Merge branch 'master' into version/4.0

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -3,22 +3,6 @@ description: 报错或漏洞请使用这个模板创建，不使用此模板创
 title: "[Bug]: "
 labels: ["bug?"]
 body:
-  - type: dropdown
-    attributes:
-      label: 消息平台适配器
-      description: "接入的消息平台类型"
-      options:
-        - 其他（或暂未使用）
-        - Nakuru（go-cqhttp）
-        - aiocqhttp（使用 OneBot 协议接入的）
-        - qq-botpy（QQ官方API WebSocket）
-        - qqofficial（QQ官方API Webhook）
-        - lark（飞书）
-        - wecom（企业微信）
-        - gewechat（个人微信）
-        - discord
-    validations:
-      required: true
   - type: input
     attributes:
       label: 运行环境

.gitignore

@@ -39,4 +39,5 @@ botpy.log*
 /poc
 /libs/wecom_api/test.py
 /venv
-/jp-tyo-churros-05.rockchin.top
+test.py
+/web_ui

README.md

@@ -8,7 +8,7 @@
 
 <a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
-<a href="https://docs.langbot.app">项目主页</a> ｜
+<a href="https://langbot.app">项目主页</a> ｜
 <a href="https://docs.langbot.app/insight/intro.html">功能介绍</a> ｜
 <a href="https://docs.langbot.app/insight/guide.html">部署文档</a> ｜
 <a href="https://docs.langbot.app/usage/faq.html">常见问题</a> ｜
@@ -87,13 +87,14 @@
 | QQ 个人号 | ✅ | QQ 个人号私聊、群聊 |
 | QQ 官方机器人 | ✅ | QQ 官方机器人，支持频道、私聊、群聊 |
 | 企业微信 | ✅ |  |
+| 企微对外客服 | ✅ |  |
 | 个人微信 | ✅ | 使用 [Gewechat](https://github.com/Devo919/Gewechat) 接入 |
 | 微信公众号 | ✅ |  |
 | 飞书 | ✅ |  |
 | 钉钉 | ✅ |  |
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
-| Slack | 🚧 |  |
+| Slack | ✅ |  |
 | LINE | 🚧 |  |
 | WhatsApp | 🚧 |  |
 
@@ -109,6 +110,7 @@
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [智谱AI](https://open.bigmodel.cn/) | ✅ |  |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 资源平台 |
 | [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
 | [Ollama](https://ollama.com/) | ✅ | 本地大模型运行平台 |
 | [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型运行平台 |
@@ -116,6 +118,7 @@
 | [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
 | [阿里云百炼](https://bailian.console.aliyun.com/) | ✅ | 大模型聚合平台, LLMOps 平台 |
 | [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | 大模型聚合平台, LLMOps 平台 |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | 大模型聚合平台 |
 | [MCP](https://modelcontextprotocol.io/) | ✅ | 支持通过 MCP 协议获取工具 |
 
 ### TTS

README_EN.md

@@ -7,7 +7,7 @@
 
 <a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
-<a href="https://docs.langbot.app">Home</a> ｜
+<a href="https://langbot.app">Home</a> ｜
 <a href="https://docs.langbot.app/insight/intro.html">Features</a> ｜
 <a href="https://docs.langbot.app/insight/guide.html">Deployment</a> ｜
 <a href="https://docs.langbot.app/usage/faq.html">FAQ</a> ｜
@@ -45,6 +45,7 @@
 >
 > - Before you start deploying in any way, please read the [New User Guide](https://docs.langbot.app/insight/guide.html).  
 > - All documentation is in Chinese, we will provide i18n version in the near future.
+> - Read [the auto-generated wiki on DeepWiki](https://deepwiki.com/RockChinQ/LangBot).
 
 #### Docker Compose Deployment
 
@@ -85,12 +86,13 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | Personal QQ | ✅ |  |
 | QQ Official API | ✅ |  |
 | WeCom | ✅ |  |
+| WeComCS | ✅ |  |
 | Personal WeChat | ✅ | Use [Gewechat](https://github.com/Devo919/Gewechat) to access |
 | Lark | ✅ |  |
 | DingTalk | ✅ |  |
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
-| Slack | 🚧 |  |
+| Slack | ✅ |  |
 | LINE | 🚧 |  |
 | WhatsApp | 🚧 |  |
 
@@ -107,12 +109,14 @@ Directly use the released version to run, see the [Manual Deployment](https://do
 | [xAI](https://x.ai/) | ✅ |  |
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
 | [Dify](https://dify.ai) | ✅ | LLMOps platform |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
 | [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |
 | [LMStudio](https://lmstudio.ai/) | ✅ | Local LLM running platform |
 | [GiteeAI](https://ai.gitee.com/) | ✅ | LLM interface gateway(MaaS) |
 | [SiliconFlow](https://siliconflow.cn/) | ✅ | LLM gateway(MaaS) |
 | [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | LLM gateway(MaaS), LLMOps platform |
 | [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | LLM gateway(MaaS), LLMOps platform |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | LLM gateway(MaaS) |
 | [MCP](https://modelcontextprotocol.io/) | ✅ | Support tool access through MCP protocol |
 
 ## 🤝 Community Contribution

README_JP.md

@@ -7,7 +7,7 @@
 
 <a href="https://trendshift.io/repositories/12901" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12901" alt="RockChinQ%2FLangBot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
-<a href="https://docs.langbot.app">ホーム</a> ｜
+<a href="https://langbot.app">ホーム</a> ｜
 <a href="https://docs.langbot.app/insight/intro.html">機能</a> ｜
 <a href="https://docs.langbot.app/insight/guide.html">デプロイ</a> ｜
 <a href="https://docs.langbot.app/usage/faq.html">FAQ</a> ｜
@@ -44,6 +44,7 @@
 >
 > - どのデプロイ方法を始める前に、必ず[新規ユーザーガイド](https://docs.langbot.app/insight/guide.html)をお読みください。  
 > - すべてのドキュメントは中国語で提供されています。近い将来、i18nバージョンを提供する予定です。
+> - Read [the auto-generated wiki on DeepWiki](https://deepwiki.com/RockChinQ/LangBot)。
 
 #### Docker Compose デプロイ
 
@@ -84,12 +85,13 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | 個人QQ | ✅ |  |
 | QQ公式API | ✅ |  |
 | WeCom | ✅ |  |
+| WeComCS | ✅ |  |
 | 個人WeChat | ✅ | [Gewechat](https://github.com/Devo919/Gewechat)を使用して接続 |
 | Lark | ✅ |  |
 | DingTalk | ✅ |  |
 | Discord | ✅ |  |
 | Telegram | ✅ |  |
-| Slack | 🚧 |  |
+| Slack | ✅ |  |
 | LINE | 🚧 |  |
 | WhatsApp | 🚧 |  |
 
@@ -105,6 +107,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [Anthropic](https://www.anthropic.com/) | ✅ |  |
 | [xAI](https://x.ai/) | ✅ |  |
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
 | [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |
 | [Ollama](https://ollama.com/) | ✅ | ローカルLLM実行プラットフォーム |
 | [LMStudio](https://lmstudio.ai/) | ✅ | ローカルLLM実行プラットフォーム |
@@ -112,6 +115,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [SiliconFlow](https://siliconflow.cn/) | ✅ | LLMゲートウェイ(MaaS) |
 | [Aliyun Bailian](https://bailian.console.aliyun.com/) | ✅ | LLMゲートウェイ(MaaS), LLMOpsプラットフォーム |
 | [Volc Engine Ark](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | LLMゲートウェイ(MaaS), LLMOpsプラットフォーム |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | LLMゲートウェイ(MaaS) |
 | [MCP](https://modelcontextprotocol.io/) | ✅ | MCPプロトコルをサポート |
 
 ## 🤝 コミュニティ貢献

docker-compose.yaml

@@ -8,6 +8,8 @@ services:
       - ./data:/app/data
       - ./plugins:/app/plugins
     restart: on-failure
+    environment:
+      - TZ=Asia/Shanghai
     ports:
       - 5300:5300  # 供 WebUI 使用
       - 2280-2290:2280-2290  # 供消息平台适配器方向连接

libs/dingtalk_api/api.py

@@ -11,7 +11,12 @@ import traceback
 
 class DingTalkClient:
     def __init__(
-        self, client_id: str, client_secret: str, robot_name: str, robot_code: str
+        self,
+        client_id: str,
+        client_secret: str,
+        robot_name: str,
+        robot_code: str,
+        markdown_card: bool,
     ):
         """初始化 WebSocket 连接并自动启动"""
         self.credential = dingtalk_stream.Credential(client_id, client_secret)
@@ -30,6 +35,7 @@ class DingTalkClient:
         self.robot_name = robot_name
         self.robot_code = robot_code
         self.access_token_expiry_time = ''
+        self.markdown_card = markdown_card
 
     async def get_access_token(self):
         url = 'https://api.dingtalk.com/v1.0/oauth2/accessToken'
@@ -114,7 +120,14 @@ class DingTalkClient:
                 await self._handle_message(event)
 
     async def send_message(self, content: str, incoming_message):
-        self.EchoTextHandler.reply_text(content, incoming_message)
+        if self.markdown_card:
+            self.EchoTextHandler.reply_markdown(
+                title=self.robot_name + '的回答',
+                text=content,
+                incoming_message=incoming_message,
+            )
+        else:
+            self.EchoTextHandler.reply_text(content, incoming_message)
 
     async def get_incoming_message(self):
         """获取收到的消息"""

libs/slack_api/api.py

@@ -0,0 +1,111 @@
+import json
+from quart import Quart, jsonify,request
+from slack_sdk.web.async_client import AsyncWebClient
+from .slackevent import SlackEvent
+from typing import Callable, Dict, Any
+from pkg.platform.types import events as platform_events, message as platform_message
+
+class SlackClient():
+    
+      def __init__(self,bot_token:str,signing_secret:str):
+
+            self.bot_token = bot_token
+            self.signing_secret = signing_secret
+            self.app = Quart(__name__)
+            self.client = AsyncWebClient(self.bot_token)
+            self.app.add_url_rule('/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST'])
+            self._message_handlers = {
+            "example":[],
+            }
+            self.bot_user_id = None # 避免机器人回复自己的消息
+
+      async def handle_callback_request(self):
+            try:
+                  body = await request.get_data()
+                  data = json.loads(body)
+                  if 'type' in data:
+                        if data['type'] == 'url_verification':
+                              return data['challenge']
+                  
+                  bot_user_id = data.get("event",{}).get("bot_id","")
+
+                  if self.bot_user_id and bot_user_id == self.bot_user_id:
+                        return jsonify({'status': 'ok'})
+                  
+                  
+                  # 处理私信
+                  if data and data.get("event", {}).get("channel_type") in ["im"]:
+                        event = SlackEvent.from_payload(data)
+                        await self._handle_message(event)
+                        return jsonify({'status': 'ok'})
+                  
+                  #处理群聊
+                  if data.get("event",{}).get("type") == 'app_mention':
+                             data.setdefault("event", {})["channel_type"] = "channel"
+                             event = SlackEvent.from_payload(data)
+                             await self._handle_message(event)
+                             return jsonify({'status':'ok'})
+
+                  return jsonify({'status': 'ok'})
+            
+            except Exception as e:
+                 raise(e)
+            
+
+
+      async def _handle_message(self, event: SlackEvent):
+        """
+        处理消息事件。
+        """
+        msg_type = event.type
+        if msg_type in self._message_handlers:
+            for handler in self._message_handlers[msg_type]:
+                await handler(event)
+
+      def on_message(self, msg_type: str):
+        """注册消息类型处理器"""
+        def decorator(func: Callable[[platform_events.Event], None]):
+            if msg_type not in self._message_handlers:
+                self._message_handlers[msg_type] = []
+            self._message_handlers[msg_type].append(func)
+            return func
+        return decorator
+
+      async def send_message_to_channel(self,text:str,channel_id:str):
+            try:
+                  response = await self.client.chat_postMessage(
+                        channel=channel_id,
+                        text=text
+                  )
+                  if self.bot_user_id is None and response.get("ok"):
+                        self.bot_user_id = response["message"]["bot_id"]
+                  return 
+            except Exception as e:
+                  raise e
+
+      async def send_message_to_one(self,text:str,user_id:str):
+            try:
+                  response = await self.client.chat_postMessage(
+                        channel = '@'+user_id,
+                        text= text
+                  )
+                  if self.bot_user_id is None and response.get("ok"):
+                        self.bot_user_id = response["message"]["bot_id"]
+                  
+                  return 
+            except Exception as e:
+                  raise e
+
+      async def run_task(self, host: str, port: int, *args, **kwargs):
+            """
+            启动 Quart 应用。
+            """
+            await self.app.run_task(host=host, port=port, *args, **kwargs)
+
+
+
+
+
+            
+
+

libs/slack_api/slackevent.py

@@ -0,0 +1,91 @@
+from typing import Dict, Any, Optional
+
+class SlackEvent(dict):
+    @staticmethod
+    def from_payload(payload: Dict[str, Any]) -> Optional["SlackEvent"]:
+        try:
+            event = SlackEvent(payload)
+            return event
+        except KeyError:
+            return None
+    
+    @property
+    def text(self) -> str:
+        
+        if self.get("event", {}).get("channel_type") == "im":
+                blocks = self.get("event", {}).get("blocks", [])
+                if not blocks:
+                    return ""
+
+                elements = blocks[0].get("elements", [])
+                if not elements:
+                    return "" 
+
+                elements = elements[0].get("elements", [])
+                text = ""
+
+                for el in elements:
+                    if el.get("type") == "text":
+                        text += el.get("text", "")
+                    elif el.get("type") == "link":
+                        text += el.get("url", "")
+
+                return text 
+
+                
+        if self.get("event",{}).get("channel_type") == 'channel': 
+            message_text = ""
+            for block in self.get("event", {}).get("blocks", []):
+                if block.get("type") == "rich_text":
+                    for element in block.get("elements", []):
+                        if element.get("type") == "rich_text_section":
+                            parts = []
+                            for el in element.get("elements", []):
+                                if el.get("type") == "text":
+                                    parts.append(el["text"])
+                                elif el.get("type") == "link":
+                                    parts.append(el["url"])
+                            message_text = "".join(parts)
+                            
+            return message_text
+
+
+    
+    @property
+    def user_id(self) -> Optional[str]:
+        return self.get("event", {}).get("user","")
+    
+    @property
+    def channel_id(self) -> Optional[str]:
+        return self.get("event", {}).get("channel","")
+    
+    @property
+    def type(self) -> str:
+        """ message对应私聊，app_mention对应频道at """
+        return self.get("event", {}).get("channel_type", "")
+    
+    @property
+    def message_id(self) -> str:
+        return self.get("event_id","")
+    
+    @property
+    def pic_url(self) -> str:
+        """提取 Slack 事件中的图片 URL"""
+        files = self.get("event", {}).get("files", [])
+        if files:
+            return files[0].get("url_private", "")
+        return None
+        
+    
+    @property
+    def sender_name(self) -> str:
+        return self.get("event", {}).get("user","")
+    
+    def __getattr__(self, key: str) -> Optional[Any]:
+        return self.get(key)
+
+    def __setattr__(self, key: str, value: Any) -> None:
+        self[key] = value
+
+    def __repr__(self) -> str:
+        return f"<SlackEvent {super().__repr__()}>"

libs/wecom_customer_service_api/api.py

@@ -0,0 +1,343 @@
+from quart import request
+from ..wecom_api.WXBizMsgCrypt3 import WXBizMsgCrypt
+import base64
+import binascii
+import httpx
+import traceback
+from quart import Quart
+import xml.etree.ElementTree as ET
+from typing import Callable, Dict, Any
+from .wecomcsevent import WecomCSEvent
+from pkg.platform.types import events as platform_events, message as platform_message
+import aiofiles
+
+
+class WecomCSClient():
+    def __init__(self,corpid:str,secret:str,token:str,EncodingAESKey:str):
+        self.corpid = corpid
+        self.secret = secret
+        self.access_token_for_contacts =''
+        self.token = token
+        self.aes = EncodingAESKey
+        self.base_url = 'https://qyapi.weixin.qq.com/cgi-bin'
+        self.access_token = ''
+        self.app = Quart(__name__)
+        self.wxcpt = WXBizMsgCrypt(self.token, self.aes, self.corpid)
+        self.app.add_url_rule('/callback/command', 'handle_callback', self.handle_callback_request, methods=['GET', 'POST'])
+        self._message_handlers = {
+            "example":[],
+        }
+
+    async def get_pic_url(self, media_id: str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+
+        url = f"{self.base_url}/media/get?access_token={self.access_token}&media_id={media_id}"
+
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url)
+            if response.headers.get("Content-Type", "").startswith("application/json"):
+                data = response.json()
+                if data.get('errcode') in [40014, 42001]:
+                    self.access_token = await self.get_access_token(self.secret)
+                    return await self.get_pic_url(media_id)
+                else:
+                    raise Exception("Failed to get image: " + str(data))
+
+            # 否则是图片，转成 base64
+            image_bytes = response.content
+            content_type = response.headers.get("Content-Type", "")
+            base64_str = base64.b64encode(image_bytes).decode("utf-8")
+            base64_str = f"data:{content_type};base64,{base64_str}"
+            return base64_str
+
+
+    #access——token操作
+    async def check_access_token(self):
+        return bool(self.access_token and self.access_token.strip())
+
+    async def check_access_token_for_contacts(self):
+        return bool(self.access_token_for_contacts and self.access_token_for_contacts.strip())
+
+    async def get_access_token(self,secret):
+        url = f'https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid={self.corpid}&corpsecret={secret}'
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url)
+            data = response.json()
+            if 'access_token' in data:
+                return data['access_token']
+            else:
+                raise Exception(f"未获取access token: {data}")
+    
+    async def get_detailed_message_list(self,xml_msg:str):
+        # 在本方法中解析消息，并且获得消息的具体内容
+        if isinstance(xml_msg, bytes):
+            xml_msg = xml_msg.decode('utf-8')
+        root = ET.fromstring(xml_msg)
+        token = root.find("Token").text
+        open_kfid = root.find("OpenKfId").text
+        
+        # if open_kfid in self.openkfid_list:
+        #     return None
+        # else:
+        #     self.openkfid_list.append(open_kfid)
+        
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        
+        url = self.base_url+'/kf/sync_msg?access_token='+ self.access_token
+        async with httpx.AsyncClient() as client:
+            params = {
+                "token": token,
+                "voice_format": 0,
+                "open_kfid": open_kfid,
+            }
+            response = await client.post(url,json=params)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.get_detailed_message_list(xml_msg)
+            if data['errcode'] != 0:
+                raise Exception("Failed to get message")
+            
+            last_msg_data = data['msg_list'][-1]
+            open_kfid = last_msg_data.get("open_kfid")
+            # 进行获取图片操作
+            if last_msg_data.get("msgtype") == "image":
+                media_id = last_msg_data.get("image").get("media_id")
+                picurl = await self.get_pic_url(media_id)
+                last_msg_data["picurl"] = picurl
+            # await self.change_service_status(userid=external_userid,openkfid=open_kfid,servicer=servicer)
+            return last_msg_data
+    
+    
+    async def change_service_status(self,userid:str,openkfid:str,servicer:str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url+"/kf/service_state/get?access_token="+self.access_token
+        async with httpx.AsyncClient() as client:
+            params = {
+                "open_kfid" : openkfid,
+                "external_userid" : userid,
+                "service_state" : 1,
+                "servicer_userid" : servicer,
+            }
+            response = await client.post(url,json=params)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.change_service_status(userid,openkfid)
+            if data['errcode'] != 0:
+                raise Exception("Failed to change service status: "+str(data))
+            
+
+    async def send_image(self,user_id:str,agent_id:int,media_id:str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+        url = self.base_url+'/media/upload?access_token='+self.access_token
+        async with httpx.AsyncClient() as client:
+            params = {
+                "touser" : user_id,
+                "toparty" : "",
+                "totag":"",
+                "agentid" : agent_id,
+                "msgtype" : "image",
+                "image" : {
+                    "media_id" : media_id,
+                },
+                "safe":0,
+                "enable_id_trans": 0,
+                "enable_duplicate_check": 0,
+                "duplicate_check_interval": 1800
+            }
+            try:
+                response = await client.post(url,json=params)
+                data = response.json()
+            except Exception as e:
+                raise Exception("Failed to send image: "+str(e))
+
+            # 企业微信错误码40014和42001，代表accesstoken问题
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.send_image(user_id,agent_id,media_id)
+
+            if data['errcode'] != 0:
+                raise Exception("Failed to send image: "+str(data))
+            
+
+    async def send_text_msg(self, open_kfid: str, external_userid: str, msgid: str,content:str):
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+
+        url = f"https://qyapi.weixin.qq.com/cgi-bin/kf/send_msg?access_token={self.access_token}"
+
+        payload = {
+            "touser": external_userid,
+            "open_kfid": open_kfid,
+            "msgid": msgid,
+            "msgtype": "text",
+            "text": {
+                "content": content,
+            }
+        }
+
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, json=payload)
+
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                return await self.send_text_msg(open_kfid,external_userid,msgid,content)
+            if data['errcode'] != 0:
+                raise Exception("Failed to send message")
+            return data
+
+
+    async def handle_callback_request(self):
+        """
+        处理回调请求，包括 GET 验证和 POST 消息接收。
+        """
+        try:
+
+            msg_signature = request.args.get("msg_signature")
+            timestamp = request.args.get("timestamp")
+            nonce = request.args.get("nonce")
+
+            if request.method == "GET":
+                echostr = request.args.get("echostr")
+                ret, reply_echo_str = self.wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
+                if ret != 0:
+                    raise Exception(f"验证失败，错误码: {ret}")
+                return reply_echo_str
+
+            elif request.method == "POST":
+                encrypt_msg = await request.data
+                ret, xml_msg = self.wxcpt.DecryptMsg(encrypt_msg, msg_signature, timestamp, nonce)
+                if ret != 0:
+                    raise Exception(f"消息解密失败，错误码: {ret}")
+
+                # 解析消息并处理
+                message_data = await self.get_detailed_message_list(xml_msg)
+                if message_data is not None:
+                    event = WecomCSEvent.from_payload(message_data) 
+                    if event:
+                        await self._handle_message(event)
+
+                return "success"
+        except Exception as e:
+            traceback.print_exc()
+            return f"Error processing request: {str(e)}", 400
+
+    async def run_task(self, host: str, port: int, *args, **kwargs):
+        """
+        启动 Quart 应用。
+        """
+        await self.app.run_task(host=host, port=port, *args, **kwargs)
+
+    def on_message(self, msg_type: str):
+        """
+        注册消息类型处理器。
+        """
+        def decorator(func: Callable[[WecomCSEvent], None]):
+            if msg_type not in self._message_handlers:
+                self._message_handlers[msg_type] = []
+            self._message_handlers[msg_type].append(func)
+            return func
+        return decorator
+
+    async def _handle_message(self, event: WecomCSEvent):
+        """
+        处理消息事件。
+        """
+        msg_type = event.type
+        if msg_type in self._message_handlers:
+            for handler in self._message_handlers[msg_type]:
+                await handler(event)
+
+    
+    @staticmethod
+    async def get_image_type(image_bytes: bytes) -> str:
+        """
+        通过图片的magic numbers判断图片类型
+        """
+        magic_numbers = {
+            b'\xFF\xD8\xFF': 'jpg',
+            b'\x89\x50\x4E\x47': 'png',
+            b'\x47\x49\x46': 'gif',
+            b'\x42\x4D': 'bmp',
+            b'\x00\x00\x01\x00': 'ico'
+        }
+    
+        for magic, ext in magic_numbers.items():
+            if image_bytes.startswith(magic):
+                return ext
+        return 'jpg'  # 默认返回jpg
+    
+
+    async def upload_to_work(self, image: platform_message.Image):
+        """
+        获取 media_id
+        """
+        if not await self.check_access_token():
+            self.access_token = await self.get_access_token(self.secret)
+
+        url = self.base_url + '/media/upload?access_token=' + self.access_token + '&type=file'
+        file_bytes = None
+        file_name = "uploaded_file.txt"
+
+        # 获取文件的二进制数据
+        if image.path:
+            async with aiofiles.open(image.path, 'rb') as f:
+                file_bytes = await f.read()
+                file_name = image.path.split('/')[-1]
+        elif image.url:
+            file_bytes = await self.download_image_to_bytes(image.url)
+            file_name = image.url.split('/')[-1]
+        elif image.base64:
+            try:
+                base64_data = image.base64
+                if ',' in base64_data:
+                    base64_data = base64_data.split(',', 1)[1]
+                padding = 4 - (len(base64_data) % 4) if len(base64_data) % 4 else 0
+                padded_base64 = base64_data + '=' * padding
+                file_bytes = base64.b64decode(padded_base64)
+            except binascii.Error as e:
+                raise ValueError(f"Invalid base64 string: {str(e)}")
+        else:
+            raise ValueError("image对象出错")
+
+        # 设置 multipart/form-data 格式的文件
+        boundary = "-------------------------acebdf13572468"
+        headers = {
+            'Content-Type': f'multipart/form-data; boundary={boundary}'
+        }
+        body = (
+            f"--{boundary}\r\n"
+            f"Content-Disposition: form-data; name=\"media\"; filename=\"{file_name}\"; filelength={len(file_bytes)}\r\n"
+            f"Content-Type: application/octet-stream\r\n\r\n"
+        ).encode('utf-8') + file_bytes + f"\r\n--{boundary}--\r\n".encode('utf-8')
+
+        # 上传文件
+        async with httpx.AsyncClient() as client:
+            response = await client.post(url, headers=headers, content=body)
+            data = response.json()
+            if data['errcode'] == 40014 or data['errcode'] == 42001:
+                self.access_token = await self.get_access_token(self.secret)
+                media_id = await self.upload_to_work(image)
+            if data.get('errcode', 0) != 0:
+                raise Exception("failed to upload file")
+
+            media_id = data.get('media_id')
+            return media_id
+
+    async def download_image_to_bytes(self,url:str) -> bytes:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url)
+            response.raise_for_status()
+            return response.content
+
+    #进行media_id的获取
+    async def get_media_id(self, image: platform_message.Image):
+
+        media_id = await self.upload_to_work(image=image)
+        return media_id

libs/wecom_customer_service_api/wecomcsevent.py

@@ -0,0 +1,134 @@
+from typing import Dict, Any, Optional
+
+
+class WecomCSEvent(dict):
+    """
+    封装从企业微信收到的事件数据对象（字典），提供属性以获取其中的字段。
+
+    除 `type` 和 `detail_type` 属性对于任何事件都有效外，其它属性是否存在（若不存在则返回 `None`）依事件类型不同而不同。
+    """
+
+    @staticmethod
+    def from_payload(payload: Dict[str, Any]) -> Optional["WecomCSEvent"]:
+        """
+        从企业微信(客服会话)事件数据构造 `WecomEvent` 对象。
+
+        Args:
+            payload (Dict[str, Any]): 解密后的企业微信事件数据。
+
+        Returns:
+            Optional[WecomEvent]: 如果事件数据合法，则返回 WecomEvent 对象；否则返回 None。
+        """
+        try:
+            event = WecomCSEvent(payload)
+            _ = event.type,
+            return event
+        except KeyError:
+            return None
+
+    @property
+    def type(self) -> str:
+        """
+        事件类型，例如 "message"、"event"、"text" 等。
+
+        Returns:
+            str: 事件类型。
+        """
+        return self.get("msgtype", "")
+    
+    @property
+    def user_id(self) -> Optional[str]:
+        """
+        用户 ID，例如消息的发送者或事件的触发者。
+
+        Returns:
+            Optional[str]: 用户 ID。
+        """
+        return self.get("external_userid")
+
+    @property
+    def receiver_id(self) -> Optional[str]:
+        """
+        接收者 ID，例如机器人自身的企业微信 ID。
+
+        Returns:
+            Optional[str]: 接收者 ID。
+        """
+        return self.get("open_kfid","")
+    
+    @property
+    def picurl(self) -> Optional[str]:
+        """
+        图片 URL，仅在图片消息中存在。
+        base64格式
+        Returns:
+            Optional[str]: 图片 URL。
+        """
+
+        return self.get("picurl","")
+
+    @property
+    def message_id(self) -> Optional[str]:
+        """
+        消息 ID，仅在消息类型事件中存在。
+
+        Returns:
+            Optional[str]: 消息 ID。
+        """
+        return self.get("msgid")
+
+    @property
+    def message(self) -> Optional[str]:
+        """
+        消息内容，仅在消息类型事件中存在。
+
+        Returns:
+            Optional[str]: 消息内容。
+        """
+        if self.get("msgtype") == 'text':
+            return self.get("text").get("content","")
+        else:
+            return None
+
+
+    @property
+    def timestamp(self) -> Optional[int]:
+        """
+        事件发生的时间戳。
+
+        Returns:
+            Optional[int]: 时间戳。
+        """
+        return self.get("send_time")
+
+
+    def __getattr__(self, key: str) -> Optional[Any]:
+        """
+        允许通过属性访问数据中的任意字段。
+
+        Args:
+            key (str): 字段名。
+
+        Returns:
+            Optional[Any]: 字段值。
+        """
+        return self.get(key)
+
+    def __setattr__(self, key: str, value: Any) -> None:
+        """
+        允许通过属性设置数据中的任意字段。
+
+        Args:
+            key (str): 字段名。
+            value (Any): 字段值。
+        """
+        self[key] = value
+
+    def __repr__(self) -> str:
+        """
+        生成事件对象的字符串表示。
+
+        Returns:
+            str: 字符串表示。
+        """
+        return f"<WecomEvent {super().__repr__()}>"

pkg/core/bootutils/deps.py

@@ -38,6 +38,7 @@ required_deps = {
     'certifi': 'certifi',
     'mcp': 'mcp',
     'sqlmodel': 'sqlmodel',
+    'telegramify_markdown': 'telegramify-markdown',
 }
 
 

pkg/core/migrations/m038_tg_dingtalk_markdown.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class("tg-dingtalk-markdown", 38)
+class TgDingtalkMarkdownMigration(migration.Migration):
+    """迁移"""
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移"""
+        
+        for adapter in self.ap.platform_cfg.data['platform-adapters']:
+            if adapter['adapter'] in ['dingtalk','telegram']:
+                if 'markdown_card' not in adapter:
+                    return True
+        return False
+    
+    async def run(self):
+        """执行迁移"""
+        for adapter in self.ap.platform_cfg.data['platform-adapters']:
+            if adapter['adapter'] in ['dingtalk','telegram']:
+                if 'markdown_card' not in adapter:
+                    adapter['markdown_card'] = False
+        await self.ap.platform_cfg.dump_config()
+                    

pkg/core/migrations/m039_modelscope_cfg_completion.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class("modelscope-config-completion", 39)
+class ModelScopeConfigCompletionMigration(migration.Migration):
+    """ModelScope配置迁移
+    """
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移
+        """
+        return 'modelscope-chat-completions' not in self.ap.provider_cfg.data['requester'] \
+            or 'modelscope' not in self.ap.provider_cfg.data['keys']
+
+    async def run(self):
+        """执行迁移
+        """
+        if 'modelscope-chat-completions' not in self.ap.provider_cfg.data['requester']:
+            self.ap.provider_cfg.data['requester']['modelscope-chat-completions'] = {
+                'base-url': 'https://api-inference.modelscope.cn/v1',
+                'args': {},
+                'timeout': 120,
+            }
+
+        if 'modelscope' not in self.ap.provider_cfg.data['keys']:
+            self.ap.provider_cfg.data['keys']['modelscope'] = []
+
+        await self.ap.provider_cfg.dump_config()

pkg/core/migrations/m040_ppio_config.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class("ppio-config", 40)
+class PPIOConfigMigration(migration.Migration):
+    """PPIO配置迁移
+    """
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移
+        """
+        return 'ppio-chat-completions' not in self.ap.provider_cfg.data['requester'] \
+            or 'ppio' not in self.ap.provider_cfg.data['keys']
+
+    async def run(self):
+        """执行迁移
+        """
+        if 'ppio-chat-completions' not in self.ap.provider_cfg.data['requester']:
+            self.ap.provider_cfg.data['requester']['ppio-chat-completions'] = {
+                'base-url': 'https://api.ppinfra.com/v3/openai',
+                'args': {},
+                'timeout': 120,
+            }
+
+        if 'ppio' not in self.ap.provider_cfg.data['keys']:
+            self.ap.provider_cfg.data['keys']['ppio'] = []
+
+        await self.ap.provider_cfg.dump_config()

pkg/platform/sources/dingtalk.py

@@ -116,6 +116,7 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):
             client_secret=config['client_secret'],
             robot_name=config['robot_name'],
             robot_code=config['robot_code'],
+            markdown_card=config['markdown_card'],
         )
 
     async def reply_message(

pkg/platform/sources/gewechat.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 import gewechat_client
 
 import typing
@@ -7,7 +5,6 @@ import asyncio
 import traceback
 import time
 import re
-import base64
 import copy
 import threading
 
@@ -21,6 +18,8 @@ from ..types import events as platform_events
 from ..types import entities as platform_entities
 from ...utils import image
 import xml.etree.ElementTree as ET
+from typing import Optional, Tuple
+from functools import partial
 
 
 class GewechatMessageConverter(adapter.MessageConverter):
@@ -49,182 +48,437 @@ class GewechatMessageConverter(adapter.MessageConverter):
                     content_list.extend(
                         await GewechatMessageConverter.yiri2target(node.message_chain)
                     )
+                content_list.append({'type': 'image', 'image': component.url})
+            elif isinstance(component, platform_message.WeChatMiniPrograms):
+                content_list.append(
+                    {
+                        'type': 'WeChatMiniPrograms',
+                        'mini_app_id': component.mini_app_id,
+                        'display_name': component.display_name,
+                        'page_path': component.page_path,
+                        'cover_img_url': component.image_url,
+                        'title': component.title,
+                        'user_name': component.user_name,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatForwardMiniPrograms):
+                content_list.append(
+                    {
+                        'type': 'WeChatForwardMiniPrograms',
+                        'xml_data': component.xml_data,
+                        'image_url': component.image_url,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatEmoji):
+                content_list.append(
+                    {
+                        'type': 'WeChatEmoji',
+                        'emoji_md5': component.emoji_md5,
+                        'emoji_size': component.emoji_size,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatLink):
+                content_list.append(
+                    {
+                        'type': 'WeChatLink',
+                        'link_title': component.link_title,
+                        'link_desc': component.link_desc,
+                        'link_thumb_url': component.link_thumb_url,
+                        'link_url': component.link_url,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatForwardLink):
+                content_list.append(
+                    {'type': 'WeChatForwardLink', 'xml_data': component.xml_data}
+                )
+            elif isinstance(component, platform_message.Voice):
+                content_list.append(
+                    {'type': 'voice', 'url': component.url, 'length': component.length}
+                )
+            elif isinstance(component, platform_message.WeChatForwardImage):
+                content_list.append(
+                    {'type': 'WeChatForwardImage', 'xml_data': component.xml_data}
+                )
+            elif isinstance(component, platform_message.WeChatForwardFile):
+                content_list.append(
+                    {'type': 'WeChatForwardFile', 'xml_data': component.xml_data}
+                )
+            elif isinstance(component, platform_message.WeChatAppMsg):
+                content_list.append(
+                    {'type': 'WeChatAppMsg', 'app_msg': component.app_msg}
+                )
+            # 引用消息转发
+            elif isinstance(component, platform_message.WeChatForwardQuote):
+                content_list.append(
+                    {'type': 'WeChatAppMsg', 'app_msg': component.app_msg}
+                )
+            elif isinstance(component, platform_message.Forward):
+                for node in component.node_list:
+                    if node.message_chain:
+                        content_list.extend(
+                            await GewechatMessageConverter.yiri2target(
+                                node.message_chain
+                            )
+                        )
 
         return content_list
 
     async def target2yiri(
         self, message: dict, bot_account_id: str
     ) -> platform_message.MessageChain:
-        if message['Data']['MsgType'] == 1:
+        """外部消息转平台消息"""
-            # 检查消息开头，如果有 wxid_sbitaz0mt65n22:\n 则删掉
+        # 数据预处理
-            regex = re.compile(r'^wxid_.*:')
+        message_list = []
-            # print(message)
+        ats_bot = False  # 是否被@
+        content = message['Data']['Content']['string']
+        content_no_preifx = content  # 群消息则去掉前缀
+        is_group_message = self._is_group_message(message)
+        if is_group_message:
+            ats_bot = self._ats_bot(message, bot_account_id)
+            if '@所有人' in content:
+                message_list.append(platform_message.AtAll())
+            elif ats_bot:
+                message_list.append(platform_message.At(target=bot_account_id))
+            content_no_preifx, _ = self._extract_content_and_sender(content)
 
-            line_split = message['Data']['Content']['string'].split('\n')
+        msg_type = message['Data']['MsgType']
 
-            if len(line_split) > 0 and regex.match(line_split[0]):
+        # 映射消息类型到处理器方法
-                message['Data']['Content']['string'] = '\n'.join(line_split[1:])
+        handler_map = {
+            1: self._handler_text,
+            3: self._handler_image,
+            34: self._handler_voice,
+            49: self._handler_compound,  # 复合类型
+        }
 
-            # 正则表达式模式，匹配'@'后跟任意数量的非空白字符
+        # 分派处理
-            pattern = r'@\S+'
+        handler = handler_map.get(msg_type, self._handler_default)
-            at_string = f'@{bot_account_id}'
+        handler_result = await handler(
-            content_list = []
+            message=message,  # 原始的message
-            if at_string in message['Data']['Content']['string']:
+            content_no_preifx=content_no_preifx,  # 处理后的content
-                content_list.append(platform_message.At(target=bot_account_id))
+        )
-                content_list.append(
-                    platform_message.Plain(
-                        message['Data']['Content']['string'].replace(at_string, '', 1)
-                    )
-                )
-            # 更优雅的替换改名后@机器人，仅仅限于单独AT的情况
-            elif (
-                'PushContent' in message['Data']
-                and '在群聊中@了你' in message['Data']['PushContent']
-            ):
-                if (
-                    '@所有人' in message['Data']['Content']['string']
-                ):  # at全员时候传入atll不当作at自己
-                    content_list.append(platform_message.AtAll())
-                else:
-                    content_list.append(platform_message.At(target=bot_account_id))
-                content_list.append(
-                    platform_message.Plain(
-                        re.sub(pattern, '', message['Data']['Content']['string'])
-                    )
-                )
-            else:
-                content_list = [
-                    platform_message.Plain(message['Data']['Content']['string'])
-                ]
 
-            return platform_message.MessageChain(content_list)
+        if handler_result and len(handler_result) > 0:
+            message_list.extend(handler_result)
 
-        elif message['Data']['MsgType'] == 3:
+        return platform_message.MessageChain(message_list)
-            image_xml = message['Data']['Content']['string']
+
+    async def _handler_text(
+        self, message: Optional[dict], content_no_preifx: str
+    ) -> platform_message.MessageChain:
+        """处理文本消息 (msg_type=1)"""
+        if message and self._is_group_message(message):
+            pattern = r'@\S{1,20}'
+            content_no_preifx = re.sub(pattern, '', content_no_preifx)
+
+        return platform_message.MessageChain(
+            [platform_message.Plain(content_no_preifx)]
+        )
+
+    async def _handler_image(
+        self, message: Optional[dict], content_no_preifx: str
+    ) -> platform_message.MessageChain:
+        """处理图像消息 (msg_type=3)"""
+        try:
+            image_xml = content_no_preifx
             if not image_xml:
                 return platform_message.MessageChain(
-                    [platform_message.Plain(text='[图片内容为空]')]
+                    [platform_message.Unknown('[图片内容为空]')]
                 )
 
-            try:
+            base64_str, image_format = await image.get_gewechat_image_base64(
-                base64_str, image_format = await image.get_gewechat_image_base64(
+                gewechat_url=self.config['gewechat_url'],
-                    gewechat_url=self.config['gewechat_url'],
+                gewechat_file_url=self.config['gewechat_file_url'],
-                    gewechat_file_url=self.config['gewechat_file_url'],
+                app_id=self.config['app_id'],
-                    app_id=self.config['app_id'],
+                xml_content=image_xml,
-                    xml_content=image_xml,
+                token=self.config['token'],
-                    token=self.config['token'],
+                image_type=2,
-                    image_type=2,
-                )
-
-                return platform_message.MessageChain(
-                    [
-                        platform_message.Image(
-                            base64=f'data:image/{image_format};base64,{base64_str}'
-                        )
-                    ]
-                )
-            except Exception as e:
-                print(f'处理图片消息失败: {str(e)}')
-                return platform_message.MessageChain(
-                    [platform_message.Plain(text='[图片处理失败]')]
-                )
-        elif message['Data']['MsgType'] == 34:
-            audio_base64 = message['Data']['ImgBuf']['buffer']
-            return platform_message.MessageChain(
-                [
-                    platform_message.Voice(
-                        base64=f'data:audio/silk;base64,{audio_base64}'
-                    )
-                ]
             )
-        elif message['Data']['MsgType'] == 49:
-            # 支持微信聊天记录的消息类型，将 XML 内容转换为 MessageChain 传递
-            try:
-                content = message['Data']['Content']['string']
-                # 有三种可能的消息结构weid开头，私聊直接<?xml>和直接<msg>
-                if content.startswith('wxid'):
-                    xml_list = content.split('\n')[2:]
-                    xml_data = '\n'.join(xml_list)
-                elif content.startswith('<?xml'):
-                    xml_list = content.split('\n')[1:]
-                    xml_data = '\n'.join(xml_list)
-                else:
-                    xml_data = content
 
-                content_data = ET.fromstring(xml_data)
+            elements = [
-                # print(xml_data)
+                platform_message.Image(
-                # 拿到细分消息类型，按照gewe接口中描述
+                    base64=f'data:image/{image_format};base64,{base64_str}'
-                """
+                ),
-                小程序：33/36
+                platform_message.WeChatForwardImage(xml_data=image_xml),  # 微信消息转发
-                引用消息：57
+            ]
-                转账消息：2000
+            return platform_message.MessageChain(elements)
-                红包消息：2001
+        except Exception as e:
-                视频号消息：51
+            print(f'处理图片失败: {str(e)}')
-                """
+            return platform_message.MessageChain(
-                appmsg_data = content_data.find('.//appmsg')
+                [platform_message.Unknown('[图片处理失败]')]
-                data_type = appmsg_data.find('.//type').text
+            )
-                if data_type == '57':
+
-                    user_data = appmsg_data.find('.//title').text  # 拿到用户消息
+    async def _handler_voice(
-                    quote_data = (
+        self, message: Optional[dict], content_no_preifx: str
-                        appmsg_data.find('.//refermsg').find('.//content').text
+    ) -> platform_message.MessageChain:
-                    )  # 引用原文
+        """处理语音消息 (msg_type=34)"""
-                    sender_id = (
+        message_List = []
-                        appmsg_data.find('.//refermsg').find('.//chatusr').text
+        try:
-                    )  # 引用用户id
+            # 从消息中提取语音数据（需根据实际数据结构调整字段名）
-                    from_name = message['Data']['FromUserName']['string']
+            audio_base64 = message['Data']['ImgBuf']['buffer']
-                    message_list = []
+
-                    if (
+            # 验证语音数据有效性
-                        message['Wxid'] == sender_id and from_name.endswith('@chatroom')
+            if not audio_base64:
-                    ):  # 因为引用机制暂时无法响应用户，所以当引用用户是机器人是构建一个at激活机器人
+                message_List.append(platform_message.Unknown(text='[语音内容为空]'))
-                        message_list.append(platform_message.At(target=bot_account_id))
+                return platform_message.MessageChain(message_List)
-                    message_list.append(
+
-                        platform_message.Quote(
+            # 转换为平台支持的语音格式（如 Silk 格式）
-                            sender_id=sender_id,
+            voice_element = platform_message.Voice(
-                            origin=platform_message.MessageChain(
+                base64=f'data:audio/silk;base64,{audio_base64}'
-                                [platform_message.Plain(quote_data)]
+            )
-                            ),
+            message_List.append(voice_element)
-                        )
+
-                    )
+        except KeyError as e:
-                    message_list.append(platform_message.Plain(user_data))
+            print(f'语音数据字段缺失: {str(e)}')
-                    return platform_message.MessageChain(message_list)
+            message_List.append(platform_message.Unknown(text='[语音数据解析失败]'))
-                elif data_type == '51':
+        except Exception as e:
-                    return platform_message.MessageChain(
+            print(f'处理语音消息异常: {str(e)}')
-                        [platform_message.Plain(text='[视频号消息]')]
+            message_List.append(platform_message.Unknown(text='[语音处理失败]'))
-                    )
+
-                    # print(content_data)
+        return platform_message.MessageChain(message_List)
-                elif data_type == '2000':
+
-                    return platform_message.MessageChain(
+    async def _handler_compound(
-                        [platform_message.Plain(text='[转账消息]')]
+        self, message: Optional[dict], content_no_preifx: str
-                    )
+    ) -> platform_message.MessageChain:
-                elif data_type == '2001':
+        """处理复合消息 (msg_type=49)，根据子类型分派"""
-                    return platform_message.MessageChain(
+        try:
-                        [platform_message.Plain(text='[红包消息]')]
+            xml_data = ET.fromstring(content_no_preifx)
-                    )
+            appmsg_data = xml_data.find('.//appmsg')
-                elif data_type == '5':
+            if appmsg_data:
-                    return platform_message.MessageChain(
+                data_type = appmsg_data.findtext('.//type', '')
-                        [platform_message.Plain(text='[公众号消息]')]
+
-                    )
+                # 二次分派处理器
-                elif data_type == '33' or data_type == '36':
+                sub_handler_map = {
-                    return platform_message.MessageChain(
+                    '57': self._handler_compound_quote,
-                        [platform_message.Plain(text='[小程序消息]')]
+                    '5': self._handler_compound_link,
-                    )
+                    '6': self._handler_compound_file,
-                # print(data_type.text)
+                    '33': self._handler_compound_mini_program,
+                    '36': self._handler_compound_mini_program,
+                    '2000': partial(
+                        self._handler_compound_unsupported, text='[转账消息]'
+                    ),
+                    '2001': partial(
+                        self._handler_compound_unsupported, text='[红包消息]'
+                    ),
+                    '51': partial(
+                        self._handler_compound_unsupported, text='[视频号消息]'
+                    ),
+                }
+
+                handler = sub_handler_map.get(
+                    data_type, self._handler_compound_unsupported
+                )
+                return await handler(
+                    message=message,  # 原始msg
+                    xml_data=xml_data,  # xml数据
+                )
+            else:
+                return platform_message.MessageChain(
+                    [platform_message.Unknown(text=content_no_preifx)]
+                )
+        except Exception as e:
+            print(f'解析复合消息失败: {str(e)}')
+            return platform_message.MessageChain(
+                [platform_message.Unknown(text=content_no_preifx)]
+            )
+
+    async def _handler_compound_quote(
+        self, message: Optional[dict], xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        """处理引用消息 (data_type=57)"""
+        message_list = []
+        # print("_handler_compound_quote", ET.tostring(xml_data, encoding='unicode'))
+        appmsg_data = xml_data.find('.//appmsg')
+        quote_data = ''  # 引用原文
+        user_data = ''  # 用户消息
+        sender_id = xml_data.findtext('.//fromusername')  # 发送方：单聊用户/群member
+        if appmsg_data:
+            user_data = appmsg_data.findtext('.//title') or ''
+            quote_data = appmsg_data.find('.//refermsg').findtext('.//content')
+            message_list.append(
+                platform_message.WeChatForwardQuote(
+                    app_msg=ET.tostring(appmsg_data, encoding='unicode')
+                )
+            )
+        # quote_data原始的消息
+        if quote_data:
+            quote_data_message_list = platform_message.MessageChain()
+            # 文本消息
+            try:
+                if '<msg>' not in quote_data:
+                    quote_data_message_list.append(platform_message.Plain(quote_data))
                 else:
-                    try:
+                    # 引用消息展开
-                        content_bytes = content.encode('utf-8')
+                    quote_data_xml = ET.fromstring(quote_data)
-                        decoded_content = base64.b64decode(content_bytes)
+                    if quote_data_xml.find('img'):
-                        return platform_message.MessageChain(
+                        quote_data_message_list.extend(
-                            [platform_message.Unknown(content=decoded_content)]
+                            await self._handler_image(None, quote_data)
                         )
-                    except Exception:
+                    elif quote_data_xml.find('voicemsg'):
-                        return platform_message.MessageChain(
+                        quote_data_message_list.extend(
-                            [platform_message.Plain(text=content)]
+                            await self._handler_voice(None, quote_data)
+                        )
+                    elif quote_data_xml.find('videomsg'):
+                        quote_data_message_list.extend(
+                            await self._handler_default(None, quote_data)
+                        )  # 先不处理
+                    else:
+                        # appmsg
+                        quote_data_message_list.extend(
+                            await self._handler_compound(None, quote_data)
                         )
             except Exception as e:
-                print(f'Error processing type 49 message: {str(e)}')
+                print(f'处理引用消息异常 expcetion:{e}')
-                return platform_message.MessageChain(
+                quote_data_message_list.append(platform_message.Plain(quote_data))
-                    [platform_message.Plain(text='[无法解析的消息]')]
+            message_list.append(
+                platform_message.Quote(
+                    sender_id=sender_id,
+                    origin=quote_data_message_list,
                 )
+            )
+            if len(user_data) > 0:
+                pattern = r'@\S{1,20}'
+                user_data = re.sub(pattern, '', user_data)
+                message_list.append(platform_message.Plain(user_data))
+
+        # for comp in message_list:
+        #     if isinstance(comp, platform_message.Quote):
+        #         print(f"quote_message_chain len={len(message_list)}")
+        #         print(f"quote_message_chain send_id={comp.sender_id}" )
+        #         for quote_item in comp.origin:
+        #             print(f"--quote_message_component [msg_type={quote_item.type}][message={quote_item}]" )
+        #     else:
+        #         print(f"quote_message_chain plain [msg_type={comp.type}][message={comp.text}]")
+        return platform_message.MessageChain(message_list)
+
+    async def _handler_compound_file(
+        self, message: dict, xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        """处理文件消息 (data_type=6)"""
+        xml_data_str = ET.tostring(xml_data, encoding='unicode')
+        return platform_message.MessageChain(
+            [platform_message.WeChatForwardFile(xml_data=xml_data_str)]
+        )
+
+    async def _handler_compound_link(
+        self, message: dict, xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        """处理链接消息（如公众号文章、外部网页）"""
+        message_list = []
+        try:
+            # 解析 XML 中的链接参数
+            appmsg = xml_data.find('.//appmsg')
+            if appmsg is None:
+                return platform_message.MessageChain()
+            message_list.append(
+                platform_message.WeChatLink(
+                    link_title=appmsg.findtext('title', ''),
+                    link_desc=appmsg.findtext('des', ''),
+                    link_url=appmsg.findtext('url', ''),
+                    link_thumb_url=appmsg.findtext('thumburl', ''),  # 这个字段拿不到
+                )
+            )
+            # 转发消息
+            xml_data_str = ET.tostring(xml_data, encoding='unicode')
+            # print(xml_data_str)
+            message_list.append(
+                platform_message.WeChatForwardLink(xml_data=xml_data_str)
+            )
+        except Exception as e:
+            print(f'解析链接消息失败: {str(e)}')
+        return platform_message.MessageChain(message_list)
+
+    async def _handler_compound_mini_program(
+        self, message: dict, xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        """处理小程序消息（如小程序卡片、服务通知）"""
+        xml_data_str = ET.tostring(xml_data, encoding='unicode')
+        return platform_message.MessageChain(
+            [platform_message.WeChatForwardMiniPrograms(xml_data=xml_data_str)]
+        )
+
+    async def _handler_default(
+        self, message: Optional[dict], content_no_preifx: str
+    ) -> platform_message.MessageChain:
+        """处理未知消息类型"""
+        if message:
+            msg_type = message['Data']['MsgType']
+        else:
+            msg_type = ''
+        return platform_message.MessageChain(
+            [platform_message.Unknown(text=f'[未知消息类型 msg_type:{msg_type}]')]
+        )
+
+    def _handler_compound_unsupported(
+        self, message: dict, xml_data: str, text: Optional[str] = None
+    ) -> platform_message.MessageChain:
+        """处理未支持复合消息类型(msg_type=49)子类型"""
+        if not text:
+            text = f'[xml_data={xml_data}]'
+        content_list = []
+        content_list.append(
+            platform_message.Unknown(
+                text=f'[处理未支持复合消息类型[msg_type=49]|{text}'
+            )
+        )
+
+        return platform_message.MessageChain(content_list)
+
+    # 返回是否被艾特
+    def _ats_bot(self, message: dict, bot_account_id: str) -> bool:
+        ats_bot = False
+        try:
+            to_user_name = message['Wxid']  # 接收方: 所属微信的wxid
+            raw_content = message['Data']['Content']['string']  # 原始消息内容
+            content_no_prefix, _ = self._extract_content_and_sender(raw_content)
+            # 直接艾特机器人（这个有bug，当被引用的消息里面有@bot,会套娃
+            # ats_bot =  ats_bot or (f"@{bot_account_id}" in content_no_prefix)
+            # 文本类@bot
+            push_content = message.get('Data', {}).get('PushContent', '')
+            ats_bot = ats_bot or ('在群聊中@了你' in push_content)
+            # 引用别人时@bot
+            msg_source = message.get('Data', {}).get('MsgSource', '') or ''
+            if len(msg_source) > 0:
+                msg_source_data = ET.fromstring(msg_source)
+                at_user_list = msg_source_data.findtext('atuserlist') or ''
+                ats_bot = ats_bot or (to_user_name in at_user_list)
+            # 引用bot
+            if message.get('Data', {}).get('MsgType', 0) == 49:
+                xml_data = ET.fromstring(content_no_prefix)
+                appmsg_data = xml_data.find('.//appmsg')
+                tousername = message['Wxid']
+                if appmsg_data:  # 接收方: 所属微信的wxid
+                    quote_id = appmsg_data.find('.//refermsg').findtext(
+                        './/chatusr'
+                    )  # 引用消息的原发送者
+                    ats_bot = ats_bot or (quote_id == tousername)
+        except Exception as e:
+            print(f'_ats_bot got except: {e}')
+        finally:
+            return ats_bot
+
+    # 提取一下content前面的sender_id, 和去掉前缀的内容
+    def _extract_content_and_sender(
+        self, raw_content: str
+    ) -> Tuple[str, Optional[str]]:
+        try:
+            # 检查消息开头，如果有 wxid_sbitaz0mt65n22:\n 则删掉
+            # add: 有些用户的wxid不是上述格式。换成user_name:
+            regex = re.compile(r'^[a-zA-Z0-9_\-]{5,20}:')
+            line_split = raw_content.split('\n')
+            if len(line_split) > 0 and regex.match(line_split[0]):
+                raw_content = '\n'.join(line_split[1:])
+                sender_id = line_split[0].strip(':')
+                return raw_content, sender_id
+        except Exception as e:
+            print(f'_extract_content_and_sender got except: {e}')
+        finally:
+            return raw_content, None
+
+    # 是否是群消息
+    def _is_group_message(self, message: dict) -> bool:
+        from_user_name = message['Data']['FromUserName']['string']
+        return from_user_name.endswith('@chatroom')
 
 
 class GewechatEventConverter(adapter.EventConverter):
@@ -314,7 +568,6 @@ class GeWeChatAdapter(adapter.MessagePlatformAdapter):
     def __init__(self, config: dict, ap: app.Application):
         self.config = config
         self.ap = ap
-
         self.quart_app = quart.Quart(__name__)
 
         self.message_converter = GewechatMessageConverter(config)
@@ -324,6 +577,7 @@ class GeWeChatAdapter(adapter.MessagePlatformAdapter):
         async def gewechat_callback():
             data = await quart.request.json
             # print(json.dumps(data, indent=4, ensure_ascii=False))
+            self.ap.logger.debug(f'Gewechat callback event: {data}')
 
             if 'data' in data:
                 data['Data'] = data['data']
@@ -346,36 +600,105 @@ class GeWeChatAdapter(adapter.MessagePlatformAdapter):
 
                 return 'ok'
 
-    async def send_message(
+    async def _handle_message(
-        self, target_type: str, target_id: str, message: platform_message.MessageChain
+        self, message: platform_message.MessageChain, target_id: str
     ):
-        geweap_msg = await self.message_converter.yiri2target(message)
+        """统一消息处理核心逻辑"""
-        # 此处加上群消息at处理
+        content_list = await self.message_converter.yiri2target(message)
-        ats = [item['target'] for item in geweap_msg if item['type'] == 'at']
+        at_targets = [item['target'] for item in content_list if item['type'] == 'at']
 
-        for msg in geweap_msg:
+        # 处理@逻辑
-            # at主动发送消息
+        at_targets = at_targets or []
-            if msg['type'] == 'text':
+        member_info = []
-                if ats:
+        if at_targets:
-                    member_info = self.bot.get_chatroom_member_detail(
+            member_info = self.bot.get_chatroom_member_detail(
-                        self.config['app_id'], target_id, ats[::-1]
+                self.config['app_id'], target_id, at_targets[::-1]
-                    )['data']
+            )['data']
 
-                    for member in member_info:
+        # 处理消息组件
-                        msg['content'] = f'@{member["nickName"]} {msg["content"]}'
+        for msg in content_list:
-                self.bot.post_text(
+            # 文本消息处理@
+            if msg['type'] == 'text' and at_targets:
+                for member in member_info:
+                    msg['content'] = f'@{member["nickName"]} {msg["content"]}'
+
+            # 统一消息派发
+            handler_map = {
+                'text': lambda msg: self.bot.post_text(
                     app_id=self.config['app_id'],
                     to_wxid=target_id,
                     content=msg['content'],
-                    ats=','.join(ats),
+                    ats=','.join(at_targets),
-                )
+                ),
-
+                'image': lambda msg: self.bot.post_image(
-            elif msg['type'] == 'image':
-                self.bot.post_image(
                     app_id=self.config['app_id'],
                     to_wxid=target_id,
                     img_url=msg['image'],
-                )
+                ),
+                'WeChatForwardMiniPrograms': lambda msg: self.bot.forward_mini_app(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    xml=msg['xml_data'],
+                    cover_img_url=msg.get('image_url'),
+                ),
+                'WeChatEmoji': lambda msg: self.bot.post_emoji(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    emoji_md5=msg['emoji_md5'],
+                    emoji_size=msg['emoji_size'],
+                ),
+                'WeChatLink': lambda msg: self.bot.post_link(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    title=msg['link_title'],
+                    desc=msg['link_desc'],
+                    link_url=msg['link_url'],
+                    thumb_url=msg['link_thumb_url'],
+                ),
+                'WeChatMiniPrograms': lambda msg: self.bot.post_mini_app(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    mini_app_id=msg['mini_app_id'],
+                    display_name=msg['display_name'],
+                    page_path=msg['page_path'],
+                    cover_img_url=msg['cover_img_url'],
+                    title=msg['title'],
+                    user_name=msg['user_name'],
+                ),
+                'WeChatForwardLink': lambda msg: self.bot.forward_url(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'WeChatForwardImage': lambda msg: self.bot.forward_image(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'WeChatForwardFile': lambda msg: self.bot.forward_file(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'voice': lambda msg: self.bot.post_voice(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    voice_url=msg['url'],
+                    voice_duration=msg['length'],
+                ),
+                'WeChatAppMsg': lambda msg: self.bot.post_app_msg(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    appmsg=msg['app_msg'],
+                ),
+                'at': lambda msg: None,
+            }
+
+            if handler := handler_map.get(msg['type']):
+                handler(msg)
+            else:
+                self.ap.logger.warning(f'未处理的消息类型: {msg["type"]}')
+                continue
+
+    async def send_message(
+        self, target_type: str, target_id: str, message: platform_message.MessageChain
+    ):
+        """主动发送消息"""
+        return await self._handle_message(message, target_id)
 
     async def reply_message(
         self,
@@ -383,32 +706,12 @@ class GeWeChatAdapter(adapter.MessagePlatformAdapter):
         message: platform_message.MessageChain,
         quote_origin: bool = False,
     ):
-        content_list = await self.message_converter.yiri2target(message)
+        """回复消息"""
-
+        if message_source.source_platform_object:
-        ats = [item['target'] for item in content_list if item['type'] == 'at']
+            target_id = message_source.source_platform_object['Data']['FromUserName'][
-
+                'string'
-        for msg in content_list:
+            ]
-            if msg['type'] == 'text':
+            return await self._handle_message(message, target_id)
-                if ats:
-                    member_info = self.bot.get_chatroom_member_detail(
-                        self.config['app_id'],
-                        message_source.source_platform_object['Data']['FromUserName'][
-                            'string'
-                        ],
-                        ats[::-1],
-                    )['data']
-
-                    for member in member_info:
-                        msg['content'] = f'@{member["nickName"]} {msg["content"]}'
-
-                self.bot.post_text(
-                    app_id=self.config['app_id'],
-                    to_wxid=message_source.source_platform_object['Data'][
-                        'FromUserName'
-                    ]['string'],
-                    content=msg['content'],
-                    ats=','.join(ats),
-                )
 
     async def is_muted(self, group_id: int) -> bool:
         pass
@@ -448,28 +751,31 @@ class GeWeChatAdapter(adapter.MessagePlatformAdapter):
             f'{self.config["gewechat_url"]}/v2/api', self.config['token']
         )
 
-        app_id, error_msg = self.bot.login(self.config['app_id'])
+        def gewechat_login_process():
-        if error_msg:
+            app_id, error_msg = self.bot.login(self.config['app_id'])
-            raise Exception(f'Gewechat 登录失败: {error_msg}')
+            if error_msg:
+                raise Exception(f'Gewechat 登录失败: {error_msg}')
 
-        self.config['app_id'] = app_id
+            self.config['app_id'] = app_id
 
-        self.ap.logger.info(f'Gewechat 登录成功，app_id: {app_id}')
+            self.ap.logger.info(f'Gewechat 登录成功，app_id: {app_id}')
 
-        await self.ap.platform_mgr.write_back_config('gewechat', self, self.config)
+            self.ap.platform_mgr.write_back_config('gewechat', self, self.config)
 
-        # 获取 nickname
+            # 获取 nickname
-        profile = self.bot.get_profile(self.config['app_id'])
+            profile = self.bot.get_profile(self.config['app_id'])
-        self.bot_account_id = profile['data']['nickName']
+            self.bot_account_id = profile['data']['nickName']
 
-        def thread_set_callback():
+            time.sleep(2)
-            time.sleep(3)
-            ret = self.bot.set_callback(
-                self.config['token'], self.config['callback_url']
-            )
-            print('设置 Gewechat 回调：', ret)
 
-        threading.Thread(target=thread_set_callback).start()
+            try:
+                # gewechat-server容器重启, token会变，但是还会登录成功
+                # 换新token也会收不到回调，要重新登陆下。
+                self.bot.set_callback(self.config['token'], self.config['callback_url'])
+            except Exception as e:
+                raise Exception(f'设置 Gewechat 回调失败， token失效： {e}')
+
+        threading.Thread(target=gewechat_login_process).start()
 
         async def shutdown_trigger_placeholder():
             while True:

pkg/platform/sources/lark.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
 import lark_oapi
-
+from lark_oapi.api.im.v1 import CreateImageRequest, CreateImageRequestBody
+import traceback
 import typing
 import asyncio
-import traceback
 import re
 import base64
 import uuid
@@ -57,12 +57,24 @@ class LarkMessageConverter(adapter.MessageConverter):
         message_chain: platform_message.MessageChain, api_client: lark_oapi.Client
     ) -> typing.Tuple[list]:
         message_elements = []
-
         pending_paragraph = []
-
         for msg in message_chain:
             if isinstance(msg, platform_message.Plain):
-                pending_paragraph.append({'tag': 'md', 'text': msg.text})
+                # Ensure text is valid UTF-8
+                try:
+                    text = msg.text.encode('utf-8').decode('utf-8')
+                    pending_paragraph.append({'tag': 'md', 'text': text})
+                except UnicodeError:
+                    # If text is not valid UTF-8, try to decode with other encodings
+                    try:
+                        text = msg.text.encode('latin1').decode('utf-8')
+                        pending_paragraph.append({'tag': 'md', 'text': text})
+                    except UnicodeError:
+                        # If still fails, replace invalid characters
+                        text = msg.text.encode('utf-8', errors='replace').decode(
+                            'utf-8'
+                        )
+                        pending_paragraph.append({'tag': 'md', 'text': text})
             elif isinstance(msg, platform_message.At):
                 pending_paragraph.append(
                     {'tag': 'at', 'user_id': msg.target, 'style': []}
@@ -73,47 +85,85 @@ class LarkMessageConverter(adapter.MessageConverter):
                 image_bytes = None
 
                 if msg.base64:
-                    image_bytes = base64.b64decode(msg.base64)
+                    try:
+                        # Remove data URL prefix if present
+                        if msg.base64.startswith('data:'):
+                            msg.base64 = msg.base64.split(',', 1)[1]
+                        image_bytes = base64.b64decode(msg.base64)
+                    except Exception:
+                        traceback.print_exc()
+                        continue
                 elif msg.url:
-                    async with aiohttp.ClientSession() as session:
+                    try:
-                        async with session.get(msg.url) as response:
+                        async with aiohttp.ClientSession() as session:
-                            image_bytes = await response.read()
+                            async with session.get(msg.url) as response:
+                                if response.status == 200:
+                                    image_bytes = await response.read()
+                                else:
+                                    traceback.print_exc()
+                                    continue
+                    except Exception:
+                        traceback.print_exc()
+                        continue
                 elif msg.path:
-                    with open(msg.path, 'rb') as f:
+                    try:
-                        image_bytes = f.read()
+                        with open(msg.path, 'rb') as f:
+                            image_bytes = f.read()
+                    except Exception:
+                        traceback.print_exc()
+                        continue
 
-                request: CreateImageRequest = (
+                if image_bytes is None:
-                    CreateImageRequest.builder()
+                    continue
-                    .request_body(
-                        CreateImageRequestBody.builder()
-                        .image_type('message')
-                        .image(image_bytes)
-                        .build()
-                    )
-                    .build()
-                )
 
-                response: CreateImageResponse = await api_client.im.v1.image.acreate(
+                try:
-                    request
+                    # Create a temporary file to store the image bytes
-                )
+                    import tempfile
 
-                if not response.success():
+                    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
-                    raise Exception(
+                        temp_file.write(image_bytes)
-                        f'client.im.v1.image.create failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+                        temp_file.flush()
-                    )
 
-                image_key = response.data.image_key
+                        # Create image request using the temporary file
+                        request = (
+                            CreateImageRequest.builder()
+                            .request_body(
+                                CreateImageRequestBody.builder()
+                                .image_type('message')
+                                .image(open(temp_file.name, 'rb'))
+                                .build()
+                            )
+                            .build()
+                        )
 
-                message_elements.append(pending_paragraph)
+                        response = await api_client.im.v1.image.acreate(request)
-                message_elements.append(
+
-                    [
+                        if not response.success():
-                        {
+                            raise Exception(
-                            'tag': 'img',
+                                f'client.im.v1.image.create failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
-                            'image_key': image_key,
+                            )
-                        }
+
-                    ]
+                        image_key = response.data.image_key
-                )
+
-                pending_paragraph = []
+                        message_elements.append(pending_paragraph)
+                        message_elements.append(
+                            [
+                                {
+                                    'tag': 'img',
+                                    'image_key': image_key,
+                                }
+                            ]
+                        )
+                        pending_paragraph = []
+                except Exception:
+                    traceback.print_exc()
+                    continue
+                finally:
+                    # Clean up the temporary file
+                    import os
+
+                    if 'temp_file' in locals():
+                        os.unlink(temp_file.name)
             elif isinstance(msg, platform_message.Forward):
                 for node in msg.node_list:
                     message_elements.extend(
@@ -326,6 +376,8 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
             try:
                 data = await quart.request.json
 
+                self.ap.logger.debug(f'Lark callback event: {data}')
+
                 if 'encrypt' in data:
                     cipher = AESCipher(self.config['encrypt-key'])
                     data = cipher.decrypt_string(data['encrypt'])
@@ -337,7 +389,6 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
                     type = context.header.event_type
 
                 if 'url_verification' == type:
-                    print(data.get('challenge'))
                     # todo 验证verification token
                     return {'challenge': data.get('challenge')}
                 context = EventContext(data)

pkg/platform/sources/slack.py

@@ -0,0 +1,204 @@
+from __future__ import annotations
+import typing
+import asyncio
+import traceback
+
+import datetime
+
+from libs.slack_api.api import SlackClient
+from pkg.platform.adapter import MessagePlatformAdapter
+from pkg.platform.types import events as platform_events, message as platform_message
+from libs.slack_api.slackevent import SlackEvent
+from pkg.core import app
+from .. import adapter
+from ...core import app
+from ..types import message as platform_message
+from ..types import events as platform_events
+from ..types import entities as platform_entities
+from ...command.errors import ParamNotEnoughError
+from ...utils import image
+
+class SlackMessageConverter(adapter.MessageConverter):
+    
+    @staticmethod
+    async def yiri2target(message_chain:platform_message.MessageChain):
+        content_list = []
+        for msg in message_chain:
+            if type(msg) is platform_message.Plain:
+                content_list.append({
+                    "content":msg.text,
+                })
+        
+        return content_list
+
+    @staticmethod
+    async def target2yiri(message:str,message_id:str,pic_url:str,bot:SlackClient):
+        yiri_msg_list = []
+        yiri_msg_list.append(
+            platform_message.Source(id=message_id,time=datetime.datetime.now())
+        )
+        if pic_url is not None:
+            base64_url = await image.get_slack_image_to_base64(pic_url=pic_url,bot_token=bot.bot_token)
+            yiri_msg_list.append(
+                platform_message.Image(base64=base64_url)
+            )
+
+        yiri_msg_list.append(platform_message.Plain(text=message))
+        chain = platform_message.MessageChain(yiri_msg_list)
+        return chain
+
+
+class SlackEventConverter(adapter.EventConverter):
+    
+    @staticmethod
+    async def yiri2target(event:platform_events.MessageEvent) -> SlackEvent:
+        return event.source_platform_object
+    
+    @staticmethod
+    async def target2yiri(event:SlackEvent,bot:SlackClient):
+        yiri_chain = await SlackMessageConverter.target2yiri(
+            message=event.text,message_id=event.message_id,pic_url=event.pic_url,bot=bot
+        )
+
+        if event.type == 'channel':
+            yiri_chain.insert(0, platform_message.At(target="SlackBot"))
+
+            sender = platform_entities.GroupMember(
+                id = event.user_id,
+                member_name= str(event.sender_name),
+                permission= 'MEMBER',
+                group = platform_entities.Group(
+                    id = event.channel_id,
+                    name = 'MEMBER',
+                    permission= platform_entities.Permission.Member
+                ),
+                special_title='',
+                join_timestamp=0,
+                last_speak_timestamp=0,
+                mute_time_remaining=0
+            )
+            time = int(datetime.datetime.utcnow().timestamp())
+            return platform_events.GroupMessage(
+                sender = sender,
+                message_chain=yiri_chain,
+                time = time,
+                source_platform_object=event
+            )
+
+        if event.type == 'im':
+            return platform_events.FriendMessage(
+                sender=platform_entities.Friend(
+                    id=event.user_id,
+                    nickname = event.sender_name,
+                    remark=""
+                ),
+                message_chain = yiri_chain,
+                time = float(datetime.datetime.now().timestamp()),
+                source_platform_object=event,
+            )
+    
+
+
+
+class SlackAdapter(adapter.MessagePlatformAdapter):
+    bot: SlackClient
+    ap: app.Application
+    bot_account_id: str
+    message_converter: SlackMessageConverter = SlackMessageConverter()
+    event_converter: SlackEventConverter = SlackEventConverter()
+    config: dict
+
+    def __init__(self,config:dict,ap:app.Application):
+        self.config = config
+        self.ap = ap
+        required_keys = [
+            "bot_token",
+            "signing_secret",
+        ]
+        missing_keys = [key for key in required_keys if key not in config]
+        if missing_keys:
+            raise ParamNotEnoughError("Slack机器人缺少相关配置项，请查看文档或联系管理员")
+
+        self.bot = SlackClient(
+            bot_token=self.config["bot_token"],
+            signing_secret=self.config["signing_secret"]
+        ) 
+
+    async def reply_message(
+        self,
+        message_source: platform_events.MessageEvent,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+    ):
+        slack_event = await SlackEventConverter.yiri2target(
+            message_source
+        )
+
+        content_list  = await SlackMessageConverter.yiri2target(message)
+
+        for content in content_list:
+            if slack_event.type == 'channel':
+                await self.bot.send_message_to_channel(
+                    content['content'],slack_event.channel_id
+                )
+            if slack_event.type == 'im':
+                await self.bot.send_message_to_one(
+                    content['content'],slack_event.user_id
+                )
+    
+    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
+        content_list = await SlackMessageConverter.yiri2target(message)
+        for content in content_list:
+            if target_type == 'person':
+                await self.bot.send_message_to_one(content['content'],target_id)
+            if target_type == 'group':
+                await self.bot.send_message_to_channel(content['content'],target_id)
+
+
+    def register_listener(
+        self,
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[
+            [platform_events.Event, adapter.MessagePlatformAdapter], None
+        ],
+    ):
+        async def on_message(event:SlackEvent):
+            self.bot_account_id = 'SlackBot'
+            try:
+                return await callback(
+                    await self.event_converter.target2yiri(event,self.bot),self
+                )
+            except:
+                traceback.print_exc()
+        
+        if event_type == platform_events.FriendMessage:
+            self.bot.on_message("im")(on_message)
+        elif event_type == platform_events.GroupMessage:
+            self.bot.on_message("channel")(on_message)
+
+
+    async def run_async(self):
+        async def shutdown_trigger_placeholder():
+            while True:
+                await asyncio.sleep(1)
+
+        await self.bot.run_task(
+            host="0.0.0.0",
+            port=self.config["port"],
+            shutdown_trigger=shutdown_trigger_placeholder,
+        )
+
+    async def kill(self) -> bool:
+        return False
+
+    async def unregister_listener(
+        self,
+        event_type: type,
+        callback: typing.Callable[[platform_events.Event, MessagePlatformAdapter], None],
+    ):
+        return super().unregister_listener(event_type, callback)
+
+
+        
+    
+

pkg/platform/sources/slack.yaml

@@ -0,0 +1,37 @@
+apiVersion: v1
+kind: MessagePlatformAdapter
+metadata:
+  name: slack
+  label:
+    en_US: Slack API
+    zh_CN: Slack API
+  description:
+    en_US: Slack API
+    zh_CN: Slack API
+spec:
+  config:
+    - name: bot_token
+      label:
+        en_US: Bot Token
+        zh_CN: 机器人令牌
+      type: string
+      required: true
+      default: ""
+    - name: signing_secret
+      label:
+        en_US: signing_secret
+        zh_CN: 密钥
+      type: string
+      required: true
+      default: ""
+    - name: port
+      label:
+        en_US: Port
+        zh_CN: 监听端口
+      type: int
+      required: true
+      default: 2288
+execution:
+  python:
+    path: ./slack.py
+    attr: SlackAdapter

pkg/platform/sources/telegram.py

@@ -4,7 +4,7 @@ import telegram
 import telegram.ext
 from telegram import Update
 from telegram.ext import ApplicationBuilder, ContextTypes, MessageHandler, filters
-
+import telegramify_markdown
 import typing
 import traceback
 import base64
@@ -74,7 +74,8 @@ class TelegramMessageConverter(adapter.MessageConverter):
             message_components.extend(parse_message_text(message_text))
 
         if message.photo:
-            message_components.extend(parse_message_text(message.caption))
+            if message.caption:
+                message_components.extend(parse_message_text(message.caption))
 
             file = await message.photo[-1].get_file()
 
@@ -117,7 +118,7 @@ class TelegramEventConverter(adapter.EventConverter):
                 time=event.message.date.timestamp(),
                 source_platform_object=event,
             )
-        elif event.effective_chat.type == 'group':
+        elif event.effective_chat.type == 'group' or 'supergroup':
             return platform_events.GroupMessage(
                 sender=platform_entities.GroupMember(
                     id=event.effective_chat.id,
@@ -196,17 +197,24 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
 
         for component in components:
             if component['type'] == 'text':
+                if self.config['markdown_card'] is True:
+                    content = telegramify_markdown.markdownify(
+                        content=component['text'],
+                    )
+                else:
+                    content = component['text']
                 args = {
                     'chat_id': message_source.source_platform_object.effective_chat.id,
-                    'text': component['text'],
+                    'text': content,
                 }
+                if self.config['markdown_card'] is True:
+                    args['parse_mode'] = 'MarkdownV2'
+        if quote_origin:
+            args['reply_to_message_id'] = (
+                message_source.source_platform_object.message.id
+            )
 
-                if quote_origin:
+        await self.bot.send_message(**args)
-                    args['reply_to_message_id'] = (
-                        message_source.source_platform_object.message.id
-                    )
-
-                await self.bot.send_message(**args)
 
     async def is_muted(self, group_id: int) -> bool:
         return False

pkg/platform/sources/wecomcs.py

@@ -0,0 +1,223 @@
+from __future__ import annotations
+import typing
+import asyncio
+import traceback
+
+import datetime
+
+from libs.wecom_customer_service_api.api import WecomCSClient
+from pkg.platform.adapter import MessagePlatformAdapter
+from pkg.platform.types import events as platform_events, message as platform_message
+from libs.wecom_customer_service_api.wecomcsevent import WecomCSEvent
+from pkg.core import app
+from .. import adapter
+from ...core import app
+from ..types import message as platform_message
+from ..types import events as platform_events
+from ..types import entities as platform_entities
+from ...command.errors import ParamNotEnoughError
+from ...utils import image
+
+class WecomMessageConverter(adapter.MessageConverter):
+
+    @staticmethod
+    async def yiri2target(
+        message_chain: platform_message.MessageChain, bot: WecomCSClient
+    ):
+        content_list = []
+
+        for msg in message_chain:
+            if type(msg) is platform_message.Plain:
+                content_list.append({
+                    "type": "text",
+                    "content": msg.text,
+                })
+            elif type(msg) is platform_message.Image:
+                content_list.append({
+                    "type": "image",
+                    "media_id": await bot.get_media_id(msg),
+                })
+            elif type(msg) is platform_message.Forward:
+                for node in msg.node_list:
+                    content_list.extend((await WecomMessageConverter.yiri2target(node.message_chain, bot)))
+            else:
+                content_list.append({
+                    "type": "text",
+                    "content": str(msg),
+                })
+
+        return content_list
+
+    @staticmethod
+    async def target2yiri(message: str, message_id: int = -1):
+        yiri_msg_list = []
+        yiri_msg_list.append(
+            platform_message.Source(id=message_id, time=datetime.datetime.now())
+        )
+
+        yiri_msg_list.append(platform_message.Plain(text=message))
+        chain = platform_message.MessageChain(yiri_msg_list)
+
+        return chain
+
+    @staticmethod
+    async def target2yiri_image(picurl: str, message_id: int = -1):
+        yiri_msg_list = []
+        yiri_msg_list.append(
+            platform_message.Source(id=message_id, time=datetime.datetime.now())
+        )
+        yiri_msg_list.append(platform_message.Image(base64=picurl))
+        chain = platform_message.MessageChain(yiri_msg_list)
+        
+        return chain
+
+
+class WecomEventConverter:
+
+    @staticmethod
+    async def yiri2target(
+        event: platform_events.Event, bot_account_id: int, bot: WecomCSClient
+    ) -> WecomCSEvent:
+        # only for extracting user information
+
+        if type(event) is platform_events.GroupMessage:
+            pass
+
+        if type(event) is platform_events.FriendMessage:
+            return event.source_platform_object
+
+    @staticmethod
+    async def target2yiri(event: WecomCSEvent):
+        """
+        将 WecomEvent 转换为平台的 FriendMessage 对象。
+
+        Args:
+            event (WecomEvent): 企业微信客服事件。
+
+        Returns:
+            platform_events.FriendMessage: 转换后的 FriendMessage 对象。
+        """
+        # 转换消息链
+        if event.type == "text":
+            yiri_chain = await WecomMessageConverter.target2yiri(
+                event.message, event.message_id
+            )
+            friend = platform_entities.Friend(
+                id=f"u{event.user_id}",
+                nickname=str(event.user_id),
+                remark="",
+            )
+
+            return platform_events.FriendMessage(
+                sender=friend, message_chain=yiri_chain, time=event.timestamp, source_platform_object=event
+            )
+        elif event.type == "image":
+            friend = platform_entities.Friend(
+                id=f"u{event.user_id}",
+                nickname=str(event.user_id),
+                remark="",
+            )
+
+            yiri_chain = await WecomMessageConverter.target2yiri_image(
+                picurl=event.picurl, message_id=event.message_id
+            )
+
+            return platform_events.FriendMessage(
+                sender=friend, message_chain=yiri_chain, time=event.timestamp, source_platform_object=event
+            )
+
+
+class WecomCSAdapter(adapter.MessagePlatformAdapter):
+
+    bot: WecomCSClient
+    ap: app.Application
+    bot_account_id: str
+    message_converter: WecomMessageConverter = WecomMessageConverter()
+    event_converter: WecomEventConverter = WecomEventConverter()
+    config: dict
+
+    def __init__(self, config: dict, ap: app.Application):
+        self.config = config
+
+        self.ap = ap
+
+        required_keys = [
+            "corpid",
+            "secret",
+            "token",
+            "EncodingAESKey",
+        ]
+        missing_keys = [key for key in required_keys if key not in config]
+        if missing_keys:
+            raise ParamNotEnoughError("企业微信客服缺少相关配置项，请查看文档或联系管理员")
+
+        self.bot = WecomCSClient(
+            corpid=config["corpid"],
+            secret=config["secret"],
+            token=config["token"],
+            EncodingAESKey=config["EncodingAESKey"],
+        )
+
+    async def reply_message(
+        self,
+        message_source: platform_events.MessageEvent,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+    ):
+
+        Wecom_event = await WecomEventConverter.yiri2target(
+            message_source, self.bot_account_id, self.bot
+        )
+        content_list = await WecomMessageConverter.yiri2target(message, self.bot)
+        
+        for content in content_list:
+            if content["type"] == "text":
+                await self.bot.send_text_msg(open_kfid=Wecom_event.receiver_id,external_userid=Wecom_event.user_id,msgid=Wecom_event.message_id,content=content["content"])
+  
+    async def send_message(
+        self, target_type: str, target_id: str, message: platform_message.MessageChain
+    ):
+        pass
+
+    def register_listener(
+        self,
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[
+            [platform_events.Event, adapter.MessagePlatformAdapter], None
+        ],
+    ):
+        async def on_message(event: WecomCSEvent):
+            self.bot_account_id = event.receiver_id
+            try:
+                return await callback(
+                    await self.event_converter.target2yiri(event), self
+                )
+            except:
+                traceback.print_exc()
+
+        if event_type == platform_events.FriendMessage:
+            self.bot.on_message("text")(on_message)
+            self.bot.on_message("image")(on_message)
+        elif event_type == platform_events.GroupMessage:
+            pass
+
+    async def run_async(self):
+        async def shutdown_trigger_placeholder():
+            while True:
+                await asyncio.sleep(1)
+
+        await self.bot.run_task(
+            host="0.0.0.0",
+            port=self.config["port"],
+            shutdown_trigger=shutdown_trigger_placeholder,
+        )
+
+    async def kill(self) -> bool:
+        return False
+
+    async def unregister_listener(
+        self,
+        event_type: type,
+        callback: typing.Callable[[platform_events.Event, MessagePlatformAdapter], None],
+    ):
+        return super().unregister_listener(event_type, callback)

pkg/platform/sources/wecomcs.yaml

@@ -0,0 +1,51 @@
+apiVersion: v1
+kind: MessagePlatformAdapter
+metadata:
+  name: wecomcs
+  label:
+    en_US: WeComCustomerService
+    zh_CN: 企业微信客服
+  description:
+    en_US: WeComCSAdapter
+    zh_CN: 企业微信客服适配器
+spec:
+  config:
+    - name: port
+      label:
+        en_US: Port
+        zh_CN: 监听端口
+      type: int
+      required: true
+      default: 2289
+    - name: corpid
+      label:
+        en_US: Corpid
+        zh_CN: 企业ID
+      type: string
+      required: true
+      default: ""
+    - name: secret
+      label:
+        en_US: Secret
+        zh_CN: 密钥
+      type: string
+      required: true
+      default: ""
+    - name: token
+      label:
+        en_US: Token
+        zh_CN: 令牌
+      type: string
+      required: true
+      default: ""
+    - name: EncodingAESKey
+      label:
+        en_US: EncodingAESKey
+        zh_CN: 消息加解密密钥
+      type: string
+      required: true
+      default: ""
+execution:
+  python:
+    path: ./wecomcs.py
+    attr: WecomCSAdapter

pkg/platform/types/message.py

@@ -1,15 +1,14 @@
 import itertools
 import logging
+import typing
 from datetime import datetime
 from pathlib import Path
-import typing
 
 import pydantic.v1 as pydantic
 
 from . import entities as platform_entities
 from .base import PlatformBaseModel, PlatformIndexedMetaclass, PlatformIndexedModel
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -685,6 +684,9 @@ class Unknown(MessageComponent):
     text: str
     """文本。"""
 
+    def __str__(self):
+        return f'Unknown Message: {self.text}'
+
 
 class Voice(MessageComponent):
     """语音。"""
@@ -863,3 +865,116 @@ class File(MessageComponent):
 
     def __str__(self):
         return f'[文件]{self.name}'
+
+
+# ================ 个人微信专用组件 ================
+
+
+class WeChatMiniPrograms(MessageComponent):
+    """小程序。个人微信专用组件。"""
+
+    type: str = 'WeChatMiniPrograms'
+    """小程序id"""
+    mini_app_id: str
+    """小程序归属用户id"""
+    user_name: str
+    """小程序名称"""
+    display_name: typing.Optional[str] = ''
+    """打开地址"""
+    page_path: typing.Optional[str] = ''
+    """小程序标题"""
+    title: typing.Optional[str] = ''
+    """首页图片"""
+    image_url: typing.Optional[str] = ''
+
+
+class WeChatForwardMiniPrograms(MessageComponent):
+    """转发小程序。个人微信专用组件。"""
+
+    type: str = 'WeChatForwardMiniPrograms'
+    """xml数据"""
+    xml_data: str
+    """首页图片"""
+    image_url: typing.Optional[str] = None
+
+    def __str__(self):
+        return self.xml_data
+
+
+class WeChatEmoji(MessageComponent):
+    """emoji表情。个人微信专用组件。"""
+
+    type: str = 'WeChatEmoji'
+    """emojimd5"""
+    emoji_md5: str
+    """emoji大小"""
+    emoji_size: int
+
+
+class WeChatLink(MessageComponent):
+    """发送链接。个人微信专用组件。"""
+
+    type: str = 'WeChatLink'
+    """标题"""
+    link_title: str = ''
+    """链接描述"""
+    link_desc: str = ''
+    """链接地址"""
+    link_url: str = ''
+    """链接略缩图"""
+    link_thumb_url: str = ''
+
+
+class WeChatForwardLink(MessageComponent):
+    """转发链接。个人微信专用组件。"""
+
+    type: str = 'WeChatForwardLink'
+    """xml数据"""
+    xml_data: str
+
+    def __str__(self):
+        return self.xml_data
+
+
+class WeChatForwardImage(MessageComponent):
+    """转发图片。个人微信专用组件。"""
+
+    type: str = 'WeChatForwardImage'
+    """xml数据"""
+    xml_data: str
+
+    def __str__(self):
+        return self.xml_data
+
+
+class WeChatForwardFile(MessageComponent):
+    """转发文件。个人微信专用组件。"""
+
+    type: str = 'WeChatForwardFile'
+    """xml数据"""
+    xml_data: str
+
+    def __str__(self):
+        return self.xml_data
+
+
+class WeChatAppMsg(MessageComponent):
+    """通用appmsg发送。个人微信专用组件。"""
+
+    type: str = 'WeChatAppMsg'
+    """xml数据"""
+    app_msg: str
+
+    def __str__(self):
+        return self.app_msg
+
+
+class WeChatForwardQuote(MessageComponent):
+    """转发引用消息。个人微信专用组件。"""
+
+    type: str = 'WeChatForwardQuote'
+    """xml数据"""
+    app_msg: str
+
+    def __str__(self):
+        return self.app_msg

pkg/provider/modelmgr/requesters/anthropicmsgs.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 
 import typing
 import json
-
+import platform
+import socket
 import anthropic
 import httpx
 
@@ -25,6 +26,12 @@ class AnthropicMessages(requester.LLMAPIRequester):
     }
 
     async def initialize(self):
+        # 兼容 Windows 缺失 TCP_KEEPINTVL 和 TCP_KEEPCNT 的问题
+        if platform.system() == 'Windows':
+            if not hasattr(socket, 'TCP_KEEPINTVL'):
+                socket.TCP_KEEPINTVL = 0
+            if not hasattr(socket, 'TCP_KEEPCNT'):
+                socket.TCP_KEEPCNT = 0
         httpx_client = anthropic._base_client.AsyncHttpxClientWrapper(
             base_url=self.requester_cfg['base_url'],
             # cast to a valid type because mypy doesn't understand our type narrowing
@@ -61,9 +68,11 @@ class AnthropicMessages(requester.LLMAPIRequester):
             if m.role == 'system':
                 system_role_message = m
 
-                messages.pop(i)
                 break
 
+        if system_role_message:
+            messages.pop(i)
+
         if isinstance(system_role_message, llm_entities.Message) and isinstance(
             system_role_message.content, str
         ):

pkg/provider/modelmgr/requesters/bailianchatcmpl.py

@@ -3,10 +3,10 @@ from __future__ import annotations
 import typing
 import openai
 
-from . import chatcmpl
+from . import modelscopechatcmpl
 
 
-class BailianChatCompletions(chatcmpl.OpenAIChatCompletions):
+class BailianChatCompletions(modelscopechatcmpl.ModelScopeChatCompletions):
     """阿里云百炼大模型平台 ChatCompletion API 请求器"""
 
     client: openai.AsyncClient

pkg/provider/modelmgr/requesters/chatcmpl.py

@@ -26,7 +26,7 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
     async def initialize(self):
         self.client = openai.AsyncClient(
             api_key='',
-            base_url=self.requester_cfg['base_url'],
+            base_url=self.requester_cfg['base-url'].replace(' ', ''),
             timeout=self.requester_cfg['timeout'],
             http_client=httpx.AsyncClient(
                 trust_env=True, timeout=self.requester_cfg['timeout']
@@ -36,8 +36,9 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
     async def _req(
         self,
         args: dict,
+        extra_body: dict = {},
     ) -> chat_completion.ChatCompletion:
-        return await self.client.chat.completions.create(**args)
+        return await self.client.chat.completions.create(**args, extra_body=extra_body)
 
     async def _make_msg(
         self,
@@ -49,6 +50,21 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
         if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
             chatcmpl_message['role'] = 'assistant'
 
+        reasoning_content = (
+            chatcmpl_message['reasoning_content']
+            if 'reasoning_content' in chatcmpl_message
+            else None
+        )
+
+        # deepseek的reasoner模型
+        if reasoning_content is not None:
+            chatcmpl_message['content'] = (
+                '<think>\n'
+                + reasoning_content
+                + '\n</think>\n'
+                + chatcmpl_message['content']
+            )
+
         message = llm_entities.Message(**chatcmpl_message)
 
         return message
@@ -87,7 +103,7 @@ class OpenAIChatCompletions(requester.LLMAPIRequester):
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         # 处理请求结果
         message = await self._make_msg(resp)

pkg/provider/modelmgr/requesters/deepseekchatcmpl.py

@@ -47,7 +47,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         if resp is None:
             raise errors.RequesterError('接口返回为空，请确定模型提供商服务是否正常')

pkg/provider/modelmgr/requesters/giteeaichatcmpl.py

@@ -44,7 +44,7 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
 
         args['messages'] = req_messages
 
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         message = await self._make_msg(resp)
 

pkg/provider/modelmgr/requesters/modelscopechatcmpl.py

@@ -0,0 +1,207 @@
+from __future__ import annotations
+ 
+import asyncio
+import typing
+import json
+import base64
+from typing import AsyncGenerator
+
+import openai
+import openai.types.chat.chat_completion as chat_completion
+import openai.types.chat.chat_completion_message_tool_call as chat_completion_message_tool_call
+import httpx
+import aiohttp
+import async_lru
+
+from .. import entities, errors, requester
+from ....core import entities as core_entities, app
+from ... import entities as llm_entities
+from ...tools import entities as tools_entities
+from ....utils import image
+
+
+class ModelScopeChatCompletions(requester.LLMAPIRequester):
+    """ModelScope ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    requester_cfg: dict
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+
+        self.requester_cfg = self.ap.provider_cfg.data['requester']['modelscope-chat-completions']
+
+    async def initialize(self):
+
+        self.client = openai.AsyncClient(
+            api_key="",
+            base_url=self.requester_cfg['base-url'],
+            timeout=self.requester_cfg['timeout'],
+            http_client=httpx.AsyncClient(
+                trust_env=True,
+                timeout=self.requester_cfg['timeout']
+            )
+        )
+
+    async def _req(
+        self,
+        args: dict,
+    ) -> chat_completion.ChatCompletion:
+        args["stream"] = True
+
+        chunk = None
+
+        pending_content = ""
+
+        tool_calls = []
+
+        resp_gen: openai.AsyncStream = await self.client.chat.completions.create(**args)
+
+        async for chunk in resp_gen:
+            # print(chunk)
+            if not chunk or not chunk.id or not chunk.choices or not chunk.choices[0] or not chunk.choices[0].delta:
+                continue
+
+            if chunk.choices[0].delta.content is not None:
+                pending_content += chunk.choices[0].delta.content
+
+            if chunk.choices[0].delta.tool_calls is not None:
+                for tool_call in chunk.choices[0].delta.tool_calls:
+                    for tc in tool_calls:
+                        if tc.index == tool_call.index:
+                            tc.function.arguments += tool_call.function.arguments
+                            break
+                    else:
+                        tool_calls.append(tool_call)
+            
+            if chunk.choices[0].finish_reason is not None:
+                break
+
+        real_tool_calls = []
+
+        for tc in tool_calls:
+            function = chat_completion_message_tool_call.Function(
+                name=tc.function.name,
+                arguments=tc.function.arguments
+            )
+            real_tool_calls.append(chat_completion_message_tool_call.ChatCompletionMessageToolCall(
+                id=tc.id,
+                function=function,
+                type="function"
+            ))
+
+        return chat_completion.ChatCompletion(
+            id=chunk.id,
+            object="chat.completion",
+            created=chunk.created,
+            choices=[
+                chat_completion.Choice(
+                    index=0,
+                    message=chat_completion.ChatCompletionMessage(
+                        role="assistant",
+                        content=pending_content,
+                        tool_calls=real_tool_calls if len(real_tool_calls) > 0 else None
+                    ),
+                    finish_reason=chunk.choices[0].finish_reason if hasattr(chunk.choices[0], 'finish_reason') and chunk.choices[0].finish_reason is not None else 'stop',
+                    logprobs=chunk.choices[0].logprobs,
+                )
+            ],
+            model=chunk.model,
+            service_tier=chunk.service_tier if hasattr(chunk, 'service_tier') else None,
+            system_fingerprint=chunk.system_fingerprint if hasattr(chunk, 'system_fingerprint') else None,
+            usage=chunk.usage if hasattr(chunk, 'usage') else None
+        ) if chunk else None
+        return await self.client.chat.completions.create(**args)
+
+    async def _make_msg(
+        self,
+        chat_completion: chat_completion.ChatCompletion,
+    ) -> llm_entities.Message:
+        chatcmpl_message = chat_completion.choices[0].message.dict()
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
+            chatcmpl_message['role'] = 'assistant'
+
+        message = llm_entities.Message(**chatcmpl_message)
+
+        return message
+
+    async def _closure(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: entities.LLMModelInfo,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+    ) -> llm_entities.Message:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = self.requester_cfg['args'].copy()
+        args["model"] = use_model.name if use_model.model_name is None else use_model.model_name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args["tools"] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg["content"], list):
+                for me in msg["content"]:
+                    if me["type"] == "image_base64":
+                        me["image_url"] = {
+                            "url": me["image_base64"]
+                        }
+                        me["type"] = "image_url"
+                        del me["image_base64"]
+
+        args["messages"] = messages
+
+        # 发送请求
+        resp = await self._req(args)
+
+        # 处理请求结果
+        message = await self._make_msg(resp)
+
+        return message
+
+    async def call(
+        self,
+        query: core_entities.Query,
+        model: entities.LLMModelInfo,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+    ) -> llm_entities.Message:
+        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
+        for m in messages:
+            msg_dict = m.dict(exclude_none=True)
+            content = msg_dict.get("content")
+            if isinstance(content, list):
+                # 检查 content 列表中是否每个部分都是文本
+                if all(isinstance(part, dict) and part.get("type") == "text" for part in content):
+                    # 将所有文本部分合并为一个字符串
+                    msg_dict["content"] = "\n".join(part["text"] for part in content)
+            req_messages.append(msg_dict)
+
+        try:
+            return await self._closure(query=query, req_messages=req_messages, use_model=model, use_funcs=funcs)
+        except asyncio.TimeoutError:
+            raise errors.RequesterError('请求超时')
+        except openai.BadRequestError as e:
+            if 'context_length_exceeded' in e.message:
+                raise errors.RequesterError(f'上文过长，请重置会话: {e.message}')
+            else:
+                raise errors.RequesterError(f'请求参数错误: {e.message}')
+        except openai.AuthenticationError as e:
+            raise errors.RequesterError(f'无效的 api-key: {e.message}')
+        except openai.NotFoundError as e:
+            raise errors.RequesterError(f'请求路径错误: {e.message}')
+        except openai.RateLimitError as e:
+            raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
+        except openai.APIError as e:
+            raise errors.RequesterError(f'请求错误: {e.message}')

pkg/provider/modelmgr/requesters/modelscopechatcmpl.yaml

@@ -0,0 +1,34 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: modelscope-chat-completions
+  label:
+    en_US: ModelScope
+    zh_CN: 魔搭社区
+spec:
+  config:
+    - name: base-url
+      label:
+        en_US: Base URL
+        zh_CN: 基础 URL
+      type: string
+      required: true
+      default: "https://api-inference.modelscope.cn/v1"
+    - name: args
+      label:
+        en_US: Args
+        zh_CN: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_CN: 超时时间
+      type: int
+      required: true
+      default: 120
+execution:
+  python:
+    path: ./modelscopechatcmpl.py
+    attr: ModelScopeChatCompletions

pkg/provider/modelmgr/requesters/moonshotchatcmpl.py

@@ -45,13 +45,13 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
             if 'content' in m and isinstance(m['content'], list):
                 m['content'] = ' '.join([c['text'] for c in m['content']])
 
-        # 删除空的
+        # 删除空的，不知道干嘛的，直接删了。
-        messages = [m for m in messages if m['content'].strip() != '']
+        # messages = [m for m in messages if m["content"].strip() != "" and ('tool_calls' not in m or not m['tool_calls'])]
 
         args['messages'] = messages
 
         # 发送请求
-        resp = await self._req(args)
+        resp = await self._req(args, extra_body=self.requester_cfg['args'])
 
         # 处理请求结果
         message = await self._make_msg(resp)

pkg/provider/modelmgr/requesters/ppiochatcmpl.py

@@ -0,0 +1,20 @@
+
+from __future__ import annotations
+
+import openai
+
+from . import chatcmpl, modelscopechatcmpl
+from .. import requester
+from ....core import app
+
+class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """欧派云 ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    requester_cfg: dict
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+
+        self.requester_cfg = self.ap.provider_cfg.data['requester']['ppio-chat-completions']

pkg/provider/modelmgr/requesters/ppiochatcmpl.yaml

@@ -0,0 +1,34 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: ppio-chat-completions
+  label:
+    en_US: ppio 
+    zh_CN: 派欧云
+spec:
+  config:
+    - name: base-url
+      label:
+        en_US: Base URL
+        zh_CN: 基础 URL
+      type: string
+      required: true
+      default: "https://api.ppinfra.com/v3/openai"
+    - name: args
+      label:
+        en_US: Args
+        zh_CN: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_CN: 超时时间
+      type: int
+      required: true
+      default: 120
+execution:
+  python:
+    path: ./ppiochatcmpl.py
+    attr: PPIOChatCompletions

pkg/provider/runners/difysvapi.py

@@ -131,6 +131,8 @@ class DifyServiceAPIRunner(runner.RequestRunner):
 
         inputs.update(query.variables)
 
+        chunk = None  # 初始化chunk变量，防止在没有响应时引用错误
+
         async for chunk in self.dify_client.chat_messages(
             inputs=inputs,
             query=plain_text,
@@ -163,6 +165,11 @@ class DifyServiceAPIRunner(runner.RequestRunner):
                     )
                     basic_mode_pending_chunk = ''
 
+        if chunk is None:
+            raise errors.DifyAPIError(
+                'Dify API 没有返回任何响应，请检查网络连接和API配置'
+            )
+
         query.session.using_conversation.uuid = chunk['conversation_id']
 
     async def _agent_chat_messages(
@@ -182,12 +189,16 @@ class DifyServiceAPIRunner(runner.RequestRunner):
             for image_id in image_ids
         ]
 
-        ignored_events = ['agent_message']
+        ignored_events = []
 
         inputs = {}
 
         inputs.update(query.variables)
 
+        pending_agent_message = ''
+
+        chunk = None  # 初始化chunk变量，防止在没有响应时引用错误
+
         async for chunk in self.dify_client.chat_messages(
             inputs=inputs,
             query=plain_text,
@@ -201,47 +212,63 @@ class DifyServiceAPIRunner(runner.RequestRunner):
 
             if chunk['event'] in ignored_events:
                 continue
-            if chunk['event'] == 'agent_thought':
-                if (
-                    chunk['tool'] != '' and chunk['observation'] != ''
-                ):  # 工具调用结果，跳过
-                    continue
 
-                if chunk['thought'].strip() != '':  # 文字回复内容
+            if chunk['event'] == 'agent_message':
-                    msg = llm_entities.Message(
+                pending_agent_message += chunk['answer']
-                        role='assistant',
+            else:
-                        content=chunk['thought'],
+                if pending_agent_message.strip() != '':
+                    pending_agent_message = pending_agent_message.replace(
+                        '</details>Action:', '</details>'
                     )
-                    yield msg
-
-                if chunk['tool']:
-                    msg = llm_entities.Message(
-                        role='assistant',
-                        tool_calls=[
-                            llm_entities.ToolCall(
-                                id=chunk['id'],
-                                type='function',
-                                function=llm_entities.FunctionCall(
-                                    name=chunk['tool'],
-                                    arguments=json.dumps({}),
-                                ),
-                            )
-                        ],
-                    )
-                    yield msg
-            if chunk['event'] == 'message_file':
-                if chunk['type'] == 'image' and chunk['belongs_to'] == 'assistant':
-                    base_url = self.dify_client.base_url
-
-                    if base_url.endswith('/v1'):
-                        base_url = base_url[:-3]
-
-                    image_url = base_url + chunk['url']
-
                     yield llm_entities.Message(
                         role='assistant',
-                        content=[llm_entities.ContentElement.from_image_url(image_url)],
+                        content=self._try_convert_thinking(pending_agent_message),
                     )
+                pending_agent_message = ''
+
+                if chunk['event'] == 'agent_thought':
+                    if (
+                        chunk['tool'] != '' and chunk['observation'] != ''
+                    ):  # 工具调用结果，跳过
+                        continue
+
+                    if chunk['tool']:
+                        msg = llm_entities.Message(
+                            role='assistant',
+                            tool_calls=[
+                                llm_entities.ToolCall(
+                                    id=chunk['id'],
+                                    type='function',
+                                    function=llm_entities.FunctionCall(
+                                        name=chunk['tool'],
+                                        arguments=json.dumps({}),
+                                    ),
+                                )
+                            ],
+                        )
+                        yield msg
+                if chunk['event'] == 'message_file':
+                    if chunk['type'] == 'image' and chunk['belongs_to'] == 'assistant':
+                        base_url = self.dify_client.base_url
+
+                        if base_url.endswith('/v1'):
+                            base_url = base_url[:-3]
+
+                        image_url = base_url + chunk['url']
+
+                        yield llm_entities.Message(
+                            role='assistant',
+                            content=[
+                                llm_entities.ContentElement.from_image_url(image_url)
+                            ],
+                        )
+                if chunk['event'] == 'error':
+                    raise errors.DifyAPIError('dify 服务错误: ' + chunk['message'])
+
+        if chunk is None:
+            raise errors.DifyAPIError(
+                'Dify API 没有返回任何响应，请检查网络连接和API配置'
+            )
 
         query.session.using_conversation.uuid = chunk['conversation_id']
 

pkg/utils/image.py

@@ -203,3 +203,14 @@ async def extract_b64_and_format(image_base64_data: str) -> typing.Tuple[str, st
     base64_str = image_base64_data.split(',')[-1]
     image_format = image_base64_data.split(':')[-1].split(';')[0].split('/')[-1]
     return base64_str, image_format
+
+
+async def get_slack_image_to_base64(pic_url: str, bot_token: str):
+    headers = {'Authorization': f'Bearer {bot_token}'}
+    try:
+        async with aiohttp.ClientSession() as session:
+            async with session.get(pic_url, headers=headers) as resp:
+                image_data = await resp.read()
+                return base64.b64encode(image_data).decode('utf-8')
+    except Exception as e:
+        raise (e)

requirements.txt

@@ -35,8 +35,11 @@ python-telegram-bot
 certifi
 mcp
 sqlmodel
+slack_sdk
+telegramify-markdown
 
 # indirect
 taskgroup==0.0.0a4
 ruff
-pre-commit
+pre-commit
+python-socks

templates/legacy/platform.json

@@ -71,29 +71,47 @@
             "token": ""
         },
         {
-            "adapter":"officialaccount",
+            "adapter": "officialaccount",
             "enable": false,
             "token": "",
-            "EncodingAESKey":"",
+            "EncodingAESKey": "",
-            "AppID":"",
+            "AppID": "",
-            "AppSecret":"",
+            "AppSecret": "",
-            "Mode":"drop",
+            "Mode": "drop",
-            "LoadingMessage":"AI正在思考中，请发送任意内容获取回复。",
+            "LoadingMessage": "AI正在思考中，请发送任意内容获取回复。",
             "host": "0.0.0.0",
             "port": 2287
         },
         {
-            "adapter":"dingtalk",
+            "adapter": "dingtalk",
             "enable": false,
-            "client_id":"",
+            "client_id": "",
-            "client_secret":"",
+            "client_secret": "",
-            "robot_code":"",
+            "robot_code": "",
-            "robot_name":""
+            "robot_name": "",
+            "markdown_card": false
         },
         {
-            "adapter":"telegram",
+            "adapter": "telegram",
             "enable": false,
-            "token":""
+            "token": "",
+            "markdown_card": false
+        },
+        {
+            "adapter": "slack",
+            "enable": false,
+            "bot_token": "",
+            "signing_secret": "",
+            "port": 2288
+        },
+        {
+            "adapter": "wecomcs",
+            "enable": false,
+            "port": 2289,
+            "corpid": "",
+            "secret": "",
+            "token": "",
+            "EncodingAESKey": ""
         }
     ],
     "track-function-calls": true,

templates/legacy/provider.json

@@ -31,6 +31,12 @@
         ],
         "volcark": [
             "xxxxxxxx"
+        ],
+        "modelscope": [
+            "xxxxxxxx"
+        ],
+        "ppio": [
+            "xxxxxxxx"
         ]
     },
     "requester": {
@@ -95,12 +101,22 @@
             "args": {},
             "base-url": "https://ark.cn-beijing.volces.com/api/v3",
             "timeout": 120
+        },
+        "modelscope-chat-completions": {
+            "base-url": "https://api-inference.modelscope.cn/v1",
+            "args": {},
+            "timeout": 120
+        },
+        "ppio-chat-completions": {
+            "base-url": "https://api.ppinfra.com/v3/openai",
+            "args": {},
+            "timeout": 120
         }
     },
     "model": "gpt-4o",
     "prompt-mode": "normal",
     "prompt": {
-        "default": ""
+        "default": "You are a helpful assistant."
     },
     "runner": "local-agent",
     "dify-service-api": {