codex should sleep/delay upon hitting TPM rate limit, not crash

Resolved 💬 2 comments Opened Apr 22, 2025 by J-a-n-u-s Closed Apr 22, 2025

What version of Codex is running?

0.1.2504211509

Which model were you using?

gpt-4.1-mini

What platform is your computer?

darwin | x64 | 22.6.0

What steps can reproduce the bug?

Hit TPM rate limit.

What is the expected behavior?

Codex should sleep / delay, or return to user input indicating which rate limit was hit, and allow user to retry.

What do you see instead?

It crashes out/exits when rate limit is hit

Additional information

Am not sure if this is a bug or feature request, so please feel free to move to feature request at your discretion.

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗