mirror of
https://github.com/openai/codex.git
synced 2026-09-05 15:18:41 +00:00
7ca611348d
- TUI markdown now keeps web links clickable with OSC 8 metadata, and cramped tables switch to readable key/value records without losing link targets. (#24472, #24636, #24825) - Sessions can now be archived from the TUI with `/archive` or from the CLI with `codex archive` / `codex unarchive`; archived sessions are protected from resume/fork until restored. (#25027, #25021) - App-server integrations can resume a thread with its initial turns page, see richer MCP server status, and launch stdio mode with `codex app-server --stdio`. (#23534, #24698, #24940) - Remote execution setup now supports `CODEX_API_KEY` registration for approved OpenAI hosts, while remote-control websockets use short-lived server tokens instead of ChatGPT access tokens. (#24666, #24141) - Windows admins get an alpha `codex sandbox setup --elevated` provisioning path, plus requirements support for allowed Windows sandbox implementations. (#24831, #23766) - A feature-gated standalone image generation extension can run through the native Codex image artifact completion pipeline. (#24723, #24972) ## Bug Fixes - ChatGPT auth refreshes tokens before the five-minute expiry window and shows a relogin-required path for reused refresh tokens instead of collapsing into a generic cloud error. (#23546, #24830) - Command-safety hardening prevents `/diff` from running repository-provided Git helpers/hooks, avoids PowerShell parser execution on non-Windows hosts, and rejects browser-origin exec-server websocket handshakes. (#24954, #24946, #24947) - Sandboxed commands clean up more reliably after interruptions or denied Windows network attempts, and `deny` read rules stay enforced for safe-command and approval-bypass paths. (#22729, #19880, #23943) - Resumed TUI sessions seed prompt history from the session transcript, multiline hook output renders as separate rows, and Vim normal-mode editing behaves correctly. (#24298, #24965, #25022) - App-server filesystem watchers debounce later batches correctly, and standalone web search calls now show and restore completed search activity. (#24716, #24693) - Bedrock auth now falls back to `AWS_REGION` / `AWS_DEFAULT_REGION`, and unsupported Bedrock GPT service tiers are no longer advertised or sent. (#25171, #25318) ## Documentation - Python SDK beta docs and package metadata now present the standard `pip install openai-codex` path, refreshed quickstarts, API reference, FAQ, and examples. (#24836, #24866, #24868, #24870) - Python SDK examples and docs now use the public `CodexConfig` name for configuring `Codex` / `AsyncCodex`. (#24800) - The bundled OpenAI Docs skill was updated with current Codex manual routing and a cached manual fetch helper. (#24914) - Built-in tool schema descriptions now clarify defaults, optional fields, bounds, and enums across shell, Code Mode, MCP, image, goal, plan, multi-agent, and related tools. (#24794) - App-server and exec-server docs now cover API-key remote registration, `--stdio`, runtime extra skill roots, and remote-control server-token behavior. (#24666, #24940, #24977, #24141) ## Chores - Python SDK releases can now be staged and published independently from runtime releases using `python-v*` tags while preserving the reviewed runtime dependency pin. (#24828, #24872) - Updated MCP dependencies to `rmcp` 1.7.0 and refreshed compatibility code. (#24763) - Refreshed Amazon Bedrock catalog metadata, including GPT-5.5, removal of unsupported OSS entries, and default-tier-only GPT model behavior. (#24701, #24960, #25318) - Removed the stale app-server debug-client pieces and cleaned up the workspace after deletion. (#25063, #25064, #25065, #25066, #25067, #25068, #25069, #25070, #25075) - Trimmed CI/build maintenance by moving Bazel Windows jobs to Codex runners, removing the libubsan workaround, and reverting the startup benchmark that broke musl builders. (#24952, #24782, #24937) ## Changelog Full Changelog: https://github.com/openai/codex/compare/rust-v0.135.0...rust-v0.136.0 - #22729 fix(linux-sandbox): preserve shell cleanup on interruption @viyatb-oai - #24472 feat(tui): add OSC 8 web links to rich content @fcoury-oai - #24636 feat(tui): render cramped markdown tables as key-value records [2 of 2] @fcoury-oai - #24666 Allow API-key auth for remote exec-server registration @sdcoffey - #24763 Update rmcp to 1.7.0 @anp-oai - #24825 [codex] Fix hyperlink-aware key-value table rendering @sayan-oai - #24800 [codex] Rename Python SDK AppServerConfig to CodexConfig @aibrahim-oai - #24819 [codex] Remove redundant SQLite dynamic tool storage @sayan-oai - #24828 [codex] Add independent beta release for the Python SDK @aibrahim-oai - #24836 [codex] Prepare Python SDK beta documentation and package metadata @aibrahim-oai - #24830 Treat refresh_token_reused 400s as relogin-required @alexsong-oai - #24866 [codex] Simplify Python SDK install guidance @aibrahim-oai - #24868 [codex] Remove Python SDK language classifiers @aibrahim-oai - #24870 [codex] Remove Python SDK beta warning note @aibrahim-oai - #24872 [codex] Stage Python SDK beta versions from release tags @aibrahim-oai - #24758 Move memories root setup out of core config @jif-oai - #24891 Stabilize Guardian client cache key handling @jif-oai - #24892 Export Guardian prompt cache key helper @jif-oai - #24893 Add Guardian review prompt cache key @jif-oai - #24894 Assert Guardian prompt cache key reuse @jif-oai - #24895 Thread Guardian cache key through session @jif-oai - #24803 Use stable Guardian prompt cache keys @jif-oai - #24902 [codex] Fix Guardian argument comment lint @jif-oai - #24898 Fix memories namespace for Responses API tools @jif-oai - #24897 Add Guardian review metrics @jif-oai - #23546 [codex-cli] Refresh near-expiry ChatGPT access tokens before requests @cooper-oai - #24915 Add thread start contributor facts @jif-oai - #24916 Add turn error lifecycle contributor @jif-oai - #24865 [codex] Store pending response items directly @pakrym-oai - #24914 [codex] Update OpenAI Docs skill @vb-openai - #24651 Add app-server startup benchmark crate @anp-oai - #24925 Gate goal tools by thread eligibility @jif-oai - #24782 Remove libubsan CI workaround @anp-oai - #24813 extension-api: add TurnItemEmitter to tool calls @sayan-oai - #23534 feat(app-server): include turns page on thread resume @btraut-openai - #24698 Expose MCP server info as part of server status @gpeal - #24903 Reap stale multi-agent slots @jif-oai - #24936 Fix extension turn item emitter test event ordering @bolinfest - #24700 [codex] Support ui visibility meta for tools @gpeal - #24701 chore: add GPT-5.5 to the Amazon Bedrock catalog @celia-oai - #23363 TUI: Unified mentions tweaks + polish mentions rendering @canvrno-oai - #24937 Revert "Add app-server startup benchmark crate" @anp-oai - #24928 Wire task completion into thread-idle lifecycle @jif-oai - #24723 Add feature-gated standalone image generation extension @won-openai - #24952 Move Bazel Windows jobs onto codex-runners @anp-oai - #24940 Add `codex app-server --stdio` alias @anp-oai - #24954 fix(tui): prevent repository-configured code execution in /diff @fcoury-oai - #24949 [codex] Handle PowerShell UTF-8 setup failures @iceweasel-oai - #24960 [codex] Remove Bedrock OSS models from catalog @celia-oai - #23768 runtime: prepend zsh fork bin dir to PATH @bolinfest - #19880 fix: cancel Windows sandbox on network denial @viyatb-oai - #24947 fix(exec-server): reject websocket requests with Origin headers @viyatb-oai - #24653 [codex] Add user input client ids @alexi-openai - #23924 Surface filesystem permission profiles in prompt context @bolinfest - #24108 windows-sandbox: pass workspace roots to runner @bolinfest - #24974 windows-sandbox: fix capture cancellation test roots @bolinfest - #24962 Tighten hook output event schemas @abhinav-oai - #24141 feat(app-server): migrate remote control to server tokens @apanasenko-oai - #24970 fix(config): use deny for Unix socket permissions @viyatb-oai - #24946 [codex] Avoid PowerShell safety parsing off Windows @adrian-openai - #24977 Add runtime extra skill roots API @xl-openai - #24298 Seed prompt history from resumed messages @etraut-openai - #23943 fix: preserve deny-read sandboxing for safe commands @bolinfest - #24716 Fix fs/watch debounce batching @etraut-openai - #24918 Use internal model context fragments for goal steering @jif-oai - #24924 Use inject_if_running for active goal steering @jif-oai - #25063 Drop the stale debug-client manifest @jif-oai - #25064 Remove the generated debug-client README @jif-oai - #25065 Delete debug-client app-server process plumbing @jif-oai - #25066 Retire debug-client interactive command parsing @jif-oai - #25067 Remove the debug-client CLI entrypoint @jif-oai - #25068 Delete debug-client JSONL output helper @jif-oai - #25069 Remove debug-client server event reader @jif-oai - #25070 Drop debug-client prompt state tracking @jif-oai - #25075 fix: main @jif-oai - #24794 [codex] Improve built-in tool schema docs @jif-oai - #25095 Handle goal usage limits from turn errors @jif-oai - #25106 Remove stale rollout TODO tests @jif-oai - #24965 Render multiline hook output in TUI @abhinav-oai - #25031 [codex] Add model tool mode selector @aibrahim-oai - #24693 Show activity for standalone web search calls @sayan-oai - #25110 Move config document helpers into their own module @jif-oai - #25013 feat: Add focused diagnostics for MCP HTTP send failures @xl-openai - #24964 [codex] Wait for MCP readiness in core integration tests @anp-oai - #24972 Route extension image generation through the native image completion pipeline @won-openai - #24831 Add Windows sandbox provisioning setup command @iceweasel-oai - #25017 Align TUI permissions labels with app @etraut-openai - #25027 Add `/archive` slash command @etraut-openai - #25035 Use session wording in `/rename` confirmation @etraut-openai - #24161 Add subagent lineage metadata for responsesapi @owenlin0 - #25116 [exec-server] Kill dropped filesystem helpers @erichoracek - #24180 code-mode: introduce durable session interface @cconger - #23165 thread-store: store permission profiles @bolinfest - #25131 [codex] Require model for standalone web search @sayan-oai - #25134 ci: use issue triage environment for issue workflows @etraut-openai - #25118 exec-server: preserve fs helper CoreFoundation env @starr-openai - #25022 [codex] Fix Vim normal mode editing @jinghanx88 - #25161 Recommend Bazel VSCode extension. @anp-oai - #24996 Filter plugin install suggestions by installed apps @nm-openai - #23766 Constrain Windows sandbox requirements @abhinav-oai - #25172 [codex] Update remote connector suggestions @ericning-o - #25171 fix: Bedrock API key region fallback @celia-oai - #24541 feat(config) experimental_request_user_input toggle @dylan-hurd-oai - #25021 Add thread archive CLI commands @etraut-openai - #25267 Rename multi-agent v2 assignment tool @jif-oai - #25318 fix: Limit Bedrock GPT models to default service tier @owenlin0 - #25381 [codex] Avoid forced directory refresh during plugin install auth checks @xl-openai
Codex CLI (Rust Implementation)
We provide Codex CLI as a standalone executable to ensure a zero-dependency install.
Installing Codex
Today, the easiest way to install Codex is via npm:
npm i -g @openai/codex
codex
You can also install via Homebrew (brew install --cask codex) or download a platform-specific release directly from our GitHub Releases.
Documentation quickstart
- First run with Codex? Start with
docs/getting-started.md(links to the walkthrough for prompts, keyboard shortcuts, and session management). - Want deeper control? See
docs/config.mdanddocs/install.md.
What's new in the Rust CLI
The Rust implementation is now the maintained Codex CLI and serves as the default experience. It includes a number of features that the legacy TypeScript CLI never supported.
Config
Codex supports a rich set of configuration options. Note that the Rust CLI uses config.toml instead of config.json. See docs/config.md for details.
Model Context Protocol Support
MCP client
Codex CLI functions as an MCP client that allows the Codex CLI and IDE extension to connect to MCP servers on startup. See the configuration documentation for details.
MCP server (experimental)
Codex can be launched as an MCP server by running codex mcp-server. This allows other MCP clients to use Codex as a tool for another agent.
Use the @modelcontextprotocol/inspector to try it out:
npx @modelcontextprotocol/inspector codex mcp-server
Use codex mcp to add/list/get/remove MCP server launchers defined in config.toml, and codex mcp-server to run the MCP server directly.
Notifications
You can enable notifications by configuring a script that is run whenever the agent finishes a turn. The notify documentation includes a detailed example that explains how to get desktop notifications via terminal-notifier on macOS. When Codex detects that it is running under WSL 2 inside Windows Terminal (WT_SESSION is set), the TUI automatically falls back to native Windows toast notifications so approval prompts and completed turns surface even though Windows Terminal does not implement OSC 9.
codex exec to run Codex programmatically/non-interactively
To run Codex non-interactively, run codex exec PROMPT (you can also pass the prompt via stdin) and Codex will work on your task until it decides that it is done and exits. If you provide both a prompt argument and piped stdin, Codex appends stdin as a <stdin> block after the prompt so patterns like echo "my output" | codex exec "Summarize this concisely" work naturally. Output is printed to the terminal directly. You can set the RUST_LOG environment variable to see more about what's going on.
Use codex exec --ephemeral ... to run without persisting session rollout files to disk.
Experimenting with the Codex Sandbox
To test to see what happens when a command is run under the sandbox provided by Codex, use the sandbox subcommand in Codex CLI:
# Uses the sandbox implementation for the current host OS:
# Seatbelt on macOS, the Linux sandbox on Linux, and Windows restricted token on Windows.
codex sandbox [COMMAND]...
# macOS-only diagnostic option
codex sandbox --log-denials [COMMAND]...
codex sandbox also accepts --profile NAME (-p NAME) to layer
$CODEX_HOME/NAME.config.toml onto the base user config for the sandboxed
command.
Selecting a sandbox policy via --sandbox
The Rust CLI exposes a dedicated --sandbox (-s) flag that lets you pick the sandbox policy without having to reach for the generic -c/--config option:
# Run Codex with the default, read-only sandbox
codex --sandbox read-only
# Allow the agent to write within the current workspace while still blocking network access
codex --sandbox workspace-write
# Danger! Disable sandboxing entirely (only do this if you are already running in a container or other isolated env)
codex --sandbox danger-full-access
In workspace-write, Codex also includes ~/.codex/memories in its writable roots so memory maintenance does not require an extra approval.
Code Organization
This folder is the root of a Cargo workspace. It contains quite a bit of experimental code, but here are the key crates:
core/contains the business logic for Codex. Ultimately, we hope this becomes a library crate that is generally useful for building other Rust/native applications that use Codex.exec/"headless" CLI for use in automation.tui/CLI that launches a fullscreen TUI built with Ratatui.cli/CLI multitool that provides the aforementioned CLIs via subcommands.
If you want to contribute or inspect behavior in detail, start by reading the module-level README.md files under each crate and run the project workspace from the top-level codex-rs directory so shared config, features, and build scripts stay aligned.