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

[project]
name = "agent-regress-cli"
version = "0.1.9"
description = "Statistical regression testing for LLM agents. Get a p-value on whether behavior actually shifted between versions, not just whether one run looked different. Apache 2.0, self-hostable, no SaaS dependency -- a Promptfoo alternative for the statistical testing gap threshold-based eval tools don't cover."
readme = "README.md"
requires-python = ">=3.10"
license = { text = "Apache-2.0" }
authors = [
    { name = "Rudrendu Paul" },
    { name = "Sourav Nandy" },
]
keywords = [
    "llm", "agents", "testing", "regression", "statistics", "p-value",
    "cohen-d", "mann-whitney", "langgraph", "openai-agents", "crewai",
    "promptfoo-alternative", "eval", "benchmark", "ci-cd",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Environment :: Console",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Typing :: Typed",
]
dependencies = [
    "scipy>=1.13",
    "numpy>=1.26",
    "jsonschema>=4.21",
]

[project.optional-dependencies]
langgraph = ["langgraph>=0.2"]
openai-agents = ["openai-agents>=0.1"]
crewai = ["crewai>=0.80"]
langchain = ["langchain-core>=0.3"]
mcp = ["mcp[cli]>=2.0.0"]
dev = [
    "pytest>=8",
    "pytest-benchmark>=4.0",
    "pytest-cov>=5.0",
    "mypy>=1.10",
    "ruff>=0.9",
    "pre-commit>=3.7",
]

[project.urls]
Homepage = "https://github.com/RudrenduPaul/agent-eval"
Repository = "https://github.com/RudrenduPaul/agent-eval"
Issues = "https://github.com/RudrenduPaul/agent-eval/issues"
"Author - Rudrendu Paul" = "https://github.com/RudrenduPaul"
"Author - Sourav Nandy" = "https://github.com/Sourav-nandy-ai"

[project.scripts]
agent-regress = "agent_regress.cli:main"
agent-regress-mcp = "agent_regress.mcp_server:main"

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

[tool.ruff]
target-version = "py310"
line-length = 88
src = ["src"]

[tool.ruff.lint]
select = ["E", "F", "B", "I", "N", "UP", "S", "PL", "RUF"]
ignore = [
    "S101",
    "PLR2004",
]

[tool.ruff.lint.per-file-ignores]
"tests/*" = ["S", "PLR2004", "PLR0913", "PLC0415", "B017", "E501"]
"benchmarks/*" = ["S", "E501", "PLC0415"]
"examples/*" = ["S", "T201"]

[tool.mypy]
python_version = "3.10"
strict = true
warn_return_any = true
warn_unused_ignores = true
show_error_codes = true
mypy_path = "src"

[[tool.mypy.overrides]]
module = [
    "scipy.*",
    "langgraph.*",
    "langchain_core.*",
    "openai.*",
    "agents.*",
    "crewai.*",
    "mcp.*",
]
ignore_missing_imports = true

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
addopts = "--tb=short -q"
markers = [
    "integration: marks tests that require real API keys",
    "slow: marks tests that take > 10s to run",
]

[tool.coverage.run]
source = ["src"]
omit = [
    "tests/*",
    "benchmarks/*",
    "examples/*",
    "src/agent_regress/integrations/*",
]

[tool.coverage.report]
fail_under = 80

[tool.uv]
# crewai (crewai extra) pins json-repair~=0.25.2, which is GHSA-xf7x-x43h-rpqh
# (unbounded CPU DoS via circular $ref). Force the patched release instead.
override-dependencies = ["json-repair>=0.60.1"]