please replace "⚠ Selected model is at capacity. Please try a different model." with a backoff algorithm

Open 💬 3 comments Opened Jul 16, 2026 by RohanAdwankar

What variant of Codex are you using?

CLI

What feature would you like to see?

Currently the behavior is when "⚠ Selected model is at capacity. Please try a different model." is sent it just stops. However it would be nice to have a backoff approach where after it gets that alert it retries in 2 minutes then 4 minutes, then 8 minutes etc. The reason being that most of these are very transient capacity issue not worth stopping the flow outright.

Additional information

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗