970e466ab3
#2747 encouraged me to audit our codebase for similar issues, as now I am particularly suspicious that our flaky tests are due to a racy deadlock. I asked Codex to audit our code, and one of its suggestions was this: > **High-Risk Patterns** > > All `send_*` methods await on a bounded `mpsc::Sender<OutgoingMessage>`. If the writer blocks, the channel fills and the processor task blocks on send, stops draining incoming requests, and stdin reader eventually blocks on its send. This creates a backpressure deadlock cycle across the three tasks. > > **Recommendations** > * Server outgoing path: break the backpressure cycle > * Option A (minimal risk): Change `OutgoingMessageSender` to use an unbounded channel to decouple producer from stdout. Add rate logging so floods are visible. > * Option B (bounded + drop policy): Change `send_*` to try_send and drop messages (or coalesce) when the queue is full, logging a warning. This prevents processor stalls at the cost of losing messages under extreme backpressure. > * Option C (two-stage buffer): Keep bounded channel, but have a dedicated “egress” task that drains an unbounded internal queue, writing to stdout with retries and a shutdown timeout. This centralizes backpressure policy. So this PR is Option A. Indeed, we previously used a bounded channel with a capacity of `128`, but as we discovered recently with #2776, there are certainly cases where we can get flooded with events. That said, `test_shell_command_approval_triggers_elicitation` just failed one one build when I put up this PR, so clearly we are not out of the woods yet... **Update:** I think I found the true source of the deadlock! See https://github.com/openai/codex/pull/2876
OpenAI Codex CLI
npm i -g @openai/codex
or brew install codex
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
If you are looking for the cloud-based agent from OpenAI, Codex Web, see chatgpt.com/codex.
Quickstart
Installing and running Codex CLI
Install globally with your preferred package manager. If you use npm:
npm install -g @openai/codex
Alternatively, if you use Homebrew:
brew install codex
Then simply run codex to get started:
codex
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, Team, 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. If you previously used an API key for usage-based billing, see the migration steps. If you're having trouble with login, please comment on this issue.
Model Context Protocol (MCP)
Codex CLI supports MCP servers. Enable by adding an mcp_servers section to your ~/.codex/config.toml.
Configuration
Codex CLI supports a rich set of configuration options, with preferences stored in ~/.codex/config.toml. For full configuration options, see Configuration.
Docs & FAQ
- Getting started
- Sandbox & approvals
- Authentication
- Advanced
- Zero data retention (ZDR)
- Contributing
- Install & build
- FAQ
- Open source fund
License
This repository is licensed under the Apache-2.0 License.