Commit Graph
5 Commits
Author SHA1 Message Date
mathiasandClaude Sonnet 5.5 62de8ac2e6 feat(wing): score a wing by its best page, not summed hits; add wingbacktest command (#205 S1)
A first backtest showed BM25 summed over a wing's top hits favours big wings
(0/4 agreement). Best-page scoring is volume-robust; pinned by a test that
failed before the change.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-20 06:04:45 +02:00
mathiasandClaude Sonnet 5.5 365130459f feat(wing): backtest metric (coverage/precision at a threshold) and shared TopWing (#205 S1)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-20 05:58:55 +02:00
mathiasandClaude Sonnet 5.5 c06509afe4 feat(wing): BM25 scorer as the independent cross-check (#205 S1)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-20 05:58:14 +02:00
mathiasandClaude Sonnet 5.5 85d8ecb5c7 feat(wing): LLM classifier with tolerant, fail-closed reply parsing (#205 S1)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-20 05:57:51 +02:00
mathiasandClaude Sonnet 5.5 5bbf47064d feat(wing): resolver that places a raw note in a wing without human typing (#205 S1)
Explicit subfolder/frontmatter wins; otherwise a classifier and an
independent scorer must agree above a threshold on a known, eligible wing.
Anything else is an Exception for a human. Never creates a wing, never
assigns an ineligible (client/untagged) wing. Mutation-checked: dropping the
eligibility, known-wing, scorer, threshold or conflict check fails a test.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-20 05:56:55 +02:00