cc-os/plugins/os-vault/eval/fixture/project
jared 42860d06d1 os-vault: WS2 wording loop — destination ladder shipped, reserve grid measured
4 iterations (destination ladder -> mechanical vault-root -> CLAUDE.md
cross-project-memory section -> ADR-vs-vault disambiguation) + candidates 2-4
unscored + post-reserve YAML-colon quoting rule. Confirm 18/18 sonnet, 16/18
haiku; held-out reserve trigger-axis 13/18, negatives 17/18 (baseline 1/19,
18/18). Checker breach-regex false positive fixed + rescored, 2 self-test
guards added. Run-set and reserve both contaminated now.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 14:01:15 -04:00
..
bin os-vault: WS2 write-behavior eval harness + untuned baseline grid 2026-07-07 12:46:22 -04:00
config os-vault: WS2 write-behavior eval harness + untuned baseline grid 2026-07-07 12:46:22 -04:00
docs/adr os-vault: WS2 write-behavior eval harness + untuned baseline grid 2026-07-07 12:46:22 -04:00
lib/reportgen os-vault: WS2 write-behavior eval harness + untuned baseline grid 2026-07-07 12:46:22 -04:00
CLAUDE.md os-vault: WS2 wording loop — destination ladder shipped, reserve grid measured 2026-07-07 14:01:15 -04:00
Rakefile os-vault: WS2 write-behavior eval harness + untuned baseline grid 2026-07-07 12:46:22 -04:00