From aa3bd6f0425396c076383967a03b71f672c41a32 Mon Sep 17 00:00:00 2001
From: t <t@t.co>
Date: Tue, 14 Jul 2026 12:56:07 -0700
Subject: [PATCH] fix(test-harness): spawn claude without shell interpolation

---
 test/helpers/session-runner.ts | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/test/helpers/session-runner.ts b/test/helpers/session-runner.ts
index 01eb0243d..f433332f5 100644
--- a/test/helpers/session-runner.ts
+++ b/test/helpers/session-runner.ts
@@ -173,13 +173,9 @@ export async function runSkillTest(options: {
   // restores operator MCP along with the operator env.
   if (isHermeticEnabled()) args.push('--strict-mcp-config');
 
-  // 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(' ')}`], {
+  // Spawn claude directly with array-form args (no shell interpolation).
+  // Prompt is piped via stdin using a Blob to avoid temp files and shell escaping.
+  const proc = Bun.spawn(['claude', ...args], {
     cwd: workingDirectory,
     // Hermetic by default (see test/helpers/hermetic-env.ts): operator
     // session context (CONDUCTOR_*, CLAUDECODE, ~/.claude config, ~/.gstack)
@@ -189,6 +185,7 @@ export async function runSkillTest(options: {
     // suite exercising the INTERACTIVE prose-fallback path opts out by passing
     // `env: { GSTACK_HEADLESS: '' }` — extraEnv wins because it spreads last.
     env: hermeticChildEnv({ GSTACK_HEADLESS: '1', ...extraEnv }),
+    stdin: new Blob([prompt]),
     stdout: 'pipe',
     stderr: 'pipe',
   });
@@ -201,11 +198,12 @@ export async function runSkillTest(options: {
   const timeoutId = setTimeout(() => {
     timedOut = true;
     proc.kill();
-    // proc.kill() only signals the `sh -c` wrapper. The claude child it
-    // spawned can survive as an orphan that inherited our stdout/stderr
-    // pipes, so without cancel() the read loop below blocks until the
-    // orphan finally exits (observed: a 600s timeout stretching past 1400s
-    // and tripping bun's per-test timeout instead of returning a result).
+    // proc.kill() signals claude itself (direct spawn, no shell wrapper),
+    // but tool subprocesses claude spawned can survive as orphans that
+    // inherited our stdout/stderr pipes, so without cancel() the read loop
+    // below blocks until the orphan finally exits (observed: a 600s timeout
+    // stretching past 1400s and tripping bun's per-test timeout instead of
+    // returning a result).
     reader.cancel().catch(() => { /* stream already closed */ });
   }, timeout);
 
@@ -314,8 +312,6 @@ export async function runSkillTest(options: {
   const exitCode = await proc.exited;
   clearTimeout(timeoutId);
 
-  try { fs.unlinkSync(promptFile); } catch { /* non-fatal */ }
-
   if (timedOut) {
     exitReason = 'timeout';
   } else if (exitCode === 0) {