OpenAI reportedly prepping Codex Replay to run and compare historical task threads in parallel

testingcatalog · x · 2026-09-16

According to unconfirmed leak by testingcatalog, OpenAI is building a 'Codex Replay' feature that lets users test task execution from imported historical conversation threads. Key points:

This enables side-by-side verification of the same task across configurations.

Original post →

More from coding & agent

coding & agent channel →