From 32aad7bd13e63baf7af96bf3d0c960a566da993e Mon Sep 17 00:00:00 2001
From: Dylan Hurd <dylan.hurd@openai.com>
Date: Fri, 24 Apr 2026 16:18:30 -0700
Subject: [PATCH] Serialize legacy Windows PowerShell sandbox tests (#19453)

## Why

Recent `main` CI had repeated Windows timeouts in the legacy sandbox
process tests:

- `codex-windows-sandbox
session::tests::legacy_capture_powershell_emits_output` failed in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
[24905411571](https://github.com/openai/codex/actions/runs/24905411571),
[24903336028](https://github.com/openai/codex/actions/runs/24903336028),
and
[24898949647](https://github.com/openai/codex/actions/runs/24898949647).
- `legacy_tty_powershell_emits_output_and_accepts_input` failed in the
same set of runs.
- `legacy_non_tty_cmd_emits_output` failed in runs
[24909500958](https://github.com/openai/codex/actions/runs/24909500958),
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
and
[24903336028](https://github.com/openai/codex/actions/runs/24903336028).
- `legacy_non_tty_powershell_emits_output` failed in runs
[24908076251](https://github.com/openai/codex/actions/runs/24908076251),
[24906197645](https://github.com/openai/codex/actions/runs/24906197645),
and
[24903336028](https://github.com/openai/codex/actions/runs/24903336028).

These failures were 30s timeouts on Windows x64 and/or arm64 rather than
assertion failures.

## Root Cause

The active legacy Windows sandbox process tests all exercise host-level
resources: sandbox setup, ACL/user state, private desktop process
launch, stdio capture, and PowerShell/cmd child cleanup. Running several
of these tests concurrently can leave them competing for the same
Windows sandbox setup path and process/session resources, which makes
command startup or output collection hang under CI load.

## What Changed

- Added a shared in-process mutex for the active legacy Windows sandbox
process tests.
- Held that guard across each legacy cmd/PowerShell process test so
those host-resource-heavy cases run one at a time.
- Kept the skipped legacy cmd TTY tests unchanged.

## Why This Should Be Reliable

The tests still use unique homes and run the real legacy sandbox process
path, but they no longer overlap the fragile host-level setup and
process/session lifecycle. Serializing just this small group removes the
concurrency race without reducing the behavioral coverage of each test.

## Verification

- `cargo test -p codex-windows-sandbox`
- GitHub Windows CI is the primary validation signal for the affected
tests; on this PR, Windows clippy, Windows release, and Windows local
Bazel passed after the serialization fix.
---
 .../windows-sandbox-rs/src/unified_exec/tests.rs    | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/codex-rs/windows-sandbox-rs/src/unified_exec/tests.rs b/codex-rs/windows-sandbox-rs/src/unified_exec/tests.rs
index a2bc7bebf..b0530a4fb 100644
--- a/codex-rs/windows-sandbox-rs/src/unified_exec/tests.rs
+++ b/codex-rs/windows-sandbox-rs/src/unified_exec/tests.rs
@@ -14,6 +14,8 @@ use std::io::Seek;
 use std::io::SeekFrom;
 use std::path::Path;
 use std::path::PathBuf;
+use std::sync::Mutex;
+use std::sync::MutexGuard;
 use std::sync::atomic::AtomicU64;
 use std::sync::atomic::Ordering;
 use std::time::Duration;
@@ -26,6 +28,13 @@ use tokio::sync::oneshot;
 use tokio::time::timeout;
 
 static TEST_HOME_COUNTER: AtomicU64 = AtomicU64::new(0);
+static LEGACY_PROCESS_TEST_LOCK: Mutex<()> = Mutex::new(());
+
+fn legacy_process_test_guard() -> MutexGuard<'static, ()> {
+    LEGACY_PROCESS_TEST_LOCK
+        .lock()
+        .expect("legacy Windows sandbox process test lock poisoned")
+}
 
 fn current_thread_runtime() -> tokio::runtime::Runtime {
     Builder::new_current_thread()
@@ -129,6 +138,7 @@ async fn collect_stdout_and_exit(
 
 #[test]
 fn legacy_non_tty_cmd_emits_output() {
+    let _guard = legacy_process_test_guard();
     let runtime = current_thread_runtime();
     runtime.block_on(async move {
         let cwd = sandbox_cwd();
@@ -167,6 +177,7 @@ fn legacy_non_tty_powershell_emits_output() {
     let Some(pwsh) = pwsh_path() else {
         return;
     };
+    let _guard = legacy_process_test_guard();
     let runtime = current_thread_runtime();
     runtime.block_on(async move {
         let cwd = sandbox_cwd();
@@ -351,6 +362,7 @@ fn legacy_capture_powershell_emits_output() {
     let Some(pwsh) = pwsh_path() else {
         return;
     };
+    let _guard = legacy_process_test_guard();
     let cwd = sandbox_cwd();
     let codex_home = sandbox_home("legacy-capture-pwsh");
     println!("capture pwsh codex_home={}", codex_home.path().display());
@@ -387,6 +399,7 @@ fn legacy_tty_powershell_emits_output_and_accepts_input() {
     let Some(pwsh) = pwsh_path() else {
         return;
     };
+    let _guard = legacy_process_test_guard();
     let runtime = current_thread_runtime();
     runtime.block_on(async move {
         let cwd = sandbox_cwd();