Your Agent Doesn't Run Out of Context. It Degrades at 79% (opens in new tab)

The first time one of my long agent sessions went sideways, I went looking for the wrong thing. I grepped for context window exceeded. For a stack trace. For a 400 from the API. There was nothing. The run finished. It just finished worse than it started — sloppier tool calls, a step that re-derived something it had already figured out, an answer that ignored a constraint stated twenty steps earlier. No crash. No error. The agent didn't run out of context. It got dumber on the way there. Here'...