test: add browser agent integration tests (#21151)

2026-04-26 04:54:25 -07:00 · 2026-03-05 18:59:35 +05:30
parent 173376ba67
commit 09259a8ec4
9 changed files with 241 additions and 4 deletions
@@ -0,0 +1,206 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+/**
+ * Integration tests for the browser agent.
+ *
+ * These tests verify the complete end-to-end flow from CLI prompt through
+ * browser_agent delegation to MCP/Chrome DevTools and back. Unlike the unit
+ * tests in packages/core/src/agents/browser/ which mock all MCP components,
+ * these tests launch real Chrome instances in headless mode.
+ *
+ * Tests are skipped on systems without Chrome/Chromium installed.
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig, assertModelHasOutput } from './test-helper.js';
+import { dirname, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { execSync } from 'node:child_process';
+import { existsSync } from 'node:fs';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const chromeAvailable = (() => {
+  try {
+    if (process.platform === 'darwin') {
+      execSync(
+        'test -d "/Applications/Google Chrome.app"  || test -d "/Applications/Chromium.app"',
+        {
+          stdio: 'ignore',
+        },
+      );
+    } else if (process.platform === 'linux') {
+      execSync(
+        'which google-chrome || which chromium-browser || which chromium',
+        { stdio: 'ignore' },
+      );
+    } else if (process.platform === 'win32') {
+      // Check standard Windows installation paths using Node.js fs
+      const chromePaths = [
+        'C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe',
+        'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe',
+        `${process.env['LOCALAPPDATA'] ?? ''}\\Google\\Chrome\\Application\\chrome.exe`,
+      ];
+      const found = chromePaths.some((p) => existsSync(p));
+      if (!found) {
+        // Fall back to PATH check
+        execSync('where chrome || where chromium', { stdio: 'ignore' });
+      }
+    } else {
+      return false;
+    }
+    return true;
+  } catch {
+    return false;
+  }
+})();
+
+describe.skipIf(!chromeAvailable)('browser-agent', () => {
+  let rig: TestRig;
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => await rig.cleanup());
+
+  it('should navigate to a page and capture accessibility tree', async () => {
+    rig.setup('browser-navigate-and-snapshot', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent.navigate-snapshot.responses',
+      ),
+      settings: {
+        agents: {
+          browser_agent: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Open https://example.com in the browser and tell me the page title and main content.',
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+  });
+
+  it('should take screenshots of web pages', async () => {
+    rig.setup('browser-screenshot', {
+      fakeResponsesPath: join(__dirname, 'browser-agent.screenshot.responses'),
+      settings: {
+        agents: {
+          browser_agent: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Navigate to https://example.com and take a screenshot.',
+    });
+
+    const toolLogs = rig.readToolLogs();
+    const browserCalls = toolLogs.filter(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(browserCalls.length).toBeGreaterThan(0);
+
+    assertModelHasOutput(result);
+  });
+
+  it('should interact with page elements', async () => {
+    rig.setup('browser-interaction', {
+      fakeResponsesPath: join(__dirname, 'browser-agent.interaction.responses'),
+      settings: {
+        agents: {
+          browser_agent: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Go to https://example.com, find any links on the page, and describe them.',
+    });
+
+    const toolLogs = rig.readToolLogs();
+    const browserAgentCall = toolLogs.find(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(
+      browserAgentCall,
+      'Expected browser_agent to be called',
+    ).toBeDefined();
+
+    assertModelHasOutput(result);
+  });
+
+  it('should clean up browser processes after completion', async () => {
+    rig.setup('browser-cleanup', {
+      fakeResponsesPath: join(__dirname, 'browser-agent.cleanup.responses'),
+      settings: {
+        agents: {
+          browser_agent: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    await rig.run({
+      args: 'Open https://example.com in the browser and check the page title.',
+    });
+
+    // Test passes if we reach here, relying on Vitest's timeout mechanism
+    // to detect hanging browser processes.
+  });
+
+  it('should handle multiple browser operations in sequence', async () => {
+    rig.setup('browser-sequential', {
+      fakeResponsesPath: join(__dirname, 'browser-agent.sequential.responses'),
+      settings: {
+        agents: {
+          browser_agent: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Navigate to https://example.com, take a snapshot of the accessibility tree, then take a screenshot.',
+    });
+
+    const toolLogs = rig.readToolLogs();
+    const browserCalls = toolLogs.filter(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+    expect(browserCalls.length).toBeGreaterThan(0);
+
+    // Should successfully complete all operations
+    assertModelHasOutput(result);
+  });
+});