Opus 5.5 stalls on long tasks; dev adds 20-min check-ins while Codex babysits well

paul_cal · x · 2026-09-28

Paul Cal reports Opus 5.5 keeps getting stuck on bad waits — multiple 5+ hour workstreams paused because a single intermediate job crashed or hung, forcing him to prompt it to schedule a session check-in every 20 minutes. Codex 5.5+, by contrast, almost never had this issue and got very good at babysitting long runs.

Original post →

More from coding & agent

coding & agent channel →