Context-Engineering on Loop & Retry https://loopandretry.github.io/tags/context-engineering/ Recent content in Context-Engineering on Loop & Retry Loop & Retry https://loopandretry.github.io/images/og-default.png https://loopandretry.github.io/images/og-default.png Hugo en-us Tue, 14 Jul 2026 05:01:00 -0400 One bad step, N bad steps: how agent failures cascade https://loopandretry.github.io/posts/how-agent-failures-cascade/ Tue, 14 Jul 2026 05:01:00 -0400 https://loopandretry.github.io/posts/how-agent-failures-cascade/ A single agent error rarely stays a single error. The bad output goes into the context, the next step reasons on top of it, and the mistake compounds down the trajectory — one wrong step becoming N wrong steps. This is the cascade, why it’s structurally different from a fleet-wide blast radius, and the three interruption points that stop a local mistake from eating the whole run. Why a long agent run costs O(N²) tokens — and how to flatten it https://loopandretry.github.io/posts/long-agent-runs-are-quadratic/ Mon, 13 Jul 2026 18:05:00 -0400 https://loopandretry.github.io/posts/long-agent-runs-are-quadratic/ A naive agent’s token bill doesn’t grow with the number of steps — it grows with the square of them, because every step re-reads the whole transcript that every previous step appended to. A small cost model shows the curve, and four structural moves turn the quadratic back into something close to linear without dropping information the agent actually needs. Compaction is a lossy operation https://loopandretry.github.io/posts/compaction-is-a-lossy-operation/ Mon, 13 Jul 2026 16:00:00 -0400 https://loopandretry.github.io/posts/compaction-is-a-lossy-operation/ When the context window fills up, the standard fix is to summarize the old turns and keep going. That summary is a lossy compression step, and the thing it silently drops is usually the one early constraint the agent needs a hundred turns later. Here’s why recency-based compaction fails, a simulation of how often the load-bearing fact survives, and the rule that actually protects it. The context window is a cache, not a memory https://loopandretry.github.io/posts/context-window-is-a-cache/ Tue, 07 Jul 2026 20:00:00 -0400 https://loopandretry.github.io/posts/context-window-is-a-cache/ 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.