833c19ed53
## Why Raw output mode intentionally sends logical source lines to the terminal without Codex-inserted wrapping so copied content retains its original line structure. In Zellij, soft-wrapped continuation rows from those raw lines are not confined by the inline history scroll region. When raw mode replays a long transcript, continuation rows can occupy the composer viewport and are overwritten on the following draw, leaving the transcript visibly truncated underneath the composer. This is specific to the combination of Zellij and raw terminal-wrapped history. Rich output and non-Zellij terminals should continue using the existing insertion behavior. Related context: #20819 introduced raw output mode, and #22214 removed the broad Zellij insertion workaround after the standard rich-output path no longer required it. | Before | After | |---|---| | <img width="1728" height="916" alt="image" src="https://github.com/user-attachments/assets/f85398a5-e930-46d9-bcfd-106a24c41466" /> | <img width="1723" height="912" alt="image" src="https://github.com/user-attachments/assets/5c62e16a-a6e5-4842-bcb2-eab163cda04c" /> | ## What Changed - Cache Zellij detection in `Tui` and select a dedicated insertion mode only for `HistoryLineWrapPolicy::Terminal` batches in Zellij. - For that guarded path, clear the existing viewport, append raw source lines through the terminal so its soft wrapping remains selection-friendly, and reserve empty viewport rows before redrawing the composer. - Add snapshot regressions for both an incremental soft-wrapped raw insert and an overflowing raw transcript replay that starts at the top of the cleared terminal. ## How to Test 1. Start Codex inside Zellij with raw output enabled or toggle raw output after a multiline response is in history. 2. Produce or replay output containing long logical lines, such as a fenced shell command with several wrapped lines. 3. Confirm the wrapped history remains visible above the composer and the composer no longer overwrites the end of the response. 4. Toggle back to rich output or run outside Zellij and confirm standard history rendering still behaves normally. Targeted tests run: - `just test -p codex-tui vt100_zellij_raw -- --nocapture` Additional validation notes: - `just test -p codex-tui` was attempted; the two new Zellij raw insertion tests passed, while two existing `app::tests::update_feature_flags_disabling_guardian_*` tests failed outside this history insertion path. - `just argument-comment-lint` was attempted but local Bazel analysis fails before reaching the changed source because the LLVM `compiler-rt` package is missing `include/sanitizer/*.h`. Modified literal callsites were inspected manually.
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.