Documentation 2026-08-10 19:00 UTC to 2026-08-11 09:01 UTC

243[Codex Auto-review](https://developers.openai.com/codex/sandboxing/auto-review). Add review and enforcement243[Codex Auto-review](https://developers.openai.com/codex/sandboxing/auto-review). Add review and enforcement

244to your own harness. The244to your own harness. The

245[open-source Codex reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)245[open-source Codex reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)

246illustrates one approach; [Cyber Safety](https://developers.openai.com/codex/cyber-safety) explains approved246illustrates one approach. Review [Models and Trusted Access](https://developers.openai.com/codex/cyber-safety)

247model access and safe engagement setup.247for approved model access and [Recommended configuration](https://developers.openai.com/codex/cyber-safety/recommended-configuration)

248for safe engagement setup.

248 249 

249## Streaming and delayed review use the same state model250## Streaming and delayed review use the same state model

250 251 

188Learn more:188Learn more:

189 189 

190- [Model evaluations hub](https://openai.com/safety/evaluations-hub)190- [Model evaluations hub](https://openai.com/safety/evaluations-hub)

191- [Cyber Safety](https://developers.openai.com/codex/cyber-safety)191- [Cyber safety models](https://developers.openai.com/codex/cyber-safety)

192- [Fine-tuning safety](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#safety-checks)192- [Fine-tuning safety](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#safety-checks)

193- [Safety checks in computer use](https://developers.openai.com/api/docs/guides/tools-computer-use#handle-user-confirmation-and-consent)193- [Safety checks in computer use](https://developers.openai.com/api/docs/guides/tools-computer-use#handle-user-confirmation-and-consent)