feat: Set up comprehensive Python testing infrastructure

.gitignore

@@ -0,0 +1,140 @@
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+.tox/
+.nox/
+
+# Claude Code settings
+.claude/*
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Virtual environments
+.virtualenv/
+.venv/
+venv/
+ENV/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Logs
+*.log
+
+# Model files (typically large)
+*.bin
+*.safetensors
+*.h5
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# poetry
+# Uncomment if you want to ignore poetry.lock
+# poetry.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/

pyproject.toml

@@ -0,0 +1,75 @@
+[tool.poetry]
+name = "chemdfm"
+version = "1.5.0"
+description = "ChemDFM - Chemical Domain Foundation Model"
+authors = ["ChemDFM Team"]
+readme = "README.md"
+packages = [{include = "chemdfm", from = "."}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+torch = "^2.0.0"
+transformers = "^4.30.0"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+
+# Poetry run commands are configured in [tool.poetry] section
+# Use: poetry run pytest
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--cov=chemdfm",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80",
+    "-v",
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests", 
+    "slow: Tests that take a long time to run",
+]
+
+[tool.coverage.run]
+source = ["chemdfm"]
+branch = true
+omit = [
+    "tests/*",
+    "*/conftest.py",
+    "*/__init__.py",
+    "*/migrations/*",
+    "*/venv/*",
+    "*/.venv/*",
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]
+show_missing = true
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"

tests/conftest.py

@@ -0,0 +1,116 @@
+"""Shared pytest fixtures and configuration."""
+
+import os
+import tempfile
+import shutil
+from pathlib import Path
+from unittest.mock import Mock, MagicMock
+import pytest
+
+
+@pytest.fixture
+def temp_dir():
+    """Create a temporary directory for test files."""
+    temp_path = tempfile.mkdtemp()
+    yield Path(temp_path)
+    shutil.rmtree(temp_path)
+
+
+@pytest.fixture
+def mock_tokenizer():
+    """Mock tokenizer for testing without loading actual model."""
+    tokenizer = Mock()
+    tokenizer.from_pretrained.return_value = tokenizer
+    tokenizer.batch_decode.return_value = ["test response"]
+    tokenizer.eos_token_id = 1
+    tokenizer.return_value = Mock(input_ids="mock_input_ids", to=Mock(return_value=Mock(input_ids="mock_input_ids")))
+    return tokenizer
+
+
+@pytest.fixture
+def mock_model():
+    """Mock model for testing without loading actual model."""
+    model = Mock()
+    model.from_pretrained.return_value = model
+    model.generate.return_value = "mock_generated_ids"
+    model.eval.return_value = None
+    return model
+
+
+@pytest.fixture
+def mock_torch():
+    """Mock torch functionality."""
+    torch_mock = Mock()
+    torch_mock.cuda.is_available.return_value = False
+    torch_mock.float16 = "float16"
+    return torch_mock
+
+
+@pytest.fixture
+def sample_args():
+    """Sample argument configuration for testing."""
+    args = Mock()
+    args.model_name_or_path = "test_model"
+    args.max_new_tokens = 100
+    args.do_sample = True
+    args.temperature = 0.7
+    args.top_k = 50
+    args.top_p = 0.9
+    args.num_beams = 1
+    args.num_beam_groups = 1
+    args.repetition_penalty = 1.0
+    args.max_round = 5
+    return args
+
+
+@pytest.fixture
+def mock_config():
+    """Mock configuration for various test scenarios."""
+    config = {
+        "model_path": "test/model/path",
+        "device": "cpu",
+        "max_tokens": 512,
+        "temperature": 0.1
+    }
+    return config
+
+
+@pytest.fixture(scope="session")
+def test_data_dir():
+    """Path to test data directory."""
+    return Path(__file__).parent / "data"
+
+
+@pytest.fixture
+def capture_stdout(monkeypatch):
+    """Fixture to capture stdout for testing print statements."""
+    import io
+    import sys
+
+    captured_output = io.StringIO()
+    monkeypatch.setattr(sys, 'stdout', captured_output)
+    return captured_output
+
+
+@pytest.fixture
+def mock_input(monkeypatch):
+    """Mock input function for interactive testing."""
+    inputs = []
+
+    def mock_input_func(prompt=""):
+        if inputs:
+            return inputs.pop(0)
+        return "/clear"
+
+    monkeypatch.setattr("builtins.input", mock_input_func)
+    return inputs
+
+
+@pytest.fixture
+def clean_environment(monkeypatch):
+    """Clean environment variables for testing."""
+    test_env = {}
+    for key in os.environ:
+        if not key.startswith("PYTEST"):
+            monkeypatch.delenv(key, raising=False)
+    return test_env