[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"]

[project.optional-dependencies]
hub = ["datasets"]            # HuggingFace-hosted datasets
parquet = ["pyarrow"]         # parquet sources (ModelScope/HF raw mirrors)
math = ["sympy", "pylatexenc"]  # symbolic math grading (aime/math family), official PRM800K logic
exec = ["numpy", "scipy"]     # DROP official aligner (linear_sum_assignment)
bfcl = ["bfcl-eval", "soundfile"]  # OFFICIAL bfcl ast_checker (heavy: pulls 5 cloud SDKs +
                                   # qwen-agent; native scorer is the dependency-free default)
all = ["datasets", "pyarrow", "sympy", "pylatexenc", "numpy", "scipy"]  # everything conflict-free

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

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

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