ovos-plugin-arena/pyproject.toml at dev · OpenVoiceOS/ovos-plugin-arena · 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
[build-system]
requires = ["setuptools>=64"]
build-backend = "setuptools.build_meta"

[project]
name = "ovos-plugin-arena"
description = "Blind A/B evaluation and benchmark leaderboards for OpenVoiceOS plugins"
readme = "README.md"
license = "Apache-2.0"
requires-python = ">=3.10"
dynamic = ["version"]
authors = [
    {name = "JarbasAi", email = "jarbasai@mailfence.com"},
]
keywords = ["ovos", "openvoiceos", "benchmark", "elo", "arena", "intent", "stt", "tts", "wake-word"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Programming Language :: Python :: 3",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
    "pydantic>=2.0,<3.0",
]

[project.urls]
Homepage = "https://github.com/OpenVoiceOS/ovos-plugin-arena"

[project.optional-dependencies]
# HuggingFace prediction dataset ingestion (assemble CLI, runners)
hf = [
    "huggingface_hub>=0.24",
    "datasets>=2.20",
]
# Audio-modality benchmarks (STT / wake word / TTS): decode + stream clips.
# The STT/TTS/wake-word OVOS plugins themselves are installed separately.
audio = [
    "numpy",
    "soundfile",
    "pyarrow>=14",
]
test = [
    "pytest>=7.4",
    "pytest-cov>=4.1",
    "huggingface_hub>=0.24",
    "numpy",
]
lint = [
    "ruff>=0.6",
    "mypy>=1.10",
]

[project.scripts]
ovos-arena = "arena.cli:main"

[tool.setuptools]
packages = ["arena", "registry", "runner"]

[tool.setuptools.dynamic]
version = {attr = "arena.version.__version__"}

[tool.pytest.ini_options]
testpaths = ["tests"]
markers = [
    "network: tests that hit external services (HuggingFace, GitHub)",
]

[tool.ruff]
target-version = "py310"
line-length = 100
exclude = ["frontend-static", "predictions"]

[tool.ruff.lint]
select = ["E", "F", "I", "UP", "B"]
ignore = ["B017"]  # pydantic raises plain ValidationError/ValueError in tests; pytest.raises(Exception) is intentional

[tool.mypy]
plugins = ["pydantic.mypy"]
check_untyped_defs = true
ignore_missing_imports = true

[[tool.mypy.overrides]]
module = ["arena.elo", "arena.models", "registry.schemas"]
disallow_untyped_defs = true

[[tool.mypy.overrides]]
module = ["runner.*"]
ignore_errors = true

[tool.coverage.run]
source = ["arena", "registry", "runner"]
omit = ["runner/migrate/*", "benchmarks/*"]

[tool.coverage.report]
fail_under = 56