fix(plan): sandbox path resolution in Plan Mode to prevent hallucinations (#22737)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

evals/plan_mode.eval.ts

@@ -132,6 +132,32 @@ 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',
+      );
+      expect(
+        exitPlanCall,
+        'Expected to find exit_plan_mode in tool logs',
+      ).toBeDefined();
+
+      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);
     },
   });
@@ -166,4 +192,89 @@ describe('plan_mode', () => {
       assertModelHasOutput(result);
     },
   });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'should create a plan in plan mode and implement it for a refactoring task',
+    params: {
+      settings,
+    },
+    files: {
+      'src/mathUtils.ts':
+        'export const sum = (a: number, b: number) => a + b;\nexport const multiply = (a: number, b: number) => a * b;',
+      'src/main.ts':
+        'import { sum } from "./mathUtils";\nconsole.log(sum(1, 2));',
+    },
+    prompt:
+      'I want to refactor our math utilities. Move the `sum` function from `src/mathUtils.ts` to a new file `src/basicMath.ts` and update `src/main.ts` to use the new file. Please create a detailed implementation plan first, then execute it.',
+    assert: async (rig, result) => {
+      const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
+      expect(
+        enterPlanCalled,
+        'Expected enter_plan_mode tool to be called',
+      ).toBe(true);
+
+      const exitPlanCalled = await rig.waitForToolCall('exit_plan_mode');
+      expect(exitPlanCalled, 'Expected exit_plan_mode tool to be called').toBe(
+        true,
+      );
+
+      await rig.waitForTelemetryReady();
+      const toolLogs = rig.readToolLogs();
+
+      const exitPlanCall = toolLogs.find(
+        (log) => log.toolRequest.name === 'exit_plan_mode',
+      );
+      expect(
+        exitPlanCall,
+        'Expected to find exit_plan_mode in tool logs',
+      ).toBeDefined();
+
+      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) =>
+          log.toolRequest.name === 'write_file' &&
+          log.toolRequest.args.includes('/plans/'),
+      );
+      expect(
+        planWrite,
+        'Expected a plan file to be written in the plans directory',
+      ).toBeDefined();
+
+      // Check for implementation files
+      const newFileWrite = toolLogs.find(
+        (log) =>
+          log.toolRequest.name === 'write_file' &&
+          log.toolRequest.args.includes('src/basicMath.ts'),
+      );
+      expect(
+        newFileWrite,
+        'Expected src/basicMath.ts to be created',
+      ).toBeDefined();
+
+      const mainUpdate = toolLogs.find(
+        (log) =>
+          ['write_file', 'replace'].includes(log.toolRequest.name) &&
+          log.toolRequest.args.includes('src/main.ts'),
+      );
+      expect(mainUpdate, 'Expected src/main.ts to be updated').toBeDefined();
+
+      assertModelHasOutput(result);
+    },
+  });
 });