Repository navigation

fix(tests): defer annotations in dataset_materialize fake client for … #2

	name: Eval Catalog
	on:
	push:
	branches: [main, master]
	pull_request:

	jobs:
	eval:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- run: pip install -e ".[dev]"
	- run: pytest tests/ -q --cov=src/analyzer --cov-report=term-missing
	- name: In-process catalog eval
	run: \|
	python - <<'PY'
	import json
	from eval.catalog_loader import load_catalog
	from eval.catalog_runner import run_catalog_inprocess
	from eval.metrics import global_counts, precision_recall_f1
	rows = run_catalog_inprocess(load_catalog())
	counts = global_counts(rows)
	p, r, f1 = precision_recall_f1(counts["TP"], counts["FP"], counts["FN"])
	print(json.dumps({"counts": counts, "precision": p, "recall": r, "f1": f1}))
	assert counts["FN"] == 0, f"FN regression: {counts['FN']}"
	assert counts["FP"] <= 10, f"FP budget exceeded: {counts['FP']}"
	PY