Posts tagged Context Window — AI × software engineering, made practical.
I said one sentence at turn 6, the agent obeyed it for thirty turns, then compaction quietly summarized it out of existence and the agent ran the exact command I'd banned — here's the fix that isn't "write a better CLAUDE.md."
One string, three tokenizers, three different token counts — and that quiet mismatch is deciding your bill, your context budget, and how much room your agent has left to actually think.
Your agent isn't running out of room; it's rotting from the inside, and the transcript will lie to your face about it.
A Claude Code subagent had room to spare and still rebuilt a feature on a file a teammate had deleted twelve minutes earlier — the cache bug hiding inside every long agent session, and four concrete hooks that kill it.
Nothing overflowed, nothing got truncated, and the model still ignored an explicit rule sitting in plain sight — because a bigger context window doesn't buy the model more attention, it buys it more competition for the same fixed budget.
Your team already built the gut instinct to size a ticket in story points — this is the same instinct, unbuilt, for the one unit that decides both your agent's bill and its memory limit.
That confident, plausible, wrong edit your agent just made wasn't a hallucination — it was a stale cache hit, and every long agentic session has the exact same one sitting inside it unmonitored.