Expanded Auto-review documentation
TL;DR
New documentation for Auto-review covers the reviewer lifecycle, trigger conditions, failure behavior, and configuration options. Updates also clarify how Auto-review interacts with the sandbox boundary.
## What changed OpenAI added expanded documentation for the Auto-review feature inside Codex on May 18, 2026. The new pages cover the full reviewer lifecycle, exact trigger conditions, failure modes, and all configuration options.
The updates also spell out how Auto-review respects sandbox boundaries and what happens when a review attempt crosses those limits.
## Why it matters Solo builders who run Codex agents against live codebases now have clearer guardrails instead of guessing at edge cases. This reduces the chance that an agent silently skips reviews or hits sandbox walls without explanation.
The change signals OpenAI is treating Auto-review as a production control rather than an experimental toggle. Teams that rely on Codex for automated pull request checks gain predictability, while those who ignored the sandbox rules may need to adjust workflows.
## How to use it Open the Auto-review section at https://developers.openai.com/codex/concepts/sandboxing/auto-review. Read the lifecycle diagram first, then the trigger and failure tables.
Test the new configuration keys in a non-production workspace before enabling them on main branches. No paid plan change is required; the docs apply to any Codex CLI or app user with review permissions turned on.
## Watch for Confirm the bet if future releases expose the same lifecycle data through the Codex SDK or GitHub Action. The bet breaks if sandbox violations still produce vague errors after the docs claim full coverage. Expect a follow-up move that adds approval-mode overrides tied directly to Auto-review outcomes.
Harsh’s take
The new docs reduce guesswork for anyone running Codex agents on real repositories. Most solo operators will still hit the same practical limit: Auto-review only fires when the sandbox already trusts the change, so you end up maintaining two sets of rules anyway.
Trade-off is clear. You gain explicit failure descriptions but lose the ability to treat the feature as a black-box safety net. If your workflow depends on agents making changes outside the declared workspace roots, the clarified boundaries will force manual review steps back into the loop.
Set aside one hour this week to map your current trigger conditions against the new lifecycle table and remove any rules that now conflict with sandbox policy.
by Harsh Desai
About OpenAI Codex
View the full OpenAI Codex page →All OpenAI Codex updatesMore from OpenAI Codex
- App UpdateCodex CLI 0.129.0 release
Codex CLI 0.129.0 adds modal Vim editing in the composer, redesigned TUI workflows for easier resuming and forking, enhanced plugin management with workspace sharing, and improved Linux sandbox reliability.
- FeatureCodex Chrome extension launch
The new Codex Chrome extension enables parallel interaction with apps and websites in your browser. It operates in the background, allowing you to maintain control over which websites Codex can access.
- App UpdateCodex CLI 0.130.0 release
Codex CLI 0.130.0 introduces plugin hook details, a new 'codex remote-control' command for headless app-server management, thread pagination, and improved Bedrock authentication using AWS login profiles.