Codex
OpenAI's Rust-based CLI for interacting with the Codex model.
🔒 Security Updates
✨ New Features
>Execpolicy: TUI can whitelist command prefixes after an approval, sandbox denials propose an amendment you can accept, shell MCP now runs execpolicy so MCP tools follow the same rules, and
SECURITY
>Cloud exec: codex cloud exec accepts --branch for remote runs and now exposes status/diff/apply flows so you can inspect and apply changes from the cloud path (#7602, #7614).
>#6846 feat(core) Add login to shell_command tool @dylan-hurd-oai
>#7033 whitelist command prefix integration in core and tui @zhao-oai
SECURITY
>#7543 execpolicy tui flow @zhao-oai
SECURITY
>#7580 feat: update sandbox policy to allow TTY @jif-oai
SECURITY
>#7602 add --branch to codex cloud exec @nornagon-openai
>#7603 Add models endpoint @aibrahim-oai
>#7609 feat: exec policy integration in shell mcp @zhao-oai
SECURITY
>#7614 cloud: status, diff, apply @nornagon-openai
>#7645 Also load skills from repo root. @xl-openai
>#7648 Add remote models feature flag @aibrahim-oai
>#7653 proposing execpolicy amendment when prompting due to sandbox denial @zhao-oai
SECURITY
>#7722 load models from disk and set a ttl and etag @aibrahim-oai
>#7729 feat: add is-mutating detection for shell command handler @jif-oai
SECURITY
🚀 Improvements
>TUI updates: cross-platform shortcut handling is consistent (Ctrl+N/P and list selection now work everywhere), so navigation matches between overlays, lists, and text areas (#7583, #7629).
>#6918 Add Enterprise plan to ChatGPT login description @ae-openai
>#7310 Inline response recording and remove process_items indirection @aibrahim-oai
>#7544 Refactor execpolicy fallback evaluation @zhao-oai
SECURITY
>#7547 Use shared check sandboxing @pakrym-oai
SECURITY
>#7554 chore(core): test apply_patch_cli on Windows @dylan-hurd-oai
>#7561 Do not emit start/end events for write stdin @pakrym-oai
>#7563 Slightly better status display for unified exec @pakrym-oai
>#7567 chore(apply-patch) scenarios for e2e testing @dylan-hurd-oai
>#7571 remove model_family from `config @aibrahim-oai
>#7588 chore: default warning messages to true @jif-oai
>#7591 chore: tool tip for /prompt @jif-oai
>#7615 chore: refactor to move Arc<RwLock> concern outside exec_policy_for @bolinfest
>#7616 Call models endpoint in models manager @aibrahim-oai
>#7617 fix: add integration tests for codex-exec-mcp-server with execpolicy @bolinfest
SECURITY
>#7621 Wire with_remote_overrides to construct model families @aibrahim-oai
>#7685 fix: refine the warning message and docs for deprecated tools config @gameofby
>#7709 Enhance model picker @aibrahim-oai
>#7711 Add formatting client version to the x.x.x style. @aibrahim-oai
>#7747 updating app server types to support execpoilcy amendment @zhao-oai
SECURITY
>#7748 Remove legacy ModelInfo and merge it with ModelFamily @aibrahim-oai
>#7754 override instructions using ModelInfo @aibrahim-oai
>#7756 use chatgpt provider for /models @aibrahim-oai
🐛 Bug Fixes
>Unified exec & shell stability: status line shows clearer progress, Windows unified-exec crash fixed, long commands wrap without breaking layout, and SSE/session cleanup reduces stuck or
>Apply-patch: Windows CRLF line endings are preserved, new e2e scenarios cover more patch shapes, and Windows-specific test coverage reduces regressions in patch flows (#7515, #7567, #7554). Thanks to @cnaples79 who contributed the [core part](https://github.com/openai/codex/pull/4017) of this fix!
>General fixes: parallel tool-call chat now returns correctly, ghost snapshot tokens aren’t billed, missing tool names no longer crash the litellm proxy, and migration prompts use HTTPS links
>#6793 FIX: WSL Paste image does not work @Waxime64
>#7515 fix(apply-patch): preserve CRLF line endings on Windows @dylan-hurd-oai
>#7583 Fix handle_shortcut_overlay_key for cross-platform consistency @448523760
>#7592 fix: release session ID when not used @jif-oai
>#7594 fix: sse for chat @jif-oai
>#7605 fix(app-server): add duration_ms to McpToolCallItem @owenlin0
>#7610 fix: taking plan type from usage endpoint instead of thru auth token @zhao-oai
>#7611 fix(app-server): add will_retry to ErrorNotification @owenlin0
>#7620 Fix unified_exec on windows @pakrym
>#7626 fix typo @zhao-oai
>#7629 fix(tui): add missing Ctrl+n/Ctrl+p support to ListSelectionView @pppp606
>#7634 fix: chat completion with parallel tool call @jif-oai
>#7638 fix: ignore ghost snapshots in token consumption @jif-oai
>#7651 fix: OTEL HTTP exporter panic and mTLS support @asm89
>#7654 fix: exec-server stream was erroring for large requests @bolinfest
>#7655 fix wrap behavior for long commands @zhao-oai
>#7660 Restore status header after stream recovery @joshka-oai
>#7705 fix: update URLs to use HTTPS in model migration prompts @rakleed
>#7724 Fixed regression for chat endpoint; missing tools name caused litellm proxy to crash @etraut-openai
>#7749 fix: pre-main hardening logic must tolerate non-UTF-8 env vars @bolinfest
>#7753 Revert "feat: windows codesign with Azure trusted signing" @shijie-oai
📚 Documentation
>#7595 Update execpolicy.md @zhao-oai
>#7665 docs: fix documentation of rmcp client flag @JaySabva
>#7669 fix(doc): TOML otel exporter example — multi-line inline table is invalid @448523760
>#7672 docs: Remove experimental_use_rmcp_client from config @JaySabva
>#7673 docs: point dev checks to just @voctory
>#7745 Make the device auth instructions more clear. @mzeng-openai
📦 Other Changes
>#7593 chore: review in read-only @jif-oai
>#7652 Move justfile to repository root @joshka-oai
>#7678 fix: clear out space on ubuntu runners before running Rust tests @bolinfest
>#7680 fix: ensure macOS CI runners for Rust tests include recent Homebrew fixes @bolinfest
>#7713 chore(deps): bump ts-rs from 11.0.1 to 11.1.0 in /codex-rs @dependabot[bot]
>#7714 chore(deps): bump derive_more from 2.0.1 to 2.1.0 in /codex-rs @dependabot[bot]
>#7715 chore(deps): bump insta from 1.43.2 to 1.44.3 in /codex-rs @dependabot[bot]
>#7716 chore(deps): bump wildmatch from 2.5.0 to 2.6.1 in /codex-rs @dependabot[bot]