Inference
Running a trained model to get output. Each request is worked on separately, and the model itself carries nothing over from one to the next, so it starts every request knowing only what that request contains.
The whole conversation is sent again on every turn, each round of asking and answering, because it is the only way the model can see it. So long sessions cost more per turn, and a fresh session has no idea what you did this morning.
Say it to your agent
“This is a new session, so you know nothing about yesterday. Read docs/handoff.md and run git log -10, then tell me where the work stopped before you change anything.”