Bug: Agent stops working due to limit, even though limit isn't reached.

Resolved 💬 2 comments Opened Nov 16, 2025 by lenardflx Closed Jan 5, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

0.58.0

What subscription do you have?

Plus

Which model were you using?

gpt-5.1

What platform is your computer?

Windows11 x64, codex run on wls

What issue are you seeing?

After reaching 95% of the 5h limit, and waiting for it to drop back to 80%, the agent continues to refuse any code change.

<img width="536" height="64" alt="Image" src="https://github.com/user-attachments/assets/dda4b823-bd29-48b3-b0e6-f2443070ebd6" />

<img width="646" height="338" alt="Image" src="https://github.com/user-attachments/assets/de20e1ac-3724-42ad-9884-d15ea498acf5" />

What steps can reproduce the bug?

Bring Codex to almost the edge of the 5h limit. Wait until the value within /status drops, then prompt him.

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 9 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #6635
  • #6617
  • #6658
  • #6513
  • #705

Powered by Codex Action

etraut-openai contributor · 7 months ago

This problem should be fixed now. If you see it again, let us know.