Merge pull request #1428 from scut-chenzk/chenzk

修复收到从微信发出的图片消息保存到本地失败的问题

.github/ISSUE_TEMPLATE/config.yml

@@ -1,6 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: 知识星球
-    url: https://public.zsxq.com/groups/88885848842852.html
-    about: 如果你想了解更多项目细节，并与开发者们交流更多关于AI技术的实践，欢迎加入星球
-

.github/workflows/deploy-image-arm.yml

@@ -0,0 +1,71 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+# GitHub recommends pinning actions to a commit SHA.
+# To get a newer version, you will need to update the SHA.
+# You can also reference a tag or branch, but the action may change without warning.
+
+name: Create and publish a Docker image
+
+on:
+  push:
+    branches: ['master']
+  create:
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Available platforms
+        run: echo ${{ steps.buildx.outputs.platforms }}
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: |
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          push: true
+          file: ./docker/Dockerfile.latest
+          platforms: linux/arm64
+          tags: ${{ steps.meta.outputs.tags }}-arm64
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - uses: actions/delete-package-versions@v4
+        with:
+          package-name: 'chatgpt-on-wechat'
+          package-type: 'container'
+          min-versions-to-keep: 10
+          delete-only-untagged-versions: 'true'
+          token: ${{ secrets.GITHUB_TOKEN }}

README.md

@@ -5,7 +5,7 @@
 最新版本支持的功能如下：
 
 - [x] **多端部署：** 有多种部署方式可选择且功能完备，目前已支持个人微信，微信公众号和企业微信应用等部署方式
-- [x] **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3, GPT-3.5, GPT-4, 文心一言模型
+- [x] **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, claude, 文心一言, 讯飞星火
 - [x] **语音识别：** 可识别语音消息，通过文字或语音回复，支持 azure, baidu, google, openai等多种语音模型
 - [x] **图片生成：** 支持图片生成 和 图生图（如照片修复），可选择 Dell-E, stable diffusion, replicate, midjourney模型
 - [x] **丰富插件：** 支持个性化插件扩展，已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结等插件
@@ -28,9 +28,11 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 
 # 更新日志
 
+>**2023.09.01：** 增加 [企微个人号](https://github.com/zhayujie/chatgpt-on-wechat/pull/1385) 通道，[claude](https://github.com/zhayujie/chatgpt-on-wechat/pull/1382) 模型
+
 >**2023.08.08：** 接入百度文心一言模型，通过 [插件](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/linkai) 支持 Midjourney 绘图
 
->**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，打造专属客服机器人。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，可在线创建领域知识库，并接入微信、公众号及企业微信中，打造专属客服机器人。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))
 
@@ -113,7 +115,7 @@ pip3 install azure-cognitiveservices-speech
 # 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。当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
+  "model": "gpt-3.5-turbo",                                   # 模型名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
   "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
@@ -129,7 +131,10 @@ pip3 install azure-cognitiveservices-speech
   "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。"
+  "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。",
+  "use_linkai": false,                                        # 是否使用LinkAI接口，默认关闭，开启后可国内访问，使用知识库和MJ
+  "linkai_api_key": "",                                       # LinkAI Api Key
+  "linkai_app_code": ""                                       # LinkAI 应用code
 }
 ```
 **配置说明：**
@@ -154,7 +159,7 @@ pip3 install azure-cognitiveservices-speech
 
 **4.其他配置**
 
-+ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k`, `wenxin`  (其中gpt-4 api暂未完全开放，申请通过后可使用)
++ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k`, `wenxin` , `claude` ,  `xunfei`(其中gpt-4 api暂未完全开放，申请通过后可使用)
 + `temperature`,`frequency_penalty`,`presence_penalty`: Chat API接口参数，详情参考[OpenAI官方文档。](https://platform.openai.com/docs/api-reference/chat)
 + `proxy`：由于目前 `openai` 接口国内无法访问，需配置代理客户端的地址，详情参考  [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)
 + 对于图像生成，在满足个人或群组触发条件外，还需要额外的关键词前缀来触发，对应配置 `image_create_prefix `
@@ -166,6 +171,12 @@ pip3 install azure-cognitiveservices-speech
 + `character_desc` 配置中保存着你对机器人说的一段话，他会记住这段话并作为他的设定，你可以为他定制任何人格      (关于会话上下文的更多内容参考该 [issue](https://github.com/zhayujie/chatgpt-on-wechat/issues/43))
 + `subscribe_msg`：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。
 
+**5.LinkAI配置 (可选)**
+
++ `use_linkai`: 是否使用LinkAI接口，开启后可国内访问，使用知识库和 `Midjourney` 绘画, 参考 [文档](https://link-ai.tech/platform/link-app/wechat)
++ `linkai_api_key`: LinkAI Api Key，可在 [控制台](https://chat.link-ai.tech/console/interface) 创建
++ `linkai_app_code`: LinkAI 应用code，选填
+
 **本说明文档可能会未及时更新，当前所有可选的配置项均在该[`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py)中列出。**
 
 ## 运行

app.py

@@ -43,7 +43,7 @@ def run():
             # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
 
         channel = channel_factory.create_channel(channel_name)
-        if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app"]:
+        if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app", "wework"]:
             PluginManager().load_plugins()
 
         # startup channel

bot/baidu/baidu_wenxin.py

@@ -2,7 +2,6 @@
 
 import requests, json
 from bot.bot import Bot
-from bridge.reply import Reply, ReplyType
 from bot.session_manager import SessionManager
 from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
@@ -77,6 +76,7 @@ class BaiduWenxinBot(Bot):
             payload = {'messages': session.messages}
             response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
             response_text = json.loads(response.text)
+            logger.info(f"[BAIDU] response text={response_text}")
             res_content = response_text["result"]
             total_tokens = response_text["usage"]["total_tokens"]
             completion_tokens = response_text["usage"]["completion_tokens"]

bot/baidu/baidu_wenxin_session.py

@@ -9,6 +9,7 @@ from common.log import logger
     ]
 """
 
+
 class BaiduWenxinSession(Session):
     def __init__(self, session_id, system_prompt=None, model="gpt-3.5-turbo"):
         super().__init__(session_id, system_prompt)
@@ -17,7 +18,6 @@ class BaiduWenxinSession(Session):
         # self.reset()
 
     def discard_exceeding(self, max_tokens, cur_tokens=None):
-        # pdb.set_trace()
         precise = True
         try:
             cur_tokens = self.calc_tokens()
@@ -27,18 +27,9 @@ class BaiduWenxinSession(Session):
                 raise e
             logger.debug("Exception when counting tokens precisely for query: {}".format(e))
         while cur_tokens > max_tokens:
-            if len(self.messages) > 2:
-                self.messages.pop(1)
-            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
-                self.messages.pop(1)
-                if precise:
-                    cur_tokens = self.calc_tokens()
-                else:
-                    cur_tokens = cur_tokens - max_tokens
-                break
-            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
-                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
-                break
+            if len(self.messages) >= 2:
+                self.messages.pop(0)
+                self.messages.pop(0)
             else:
                 logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens, len(self.messages)))
                 break
@@ -52,36 +43,11 @@ class BaiduWenxinSession(Session):
         return num_tokens_from_messages(self.messages, self.model)
 
 
-# refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
 def num_tokens_from_messages(messages, model):
     """Returns the number of tokens used by a list of messages."""
-    import tiktoken
-
-    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":
-        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":
-        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.")
-        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
-    num_tokens = 0
-    for message in messages:
-        num_tokens += tokens_per_message
-        for key, value in message.items():
-            num_tokens += len(encoding.encode(value))
-            if key == "name":
-                num_tokens += tokens_per_name
-    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
-    return num_tokens
+    tokens = 0
+    for msg in messages:
+        # 官方token计算规则暂不明确： "大约为 token数为 "中文字 + 其他语种单词数 x 1.3"
+        # 这里先直接根据字数粗略估算吧，暂不影响正常使用，仅在判断是否丢弃历史会话的时候会有偏差
+        tokens += len(msg["content"])
+    return tokens

bot/bot_factory.py

@@ -14,31 +14,33 @@ def create_bot(bot_type):
         # 替换Baidu Unit为Baidu文心千帆对话接口
         # from bot.baidu.baidu_unit_bot import BaiduUnitBot
         # return BaiduUnitBot()
-
         from bot.baidu.baidu_wenxin import BaiduWenxinBot
-
         return BaiduWenxinBot()
 
     elif bot_type == const.CHATGPT:
         # ChatGPT 网页端web接口
         from bot.chatgpt.chat_gpt_bot import ChatGPTBot
-
         return ChatGPTBot()
 
     elif bot_type == const.OPEN_AI:
         # 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()
 
+    elif bot_type == const.XUNFEI:
+        from bot.xunfei.xunfei_spark_bot import XunFeiBot
+        return XunFeiBot()
+
     elif bot_type == const.LINKAI:
         from bot.linkai.link_ai_bot import LinkAIBot
         return LinkAIBot()
 
+    elif bot_type == const.CLAUDEAI:
+        from bot.claude.claude_ai_bot import ClaudeAIBot
+        return ClaudeAIBot()
     raise RuntimeError

bot/chatgpt/chat_gpt_session.py

@@ -55,11 +55,16 @@ class ChatGPTSession(Session):
 # refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
 def num_tokens_from_messages(messages, model):
     """Returns the number of tokens used by a list of messages."""
+
+    if model in ["wenxin", "xunfei"]:
+        return num_tokens_by_character(messages)
+
     import tiktoken
 
     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"]:
+    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:
@@ -85,3 +90,11 @@ def num_tokens_from_messages(messages, model):
                 num_tokens += tokens_per_name
     num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
     return num_tokens
+
+
+def num_tokens_by_character(messages):
+    """Returns the number of tokens used by a list of messages."""
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/claude/claude_ai_bot.py

@@ -0,0 +1,222 @@
+import re
+import time
+import json
+import uuid
+from curl_cffi import requests
+from bot.bot import Bot
+from bot.claude.claude_ai_session import ClaudeAiSession
+from bot.openai.open_ai_image import OpenAIImage
+from bot.session_manager import SessionManager
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+
+
+class ClaudeAIBot(Bot, OpenAIImage):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ClaudeAiSession, model=conf().get("model") or "gpt-3.5-turbo")
+        self.claude_api_cookie = conf().get("claude_api_cookie")
+        self.proxy = conf().get("proxy")
+        self.con_uuid_dic = {}
+        if self.proxy:
+            self.proxies = {
+            "http": self.proxy,
+            "https": self.proxy
+        }
+        else:
+            self.proxies = None
+        self.error = ""
+        self.org_uuid = self.get_organization_id()
+
+    def generate_uuid(self):
+        random_uuid = uuid.uuid4()
+        random_uuid_str = str(random_uuid)
+        formatted_uuid = f"{random_uuid_str[0:8]}-{random_uuid_str[9:13]}-{random_uuid_str[14:18]}-{random_uuid_str[19:23]}-{random_uuid_str[24:]}"
+        return formatted_uuid
+        
+    def reply(self, query, context: Context = None) -> Reply:
+        if context.type == ContextType.TEXT:
+            return self._chat(query, context)
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, res = self.create_img(query, 0)
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, res)
+            else:
+                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 get_organization_id(self):
+        url = "https://claude.ai/api/organizations"
+        headers = {
+            'User-Agent':
+                'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Referer': 'https://claude.ai/chats',
+            'Content-Type': 'application/json',
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-origin',
+            'Connection': 'keep-alive',
+            'Cookie': f'{self.claude_api_cookie}'
+        }
+        try:
+            response = requests.get(url, headers=headers, impersonate="chrome110", proxies =self.proxies, timeout=400)
+            res = json.loads(response.text)
+            uuid = res[0]['uuid']
+        except:
+            if "App unavailable" in response.text:
+                logger.error("IP error: The IP is not allowed to be used on Claude")
+                self.error = "ip所在地区不被claude支持"
+            elif "Invalid authorization" in response.text:
+                logger.error("Cookie error: Invalid authorization of claude, check cookie please.")
+                self.error = "无法通过claude身份验证，请检查cookie"
+            return None
+        return uuid
+
+    def conversation_share_check(self,session_id):
+        if conf().get("claude_uuid") is not None and conf().get("claude_uuid") != "":
+            con_uuid = conf().get("claude_uuid")
+            return con_uuid
+        if session_id not in self.con_uuid_dic:
+            self.con_uuid_dic[session_id] = self.generate_uuid()
+            self.create_new_chat(self.con_uuid_dic[session_id])
+        return self.con_uuid_dic[session_id]
+
+    def check_cookie(self):
+        flag = self.get_organization_id()
+        return flag
+
+    def create_new_chat(self, con_uuid):
+        """
+        新建claude对话实体
+        :param con_uuid: 对话id
+        :return:
+        """
+        url = f"https://claude.ai/api/organizations/{self.org_uuid}/chat_conversations"
+        payload = json.dumps({"uuid": con_uuid, "name": ""})
+        headers = {
+            'User-Agent':
+                'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Referer': 'https://claude.ai/chats',
+            'Content-Type': 'application/json',
+            'Origin': 'https://claude.ai',
+            'DNT': '1',
+            'Connection': 'keep-alive',
+            'Cookie': self.claude_api_cookie,
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-origin',
+            'TE': 'trailers'
+        }
+        response = requests.post(url, headers=headers, data=payload, impersonate="chrome110", proxies=self.proxies, timeout=400)
+        # Returns JSON of the newly created conversation information
+        return response.json()
+        
+    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("[CLAUDEAI] failed after maximum number of retry times")
+            return Reply(ReplyType.ERROR, "请再问我一次吧")
+
+        try:
+            session_id = context["session_id"]
+            if self.org_uuid is None:
+                return Reply(ReplyType.ERROR, self.error)
+
+            session = self.sessions.session_query(query, session_id)
+            con_uuid = self.conversation_share_check(session_id)
+
+            model = conf().get("model") or "gpt-3.5-turbo"
+            # remove system message
+            if session.messages[0].get("role") == "system":
+                if model == "wenxin" or model == "claude":
+                    session.messages.pop(0)
+            logger.info(f"[CLAUDEAI] query={query}")
+
+            # do http request
+            base_url = "https://claude.ai"
+            payload = json.dumps({
+                "completion": {
+                    "prompt": f"{query}",
+                    "timezone": "Asia/Kolkata",
+                    "model": "claude-2"
+                },
+                "organization_uuid": f"{self.org_uuid}",
+                "conversation_uuid": f"{con_uuid}",
+                "text": f"{query}",
+                "attachments": []
+            })
+            headers = {
+                'User-Agent':
+                    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+                'Accept': 'text/event-stream, text/event-stream',
+                'Accept-Language': 'en-US,en;q=0.5',
+                'Referer': 'https://claude.ai/chats',
+                'Content-Type': 'application/json',
+                'Origin': 'https://claude.ai',
+                'DNT': '1',
+                'Connection': 'keep-alive',
+                'Cookie': f'{self.claude_api_cookie}',
+                'Sec-Fetch-Dest': 'empty',
+                'Sec-Fetch-Mode': 'cors',
+                'Sec-Fetch-Site': 'same-origin',
+                'TE': 'trailers'
+            }
+
+            res = requests.post(base_url + "/api/append_message", headers=headers, data=payload,impersonate="chrome110",proxies= self.proxies,timeout=400)
+            if res.status_code == 200 or "pemission" in res.text:
+                # execute success
+                decoded_data = res.content.decode("utf-8")
+                decoded_data = re.sub('\n+', '\n', decoded_data).strip()
+                data_strings = decoded_data.split('\n')
+                completions = []
+                for data_string in data_strings:
+                    json_str = data_string[6:].strip()
+                    data = json.loads(json_str)
+                    if 'completion' in data:
+                        completions.append(data['completion'])
+
+                reply_content = ''.join(completions)
+
+                if "rate limi" in reply_content:
+                    logger.error("rate limit error: The conversation has reached the system speed limit and is synchronized with Cladue. Please go to the official website to check the lifting time")
+                    return Reply(ReplyType.ERROR, "对话达到系统速率限制，与cladue同步，请进入官网查看解除限制时间")
+                logger.info(f"[CLAUDE] reply={reply_content}, total_tokens=invisible")
+                self.sessions.session_reply(reply_content, session_id, 100)
+                return Reply(ReplyType.TEXT, reply_content)
+            else:
+                flag = self.check_cookie()
+                if flag == None:
+                    return Reply(ReplyType.ERROR, self.error)
+
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[CLAUDE] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}, detail: {res.text}, uuid: {con_uuid}")
+
+                if res.status_code >= 500:
+                    # server error, need retry
+                    time.sleep(2)
+                    logger.warn(f"[CLAUDE] do retry, times={retry_count}")
+                    return self._chat(query, context, retry_count + 1)
+                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)
+            # retry
+            time.sleep(2)
+            logger.warn(f"[CLAUDE] do retry, times={retry_count}")
+            return self._chat(query, context, retry_count + 1)

bot/claude/claude_ai_session.py

@@ -0,0 +1,9 @@
+from bot.session_manager import Session
+
+
+class ClaudeAiSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="claude"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        # claude逆向不支持role prompt
+        # self.reset()

bot/linkai/link_ai_bot.py

@@ -22,8 +22,8 @@ class LinkAIBot(Bot, OpenAIImage):
 
     def __init__(self):
         super().__init__()
-        self.base_url = "https://api.link-ai.chat/v1"
         self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "gpt-3.5-turbo")
+        self.args = {}
 
     def reply(self, query, context: Context = None) -> Reply:
         if context.type == ContextType.TEXT:
@@ -73,17 +73,21 @@ class LinkAIBot(Bot, OpenAIImage):
             body = {
                 "app_code": app_code,
                 "messages": session.messages,
-                "model": model,     # 对话模型的名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin
+                "model": model,     # 对话模型的名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
                 "temperature": conf().get("temperature"),
                 "top_p": conf().get("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
             }
-            logger.info(f"[LINKAI] query={query}, app_code={app_code}, mode={body.get('model')}")
+            file_id = context.kwargs.get("file_id")
+            if file_id:
+                body["file_id"] = file_id
+            logger.info(f"[LINKAI] query={query}, app_code={app_code}, mode={body.get('model')}, file_id={file_id}")
             headers = {"Authorization": "Bearer " + linkai_api_key}
 
             # do http request
-            res = requests.post(url=self.base_url + "/chat/completions", json=body, headers=headers,
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
                                 timeout=conf().get("request_timeout", 180))
             if res.status_code == 200:
                 # execute success
@@ -114,3 +118,68 @@ class LinkAIBot(Bot, OpenAIImage):
             time.sleep(2)
             logger.warn(f"[LINKAI] do retry, times={retry_count}")
             return self._chat(query, context, retry_count + 1)
+
+    def reply_text(self, session: ChatGPTSession, app_code="", retry_count=0) -> dict:
+        if retry_count >= 2:
+            # exit from retry 2 times
+            logger.warn("[LINKAI] failed after maximum number of retry times")
+            return {
+                "total_tokens": 0,
+                "completion_tokens": 0,
+                "content": "请再问我一次吧"
+            }
+
+        try:
+            body = {
+                "app_code": app_code,
+                "messages": session.messages,
+                "model": conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
+                "temperature": conf().get("temperature"),
+                "top_p": conf().get("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
+            }
+            if self.args.get("max_tokens"):
+                body["max_tokens"] = self.args.get("max_tokens")
+            headers = {"Authorization": "Bearer " +  conf().get("linkai_api_key")}
+
+            # do http request
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            res = requests.post(url=base_url + "/v1/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}")
+                return {
+                    "total_tokens": total_tokens,
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": reply_content,
+                }
+
+            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')}")
+
+                if res.status_code >= 500:
+                    # server error, need retry
+                    time.sleep(2)
+                    logger.warn(f"[LINKAI] do retry, times={retry_count}")
+                    return self.reply_text(session, app_code, retry_count + 1)
+
+                return {
+                    "total_tokens": 0,
+                    "completion_tokens": 0,
+                    "content": "提问太快啦，请休息一下再问我吧"
+                }
+
+        except Exception as e:
+            logger.exception(e)
+            # retry
+            time.sleep(2)
+            logger.warn(f"[LINKAI] do retry, times={retry_count}")
+            return self.reply_text(session, app_code, retry_count + 1)

bot/xunfei/xunfei_spark_bot.py

@@ -0,0 +1,250 @@
+# encoding:utf-8
+
+import requests, json
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
+from bridge.context import ContextType, Context
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from common import const
+import time
+import _thread as thread
+import datetime
+from datetime import datetime
+from wsgiref.handlers import format_date_time
+from urllib.parse import urlencode
+import base64
+import ssl
+import hashlib
+import hmac
+import json
+from time import mktime
+from urllib.parse import urlparse
+import websocket
+import queue
+import threading
+import random
+
+# 消息队列 map
+queue_map = dict()
+
+# 响应队列 map
+reply_map = dict()
+
+
+class XunFeiBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.app_id = conf().get("xunfei_app_id")
+        self.api_key = conf().get("xunfei_api_key")
+        self.api_secret = conf().get("xunfei_api_secret")
+        # 默认使用v2.0版本，1.5版本可设置为 general
+        self.domain = "generalv2"
+        # 默认使用v2.0版本，1.5版本可设置为 "ws://spark-api.xf-yun.com/v1.1/chat"
+        self.spark_url = "ws://spark-api.xf-yun.com/v2.1/chat"
+        self.host = urlparse(self.spark_url).netloc
+        self.path = urlparse(self.spark_url).path
+        # 和wenxin使用相同的session机制
+        self.sessions = SessionManager(BaiduWenxinSession, model=const.XUNFEI)
+
+    def reply(self, query, context: Context = None) -> Reply:
+        if context.type == ContextType.TEXT:
+            logger.info("[XunFei] query={}".format(query))
+            session_id = context["session_id"]
+            request_id = self.gen_request_id(session_id)
+            reply_map[request_id] = ""
+            session = self.sessions.session_query(query, session_id)
+            threading.Thread(target=self.create_web_socket, args=(session.messages, request_id)).start()
+            depth = 0
+            time.sleep(0.1)
+            t1 = time.time()
+            usage = {}
+            while depth <= 300:
+                try:
+                    data_queue = queue_map.get(request_id)
+                    if not data_queue:
+                        depth += 1
+                        time.sleep(0.1)
+                        continue
+                    data_item = data_queue.get(block=True, timeout=0.1)
+                    if data_item.is_end:
+                        # 请求结束
+                        del queue_map[request_id]
+                        if data_item.reply:
+                            reply_map[request_id] += data_item.reply
+                        usage = data_item.usage
+                        break
+
+                    reply_map[request_id] += data_item.reply
+                    depth += 1
+                except Exception as e:
+                    depth += 1
+                    continue
+            t2 = time.time()
+            logger.info(f"[XunFei-API] response={reply_map[request_id]}, time={t2 - t1}s, usage={usage}")
+            self.sessions.session_reply(reply_map[request_id], session_id, usage.get("total_tokens"))
+            reply = Reply(ReplyType.TEXT, reply_map[request_id])
+            del reply_map[request_id]
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def create_web_socket(self, prompt, session_id, temperature=0.5):
+        logger.info(f"[XunFei] start connect, prompt={prompt}")
+        websocket.enableTrace(False)
+        wsUrl = self.create_url()
+        ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close,
+                                    on_open=on_open)
+        data_queue = queue.Queue(1000)
+        queue_map[session_id] = data_queue
+        ws.appid = self.app_id
+        ws.question = prompt
+        ws.domain = self.domain
+        ws.session_id = session_id
+        ws.temperature = temperature
+        ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
+
+    def gen_request_id(self, session_id: str):
+        return session_id + "_" + str(int(time.time())) + "" + str(random.randint(0, 100))
+
+    # 生成url
+    def create_url(self):
+        # 生成RFC1123格式的时间戳
+        now = datetime.now()
+        date = format_date_time(mktime(now.timetuple()))
+
+        # 拼接字符串
+        signature_origin = "host: " + self.host + "\n"
+        signature_origin += "date: " + date + "\n"
+        signature_origin += "GET " + self.path + " HTTP/1.1"
+
+        # 进行hmac-sha256进行加密
+        signature_sha = hmac.new(self.api_secret.encode('utf-8'), signature_origin.encode('utf-8'),
+                                 digestmod=hashlib.sha256).digest()
+
+        signature_sha_base64 = base64.b64encode(signature_sha).decode(encoding='utf-8')
+
+        authorization_origin = f'api_key="{self.api_key}", algorithm="hmac-sha256", headers="host date request-line", ' \
+                               f'signature="{signature_sha_base64}"'
+
+        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
+
+        # 将请求的鉴权参数组合为字典
+        v = {
+            "authorization": authorization,
+            "date": date,
+            "host": self.host
+        }
+        # 拼接鉴权参数，生成url
+        url = self.spark_url + '?' + urlencode(v)
+        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致
+        return url
+
+    def gen_params(self, appid, domain, question):
+        """
+        通过appid和用户的提问来生成请参数
+        """
+        data = {
+            "header": {
+                "app_id": appid,
+                "uid": "1234"
+            },
+            "parameter": {
+                "chat": {
+                    "domain": domain,
+                    "random_threshold": 0.5,
+                    "max_tokens": 2048,
+                    "auditing": "default"
+                }
+            },
+            "payload": {
+                "message": {
+                    "text": question
+                }
+            }
+        }
+        return data
+
+
+class ReplyItem:
+    def __init__(self, reply, usage=None, is_end=False):
+        self.is_end = is_end
+        self.reply = reply
+        self.usage = usage
+
+
+# 收到websocket错误的处理
+def on_error(ws, error):
+    logger.error(f"[XunFei] error: {str(error)}")
+
+
+# 收到websocket关闭的处理
+def on_close(ws, one, two):
+    data_queue = queue_map.get(ws.session_id)
+    data_queue.put("END")
+
+
+# 收到websocket连接建立的处理
+def on_open(ws):
+    logger.info(f"[XunFei] Start websocket, session_id={ws.session_id}")
+    thread.start_new_thread(run, (ws,))
+
+
+def run(ws, *args):
+    data = json.dumps(gen_params(appid=ws.appid, domain=ws.domain, question=ws.question, temperature=ws.temperature))
+    ws.send(data)
+
+
+# Websocket 操作
+# 收到websocket消息的处理
+def on_message(ws, message):
+    data = json.loads(message)
+    code = data['header']['code']
+    if code != 0:
+        logger.error(f'请求错误: {code}, {data}')
+        ws.close()
+    else:
+        choices = data["payload"]["choices"]
+        status = choices["status"]
+        content = choices["text"][0]["content"]
+        data_queue = queue_map.get(ws.session_id)
+        if not data_queue:
+            logger.error(f"[XunFei] can't find data queue, session_id={ws.session_id}")
+            return
+        reply_item = ReplyItem(content)
+        if status == 2:
+            usage = data["payload"].get("usage")
+            reply_item = ReplyItem(content, usage)
+            reply_item.is_end = True
+            ws.close()
+        data_queue.put(reply_item)
+
+
+def gen_params(appid, domain, question, temperature=0.5):
+    """
+    通过appid和用户的提问来生成请参数
+    """
+    data = {
+        "header": {
+            "app_id": appid,
+            "uid": "1234"
+        },
+        "parameter": {
+            "chat": {
+                "domain": domain,
+                "temperature": temperature,
+                "random_threshold": 0.5,
+                "max_tokens": 2048,
+                "auditing": "default"
+            }
+        },
+        "payload": {
+            "message": {
+                "text": question
+            }
+        }
+    }
+    return data

bridge/bridge.py

@@ -25,9 +25,14 @@ class Bridge(object):
             self.btype["chat"] = const.CHATGPTONAZURE
         if model_type in ["wenxin"]:
             self.btype["chat"] = const.BAIDU
+        if model_type in ["xunfei"]:
+            self.btype["chat"] = const.XUNFEI
         if conf().get("use_linkai") and conf().get("linkai_api_key"):
             self.btype["chat"] = const.LINKAI
+        if model_type in ["claude"]:
+            self.btype["chat"] = const.CLAUDEAI
         self.bots = {}
+        self.chat_bots = {}
 
     def get_bot(self, typename):
         if self.bots.get(typename) is None:
@@ -57,6 +62,11 @@ class Bridge(object):
     def fetch_translate(self, text, from_lang="", to_lang="en") -> Reply:
         return self.get_bot("translate").translate(text, from_lang, to_lang)
 
+    def find_chat_bot(self, bot_type: str):
+        if self.chat_bots.get(bot_type) is None:
+            self.chat_bots[bot_type] = create_bot(bot_type)
+        return self.chat_bots.get(bot_type)
+
     def reset_bot(self):
         """
         重置bot路由

bridge/context.py

@@ -7,9 +7,14 @@ class ContextType(Enum):
     TEXT = 1  # 文本消息
     VOICE = 2  # 音频消息
     IMAGE = 3  # 图片消息
+    FILE = 4  # 文件信息
+    VIDEO = 5  # 视频信息
+    SHARING = 6  # 分享信息
+
     IMAGE_CREATE = 10  # 创建图片命令
     JOIN_GROUP = 20  # 加入群聊
     PATPAT = 21  # 拍了拍
+    FUNCTION = 22  # 函数调用
 
     def __str__(self):
         return self.name

bridge/reply.py

@@ -8,9 +8,15 @@ class ReplyType(Enum):
     VOICE = 2  # 音频文件
     IMAGE = 3  # 图片文件
     IMAGE_URL = 4  # 图片URL
-
+    VIDEO_URL = 5  # 视频URL
+    FILE = 6  # 文件
+    CARD = 7  # 微信名片，仅支持ntchat
+    InviteRoom = 8  # 邀请好友进群
     INFO = 9
     ERROR = 10
+    TEXT_ = 11  # 强制文本
+    VIDEO = 12
+    MINIAPP = 13  # 小程序
 
     def __str__(self):
         return self.name

channel/channel_factory.py

@@ -33,4 +33,8 @@ def create_channel(channel_type):
         from channel.wechatcom.wechatcomapp_channel import WechatComAppChannel
 
         return WechatComAppChannel()
+    elif channel_type == "wework":
+        from channel.wework.wework_channel import WeworkChannel
+
+        return WeworkChannel()
     raise RuntimeError

channel/chat_channel.py

@@ -99,21 +99,26 @@ class ChatChannel(Channel):
                 match_prefix = check_prefix(content, conf().get("group_chat_prefix"))
                 match_contain = check_contain(content, conf().get("group_chat_keyword"))
                 flag = False
-                if match_prefix is not None or match_contain is not None:
-                    flag = True
-                    if match_prefix:
-                        content = content.replace(match_prefix, "", 1).strip()
-                if context["msg"].is_at:
-                    logger.info("[WX]receive group at")
-                    if not conf().get("group_at_off", False):
+                if context["msg"].to_user_id != context["msg"].actual_user_id:
+                    if match_prefix is not None or match_contain is not None:
                         flag = True
-                    pattern = f"@{re.escape(self.name)}(\u2005|\u0020)"
-                    subtract_res = re.sub(pattern, r"", content)
-                    if subtract_res == content and context["msg"].self_display_name:
-                        # 前缀移除后没有变化，使用群昵称再次移除
-                        pattern = f"@{re.escape(context['msg'].self_display_name)}(\u2005|\u0020)"
+                        if match_prefix:
+                            content = content.replace(match_prefix, "", 1).strip()
+                    if context["msg"].is_at:
+                        logger.info("[WX]receive group at")
+                        if not conf().get("group_at_off", False):
+                            flag = True
+                        pattern = f"@{re.escape(self.name)}(\u2005|\u0020)"
                         subtract_res = re.sub(pattern, r"", content)
-                    content = subtract_res
+                        if isinstance(context["msg"].at_list, list):
+                            for at in context["msg"].at_list:
+                                pattern = f"@{re.escape(at)}(\u2005|\u0020)"
+                                subtract_res = re.sub(pattern, r"", subtract_res)
+                        if subtract_res == content and context["msg"].self_display_name:
+                            # 前缀移除后没有变化，使用群昵称再次移除
+                            pattern = f"@{re.escape(context['msg'].self_display_name)}(\u2005|\u0020)"
+                            subtract_res = re.sub(pattern, r"", content)
+                        content = subtract_res
                 if not flag:
                     if context["origin_ctype"] == ContextType.VOICE:
                         logger.info("[WX]receive group voice, but checkprefix didn't match")
@@ -197,7 +202,10 @@ class ChatChannel(Channel):
                         reply = self._generate_reply(new_context)
                     else:
                         return
-            elif context.type == ContextType.IMAGE:  # 图片消息，当前无默认逻辑
+            elif context.type == ContextType.IMAGE:  # 图片消息，当前仅做下载保存到本地的逻辑
+                cmsg = context["msg"]
+                cmsg.prepare()
+            elif context.type == ContextType.FUNCTION or context.type == ContextType.FILE:  # 文件消息及函数调用等，当前无默认逻辑
                 pass
             else:
                 logger.error("[WX] unknown context type: {}".format(context.type))
@@ -233,7 +241,7 @@ class ChatChannel(Channel):
                     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:
+                elif reply.type == ReplyType.IMAGE_URL or reply.type == ReplyType.VOICE or reply.type == ReplyType.IMAGE or reply.type == ReplyType.FILE or reply.type == ReplyType.VIDEO or reply.type == ReplyType.VIDEO_URL:
                     pass
                 else:
                     logger.error("[WX] unknown reply type: {}".format(reply.type))

channel/chat_message.py

@@ -53,6 +53,7 @@ class ChatMessage(object):
     is_at = False
     actual_user_id = None
     actual_user_nickname = None
+    at_list = None
 
     _prepare_fn = None
     _prepared = False
@@ -67,7 +68,7 @@ class ChatMessage(object):
             self._prepare_fn()
 
     def __str__(self):
-        return "ChatMessage: id={}, create_time={}, ctype={}, content={}, from_user_id={}, from_user_nickname={}, to_user_id={}, to_user_nickname={}, other_user_id={}, other_user_nickname={}, is_group={}, is_at={}, actual_user_id={}, actual_user_nickname={}".format(
+        return "ChatMessage: id={}, create_time={}, ctype={}, content={}, from_user_id={}, from_user_nickname={}, to_user_id={}, to_user_nickname={}, other_user_id={}, other_user_nickname={}, is_group={}, is_at={}, actual_user_id={}, actual_user_nickname={}, at_list={}".format(
             self.msg_id,
             self.create_time,
             self.ctype,
@@ -82,4 +83,5 @@ class ChatMessage(object):
             self.is_at,
             self.actual_user_id,
             self.actual_user_nickname,
+            self.at_list
         )

channel/wechat/wechat_channel.py

@@ -25,7 +25,7 @@ from lib import itchat
 from lib.itchat.content import *
 
 
-@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE])
+@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE, ATTACHMENT, SHARING])
 def handler_single_msg(msg):
     try:
         cmsg = WechatMessage(msg, False)
@@ -36,7 +36,7 @@ def handler_single_msg(msg):
     return None
 
 
-@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE], isGroupChat=True)
+@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE, ATTACHMENT, SHARING], isGroupChat=True)
 def handler_group_msg(msg):
     try:
         cmsg = WechatMessage(msg, True)
@@ -172,6 +172,8 @@ class WechatChannel(ChatChannel):
         elif cmsg.ctype == ContextType.TEXT:
             # logger.debug("[WX]receive group msg: {}, cmsg={}".format(json.dumps(cmsg._rawmsg, ensure_ascii=False), cmsg))
             pass
+        elif cmsg.ctype == ContextType.FILE:
+            logger.debug(f"[WX]receive attachment msg, file_name={cmsg.content}")
         else:
             logger.debug("[WX]receive group msg: {}".format(cmsg.content))
         context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg)
@@ -192,10 +194,14 @@ class WechatChannel(ChatChannel):
             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
+            logger.debug(f"[WX] start download image, img_url={img_url}")
             pic_res = requests.get(img_url, stream=True)
             image_storage = io.BytesIO()
+            size = 0
             for block in pic_res.iter_content(1024):
+                size += len(block)
                 image_storage.write(block)
+            logger.info(f"[WX] download image success, size={size}, img_url={img_url}")
             image_storage.seek(0)
             itchat.send_image(image_storage, toUserName=receiver)
             logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
@@ -204,3 +210,24 @@ class WechatChannel(ChatChannel):
             image_storage.seek(0)
             itchat.send_image(image_storage, toUserName=receiver)
             logger.info("[WX] sendImage, receiver={}".format(receiver))
+        elif reply.type == ReplyType.FILE:  # 新增文件回复类型
+            file_storage = reply.content
+            itchat.send_file(file_storage, toUserName=receiver)
+            logger.info("[WX] sendFile, receiver={}".format(receiver))
+        elif reply.type == ReplyType.VIDEO:  # 新增视频回复类型
+            video_storage = reply.content
+            itchat.send_video(video_storage, toUserName=receiver)
+            logger.info("[WX] sendFile, receiver={}".format(receiver))
+        elif reply.type == ReplyType.VIDEO_URL:  # 新增视频URL回复类型
+            video_url = reply.content
+            logger.debug(f"[WX] start download video, video_url={video_url}")
+            video_res = requests.get(video_url, stream=True)
+            video_storage = io.BytesIO()
+            size = 0
+            for block in video_res.iter_content(1024):
+                size += len(block)
+                video_storage.write(block)
+            logger.info(f"[WX] download video success, size={size}, video_url={video_url}")
+            video_storage.seek(0)
+            itchat.send_video(video_storage, toUserName=receiver)
+            logger.info("[WX] sendVideo url={}, receiver={}".format(video_url, receiver))

channel/wechat/wechat_message.py

@@ -7,7 +7,6 @@ from common.tmp_dir import TmpDir
 from lib import itchat
 from lib.itchat.content import *
 
-
 class WechatMessage(ChatMessage):
     def __init__(self, itchat_msg, is_group=False):
         super().__init__(itchat_msg)
@@ -42,6 +41,14 @@ class WechatMessage(ChatMessage):
                     self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
             else:
                 raise NotImplementedError("Unsupported note message: " + itchat_msg["Content"])
+        elif itchat_msg["Type"] == ATTACHMENT:
+            self.ctype = ContextType.FILE
+            self.content = TmpDir().path() + itchat_msg["FileName"]
+            self._prepare_fn = lambda: itchat_msg.download(self.content)
+        elif itchat_msg["Type"] == SHARING:
+            self.ctype = ContextType.SHARING
+            self.content = itchat_msg.get("Url")
+
         else:
             raise NotImplementedError("Unsupported message type: Type:{} MsgType:{}".format(itchat_msg["Type"], itchat_msg["MsgType"]))
 

channel/wechatmp/passive_reply.py

@@ -49,7 +49,7 @@ class Query:
 
                 # New request
                 if (
-                    from_user not in channel.cache_dict
+                    channel.cache_dict.get(from_user) is None
                     and from_user not in channel.running
                     or content.startswith("#")
                     and message_id not in channel.request_cnt  # insert the godcmd
@@ -131,8 +131,10 @@ class Query:
 
                 # Only one request can access to the cached data
                 try:
-                    (reply_type, reply_content) = channel.cache_dict.pop(from_user)
-                except KeyError:
+                    (reply_type, reply_content) = channel.cache_dict[from_user].pop(0)
+                    if not channel.cache_dict[from_user]:  # If popping the message makes the list empty, delete the user entry from cache
+                        del channel.cache_dict[from_user]
+                except IndexError:
                     return "success"
 
                 if reply_type == "text":
@@ -146,7 +148,7 @@ class Query:
                             max_split=1,
                         )
                         reply_text = splits[0] + continue_text
-                        channel.cache_dict[from_user] = ("text", splits[1])
+                        channel.cache_dict[from_user].append(("text", splits[1]))
 
                     logger.info(
                         "[wechatmp] Request {} do send to {} {}: {}\n{}".format(

channel/wechatmp/wechatmp_channel.py

@@ -10,6 +10,7 @@ import requests
 import web
 from wechatpy.crypto import WeChatCrypto
 from wechatpy.exceptions import WeChatClientException
+from collections import defaultdict
 
 from bridge.context import *
 from bridge.reply import *
@@ -20,7 +21,7 @@ from common.log import logger
 from common.singleton import singleton
 from common.utils import split_string_by_utf8_length
 from config import conf
-from voice.audio_convert import any_to_mp3
+from voice.audio_convert import any_to_mp3, split_audio
 
 # If using SSL, uncomment the following lines, and modify the certificate path.
 # from cheroot.server import HTTPServer
@@ -46,7 +47,7 @@ class WechatMPChannel(ChatChannel):
             self.crypto = WeChatCrypto(token, aes_key, appid)
         if self.passive_reply:
             # Cache the reply to the user's first message
-            self.cache_dict = dict()
+            self.cache_dict = defaultdict(list)
             # Record whether the current message is being processed
             self.running = set()
             # Count the request from wechat official server by message_id
@@ -82,24 +83,28 @@ class WechatMPChannel(ChatChannel):
             if reply.type == ReplyType.TEXT or reply.type == ReplyType.INFO or reply.type == ReplyType.ERROR:
                 reply_text = reply.content
                 logger.info("[wechatmp] text cached, receiver {}\n{}".format(receiver, reply_text))
-                self.cache_dict[receiver] = ("text", reply_text)
+                self.cache_dict[receiver].append(("text", reply_text))
             elif reply.type == ReplyType.VOICE:
-                try:
-                    voice_file_path = reply.content
-                    with open(voice_file_path, "rb") as f:
-                        # support: <2M, <60s, mp3/wma/wav/amr
-                        response = self.client.material.add("voice", f)
-                        logger.debug("[wechatmp] upload voice response: {}".format(response))
-                        # 根据文件大小估计一个微信自动审核的时间，审核结束前返回将会导致语音无法播放，这个估计有待验证
-                        f_size = os.fstat(f.fileno()).st_size
-                        time.sleep(1.0 + 2 * f_size / 1024 / 1024)
-                        # todo check media_id
-                except WeChatClientException as e:
-                    logger.error("[wechatmp] upload voice failed: {}".format(e))
-                    return
-                media_id = response["media_id"]
-                logger.info("[wechatmp] voice uploaded, receiver {}, media_id {}".format(receiver, media_id))
-                self.cache_dict[receiver] = ("voice", media_id)
+                voice_file_path = reply.content
+                duration, files = split_audio(voice_file_path, 60 * 1000)
+                if len(files) > 1:
+                    logger.info("[wechatmp] voice too long {}s > 60s , split into {} parts".format(duration / 1000.0, len(files)))
+
+                for path in files:
+                    # support: <2M, <60s, mp3/wma/wav/amr
+                    try:
+                        with open(path, "rb") as f:
+                            response = self.client.material.add("voice", f)
+                            logger.debug("[wechatmp] upload voice response: {}".format(response))
+                            f_size = os.fstat(f.fileno()).st_size
+                            time.sleep(1.0 + 2 * f_size / 1024 / 1024)
+                            # todo check media_id
+                    except WeChatClientException as e:
+                        logger.error("[wechatmp] upload voice failed: {}".format(e))
+                        return
+                    media_id = response["media_id"]
+                    logger.info("[wechatmp] voice uploaded, receiver {}, media_id {}".format(receiver, media_id))
+                    self.cache_dict[receiver].append(("voice", media_id))
 
             elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
                 img_url = reply.content
@@ -119,7 +124,7 @@ class WechatMPChannel(ChatChannel):
                     return
                 media_id = response["media_id"]
                 logger.info("[wechatmp] image uploaded, receiver {}, media_id {}".format(receiver, media_id))
-                self.cache_dict[receiver] = ("image", media_id)
+                self.cache_dict[receiver].append(("image", media_id))
             elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
                 image_storage = reply.content
                 image_storage.seek(0)
@@ -134,7 +139,7 @@ class WechatMPChannel(ChatChannel):
                     return
                 media_id = response["media_id"]
                 logger.info("[wechatmp] image uploaded, receiver {}, media_id {}".format(receiver, media_id))
-                self.cache_dict[receiver] = ("image", media_id)
+                self.cache_dict[receiver].append(("image", media_id))
         else:
             if reply.type == ReplyType.TEXT or reply.type == ReplyType.INFO or reply.type == ReplyType.ERROR:
                 reply_text = reply.content
@@ -162,13 +167,28 @@ class WechatMPChannel(ChatChannel):
                         file_name = os.path.basename(file_path)
                         file_type = "audio/mpeg"
                     logger.info("[wechatmp] file_name: {}, file_type: {} ".format(file_name, file_type))
-                    # support: <2M, <60s, AMR\MP3
-                    response = self.client.media.upload("voice", (file_name, open(file_path, "rb"), file_type))
-                    logger.debug("[wechatmp] upload voice response: {}".format(response))
+                    media_ids = []
+                    duration, files = split_audio(file_path, 60 * 1000)
+                    if len(files) > 1:
+                        logger.info("[wechatmp] voice too long {}s > 60s , split into {} parts".format(duration / 1000.0, len(files)))
+                    for path in files:
+                        # support: <2M, <60s, AMR\MP3
+                        response = self.client.media.upload("voice", (os.path.basename(path), open(path, "rb"), file_type))
+                        logger.debug("[wechatcom] upload voice response: {}".format(response))
+                        media_ids.append(response["media_id"])
+                        os.remove(path)
                 except WeChatClientException as e:
                     logger.error("[wechatmp] upload voice failed: {}".format(e))
                     return
-                self.client.message.send_voice(receiver, response["media_id"])
+
+                try:
+                    os.remove(file_path)
+                except Exception:
+                    pass
+
+                for media_id in media_ids:
+                    self.client.message.send_voice(receiver, media_id)
+                    time.sleep(1)
                 logger.info("[wechatmp] Do send voice to {}".format(receiver))
             elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
                 img_url = reply.content

channel/wework/run.py

@@ -0,0 +1,17 @@
+import os
+import time
+os.environ['ntwork_LOG'] = "ERROR"
+import ntwork
+
+wework = ntwork.WeWork()
+
+
+def forever():
+    try:
+        while True:
+            time.sleep(0.1)
+    except KeyboardInterrupt:
+        ntwork.exit_()
+        os._exit(0)
+
+

channel/wework/wework_channel.py

@@ -0,0 +1,326 @@
+import io
+import os
+import random
+import tempfile
+import threading
+os.environ['ntwork_LOG'] = "ERROR"
+import ntwork
+import requests
+import uuid
+
+from bridge.context import *
+from bridge.reply import *
+from channel.chat_channel import ChatChannel
+from channel.wework.wework_message import *
+from channel.wework.wework_message import WeworkMessage
+from common.singleton import singleton
+from common.log import logger
+from common.time_check import time_checker
+from common.utils import compress_imgfile, fsize
+from config import conf
+from channel.wework.run import wework
+from channel.wework import run
+from PIL import Image
+
+
+def get_wxid_by_name(room_members, group_wxid, name):
+    if group_wxid in room_members:
+        for member in room_members[group_wxid]['member_list']:
+            if member['room_nickname'] == name or member['username'] == name:
+                return member['user_id']
+    return None  # 如果没有找到对应的group_wxid或name，则返回None
+
+
+def download_and_compress_image(url, filename, quality=30):
+    # 确定保存图片的目录
+    directory = os.path.join(os.getcwd(), "tmp")
+    # 如果目录不存在，则创建目录
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+    # 下载图片
+    pic_res = requests.get(url, stream=True)
+    image_storage = io.BytesIO()
+    for block in pic_res.iter_content(1024):
+        image_storage.write(block)
+
+    # 检查图片大小并可能进行压缩
+    sz = fsize(image_storage)
+    if sz >= 10 * 1024 * 1024:  # 如果图片大于 10 MB
+        logger.info("[wework] image too large, ready to compress, sz={}".format(sz))
+        image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
+        logger.info("[wework] image compressed, sz={}".format(fsize(image_storage)))
+
+    # 将内存缓冲区的指针重置到起始位置
+    image_storage.seek(0)
+
+    # 读取并保存图片
+    image = Image.open(image_storage)
+    image_path = os.path.join(directory, f"{filename}.png")
+    image.save(image_path, "png")
+
+    return image_path
+
+
+def download_video(url, filename):
+    # 确定保存视频的目录
+    directory = os.path.join(os.getcwd(), "tmp")
+    # 如果目录不存在，则创建目录
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+    # 下载视频
+    response = requests.get(url, stream=True)
+    total_size = 0
+
+    video_path = os.path.join(directory, f"{filename}.mp4")
+
+    with open(video_path, 'wb') as f:
+        for block in response.iter_content(1024):
+            total_size += len(block)
+
+            # 如果视频的总大小超过30MB (30 * 1024 * 1024 bytes)，则停止下载并返回
+            if total_size > 30 * 1024 * 1024:
+                logger.info("[WX] Video is larger than 30MB, skipping...")
+                return None
+
+            f.write(block)
+
+    return video_path
+
+
+def create_message(wework_instance, message, is_group):
+    logger.debug(f"正在为{'群聊' if is_group else '单聊'}创建 WeworkMessage")
+    cmsg = WeworkMessage(message, wework=wework_instance, is_group=is_group)
+    logger.debug(f"cmsg:{cmsg}")
+    return cmsg
+
+
+def handle_message(cmsg, is_group):
+    logger.debug(f"准备用 WeworkChannel 处理{'群聊' if is_group else '单聊'}消息")
+    if is_group:
+        WeworkChannel().handle_group(cmsg)
+    else:
+        WeworkChannel().handle_single(cmsg)
+    logger.debug(f"已用 WeworkChannel 处理完{'群聊' if is_group else '单聊'}消息")
+
+
+def _check(func):
+    def wrapper(self, cmsg: ChatMessage):
+        msgId = cmsg.msg_id
+        create_time = cmsg.create_time  # 消息时间戳
+        if create_time is None:
+            return func(self, cmsg)
+        if 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
+        return func(self, cmsg)
+
+    return wrapper
+
+
+@wework.msg_register(
+    [ntwork.MT_RECV_TEXT_MSG, ntwork.MT_RECV_IMAGE_MSG, 11072, ntwork.MT_RECV_VOICE_MSG])
+def all_msg_handler(wework_instance: ntwork.WeWork, message):
+    logger.debug(f"收到消息: {message}")
+    if 'data' in message:
+        # 首先查找conversation_id，如果没有找到，则查找room_conversation_id
+        conversation_id = message['data'].get('conversation_id', message['data'].get('room_conversation_id'))
+        if conversation_id is not None:
+            is_group = "R:" in conversation_id
+            try:
+                cmsg = create_message(wework_instance=wework_instance, message=message, is_group=is_group)
+            except NotImplementedError as e:
+                logger.error(f"[WX]{message.get('MsgId', 'unknown')} 跳过: {e}")
+                return None
+            delay = random.randint(1, 2)
+            timer = threading.Timer(delay, handle_message, args=(cmsg, is_group))
+            timer.start()
+        else:
+            logger.debug("消息数据中无 conversation_id")
+            return None
+    return None
+
+
+def accept_friend_with_retries(wework_instance, user_id, corp_id):
+    result = wework_instance.accept_friend(user_id, corp_id)
+    logger.debug(f'result:{result}')
+
+
+# @wework.msg_register(ntwork.MT_RECV_FRIEND_MSG)
+# def friend(wework_instance: ntwork.WeWork, message):
+#     data = message["data"]
+#     user_id = data["user_id"]
+#     corp_id = data["corp_id"]
+#     logger.info(f"接收到好友请求，消息内容：{data}")
+#     delay = random.randint(1, 180)
+#     threading.Timer(delay, accept_friend_with_retries, args=(wework_instance, user_id, corp_id)).start()
+#
+#     return None
+
+
+def get_with_retry(get_func, max_retries=5, delay=5):
+    retries = 0
+    result = None
+    while retries < max_retries:
+        result = get_func()
+        if result:
+            break
+        logger.warning(f"获取数据失败，重试第{retries + 1}次······")
+        retries += 1
+        time.sleep(delay)  # 等待一段时间后重试
+    return result
+
+
+@singleton
+class WeworkChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+
+    def startup(self):
+        smart = conf().get("wework_smart", True)
+        wework.open(smart)
+        logger.info("等待登录······")
+        wework.wait_login()
+        login_info = wework.get_login_info()
+        self.user_id = login_info['user_id']
+        self.name = login_info['nickname']
+        logger.info(f"登录信息:>>>user_id:{self.user_id}>>>>>>>>name:{self.name}")
+        logger.info("静默延迟60s，等待客户端刷新数据，请勿进行任何操作······")
+        time.sleep(60)
+        contacts = get_with_retry(wework.get_external_contacts)
+        rooms = get_with_retry(wework.get_rooms)
+        directory = os.path.join(os.getcwd(), "tmp")
+        if not contacts or not rooms:
+            logger.error("获取contacts或rooms失败，程序退出")
+            ntwork.exit_()
+            os.exit(0)
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+        # 将contacts保存到json文件中
+        with open(os.path.join(directory, 'wework_contacts.json'), 'w', encoding='utf-8') as f:
+            json.dump(contacts, f, ensure_ascii=False, indent=4)
+        with open(os.path.join(directory, 'wework_rooms.json'), 'w', encoding='utf-8') as f:
+            json.dump(rooms, f, ensure_ascii=False, indent=4)
+        # 创建一个空字典来保存结果
+        result = {}
+
+        # 遍历列表中的每个字典
+        for room in rooms['room_list']:
+            # 获取聊天室ID
+            room_wxid = room['conversation_id']
+
+            # 获取聊天室成员
+            room_members = wework.get_room_members(room_wxid)
+
+            # 将聊天室成员保存到结果字典中
+            result[room_wxid] = room_members
+
+        # 将结果保存到json文件中
+        with open(os.path.join(directory, 'wework_room_members.json'), 'w', encoding='utf-8') as f:
+            json.dump(result, f, ensure_ascii=False, indent=4)
+        logger.info("wework程序初始化完成········")
+        run.forever()
+
+    @time_checker
+    @_check
+    def handle_single(self, cmsg: ChatMessage):
+        if cmsg.from_user_id == cmsg.to_user_id:
+            # ignore self reply
+            return
+        if cmsg.ctype == ContextType.VOICE:
+            if not conf().get("speech_recognition"):
+                return
+            logger.debug("[WX]receive voice msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[WX]receive image msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.PATPAT:
+            logger.debug("[WX]receive patpat msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            logger.debug("[WX]receive text msg: {}, cmsg={}".format(json.dumps(cmsg._rawmsg, ensure_ascii=False), cmsg))
+        else:
+            logger.debug("[WX]receive msg: {}, cmsg={}".format(cmsg.content, cmsg))
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=False, msg=cmsg)
+        if context:
+            self.produce(context)
+
+    @time_checker
+    @_check
+    def handle_group(self, cmsg: ChatMessage):
+        if cmsg.ctype == ContextType.VOICE:
+            if not conf().get("speech_recognition"):
+                return
+            logger.debug("[WX]receive voice for group msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[WX]receive image for group msg: {}".format(cmsg.content))
+        elif cmsg.ctype in [ContextType.JOIN_GROUP, ContextType.PATPAT]:
+            logger.debug("[WX]receive note msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            pass
+        else:
+            logger.debug("[WX]receive group msg: {}".format(cmsg.content))
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg)
+        if context:
+            self.produce(context)
+
+    # 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, context: Context):
+        logger.debug(f"context: {context}")
+        receiver = context["receiver"]
+        actual_user_id = context["msg"].actual_user_id
+        if reply.type == ReplyType.TEXT or reply.type == ReplyType.TEXT_:
+            match = re.search(r"^@(.*?)\n", reply.content)
+            logger.debug(f"match: {match}")
+            if match:
+                new_content = re.sub(r"^@(.*?)\n", "\n", reply.content)
+                at_list = [actual_user_id]
+                logger.debug(f"new_content: {new_content}")
+                wework.send_room_at_msg(receiver, new_content, at_list)
+            else:
+                wework.send_text(receiver, reply.content)
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+            wework.send_text(receiver, reply.content)
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+            image_storage = reply.content
+            image_storage.seek(0)
+            # Read data from image_storage
+            data = image_storage.read()
+            # Create a temporary file
+            with tempfile.NamedTemporaryFile(delete=False) as temp:
+                temp_path = temp.name
+                temp.write(data)
+            # Send the image
+            wework.send_image(receiver, temp_path)
+            logger.info("[WX] sendImage, receiver={}".format(receiver))
+            # Remove the temporary file
+            os.remove(temp_path)
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+            img_url = reply.content
+            filename = str(uuid.uuid4())
+
+            # 调用你的函数，下载图片并保存为本地文件
+            image_path = download_and_compress_image(img_url, filename)
+
+            wework.send_image(receiver, file_path=image_path)
+            logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
+        elif reply.type == ReplyType.VIDEO_URL:
+            video_url = reply.content
+            filename = str(uuid.uuid4())
+            video_path = download_video(video_url, filename)
+
+            if video_path is None:
+                # 如果视频太大，下载可能会被跳过，此时 video_path 将为 None
+                wework.send_text(receiver, "抱歉，视频太大了！！！")
+            else:
+                wework.send_video(receiver, video_path)
+            logger.info("[WX] sendVideo, receiver={}".format(receiver))
+        elif reply.type == ReplyType.VOICE:
+            current_dir = os.getcwd()
+            voice_file = reply.content.split("/")[-1]
+            reply.content = os.path.join(current_dir, "tmp", voice_file)
+            wework.send_file(receiver, reply.content)
+            logger.info("[WX] sendFile={}, receiver={}".format(reply.content, receiver))

channel/wework/wework_message.py

@@ -0,0 +1,211 @@
+import datetime
+import json
+import os
+import re
+import time
+import pilk
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from ntwork.const import send_type
+
+
+def get_with_retry(get_func, max_retries=5, delay=5):
+    retries = 0
+    result = None
+    while retries < max_retries:
+        result = get_func()
+        if result:
+            break
+        logger.warning(f"获取数据失败，重试第{retries + 1}次······")
+        retries += 1
+        time.sleep(delay)  # 等待一段时间后重试
+    return result
+
+
+def get_room_info(wework, conversation_id):
+    logger.debug(f"传入的 conversation_id: {conversation_id}")
+    rooms = wework.get_rooms()
+    if not rooms or 'room_list' not in rooms:
+        logger.error(f"获取群聊信息失败: {rooms}")
+        return None
+    time.sleep(1)
+    logger.debug(f"获取到的群聊信息: {rooms}")
+    for room in rooms['room_list']:
+        if room['conversation_id'] == conversation_id:
+            return room
+    return None
+
+
+def cdn_download(wework, message, file_name):
+    data = message["data"]
+    aes_key = data["cdn"]["aes_key"]
+    file_size = data["cdn"]["size"]
+
+    # 获取当前工作目录，然后与文件名拼接得到保存路径
+    current_dir = os.getcwd()
+    save_path = os.path.join(current_dir, "tmp", file_name)
+
+    # 下载保存图片到本地
+    if "url" in data["cdn"].keys() and "auth_key" in data["cdn"].keys():
+        url = data["cdn"]["url"]
+        auth_key = data["cdn"]["auth_key"]
+        # result = wework.wx_cdn_download(url, auth_key, aes_key, file_size, save_path)  # ntwork库本身接口有问题，缺失了aes_key这个参数
+        """
+        下载wx类型的cdn文件，以https开头
+        """
+        data = {
+            'url': url,
+            'auth_key': auth_key,
+            'aes_key': aes_key,
+            'size': file_size,
+            'save_path': save_path
+        }
+        result = wework._WeWork__send_sync(send_type.MT_WXCDN_DOWNLOAD_MSG, data)  # 直接用wx_cdn_download的接口内部实现来调用
+    elif "file_id" in data["cdn"].keys():
+        file_type = 2
+        file_id = data["cdn"]["file_id"]
+        result = wework.c2c_cdn_download(file_id, aes_key, file_size, file_type, save_path)
+    else:
+        logger.error(f"something is wrong, data: {data}")
+        return
+
+    # 输出下载结果
+    logger.debug(f"result: {result}")
+
+
+def c2c_download_and_convert(wework, message, file_name):
+    data = message["data"]
+    aes_key = data["cdn"]["aes_key"]
+    file_size = data["cdn"]["size"]
+    file_type = 5
+    file_id = data["cdn"]["file_id"]
+
+    current_dir = os.getcwd()
+    save_path = os.path.join(current_dir, "tmp", file_name)
+    result = wework.c2c_cdn_download(file_id, aes_key, file_size, file_type, save_path)
+    logger.debug(result)
+
+    # 在下载完SILK文件之后，立即将其转换为WAV文件
+    base_name, _ = os.path.splitext(save_path)
+    wav_file = base_name + ".wav"
+    pilk.silk_to_wav(save_path, wav_file, rate=24000)
+
+    # 删除SILK文件
+    try:
+        os.remove(save_path)
+    except Exception as e:
+        pass
+
+
+class WeworkMessage(ChatMessage):
+    def __init__(self, wework_msg, wework, is_group=False):
+        try:
+            super().__init__(wework_msg)
+            self.msg_id = wework_msg['data'].get('conversation_id', wework_msg['data'].get('room_conversation_id'))
+            # 使用.get()防止 'send_time' 键不存在时抛出错误
+            self.create_time = wework_msg['data'].get("send_time")
+            self.is_group = is_group
+            self.wework = wework
+
+            if wework_msg["type"] == 11041:  # 文本消息类型
+                if any(substring in wework_msg['data']['content'] for substring in ("该消息类型暂不能展示", "不支持的消息类型")):
+                    return
+                self.ctype = ContextType.TEXT
+                self.content = wework_msg['data']['content']
+            elif wework_msg["type"] == 11044:  # 语音消息类型，需要缓存文件
+                file_name = datetime.datetime.now().strftime('%Y%m%d%H%M%S') + ".silk"
+                base_name, _ = os.path.splitext(file_name)
+                file_name_2 = base_name + ".wav"
+                current_dir = os.getcwd()
+                self.ctype = ContextType.VOICE
+                self.content = os.path.join(current_dir, "tmp", file_name_2)
+                self._prepare_fn = lambda: c2c_download_and_convert(wework, wework_msg, file_name)
+            elif wework_msg["type"] == 11042:  # 图片消息类型，需要下载文件
+                file_name = datetime.datetime.now().strftime('%Y%m%d%H%M%S') + ".jpg"
+                current_dir = os.getcwd()
+                self.ctype = ContextType.IMAGE
+                self.content = os.path.join(current_dir, "tmp", file_name)
+                self._prepare_fn = lambda: cdn_download(wework, wework_msg, file_name)
+            elif wework_msg["type"] == 11072:  # 新成员入群通知
+                self.ctype = ContextType.JOIN_GROUP
+                member_list = wework_msg['data']['member_list']
+                self.actual_user_nickname = member_list[0]['name']
+                self.actual_user_id = member_list[0]['user_id']
+                self.content = f"{self.actual_user_nickname}加入了群聊！"
+                directory = os.path.join(os.getcwd(), "tmp")
+                rooms = get_with_retry(wework.get_rooms)
+                if not rooms:
+                    logger.error("更新群信息失败···")
+                else:
+                    result = {}
+                    for room in rooms['room_list']:
+                        # 获取聊天室ID
+                        room_wxid = room['conversation_id']
+
+                        # 获取聊天室成员
+                        room_members = wework.get_room_members(room_wxid)
+
+                        # 将聊天室成员保存到结果字典中
+                        result[room_wxid] = room_members
+                    with open(os.path.join(directory, 'wework_room_members.json'), 'w', encoding='utf-8') as f:
+                        json.dump(result, f, ensure_ascii=False, indent=4)
+                    logger.info("有新成员加入，已自动更新群成员列表缓存！")
+            else:
+                raise NotImplementedError(
+                    "Unsupported message type: Type:{} MsgType:{}".format(wework_msg["type"], wework_msg["MsgType"]))
+
+            data = wework_msg['data']
+            login_info = self.wework.get_login_info()
+            logger.debug(f"login_info: {login_info}")
+            nickname = f"{login_info['username']}({login_info['nickname']})" if login_info['nickname'] else login_info['username']
+            user_id = login_info['user_id']
+
+            sender_id = data.get('sender')
+            conversation_id = data.get('conversation_id')
+            sender_name = data.get("sender_name")
+
+            self.from_user_id = user_id if sender_id == user_id else conversation_id
+            self.from_user_nickname = nickname if sender_id == user_id else sender_name
+            self.to_user_id = user_id
+            self.to_user_nickname = nickname
+            self.other_user_nickname = sender_name
+            self.other_user_id = conversation_id
+
+            if self.is_group:
+                conversation_id = data.get('conversation_id') or data.get('room_conversation_id')
+                self.other_user_id = conversation_id
+                if conversation_id:
+                    room_info = get_room_info(wework=wework, conversation_id=conversation_id)
+                    self.other_user_nickname = room_info.get('nickname', None) if room_info else None
+                    at_list = data.get('at_list', [])
+                    tmp_list = []
+                    for at in at_list:
+                        tmp_list.append(at['nickname'])
+                    at_list = tmp_list
+                    logger.debug(f"at_list: {at_list}")
+                    logger.debug(f"nickname: {nickname}")
+                    self.is_at = False
+                    if nickname in at_list or login_info['nickname'] in at_list or login_info['username'] in at_list:
+                        self.is_at = True
+                    self.at_list = at_list
+
+                    # 检查消息内容是否包含@用户名。处理复制粘贴的消息，这类消息可能不会触发@通知，但内容中可能包含 "@用户名"。
+                    content = data.get('content', '')
+                    name = nickname
+                    pattern = f"@{re.escape(name)}(\u2005|\u0020)"
+                    if re.search(pattern, content):
+                        logger.debug(f"Wechaty message {self.msg_id} includes at")
+                        self.is_at = True
+
+                    if not self.actual_user_id:
+                        self.actual_user_id = data.get("sender")
+                    self.actual_user_nickname = sender_name if self.ctype != ContextType.JOIN_GROUP else self.actual_user_nickname
+                else:
+                    logger.error("群聊消息中没有找到 conversation_id 或 room_conversation_id")
+
+            logger.debug(f"WeworkMessage has been successfully instantiated with message id: {self.msg_id}")
+        except Exception as e:
+            logger.error(f"在 WeworkMessage 的初始化过程中出现错误：{e}")
+            raise e

common/const.py

@@ -2,7 +2,11 @@
 OPEN_AI = "openAI"
 CHATGPT = "chatGPT"
 BAIDU = "baidu"
+XUNFEI = "xunfei"
 CHATGPTONAZURE = "chatGPTOnAzure"
 LINKAI = "linkai"
 
 VERSION = "1.3.0"
+
+CLAUDEAI = "claude"
+MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "xunfei","claude"]

config-template.json

@@ -30,6 +30,8 @@
   "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。",
+  "temperature": 0.7,
+  "top_p": 1,
   "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支持图片输入。\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tool、角色扮演和文字冒险等丰富的插件。\n输入{trigger_prefix}#help 查看详细指令。",
   "use_linkai": false,
   "linkai_api_key": "",

config.py

@@ -16,15 +16,15 @@ available_setting = {
     "open_ai_api_base": "https://api.openai.com/v1",
     "proxy": "",  # openai使用的代理
     # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
-    "model": "gpt-3.5-turbo",    # 还支持 gpt-3.5-turbo-16k, gpt-4, wenxin
+    "model": "gpt-3.5-turbo",  # 还支持 gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
     "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
-    "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 
+    "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
@@ -52,16 +52,25 @@ available_setting = {
     "request_timeout": 60,  # chatgpt请求超时时间，openai接口默认设置为600，对于难问题一般需要较长时间
     "timeout": 120,  # chatgpt重试超时时间，在这个时间内，将会自动重试
     # Baidu 文心一言参数
-    "baidu_wenxin_model": "eb-instant", # 默认使用ERNIE-Bot-turbo模型
-    "baidu_wenxin_api_key": "", # Baidu api key
-    "baidu_wenxin_secret_key": "", # Baidu secret key
+    "baidu_wenxin_model": "eb-instant",  # 默认使用ERNIE-Bot-turbo模型
+    "baidu_wenxin_api_key": "",  # Baidu api key
+    "baidu_wenxin_secret_key": "",  # Baidu secret key
+    # 讯飞星火API
+    "xunfei_app_id": "",  # 讯飞应用ID
+    "xunfei_api_key": "",  # 讯飞 API key
+    "xunfei_api_secret": "",  # 讯飞 API secret
+    # claude 配置
+    "claude_api_cookie": "",
+    "claude_uuid": "",
+    # wework的通用配置
+    "wework_smart": True,  # 配置wework是否使用已登录的企业微信，False为多开
     # 语音设置
     "speech_recognition": False,  # 是否开启语音识别
     "group_speech_recognition": False,  # 是否开启群组语音识别
     "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
     "always_reply_voice": False,  # 是否一直使用语音回复
     "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure
-    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure
+    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure,elevenlabs
     # baidu 语音api配置， 使用百度语音识别和语音合成时需要
     "baidu_app_id": "",
     "baidu_api_key": "",
@@ -71,6 +80,9 @@ available_setting = {
     # azure 语音api配置， 使用azure语音识别和语音合成时需要
     "azure_voice_api_key": "",
     "azure_voice_region": "japaneast",
+    # elevenlabs 语音api配置
+    "xi_api_key": "",    #获取ap的方法可以参考https://docs.elevenlabs.io/api-reference/quick-start/authentication
+    "xi_voice_id": "",   #ElevenLabs提供了9种英式、美式等英语发音id，分别是“Adam/Antoni/Arnold/Bella/Domi/Elli/Josh/Rachel/Sam”
     # 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
@@ -112,7 +124,8 @@ available_setting = {
     # 知识库平台配置
     "use_linkai": False,
     "linkai_api_key": "",
-    "linkai_app_code": ""
+    "linkai_app_code": "",
+    "linkai_api_base": "https://api.link-ai.chat",  # linkAI服务地址，若国内无法访问或延迟较高可改为 https://api.link-ai.tech
 }
 
 

docker/Dockerfile.latest

@@ -1,4 +1,4 @@
-FROM python:3.10-slim
+FROM python:3.10-slim-bullseye
 
 LABEL maintainer="foo@bar.com"
 ARG TZ='Asia/Shanghai'
@@ -32,4 +32,4 @@ RUN chmod +x /entrypoint.sh \
 
 USER noroot
 
-ENTRYPOINT ["/entrypoint.sh"]
+ENTRYPOINT ["/entrypoint.sh"]

plugins/godcmd/godcmd.py

@@ -4,15 +4,15 @@ import json
 import os
 import random
 import string
-import traceback
+import logging
 from typing import Tuple
 
+import bridge.bridge
 import plugins
 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, load_config, global_config
 from plugins import *
 
@@ -32,6 +32,10 @@ COMMANDS = {
         "args": ["口令"],
         "desc": "管理员认证",
     },
+    "model": {
+        "alias": ["model", "模型"],
+        "desc": "查看和设置全局模型",
+    },
     "set_openai_api_key": {
         "alias": ["set_openai_api_key"],
         "args": ["api_key"],
@@ -257,6 +261,18 @@ class Godcmd(Plugin):
                                 break
                         if not ok:
                             result = "插件不存在或未启用"
+                elif cmd == "model":
+                    if not isadmin and not self.is_admin_in_group(e_context["context"]):
+                        ok, result = False, "需要管理员权限执行"
+                    elif len(args) == 0:
+                        ok, result = True, "当前模型为: " + str(conf().get("model"))
+                    elif len(args) == 1:
+                        if args[0] not in const.MODEL_LIST:
+                            ok, result = False, "模型名称不存在"
+                        else:
+                            conf()["model"] = args[0]
+                            Bridge().reset_bot()
+                            ok, result = True, "模型设置为: " + str(conf().get("model"))
                 elif cmd == "id":
                     ok, result = True, user
                 elif cmd == "set_openai_api_key":
@@ -294,8 +310,10 @@ class Godcmd(Plugin):
                     except Exception as e:
                         ok, result = False, "你没有设置私有GPT模型"
                 elif cmd == "reset":
-                    if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI]:
+                    if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI]:
                         bot.sessions.clear_session(session_id)
+                        if Bridge().chat_bots.get(bottype):
+                            Bridge().chat_bots.get(bottype).sessions.clear_session(session_id)
                         channel.cancel_session(session_id)
                         ok, result = True, "会话已重置"
                     else:
@@ -317,15 +335,20 @@ class Godcmd(Plugin):
                             load_config()
                             ok, result = True, "配置已重载"
                         elif cmd == "resetall":
-                            if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI]:
+                            if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI,
+                                           const.BAIDU, const.XUNFEI]:
                                 channel.cancel_all_session()
                                 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"
+                            if logger.getEffectiveLevel() == logging.DEBUG:  # 判断当前日志模式是否DEBUG
+                                logger.setLevel(logging.INFO)
+                                ok, result = True, "DEBUG模式已关闭"
+                            else:
+                                logger.setLevel(logging.DEBUG)
+                                ok, result = True, "DEBUG模式已开启"
                         elif cmd == "plist":
                             plugins = PluginManager().list_plugins()
                             ok = True
@@ -437,3 +460,9 @@ class Godcmd(Plugin):
 
     def get_help_text(self, isadmin=False, isgroup=False, **kwargs):
         return get_help_text(isadmin, isgroup)
+
+
+    def is_admin_in_group(self, context):
+        if context["isgroup"]:
+            return context.kwargs.get("msg").actual_user_id in global_config["admin_users"]
+        return False

plugins/keyword/keyword.py

@@ -2,7 +2,7 @@
 
 import json
 import os
-
+import requests
 import plugins
 from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
@@ -51,15 +51,37 @@ class Keyword(Plugin):
         content = e_context["context"].content.strip()
         logger.debug("[keyword] on_handle_context. content: %s" % content)
         if content in self.keyword:
-            logger.debug(f"[keyword] 匹配到关键字【{content}】")
+            logger.info(f"[keyword] 匹配到关键字【{content}】")
             reply_text = self.keyword[content]
 
             # 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
+            if (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".jpg", ".jpeg", ".png", ".gif", ".img"]):
+            # 如果是以 http:// 或 https:// 开头，且".jpg", ".jpeg", ".png", ".gif", ".img"结尾，则认为是图片 URL。
                 reply = Reply()
                 reply.type = ReplyType.IMAGE_URL
                 reply.content = reply_text
+                
+            elif (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".pdf", ".doc", ".docx", ".xls", "xlsx",".zip", ".rar"]):
+            # 如果是以 http:// 或 https:// 开头，且".pdf", ".doc", ".docx", ".xls", "xlsx",".zip", ".rar"结尾，则下载文件到tmp目录并发送给用户
+                file_path = "tmp"
+                if not os.path.exists(file_path):
+                    os.makedirs(file_path)
+                file_name = reply_text.split("/")[-1]  # 获取文件名
+                file_path = os.path.join(file_path, file_name)
+                response = requests.get(reply_text)
+                with open(file_path, "wb") as f:
+                    f.write(response.content)
+                #channel/wechat/wechat_channel.py和channel/wechat_channel.py中缺少ReplyType.FILE类型。
+                reply = Reply()
+                reply.type = ReplyType.FILE
+                reply.content = file_path
+            
+            elif (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".mp4"]):
+            # 如果是以 http:// 或 https:// 开头，且".mp4"结尾，则下载视频到tmp目录并发送给用户
+                reply = Reply()
+                reply.type = ReplyType.VIDEO_URL
+                reply.content = reply_text
+                
             else:
             # 否则认为是普通文本
                 reply = Reply()
@@ -68,7 +90,7 @@ class Keyword(Plugin):
             
             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
-
+            
     def get_help_text(self, **kwargs):
         help_text = "关键词过滤"
         return help_text

plugins/linkai/README.md

@@ -1,18 +1,18 @@
 ## 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。平台地址: https://chat.link-ai.tech/console
+基于 LinkAI 提供的知识库、Midjourney绘画、文档对话等能力对机器人的功能进行增强。平台地址: https://chat.link-ai.tech/console
 
 ## 插件配置
 
-将 `plugins/linkai` 目录下的 `config.json.template` 配置模板复制为最终生效的 `config.json`:
+将 `plugins/linkai` 目录下的 `config.json.template` 配置模板复制为最终生效的 `config.json`。 (如果未配置则会默认使用`config.json.template`模板中配置，但功能默认关闭，需要可通过指令进行开启)。
 
-以下是配置项说明：
+以下是插件配置项说明：
 
 ```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"
+    "group_app_map": {               # 群聊 和 应用编码 的映射关系
+        "测试群名称1": "default",      # 表示在名称为 "测试群名称1" 的群聊中将使用app_code 为 default 的应用
+        "测试群名称2": "Kv2fXJcH"
     },
     "midjourney": {
         "enabled": true,          # midjourney 绘画开关
@@ -21,19 +21,30 @@
         "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
+    },
+    "summary": {
+        "enabled": true,              # 文档总结和对话功能开关
+        "group_enabled": true,        # 是否支持群聊开启
+        "max_file_size": 10000        # 文件的大小限制，单位KB，默认为10M，超过该大小直接忽略
     }
 }
-
 ```
+
+根目录 `config.json` 中配置，`API_KEY` 在 [控制台](https://chat.link-ai.tech/console/interface) 中创建并复制过来:
+
+```bash
+"linkai_api_key": "Link_xxxxxxxxx"
+```
+
 注意：
 
- - 配置项中 `group_app_map` 部分是用于映射群聊与LinkAI平台上的应用， `midjourney` 部分是 mj 画图的配置，可根据需要进行填写，未填写配置时默认不开启相应功能
+ - 配置项中 `group_app_map` 部分是用于映射群聊与LinkAI平台上的应用， `midjourney` 部分是 mj 画图的配置，`summary` 部分是文档总结及对话功能的配置。三部分的配置相互独立，可按需开启
  - 实际 `config.json` 配置中应保证json格式，不应携带 '#' 及后面的注释
  - 如果是`docker`部署，可通过映射 `plugins/config.json` 到容器中来完成插件配置，参考[文档](https://github.com/zhayujie/chatgpt-on-wechat#3-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
 
 ## 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，依赖全局 `config.json` 中的 `use_linkai` 和 `linkai_api_key` 配置；而midjourney绘画功能则只需填写 `linkai_api_key` 配置，`use_linkai` 无论是否关闭均可使用。具体可参考 [详细文档](https://link-ai.tech/platform/link-app/wechat)。
+> 使用插件中的知识库管理功能需要首先开启`linkai`对话，依赖全局 `config.json` 中的 `use_linkai` 和 `linkai_api_key` 配置；而midjourney绘画 和 summary文档总结对话功能则只需填写 `linkai_api_key` 配置，`use_linkai` 无论是否关闭均可使用。具体可参考 [详细文档](https://link-ai.tech/platform/link-app/wechat)。
 
 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。
 
@@ -51,6 +62,8 @@
 
 ### 2.Midjourney绘画功能
 
+若未配置 `plugins/linkai/config.json`，默认会关闭画图功能，直接使用 `$mj open` 可基于默认配置直接使用mj画图。
+
 指令格式：
 
 ```
@@ -69,7 +82,27 @@
 "$mjr 11055927171882"
 ```
 
-注：
-1. 开启 `use_image_create_prefix` 配置后可直接复用全局画图触发词，以"画"开头便可以生成图片。
-2. 提示词内容中包含敏感词或者参数格式错误可能导致绘画失败，生成失败不消耗积分
-3. 使用 `$mj open` 和 `$mj close` 指令可以快速打开和关闭绘图功能
+注意事项：
+1. 使用 `$mj open` 和 `$mj close` 指令可以快速打开和关闭绘图功能
+2. 海外环境部署请将 `img_proxy` 设置为 `false`
+3. 开启 `use_image_create_prefix` 配置后可直接复用全局画图触发词，以"画"开头便可以生成图片。
+4. 提示词内容中包含敏感词或者参数格式错误可能导致绘画失败，生成失败不消耗积分
+5. 若未收到图片可能有两种可能，一种是收到了图片但微信发送失败，可以在后台日志查看有没有获取到图片url，一般原因是受到了wx限制，可以稍后重试或更换账号尝试；另一种情况是图片提示词存在疑似违规，mj不会直接提示错误但会在画图后删掉原图导致程序无法获取，这种情况不消耗积分。
+
+### 3.文档总结对话功能
+
+#### 配置
+
+该功能依赖 LinkAI的知识库及对话功能，需要在项目根目录的config.json中设置 `linkai_api_key`， 同时根据上述插件配置说明，在插件config.json添加 `summary` 部分的配置，设置 `enabled` 为 true。
+
+如果不想创建 `plugins/linkai/config.json` 配置，可以直接通过 `$linkai sum open` 指令开启该功能。
+
+#### 使用
+
+功能开启后，向机器人发送 **文件** 或 **分享链接卡片** 即可生成摘要，进一步可以与文件或链接的内容进行多轮对话。
+
+#### 限制
+
+ 1. 文件目前 支持 `txt`, `docx`, `pdf`, `md`, `csv`格式，文件大小由 `max_file_size` 限制，最大不超过15M，文件字数最多可支持百万字的文件。但不建议上传字数过多的文件，一是token消耗过大，二是摘要很难覆盖到全部内容，只能通过多轮对话来了解细节。
+ 2. 分享链接 目前仅支持 公众号文章，后续会支持更多文章类型及视频链接等
+ 3. 总结及对话的 费用与 LinkAI 3.5-4K 模型的计费方式相同，按文档内容的tokens进行计算

plugins/linkai/config.json.template

@@ -1,7 +1,7 @@
 {
     "group_app_map": {
-        "测试群1": "default",
-        "测试群2": "Kv2fXJcH"
+        "测试群名1": "default",
+        "测试群名2": "Kv2fXJcH"
     },
     "midjourney": {
         "enabled": true,
@@ -10,5 +10,10 @@
         "max_tasks": 3,
         "max_tasks_per_user": 1,
         "use_image_create_prefix": true
+    },
+    "summary": {
+        "enabled": true,
+        "group_enabled": true,
+        "max_file_size": 15000
     }
 }

plugins/linkai/linkai.py

@@ -4,7 +4,11 @@ from bridge.reply import Reply, ReplyType
 from config import global_config
 from plugins import *
 from .midjourney import MJBot
+from .summary import LinkSummary
 from bridge import bridge
+from common.expired_dict import ExpiredDict
+from common import const
+import os
 
 
 @plugins.register(
@@ -12,16 +16,24 @@ from bridge import bridge
     desc="A plugin that supports knowledge base and midjourney drawing.",
     version="0.1.0",
     author="https://link-ai.tech",
+    desire_priority=99
 )
 class LinkAI(Plugin):
     def __init__(self):
         super().__init__()
         self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
         self.config = super().load_config()
+        if not self.config:
+            # 未加载到配置，使用模板中的配置
+            self.config = self._load_config_template()
         if self.config:
             self.mj_bot = MJBot(self.config.get("midjourney"))
+        self.sum_config = {}
+        if self.config:
+            self.sum_config = self.config.get("summary")
         logger.info("[LinkAI] inited")
 
+
     def on_handle_context(self, e_context: EventContext):
         """
         消息处理逻辑
@@ -31,10 +43,39 @@ class LinkAI(Plugin):
             return
 
         context = e_context['context']
-        if context.type not in [ContextType.TEXT, ContextType.IMAGE, ContextType.IMAGE_CREATE]:
+        if context.type not in [ContextType.TEXT, ContextType.IMAGE, ContextType.IMAGE_CREATE, ContextType.FILE, ContextType.SHARING]:
             # filter content no need solve
             return
 
+        if context.type == ContextType.FILE and self._is_summary_open(context):
+            # 文件处理
+            context.get("msg").prepare()
+            file_path = context.content
+            if not LinkSummary().check_file(file_path, self.sum_config):
+                return
+            _send_info(e_context, "正在为你加速生成摘要，请稍后")
+            res = LinkSummary().summary_file(file_path)
+            if not res:
+                _set_reply_text("总结出现异常，请稍后再试吧", e_context)
+                return
+            USER_FILE_MAP[_find_user_id(context) + "-sum_id"] = res.get("summary_id")
+            _set_reply_text(res.get("summary") + "\n\n💬 发送 \"开启对话\" 可以开启与文件内容的对话", e_context, level=ReplyType.TEXT)
+            os.remove(file_path)
+            return
+
+        if (context.type == ContextType.SHARING and self._is_summary_open(context)) or \
+                (context.type == ContextType.TEXT and LinkSummary().check_url(context.content)):
+            if not LinkSummary().check_url(context.content):
+                return
+            _send_info(e_context, "正在为你加速生成摘要，请稍后")
+            res = LinkSummary().summary_url(context.content)
+            if not res:
+                _set_reply_text("总结出现异常，请稍后再试吧", e_context)
+                return
+            _set_reply_text(res.get("summary") + "\n\n💬 发送 \"开启对话\" 可以开启与文章内容的对话", e_context, level=ReplyType.TEXT)
+            USER_FILE_MAP[_find_user_id(context) + "-sum_id"] = res.get("summary_id")
+            return
+
         mj_type = self.mj_bot.judge_mj_task_type(e_context)
         if mj_type:
             # MJ作图任务处理
@@ -46,10 +87,38 @@ class LinkAI(Plugin):
             self._process_admin_cmd(e_context)
             return
 
+        if context.type == ContextType.TEXT and context.content == "开启对话" and _find_sum_id(context):
+            # 文本对话
+            _send_info(e_context, "正在为你开启对话，请稍后")
+            res = LinkSummary().summary_chat(_find_sum_id(context))
+            if not res:
+                _set_reply_text("开启对话失败，请稍后再试吧", e_context)
+                return
+            USER_FILE_MAP[_find_user_id(context) + "-file_id"] = res.get("file_id")
+            _set_reply_text("💡你可以问我关于这篇文章的任何问题，例如：\n\n" + res.get("questions") + "\n\n发送 \"退出对话\" 可以关闭与文章的对话", e_context, level=ReplyType.TEXT)
+            return
+
+        if context.type == ContextType.TEXT and context.content == "退出对话" and _find_file_id(context):
+            del USER_FILE_MAP[_find_user_id(context) + "-file_id"]
+            bot = bridge.Bridge().find_chat_bot(const.LINKAI)
+            bot.sessions.clear_session(context["session_id"])
+            _set_reply_text("对话已退出", e_context, level=ReplyType.TEXT)
+            return
+
+        if context.type == ContextType.TEXT and _find_file_id(context):
+            bot = bridge.Bridge().find_chat_bot(const.LINKAI)
+            context.kwargs["file_id"] = _find_file_id(context)
+            reply = bot.reply(context.content, context)
+            e_context["reply"] = reply
+            e_context.action = EventAction.BREAK_PASS
+            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']
@@ -70,7 +139,7 @@ class LinkAI(Plugin):
                 is_open = False
             conf()["use_linkai"] = is_open
             bridge.Bridge().reset_bot()
-            _set_reply_text(f"知识库功能已{tips_text}", e_context, level=ReplyType.INFO)
+            _set_reply_text(f"LinkAI对话功能{tips_text}", e_context, level=ReplyType.INFO)
             return
 
         if len(cmd) == 3 and cmd[1] == "app":
@@ -91,11 +160,36 @@ class LinkAI(Plugin):
             # 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
 
+        if len(cmd) == 3 and cmd[1] == "sum" and (cmd[2] == "open" or cmd[2] == "close"):
+            # 知识库开关指令
+            if not _is_admin(e_context):
+                _set_reply_text("需要管理员权限执行", e_context, level=ReplyType.ERROR)
+                return
+            is_open = True
+            tips_text = "开启"
+            if cmd[2] == "close":
+                tips_text = "关闭"
+                is_open = False
+            if not self.sum_config:
+                _set_reply_text(f"插件未启用summary功能，请参考以下链添加插件配置\n\nhttps://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/linkai/README.md", e_context, level=ReplyType.INFO)
+            else:
+                self.sum_config["enabled"] = is_open
+                _set_reply_text(f"文章总结功能{tips_text}", e_context, level=ReplyType.INFO)
+            return
+
+        _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
+
+    def _is_summary_open(self, context) -> bool:
+        if not self.sum_config or not self.sum_config.get("enabled"):
+            return False
+        if not context.kwargs.get("isgroup") and not self.sum_config.get("group_enabled"):
+            return False
+        return True
+
     # LinkAI 对话任务处理
     def _is_chat_task(self, e_context: EventContext):
         context = e_context['context']
@@ -109,7 +203,7 @@ class LinkAI(Plugin):
         """
         context = e_context['context']
         # 群聊应用管理
-        group_name = context.kwargs.get("msg").from_user_nickname
+        group_name = context.get("msg").from_user_nickname
         app_code = self._fetch_group_app_code(group_name)
         if app_code:
             context.kwargs['app_code'] = app_code
@@ -127,7 +221,7 @@ class LinkAI(Plugin):
 
     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"
+        help_text = "用于集成 LinkAI 提供的知识库、Midjourney绘画、文档总结对话等能力。\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'
@@ -137,8 +231,27 @@ class LinkAI(Plugin):
         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 - 变换: {trigger_prefix}mjv 图片ID 图片序号\n - 重置: {trigger_prefix}mjr 图片ID"
         help_text += f"\n\n例如：\n\"{trigger_prefix}mj a little cat, white --ar 9:16\"\n\"{trigger_prefix}mju 11055927171882 2\""
         help_text += f"\n\"{trigger_prefix}mjv 11055927171882 2\"\n\"{trigger_prefix}mjr 11055927171882\""
+        help_text += f"\n\n💡 文档总结和对话\n - 开启: {trigger_prefix}linkai sum open\n - 使用: 发送文件、公众号文章等可生成摘要，并与内容对话"
         return help_text
 
+    def _load_config_template(self):
+        logger.debug("No LinkAI plugin config.json, use plugins/linkai/config.json.template")
+        try:
+            plugin_config_path = os.path.join(self.path, "config.json.template")
+            if os.path.exists(plugin_config_path):
+                with open(plugin_config_path, "r", encoding="utf-8") as f:
+                    plugin_conf = json.load(f)
+                    plugin_conf["midjourney"]["enabled"] = False
+                    plugin_conf["summary"]["enabled"] = False
+                    return plugin_conf
+        except Exception as e:
+            logger.exception(e)
+
+
+def _send_info(e_context: EventContext, content: str):
+    reply = Reply(ReplyType.TEXT, content)
+    channel = e_context["channel"]
+    channel.send(reply, e_context["context"])
 
 # 静态方法
 def _is_admin(e_context: EventContext) -> bool:
@@ -154,11 +267,26 @@ def _is_admin(e_context: EventContext) -> bool:
         return context["receiver"] in global_config["admin_users"]
 
 
+def _find_user_id(context):
+    if context["isgroup"]:
+        return context.kwargs.get("msg").actual_user_id
+    else:
+        return context["receiver"]
+
+
 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", "$")
+
+def _find_sum_id(context):
+    return USER_FILE_MAP.get(_find_user_id(context) + "-sum_id")
+
+def _find_file_id(context):
+    return USER_FILE_MAP.get(_find_user_id(context) + "-file_id")
+
+
+USER_FILE_MAP = ExpiredDict(conf().get("expires_in_seconds") or 60 * 60)

plugins/linkai/midjourney.py

@@ -5,7 +5,6 @@ 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
@@ -68,8 +67,7 @@ class MJTask:
 # midjourney bot
 class MJBot:
     def __init__(self, config):
-        self.base_url = "https://api.link-ai.chat/v1/img/midjourney"
-
+        self.base_url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/img/midjourney"
         self.headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
         self.config = config
         self.tasks = {}
@@ -97,7 +95,7 @@ class MJBot:
                 return TaskType.VARIATION
             elif cmd_list[0].lower() == f"{trigger_prefix}mjr":
                 return TaskType.RESET
-        elif context.type == ContextType.IMAGE_CREATE and self.config.get("use_image_create_prefix"):
+        elif context.type == ContextType.IMAGE_CREATE and self.config.get("use_image_create_prefix") and self.config.get("enabled"):
             return TaskType.GENERATE
 
     def process_mj_task(self, mj_type: TaskType, e_context: EventContext):
@@ -310,7 +308,7 @@ class MJBot:
         # send img
         reply = Reply(ReplyType.IMAGE_URL, task.img_url)
         channel = e_context["channel"]
-        channel._send(reply, e_context["context"])
+        _send(channel, reply, e_context["context"])
 
         # send info
         trigger_prefix = conf().get("plugin_trigger_prefix", "$")
@@ -327,7 +325,7 @@ class MJBot:
             text += f"\n\n🔄使用 {trigger_prefix}mjr 命令重新生成图片\n"
             text += f"例如：\n{trigger_prefix}mjr {task.img_id}"
             reply = Reply(ReplyType.INFO, text)
-            channel._send(reply, e_context["context"])
+            _send(channel, reply, e_context["context"])
 
         self._print_tasks()
         return
@@ -406,6 +404,19 @@ class MJBot:
         return result
 
 
+def _send(channel, reply: Reply, context, retry_cnt=0):
+    try:
+        channel.send(reply, context)
+    except Exception as e:
+        logger.error("[WX] sendMsg error: {}".format(str(e)))
+        if isinstance(e, NotImplementedError):
+            return
+        logger.exception(e)
+        if retry_cnt < 2:
+            time.sleep(3 + 3 * retry_cnt)
+            channel.send(reply, context, retry_cnt + 1)
+
+
 def check_prefix(content, prefix_list):
     if not prefix_list:
         return None

plugins/linkai/summary.py

@@ -0,0 +1,89 @@
+import requests
+from config import conf
+from common.log import logger
+import os
+
+
+class LinkSummary:
+    def __init__(self):
+        pass
+
+    def summary_file(self, file_path: str):
+        file_body = {
+            "file": open(file_path, "rb"),
+            "name": file_path.split("/")[-1],
+        }
+        res = requests.post(url=self.base_url() + "/v1/summary/file", headers=self.headers(), files=file_body, timeout=(5, 180))
+        return self._parse_summary_res(res)
+
+    def summary_url(self, url: str):
+        body = {
+            "url": url
+        }
+        res = requests.post(url=self.base_url() + "/v1/summary/url", headers=self.headers(), json=body, timeout=(5, 180))
+        return self._parse_summary_res(res)
+
+    def summary_chat(self, summary_id: str):
+        body = {
+            "summary_id": summary_id
+        }
+        res = requests.post(url=self.base_url() + "/v1/summary/chat", headers=self.headers(), json=body, timeout=(5, 180))
+        if res.status_code == 200:
+            res = res.json()
+            logger.debug(f"[LinkSum] chat open, res={res}")
+            if res.get("code") == 200:
+                data = res.get("data")
+                return {
+                    "questions": data.get("questions"),
+                    "file_id": data.get("file_id")
+                }
+        else:
+            res_json = res.json()
+            logger.error(f"[LinkSum] summary error, status_code={res.status_code}, msg={res_json.get('message')}")
+            return None
+
+    def _parse_summary_res(self, res):
+        if res.status_code == 200:
+            res = res.json()
+            logger.debug(f"[LinkSum] url summary, res={res}")
+            if res.get("code") == 200:
+                data = res.get("data")
+                return {
+                    "summary": data.get("summary"),
+                    "summary_id": data.get("summary_id")
+                }
+        else:
+            res_json = res.json()
+            logger.error(f"[LinkSum] summary error, status_code={res.status_code}, msg={res_json.get('message')}")
+            return None
+
+    def base_url(self):
+        return conf().get("linkai_api_base", "https://api.link-ai.chat")
+
+    def headers(self):
+        return {"Authorization": "Bearer " + conf().get("linkai_api_key")}
+
+    def check_file(self, file_path: str, sum_config: dict) -> bool:
+        file_size = os.path.getsize(file_path) // 1000
+
+        if (sum_config.get("max_file_size") and file_size > sum_config.get("max_file_size")) or file_size > 15000:
+            logger.warn(f"[LinkSum] file size exceeds limit, No processing, file_size={file_size}KB")
+            return True
+
+        suffix = file_path.split(".")[-1]
+        support_list = ["txt", "csv", "docx", "pdf", "md"]
+        if suffix not in support_list:
+            logger.warn(f"[LinkSum] unsupported file, suffix={suffix}, support_list={support_list}")
+            return False
+
+        return True
+
+    def check_url(self, url: str):
+        if not url:
+            return False
+        support_list = ["http://mp.weixin.qq.com", "https://mp.weixin.qq.com"]
+        for support_url in support_list:
+            if url.strip().startswith(support_url):
+                return True
+        logger.debug("[LinkSum] unsupported url, no need to process")
+        return False

plugins/plugin.py

@@ -15,8 +15,8 @@ class Plugin:
         """
         # 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
+        if not plugin_conf:
+            # 全局配置不存在，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", encoding="utf-8") as f:

requirements-optional.txt

@@ -16,13 +16,17 @@ dulwich
 # wechaty
 wechaty>=0.10.7
 wechaty_puppet>=0.4.23
-pysilk_mod>=1.6.0 # needed by send voice
+# pysilk_mod>=1.6.0 # needed by send voice only in wechaty
 
 # wechatmp wechatcom
 web.py
 wechatpy
 
 # chatgpt-tool-hub plugin
-
---extra-index-url https://pypi.python.org/simple
 chatgpt_tool_hub==0.4.6
+
+# xunfei spark
+websocket-client==1.2.0
+
+# claude bot
+curl_cffi

requirements.txt

@@ -6,3 +6,4 @@ requests>=2.28.2
 chardet>=5.1.0
 Pillow
 pre-commit
+web.py

voice/elevent/elevent_voice.py

@@ -0,0 +1,33 @@
+import time
+
+from elevenlabs import set_api_key,generate
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+from config import conf
+
+XI_API_KEY = conf().get("xi_api_key")
+set_api_key(XI_API_KEY)
+name = conf().get("xi_voice_id")
+
+class ElevenLabsVoice(Voice):
+
+    def __init__(self):
+        pass
+
+    def voiceToText(self, voice_file):
+        pass
+
+    def textToVoice(self, text):
+        audio = generate(
+            text=text,
+            voice=name,
+            model='eleven_multilingual_v1'
+        )
+        fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"
+        with open(fileName, "wb") as f:
+            f.write(audio)
+        logger.info("[ElevenLabs] textToVoice text={} voice file name={}".format(text, fileName))
+        return Reply(ReplyType.VOICE, fileName)

voice/factory.py

@@ -29,4 +29,8 @@ def create_voice(voice_type):
         from voice.azure.azure_voice import AzureVoice
 
         return AzureVoice()
+    elif voice_type == "elevenlabs":
+        from voice.elevent.elevent_voice import ElevenLabsVoice
+
+        return ElevenLabsVoice()
     raise RuntimeError