Marius CiepluchandClaude Opus 5.5 67699e8737 bench(plane): increment gate met after the tie-break -- 16/20 agreed at $0.0205/candidate ...

A third verify pass on the 10 disputed candidates, 2-of-3 agreement (Req 6.4),
run on ax by extending the same Run: 16/20 declared sites agreed (reference 16),
$0.0205 per candidate with recorded triage (reference $0.022). Caveats recorded:
a design change on the same set; 17 vs 19 sites flagged in any pass; three
non-declared pgadmin candidates promoted.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

2026-09-30 08:35:41 +02:00

..

dev

chore(dev): token-lean workflow tools -- read guard, bulk reader, transcript report

2026-09-29 17:23:30 +02:00

fixtures

feat(three-stage-scan): gate stage-2 maps against split-sink ranking

2026-09-04 11:53:06 +02:00

independent

bench(plane): increment gate met after the tie-break -- 16/20 agreed at $0.0205/candidate

2026-09-30 08:35:41 +02:00

manifests

feat(three-stage-scan): add aliased-sink mutation the regex scan misses

2026-09-04 11:50:44 +02:00

measurements

feat(plane): per-task egress policy; receiver by name through the gateway

2026-09-29 20:51:21 +02:00

pairs

feat(corpus): vendor 40 OWASP xss pairs as the owasp slice

2026-09-08 17:28:11 +02:00

push

perf(taint): ask the caller check only of a parameter that starts a flow into the field

2026-09-23 22:49:44 +02:00

ranking

feat(pre-push-safety-net): preserve uncertainty in benchmark scoring

2026-09-12 19:04:20 +02:00

repos

feat(pre-push-safety-net): pin labeled evaluation inputs

2026-09-12 18:45:54 +02:00