Felipe Coury
359e17a852
## TL;DR
- Fetches account/rateLimits/read asynchronously so the TUI can continue
starting without waiting for the rate-limit response.
- Fixes the /status card so it no longer leaves a stale “refreshing
cached limits...” notice in terminal history.
## Problem
The TUI bootstrap path fetched account rate limits synchronously
(`account/rateLimits/read`) before the event loop started for
ChatGPT/OpenAI-authenticated startups. This added ~670 ms of blocking
latency in the measured hot-start case, even though rate-limit data is
not needed to render the initial UI or accept user input. The delay was
especially noticeable on hot starts where every other RPC
(`account/read`, `model/list`, `thread/start`) completed in under 70 ms
total.
Moving that fetch to the background also exposed a `/status` UI bug: the
status card is flattened into terminal scrollback when it is inserted. A
transient "refreshing limits in background..." line could not be cleared
later, because the async completion updated the retained `HistoryCell`,
not the already-written terminal history.
## Mental model
Before this change, `AppServerSession::bootstrap()` performed three
sequential RPCs: `account/read` → `model/list` →
`account/rateLimits/read`. The result of the third call was baked into
`AppServerBootstrap` and applied to the chat widget before the event
loop began.
After this change, `bootstrap()` only performs two RPCs (`account/read`
+ `model/list`), and rate-limit fetching is kicked off as an async
background task immediately after the first frame is scheduled. A new
enum, `RateLimitRefreshOrigin`, tags each fetch so the event handler
knows whether the result came from the startup prefetch or from a
user-initiated `/status` command; they have different completion
side-effects.
The `get_login_status()` helper (used outside the main app flow) was
also decoupled: it previously called the full `bootstrap()` just to
check auth mode, wasting model-list and rate-limit work. It now calls
the narrower `read_account()` directly.
For `/status`, this PR keeps the background refresh request but stops
printing transient refresh notices into status history when cached
limits are already available. If a refresh updates the cache, the next
`/status` command will render the new values.
## Non-goals
- This change does not alter the rate-limit data itself.
- This change does not introduce caching, retries, or staleness
management for rate limits.
- This change does not affect the `model/list` or `thread/start` RPCs;
they remain on the critical startup path.
## Tradeoffs
- **Stale-on-first-render**: The status bar will briefly show no
rate-limit info until the background fetch completes; observed
background fetches landed roughly in the 400-900 ms range after the UI
appeared. This is acceptable because the user cannot meaningfully act on
rate-limit data in the first fraction of a second.
- **Error silence on startup prefetch**: If the startup prefetch fails,
the error is logged but the UI is not notified (unlike `/status` refresh
failures, which go through the status-command completion path). This
avoids surfacing transient network errors as a startup blocker.
- **Static `/status` history**: `/status` output is terminal history,
not a live widget. The card now avoids progress-style language that
would appear stuck in scrollback; users can run `/status` again to see
newly cached values.
- **`account_auth_mode` field removed from `AppServerBootstrap`**: The
only consumer was `get_login_status()`, which no longer goes through
`bootstrap()`. The field was dead weight.
## Architecture
### New types
- `RateLimitRefreshOrigin` (in `app_event.rs`): A `Copy` enum
distinguishing `StartupPrefetch` from `StatusCommand { request_id }`.
Carried through `RefreshRateLimits` and `RateLimitsLoaded` events so the
handler applies the right completion behavior.
### Modified types
- `AppServerBootstrap`: Lost `account_auth_mode` and
`rate_limit_snapshots`; gained `requires_openai_auth: bool` (passed
through from the account response so the caller can decide whether to
fire the prefetch).
### Control flow
1. `bootstrap()` returns with `requires_openai_auth` and
`has_chatgpt_account`.
2. After scheduling the first frame, `App::run_inner` fires
`refresh_rate_limits(StartupPrefetch)` if both flags are true.
3. When `RateLimitsLoaded { StartupPrefetch, Ok(..) }` arrives,
snapshots are applied and a frame is scheduled to repaint the status
bar.
4. When `RateLimitsLoaded { StartupPrefetch, Err(..) }` arrives, the
error is logged and no UI update occurs.
5. `/status`-initiated refreshes continue to use `StatusCommand {
request_id }` and call `finish_status_rate_limit_refresh` on completion
(success or failure).
6. `/status` history cells with cached rate-limit rows no longer render
an additional "refreshing limits" notice; the async refresh updates the
cache for future status output.
### Extracted method
- `AppServerSession::read_account()`: Factored out of `bootstrap()` so
that `get_login_status()` can call it independently without triggering
model-list or rate-limit work.
## Observability
- The existing `tracing::warn!` for rate-limit fetch failures is
preserved for the startup path.
- No new metrics or spans are introduced. The startup-time improvement
is observable via the existing `ready` timestamp in TUI startup logs.
## Tests
- Existing tests in `status_command_tests.rs` are updated to match on
`RateLimitRefreshOrigin::StatusCommand { request_id }` instead of a bare
`request_id`.
- Focused `/status` tests now assert that status history avoids
transient refresh text, continues to request an async refresh, and uses
refreshed cached limits in future status output.
- No new tests are added for the startup prefetch path because it is a
fire-and-forget spawn with no observable side-effect other than the
widget state update, which is already covered by the
snapshot-application tests.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.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. 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, 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.