Claude does the same when you hit the context limit, but the difference is that claude's context limit is 1m and Codex's is 272k now. Claude lets you get a lot more done before you have to worry about the start getting compacted away.
Codex context limit is 400k total, including 128,000 reserved output tokens.
There are numerous Claude settings to disable or modify this behavior
Have you observed any decrease in performance at context higher than 200k?
That used to be one of the major issues why clearing or compacting context when the context nears 150 to 170k is usually preferred.