Codex updates

Radar Ultra

Releases: 217

0.64.0

CLIGitHub

AI summary

  • Safety and approvals are improved: workspace-write treats .git as read-only, risky browser or URL launches on Windows are flagged, and sandbox assessments and approvals better follow trust policies.
  • Reviews now have a detached mode and clearer enter/exit events, and review history remains visible after rollout filtering changes.
  • The app server provides more session details and updates, including working-directory and Git information, file-change deltas, plan updates, token-usage changes, and compaction events.
  • Execution and tool support expand with per-run custom environment settings, an experimental “exp” model, session-bloat pruning, and improved Windows and WSL history lookup.
  • Several reliability issues are fixed, including a cancellation hang, stale conversation conflicts when starting a new session, and inaccurate token-budget handling during compaction.

Written by AI from the official notes. The original prevails.

0.63.0

CLIGitHub

AI summary

  • Fixes an error that could occur when web search was enabled: Invalid value: 'other'.
  • The notes mention a fix for web search but don’t specify any other changes or limitations.
  • The fix addresses an error that could occur when enabling web search; the notes don’t say that all web search errors are resolved.

Written by AI from the official notes. The original prevails.

0.61.0

CLIGitHub

AI summary

  • Shell behavior is more reliable: fallback shell selection is hardened, and warnings about world-writable directories are less noisy, with clearer messaging on Windows.
  • Errors and truncated output are handled more clearly: truncation avoids duplicate work, and error events can include an optional status code.
  • Several interface issues are fixed: reasoning displays correctly, /review keeps its footer context, and the model migration screen appears only once.
  • The core integrates the ExecPolicy2 policy engine and includes groundwork for exec-server changes, along with quickstart documentation for teams adopting the engine.

Written by AI from the official notes. The original prevails.

0.60.1

CLIGitHub

AI summary

  • API users now get gpt-5.1-codex as the default model.
  • This is a bug-fix release; most important new changes are listed in the linked v0.59.0 release notes.

Written by AI from the official notes. The original prevails.

0.59.0

CLIGitHub

AI summary

  • GPT-5.1-Codex-Max is a new coding model designed for higher reliability, faster iteration, and long-running, project-scale workflows.
  • On native Windows, Agent mode can read and write files and run commands in your working folder with fewer approvals. It uses an experimental sandbox to limit filesystem and network access.
  • Codex now supports Compaction to improve performance during extended coding sessions.
  • Codex models can use up to 10,000 tokens for tool output; you can set the limit in config.toml using tool_output_token_limit.
  • The interface now avoids ghost snapshot notices when no Git repository is present, shows branches in Resume and filters by the current working directory, adds placeholder icons for images, and displays credits in /status.

Written by AI from the official notes. The original prevails.

0.58.0

CLIGitHub

AI summary

  • Codex now supports the gpt5.1 model family.
  • The app server has several enhancements, including a command for generating JSON schemas and events that signal when items start and finish.
  • Various fixes and usability updates include inline TUI shortcuts, clearer warnings, and fixes related to Wayland, brew, compaction, and cloud tasks. Documentation and status output were also updated.

Written by AI from the official notes. The original prevails.

0.57.0

CLIGitHub

AI summary

  • The terminal interface is easier to navigate: Ctrl-N and Ctrl-P move through slash-command lists, and backtracking skips the /status noise.
  • Timeout handling has been improved for long-running commands.
  • The notes don’t specify how the timeout behavior changed.

Written by AI from the official notes. The original prevails.

0.56.0

CLIGitHub

AI summary

  • A new model, GPT-5-Codex-Mini, is available. It’s a more compact and cost-efficient version of GPT-5-Codex.
  • - Introducing our new model GPT-5-Codex-Mini — a more compact and cost-efficient version of GPT-5-Codex
  • GPT-5-Codex-Mini is a smaller, more cost-efficient option than GPT-5-Codex.

Written by AI from the official notes. The original prevails.

0.55.0

CLIGitHub

AI summary

  • The Linux Codex CLI startup failure reported in #6220, along with similar failures, was fixed by reverting #6189.
  • No other changes are listed in these notes.
  • The fix was included in change #6222.

Written by AI from the official notes. The original prevails.

0.54.0

CLIGitHub

AI summary

  • The attempt to pin musl 1.2.5 to fix DNS issues was reverted because it was the wrong fix; the release published as version 0.55.0.
  • The rest of the release mostly contains bug fixes and documentation updates.
  • The rest of the release mostly contains bug fixes and documentation updates.

Written by AI from the official notes. The original prevails.

0.53.0

CLIGitHub

AI summary

  • Some error 400 issues have been fixed.
  • Sandboxing for Java has been improved.
  • Some error 400 issues have been fixed.
  • Sandboxing for Java has been improved.

Written by AI from the official notes. The original prevails.

0.52.0

CLIGitHub

AI summary

  • You can now buy credits for additional usage.
  • You can run a command directly by typing ! followed by the command.
  • The interface now keeps queued messages visible while Codex is responding, and adds an undo operation. Compaction prompts are configurable, with Windows auto-mode guidance also improved.
  • Image handling now resizes images on the client and checks their MIME type to help prevent crashes.
  • Authentication now supports a keyring and configurable storage backends. Conversation and execution updates include conversation summaries, streaming events, and more consistent handling of tool-output truncation.

Written by AI from the official notes. The original prevails.

Radar Ultra
An unofficial tool, not affiliated with OpenAI. Compiled from public posts; the original posts are authoritative.