pyproject.toml

[project]
name = "prolewiki-llm"
version = "0.1.0"
description = "GRPO fine-tuning and reward functions for Marxist-Leninist language models"
readme = "README.md"
license = { text = "AGPL-3.0-only" }
requires-python = ">=3.12"
dependencies = [
    # Core ML
    "transformers>=4.40.0",
    "sentence-transformers>=3.0.0",
    "torch>=2.0.0",
    # NLP
    "spacy>=3.8.0",
    # Logging
    "wandb>=0.17.0",
    # Data
    "pydantic>=2.0.0",
]

[dependency-groups]
dev = [
    # Testing
    "pytest>=8.0.0",
    "pytest-asyncio>=0.24.0",
    "pytest-cov>=6.0.0",
    "pytest-mock>=3.14.0",
    # Code Quality
    "mypy>=1.13.0",
    "ruff>=0.8.0",
    "pre-commit>=4.0.0",
    # Type Stubs
    "types-PyYAML>=6.0.0",
]
training = [
    # GRPO training (GPU required)
    "unsloth>=2024.8",
    "trl>=0.9.0",
    "peft>=0.12.0",
    "bitsandbytes>=0.43.0",
    "datasets>=2.20.0",
    "vllm>=0.5.0",
]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["src/prolewiki_llm"]

# =============================================================================
# PYTEST
# =============================================================================
[tool.pytest.ini_options]
pythonpath = ["src"]
testpaths = ["tests"]
asyncio_mode = "auto"
asyncio_default_fixture_loop_scope = "function"
markers = [
    "unit: Fast unit tests for isolated components (no I/O)",
    "integration: Integration tests for shell scripts and Docker behavior",
    "slow: Tests that take significant time (NLI, embedding)",
    "gpu: Tests requiring GPU (training)",
]

# =============================================================================
# RUFF (Linting + Formatting + Import Sorting)
# =============================================================================
[tool.ruff]
line-length = 100
target-version = "py312"
src = ["src"]

[tool.ruff.lint]
select = [
    "E",      # pycodestyle errors
    "W",      # pycodestyle warnings
    "F",      # pyflakes
    "I",      # isort (import sorting)
    "B",      # flake8-bugbear
    "C4",     # flake8-comprehensions
    "UP",     # pyupgrade
    "ARG",    # unused arguments
    "SIM",    # flake8-simplify
    "RUF",    # ruff-specific
]
ignore = [
    "E501",   # line length handled by formatter
    "RUF001", # ambiguous unicode (we use Cyrillic/Chinese text)
]

[tool.ruff.lint.per-file-ignores]
"tests/**/*.py" = [
    "ARG001",  # unused mock function arguments are common in tests
    "ARG002",  # unused method arguments (fixtures) are common in tests
    "SIM117",  # nested with statements for multiple mocks are clearer
]
"src/prolewiki_llm/**/*.py" = [
    "ARG001",  # **kwargs required by GRPOTrainer reward function interface
]

[tool.ruff.lint.isort]
known-first-party = ["prolewiki_llm"]

[tool.ruff.format]
quote-style = "double"
indent-style = "space"

# =============================================================================
# MYPY (Type Checking)
# =============================================================================
[tool.mypy]
python_version = "3.12"
strict = true
mypy_path = ["src"]
explicit_package_bases = true
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
show_error_codes = true
exclude = ["tests/", "build/", "dist/"]

[[tool.mypy.overrides]]
module = [
    "transformers",
    "transformers.*",
    "sentence_transformers.*",
    "spacy",
    "spacy.*",
    "torch",
    "torch.*",
    "wandb",
    "wandb.*",
    "datasets",
    "datasets.*",
    "trl",
    "trl.*",
    "unsloth",
    "unsloth.*",
    "vllm",
    "vllm.*",
    "peft",
    "peft.*",
]
ignore_missing_imports = true

# =============================================================================
# COVERAGE
# =============================================================================
[tool.coverage.run]
source = ["src/prolewiki_llm"]
branch = true
omit = ["*/tests/*"]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "if TYPE_CHECKING:",
    "raise NotImplementedError",
]