open/llm-ingestion-okf
1
0
Fork 0
Code Issues Releases 4 Activity

test(gates): retire the K2 track; re-measure the retrieval gate's premises for BM25

Browse source 
Operator decision 2026-09-21: the test track built on material tied to the
operator's employer (K2) is retired -- not re-measured, not frozen. Public
tests and gates run on invented material.

Retrieval gate:
- The four FUSION_PREMISE xfails are gone and pass through their INPUTS: the
  synthetic MISS, LOOKUP and QUOTA bundles were re-measured for BM25 (the
  miss fasit no longer shares the rare word `maa`; lookup and quota decoys
  carry the question's words so each partition and the quota decide their
  own fixture). SPECS_SHA256 moved with them. Rows 2 and 3 green again.
- Row 7's mutants M04, M06, M07, M08, M10 now patch `bm25`, the code the
  default runs. Three survive with 0 ranks moved (passage body, title
  weight, bm25.RRF_K), each with its mechanism printed. M07 was not forced:
  every synthetic body carries its title as a heading.
- Row 9 (K2) removed; row 8 requires `wiki-20` alone, the `r761` and
  `vegnormal` adapters are gone. Chose the broad reading of "K2" because the
  operator decision defines it as employer-tied material and the order's
  grep includes `vegnormal`.

Also removed: tests/test_default_bundle_pin.py, the K2 arms of
test_okf_consume, the four real-arm tests of test_quality, the R761 soft
hyphen test, the N101/N200 delivery tests and okf_accounting_gate's default
real corpus (and H5's guard, which only existed for those defaults). Two
fixtures carrying road-standard identifiers are rewritten with invented ones.

Gate after: 1 10/10, 2 7/7, 3 5/5, 4 6/6, 5 0/1, 6 10/10, 7 11/14,
8 NOT RUN -> GATE RED: rows 5, 7, 8. Suite 2423 passed, 1 skipped,
0 xfailed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-21 10:05:43 +02:00
commit 3d149f955a
12 changed files with 288 additions and 1096 deletions
Download patch file Download diff file Expand all files Collapse all files

150
tests/test_okf_consume.py
View file

@ -853,118 +853,6 @@ def test_the_empty_payload_still_passes_the_checker() -> None:
assert okf_contract_check.check(_skill_declaring(payload), payload).findings == ()
# --- Corpus-conditional arms --------------------------------------------------
K2_BUNDLE = Path.home() / "corpora" / "okf-telling-20260829" / "K2-bundle-20260903"
K2_CONCEPTS = 629
K2_PROPOSED = 618
K2_KEYLESS = 11
requires_k2 = pytest.mark.skipif(
not K2_BUNDLE.is_dir(),
reason=(
f"the K2 corpus is not present at {K2_BUNDLE}. NOT MEASURED, not zero: "
f"this arm covers a denominator of {K2_CONCEPTS} concepts, of which "
f"{K2_PROPOSED} carry `adjudication: proposed` and {K2_KEYLESS} carry no "
"`adjudication` key at all. A skip here is an unmeasured denominator, "
"never a pass."
),
)
@requires_k2
def test_the_eleven_keyless_k2_concepts_come_back_unknown_over_a_stated_denominator() -> None:
# SS 6.1's third state, on real data rather than on a fixture. The 11 are
# asserted as ONE named set: measured, the concepts carrying no
# `adjudication` are EXACTLY those carrying no `bundle_id`, so three
# independent counts would share one blind spot.
root_bundle_id = parse_frontmatter(K2_BUNDLE / "index.md")["bundle_id"]
concepts = [
okf_consume.read_concept(
K2_BUNDLE / f"{concept_id}.md",
bundle_root=K2_BUNDLE,
root_bundle_id=root_bundle_id,
)
for concept_id in okf_consume.enumerate_concepts(K2_BUNDLE)
]
assert len(concepts) == K2_CONCEPTS
unknown = {c.concept_id for c in concepts if c.adjudication == "unknown"}
inherited = {c.concept_id for c in concepts if c.bundle_id_inherited}
proposed = [c for c in concepts if c.adjudication == "proposed"]
assert len(proposed) == K2_PROPOSED
assert len(unknown) == K2_KEYLESS
assert unknown == inherited, "the two sets diverged; the fallback is no longer one fact"
assert all(c.bundle_id == root_bundle_id for c in concepts if c.bundle_id_inherited)
# `adjudicated` has denominator ZERO on this corpus. Stated, not implied.
assert [c for c in concepts if c.adjudication == "adjudicated"] == []
@requires_k2
def test_spent_is_the_delivered_set_where_the_whole_payload_reading_would_refuse() -> None:
# The regression guard, with figures RE-MEASURED here rather than carried
# from the plan: the plan predicted 101 576 B for this excerpt and 188 758 B
# for the payload, both taken before per-line trailing-whitespace stripping
# landed. What this build actually produces is recorded instead.
# Run with `--withheld-full`, because the DEFAULT no longer reaches this
# case and that is the point of `okf-consumption/2`: the whole payload of
# this bundle came to 117 561 B under the default -- inside the limit --
# where under the flat list it did not. The distinction between the two
# readings of SS 7.2 is still real and still reachable, so it is measured
# where it is reachable rather than deleted with the shape that produced
# it. The control below fires if that stops being true.
payload = okf_consume.build_payload(
K2_BUNDLE, question="Hvordan skal prisene fylles ut?", withheld_full=True
)
budget, excerpts = payload["budget"], payload["excerpts"]
assert isinstance(budget, dict) and isinstance(excerpts, list)
whole_payload = len(okf_consume.serialise(payload).encode("utf-8"))
assert whole_payload > int(budget["limit"]), (
"the guard measures nothing: the whole payload already fits, so the two "
"readings of SS 7.2 cannot be told apart on this case"
)
assert int(budget["spent"]) <= int(budget["limit"])
# And the default is now the other side of that line, on the same bundle
# and the same question: the bookkeeping stopped dwarfing the content.
default = okf_consume.build_payload(K2_BUNDLE, question="Hvordan skal prisene fylles ut?")
assert len(okf_consume.serialise(default).encode("utf-8")) < whole_payload
#: The gold set is LOCAL-ONLY: it names corpus documents, which never reach a
#: tracked file here. The test reads it rather than restating it, so this file
#: carries the assertion and not the answer key.
GOLD_SET = PROJECT_ROOT / ".claude/projects/2026-09-07-okf-consume-prepass/hit-at-k-questions.json"
@requires_k2
@pytest.mark.skipif(not GOLD_SET.is_file(), reason=f"the local gold set is absent ({GOLD_SET})")
def test_every_gold_document_in_the_local_set_is_reached_or_named_as_a_miss() -> None:
# SC5 and SC6 together, run against the answer key rather than a literal.
# Row 1's gold is the one confirmed by a signal from outside this
# repository -- a live model reached that document unprompted in three
# navigation steps on 2026-09-06 -- and its gold document holds exactly one
# concept, so it is also the one concept-granularity row.
spec = json.loads(GOLD_SET.read_text(encoding="utf-8"))
questions = spec["questions"]
assert len(questions) >= 5, "fewer than five questions is not the measurement"
hits = 0
for entry in questions:
payload = okf_consume.build_payload(K2_BUNDLE, question=entry["question"], ranking="fusion")
excerpts = payload["excerpts"]
assert isinstance(excerpts, list)
if okf_consume_measure.hit_rank(excerpts, entry["gold_document"]) is not None:
hits += 1
# The published bar, and the published number. A regression that drops a
# row goes red here rather than in a document nobody re-runs.
#
# 5 -> 6 ON 2026-09-10, with no bundle changing: `DEFAULT_SOURCE_QUOTA = 2`
# reaches the one row that had missed everywhere. What that gain is not:
# this metric asks whether the gold DOCUMENT was delivered, and a document
# quota raises how many distinct documents a payload holds, so it is not
# neutral with respect to the rule that moved it.
assert hits == 6, f"hit@8 moved: {hits} of {len(questions)}"
# --- Step 9: the CLI ----------------------------------------------------------
TOOL = PROJECT_ROOT / "tools" / "okf_consume.py"
@ -1198,44 +1086,6 @@ def test_the_shipped_skill_is_the_generator_output_with_the_checkout_made_relati
assert SKILL.read_text(encoding="utf-8") == generated.replace(prefix, "")
@requires_k2
def test_no_corpus_document_name_reaches_any_file_this_work_tracks() -> None:
# CLAUDE.md's public-file rule. The pattern is DERIVED from the corpus's own
# top-level document names at run time rather than hand-picked, so it covers
# every document rather than the six someone thought of -- and so this
# tracked file carries no corpus name of its own.
documents = sorted(
{concept_id.split("/", 1)[0] for concept_id in okf_consume.enumerate_concepts(K2_BUNDLE)}
)
assert len(documents) > 30, "too few documents to be the real corpus"
leak = re.compile("|".join(re.escape(name) for name in documents), re.IGNORECASE)
# The known-positive, first: the pattern must be shown able to find before
# its zero counts as a measurement.
control = (K2_BUNDLE / "index.md").read_text(encoding="utf-8")
assert leak.findall(control), "the pattern cannot find; the zeros below would mean nothing"
tracked = [
SKILL,
SKILL.parent / "references" / "README.md",
SKILL.parent / "references" / "example-payload.json",
PROJECT_ROOT / "tools" / "okf_consume.py",
PROJECT_ROOT / "tools" / "okf_consume_measure.py",
PROJECT_ROOT / "tests" / "test_okf_consume.py",
PROJECT_ROOT / "docs" / "2026-09-07-okf-konsumskill-maaling.md",
PROJECT_ROOT / "docs" / "2026-09-08-blindsone-below-k-k2.md",
PROJECT_ROOT / "docs" / "2026-09-08-blindsone-laas2-budsjett-k2.md",
PROJECT_ROOT / "docs" / "2026-09-08-prisform-og-loggen-k2.md",
PROJECT_ROOT / "docs" / "2026-09-08-kravnummer-tokenisering.md",
PROJECT_ROOT / "docs" / "2026-09-08-sjeldenhetsvekt.md",
PROJECT_ROOT / "docs" / "2026-09-08-claude-code-skill-vilkaarlig-bundle.md",
PROJECT_ROOT / "README.md",
PROJECT_ROOT / "CLAUDE.md",
]
for path in tracked:
assert leak.findall(path.read_text(encoding="utf-8")) == [], path
def _quota_concept(concept_id: str, *, source_file: str) -> okf_consume.Concept:
"""A minimal concept whose only interesting property is its source document."""
return okf_consume.Concept(