Skip to content

Codex CLI 0.163.0 lets you steer OpenAI's agent mid-response

The release adds instant interruption, parallel read-only tool calls, a configurable leader key, and proxy checks that close a way agents could dodge network inspection.

Source: OpenAI

OpenAI shipped Codex CLI 0.163.0 on 15 October with instant response steering: you can send a follow-up while Codex is still answering and it redirects immediately, rather than waiting for the current turn to finish. Interrupting a turn also stops any active Code Mode cells and their nested tool calls.

The same release lets Codex run independent read-only tools in parallel, including skill, memory and conversation-history lookups, and makes the leader key configurable through /keymap (default Ctrl+X, with voice mute moved to F9). On the security side, the network proxy now checks permission before a DNS lookup, rejects duplicate Host headers, and stops credential aliases from bypassing inspection hooks. Resuming a saved thread restores its permissions and network approvals rather than resetting them.

npm install -g @openai/codex@0.163.0

Why it matters: anyone running Codex as a coding agent gets faster course correction instead of babysitting a turn to completion, and parallel read-only tool calls should cut dead time on research-heavy steps. The proxy tightening matters more quietly: it closes a plausible route for an agent to route a request around the sandbox’s own network controls.

Share

Related reading

ML for Web Devs

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

More from The Wire

All briefs

GitHub Copilot retires six AI models today

Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 stop working across Copilot Chat, inline edits, agent mode and completions from today.

via GitHub