🤖 AI Testing Agent

AI-powered testing agent for frontend, backend, Logic Apps, and Function Apps using Model Context Protocol (MCP). Automate your testing workflows with intelligent test generation and execution.

✨ Features

• 🎯 Multi-Platform Testing: Frontend UI, Backend APIs, Azure Logic Apps, and Function Apps
• 🤖 AI-Powered: Generate test cases from natural language descriptions
• 🔧 MCP Integration: Built on Model Context Protocol for extensibility
• ⚡ Parallel Execution: Run multiple tests simultaneously
• 📊 Rich Reporting: Detailed test results with screenshots and logs
• 🛠️ CLI & Programmatic: Use via command line or import in your code
• 🎨 TypeScript Support: Full type definitions included

🚀 Quick Start

Installation

# Install globally for CLI usage
npm install -g @ai-testing/agent

# Or install locally in your project
npm install @ai-testing/agent

CLI Usage

# Create a test case template
ai-testing-agent create "Login Test" --type frontend --output login-test.json

# Run test cases
ai-testing-agent run test-cases.json --parallel --headless

# Validate test cases
ai-testing-agent validate test-cases.json

# Start MCP server
ai-testing-agent server --port 8080

Programmatic Usage

import { TestOrchestrator, TestCase } from '@ai-testing/agent';

const orchestrator = new TestOrchestrator();

const testCase: TestCase = {
  id: 'login-test',
  name: 'User Login Test',
  description: 'Test user login functionality',
  type: 'frontend',
  targetUrl: 'https://example.com',
  steps: [
    { action: 'navigate', url: 'https://example.com/login' },
    { action: 'type', selector: '#email', value: '[email protected]' },
    { action: 'type', selector: '#password', value: 'password123' },
    { action: 'click', selector: '#login-button' }
  ],
  expectedResults: [
    'User should be redirected to dashboard',
    'Welcome message should be displayed'
  ]
};

// Run the test
const result = await orchestrator.runTest(testCase);
console.log(`Test ${result.status}: ${result.duration}ms`);

📋 Test Types

Frontend Testing

Automated browser testing using Playwright:

const frontendTest: TestCase = {
  type: 'frontend',
  targetUrl: 'https://myapp.com',
  steps: [
    { action: 'navigate', url: 'https://myapp.com' },
    { action: 'click', selector: '.login-button' },
    { action: 'type', selector: '#email', value: '[email protected]' },
    { action: 'assert', selector: '.success-message', expected: 'Login successful' }
  ]
};

Backend API Testing

REST API testing with Axios:

const backendTest: TestCase = {
  type: 'backend',
  targetUrl: 'https://api.example.com',
  steps: [
    { action: 'api-call', endpoint: '/auth/login', method: 'POST', payload: { email: '[email protected]', password: 'password' } },
    { action: 'assert', expected: { status: 200, data: { token: 'string' } } }
  ]
};

Azure Logic App Testing

Test Azure Logic App workflows:

const logicAppTest: TestCase = {
  type: 'logic-app',
  steps: [
    { action: 'trigger', endpoint: 'https://your-logic-app.azurewebsites.net/api/trigger' },
    { action: 'assert', expected: { status: 'Succeeded' } }
  ]
};

Azure Function App Testing

Test Azure Functions:

const functionAppTest: TestCase = {
  type: 'function-app',
  steps: [
    { action: 'trigger', endpoint: 'https://your-function-app.azurewebsites.net/api/process' },
    { action: 'assert', expected: { status: 200 } }
  ]
};

🔧 Configuration

Test Configuration

import { TestRunner } from '@ai-testing/agent';

const runner = new TestRunner({
  headless: true,           // Run browser in headless mode
  timeout: 30000,          // Test timeout in milliseconds
  parallel: true,          // Run tests in parallel
  maxConcurrency: 5,       // Maximum concurrent tests
  screenshotOnFailure: true, // Take screenshots on failure
  outputDir: './test-results' // Output directory for results
});

Azure Configuration

import { LogicAppTestingEngine, FunctionAppTestingEngine } from '@ai-testing/agent';

// Configure Azure credentials
const logicAppEngine = new LogicAppTestingEngine();
logicAppEngine.setAzureCredentials(
  'your-subscription-id',
  'your-resource-group',
  'your-access-token'
);

const functionAppEngine = new FunctionAppTestingEngine();
functionAppEngine.setFunctionAppCredentials(
  'https://your-function-app.azurewebsites.net',
  'your-function-key'
);

📊 Test Results

Test results include comprehensive information:

interface TestResult {
  testId: string;
  status: 'running' | 'passed' | 'failed' | 'error';
  steps: StepResult[];
  screenshot?: string | Buffer;
  logs: string[];
  duration: number;
  error?: string;
  startTime?: number;
  endTime?: number;
}

🛠️ Development

Building the Package

# Build the package
npm run build:package

# Test the build
npm run pack

# Publish to npm
npm run publish:public

Project Structure

src/
├── index.ts              # Main exports
├── cli/
│   └── index.ts          # CLI implementation
├── mcp/
│   ├── client.ts         # MCP client
│   └── server.ts         # MCP server
├── testing/
│   ├── test-orchestrator.ts
│   ├── frontend-engine.ts
│   ├── backend-engine.ts
│   ├── logic-app-engine.ts
│   └── function-app-engine.ts
├── runner/
│   └── test-runner.ts    # Test runner
├── types.ts              # TypeScript definitions
└── utils/
    └── test-helpers.ts   # Utility functions

🤝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Playwright for browser automation
• Model Context Protocol for extensibility
• Commander.js for CLI interface
• Axios for HTTP requests

📞 Support

• 📖 Documentation
• 🐛 Report Issues
• 💬 Discussions

Made with ❤️ by the AI Testing Agent Team