feat: Set up comprehensive Python testing infrastructure with Poetry

.gitignore

@@ -158,3 +158,21 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Claude Code settings
+.claude/*
+
+# Additional IDE files
+.vscode/
+*.swp
+*.swo
+*~
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db

pyproject.toml

@@ -0,0 +1,80 @@
+[tool.poetry]
+name = "textcraft-research"
+version = "0.1.0"
+description = "TextCraft research project with adaptive planning for text-based environments"
+authors = ["Research Team <research@example.com>"]
+readme = "README.md"
+packages = [{include = "TextCraft"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+# Core dependencies - install these as needed based on requirements.txt
+numpy = "^1.21.0"
+requests = "^2.28.0"
+pyyaml = "^6.0"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.1"
+
+# Poetry scripts for running tests
+# Use: poetry run pytest or poetry run test-suite
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--strict-config",
+    "--cov=TextCraft",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80"
+]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+markers = [
+    "unit: marks tests as unit tests (deselect with '-m \"not unit\"')",
+    "integration: marks tests as integration tests (deselect with '-m \"not integration\"')",
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')"
+]
+
+[tool.coverage.run]
+source = ["TextCraft"]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/.*",
+    "setup.py",
+    "*/venv/*",
+    "*/.venv/*"
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:"
+]
+show_missing = true
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/__init__.py

@@ -0,0 +1 @@
+# Test package initialization

tests/conftest.py

@@ -0,0 +1,138 @@
+"""
+Shared pytest fixtures for the TextCraft test suite.
+"""
+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 temp_file(temp_dir):
+    """Create a temporary file in the temp directory."""
+    file_path = temp_dir / "test_file.txt"
+    file_path.write_text("test content")
+    return file_path
+
+
+@pytest.fixture
+def mock_openai_client():
+    """Mock OpenAI client for testing."""
+    mock_client = Mock()
+    mock_response = Mock()
+    mock_response.choices = [Mock()]
+    mock_response.choices[0].message.content = "Test response"
+    mock_client.chat.completions.create.return_value = mock_response
+    return mock_client
+
+
+@pytest.fixture
+def mock_environment():
+    """Mock environment configuration."""
+    return {
+        'api_key': 'test-api-key',
+        'model': 'gpt-3.5-turbo',
+        'temperature': 0.7,
+        'max_tokens': 150
+    }
+
+
+@pytest.fixture
+def sample_crafting_tree():
+    """Sample crafting tree data for testing."""
+    return {
+        'nodes': [
+            {'id': 'wood', 'type': 'resource', 'available': True},
+            {'id': 'stick', 'type': 'craft', 'recipe': ['wood'], 'available': False}
+        ],
+        'edges': [
+            {'from': 'wood', 'to': 'stick', 'quantity': 2}
+        ]
+    }
+
+
+@pytest.fixture
+def mock_alfworld_env():
+    """Mock AlfWorld environment for testing."""
+    mock_env = MagicMock()
+    mock_env.reset.return_value = ("Initial observation", {})
+    mock_env.step.return_value = ("Step observation", 0, False, {})
+    return mock_env
+
+
+@pytest.fixture
+def mock_textcraft_env():
+    """Mock TextCraft environment for testing."""
+    mock_env = MagicMock()
+    mock_env.reset.return_value = "Initial state"
+    mock_env.step.return_value = ("New state", 0, False, {})
+    return mock_env
+
+
+@pytest.fixture
+def sample_prompt_data():
+    """Sample prompt data for testing."""
+    return {
+        'system': 'You are a helpful assistant for text-based games.',
+        'examples': [
+            {'input': 'look around', 'output': 'You see a room with furniture.'},
+            {'input': 'take key', 'output': 'You pick up the key.'}
+        ]
+    }
+
+
+@pytest.fixture
+def mock_file_system(tmp_path, monkeypatch):
+    """Mock file system operations."""
+    monkeypatch.chdir(tmp_path)
+    return tmp_path
+
+
+@pytest.fixture(autouse=True)
+def clean_environment():
+    """Clean environment variables before and after tests."""
+    # Store original values
+    original_env = os.environ.copy()
+
+    yield
+
+    # Restore original environment
+    os.environ.clear()
+    os.environ.update(original_env)
+
+
+@pytest.fixture
+def mock_json_response():
+    """Mock JSON response for API testing."""
+    return {
+        'status': 'success',
+        'data': {
+            'action': 'move north',
+            'confidence': 0.95,
+            'reasoning': 'The description suggests a door to the north.'
+        }
+    }
+
+
+# Pytest configuration hooks
+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"
+    )

tests/integration/__init__.py

@@ -0,0 +1 @@
+# Integration tests package initialization

tests/test_setup_validation.py

@@ -0,0 +1,96 @@
+"""
+Validation tests to ensure the testing infrastructure is set up correctly.
+"""
+import pytest
+import sys
+from pathlib import Path
+
+
+class TestInfrastructureSetup:
+    """Test that the testing infrastructure is properly configured."""
+
+    def test_pytest_is_working(self):
+        """Verify that pytest is functioning correctly."""
+        assert True
+
+    def test_python_path_includes_project_root(self):
+        """Verify that the project root is in the Python path."""
+        project_root = Path(__file__).parent.parent
+        assert str(project_root) in sys.path or any(
+            project_root.samefile(Path(p)) for p in sys.path if Path(p).exists()
+        )
+
+    @pytest.mark.unit
+    def test_unit_marker_works(self):
+        """Test that the unit test marker is working."""
+        assert True
+
+    @pytest.mark.integration
+    def test_integration_marker_works(self):
+        """Test that the integration test marker is working."""
+        assert True
+
+    @pytest.mark.slow
+    def test_slow_marker_works(self):
+        """Test that the slow test marker is working."""
+        assert True
+
+    def test_temp_dir_fixture(self, temp_dir):
+        """Test that the temp_dir fixture works correctly."""
+        assert temp_dir.exists()
+        assert temp_dir.is_dir()
+
+    def test_temp_file_fixture(self, temp_file):
+        """Test that the temp_file fixture works correctly."""
+        assert temp_file.exists()
+        assert temp_file.is_file()
+        assert temp_file.read_text() == "test content"
+
+    def test_mock_openai_client_fixture(self, mock_openai_client):
+        """Test that the mock OpenAI client fixture works."""
+        response = mock_openai_client.chat.completions.create()
+        assert response.choices[0].message.content == "Test response"
+
+    def test_mock_environment_fixture(self, mock_environment):
+        """Test that the mock environment fixture works."""
+        assert 'api_key' in mock_environment
+        assert 'model' in mock_environment
+        assert mock_environment['model'] == 'gpt-3.5-turbo'
+
+    def test_sample_crafting_tree_fixture(self, sample_crafting_tree):
+        """Test that the sample crafting tree fixture works."""
+        assert 'nodes' in sample_crafting_tree
+        assert 'edges' in sample_crafting_tree
+        assert len(sample_crafting_tree['nodes']) > 0
+
+    def test_textcraft_module_can_be_imported(self):
+        """Test that the TextCraft module can be imported."""
+        try:
+            import TextCraft
+            assert True
+        except ImportError:
+            # If the module doesn't exist yet, that's okay for this validation
+            pytest.skip("TextCraft module not yet available for import")
+
+    def test_project_structure_exists(self):
+        """Test that the expected project structure exists."""
+        project_root = Path(__file__).parent.parent
+
+        # Check for main directories
+        assert (project_root / "TextCraft").exists()
+        assert (project_root / "tests").exists()
+        assert (project_root / "tests" / "unit").exists()
+        assert (project_root / "tests" / "integration").exists()
+
+        # Check for configuration files
+        assert (project_root / "pyproject.toml").exists()
+
+    def test_pytest_mock_is_available(self):
+        """Test that pytest-mock plugin is available."""
+        pytest_mock = pytest.importorskip("pytest_mock")
+        assert pytest_mock is not None
+
+    def test_coverage_is_available(self):
+        """Test that coverage tools are available."""
+        coverage = pytest.importorskip("coverage")
+        assert coverage is not None

tests/unit/__init__.py

@@ -0,0 +1 @@
+# Unit tests package initialization