feat: Set up comprehensive Python testing infrastructure

.gitignore

@@ -1,4 +1,57 @@
+# Python
 __pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Testing
 .pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+*.cover
+.hypothesis/
+.tox/
+
+# Virtual environments
 .venv/
+venv/
+ENV/
+env/
+virtualenv/
+
+# IDEs
 .vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Claude
+.claude/*
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Project specific
+*.log
+*.pid
+*.seed
+*.pid.lock

pyproject.toml

@@ -0,0 +1,94 @@
+[tool.poetry]
+name = "mamba-chat"
+version = "0.1.0"
+description = "Mamba Chat - A conversational AI implementation using Mamba architecture"
+authors = ["Your Name <you@example.com>"]
+readme = "README.md"
+packages = [{include = "mamba_chat"}]
+
+[tool.poetry.dependencies]
+python = "^3.9"
+# Production dependencies are managed in requirements.txt
+# This pyproject.toml focuses on testing infrastructure
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.3"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.12.0"
+
+# Poetry scripts are not needed for pytest
+# Use 'poetry run test' or 'poetry run tests' commands directly
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "-v",
+    "--strict-markers",
+    "--tb=short",
+    "--cov=.",
+    "--cov-config=pyproject.toml",
+    "--cov-report=term-missing:skip-covered",
+    "--cov-report=html",
+    "--cov-report=xml",
+    "--cov-fail-under=80",
+]
+markers = [
+    "unit: marks tests as unit tests (fast, isolated)",
+    "integration: marks tests as integration tests (may require external resources)",
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
+]
+norecursedirs = [
+    ".git",
+    ".tox",
+    "dist",
+    "build",
+    "*.egg",
+    "__pycache__",
+    ".pytest_cache",
+    "htmlcov",
+]
+
+[tool.coverage.run]
+source = ["."]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/virtualenv/*",
+    "*/.venv/*",
+    "*/setup.py",
+    "*/conftest.py",
+    "*/site-packages/*",
+    ".venv/*",
+    "tests/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "def __str__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
+show_missing = true
+skip_covered = true
+fail_under = 80
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/conftest.py

@@ -0,0 +1,157 @@
+"""
+Shared pytest fixtures and configuration for all tests.
+"""
+import os
+import sys
+import tempfile
+from pathlib import Path
+from unittest.mock import Mock, patch
+
+import pytest
+
+# Add the project root to the Python path
+PROJECT_ROOT = Path(__file__).parent.parent
+sys.path.insert(0, str(PROJECT_ROOT))
+
+
+@pytest.fixture
+def temp_dir():
+    """Create a temporary directory for test files."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        yield Path(tmpdir)
+
+
+@pytest.fixture
+def temp_file(temp_dir):
+    """Create a temporary file in the temp directory."""
+    def _create_temp_file(name="test_file.txt", content=""):
+        file_path = temp_dir / name
+        file_path.write_text(content)
+        return file_path
+    return _create_temp_file
+
+
+@pytest.fixture
+def mock_config():
+    """Provide a mock configuration object."""
+    config = Mock()
+    config.model_name = "test-model"
+    config.batch_size = 32
+    config.learning_rate = 0.001
+    config.num_epochs = 10
+    config.device = "cpu"
+    return config
+
+
+@pytest.fixture
+def mock_model():
+    """Provide a mock model object."""
+    model = Mock()
+    model.forward = Mock(return_value=Mock(loss=0.5))
+    model.generate = Mock(return_value=[1, 2, 3, 4, 5])
+    model.eval = Mock()
+    model.train = Mock()
+    return model
+
+
+@pytest.fixture
+def mock_tokenizer():
+    """Provide a mock tokenizer object."""
+    tokenizer = Mock()
+    tokenizer.encode = Mock(return_value=[1, 2, 3, 4, 5])
+    tokenizer.decode = Mock(return_value="decoded text")
+    tokenizer.pad_token_id = 0
+    tokenizer.eos_token_id = 1
+    return tokenizer
+
+
+@pytest.fixture
+def mock_dataset():
+    """Provide a mock dataset object."""
+    dataset = Mock()
+    dataset.__len__ = Mock(return_value=100)
+    dataset.__getitem__ = Mock(return_value={"input_ids": [1, 2, 3], "labels": [4, 5, 6]})
+    return dataset
+
+
+@pytest.fixture
+def mock_torch():
+    """Mock torch module for tests that don't need actual PyTorch."""
+    with patch.dict(sys.modules, {"torch": Mock()}):
+        yield sys.modules["torch"]
+
+
+@pytest.fixture
+def isolated_filesystem(temp_dir, monkeypatch):
+    """Change to a temporary directory for the test."""
+    original_dir = Path.cwd()
+    monkeypatch.chdir(temp_dir)
+    yield temp_dir
+    monkeypatch.chdir(original_dir)
+
+
+@pytest.fixture(autouse=True)
+def reset_environment(monkeypatch):
+    """Reset environment variables that might affect tests."""
+    # Clear any CUDA-related environment variables
+    cuda_vars = ["CUDA_VISIBLE_DEVICES", "CUDA_DEVICE_ORDER"]
+    for var in cuda_vars:
+        monkeypatch.delenv(var, raising=False)
+
+    # Set deterministic behavior
+    monkeypatch.setenv("PYTHONHASHSEED", "0")
+
+
+@pytest.fixture
+def capture_logs():
+    """Capture log messages during tests."""
+    import logging
+    from io import StringIO
+
+    log_capture = StringIO()
+    handler = logging.StreamHandler(log_capture)
+    handler.setLevel(logging.DEBUG)
+
+    # Add handler to root logger
+    root_logger = logging.getLogger()
+    root_logger.addHandler(handler)
+    original_level = root_logger.level
+    root_logger.setLevel(logging.DEBUG)
+
+    yield log_capture
+
+    # Cleanup
+    root_logger.removeHandler(handler)
+    root_logger.setLevel(original_level)
+
+
+# Markers for slow tests
+def pytest_configure(config):
+    """Configure pytest with custom markers."""
+    config.addinivalue_line(
+        "markers", "unit: mark test as a unit test"
+    )
+    config.addinivalue_line(
+        "markers", "integration: mark test as an integration test"
+    )
+    config.addinivalue_line(
+        "markers", "slow: mark test as slow running"
+    )
+
+
+# Skip slow tests by default unless --runslow is provided
+def pytest_addoption(parser):
+    """Add custom command line options."""
+    parser.addoption(
+        "--runslow", action="store_true", default=False, help="run slow tests"
+    )
+
+
+def pytest_collection_modifyitems(config, items):
+    """Modify test collection to skip slow tests by default."""
+    if config.getoption("--runslow"):
+        return
+    skip_slow = pytest.mark.skip(reason="need --runslow option to run")
+    for item in items:
+        if "slow" in item.keywords:
+            item.add_marker(skip_slow)