Keeps creating branches after being explicitly told not to
Resolved 💬 3 comments Opened Oct 11, 2025 by matssk Closed Nov 11, 2025
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
0.46
Which model were you using?
gpt-5-high
What platform is your computer?
_No response_
What steps can reproduce the bug?
It will frequently create new branches even though I explicitly tell it not to and have this instructed in AGENTS.md too. This might be related to the review feature.
What is the expected behavior?
_No response_
What do you see instead?
_No response_
Additional information
_No response_
3 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
It's not really the same. And I think this behavior might be new. It's just a few days ago since it started to frequently create new branches all the time, perhaps something introduced in 0.46.
Thanks for the bug report. We've shared the feedback with the team members who are responsible for training our codex models. We're tracking this feedback and similar reports so we can make the model more robust in future iterations.
If you see other model behavior that you'd like to report, please use the recently-added
/feedbackcommand in the CLI. That will provide us with additional details including logs and conversation text.