latestaiagents/test-generation-patterns

Test Generation Patterns

Generate comprehensive tests with AI assistance following 2026 best practices.

When to Use

• Adding tests to existing code
• Creating test suites for new features
• Improving test coverage
• Setting up testing patterns for a project
• Generating edge case tests

The Testing Pyramid (2026)

        ┌─────────┐
        │   E2E   │  Few, slow, high confidence
        ├─────────┤
        │ Integr. │  Some, medium speed
        ├─────────┤
        │  Unit   │  Many, fast, isolated
        └─────────┘

Unit Test Generation

Step 1: Identify Test Cases

For any function, test:

1. Happy path - Normal expected input
2. Edge cases - Boundaries, empty, null
3. Error cases - Invalid input, failures
4. State changes - If function has side effects

AI Prompt Template

Generate comprehensive unit tests for this function:

```[paste function]```

Include tests for:
1. Happy path with typical inputs
2. Edge cases (empty, null, boundary values)
3. Error handling
4. Any state changes or side effects

Use [Vitest/Jest/pytest] with [testing-library if applicable].
Follow AAA pattern (Arrange, Act, Assert).

Example: Testing a Utility Function

Code to test:

function parseAmount(input: string): number | null {
  if (!input || typeof input !== 'string') return null;
  const cleaned = input.replace(/[$,]/g, '').trim();
  const num = parseFloat(cleaned);
  return isNaN(num) ? null : Math.round(num * 100) / 100;
}

Generated tests:

import { describe, it, expect } from 'vitest';
import { parseAmount } from './parseAmount';

describe('parseAmount', () => {
  describe('happy path', () => {
    it('parses plain number', () => {
      expect(parseAmount('123.45')).toBe(123.45);
    });

    it('parses number with dollar sign', () => {
      expect(parseAmount('$99.99')).toBe(99.99);
    });

    it('parses number with commas', () => {
      expect(parseAmount('1,234.56')).toBe(1234.56);
    });

    it('parses number with dollar sign and commas', () => {
      expect(parseAmount('$1,234.56')).toBe(1234.56);
    });

    it('rounds to 2 decimal places', () => {
      expect(parseAmount('123.456')).toBe(123.46);
    });
  });

  describe('edge cases', () => {
    it('handles zero', () => {
      expect(parseAmount('0')).toBe(0);
    });

    it('handles negative numbers', () => {
      expect(parseAmount('-50.00')).toBe(-50);
    });

    it('trims whitespace', () => {
      expect(parseAmount('  123.45  ')).toBe(123.45);
    });

    it('handles integer input', () => {
      expect(parseAmount('100')).toBe(100);
    });
  });

  describe('error cases', () => {
    it('returns null for empty string', () => {
      expect(parseAmount('')).toBeNull();
    });

    it('returns null for null input', () => {
      expect(parseAmount(null as any)).toBeNull();
    });

    it('returns null for undefined', () => {
      expect(parseAmount(undefined as any)).toBeNull();
    });

    it('returns null for non-string input', () => {
      expect(parseAmount(123 as any)).toBeNull();
    });

    it('returns null for non-numeric string', () => {
      expect(parseAmount('abc')).toBeNull();
    });

    it('returns null for only symbols', () => {
      expect(parseAmount('$,')).toBeNull();
    });
  });
});

React Component Testing

AI Prompt Template

Generate tests for this React component:

```[paste component]```

Test:
1. Renders correctly with required props
2. Renders correctly with optional props
3. User interactions (clicks, inputs)
4. Loading/error states if applicable
5. Accessibility (basic a11y)

Use React Testing Library and Vitest.
Focus on user behavior, not implementation details.

Example: Component Tests

Component:

interface ButtonProps {
  label: string;
  onClick: () => void;
  disabled?: boolean;
  loading?: boolean;
}

export function Button({ label, onClick, disabled, loading }: ButtonProps) {
  return (
    <button
      onClick={onClick}
      disabled={disabled || loading}
      aria-busy={loading}
    >
      {loading ? 'Loading...' : label}
    </button>
  );
}

Generated tests:

import { render, screen } from '@testing-library/react';
import userEvent from '@testing-library/user-event';
import { describe, it, expect, vi } from 'vitest';
import { Button } from './Button';

describe('Button', () => {
  const defaultProps = {
    label: 'Click me',
    onClick: vi.fn(),
  };

  describe('rendering', () => {
    it('renders with label', () => {
      render(<Button {...defaultProps} />);
      expect(screen.getByRole('button', { name: 'Click me' })).toBeInTheDocument();
    });

    it('renders loading state', () => {
      render(<Button {...defaultProps} loading />);
      expect(screen.getByRole('button', { name: 'Loading...' })).toBeInTheDocument();
      expect(screen.getByRole('button')).toHaveAttribute('aria-busy', 'true');
    });

    it('renders disabled state', () => {
      render(<Button {...defaultProps} disabled />);
      expect(screen.getByRole('button')).toBeDisabled();
    });
  });

  describe('interactions', () => {
    it('calls onClick when clicked', async () => {
      const onClick = vi.fn();
      render(<Button {...defaultProps} onClick={onClick} />);

      await userEvent.click(screen.getByRole('button'));

      expect(onClick).toHaveBeenCalledTimes(1);
    });

    it('does not call onClick when disabled', async () => {
      const onClick = vi.fn();
      render(<Button {...defaultProps} onClick={onClick} disabled />);

      await userEvent.click(screen.getByRole('button'));

      expect(onClick).not.toHaveBeenCalled();
    });

    it('does not call onClick when loading', async () => {
      const onClick = vi.fn();
      render(<Button {...defaultProps} onClick={onClick} loading />);

      await userEvent.click(screen.getByRole('button'));

      expect(onClick).not.toHaveBeenCalled();
    });
  });

  describe('accessibility', () => {
    it('is focusable', async () => {
      render(<Button {...defaultProps} />);

      await userEvent.tab();

      expect(screen.getByRole('button')).toHaveFocus();
    });

    it('can be activated with Enter key', async () => {
      const onClick = vi.fn();
      render(<Button {...defaultProps} onClick={onClick} />);

      await userEvent.tab();
      await userEvent.keyboard('{Enter}');

      expect(onClick).toHaveBeenCalled();
    });
  });
});

API/Integration Testing

AI Prompt Template

Generate integration tests for this API endpoint:

```[paste route handler]```

Test:
1. Successful requests with valid data
2. Validation errors (400)
3. Authentication/authorization (401/403)
4. Not found cases (404)
5. Server errors (500)

Use [supertest/axios] with proper mocking.

Test Coverage Patterns

Coverage Checklist

| Area | Target | Priority | |------|--------|----------| | Business logic | 90%+ | High | | Utilities | 100% | High | | API routes | 80%+ | High | | Components | 70%+ | Medium | | Integrations | 60%+ | Medium |

Generating Tests for Coverage Gaps

Here's my current code and test file. Identify untested paths
and generate tests to cover them:

Code:
```[paste code]```

Existing tests:
```[paste tests]```

Coverage report shows these lines uncovered: [lines]

Test Data Generation

AI Prompt for Test Fixtures

Generate test fixtures for this type:

```typescript
interface Order {
  id: string;
  customerId: string;
  items: OrderItem[];
  status: 'pending' | 'processing' | 'shipped' | 'delivered';
  total: number;
  createdAt: Date;
}

Create:

1. A valid complete order
2. A minimal valid order
3. Orders in each status
4. Edge case orders (empty items, zero total, etc.)

## Common Testing Patterns

### Factory Pattern
```typescript
function createOrder(overrides: Partial<Order> = {}): Order {
  return {
    id: 'order-123',
    customerId: 'customer-456',
    items: [{ productId: 'prod-1', quantity: 1, price: 10 }],
    status: 'pending',
    total: 10,
    createdAt: new Date('2024-01-01'),
    ...overrides,
  };
}

// Usage in tests
const pendingOrder = createOrder();
const shippedOrder = createOrder({ status: 'shipped' });
const emptyOrder = createOrder({ items: [], total: 0 });

Mock Patterns

// Service mock
vi.mock('./userService', () => ({
  getUser: vi.fn().mockResolvedValue({ id: '1', name: 'John' }),
}));

// Spy on method
const logSpy = vi.spyOn(console, 'log').mockImplementation(() => {});

// Mock module partially
vi.mock('./utils', async () => {
  const actual = await vi.importActual('./utils');
  return {
    ...actual,
    formatDate: vi.fn().mockReturnValue('2024-01-01'),
  };
});

Verification After Generation

• [ ] Tests actually test the code (not just pass)
• [ ] No hardcoded values that match implementation
• [ ] Edge cases are meaningful
• [ ] Mocks don't hide real bugs
• [ ] Tests are readable and maintainable