diff --git a/evals/subprocess-xml.eval.ts b/evals/subprocess-xml.eval.ts
new file mode 100644
index 0000000000..44dfbf3bd6
--- /dev/null
+++ b/evals/subprocess-xml.eval.ts
@@ -0,0 +1,67 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('Subprocess XML tagging behavior', () => {
+ evalTest('ALWAYS_PASSES', {
+ name: 'should detect successful command execution with exit code 0',
+ prompt:
+ "Run 'echo Hello' and tell me if it succeeded. Only say 'Yes' or 'No'.",
+ assert: async (rig, result) => {
+ await rig.waitForToolCall('run_shell_command');
+ expect(result.toLowerCase()).toContain('yes');
+
+ const lastRequest = rig.readLastApiRequest();
+ expect(lastRequest?.attributes?.request_text).toContain(
+ '0',
+ );
+ },
+ });
+
+ evalTest('ALWAYS_PASSES', {
+ name: 'should detect failed command execution with non-zero exit code',
+ prompt:
+ "Run 'ls non_existent_file_12345' and tell me if it failed. Only say 'Yes' or 'No'.",
+ assert: async (rig, result) => {
+ await rig.waitForToolCall('run_shell_command');
+ expect(result.toLowerCase()).toContain('yes');
+
+ const lastRequest = rig.readLastApiRequest();
+ expect(lastRequest?.attributes?.request_text).toMatch(
+ /[1-9]\d*<\/exit_code>/,
+ );
+ },
+ });
+
+ evalTest('ALWAYS_PASSES', {
+ name: 'should correctly parse content from