Codex can now keep coding while it waits for your answer
Long-running coding agents face an awkward choice when they need a developer’s input. They can stop and wait or make The post Codex can now keep coding while it waits for your answer appeared first on The New Stack .
OpenAI is testing a new feature for Codex that allows the coding agent to ask a developer a question, continue working on other tasks independently, and then adjust its approach once the developer provides a response. The feature, send_user_message_async, has been merged into the public Codex repository but has not been announced as a general capability.
Rather than waiting for a developer's input, Codex can send the question, receive confirmation that the message was accepted, and continue working on other tasks that do not depend on the answer. This allows Codex to report what it is doing or ask for a decision while continuing work. There is no mechanism in place to prevent Codex from moving past a decision made while waiting for a developer's response, which could lead to conflicts if the developer provides an unexpected answer.
OpenAI removed the requirement for developers to enable an experimental feature flag, suggesting that the tool will be controlled through model metadata rather than requiring explicit developer consent.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
