[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",
    "rich",
    "xlsxwriter",     # excel result workbook
    "httpx",          # model fingerprint probing (evalharness/fingerprint)
    "tree_sitter>=0.21",        # vendored BFCL official AST checker (python)
    "tree-sitter-java>=0.21",   # bfcl java categories
    "tree-sitter-javascript>=0.21",  # bfcl javascript categories
]

[project.optional-dependencies]
# none today: the official BFCL checker is vendored under
# evalharness/third_party/bfcl (Apache-2.0); heavy execution environments
# (humaneval/bigcodebench/swe) live in docker images, never in the venv

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

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

[tool.setuptools.package-data]
"*" = ["*.jsonl", "*.json", "*.csv", "*.tsv", "*.txt", "*.md", "*.yaml", "references/*.json"]