New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add logs when stuck #33

Closed

steve8708 opened this issue Jun 19, 2024 · 0 comments · Fixed by #40

Labels

Contributor

steve8708 commented Jun 19, 2024

Currently, we detect when the agent gets stuck and abort

It would be great instead to

check with the LLM if it is stuck because of a bad test command, or just the same test failure on repeat
if ti is test failure on repeat - instruct the LLM to add logs to the code and set an internal flag that this was set

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

steve8708 added the help wanted label

nexxeln mentioned this issue

add logs when stuck #40

Merged

steve8708 closed this as completed in #40

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment