portfolio-optimiser-claude/tests/test_ingest_loadbearing.py

"""Load-bearing ingest seams (ingest-spec §11) — D7 mirror of MAF I2's set.

Each test must go RED when its seam is detached (the method-spec §11 regime): a
grønn-men-død test is the failure mode the rule exists for. The seams mirrored here,
proven through the consumer seam (``portfolio_optimiser_claude.ingest``, backed by
llm-ingestion-okf since the adoption):

- Provenance stamping — a generated file carries the §7 provenance layer, in order.
- Navigability — the generated bundle is consumable by the UNCHANGED ``okf`` navigation
  (index links included), incl. the frontmatter-less generated index.
- Verdict reservation — a manifest mapping to ``type: verdict`` is rejected fail-fast,
  before any source call.
- Re-ingest layer safety — re-materialization over a bundle carrying a promoted verdict
  preserves the verdict file AND its index link (curated content always survives).
"""

from __future__ import annotations

import hashlib
import json
import shutil
from pathlib import Path

import pytest

from portfolio_optimiser_claude import okf
from portfolio_optimiser_claude.ingest import ManifestError, load_manifest, materialize

GOLDEN = Path(__file__).resolve().parents[1] / "examples" / "ingest-golden-file"
INGESTED_AT = (GOLDEN / "ingested-at.txt").read_text(encoding="utf-8").strip()

_PROVENANCE_KEYS = ("source_system", "source_query", "ingested_at", "ingest_manifest", "generated")


def _expected_stamp(manifest_path: Path) -> str:
    # The §5 stamp rule, recomputed INDEPENDENTLY of the implementation:
    # ``{manifest stem}@{sha256(raw bytes)[:16]}`` — RED if the stamping detaches.
    digest = hashlib.sha256(manifest_path.read_bytes()).hexdigest()[:16]
    return f"{manifest_path.stem}@{digest}"


def _materialized(tmp_path: Path) -> Path:
    bundle = tmp_path / "bundle"
    bundle.mkdir()
    materialize(GOLDEN / "manifest.json", bundle, INGESTED_AT)
    return bundle


class TestProvenanceStamping:
    """Seam: a generated file carries the §7 provenance layer (RED if it stops)."""

    def test_generated_file_carries_the_provenance_layer(self, tmp_path: Path) -> None:
        bundle = _materialized(tmp_path)
        concept = okf.parse_concept_file(bundle / "ingest-costs.md")
        for key in _PROVENANCE_KEYS:
            assert key in concept.frontmatter, f"provenance key {key} detached"
        assert concept.frontmatter["source_system"] == "prosjekt-arkiv"
        assert concept.frontmatter["ingested_at"] == INGESTED_AT
        # NOT a conformance claim: §7 defines the O2 mapping since commons' V1, and the
        # pinned emitter still writes the pre-V1 literal. The divergence is recorded and
        # ratcheted in `test_ingest_stamp_conformance_loadbearing.py` — adopt there first.
        assert concept.frontmatter["generated"] == "true"
        assert concept.frontmatter["ingest_manifest"] == _expected_stamp(GOLDEN / "manifest.json")

    def test_provenance_keys_are_in_the_spec_order(self, tmp_path: Path) -> None:
        # §5: exactly these keys, in exactly this order — the chain is a contract.
        bundle = _materialized(tmp_path)
        lines = (bundle / "ingest-costs.md").read_text(encoding="utf-8").splitlines()
        keys = [ln.split(":", 1)[0] for ln in lines[1 : lines.index("---", 1)]]
        assert keys == [
            "type",
            "title",
            "source_system",
            "source_query",
            "ingested_at",
            "ingest_manifest",
            "generated",
        ]


class TestNavigability:
    """Seam: the generated bundle is consumable by the UNCHANGED okf navigation."""

    def test_generated_bundle_navigates_via_unchanged_okf(self, tmp_path: Path) -> None:
        bundle = _materialized(tmp_path)
        names = [c.path.name for c in okf.navigate_bundle(bundle)]
        # Every generated ingest file must be REACHABLE via index cross-links — an
        # unlinked generated file is unreachable (RED if index linking detaches).
        assert names == ["index.md", "ingest-costs.md", "ingest-edge.md"]

    def test_generated_context_renders_the_extracted_rows(self, tmp_path: Path) -> None:
        bundle = _materialized(tmp_path)
        context = okf.bundle_context(bundle)
        assert "led-retrofit" in context and "requires vendor quote" in context

    def test_generated_index_is_frontmatterless_and_still_navigates(self, tmp_path: Path) -> None:
        # The generated index carries no frontmatter (§6 shape) — navigation must
        # still work, exercising the okf entry-point relaxation end to end.
        bundle = _materialized(tmp_path)
        assert not (bundle / "index.md").read_text(encoding="utf-8").startswith("---")
        assert okf.navigate_bundle(bundle)[0].path.name == "index.md"


class TestVerdictReservation:
    """Seam: an ingest mapping to the verdict layer is rejected fail-fast (§3)."""

    def _manifest(self, okf_type: str) -> dict:
        return {
            "manifest_version": 1,
            "source": {"type": "file", "id": "x", "root": "fixture"},
            "bundle_summary": "s",
            "extractions": [
                {"id": "e", "title": "T", "query": "e.csv", "okf_type": okf_type, "max_rows": 1}
            ],
        }

    def _write(self, tmp_path: Path, okf_type: str) -> Path:
        manifest = tmp_path / "manifest.json"
        manifest.write_text(json.dumps(self._manifest(okf_type)), encoding="utf-8")
        return manifest

    def test_verdict_okf_type_is_rejected(self, tmp_path: Path) -> None:
        with pytest.raises(ManifestError):
            load_manifest(self._write(tmp_path, "verdict"))

    def test_verdict_reservation_is_case_insensitive(self, tmp_path: Path) -> None:
        with pytest.raises(ManifestError):
            load_manifest(self._write(tmp_path, "Verdict"))

    def test_rejection_is_fail_fast_before_any_source_call(self, tmp_path: Path) -> None:
        # A verdict manifest never touches the source: no bundle is written.
        manifest = self._write(tmp_path, "verdict")
        bundle = tmp_path / "bundle"
        with pytest.raises(ManifestError):
            materialize(manifest, bundle, INGESTED_AT)
        assert not bundle.exists() or not any(bundle.iterdir())


class TestReingestLayerSafety:
    """Seam: re-ingest preserves a promoted verdict AND its index link (§3, §6)."""

    def _promote(self, bundle: Path) -> None:
        # Simulate the promotion gate writing a verdict file + its (neutral) index link,
        # plus a curated file + link. Neither carries the ingest stamp.
        (bundle / "promoted-verdict-led.md").write_text(
            "---\ntype: verdict\ndecision: approved\ndescription: LED holds up.\n---\n\nBody.\n",
            encoding="utf-8",
        )
        (bundle / "curated-note.md").write_text(
            "---\ntype: reference\ntitle: Curated\n---\n\nHand-written.\n", encoding="utf-8"
        )
        index = bundle / "index.md"
        index.write_text(
            index.read_text(encoding="utf-8")
            + "- [promoted](promoted-verdict-led.md)\n"
            + "- [Curated](curated-note.md)\n",
            encoding="utf-8",
        )

    def test_promoted_verdict_and_curated_survive_reingest(self, tmp_path: Path) -> None:
        bundle = _materialized(tmp_path)
        self._promote(bundle)
        materialize(GOLDEN / "manifest.json", bundle, INGESTED_AT)  # re-ingest

        assert (bundle / "promoted-verdict-led.md").is_file()  # verdict file survives
        assert (bundle / "curated-note.md").is_file()  # curated file survives
        index_text = (bundle / "index.md").read_text(encoding="utf-8")
        assert "- [promoted](promoted-verdict-led.md)" in index_text  # verdict link survives
        assert "- [Curated](curated-note.md)" in index_text  # curated link survives
        # ...and the ingest files were still refreshed.
        assert (bundle / "ingest-costs.md").is_file()
        assert "](ingest-costs.md)" in index_text

    def test_reingest_drops_a_stale_ingest_file_and_its_link(self, tmp_path: Path) -> None:
        # A manifest that no longer generates ingest-edge → the stale file AND its index
        # link are removed; the promoted/curated content is untouched (RED if replacement
        # over-reaches or under-reaches).
        bundle = _materialized(tmp_path)
        self._promote(bundle)
        # Positive control for the negative assertion below: the link is present, in
        # EXACTLY the form the removal assertion searches for. Without this the `not in`
        # would also pass if the link form drifted — green for the wrong reason.
        assert "](ingest-edge.md)" in (bundle / "index.md").read_text(encoding="utf-8")
        # The shrunk manifest must sit beside its own fixture/ (root resolves relative to
        # the manifest dir), so copy the golden case and rewrite the manifest there.
        case = tmp_path / "case"
        shutil.copytree(GOLDEN, case)
        shrunk = json.loads((case / "manifest.json").read_text(encoding="utf-8"))
        shrunk["extractions"] = [e for e in shrunk["extractions"] if e["id"] == "costs"]
        (case / "manifest.json").write_text(json.dumps(shrunk), encoding="utf-8")
        materialize(case / "manifest.json", bundle, INGESTED_AT)

        assert not (bundle / "ingest-edge.md").exists()  # stale ingest file removed
        index_text = (bundle / "index.md").read_text(encoding="utf-8")
        assert "](ingest-edge.md)" not in index_text  # stale ingest link removed
        assert "- [promoted](promoted-verdict-led.md)" in index_text  # promoted survives
        assert (bundle / "ingest-costs.md").is_file()  # kept extraction survives