portfolio-optimiser/tests/test_step1_expel_loadbearing.py

"""Step-1 load-bearing seam (målbilde §5 / §7): a prior expert verdict MUST reach the next
hypothesis prompt.

The diagnosis (fot-i-bakken, verified in code): ExpeL retrieval was computed AFTER generation and
written into a discarded ``SessionContext`` — so the seed verdict could not influence any
hypothesis (``context_providers`` = 0). Fase 2a wires it: before ``generate_via_llm``, the
candidate's prior verdicts are folded into the generation context.

These two tests are a load-bearing PAIR, not a smoke test (per the Fase-2 green-but-dead trap):
- the positive test asserts the seed verdict's realization signal ("0.82") IS in the generation
  prompt — it goes RED the moment the fold is detached;
- the empty-store test asserts the signal is ABSENT without a seed — proving the signal's presence
  is CAUSED by the seam, not incidental to the fixture.
"""

from __future__ import annotations

from pathlib import Path

from portfolio_optimiser.run import run_project
from portfolio_optimiser.validator import ValidatedProposal
from portfolio_optimiser.verdicts import VerdictStore, seed_store_from_bundle

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

# A VALID BYGG-KONTOR-NORD proposal: affected total = 300000 x 1.0; no assumptions -> degenerate
# Monte Carlo P90 = 0.30 x 300000 = 90000 >= claimed 30000 -> validates on the first attempt.
_ENERGY_REPLY = (
    '{"measure":"LED-retrofit av kontorbelysning","affected_items":'
    '[{"code":"ENERGI-TOTAL-EL","quantity":300000,"unit_cost":1.0}],"claimed_saving_nok":30000}'
)
_VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"}

# Two load-bearing markers, by design:
#  - the seed verdict's MINTED id (16-char content hash ``format_fewshot`` emits as ``- [<id>] ...``);
#    it cannot appear in the bundle's raw text, so it isolates the STRUCTURAL ExpeL path.
#  - the realization rate "0.82". Fase 2b replaced keyword chunk-stuffing with OKF-navigation that
#    EXCLUDES ``type: verdict`` from the bundle context, so the signal now reaches a prompt ONLY via
#    the gated ExpeL fold. Pre-2b (``docs_dir == bundle_dir``) chunk-stuffing leaked "0.82" from the
#    verdict + golden files into the debate prompt regardless of the fold — which the empty-store
#    control below asserts is no longer true (it goes RED against the pre-2b chunk-stuffing path).
_SEED_ID = seed_store_from_bundle(str(BUNDLE_DIR)).verdicts[0].id
_REALIZATION_SIGNAL = "realiseringsgrad=0.82"  # the exact ``_verdict_rationale`` fewshot string


def _generation_prompts(sink: list[str]) -> list[str]:
    """The generation-call prompts (``generate._build_messages`` embeds 'SavingsProposal'),
    isolated from the debate-round prompts also captured in the sink."""
    return [p for p in sink if "SavingsProposal" in p]


async def test_prior_verdict_reaches_hypothesis_prompt(make_recording_client_factory) -> None:
    """LOAD-BEARING: with the energi bundle's seed verdict in the store, the realization signal
    reaches the hypothesis-generation prompt. Detach the fold in ``run.py`` and this goes red."""
    store = seed_store_from_bundle(str(BUNDLE_DIR))
    assert store.verdicts, "precondition: the bundle seeds exactly one verdict"
    factory, recorded = make_recording_client_factory(_ENERGY_REPLY)

    result = await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        store=store,
        client_factory=factory,
    )

    assert isinstance(result.outcome, ValidatedProposal)
    gen_prompts = _generation_prompts(recorded)
    assert gen_prompts, "the generation call must have happened"
    assert any(_SEED_ID in p for p in gen_prompts), (
        "the seed verdict did not reach the hypothesis prompt — the ExpeL->prompt fold is detached"
    )
    # Fase 2b: the realization SIGNAL itself (not just the id) is now a clean marker — it can only
    # reach the prompt via the gated fold, since OKF-navigation excludes the verdict from context.
    assert any(_REALIZATION_SIGNAL in p for p in gen_prompts), (
        "the realization signal did not reach the hypothesis prompt via the ExpeL fold"
    )


async def test_empty_store_leaves_no_signal_in_prompt(make_recording_client_factory) -> None:
    """CAUSALITY CONTROL: the same run with an EMPTY store carries no realization signal into the
    prompt — proving the signal above is caused by the seam, making the positive test load-bearing
    (not merely green against the fixture's mere presence)."""
    factory, recorded = make_recording_client_factory(_ENERGY_REPLY)

    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,
    )

    assert all(_SEED_ID not in p for p in recorded), (
        "no seed verdict in the store, yet its id appeared in a prompt — "
        "the assertion is not actually load-bearing"
    )
    # Fase 2b LOAD-BEARING: with no fold, the realization rate must appear in NO prompt. This goes
    # RED against the pre-2b chunk-stuffing path (which leaked "0.82" from the verdict + golden files
    # into the debate prompt) and only passes once OKF-navigation excludes the verdict from context.
    assert all("0.82" not in p for p in recorded), (
        "the realization rate leaked into a prompt without a seed verdict — bundle context is still "
        "chunk-stuffing the verdict/golden files (Fase 2b OKF-navigation not in effect)"
    )