Background & Settings:
I have agent mode enabled + auto-run (aka YOLO) & I’ve given the agent free reign to run terminal commands with a command prompt: “Whenever you make changes based on my instructions, you should then run try to test the changes in terminal to see if it does what is necessary. If it fails then make changes again and test again until it has been debugged.”
I then proceed to accept all changes using the change summary box (that is review changes beta feature: Display Button) at the bottom which works for all changes & commands for that response. So it begins it’s writing & debugging of a feature.
The Bug: BUT THEN, some of its commands will complete normally (without any errors) and the agent won’t even notice. It will just hang until I hit “Skip and Continue”. I think it is more likely to happen for long-running commands but I don’t know.
This is probably some kind of bug but I want to know if there is a workaround? I’d like to just let it run while I do other stuff…
Check the forum to ensure the issue hasn’t been reported already
Provide a clear description of the bug
Explain how to reproduce the bug (if known)
Attach screenshots or recordings (e.g.,
.jpg
, .png
, .mp4
).
Tell us your operating system and your Cursor version (e.g.,
Windows, 0.x.x
).
Tell us if the issue stops you from using Cursor.