From 96752a13f60b396c4c1c5816f6ff612315aa845c Mon Sep 17 00:00:00 2001
From: "A.K.M. Adib" <adibakm@google.com>
Date: Mon, 23 Mar 2026 14:14:51 -0400
Subject: [PATCH] update evals for changes

---
 evals/plan_mode.eval.ts | 46 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/evals/plan_mode.eval.ts b/evals/plan_mode.eval.ts
index a37e5f91b4..9794dd2b6b 100644
--- a/evals/plan_mode.eval.ts
+++ b/evals/plan_mode.eval.ts
@@ -136,6 +136,30 @@ describe('plan_mode', () => {
       expect(wasToolCalled, 'Expected exit_plan_mode tool to be called').toBe(
         true,
       );
+
+      const toolLogs = rig.readToolLogs();
+      const exitPlanCall = toolLogs.find(
+        (log) => log.toolRequest.name === 'exit_plan_mode',
+      );
+      if (exitPlanCall) {
+        const args = JSON.parse(exitPlanCall.toolRequest.args);
+        expect(
+          args.plan_filename,
+          'plan_filename should be a string',
+        ).toBeTypeOf('string');
+        expect(args.plan_filename, 'plan_filename should end with .md').toMatch(
+          /\.md$/,
+        );
+        expect(
+          args.plan_filename,
+          'plan_filename should not be a path',
+        ).not.toContain('/');
+        expect(
+          args.plan_filename,
+          'plan_filename should not be a path',
+        ).not.toContain('\\');
+      }
+
       assertModelHasOutput(result);
     },
   });
@@ -199,6 +223,28 @@ describe('plan_mode', () => {
       await rig.waitForTelemetryReady();
       const toolLogs = rig.readToolLogs();
 
+      const exitPlanCall = toolLogs.find(
+        (log) => log.toolRequest.name === 'exit_plan_mode',
+      );
+      if (exitPlanCall) {
+        const args = JSON.parse(exitPlanCall.toolRequest.args);
+        expect(
+          args.plan_filename,
+          'plan_filename should be a string',
+        ).toBeTypeOf('string');
+        expect(args.plan_filename, 'plan_filename should end with .md').toMatch(
+          /\.md$/,
+        );
+        expect(
+          args.plan_filename,
+          'plan_filename should not be a path',
+        ).not.toContain('/');
+        expect(
+          args.plan_filename,
+          'plan_filename should not be a path',
+        ).not.toContain('\\');
+      }
+
       // Check if plan was written
       const planWrite = toolLogs.find(
         (log) =>