ai-agents-reality-check/pyproject.toml at main · Cre4T3Tiv3/ai-agents-reality-check · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
[project]
name = "ai-agents-reality-check"
version = "0.1.0"
description = "Revealing the high failure rate of AI agents with empirical benchmarks, statistical analysis, and real-world citations."
authors = [{name = "Jesse Moses (@Cre4T3Tiv3)", email = "jesse@bytestacklabs.com"}]
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.11"
keywords = ["ai", "agents", "benchmark", "machine-learning", "reality-check"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Testing",
]

dependencies = [
    "matplotlib>=3.5.0",
    "numpy>=1.21.0",
    "pandas>=1.3.0",
    "seaborn>=0.11.0",
    "rich>=10.0.0",
    "typer>=0.9.0",
    "markdown",
    "scipy>=1.7.0",
    "jsonschema>=4.21.1",
]

[project.optional-dependencies]
dev = [
    "pytest>=7.0.0",
    "pytest-asyncio>=0.21.0",
    "black>=22.0.0",
    "mypy>=1.0.0",
    "pandas-stubs",
    "types-Markdown>=3.0.0",
    "types-seaborn",
    "ruff>=0.4.0",
    "jsonschema>=4.21.1",
    "scikit-learn>=1.0.0",
    "plotly>=5.0.0",
    "dash>=2.0.0",
]

[project.urls]
Homepage = "https://github.com/Cre4T3Tiv3/ai-agents-reality-check"
Repository = "https://github.com/Cre4T3Tiv3/ai-agents-reality-check"
Issues = "https://github.com/Cre4T3Tiv3/ai-agents-reality-check/issues"
Documentation = "https://github.com/Cre4T3Tiv3/ai-agents-reality-check#readme"

[project.scripts]
agent-benchmark = "ai_agents_reality_check.cli:main"

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

[tool.black]
line-length = 88
target-version = ['py311', 'py312']

[tool.mypy]
ignore_missing_imports = true
python_version = "3.11"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
addopts = [
    "-v",
    "--tb=short",
    "--strict-markers",
    "--disable-warnings",
    "--color=yes"
]
asyncio_mode = "auto"
markers = [
    "unit: Unit tests for individual components",
    "functional: Functional tests for end-to-end workflows",
    "integration: Integration tests with external dependencies",
    "slow: Tests that take more than 10 seconds",
    "benchmark: Benchmark execution tests"
]


# Add test coverage configuration
[tool.coverage.run]
source = ["ai_agents_reality_check"]
omit = [
    "tests/*",
    "*/conftest.py",
    "*/__init__.py"
]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "raise AssertionError",
    "raise NotImplementedError"
]

[tool.ruff]
target-version = "py311"
line-length = 88
src = ["ai_agents_reality_check", "tests"]
exclude = ["__pypackages__", "venv", ".venv", "build", "dist"]

[tool.ruff.lint]
select = [
    "E",  # pycodestyle errors
    "F",  # pyflakes
    "I",  # isort
    "N",  # pep8-naming
    "UP", # pyupgrade
    "B",  # flake8-bugbear
    "C4", # flake8-comprehensions
    "PL", # pylint
    "SIM", # flake8-simplify
]
ignore = [
    "E501",   # line too long (handled by formatter)
    "PLR0913", # too many arguments
    "PLR0915", # too many statements
]

[tool.ruff.lint.per-file-ignores]
"tests/*" = ["PLR2004"]  # magic value comparison in tests is OK

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