ChatGPT & Codex changelog
ChatGPT & Codex changelog
Latest updates to ChatGPT and Codex
The official changelog is a dynamic release feed. This local page keeps the newest high-level entries available to search and links to the complete live feed for CLI release details.
October 2026
-
Codex CLI 0.165.0
npm install -g @openai/codex@0.165.0View details
New Features
- Added a built-in Google Cloud Vertex AI provider, configured with
model_provider = "gcp". (#56265) - Added GPT-6.1 Terra to the model catalogs. (#57337)
- Added a repository filter to the session picker and directory grouping to the agent command center, making it easier to navigate sessions across linked worktrees. (#56308)
- Added experimental attached thread forks to the app-server API. (#56351)
- Enabled reasoning effort changes during a conversation by default for supported models. (#56163)
- Enabled memory v2 by default for fresh profiles and added support for importing external-agent memories into it. (#56211, #56414)
Bug Fixes
- Fixed fresh TUI sessions to honor the server’s default approval reviewer when no explicit override is provided. (#56090)
- Kept TUI preferences editable and immediately applicable when execution settings are invalid. (#56091)
- Cancelled remote MCP tool requests when their local response futures are dropped. (#56132)
- Prevented queued agent messages from restarting work after an interrupt or a switch to Plan mode. (#56330)
- Stopped retrying when a provider reports that a model was not found, preserving its error message. (#56445)
- Closed a marketplace URL validation gap that could allow Git to connect to a different host than the one checked against allowed patterns. (#56263)
Changelog
Full Changelog: rust-v0.164.0...rust-v0.165.0
- #56081 Cache decrypted Codex auth and managed secrets @celia-oai
- #56090 Honor server approval reviewer defaults on fresh TUI startup @etraut-openai
- #56091 Keep TUI preferences editable when execution settings are invalid @etraut-openai
- #56097 Prepare TUI startup to accept multiple backend sessions @bc-openai
- #56124 Forward Guardian reviewer events to parent raw-event subscribers @jif-oai
- #56127 Avoid blocking EMA auth status checks on account refresh @jif-oai
- #56132 Cancel MCP tool requests when response futures are dropped @rhan-oai
- #56133 Defer agent mail after empty final answers @eknight-oai
- #56139 Fix the MCP auth status test's IdP OAuth configuration @jif-oai
- #56153 Preserve safe enterprise MCP authentication error details @jif-oai
- #56154 Add managed network review domains before allow rules @olliem-oai
- #56163 Enable reasoning effort overrides by default @felixxia-oai
- #56182 Add AWS SigV4 signing to network proxy MITM hooks @viyatb-oai
- #56210 Stabilize the marketplace staging cleanup test @felixxia-oai
- #56211 Default fresh memory profiles to v2 @jif-oai
- #56214 Remove the
u64cast from WSL DrvFS detection @felixxia-oai - #56220 Use cargo_bin in the Windows sandbox manifest test @felixxia-oai
- #56222 Consolidate Bazel CI setup into
prepare-bazel-ci@anp-oai - #56224 Reuse current model context across paginated resume config loading @charliemarsh-oai
- #56233 Make Opus encoder test timestamps follow sample time @goodman-oai
- #56234 Emit prompt telemetry only after hooks accept input @abhinav-oai
- #56236 Make the code mode yield/resume test yield explicitly between phases @goodman-oai
- #56246 Bump Bazelisk to 1.30.0 in the Bazel CI setup action @anp-oai
- #56247 Consolidate Rust unit tests under dedicated test modules @dkovalenko-oai
- #56248 Bump uv to 0.13.5 in CI and release workflows @anp-oai
- #56250 Avoid redundant settings checkpoints when resuming threads @owenlin0
- #56261 Isolate V8 source dependencies and their C++ runtime settings @seanh-oai
- #56263 Reject backslashes in HTTP(S) marketplace URL userinfo @willwang-openai
- #56265 Add a built-in Google Cloud Vertex AI provider @celia-oai
- #56266 Preserve MCP disable reasons across runtime overlays @mzeng-openai
- #56272 Upgrade Python SDK model generation to datamodel-code-generator 0.64.0 @anp-oai
- #56274 Wait for cloud config refresh cancellation in loader lifetime tests @goodman-oai
- #56277 Support bounded request bodies in AWS SigV4 signing @viyatb-oai
- #56278 Add negotiated network policy metadata support for MCP calls @viyatb-oai
- #56280 Group consecutive transcript prompts into one background block @bc-openai
- #56284 Scope model catalogs and caches by thread originator @kennyyi-oai
- #56286 Bump
@modelcontextprotocol/sdkto1.32.0@anp-oai - #56288 Pin Linux artifact signing to Cosign v3.1.4 @anp-oai
- #56290 Lock Python release build tools with uv @anp-oai
- #56292 Fix MCP cancellation tests to use the metadata callback @anp-oai
- #56293 Use fixed-token auth fixtures in Vertex tests @anp-oai
- #56295 Decouple managed configuration loading from ChatGPT authentication @smurching-oai
- #56297 Mark built-in dummy credentials and strengthen collision checks @viyatb-oai
- #56301 Add TLS forwarding tests for MITM SigV4 requests @viyatb-oai
- #56302 Add hook configuration to environment attachments @andrewgu-oai
- #56304 Add support for environment-scoped managed hooks @andrewgu-oai
- #56308 Separate directory and repository scopes in the TUI @bc-openai
- #56309 Support model-specific writable-root permission wording @goodman-oai
- #56312 Track accepted conversation history in rollout traces @cassirer-openai
- #56313 Apply model catalog overrides to history, notes, and context tools @rhan-oai
- #56314 Add managed configuration loaders for custom config servers @smurching-oai
- #56330 Make agent-message wakes respect interrupts and Plan mode @alishobeiri-oai
- #56342 Match rollout trace image content across request snapshots @cassirer-openai
- #56343 Run environment hooks on their owning executors @andrewgu-oai
- #56351 Add experimental attached thread forks @btraut-openai
- #56364 Allow callers to set the thread source for sampling @keyz
- #56371 Make the Guardian review timeout configurable @vivi
- #56414 Support memory v2 in external-agent memory imports @jif-oai
- #56439 Update
ctutilsfrom 0.4.2 to 0.4.5 @felixxia-oai - #56445 Treat model-not-found provider errors as terminal failures @charliemarsh-oai
- #56453 Make the Realtime V2 background-agent steering test deterministic @felixxia-oai
- #56454 Make sandbox mount cleanup tests tolerate file descriptor reuse @felixxia-oai
- #56459 Add Guardian V3 feature configuration @felixxia-oai
- #56460 Add Guardian v3 local board helpers @felixxia-oai
- #56461 Add silent append support to message boards @felixxia-oai
- #56462 Prevent memory imports from racing with consolidation @jif-oai
- #56465 Add experimental thread memory summary reads @jif-oai
- #57337 [0.165.0-alpha.1.2] Backport GPT-6.1 Terra to the model catalogs @shijie-oai
- Added a built-in Google Cloud Vertex AI provider, configured with
-
GPT-6.1 Terra in Work and Codex
GPT-6.1 Terra is now available in ChatGPT Work and Codex on Plus, Pro, Business, Enterprise, and Edu plans. It’s a fast, efficient model for professional work that combines strong image understanding with precise computer use.
Reason about images and screens, then act on what you find across your browser, desktop, and apps. Terra also provides clear, direct writing that puts results first and explains supporting details in plain language.
Choose GPT-6.1 Terra from the model list in Advanced in the ChatGPT desktop app or ChatGPT Work on the web. Work also supports Terra on mobile. The model isn’t available in Chat and does not support UAE inference residency. Enterprise access depends on workspace availability and administrator controls.
See Models for guidance and browser use and computer use for tool setup and access requirements.
-
Codex CLI 0.164.0
npm install -g @openai/codex@0.164.0View details
New Features
- Save reusable prompts and slash commands in ten numbered
/presetsslots, with a keyboard menu for quick access. (#54380, #54381) - Set model, reasoning effort, speed, and permission profiles directly with inline
/modeland/permissionsarguments. (#54378, #54383) - Preview viewed and generated images in the fullscreen transcript on terminals supporting Kitty or Sixel graphics. (#54216)
- Authenticate enterprise MCP connections using eligible Codex account grants or dedicated sign-in, including OAuth clients requiring secrets. (#55334, #55859, #56001)
- Mask credentials during supported remote Bash commands and Zsh snapshot sessions, including credentials from custom providers. (#54309, #54432, #56049)
- The Amazon Bedrock setup wizard is now enabled by default, with API key entry grouped alongside other AWS sign-in methods when credentials are detected. (#56033, #56023)
Bug Fixes
- Failed compaction no longer leaves partial summaries in conversation history, and background compaction failures fall back without panicking. (#53932, #55581)
- Resuming sessions now finds compressed histories and restores saved thread settings instead of replacing them with global defaults. (#54008, #55923)
- Windows HTTPS and WebSocket connections now handle proxy authentication challenges using the signed-in user’s Negotiate or NTLM credentials. (#55994, #56000)
- CLI configuration overrides are preserved when
-cor--configappears at multiple subcommand levels. (#56022) - Queued prompts now wait for pending permission selections to resolve before continuing. (#55682)
- Hardened sandbox checks for case-variant metadata paths on macOS and replaceable symlinks used to locate executables. (#54273, #55384)
Chores
- Reduced disk usage by pruning unused installations, cleaning abandoned marketplace checkouts, and bounding daemon logs. (#53827, #55149, #55689, #55690, #55856)
- Updated the embedded JavaScript runtime with safety checks for optimized
Array.sortoperations. (#54519)
Changelog
Full Changelog: rust-v0.163.0...rust-v0.164.0
- #53725 Render Markdown web links as labels in Rex @bc-openai
- #53728 Preserve the remote cwd filter in the in-app resume picker @fcoury-oai
- #53732 Reuse compiled search patterns across compressed rollouts @ethernetdan-openai
- #53733 Default Guardian v2 async classification to conversation mode @felixxia-oai
- #53736 Acquire and cache opt-in executor capability inventories via V2 @TAFOYA-OAI
- #53745 Remove
modelSlugfrom the latest-model resolver output @kkahadze-oai - #53747 Prefer remote Visualize installs over the bundled plugin @philipp-oai
- #53751 Apply feature overrides when restarting the app-server daemon @jif-oai
- #53753 Extend copy-on-select to composer text @fcoury-oai
- #53754 Support Command/Super shortcuts in the TUI keymap @fcoury-oai
- #53763 Enrich V2 capability discovery with resolved plugin and skill metadata @TAFOYA-OAI
- #53780 Remove redundant Codex manual cache directory check @kkahadze-oai
- #53781 Remove the product-gating TODO from
SkillPolicy@kkahadze-oai - #53784 Forward client voice session IDs in realtime requests @chrisdong-oai
- #53790 Fix cancellation of macOS user-verification prompts @bz-openai
- #53794 Retain rollout migration locks across worker cancellation @jif-oai
- #53795 Use the bundled model catalog in the MCP startup invalidation test @OLI-OAI
- #53797 Refresh Guardian reviews when review context changes @jif-oai
- #53800 Wire background compaction into the turn lifecycle @rka-oai
- #53804 Keep the Agent command center visible during archive and delete @etraut-openai
- #53805 Add safe diagnostics to workspace routing configuration errors @etraut-openai
- #53811 Support daemon installation from Windows WinGet packages @etraut-openai
- #53816 Reject Guardian review threads during interactive CLI resume @dylan-hurd-oai
- #53827 Prune unused app-server daemon releases safely @etraut-openai
- #53831 Track content provenance through prompt assembly and compaction @tz-openai
- #53845 Fix daemon updater socket binding and bootstrap readiness on Unix @etraut-openai
- #53853 Reuse staged file digests when preparing daemon installs @charliemarsh-oai
- #53859 Record bucketed terminal sizes in TUI telemetry @imac-oai
- #53872 Refresh model instructions in incremental-tool context windows @rhan-oai
- #53879 Preserve running turn recovery across thread settings updates @bc-openai
- #53895 Resume unloaded subagent threads when selected in the TUI @etraut-openai
- #53897 Isolate daemon package tests to reduce disk contention @etraut-openai
- #53908 Keep the agent dashboard browsable during task removal @etraut-openai
- #53932 Preserve conversation history when compaction fails @jif-oai
- #53940 Bound rollout input for memory extraction @jif-oai
- #53947 Stop rollout reads when the calling task is cancelled @jif-oai
- #53963 Test memory extraction budgets with excluded items and ciphertext @jif-oai
- #53969 Avoid reconnect races in the daemon restart test @jif-oai
- #53987 Skip service backoff for stale Guardian authorization retries @jif-oai
- #53990 Keep host MCP and plugin configuration local with remote environments @jif-oai
- #53991 Report the reason for ChatGPT token refresh requests @tejsudha-openai
- #53996 Bump
rustlsto0.23.46@jif-oai - #53997 Filter rollout filenames before checking compressed siblings @bbrown-oai
- #54003 Include compressed rollouts in doctor storage statistics @jif-oai
- #54008 Fix session lookup and resume after rollout compression @jif-oai
- #54027 Preserve Windows startup variables and MXC child environment defaults @iceweasel-oai
- #54032 Bound concurrent Git diffs for untracked files @yuzhu-oai
- #54033 Extend memory extension resource retention to 14 days @josh-oai
- #54039 Return async Guardian approvals before review cleanup finishes @jif-oai
- #54044 Keep fork lineage ahead of paginated transcript history @fcoury-oai
- #54046 Track approval cancellation sources and Guardian context changes @vkg-oai
- #54047 Restore elapsed time for replayed in-progress turns @etraut-openai
- #54048 Defer folder trust checks until starting a task from agents overview @etraut-openai
- #54050 Scope TUI skill refreshes and workspace commands to explicit directories @etraut-openai
- #54053 Add Responses API client metadata patches for turn start and steer @marksteinbrick-oai
- #54056 Coalesce overlapping native TLS root certificate loads @jif-oai
- #54057 Distinguish unsupported evidence in Decisions comparison metrics @swastik-oai
- #54058 Forward turn metadata to image generation and edit requests @duc-openai
- #54059 Support store-owned preparation when resuming threads @owenlin0
- #54060 Limit unarchive scans to the requested thread's archived rollouts @bz-openai
- #54069 Fix Windows environment handling for remote MCP servers @iceweasel-oai
- #54070 Expose gateway authentication as a reusable OAuth session API @smurching-oai
- #54076 Avoid false URL-launch detections in literal PowerShell commands @jif-oai
- #54078 Update
gixto 0.89.0 andgix-urlto 0.40.0 @jif-oai - #54079 Retire rejected MCP OAuth refresh tokens @mzeng-openai
- #54080 Extract TUI user-turn submission into a dedicated module @bc-openai
- #54081 Centralize vertical navigation in TUI list views @bc-openai
- #54082 Stabilize the Guardian network review timeout test @felixxia-oai
- #54087 Upgrade Bazel's
rules_pythonto 2.4.2 @dkovalenko-oai - #54094 Preserve specific MCP failure codes in metrics and spans @TAFOYA-OAI
- #54096 Add Bazel targets for on-demand schemas and Python SDK generation @dkovalenko-oai
- #54097 Show Daybreak notices after the session header @charliemarsh-oai
- #54098 Keep environment tools stable across readiness changes @aibrahim-oai
- #54099 Wait for readiness in the SIGTERM cancellation test @felixxia-oai
- #54113 Embed generated app-server schema bundles in Bazel builds @dkovalenko-oai
- #54114 Report terminal completion states and blocking reasons @cconger
- #54119 Allow stdin review under active grants with sandbox prompts disabled @tepman-oai
- #54133 Record per-tool incremental update and description size metrics @akira-oai
- #54135 Allow large file writes over direct exec-server WebSockets @ostepanian
- #54151 Generate keymap descriptors and binding accessors from one catalog @bc-openai
- #54169 Reload the model catalog after account changes @smurching-oai
- #54170 Preserve ChatGPT authentication for Gov MCP servers @lsingh-oai
- #54175 Retire worktree and voice feature flags @bc-openai
- #54216 Show image previews in the fullscreen transcript @etraut-openai
- #54217 Apply syntax theme colors to Markdown prose in the TUI @etraut-openai
- #54250 Add regression tests for case-variant metadata protection @jif-oai
- #54257 Preserve recent speech when trimming realtime transcripts @jif-oai
- #54263 Require fresh Guardian approval for escalated tool retries @jif-oai
- #54264 Track Guardian transcript admission across failed reviews @jif-oai
- #54265 Add regression coverage for Guardian sandbox retry approvals @jif-oai
- #54273 Protect metadata writes through macOS case aliases @jif-oai
- #54278 Share Guardian image deduplication and checkpoint restoration @felixxia-oai
- #54281 Attribute compaction summaries to the assistant in Guardian transcripts @jif-oai
- #54309 Enable credential masking for remote exec-server commands @viyatb-oai
- #54315 Keep TUI Markdown colors readable against their backgrounds @fcoury-oai
- #54316 Centralize context fragment kind constants @ioanbudea-OAI
- #54346 Add scoped executor credential auth for remote exec-server @viyatb-oai
- #54351 Use the turn index for turn-scoped item pagination @bz-openai
- #54363 Filter uninspectable network roots from implicit MXC read grants @iceweasel-oai
- #54365 Prevent duplicate assistant messages around interleaved commands @fcoury-oai
- #54369 Retry SQLite operations on transient writer contention @willwang-openai
- #54378 Support inline model, reasoning, and speed selection in
/model@fcoury-oai - #54379 Add configuration support for TUI input presets @fcoury-oai
- #54380 Add
/presetsfor reusable prompts and slash commands @fcoury-oai - #54381 Add a keyboard shortcut menu for presets @fcoury-oai
- #54383 Support inline permission profile selection with
/permissions@fcoury-oai - #54385 Allow saving current permission settings as presets @fcoury-oai
- #54387 Add session-only arguments to
/titleand/statusline@fcoury-oai - #54388 Add quick dial presets for terminal title and status line layouts @fcoury-oai
- #54389 Preserve existing SQLite journal modes on startup @dkovalenko-oai
- #54398 Store generated image items as attachment references @kchainani-oai
- #54401 Run managed daemon processes at background priority on macOS @bc-openai
- #54414 Allow root turn suspension with live descendants @miz-openai
- #54417 Skip SQLite page reclamation on Linux NFS mounts @dkovalenko-oai
- #54419 Support line breaks in Mermaid flowchart node labels @etraut-openai
- #54420 Record local image inputs on completed image-generation items @mjkaufer-openai
- #54421 Treat explicit connections to the verified default daemon as local @etraut-openai
- #54424 Add remote plugin metadata to plugin configuration @mzeng-openai
- #54432 Support remote credential masking with Zsh shell snapshots @viyatb-oai
- #54433 Use neutral labels for nonzero exits in compact TUI output @bc-openai
- #54434 Add rotating stdin credentials for remote exec-server @viyatb-oai
- #54445 Remove obsolete protected-path monitoring from the Linux sandbox @viyatb-oai
- #54475 Use a synchronous mutex for remote metadata request tracking @anp-oai
- #54505 Add streaming file replacement to filesystem abstractions @anp-oai
- #54519 Upgrade V8 to 152.2.0 and backport Array.sort safety guards @seanh-oai
- #54589 Preserve evidence message structure in Guardian Decisions requests @swastik-oai
- #54590 Capture sender context for
codex_app.create_threaddeliveries @felixxia-oai - #54619 Bind plugin hook approval to plugin contents @jif-oai
- #54623 Resolve stable releases dynamically for exec-server compatibility tests @felixxia-oai
- #54637 Preserve disconnect reasons in Noise handshake errors @virajrai-oai
- #54639 Stream rollout records during thread history materialization @chess-oai
- #54641 Retry npm release publishing and match macOS verification runners @jif-oai
- #54647 Make remote-control conflict retry tests deterministic @jif-oai
- #54653 Prefer resource-specific scopes during MCP OAuth discovery @zamoshchin-openai
- #54654 Allow dynamic tool calls to execute in parallel @sdcoffey
- #54656 Honor MCP tool-list changes within a turn @jif-oai
- #54664 Distinguish retryable thread-store errors from unknown write outcomes @wiltzius-openai
- #54672 Use shared Bazel CI preparation for lint and V8 jobs @anp-oai
- #54674 Add an opt-in tool for copying files between environments @anp-oai
- #54679 Distinguish MCP approval cancellation reasons @vkg-oai
- #54681 Keep TUI session selections bound to their backend @bc-openai
- #54686 Preserve MCP tool-list metadata in server status @victor-openai
- #54708 Honor home deletion preferences during Windows uninstall @chess-oai
- #54710 Move V8's ICU Bazel rules into the workspace @seanh-oai
- #54716 Keep prereleases in draft until release assets finish uploading @ioanbudea-OAI
- #54724 Preserve prereleased events when creating GitHub prereleases @ioanbudea-OAI
- #54737 Enable BuildBuddy for voice release builds @anp-oai
- #54739 Close arg0 lock files before removing temporary directories @dkovalenko-oai
- #54741 Gate the file-copy extension behind
multi_env_copy_file@anp-oai - #54742 Render slash command prefixes as composer prompt markers @bc-openai
- #54754 Reduce memory overhead in tool JSON schemas @charliemarsh-oai
- #54761 Upgrade
zipto 9.0.0 and update plugin archive extraction @anp-oai - #54763 Stop applying macOS background priority to managed daemons @bc-openai
- #54766 Defer unknown TUI config fields to the shared strict-config policy @etraut-openai
- #54776 Support typed content in contextual prompt fragments @pakrym-oai
- #54930 Add negotiated zstd compression to app-server WebSockets @thorvald-oai
- #54945 Share additional tool declarations across response item clones @charliemarsh-oai
- #54946 Preserve model catalog caches across header credential rotation @hlevy-openai
- #54949 Gate app-server WebSocket compression behind a feature flag @thorvald-oai
- #54961 Allow agent messages to wake idle root sessions behind a feature flag @alishobeiri-oai
- #55144 Add observation-only model request lifecycle hooks @vivi
- #55149 Prune unused standalone releases after successful installation @etraut-openai
- #55226 Bucket admitted Guardian request metrics by input size @ioanbudea-OAI
- #55227 Allow plus signs in metric tags @swastik-oai
- #55234 Record Guardian sampling retries, attempts, and delivery outcomes @ioanbudea-OAI
- #55237 Add Guardian review routing and cached score metrics @ioanbudea-OAI
- #55244 Batch thread history materialization into SQLite @jif-oai
- #55252 Preserve rollout access metadata across compression and restoration @jif-oai
- #55255 Unload idle ephemeral composer prediction threads without delay @jif-oai
- #55261 Share dynamic tool specifications across turn snapshots @charliemarsh-oai
- #55262 Stop memory dual-write when v2 is selected @jif-oai
- #55263 Start dormant MCP servers for hook calls @charliemarsh-oai
- #55265 Avoid cloning the full catalog for model metadata lookups @charliemarsh-oai
- #55270 Honor per-thread unload delays in app-server @jif-oai
- #55274 Stabilize daemon reconnect and Rosetta package startup tests @jif-oai
- #55278 Fall back when macOS rejects high stdio descriptors @chrishayduk-oai
- #55283 Avoid cloning events in the app-server thread listener @charliemarsh-oai
- #55287 Track MCP enterprise auth cancellation across config reloads @jif-oai
- #55288 Recheck EMA request authority at HTTP boundaries @jif-oai
- #55293 Keep only the latest adjacent reasoning effort update in requests @felixxia-oai
- #55296 Encapsulate Responses API proxy authentication @ee-oai
- #55297 Add GitHub Actions OIDC token acquisition to the responses API proxy @ee-oai
- #55298 Add renewable federated auth primitives to the Responses API proxy @ee-oai
- #55299 Refresh rejected proxy credentials and back off failed renewals @ee-oai
- #55300 Add one-shot app-server startup configuration discovery @acrognale-oai
- #55301 Reconcile V2 executor plugins with cloud catalogs @TAFOYA-OAI
- #55302 Stop the closest remote SHA search at zero distance @jif-oai
- #55303 Route skill reads by alias source @TAFOYA-OAI
- #55304 Reject TUI events from a different backend @bc-openai
- #55320 Enable GitHub Actions OIDC authentication in the Responses API proxy @ee-oai
- #55322 Integrate discovery V2 with step-scoped skill catalogs @TAFOYA-OAI
- #55324 Remove thread title generation spinners from the TUI @cconger
- #55327 Add configured thread environment inheritance for subagents @jif-oai
- #55330 Expose skill installations and stabilize package aliases @TAFOYA-OAI
- #55331 Use step environment snapshots for subagent inheritance @jif-oai
- #55334 Enable enterprise-managed authorization for MCP connections @jif-oai
- #55339 Add experimental
thread/samplerequests to the app server @liame-oai - #55342 Consolidate cached and fetched Codex manual handling @kkahadze-oai
- #55347 Add Guardian retry metrics and preserve turn attribution @ioanbudea-OAI
- #55351 Reduce path storage in the file-search index @charliemarsh-oai
- #55355 Remove the long-thread accuracy warning after compaction @asohrabi-oai
- #55357 Prepare skill catalogs before building step tools @TAFOYA-OAI
- #55358 Add a shared cleanup lock guard for local log directories @dkovalenko-oai
- #55365 Import only the continuation of backgrounded Claude sessions @jgrodman-arch
- #55366 Support catalog templates for approved command prefixes @dylan-hurd-oai
- #55368 Enable incremental tools by default for Responses Lite @akira-oai
- #55372 Fix recall of command-line initial prompts in the TUI @joesavona
- #55375 Add configured thread environment inheritance for subagents @jif-oai
- #55378 Migrate the Windows MXC sandbox to
mxc-sdk@johnl-oai - #55379 Handle response body failures in OpenAI docs downloads @kkahadze-oai
- #55380 Preserve thread metadata before rollout files are materialized @jif-oai
- #55381 Manage TUI backend sessions independently @bc-openai
- #55384 Reject replaceable symlinks in pre-sandbox executable lookup @keeley-openai
- #55387 Add support for Academic Researchers plans @etraut-openai
- #55388 Mark
transcript_v2as removed @etraut-openai - #55391 Deduplicate native agent messages in Guardian review context @jif-oai
- #55394 Use thread connections for enterprise MCP status listings @jif-oai
- #55395 Roll back interrupted Guardian reviews to preserve evidence @jif-oai
- #55396 Prefetch sibling rollout paths when reading history pages @bz-openai
- #55397 Record OAuth provenance and login identity for account tokens @jif-oai
- #55398 Add wire types for runtime agent registration @cooper-oai
- #55401 Defer environment disconnect notifications until recovery fails @richardopenai
- #55402 Add ephemeral runtime registration and signed assertions @cooper-oai
- #55406 Trace harness-side Noise handshake failures @alishobeiri-oai
- #55407 Clarify API key login and status messages @fcoury-oai
- #55409 Retry TUI startup after a server shutdown refusal @fcoury-oai
- #55410 Track credential sources separately from auth owners @cooper-oai
- #55411 Render async question prompts as Markdown in the TUI @bc-openai
- #55413 Share runtime authentication across requests and credential refreshes @cooper-oai
- #55441 Add cancellation for experimental thread samples @liame-oai
- #55442 Check daemon feature overrides and prompt for mismatch recovery @etraut-openai
- #55456 Support Windows registry overrides for
requirements.toml@johnl-oai - #55463 Add optional MCP disablement for prediction forks and samples @liame-oai
- #55498 Add correlated diagnostics for Noise relay handshakes @virajrai-oai
- #55524 Make the startup migration contention test deterministic @jif-oai
- #55533 Separate Guardian conversation preparation from execution @swastik-oai
- #55545 Improve diagnostics for compressed rollout read failures @jif-oai
- #55546 Add scoped leases for persisted account OAuth grants @jif-oai
- #55547 Ignore the basic-toml advisory in dependency audits @jif-oai
- #55548 Preserve parent history by default in full agent forks @jif-oai
- #55581 Avoid panics after background compaction fails before a checkpoint @jif-oai
- #55587 Allow callers to control prompt cache keys independently of session IDs @rm-openai
- #55591 Measure Guardian approval blocking time per turn @ioanbudea-OAI
- #55593 Reject unpackaged Windows sandbox provisioning clients @chess-oai
- #55596 Rank
$mentions by recent selection frequency @bc-openai - #55597 Extract shared TUI user prompt helpers from IDE context @bc-openai
- #55607 Propagate authentication header failures before sending requests @cooper-oai
- #55616 Update
rustls-webpkiandwebpki-rootslockfile versions @jif-oai - #55620 Move Linux sandbox unit tests into separate files @bolinfest
- #55623 Refactor Guardian v2 Decisions snapshot comparison @swastik-oai
- #55627 Reserve a sibling rollout candidate slot for the first ancestor @bz-openai
- #55631 Add frozen cloud skill snapshots to the app server @fc-oai
- #55633 Treat code-mode collaboration messages as plaintext @hlevy-openai
- #55635 Enable Decisions comparisons for Guardian V2 conversation mode @swastik-oai
- #55636 Add runtime assertion authentication modes and an auth provider @cooper-oai
- #55644 Make pending injections interrupt agent waits and sleep @jif-oai
- #55645 Fix in-process app-server shutdown with full queues @jif-oai
- #55646 Guard auth persistence and reloads against concurrent login changes @jif-oai
- #55652 Search compressed rollouts concurrently @ethernetdan-openai
- #55653 Track code-mode cell lifecycle and result buffering time @euroelessar
- #55657 Add lifecycle hooks for inter-agent messages @euroelessar
- #55666 Omit reasoning and compaction from Decisions snapshot comparisons @swastik-oai
- #55667 Enable app routing for remote curated Agent Plugins @tsarlandie-oai
- #55677 Upgrade the Rust toolchain to 1.99.1 @dkovalenko-oai
- #55680 Recheck account login ownership for enterprise MCP @jif-oai
- #55682 Fix TUI permission selection and session state handling @etraut-openai
- #55685 Add account credential support to EMA token exchange helpers @jif-oai
- #55689 Clean up failed and abandoned marketplace staging directories @dkovalenko-oai
- #55690 Reclaim aged legacy marketplace staging directories @dkovalenko-oai
- #55691 Refine enterprise MCP auth errors and request authority checks @jif-oai
- #55692 Tag tool registration metrics with effective incremental tools mode @akira-oai
- #55693 Use hermetic dsymutil for macOS Bazel builds @dkovalenko-oai
- #55696 Preserve enterprise MCP authorization across runtime refreshes @jif-oai
- #55698 Reuse Codex account grants for enterprise MCP authentication @jif-oai
- #55701 Enable MCP OAuth refresh coordination by default @mzeng-openai
- #55705 Centralize cloud skill cache state under the catalog lock @TAFOYA-OAI
- #55710 Resolve MCP backend identity from runtime events in rollout traces @cassirer-openai
- #55719 Allow unified exec to fall back when credential masking is unavailable @viyatb-oai
- #55723 Avoid redundant clones when sending app-server notifications @charliemarsh-oai
- #55724 Share prepared MCP tool definitions across sessions @charliemarsh-oai
- #55725 Preserve code cell response metadata in rollout traces @cassirer-openai
- #55733 Box session metadata and compaction payloads in
RolloutItem@charliemarsh-oai - #55804 Add a critical-path utility for exclusive duration attribution @taohong339
- #55846 Measure Guardian review latency once with a monotonic clock @ioanbudea-OAI
- #55847 Bound retained turn analytics and clean up closed threads @jif-oai
- #55848 Pause relay test time while inspecting handshake diagnostics @jif-oai
- #55856 Bound managed app-server and updater stderr logging @jif-oai
- #55859 Fix enterprise MCP credential selection and reauthentication @jif-oai
- #55883 Expand enterprise MCP authorization lifecycle test coverage @jif-oai
- #55913 Skip conversation scoring superseded by newer scores and history @jif-oai
- #55923 Preserve thread model settings across resume and revert @etraut-openai
- #55940 Add local diagnostic ZIP exports to the app server @viktor-oai
- #55946 Bound remote installed-plugin inventory pagination @mzeng-openai
- #55954 Separate retained instruction collection from budget policy @ioanbudea-OAI
- #55957 Refresh cloud plugin and skill catalogs after mid-turn auth changes @TAFOYA-OAI
- #55958 Preserve provider model catalogs when refreshes fail @abhinav-oai
- #55965 Add managed Desktop workspace storage requirements @acrognale-oai
- #55968 Back off failed cloud skill and plugin catalog refreshes @TAFOYA-OAI
- #55969 Drain WebSocket responses on mailbox preemption @jif-oai
- #55970 Extract shared message-board code into
codex-message-board@felixxia-oai - #55971 Add storage namespaces for local message boards @felixxia-oai
- #55973 Allow consumers to select message-board tools @felixxia-oai
- #55975 Add an experimental command to migrate NFS databases to DELETE mode @dkovalenko-oai
- #55978 Route SQLite logs to an explicitly configured
log_dir@dkovalenko-oai - #55987 Refresh remote exec-server credentials after unauthorized responses @apanasenko-oai
- #55991 Avoid double-counting retained reasoning in token usage @dkovalenko-oai
- #55993 Preserve per-execution trace context in code-mode stdio callbacks @bschoepke-openai
- #55994 Add a Windows proxy authentication tunnel helper @efrazer-oai
- #56000 Retry proxy CONNECT challenges with Windows authentication @efrazer-oai
- #56001 Support confidential OAuth clients for enterprise-managed MCP auth @jif-oai
- #56003 Scope MITM credential substitution to trusted origins and placeholders @viyatb-oai
- #56006 Assert shell tool overlap directly in the parallelism test @goodman-oai
- #56007 Pause Tokio time in the reused Guardian session test @goodman-oai
- #56008 Add a critical-path timing recorder for direct tool calls @taohong339
- #56011 Keep rollout trace terminal sessions distinct when process IDs are reused @cassirer-openai
- #56018 Avoid nested CLI startup in the MCP OAuth persistence test @goodman-oai
- #56020 Allow thread sampling after failed or interrupted turns @liame-oai
- #56021 Keep slash command prefixes in editable composer text @bc-openai
- #56022 Preserve config overrides across CLI subcommand boundaries @jmickey-oai
- #56023 Group Bedrock API key entry with other AWS sign-in methods @alexsong-oai
- #56024 Limit decoded HTTP/3 response headers in the TCP tunnel @richardopenai
- #56031 Support client Responses API metadata in
thread/sample@liame-oai - #56032 Fix entrypoint lookup in package debug-symbol smoke tests @dkovalenko-oai
- #56033 Enable the Bedrock setup wizard by default @alexsong-oai
- #56036 Add request-scoped OAuth credentials and session lifecycle APIs @smurching-oai
- #56037 Add a channel-backed cloud app-server client @bc-openai
- #56044 Enable executor cleanup hooks with V2 capability discovery @TAFOYA-OAI
- #56049 Support configured credential providers in remote execution @viyatb-oai
- #56055 Require managed configuration from the configured server @smurching-oai
- Save reusable prompts and slash commands in ten numbered
-
ChatGPT for iOS 1.2026.286
New features
- View and stop background commands from a new pill above the composer on supported remote hosts.
- Mention chats from other connected hosts with
@.
Improvements and bug fixes
- A loading indicator now shows when saved messages are refreshing.
- Activity groups are cleaner, and you can open images inspected by Codex on demand.
- Unanswered questions remain available after a turn finishes and when reopening a chat.
- More reliable replies to questions while another prompt is starting or finishing.
- Autocomplete suggestions appear as each source loads, without waiting for slower sources.
- Usage-limit explanations and reset times now appear directly in the chat.
- Fixed prompts incorrectly appearing to fail after a response timeout.
- Corrected extra diff lines after repeated edits to the same file.
- Images in responses open in the full-screen gallery, and attachment removal targets the correct image.
- The voice button returns after a call ends, so you can start another without reopening the chat.
-
Codex CLI 0.163.0
npm install -g @openai/codex@0.163.0View details
New Features
- Open
/configto search preferences across categories, change supported settings immediately, and see which changes require a restart. (#52990, #53429) - Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls. (#51812, #51835)
- Configure a leader key in
/keymap. The default is Ctrl+X, shortcut hints stay open until you choose or cancel, and voice mute moves toF9. (#52273) - Restart a managed background server from
/daemon. Codex warns about work the restart could interrupt, then reconnects automatically. (#53173) - Codex can run independent read-only tools in parallel, including skill, memory, and conversation-history lookups. (#52245)
- Daybreak is enabled by default for eligible accounts.
codex execcan also select it with an OpenAI API key when the server offers access. (#53701, #53717)
Bug Fixes
- Resuming a saved thread restores its permissions and network approvals, while respecting explicit overrides and current managed policy. (#53150, #53419, #53424)
- The network proxy now checks permission before a DNS lookup, rejects duplicate
Hostheaders, and prevents credential aliases from bypassing inspection hooks. (#51650, #52661, #53506) - Return to an existing side conversation with
/sideafter switching threads. Answers to pending prompts also go back to the thread that asked. (#52184, #53436) - On Windows, Ctrl+V and Shift+Insert paste text as well as images. On WSL, repeated pastes reuse the clipboard reader, and copy attempts time out instead of hanging. (#53224, #52967, #53453)
- Local commands finish promptly when a child keeps an output pipe open. Remote commands preserve late-arriving output so the final poll can still collect it. (#52652, #53331, #53622)
codex execno longer prints the same file diff again after an unrelated command. (#53444)
Documentation
- Updated the bundled OpenAI Docs guidance for migrations to the GPT-6 family, including model-specific reasoning, tool use, and data residency considerations. (#51768)
- Clarified how the Linux sandbox uses bubblewrap for filesystem isolation and seccomp for syscall filtering. (#52610)
Chores
- Codex now uses its standard shell executor and no longer bundles a patched
zsh. Configurations using the retired shell flags receive a migration notice. (#52160, #52213) - Reduced Linux and macOS release package size by stripping symbols from packaged binaries while preserving them in the original build outputs. (#52178)
Changelog
Full Changelog: rust-v0.162.0...rust-v0.163.0
- #51539 Add completion-aware realtime attachment and session-scoped detach @zahan-oai
- #51547 Add a Windows MXC sandbox opt-out @iceweasel-oai
- #51556 Complete dynamic tool lifecycles on cancellation @mikelam-oai
- #51575 Expose package assembly helpers and support gzip DotSlash artifacts @bolinfest
- #51595 Add thread ID exclusions to
thread/list@btraut-openai - #51602 Distinguish thread listing failures from exhausted history @btraut-openai
- #51611 Signal abandonment of unanswered MCP elicitations @nicksteele-oai
- #51627 Stabilize Guardian snapshot prefixes by separating assistant context @jif-oai
- #51642 Fix retained context handling for typed section content @jif-oai
- #51650 Require hostname authorization before proxy DNS lookups @jif-oai
- #51651 Persist Guardian review failures for reports across restarts @jif-oai
- #51652 Record telemetry for AGENTS.md changes made by apply_patch @jif-oai
- #51678 Move Windows sandbox tests into a dedicated integration binary @jif-oai
- #51683 Roll back stale Guardian reviews before reusing reviewer history @olliem-oai
- #51689 Wait for helper completion in HTTP header cancellation tests @jif-oai
- #51690 Add a feature flag for Code Mode tool description ordering @swastik-oai
- #51704 Honor tool-description-first ordering in Code Mode @swastik-oai
- #51710 Fix a discovery race in the external auth refresh test @jgershen-oai
- #51734 Load persisted sender context for Guardian reviews @jif-oai
- #51755 Reuse MCP handler metadata for cache comparisons @owenlin0
- #51761 Reduce tool metadata cloning in the code-mode runtime @akira-oai
- #51768 Expand OpenAI Docs migration guidance to the GPT-6 model family @kkahadze-oai
- #51775 Prevent recursive Tokio tracing in telemetry and SQLite logs @zbarsky-openai
- #51786 Preserve sandbox overrides across execution requests @iceweasel-oai
- #51794 Advertise Ultrafast for GPT-6.1 Sol on Amazon Bedrock @celia-oai
- #51800 Remove duplicate field initializers in extension registry tests @anp-oai
- #51808 Preserve diagnostic reasons for MCP user verification failures @berkdeniz-oai
- #51812 Enable instant interrupts by default @pakrym-oai
- #51819 Migrate the MXC sandbox to the 1.0.0 SDK @iceweasel-oai
- #51822 Avoid sharing violations when repairing Windows runtime ACLs @johnl-oai
- #51823 Share MCP binding tool metadata with prepared calls @owenlin0
- #51828 Add policy-based file contents integrity checks @iceweasel-oai
- #51831 Add MXC sandbox integrity dependency and policy preparation @iceweasel-oai
- #51835 Enable code mode interruption by default @won-openai
- #51840 Add a bubblewrap backend for sandbox integrity checks @iceweasel-oai
- #51841 Add a macOS Seatbelt backend for sandbox integrity @iceweasel-oai
- #51842 Add a sandbox integrity runner with outcome and timing metrics @iceweasel-oai
- #51843 Run sandbox integrity checks before commands and filesystem operations @iceweasel-oai
- #51847 Preserve Cargo package names in Bazel Rust builds @dkovalenko-oai
- #51848 Align Bazel release builds with Cargo and fix platform compatibility @dkovalenko-oai
- #51849 Fix package smoke tests for Cargo and Bazel debug symbols @dkovalenko-oai
- #51850 Add Bazel release staging archives @dkovalenko-oai
- #51855 Add Bazel support to the Codex package build action @dkovalenko-oai
- #51856 Build Bazel release artifacts alongside Cargo artifacts @dkovalenko-oai
- #51857 Add an app-server prompt prefix compatibility test @jif-oai
- #51865 Use readable plugin mentions without suppressing same-name skills @canvrno-oai
- #51866 Preserve line breaks and links in multiline async questions @pash-openai
- #51868 Record tool registration metrics for each sampling request @akira-oai
- #51872 Keep global app-server config independent of the launch directory @etraut-openai
- #51884 Add experimental prediction forks that inherit parent context @liame-oai
- #51890 Add the missing
mxc-sdkUTF-8 resource patch for Bazel @iceweasel-oai - #51892 Preserve tool call completeness when recorded arguments are truncated @ningyi-oai
- #51893 Record metrics for incremental tool updates @akira-oai
- #51895 Report specific reasons for WebSocket continuation failures @pakrym-oai
- #51896 Preserve native errors in Windows sandbox ACL diagnostics @alishobeiri-oai
- #51897 Use a dedicated matcher for network domain policies @rafael-oai
- #51908 Honor the user input setting for asynchronous questions @mandal-OAI
- #51930 Support model-specific function description prefixes @tz-openai
- #51963 Attribute compaction analytics to the correct voice session @reia-oai
- #51974 Log Windows sandbox availability and backend selection @iceweasel-oai
- #52034 Preserve agent state when unloading idle multi-agent v2 children @jif-oai
- #52040 Add regression coverage for cancelled agent reloads @jif-oai
- #52048 Cover instant interruption in steered-input persistence tests @jif-oai
- #52061 Run Guardian conversation classifiers concurrently and preserve action order @felixxia-oai
- #52062 Add scenario coverage for worker context across idle eviction @jif-oai
- #52065 Require assessment text in the Guardian parser @ioanbudea-OAI
- #52081 Fix idle cleanup for disconnected multi-agent v2 children @jif-oai
- #52119 Expose originating tool call metadata in command environments @leo-oai
- #52160 Remove the patched zsh shell execution backend @jif-oai
- #52164 Make environment context date and timezone configurable @surajs-oai
- #52176 Show AWS GovCloud guidance at startup and remember acknowledgment @jackz100
- #52177 Set a User-Agent for package archive downloads @bolinfest
- #52178 Strip symbols from source-built release package binaries @bolinfest
- #52182 Expose a verified sandbox launcher to local MCP servers @bolinfest
- #52183 Add optional descriptions to agent message board channels @jif-oai
- #52184 Preserve side conversations across thread navigation @etraut-openai
- #52193 Enforce managed MXC requirements on Windows @iceweasel-oai
- #52195 Track source attribution for individual context parts @tz-openai
- #52200 Allow plugin toggles while searching and preserve filters on refresh @fcoury-oai
- #52203 Expose Codex lifecycle status in iTerm2 sessions @fcoury-oai
- #52213 Stop bundling patched zsh in Codex packages @jif-oai
- #52215 Enforce application network policy in standalone MCP commands @lsingh-oai
- #52220 Add configurable default plugin activation policy @stevenlee-oai
- #52223 Enforce application network policy for daemon updates @jackz100
- #52225 Fix config rebuild call in the Windows MXC preference test @virajrai-oai
- #52226 Include foreground activity in iTerm2 session status @fcoury-oai
- #52228 Honor API-key feature gates in TUI Daybreak selection @julee-oai
- #52234 Support request IDs in exec-server WebSocket handshakes @mattj-openai
- #52235 Recover gRPC code-mode sessions after missing-session errors @surajs-oai
- #52241 Preserve subagent capabilities independently of forked history @anp-oai
- #52245 Enable parallel execution for read-only tools @zamoshchin-openai
- #52250 Add opt-in Guardian trust for orchestrator connector identities @ankushg
- #52256 Normalize formatting in docs, web assets, and sample scripts @anp-oai
- #52268 Preserve large arguments in executed tool call metadata @ningyi-oai
- #52270 Enable text selection in the fullscreen TUI footer @fcoury-oai
- #52273 Add configurable persistent leader shortcuts to the TUI @fcoury-oai
- #52274 Add structured tracing for Guardian reviews and background scoring @ioanbudea-OAI
- #52277 Preserve UTF-8 byte semantics in network domain matching @rafael-oai
- #52278 Honor custom OTLP metrics exporters when analytics is disabled @jackz100
- #52288 Remove duplicate field initializers from extension registry tests @anp-oai
- #52295 Emit one developer notice per incremental namespace update batch @akira-oai
- #52299 Make Bazel release jobs advisory @anp-oai
- #52302 Add opt-in credential masking for proxied sandboxed sessions @winston-openai
- #52304 Persist remote-control RPC preferences in managed daemon settings @etraut-openai
- #52325 Track history initialization in Responses turn metadata @anp-oai
- #52329 Remove per-content source attribution metadata @anp-oai
- #52330 Clamp wrapped source ranges before remapping terminal hyperlinks @bc-openai
- #52337 Add durable thread read state with revision-checked updates @btraut-openai
- #52350 Expose experimental durable thread read state in the app server @btraut-openai
- #52363 Expand realtime v3 voice support @jacksonmoody-oai
- #52381 Preserve per-session routing for gRPC code mode @cassirer-openai
- #52384 Notify subscribers when thread read state changes @btraut-openai
- #52395 Add experimental app-server thread read-state updates @btraut-openai
- #52418 Avoid an extra blank quote line when pasting text with a trailing newline @bc-openai
- #52535 Add opt-in history prefix preservation for full agent forks @jif-oai
- #52557 Forward clipboard copies to the terminal in Herdr sessions @fcoury-oai
- #52568 Expose message board permissions and structured denials @jif-oai
- #52591 Fix races in remote environment and session replacement tests @jif-oai
- #52608 Upgrade
hyperto 1.11.1 and test connection closure @jif-oai - #52610 Align Linux sandbox names and docs with bubblewrap and seccomp @bolinfest
- #52621 Add template setup for local agent message boards @jif-oai
- #52629 Consolidate local message board storage helpers @jif-oai
- #52635 Skip background workspace routing reads without ChatGPT auth @joesavona
- #52637 Add experimental thread item lookup by ID @btraut-openai
- #52640 Count interrupted goal continuations toward the no-activity limit @etraut-openai
- #52648 Limit daemon feature compatibility checks to explicit CLI overrides @etraut-openai
- #52652 Bound local exec-server output draining after process exit @jif-oai
- #52659 Add an opt-in feature for subagent model context defaults @hlevy-openai
- #52660 Handle completion events in either order in shell snapshot tests @jif-oai
- #52661 Prevent brokered credential aliases from bypassing MITM hooks @viyatb-oai
- #52671 Add retention annotations to submitted tool outputs @won-openai
- #52674 Move the exec-server test fixture into shared test support @anp-oai
- #52676 Refresh persisted capability roots from owner-provided configuration @teddywyly-oai
- #52679 Add timeout-aware exec-server configuration reads @hlevy-openai
- #52681 Reject reserved Serde JSON keys in code mode @cassirer-openai
- #52682 Validate Windows sandbox accounts before password repair @zm-oai
- #52685 Preserve code mode cancellation during output serialization @cassirer-openai
- #52686 Add opt-in retention for turn tool outputs @won-openai
- #52689 Forward per-turn Cyber access programs to Guardian @daneschneider-oai
- #52696 Fix marketplace path matching for Windows junctions @zm-oai
- #52700 Update the exec-server stable compatibility baseline to Codex 0.162.1 @iceweasel-oai
- #52702 Retry bootstrap GETs through the system proxy after request failures @abhinav-oai
- #52707 Migrate the Windows MXC sandbox to split MXC crates @iceweasel-oai
- #52721 Explain session creation failures during server shutdown @etraut-openai
- #52723 Add opt-in gRPC over stdio for the code-mode host @cconger
- #52724 Add observers for initial exec-server connection attempts @aaronl-openai
- #52725 Report terminal program status with OSC 7501 @fcoury-oai
- #52736 Allow model catalogs to override incremental tool notices @akira-oai
- #52742 Add opt-in output token replay for OpenAI requests @pakrym-oai
- #52748 Make code-mode
exit()stop the entire cell @cconger - #52756 Classify voice session failures and record terminal outcomes @bc-openai
- #52778 Make pinned transcript prompts clickable @fcoury-oai
- #52825 Report exec runtime resets before accepting further requests @JenZhao
- #52923 Stabilize the realtime steering timeline test @anp-oai
- #52937 Retain client-marked tool outputs across compaction @won-openai
- #52946 Keep agent command center rows stable across progress updates @fcoury-oai
- #52952 Verify reset notification during code-mode host recovery @etraut-openai
- #52959 Reduce stack usage in async TUI tests @jif-oai
- #52964 Defer owned transcript redraws during raw paste bursts @etraut-openai
- #52967 Reuse and prewarm the WSL clipboard text reader @etraut-openai
- #52968 Keep startup modals protected when terminal input draining times out @etraut-openai
- #52972 Upgrade
rmcpto3.5.1and harden lifecycle tests @alishobeiri-oai - #52990 Add a searchable
/configpreferences panel to the TUI @fcoury-oai - #53049 Add connection-bound reply handles for app-server requests @bc-openai
- #53109 Handle broken pipes gracefully in plugin list output @fcoury-oai
- #53148 Fix startup draft recovery for pending Vim Replace keys @etraut-openai
- #53150 Restore thread-owned permissions on cold resume @etraut-openai
- #53152 Allow selecting and copying TUI turn tips @etraut-openai
- #53153 Show subagent navigation shortcuts in TUI help @etraut-openai
- #53155 Keep remote app-server events deliverable during shutdown @etraut-openai
- #53156 Simplify the custom terminal drawing API @bc-openai
- #53173 Allow restarting managed background servers from the TUI @etraut-openai
- #53201 Keep agents navigation available after a thread is archived @etraut-openai
- #53224 Support Windows clipboard text paste shortcuts in the TUI @etraut-openai
- #53331 Finish remote exec cleanup when output streams remain open @jif-oai
- #53339 Test final polling of remote processes with open output streams @jif-oai
- #53358 Remove selected protocol, apply-patch, MCP, and TUI tests @vb-openai
- #53369 Allow turns when the agent message board is unavailable @jif-oai
- #53382 Ignore the unsafe-libyaml advisory in dependency audits @swastik-oai
- #53389 Use cached login credentials for Guardian decisions @swastik-oai
- #53393 Distinguish Guardian parent-compaction failure reasons @ioanbudea-OAI
- #53400 Add explicit local board connections with fixed runtime access @jif-oai
- #53412 Isolate arg0 helper directories by operating system @jif-oai
- #53419 Restore saved thread permissions during configuration loading @jif-oai
- #53424 Add regression coverage for network grants on cold thread resume @jif-oai
- #53426 Preserve Windows runtime registration failure diagnostics @zm-oai
- #53429 Apply configuration toggles live and improve settings navigation @fcoury-oai
- #53436 Route TUI request replies to their originating connection and thread @bc-openai
- #53438 Stop identifying Apple Terminal from
TERM_SESSION_ID@etraut-openai - #53440 Preserve status line accents on 16-color terminals @etraut-openai
- #53443 Use local MSVC toolchains for native Windows Bazel tests @etraut-openai
- #53444 Suppress repeated turn diffs in
codex exechuman output @fcoury-oai - #53451 Treat incomplete responses as terminal errors @jif-oai
- #53452 Close input admission while a turn finishes recording @etraut-openai
- #53453 Prefer the Windows clipboard and bound copy attempts on WSL @etraut-openai
- #53485 Update
quinn-prototo 0.11.18 @smurching-oai - #53496 Preserve pending Effects toggles across save refreshes @fcoury-oai
- #53506 Reject duplicate Host headers in the network proxy @jfoo-oai
- #53556 Deduplicate TUI modifier handling and terminal color caching @bc-openai
- #53595 Add async compaction feature configuration @rka-oai
- #53606 Prepare compaction helpers for background requests @rka-oai
- #53614 Add infrastructure for speculative remote V2 compaction @rka-oai
- #53617 Allow hiding native tools while retaining the multi-agent V2 runtime @jif-oai
- #53620 Reuse background results for remote V2 compaction @rka-oai
- #53622 Preserve remote exec output until it is collected @jif-oai
- #53628 Record truncation metrics for accepted Guardian review inputs @ioanbudea-OAI
- #53631 Materialize the thread before testing a discovered daemon restart @jif-oai
- #53632 Stabilize write ordering in the shared message board scenario @jif-oai
- #53633 Add an environment API key fallback for Guardian Decisions @swastik-oai
- #53654 Keep spawned children provisional until the spawn result returns @jif-oai
- #53657 Share hook configuration across cloned hook views @jif-oai
- #53660 Extract shared multi-agent v2 thread spawning @jif-oai
- #53668 Improve remote exec-server test startup diagnostics @jif-oai
- #53670 Account for token usage from incomplete responses @jif-oai
- #53672 Keep discovered Apps tools available during startup recovery @jif-oai
- #53673 Publish Rust releases with the GitHub CLI @jif-oai
- #53678 Preserve inherited context in prediction forks @keyz
- #53689 Constrain API-key model access programs to server support @julee-oai
- #53691 Account for replay caches in encrypted compaction budgets @ioanbudea-OAI
- #53693 Add keyboard selection support to the transcript view @fcoury-oai
- #53698 Interrupt and drain canceled classifier responses before socket reuse @felixxia-oai
- #53699 Cancel Guardian V2 classifications that exceed the tool-call lag window @felixxia-oai
- #53701 Enable CLI Daybreak by default and enforce background-turn eligibility @julee-oai
- #53706 Preserve URLs and email addresses during external agent migration @jif-oai
- #53709 Separate MCP sandbox policy from launcher metadata @bolinfest
- #53717 Enable Cyber access programs for API-key sessions by default @julee-oai
- #53723 Wire V2 capability discovery through exec-server RPC @TAFOYA-OAI
Source: Official changelog entry
- Open
-
GPT-5.5 retirement in Codex
Effective October 14, 2026, at noon PDT (19:00 UTC), GPT-5.5 retires from Codex for users signed in with ChatGPT. The OpenAI API and Codex sessions authenticated with an API key aren't affected.
Use GPT-6.1 Sol (
gpt-6.1-sol) when available to your plan and client. Update workspace defaults, saved model settings, managed configurations, custom agents, scheduled tasks, and scripts that still selectgpt-5.5.See GPT-5.5 retirement for plan-specific replacements and workspace model availability for administrator guidance.
Source: Official changelog entry
-
Composer predictions in Codex
Composer predictions adds autocomplete-style suggestions for your next message in the Codex desktop app. After Codex responds, it uses the current conversation to suggest a follow-up prompt in the message box. Press Tab to accept the suggestion as an editable draft, or type your own message. Accepting a prediction doesn't send it for you.
The feature is available in beta to users aged 18 and older with personal ChatGPT Pro plans in supported regions, in local and SSH threads with GPT-6 Astra and GPT-6.1 Sol.
Learn more about composer predictions.
Source: Official changelog entry
-
Codex app 26.1007
Performance improvements and bug fixes
- Fixed queued messages getting stuck on Sending and restored Steer in secondary app windows.
- Improved scrolling and navigation between files in the Changes panel.
- Added clearer recovery guidance when a tool call needs approval but the chat's permissions prevent approval requests, with a link to those permissions when available.
Source: Official changelog entry
-
Codex CLI 0.162.1
npm install -g @openai/codex@0.162.1View details
Bug Fixes
- Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. (#51866)
- Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults. Compatibility checks now apply only to explicit command-line feature overrides. (#52648)
Full Changelog: rust-v0.162.0...rust-v0.162.1
Source: Official changelog entry
-
GPT-6.1 Sol Ultrafast in Codex and ChatGPT Work
Ultrafast mode speeds up token generation with GPT-6.1 Sol in Codex and ChatGPT Work.
Ultrafast is available on Pro $500 and eligible Enterprise and Edu plans. Enterprise access is off by default; workspace owners must enable it. GPT-6.1 Sol Ultrafast supports inference residency in the United States and Europe (EEA + Switzerland).
See Ultrafast mode for plan and workspace requirements, Models for model guidance, and Pricing for usage and credit rates.
Source: Official changelog entry
-
Codex CLI 0.162.0
npm install -g @openai/codex@0.162.0View details
New Features
Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. (#50148)
Pin tasks in the agent Command Center with
pand keep them in a shared Pinned group when supported by the server. (#51500)Navigate and copy transcript blocks with
/copy, use Ctrl+Insert to copy selections, and tune mouse-wheel scrolling withtui.mouse_scroll_speed. (#50434, #50215, #50209)Make URLs clickable in approval headers, questions, MCP prompts, warnings, banners, and verification prompts, including when links wrap across lines. (#51439, #51449, #51450, #51451, #51452, #51458)
Configure live web access and remote compaction capabilities for custom Responses-compatible model providers. (#50459)
Add JavaScript helpers for streaming promise results as they settle, plus opt-in ranked tool search in Code Mode. (#51126, #51209)
Bug Fixes
Respect server model and reasoning-summary defaults for new TUI threads while retaining explicit launch overrides. (#50013, #50811, #50913)
Preserve existing CRLF line endings in
apply_patchupdates without requiring an opt-in. (#51203)Fix Linux sandbox startup with multiple denied files, reject writable sandbox-construction executables, and keep ripgrep configuration from weakening deny-glob masks. (#50059, #51211, #51407, #51527)
Restore ordinary drive-letter file access on Windows 10 and match Windows sandbox temp permissions to the child process environment. (#51511, #51512)
Honor server
Retry-Afteradvice for retryable Responses and WebSocket failures. (#50418, #51440)Fix archive checksum verification when installing through Windows PowerShell with PowerShell 7 module paths present. (#51257)
Chores
Publish a signed PowerShell installer with Windows releases. (#51158)
Keep older stable releases and prereleases from replacing newer stable download targets or installer aliases. (#51186, #51425)
Changelog
Full Changelog: rust-v0.161.0...rust-v0.162.0
#50013 Honor server model defaults when starting fresh TUI threads @etraut-openai
#50018 Use descriptor-safe helpers for executable test fixtures @jif-oai
#50019 Protect the guardian decisions API key from environment forwarding @swastik-oai
#50026 Preserve user restrictions in Guardian handoff context @jif-oai
#50035 Follow MCP tool pagination in legacy protocol mode @jif-oai
#50039 Keep transcript Find results readable after closing the query @fcoury-oai
#50045 Keep transcript Find expansion scoped to the current match @fcoury-oai
#50046 Stabilize Windows voice build cache keys across tool reinstalls @anp-oai
#50050 Keep plugin and skill snapshots scoped to each step @sayan-oai
#50052 Preserve question context in recovered TUI answer drafts @imac-oai
#50054 Check token estimate filtering directly on the tracing subscriber @tamird
#50058 Upgrade Windows bindings to
windows-sys0.61.2 @tamird#50059 Fix Linux sandbox startup with multiple denied files @yuzhu-oai
#50066 Add a bounded Decisions transport for Guardian comparison classification @swastik-oai
#50082 Enable dynamic tool inheritance for fresh V2 subagents @ke-oai
#50083 Add paginated reverse lookup for thread attachments @joeytrasatti-openai
#50087 Preserve queued agent mail across session eviction @jif-oai
#50093 Prevent shared instruction providers from delegating to themselves @bryanashley
#50094 Add attachment owner lookup to the app-server @joeytrasatti-openai
#50099 Add opt-in Decisions comparison for Guardian V2 @swastik-oai
#50105 Consolidate chat composer footer logic in
footer_state@imac-oai#50109 Keep fullscreen prompts bounded and scrollable @imac-oai
#50112 Centralize TUI loading glyphs and frame scheduling @imac-oai
#50113 Add a native gRPC client for cloud thread resume and attach @bc-openai
#50128 Expose the model selected for a running turn's next step @sayan-oai
#50129 Preserve Windows environment variables for remote MCP servers @aidanv-oai
#50131 Add opt-in JSON diagnostics for TCP tunnels @richardopenai
#50140 Use the server permission catalog for TUI permission shortcuts @etraut-openai
#50148 Add managed worktree tools to the TUI @bc-openai
#50166 Upgrade
ageto 0.12.1 and remove the obsolete advisory exception @michaelm-openai#50177 Enable writable file streaming in exec-server @anp-oai
#50183 Add
dotsto issue labeler guidance @etraut-openai#50189 Replace the Figma OAuth exception with Mercado Pago @mzeng-openai
#50199 Restore the account email in
/statusafter account updates @etraut-openai#50200 Report the configured TUI mode in
codex doctor@etraut-openai#50207 Release stable Markdown tables into scrollback during streaming @etraut-openai
#50209 Make transcript mouse scroll speed configurable @etraut-openai
#50215 Support Ctrl+Insert for copying TUI selections @etraut-openai
#50216 Use the shared text editor for command-center task renaming @bc-openai
#50219 Bound tmux option probes to one second @etraut-openai
#50273 Record Guardian V2 Decisions agreement and latency metrics @swastik-oai
#50339 Add end-to-end coverage for MCP sandbox state enforcement @bolinfest
#50345 Keep the subagent picker consistent with thread archive state @etraut-openai
#50348 Back off automatic remote control reconnects with jitter @cooper-oai
#50354 Skip unrelated subtrees during config alias normalization @btraut-openai
#50359 Render ANSI styles in TUI hook system messages @etraut-openai
#50360 Remove initial messages from session configuration events @owenlin0
#50375 Use printable ASCII terminal titles under GNU Screen @imac-oai
#50380 Fix thread unloading after disconnect during MCP startup @yuzhu-oai
#50384 Allow opting into 16 KiB ARM64 code pages for macOS signing @chess-oai
#50389 Honor configured keybindings before transcript navigation @etraut-openai
#50396 Honor pager bindings for transcript page keys @bc-openai
#50402 Consolidate command execution output into
aggregated_output@owenlin0#50416 Clarify Git worktree choices for new and forked conversations @bc-openai
#50418 Honor Retry-After headers in failed Responses events @anp-oai
#50427 Cap persisted command output in paginated history at 64 KiB @owenlin0
#50431 Preserve terminal hyperlinks in agents overview previews @bc-openai
#50433 Allow API-key accounts to use Daybreak in the TUI @etraut-openai
#50434 Add keyboard copy selection to the owned transcript @bc-openai
#50435 Persist additional tool definitions in rollout history @pakrym-oai
#50437 Add a CLI command to uninstall the legacy Windows sandbox @chess-oai
#50441 Support ordered response items in world-state context updates @pakrym-oai
#50442 Preserve native USD amounts in thread usage responses @asohrabi-oai
#50443 Stabilize paused-time code-mode service tests @seanh-oai
#50445 Assert that only direct tool calls emit timing events @seanh-oai
#50446 Bundle rollout attachments into a gzip tar archive @dkovalenko-oai
#50447 Remove the provider capability gate for tool namespaces @pakrym-oai
#50454 Measure rollout persistence size reductions @owenlin0
#50458 Truncate oversized MCP results in paginated thread history @owenlin0
#50459 Add capability overrides for custom model providers @celia-oai
#50462 Populate thread previews from delegated task inputs @bc-openai
#50464 Add the
incremental_toolsfeature flag @pakrym-oai#50465 Retry registry authentication outages and jitter executor reconnects @apanasenko-oai
#50467 Copy transcript selections as literal text while preserving rich HTML @fcoury-oai
#50470 Account for JSON overhead when truncating MCP tool results @owenlin0
#50472 Enable Ultrafast service tiers for Amazon Bedrock Astra models @celia-oai
#50477 Use the app-server default output cap for TUI workspace commands @etraut-openai
#50480 Skip managed config loading for registered Windows sandbox refreshes @zm-oai
#50499 Include installer stderr in daemon update failures @etraut-openai
#50503 Use Enter to accept transcript Find results and Escape to cancel @fcoury-oai
#50504 Center TUI confirmations over their retained backdrop @bc-openai
#50505 Keep Command Center selection adjacent after task removal @bc-openai
#50507 Record Windows sandbox service stop diagnostics @zm-oai
#50510 Require GovCloud guidance acknowledgment after Bedrock setup @jackz100
#50516 Add scenario coverage for remote
/compactcontext preservation @pakrym-oai#50525 Reject unknown TUI keys in strict config validation @etraut-openai
#50531 Persist realtime transcript tails before closure without inference @guinness-oai
#50536 Keep shared MCP types stable in Code Mode exec descriptions @aibrahim-oai
#50540 Send incremental tool catalog updates in Responses Lite @pakrym-oai
#50546 Keep MCP resource helpers available in code mode @aibrahim-oai
#50555 Skip daemon auto-start for Windows-mounted WSL homes @etraut-openai
#50558 Avoid reading the current directory when resolving absolute paths @etraut-openai
#50559 Distinguish daemon release identity from executable contents @etraut-openai
#50562 Keep Code Mode tool discovery guidance stable across catalog changes @aibrahim-oai
#50564 Allow transcript selection and copying while bottom modals are open @etraut-openai
#50687 Keep third-party tools deferred in strict Code Mode Only @aibrahim-oai
#50695 Preserve local Markdown link labels in the TUI @bc-openai
#50700 Let the transport create the Windows remote-control socket directory @etraut-openai
#50720 Decode Windows Terminal's mapped Shift+Enter sequence @bc-openai
#50727 Show model and reasoning effort near the top of task details @etraut-openai
#50741 Keep environment-backed tools exposed across readiness changes @won-openai
#50756 Show unavailable slash commands when searched in side conversations @bc-openai
#50764 Allow
/archivewhile a turn is running @bc-openai#50781 Restrict TUI MCP startup notifications to owned threads @etraut-openai
#50782 Retry Windows daemon release publication on transient file locks @etraut-openai
#50786 Remember Command Center grouping across launches @bc-openai
#50788 Open slash commands from empty drafts in Vim Normal mode @bc-openai
#50802 Fall back to mklink when Windows daemon junction updates are denied @etraut-openai
#50803 Use the managed daemon for eligible remote-control launches @etraut-openai
#50804 Preserve review lifecycle ordering on failure @etraut-openai
#50808 Prune TUI snapshots and consolidate behavior tests @etraut-openai
#50811 Honor server reasoning summary defaults in new TUI threads @etraut-openai
#50913 Use server model defaults for connected TUI fresh starts @etraut-openai
#50940 Recover malformed Windows deny-read ACL state safely @zm-oai
#50962 Gate stable environment tool exposure behind a feature flag @aibrahim-oai
#50964 Track inference tool changes in turn analytics @aibrahim-oai
#50977 Isolate tracing in the strict third-party tool deferral test @alishobeiri-oai
#51061 Gate Guardian continuation tests on classifier request capture @jif-oai
#51063 Honor prior cancellation before starting Codex delegates @jif-oai
#51064 Ignore stale refresh responses in agents overview tests @jif-oai
#51065 Scope Guardian V2 response timing to snapshot sampling @swastik-oai
#51067 Use issuing-step context for Guardian MCP elicitation reviews @jif-oai
#51070 Preserve trusted-tool context in Guardian Decisions requests @swastik-oai
#51117 Install full context in compaction replacement history @pakrym-oai
#51119 Clarify incremental tool namespace updates in Responses Lite @akira-oai
#51126 Add promise settlement streaming helpers to code mode @cconger
#51133 Allow Guardian Decisions to fall back to
OPENAI_API_KEY@swastik-oai#51137 Recover Guardian reviews from parent checkpoints @felixxia-oai
#51139 Force fresh Guardian sessions for parent-checkpoint recovery @felixxia-oai
#51140 Isolate Guardian checkpoint recovery flags per review attempt @felixxia-oai
#51156 Send base instructions as Responses input messages @pakrym-oai
#51157 Enforce required environment skills before model inference @anp-oai
#51158 Sign the PowerShell installer in Windows releases @chess-oai
#51184 Remove obsolete Guardian thread-context enables from tests @felixxia-oai
#51185 Retry transient gRPC code-mode session admission failures @cassirer-openai
#51186 Prevent stable release pointers from moving backward @andrewgu-oai
#51188 Record base instructions in incremental tool history @pakrym-oai
#51191 Clean up Unix app-server control-socket startup lock files @etraut-openai
#51192 Wait for SIGCONT when resuming the TUI @etraut-openai
#51193 Test thread archiving before the first turn @btraut-openai
#51194 Add browser extension request headers to config requirements @jn-openai
#51198 Allow concurrent release builds while serializing publication @andrewgu-oai
#51200 Upgrade Bazel to 9.2.0 and refresh the module lockfile @anp-oai
#51202 Distinguish namespace removals in incremental tool updates @akira-oai
#51203 Make apply_patch preserve line endings unconditionally @charliemarsh-oai
#51206 Record initialization analytics for resumed subagents @peilin-openai
#51207 Gate CLI Daybreak controls and selection behind an opt-in feature @julee-oai
#51209 Add ranked tool discovery to JavaScript code mode @zamoshchin-openai
#51211 Reject sandbox-writable bubblewrap executables from PATH @viyatb-oai
#51215 Measure raw MCP tool catalog sizes in telemetry @owenlin0
#51217 Preserve review targets and scope misalignment continuation metadata @yunhan-wei
#51220 Honor the OTLP metrics temporality preference @daniel-oai
#51221 Separate environment requests from runtime selections @anp-oai
#51223 Remove legacy personality template metadata @rhan-oai
#51230 Make session lookup pagination stable and report listing failures @etraut-openai
#51235 Remove default model labels from TUI model pickers @etraut-openai
#51249 Handle partial answers consistently across agent workflows @rb-oai
#51253 Enforce Fast and Ultra Fast policies independently @dpatel-oai
#51256 Start the Windows sandbox service during registered Core setup @zm-oai
#51257 Fix installer checksum verification under Windows PowerShell @zm-oai
#51260 Handle partial answers in realtime routing and thread search @rb-oai
#51330 Measure total Guardian approval decision duration @jif-oai
#51333 Record the multi-agent version in turn analytics @jif-oai
#51334 Count Guardian denial-limit interruptions in telemetry @jif-oai
#51335 Update collaboration snapshots for full-history fork instructions @jif-oai
#51347 Measure shell snapshot use and wait time per command @jif-oai
#51350 Allow larger shell snapshots when replaying from a file @jif-oai
#51355 Add bounded diagnostics for agent spawn failures @jif-oai
#51378 Keep Guardian v2 WebSocket pools warm with concurrent replenishment @jif-oai
#51391 Make URLs in asynchronous question titles clickable @charliemarsh-oai
#51396 Let late low-risk scores complete pending Guardian reviews @jif-oai
#51400 Prevent later Guardian scores from releasing earlier pending reviews @jif-oai
#51402 Preserve turn attribution across recovery and compaction @eddie-openai
#51407 Protect ripgrep lookup during Linux sandbox construction @viyatb-oai
#51411 Suppress repeated image paste presses in legacy terminals @etraut-openai
#51415 Expose and persist turn lineage across the app server @eddie-openai
#51419 Preserve turn attribution when queued mail wakes durable sleep @eddie-openai
#51420 Finish idle thread unloads after slow shutdown @jif-oai
#51421 Include root turn IDs in host-owned Apps tool calls @eddie-openai
#51422 Accept environment requests at thread and turn settings boundaries @anp-oai
#51425 Skip stable installer alias publishing for prereleases @zsol-openai
#51426 Remove the Bazel JVM override for Windows ARM64 voice builds @anp-oai
#51427 Prevent invalidated wakeups from starting a turn @jif-oai
#51433 Show hook status messages as titles in the hooks browser @abhinav-oai
#51439 Preserve clickable URLs in TUI approval headers @charliemarsh-oai
#51441 Fix core integration tests for updated turn APIs @anp-oai
#51449 Make URLs clickable in TUI user input questions @charliemarsh-oai
#51450 Make URLs clickable in MCP elicitation prompts @charliemarsh-oai
#51451 Make URLs in the TUI warnings viewer clickable @charliemarsh-oai
#51452 Make banner URLs clickable across wrapped lines @charliemarsh-oai
#51457 Preserve status usage hyperlinks when the URL wraps @charliemarsh-oai
#51458 Make URLs clickable in user verification prompts @charliemarsh-oai
#51459 Preserve wrapped help links in Windows sandbox prompts @charliemarsh-oai
#51460 Retry realtime sideband attachment while an existing call activates @bullman-oai
#51463 Record resolved model and reasoning effort in sub-agent activity @sdcoffey
#51465 Add an optional JSON transcript format for Guardian @felixxia-oai
#51466 Keep Guardian transcript records structured through budget recovery @felixxia-oai
#51467 Keep submission logs useful without exposing payloads @chess-oai
#51470 Raise the managed app-server file descriptor limit on Unix @etraut-openai
#51471 Preserve clickable URLs in pending input previews @charliemarsh-oai
#51472 Preserve clickable URLs in TUI selection rows @charliemarsh-oai
#51473 Preserve URL destinations in wrapped hook details @charliemarsh-oai
#51480 Preserve tool declaration mode across resumed context windows @pakrym-oai
#51482 Use PathUri for skill identity and path matching @anp-oai
#51483 Add correlated, credential-free rendezvous connection diagnostics @alexi-openai
#51491 Classify executor capability root ownership independently of parsing @stevenlee-oai
#51492 Remove obsolete fields from persisted turn context @pakrym-oai
#51493 Bind capability roots to environment selections @anp-oai
#51499 Load rollout history on a single blocking worker @charliemarsh-oai
#51500 Add shared task pinning to the agent command center @etraut-openai
#51502 Bound relay connection attempts and handle pongs during blocked writes @alexi-openai
#51503 Expose selected environments to MCP contributors @mtsui-oai
#51510 Preserve live TUI settings when configuration reloads fail @imac-oai
#51511 Fix Windows 10 drive-letter opens for no-follow filesystem operations @zm-oai
#51512 Align Windows sandbox temp permissions with the child environment @zm-oai
#51515 Expose detailed agent tree shutdown failure reports @keitht-openai
#51517 Pass thread persistence intent to attachment uploads @kchainani-oai
#51525 Preserve the CLI MXC preference in executor config reads @zm-oai
#51527 Ignore ripgrep configuration when expanding sandbox deny globs @viyatb-oai
Source: Official changelog entry
-
ChatGPT for iOS 1.2026.272
New features
Page previews now appear inline in responses.
Added support for opening Codex task links directly on iOS.
Improvements and bug fixes
Redesigned the approval picker with clearer permission choices.
Find plugins from a single Plugins entry in the composer’s plus menu.
Faster streaming in long threads, with fewer freezes.
New tasks keep your selected computer while it reconnects or is offline.
Improved worktree support so files and changes match the checkout used on desktop.
Fixed task lists remaining empty after connecting.
Smoother keyboard transitions when starting tasks and swiping back.
Status updates no longer appear as questions that need an answer.
Clearer manual pairing code entry, including support for pasting formatted codes.
Source: Official changelog entry
-
Codex CLI 0.161.0
npm install -g @openai/codex@0.161.0View details
New Features
GPT-6.1 Sol is now the default model in the bundled and Amazon Bedrock catalogs. (#49318, #49339)
Amazon Bedrock supports multi-agent V2 and Ultra reasoning on compatible models; Bedrock Mantle also accepts AWS GovCloud regions. (#49345, #49813)
Sign in to MCP servers from an active terminal session with
/mcp login <name>. (#49290)Choose your microphone, speaker, and microphone input channels for voice conversations, with preferences saved locally. (#49437, #49836)
Daybreak is opt-in through
--enable cli_daybreakorfeatures.cli_daybreak=true;daybreak=truealone is insufficient. By default, controls and indicators are hidden,/daybreakis unavailable, and automatic Cyber routing is omitted—even for saved Daybreak threads. Saved preferences remain intact. Opt-in routing requires eligible ChatGPT sign-in, the OpenAI provider, and advertised model/program support. (#49856, #49858, #49859, #49861, #51207)Select a Cyber access program per turn with
codex exec --cyber-access-programor the TypeScript SDK’scyberAccessProgramoption. The explicit exec override remains available withcli_daybreakdisabled and leaves the saved choice unchanged. (#49939, #51207)
Bug Fixes
Approved filesystem escalation can now grant broader write access while preserving denied reads and network restrictions. Background tasks retain their originating turn’s permissions. (#49353, #49880)
Explicit launch permissions survive terminal reconnects and new sessions, while implicit client settings no longer overwrite server or saved-thread web-search settings. (#49809, #49799)
Elevated Windows terminal sessions can start using an embedded server, and sandboxed PowerShell preserves relative paths beneath protected user profiles. (#49855, #49690)
Enter correctly submits buffered input after paste detection expires, including in Vim insert mode. (#49810)
Thread resume includes the latest committed history. Startup detects recoverable SQLite corruption earlier and preserves damaged databases as backups. (#49599, #49701)
Responses retries and WebSocket-to-HTTP fallback honor server retry guidance, reducing premature failures during overload. (#49441)
Documentation
- Authentication guidance now accounts for keyring storage instead of implying credentials always reside in
auth.json. (#49361)
Chores
- Publishing an older alpha or hotfix no longer moves npm alpha tags backward. (#49704)
Changelog
Full Changelog: rust-v0.160.0...rust-v0.161.0
#49246 Use executable fixture copying in the bundled bwrap test @felixxia-oai
#49257 Allow Guardian cached approvals with incomplete root context @felixxia-oai
#49260 Restrict enterprise MCP auth and fail closed on config refresh @nicksteele-oai
#49261 Preserve Windows sandbox runner launch errors @zm-oai
#49262 Trace turn phases and correlate accepted input with turns @jif-oai
#49266 Remove the remote agent message board client README @jif-oai
#49267 Support remote agent message boards in multi-agent sessions @jif-oai
#49269 Preserve thread overrides and cloud policy validity during config reloads @nicksteele-oai
#49275 Isolate realtime conversation tests from Responses prewarm connections @felixxia-oai
#49276 Enable enterprise MCP sign-in and account-scoped grant cleanup @nicksteele-oai
#49277 Avoid a turn teardown race in the Guardian agent message test @felixxia-oai
#49280 Restrict capability roots to captured turn environments @miz-openai
#49286 Model exec-server session attachment state as an enum @jif-oai
#49290 Add
/mcp login <name>to the TUI @nicksteele-oai#49294 Record Guardian context mode in review and classification telemetry @felixxia-oai
#49295 Simplify configuration fingerprint canonicalization @jif-oai
#49297 Scan the session index backwards for batch thread name lookups @jif-oai
#49300 Compact the inline hidden tag buffer once per chunk @jif-oai
#49305 Batch metadata reads when resolving thread names @jif-oai
#49308 Run piped legacy Windows sandbox processes without a console @etraut-openai
#49312 Notify parent agents when Guardian stops a subagent @jif-oai
#49316 Bump taiki-e/install-action to v2.87.21 in CI setup @jgershen-oai
#49318 Add GPT-6.1 Sol as the default catalog model @andrewgu-oai
#49325 Retry Windows sandbox runner logon once on error 1056 @zm-oai
#49330 Keep remote control reconnect backoff capped during sustained failures @yansenzhou-oai
#49332 Clean up canceled exec-server RPC requests immediately @jif-oai
#49339 Add GPT-6.1 Sol to Bedrock catalogs and make it the default @celia-oai
#49345 Enable multi-agent V2 and Ultra reasoning on Amazon Bedrock @celia-oai
#49353 Allow approved filesystem escalation while preserving denied reads @viyatb-oai
#49357 Continue Markdown blockquotes when pasting multiline text @bc-openai
#49360 Carry shell invocation metadata and report executor PATH directories @anp-oai
#49361 Clarify credential storage wording across authentication UI and docs @celia-oai
#49369 Update Bedrock GPT-6 Sol catalog tests to expect multi-agent V2 @celia-oai
#49384 Track credential storage outcomes and redact sensitive errors @celia-oai
#49388 Fix Windows path inference for opaque URIs with slash prefixes @dkovalenko-oai
#49389 Serialize tests that share Windows sandbox accounts @jgershen-oai
#49392 Add attributed MCP OAuth credential storage telemetry @celia-oai
#49395 Remove randomized greetings from TUI session headers @etraut-openai
#49401 Preserve live tool-call metadata across request windows @ningyi-oai
#49403 Add an experimental flag for bundled tools in login shells @anp-oai
#49406 Support explicit cyber access programs with OpenAI API keys @julee-oai
#49407 Recover exec-server sessions after environment info timeouts @vivi
#49408 Compare tool call metadata in the recorder refresh test @euroelessar
#49411 Bind the app-server time provider to a local variable @euroelessar
#49414 Filter graceful shutdown guard and trigger traces from SQLite logs @dkovalenko-oai
#49415 Truncate input text in protocol debug output @dkovalenko-oai
#49416 Omit payloads from multiline ANSI warnings @dkovalenko-oai
#49424 Infer Windows UNC paths with forward and mixed slashes @dkovalenko-oai
#49425 Prune diagnostic logs periodically by age and database size @dkovalenko-oai
#49426 Enable analytics by default for daemon-launched app servers @bc-openai
#49432 Preserve bootstrap discovery across authentication changes @cooper-oai
#49437 Add local audio device selection to TUI voice settings @bc-openai
#49441 Honor server retry advice across Responses retries and fallback @anp-oai
#49444 Use
memrchrto find newlines in reverse JSONL scans @btraut-openai#49467 Restore executor tool paths after login shell startup @anp-oai
#49472 Use server-authoritative permissions in the TUI @etraut-openai
#49473 Use the rmcp SDK for enterprise-managed token exchanges @nicksteele-oai
#49475 Complete turn abort callbacks before emitting terminal events @euroelessar
#49478 Discover and validate MCP authorization servers before ID-JAG exchange @nicksteele-oai
#49480 Add experimental thread prediction protocol types @keyz
#49489 Add regression coverage for account switches between analytics batches @anp-oai
#49517 Add a fork shortcut to the TUI command center @etraut-openai
#49560 Add an opt-in model catalog to multi-agent context @jif-oai
#49564 Copy selected file paths as plain text in the TUI @fcoury-oai
#49584 Skip host skill discovery for Guardian reviews @jif-oai
#49595 Make the strict network approval test independent of request order @jif-oai
#49598 Persist explicit user goal edits in model history @felixxia-oai
#49599 Return authoritative replay history when resuming a thread @felixxia-oai
#49600 Reuse unchanged history snapshots when resuming threads @felixxia-oai
#49624 Use server authentication for explicit remote session commands @cooper-oai
#49642 Allow managed requirements to disable the Windows MXC sandbox @iceweasel-oai
#49675 Serialize Responses routing fields before large inputs @jbeckwith-oai
#49678 Escape command drafts when recovering question answers @imac-oai
#49683 Add a managed feature gate for in-app voice @vishnu-oai
#49686 Deliver remote message board notifications to active turns @jif-oai
#49689 Export skill invocation events through OpenTelemetry @jif-oai
#49690 Preserve PowerShell relative paths in the elevated Windows sandbox @johnl-oai
#49692 Keep compressed rollout snippet searches on one blocking worker @npancha-openai
#49693 Move thread history projection into one blocking task @charliemarsh-oai
#49694 Batch rollout listing scans on cancellable blocking workers @charliemarsh-oai
#49696 Make exec-server file reads cancellable between chunks @charliemarsh-oai
#49701 Detect SQLite corruption during startup and preserve recovery backups @dkovalenko-oai
#49702 Rename exec-server file handle management identifiers @anp-oai
#49704 Prevent npm alpha dist-tags from moving backward @imac-oai
#49706 Upgrade the argument comment lint toolchain and Dylint @tamird
#49708 Move session index I/O off async runtime threads @charliemarsh-oai
#49710 Classify SQLite corruption using typed error codes @dkovalenko-oai
#49712 Avoid full-string scans in token-budget truncation @jif-oai
#49713 Remove repository-local Codex guidance, skills, and environment config @anp-oai
#49714 Decouple API-key cyber access programs from model discovery @julee-oai
#49715 Add account security setup reminders to the TUI @dennyku
#49778 Define exec-server protocol types for streamed file writes @anp-oai
#49781 Include the environment's MXC backend in MCP sandbox metadata @zm-oai
#49782 Clean up process groups for failed shell snapshot captures @jif-oai
#49783 Preserve background thread requests when forking in the TUI @etraut-openai
#49784 Add a requirements feature gate for the browser annotation API @tepman-oai
#49785 Persist empty paginated threads when naming them @rd-oai
#49786 Clarify V2 spawn model override guidance for context catalogs @jif-oai
#49787 Remove
AGENTS.mdfrom Bazel core test data @andrewgu-oai#49792 Add retained conversation support to Guardian async sampling @felixxia-oai
#49793 Add conversation mode to Guardian v2 async classification @felixxia-oai
#49795 Avoid duplicate sync reviews in Guardian classifier continuations @felixxia-oai
#49796 Deduplicate Guardian retained-context omission notices @felixxia-oai
#49798 Share cached exec-server environment info with Arc @anp-oai
#49799 Preserve server web-search settings in the TUI @etraut-openai
#49800 Allow cleanup of replay-only side conversations with missing threads @bc-openai
#49801 Update the Rust toolchain action for argument-comment linting @andrewgu-oai
#49804 Use platform-specific modifier labels in TUI shortcut hints @bc-openai
#49805 Add capability-gated writable file streams to the exec-server client @anp-oai
#49806 Accept unknown Codex error variants in the app-server protocol @anp-oai
#49807 Enable API-key model discovery by default @andrewgu-oai
#49809 Preserve local launch permissions across TUI sessions and reconnects @etraut-openai
#49810 Flush expired paste bursts before handling Enter @bc-openai
#49811 Handle unsupported
fs/writeBlockrequests in exec-server @anp-oai#49812 Move shadow skill ranking off the turn preparation path @vkg-oai
#49813 Support AWS GovCloud regions for Amazon Bedrock Mantle @alexsong-oai
#49814 Add coordinated shutdown for local agent trees @owenlin0
#49816 Remove browser-open success messages from the TUI @bc-openai
#49817 Add an advisory Bedrock GovCloud requirements check @alexsong-oai
#49818 Use dedicated parameters for sandboxed file opens @anp-oai
#49819 Recover daemon startup and updater re-exec after cwd deletion @etraut-openai
#49822 Box the resume future in the agents overview permissions test @sayan-oai
#49835 Clarify service tier default save errors in the TUI @etraut-openai
#49836 Allow microphone channel selection for voice conversations @bc-openai
#49843 Preserve daemon diagnostics and include updater logs in reports @etraut-openai
#49846 Capture host-supplied extension data for each turn @sayan-oai
#49847 Persist world-state snapshots alongside rendered context @pakrym-oai
#49850 Launch Windows daemon children in a dedicated working directory @etraut-openai
#49852 Improve diagnostics for report attachment failures @dkovalenko-oai
#49855 Use embedded mode for elevated Windows TUI sessions @etraut-openai
#49856 Support Daybreak selection in
codex exec@etraut-openai#49857 Use the model catalog to select TUI cyber refusal guidance @etraut-openai
#49858 Add a persistent
/daybreaktoggle to the TUI @etraut-openai#49859 Honor Daybreak settings in TUI continuations and background tasks @etraut-openai
#49861 Add Daybreak state to the status line and terminal title @etraut-openai
#49867 Update elevated-launch warning snapshot to use
⌃ofor copy @etraut-openai#49874 Point usage and credit links to ChatGPT settings @etraut-openai
#49875 Decouple TUI startup presentation from execution configuration @etraut-openai
#49876 Remove personality plumbing from the TUI @etraut-openai
#49880 Bind permission grants to the originating turn @anp-oai
#49894 Return world-state snapshots and context updates together @pakrym-oai
#49898 Scope extension filesystem access to callback permissions @anp-oai
#49910 Preserve validation errors for invalid TUI keybindings @etraut-openai
#49912 Respect approval policies in temporary structured threads @etraut-openai
#49939 Add per-turn Cyber access program selection to exec and the SDK @mldangelo-oai
#49946 Prevent stale file search results from being labeled with a new query @jif-oai
#49951 Include preceding assistant context in Guardian sender reviews @jif-oai
#49956 Cache the placeholder regex for MCP hook argument expansion @jif-oai
#49959 Test session index thread-name append and removal @jif-oai
#49972 Share byte buffers across exec-server output chunks @jif-oai
#49987 Add renewable EMA HTTP authentication and credential versioning @nicksteele-oai
#49993 Preserve the async Guardian history prefix as retained context changes @felixxia-oai
Source: Official changelog entry
-
Codex CLI 0.160.1
npm install -g @openai/codex@0.160.1View details
Bug Fixes
- Preserve
SYSTEMROOT,TEMP, andTMPwhen launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment.
Changelog
- #51121: Backport Windows remote MCP environment preservation to 0.160.
Source: Official changelog entry
- Preserve
-
Codex CLI 0.160.0
npm install -g @openai/codex@0.160.0View details
New Features
Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)
Bug Fixes
Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)
Documentation
- Clarified how provider credentials use the configured storage backend and how
env_keyidentifies the API-key environment variable. (#49118)
Chores
Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)
Added background reclamation of unused log database space to reduce disk usage. (#49069)
Source: Official changelog entry
September 2026
-
Codex CLI 0.159.3
npm install -g @openai/codex@0.159.3View details
New Features
- Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. (#49744)
Source: Official changelog entry
-
GPT-6.1 Sol in Codex and ChatGPT Work
GPT-6.1 Sol offers near-Astra performance for complex work at a lower cost than Astra. Consider it for repeated, long-running work across code, apps, and documents. Availability depends on your plan, client, and workspace settings.
Use
gpt-6.1-sol. See Models for availability and model selection to compare models.Source: Official changelog entry
-
Codex CLI 0.159.2
npm install -g @openai/codex@0.159.2View details
Bug Fixes
- Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. (#49385)
Source: Official changelog entry
-
Codex CLI 0.159.1
npm install -g @openai/codex@0.159.1View details
New Features
- Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. (#49323, #49342)
Source: Official changelog entry
-
Codex CLI 0.159.0
npm install -g @openai/codex@0.159.0View details
New Features
Opt-in
instant_interruptlets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141)New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)
The warnings viewer dismisses reviewed warnings when closed; press
kto keep one for later. (#48205, #48206)You can scroll the transcript while deciding whether to implement a plan. (#48805)
Native Mermaid rendering supports more flowchart edges, labels, and node groups. (#48814, #48895)
App-server clients can paginate thread history from a specific item. (#48151)
Bug Fixes
Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. (#48138, #48238, #48483, #48491)
Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. (#48548, #48549, #48469)
Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. (#48628, #48828, #48199)
Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. (#48502, #48544)
Approved commands retain explicit filesystem denials, and
.awsdirectories are protected by default under writable roots. (#48155, #48176)Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. (#48565, #48198)
Chores
Removed automatic follow-up prompt suggestions and the
tui.prompt_suggestionssetting. (#48621)Removed the bundled
plugin-creatorskill. (#48604)
Source: Official changelog entry
-
Codex CLI 0.158.0
npm install -g @openai/codex@0.158.0View details
New Features
Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. (#47639, #47896, #48118)
Connect to MCP servers that require pre-registered OAuth client secrets, including through
codex mcp add --oauth-client-secret. (#47891)Secure direct exec-server WebSocket connections with bearer tokens, including connections configured through app-server. (#47601, #47648)
Image generation and editing can explicitly request transparent backgrounds, and edits now accept file-backed conversation images. (#47484, #47956)
Terminal input approval is enabled by default for commands running with elevated permissions; runtime-only grants no longer cause unnecessary reviews. (#47799, #48073)
Bug Fixes
Fixed Windows sandbox failures involving ordinary Windows 10 paths, rejected stored credentials, and large permission policies. (#47672, #47695, #47919)
Fixed Linux sandbox startup with nested writable roots and preserved Git metadata protections across writable roots on Linux and macOS. (#47623, #47974)
macOS patch operations now recognize system path aliases covered by existing permissions, avoiding unnecessary approval prompts. (#47879)
Approval reviews now retry when new user input arrives, so a status question does not automatically abort a pending action. (#47819)
Mermaid flowcharts now render quoted labels and ampersands; unsupported diagrams explain why they fall back to source. (#47572, #47678)
Command completion events now include early output and report process-launch failures to clients. (#47529, #47665)
Source: Official changelog entry
-
Codex CLI 0.157.1
npm install -g @openai/codex@0.157.1View details
The official entry does not provide verified release highlights: its supplied PR index is empty, and the GitHub tag comparison returned 404. See the full GitHub release for details.
Source: Official changelog entry
-
macOS security update 26.924
Security fixes
- Fixed CVE-2026-100754 on macOS in version 26.924.20706, with thanks to Patrick Wardle, Objective-See Foundation.
Source: Official changelog entry
-
Codex CLI 0.157.0
npm install -g @openai/codex@0.157.0View details
New features
- Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models.
- Enabled fullscreen transcripts by default and added Shift-click selection.
- Started eligible background servers automatically and added recovery choices for incompatible settings.
- Added an
fshortcut to fork conversations open in another app while preserving drafts and queued prompts. - Made
/importavailable in remote and local background-server sessions. - Improved terminal rendering of bullets, checkboxes, equations, and optimization notation.
Bug fixes
- Preserved active voice conversations when switching tasks and recovered unsent answers to questions into the composer.
- Respected tmux mouse settings and restored native Terminal.app scrollback over SSH.
- Fixed proxy routing for realtime connections and standalone web search, including redirects.
- Retried transient file-upload failures and raised the upload timeout to five minutes.
- Enforced network restrictions across redirects and ongoing HTTP and WebSocket traffic.
Full changelog: rust-v0.156.0...rust-v0.157.0
Source: Official changelog entry
-
ChatGPT for iOS 1.2026.258
New features
- Redesigned the home screen.
- Added an iPad split view that keeps the task list beside the open task in landscape.
- Added support for browsing changes inside nested Git repositories.
Improvements and bug fixes
- Side chats now retain attachments, selected text, and review comments.
- Fixed blank or incomplete replies when the next queued prompt starts.
- New tasks preserve the selected computer and better recognize project checkouts and worktrees.
- Improved file-link reliability and loading feedback when opening files and new tasks.
- Clarified task-history loading errors and recovery steps.
- Smoothed animations when adding photos from the camera or Photo Library.
- Fixed pairing failures caused by an incorrect device clock or SSH connection issues on Mac and Linux.
Source: Official changelog entry
-
Codex CLI 0.156.1
npm install -g @openai/codex@0.156.1View details
New features
- Added GPT-6 Sol and GPT-6 Luna to the model picker. The rate-limit switch prompt now recommends GPT-6 Luna.
Full changelog: rust-v0.156.0...rust-v0.156.1
Source: Official changelog entry
-
GPT-6 Sol and Luna in Codex and ChatGPT Work
GPT-6 Sol and GPT-6 Luna are rolling out to Codex and ChatGPT Work at lower token prices than their GPT-5.6 predecessors. Use Sol for complex coding and agentic workflows, and Luna for focused, high-volume tasks.
Both models are rolling out to Plus, Pro, Business, Enterprise, and Edu users. Free and Go users can access Luna in the desktop app. Availability depends on rollout and workspace settings; Enterprise administrators must enable the new models. In ChatGPT, the models are available in Work and Codex, but not Chat.
Choose a model in the picker when available. In the CLI, use
/modelor start a task withcodex --model gpt-6-solorcodex --model gpt-6-luna. See Models, Pricing, and Workspace model availability for details.Source: Official changelog entry
-
Codex CLI 0.156.0
npm install -g @openai/codex@0.156.0View details
New features
- Added an optional fullscreen
/tuiexperience with transcript search, mouse selection, and right-click copying. - Enabled voice conversations by default, with an F8 toggle and
/voicesettings picker. - Added the
/usageanalytics dashboard for account usage, token totals, and plugin and skill activity. - Enabled worktree support by default and improved task filtering and worktree creation in the agent command center.
- Added six terminal themes, Mermaid diagrams, display equations, and
/daemonupdates.
Bug fixes
- Preserved streamed answers and plans when turns fail or are interrupted.
- Fixed clipboard forwarding in tmux and SSH, and preserved pasted indentation.
- Restored Plan mode on resume, improved proxy login and MCP credential recovery, and hardened sandbox isolation.
Full changelog: rust-v0.155.0...rust-v0.156.0
Source: Official changelog entry
- Added an optional fullscreen
-
ChatGPT for iOS 1.2026.251
New features
- Create folders directly from the file picker.
- Added support for writing blocks, with draft alternatives and copy actions.
Improvements and bug fixes
- New tasks remember your worktree mode and setup environment for each project.
- Long queued prompts show a compact preview and expand on tap.
- Fixed queued prompts missing or appearing outdated after reopening a task.
- Worktree task cards now open correctly after setup completes.
- Restored the new-task button for projects containing only worktree tasks.
- Improved voice-call reliability during temporary connection interruptions.
- Better alignment of project, environment, and Git controls on iPad.
- Fixed the thinking timer resetting when a new task starts.
Source: Official changelog entry
-
Codex CLI 0.155.1
npm install -g @openai/codex@0.155.1View details
Bug fixes
- New local TUI sessions now leave reasoning summaries disabled by default, fixing request rejection by providers that do not support them. Explicit reasoning-summary settings remain respected.
Full changelog: rust-v0.155.0...rust-v0.155.1
Source: Official changelog entry
-
Codex CLI 0.155.0
npm install -g @openai/codex@0.155.0View details
New features
- Added experimental
/voiceconversations with live transcripts and microphone controls on supported builds, enabled through/experimental. - The TUI now shows live reasoning summaries in the status row and completion timestamps after successful turns.
- Added task hiding, archiving, and deletion in the agents overview, plus worktree ownership details and confirmed deletion of clean managed worktrees.
- Added Touch ID verification for MCP requests in local TUI sessions on supported Macs.
- Added configurable daemon update schedules and
codex app-server daemon update; saved threads and active goals can recover after daemon restarts. - Amazon Bedrock can now obtain AWS credentials from configured commands, with caching, expiration-based refresh, and authentication recovery.
Bug fixes
- Accepted prompts are now saved even when compaction fails before a turn starts.
- Fixed missed tmux resizes, transcript viewport restoration, and stale history appearing after switching threads.
- MCP servers now report expired OAuth credentials accurately and provide reconnect guidance when token refresh fails.
- Automatic approval reviews now preserve complete actions and authorization evidence more reliably, retry transient failures, and distinguish review failures from unsafe-action findings.
- Switching accounts now invalidates remote-control sessions, cached WebSocket state, and model catalogs belonging to the previous identity.
- Blocked Windows-process escapes from restricted WSL sandboxes and hardened brokered shell snapshots against credential exposure.
Chores
- Aligned Python SDK and runtime publishing with stable CLI releases, using matching versions and verifying runtime assets before SDK publication.
Full changelog: rust-v0.154.0...rust-v0.155.0
Source: Official changelog entry
- Added experimental
-
GPT-5.3-Codex-Spark deprecated
GPT-5.3-Codex-Spark was deprecated on September 14, 2026. The research preview is no longer available in the ChatGPT desktop app, Codex CLI, or IDE extension.
Switch to one of the recommended models, and update saved configurations, custom agents, and scripts that select
gpt-5.3-codex-spark.For faster responses with a supported model, see Fast mode.
Source: Official changelog entry
-
GPT-5.5 retires from ChatGPT, ChatGPT Work, and Codex on October 14
On October 14, 2026, GPT-5.5 will retire from ChatGPT, ChatGPT Work, and Codex on all plans, including consumer, Business, Enterprise, and Edu plans. This retirement does not apply to the OpenAI API.
For Codex with ChatGPT sign-in, switch from
gpt-5.5togpt-5.6-sol(GPT-5.6 Sol) before the retirement date.Update workspace defaults, saved model settings, managed configurations, custom agents, scheduled tasks, and scripts that still select
gpt-5.5.See GPT-5.5 retirement and workspace model availability for migration guidance.
Source: Official changelog entry
-
Quick chats with Pets and Appshots on Windows 26.908
Chat while you work
Keep ChatGPT close while you work in other apps. In the ChatGPT desktop app on macOS and Windows, you can now type a quick chat from the floating Pets controls and press Enter to send it. Use
@to add context and$to choose a skill. Select the bell icon to follow progress in your threads, then select a thread to open the full conversation.Choose a companion or show just the controls in Settings > Pets. Press Option+Space on macOS or Windows+Alt+P on Windows to show the controls and focus Quick Chat. Pressing the shortcut again keeps Quick Chat open. You can change Show pet in Settings > Keyboard shortcuts. To hide the controls, select Hide pet in the command menu or Settings > Pets.
On macOS, you can also send an appshot to the floating controls. Keep the main ChatGPT window in the background and choose Automatic for Appshot destination.
Learn more about Pets.
Share an app window on Windows
Appshots are now available in the ChatGPT desktop app on Windows. Press both Alt keys to share the frontmost app window with ChatGPT, then ask a question or describe what you want to do. An appshot includes a screenshot and available text from that window. You can customize the shortcut and choose which chat receives it in settings.
Other improvements and bug fixes
- Open files directly from a conversation's Sources panel, or download files that ChatGPT can't preview.
- Assign a Codex Micro key to Insert text and add your own reusable text to the active prompt without sending it.
- Reset a pet to its default size in settings. Custom pets also stay in place when you refresh their artwork.
- Keep unfinished comments on response text when you switch chats and return.
- ChatGPT dictation now respects your saved Main language preference.
- Keep tab widths and scroll positions more stable as you close browser tabs in full and split views.
Source: Official changelog entry
-
Codex CLI Python SDK 0.154.0
npm install -g @openai/codex@0.154.0View details
Install with
pip install --upgrade openai-codex==0.154.0(Python 3.10 or later). This release includes the matchingopenai-codex-cli-bin==0.154.0runtime.Add
maxandultrareasoning-effort values. #39662Add
ExternalMessageto synchronous and asynchronousrun()andturn()calls. External content can start a turn or join an active regular turn with tool-level authority; it does not grant user authorization. Consumers receive independent event streams. #44086Add
include_turnson resume/fork,turn_service_tierfor one newly started turn, andsourcemetadata. History selection changes the returned response, not model context. Existing defaults are preserved when these options are omitted. #44084Refresh generated protocol models and notifications, and preserve completion events that arrive before a turn-start response. #44032, #44400
Check these migrations when upgrading:
HookMetadatawraps its handler in.root. Replace accesses such ashook.commandwithhook.root.command, checkinghook.root.handler_typebefore reading handler-specific fields.Some previously unknown notifications now have typed payloads. Read named fields instead of
.params; unknown or invalid payloads still useUnknownNotification.Manually constructed or late-joining turn handles receive events from their attachment point. Earlier output is not replayed, so collected results can be partial; attaching after completion can raise
TransportClosedError. Usethread.read(include_turns=True)for saved history. Handles returned directly bythread.turn(...)retain events from when their request is sent.
Custom
codex_binoverrides require CLI 0.151.0 or newer forExternalMessageand the new history/per-turn options.Source: Official changelog entry
-
Codex CLI Cygwin build inputs and matching source for Windows voice
npm install -g @openai/codex@voice-cygwin-108b38cf67cbb731View details
CI-only build tools for native Windows voice releases. These archives are not included in Codex user packages.
cygwin-build-inputs.tar.gz: 103 pinned Cygwin binary packages and the signed package index used by the offline build installer.cygwin-build-sources.tar: all 83 corresponding source package archives at the exact versions named by that index. It includes the upstream source, patches, and build recipes provided in Cygwin's-srcpackages.cygwin-source-map.json: each selected binary package mapped to its source archive and the source size and SHA-512 digest from the pinned index.CYGWIN-SOURCE-NOTICE.txt: source access and licensing notice.
The binary and source archive SHA-256 pins live in
.github/scripts/voice-cygwin-snapshot.jsonin the Codex repository. Cygwin describes the licensing terms at https://cygwin.com/licensing.html. Licenses vary by package; consult the corresponding source and binary package archives for their notices.Source: Official changelog entry
-
Codex CLI 0.154.0
npm install -g @openai/codex@0.154.0View details
New Features
GPT-6-Astra is now available in the model picker and Amazon Bedrock catalogs. (#42879, #42619)
Experimental worktree support lets you create isolated checkouts for new or forked sessions using
--worktreeor/worktree, then browse and resume them. (#42652, #43069, #43120, #43286)Answer questions inline while Codex continues working, using suggested choices or custom text without losing your main draft. (#42891, #42894, #42897)
Windows sessions can now share a background Codex server, with daemon lifecycle commands and managed updates. (#42405, #42392)
Vim editing gains
Rreplace mode with undo and dot-repeat, plus more reliable Escape handling in legacy terminals. (#42194, #42584)Copying responses preserves formatting in rich-text apps, and
/copycan copy status output or individual session fields. (#42847, #43055)
Bug Fixes
Existing sessions pick up newly installed plugin tools and refresh skills and hooks after external plugin upgrades or rollbacks. (#42284, #42593, #42990)
MCP connections coordinate OAuth token refreshes and surface login challenges when refresh fails, without automatically replaying rejected tool calls. (#42413, #42552)
Startup avoids running workspace-controlled helpers before trust is established, and the macOS sandbox blocks terminal input injection. (#42324, #42590)
Remote resume and fork operations preserve saved permissions; fresh sessions and forks respect server model defaults unless explicitly overridden. (#43330, #43177, #43355)
Resuming a conversation open in another app now shows a read-only transcript with a retry option while preserving your draft. (#43253)
Automatic approval reviews better preserve authorization context through compaction and reject approvals invalidated by new user instructions or answers. (#42844, #42852, #43442)
Documentation
- Updated the bundled OpenAI Docs skill with GPT-6-Astra migration, compatibility, and prompting guidance. (#42931)
Chores
- The deprecated
codex mcp-serverentry point is no longer available. (#42993)
Full Changelog: rust-v0.153.0...rust-v0.154.0
Source: Official changelog entry
-
ChatGPT for iOS 1.2026.244
New features
Reference other tasks directly in the composer with
@mentions.Answer live questions while Codex continues working, without losing your draft.
Explore files with Back navigation, recent files, and remembered reading positions.
Choose a starting branch for new worktrees, or include your current local changes.
Worktree setup can now continue in the background on iOS 26, with progress shown in a Live Activity.
Improvements and bug fixes
Voice now respects your selected model and reasoning effort.
Restored missing delegated-task messages and fixed navigation between linked tasks.
Code reviews now complete more reliably, without duplicate activity or stuck running states.
Fixed crashes and stale queued messages when switching from Queue to Steer.
Improved reconnect reliability and preserved device pairing during temporary service outages.
Resolved duplicate plugin skills in composer suggestions.
Source: Official changelog entry
-
Codex CLI 0.153.4
npm install -g @openai/codex@0.153.4View details
Bug fixes
- Fixed Astra’s visibility in the bundled model picker and made it the bundled default when no model is explicitly configured. (#42874)
- Updated Astra’s guidance to use asynchronous questions only when the tool is available in the session. (#42878)
Full changelog: rust-v0.153.3...rust-v0.153.4
GitHub release: rust-v0.153.4
Source: Official changelog entry
-
Codex CLI 0.153.3
npm install -g @openai/codex@0.153.3View details
New features
- Added GPT-6-Astra to the Amazon Bedrock model picker for Mantle and Runtime global/US routes. (#42805)
Bug fixes
- Corrected GPT-6-Astra’s guidance for asynchronous clarification questions to use the supported tool and recognize that it accepts text only. (#42809)
Full changelog: rust-v0.153.2...rust-v0.153.3
GitHub release: rust-v0.153.3
Source: Official changelog entry
-
Codex CLI 0.153.2
npm install -g @openai/codex@0.153.2View details
Bug fixes
- Corrected the GPT-6-Astra Fast tier description to say “2x speed, increased usage” instead of “1.5x.” This changes only the displayed text, not how requests run. (#42632)
Full changelog: rust-v0.153.1...rust-v0.153.2
GitHub release: rust-v0.153.2
Source: Official changelog entry
-
Codex CLI 0.153.1
npm install -g @openai/codex@0.153.1View details
New features
- Added support for configuring GPT-6-Astra through the API without changing the default model or showing it in the model picker. (#42605)
Full changelog: rust-v0.153.0...rust-v0.153.1
GitHub release: rust-v0.153.1
Source: Official changelog entry
-
Codex CLI 0.153.0
npm install -g @openai/codex@0.153.0View details
New features
- Vim mode adds undo with
uand redo with Ctrl+R, preserving complete drafts including pasted content and attachments. (#41941, #42140) - The plugin CLI can list, install, and remove plugins from remote marketplaces. (#42150)
tui.auto_recap = falsedisables automatic recaps while retaining manual/recap. (#42101)- TUI history now includes complete patches, input sent to background terminals, and individual completed commands. (#41893, #42107)
- Plus and Team users receive an earlier warning when less than half their allowance remains in the approximate five-hour window. (#42142)
Bug fixes
- The TUI reconnects after an external app-server disconnect while preserving drafts and transcripts; uncertain or queued submissions pause for review. (#41911, #41916, #41918)
- Full Access skips Guardian review for confirmation-only actions, while User approval skips background Guardian scoring and prewarming; sensitive checks and input requests remain unchanged. (#42147, #42256)
- Guardian history survives compaction, restarts, and user forks, respects rollback, and isolates subagent history. (#41879, #42065)
- Remembered MCP approvals are scoped to the selected app account, and relative MCP executable paths start more reliably on macOS. (#42133, #42117)
- Rollout compression includes shared histories;
codex exec resumehandles compressed rollouts selected by working directory, and forks work with symlinked session roots. (#42039, #42135)
Configuration and API updates
- App-server thread metadata allows nullable
modelandreasoningEffort; structured asynchronous questions userequest_user_input_asyncwhen enabled by the model catalog. (#42151, #42178) tui.disable_paste_burstreplaces the top-level setting, with the old setting retained as fallback. (#41976)- A disabled-by-default
features.context_management.experimental_modeadds token-budget context, history notes, andnew_contextfor eligible Plus/Pro/Pro Lite Codex-backend sessions; API-key, custom-provider, and temporary structured threads are excluded. (#42385)
Full changelog: rust-v0.152.1...rust-v0.153.0
GitHub release: rust-v0.153.0
Source: Official changelog entry
- Vim mode adds undo with
-
ChatGPT for iOS 1.2026.237
New features
- Attachments now work across all connected hosts, including Windows and Linux, and support videos from the Photo Library.
- Press and hold the attachment button to attach recent photos.
- A new Priority view brings running tasks, unread updates, and tasks awaiting your response to the top of the task list.
- Queued prompts now sync with the connected host, remain editable, and send even when the app is in the background.
- Long-running tasks now show their live working time.
- Task menus now include an option to copy the thread ID.
Improvements and bug fixes
- Task list loading and organization are faster and more reliable, with simpler date sections and fewer stalls or disappearing projects.
- Reconnects are more reliable, resolving stuck Send states, missing approvals, and stale task updates.
- Long responses now stream with fewer visual interruptions.
- Side chat messages remain available until you close them, even after the chat can no longer reconnect.
Source: Official changelog entry
-
Codex CLI 0.152.1
npm install -g @openai/codex@0.152.1View details
Bug fixes
- Guardian approval review now honors Node REPL policies provided through model metadata.
Full changelog: rust-v0.152.0...rust-v0.152.1
GitHub release: rust-v0.152.1
Source: Official changelog entry
-
Codex CLI 0.152.0
npm install -g @openai/codex@0.152.0View details
New features
- Vim mode now supports
/and?searches within drafts, highlights matches, and repeats navigation withnandN. (#41586) - Rate-limit banners now provide actions for checking usage, managing credits, resetting limits, and managing plans. (#41742)
- The terminal UI and
codex execnow show credential-refresh progress, including Amazon Bedrock reauthentication. (#41239) - MCP server names can contain
:,@,/, and., supporting package-style names throughout CLI commands and authentication. (#41700) - Individual MCP tools support an
output_token_limitsetting, with consistent truncation across session resumes. (#41421) - App-server clients can configure
thread/shellCommandtimeouts, including deadlines longer than one hour. (#41384)
Bug fixes
- Automatic approval reviews now preserve user instructions, answers, and valid authorizations across history compaction. (#41660, #41846, #41852)
- Resumed threads restore their saved working directory when none is supplied, and client metadata updates preserve filesystem permissions. (#41567, #41464)
- MCP tools remain available through cache refreshes and remote plugin changes; authentication retries use refreshed helper-provided headers. (#41336, #41344, #41396, #41400)
- Opening the model picker refreshes available models without losing the highlighted choice. (#41467)
- Fixed Windows sandbox execution with Microsoft Store PowerShell, subprocess hangs on terminal queries, and cursor-related display corruption in older JediTerm terminals. (#41227, #41436, #41673)
- Cloud task requests now reject untrusted backend URLs and disable redirects to protect saved credentials. (#41403)
Chores
- The planning tool is disabled by default; enable it with
tools.update_plan.enabled = true. (#41744) - Plugin recommendations now begin loading during startup, reducing delays before the first turn. (#41375)
Full changelog: rust-v0.151.0...rust-v0.152.0
GitHub release: rust-v0.152.0
Source: Official changelog entry
- Vim mode now supports
August 2026
-
Codex CLI 0.151.0
npm install -g @openai/codex@0.151.0View details
New features
- Added a configurable grace period for discovering tools from optional MCP servers. (#41199)
- Extensions can now inspect or replace MCP tool results before they reach the model. (#41202)
- Plugin catalogs now combine per-repository configuration and report invalid project marketplaces without hiding valid plugins. (#41208)
Bug fixes
- Preserved restored permission profiles across TUI turns and prevented
/cdfrom weakening sandbox restrictions. (#41192) - Kept tool availability and reasoning effort correct when switching models or falling back to another model. (#41195, #41206)
- Improved remote sandbox enforcement using the executor's actual home directory, operating system, and path conventions. (#41196, #41204, #41207, #41209)
- Preserved structured MCP tool and resource errors in app-server responses. (#41196)
- Counted nested subagent token usage toward root goal budgets. (#41183)
- Prevented stale Guardian classifications from authorizing actions after permission state changes. (#41196)
Chores
- Added telemetry for escalated stdin reviews and remote executor MCP discovery. (#41189, #41205)
- Stabilized Guardian WebSocket and core fixture tests under slow or highly concurrent CI. (#41191, #41194)
Full changelog: rust-v0.150.0...rust-v0.151.0
GitHub release: rust-v0.151.0
Source: Official changelog entry
-
Codex CLI 0.150.1
npm install -g @openai/codex@0.150.1View details
Bug fixes
- Remote compaction now counts retained images toward the token budget by default and trims older images when needed. (#41003)
Full changelog: rust-v0.150.0...rust-v0.150.1
GitHub release: rust-v0.150.1
Source: Official changelog entry
-
ChatGPT for iOS 1.2026.230
New features
- Search for tasks across titles and conversation content on connected hosts.
- Set reasoning effort from a compact gauge in the composer.
- Open a full-screen editor for longer prompts.
- Configure Home Screen shortcuts for ChatGPT, Work, and Codex Remote.
- Add optional comments to selected response annotations.
Improvements
- Long threads load faster by fetching older history as needed.
- Task list layout, ordering, and pinning now match the desktop app.
- Inline visualizations follow the iOS appearance and accent settings.
Source: Official changelog entry
-
Codex CLI 0.150.0
npm install -g @openai/codex@0.150.0View details
New features
- Mention other Codex tasks with
@to read, create, and message tasks from the terminal. (#40308, #40315) - Use
/copyto choose responses, code blocks, and blockquotes to copy. (#39997) - Automatically title unnamed terminal tasks and use
/renamewith suggested titles. (#40492, #40495) - Open clickable Markdown link labels in supported terminals. (#40471)
- Cycle permission modes with keybindings and repeat Vim edits with
.. (#39873, #40521) - Run
Interrupthooks when an active top-level turn is interrupted. (#40511)
Bug fixes
- Untrusted projects no longer load project
AGENTS.mdfiles, and managed deny-read policies persist correctly. (#39837, #40004) - App-server diagnostics redact credentials. (#39993)
- Remote MCP bearer-token lookup, required-server startup, and backward compatibility are more reliable. (#39926, #39952, #39979)
- The elevated Windows sandbox handles Unicode paths correctly. (#39971, #40570)
- Unix shutdown no longer hangs on detached processes, and terminal output is preserved completely. (#40460)
- Conversation compaction and multi-agent workflows now work correctly with Amazon Bedrock. (#39804, #39825)
Full changelog: rust-v0.149.0...rust-v0.150.0
GitHub release: rust-v0.150.0
Source: Official changelog entry
- Mention other Codex tasks with
-
Browser extensions, site tools, and cloud sign-in
- More browsers: Use the ChatGPT browser extension in Microsoft Edge, Brave, Opera, and Vivaldi, as well as Chrome. Set up your browser in Settings > Computer Use in the ChatGPT desktop app. All five support tab mentions and browser control; Opera doesn't support side chat.
- Site tools (WebMCP): In the desktop app's built-in browser, ChatGPT Work and Codex can use tools provided by a website to work with the page. Use GPT-5.6 Sol or GPT-5.6 Terra and update to the latest desktop app. Site tools aren't available with GPT-5.6 Luna or in Enterprise or Edu workspaces.
- Cloud browser sign-in: On eligible plans, ChatGPT Work on the web, iOS, and Android can ask you to sign in to a supported website through the cloud browser. Enter your details in the sign-in flow, not in the chat. Cloud browser sessions stay separate from your local browser. Website sign-in isn't available for Enterprise or Edu workspaces.
Availability depends on rollout and workspace settings. Website-access and action-confirmation requirements still apply.
Source: Official changelog entry
-
Trigger scheduled tasks from Gmail, Slack, and GitHub events
ChatGPT scheduled tasks can now run when supported events occur in Gmail, Slack, or GitHub. Filter Gmail messages by sender or subject, watch selected Slack channels, or respond to pull request activity such as reviews, comments, commit updates, and merges.
Event-triggered tasks are available in ChatGPT on the web and mobile for eligible plans. Connect the relevant app and approve its requested access before creating a task. The ChatGPT Slack app must be a member of each watched channel, and the connected GitHub app must have access to each watched repository.
An event-triggered task can't also use a time-based schedule. When matching events arrive close together, ChatGPT may combine them in one run. Open Scheduled to review pending events or choose Run now.
Learn how to trigger scheduled tasks from app events.
Source: Official changelog entry
-
Codex MCP server command deprecated
The
codex mcp-servercommand is now deprecated. Use the Codex app server instead. To use Codex from Claude Code, use the Codex plugin for Claude Code.Source: Official changelog entry
-
Codex CLI 0.149.1
npm install -g @openai/codex@0.149.1View details
Full changelog: rust-v0.149.0...rust-v0.149.1
GitHub release: rust-v0.149.1
Source: Official changelog entry
-
Codex and ChatGPT updates
New features
- Apple Messages: Use the Apple Messages plugin in ChatGPT Work and Codex on macOS to read, search, draft, and send messages. Sends require approval by default. See the plugin guide.
- Site co-editing: Where available, Site owners can invite active members of the same workspace as editors. Editors can read the live database and publish updates after the owner completes the first publish.
- Editable Site URLs: Where available, owners can change a Site's ChatGPT-hosted address without creating another deployment. The old address redirects to the new one.
- Computer History in Europe: Computer History is now available in the EEA, Switzerland, and the United Kingdom. It remains off by default and requires Memories; managed workspace administrators must enable access first.
- Shared thread snapshots: Share a read-only snapshot of a local Codex thread from the ChatGPT desktop app for macOS. Review snapshots before sharing even though known secret patterns are redacted.
- Unified pinned threads: Pinned chats now stay in sync between the ChatGPT desktop app and iOS.
Source: Official changelog entry
-
Codex CLI 0.149.0
npm install -g @openai/codex@0.149.0View details
New features
- Added an interactive
codex agentsdashboard for finding, starting, opening, renaming, and stopping tasks. - Added
/cd,/pwd, and/cwdworking-directory commands andcodex queuefor messaging existing local or remote sessions. - Expanded Vim editing, strengthened
codex doctordiagnostics, and added SDK support for exact CLI overrides plusmaxandultrareasoning effort.
Bug fixes
- Improved queued-message wakeups and naming, restored permission profiles on resumed or forked threads, and removed duplicate subagent activity.
- Reconnected interrupted Realtime WebRTC sideband sessions, preserved Windows Terminal scrollback, and bounded inactive TUI replay buffers.
Full changelog: rust-v0.148.0...rust-v0.149.0
GitHub release: rust-v0.149.0
Source: Official changelog entry
- Added an interactive
-
GitLab support in Codex cloud (Beta)
GitLab support is available in beta on all ChatGPT plans. Connect a GitLab project to Codex cloud, create an environment, start tasks from issues or merge requests with
@codex, and request one-off or automatic merge request reviews.The integration runs in Codex cloud. A managed workspace administrator can disable the connector. GitLab-triggered activity requires permission to configure the applicable webhook. GitLab Self-Managed and GitLab Dedicated connections require workspace administrator setup, and webhook activity requires GitLab 19.0 or later. Codex cannot complete a review when GitLab omits a collapsed or oversize diff.
Learn more in GitLab integration.
Source: Official changelog entry
-
Computer History
Computer History is an opt-in feature in the ChatGPT desktop app on macOS that turns activity across apps and websites into memories and a timeline that ChatGPT and Codex can use. Choose which apps and websites contribute, pause collection, and review or delete your history at any time.
Computer History is available to ChatGPT Pro, Business, and Enterprise users. Business and Enterprise administrators must enable access before workspace members can turn it on. Initial availability excludes the European Economic Area (EEA), Switzerland, and the United Kingdom.
Source: Official changelog entry
-
Linux desktop preview and agent imports
Install the ChatGPT desktop app on Linux
The ChatGPT desktop app for Linux is available in preview for supported Ubuntu, Debian, and Fedora desktop distributions on x64 and ARM64 processors. Download the
.debor.rpmpackage for your distribution, then sign in to work with projects, local files, and Codex.Import setup and recent work from other agents
The desktop app supports Claude Code, Claude Cowork, and Cursor. Import instructions, settings, skills, plugins, projects, and recent work, then turn on automatic updates in Settings > Import to keep imported work in sync.
Codex CLI can also import supported setup and recent chats from Claude Code and Cursor with
/import.Source: Official changelog entry
-
Introducing Daybreak Blue and Daybreak Red
Daybreak now offers two access tiers for approved defenders: Daybreak Blue and Daybreak Red. Use them to move from security findings to validated fixes in explicitly authorized engagements.
Start with Daybreak Blue for most defensive security work. It provides access to general-purpose models such as GPT-5.6 Sol for vulnerability discovery, secure code review, detection engineering, incident response, malware analysis, and patch validation.
Daybreak Red provides separately approved access to purpose-trained models such as GPT-5.6 Cyber for authorized vulnerability reproduction, exploit validation, penetration testing, red teaming, and complex system analysis.
Access requires approval through Trusted Access for Cyber and applies only to the approved identity, workspace or API organization and project, model, and product surface. Daybreak Red requires separate approval and provisioning; Daybreak Blue access doesn't grant access to Daybreak Red.
Work in an isolated environment, define your engagement scope, use least-privilege permission profiles, and configure Auto-review for eligible actions before they cross the sandbox boundary.
Learn more about Cyber Safety, Codex credit rates, and API token prices.
Source: Official changelog entry
-
Codex CLI 0.146.1
npm install -g @openai/codex@0.146.1View details
Bug fixes
- Apply safer automatic-review defaults for cyber-capable models and explain permission changes in the terminal interface. (#37057)
Full changelog: rust-v0.146.0...rust-v0.146.1
GitHub release: rust-v0.146.1
Source: Official changelog entry
July 2026
-
GPT-5.4 and GPT-5.4 mini retire from Codex on August 31
On August 31, 2026, GPT-5.4 and GPT-5.4 mini will no longer be available in Codex for users signed in with ChatGPT. GPT-5.4 and GPT-5.4 mini will remain available on the OpenAI API and in Codex sessions authenticated with an API key.
Switch to their recommended replacements:
- Replace
gpt-5.4withgpt-5.6-terra(GPT-5.6 Terra). - Replace
gpt-5.4-miniwithgpt-5.6-luna(GPT-5.6 Luna).
Before the cutoff, update workspace defaults, saved model settings, managed configurations, custom agents, and scheduled tasks that use either model.
See Codex models and workspace model availability for details.
Source: Official changelog entry
- Replace
-
Browser upgrades, multi-repository review, and image editing 26.727
The latest ChatGPT desktop app update makes browsing, reviewing code, and editing generated images faster and easier.
Browse and find context faster
- Type in the built-in browser's address bar to revisit pages from your browsing history or search Google when there's no match.
- Manage your browsing history in Settings, and let ChatGPT search that history when a task needs to find a page you visited before.
- Use the Chrome extension to mention open tabs or bring highlighted page text into your side chat.
- Ask questions about any YouTube video in the Chrome extension and get answers in seconds.
- Right-click a webpage and select Ask ChatGPT.
Learn more about the built-in browser and the Chrome extension.
Review changes across repositories
See all repositories in a multi-folder project and the lines changed in each one. Select Review to inspect diffs across those repositories without switching between separate review views.
Refine generated images
Open generated images in an expanded viewer, and switch between Focused view and Canvas view. Add comments across images, choose the ones you want, and send targeted edits without leaving your conversation. Learn more about image generation.
Other improvements and bug fixes
- Added a new Activity view in the sidebar for chats you recently engaged with or that require attention. Select the bell or press Cmd/Ctrl+Opt+U.
- Updated browser settings to show only supported browsers.
- Improved Windows installation reliability when package file paths are long.
- Other performance and bug fixes.
Source: Official changelog entry
-
Sign in with ChatGPT (beta)
Sign in with ChatGPT is beginning to roll out in beta across select plugins and partner sites, starting with Airtable, GitLab, HubSpot, Notion, Supabase, and Vercel.
When you connect a supported plugin from the ChatGPT plugin directory, you can use Sign in with ChatGPT to create or link an account with that service in fewer steps. On participating partner sites, you can also select Sign in with ChatGPT to create or access your account.
This makes it easier to start working with supported tools in ChatGPT and Codex.
When you sign in, the partner receives only your name, email address, and profile picture, if available. You must still review and approve each plugin's requested access as a separate step.
Source: Official changelog entry
-
Codex CLI 0.146.0
npm install -g @openai/codex@0.146.0View details
New features
- Name new sessions with
/newor/clear, pin important threads, and switch between side conversations without closing them. - Support Agent Plugins manifests, workspace plugin publishing, and additional plugin marketplaces for Amazon Bedrock and Claude Code.
- Fork threads with paginated history, including temporary forks that do not appear in thread listings.
- Connect App Server to remote Code Mode hosts over WebSocket.
- Enable standalone web search for compatible custom model providers.
- Discover executor-provided skills and securely read their associated resources, including explicitly selected skills.
Bug fixes
- Honor configured proxies across authentication, plugin downloads, MCP authorization, remote execution, WebSockets, redirects, and LM Studio connections.
- Keep MCP connections and Apps tools current when authentication or configuration changes, reconnecting closed servers without restarting healthy connections.
- Preserve submitted messages, final responses, failed-turn errors, imported timestamps, and approval settings across interruptions, replay, imports, and forks.
- Improve terminal responsiveness and rendering, including nonblocking interrupts, keyboard handling, narrow layouts, hyperlinks, and refreshed mention results.
- Fix Windows navigation keys, reliably terminate sandboxed process trees, and preserve proxy settings during security reviews.
- Retain more available skills under tight context budgets and warn when skill catalogs must be truncated.
Documentation
- Document shared HTTP-client usage, proxy-aware connection pooling, and safe outbound request handling.
- Clarify Windows drive-letter canonicalization for
PathUrivalues.
Chores
- Publish release artifacts, channel metadata, and installer aliases through OpenAI-hosted release infrastructure, with GitHub fallback.
- Sign and notarize bundled macOS helper executables before packaging.
- Reduce App Server serialization overhead and unnecessary request-building allocations.
- Add enterprise-plan recognition and administrator controls for in-app updates.
Full changelog: rust-v0.145.0...rust-v0.146.0
GitHub release: rust-v0.146.0
Source: Official changelog entry
- Name new sessions with
-
ChatGPT for iOS 1.2026.202
Improvements and bug fixes
- Voice conversations now use your selected ChatGPT voice and show usage-limit warnings.
- Improved task reconnection and continuity when returning to the App or unlocking with Face ID.
- Composer autocomplete now matches desktop plugin mentions and includes skills from installed plugins.
- Selected-text references remain available after sending so you can preview them again.
- Improved goal controls with clearer progress when pausing or resuming.
- Inline visualizations now render tables and visual themes more reliably.
- Large workspace diffs are more responsive.
- Fixed restored tasks changing the selected model.
- Prevented the composer from becoming stuck after a prompt started.
- Corrected browser and computer tool labels, icons, and placeholder output.
Source: Official changelog entry
-
ChatGPT Voice and multi-folder projects 26.715
Powered by GPT-Live, ChatGPT Voice lets you talk through work and coordinate tasks in Chat, Work, and Codex in the ChatGPT desktop app.
New features
- Start a new chat or task in voice mode, then ask ChatGPT to start, check, or steer work in other threads.
- On macOS, turn on Screen context to share an appshot of the frontmost window.
- Use Voice with Plus, Pro, Business, Edu, and Enterprise plans in the desktop app and through Remote on iOS.
- Add multiple related folders to a local project, choose a primary folder for new chats, Git operations, and automatic discovery of
AGENTS.md, skills, andconfig.toml, while keeping secondary folders available for file search, reading, and editing.
Get started with ChatGPT Voice and multi-folder local projects.
Source: Official changelog entry
-
Codex CLI 0.145.0
npm install -g @openai/codex@0.145.0New features
- Added paginated thread history with resume, search, persisted names, subagent support, and memories.
- Expanded
/importfor Cursor and Claude Code settings, MCP servers, plugins, sessions, commands, and project memories. - Added experimental Amazon Bedrock login and endpoints, audio input and output, realtime V3, multi-agent V2 controls, and secure clickable terminal visualizations.
Improvements and bug fixes
- Preserved context when editing earlier prompts or retrying safety-buffered turns.
- Improved long-conversation terminal rendering, MCP startup and OAuth handling, Windows execution and sandboxing, macOS code-mode fallback, and safety approvals.
- Updated the bundled OpenAI Docs skill for GPT-5.6 and upgraded packaged ripgrep to 15.2.0.
-
ChatGPT for iOS 1.2026.195
New features
- Added inline Mermaid diagrams, interactive forms in Codex tasks, and restoration of unsent prompts across tasks, hosts, and workspaces.
Improvements and bug fixes
- Improved task lists, composer transitions, goals resume, plan progress, Fast controls, dictation, Remote onboarding, and iPad navigation.
- Fixed duplicate task-list crashes, iOS 18 task actions, spacing, attachment padding, and duplicate transcription indicators.
-
Codex CLI 0.144.6
npm install -g @openai/codex@0.144.6Bug fixes
- Refreshed bundled GPT-5.6 Sol, Terra, and Luna instructions and corrected their context windows to 272,000 tokens.
-
Codex CLI 0.144.5
npm install -g @openai/codex@0.144.5Bug fixes
- Improved dangerous-command detection for more forced
rmforms and made command-rejection reasons clearer.
- Improved dangerous-command detection for more forced
-
Codex CLI 0.144.4
npm install -g @openai/codex@0.144.4Chores
- This patch release contains no user-facing changes.
-
ChatGPT for iOS 1.2026.188
New features
- Added support for inline visualizations in Codex tasks.
Improvements and bug fixes
- Improved creating and managing tasks from conversations, with reliable links to newly created tasks.
- Improved tool activity styling and progress indicators.
- Improved file-opening feedback.
- Improved the composer so controls remain visible above the keyboard for long prompts and larger text sizes.
- Fixed Fast mode selection and restoration for each task.
- Fixed initial prompts ignoring the selected approval preset.
- Fixed autocomplete backgrounds and task rows becoming unresponsive during swipe gestures.
-
Codex CLI 0.144.3
npm install -g @openai/codex@0.144.3Chores
- This version-only release contains no merged pull request changes since
rust-v0.144.2.
- This version-only release contains no merged pull request changes since
-
Codex CLI 0.144.2
npm install -g @openai/codex@0.144.2Bug fixes
- Restored the previous Guardian auto-review policy, request format, and tool behavior after rolling back a prompting regression.
-
Codex joins the ChatGPT desktop app
Codex is now part of the ChatGPT desktop app on macOS and Windows. Existing Codex App users can update as usual and keep their projects, settings, and workflows.
New features
- Edit Markdown and code directly with inline annotations.
- Review GitHub PRs in the sidebar.
- Work across repositories in a single project.
Improvements and bug fixes
- Improved Computer Use with GPT-5.6.
- Improved task activity and plugin management.
- Improved mobile connection reliability.
- Improved video rendering for SSH projects.
-
Codex CLI 0.144.1 and 0.144.0
npm install -g @openai/codex@0.144.1 -
Codex CLI 0.143.0
npm install -g @openai/codex@0.143.0 -
ChatGPT for iOS 1.2026.181
New features
- Create and manage Codex tasks.
- Use richer diff filters.
- Send transcript selections to the composer.
- Preview attachments.
- Open SSH connection shortcuts.
Improvements
- Made usage information clearer.
-
Codex CLI 0.142.5
npm install -g @openai/codex@0.142.5