Pruning an assistant's response like that would break prompt caching.

Prompt caching is probably the single most important thing that people building harnesses think about and yet it's mind share in end users is virtually zero. If you had to think of all the weirdest, most seemingly baffling design decisions in an AI product, the answer to "why" is probably "to not break prompt caching".

Maybe so, but pruning is still a useful feature.

If it hurts performance that much, maybe pruning could just hide the text leaving the cache intact?