llm-ingestion-okf/tests/test_import_consumable.py

"""Door C's own outcome is a bundle the reading direction can open.

A downstream consumer repository, 2026-09-08 (its finding 1): `import_bundle` wrote the root index with
no frontmatter and took no `root_frontmatter_values`, so it could not declare
`bundle_id`. `okf consume` then refused the result with exit 1,
`bundle_id_missing` -- section 3.1's identity tuple is `(bundle_id,
concept_id)` and half of it was absent. The consumer's workaround was to use
Door C as a GATE and write the consumable tree themselves.

The fix is the mechanism Door B already has and Door C did not: a profile
names a key, the CALLER owns its value (decision E1). It is keyword-only with
a default of `None`, so every existing call site emits the bytes it always did
-- a consumer with branch bases built through this door is not asked to
rebuild them, which is the boundary this repository states for its own
consumers.
"""

from __future__ import annotations

import json
import subprocess
import sys
from pathlib import Path

from test_import_flow import CONCEPT, StubImportGate, place

from llm_ingestion_okf.importer import import_bundle
from llm_ingestion_okf.materialize import parse_frontmatter
from llm_ingestion_okf.profiles import DEFAULT, SEGMENTED_V1

PROJECT_ROOT = Path(__file__).resolve().parents[1]
TOOL = PROJECT_ROOT / "tools" / "okf_consume.py"
KNOWN_POSITIVE = PROJECT_ROOT / "examples" / "ingest-golden-segmented-okf-v0-2" / "expected-bundle"


def _consume(bundle: Path) -> subprocess.CompletedProcess[str]:
    return subprocess.run(
        [sys.executable, str(TOOL), str(bundle), "--question", "users"],
        capture_output=True,
        text=True,
        check=False,
    )


def test_the_known_positive_is_readable_first() -> None:
    """Before an exit 1 counts as a finding, the chain must be shown able to pass."""
    assert _consume(KNOWN_POSITIVE).returncode == 0


def test_door_c_without_a_bundle_id_is_still_refused(tmp_path: Path) -> None:
    """The defect, kept as a test: silence is not the fix, a named value is."""
    place(tmp_path / "source", "tables/users.md", CONCEPT)
    bundle = tmp_path / "bundle"
    import_bundle(
        tmp_path / "source",
        bundle,
        "1970-01-01T00:00:00Z",
        origin="external",
        channel="manual",
        gate=StubImportGate(),
    )
    assert (bundle / "index.md").is_file()
    assert "bundle_id" not in parse_frontmatter(bundle / "index.md")
    assert _consume(bundle).returncode == 1


def test_door_c_with_a_bundle_id_produces_a_consumable_bundle(tmp_path: Path) -> None:
    place(tmp_path / "source", "tables/users.md", CONCEPT)
    bundle = tmp_path / "bundle"
    import_bundle(
        tmp_path / "source",
        bundle,
        "1970-01-01T00:00:00Z",
        origin="external",
        channel="manual",
        gate=StubImportGate(),
        profile=SEGMENTED_V1,
        root_frontmatter_values={"bundle_id": "imported-2026-09-09"},
    )
    declared = parse_frontmatter(bundle / "index.md")
    assert declared["bundle_id"] == "imported-2026-09-09"
    done = _consume(bundle)
    assert done.returncode == 0, done.stderr
    payload = json.loads(done.stdout)
    assert payload["bundle"]["bundle_id"] == "imported-2026-09-09"


def test_a_second_run_does_not_duplicate_the_declaration(tmp_path: Path) -> None:
    """The index is APPENDED to across runs; the frontmatter must not be."""
    place(tmp_path / "source", "tables/users.md", CONCEPT)
    bundle = tmp_path / "bundle"
    for _ in range(2):
        import_bundle(
            tmp_path / "source",
            bundle,
            "1970-01-01T00:00:00Z",
            origin="external",
            channel="manual",
            gate=StubImportGate(),
            profile=SEGMENTED_V1,
            root_frontmatter_values={"bundle_id": "imported-2026-09-09"},
        )
    text = (bundle / "index.md").read_text(encoding="utf-8")
    assert text.count("bundle_id:") == 1
    assert parse_frontmatter(bundle / "index.md")["bundle_id"] == "imported-2026-09-09"


def test_the_default_profile_names_no_root_key_and_says_so(tmp_path: Path) -> None:
    """Naming a key the profile does not carry is refused BEFORE any write."""
    place(tmp_path / "source", "tables/users.md", CONCEPT)
    bundle = tmp_path / "bundle"
    assert DEFAULT.index.root_frontmatter == ()
    try:
        import_bundle(
            tmp_path / "source",
            bundle,
            "1970-01-01T00:00:00Z",
            origin="external",
            channel="manual",
            gate=StubImportGate(),
            root_frontmatter_values={"bundle_id": "x"},
        )
    except Exception as exc:
        assert getattr(exc, "code", "") == "index_root_frontmatter_unexpected"
    else:  # pragma: no cover - a pass here is the defect
        raise AssertionError("an unnamed root key was written")
    assert not bundle.exists(), "a refused call left a partially written bundle"