diff --git a/test/helpers/agent-sdk-runner.ts b/test/helpers/agent-sdk-runner.ts
index ce4512bfe..c35585438 100644
--- a/test/helpers/agent-sdk-runner.ts
+++ b/test/helpers/agent-sdk-runner.ts
@@ -300,6 +300,14 @@ export async function runAgentSdkTest(
   const queryImpl: QueryProvider = opts.queryProvider ?? query;
   const model = opts.model ?? 'claude-opus-4-7';
 
+  // Default GSTACK_HEADLESS=1 so SDK-driven eval/E2E runs classify as headless: an
+  // AskUserQuestion failure BLOCKs instead of emitting a prose question no human can
+  // answer. Set ambiently (the SDK child inherits process.env) rather than via
+  // sdkOpts.env — passing an env object to the SDK breaks its auth pipeline (see
+  // CLAUDE.md). A suite testing the interactive prose-fallback path sets
+  // process.env.GSTACK_HEADLESS='' before calling.
+  if (process.env.GSTACK_HEADLESS === undefined) process.env.GSTACK_HEADLESS = '1';
+
   let attempt = 0;
   let lastErr: unknown = null;
 
diff --git a/test/helpers/providers/claude.ts b/test/helpers/providers/claude.ts
index 5e3c1acb1..ce77767c2 100644
--- a/test/helpers/providers/claude.ts
+++ b/test/helpers/providers/claude.ts
@@ -52,6 +52,9 @@ export class ClaudeAdapter implements ProviderAdapter {
         timeout: opts.timeoutMs,
         encoding: 'utf-8',
         maxBuffer: 32 * 1024 * 1024,
+        // Default GSTACK_HEADLESS=1 so a benchmark run classifies as headless (an
+        // AskUserQuestion failure BLOCKs rather than emitting unanswerable prose).
+        env: { ...process.env, GSTACK_HEADLESS: '1' },
       });
       const parsed = this.parseOutput(out);
       return {
diff --git a/test/helpers/session-runner.ts b/test/helpers/session-runner.ts
index ae0454335..675255cf2 100644
--- a/test/helpers/session-runner.ts
+++ b/test/helpers/session-runner.ts
@@ -176,7 +176,11 @@ export async function runSkillTest(options: {
 
   const proc = Bun.spawn(['sh', '-c', `cat "${promptFile}" | claude ${args.map(a => `"${a}"`).join(' ')}`], {
     cwd: workingDirectory,
-    env: extraEnv ? { ...process.env, ...extraEnv } : undefined,
+    // Default GSTACK_HEADLESS=1 so eval/E2E runs classify as headless (BLOCK on an
+    // AskUserQuestion failure rather than emit a prose question no human reads). A
+    // suite exercising the INTERACTIVE prose-fallback path opts out by passing
+    // `env: { GSTACK_HEADLESS: '' }` — extraEnv wins because it spreads last.
+    env: { ...process.env, GSTACK_HEADLESS: '1', ...extraEnv },
     stdout: 'pipe',
     stderr: 'pipe',
   });