feat(core): discourage update topic tool for simple tasks (#24640)

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

evals/update_topic.eval.ts

@@ -5,6 +5,8 @@
  */
 
 import { describe, expect } from 'vitest';
+import fs from 'node:fs';
+import path from 'node:path';
 import { evalTest } from './test-helper.js';
 
 describe('update_topic_behavior', () => {
@@ -113,4 +115,104 @@ describe('update_topic_behavior', () => {
       }
     },
   });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'update_topic should NOT be used for informational coding tasks (Obvious)',
+    approvalMode: 'default',
+    prompt:
+      'Explain the difference between Map and Object in JavaScript and provide a performance-focused code snippet for each.',
+    files: {
+      '.gemini/settings.json': JSON.stringify({
+        experimental: {
+          topicUpdateNarration: true,
+        },
+      }),
+    },
+    assert: async (rig) => {
+      const toolLogs = rig.readToolLogs();
+      const topicCalls = toolLogs.filter(
+        (l) => l.toolRequest.name === UPDATE_TOPIC_TOOL_NAME,
+      );
+
+      expect(
+        topicCalls.length,
+        `Expected 0 update_topic calls for an informational task, but found ${topicCalls.length}`,
+      ).toBe(0);
+    },
+  });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'update_topic should NOT be used for surgical symbol searches (Grey Area)',
+    approvalMode: 'default',
+    prompt:
+      "Find the file where the 'UPDATE_TOPIC_TOOL_NAME' constant is defined.",
+    files: {
+      'packages/core/src/tools/tool-names.ts':
+        "export const UPDATE_TOPIC_TOOL_NAME = 'update_topic';",
+      '.gemini/settings.json': JSON.stringify({
+        experimental: {
+          topicUpdateNarration: true,
+        },
+      }),
+    },
+    assert: async (rig) => {
+      const toolLogs = rig.readToolLogs();
+      const topicCalls = toolLogs.filter(
+        (l) => l.toolRequest.name === UPDATE_TOPIC_TOOL_NAME,
+      );
+
+      expect(
+        topicCalls.length,
+        `Expected 0 update_topic calls for a surgical symbol search, but found ${topicCalls.length}`,
+      ).toBe(0);
+    },
+  });
+
+  evalTest('USUALLY_PASSES', {
+    name: 'update_topic should be used for medium complexity multi-step tasks',
+    prompt:
+      'Refactor the `users-api` project. Move the routing logic from src/app.ts into a new file src/routes.ts, and update app.ts to use the new routes file.',
+    files: {
+      'package.json': JSON.stringify(
+        {
+          name: 'users-api',
+          version: '1.0.0',
+        },
+        null,
+        2,
+      ),
+      'src/app.ts': `
+import express from 'express';
+const app = express();
+
+app.get('/users', (req, res) => {
+  res.json([{id: 1, name: 'Alice'}]);
+});
+
+app.post('/users', (req, res) => {
+  res.status(201).send();
+});
+
+export default app;
+      `,
+      '.gemini/settings.json': JSON.stringify({
+        experimental: {
+          topicUpdateNarration: true,
+        },
+      }),
+    },
+    assert: async (rig) => {
+      const toolLogs = rig.readToolLogs();
+      const topicCalls = toolLogs.filter(
+        (l) => l.toolRequest.name === UPDATE_TOPIC_TOOL_NAME,
+      );
+
+      // This is a multi-step task (read, create new file, edit old file).
+      // It should clear the bar and use update_topic at least at the start and end.
+      expect(topicCalls.length).toBeGreaterThanOrEqual(2);
+
+      // Verify it actually did the refactoring to ensure it didn't just fail immediately
+      expect(fs.existsSync(path.join(rig.testDir, 'src/routes.ts'))).toBe(true);
+    },
+  });
 });