The context window is a cache, not a memory

Treating the context window as append-only memory is how agents get slow, expensive, and quietly wrong. The fix is to run it like a cache with a budget and an eviction policy: decide what earns its tokens every turn. Here’s the cost math, the accuracy failure mode, and a working context manager.

July 7, 2026 · 9 min · 1826 words · Loop & Retry