Codex desktop app won't show which command the agent ran, user complains

amplifiedamp · x · 2026-09-22

A user criticizes the OpenAI Codex desktop app's observability: when the agent executes a command, the UI only says it "ran a command" without revealing which one. The author argues this is terrible for understanding what context the agent is actually working with.

Original post →

More from coding & agent

coding & agent channel →