From 08f4937134fd316a251995f5b734d56db2f3e8b3 Mon Sep 17 00:00:00 2001
From: Garry Tan <garrytan@gmail.com>
Date: Sat, 21 Mar 2026 13:59:24 -0700
Subject: [PATCH] fix: move prompt temp file outside workingDirectory to
 prevent race condition

The .prompt-tmp file was written inside workingDirectory, which gets deleted
by afterAll cleanup. With --concurrent --retry, afterAll can interleave with
retries, causing "No such file or directory" crashes at 0s (seen in
review-design-lite and office-hours-spec-review).

Fix: write prompt file to os.tmpdir() with a unique suffix so it survives
directory cleanup. Also convert review-design-lite from describeE2E to
describeIfSelected for proper diff-based test selection.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 test/helpers/session-runner.ts | 6 ++++--
 test/skill-e2e-review.test.ts  | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/test/helpers/session-runner.ts b/test/helpers/session-runner.ts
index c9b85de0..ab9e2ee5 100644
--- a/test/helpers/session-runner.ts
+++ b/test/helpers/session-runner.ts
@@ -161,8 +161,10 @@ export async function runSkillTest(options: {
     '--allowed-tools', ...allowedTools,
   ];
 
-  // Write prompt to a temp file and pipe it via shell to avoid stdin buffering issues
-  const promptFile = path.join(workingDirectory, '.prompt-tmp');
+  // Write prompt to a temp file OUTSIDE workingDirectory to avoid race conditions
+  // where afterAll cleanup deletes the dir before cat reads the file (especially
+  // with --concurrent --retry). Using os.tmpdir() + unique suffix keeps it stable.
+  const promptFile = path.join(os.tmpdir(), `.prompt-${process.pid}-${Date.now()}-${Math.random().toString(36).slice(2)}`);
   fs.writeFileSync(promptFile, prompt);
 
   const proc = Bun.spawn(['sh', '-c', `cat "${promptFile}" | claude ${args.map(a => `"${a}"`).join(' ')}`], {
diff --git a/test/skill-e2e-review.test.ts b/test/skill-e2e-review.test.ts
index 2d1b8550..103c6c9c 100644
--- a/test/skill-e2e-review.test.ts
+++ b/test/skill-e2e-review.test.ts
@@ -2,7 +2,7 @@ import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
 import { runSkillTest } from './helpers/session-runner';
 import {
   ROOT, browseBin, runId, evalsEnabled, selectedTests,
-  describeIfSelected, describeE2E, testConcurrentIfSelected,
+  describeIfSelected, testConcurrentIfSelected,
   copyDirSync, setupBrowseShims, logCost, recordE2E,
   createEvalCollector, finalizeEvalCollector,
 } from './helpers/e2e-helpers';
@@ -161,7 +161,7 @@ The diff adds a new "returned" status to the Order model. Your job is to check i
 
 // --- Review: Design review lite E2E ---
 
-describeE2E('Review design lite E2E', () => {
+describeIfSelected('Review design lite E2E', ['review-design-lite'], () => {
   let designDir: string;
 
   beforeAll(() => {