Development

# Clone and install for development
git clone https://github.com/PrimeIntellect-ai/verifiers.git
cd verifiers

# CPU-only development:
uv sync

# GPU-based trainer development:
uv sync --all-extras

# Install pre-commit hooks:
uv run pre-commit install

verifiers/
├── verifiers/          # Main package
│   ├── envs/           # Environment classes
│   │   ├── integrations/   # Third-party wrappers (TextArena, ReasoningGym)
│   │   └── experimental/   # Newer environments (MCP, Harbor, etc.)
│   ├── parsers/        # Parser classes  
│   ├── rubrics/        # Rubric classes
│   ├── rl/             # Training infrastructure
│   │   ├── inference/  # vLLM server utilities
│   │   └── trainer/    # RLTrainer implementation
│   ├── scripts/        # CLI entry points
│   └── utils/          # Utilities
├── environments/       # Installable environment modules
├── configs/            # Example training configurations
├── tests/              # Test suite
└── docs/               # Documentation

# Run all tests
uv run pytest tests/

# Run with coverage
uv run pytest tests/ --cov=verifiers --cov-report=html

# Run specific test file
uv run pytest tests/test_parser.py

# Stop on first failure with verbose output
uv run pytest tests/ -xvs

# Run tests matching a pattern
uv run pytest tests/ -k "xml_parser"

# Run environment tests
uv run pytest tests/test_envs.py -vv

# Run environment tests across all CPU cores
uv run pytest -n auto tests/test_envs.py -vv

# Run specific environment tests
uv run pytest tests/test_envs.py -k math_python

class TestFeature:
    """Test the feature functionality."""
    
    def test_basic_functionality(self):
        """Test normal operation."""
        # Arrange
        feature = Feature()
        
        # Act
        result = feature.process("input")
        
        # Assert
        assert result == "expected"
    
    def test_error_handling(self):
        """Test error cases."""
        with pytest.raises(ValueError):
            Feature().process(invalid_input)

from tests.mock_openai_client import MockOpenAIClient

def test_with_mock(mock_client):
    env = vf.SingleTurnEnv(client=mock_client)
    # Test without real API calls

# Ensure package is installed in development mode
uv sync

# Install optional dependencies for specific integrations
uv sync --extra ta   # for TextArenaEnv
uv sync --extra rg   # for ReasoningGymEnv

# Debug specific test
uv run pytest tests/test_file.py::test_name -vvs --pdb

# Initialize template
vf-init my-environment

# Install locally for testing
vf-install my-environment

# Test your environment
vf-eval my-environment -m gpt-4.1-mini -n 5

# my_environment.py
import verifiers as vf

def load_environment(**kwargs):
    """Load the environment."""
    dataset = vf.load_example_dataset("dataset_name")
    parser = vf.XMLParser(fields=["reasoning", "answer"])
    
    def reward_func(parser, completion, answer, **kwargs):
        return 1.0 if parser.parse_answer(completion) == answer else 0.0
    
    rubric = vf.Rubric(
        funcs=[reward_func, parser.get_format_reward_func()],
        weights=[1.0, 0.2],
        parser=parser
    )
    
    return vf.SingleTurnEnv(
        dataset=dataset,
        parser=parser,
        rubric=rubric,
        **kwargs
    )

# Development setup
uv sync                               # CPU-only
uv sync --all-extras                  # With RL/training extras

# Run tests
uv run pytest tests/                  # All tests
uv run pytest tests/ -xvs             # Debug mode
uv run pytest tests/ --cov=verifiers  # With coverage

# Run environment tests
uv run pytest tests/test_envs.py -vv              # All environments
uv run pytest tests/test_envs.py -k math_python   # Specific environment

# Linting
uv run ruff check --fix .             # Fix lint errors
uv run pre-commit run --all-files     # Run all pre-commit hooks

# Environment tools
vf-init new-env                       # Create environment
vf-install new-env                    # Install environment
vf-eval new-env -m gpt-4.1-mini -n 5  # Test environment
vf-tui                                # Browse eval results