2026-06-22
How the model input is cached — and kept fresh
Sending a long input every round is pure waste — most of it doesn't change. This short follows the input across calls : how the expensive prefix is reused instead of re-sent, how the freshest signals stay fresh, and how the agent can drop junk early without busting the cache. The trick isn't pretending context never changes — it's shaping what stays visible.
react-agentprompt-cachingcache-pointsttl-pruningcompaction