Felipe Coury
e9996ec62a
## TL;DR When running codex with `-c features.tui_app_server=true` we see corruption when streaming large amounts of data. This PR marks other event types as _critical_ by making them _must-deliver_. ## Problem When the TUI consumer falls behind the app-server event stream, the bounded `mpsc` channel fills up and the forwarding layer drops events via `try_send`. Previously only `TurnCompleted` was marked as must-deliver. Streamed assistant text (`AgentMessageDelta`) and the authoritative final item (`ItemCompleted`) were treated as droppable — the same as ephemeral command output deltas. Because the TUI renders markdown incrementally from these deltas, dropping any of them produces permanently corrupted or incomplete paragraphs that persist for the rest of the session. ## Mental model The app-server event stream has two tiers of importance: 1. **Lossless (transcript + terminal):** Events that form the authoritative record of what the assistant said or that signal turn lifecycle transitions. Losing any of these corrupts the visible output or leaves surfaces waiting forever. These are: `AgentMessageDelta`, `PlanDelta`, `ReasoningSummaryTextDelta`, `ReasoningTextDelta`, `ItemCompleted`, and `TurnCompleted`. 2. **Best-effort (everything else):** Ephemeral status events like `CommandExecutionOutputDelta` and progress notifications. Dropping these under load causes cosmetic gaps but no permanent corruption. The forwarding layer uses `try_send` for best-effort events (dropping on backpressure) and blocking `send().await` for lossless events (applying back-pressure to the producer until the consumer catches up). ## Non-goals - Eliminating backpressure entirely. The bounded queue is intentional; this change only widens the set of events that survive it. - Changing the event protocol or adding new notification types. - Addressing root causes of consumer slowness (e.g. TUI render cost). ## Tradeoffs Blocking on transcript events means a slow consumer can now stall the producer for the duration of those events. This is acceptable because: (a) the alternative is permanently broken output, which is worse; (b) the consumer already had to keep up with `TurnCompleted` blocking sends; and (c) transcript events arrive at model-output speed, not burst speed, so sustained saturation is unlikely in practice. ## Architecture Two parallel changes, one per transport: - **In-process path** (`lib.rs`): The inline forwarding logic was extracted into `forward_in_process_event`, a standalone async function that encapsulates the lag-marker / must-deliver / try-send decision tree. The worker loop now delegates to it. A new `server_notification_requires_delivery` function (shared `pub(crate)`) centralizes the notification classification. - **Remote path** (`remote.rs`): The local `event_requires_delivery` now delegates to the same shared `server_notification_requires_delivery`, keeping both transports in sync. ## Observability No new metrics or log lines. The existing `warn!` on event drops continues to fire for best-effort events. Lossless events that block will not produce a log line (they simply wait). ## Tests - `event_requires_delivery_marks_transcript_and_terminal_events`: unit test confirming the expanded classification covers `AgentMessageDelta`, `ItemCompleted`, `TurnCompleted`, and excludes `CommandExecutionOutputDelta` and `Lagged`. - `forward_in_process_event_preserves_transcript_notifications_under_backpressure`: integration-style test that fills a capacity-1 channel, verifies a best-effort event is dropped (skipped count increments), then sends lossless transcript events and confirms they all arrive in order with the correct lag marker preceding them. - `remote_backpressure_preserves_transcript_notifications`: end-to-end test over a real websocket that verifies the remote transport preserves transcript events under the same backpressure scenario. - `event_requires_delivery_marks_transcript_and_disconnect_events` (remote): unit test confirming the remote-side classification covers transcript events and `Disconnected`. --------- Co-authored-by: Eric Traut <etraut@openai.com>
Codex CLI (Rust Implementation)
We provide Codex CLI as a standalone, native 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. 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, we provide the following subcommands in Codex CLI:
# macOS
codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...
# Linux
codex sandbox linux [--full-auto] [COMMAND]...
# Windows
codex sandbox windows [--full-auto] [COMMAND]...
# Legacy aliases
codex debug seatbelt [--full-auto] [--log-denials] [COMMAND]...
codex debug landlock [--full-auto] [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
The same setting can be persisted in ~/.codex/config.toml via the top-level sandbox_mode = "MODE" key, e.g. sandbox_mode = "workspace-write".
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 to be 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.