This feels like an aggressive push to force codex users to adapt to GPT3.5/4. I'd imagine they will be integrating some of codex's features into GPT4 soon.
All you have to do is 1) call the chat completion API, 2) structure your prompt in JSON as system+agent+user, and 3) get the completion from a different JSON node. You don’t have to round trip or maintain context or anything.