nanobot/agent/tools/message.py

@@ -1,6 +1,6 @@
 """Message tool for sending messages to users."""
 
-from typing import Any, Awaitable, Callable
+from typing import Any, Callable, Awaitable
 
 from nanobot.agent.tools.base import Tool
 from nanobot.bus.events import OutboundMessage
@@ -9,44 +9,36 @@ from nanobot.session import SessionManager
 
 class MessageTool(Tool):
     """Tool to send messages to users on chat channels."""
-
+    
     def __init__(
         self,
         send_callback: Callable[[OutboundMessage], Awaitable[None]] | None = None,
         sessions: SessionManager | None = None,
         default_channel: str = "",
-        default_chat_id: str = "",
-        default_message_id: str | None = None,
+        default_chat_id: str = ""
     ):
         self._send_callback = send_callback
         self._sessions = sessions
         self._default_channel = default_channel
         self._default_chat_id = default_chat_id
-        self._default_message_id = default_message_id
-        self._sent_in_turn: bool = False
-
-    def set_context(self, channel: str, chat_id: str, message_id: str | None = None) -> None:
+    
+    def set_context(self, channel: str, chat_id: str) -> None:
         """Set the current message context."""
         self._default_channel = channel
         self._default_chat_id = chat_id
-        self._default_message_id = message_id
-
+    
     def set_send_callback(self, callback: Callable[[OutboundMessage], Awaitable[None]]) -> None:
         """Set the callback for sending messages."""
         self._send_callback = callback
-
-    def start_turn(self) -> None:
-        """Reset per-turn send tracking."""
-        self._sent_in_turn = False
-
+    
     @property
     def name(self) -> str:
         return "message"
-
+    
     @property
     def description(self) -> str:
         return "Send a message to the user. Use this when you want to communicate something."
-
+    
     @property
     def parameters(self) -> dict[str, Any]:
         return {
@@ -56,6 +48,11 @@ class MessageTool(Tool):
                     "type": "string",
                     "description": "The message content to send"
                 },
+                "media": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "description": "Optional: list of media file paths or URLs to attach"
+                },
                 "channel": {
                     "type": "string",
                     "description": "Optional: target channel (telegram, discord, etc.)"
@@ -63,28 +60,21 @@ class MessageTool(Tool):
                 "chat_id": {
                     "type": "string",
                     "description": "Optional: target chat/user ID"
-                },
-                "media": {
-                    "type": "array",
-                    "items": {"type": "string"},
-                    "description": "Optional: list of file paths to attach (images, audio, documents)"
                 }
             },
             "required": ["content"]
         }
-
+    
     async def execute(
         self,
         content: str,
+        media: list[str] | None = None,
         channel: str | None = None,
         chat_id: str | None = None,
-        message_id: str | None = None,
-        media: list[str] | None = None,
         **kwargs: Any
     ) -> str:
         channel = channel or self._default_channel
         chat_id = chat_id or self._default_chat_id
-        message_id = message_id or self._default_message_id
 
         if not channel or not chat_id:
             return "Error: No target channel/chat specified"
@@ -96,12 +86,9 @@ class MessageTool(Tool):
             channel=channel,
             chat_id=chat_id,
             content=content,
-            media=media or [],
-            metadata={
-                "message_id": message_id,
-            }
+            media=media or []
         )
-
+        
         try:
             await self._send_callback(msg)
 
@@ -111,9 +98,6 @@ class MessageTool(Tool):
                 session.add_message("assistant", content)
                 self._sessions.save(session)
 
-            if channel == self._default_channel and chat_id == self._default_chat_id:
-                self._sent_in_turn = True
-            media_info = f" with {len(media)} attachments" if media else ""
-            return f"Message sent to {channel}:{chat_id}{media_info}"
+            return f"Message sent to {channel}:{chat_id}"
         except Exception as e:
             return f"Error sending message: {str(e)}"

nanobot/channels/telegram.py

@@ -199,11 +199,17 @@ class TelegramChannel(BaseChannel):
             chat_id = int(msg.chat_id)
             # Convert markdown to Telegram HTML
             html_content = _markdown_to_telegram_html(msg.content)
-            await self._app.bot.send_message(
-                chat_id=chat_id,
-                text=html_content,
-                parse_mode="HTML"
-            )
+
+            # Check if message has media attachments
+            if msg.media:
+                await self._send_with_media(chat_id, html_content, msg.media)
+            else:
+                # Text-only message
+                await self._app.bot.send_message(
+                    chat_id=chat_id,
+                    text=html_content,
+                    parse_mode="HTML"
+                )
         except ValueError:
             logger.error(f"Invalid chat_id: {msg.chat_id}")
         except Exception as e:
@@ -216,7 +222,161 @@ class TelegramChannel(BaseChannel):
                 )
             except Exception as e2:
                 logger.error(f"Error sending Telegram message: {e2}")
-    
+
+    async def _send_with_media(self, chat_id: int, caption: str, media_paths: list[str]) -> None:
+        """
+        Send message with media attachments.
+
+        Args:
+            chat_id: Telegram chat ID
+            caption: Message caption
+            media_paths: List of file paths or URLs
+        """
+        from telegram import InputMediaPhoto, InputMediaVideo
+
+        from nanobot.channels.telegram_media import (
+            MediaKind,
+            classify_media,
+            detect_mime,
+            fetch_media,
+            group_media_for_album,
+            optimize_image,
+        )
+
+        # Process each media item
+        processed_media: list[tuple[str, MediaKind, bytes]] = []
+
+        for path in media_paths:
+            try:
+                # Fetch remote URLs
+                if path.startswith(("http://", "https://")):
+                    content, mime = await fetch_media(path, max_bytes=100_000_000)
+                    kind = classify_media(mime)
+                else:
+                    # Local file
+                    file_path = Path(path)
+                    if not file_path.exists():
+                        logger.warning(f"Media file not found: {path}")
+                        continue
+
+                    with open(file_path, "rb") as f:
+                        content = f.read()
+
+                    mime = detect_mime(path, content)
+                    kind = classify_media(mime)
+
+                    # Optimize images
+                    if kind == MediaKind.IMAGE:
+                        try:
+                            content = optimize_image(path, max_bytes=6_000_000)
+                        except Exception as e:
+                            logger.warning(f"Image optimization failed: {e}, sending original")
+
+                processed_media.append((path, kind, content))
+
+            except Exception as e:
+                logger.error(f"Failed to process media {path}: {e}")
+                continue
+
+        if not processed_media:
+            # No media could be processed, send text only
+            await self._app.bot.send_message(
+                chat_id=chat_id,
+                text=caption,
+                parse_mode="HTML"
+            )
+            return
+
+        # Group media for album sending
+        media_items = [(path, kind) for path, kind, _ in processed_media]
+        grouping = group_media_for_album(media_items)
+
+        # Handle caption length (Telegram limit: 1024 chars)
+        if len(caption) > 1024:
+            # Send media without caption, then follow-up text
+            media_caption = None
+            followup_text = caption
+        else:
+            media_caption = caption
+            followup_text = None
+
+        # Send album if grouped
+        if grouping["album"]:
+            album_paths = grouping["album"]
+            album_media = []
+
+            for path, kind, content in processed_media:
+                if path not in album_paths:
+                    continue
+
+                if kind == MediaKind.IMAGE:
+                    media_obj = InputMediaPhoto(
+                        media=content,
+                        caption=media_caption if len(album_media) == 0 else None,
+                        parse_mode="HTML" if media_caption else None
+                    )
+                elif kind == MediaKind.VIDEO:
+                    media_obj = InputMediaVideo(
+                        media=content,
+                        caption=media_caption if len(album_media) == 0 else None,
+                        parse_mode="HTML" if media_caption else None
+                    )
+                else:
+                    continue  # Skip non-album types
+
+                album_media.append(media_obj)
+
+            if album_media:
+                await self._app.bot.send_media_group(
+                    chat_id=chat_id,
+                    media=album_media
+                )
+
+        # Send separate media
+        for i, (path, kind, content) in enumerate(processed_media):
+            if path in grouping["album"]:
+                continue  # Already sent in album
+
+            # Only first separate item gets caption
+            item_caption = media_caption if i == 0 else None
+
+            if kind == MediaKind.IMAGE:
+                await self._app.bot.send_photo(
+                    chat_id=chat_id,
+                    photo=content,
+                    caption=item_caption,
+                    parse_mode="HTML" if item_caption else None
+                )
+            elif kind == MediaKind.VIDEO:
+                await self._app.bot.send_video(
+                    chat_id=chat_id,
+                    video=content,
+                    caption=item_caption,
+                    parse_mode="HTML" if item_caption else None
+                )
+            elif kind == MediaKind.AUDIO:
+                await self._app.bot.send_audio(
+                    chat_id=chat_id,
+                    audio=content,
+                    caption=item_caption,
+                    parse_mode="HTML" if item_caption else None
+                )
+            elif kind == MediaKind.DOCUMENT:
+                await self._app.bot.send_document(
+                    chat_id=chat_id,
+                    document=content,
+                    caption=item_caption,
+                    parse_mode="HTML" if item_caption else None
+                )
+
+        # Send follow-up text if caption was too long
+        if followup_text:
+            await self._app.bot.send_message(
+                chat_id=chat_id,
+                text=followup_text,
+                parse_mode="HTML"
+            )
+
     async def _on_start(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
         """Handle /start command."""
         if not update.message or not update.effective_user: