## Summary Backport #40994 to the 0.150 stable release line. Enable `compaction_image_budget` by default so retained images count against the existing remote-compaction token budget and older images are trimmed as needed. Explicitly disabling the feature preserves the previous behavior. The runtime change is a clean cherry-pick of `528fd7ace5ec0a1c2a387dcb9c76a09f3fa011ee`. The implementation is already present in 0.150.0; only the feature default/stability and the existing integration test expectations change. CI-only corrections address failures already present in the public release base: recognize the valid `OFlags::WRONLY` identifier in codespell, remove the obsolete code-mode manifest-feature exception, remove an unused test import left by the public export, and stage the code-mode host beside the CLI in SDK tests. The SDK staging change matches the existing internal workflow. These changes do not alter CLI runtime behavior or dependencies. ## Validation - Existing integration coverage exercises default/on/off behavior across repeated compactions and checks retained images in follow-up requests. - `just test -p codex-features`: 39 passed, none skipped. - `just test -p codex-core --test all remote_compact_v2_charges_retained_images_to_token_budget`: all three default/on/off cases passed. - `just test -p codex-core --lib image_budget_tests`: 4 passed. - `python3 .github/scripts/verify_cargo_workspace_manifests.py`, the pinned codespell check for the affected identifier, pinned `just fmt`, and `git diff --check` passed. - CI must pass on the final head before release. ## Release Targets `release/0.150`, based on the source commit for 0.150.0 (`076f17c114b0a82d7235552ccec5ff2d69f3266a`). Intended for the next 0.150 stable patch. --------- Co-authored-by: pakrym-oai <pakrym@openai.com>
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.
If you want the desktop app experience, run
codex app or visit the Codex App page.
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.
Quickstart
Installing and running Codex CLI
Run the following on Mac or Linux to install Codex CLI:
curl -fsSL https://chatgpt.com/codex/install.sh | sh
Run the following on Windows to install Codex CLI:
powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex"
The standalone installers download from https://releases.openai.com/codex by default and fall back to GitHub Releases if a metadata or asset download is unavailable. To force GitHub Releases, set CODEX_INSTALLER_USE_RELEASES_OPENAI_COM to false (0 and no are also accepted):
curl -fsSL https://chatgpt.com/codex/install.sh | CODEX_INSTALLER_USE_RELEASES_OPENAI_COM=false sh
$env:CODEX_INSTALLER_USE_RELEASES_OPENAI_COM='false'; irm https://chatgpt.com/codex/install.ps1 | iex
Codex CLI can also be installed via the following package managers:
# Install using npm
npm install -g @openai/codex
# Install using Homebrew
brew install --cask codex
Then simply run codex to get started.
You can also go to the latest GitHub Release and download the appropriate binary for your platform.
Each GitHub Release contains many executables, but in practice, you likely want one of these:
- macOS
- Apple Silicon/arm64:
codex-aarch64-apple-darwin.tar.gz - x86_64 (older Mac hardware):
codex-x86_64-apple-darwin.tar.gz
- Apple Silicon/arm64:
- Linux
- x86_64:
codex-x86_64-unknown-linux-musl.tar.gz - arm64:
codex-aarch64-unknown-linux-musl.tar.gz
- x86_64:
Each archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.
Using Codex with your ChatGPT plan
Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.
You can also use Codex with an API key, but this requires additional setup.
Docs
This repository is licensed under the Apache-2.0 License.
