ai-agent
14 turns, 3 context resets, and the turn-1 constraint still holds: long sessions in suga
Keep an agent in one session long enough and three things go wrong. The context fills up and gets compacted, and the part that gets dropped is the constraint you gave it in the first turn. Every request carries a few thousand tokens of fixed overhead, so long sessions get expensive. And when something breaks, there is no record of what the agent did.
suga is a personal coding agent I write in Go. The goal is a session that can stay with me for a full working day. This post covers the trade-offs it makes for long sessions, which of them are backed by data and which experiments failed, and how it works with gofer, my job platform. suga itself is built on gofer, one batch of agent jobs at a time.
The current version is v0.49. It is
v0, so minor releases may break things. It is MIT licensed. What follows is an introduction to suga.
