Bastien Chanot c3ba540372 chore(memory): BDR-001 won't-build + LRN-080 + TODO requalify (--help measured non-rentable) ... --help chantier ABANDONED after measurement (not built — nothing to build): - BDR-001 append (won't-build 2026-06-30): behavioral RED, 6 reps (/web-validate + /harden, no instruction) → 6/6 already render help AND stop without dispatch; residual value = format consistency only → ROI insufficient on a solo repo. Original Decision/Why/Rejected intact (append-only); Index status cell updated. - LRN-080: measure if the model already does X before adding an instruction to make it do X — the behavioral RED kills phantom-value additions. Links LRN-075. - TODO: chantier requalified WON'T-BUILD (3rd state — not done, not open). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01C6bUdvHnajCNzgVQefZowj		2026-06-30 16:27:04 +02:00
..
blockers.md	chore(memory): backfill 34 missing Index rows + re-sort LRN-021	2026-06-29 19:25:42 +02:00
decisions.md	chore(memory): BDR-001 won't-build + LRN-080 + TODO requalify (--help measured non-rentable)	2026-06-30 16:27:04 +02:00
evals.md	chore(memory): capitalize /release-candidate — BDR-042 + LRN-078/079 + EVAL-012	2026-06-30 14:41:12 +02:00
journal.md	chore(memory): capitalize /release-candidate — BDR-042 + LRN-078/079 + EVAL-012	2026-06-30 14:41:12 +02:00
learnings.md	chore(memory): BDR-001 won't-build + LRN-080 + TODO requalify (--help measured non-rentable)	2026-06-30 16:27:04 +02:00