agentevals/pyproject.toml at main · agentevals-dev/agentevals · 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
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "agentevals-cli"
version = "0.7.1"
description = "Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces"
readme = "README.md"
requires-python = ">=3.11"
dependencies = [
    "google-adk[eval]>=1.30.0",
    "click>=8.0",
    "tabulate>=0.9.0",
    "fastapi>=0.115.0",
    "uvicorn[standard]>=0.32.0",
    "python-multipart>=0.0.12",
    "python-dotenv>=1.0.0",
    "opentelemetry-proto>=1.36.0",
    "pyyaml>=6.0",
    "httpx>=0.27.0",
]

[project.optional-dependencies]
live = [
    "mcp>=1.26.0",
    "httpx>=0.27.0",
]
streaming = [
    "opentelemetry-sdk>=1.20.0",
    "websockets>=12.0",
]
openai = [
    "openai>=2.0",
]

[project.scripts]
agentevals = "agentevals.cli:main"

[tool.hatch.build]
artifacts = ["src/agentevals/_static/**"]

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

[tool.uv.workspace]
members = ["packages/evaluator-sdk-py"]

[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src"]
markers = [
    "integration: OTLP pipeline tests with ASGI apps (no API keys)",
    "e2e: End-to-end tests requiring API keys and real agents",
]
asyncio_mode = "auto"

[dependency-groups]
dev = [
    "pytest>=9.0.2",
    "pytest-asyncio>=0.24.0",
    "httpx>=0.27.0",
    "ruff>=0.11.0",
]
e2e = [
    "strands-agents[openai]>=1.29.0",
    "langchain>=1.2.0",
    "langchain-openai>=1.1.10",
    "openai>=2.30.0",
    "openai-agents>=0.13.0",
    "opentelemetry-sdk>=1.36.0",
    "opentelemetry-exporter-otlp-proto-http>=1.36.0",
    "opentelemetry-instrumentation-openai-v2",
    "opentelemetry-instrumentation-openai-agents-v2>=0.1.0",
    "python-dotenv>=1.0.0",
]

[tool.ruff]
target-version = "py311"
line-length = 120
fix = true
src = ["src", "packages", "tests"]

[tool.ruff.lint.isort]
known-first-party = ["agentevals"]

[tool.ruff.format]
docstring-code-format = true

[tool.ruff.lint]
select = ["E", "F", "W", "B", "Q", "I", "ASYNC", "T20"]
ignore = ["F401", "E501", "B008", "ASYNC109"]

[tool.ruff.lint.per-file-ignores]
"examples/**" = ["T201", "E402", "B007"]
"src/agentevals/sdk.py" = ["T201"]
"src/agentevals/streaming/__init__.py" = ["T201"]
"packages/evaluator-sdk-py/**" = ["T201"]
"tests/test_otlp_receiver.py" = ["E402"]

[tool.uv.extra-build-dependencies]
rouge-score = ["setuptools"]