import { describe, expect } from 'vitest'; import { evalTest } from './test-helper.js'; describe('core_feature', () => { // New tests MUST start as USUALLY_PASSES evalTest('USUALLY_PASSES', { name: 'should perform expected agent action', setup: async (rig) => { // For mocking offline MCP: // rig.addMockMcpServer('workspace-server', 'google-workspace'); }, files: { 'src/app.ts': '// some code', }, prompt: 'Task description here', timeout: 60000, // 1 minute safety limit assert: async (rig, result) => { // 1. Audit the trajectory (Safe for standard evalTest) const logs = rig.readToolLogs(); const hasTool = logs.some((l) => l.toolRequest.name === 'read_file'); expect(hasTool, 'Agent should have read the file').toBe(true); // 2. Assert efficiency (Cost/Turn) expect(logs.length).toBeLessThan(5); // 3. Assert final output expect(result).toContain('Expected Keyword'); }, }); });