AI & Agents

What’s New in Codex CLI 0.164.0: /presets, Inline /model and Credential Masking

Leave a comment

Codex CLI 0.164.0 is out as a stable release. Here’s what’s in it.

New features

  • /presets: save reusable prompts and slash commands in ten numbered preset slots, with a keyboard menu for quick access.
  • Inline arguments: set the model, reasoning effort, speed and permission profiles right from /model and /permissions arguments.
  • Preview viewed and generated images in the fullscreen transcript on terminals that support Kitty or Sixel graphics.
  • Authenticate enterprise MCP connections using eligible Codex account grants or dedicated sign-in, including OAuth clients that require secrets.
  • Credential masking: credentials, including ones from custom providers, are masked during supported remote Bash commands and Zsh snapshot sessions.
  • The Amazon Bedrock setup wizard is now on by default, with API key entry grouped alongside other AWS sign-in methods when credentials are detected.

Fixes

  • A failed compaction no longer leaves partial summaries in the conversation history, and background compaction failures fall back without panicking.
  • Resuming a session now finds compressed histories and restores saved thread settings instead of replacing them with global defaults.
  • Windows connections handle proxy authentication challenges using the signed-in user’s Negotiate or NTLM credentials.
  • CLI configuration overrides are preserved when -c or --config appears at more than one subcommand level.
  • Queued prompts now wait for pending permission selections to resolve before continuing.
  • Hardened sandbox checks for case-variant metadata paths on macOS and for replaceable symlinks used to locate executables.

My take

/presets is a nice quality-of-life win if you keep retyping the same instructions. The credential masking and sandbox hardening are the ones I’d care about most, because agents running remote shell commands are where secrets leak.

Have a blessed day! And Happy Hacking!

References & Further Reading

Subscribe (RSS) Follow AI & Agents via RSS

Leave a note

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.