From 852228ea8c3b838d225b413c6261889927b8d64c Mon Sep 17 00:00:00 2001
From: llbbl <logan@llbbl.com>
Date: Sun, 29 Jun 2025 13:34:38 -0500
Subject: [PATCH] feat: Set up comprehensive Python testing infrastructure with
 Poetry

- Migrated from requirements.txt to Poetry for modern dependency management
- Added pytest with coverage reporting and custom markers
- Created test directory structure with unit/integration subdirectories
- Configured pytest with 80% coverage threshold and multiple report formats
- Added comprehensive test fixtures in conftest.py
- Set up Poetry script commands for running tests
- Updated .gitignore with testing artifacts and Claude settings
- Created validation tests to verify infrastructure setup
---
 .gitignore                     |   7 ++
 pyproject.toml                 | 128 +++++++++++++++++++++++
 tests/__init__.py              |   0
 tests/conftest.py              | 179 +++++++++++++++++++++++++++++++++
 tests/integration/__init__.py  |   0
 tests/test_setup_validation.py | 120 ++++++++++++++++++++++
 tests/unit/__init__.py         |   0
 7 files changed, 434 insertions(+)
 create mode 100644 pyproject.toml
 create mode 100644 tests/__init__.py
 create mode 100644 tests/conftest.py
 create mode 100644 tests/integration/__init__.py
 create mode 100644 tests/test_setup_validation.py
 create mode 100644 tests/unit/__init__.py

diff --git a/.gitignore b/.gitignore
index b10180d..93c9167 100644
--- a/.gitignore
+++ b/.gitignore
@@ -161,6 +161,13 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
 
+# VSCode
+.vscode/
+*.code-workspace
+
+# Claude
+.claude/*
+
 outputs/
 logs/
 
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..3451880
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,128 @@
+[tool.poetry]
+name = "vista-vwm"
+version = "0.1.0"
+description = "VISTA: Generalizable World Model with Scaling Up Autonomous Driving Data"
+authors = ["Your Name <you@example.com>"]
+readme = "README.md"
+license = "MIT"
+packages = [{include = "vwm"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+torch = ">=2.0.1"
+torchvision = "*"
+torchaudio = "*"
+numpy = "*"
+av = "*"
+black = "23.7.0"
+clip = {git = "https://github.com/openai/CLIP.git"}
+deepspeed = "*"
+diffusers = "*"
+ftfy = "*"
+imageio = "*"
+imageio-ffmpeg = "*"
+kornia = "*"
+matplotlib = "*"
+nuscenes-devkit = "*"
+omegaconf = "*"
+opencv-python = "*"
+pandas = "*"
+pillow = "*"
+pytorch-lightning = "*"
+regex = "*"
+scipy = "*"
+tensorboardx = "*"
+timm = "*"
+torchdata = "*"
+torchmetrics = "*"
+tqdm = "*"
+transformers = "*"
+trimesh = "*"
+wandb = "*"
+webdataset = "*"
+xformers = "*"
+einops = "*"
+beartype = "*"
+scikit-image = "*"
+scikit-video = "*"
+h5py = "*"
+lpips = "*"
+safetensors = "*"
+urllib3 = "<1.27,>=1.25.4"
+torchdiffeq = "*"
+controlnet-aux = "*"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+
+[tool.poetry.scripts]
+test = "pytest:main"
+tests = "pytest:main"
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--cov=vwm",
+    "--cov-branch",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-fail-under=80",
+    "-vv"
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests",
+    "slow: Tests that take a long time to run"
+]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["vwm"]
+branch = true
+parallel = true
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__init__.py",
+    "*/setup.py",
+    "*/conftest.py"
+]
+
+[tool.coverage.report]
+precision = 2
+show_missing = true
+skip_covered = false
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if TYPE_CHECKING:",
+    "if __name__ == .__main__.:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if False:",
+    "@abstractmethod",
+    "@abc.abstractmethod"
+]
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
\ No newline at end of file
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..c674388
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,179 @@
+import os
+import tempfile
+from pathlib import Path
+from typing import Generator
+
+import pytest
+import torch
+from omegaconf import OmegaConf
+
+
+@pytest.fixture
+def temp_dir() -> Generator[Path, None, None]:
+    """Create a temporary directory for test files."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        yield Path(tmpdir)
+
+
+@pytest.fixture
+def mock_config():
+    """Create a mock configuration for testing."""
+    config = OmegaConf.create({
+        "model": {
+            "type": "test_model",
+            "params": {
+                "in_channels": 3,
+                "out_channels": 3,
+                "hidden_dim": 128
+            }
+        },
+        "data": {
+            "batch_size": 4,
+            "num_workers": 0,
+            "dataset": "test_dataset"
+        },
+        "training": {
+            "epochs": 10,
+            "learning_rate": 1e-4,
+            "optimizer": "adam"
+        },
+        "paths": {
+            "data_dir": "/tmp/test_data",
+            "output_dir": "/tmp/test_output"
+        }
+    })
+    return config
+
+
+@pytest.fixture
+def sample_tensor():
+    """Create a sample tensor for testing."""
+    return torch.randn(2, 3, 64, 64)
+
+
+@pytest.fixture
+def sample_video_tensor():
+    """Create a sample video tensor for testing (batch, time, channels, height, width)."""
+    return torch.randn(2, 8, 3, 64, 64)
+
+
+@pytest.fixture
+def mock_dataset_item():
+    """Create a mock dataset item."""
+    return {
+        "image": torch.randn(3, 256, 256),
+        "label": torch.randint(0, 10, (1,)).item(),
+        "metadata": {
+            "filename": "test_image.jpg",
+            "timestamp": 1234567890
+        }
+    }
+
+
+@pytest.fixture
+def mock_model_state():
+    """Create a mock model state dictionary."""
+    return {
+        "encoder.weight": torch.randn(128, 3, 3, 3),
+        "encoder.bias": torch.randn(128),
+        "decoder.weight": torch.randn(3, 128, 3, 3),
+        "decoder.bias": torch.randn(3),
+        "epoch": 5,
+        "global_step": 1000,
+        "optimizer_state": {}
+    }
+
+
+@pytest.fixture
+def device():
+    """Get the appropriate device for testing."""
+    return torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+
+@pytest.fixture
+def mock_checkpoint_path(temp_dir):
+    """Create a mock checkpoint path."""
+    checkpoint_dir = temp_dir / "checkpoints"
+    checkpoint_dir.mkdir(exist_ok=True)
+    return checkpoint_dir / "checkpoint_epoch_5.pt"
+
+
+@pytest.fixture(autouse=True)
+def reset_random_seeds():
+    """Reset random seeds before each test for reproducibility."""
+    import random
+    import numpy as np
+    
+    random.seed(42)
+    np.random.seed(42)
+    torch.manual_seed(42)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed(42)
+        torch.cuda.manual_seed_all(42)
+
+
+@pytest.fixture
+def mock_wandb(monkeypatch):
+    """Mock wandb for testing without actual logging."""
+    class MockWandb:
+        def init(self, *args, **kwargs):
+            return self
+        
+        def log(self, *args, **kwargs):
+            pass
+        
+        def finish(self):
+            pass
+        
+        def watch(self, *args, **kwargs):
+            pass
+        
+        class config:
+            @staticmethod
+            def update(*args, **kwargs):
+                pass
+    
+    mock = MockWandb()
+    monkeypatch.setattr("wandb.init", mock.init)
+    monkeypatch.setattr("wandb.log", mock.log)
+    monkeypatch.setattr("wandb.finish", mock.finish)
+    monkeypatch.setattr("wandb.watch", mock.watch)
+    monkeypatch.setattr("wandb.config", mock.config)
+    return mock
+
+
+@pytest.fixture
+def mock_env_vars(monkeypatch):
+    """Set up mock environment variables for testing."""
+    test_env_vars = {
+        "CUDA_VISIBLE_DEVICES": "0",
+        "WANDB_MODE": "offline",
+        "PYTHONPATH": "/workspace"
+    }
+    for key, value in test_env_vars.items():
+        monkeypatch.setenv(key, value)
+    return test_env_vars
+
+
+@pytest.fixture
+def capture_stdout(monkeypatch):
+    """Capture stdout for testing print statements."""
+    import io
+    import sys
+    
+    captured_output = io.StringIO()
+    monkeypatch.setattr(sys, 'stdout', captured_output)
+    
+    yield captured_output
+    
+    captured_output.close()
+
+
+def pytest_configure(config):
+    """Configure pytest with custom settings."""
+    config.addinivalue_line(
+        "markers", "gpu: mark test to run only when GPU is available"
+    )
+    config.addinivalue_line(
+        "markers", "requires_data: mark test that requires external data"
+    )
\ No newline at end of file
diff --git a/tests/integration/__init__.py b/tests/integration/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/test_setup_validation.py b/tests/test_setup_validation.py
new file mode 100644
index 0000000..3e727d4
--- /dev/null
+++ b/tests/test_setup_validation.py
@@ -0,0 +1,120 @@
+import sys
+from pathlib import Path
+
+import pytest
+import torch
+
+
+def test_python_version():
+    """Test that Python version meets requirements."""
+    assert sys.version_info >= (3, 8), "Python 3.8 or higher is required"
+
+
+def test_project_structure():
+    """Test that the project structure is set up correctly."""
+    project_root = Path(__file__).parent.parent
+    
+    # Check main directories exist
+    assert (project_root / "vwm").exists(), "vwm package directory not found"
+    assert (project_root / "tests").exists(), "tests directory not found"
+    assert (project_root / "configs").exists(), "configs directory not found"
+    
+    # Check test subdirectories
+    assert (project_root / "tests" / "unit").exists(), "unit tests directory not found"
+    assert (project_root / "tests" / "integration").exists(), "integration tests directory not found"
+    
+    # Check important files
+    assert (project_root / "pyproject.toml").exists(), "pyproject.toml not found"
+    assert (project_root / "README.md").exists(), "README.md not found"
+
+
+def test_pytorch_available():
+    """Test that PyTorch is available and working."""
+    assert torch.__version__ is not None
+    
+    # Test basic tensor operations
+    x = torch.tensor([1.0, 2.0, 3.0])
+    y = torch.tensor([4.0, 5.0, 6.0])
+    z = x + y
+    assert torch.allclose(z, torch.tensor([5.0, 7.0, 9.0]))
+
+
+def test_conftest_fixtures(temp_dir, mock_config, sample_tensor):
+    """Test that conftest fixtures are available."""
+    # Test temp_dir fixture
+    assert temp_dir.exists()
+    assert temp_dir.is_dir()
+    
+    # Test mock_config fixture
+    assert mock_config is not None
+    assert "model" in mock_config
+    assert mock_config.model.type == "test_model"
+    
+    # Test sample_tensor fixture
+    assert sample_tensor.shape == (2, 3, 64, 64)
+    assert sample_tensor.dtype == torch.float32
+
+
+@pytest.mark.unit
+def test_unit_marker():
+    """Test that the unit marker works."""
+    assert True
+
+
+@pytest.mark.integration
+def test_integration_marker():
+    """Test that the integration marker works."""
+    assert True
+
+
+@pytest.mark.slow
+def test_slow_marker():
+    """Test that the slow marker works."""
+    import time
+    time.sleep(0.1)  # Simulate slow test
+    assert True
+
+
+def test_gpu_availability():
+    """Test GPU availability (informational, not failing)."""
+    if torch.cuda.is_available():
+        print(f"GPU is available: {torch.cuda.get_device_name(0)}")
+        assert torch.cuda.device_count() > 0
+    else:
+        print("GPU is not available, tests will run on CPU")
+        assert True  # Don't fail if GPU is not available
+
+
+def test_import_main_package():
+    """Test that the main package can be imported."""
+    import vwm
+    assert vwm is not None
+    
+    # Test submodules can be imported
+    from vwm import models
+    from vwm import data
+    from vwm import modules
+    
+    assert models is not None
+    assert data is not None
+    assert modules is not None
+
+
+class TestCoverageValidation:
+    """Test class to validate coverage reporting works."""
+    
+    def test_covered_function(self):
+        """This function should be covered."""
+        result = self._helper_function(5)
+        assert result == 10
+    
+    def _helper_function(self, x):
+        """Helper function for coverage testing."""
+        if x > 0:
+            return x * 2
+        else:
+            return 0  # This line won't be covered in tests
+    
+    def test_partial_coverage(self):
+        """Test to demonstrate partial coverage."""
+        assert self._helper_function(3) == 6
\ No newline at end of file
diff --git a/tests/unit/__init__.py b/tests/unit/__init__.py
new file mode 100644
index 0000000..e69de29