llm-ingestion-okf/tests/test_segmented_golden.py

"""The SEGMENTED_V1 golden: bytes, pinned.

A NEW golden directory, never an edit to the four that exist. That is how
`2504011` shipped `OKF_V0_2`'s golden -- zero bytes changed in the three that
were already there -- and it is what makes "additive" a measured claim rather
than an intention. The second test below is the measurement.

The fixture is synthetic throughout. No consumer content, no real N500 or
procurement prose: this repository is public, and a golden is the most durable
place a leak could land.

Door B shaped, unlike the four Door A goldens: the inputs are an inbox, a
segmentation plan and a `bundle_id`, because those are exactly what a rebuild
replays. Re-materializing them into an empty directory must reproduce the
shipped tree file for file -- which is S7 stated as a fixture instead of as a
property test.
"""

from __future__ import annotations

import json
import subprocess
from pathlib import Path

from llm_ingestion_okf.inbox import GateDecision, process_inbox
from llm_ingestion_okf.profiles import SEGMENTED_V1
from llm_ingestion_okf.segmentation import parse_segmentation_plan

EXAMPLES = Path(__file__).resolve().parents[1] / "examples"
CASE = EXAMPLES / "ingest-golden-segmented"

EXISTING_GOLDENS = (
    "ingest-golden-file",
    "ingest-golden-sql",
    "ingest-golden-http",
    "ingest-golden-okf-v0-2",
)


def gate(text: str) -> GateDecision:
    return GateDecision(sanitized_text=text, disposition="warn")


def materialize(out_dir: Path) -> None:
    plan = parse_segmentation_plan(json.loads((CASE / "segmentation-plan.json").read_text("utf-8")))
    process_inbox(
        CASE / "fixture" / "inbox",
        out_dir,
        (CASE / "ingested-at.txt").read_text(encoding="utf-8").strip(),
        okf_type="reference",
        gate=gate,
        profile=SEGMENTED_V1,
        root_frontmatter_values={
            "bundle_id": (CASE / "bundle-id.txt").read_text(encoding="utf-8").strip()
        },
        segmentation=plan,
    )


def tree(root: Path) -> dict[str, bytes]:
    return {
        path.relative_to(root).as_posix(): path.read_bytes()
        for path in sorted(root.rglob("*"))
        if path.is_file()
    }


def test_the_golden_rematerializes_byte_for_byte(tmp_path: Path) -> None:
    out_dir = tmp_path / "bundle"
    materialize(out_dir)
    expected = tree(CASE / "expected-bundle")
    actual = tree(out_dir)
    assert sorted(actual) == sorted(expected)
    for name in sorted(expected):
        assert actual[name] == expected[name], f"{name} diverges from the golden bytes"


def test_the_golden_covers_the_shape_the_profile_exists_for(tmp_path: Path) -> None:
    # A golden that happened to be flat would pin nothing this profile adds.
    expected = tree(CASE / "expected-bundle")
    concepts = [name for name in expected if not name.endswith(SEGMENTED_V1.index.name)]
    assert len(concepts) >= 3
    assert any("/" in name for name in concepts)
    assert len([name for name in expected if name.endswith(SEGMENTED_V1.index.name)]) >= 3
    assert expected["index.md"].startswith(b"---\nbundle_id: ")


def test_the_four_existing_goldens_are_untouched() -> None:
    # Measured against the baseline commit, not asserted. `git status` covers
    # an uncommitted edit; `git diff` against the baseline covers a committed
    # one -- and this voyage makes commits, so the second is the one that bites.
    baseline = (
        Path(__file__).resolve().parents[1]
        / ".claude/projects/2026-08-30-door-b-concept-granularity/baseline/sha"
    )
    if not baseline.is_file():
        # The baseline is LOCAL-ONLY and gitignored, so a fresh clone has none.
        # Skipping silently would make this test vacuous where it matters most,
        # so the weaker check still runs.
        result = subprocess.run(
            [
                "git",
                "status",
                "--porcelain",
                "--",
                *(f"examples/{name}" for name in EXISTING_GOLDENS),
            ],
            cwd=Path(__file__).resolve().parents[1],
            capture_output=True,
            text=True,
            check=True,
        )
        assert result.stdout == ""
        return

    result = subprocess.run(
        [
            "git",
            "diff",
            "--exit-code",
            baseline.read_text(encoding="utf-8").strip(),
            "--",
            *(f"examples/{name}" for name in EXISTING_GOLDENS),
        ],
        cwd=Path(__file__).resolve().parents[1],
        capture_output=True,
        text=True,
        check=False,
    )
    assert result.returncode == 0, f"an existing golden moved:\n{result.stdout}"


def test_the_new_golden_was_absent_at_the_baseline() -> None:
    # Without this, the exclusion above could be hiding churn inside an
    # existing golden that had been renamed into the new directory.
    baseline = (
        Path(__file__).resolve().parents[1]
        / ".claude/projects/2026-08-30-door-b-concept-granularity/baseline/sha"
    )
    if not baseline.is_file():
        return
    result = subprocess.run(
        [
            "git",
            "cat-file",
            "-e",
            f"{baseline.read_text(encoding='utf-8').strip()}:examples/ingest-golden-segmented",
        ],
        cwd=Path(__file__).resolve().parents[1],
        capture_output=True,
        text=True,
        check=False,
    )
    assert result.returncode != 0, "the new golden already existed at the baseline"