llm-ingestion-okf/tests/test_working_method.py
Kjell Tore Guttormsen cf21449ddb docs: remove what this repository published about a consumer's corpus
Operator decision 2026-09-21: nothing from that consumer's collection goes out
on the public remote. The NAME stays where it is already published -- it is a
consumer of this library, named as such, and removing it would mean rewriting
published history, which this repository does not do. What goes is everything
that describes their CONTENT.

Removed across README, CLAUDE.md, CHANGELOG, four dated reports, the
consumption contract, three source modules and three test modules: their
corpus's document and page counts, the concept count of a bundle built from
it, the byte figures of a payload built from it, the question and fasit counts
and recorded score of their evaluation set, a bundle id with two content refs,
an order id naming them, and a path into their repository.

Kept, because the argument survives without the corpus: RATIOS and
percentages. A ratio is the finding -- a withheld list that is 65.5 % of a
payload is a defect at any corpus size -- and it discloses nothing about how
large anyone's collection is. Where a claim lost its denominator it now SAYS
so rather than quietly reading as unmeasured: the gate-refusal limitation in
the README states that the corpus and its counts are deliberately withheld and
points the reader at their own build, which is the number that binds them
anyway.

One integrity pin is kept and named here rather than left to be found: the
retrieval gate still pins that set by sha256, because the pin is what refuses
a self-written file in the right shape, and a checksum discloses nothing about
what it checksums. Its recorded SCORE is gone -- that was their figure about
their own corpus, and the row now says so instead of restating it.

The known-positive constants move with the contract document, as they must.
Suite green, 2372 passed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-21 04:28:15 +02:00

155 lines
6 KiB
Python

"""The generic skill states a WORKING METHOD and an ANSWER FORM, and is default.
Measured by the operator on a large real bundle
documentation, 2026-09-20: the generated skill was an audit contract. All the
discipline sat on the accounting -- markings, denominators, budget lines -- and
none of it on understanding the question, searching again, or writing one
coherent answer. Two sentences actively forbade the second of those.
These tests hold the repair from both sides: the five steps must be there, and
the two forbidding sentences must not come back.
"""
from __future__ import annotations
import json
import subprocess
import sys
from pathlib import Path
PROJECT_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(PROJECT_ROOT / "src"))
from llm_ingestion_okf import contract_check, project, skill # noqa: E402
GOLDEN = PROJECT_ROOT / "examples" / "ingest-golden-segmented-okf-v0-2" / "expected-bundle"
#: The two sentences that made the skill an audit contract. Removed, and named
#: here so a template edit cannot quietly restore either.
FORBIDDEN = (
"Do not go looking for context the pre-pass deliberately withheld",
"not something to retry with a narrower question",
)
#: The five links of the working method, each by a phrase the section must
#: carry. Phrases and not headings, so a rename does not silently pass.
METHOD_MARKS = (
"## Working method",
"Understand the question first",
"Several searches are normal",
"Several bundles",
"Put it together",
"## Answer form",
)
def _generic() -> str:
return skill.render_generic()
def test_the_generic_skill_carries_every_link_of_the_working_method() -> None:
text = _generic()
missing = [mark for mark in METHOD_MARKS if mark not in text]
assert missing == [], f"the generic skill states no {missing}"
def test_neither_forbidding_sentence_survives_in_any_shipped_skill_text() -> None:
template = (PROJECT_ROOT / "skills" / "okf-consume-template" / "SKILL.md").read_text(
encoding="utf-8"
)
shipped = (PROJECT_ROOT / "skills" / "okf-consume" / "SKILL.md").read_text(encoding="utf-8")
generic = _generic()
# The control: the strings are findable at all, measured on a text that
# carries them, so the three zeros below are a measurement.
carrier = "before: " + FORBIDDEN[0] + " and " + FORBIDDEN[1]
for sentence in FORBIDDEN:
assert sentence in carrier
for name, text in (("template", template), ("shipped", shipped), ("generic", generic)):
assert sentence not in text, f"{name} still forbids it"
def test_the_working_method_says_searching_again_is_expected() -> None:
text = _generic()
assert "allowed and expected" in text
assert "okf consume" in text
def test_the_answer_form_names_the_jargon_it_keeps_out_of_the_answer() -> None:
"""The reader gets prose, not the instrument's vocabulary."""
text = _generic()
form = text.split("## Answer form", 1)[1].split("\n## ", 1)[0]
for token in ("below_k", "sha256", "denominator"):
assert token in form, f"the answer form does not name {token} as jargon to keep out"
assert "the questioner's language" in form
def test_the_audit_trail_is_a_choice_and_the_answer_is_not() -> None:
text = _generic()
form = text.split("## Answer form", 1)[1].split("\n## ", 1)[0]
assert "only when the questioner asks" in form
def test_the_generic_skill_is_what_okf_skill_writes_by_default(tmp_path: Path) -> None:
"""The default moves: one skill that serves any bundle and never goes stale.
A per-bundle skill has to be regenerated every time its bundle is rebuilt,
and it refuses out loud (`bundle_mismatch`) when it was not -- so its cost
is not silence, it is a stopped session. The generic one has no bundle's
numbers to go stale.
"""
out = tmp_path / "generic"
written = skill.generate_any(out=out)
assert written.read_text(encoding="utf-8") == _generic()
from llm_ingestion_okf.skill import main as skill_main
assert skill_main([str(GOLDEN), "--out", str(tmp_path / "cli")]) == 0
assert (tmp_path / "cli" / "SKILL.md").read_text(encoding="utf-8") == _generic()
def test_the_per_bundle_form_is_still_reachable(tmp_path: Path) -> None:
from llm_ingestion_okf.skill import main as skill_main
assert skill_main([str(GOLDEN), "--out", str(tmp_path / "one"), "--for-bundle"]) == 0
text = (tmp_path / "one" / "SKILL.md").read_text(encoding="utf-8")
assert "golden-segmented" in text
assert text != _generic()
def test_okf_project_writes_the_generic_skill(tmp_path: Path) -> None:
folder = tmp_path / "Dokumenter"
folder.mkdir()
(folder / "krav.md").write_text(
"## 4 Grunnforhold\n\nGrunnen er morene over berg.\n", encoding="utf-8", newline=""
)
_, written, _ = project.create(folder, out=tmp_path / "project")
assert written.read_text(encoding="utf-8") == _generic()
def test_the_checker_accepts_the_new_template_and_still_refuses_a_thin_one(
tmp_path: Path,
) -> None:
"""`okf check`'s section rule follows the template, never the other way."""
example = PROJECT_ROOT / "skills" / "okf-consume" / "references" / "example-payload.json"
payload = json.loads(example.read_text(encoding="utf-8"))
out = tmp_path / "generic"
written = skill.generate_any(out=out)
report = contract_check.check(written.read_text(encoding="utf-8"), payload)
assert [finding.code for finding in report.findings] == []
thin = written.read_text(encoding="utf-8").replace("## Working method", "## Notes")
assert "skill_section_missing" in {
finding.code for finding in contract_check.check(thin, payload).findings
}
def test_the_installed_command_writes_the_generic_skill(tmp_path: Path) -> None:
result = subprocess.run(
[sys.executable, "-m", "llm_ingestion_okf.cli", "skill", "--out", str(tmp_path / "s")],
capture_output=True,
text=True,
check=False,
cwd=PROJECT_ROOT,
)
assert result.returncode == 0, result.stderr
assert (tmp_path / "s" / "SKILL.md").read_text(encoding="utf-8") == _generic()