gpt-oss-120b keeps stopping for me in Codex. (Also in Crush.)

I have to say "continue" constantly.

See https://news.ycombinator.com/item?id=45773874 (TLDR, you need to hard-code some inference parameters to be the right ones, otherwise you'd get really bad behaviour + prompting to get the workflow right)

Thanks. Did you need to modify Codex's prompt?