portfolio-optimiser/tests/test_baseline_visibility_loadbearing.py

"""An UN-ANCHORED run says so — in a machine-readable field AND in one line on stdout.

S4.0 made the deterministic gate anchorable: when a bundle ships ``cost-baseline.json`` the
validator's stage 0 reconciles every ``affected_item`` against the project's own cost lines BEFORE
the solver, and when it does not, that stage is simply skipped (``None`` = pre-amendment behaviour,
which is what keeps every commons-owned golden bundle running). The anchoring stayed OPTIONAL on
purpose — and that is not what this file changes.

What it changes is that the skip was INVISIBLE. Measured (session 48, ``9d149b3``): four
``--live-dry-run``s over copies of the veglys bundle — intact rc 0 · without ``validator-input.json``
rc 1 · **without ``cost-baseline.json`` rc 0 with no message at all** · corrupt baseline rc 1. And
``grep baseline provenance.py outbox.py`` returned 0 hits, so neither the stamp nor the outbox
artefacts carried it either. An operator could therefore run the whole gate un-anchored, read a
clean rc 0, and have nothing anywhere to tell them the fabrication stage never ran.

Two teeth, both small:

1. ``ProvenanceStamp.cost_baseline_anchored`` — a REQUIRED bool, no default. "Was the gate
   anchored" is a binary fact about a falsifier, in the same class as ``BudgetExceeded``'s
   ``kind``/``limit``/``observed`` (kø-(y)): it must be readable by machine, not inferred from
   prose. It carries no default because BOTH defaults lie — ``True`` would let a forgetful
   constructor claim an anchoring that never happened, ``False`` would under-claim a real one — and
   a binary fact with no honest default is exactly what a required field is for. It reaches the
   outbox for free: ``outbox.write_proposal`` dumps the whole stamp.
2. ``run.cost_baseline_notice`` — ONE renderer, rendering ONE line when the run is un-anchored and
   ``None`` when it is anchored. Omission, not an empty row, mirrors ``mandate.announce``'s rule
   that a line for something the run does not have is left out rather than rendered blank.

**The line is rendered from the run's OWN resolution, never from a second read of the bundle**
(kø-(p)). ``run_project`` is the single place that calls ``okf.load_optional_cost_baseline`` on the
run path; the fact leaves the run as a typed field on ``DryRunReport`` and on ``ProvenanceStamp``,
and ``main`` prints from that. Rendering it inside ``mandate.announce`` was MEASURED and rejected:
``announce`` fires only when ``--mandate`` is given, so the very runs this file exists for — the
four bare dry-runs above, none of which had a mandate — would still have printed nothing.

Arms:
(a) the provenance field is ``False`` on an un-anchored bundle run and ``True`` on an anchored one,
    end-to-end through ``run_project`` (+ the road path, which is anchored by construction);
(b) the notice EXISTS un-anchored and is ABSENT anchored — asserted on a sentinel that the anchored
    branch cannot contain, because it prints no line at all (never a substring both branches share:
    the 08-09 class);
(c) both CLI surfaces carry it — ``--live-dry-run`` and the full run;
(d) the outbox artefact carries the field.
"""

from __future__ import annotations

import json
from pathlib import Path

import pytest
from conftest import SyntheticUsageChatClient

from portfolio_optimiser import run
from portfolio_optimiser.ir import AffectedItem, SavingsProposal
from portfolio_optimiser.provenance import Citation, ProvenanceStamp
from portfolio_optimiser.retrieval import TextSpan
from portfolio_optimiser.run import (
    DryRunReport,
    PortfolioResult,
    RunResult,
    cost_baseline_notice,
    run_project,
)
from portfolio_optimiser.validator import Rejection
from portfolio_optimiser.verdicts import ProposalFeatures, Verdict, VerdictStore

_DATA = Path(__file__).resolve().parents[1] / "src" / "portfolio_optimiser" / "data" / "bundles"
#: The ONLY repo-local bundle shipping a ``cost-baseline.json`` (S4.0 fixture) -> anchored.
BASELINE_BUNDLE = _DATA / "bygg-energi-baseline-mikro"
#: A bundle written before the amendment -> legitimately un-anchored (this is the case under test).
PRE_AMENDMENT_BUNDLE = _DATA / "bygg-energi-mikro-a"

_VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"}

#: A reply that reconciles against the S4.0 fixture's own line, so the ANCHORED control run reaches
#: a proposal rather than being rejected by stage 0 — the arms below are about visibility, and a
#: control that died in the gate would not exercise the stamp.
_REPLY = json.dumps(
    {
        "measure": "LED-retrofit",
        "affected_items": [{"code": "ENERGI-TOTAL-EL", "quantity": 180000, "unit_cost": 1.0}],
        "claimed_saving_nok": 30000,
    }
)

#: The word the un-anchored line carries and the anchored branch cannot: it prints NO line at all.
_SENTINEL = "un-anchored"


def _factory(reply: str = _REPLY):
    def factory(role: str):
        return SyntheticUsageChatClient(default_reply=reply)

    return factory


@pytest.fixture(autouse=True)
def _isolate_model_env(monkeypatch: pytest.MonkeyPatch) -> None:
    """Hermetic env (mirrors ``test_scripted_cli_door_loadbearing``): the operator's Foundry
    overrides must not reach the CLI arms."""
    monkeypatch.delenv("PORTFOLIO_MODEL_MAP", raising=False)
    monkeypatch.delenv("PORTFOLIO_FOUNDRY_PROJECT_ENDPOINT", raising=False)


# --- Arm (a): the structured field ----------------------------------------------------------------


async def test_provenance_records_an_unanchored_bundle_run(fresh_store) -> None:
    """RED: a bundle with no ``cost-baseline.json`` stamps ``cost_baseline_anchored=False``. Detach
    the wiring (stamp a constant, or drop the field) and the run again records nothing about the
    skipped stage."""
    result = await run_project(
        "BYGG-ENERGI-MIKRO-A",
        "local",
        docs_dir=str(PRE_AMENDMENT_BUNDLE),
        bundle_dir=str(PRE_AMENDMENT_BUNDLE),
        verdict_input=_VERDICT_INPUT,
        client_factory=_factory(),
        store=fresh_store,
    )
    assert result.provenance.cost_baseline_anchored is False


async def test_provenance_records_an_anchored_bundle_run(fresh_store) -> None:
    """Causality control: the SAME code path over a bundle that DOES ship a baseline stamps
    ``True``. Without this the arm above would pass on a constant ``False``."""
    result = await run_project(
        "BYGG-ENERGI-BASELINE-MIKRO",
        "local",
        docs_dir=str(BASELINE_BUNDLE),
        bundle_dir=str(BASELINE_BUNDLE),
        verdict_input=_VERDICT_INPUT,
        client_factory=_factory(),
        store=fresh_store,
    )
    assert result.provenance.cost_baseline_anchored is True


async def test_road_path_is_anchored_by_construction(docs_dir, fresh_store) -> None:
    """The road path derives its baseline from the reference project's own ``cost_items``, so it is
    ALWAYS anchored — the stamp says so rather than leaving the reader to know it."""
    result = await run_project(
        "FV42-GSV-E1",
        "local",
        docs_dir=docs_dir,
        verdict_input=_VERDICT_INPUT,
        client_factory=_factory(
            json.dumps(
                {
                    "measure": "Reduce scope",
                    "affected_items": [{"code": "05.2", "quantity": 4300.0, "unit_cost": 215.0}],
                    "claimed_saving_nok": 200000.0,
                }
            )
        ),
        store=fresh_store,
    )
    assert result.provenance.cost_baseline_anchored is True


def test_the_field_has_no_default() -> None:
    """A binary fact about a falsifier gets no default: both defaults lie (see the module docstring),
    so a stamp that forgot to say must not construct at all."""
    with pytest.raises(Exception):
        ProvenanceStamp(  # type: ignore[call-arg]
            citations=[],
            model="m",
            role="proposer",
            validator_decision="validated",
            token_usage=0,
        )


# --- Arm (b): the renderer ------------------------------------------------------------------------


def test_notice_is_rendered_only_when_unanchored() -> None:
    """One renderer, two branches that share NO wording: un-anchored returns a line carrying the
    sentinel, anchored returns ``None`` (omitted, never an empty row — ``announce``'s rule)."""
    unanchored = cost_baseline_notice(False)
    assert unanchored is not None
    assert _SENTINEL in unanchored
    assert cost_baseline_notice(True) is None


def test_dry_run_report_carries_the_anchoring(fresh_store) -> None:
    """The dry-run type is the carrier for the surface the order measured: a run that stops before
    the first model call still knows whether the gate would have been anchored."""
    assert "cost_baseline_anchored" in DryRunReport.__dataclass_fields__


# --- Arm (c): both CLI surfaces -------------------------------------------------------------------


def _dry_run(bundle: Path, project_id: str) -> list[str]:
    return [
        project_id,
        "--docs-dir",
        str(bundle),
        "--bundle-dir",
        str(bundle),
        "--live-dry-run",
    ]


def test_cli_dry_run_announces_an_unanchored_bundle(capsys) -> None:
    """RED (the measured defect, verbatim): ``--live-dry-run`` over a bundle without
    ``cost-baseline.json`` exits 0 — and now SAYS the gate is un-anchored instead of exiting
    silently."""
    rc = run.main(_dry_run(PRE_AMENDMENT_BUNDLE, "BYGG-ENERGI-MIKRO-A"))
    assert rc == 0
    assert _SENTINEL in capsys.readouterr().out


def test_cli_dry_run_says_nothing_when_the_bundle_is_anchored(capsys) -> None:
    """Control: the anchored bundle prints NO baseline line at all. Lines for what a run does not
    have are omitted (``announce``); a run that IS anchored has nothing to warn about."""
    rc = run.main(_dry_run(BASELINE_BUNDLE, "BYGG-ENERGI-BASELINE-MIKRO"))
    assert rc == 0
    out = capsys.readouterr().out
    assert _SENTINEL not in out
    assert "Cost baseline" not in out


def test_cli_full_run_announces_an_unanchored_bundle(tmp_path, capsys) -> None:
    """The full-run surface too, through the offline scripted door — so the notice is a property of
    a RUN, not of the dry-run branch alone."""
    replies = tmp_path / "replies.json"
    replies.write_text(
        json.dumps({"proposer": _REPLY, "checker": "Holder. VERDICT: APPROVE"}), encoding="utf-8"
    )
    rc = run.main(
        [
            "BYGG-ENERGI-MIKRO-A",
            "--docs-dir",
            str(PRE_AMENDMENT_BUNDLE),
            "--bundle-dir",
            str(PRE_AMENDMENT_BUNDLE),
            "--scripted-replies",
            str(replies),
        ]
    )
    assert rc == 0
    assert _SENTINEL in capsys.readouterr().out


# --- Arm (d): the outbox artefact -----------------------------------------------------------------


async def test_outbox_proposal_carries_the_anchoring(tmp_path, fresh_store) -> None:
    """The outbox needed no change of its own: the artefact dumps the whole stamp, so the field
    lands in ``{run_id}-proposal.json`` the moment it exists on the stamp."""
    await run_project(
        "BYGG-ENERGI-MIKRO-A",
        "local",
        docs_dir=str(PRE_AMENDMENT_BUNDLE),
        bundle_dir=str(PRE_AMENDMENT_BUNDLE),
        verdict_input=_VERDICT_INPUT,
        client_factory=_factory(),
        store=fresh_store,
        outbox_dir=str(tmp_path),
        run_id="vis-1",
    )
    payload = json.loads((tmp_path / "vis-1-proposal.json").read_text(encoding="utf-8"))
    assert payload["provenance"]["cost_baseline_anchored"] is False


# --- Arm (e): the portfolio surface (DEFENSIVE, and said out loud) --------------------------------


def _unanchored_run() -> RunResult:
    """One ``RunResult`` whose stamp says the gate was un-anchored."""
    proposal = SavingsProposal(
        project_id="P",
        measure="m",
        affected_items=[AffectedItem(code="05.2", quantity=1.0, unit_cost=1.0)],
        claimed_saving_nok=1.0,
        assumptions={},
    )
    return RunResult(
        outcome=Rejection(proposal=proposal, reason="r"),
        provenance=ProvenanceStamp(
            citations=[Citation(file="f.md", locator=TextSpan(0, 1), snippet="x")],
            model="synthetic",
            role="proposer",
            validator_decision="rejected",
            token_usage=1,
            cost_baseline_anchored=False,
            bundle_id_source=None,
        ),
        verdict=Verdict(
            id="v1",
            proposal_features=ProposalFeatures(
                affected_codes=frozenset({"05.2"}), measure_type="m", claimed_saving_nok=1.0
            ),
            decision="rejected",
            rationale="r",
        ),
        retrieved=[],
        store=VerdictStore([]),
        debate_output="",
    )


def test_portfolio_surface_announces_an_unanchored_run(monkeypatch, capsys) -> None:
    """The portfolio branch reports per project, because anchoring is a per-project fact.

    Driven by a CRAFTED ``PortfolioResult`` (the ``budget_stop`` precedent in
    ``test_portfolio_cli_offline_loadbearing``), and for the same measured reason: no reference
    project sets ``bundle_dir``, so every portfolio run today takes the road path and is anchored by
    construction. This arm is therefore DEFENSIVE — it guards the surface for the day a bundle-backed
    project is wired into a pass, rather than covering a path reachable now."""

    async def _fake(*_args, **_kwargs) -> PortfolioResult:
        return PortfolioResult(
            runs=(_unanchored_run(),),
            store=VerdictStore([]),
            validated_count=0,
            rejected_count=1,
            sum_claimed_saving_nok=0.0,
            sum_token_usage=1,
        )

    monkeypatch.setattr(run, "run_portfolio", _fake)
    rc = run.main(["--portfolio"])
    assert rc == 0
    assert _SENTINEL in capsys.readouterr().out