portfolio-optimiser/tests/test_a5_per_approach_artifacts_loadbearing.py

"""Load-bearing: EVERY evaluated approach gets its own judgeable artefacts (Trekk A5).

Trekk A3/A4 made a run *evaluate* every commissioned approach and *report* what became of each.
That closes the reporting half of krav 1 but not the learning half: ``write_outbox`` still wrote
ONE proposal per run, so of three evaluated approaches only the selected one could ever receive an
expert verdict. The other two taught the system nothing — the coverage report said they happened,
and the learning loop never saw them.

The defect class is a KEY COLLAPSE, and it has two independent halves, each pinned here:

* the WRITER — one artefact pair per run means the non-selected approaches are never written;
* the READER — ``hitl._read_outbox_proposals`` joins proposal to outcome on the ``run_id`` FIELD
  read from file content. Per-approach files that all carry the same ``run_id`` collapse onto one
  dict key (last write wins), so writing three pairs while joining on ``run_id`` alone still yields
  one pending row. This is the S3.2 key-collision class: two rows sharing one key silently become
  one.

A third property is what makes the artefacts genuinely judgeable rather than merely present: each
one must carry the verdict id THAT approach's proposal would be judged under
(``verdicts.verdict_key``, the S3.2 content hash). Sharing one run-level verdict id would mean a
single expert verdict marked all three approaches judged — the collapse again, one layer down.

Detach points, each RED on its own:

* write one artefact pair per run instead of one per evaluated approach;
* key the outbox join on ``run_id`` alone -> ``hitl pending`` reports one row for three approaches;
* stamp every per-approach artefact with the run's single verdict id -> judging one clears all.

The control (``test_without_a_mandate_the_outbox_is_byte_unchanged``) proves the addition is inert
on the no-mandate path: the same un-suffixed filenames as before, carrying no ``approach_id`` key at
all.
"""

from __future__ import annotations

import json
from collections.abc import Callable
from pathlib import Path

from portfolio_optimiser import hitl
from portfolio_optimiser.mandate import OWN_PROPOSAL_ID, Approach, Mandate
from portfolio_optimiser.run import run_project
from portfolio_optimiser.simulation import ScriptedChatClient
from portfolio_optimiser.verdicts import (
    ProposalFeatures,
    VerdictStore,
    capture_verdict,
    write_verdict,
)

BUNDLE_DIR = Path(__file__).resolve().parents[1] / "shared" / "examples" / "bygg-energi-mikro"
_VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"}
_RUN_ID = "run-a5"

# BYGG-KONTOR-NORD: affected total = 300000 x 1.0 -> degenerate Monte Carlo P90 = 0.30 x 300000
# = 90000. A claim <= 90000 validates; a claim above it is REJECTED by the deterministic validator.


def _reply(measure: str, claimed: int) -> str:
    return (
        f'{{"measure":"{measure}","affected_items":'
        f'[{{"code":"ENERGI-TOTAL-EL","quantity":300000,"unit_cost":1.0}}],'
        f'"claimed_saving_nok":{claimed}}}'
    )


# Labels ABSENT from the bundle's own prose (the "LED-retrofit" trap: it appears in 6 bundle files,
# so a client keyed on it would match every prompt through the context and prove nothing).
_LED = Approach(id="led-retrofit", label="Behovsstyrt belysning i fellesarealer")
_HVAC = Approach(id="hvac-swap", label="Utskifting av ventilasjonsaggregat")

_LED_MEASURE = "Behovsstyrt belysning i fellesarealer"
_HVAC_MEASURE = "Utskifting av ventilasjonsaggregat"
_OWN_MEASURE = "Systemets eget forslag"

#: LED validates (30k <= cap); HVAC is above the cap -> the validator rejects it. The three claims
#: are DISTINCT, so each approach mints a distinct verdict key — a test where two approaches shared
#: a claim could not tell per-approach keying from one shared key.
#:
#: Written as FLOATS where a verdict key is minted from them: ``SavingsProposal.claimed_saving_nok``
#: is typed ``float``, so pydantic coerces the JSON ``30000`` to ``30000.0`` — and ``_mint_id``
#: hashes the raw value, where ``30000`` and ``30000.0`` are different keys (the S3.2 magnitude
#: rule). An expert judging the artefact reads the same coerced value back out of it.
_LED_CLAIM, _HVAC_CLAIM, _OWN_CLAIM = 30_000, 200_000, 20_000

_REPLY_BY_LABEL = {
    _LED.label: _reply(_LED_MEASURE, _LED_CLAIM),
    _HVAC.label: _reply(_HVAC_MEASURE, _HVAC_CLAIM),
}
_DEFAULT_REPLY = _reply(_OWN_MEASURE, _OWN_CLAIM)


def _select_reply(blob: str, _role: str) -> str:
    """Reply according to WHICH approach the prompt carries (canonical ``reply_selector`` seam —
    never a copied ``_inner_get_response`` body, S2.5 consolidation guard)."""
    return next((r for label, r in _REPLY_BY_LABEL.items() if label in blob), _DEFAULT_REPLY)


def _factory(sink: list[str]) -> Callable[[str], ScriptedChatClient]:
    def factory(role: str) -> ScriptedChatClient:
        return ScriptedChatClient(
            sink=sink, role=role, reply_selector=_select_reply, default_reply=_DEFAULT_REPLY
        )

    return factory


_MANDATE = Mandate(
    objective="Cut energy cost without rebuilding.",
    approaches=(_LED, _HVAC),
    allow_own_proposals=True,
)


async def _run(mandate: Mandate | None, outbox_dir: Path):
    sink: list[str] = []
    return await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        store=VerdictStore(verdicts=[]),
        client_factory=_factory(sink),
        mandate=mandate,
        outbox_dir=str(outbox_dir),
        run_id=_RUN_ID,
    )


def _payload(path: Path) -> dict:
    return json.loads(path.read_text(encoding="utf-8"))


def _verdict_key_for(measure: str, claimed: float) -> str:
    """The id an expert verdict on THAT proposal would key under — minted through the SAME public
    primitive the run uses, so the test cannot pass against a private copy of the hash."""
    return capture_verdict(
        ProposalFeatures(
            affected_codes=frozenset({"ENERGI-TOTAL-EL"}),
            measure_type=measure,
            claimed_saving_nok=claimed,
            description=measure,
        ),
        "approved",
        "irrelevant to the id",
    ).id


async def test_each_evaluated_approach_gets_its_own_artefacts(tmp_path: Path) -> None:
    """Three evaluated approaches -> three proposal artefacts, each carrying ITS OWN candidate.

    RED when the writer stays one-pair-per-run: only the selected approach's file exists, and the
    two the expert also commissioned cannot be judged.
    """
    outbox = tmp_path / "outbox"
    await _run(_MANDATE, outbox)

    proposals = sorted(p.name for p in outbox.glob("*-proposal.json"))
    assert proposals == [
        f"{_RUN_ID}-hvac-swap-proposal.json",
        f"{_RUN_ID}-led-retrofit-proposal.json",
        f"{_RUN_ID}-{OWN_PROPOSAL_ID}-proposal.json",
    ]

    by_approach = {
        _payload(p)["approach_id"]: _payload(p)["proposal"] for p in outbox.glob("*-proposal.json")
    }
    assert by_approach["led-retrofit"]["measure"] == _LED_MEASURE
    assert by_approach["hvac-swap"]["measure"] == _HVAC_MEASURE
    assert by_approach[OWN_PROPOSAL_ID]["measure"] == _OWN_MEASURE


async def test_each_approach_outcome_is_written_with_its_own_status(tmp_path: Path) -> None:
    """The outcome half must follow its own approach too: the rejected approach's artefact carries
    the rejection, not the selected approach's success."""
    outbox = tmp_path / "outbox"
    await _run(_MANDATE, outbox)

    by_approach = {_payload(p)["approach_id"]: _payload(p) for p in outbox.glob("*-outcome.json")}
    assert by_approach["led-retrofit"]["outcome_type"] == "validated"
    assert by_approach["hvac-swap"]["outcome_type"] == "rejected"
    assert by_approach["hvac-swap"]["reason"], "a rejected approach must carry the reason"
    assert by_approach[OWN_PROPOSAL_ID]["outcome_type"] == "validated"


async def test_each_artefact_stamps_its_own_validator_decision(tmp_path: Path) -> None:
    """Provenance follows the artefact it stamps.

    RED when every per-approach artefact reuses the run's stamp: the rejected approach's file would
    then carry ``validator_decision="validated"`` — the artefact would claim the deterministic gate
    admitted a candidate it actually refused, which is the one field in the stamp nothing else can
    correct.
    """
    outbox = tmp_path / "outbox"
    await _run(_MANDATE, outbox)

    decisions = {
        _payload(p)["approach_id"]: _payload(p)["provenance"]["validator_decision"]
        for p in outbox.glob("*-proposal.json")
    }
    assert decisions == {
        "led-retrofit": "validated",
        "hvac-swap": "rejected",
        OWN_PROPOSAL_ID: "validated",
    }


async def test_hitl_pending_lists_each_approach_separately(tmp_path: Path) -> None:
    """The READER half. RED while the outbox join keys on ``run_id`` alone: three files sharing one
    ``run_id`` collapse to a single pending row, and two commissioned approaches disappear from the
    expert's queue even though their artefacts are on disk."""
    outbox, inbox = tmp_path / "outbox", tmp_path / "inbox"
    inbox.mkdir()
    await _run(_MANDATE, outbox)

    rows = hitl.pending(str(outbox), str(inbox))
    assert {r.approach_id for r in rows} == {"led-retrofit", "hvac-swap", OWN_PROPOSAL_ID}
    assert len({r.verdict_id for r in rows}) == 3, "each approach must be judgeable on its own key"


async def test_judging_one_approach_leaves_the_others_pending(tmp_path: Path) -> None:
    """The keys must be the approaches' OWN verdict keys, not one run-level id.

    RED when every per-approach artefact is stamped with the run's single verdict id: one delivered
    verdict would then clear all three from the queue, and the two unjudged approaches would be
    reported as judged.
    """
    outbox, inbox = tmp_path / "outbox", tmp_path / "inbox"
    await _run(_MANDATE, outbox)

    judged = _verdict_key_for(_LED_MEASURE, float(_LED_CLAIM))
    write_verdict(
        str(inbox),
        capture_verdict(
            ProposalFeatures(
                affected_codes=frozenset({"ENERGI-TOTAL-EL"}),
                measure_type=_LED_MEASURE,
                claimed_saving_nok=float(_LED_CLAIM),
                description=_LED_MEASURE,
            ),
            "approved",
            "the expert judged this approach and only this one",
        ),
    )

    rows = hitl.pending(str(outbox), str(inbox))
    assert judged not in {r.verdict_id for r in rows}
    assert {r.approach_id for r in rows} == {"hvac-swap", OWN_PROPOSAL_ID}


async def test_without_a_mandate_the_outbox_is_byte_unchanged(tmp_path: Path) -> None:
    """Control: the no-mandate path keeps today's two filenames and carries NO ``approach_id`` key.

    A run nobody commissioned has no approaches to key on, and adding a null field would change the
    bytes of every existing artefact (the writers are byte-deterministic by contract).
    """
    outbox = tmp_path / "outbox"
    await _run(None, outbox)

    # ``-debate.json`` is S2c's tool trace, written on every bundle-path run with an outbox and
    # unrelated to the per-approach keying this control is about; it is listed so the assertion
    # stays an EXACT set rather than degrading into "at least these".
    written = sorted(p.name for p in outbox.glob("*.json"))
    assert written == [
        f"{_RUN_ID}-debate.json",
        f"{_RUN_ID}-outcome.json",
        f"{_RUN_ID}-proposal.json",
        f"{_RUN_ID}-runconfig.json",
    ]
    assert "approach_id" not in _payload(outbox / f"{_RUN_ID}-proposal.json")
    assert "approach_id" not in _payload(outbox / f"{_RUN_ID}-outcome.json")