OpenAI Agents API update: command auto-review, background compaction and time awareness
What is it?
The Agents API is OpenAI's managed agent runtime, where OpenAI runs the Codex harness for you. Five things shipped this week. Auto Review checks shell commands before they run, the same way Codex does. Async Compaction moves conversation compaction (summarizing a long history to shrink it) into the background. Time awareness, an experimental feature, gives the model a sense of time passing. Sessions can now change their tool list mid-session, and system prompts are cached automatically across all sessions. In the Python SDK, the compaction, review and experimental settings are available from v3.42.0.
Why does it matter?
Handing an agent a shell always raises the question of what it will run, and now the server screens commands first, so you don't have to build that step yourself. Background compaction cuts the pauses long sessions hit while summarizing, and time awareness is meant to help the model respect instructions like "timebox CI fixes to 10 minutes." Automatic system-prompt caching lowers input costs right away for products that open lots of sessions.
Maturity
GAWe rated this GA because the features went straight into the Agents API. OpenAI calls Time awareness experimental, though, and there's no official changelog entry yet. We confirmed it only through the X posts and the SDK release.
How to track it
- Docs: watch the OpenAI API changelog and the Agents guide for write-ups of Auto Review and Time awareness, with field names.
- Auto Review scope: see whether OpenAI says which commands it blocks and what latency or cost the review adds.
- SDKs: check whether the next openai-python and openai-node releases promote the experimental fields to stable ones.