build

docs: audit remote-only liveness evidence #66

	name: build

	on:
	push:
	pull_request:
	workflow_dispatch:

	jobs:
	build-and-test:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- name: Install
	run: pip install -e ".[dev]"
	- name: Rebuild curated dataset (must be deterministic)
	run: \|
	python pipeline/build_security_dataset.py \
	--in data/raw/train.classified.parquet \
	--out /tmp/rebuilt.parquet
	python - <<'PY'
	import pandas as pd
	a = pd.read_parquet("data/ethereum_vulns.parquet")
	b = pd.read_parquet("/tmp/rebuilt.parquet")
	assert len(a) == len(b), f"row count drift: committed {len(a)} vs rebuilt {len(b)}"
	assert set(a["id"]) == set(b["id"]), "id set drift — commit the rebuilt parquet"
	print(f"deterministic: {len(a)} rows")
	PY
	- name: Test
	run: pytest -q

Navigation Menu