Primary navigation

Codex changelog

Latest updates to Codex, OpenAI’s coding agent

January 2026 December 2025 November 2025 October 2025 September 2025 August 2025 June 2025 May 2025

January 2026

  • Web search is now enabled by default

    Codex now enables web search for local tasks in the Codex CLI and IDE Extension. By default, Codex uses a web search cache. If you are using --yolo or another full access sandbox setting, web search defaults to live results. Cached mode uses the web search cache, while live mode fetches the most recent data from the web. To disable this behavior or switch modes, use the web_search configuration option:

    • web_search = "cached" (default; serves results from the web search cache)
    • web_search = "live" (fetches the most recent data from the web; same as --search)
    • web_search = "disabled" to remove the tool

    To learn more, check out the configuration documentation.

  • Codex CLI 0.92.0 

    $ npm install -g @openai/codex@0.92.0
    View details

    New Features

    • API v2 threads can now inject dynamic tools at startup and route their calls/responses end-to-end through the server and core tool pipeline. (#9539)
    • Added filtering on the thread list in the app server to make large thread sets easier to browse. (#9897)
    • Introduced a thread/unarchive RPC to restore archived rollouts back into active sessions. (#9843)
    • MCP servers can now define OAuth scopes in config.toml, reducing the need to pass --scopes on each login. (#9647)
    • Multi-agent collaboration is more capable and safer, with an explorer role, better collab event mapping, and max-depth guardrails. (#9817, #9818, #9918, #9899)
    • Cached web_search is now the default client behavior. (#9974)

    Bug Fixes

    • Fixed a TUI deadlock/freeze under high streaming throughput by avoiding blocking sends on the main Tokio thread. (#9951)
    • The web_search tool now handles and displays all action types, and shows in-progress activity instead of appearing stuck. (#9960)
    • Reduced high CPU usage in collaboration flows by eliminating busy-waiting on subagents. (#9776)
    • Fixed codex resume --last --json so prompts parse correctly without conflicting argument errors. (#9475)
    • Windows sandbox logging now handles UTF-8 safely, preventing failures when truncating multibyte content. (#8647)
    • request_user_input is now rejected outside Plan/Pair modes to prevent invalid tool calls. (#9955)

    Documentation

    • Updated the contribution guidelines for clearer onboarding and workflow expectations. (#9933)
    • Refreshed protocol/MCP docs to reflect thread/unarchive and the updated request_user_input question shape. (#9843, #9890)

    Chores

    • Self-update via Homebrew now uses an explicit cask upgrade command to avoid warnings and ambiguity. (#9823)
    • Release packaging now consistently writes the bundle zip to dist/. (#9934)
    • Updated key dependencies in the Rust workspace (including axum, tracing, globset, and tokio-test). (#9880, #9882, #9883, #9884)
    • Aligned feature stage naming with public maturity stages and added clearer warnings for underdevelopment features. (#9929, #9954)

    Changelog

    Full Changelog: rust-v0.91.0...rust-v0.92.0

    Full release on Github

  • Codex CLI 0.91.0

  • Codex CLI 0.90.0 

    $ npm install -g @openai/codex@0.90.0
    View details

    New Features

    • Added a network sandbox proxy with policy enforcement to better control outbound network access. (#8442)
    • Introduced the first phase of connectors support via the app server and MCP integration, including new config/docs updates. (#9667)
    • Shipped collaboration mode as beta in the TUI, with a clearer plan → execute handoff and simplified mode selection (Coding vs Plan). (#9690, #9712, #9802, #9834)
    • Added ephemeral threads and improved collaboration tool provenance metadata for spawned threads. (#9765, #9769)
    • WebSocket connections now support proxy configuration. (#9719)
    • More strict limitation on multi-agents

    Bug Fixes

    • Fixed exec policy parsing for multiline quoted arguments. (#9565)
    • --yolo now skips the git repository check instead of failing outside a repo. (#9590)
    • Improved resume reliability by handling out-of-order events and prompting for the working directory when it differs. (#9512, #9731)
    • Backspace no longer deletes a text element when the cursor is at the element’s left edge. (#9630)
    • Config loading errors are clearer and more actionable across surfaces. (#9746)
    • Default model selection now respects filtered presets to avoid invalid defaults. (#9782)

    Documentation

    • Corrected a typo in the experimental collaboration prompt template. (#9716)
    • Added documentation for the new connectors configuration surface. (#9667)

    Chores

    • Refreshed the bundled model catalog/presets. (#9726)
    • Updated GitHub Actions for Node 24 compatibility. (#9722)

    Changelog

    Full Changelog: rust-v0.89.0...rust-v0.90.0

    Full release on Github

  • Team Config for shared configuration

    Team Config groups the files teams use to standardize Codex across repositories and machines. Use it to share:

    • config.toml defaults
    • rules/ for command controls outside the sandbox
    • skills/ for reusable workflows

    Codex loads these layers from .codex/ folders in the current working directory, parent folders, and the repo root, plus user (~/.codex/) and system (/etc/codex/) locations. Higher-precedence locations override lower-precedence ones.

    Admins can still enforce constraints with requirements.toml, which overrides defaults regardless of location.

    Learn more in Team Config.

  • Custom prompts deprecated

    Custom prompts are now deprecated. Use skills for reusable instructions and workflows instead.

  • Codex CLI 0.89.0 

    $ npm install -g @openai/codex@0.89.0
    View details

    New Features

    • Added a /permissions command with a shorter approval set while keeping /approvals for compatibility. (#9561)
    • Added a /skill UI to enable or disable individual skills. (#9627)
    • Improved slash-command selection by prioritizing exact and prefix matches over fuzzy matches. (#9629)
    • App server now supports thread/read and can filter archived threads in thread/list. (#9569, #9571)
    • App server clients now support layered config.toml resolution and config/read can compute effective config from a given cwd. (#9510)
    • Release artifacts now include a stable URL for the published config schema. (#9572)

    Bug Fixes

    • Prevented tilde expansion from escaping HOME on paths like ~//.... (#9621)
    • TUI turn timing now resets between assistant messages so elapsed time reflects the latest response. (#9599)

    Documentation

    • Updated MCP subcommand docs to match current CLI behavior. (#9622)
    • Refreshed the skills/list protocol README example to match the latest response shape. (#9623)

    Chores

    • Removed the TUI2 experiment and its related config/docs, keeping Codex on the terminal-native UI. (#9640)

    Changelog

    Full Changelog: rust-v0.88.0...rust-v0.89.0

    Full release on Github

  • Codex CLI 0.88.0 

    $ npm install -g @openai/codex@0.88.0
    View details

    New Features

    • Added device-code auth as a standalone fallback in headless environments. (#9333)

    Bug Fixes

    • Load configs from trusted folders only and fix symlinked config.toml resolution. (#9533, #9445)
    • Fixed Azure endpoint invalid input errors. (#9387)
    • Resolved a memory leak in core runtime. (#9543)
    • Prevented interrupted turns from repeating. (#9043)
    • Fixed WSL TUI image paste regression. (#9473)

    Documentation

    • Updated MCP documentation link to the current destination. (#9490)
    • Corrected a “Multi-agents” naming typo in docs. (#9542)
    • Added developer instructions for collaboration modes. (#9424)

    Chores

    Changelog

    Full Changelog: rust-v0.87.0...rust-v0.88.0

    Full release on Github

  • Codex CLI 0.87.0 

    $ npm install -g @openai/codex@0.87.0
    View details

    New Features

    • User message metadata (text elements and byte ranges) now round-trips through protocol/app-server/core so UI annotations can survive history rebuilds. (#9331)
    • Collaboration wait calls can block on multiple IDs in one request, simplifying multi-thread coordination. (#9294)
    • User shell commands now run under the user snapshot so aliases and shell config are honored. (#9357)
    • The TUI now surfaces approval requests from spawned/unsubscribed threads. (#9232)

    Bug Fixes

    • Token estimation during compaction is now accurate, improving budgeting during long sessions. (#9337)
    • MCP CallToolResult now includes threadId in both content and structuredContent, and returns a defined output schema for compatibility. (#9338)
    • The TUI “Worked for” separator only appears after actual work has occurred. (#8958)
    • Piped non-PTY commands no longer hang waiting on stdin. (#9369)

    Documentation

    • MCP interface docs updated to reflect structured output schema and threadId behavior. (#9338)

    Chores

    • Windows builds enable the PowerShell UTF-8 feature by default. (#9195)

    Changelog

    Full Changelog: rust-v0.86.0...rust-v0.87.0

    Full release on Github

  • Codex CLI 0.86.0 

    $ npm install -g @openai/codex@0.86.0
    View details

    New Features

    • Skill metadata can now be defined in SKILL.toml (names, descriptions, icons, brand color, default prompt) and surfaced in the app server and TUI (#9125)
    • Clients can explicitly disable web search and signal eligibility via a header to align with server-side rollout controls (#9249)

    Bug Fixes

    • Accepting an MCP elicitation now sends an empty JSON payload instead of null to satisfy servers expecting content (#9196)
    • Input prompt placeholder styling is back to non-italic to avoid terminal rendering issues (#9307)
    • Empty paste events no longer trigger clipboard image reads (#9318)
    • Unified exec cleans up background processes to prevent late End events after listeners stop (#9304)

    Chores

    • Refresh the orchestrator prompt to improve internal routing behavior (#9301)
    • Reduce noisy needs_follow_up error logging (#9272)

    Changelog

    Full Changelog: rust-v0.85.0...rust-v0.86.0

    Full release on Github

  • Codex CLI 0.85.0 

    $ npm install -g @openai/codex@0.85.0
    View details

    New Features

    • App-server v2 now emits collaboration tool calls as item events in the turn stream, so clients can render agent coordination in real time. (#9213)
    • Collaboration tools gained richer agent control: spawn_agent accepts an agent role preset, and send_input can optionally interrupt a running agent before delivering the message. (#9275, #9276)
    • /models metadata now includes upgrade migration markdown so clients can display richer guidance when suggesting model upgrades. (#9219)

    Bug Fixes

    • [revert] Linux sandboxing now falls back to Landlock-only restrictions when user namespaces are unavailable, and sets no_new_privs before applying sandbox rules. (#9250)
    • codex resume --last now respects the current working directory, with --all as an explicit override. (#9245)
    • Stdin prompt decoding now handles BOMs/UTF-16 and provides clearer errors for invalid encodings. (#9151)

    Changelog

    Full Changelog: rust-v0.84.0...rust-v0.85.0

    Full release on Github

  • Codex CLI 0.84.0 

    $ npm install -g @openai/codex@0.84.0
    View details

    New Features

    • Extend the Rust protocol/types to include additional metadata on text elements, enabling richer client rendering and schema evolution (#9235)

    Chores

    • Reduce flaky Rust release pipelines (notably on Windows) by increasing the release build job timeout (#9242)

    Changelog

    Full Changelog: rust-v0.83.0...rust-v0.84.0

    Full release on Github

  • GPT-5.2-Codex API availability

    GPT-5.2-Codex is now available in the API and for users who sign into Codex with the API.

    To learn more about using GPT-5.2-Codex check out our API documentation.

  • Codex CLI 0.81.0 

    $ npm install -g @openai/codex@0.81.0
    View details

    New Features

    • Default API model moved to gpt-5.2-codex. (#9188)
    • The codex tool in codex mcp-server now includes the threadId in the response so it can be used with the codex-reply tool, fixing #3712. The documentation has been updated at https://developers.openai.com/codex/guides/agents-sdk/. (#9192)
    • Headless runs now switch to device-code login automatically so sign-in works without a browser. (#8756)
    • Linux sandbox can mount paths read-only to better protect files from writes. (#9112)
    • Support partial tool calls rendering in tui

    Bug Fixes

    • Alternate-screen handling now avoids breaking Zellij scrollback and adds a config/flag to control it. (#8555)
    • Windows correctly prompts before unsafe commands when running with a read-only sandbox policy. (#9117)
    • Config.toml and rules parsing errors are reported to app-server clients/TUI instead of failing silently. (#9182, #9011)
    • Worked around a macOS system-configuration crash in proxy discovery. (#8954)
    • Invalid user image uploads now surface an error instead of being silently replaced. (#9146)

    Documentation

    • Published a generated JSON Schema for config.toml in docs/ to validate configs. (#8956)
    • Documented the TUI paste-burst state machine for terminals without reliable bracketed paste. (#9020)

    Chores

    • Added Bazel build support plus a just bazel-codex helper for contributors. (#8875, #9177)

    Changelog

    Full Changelog: rust-v0.80.0...rust-v0.81.0

    Full release on Github

  • Codex CLI 0.80.0 

    $ npm install -g @openai/codex@0.80.0
    View details

    New Features

    • Add conversation/thread fork endpoints in the protocol and app server so clients can branch a session into a new thread. (#8866)
    • Expose requirements via requirement/list so clients can read requirements.toml and adjust agent-mode UX. (#8800)
    • Introduce metrics capabilities with additional counters for observability. (#8318, #8910)
    • Add elevated sandbox onboarding with prompts for upgrade/degraded mode plus the /elevate-sandbox command. (#8789)
    • Allow explicit skill invocations through v2 API user input. (#8864)

    Bug Fixes

    • Codex CLI subprocesses again inherit env vars like LD_LIBRARY_PATH/DYLD_LIBRARY_PATH to avoid runtime issues. As explained in #8945, failure to pass along these environment variables to subprocesses that expect them (notably GPU-related ones), was causing 10x+ performance regressions! Special thanks to @johnzfitch for the detailed investigation and write-up in #8945. (#8951)
    • /review <instructions> in TUI/TUI2 now launches the review flow instead of sending plain text. (#8823)
    • Patch approval “allow this session” now sticks for previously approved files. (#8451)
    • Model upgrade prompt now appears even if the current model is hidden from the picker. (#8802)
    • Windows paste handling now supports non-ASCII multiline input reliably. Special thanks to @occurrent laying the groundwork for this fix in #8021! (#8774)
    • Git apply path parsing now handles quoted/escaped paths and /dev/null correctly to avoid misclassified changes. (#8824)

    Documentation

    • App-server README now documents skills support and usage. (#8853)
    • Skill-creator docs clarify YAML frontmatter formatting and quoting rules. (#8610)

    Changelog

    Full Changelog: rust-v0.79.0...rust-v0.80.0

    Full release on Github

  • Codex CLI 0.79.0 

    $ npm install -g @openai/codex@0.79.0
    View details

    New Features

    • Add multi-conversation “agent control” so a session can spawn or message other conversations programmatically (#8783, #8788)
    • Add app-server thread/rollback so IDE clients can undo the last N turns without rewriting history (#8454)
    • Add web_search_cached to enable cached-only Web Search results as a safer alternative to live requests (#8795)
    • Allow global exec flags (model/json/sandbox toggles, etc.) to be passed after codex exec resume (#8440)
    • Show time/version-targeted announcement tips in the TUI, driven by a TOML file in the repo (#8752)
    • Add an [analytics] enabled=... config section to control analytics behavior (#8350)

    Bug Fixes

    • Fix TUI2 transcripts so streamed markdown reflows on resize and copy/paste preserves soft wraps (#8761)
    • Make apply_patch parsing tolerant of whitespace-padded *** Begin Patch / *** End Patch markers (#8746)
    • Render paths relative to the current working directory before checking git roots, improving output in non-git workspaces (#8771)
    • Prevent CODEX_MANAGED_CONFIG_PATH from overriding managed config in production, closing a policy bypass (#8762)
    • Ensure app-server conversations respect the config passed in by the client (#8765)
    • Reduce TUI UX glitches: suppress popups when browsing input history, fix copy “pill” rendering, and clear background terminals on interrupt (#8772, #8777, #8786)

    Documentation

    • Clarify onboarding/login guidance for headless/remote setups by steering users to codex login --device-auth (#8753)
    • Update model examples used in tooling/config to current gpt-5.2 naming (#8566)

    Chores

    • Refactor skills discovery to use the config layer stack so all configured skill folders are considered (#8497)
    • Auto-populate GitHub release notes at release creation time (#8799)
    • Add more apply_patch test scenarios to harden coverage (#8230)
    • Tweak unified exec event emission to only send “begin” when a PTY is present (#8780)

    Changelog

    Full Changelog: rust-v0.78.0...rust-v0.79.0

    Full release on Github

  • Codex CLI 0.78.0 

    $ npm install -g @openai/codex@0.78.0
    View details

    New Features

    • Add Ctrl+G to open the current prompt in your configured external editor ($VISUAL/$EDITOR) and sync edits back into the TUI. (#7606)
    • Support project-aware config layering: load repo-local .codex/config.toml, honor configurable project_root_markers, and merge that with system config like /etc/codex/config.toml. (#8354, #8359, #8461)
    • Support enterprise-managed configuration requirements on macOS via an MDM-provided TOML payload. (#8743)
    • Improve tui2 transcript navigation with multi-click selection, a copy shortcut/affordance, and a draggable auto-hiding scrollbar. (#8462, #8471, #8728)
    • Start Windows PowerShell sessions in UTF-8 mode to reduce encoding-related prompt/output issues. (#7902)
    • Exec policy rules can now include human-readable justifications, and policy loading follows the unified config-layer stack. (#8349, #8453, #8751)

    Bug Fixes

    • Fix failures when the model returns multiple tool calls in a single turn by emitting tool calls in the format the Chat Completions API expects. (#8556)
    • Make /review compute diffs from the session’s working directory so base-branch detection works correctly with runtime cwd overrides. (#8738)
    • Handle the legacy Chat Completions streaming terminator cleanly to avoid spurious SSE parse errors. (#8708)
    • Fix a set of tui2 rendering/input edge cases (screen corruption, scroll stickiness, and selection/copy correctness). (#8463, #8695, #8449)
    • Improve diagnostics when ripgrep download fails during CLI packaging so failures are easier to debug. (#8486)
    • Avoid a panic when parsing alpha/stable version strings. (#8406)

    Documentation

    • Replace and de-duplicate user docs with links to the developer documentation site (including skills docs). (#8662, #8407)
    • Clarify configuration documentation, including the developer_instructions option. (#8376, #8701)
    • Fix broken README links. (#8682)

    Chores

    • Performance tuning for TUIs: cap redraw scheduling and reduce unnecessary rerenders during streaming to lower CPU usage. (#8499, #8681, #8693)
    • Update Rust dependencies across codex-rs. (#8414, #8596, #8597)

    Changelog

    Full Changelog: rust-v0.77.0...rust-v0.78.0

    Full release on Github

December 2025

  • Codex CLI 0.77.0 

    $ npm install -g @openai/codex@0.77.0
    View details

    New Features

    • TUI2: Normalize mouse wheel + trackpad scrolling across terminals; add tui.scroll_* config settings (PR #8357)
    • Add allowed_sandbox_modes to requirements.toml to constrain permitted sandbox modes (PR #8298)
    • MCP: OAuth login for streamable HTTP MCP servers no longer requires the rmcp_client feature flag (PR #8087)
    • Improve fuzzy file search display/consistency by centralizing file-name derivation in codex-file-search (PR #8334)
    • Update bundled model metadata (models.json) (PR #8168)

    Bug Fixes

    • Fix /undo interacting destructively with git staging / ghost commits (PR #8303)
    • TUI2: Reduce redundant redraws while scrolling transcripts (PR #8295)
    • Docs: Fix link to contributing.md in experimental.md (PR #8311)

    Full Changelog: rust-v0.76.0...rust-v0.77.0

    Changelog (PRs merged in this tag range)

    • #8374 Remove plan from system skills: #8374
    • #8357 TUI2 scroll normalization + config knobs: #8357
    • #8353 Thread config loading now receives cwd (internal plumbing): #8353
    • #8346 Rename “OpenAI models” to “models manager” (internal refactor): #8346
    • #8345 Bump cargo-deny-action version (CI): #8345
    • #8334 Move file-name derivation into codex-file-search: #8334
    • #8333 Enable resume_warning suite module (test coverage / wiring fix): #8333
    • #8330 Make ConstraintError an enum (more structured errors): #8330
    • #8303 Fix /undo staging interaction: #8303
    • #8298 Add allowed_sandbox_modes in requirements.toml: #8298
    • #8295 Coalesce transcript scroll redraws (TUI2 performance): #8295
    • #8168 Update models.json: #8168
    • #8087 Remove rmcp_client feature flag usage (no longer needed for OAuth login): #8087
    • #8311 Fix docs link in experimental.md: #8311

    Full release on Github

  • Agent skills in Codex

    Codex now supports agent skills: reusable bundles of instructions (plus optional scripts and resources) that help Codex reliably complete specific tasks.

    Skills are available in both the Codex CLI and IDE extensions.

    You can invoke a skill explicitly by typing $skill-name (for example, $skill-installer or the experimental $create-plan skill after installing it), or let Codex select a skill automatically based on your prompt.

    Learn more in the skills documentation.

    Folder-based standard (agentskills.io)

    Following the open agent skills specification, a skill is a folder with a required SKILL.md and optional supporting files:

    my-skill/
  SKILL.md       # Required: instructions + metadata
  scripts/       # Optional: executable code
  references/    # Optional: documentation
  assets/        # Optional: templates, resources

    Install skills per-user or per-repo

    You can install skills for just yourself in ~/.codex/skills, or for everyone on a project by checking them into .codex/skills in the repository.

    Codex also ships with a few built-in system skills to get started, including $skill-creator and $skill-installer. The $create-plan skill is experimental and needs to be installed (for example: $skill-installer install the create-plan skill from the .experimental folder).

    Curated skills directory

    Codex ships with a small curated set of skills inspired by popular workflows at OpenAI. Install them with $skill-installer, and expect more over time.

  • Codex CLI 0.76.0 

    $ npm install -g @openai/codex@0.76.0
    View details

    New Features

    • Add a macOS DMG build target (PR #8207)
    • Improve terminal detection metadata for per-terminal scroll tuning (PR #8252)
    • UI tweaks on the skills popup (PR #8250)
    • TUI search cell rendering improvements (PR #8273)
    • Add /ps command (PR #8279)
    • Add support for /etc/codex/requirements.toml on UNIX (PR #8277)
    • Support shortDescription for skills (PR #8278, PR #8301)
    • Add model list UI (PR #8286)
    • Add app-server v2 deprecation notice event (PR #8285)
    • Introduce ExternalSandbox policy (PR #8290)
    • Skills default on (PR #8297)
    • Support admin-scoped skills (PR #8296)
    • Update bundled system skills (PR #8253, PR #8328)
    • Set exclude default to true in app server (PR #8281)

    Bug Fixes

    • Ensure pipes work in restricted sandbox tokens (PR #8280)
    • Grant read ACL to the command-runner directory earlier (PR #8275)
    • Fix duplicate shell_snapshot FeatureSpec regression (PR #8274)
    • Fix sandbox-state update ordering by switching to request (PR #8142)

    PRs Merged

    • #8328 Update system skills from OSS repo
    • #8325 Revert "Keep skills feature flag default OFF for windows."
    • #8308 Keep skills feature flag default OFF for windows.
    • #8305 Fix admin skills.
    • #8301 Add short descriptions to system skills
    • #8299 Fix tests
    • #8297 skills feature default on.
    • #8296 Support admin scope skills.
    • #8290 feat: introduce ExternalSandbox policy
    • #8288 chore: upgrade rmcp crate from 0.10.0 to 0.12.0
    • #8286 model list
    • #8285 feat(app-server): add v2 deprecation notice
    • #8282 fix: flaky tests 5
    • #8281 Set exclude to true by default in app server
    • #8280 add a default dacl to restricted token to enable reading of pipes
    • #8279 feat: add /ps
    • #8278 Support skills shortDescription.
    • #8277 feat: add support for /etc/codex/requirements.toml on UNIX
    • #8276 chore: migrate from Config::load_from_base_config_with_overrides to ConfigBuilder
    • #8275 grant read ACL to exe directory first so we can call the command runner
    • #8274 fix: remove duplicate shell_snapshot FeatureSpec
    • #8273 tui: improve rendering of search cell
    • #8271 use mainline version as baseline in ci
    • #8257 feat: collapse "waiting" of unified_exec
    • #8253 Update system skills bundled with codex-rs
    • #8252 Terminal Detection Metadata for Per-Terminal Scroll Scaling
    • #8250 UI tweaks on skills popup.
    • #8207 [release] Add a dmg target for MacOS
    • #8142 fix: change codex/sandbox-state/update from a notification to a request

    Full release on Github

  • Introducing GPT-5.2-Codex

    Today we are releasing GPT-5.2-Codex, the most advanced agentic coding model yet for complex, real-world software engineering.

    GPT-5.2-Codex is a version of GPT-5.2 further optimized for agentic coding in Codex, including improvements on long-horizon work through context compaction, stronger performance on large code changes like refactors and migrations, improved performance in Windows environments, and significantly stronger cybersecurity capabilities.

    Starting today, the CLI and IDE Extension will default to gpt-5.2-codex for users who are signed in with ChatGPT. API access for the model will come soon.

    If you have a model specified in your config.toml configuration file, you can instead try out gpt-5.2-codex for a new Codex CLI session using:

    codex --model gpt-5.2-codex

    You can also use the /model slash command in the CLI. In the Codex IDE Extension you can select GPT-5.2-Codex from the dropdown menu.

    If you want to switch for all sessions, you can change your default model to gpt-5.2-codex by updating your config.toml configuration file:

    model = "gpt-5.2-codex”

  • Codex CLI 0.75.0 

    $ npm install -g @openai/codex@0.75.0
    View details

    PRs Merged

    #8270 — splash screen
    #8251 — migrate to new constraint-based loading strategy
    #7460 — cloud: default to current branch in cloud exec

    Full release on Github

  • Codex CLI 0.74.0 

    $ npm install -g @openai/codex@0.74.0
    View details

    Highlights

    • Introducing gpt-5.2-codex our latest frontier model with improvements across knowledge, reasoning and coding. Learn more
    • Add new slash command /experimental for trying out experimental features
    • Ghost snapshot warning disable toggle (#8178)
    • UI polish (background terminals, picker cleanup) (#8255, #8232).

    PRs Merged

    • #8266 feat: add name to beta features
    • #8265 caribou
    • #8264 docs: clarify codex resume --all (CWD column & filtering)
    • #8255 nit: ui background terminals
    • #8249 chore: prefer AsRef to &Path
    • #8248 chore: simplify loading of Mac-specific logic in config_loader
    • #8244 Reintroduce feature flags for skills.
    • #8243 Make loading malformed skills fail-open
    • #8235 fix: introduce ConfigBuilder
    • #8232 chores: clean picker
    • #8228 Show migration link
    • #8226 chore: cleanup Config instantiation codepaths
    • #8221 Change “Team” to “Buisness” and add Education
    • #8220 Support SYSTEM skills.
    • #8216 speed and reliability improvements for setting reads ACLs
    • #8209 feat: model picker
    • #8205 fix: PathBuf -> AbsolutePathBuf in ConfigToml struct
    • #8203 download new windows binaries when staging npm package
    • #8201 chore: add beta features
    • #8199 chore: move back stuff out of beta program
    • #8198 feat: make list_models non-blocking
    • #8196 fix: session downgrade
    • #8194 fix: proper skills dir cleanup
    • #8186 nit: doc
    • #8182 nit: drop dead branch with unified_exec tool
    • #8181 nit: prevent race in event rendering
    • #8178 feat: add config to disable warnings around ghost snapshot
    • #8175 fix: flaky test 6
    • #8163 fix the models script
    • #8153 Load models from static file
    • #8152 [app-server] add new RawResponseItem v2 event
    • #8151 chore: update listMcpServerStatus to be non-blocking
    • #8149 Add user_agent header
    • #8141 chore(apply-patch) unicode scenario
    • #8140 include new windows binaries in npm package.
    • #8127 Revert “chore: review in read-only (#7593)”
    • #8124 fix tui2 compile error
    • #8122 docs: refine tui2 viewport roadmap
    • #8118 Add a workflow for a hardcoded version of models
    • #8117 feat: unified exec footer
    • #8114 chore: update listMcpServers to listMcpServerStatus
    • #8111 chore(apply-patch) move invocation tests
    • #8109 Revert “feat: unified exec footer”
    • #8108 feat(sdk): add xhigh reasoning effort support to TypeScript SDK
    • #8102 Upgrade GitHub Actions for Node 24 compatibility
    • #8098 Add public skills + improve repo skill discovery and error UX
    • #8095 feat: change ConfigLayerName into a disjoint union rather than a simple enum
    • #8094 bug fixes and perf improvements for elevated sandbox setup
    • #8089 refactor(tui2): make transcript line metadata explicit
    • #8088 feat: if .codex is a sub-folder of a writable root, then make it read-only to the sandbox
    • #8086 chore(app-server): remove stubbed thread/compact API
    • #8085 chore: mac codesign refactor
    • #8084 chore(ci): drop Homebrew origin/main workaround for macOS runners
    • #8079 docs: fix gpt-5.2 typo in config.md
    • #8077 better name for windows sandbox features
    • #8075 feat: fallback unified_exec to shell_command
    • #8071 feat: experimental menu
    • #8067 feat: unified exec footer
    • #8060 feat: do not compact on last user turn
    • #8057 chore: dedup review result duplication
    • #8053 nit: trace span for regular task
    • #8052 feat: close unified_exec at end of turn
    • #8020 Fixes mcp elicitation test that fails for me when run locally
    • #8004 Fix: Detect Bun global install via path check
    • #8000 Fixed resume matching to respect case insensitivity when using WSL mount points
    • #7997 feat: merge remote models instead of destructing
    • #7969 Fix: Skip Option<()> schema generation to avoid invalid Windows filenames (#7479)
    • #7961 refactor TUI event loop to enable dropping + recreating crossterm event stream
    • #7956 fix parallel tool calls
    • #7935 exec-server: additional context for errors
    • #7931 chore: persist comments in edit
    • #7791 chore(shell_command) fix freeform timeout output
    • #7778 feat: Constrain values for approval_policy
    • #7601 WIP: Rework TUI viewport, history printing, and selection/copy

    Full release on Github

  • Introducing Codex for Linear

    Assign or mention @Codex in an issue to kick-off a Codex cloud task. As Codex works, it posts updates back to Linear, providing a link to the completed task so you can review, open a PR, or keep working.

    Screenshot of a successful Codex task started in Linear

    To learn more about how to connect Codex to Linear both locally through MCP and through the new integration, check out the Codex for Linear documentation.

November 2025

  • Usage and credits fixes

    Minor updates to address a few issues with Codex usage and credits:

    • Adjusted all usage dashboards to show “limits remaining” for consistency. The CLI previously displayed “limits used.”
    • Fixed an issue preventing users from buying credits if their ChatGPT subscription was purchased via iOS or Google Play.
    • Fixed an issue where the CLI could display stale usage information; it now refreshes without needing to send a message first.
    • Optimized the backend to help smooth out usage throughout the day, irrespective of overall Codex load or how traffic is routed. Before, users could get unlucky and hit a few cache misses in a row, leading to much less usage.

  • Introducing GPT-5.1-Codex-Max

    Today we are releasing GPT-5.1-Codex-Max, our new frontier agentic coding model.

    GPT‑5.1-Codex-Max is built on an update to our foundational reasoning model, which is trained on agentic tasks across software engineering, math, research, and more. GPT‑5.1-Codex-Max is faster, more intelligent, and more token-efficient at every stage of the development cycle–and a new step towards becoming a reliable coding partner.

    Starting today, the CLI and IDE Extension will default to gpt-5.1-codex-max for users that are signed in with ChatGPT. API access for the model will come soon.

    For non-latency-sensitive tasks, we’ve also added a new Extra High (xhigh) reasoning effort, which lets the model think for an even longer period of time for a better answer. We still recommend medium as your daily driver for most tasks.

    If you have a model specified in your config.toml configuration file, you can instead try out gpt-5.1-codex-max for a new Codex CLI session using:

    codex --model gpt-5.1-codex-max

    You can also use the /model slash command in the CLI. In the Codex IDE Extension you can select GPT-5.1-Codex from the dropdown menu.

    If you want to switch for all sessions, you can change your default model to gpt-5.1-codex-max by updating your config.toml configuration file:

    model = "gpt-5.1-codex-max”

  • Introducing GPT-5.1-Codex and GPT-5.1-Codex-Mini

    Along with the GPT-5.1 launch in the API, we are introducing new gpt-5.1-codex-mini and gpt-5.1-codex model options in Codex, a version of GPT-5.1 optimized for long-running, agentic coding tasks and use in coding agent harnesses in Codex or Codex-like harnesses.

    Starting today, the CLI and IDE Extension will default to gpt-5.1-codex on macOS and Linux and gpt-5.1 on Windows.

    If you have a model specified in your config.toml configuration file, you can instead try out gpt-5.1-codex for a new Codex CLI session using:

    codex --model gpt-5.1-codex

    You can also use the /model slash command in the CLI. In the Codex IDE Extension you can select GPT-5.1-Codex from the dropdown menu.

    If you want to switch for all sessions, you can change your default model to gpt-5.1-codex by updating your config.toml configuration file:

    model = "gpt-5.1-codex”

  • Introducing GPT-5-Codex-Mini

    Today we are introducing a new gpt-5-codex-mini model option to Codex CLI and the IDE Extension. The model is a smaller, more cost-effective, but less capable version of gpt-5-codex that provides approximately 4x more usage as part of your ChatGPT subscription.

    Starting today, the CLI and IDE Extension will automatically suggest switching to gpt-5-codex-mini when you reach 90% of your 5-hour usage limit, to help you work longer without interruptions.

    You can try the model for a new Codex CLI session using:

    codex --model gpt-5-codex-mini

    You can also use the /model slash command in the CLI. In the Codex IDE Extension you can select GPT-5-Codex-Mini from the dropdown menu.

    Alternatively, you can change your default model to gpt-5-codex-mini by updating your config.toml configuration file:

    model = "gpt-5-codex-mini”

  • GPT-5-Codex model update

    We’ve shipped a minor update to GPT-5-Codex:

    • More reliable file edits with apply_patch.
    • Fewer destructive actions such as git reset.
    • More collaborative behavior when encountering user edits in files.
    • 3% more efficient in time and usage.

October 2025

  • Credits on ChatGPT Pro and Plus

    Codex users on ChatGPT Plus and Pro can now use on-demand credits for more Codex usage beyond what’s included in your plan. Learn more.

  • Tag @Codex on GitHub Issues and PRs

    You can now tag @codex on a teammate’s pull request to ask clarifying questions, request a follow-up, or ask Codex to make changes. GitHub Issues now also support @codex mentions, so you can kick off tasks from any issue, without leaving your workflow.

    Codex responding to a GitHub pull request and issue after an @Codex mention.

  • Codex is now GA

    Codex is now generally available with 3 new features — @Codex in Slack, Codex SDK, and new admin tools.

    @Codex in Slack

    You can now questions and assign tasks to Codex directly from Slack. See the Slack guide to get started.

    Codex SDK

    Integrate the same agent that powers the Codex CLI inside your own tools and workflows with the Codex SDK in Typescript. With the new Codex GitHub Action, you can easily add Codex to CI/CD workflows. See the Codex SDK guide to get started.

    import { Codex } from "@openai/codex-sdk";

const agent = new Codex();
const thread = await agent.startThread();

const result = await thread.run("Explore this repo");
console.log(result);

const result2 = await thread.run("Propose changes");
console.log(result2);

    New admin controls and analytics

    ChatGPT workspace admins can now edit or delete Codex Cloud environments. With managed config files, they can set safe defaults for CLI and IDE usage and monitor how Codex uses commands locally. New analytics dashboards help you track Codex usage and code review feedback. Learn more in the enterprise admin guide.

    Availability and pricing updates

    The Slack integration and Codex SDK are available to developers on ChatGPT Plus, Pro, Business, Edu, and Enterprise plans starting today, while the new admin features will be available to Business, Edu, and Enterprise. Beginning October 20, Codex Cloud tasks will count toward your Codex usage. Review the Codex pricing guide for plan-specific details.

September 2025

  • GPT-5-Codex in the API

    GPT-5-Codex is now available in the Responses API, and you can also use it with your API Key in the Codex CLI. We plan on regularly updating this model snapshot. It is available at the same price as GPT-5. You can learn more about pricing and rate limits for this model on our model page.

  • Introducing GPT-5-Codex

    New model: GPT-5-Codex

    codex-switch-model

    GPT-5-Codex is a version of GPT-5 further optimized for agentic coding in Codex. It’s available in the IDE extension and CLI when you sign in with your ChatGPT account. It also powers the cloud agent and Code Review in GitHub.

    To learn more about GPT-5-Codex and how it performs compared to GPT-5 on software engineering tasks, see our announcement blog post.

    Image outputs

    codex-image-outputs

    When working in the cloud on front-end engineering tasks, GPT-5-Codex can now display screenshots of the UI in Codex web for you to review. With image output, you can iterate on the design without needing to check out the branch locally.

    New in Codex CLI

    • You can now resume sessions where you left off with codex resume.
    • Context compaction automatically summarizes the session as it approaches the context window limit.

    Learn more in the latest release notes

August 2025

  • Late August update

    IDE extension (Compatible with VS Code, Cursor, Windsurf)

    Codex now runs in your IDE with an interactive UI for fast local iteration. Easily switch between modes and reasoning efforts.

    Sign in with ChatGPT (IDE & CLI)

    One-click authentication that removes API keys and uses ChatGPT Enterprise credits.

    Move work between local ↔ cloud

    Hand off tasks to Codex web from the IDE with the ability to apply changes locally so you can delegate jobs without leaving your editor.

    Code Reviews

    Codex goes beyond static analysis. It checks a PR against its intent, reasons across the codebase and dependencies, and can run code to validate the behavior of changes.

  • Mid August update

    Image inputs

    You can now attach images to your prompts in Codex web. This is great for asking Codex to implement frontend changes or follow up on whiteboarding sessions.

    Container caching

    Codex now caches containers to start new tasks and followups 90% faster, dropping the median start time from 48 seconds to 5 seconds. You can optionally configure a maintenance script to update the environment from its cached state to prepare for new tasks. See the docs for more.

    Automatic environment setup

    Now, environments without manual setup scripts automatically run the standard installation commands for common package managers like yarn, pnpm, npm, go mod, gradle, pip, poetry, uv, and cargo. This reduces test failures for new environments by 40%.

June 2025

  • Best of N

    Codex can now generate multiple responses simultaneously for a single task, helping you quickly explore possible solutions to pick the best approach.

    Fixes & improvements

    • Added some keyboard shortcuts and a page to explore them. Open it by pressing ⌘-/ on macOS and Ctrl+/ on other platforms.

    • Added a “branch” query parameter in addition to the existing “environment”, “prompt” and “tab=archived” parameters.

    • Added a loading indicator when downloading a repo during container setup.

    • Added support for cancelling tasks.

    • Fixed issues causing tasks to fail during setup.

    • Fixed issues running followups in environments where the setup script changes files that are gitignored.

    • Improved how the agent understands and reacts to network access restrictions.

    • Increased the update rate of text describing what Codex is doing.

    • Increased the limit for setup script duration to 20 minutes for Pro and Business users.

    • Polished code diffs: You can now option-click a code diff header to expand/collapse all of them.

  • June update

    Agent internet access

    Now you can give Codex access to the internet during task execution to install dependencies, upgrade packages, run tests that need external resources, and more.

    Internet access is off by default. Plus, Pro, and Business users can enable it for specific environments, with granular control of which domains and HTTP methods Codex can access. Internet access for Enterprise users is coming soon.

    Learn more about usage and risks in the docs.

    Update existing PRs

    Now you can update existing pull requests when following up on a task.

    Voice dictation

    Now you can dictate tasks to Codex.

    Fixes & improvements

    • Added a link to this changelog from the profile menu.

    • Added support for binary files: When applying patches, all file operations are supported. When using PRs, only deleting or renaming binary files is supported for now.

    • Fixed an issue on iOS where follow up tasks where shown duplicated in the task list.

    • Fixed an issue on iOS where pull request statuses were out of date.

    • Fixed an issue with follow ups where the environments were incorrectly started with the state from the first turn, rather than the most recent state.

    • Fixed internationalization of task events and logs.

    • Improved error messages for setup scripts.

    • Increased the limit on task diffs from 1 MB to 5 MB.

    • Increased the limit for setup script duration from 5 to 10 minutes.

    • Polished GitHub connection flow.

    • Re-enabled Live Activities on iOS after resolving an issue with missed notifications.

    • Removed the mandatory two-factor authentication requirement for users using SSO or social logins.

May 2025

  • Reworked environment page

    It’s now easier and faster to set up code execution.

    Fixes & improvements

    • Added a button to retry failed tasks

    • Added indicators to show that the agent runs without network access after setup

    • Added options to copy git patches after pushing a PR

    • Added support for unicode branch names

    • Fixed a bug where secrets were not piped to the setup script

    • Fixed creating branches when there’s a branch name conflict.

    • Fixed rendering diffs with multi-character emojis.

    • Improved error messages when starting tasks, running setup scripts, pushing PRs, or disconnected from GitHub to be more specific and indicate how to resolve the error.

    • Improved onboarding for teams.

    • Polished how new tasks look while loading.

    • Polished the followup composer.

    • Reduced GitHub disconnects by 90%.

    • Reduced PR creation latency by 35%.

    • Reduced tool call latency by 50%.

    • Reduced task completion latency by 20%.

    • Started setting page titles to task names so Codex tabs are easier to tell apart.

    • Tweaked the system prompt so that agent knows it’s working without network, and can suggest that the user set up dependencies.

    • Updated the docs.

  • Codex in the ChatGPT iOS app

    Start tasks, view diffs, and push PRs—while you’re away from your desk.