Closed steve8708 closed 2 months ago
Currently, we detect when the agent gets stuck and abort
It would be great instead to
the idea is, with some logs, perhaps this will help the AI see more info and get unstuck just like a human
then, if the flag is on, at the end tell the AI to remove the logs from the code before fully finishing
Currently, we detect when the agent gets stuck and abort
It would be great instead to
the idea is, with some logs, perhaps this will help the AI see more info and get unstuck just like a human
then, if the flag is on, at the end tell the AI to remove the logs from the code before fully finishing