core-agent-ide/codex-rs/command/src/powershell.rs
Michael Bolin d8f9bb65e2
# Split command parsing/safety out of codex-core into new codex-command (#11361)
`codex-core` had accumulated command parsing and command safety logic
(`bash`, `powershell`, `parse_command`, and `command_safety`) that is
logically cohesive but orthogonal to most core session/runtime logic.
Keeping this code in `codex-core` made the crate increasingly monolithic
and raised iteration cost for unrelated core changes.

This change extracts that surface into a dedicated crate,
`codex-command`, while preserving existing `codex_core::...` call sites
via re-exports.

## Why this refactor

During analysis, command parsing/safety stood out as a good first split
because it has:

- a clear domain boundary (shell parsing + safety classification)
- relatively self-contained dependencies (notably `tree-sitter` /
`tree-sitter-bash`)
- a meaningful standalone test surface (`134` tests moved with the
crate)
- many downstream uses that benefit from independent compilation and
caching

The practical problem was build latency from a large `codex-core`
compile/test graph. Clean-build timings before and after this split
showed measurable wins:

- `cargo check -p codex-core`: `57.08s` -> `53.54s` (~`6.2%` faster)
- `cargo test -p codex-core --no-run`: `2m39.9s` -> `2m20s` (~`12.4%`
faster)
- `codex-core lib` compile unit: `57.18s` -> `49.67s` (~`13.1%` faster)
- `codex-core lib(test)` compile unit: `60.87s` -> `53.21s` (~`12.6%`
faster)

This gives a concrete reduction in core build overhead without changing
behavior.

## What changed

### New crate

- Added `codex-rs/command` as workspace crate `codex-command`.
- Added:
  - `command/src/lib.rs`
  - `command/src/bash.rs`
  - `command/src/powershell.rs`
  - `command/src/parse_command.rs`
  - `command/src/command_safety/*`
  - `command/src/shell_detect.rs`
  - `command/BUILD.bazel`

### Code moved out of `codex-core`

- Moved modules from `core/src` into `command/src`:
  - `bash.rs`
  - `powershell.rs`
  - `parse_command.rs`
  - `command_safety/*`

### Dependency graph updates

- Added workspace member/dependency entries for `codex-command` in
`codex-rs/Cargo.toml`.
- Added `codex-command` dependency to `codex-rs/core/Cargo.toml`.
- Removed `tree-sitter` and `tree-sitter-bash` from `codex-core` direct
deps (now owned by `codex-command`).

### API compatibility for callers

To avoid immediate downstream churn, `codex-core` now re-exports the
moved modules/functions:

- `codex_command::bash`
- `codex_command::powershell`
- `codex_command::parse_command`
- `codex_command::is_safe_command`
- `codex_command::is_dangerous_command`

This keeps existing `codex_core::...` paths working while enabling
gradual migration to direct `codex-command` usage.

### Internal decoupling detail

- Added `command::shell_detect` so moved `bash`/`powershell` logic no
longer depends on core shell internals.
- Adjusted PowerShell helper visibility in `codex-command` for existing
core test usage (`UTF8` prefix helper + executable discovery functions).

## Validation

- `just fmt`
- `just fix -p codex-command -p codex-core`
- `cargo test -p codex-command` (`134` passed)
- `cargo test -p codex-core --no-run`
- `cargo test -p codex-core shell_command_handler`

## Notes / follow-up

This commit intentionally prioritizes boundary extraction and
compatibility. A follow-up can migrate downstream crates to depend
directly on `codex-command` (instead of through `codex-core` re-exports)
to realize additional incremental build wins.
2026-02-10 14:43:16 -08:00

204 lines
6.8 KiB
Rust

use std::path::PathBuf;
use codex_utils_absolute_path::AbsolutePathBuf;
use crate::shell_detect::ShellType;
use crate::shell_detect::detect_shell_type;
const POWERSHELL_FLAGS: &[&str] = &["-nologo", "-noprofile", "-command", "-c"];
/// Prefixed command for powershell shell calls to force UTF-8 console output.
pub const UTF8_OUTPUT_PREFIX: &str = "[Console]::OutputEncoding=[System.Text.Encoding]::UTF8;\n";
pub fn prefix_powershell_script_with_utf8(command: &[String]) -> Vec<String> {
let Some((_, script)) = extract_powershell_command(command) else {
return command.to_vec();
};
let trimmed = script.trim_start();
let script = if trimmed.starts_with(UTF8_OUTPUT_PREFIX) {
script.to_string()
} else {
format!("{UTF8_OUTPUT_PREFIX}{script}")
};
let mut command: Vec<String> = command[..(command.len() - 1)]
.iter()
.map(std::string::ToString::to_string)
.collect();
command.push(script);
command
}
/// Extract the PowerShell script body from an invocation such as:
///
/// - ["pwsh", "-NoProfile", "-Command", "Get-ChildItem -Recurse | Select-String foo"]
/// - ["powershell.exe", "-Command", "Write-Host hi"]
/// - ["powershell", "-NoLogo", "-NoProfile", "-Command", "...script..."]
///
/// Returns (`shell`, `script`) when the first arg is a PowerShell executable and a
/// `-Command` (or `-c`) flag is present followed by a script string.
pub fn extract_powershell_command(command: &[String]) -> Option<(&str, &str)> {
if command.len() < 3 {
return None;
}
let shell = &command[0];
if !matches!(
detect_shell_type(&PathBuf::from(shell)),
Some(ShellType::PowerShell)
) {
return None;
}
// Find the first occurrence of -Command (accept common short alias -c as well)
let mut i = 1usize;
while i + 1 < command.len() {
let flag = &command[i];
// Reject unknown flags
if !POWERSHELL_FLAGS.contains(&flag.to_ascii_lowercase().as_str()) {
return None;
}
if flag.eq_ignore_ascii_case("-Command") || flag.eq_ignore_ascii_case("-c") {
let script = &command[i + 1];
return Some((shell, script));
}
i += 1;
}
None
}
/// This function attempts to find a valid PowerShell executable on the system.
/// It first tries to find pwsh.exe, and if that fails, it tries to find
/// powershell.exe.
#[cfg(windows)]
#[allow(dead_code)]
pub(crate) fn try_find_powershellish_executable_blocking() -> Option<AbsolutePathBuf> {
if let Some(pwsh_path) = try_find_pwsh_executable_blocking() {
Some(pwsh_path)
} else {
try_find_powershell_executable_blocking()
}
}
/// This function attempts to find a powershell.exe executable on the system.
pub fn try_find_powershell_executable_blocking() -> Option<AbsolutePathBuf> {
try_find_powershellish_executable_in_path(&["powershell.exe"])
}
/// This function attempts to find a pwsh.exe executable on the system.
/// Note that pwsh.exe and powershell.exe are different executables:
///
/// - pwsh.exe is the cross-platform PowerShell Core (v6+) executable
/// - powershell.exe is the Windows PowerShell (v5.1 and earlier) executable
///
/// Further, while powershell.exe is included by default on Windows systems,
/// pwsh.exe must be installed separately by the user. And even when the user
/// has installed pwsh.exe, it may not be available in the system PATH, in which
/// case we attempt to locate it via other means.
pub fn try_find_pwsh_executable_blocking() -> Option<AbsolutePathBuf> {
if let Some(ps_home) = std::process::Command::new("cmd")
.args(["/C", "pwsh", "-NoProfile", "-Command", "$PSHOME"])
.output()
.ok()
.and_then(|out| {
if !out.status.success() {
return None;
}
let stdout = String::from_utf8_lossy(&out.stdout);
let trimmed = stdout.trim();
(!trimmed.is_empty()).then(|| trimmed.to_string())
})
{
let candidate = AbsolutePathBuf::resolve_path_against_base("pwsh.exe", &ps_home);
if let Ok(candidate_abs_path) = candidate
&& is_powershellish_executable_available(candidate_abs_path.as_path())
{
return Some(candidate_abs_path);
}
}
try_find_powershellish_executable_in_path(&["pwsh.exe"])
}
fn try_find_powershellish_executable_in_path(candidates: &[&str]) -> Option<AbsolutePathBuf> {
for candidate in candidates {
let Ok(resolved_path) = which::which(candidate) else {
continue;
};
if !is_powershellish_executable_available(&resolved_path) {
continue;
}
let Ok(abs_path) = AbsolutePathBuf::from_absolute_path(resolved_path) else {
continue;
};
return Some(abs_path);
}
None
}
fn is_powershellish_executable_available(powershell_or_pwsh_exe: &std::path::Path) -> bool {
// This test works for both powershell.exe and pwsh.exe.
std::process::Command::new(powershell_or_pwsh_exe)
.args(["-NoLogo", "-NoProfile", "-Command", "Write-Output ok"])
.output()
.map(|output| output.status.success())
.unwrap_or(false)
}
#[cfg(test)]
mod tests {
use super::extract_powershell_command;
#[test]
fn extracts_basic_powershell_command() {
let cmd = vec![
"powershell".to_string(),
"-Command".to_string(),
"Write-Host hi".to_string(),
];
let (_shell, script) = extract_powershell_command(&cmd).expect("extract");
assert_eq!(script, "Write-Host hi");
}
#[test]
fn extracts_lowercase_flags() {
let cmd = vec![
"powershell".to_string(),
"-nologo".to_string(),
"-command".to_string(),
"Write-Host hi".to_string(),
];
let (_shell, script) = extract_powershell_command(&cmd).expect("extract");
assert_eq!(script, "Write-Host hi");
}
#[test]
fn extracts_full_path_powershell_command() {
let command = if cfg!(windows) {
"C:\\windows\\System32\\WindowsPowerShell\\v1.0\\powershell.exe".to_string()
} else {
"/usr/local/bin/powershell.exe".to_string()
};
let cmd = vec![command, "-Command".to_string(), "Write-Host hi".to_string()];
let (_shell, script) = extract_powershell_command(&cmd).expect("extract");
assert_eq!(script, "Write-Host hi");
}
#[test]
fn extracts_with_noprofile_and_alias() {
let cmd = vec![
"pwsh".to_string(),
"-NoProfile".to_string(),
"-c".to_string(),
"Get-ChildItem | Select-String foo".to_string(),
];
let (_shell, script) = extract_powershell_command(&cmd).expect("extract");
assert_eq!(script, "Get-ChildItem | Select-String foo");
}
}