[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"

[project]
name = "evalharness"
version = "0.1.0"
description = "A plugin-based LLM/agent evaluation harness (data layer first)"
requires-python = ">=3.10"
dependencies = [
    "pydantic>=2",
    "datasets",       # HuggingFace-hosted datasets (light, conflict-free)
    "pyarrow",        # parquet sources (ModelScope/HF raw mirrors)
    "sympy",          # official PRM800K symbolic math grading
    "pylatexenc",
    "numpy",          # official DROP aligner
    "scipy",
]

[project.optional-dependencies]
bfcl = ["bfcl-eval", "soundfile"]  # heavy: official bfcl ast_checker (pulls 5 cloud SDKs
                                   # + qwen-agent); native scorer is the default

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

[tool.setuptools.packages.find]
include = ["evalharness*"]

[tool.setuptools.package-data]
"*" = ["*.jsonl", "*.json", "*.csv", "*.tsv"]