In the Computer Use Agent (CUA) model, is it possible to have multiple actions per each CUA response? for example, instead of having two requests and responses one for type("Emma Watson")
and one for keypress("Enter")
, is it possible to have one response call as an array including both type(...)
and keypress(...)
which significantly increases the speed of the process?
[UPDATE]
I also added this question to the GitHub OpenAI CUA sample app issue.