"""The bundle the DEFAULT build produces, pinned where a regression goes red. `tests/test_okf_consume.py` pinned hit@8 against the Arm B bundle alone -- the configuration `okf build` stopped emitting on 2026-09-08. A published number measured on a bundle nobody produces is a number that cannot regress, so the guarantee it looks like was never held by anything. This file pins the CURRENT default: `--outline-run 3 --table-grid --unit-fold --drop-wrapped-outline --outline-gate`, the configuration round 6 moved the default to on 2026-09-09 after measuring hit@8 on exactly this bundle. The gold set is LOCAL-ONLY and stays that way: no question and no `gold_document` is reproduced here, and a row is named by its INDEX, the way `docs/2026-09-07-okf-konsumskill-maaling.md` already names them. The bundle itself is a build artefact, not a fixture: it is 810 files of a consumer's corpus and this repository is public. Absent, these tests SKIP with the command that rebuilds it -- "not measured", never zero. """ from __future__ import annotations import json import sys from pathlib import Path import pytest PROJECT_ROOT = Path(__file__).resolve().parents[1] sys.path.insert(0, str(PROJECT_ROOT / "tools")) import okf_consume # noqa: E402 import okf_consume_measure # noqa: E402 #: Built by: #: okf build /K2/trinn1 \ #: --bundle ~/corpora/okf-telling-20260829/K2-bundle-default-20260909 \ #: --bundle-id k2-trinn1-20260903 --okf-version 0.2 #: with no arm flag at all -- the package default, which is the point. DEFAULT_BUNDLE = Path.home() / "corpora" / "okf-telling-20260829" / "K2-bundle-default-20260909" GOLD_SET = PROJECT_ROOT / ".claude/projects/2026-09-07-okf-consume-prepass/hit-at-k-questions.json" requires_default_bundle = pytest.mark.skipif( not DEFAULT_BUNDLE.is_dir() or not GOLD_SET.is_file(), reason=( f"the default-configuration K2 bundle is not present at {DEFAULT_BUNDLE}. " "NOT MEASURED, not zero: rebuild it with `okf build /K2/trinn1 " "--bundle --bundle-id k2-trinn1-20260903 --okf-version 0.2`" ), ) #: Measured 2026-09-09 on the bundle above. EXPECTED_CONCEPTS = 425 EXPECTED_HITS = 5 #: Rank per question INDEX, `None` for the row that misses on every bundle and #: every configuration measured so far. The identity is the index; the question #: stays in the local-only gold set. EXPECTED_RANKS = (1, 1, 1, 1, 1, None) @requires_default_bundle def test_the_default_bundle_holds_its_concept_count() -> None: assert len(list(okf_consume.enumerate_concepts(DEFAULT_BUNDLE))) == EXPECTED_CONCEPTS @requires_default_bundle def test_hit_at_eight_holds_rank_one_on_every_row_it_held() -> None: """The acceptance criterion round 6's default move had to clear. Not the hit COUNT alone: the count survived a configuration that lost a row from rank 1 to rank 2, which is exactly how the previous round's regression hid. The rank per row is the pin. """ questions = json.loads(GOLD_SET.read_text(encoding="utf-8"))["questions"] assert len(questions) == len(EXPECTED_RANKS), "the gold set changed shape" ranks = [] for entry in questions: payload = okf_consume.build_payload(DEFAULT_BUNDLE, question=entry["question"]) excerpts = payload["excerpts"] assert isinstance(excerpts, list) ranks.append(okf_consume_measure.hit_rank(excerpts, entry["gold_document"])) assert tuple(ranks) == EXPECTED_RANKS, f"hit@8 ranks moved: {ranks}" assert sum(rank is not None for rank in ranks) == EXPECTED_HITS @requires_default_bundle def test_the_bundle_declares_the_identity_the_reader_needs() -> None: """Whatever else moves, the bundle stays one the reading direction opens.""" assert okf_consume.root_bundle_id_of(DEFAULT_BUNDLE) == "k2-trinn1-20260903"