OpenAI Codexcodex-cli 0.154 · macOS, Linux, WSL, Windows
1
Curious builder0 XP earned · 300 to level 2
0 daysFinish a lesson to begin
Badge collection0 of 6 unlocked
26 small wins to finish your pathNext lesson

Auto-review

Approvals interrupt you. Auto-review keeps the same boundary and changes who answers the question.

The documentation puts it precisely: auto-review replaces manual approval at the sandbox boundary with a separate reviewer agent. The main agent still runs inside the same sandbox, with the same approval policy and the same network and filesystem limits. What changes is who reviews eligible escalation requests.

When it applies

Only when approvals are interactive, which in practice means approval_policy = "on-request" or a granular policy that still raises the relevant prompt. With never there is nothing to review, because nothing is being asked.

toml
sandbox_mode = "workspace-write"
approval_policy = "on-request"

That is the setting auto-review sits on top of. It is not a way to turn approvals off: the boundary is unchanged and the requests still happen.

What it buys, and what it costs

What you gainFewer interruptions on requests that are obviously fine
What you give upA human reading each escalation
What does not changeThe sandbox, the policy, the network and filesystem limits

So the question is not whether you trust the reviewer. It is whether the boundary is narrow enough that an escalation being approved without you is acceptable. That is lesson 4's decision, again.

Fatigue is the real risk
If the answer is no, the fix is a narrower profile rather than more prompts. Approval fatigue is what makes people turn the sandbox off, which is the outcome everything in this part is trying to avoid.
Try it yourself
  • Work for an afternoon on request and count how many approvals you actually read.
  • Narrow the profile until the ones left are ones you want to see.

You understood something today that you didn't yesterday.