COE-231: Bootstrap repository, tooling, and package skeleton

.gitignore

@@ -1 +1,60 @@
-old
+# 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
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
+
+# Type checking
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Linting
+.ruff_cache/
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# uv
+
+# OS
+.DS_Store
+Thumbs.db

Makefile

@@ -0,0 +1,44 @@
+# StackPerf Developer Commands
+# Run with: make <target>
+
+.PHONY: help install sync lint format type-check test test-cov clean quality
+
+help: ## Show this help message
+	@echo "StackPerf - Available commands:"
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-15s\033[0m %s\n", $$1, $$2}'
+
+install: ## Install dependencies with uv
+	uv sync --all-extras
+
+sync: ## Sync dependencies with uv (includes dev extras)
+	uv sync --all-extras
+
+lint: ## Run linting with ruff
+	uv run ruff check src tests
+
+format: ## Format code with ruff
+	uv run ruff format src tests
+	uv run ruff check --fix src tests
+
+type-check: ## Run static type checking with mypy
+	uv run mypy src
+
+test: ## Run tests with pytest
+	uv run pytest
+
+test-cov: ## Run tests with coverage report
+	uv run pytest --cov=src --cov-report=term-missing
+
+clean: ## Clean build artifacts and cache
+	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
+	find . -type d -name "*.egg-info" -exec rm -rf {} + 2>/dev/null || true
+	find . -type d -name ".mypy_cache" -exec rm -rf {} + 2>/dev/null || true
+	find . -type d -name ".pytest_cache" -exec rm -rf {} + 2>/dev/null || true
+	find . -type d -name ".ruff_cache" -exec rm -rf {} + 2>/dev/null || true
+	rm -rf .coverage htmlcov dist build 2>/dev/null || true
+	@echo "Cleaned build artifacts and caches"
+
+quality: ## Run all quality checks (lint, type-check, test)
+	$(MAKE) lint
+	$(MAKE) type-check
+	$(MAKE) test

pyproject.toml

@@ -0,0 +1,94 @@
+[project]
+name = "stackperf"
+version = "0.1.0"
+description = "LiteLLM benchmarking system for provider, model, and harness comparison"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "Proprietary" }
+authors = [{ name = "Trilogy AI COE" }]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+
+dependencies = []
+
+[project.optional-dependencies]
+dev = [
+    "ruff>=0.4.0",
+    "mypy>=1.10.0",
+    "pytest>=8.0.0",
+    "pytest-cov>=4.1.0",
+    "hatchling>=1.0.0",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/stackperf"]
+
+[tool.ruff]
+target-version = "py311"
+line-length = 88
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # Pyflakes
+    "I",   # isort
+    "B",   # flake8-bugbear
+    "C4",  # flake8-comprehensions
+    "UP",  # pyupgrade
+    "SIM", # flake8-simplify
+]
+ignore = [
+    "E501", # line too long (handled by formatter)
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["stackperf"]
+
+[tool.mypy]
+python_version = "3.11"
+strict = true
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+check_untyped_defs = true
+disallow_untyped_decorators = true
+no_implicit_optional = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_no_return = true
+follow_imports = "silent"
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = "tests.*"
+disallow_untyped_defs = false
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_functions = ["test_*"]
+addopts = "-v --tb=short"
+
+[tool.coverage.run]
+source = ["src"]
+omit = ["tests/*"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise NotImplementedError",
+    "if TYPE_CHECKING:",
+]

src/stackperf/__init__.py

@@ -0,0 +1,3 @@
+"""StackPerf - LiteLLM benchmarking system for provider, model, and harness comparison."""
+
+__version__ = "0.1.0"

src/stackperf/api/__init__.py

@@ -0,0 +1 @@
+"""StackPerf module."""

src/stackperf/benchmark_core/__init__.py

@@ -0,0 +1 @@
+"""StackPerf module."""

src/stackperf/cli/__init__.py

@@ -0,0 +1 @@
+"""StackPerf module."""

src/stackperf/collectors/__init__.py

@@ -0,0 +1 @@
+"""StackPerf module."""

src/stackperf/reporting/__init__.py

@@ -0,0 +1 @@
+"""StackPerf module."""

tests/__init__.py

@@ -0,0 +1 @@
+"""StackPerf test suite."""

tests/test_imports.py

@@ -0,0 +1,44 @@
+"""Import smoke tests for each top-level package."""
+
+
+
+def test_import_stackperf() -> None:
+    """Test that the main package can be imported."""
+    import stackperf
+
+    assert stackperf.__version__ == "0.1.0"
+
+
+def test_import_benchmark_core() -> None:
+    """Test that benchmark_core module can be imported."""
+    from stackperf import benchmark_core
+
+    assert benchmark_core is not None
+
+
+def test_import_cli() -> None:
+    """Test that cli module can be imported."""
+    from stackperf import cli
+
+    assert cli is not None
+
+
+def test_import_collectors() -> None:
+    """Test that collectors module can be imported."""
+    from stackperf import collectors
+
+    assert collectors is not None
+
+
+def test_import_reporting() -> None:
+    """Test that reporting module can be imported."""
+    from stackperf import reporting
+
+    assert reporting is not None
+
+
+def test_import_api() -> None:
+    """Test that api module can be imported."""
+    from stackperf import api
+
+    assert api is not None