Post

A good part of my time working on AgentControl (side-project, it's my primary tool. Main project is still LinkBunny) recently has been managing the amount of information I have in my agent transcripts.

I think that's a major benefit of building my own orchestration tool. It's not as easy to do (or is it even possible) using a stock coding agent app/cli. In this case I make it collapse the cli callback which has excessive information. From vs to:

Collapsing the callback is what a stock CLI leaves to the model. The full output enters context once, then every later turn carries it. Cutting it before it lands is a cost decision as much as a readability one.