68 lines
1.6 KiBLFS
TOML
68 lines
1.6 KiBLFS
TOML
[project]
|
|
name = "skillsbench"
|
|
version = "0.1.0"
|
|
description = "A benchmark that evaluate both skill effectiveness and agent behavior through gym-style benchmarking"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"a2a-sdk[http-server]==0.3.20",
|
|
"benchflow[sandbox-daytona]>=0.6.3,<0.7",
|
|
"fastapi>=0.115.0",
|
|
"httpx>=0.28.0",
|
|
"pyyaml>=6.0.0",
|
|
"uvicorn>=0.38.0",
|
|
]
|
|
|
|
[tool.ruff]
|
|
target-version = "py312"
|
|
line-length = 144
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"E", # pycodestyle errors
|
|
"W", # pycodestyle warnings
|
|
"F", # pyflakes
|
|
"I", # isort
|
|
"B", # flake8-bugbear
|
|
"C4", # flake8-comprehensions
|
|
"UP", # pyupgrade
|
|
"RUF", # ruff-specific rules
|
|
]
|
|
ignore = [
|
|
"E501", # line too long (handled by formatter)
|
|
"E722", # bare except (common in scripts)
|
|
"B008", # function call in default argument
|
|
"B905", # zip without strict
|
|
]
|
|
|
|
[tool.ruff.lint.isort]
|
|
known-first-party = ["skillsbench"]
|
|
force-single-line = false
|
|
combine-as-imports = true
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
skip-magic-trailing-comma = false
|
|
line-ending = "auto"
|
|
docstring-code-format = true
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
strict = true
|
|
warn_return_any = true
|
|
warn_unused_ignores = true
|
|
|
|
[tool.uv.sources]
|
|
skills-ref = { git = "https://github.com/agentskills/agentskills.git", subdirectory = "skills-ref", rev = "7f094a2f794fbf6ccf805f601cdc497110b8a8cd" }
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"duckdb>=1.4.0",
|
|
"mypy>=1.13.0",
|
|
"pre-commit>=4.0.0",
|
|
"pytest-asyncio>=1.3.0",
|
|
"ruff>=0.8.0",
|
|
"skills-ref>=0.1.0",
|
|
]
|