mirror of
https://github.com/openai/codex.git
synced 2026-09-16 12:13:30 +00:00
5fb3b7e401
## Why Matches starting inside a lowercase expansion such as `İ` → `i̇` could receive an incorrect prefix bonus or gap penalty, causing strings that lowercase identically to rank differently. ## What changed Track the first matched position in the lowercased text directly when calculating scores. Preserve original character indices for highlighting. ## Testing Add a skill popup regression test and snapshot covering ranking and highlighting for matches beginning at the combining dot in expanded and already-lowercase names. GitOrigin-RevId: 78a8b79f1defca9f76fde5df945b0b1ff4af25da