the diff / OpenAI Agents API / November 6, 2026
OpenAI Agents API adds auto_review, a model answers approvals
score per-tool overrides: 0
OpenAI's Agents API adds auto_review, a model that approves or denies shell, file, permission, network and MCP requests. Off by default, tokens billed extra.
official source: developers.openai.com →
What changed
OpenAI's API changelog for October 30 adds automatic review to eligible Agents API projects. Set a session's review field to auto_review and an OpenAI-managed model weighs each action's intent and risk, then approves or denies it. It covers shell commands and terminal input that need approval, file changes that need approval, requests for broader filesystem or network access, and MCP tool calls whose rules require confirmation, for the turn and its subagents. Browser sign-in, MCP forms and URL hand-offs still reach your app. Default is none; review tokens bill on top of the agent's usage, and a project without access gets the request rejected.
Why it matters if you ship with an agent
Who approves: a model the docs do not name. There is no per-tool override; what stays manual is what the environment forbids. Put network limits in the environment, not the reviewer, and read the turn's events afterwards.
By MK · Source: https://developers.openai.com/api/docs/changelog
keep handy: AI coding tool pricing tracker · vibe coding vs AI coding · agent fail hall of fame
The Diff is Accept All's short note on changes that alter how you ship with an agent. Newer: Claude Code 2.1.321 defaults Fable to 5.2, mods skip prompts. Older: Claude Code 2.1.319 can deny instead of prompting, auto mode loses fallback.