mirror of
https://github.com/expo/code-review-cli.git
synced 2026-11-14 17:49:25 -10:00
Measured on ~13 real PRs, the deterministic "evidence absent from file → hard drop" rule was too aggressive: it dropped 3 findings vs 1 surfaced, and at least one drop was a confirmed real bug. Exact-substring is a good positive signal but a poor negative one — it misfires on structural/"missing" bugs, cross-line quotes, ellipsis, copied comment/diff markers, and slightly-wrong locations. - Fuzzy match (matchEvidence/evidenceFragments): exact substring OR any substantive line/fragment present verbatim, after stripping comment/diff markers and splitting on newlines + ellipsis. - Escalate, don't drop: absent evidence (any severity) now routes to the LLM verifier instead of a hard drop; a finding is dropped only on refutation. present/unknown non-criticals keep the no-LLM fast path. - Verifier judges substance not wording (quote treated as an imperfect hint); reviewer prompt asks for one contiguous verbatim line. Tests: +8 (pure matchEvidence/evidenceFragments cases + escalate-not-drop guard).