mirror of
https://github.com/openai/codex.git
synced 2026-10-23 18:08:45 +00:00
Hardens codex-rs/app-server connection lifecycle and outbound routing for websocket clients. Fixes some FUD I was having - Added per-connection disconnect signaling (CancellationToken) for websocket transports. - Split websocket handling into independent inbound/outbound tasks coordinated by cancellation. - Changed outbound routing so websocket connections use non-blocking try_send; slow/full websocket writers are disconnected instead of stalling broadcast delivery. - Kept stdio behavior blocking-on-send (no forced disconnect) so local stdio clients are not dropped when queues are temporarily full. - Simplified outbound router flow by removing deferred pending_closed_connections handling. - Added guards to drop incoming response/notification/error messages from unknown connections. - Fixed listener teardown race in thread listener tasks using a listener_generation check so stale tasks do not clear newer listeners. Fixes https://linear.app/openai/issue/CODEX-4966/multiclient-handle-slow-notification-consumers ## Tests Added/updated transport tests covering: - broadcast does not block on a slow/full websocket connection - stdio connection waits instead of disconnecting on full queue I (maxj) have tested manually and will retest before landing