clay-borg/tools
tegwick c0eef604e8 T05: CB-EV-0002 — all 9 metrics met, and /compact measured at 3.1x
AC-1 $93.32 ($92.21 main + $1.11 subagent), residual $0.000000. No
unmeasured rows. Composition: 88.0% cache, 11.9% output, 249:1 context
re-read to text written.

The question that could not be answered before: what /compact costs.
The transcript records it directly — 542,991 -> 19,974 tokens, a 27x
reduction. Cost per turn fell from $0.457 (136 turns before) to $0.149
(202 turns after). The 202 post-compact turns cost less than half the
136 before them.

This qualifies CB-WP-0003 T04: sessions are bounded-quadratic, not
quadratic. Cost grows with context between compactions and resets at
each one, so the failure mode is a long UNCOMPACTED session. Whether a
fresh session beats a compaction is now measurable, and T04 should
measure it before prescribing one task per session.

Stale $0.66/$92.87 targets updated across survey and workplan.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-31 08:51:50 +02:00
..
__pycache__ T05: CB-EV-0002 — all 9 metrics met, and /compact measured at 3.1x 2026-07-31 08:51:50 +02:00
cb-sim CI: enforce every gate; close the silent-skip holes 2026-07-31 04:02:33 +02:00
cb-cost.py T04: tools/cb-cost.py — and its positive control fires on first contact 2026-07-31 08:50:04 +02:00
dep-weight.py CI: enforce every gate; close the silent-skip holes 2026-07-31 04:02:33 +02:00
rule-coverage.py Add the AM-1 rule-coverage gate 2026-07-31 02:23:38 +02:00