stream disconnected before completion: Rate limit is exceeded.

What version of Codex is running?

0.36

Which model were you using?

gpt-5

What platform is your computer?

Linux 5.15.0-1089-azure x86_64 x86_64

What steps can reproduce the bug?

 When I ask codex cli to finsih job like 'please add unit test for current project' , it will runs, then quickly meet sh stream error:

stream disconnected before completion: Rate limit is exceeded. Try again in 17 seconds.; retrying 5/5 in 3.32s…

■ stream disconnected before completion: Rate limit is exceeded. Try again in 11 seconds.

then I have to keep input ' please go ahead' to make codex go ahead, the best thing is that it can go ahead, the bad thing is that I have to keep 'internative'

What is the expected behavior?

possiblt to set the 'intervals' or 'timeout' for the codex cli? so that it can adapt the backend model rate limit? thanks.
and btw, I am not sure whether the 'root cause' is the 'rate limit for the model'.are there any other factors to invoke the 'rate limit message' in codex cli? thanks.

What do you see instead?

⚠️ stream error: stream disconnected before completion: Rate limit is exceeded. Try again in 4 seconds.; retrying 1/5 in 209ms…

Additional information

_No response_