[e1g]

Hmmm, no, I don't know this for sure. In my testing, the /compact endpoint seems to work almost too well for large/complex conversations, and it feels like it cannot contain the entire latent space, so I assumed it keeps pointers inside it (ala previous_response_id). On the other hand, OpenAI says it's stateless and compatible with Zero Data Retention, so maybe it can contain everything.

[EnPissant]

They say they do not compress the user messages, but yeah, it's purpose is to do very lossy compression of everything else. I'd expect it to be small.