Files
clawmates/docs
Omar SobhandClaude Opus 5 93a386e706
deploy / test (push) Successful in 5m26s
deploy / build (push) Successful in 5m32s
perf(judge): earlier check outputs shrink to a reminder before the next round
Measured on prod: 7 of 9 verdicts ran to the 12-check cap. Every round
resends the whole history, and each check's output is bounded at 12 KB — so
by the last round the judge was paying for ~144 KB of outputs it had already
read, on top of up to 120 KB of evidence, and it paid that on every round.
That is the quadratic term in a verdict's cost, and the reason a single
blocked phase could empty a weekly plan.

Before this round's results go in, every earlier tool result compacts to an
800-byte head plus a marker saying the rest was shown when the check ran.
The round that just ran stays whole; a result already carrying the marker is
left alone. The budget of checks is unchanged — each one is cheaper to
remember, not fewer to run.

Also: docs/NEXT-SESSION.md rewritten for the state as of today.

Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz
2026-09-14 08:17:20 -05:00
..