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:
- Replay runs as an independent controller on a loopback port, in Codex Desktop and CLI, preferring the in-app browser;
- Users can select multiple historical threads and run isolated parallel sessions with shared Codex models, defaulting to GPT-5.6 Sol, Terra, and Luna;
- Each thread's state and configuration are detected separately, and finished comparisons can be viewed individually or in aggregate.
This enables side-by-side verification of the same task across configurations.
More from coding & agent
- Atom goes live on Stripe's Machine Payments Protocol, letting AI agents buy domains autonomously — jeff_weinstein · 2026-09-16
- Astra Is Flawless for Hours, Then Randomly Stops and Makes Up Excuses — altryne · 2026-09-16
- Agent-installed skill/CLI survives a VM temp files wipe — MurrLincoln · 2026-09-16
- ComfyUI MCP + Claude diagnosis cuts video gen workflow from 22 to 9 minutes — CanadianDocWild · 2026-09-16
- A senior Google AI engineer's 482-page doc on agentic design patterns — mdancho84 · 2026-09-16
- Developer adds reusable saved tasks to a browser agent, prompts now work across repos — Silly_Entertainer92 · 2026-09-16