other_user_nickname = itchat_msg["User"]["NickName"]
            if self.other_user_id == self.from_user_id:
@@ -2,6 +2,7 @@
  "open_ai_api_key": "YOUR API KEY",
  "model": "gpt-3.5-turbo",
  "proxy": "",
+  "hot_reload": false,
  "single_chat_prefix": [
    "bot",
    "@bot"
@@ -19,11 +19,14 @@ available_setting = {
    "model": "gpt-3.5-turbo",
    "use_azure_chatgpt": False,  # 是否使用azure的chatgpt
    "azure_deployment_id": "",  # azure 模型部署名称
+    "azure_api_version": "",  # azure api版本
    # 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
+    "single_chat_reply_suffix": "",  # 私聊时自动回复的后缀，\n 可以换行    
+    "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_reply_suffix": "",  # 群聊时自动回复的后缀，\n 可以换行
    "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
@@ -35,7 +38,8 @@ available_setting = {
    "image_create_size": "256x256",  # 图片大小,可选有 256x256, 512x512, 1024x1024
    # 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
+    # 人格描述
+    "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。",
    "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
@@ -99,6 +103,8 @@ available_setting = {
    "appdata_dir": "",  # 数据目录
    # 插件配置
    "plugin_trigger_prefix": "$",  # 规范插件提供聊天相关指令的前缀，建议不要和管理员指令前缀"#"冲突
+    # 是否使用全局插件配置
+    "use_global_plugin_config": False,
    # 知识库平台配置
    "use_linkai": False,
    "linkai_api_key": "",
@@ -226,3 +232,32 @@ def subscribe_msg():
    trigger_prefix = conf().get("single_chat_prefix", [""])[0]
    msg = conf().get("subscribe_msg", "")
    return msg.format(trigger_prefix=trigger_prefix)
+
+
+# global plugin config
+plugin_config = {}
+
+
+def write_plugin_config(pconf: dict):
+    """
+    写入插件全局配置
+    :param pconf: 全量插件配置
+    """
+    global plugin_config
+    for k in pconf:
+        plugin_config[k.lower()] = pconf[k]
+
+
+def pconf(plugin_name: str) -> dict:
+    """
+    根据插件名称获取配置
+    :param plugin_name: 插件名称
+    :return: 该插件的配置项
+    """
+    return plugin_config.get(plugin_name.lower())
+
+
+# 全局配置，用于存放全局生效的状态
+global_config = {
+    "admin_users": []
+}
@@ -1,39 +0,0 @@
-FROM python:3.10-alpine
-
-LABEL maintainer="foo@bar.com"
-ARG TZ='Asia/Shanghai'
-
-ARG CHATGPT_ON_WECHAT_VER
-
-ENV BUILD_PREFIX=/app
-
-RUN apk add --no-cache \
-        bash \
-        curl \
-        wget \
-    && export BUILD_GITHUB_TAG=${CHATGPT_ON_WECHAT_VER:-`curl -sL "https://api.github.com/repos/zhayujie/chatgpt-on-wechat/releases/latest" | \
-        grep '"tag_name":' | \
-        sed -E 's/.*"([^"]+)".*/\1/'`} \
-    && wget -t 3 -T 30 -nv -O chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-            https://github.com/zhayujie/chatgpt-on-wechat/archive/refs/tags/${BUILD_GITHUB_TAG}.tar.gz \
-    && tar -xzf chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-    && mv chatgpt-on-wechat-${BUILD_GITHUB_TAG} ${BUILD_PREFIX} \
-    && rm chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-    && cd ${BUILD_PREFIX} \
-    && cp config-template.json ${BUILD_PREFIX}/config.json \
-    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
-    && pip install --no-cache -r requirements.txt --extra-index-url https://alpine-wheels.github.io/index\
-    && pip install --no-cache -r requirements-optional.txt --extra-index-url https://alpine-wheels.github.io/index\
-    && apk del curl wget
-
-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 -R noroot:noroot ${BUILD_PREFIX}
-
-USER noroot
-
-ENTRYPOINT ["/entrypoint.sh"]
@@ -1,29 +0,0 @@
-FROM python:3.10-alpine
-
-LABEL maintainer="foo@bar.com"
-ARG TZ='Asia/Shanghai'
-
-ARG CHATGPT_ON_WECHAT_VER
-
-ENV BUILD_PREFIX=/app
-
-ADD . ${BUILD_PREFIX}
-
-RUN apk add --no-cache bash ffmpeg espeak \
-    && cd ${BUILD_PREFIX} \
-    && cp config-template.json config.json \
-    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
-    && pip install --no-cache -r requirements.txt --extra-index-url https://alpine-wheels.github.io/index\
-    && pip install --no-cache -r requirements-optional.txt --extra-index-url https://alpine-wheels.github.io/index
-
-WORKDIR ${BUILD_PREFIX}
-
-ADD docker/entrypoint.sh /entrypoint.sh
-
-RUN chmod +x /entrypoint.sh \
-    && adduser -D -h /home/noroot -u 1000 -s /bin/bash noroot \
-    && chown -R noroot:noroot ${BUILD_PREFIX}
-
-USER noroot
-
-ENTRYPOINT ["/entrypoint.sh"]
@@ -1,41 +0,0 @@
-FROM python:3.10
-
-LABEL maintainer="foo@bar.com"
-ARG TZ='Asia/Shanghai'
-
-ARG CHATGPT_ON_WECHAT_VER
-
-ENV BUILD_PREFIX=/app
-
-RUN apt-get update  \
-    && apt-get install -y --no-install-recommends \
-        wget \
-        curl  \
-    && rm -rf /var/lib/apt/lists/* \
-    && export BUILD_GITHUB_TAG=${CHATGPT_ON_WECHAT_VER:-`curl -sL "https://api.github.com/repos/zhayujie/chatgpt-on-wechat/releases/latest" | \
-        grep '"tag_name":' | \
-        sed -E 's/.*"([^"]+)".*/\1/'`} \
-    && wget -t 3 -T 30 -nv -O chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-            https://github.com/zhayujie/chatgpt-on-wechat/archive/refs/tags/${BUILD_GITHUB_TAG}.tar.gz \
-    && tar -xzf chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-    && mv chatgpt-on-wechat-${BUILD_GITHUB_TAG} ${BUILD_PREFIX} \
-    && rm chatgpt-on-wechat-${BUILD_GITHUB_TAG}.tar.gz \
-    && cd ${BUILD_PREFIX} \
-    && cp config-template.json ${BUILD_PREFIX}/config.json \
-    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
-    && pip install --no-cache -r requirements.txt \
-    && pip install --no-cache -r requirements-optional.txt
-
-WORKDIR ${BUILD_PREFIX}
-
-ADD ./entrypoint.sh /entrypoint.sh
-
-RUN chmod +x /entrypoint.sh \
-    && mkdir -p /home/noroot \
-    && groupadd -r noroot \
-    && useradd -r -g noroot -s /bin/bash -d /home/noroot noroot \
-    && chown -R noroot:noroot /home/noroot ${BUILD_PREFIX} /usr/local/lib
-
-USER noroot
-
-ENTRYPOINT ["/entrypoint.sh"]
@@ -1,15 +0,0 @@
-#!/bin/bash
-
-# fetch latest release tag
-CHATGPT_ON_WECHAT_TAG=`curl -sL "https://api.github.com/repos/zhayujie/chatgpt-on-wechat/releases/latest" | \
-     grep '"tag_name":' | \
-     sed -E 's/.*"([^"]+)".*/\1/'`
-
-# build image
-docker build -f Dockerfile.alpine \
-             --build-arg CHATGPT_ON_WECHAT_VER=$CHATGPT_ON_WECHAT_TAG \
-             -t zhayujie/chatgpt-on-wechat .
-
-# tag image
-docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:alpine
-docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:$CHATGPT_ON_WECHAT_TAG-alpine
@@ -1,15 +0,0 @@
-#!/bin/bash
-
-# fetch latest release tag
-CHATGPT_ON_WECHAT_TAG=`curl -sL "https://api.github.com/repos/zhayujie/chatgpt-on-wechat/releases/latest" | \
-     grep '"tag_name":' | \
-     sed -E 's/.*"([^"]+)".*/\1/'`
-
-# build image
-docker build -f Dockerfile.debian \
-             --build-arg CHATGPT_ON_WECHAT_VER=$CHATGPT_ON_WECHAT_TAG \
-             -t zhayujie/chatgpt-on-wechat .
-
-# tag image
-docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:debian
-docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:$CHATGPT_ON_WECHAT_TAG-debian
@@ -1,23 +0,0 @@
-FROM zhayujie/chatgpt-on-wechat:alpine
-
-LABEL maintainer="foo@bar.com"
-ARG TZ='Asia/Shanghai'
-
-USER root
-
-RUN apk add --no-cache \
-        ffmpeg  \
-        espeak \
-    && pip install --no-cache \
-        baidu-aip \
-        chardet \
-        SpeechRecognition
-
-# replace entrypoint
-ADD ./entrypoint.sh /entrypoint.sh
-
-RUN chmod +x /entrypoint.sh
-
-USER noroot
-
-ENTRYPOINT ["/entrypoint.sh"]
@@ -1,24 +0,0 @@
-FROM zhayujie/chatgpt-on-wechat:debian
-
-LABEL maintainer="foo@bar.com"
-ARG TZ='Asia/Shanghai'
-
-USER root
-
-RUN apt-get update  \
-    && apt-get install -y --no-install-recommends \
-        ffmpeg \
-        espeak  \
-    && pip install --no-cache \
-        baidu-aip \
-        chardet \
-        SpeechRecognition
-
-# replace entrypoint
-ADD ./entrypoint.sh /entrypoint.sh
-
-RUN chmod +x /entrypoint.sh
-
-USER noroot
-
-ENTRYPOINT ["/entrypoint.sh"]
@@ -1,24 +0,0 @@
-version: '2.0'
-services:
-  chatgpt-on-wechat:
-    build:
-      context: ./
-      dockerfile: Dockerfile.alpine
-    image: zhayujie/chatgpt-on-wechat-voice-reply
-    container_name: chatgpt-on-wechat-voice-reply
-    environment:
-      OPEN_AI_API_KEY: 'YOUR API KEY'
-      OPEN_AI_PROXY: ''
-      SINGLE_CHAT_PREFIX: '["bot", "@bot"]'
-      SINGLE_CHAT_REPLY_PREFIX: '"[bot] "'
-      GROUP_CHAT_PREFIX: '["@bot"]'
-      GROUP_NAME_WHITE_LIST: '["ChatGPT测试群", "ChatGPT测试群2"]'
-      IMAGE_CREATE_PREFIX: '["画", "看", "找"]'
-      CONVERSATION_MAX_TOKENS: 1000
-      SPEECH_RECOGNITION: 'true'
-      CHARACTER_DESC: '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'
-      EXPIRES_IN_SECONDS: 3600
-      VOICE_REPLY_VOICE: 'true'
-      BAIDU_APP_ID: 'YOUR BAIDU APP ID'
-      BAIDU_API_KEY: 'YOUR BAIDU API KEY'
-      BAIDU_SECRET_KEY: 'YOUR BAIDU SERVICE KEY'
@@ -1,117 +0,0 @@
-#!/bin/bash
-set -e
-
-# build prefix
-CHATGPT_ON_WECHAT_PREFIX=${CHATGPT_ON_WECHAT_PREFIX:-""}
-# path to config.json
-CHATGPT_ON_WECHAT_CONFIG_PATH=${CHATGPT_ON_WECHAT_CONFIG_PATH:-""}
-# execution command line
-CHATGPT_ON_WECHAT_EXEC=${CHATGPT_ON_WECHAT_EXEC:-""}
-
-OPEN_AI_API_KEY=${OPEN_AI_API_KEY:-""}
-OPEN_AI_PROXY=${OPEN_AI_PROXY:-""}
-SINGLE_CHAT_PREFIX=${SINGLE_CHAT_PREFIX:-""}
-SINGLE_CHAT_REPLY_PREFIX=${SINGLE_CHAT_REPLY_PREFIX:-""}
-GROUP_CHAT_PREFIX=${GROUP_CHAT_PREFIX:-""}
-GROUP_NAME_WHITE_LIST=${GROUP_NAME_WHITE_LIST:-""}
-IMAGE_CREATE_PREFIX=${IMAGE_CREATE_PREFIX:-""}
-CONVERSATION_MAX_TOKENS=${CONVERSATION_MAX_TOKENS:-""}
-SPEECH_RECOGNITION=${SPEECH_RECOGNITION:-""}
-CHARACTER_DESC=${CHARACTER_DESC:-""}
-EXPIRES_IN_SECONDS=${EXPIRES_IN_SECONDS:-""}
-
-VOICE_REPLY_VOICE=${VOICE_REPLY_VOICE:-""}
-BAIDU_APP_ID=${BAIDU_APP_ID:-""}
-BAIDU_API_KEY=${BAIDU_API_KEY:-""}
-BAIDU_SECRET_KEY=${BAIDU_SECRET_KEY:-""}
-
-# CHATGPT_ON_WECHAT_PREFIX is empty, use /app
-if [ "$CHATGPT_ON_WECHAT_PREFIX" == "" ] ; then
-    CHATGPT_ON_WECHAT_PREFIX=/app
-fi
-
-# CHATGPT_ON_WECHAT_CONFIG_PATH is empty, use '/app/config.json'
-if [ "$CHATGPT_ON_WECHAT_CONFIG_PATH" == "" ] ; then
-    CHATGPT_ON_WECHAT_CONFIG_PATH=$CHATGPT_ON_WECHAT_PREFIX/config.json
-fi
-
-# CHATGPT_ON_WECHAT_EXEC is empty, use ‘python app.py’
-if [ "$CHATGPT_ON_WECHAT_EXEC" == "" ] ; then
-    CHATGPT_ON_WECHAT_EXEC="python app.py"
-fi
-
-# modify content in config.json
-if [ "$OPEN_AI_API_KEY" != "" ] ; then
-    sed -i "s/\"open_ai_api_key\".*,$/\"open_ai_api_key\": \"$OPEN_AI_API_KEY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-else
-    echo -e "\033[31m[Warning] You need to set OPEN_AI_API_KEY before running!\033[0m"
-fi
-
-# use http_proxy as default
-if [ "$HTTP_PROXY" != "" ] ; then
-    sed -i "s/\"proxy\".*,$/\"proxy\": \"$HTTP_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$OPEN_AI_PROXY" != "" ] ; then
-    sed -i "s/\"proxy\".*,$/\"proxy\": \"$OPEN_AI_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$SINGLE_CHAT_PREFIX" != "" ] ; then
-    sed -i "s/\"single_chat_prefix\".*,$/\"single_chat_prefix\": $SINGLE_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$SINGLE_CHAT_REPLY_PREFIX" != "" ] ; then
-    sed -i "s/\"single_chat_reply_prefix\".*,$/\"single_chat_reply_prefix\": $SINGLE_CHAT_REPLY_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$GROUP_CHAT_PREFIX" != "" ] ; then
-    sed -i "s/\"group_chat_prefix\".*,$/\"group_chat_prefix\": $GROUP_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$GROUP_NAME_WHITE_LIST" != "" ] ; then
-    sed -i "s/\"group_name_white_list\".*,$/\"group_name_white_list\": $GROUP_NAME_WHITE_LIST,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$IMAGE_CREATE_PREFIX" != "" ] ; then
-    sed -i "s/\"image_create_prefix\".*,$/\"image_create_prefix\": $IMAGE_CREATE_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$CONVERSATION_MAX_TOKENS" != "" ] ; then
-    sed -i "s/\"conversation_max_tokens\".*,$/\"conversation_max_tokens\": $CONVERSATION_MAX_TOKENS,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$SPEECH_RECOGNITION" != "" ] ; then
-    sed -i "s/\"speech_recognition\".*,$/\"speech_recognition\": $SPEECH_RECOGNITION,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$CHARACTER_DESC" != "" ] ; then
-    sed -i "s/\"character_desc\".*,$/\"character_desc\": \"$CHARACTER_DESC\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$EXPIRES_IN_SECONDS" != "" ] ; then
-    sed -i "s/\"expires_in_seconds\".*$/\"expires_in_seconds\": $EXPIRES_IN_SECONDS/" $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-# append
-if [ "$BAIDU_SECRET_KEY" != "" ] ; then
-    sed -i "1a \ \ \"baidu_secret_key\": \"$BAIDU_SECRET_KEY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$BAIDU_API_KEY" != "" ] ; then
-    sed -i "1a \ \ \"baidu_api_key\": \"$BAIDU_API_KEY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$BAIDU_APP_ID" != "" ] ; then
-    sed -i "1a \ \ \"baidu_app_id\": \"$BAIDU_APP_ID\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-if [ "$VOICE_REPLY_VOICE" != "" ] ; then
-    sed -i "1a \ \ \"voice_reply_voice\": $VOICE_REPLY_VOICE," $CHATGPT_ON_WECHAT_CONFIG_PATH
-fi
-
-# go to prefix dir
-cd $CHATGPT_ON_WECHAT_PREFIX
-# excute
-$CHATGPT_ON_WECHAT_EXEC
-
-
@@ -1,20 +1,24 @@
 version: '2.0'
 services:
  chatgpt-on-wechat:
-    build:
-      context: ./
-      dockerfile: Dockerfile.alpine
    image: zhayujie/chatgpt-on-wechat
-    container_name: sample-chatgpt-on-wechat
+    container_name: chatgpt-on-wechat
+    security_opt:
+      - seccomp:unconfined
    environment:
      OPEN_AI_API_KEY: 'YOUR API KEY'
-      OPEN_AI_PROXY: ''
+      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"]'
      CONVERSATION_MAX_TOKENS: 1000
-      SPEECH_RECOGNITION: "False"
+      SPEECH_RECOGNITION: 'False'
      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。'
-      EXPIRES_IN_SECONDS: 3600
+      EXPIRES_IN_SECONDS: 3600
+      USE_GLOBAL_PLUGIN_CONFIG: 'True'
+      USE_LINKAI: 'False'
+      LINKAI_API_KEY: ''
+      LINKAI_APP_CODE: ''
@@ -1,16 +0,0 @@
-OPEN_AI_API_KEY=YOUR API KEY
-OPEN_AI_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"]
-CONVERSATION_MAX_TOKENS=1000
-SPEECH_RECOGNITION=false
-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。
-EXPIRES_IN_SECONDS=3600
-
-# Optional
-#CHATGPT_ON_WECHAT_PREFIX=/app
-#CHATGPT_ON_WECHAT_CONFIG_PATH=/app/config.json
-#CHATGPT_ON_WECHAT_EXEC=python app.py
@@ -1,26 +0,0 @@
-IMG:=`cat Name`
-MOUNT:=
-PORT_MAP:=
-DOTENV:=.env
-CONTAINER_NAME:=sample-chatgpt-on-wechat
-
-echo:
-	echo $(IMG)
-
-run_d:
-	docker rm $(CONTAINER_NAME) || echo
-	docker run -dt  --name $(CONTAINER_NAME) $(PORT_MAP) \
-			--env-file=$(DOTENV) \
-			$(MOUNT) $(IMG)
-
-run_i:
-	docker rm $(CONTAINER_NAME) || echo
-	docker run -it  --name $(CONTAINER_NAME) $(PORT_MAP) \
-			--env-file=$(DOTENV) \
-			$(MOUNT) $(IMG)
-
-stop:
-	docker stop $(CONTAINER_NAME)
-
-rm:     stop
-	docker rm $(CONTAINER_NAME)
@@ -1 +0,0 @@
-zhayujie/chatgpt-on-wechat
@@ -24,16 +24,17 @@ class Banwords(Plugin):
    def __init__(self):
        super().__init__()
        try:
+            # load config
+            conf = super().load_config()
            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)
+            if not conf:
+                # 配置不存在则写入默认配置
+                config_path = os.path.join(curdir, "config.json")
+                if not os.path.exists(config_path):
+                    conf = {"action": "ignore"}
+                    with open(config_path, "w") as f:
+                        json.dump(conf, f, indent=4)
+
            self.searchr = WordsSearch()
            self.action = conf["action"]
            banwords_path = os.path.join(curdir, "banwords.txt")
@@ -29,14 +29,9 @@ class BDunit(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 = super().load_config()
+            if not conf:
                raise Exception("config.json not found")
-            else:
-                with open(config_path, "r") as f:
-                    conf = json.load(f)
            self.service_id = conf["service_id"]
            self.api_key = conf["api_key"]
            self.secret_key = conf["secret_key"]
@@ -0,0 +1,38 @@
+{
+    "godcmd": {
+        "password": "",
+        "admin_users": []
+    },
+    "banwords": {
+        "action": "replace",
+        "reply_filter": true,
+        "reply_action": "ignore"
+    },
+    "tool": {
+        "tools": [
+            "python",
+            "url-get",
+            "terminal",
+            "meteo-weather"
+        ],
+        "kwargs": {
+            "top_k_results": 2,
+            "no_default": false,
+            "model_name": "gpt-3.5-turbo"
+        }
+    },
+    "linkai": {
+        "group_app_map": {
+            "测试群1": "default",
+            "测试群2": "Kv2fXJcH"
+        },
+        "midjourney": {
+            "enabled": true,
+            "auto_translate": true,
+            "img_proxy": true,
+            "max_tasks": 3,
+            "max_tasks_per_user": 1,
+            "use_image_create_prefix": true
+        }
+    }
+}
@@ -13,7 +13,7 @@ from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
 from common import const
 from common.log import logger
-from config import conf, load_config
+from config import conf, load_config, global_config
 from plugins import *

 # 定义指令集
@@ -178,16 +178,13 @@ 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)
+        config_path = os.path.join(os.path.dirname(__file__), "config.json")
+        gconf = super().load_config()
+        if not gconf:
+            if not os.path.exists(config_path):
+                gconf = {"password": "", "admin_users": []}
+                with open(config_path, "w") as f:
+                    json.dump(gconf, f, indent=4)
        if gconf["password"] == "":
            self.temp_password = "".join(random.sample(string.digits, 4))
            logger.info("[Godcmd] 因未设置口令，本次的临时口令为%s。" % self.temp_password)
@@ -429,9 +426,11 @@ class Godcmd(Plugin):
        password = args[0]
        if password == self.password:
            self.admin_users.append(userid)
+            global_config["admin_users"].append(userid)
            return True, "认证成功"
        elif password == self.temp_password:
            self.admin_users.append(userid)
+            global_config["admin_users"].append(userid)
            return True, "认证成功，请尽快设置口令"
        else:
            return False, "认证失败"
@@ -34,14 +34,14 @@ class Hello(Plugin):
            e_context["context"].type = ContextType.TEXT
            msg: ChatMessage = e_context["context"]["msg"]
            e_context["context"].content = f'请你随机使用一种风格说一句问候语来欢迎新用户"{msg.actual_user_nickname}"加入群聊。'
-            e_context.action = EventAction.CONTINUE  # 事件继续，交付给下个插件或默认逻辑
+            e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑
            return

        if e_context["context"].type == ContextType.PATPAT:
            e_context["context"].type = ContextType.TEXT
            msg: ChatMessage = e_context["context"]["msg"]
            e_context["context"].content = f"请你随机使用一种风格介绍你自己，并告诉用户输入#help可以查看帮助信息。"
-            e_context.action = EventAction.CONTINUE  # 事件继续，交付给下个插件或默认逻辑
+            e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑
            return

        content = e_context["context"].content
@@ -54,9 +54,18 @@ class Keyword(Plugin):
            logger.debug(f"[keyword] 匹配到关键字【{content}】")
            reply_text = self.keyword[content]

-            reply = Reply()
-            reply.type = ReplyType.TEXT
-            reply.content = reply_text
+            # 判断匹配内容的类型
+            if (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".jpg", ".jpeg", ".png", ".gif", ".webp"]):
+                # 如果是以 http:// 或 https:// 开头，且.jpg/.jpeg/.png/.gif结尾，则认为是图片 URL
+                reply = Reply()
+                reply.type = ReplyType.IMAGE_URL
+                reply.content = reply_text
+            else:
+            # 否则认为是普通文本
+                reply = Reply()
+                reply.type = ReplyType.TEXT
+                reply.content = reply_text
+            
            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

@@ -0,0 +1,58 @@
+## 插件说明
+
+基于 LinkAI 提供的知识库、Midjourney绘画等能力对机器人的功能进行增强。地址: https://chat.link-ai.tech/console
+
+## 插件配置
+
+将 `plugins/linkai` 下的 `config.json.template` 复制为 `config.json`。如果是`docker`部署，可通过映射 plugins/config.json 来完成配置。以下是配置项说明：
+
+```bash
+{
+    "group_app_map": {            # 群聊 和 应用编码 的映射关系
+        "测试群1": "default",      # 表示在名称为 "测试群1" 的群聊中将使用app_code 为 default 的应用
+        "测试群2": "Kv2fXJcH"
+    },
+    "midjourney": {
+        "enabled": true,          # midjourney 绘画开关
+        "auto_translate": true,   # 是否自动将提示词翻译为英文
+        "img_proxy": true,        # 是否对生成的图片使用代理，如果你是国外服务器，将这一项设置为false会获得更快的生成速度
+        "max_tasks": 3,           # 支持同时提交的总任务个数
+        "max_tasks_per_user": 1,  # 支持单个用户同时提交的任务个数
+        "use_image_create_prefix": true   # 是否使用全局的绘画触发词，如果开启将同时支持由`config.json`中的 image_create_prefix 配置触发
+    }
+}
+
+```
+注意：实际 `config.json` 配置中应保证json格式，不应携带 '#' 及后面的注释。
+
+## 插件使用
+
+> 使用插件中的知识库管理功能需要首先开启`linkai`对话，依赖于全局 `config.json` 中的 `use_linkai` 和 `linkai_api_key` 配置；midjourney绘画功能则只需填写 `linkai_api_key` 配置。
+
+完成配置后运行项目，会自动运行插件，输入 `#help linkai` 可查看插件功能。
+
+### 1.知识库管理功能
+
+提供在不同群聊使用不同应用的功能。可以在上述 `group_app_map` 配置中固定映射关系，也可以通过指令在群中快速完成切换。
+
+应用切换指令需要首先完成管理员 (`godcmd`) 插件的认证，然后按以下格式输入：
+
+`$linkai app {app_code}`
+
+例如输入 `$linkai app Kv2fXJcH`，即将当前群聊与 app_code为 Kv2fXJcH 的应用绑定。
+
+### 2.Midjourney绘画功能
+
+指令格式：
+
+```
+ - 图片生成: $mj 描述词1, 描述词2..
+ - 图片放大: $mju 图片ID 图片序号
+```
+
+例如：
+
+```
+"$mj a little cat, white --ar 9:16"
+"$mju 1105592717188272288 2"
+```
@@ -0,0 +1 @@
+from .linkai import *
@@ -0,0 +1,14 @@
+{
+    "group_app_map": {
+        "测试群1": "default",
+        "测试群2": "Kv2fXJcH"
+    },
+    "midjourney": {
+        "enabled": true,
+        "auto_translate": true,
+        "img_proxy": true,
+        "max_tasks": 3,
+        "max_tasks_per_user": 1,
+        "use_image_create_prefix": true
+    }
+}
@@ -0,0 +1,137 @@
+import asyncio
+import json
+import threading
+from concurrent.futures import ThreadPoolExecutor
+
+import plugins
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from config import conf, global_config
+from plugins import *
+from .midjourney import MJBot, TaskType
+
+# 任务线程池
+task_thread_pool = ThreadPoolExecutor(max_workers=4)
+
+
+@plugins.register(
+    name="linkai",
+    desc="A plugin that supports knowledge base and midjourney drawing.",
+    version="0.1.0",
+    author="https://link-ai.tech",
+)
+class LinkAI(Plugin):
+    def __init__(self):
+        super().__init__()
+        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        self.config = super().load_config()
+        if self.config:
+            self.mj_bot = MJBot(self.config.get("midjourney"))
+        logger.info("[LinkAI] inited")
+
+    def on_handle_context(self, e_context: EventContext):
+        """
+        消息处理逻辑
+        :param e_context: 消息上下文
+        """
+        if not self.config:
+            return
+
+        context = e_context['context']
+        if context.type not in [ContextType.TEXT, ContextType.IMAGE, ContextType.IMAGE_CREATE]:
+            # filter content no need solve
+            return
+
+        mj_type = self.mj_bot.judge_mj_task_type(e_context)
+        if mj_type:
+            # MJ作图任务处理
+            self.mj_bot.process_mj_task(mj_type, e_context)
+            return
+
+        if context.content.startswith(f"{_get_trigger_prefix()}linkai"):
+            # 应用管理功能
+            self._process_admin_cmd(e_context)
+            return
+
+        if self._is_chat_task(e_context):
+            # 文本对话任务处理
+            self._process_chat_task(e_context)
+
+    # 插件管理功能
+    def _process_admin_cmd(self, e_context: EventContext):
+        context = e_context['context']
+        cmd = context.content.split()
+        if len(cmd) == 1 or (len(cmd) == 2 and cmd[1] == "help"):
+            _set_reply_text(self.get_help_text(verbose=True), e_context, level=ReplyType.INFO)
+            return
+        if len(cmd) == 3 and cmd[1] == "app":
+            if not context.kwargs.get("isgroup"):
+                _set_reply_text("该指令需在群聊中使用", e_context, level=ReplyType.ERROR)
+                return
+            if context.kwargs.get("msg").actual_user_id not in global_config["admin_users"]:
+                _set_reply_text("需要管理员权限执行", e_context, level=ReplyType.ERROR)
+                return
+            app_code = cmd[2]
+            group_name = context.kwargs.get("msg").from_user_nickname
+            group_mapping = self.config.get("group_app_map")
+            if group_mapping:
+                group_mapping[group_name] = app_code
+            else:
+                self.config["group_app_map"] = {group_name: app_code}
+            # 保存插件配置
+            super().save_config(self.config)
+            _set_reply_text(f"应用设置成功: {app_code}", e_context, level=ReplyType.INFO)
+        else:
+            _set_reply_text(f"指令错误，请输入{_get_trigger_prefix()}linkai help 获取帮助", e_context, level=ReplyType.INFO)
+            return
+
+    # LinkAI 对话任务处理
+    def _is_chat_task(self, e_context: EventContext):
+        context = e_context['context']
+        # 群聊应用管理
+        return self.config.get("group_app_map") and context.kwargs.get("isgroup")
+
+    def _process_chat_task(self, e_context: EventContext):
+        """
+        处理LinkAI对话任务
+        :param e_context: 对话上下文
+        """
+        context = e_context['context']
+        # 群聊应用管理
+        group_name = context.kwargs.get("msg").from_user_nickname
+        app_code = self._fetch_group_app_code(group_name)
+        if app_code:
+            context.kwargs['app_code'] = app_code
+
+    def _fetch_group_app_code(self, group_name: str) -> str:
+        """
+        根据群聊名称获取对应的应用code
+        :param group_name: 群聊名称
+        :return: 应用code
+        """
+        group_mapping = self.config.get("group_app_map")
+        if group_mapping:
+            app_code = group_mapping.get(group_name) or group_mapping.get("ALL_GROUP")
+            return app_code
+
+    def get_help_text(self, verbose=False, **kwargs):
+        trigger_prefix = _get_trigger_prefix()
+        help_text = "用于集成 LinkAI 提供的知识库、Midjourney绘画等能力。\n\n"
+        if not verbose:
+            return help_text
+        help_text += f'📖 知识库\n - 群聊中指定应用: {trigger_prefix}linkai app 应用编码\n\n例如: \n"$linkai app Kv2fXJcH"\n\n'
+        help_text += f"🎨 绘画\n - 生成: {trigger_prefix}mj 描述词1, 描述词2.. \n - 放大: {trigger_prefix}mju 图片ID 图片序号\n\n例如：\n\"{trigger_prefix}mj a little cat, white --ar 9:16\"\n\"{trigger_prefix}mju 1105592717188272288 2\""
+        return help_text
+
+
+# 静态方法
+def _set_reply_text(content: str, e_context: EventContext, level: ReplyType = ReplyType.ERROR):
+    reply = Reply(level, content)
+    e_context["reply"] = reply
+    e_context.action = EventAction.BREAK_PASS
+
+
+def _get_trigger_prefix():
+    return conf().get("plugin_trigger_prefix", "$")
@@ -0,0 +1,391 @@
+from enum import Enum
+from config import conf
+from common.log import logger
+import requests
+import threading
+import time
+from bridge.reply import Reply, ReplyType
+import aiohttp
+import asyncio
+from bridge.context import ContextType
+from plugins import EventContext, EventAction
+
+INVALID_REQUEST = 410
+
+class TaskType(Enum):
+    GENERATE = "generate"
+    UPSCALE = "upscale"
+    VARIATION = "variation"
+    RESET = "reset"
+
+
+class Status(Enum):
+    PENDING = "pending"
+    FINISHED = "finished"
+    EXPIRED = "expired"
+    ABORTED = "aborted"
+
+    def __str__(self):
+        return self.name
+
+
+class TaskMode(Enum):
+    FAST = "fast"
+    RELAX = "relax"
+
+
+class MJTask:
+    def __init__(self, id, user_id: str, task_type: TaskType, raw_prompt=None, expires: int = 60 * 30,
+                 status=Status.PENDING):
+        self.id = id
+        self.user_id = user_id
+        self.task_type = task_type
+        self.raw_prompt = raw_prompt
+        self.send_func = None  # send_func(img_url)
+        self.expiry_time = time.time() + expires
+        self.status = status
+        self.img_url = None  # url
+        self.img_id = None
+
+    def __str__(self):
+        return f"id={self.id}, user_id={self.user_id}, task_type={self.task_type}, status={self.status}, img_id={self.img_id}"
+
+
+# midjourney bot
+class MJBot:
+    def __init__(self, config):
+        self.base_url = "https://api.link-ai.chat/v1/img/midjourney"
+
+        self.headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
+        self.config = config
+        self.tasks = {}
+        self.temp_dict = {}
+        self.tasks_lock = threading.Lock()
+        self.event_loop = asyncio.new_event_loop()
+
+    def judge_mj_task_type(self, e_context: EventContext):
+        """
+        判断MJ任务的类型
+        :param e_context: 上下文
+        :return: 任务类型枚举
+        """
+        if not self.config or not self.config.get("enabled"):
+            return None
+        trigger_prefix = conf().get("plugin_trigger_prefix", "$")
+        context = e_context['context']
+        if context.type == ContextType.TEXT:
+            cmd_list = context.content.split(maxsplit=1)
+            if cmd_list[0].lower() == f"{trigger_prefix}mj":
+                return TaskType.GENERATE
+            elif cmd_list[0].lower() == f"{trigger_prefix}mju":
+                return TaskType.UPSCALE
+        elif context.type == ContextType.IMAGE_CREATE and self.config.get("use_image_create_prefix"):
+            return TaskType.GENERATE
+
+    def process_mj_task(self, mj_type: TaskType, e_context: EventContext):
+        """
+        处理mj任务
+        :param mj_type: mj任务类型
+        :param e_context: 对话上下文
+        """
+        context = e_context['context']
+        session_id = context["session_id"]
+        cmd = context.content.split(maxsplit=1)
+        if len(cmd) == 1 and context.type == ContextType.TEXT:
+            self._set_reply_text(self.get_help_text(verbose=True), e_context, level=ReplyType.INFO)
+            return
+
+        if not self._check_rate_limit(session_id, e_context):
+            logger.warn("[MJ] midjourney task exceed rate limit")
+            return
+
+        if mj_type == TaskType.GENERATE:
+            if context.type == ContextType.IMAGE_CREATE:
+                raw_prompt = context.content
+            else:
+                # 图片生成
+                raw_prompt = cmd[1]
+            reply = self.generate(raw_prompt, session_id, e_context)
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS
+            return
+
+        elif mj_type == TaskType.UPSCALE:
+            # 图片放大
+            clist = cmd[1].split()
+            if len(clist) < 2:
+                self._set_reply_text(f"{cmd[0]} 命令缺少参数", e_context)
+                return
+            img_id = clist[0]
+            index = int(clist[1])
+            if index < 1 or index > 4:
+                self._set_reply_text(f"图片序号 {index} 错误，应在 1 至 4 之间", e_context)
+                return
+            key = f"{TaskType.UPSCALE.name}_{img_id}_{index}"
+            if self.temp_dict.get(key):
+                self._set_reply_text(f"第 {index} 张图片已经放大过了", e_context)
+                return
+            # 图片放大操作
+            reply = self.upscale(session_id, img_id, index, e_context)
+            e_context['reply'] = reply
+            e_context.action = EventAction.BREAK_PASS
+            return
+
+        else:
+            self._set_reply_text(f"暂不支持该命令", e_context)
+
+    def generate(self, prompt: str, user_id: str, e_context: EventContext) -> Reply:
+        """
+        图片生成
+        :param prompt: 提示词
+        :param user_id: 用户id
+        :param e_context: 对话上下文
+        :return: 任务ID
+        """
+        logger.info(f"[MJ] image generate, prompt={prompt}")
+        mode = self._fetch_mode(prompt)
+        body = {"prompt": prompt, "mode": mode, "auto_translate": self.config.get("auto_translate")}
+        if not self.config.get("img_proxy"):
+            body["img_proxy"] = False
+        res = requests.post(url=self.base_url + "/generate", json=body, headers=self.headers, timeout=(5, 40))
+        if res.status_code == 200:
+            res = res.json()
+            logger.debug(f"[MJ] image generate, res={res}")
+            if res.get("code") == 200:
+                task_id = res.get("data").get("task_id")
+                real_prompt = res.get("data").get("real_prompt")
+                if mode == TaskMode.RELAX.value:
+                    time_str = "1~10分钟"
+                else:
+                    time_str = "1分钟"
+                content = f"🚀您的作品将在{time_str}左右完成，请耐心等待\n- - - - - - - - -\n"
+                if real_prompt:
+                    content += f"初始prompt: {prompt}\n转换后prompt: {real_prompt}"
+                else:
+                    content += f"prompt: {prompt}"
+                reply = Reply(ReplyType.INFO, content)
+                task = MJTask(id=task_id, status=Status.PENDING, raw_prompt=prompt, user_id=user_id,
+                              task_type=TaskType.GENERATE)
+                # put to memory dict
+                self.tasks[task.id] = task
+                # asyncio.run_coroutine_threadsafe(self.check_task(task, e_context), self.event_loop)
+                self._do_check_task(task, e_context)
+                return reply
+        else:
+            res_json = res.json()
+            logger.error(f"[MJ] generate error, msg={res_json.get('message')}, status_code={res.status_code}")
+            if res.status_code == INVALID_REQUEST:
+                reply = Reply(ReplyType.ERROR, "图片生成失败，请检查提示词参数或内容")
+            else:
+                reply = Reply(ReplyType.ERROR, "图片生成失败，请稍后再试")
+            return reply
+
+    def upscale(self, user_id: str, img_id: str, index: int, e_context: EventContext) -> Reply:
+        logger.info(f"[MJ] image upscale, img_id={img_id}, index={index}")
+        body = {"type": TaskType.UPSCALE.name, "img_id": img_id, "index": index}
+        if not self.config.get("img_proxy"):
+            body["img_proxy"] = False
+        res = requests.post(url=self.base_url + "/operate", json=body, headers=self.headers, timeout=(5, 40))
+        logger.debug(res)
+        if res.status_code == 200:
+            res = res.json()
+            if res.get("code") == 200:
+                task_id = res.get("data").get("task_id")
+                logger.info(f"[MJ] image upscale processing, task_id={task_id}")
+                content = f"🔎图片正在放大中，请耐心等待"
+                reply = Reply(ReplyType.INFO, content)
+                task = MJTask(id=task_id, status=Status.PENDING, user_id=user_id, task_type=TaskType.UPSCALE)
+                # put to memory dict
+                self.tasks[task.id] = task
+                key = f"{TaskType.UPSCALE.name}_{img_id}_{index}"
+                self.temp_dict[key] = True
+                # asyncio.run_coroutine_threadsafe(self.check_task(task, e_context), self.event_loop)
+                self._do_check_task(task, e_context)
+                return reply
+        else:
+            error_msg = ""
+            if res.status_code == 461:
+                error_msg = "请输入正确的图片ID"
+            res_json = res.json()
+            logger.error(f"[MJ] upscale error, msg={res_json.get('message')}, status_code={res.status_code}")
+            reply = Reply(ReplyType.ERROR, error_msg or "图片生成失败，请稍后再试")
+            return reply
+
+    def check_task_sync(self, task: MJTask, e_context: EventContext):
+        logger.debug(f"[MJ] start check task status, {task}")
+        max_retry_times = 90
+        while max_retry_times > 0:
+            time.sleep(10)
+            url = f"{self.base_url}/tasks/{task.id}"
+            try:
+                res = requests.get(url, headers=self.headers, timeout=8)
+                if res.status_code == 200:
+                    res_json = res.json()
+                    logger.debug(f"[MJ] task check res sync, task_id={task.id}, status={res.status_code}, "
+                                 f"data={res_json.get('data')}, thread={threading.current_thread().name}")
+                    if res_json.get("data") and res_json.get("data").get("status") == Status.FINISHED.name:
+                        # process success res
+                        if self.tasks.get(task.id):
+                            self.tasks[task.id].status = Status.FINISHED
+                        self._process_success_task(task, res_json.get("data"), e_context)
+                        return
+                    max_retry_times -= 1
+                else:
+                    res_json = res.json()
+                    logger.warn(f"[MJ] image check error, status_code={res.status_code}, res={res_json}")
+                    max_retry_times -= 20
+            except Exception as e:
+                max_retry_times -= 20
+                logger.warn(e)
+        logger.warn("[MJ] end from poll")
+        if self.tasks.get(task.id):
+            self.tasks[task.id].status = Status.EXPIRED
+
+    async def check_task_async(self, task: MJTask, e_context: EventContext):
+        try:
+            logger.debug(f"[MJ] start check task status, {task}")
+            max_retry_times = 90
+            while max_retry_times > 0:
+                await asyncio.sleep(10)
+                async with aiohttp.ClientSession() as session:
+                    url = f"{self.base_url}/tasks/{task.id}"
+                    try:
+                        async with session.get(url, headers=self.headers) as res:
+                            if res.status == 200:
+                                res_json = await res.json()
+                                logger.debug(f"[MJ] task check res, task_id={task.id}, status={res.status}, "
+                                             f"data={res_json.get('data')}, thread={threading.current_thread().name}")
+                                if res_json.get("data") and res_json.get("data").get("status") == Status.FINISHED.name:
+                                    # process success res
+                                    if self.tasks.get(task.id):
+                                        self.tasks[task.id].status = Status.FINISHED
+                                    self._process_success_task(task, res_json.get("data"), e_context)
+                                    return
+                            else:
+                                res_json = await res.json()
+                                logger.warn(f"[MJ] image check error, status_code={res.status}, res={res_json}")
+                                max_retry_times -= 20
+                    except Exception as e:
+                        max_retry_times -= 20
+                        logger.warn(e)
+                max_retry_times -= 1
+            logger.warn("[MJ] end from poll")
+            if self.tasks.get(task.id):
+                self.tasks[task.id].status = Status.EXPIRED
+        except Exception as e:
+            logger.error(e)
+
+    def _do_check_task(self, task: MJTask, e_context: EventContext):
+        threading.Thread(target=self.check_task_sync, args=(task, e_context)).start()
+
+    def _process_success_task(self, task: MJTask, res: dict, e_context: EventContext):
+        """
+        处理任务成功的结果
+        :param task: MJ任务
+        :param res: 请求结果
+        :param e_context: 对话上下文
+        """
+        # channel send img
+        task.status = Status.FINISHED
+        task.img_id = res.get("img_id")
+        task.img_url = res.get("img_url")
+        logger.info(f"[MJ] task success, task_id={task.id}, img_id={task.img_id}, img_url={task.img_url}")
+
+        # send img
+        reply = Reply(ReplyType.IMAGE_URL, task.img_url)
+        channel = e_context["channel"]
+        channel._send(reply, e_context["context"])
+
+        # send info
+        trigger_prefix = conf().get("plugin_trigger_prefix", "$")
+        text = ""
+        if task.task_type == TaskType.GENERATE:
+            text = f"🎨绘画完成!\nprompt: {task.raw_prompt}\n- - - - - - - - -\n图片ID: {task.img_id}"
+            text += f"\n\n🔎可使用 {trigger_prefix}mju 命令放大指定图片\n"
+            text += f"例如：\n{trigger_prefix}mju {task.img_id} 1"
+            reply = Reply(ReplyType.INFO, text)
+            channel._send(reply, e_context["context"])
+
+        self._print_tasks()
+        return
+
+    def _check_rate_limit(self, user_id: str, e_context: EventContext) -> bool:
+        """
+        midjourney任务限流控制
+        :param user_id: 用户id
+        :param e_context: 对话上下文
+        :return: 任务是否能够生成, True:可以生成, False: 被限流
+        """
+        tasks = self.find_tasks_by_user_id(user_id)
+        task_count = len([t for t in tasks if t.status == Status.PENDING])
+        if task_count >= self.config.get("max_tasks_per_user"):
+            reply = Reply(ReplyType.INFO, "您的Midjourney作图任务数已达上限，请稍后再试")
+            e_context["reply"] = reply
+            e_context.action = EventAction.BREAK_PASS
+            return False
+        task_count = len([t for t in self.tasks.values() if t.status == Status.PENDING])
+        if task_count >= self.config.get("max_tasks"):
+            reply = Reply(ReplyType.INFO, "Midjourney作图任务数已达上限，请稍后再试")
+            e_context["reply"] = reply
+            e_context.action = EventAction.BREAK_PASS
+            return False
+        return True
+
+    def _fetch_mode(self, prompt) -> str:
+        mode = self.config.get("mode")
+        if "--relax" in prompt or mode == TaskMode.RELAX.value:
+            return TaskMode.RELAX.value
+        return mode or TaskMode.FAST.value
+
+    def _run_loop(self, loop: asyncio.BaseEventLoop):
+        """
+        运行事件循环，用于轮询任务的线程
+        :param loop: 事件循环
+        """
+        loop.run_forever()
+        loop.stop()
+
+    def _print_tasks(self):
+        for id in self.tasks:
+            logger.debug(f"[MJ] current task: {self.tasks[id]}")
+
+    def _set_reply_text(self, content: str, e_context: EventContext, level: ReplyType = ReplyType.ERROR):
+        """
+        设置回复文本
+        :param content: 回复内容
+        :param e_context: 对话上下文
+        :param level: 回复等级
+        """
+        reply = Reply(level, content)
+        e_context["reply"] = reply
+        e_context.action = EventAction.BREAK_PASS
+
+    def get_help_text(self, verbose=False, **kwargs):
+        trigger_prefix = conf().get("plugin_trigger_prefix", "$")
+        help_text = "🎨利用Midjourney进行画图\n\n"
+        if not verbose:
+            return help_text
+        help_text += f" - 生成: {trigger_prefix}mj 描述词1, 描述词2.. \n - 放大: {trigger_prefix}mju 图片ID 图片序号\n\n例如：\n\"{trigger_prefix}mj a little cat, white --ar 9:16\"\n\"{trigger_prefix}mju 1105592717188272288 2\""
+
+        return help_text
+
+    def find_tasks_by_user_id(self, user_id) -> list:
+        result = []
+        with self.tasks_lock:
+            now = time.time()
+            for task in self.tasks.values():
+                if task.status == Status.PENDING and now > task.expiry_time:
+                    task.status = Status.EXPIRED
+                    logger.info(f"[MJ] {task} expired")
+                if task.user_id == user_id:
+                    result.append(task)
+        return result
+
+
+def check_prefix(content, prefix_list):
+    if not prefix_list:
+        return None
+    for prefix in prefix_list:
+        if content.startswith(prefix):
+            return prefix
+    return None
@@ -1,6 +1,45 @@
+import os
+import json
+from config import pconf, plugin_config, conf
+from common.log import logger
+
+
 class Plugin:
    def __init__(self):
        self.handlers = {}

+    def load_config(self) -> dict:
+        """
+        加载当前插件配置
+        :return: 插件配置字典
+        """
+        # 优先获取 plugins/config.json 中的全局配置
+        plugin_conf = pconf(self.name)
+        if not plugin_conf or not conf().get("use_global_plugin_config"):
+            # 全局配置不存在 或者 未开启全局配置开关，则获取插件目录下的配置
+            plugin_config_path = os.path.join(self.path, "config.json")
+            if os.path.exists(plugin_config_path):
+                with open(plugin_config_path, "r") as f:
+                    plugin_conf = json.load(f)
+        logger.debug(f"loading plugin config, plugin_name={self.name}, conf={plugin_conf}")
+        return plugin_conf
+
+    def save_config(self, config: dict):
+        try:
+            plugin_config[self.name] = config
+            # 写入全局配置
+            global_config_path = "./plugins/config.json"
+            if os.path.exists(global_config_path):
+                with open(global_config_path, "w", encoding='utf-8') as f:
+                    json.dump(plugin_config, f, indent=4, ensure_ascii=False)
+            # 写入插件配置
+            plugin_config_path = os.path.join(self.path, "config.json")
+            if os.path.exists(plugin_config_path):
+                with open(plugin_config_path, "w", encoding='utf-8') as f:
+                    json.dump(config, f, indent=4, ensure_ascii=False)
+
+        except Exception as e:
+            logger.warn("save plugin config failed: {}".format(e))
+
    def get_help_text(self, **kwargs):
        return "暂无帮助信息"
@@ -9,7 +9,7 @@ import sys
 from common.log import logger
 from common.singleton import singleton
 from common.sorted_dict import SortedDict
-from config import conf
+from config import conf, write_plugin_config

 from .event import *

@@ -62,6 +62,28 @@ class PluginManager:
            self.save_config()
        return pconf

+    @staticmethod
+    def _load_all_config():
+        """
+        背景: 目前插件配置存放于每个插件目录的config.json下，docker运行时不方便进行映射，故增加统一管理的入口，优先
+        加载 plugins/config.json，原插件目录下的config.json 不受影响
+
+        从 plugins/config.json 中加载所有插件的配置并写入 config.py 的全局配置中，供插件中使用
+        插件实例中通过 config.pconf(plugin_name) 即可获取该插件的配置
+        """
+        all_config_path = "./plugins/config.json"
+        try:
+            if os.path.exists(all_config_path):
+                # read from all plugins config
+                with open(all_config_path, "r", encoding="utf-8") as f:
+                    all_conf = json.load(f)
+                    logger.info(f"load all config from plugins/config.json: {all_conf}")
+
+                # write to global config
+                write_plugin_config(all_conf)
+        except Exception as e:
+            logger.error(e)
+
    def scan_plugins(self):
        logger.info("Scaning plugins ...")
        plugins_dir = "./plugins"
@@ -88,7 +110,7 @@ class PluginManager:
                            self.loaded[plugin_path] = importlib.import_module(import_path)
                        self.current_plugin_path = None
                    except Exception as e:
-                        logger.exception("Failed to import plugin %s: %s" % (plugin_name, e))
+                        logger.warn("Failed to import plugin %s: %s" % (plugin_name, e))
                        continue
        pconf = self.pconf
        news = [self.plugins[name] for name in self.plugins]
@@ -123,7 +145,7 @@ class PluginManager:
                    try:
                        instance = plugincls()
                    except Exception as e:
-                        logger.exception("Failed to init %s, diabled. %s" % (name, e))
+                        logger.warn("Failed to init %s, diabled. %s" % (name, e))
                        self.disable_plugin(name)
                        failed_plugins.append(name)
                        continue
@@ -149,6 +171,8 @@ class PluginManager:
    def load_plugins(self):
        self.load_config()
        self.scan_plugins()
+        # 加载全量插件配置
+        self._load_all_config()
        pconf = self.pconf
        logger.debug("plugins.json config={}".format(pconf))
        for name, plugin in pconf["plugins"].items():
@@ -11,6 +11,10 @@
    "summary": {
      "url": "https://github.com/lanvent/plugin_summary.git",
      "desc": "总结聊天记录的插件"
+    },
+    "timetask": {
+      "url": "https://github.com/haikerapples/timetask.git",
+      "desc": "一款定时任务系统的插件"
    }
  }
 }
@@ -114,18 +114,19 @@ $tool reset: 重置工具。
 ---

 ###### 注1：带*工具需要获取api-key才能使用(在config.json内的kwargs添加项)，部分工具需要外网支持  
-#### [申请方法](https://github.com/goldfishh/chatgpt-tool-hub/blob/master/docs/apply_optional_tool.md)
+## [工具的api申请方法](https://github.com/goldfishh/chatgpt-tool-hub/blob/master/docs/apply_optional_tool.md)

 ## config.json 配置说明
-###### 默认工具无需配置，其它工具需手动配置，一个例子：
+###### 默认工具无需配置，其它工具需手动配置，以增加morning-news和bing-search两个工具为例：
 ```json
 {
-  "tools": ["wikipedia", "你想要添加的其他工具"],  // 填入你想用到的额外工具名
+  "tools": ["bing-search", "news", "你想要添加的其他工具"],  // 填入你想用到的额外工具名，这里加入了工具"bing-search"和工具"news"(news工具会自动加载morning-news、finance-news等子工具)
  "kwargs": {
      "debug": true, // 当你遇到问题求助时，需要配置
      "request_timeout": 120,  // openai接口超时时间
      "no_default": false,  // 是否不使用默认的4个工具
-      // 带*工具需要申请api-key，在这里填入，api_name参考前述`申请方法`
+      "bing_subscription_key": "4871f273a4804743",//带*工具需要申请api-key，这里填入了工具bing-search对应的api，api_name参考前述`工具的api申请方法`
+      "morning_news_api_key": "5w1kjNh9VQlUc",// 这里填入了morning-news对应的api，
  }
 }

@@ -10,7 +10,6 @@ from bridge.bridge import Bridge
 from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
 from common import const
-from common.log import logger
 from config import conf
 from plugins import *

@@ -119,15 +118,8 @@ class Tool(Plugin):
        return

    def _read_json(self) -> dict:
-        curdir = os.path.dirname(__file__)
-        config_path = os.path.join(curdir, "config.json")
-        tool_config = {"tools": [], "kwargs": {}}
-        if not os.path.exists(config_path):
-            return tool_config
-        else:
-            with open(config_path, "r") as f:
-                tool_config = json.load(f)
-        return tool_config
+        default_config = {"tools": [], "kwargs": {}}
+        return super().load_config() or default_config

    def _build_tool_kwargs(self, kwargs: dict):
        tool_model_name = kwargs.get("model_name")
@@ -137,6 +129,7 @@ class Tool(Plugin):
            "debug": kwargs.get("debug", False),
            "openai_api_key": conf().get("open_ai_api_key", ""),
            "open_ai_api_base": conf().get("open_ai_api_base", "https://api.openai.com/v1"),
+            "deployment_id": conf().get("azure_deployment_id", ""),
            "proxy": conf().get("proxy", ""),
            "request_timeout": request_timeout if request_timeout else conf().get("request_timeout", 120),
            # note: 目前tool暂未对其他模型测试，但这里仍对配置来源做了优先级区分，一般插件配置可覆盖全局配置
@@ -25,4 +25,4 @@ wechatpy
 # chatgpt-tool-hub plugin

 --extra-index-url https://pypi.python.org/simple
-chatgpt_tool_hub==0.4.4
+chatgpt_tool_hub==0.4.6
@@ -1,8 +1,8 @@
-openai==0.27.2
+openai>=0.27.8
 HTMLParser>=0.0.2
 PyQRCode>=1.2.1
 qrcode>=7.4.2
 requests>=2.28.2
 chardet>=5.1.0
 Pillow
-pre-commit
+pre-commit
Author	SHA1	Message	Date
zhayujie	ca916b7ce5	fix: default to fast mode	2023-07-31 21:40:50 +08:00
zhayujie	01e02934da	Merge pull request #1334 from zyqfork/master azure api add api-version https://learn.microsoft.com/zh-cn/azure/ai-serv…	2023-07-31 18:40:06 +08:00
zhayujie	c81a79f7b9	Merge pull request #1104 from mari1995/feat_my_msg feat: 手机上回复消息，不触发机器人	2023-07-31 18:02:41 +08:00
zhayujie	1133648bf6	Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat	2023-07-31 17:58:06 +08:00
zhayujie	e05bc541d7	Merge pull request #1346 from befantasy/patch-1 Update keyword.py 增加返回图片的功能	2023-07-31 17:53:46 +08:00
zhayujie	d689d20482	docs: update README.md	2023-07-31 17:52:05 +08:00
zhayujie	39dd99b272	Merge pull request #1343 from zhayujie/feat-1.3.4 feat: add midjourney and app manager plugin	2023-07-31 17:15:22 +08:00
zhayujie	cda21acb43	feat: use new linkai completion api	2023-07-31 16:11:33 +08:00
zhayujie	9bd7d09f20	fix: remove relax mode temporarily	2023-07-31 14:42:50 +08:00
zhayujie	b22994c2d2	fix: some image bug	2023-07-30 19:55:56 +08:00
zhayujie	e027286b6d	fix: midjourney check task thread	2023-07-30 15:16:19 +08:00
befantasy	d6e16995e0	Update keyword.py 增加返回图片的功能增加返回图片的功能。以http/https开头，且以.jpg/.jpeg/.png/.gif结尾的内容，识别为URL，自动以图片发送。	2023-07-30 14:40:07 +08:00
zhayujie	782bff3a51	fix: add debug log	2023-07-29 12:22:45 +08:00
zhayujie	de26dc0597	fix: fast mode and relax mode checkout	2023-07-28 18:50:21 +08:00
zhayujie	233b24ab0f	feat: add global admin config	2023-07-28 16:33:41 +08:00
zhayujie	2f9e5b1219	feat: check app_code dynamically	2023-07-28 12:40:06 +08:00
zhayujie	dd36b8b150	config: add config template	2023-07-27 21:29:50 +08:00
zhayujie	f81ac31fe1	feat: add linkai plugin to support midjourney and distinguish app between groups	2023-07-27 21:21:36 +08:00
zyqcn@live.com	74a253f521	azure api add api-version:https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference	2023-07-24 16:28:05 +08:00
zhayujie	41762a1c57	Merge pull request #1332 from zhayujie/feat-1.3.3 fix: reduce memory usage	2023-07-21 17:18:56 +08:00
zhayujie	a786fa4b75	fix: reduce the expiration time and avoid storing the original message text to decrease memory usage	2023-07-21 17:16:34 +08:00
zhayujie	e4c7602c0c	docs: update README.md	2023-07-21 17:14:11 +08:00
zhayujie	e0d2e34980	Merge pull request #1328 from zhayujie/feat-1.3.3 feat: support global plugin config for docker env	2023-07-21 10:50:16 +08:00
zhayujie	9ef8e1be3f	feat: move loading config method to base class	2023-07-20 16:08:19 +08:00
zhayujie	aae9b64833	fix: reduce unnecessary error traceback logs	2023-07-20 14:46:41 +08:00
zhayujie	4bab4299f2	fix: global plugin config read	2023-07-20 14:24:40 +08:00
zhayujie	954e55f4b4	feat: add plugin global config to support docker volumes	2023-07-20 11:36:02 +08:00
zhayujie	2361e3c28c	docs: update README for railway cancelled free service	2023-07-19 18:23:59 +08:00
zhayujie	8aac86f0a9	Merge pull request #1291 from 6vision/master (tool)fix azure model	2023-07-05 01:44:06 +08:00
vision	6384e9310b	plugin(tool): 更新0.4.6 1、temp fix summary tool not ending bug 2、兼容0613 gpt-3.5 3、add azure's model name: gpt-35-turbo	2023-07-05 01:06:53 +08:00
vision	7a9205dfba	fix azure model 更新chatgpt_tool_hub至0.4.6，拉取最新代码。tool即可使用azure接口！	2023-07-05 01:01:46 +08:00
Jianglang	94b47a56f4	Merge pull request #1282 from haikerapples/master_haiker_timetask 内置 timetask 插件	2023-07-01 18:37:07 +08:00
zhayujie	709b5be634	fix: group voice config and azure model calc support	2023-07-01 13:17:08 +08:00
haikerwang	f970b2c168	内置 timetask 插件	2023-06-29 00:58:57 +08:00
zhayujie	973acb37ed	docs: update README.md	2023-06-27 22:28:51 +08:00
zhayujie	1c9020a565	docs: update README.md	2023-06-26 23:52:32 +08:00
zhayujie	c5f1d0042c	docs: update README.md	2023-06-26 20:11:35 +08:00
zhayujie	fa706e8b1d	Merge pull request #1275 from zhayujie/feat-docker chore: remove useless docker files	2023-06-26 14:16:18 +08:00
zhayujie	12c170f227	chore: remove useless docker files	2023-06-26 14:05:08 +08:00
zhayujie	db27dfe227	docs: modify docker deploy steps	2023-06-26 13:10:51 +08:00
zhayujie	2db4673392	chore: fixed openai version	2023-06-26 12:29:09 +08:00
zhayujie	38619db629	Merge pull request #1274 from zhayujie/feat-dockerhub feat: modify docker-compose file to pull image from dockerhub	2023-06-26 12:00:57 +08:00
zhayujie	930fd436ea	feat: modify docker-compose file to pull image from dockerhub	2023-06-26 11:58:55 +08:00
zhayujie	98b8ff2fc8	Merge pull request #1271 from zhayujie/feat-dockerhub feat: publish to dockerhub in github CI simultaneously	2023-06-26 01:24:24 +08:00
zhayujie	d0662683f9	feat: publish to dockerhub in github CI simultaneously	2023-06-26 01:20:04 +08:00
zhayujie	957f2574a9	Merge pull request #1257 from 6vision/master add reply_suffix	2023-06-17 16:50:11 +08:00
vision	109b362ebd	Update config.py	2023-06-17 16:42:52 +08:00
vision	ff3fdfa738	add reply_suffix	2023-06-17 16:36:08 +08:00
vision	e2636ed54a	add replay_suffix 增加自动回复后缀的可选配置参数	2023-06-17 15:53:49 +08:00
vision	dbe2f17e1a	add reply_suffix 增加私聊和群聊回复后缀的可选配置	2023-06-17 15:46:03 +08:00
zhayujie	4dc535673f	Merge pull request #1252 from 6vision/master Update Tool README.md	2023-06-16 15:48:04 +08:00
vision	f414b6408e	Update README.md	2023-06-16 15:08:57 +08:00
lanvent	3aa2e6a04d	fix: caclucate tokens correctly for *0613 models	2023-06-16 00:51:29 +08:00
lanvent	1963ff273f	chore(hello): change plugin logic	2023-06-14 13:40:20 +08:00
lanvent	bb737a71d5	feat: update counting tokens for new models	2023-06-14 13:36:07 +08:00
SSMario	4dbc54fa15	Revert "feat: 增加eleventLabs" This reverts commit `1d4ff796d7`.	2023-05-16 12:00:05 +08:00
SSMario	1d4ff796d7	feat: 增加eleventLabs	2023-05-16 11:50:54 +08:00
SSMario	44cb54a9ea	feat: 手机上回复消息，不触发机器人	2023-05-16 09:38:38 +08:00