feat(consume): read a concept, with adjudication absence as its own state

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-07 09:08:41 +02:00
commit 1ec3f5289c
2 changed files with 205 additions and 0 deletions

View file

@ -21,15 +21,20 @@ house pattern rather than new inventions:
from __future__ import annotations from __future__ import annotations
import hashlib
import os import os
import sys import sys
from pathlib import Path from pathlib import Path
import pytest
PROJECT_ROOT = Path(__file__).resolve().parents[1] PROJECT_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(PROJECT_ROOT / "tools")) sys.path.insert(0, str(PROJECT_ROOT / "tools"))
import okf_consume # noqa: E402 import okf_consume # noqa: E402
from llm_ingestion_okf.materialize import parse_frontmatter # noqa: E402
GOLDEN = PROJECT_ROOT / "examples" / "ingest-golden-segmented-okf-v0-2" / "expected-bundle" GOLDEN = PROJECT_ROOT / "examples" / "ingest-golden-segmented-okf-v0-2" / "expected-bundle"
@ -108,3 +113,81 @@ def test_the_ref_covers_the_indexes_too_since_the_walk_reads_them(tmp_path: Path
nested = copy / "krav" / "1-1" / "index.md" nested = copy / "krav" / "1-1" / "index.md"
nested.write_text(nested.read_text(encoding="utf-8") + "\nfritekst\n", encoding="utf-8") nested.write_text(nested.read_text(encoding="utf-8") + "\nfritekst\n", encoding="utf-8")
assert okf_consume.bundle_ref(copy) != before assert okf_consume.bundle_ref(copy) != before
# --- Step 2: one concept, read into a record ----------------------------------
PROPOSED_CONCEPT = "krav/1-1/foerste-krav"
ROOT_BUNDLE_ID = "b-golden-segmented-okf-v0-2"
def _read(concept_id: str, root: Path = GOLDEN) -> okf_consume.Concept:
return okf_consume.read_concept(
root / f"{concept_id}.md", bundle_root=root, root_bundle_id=ROOT_BUNDLE_ID
)
def test_a_concept_carrying_adjudication_reads_that_value() -> None:
assert _read(PROPOSED_CONCEPT).adjudication == "proposed"
def test_a_concept_carrying_no_adjudication_key_reads_as_unknown(tmp_path: Path) -> None:
# SS 6.1: `unknown` is written EXPLICITLY. "Not judged" and "we cannot tell
# whether it was judged" are different facts, and only one is about the
# concept.
root = tmp_path / "bundle"
_copy_bundle(GOLDEN, root)
target = root / f"{PROPOSED_CONCEPT}.md"
target.write_text(
target.read_text(encoding="utf-8").replace("adjudication: proposed\n", ""),
encoding="utf-8",
)
concept = _read(PROPOSED_CONCEPT, root)
assert concept.adjudication == "unknown"
assert concept.adjudication_present is False
def test_an_adjudication_value_outside_the_wire_set_is_refused_by_name(tmp_path: Path) -> None:
# Mapping an unrecognised value to `unknown` would report "we cannot tell"
# where the truth is "the bundle said something this consumer does not
# understand" -- a defect laundered into a state.
root = tmp_path / "bundle"
_copy_bundle(GOLDEN, root)
target = root / f"{PROPOSED_CONCEPT}.md"
target.write_text(
target.read_text(encoding="utf-8").replace("adjudication: proposed", "adjudication: seen"),
encoding="utf-8",
)
with pytest.raises(okf_consume.ConsumeError) as raised:
_read(PROPOSED_CONCEPT, root)
assert raised.value.code == "adjudication_unknown_value"
def test_the_digest_is_of_the_concept_file_and_is_not_the_source_sha256() -> None:
concept = _read(PROPOSED_CONCEPT)
on_disk = hashlib.sha256((GOLDEN / f"{PROPOSED_CONCEPT}.md").read_bytes()).hexdigest()
assert concept.sha256 == on_disk
assert len(concept.sha256) == 64
frontmatter = parse_frontmatter(GOLDEN / f"{PROPOSED_CONCEPT}.md")
assert frontmatter["source_sha256"] != concept.sha256
def test_the_concept_id_keeps_its_slashes_where_import_slug_would_flatten_them() -> None:
# `importer.import_slug` flattens one line below the rule this id follows.
# A flattened id fails a document-prefix match in a way that looks like a
# ranking miss rather than an id-format bug.
assert _read(PROPOSED_CONCEPT).concept_id == "krav/1-1/foerste-krav"
def test_bundle_id_falls_back_to_the_root_index_and_says_that_it_did(tmp_path: Path) -> None:
root = tmp_path / "bundle"
_copy_bundle(GOLDEN, root)
target = root / f"{PROPOSED_CONCEPT}.md"
target.write_text(
target.read_text(encoding="utf-8").replace(f"bundle_id: {ROOT_BUNDLE_ID}\n", ""),
encoding="utf-8",
)
concept = _read(PROPOSED_CONCEPT, root)
assert concept.bundle_id == ROOT_BUNDLE_ID
assert concept.bundle_id_inherited is True
assert _read(PROPOSED_CONCEPT).bundle_id_inherited is False

View file

@ -33,10 +33,19 @@ from __future__ import annotations
import hashlib import hashlib
import sys import sys
from collections.abc import Mapping
from dataclasses import dataclass
from pathlib import Path from pathlib import Path
from typing import Literal
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src")) sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
from llm_ingestion_okf.inbox import ( # noqa: E402
ADJUDICATION_ADJUDICATED,
ADJUDICATION_PROPOSED,
ADJUDICATION_STATES,
)
from llm_ingestion_okf.materialize import parse_frontmatter # noqa: E402
from llm_ingestion_okf.profiles import SEGMENTED_OKF_V0_2, BundleProfile # noqa: E402 from llm_ingestion_okf.profiles import SEGMENTED_OKF_V0_2, BundleProfile # noqa: E402
#: The profile whose index policy reads a faceted, per-directory index -- the #: The profile whose index policy reads a faceted, per-directory index -- the
@ -51,6 +60,10 @@ DEFAULT_PROFILE = SEGMENTED_OKF_V0_2
#: the algorithm inline is what lets a consumer reproduce it without a document. #: the algorithm inline is what lets a consumer reproduce it without a document.
REF_ALGORITHM = "sha256-tree" REF_ALGORITHM = "sha256-tree"
#: The one concept suffix this instrument reads, taken from the profile so a
#: second literal cannot drift from it.
CONCEPT_SUFFIX = DEFAULT_PROFILE.paths.concept_suffix
def _walk_index_tree( def _walk_index_tree(
bundle_root: Path, *, profile: BundleProfile bundle_root: Path, *, profile: BundleProfile
@ -182,3 +195,112 @@ def bundle_ref(bundle_root: Path, *, profile: BundleProfile = DEFAULT_PROFILE) -
lines.append(f"{relative}\t{digest}".encode()) lines.append(f"{relative}\t{digest}".encode())
joined = b"\n".join(sorted(lines)) joined = b"\n".join(sorted(lines))
return f"{REF_ALGORITHM}:{hashlib.sha256(joined).hexdigest()}" return f"{REF_ALGORITHM}:{hashlib.sha256(joined).hexdigest()}"
class ConsumeError(Exception):
"""A refusal this instrument can name.
Carries a `code` for the same reason `okf_contract_check.Finding` does: one
"invalid" verdict over a dozen defects is a diagnostic no caller can act on.
"""
def __init__(self, message: str, *, code: str) -> None:
super().__init__(message)
self.code = code
#: The three states a CONSUMER must distinguish (SS 6.1), against the two the
#: WIRE carries (`inbox.ADJUDICATION_STATES`). The difference is the whole
#: point: `unknown` is not a value a producer writes, it is what the absence of
#: the key means, and it is written explicitly here so a reader never has to
#: infer it from a missing member.
CONSUMER_ADJUDICATION_STATES = (*ADJUDICATION_STATES, "unknown")
AdjudicationState = Literal["proposed", "adjudicated", "unknown"]
@dataclass(frozen=True)
class Concept:
"""One concept read off disk, with every state written rather than implied."""
path: Path
concept_id: str
bundle_id: str
#: `True` when `bundle_id` came from the root index rather than the concept.
#: Recorded rather than silently defaulted: SS 3.1 makes identity the
#: `(bundle_id, concept_id)` tuple, so where the first half came from is
#: part of what the payload is asserting.
bundle_id_inherited: bool
sha256: str
okf_type: str
title: str
source_file: str
adjudication: AdjudicationState
#: `False` when the key was absent. `adjudication == "unknown"` already says
#: so, but a separate flag keeps the two facts from being one inference.
adjudication_present: bool
frontmatter: Mapping[str, str]
body: str
def read_concept(path: Path, *, bundle_root: Path, root_bundle_id: str) -> Concept:
"""One concept file as a record. Reads; derives nothing about the question.
`sha256` is the digest of the CONCEPT FILE (SS 3.2), never the
`source_sha256` frontmatter key -- that one digests the source document the
concept was extracted from, and conflating them would make the payload's
content identity point at a PDF nobody in the chain reads. Both exist on
every K2 concept, which is what makes the confusion available.
"""
frontmatter = parse_frontmatter(path)
relative = path.relative_to(bundle_root).as_posix()
#: The slash-preserving id: the bundle-relative path minus the suffix. This
#: instrument's own choice, consistent with the RULE at `importer.py:244`
#: and `inbox.py:1101-1102` -- but deliberately NOT `importer.import_slug`,
#: which one line further down flattens the id to a single hyphenated
#: segment. A flattened id fails a document-prefix match in a way that looks
#: like a ranking miss rather than an id-format bug.
concept_id = relative[: -len(CONCEPT_SUFFIX)] if relative.endswith(CONCEPT_SUFFIX) else relative
raw = frontmatter.get("adjudication")
if raw is None:
adjudication: AdjudicationState = "unknown"
elif raw == ADJUDICATION_PROPOSED:
adjudication = "proposed"
elif raw == ADJUDICATION_ADJUDICATED:
adjudication = "adjudicated"
else:
raise ConsumeError(
f"{relative} carries adjudication={raw!r}, outside the wire set "
f"{ADJUDICATION_STATES}; refusing to map it to 'unknown', which "
"would report 'we cannot tell whether it was judged' where the "
"truth is that the bundle said something this consumer does not "
"understand",
code="adjudication_unknown_value",
)
declared = frontmatter.get("bundle_id")
return Concept(
path=path,
concept_id=concept_id,
bundle_id=declared if declared else root_bundle_id,
bundle_id_inherited=not declared,
sha256=hashlib.sha256(path.read_bytes()).hexdigest(),
okf_type=frontmatter.get("type", ""),
title=frontmatter.get("title", ""),
source_file=frontmatter.get("source_file", ""),
adjudication=adjudication,
adjudication_present=raw is not None,
frontmatter=frontmatter,
body=_body(path),
)
def _body(path: Path) -> str:
"""The text after the frontmatter block, or the whole file when there is none."""
text = path.read_text(encoding="utf-8")
lines = text.splitlines()
if not lines or lines[0].strip() != "---":
return text
for offset, line in enumerate(lines[1:], start=2):
if line.strip() == "---":
return "\n".join(lines[offset:])
return text