portfolio-optimiser-claude/tests/test_step8_promotion_loadbearing.py

"""Step-8 promotion gate — LOAD-BEARING (method-spec §3 Step 8, §6, §11).

The seam this file keeps alive: only APPROVED knowledge enters the wiki
(fail-closed), the promoted file is NAVIGABLE (index-linked — an unlinked file
is unreachable), and the index label is NEUTRAL (the index body flows verbatim
into the rendered read-context, so a descriptive label would leak the learning
signal around the gated fold). RED when a non-approved verdict reaches the
wiki, when an approved one is not navigable, or when the label leaks.
"""

from __future__ import annotations

import shutil
from pathlib import Path

import pytest

from portfolio_optimiser_claude.experience import (
    CandidateFeatures,
    VerdictStore,
    fold_experience,
    seed_store_from_bundle,
)
from portfolio_optimiser_claude.inbox import VerdictDocument
from portfolio_optimiser_claude.ir import load_validator_input
from portfolio_optimiser_claude.okf import bundle_context, navigate_bundle, parse_concept_file
from portfolio_optimiser_claude.promotion import PromotionError, promote

SHARED_BUNDLE = Path(__file__).resolve().parents[1] / "shared" / "examples" / "bygg-energi-mikro"

MARKER = "realiseringsgrad=0.79"
RATIONALE = f"Godkjent med korreksjon: i drift realiseres ~79% ({MARKER})."
BASE_PROMPT = "Propose exactly one cost-saving measure for this project."

# Structured learning fields a promoted file MUST NOT reproduce (§6) — the raw
# verdict model carries the signal only as rationale prose.
_SEED_ONLY_FIELDS = (
    "realization_rate",
    "expected_actual_saving_nok",
    "modelled_saving_nok",
    "gap_source",
    "context_key",
)


def _document(
    decision: str = "approved",
    rationale: str = RATIONALE,
    codes: frozenset[str] = frozenset({"E01"}),
    verdict_id: str | None = None,
) -> VerdictDocument:
    doc = VerdictDocument.from_candidate(
        CandidateFeatures(
            affected_codes=codes, measure_type="led-retrofit", claimed_saving_nok=25000.0
        ),
        decision=decision,
        rationale=rationale,
        description="LED retrofit",
    )
    if verdict_id is not None:
        doc = doc.model_copy(update={"id": verdict_id})
    return doc


def _promote(doc: VerdictDocument, bundle: Path) -> Path:
    return promote(
        doc,
        bundle,
        approved_by="persona:expert-reviewer",
        experiment="S9-offline-sim",
        timestamp="2026-07-03T12:00:00Z",
    )


@pytest.fixture()
def bundle(tmp_path: Path) -> Path:
    target = tmp_path / "bundle"
    shutil.copytree(SHARED_BUNDLE, target)
    return target


class TestFailClosed:
    """§6: a non-approved verdict is refused — writing and linking NOTHING."""

    @pytest.mark.parametrize("decision", ["rejected", "maybe"])
    def test_non_approved_decisions_are_refused_writing_nothing(
        self, bundle: Path, decision: str
    ) -> None:
        index_before = (bundle / "index.md").read_bytes()
        files_before = sorted(p.name for p in bundle.iterdir())
        with pytest.raises(PromotionError):
            _promote(_document(decision=decision), bundle)
        assert (bundle / "index.md").read_bytes() == index_before
        assert sorted(p.name for p in bundle.iterdir()) == files_before

    @pytest.mark.parametrize("decision", ["approved", "approved_with_adjustment"])
    def test_the_accepted_set_is_exactly_the_two_approval_forms(
        self, bundle: Path, decision: str
    ) -> None:
        assert _promote(_document(decision=decision), bundle).is_file()


class TestPromotedFile:
    """§6: minimal promoted file — signal as rationale prose, provenance-stamped."""

    def test_frontmatter_carries_the_contract_fields(self, bundle: Path) -> None:
        doc = _document()
        concept = parse_concept_file(_promote(doc, bundle))
        assert concept.type == "verdict"
        assert concept.frontmatter["decision"] == "approved"
        assert concept.frontmatter["description"] == RATIONALE
        assert concept.frontmatter["verdict_id"] == doc.id  # verbatim
        provenance = concept.frontmatter["provenance"]
        for part in ("persona:expert-reviewer", "S9-offline-sim", "2026-07-03T12:00:00Z"):
            assert part in provenance

    def test_no_structured_learning_fields_are_reproduced(self, bundle: Path) -> None:
        concept = parse_concept_file(_promote(_document(), bundle))
        for field in _SEED_ONLY_FIELDS:
            assert field not in concept.frontmatter

    def test_timestamp_is_an_explicit_required_argument(self, bundle: Path) -> None:
        # No wall-clock default — promotion is deterministic and reproducible.
        with pytest.raises(TypeError):
            promote(  # type: ignore[call-arg]
                _document(), bundle, approved_by="x", experiment="y"
            )

    def test_same_candidate_id_is_last_write_wins_per_file(self, bundle: Path) -> None:
        first = _promote(_document(rationale=f"first ({MARKER})"), bundle)
        second = _promote(_document(rationale=f"second ({MARKER})"), bundle)
        assert first == second
        assert parse_concept_file(second).frontmatter["description"] == f"second ({MARKER})"


class TestNavigability:
    """LOAD-BEARING (§11): an approved verdict must be navigable — and fold back."""

    def test_promoted_file_is_reachable_via_index_navigation(self, bundle: Path) -> None:
        path = _promote(_document(), bundle)
        assert path.name in {c.path.name for c in navigate_bundle(bundle)}

    def test_promoted_verdict_closes_the_loop_through_seeding(self, bundle: Path) -> None:
        # Promotion → navigation → seeding → fold: the expert's rationale (the
        # learning signal as prose) reaches the next run's hypothesis prompt.
        _promote(_document(), bundle)
        store = VerdictStore()
        seed_store_from_bundle(store, bundle)
        features = CandidateFeatures.from_proposal(load_validator_input(bundle))
        prompt = fold_experience(store, features, BASE_PROMPT, k=3)
        assert MARKER in prompt

    def test_two_promoted_candidates_both_seed_verbatim_ids(self, bundle: Path) -> None:
        # §4.2 read-VERBATIM at the seeding layer: distinct candidates get
        # distinct store entries — re-minting from bundle features would
        # collide them (first-write-wins) and silently drop one rationale.
        _promote(_document(codes=frozenset({"E01"}), rationale=f"one ({MARKER})"), bundle)
        _promote(_document(codes=frozenset({"E02"}), rationale=f"two ({MARKER})"), bundle)
        store = VerdictStore()
        seed_store_from_bundle(store, bundle)
        features = CandidateFeatures.from_proposal(load_validator_input(bundle))
        rationales = {r.rationale for r in store.retrieve(features, k=10)}
        assert f"one ({MARKER})" in rationales
        assert f"two ({MARKER})" in rationales

    def test_linking_is_idempotent(self, bundle: Path) -> None:
        path = _promote(_document(), bundle)
        _promote(_document(), bundle)
        index_text = (bundle / "index.md").read_text(encoding="utf-8")
        assert index_text.count(f"]({path.name})") == 1


class TestNeutralLabel:
    """LOAD-BEARING (§11): the index label carries NO verdict signal."""

    def test_index_never_carries_the_rationale_or_marker(self, bundle: Path) -> None:
        _promote(_document(), bundle)
        index_text = (bundle / "index.md").read_text(encoding="utf-8")
        assert MARKER not in index_text
        assert RATIONALE not in index_text

    def test_label_is_fixed_across_verdicts(self, bundle: Path) -> None:
        a = _promote(_document(codes=frozenset({"E01"})), bundle)
        b = _promote(_document(codes=frozenset({"E02"})), bundle)
        index_lines = (bundle / "index.md").read_text(encoding="utf-8").splitlines()
        line_a = next(line for line in index_lines if a.name in line)
        line_b = next(line for line in index_lines if b.name in line)
        assert line_a.replace(a.name, "") == line_b.replace(b.name, "")

    def test_rendered_read_context_never_carries_the_marker(self, bundle: Path) -> None:
        # Belt and braces: the index body flows verbatim into the rendered
        # read-context — after promotion it must still exclude the signal.
        _promote(_document(), bundle)
        assert MARKER not in bundle_context(bundle)


class TestPathSafety:
    """§6: path-safe, fail-closed against escaping names."""

    def test_escaping_id_is_sanitised_into_the_bundle(self, bundle: Path, tmp_path: Path) -> None:
        path = _promote(_document(verdict_id="../../evil"), bundle)
        assert path.parent == bundle
        assert not (tmp_path / "evil").exists()
        assert "/" not in path.name and "\\" not in path.name

    def test_sanitised_ids_never_collide_with_a_distinct_id_owning_the_name(
        self, bundle: Path
    ) -> None:
        # C2.5 restarbeid-funn 2: 'e/vil' used to sanitise to 'evil' — the
        # SAME promoted filename as the distinct id 'evil', so the second
        # promotion silently overwrote the first curated verdict.
        first = _promote(_document(verdict_id="e/vil", rationale=f"one ({MARKER})"), bundle)
        second = _promote(_document(verdict_id="evil", rationale=f"two ({MARKER})"), bundle)
        assert first != second
        assert parse_concept_file(first).frontmatter["verdict_id"] == "e/vil"
        assert parse_concept_file(second).frontmatter["verdict_id"] == "evil"

    def test_degenerate_token_falls_back_to_a_content_hash(self, bundle: Path) -> None:
        path = _promote(_document(verdict_id="///"), bundle)
        assert path.parent == bundle
        token = path.name.removeprefix("promoted-verdict-").removesuffix(".md")
        assert token, "degenerate token must fall back to a non-empty content hash"
        assert set(token) <= set("0123456789abcdef")