exploitbench-eval/pyproject.toml at main · Generality-Labs/exploitbench-eval · 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
[build-system]
requires = ["setuptools>=64", "setuptools_scm[toml]>=8"]
build-backend = "setuptools.build_meta"

[tool.setuptools_scm]
fallback_version = "0.0.0+unknown"

[tool.setuptools.packages.find]
where = ["src"]
include = ["exploitbench*"]

[tool.setuptools.package-data]
"*" = ["compose.yaml", "eval.yaml", "run_configs/*.yaml"]

[tool.ruff]
src = ["src"]
target-version = "py311"

[tool.ruff.lint]
select = [
    "E",
    "W",
    "F",
    "I",
    "SIM101",
    "YTT",
    "LOG",
    "NPY",
    "PLE",
    "PLR",
    "PLW",
    "UP006",
    "UP007",
    "UP045",
    "FURB",
    "TID252",
]
ignore = [
    "E501",
    "PLR0911",
    "PLR0912",
    "PLR0913",
    "PLR0915",
]

[tool.ruff.lint.per-file-ignores]
"**/tests/*" = ["PLR2004"]

[tool.ruff.lint.flake8-tidy-imports]
ban-relative-imports = "all"

[tool.pytest.ini_options]
minversion = "7.0"
addopts = "--import-mode=importlib"
testpaths = ["tests"]
asyncio_mode = "auto"
log_level = "WARNING"
markers = [
    "slow: marks tests that are slow to run; enable with --runslow or RUN_SLOW_TESTS=1",
    "docker: marks tests that pull or build docker images",
]

[tool.mypy]
exclude = [
    "build",
]
warn_unused_ignores = true
no_implicit_reexport = true
strict_equality = true
warn_redundant_casts = true
warn_unused_configs = true

[[tool.mypy.overrides]]
module = ["exploitbench.*"]
warn_return_any = true
disallow_untyped_defs = true
disallow_any_generics = true
disallow_subclassing_any = true
disallow_untyped_calls = true
disallow_untyped_decorators = true
extra_checks = true

[project]
name = "exploitbench"
description = "ExploitBench bench-v8 (V8 memory-corruption exploit development) as an Inspect AI eval"
authors = [{ name = "ChaoticCooties" }]
readme = "README.md"
requires-python = ">=3.11"
license = "MIT"
dynamic = ["version"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Environment :: Console",
    "Intended Audience :: Science/Research",
    "Natural Language :: English",
    "Programming Language :: Python :: 3",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Operating System :: OS Independent",
]
dependencies = [
    "anthropic",
    "google-genai",
    "inspect_ai==0.3.263",
    "inspect_swe==0.2.70",
    "openai",
    "pyyaml>=5.1.0",
    "mcp>=1.0.0",
]

[project.urls]
"Source Code" = "https://github.com/Generality-Labs/exploitbench-eval"
"Issue Tracker" = "https://github.com/Generality-Labs/exploitbench-eval/issues"

[project.entry-points.inspect_ai]
exploitbench = "exploitbench"

[project.scripts]
exploitbench-report = "exploitbench.reporting:main"

[dependency-groups]
dev = [
    "mypy",
    "pytest",
    "pytest-asyncio",
    "ruff==0.13.2",
    "types-PyYAML",
]