This is an interesting problem to tackle. It's not clear from the github readme what the output of this looks like, specifically what does it return to the LLM?
Does it look clearer from there? (can update the docs as well if it is not clear, but will definitely add the section 'what does it return to agent', need just to think a bit about it).
Does it look clearer from there? (can update the docs as well if it is not clear, but will definitely add the section 'what does it return to agent', need just to think a bit about it).