nanobot/agent/loop.py

@@ -309,7 +309,10 @@ class AgentLoop:
         cron_tool = self.tools.get("cron")
         if isinstance(cron_tool, CronTool):
             cron_tool.set_context(msg.channel, msg.chat_id)
-        
+
+        # Track media for this turn (screenshots from computer tool)
+        media_paths_for_turn: list[str] = []
+
         # Prepend current time + optional time-gap notice to every user message
         now_dt = datetime.now()
         tz = time.strftime("%Z") or "UTC"
@@ -416,6 +419,16 @@ class AgentLoop:
 
                         # If there's an image, use multipart content
                         if result.base64_image:
+                            # Save screenshot to disk for user
+                            import base64
+                            media_dir = Path.home() / ".nanobot" / "media"
+                            media_dir.mkdir(parents=True, exist_ok=True)
+                            screenshot_path = media_dir / f"screenshot_{int(time.time() * 1000)}.png"
+                            screenshot_path.write_bytes(base64.b64decode(result.base64_image))
+                            media_paths_for_turn.append(str(screenshot_path))
+                            logger.info(f"Saved screenshot to {screenshot_path}")
+
+                            # Include in tool result for model to see
                             content_parts = [
                                 {"type": "text", "text": text_content},
                                 {
@@ -520,6 +533,7 @@ class AgentLoop:
             chat_id=msg.chat_id,
             content=final_content_for_session,
             metadata=outbound_metadata,
+            media=media_paths_for_turn if media_paths_for_turn else None,
         )
     
     async def _process_system_message(self, msg: InboundMessage) -> OutboundMessage | None: