Codex updates

Radar Ultra

Releases: 217

0.84.0

CLIGitHub

AI summary

  • Text elements can now include additional metadata, allowing clients to render them in richer ways and making the schema easier to evolve.
  • Rust release builds have a longer job timeout to reduce flaky pipeline failures, particularly on Windows.
  • Rust release builds have a longer job timeout to reduce flaky pipeline failures, particularly on Windows.

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

0.81.0

CLIGitHub

AI summary

  • The default API model is now gpt-5.2-codex.
  • Headless runs now switch to device-code sign-in automatically, so you can sign in without a browser.
  • On Linux, the sandbox can mount paths read-only to better protect files from changes.
  • The codex tool in codex mcp-server now returns a threadId that can be used with codex-reply.
  • Several issues were fixed: Zellij scrollback handling, unsafe-command prompts on Windows with a read-only sandbox, reporting configuration and rules parsing errors, a macOS proxy-discovery crash, and errors for invalid image uploads.

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

0.80.0

CLIGitHub

AI summary

  • CLI subprocesses again inherit important environment variables, fixing runtime problems that could cause 10× or greater performance regressions, especially for GPU-related subprocesses.
  • You can now branch a session into a separate thread using new conversation-fork endpoints.
  • Codex now offers elevated-sandbox onboarding, including prompts for upgrading or continuing in degraded mode and an /elevate-sandbox command.
  • In the TUI and TUI2, /review <instructions> now starts the review flow instead of being sent as ordinary text.
  • Other updates add explicit skill invocation through the v2 API, expose requirements for clients, and add observability counters.

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

0.79.0

CLIGitHub

AI summary

  • Sessions can now spawn or message other conversations, making it possible to coordinate work across multiple conversations.
  • IDE clients can undo the last several turns in a conversation without rewriting its history.
  • Web Search can use cached results only, as an alternative to making live requests.
  • A production policy bypass was closed: CODEX_MANAGED_CONFIG_PATH can no longer override managed configuration in production.
  • Several usability and reliability fixes improve transcript resizing and copy/paste, tolerate extra whitespace in apply_patch markers, and reduce TUI glitches.

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

0.78.0

CLIGitHub

AI summary

  • You can press Ctrl+G to edit your current prompt in your configured external editor; edits sync back into Codex.
  • Codex can combine project-level .codex/config.toml settings with system configuration. Project-root detection can use configurable markers, and enterprise-managed configuration requirements are supported on macOS through an MDM-provided TOML payload.
  • Multiple tool calls returned by a model in one turn are now handled in the expected format, fixing failures in those cases.
  • The tui2 interface has improved transcript selection, copying, and scrolling, along with fixes for rendering and input edge cases.
  • Windows PowerShell sessions now start in UTF-8 mode to reduce encoding-related prompt and output issues.

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

0.77.0

CLIGitHub

AI summary

  • The /undo command is fixed so it no longer disrupts Git staging or ghost commits.
  • Mouse-wheel and trackpad scrolling are more consistent across terminals, with new settings to adjust scrolling.
  • Requirements can now specify which sandbox modes are allowed, helping constrain the modes Codex may use.
  • OAuth login for streamable HTTP MCP servers no longer requires the rmcp_client feature flag.
  • File search now uses centralized filename handling to improve the display and consistency of fuzzy search results.

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

0.76.0

CLIGitHub

AI summary

  • Skills are enabled by default, with support for administrator-scoped skills and short descriptions. The notes do not specify the default behavior on Windows.
  • A model-list interface was added.
  • On UNIX, Codex can now use /etc/codex/requirements.toml.
  • A macOS disk-image (DMG) build target was added.
  • Bug fixes improve pipe access in restricted sandbox tokens and the timing of command-runner directory access.

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

0.75.0

CLIGitHub

The official source did not provide curated notes.

0.74.0

CLIGitHub

AI summary

  • Codex adds gpt-5.2-codex, a new model with improvements in knowledge, reasoning, and coding.
  • A new /experimental slash command lets you try experimental features.
  • You can now disable ghost snapshot warnings with a toggle.
  • The interface has been polished, including background terminals and a cleaned-up picker.

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

0.73.0

CLIGitHub

AI summary

  • Codex is less likely to crash when a session contains a tool call with no output.
  • Skills are now discovered through a new shared loading system, for more consistent discovery.
  • Ghost snapshot v2 improves session capture, and ghost commits can now be configured.
  • Codex adds OpenTelemetry tracing, which records tracing data about Codex.
  • Several smaller fixes adjust how the interface responds to bursts of typing, change the default text-wrapping method, and include errors in log messages.

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

0.72.0

CLIGitHub

AI summary

  • API-key users can now use remote compacting in their sessions.
  • Configuration loading and its API have been cleaned up.
  • The TUI again shows MCP startup progress and uses the latest on-disk values for server status.
  • Windows improvements include more reliable discovery of PowerShell, parsing PowerShell with PowerShell, signing two additional executables, and fixing toasts under WSL 2.
  • Safety and model guidance were updated: the release adds Elevated Sandbox 3 and 4 plus more safe commands, and clarifies gpt-5.2 xhigh reasoning warnings and documentation.

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

0.71.0

CLIGitHub

AI summary

  • Codex now introduces GPT-5.2, a new frontier model with improvements in knowledge, reasoning, and coding.
  • Learn more about GPT-5.2 in the linked announcement.
  • The notes do not specify further details about these improvements.

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

0.69.0

CLIGitHub

AI summary

  • When you explicitly select a skill, Codex now adds its SKILL.md content to that turn. Skills load once per session, and Codex warns if it can’t read the file.
  • Configuration handling is more compatible with real config files: config reads are typed, writes preserve comments and ordering, and the model setting can be omitted.
  • Several usability fixes improve navigation and transcripts: vim-style keys work in option selection and the transcript pager, transcript paging continuity is fixed, invalid input no longer opens the slash-command popup, and TUI log files omit ANSI codes.
  • Execution and sandbox changes include shell snapshotting, updated unified-exec events, allowing sendmsg/recvmsg in the Linux sandbox, clearer rate-limit warnings, and request-ID logging.
  • Other additions and fixes include MCP in-session login, review support using remote branches, graceful errors for unsupported images, and a feature-flagged experimental tui2 frontend.

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

0.66.0

CLIGitHub

AI summary

  • Cloud runs now accept a branch name, and you can check their status, inspect changes, and apply them.
  • After approving a command, you can allow its command prefix for future use. If a command is blocked by the sandbox, Codex can suggest a rule change for you to accept. Shell MCP tools follow the same execution rules, and safety checks inspect each part of a command pipeline.
  • Several stability and usability fixes improve command progress display, long-command layout, Windows unified-exec reliability, and cleanup of tool sessions.
  • Keyboard shortcuts for navigating lists and overlays now work consistently across platforms.
  • Patch handling on Windows preserves CRLF line endings, with additional tests covering patch flows.

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

0.65.0

CLIGitHub

AI summary

  • Codex Max is now the default model. A related TUI panic was also fixed.
  • You can use the new /resume command to pick up work again, and resuming is faster.
  • History is trimmed according to history.max_bytes, and common junk directories—including pycache—are ignored by default.
  • The TUI adds Ctrl-P/N navigation, limits shell output by screen lines, and restores image pasting from the clipboard on Windows.
  • Tips and tooltips now use markdown, with a bold “Tip” label and richer Codex tooltips across the app.

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

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.

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