mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
Michael Bolin
3c7f013f97
## Why `ToolHandler` was still paying a large compile-time tax from `#[async_trait]` on every concrete handler impl, even though the only object-safe boundary the registry actually stores is the internal `AnyToolHandler` adapter. This PR removes that macro-generated async wrapper layer from concrete `ToolHandler` impls while keeping the existing object-safe shim in `AnyToolHandler`. In practice, that gets essentially the same compile-time win as the larger type-erasure refactor in #16627, but with a much smaller diff and without changing the public shape of `ToolHandler<Output = T>`. That tradeoff matters here because this is a broad `codex-core` hotspot and reviewers should be able to judge the compile-time impact from hard numbers, not vibes. ## Headline result On a clean `codex-core` package rebuild (`cargo clean -p codex-core` before each command), rustc `total` dropped from **187.15s to 68.98s** versus the shared `0bd31dc382bd` baseline: **-63.1%**. The biggest hot passes dropped by roughly **71-72%**: | Metric | Baseline `0bd31dc382bd` | This PR `41f7ac0adeac` | Delta | |---|---:|---:|---:| | `total` | 187.15s | 68.98s | **-63.1%** | | `generate_crate_metadata` | 84.53s | 24.49s | **-71.0%** | | `MIR_borrow_checking` | 84.13s | 24.58s | **-70.8%** | | `monomorphization_collector_graph_walk` | 79.74s | 22.19s | **-72.2%** | | `evaluate_obligation` self-time | 180.62s | 46.91s | **-74.0%** | Important caveat: `-Z time-passes` timings are nested, so `generate_crate_metadata` and `monomorphization_collector_graph_walk` are mostly overlapping, not additive. ## Why this PR over #16627 #16627 already proved that the `ToolHandler` stack was the right hotspot, but it got there by making `ToolHandler` object-safe and changing every handler to return `BoxFuture<Result<AnyToolResult, _>>` directly. This PR keeps the lower-churn shape: - `ToolHandler` remains generic over `type Output`. - Concrete handlers use native RPITIT futures with explicit `Send` bounds. - `AnyToolHandler` remains the only object-safe adapter and still does the boxing at the registry boundary, as before. - The implementation diff is only **33 files, +28/-77**. The measurements are at least comparable, and in this run this PR is slightly faster than #16627 on the pass-level total: | Metric | #16627 | This PR | Delta | |---|---:|---:|---:| | `total` | 79.90s | 68.98s | **-13.7%** | | `generate_crate_metadata` | 25.88s | 24.49s | **-5.4%** | | `monomorphization_collector_graph_walk` | 23.54s | 22.19s | **-5.7%** | | `evaluate_obligation` self-time | 43.29s | 46.91s | +8.4% | ## Profile data ### Crate-level timings `cargo +nightly build -p codex-core --lib -Z unstable-options --timings=json` after `cargo clean -p codex-core`. Baseline data below is reused from the shared parent `0bd31dc382bd` profile because this PR and #16627 are both one commit on top of that same parent. | Crate | Baseline `duration` | This PR `duration` | Delta | Baseline `rmeta_time` | This PR `rmeta_time` | Delta | |---|---:|---:|---:|---:|---:|---:| | `codex_core` | 187.380776583s | 69.171113833s | **-63.1%** | 174.474507208s | 55.873015583s | **-68.0%** | | `starlark` | 17.90s | 16.773824125s | -6.3% | n/a | 8.8999965s | n/a | ### Pass-level timings `cargo +nightly rustc -p codex-core --lib -- -Z time-passes -Z time-passes-format=json` after `cargo clean -p codex-core`. | Pass | Baseline | This PR | Delta | |---|---:|---:|---:| | `total` | 187.150662083s | 68.978770375s | **-63.1%** | | `generate_crate_metadata` | 84.531864625s | 24.487462958s | **-71.0%** | | `MIR_borrow_checking` | 84.131389375s | 24.575553875s | **-70.8%** | | `monomorphization_collector_graph_walk` | 79.737515042s | 22.190207417s | **-72.2%** | | `codegen_crate` | 12.362532292s | 12.695237625s | +2.7% | | `type_check_crate` | 4.4765405s | 5.442019542s | +21.6% | | `coherence_checking` | 3.311121208s | 4.239935292s | +28.0% | | process `real` / `user` / `sys` | 187.70s / 201.87s / 4.99s | 69.52s / 85.90s / 2.92s | n/a | ### Self-profile query summary `cargo +nightly rustc -p codex-core --lib -- -Z self-profile=... -Z self-profile-events=default,query-keys,args,llvm,artifact-sizes` after `cargo clean -p codex-core`, summarized with `measureme summarize -p 0.5`. | Query / phase | Baseline self time | This PR self time | Delta | Baseline total time | This PR total time | Baseline item count | This PR item count | Baseline cache hits | This PR cache hits | |---|---:|---:|---:|---:|---:|---:|---:|---:|---:| | `evaluate_obligation` | 180.62s | 46.91s | **-74.0%** | 182.08s | 48.37s | 572,234 | 388,659 | 1,130,998 | 1,058,553 | | `mir_borrowck` | 1.42s | 1.49s | +4.9% | 93.77s | 29.59s | n/a | 6,184 | n/a | 15,298 | | `typeck` | 1.84s | 1.87s | +1.6% | 2.38s | 2.44s | n/a | 9,367 | n/a | 79,247 | | `LLVM_module_codegen_emit_obj` | n/a | 17.12s | n/a | 17.01s | 17.12s | n/a | 256 | n/a | 0 | | `LLVM_passes` | n/a | 13.07s | n/a | 12.95s | 13.07s | n/a | 1 | n/a | 0 | | `codegen_module` | n/a | 12.33s | n/a | 12.22s | 13.64s | n/a | 256 | n/a | 0 | | `items_of_instance` | n/a | 676.00ms | n/a | n/a | 24.96s | n/a | 99,990 | n/a | 0 | | `type_op_prove_predicate` | n/a | 660.79ms | n/a | n/a | 24.78s | n/a | 78,762 | n/a | 235,877 | | Summary | Baseline | This PR | |---|---:|---:| | `evaluate_obligation` % of total CPU | 70.821% | 38.880% | | self-profile total CPU time | 255.042999997s | 120.661175956s | | process `real` / `user` / `sys` | 220.96s / 235.02s / 7.09s | 86.35s / 103.66s / 3.54s | ### Artifact sizes From the same `measureme summarize` output: | Artifact | Baseline | This PR | Delta | |---|---:|---:|---:| | `crate_metadata` | 26,534,471 bytes | 26,545,248 bytes | +10,777 | | `dep_graph` | 253,181,425 bytes | 239,240,806 bytes | -13,940,619 | | `linked_artifact` | 565,366,624 bytes | 562,673,176 bytes | -2,693,448 | | `object_file` | 513,127,264 bytes | 510,464,096 bytes | -2,663,168 | | `query_cache` | 137,440,945 bytes | 136,982,566 bytes | -458,379 | | `cgu_instructions` | 3,586,307 bytes | 3,575,121 bytes | -11,186 | | `codegen_unit_size_estimate` | 2,084,846 bytes | 2,078,773 bytes | -6,073 | | `work_product_index` | 19,565 bytes | 19,565 bytes | 0 | ### Baseline hotspots before this change These are the top normalized obligation buckets from the shared baseline profile: | Obligation bucket | Samples | Duration | |---|---:|---:| | `outlives:tasks::review::ReviewTask` | 1,067 | 6.33s | | `outlives:tools::handlers::unified_exec::UnifiedExecHandler` | 896 | 5.63s | | `trait:T as tools::registry::ToolHandler` | 876 | 5.45s | | `outlives:tools::handlers::shell::ShellHandler` | 888 | 5.37s | | `outlives:tools::handlers::shell::ShellCommandHandler` | 870 | 5.29s | | `outlives:tools::runtimes::shell::unix_escalation::CoreShellActionProvider` | 637 | 3.73s | | `outlives:tools::handlers::mcp::McpHandler` | 695 | 3.61s | | `outlives:tasks::regular::RegularTask` | 726 | 3.57s | Top `items_of_instance` entries before this change were mostly concrete async handler/task impls: | Instance | Duration | |---|---:| | `tasks::regular::{impl#2}::run` | 3.79s | | `tools::handlers::mcp::{impl#0}::handle` | 3.27s | | `tools::runtimes::shell::unix_escalation::{impl#2}::determine_action` | 3.09s | | `tools::handlers::agent_jobs::{impl#11}::handle` | 3.07s | | `tools::handlers::multi_agents::spawn::{impl#1}::handle` | 2.84s | | `tasks::review::{impl#4}::run` | 2.82s | | `tools::handlers::multi_agents_v2::spawn::{impl#2}::handle` | 2.80s | | `tools::handlers::multi_agents::resume_agent::{impl#1}::handle` | 2.73s | | `tools::handlers::unified_exec::{impl#2}::handle` | 2.54s | | `tasks::compact::{impl#4}::run` | 2.45s | ## What changed Relevant pre-change registry shape: [`codex-rs/core/src/tools/registry.rs`](https://github.com/openai/codex/blob/0bd31dc382bd1c33dc2bb6b97069c76aa10ba14b/codex-rs/core/src/tools/registry.rs#L38-L219) Current registry shape in this PR: [`codex-rs/core/src/tools/registry.rs`](https://github.com/openai/codex/blob/41f7ac0adeac81d667541853d6546267d6083613/codex-rs/core/src/tools/registry.rs#L38-L203) - `ToolHandler::{is_mutating, handle}` now return native `impl Future + Send` futures instead of using `#[async_trait]`. - `AnyToolHandler` remains the object-safe adapter and boxes those futures at the registry boundary with explicit lifetimes. - Concrete handlers and the registry test handler drop `#[async_trait]` but otherwise keep their async method bodies intact. - Representative examples: [`codex-rs/core/src/tools/handlers/shell.rs`](https://github.com/openai/codex/blob/41f7ac0adeac81d667541853d6546267d6083613/codex-rs/core/src/tools/handlers/shell.rs#L223-L379), [`codex-rs/core/src/tools/handlers/unified_exec.rs`](https://github.com/openai/codex/blob/41f7ac0adeac81d667541853d6546267d6083613/codex-rs/core/src/tools/handlers/unified_exec.rs), [`codex-rs/core/src/tools/registry_tests.rs`](https://github.com/openai/codex/blob/41f7ac0adeac81d667541853d6546267d6083613/codex-rs/core/src/tools/registry_tests.rs) ## Tradeoff This is intentionally less invasive than #16627: it does **not** move result boxing into every concrete handler and does **not** change `ToolHandler` into an object-safe trait. Instead, it keeps the existing registry-level type-erasure boundary and only removes the macro-generated async wrapper layer from concrete impls. So the runtime boxing story stays basically the same as before, while the compile-time savings are still large. ## Verification Existing verification for this branch still applies: - Ran `cargo test -p codex-core`; this change compiled and the suite reached the known unrelated `config::tests::*guardian*` failures, with no local diff under `codex-rs/core/src/config/`. Profiling commands used for the tables above: - `cargo clean -p codex-core` - `cargo +nightly build -p codex-core --lib -Z unstable-options --timings=json` - `cargo +nightly rustc -p codex-core --lib -- -Z time-passes -Z time-passes-format=json` - `cargo +nightly rustc -p codex-core --lib -- -Z self-profile=... -Z self-profile-events=default,query-keys,args,llvm,artifact-sizes` - `measureme summarize -p 0.5`
3c7f013f97
·
2026-04-02 16:03:52 -07:00
History
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.