feat(agent): 支持图片消息处理

app/agent/__init__.py

@@ -10,7 +10,7 @@ from langchain.agents.middleware import (
     SummarizationMiddleware,
     LLMToolSelectorMiddleware,
 )
-from langchain_core.messages import (
+from langchain_core.messages import (  # noqa: F401
     HumanMessage,
     BaseMessage,
 )
@@ -174,19 +174,31 @@ class MoviePilotAgent:
             logger.error(f"创建 Agent 失败: {e}")
             raise e
 
-    async def process(self, message: str) -> str:
+    async def process(self, message: str, images: List[str] = None) -> str:
         """
         处理用户消息，流式推理并返回 Agent 回复
         """
         try:
-            logger.info(f"Agent推理: session_id={self.session_id}, input={message}")
+            logger.info(
+                f"Agent推理: session_id={self.session_id}, input={message}, images={len(images) if images else 0}"
+            )
 
             # 获取历史消息
             messages = memory_manager.get_agent_messages(
                 session_id=self.session_id, user_id=self.user_id
             )
 
-            # 增加用户消息
+            # 构建用户消息内容
+            if images:
+                from langchain_core.messages import HumanMessage
+
+                content = []
+                if message:
+                    content.append({"type": "text", "text": message})
+                for img in images:
+                    content.append({"type": "image_url", "image_url": {"url": img}})
+                messages.append(HumanMessage(content=content))
+            else:
                 messages.append(HumanMessage(content=message))
 
             # 执行推理
@@ -421,6 +433,7 @@ class _MessageTask:
     session_id: str
     user_id: str
     message: str
+    images: Optional[List[str]] = None
     channel: Optional[str] = None
     source: Optional[str] = None
     username: Optional[str] = None
@@ -471,6 +484,7 @@ class AgentManager:
         session_id: str,
         user_id: str,
         message: str,
+        images: List[str] = None,
         channel: str = None,
         source: str = None,
         username: str = None,
@@ -483,6 +497,7 @@ class AgentManager:
             session_id=session_id,
             user_id=user_id,
             message=message,
+            images=images,
             channel=channel,
             source=source,
             username=username,
@@ -584,7 +599,7 @@ class AgentManager:
             if task.username:
                 agent.username = task.username
 
-        return await agent.process(task.message)
+        return await agent.process(task.message, images=task.images)
 
     async def clear_session(self, session_id: str, user_id: str):
         """

app/modules/discord/__init__.py

@@ -130,10 +130,11 @@ class DiscordModule(_ModuleBase, _MessageBase[Discord]):
         if msg_type == "message":
             text = msg_json.get("text")
             chat_id = msg_json.get("chat_id")
-            if text and userid:
+            images = self._extract_images(msg_json)
+            if (text or images) and userid:
                 logger.info(
                     f"收到来自 {client_config.name} 的 Discord 消息："
-                    f"userid={userid}, username={username}, text={text}"
+                    f"userid={userid}, username={username}, text={text}, images={len(images) if images else 0}"
                 )
                 return CommingMessage(
                     channel=MessageChannel.Discord,
@@ -142,9 +143,26 @@ class DiscordModule(_ModuleBase, _MessageBase[Discord]):
                     username=username,
                     text=text,
                     chat_id=str(chat_id) if chat_id else None,
+                    images=images,
                 )
         return None
 
+    @staticmethod
+    def _extract_images(msg_json: dict) -> Optional[List[str]]:
+        """
+        从Discord消息中提取图片URL
+        """
+        attachments = msg_json.get("attachments", [])
+        if not attachments:
+            return None
+        images = []
+        for attachment in attachments:
+            if attachment.get("type") == "image":
+                url = attachment.get("url")
+                if url:
+                    images.append(url)
+        return images if images else None
+
     def post_message(self, message: Notification, **kwargs) -> None:
         """
         发送通知消息

app/modules/slack/__init__.py

@@ -198,10 +198,12 @@ class SlackModule(_ModuleBase, _MessageBase[Slack]):
             logger.debug(f"解析Slack消息失败：{str(err)}")
             return None
         if msg_json:
+            images = None
             if msg_json.get("type") == "message":
                 userid = msg_json.get("user")
                 text = msg_json.get("text")
                 username = msg_json.get("user")
+                images = self._extract_images(msg_json)
             elif msg_json.get("type") == "block_actions":
                 userid = msg_json.get("user", {}).get("id")
                 callback_data = msg_json.get("actions")[0].get("value")
@@ -243,6 +245,7 @@ class SlackModule(_ModuleBase, _MessageBase[Slack]):
                     flags=re.IGNORECASE,
                 ).strip()
                 username = ""
+                images = self._extract_images(msg_json.get("event", {}))
             elif msg_json.get("type") == "shortcut":
                 userid = msg_json.get("user", {}).get("id")
                 text = msg_json.get("callback_id")
@@ -254,7 +257,7 @@ class SlackModule(_ModuleBase, _MessageBase[Slack]):
             else:
                 return None
             logger.info(
-                f"收到来自 {client_config.name} 的Slack消息：userid={userid}, username={username}, text={text}"
+                f"收到来自 {client_config.name} 的Slack消息：userid={userid}, username={username}, text={text}, images={len(images) if images else 0}"
             )
             return CommingMessage(
                 channel=MessageChannel.Slack,
@@ -262,9 +265,26 @@ class SlackModule(_ModuleBase, _MessageBase[Slack]):
                 userid=userid,
                 username=username,
                 text=text,
+                images=images,
             )
         return None
 
+    @staticmethod
+    def _extract_images(msg_json: dict) -> Optional[List[str]]:
+        """
+        从Slack消息中提取图片URL
+        """
+        files = msg_json.get("files", [])
+        if not files:
+            return None
+        images = []
+        for file in files:
+            if file.get("type") in ("image", "jpg", "jpeg", "png", "gif", "webp"):
+                url = file.get("url_private") or file.get("url_private_download")
+                if url:
+                    images.append(url)
+        return images if images else None
+
     def post_message(self, message: Notification, **kwargs) -> None:
         """
         发送消息

app/modules/telegram/__init__.py

@@ -194,26 +194,33 @@ class TelegramModule(_ModuleBase, _MessageBase[Telegram]):
         text = msg.get("text")
         user_id = msg.get("from", {}).get("id")
         user_name = msg.get("from", {}).get("username")
-        # Extract chat_id to enable correct reply targeting
         chat_id = msg.get("chat", {}).get("id")
 
-        if text and user_id:
+        images = self._extract_images(msg)
+
+        if user_id:
+            if not text and not images:
+                logger.debug(
+                    f"收到来自 {client_config.name} 的Telegram消息无文本和图片"
+                )
+                return None
+
             logger.info(
                 f"收到来自 {client_config.name} 的Telegram消息："
-                f"userid={user_id}, username={user_name}, chat_id={chat_id}, text={text}"
+                f"userid={user_id}, username={user_name}, chat_id={chat_id}, text={text}, images={len(images) if images else 0}"
             )
 
-            # Clean bot mentions from text to ensure consistent processing
+            cleaned_text = (
-            cleaned_text = self._clean_bot_mention(
+                self._clean_bot_mention(text, client.bot_username if client else None)
-                text, client.bot_username if client else None
+                if text
+                else None
             )
 
-            # 检查权限
             admin_users = client_config.config.get("TELEGRAM_ADMINS")
             user_list = client_config.config.get("TELEGRAM_USERS")
             config_chat_id = client_config.config.get("TELEGRAM_CHAT_ID")
 
-            if cleaned_text.startswith("/"):
+            if cleaned_text and cleaned_text.startswith("/"):
                 if (
                     admin_users
                     and str(user_id) not in admin_users.split(",")
@@ -236,11 +243,34 @@ class TelegramModule(_ModuleBase, _MessageBase[Telegram]):
                 source=client_config.name,
                 userid=user_id,
                 username=user_name,
-                text=cleaned_text,  # Use cleaned text
+                text=cleaned_text,
                 chat_id=str(chat_id) if chat_id else None,
+                images=images if images else None,
             )
         return None
 
+    @staticmethod
+    def _extract_images(msg: dict) -> Optional[List[str]]:
+        """
+        从Telegram消息中提取图片file_id
+        """
+        images = []
+        photo = msg.get("photo")
+        if photo and isinstance(photo, list):
+            largest_photo = photo[-1]
+            file_id = largest_photo.get("file_id")
+            if file_id:
+                images.append(file_id)
+
+        document = msg.get("document")
+        if document:
+            file_id = document.get("file_id")
+            mime_type = document.get("mime_type", "")
+            if file_id and mime_type.startswith("image/"):
+                images.append(file_id)
+
+        return images if images else None
+
     @staticmethod
     def _clean_bot_mention(text: str, bot_username: Optional[str]) -> str:
         """

app/schemas/message.py

@@ -53,6 +53,8 @@ class CommingMessage(BaseModel):
     chat_id: Optional[str] = None
     # 完整的回调查询信息（原始数据）
     callback_query: Optional[Dict] = None
+    # 图片列表（图片URL或file_id）
+    images: Optional[List[str]] = None
 
     def to_dict(self):
         """