Codex lacks visual indicator for multi-day agent runs, user resorts to renaming tasks

chrisalbon · x · 2026-11-17

chrisalbon highlights a UX gap in Codex: he runs two multi-day analyses managed by GPT Sol, where the model stays mostly dormant and only occasionally steers — but Codex shows no visual cue that the run is still active. His workaround: manually renaming the task with a "[running]" prefix. He tags the team suggesting a proper long-run status indicator.

Original post →

More from coding & agent

coding & agent channel →