mirror of
https://github.com/openai/codex.git
synced 2026-08-23 13:09:46 +00:00
## Why Terminal probes and other bootstrap work can leave keys or partial control sequences buffered before an interactive startup screen is visible. Those inputs must not accidentally select or confirm an action, while typeahead intended for the composer should survive terminal initialization. ## What changed - Replay user input consumed by Unix startup probes through Crossterm while filtering completed terminal color replies, and avoid consuming the Windows console input queue when detecting default colors. - Drain decoded and unread input after rendering actionable startup screens, including onboarding trust, migration, update, provider, resume, and hooks prompts. Keep incomplete control sequences quarantined and fail closed when an input boundary cannot be resolved. - Restore terminal modes if initialization exits early and bound terminal probe reads by time and byte limits. ## Testing Add parser, boundary, onboarding, and PTY coverage for preserved typeahead, split escape sequences, bracketed paste, delayed input, and fresh input after an interactive screen becomes ready. GitOrigin-RevId: 321198996cdd88fe9b43c4a762e750bff450482c
1.5 MiB
1.5 MiB