mirror of
https://github.com/openai/codex.git
synced 2026-10-25 23:57:40 +00:00
Benjamin Carlsson
9ab176f488
## Why Pending input previews display at most three wrapped rows, but previously wrapped every logical line before truncating the result. This made rendering do unnecessary work for very large multiline inputs. ## What changed Limit pending steers, rejected steers, and queued follow-up inputs to four source lines before wrapping: three for the preview and one to detect overflow and render the ellipsis. ## Testing Keep multiline preview coverage for queued messages and pending steers, including blank lines near the truncation boundary. GitOrigin-RevId: 4c300b13532983ff9c3bdfbd62d6ca722ea3a5aa