"""S4.0 load-bearing seam: the deterministic gate is ANCHORED to the project's real cost baseline. Review finding F3: every stage of ``validate_proposal`` reasoned about the numbers the *proposal itself* supplied, so a hallucinated cost line (an invented code, or a real code at an invented magnitude) could clear the whole gate as long as its own arithmetic was internally consistent. The reconciliation stage closes that: each ``affected_item`` must correspond to a line in the project's cost baseline, within a configured tolerance. Every RED here is a genuine OUTCOME FLIP, not a reason-string check: the fabricated proposals are deliberately built to pass the P90 / nominal / method stages, so detaching the reconciliation makes them ``ValidatedProposal`` again. Controls prove causality (a real baseline line, same shape, validates), and the no-baseline arm proves the argument stays OPTIONAL (``None`` = pre-S4.0 behaviour, which is why the existing suite stands). Measured detach points (see the session log): the reconciliation stage · the magnitude tolerance · the road-path wiring in ``run.py`` · the bundle-path wiring · the method-cap registry key (F8). """ from __future__ import annotations import json from pathlib import Path import pytest from conftest import SyntheticUsageChatClient from pydantic import ValidationError from portfolio_optimiser import okf from portfolio_optimiser.ir import AffectedItem, CostBaseline, CostBaselineLine, SavingsProposal from portfolio_optimiser.reference_domain import load_reference_projects from portfolio_optimiser.run import run_project from portfolio_optimiser.validator import ( Rejection, ValidatedProposal, baseline_from_project, validate_proposal, ) # The repo-local S4.0 fixture bundle: the ONLY bundle carrying a ``cost-baseline.json`` (the pre- # amendment bundles deliberately have none — that is the optional-argument control below). _DATA = Path(__file__).resolve().parents[1] / "src" / "portfolio_optimiser" / "data" / "bundles" BASELINE_BUNDLE = _DATA / "bygg-energi-baseline-mikro" PRE_AMENDMENT_BUNDLE = _DATA / "bygg-energi-mikro-a" _VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"} # FV42-GSV-E1's real cost line 05.2 (Asfalt Ab11): 4300 m2 x 215 NOK. Affected total 924500 -> # degenerate P90 = 0.30 x 924500 = 277350, so claimed 200000 clears every pre-S4.0 stage. _REAL_CODE = "05.2" _REAL_QTY = 4300.0 _REAL_UNIT_COST = 215.0 _REAL_CLAIM = 200000.0 # The F3 scenario: an invented code carrying a 10 MNOK line. The claim is set at exactly the generic # feasible (0.30 x 10 MNOK) so the fabrication is numerically IMPECCABLE — every pre-S4.0 stage # passes it. Only the baseline reconciliation can reject it, which is what makes the detach a flip. _FAKE_CODE = "XX" _FAKE_UNIT_COST = 10_000_000.0 _FAKE_CLAIM = 3_000_000.0 def _fv42_baseline() -> CostBaseline: return baseline_from_project( next(p for p in load_reference_projects() if p.id == "FV42-GSV-E1") ) def _proposal(code: str, quantity: float, unit_cost: float, claimed: float) -> SavingsProposal: return SavingsProposal( project_id="FV42-GSV-E1", measure="Reduce scope", affected_items=[AffectedItem(code=code, quantity=quantity, unit_cost=unit_cost)], claimed_saving_nok=claimed, assumptions={}, ) # --- Arm 1: the reconciliation stage itself ------------------------------------------------------- def test_fabricated_cost_code_is_rejected() -> None: """RED (F3): a proposal citing a cost code that exists nowhere in the project's baseline is rejected, even though its own arithmetic clears the LP/P90/nominal stages. Detach the reconciliation stage and the SAME proposal validates.""" result = validate_proposal( _proposal(_FAKE_CODE, 1.0, _FAKE_UNIT_COST, _FAKE_CLAIM), baseline=_fv42_baseline() ) assert isinstance(result, Rejection), "a hallucinated cost code must never reach validated" assert "unknown cost code" in result.reason assert _FAKE_CODE in result.reason def test_real_baseline_line_still_validates() -> None: """Causality control: the same shape of proposal on a REAL baseline line validates — so the rejection above is caused by the code being absent from the baseline, not by the new stage rejecting everything.""" result = validate_proposal( _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST, _REAL_CLAIM), baseline=_fv42_baseline() ) assert isinstance(result, ValidatedProposal) def test_baseline_is_optional_and_none_is_pre_s40_behaviour() -> None: """The baseline argument is OPTIONAL: with ``None`` the fabricated proposal validates exactly as it did before S4.0. This is the property the existing suite rests on — and the reason the RED above is a flip rather than a tightening of an already-rejecting path.""" result = validate_proposal(_proposal(_FAKE_CODE, 1.0, _FAKE_UNIT_COST, _FAKE_CLAIM)) assert isinstance(result, ValidatedProposal) # --- Arm 2: the magnitude tolerance --------------------------------------------------------------- def test_inflated_unit_cost_on_a_real_code_is_rejected() -> None: """RED: a REAL cost code at an invented unit_cost (+20%, well past the 5% default tolerance) is rejected. Detach the tolerance check and only the code-membership test remains — the inflated line then validates, because the code itself is genuine.""" inflated = _REAL_UNIT_COST * 1.20 result = validate_proposal( _proposal(_REAL_CODE, _REAL_QTY, inflated, _REAL_CLAIM), baseline=_fv42_baseline() ) assert isinstance(result, Rejection) assert "unit_cost" in result.reason and _REAL_CODE in result.reason def test_inflated_quantity_on_a_real_code_is_rejected() -> None: """RED: the same for quantity — a real code at an invented quantity (+20%) is rejected.""" result = validate_proposal( _proposal(_REAL_CODE, _REAL_QTY * 1.20, _REAL_UNIT_COST, _REAL_CLAIM), baseline=_fv42_baseline(), ) assert isinstance(result, Rejection) assert "quantity" in result.reason def test_within_tolerance_deviation_is_admitted() -> None: """Causality control for the tolerance: a 2% deviation (rounding-scale, inside the 5% default) validates — the rejections above are caused by the SIZE of the deviation, not by any deviation at all.""" result = validate_proposal( _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST * 1.02, _REAL_CLAIM), baseline=_fv42_baseline(), ) assert isinstance(result, ValidatedProposal) def test_tolerance_is_configurable() -> None: """The tolerance is config, not a constant: the same 2% deviation is rejected under a stricter caller-supplied tolerance.""" result = validate_proposal( _proposal(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST * 1.02, _REAL_CLAIM), baseline=_fv42_baseline(), tolerance=0.001, ) assert isinstance(result, Rejection) # --- Arm 3: the loader (fail-fast, mirroring ``load_ir_projection``) ------------------------------- def test_bundle_baseline_loads_from_the_fixture() -> None: baseline = okf.load_cost_baseline(str(BASELINE_BUNDLE)) assert baseline.project_id == "BYGG-ENERGI-BASELINE-MIKRO" assert baseline.items["ENERGI-TOTAL-EL"] == CostBaselineLine(quantity=180000, unit_cost=1.0) def test_missing_baseline_is_fail_fast_but_optional_loader_returns_none() -> None: """Two deliberately different contracts over the same absence: the fail-fast loader raises (it is authoritative startup input, like ``load_ir_projection``), while the OPTIONAL loader the run path uses returns ``None`` — a bundle written before the amendment is not an error, it is simply un-anchored.""" with pytest.raises(FileNotFoundError): okf.load_cost_baseline(str(PRE_AMENDMENT_BUNDLE)) assert okf.load_optional_cost_baseline(str(PRE_AMENDMENT_BUNDLE)) is None def test_malformed_baseline_raises_even_on_the_optional_path(tmp_path) -> None: """Fail-closed where it matters: a baseline that EXISTS but is malformed raises on BOTH loaders. Tolerating it would silently un-anchor the gate — the RAW-inbox skip rule stops at this layer.""" (tmp_path / "cost-baseline.json").write_text( json.dumps({"project_id": "P", "items": {"01.1": {"quantity": 1}}}), encoding="utf-8" ) with pytest.raises(ValidationError): okf.load_optional_cost_baseline(str(tmp_path)) # --- Arm 4: the run-path wiring (road + bundle) --------------------------------------------------- def _reply(code: str, quantity: float, unit_cost: float, claimed: float) -> str: return json.dumps( { "measure": "Reduce scope", "affected_items": [{"code": code, "quantity": quantity, "unit_cost": unit_cost}], "claimed_saving_nok": claimed, } ) def _factory(reply: str): def factory(role: str): return SyntheticUsageChatClient(default_reply=reply) return factory async def test_road_path_anchors_the_gate_to_the_reference_baseline(docs_dir, fresh_store) -> None: """RED (road wiring): a numerically-impeccable fabricated cost line is REJECTED end-to-end through ``run_project``. Detach the road-path baseline (stop passing it) and the same run returns a ValidatedProposal.""" result = await run_project( "FV42-GSV-E1", "local", docs_dir=docs_dir, verdict_input=_VERDICT_INPUT, client_factory=_factory(_reply(_FAKE_CODE, 1.0, _FAKE_UNIT_COST, _FAKE_CLAIM)), store=fresh_store, ) assert isinstance(result.outcome, Rejection) assert "unknown cost code" in result.outcome.reason async def test_road_path_control_real_line_validates(docs_dir, fresh_store) -> None: """Causality control for the road wiring: the real 05.2 line validates through the same path.""" result = await run_project( "FV42-GSV-E1", "local", docs_dir=docs_dir, verdict_input=_VERDICT_INPUT, client_factory=_factory(_reply(_REAL_CODE, _REAL_QTY, _REAL_UNIT_COST, _REAL_CLAIM)), store=fresh_store, ) assert isinstance(result.outcome, ValidatedProposal) async def test_bundle_path_anchors_when_the_bundle_declares_a_baseline(fresh_store) -> None: """RED (bundle wiring): a bundle that ships ``cost-baseline.json`` anchors its run — the fabricated line is rejected. Detach the bundle-path load and it validates again.""" 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(_reply(_FAKE_CODE, 1.0, 300000.0, 90000.0)), store=fresh_store, ) assert isinstance(result.outcome, Rejection) assert "unknown cost code" in result.outcome.reason async def test_pre_amendment_bundle_runs_unchanged(fresh_store) -> None: """Control + backward compatibility: the SAME fabricated reply validates against a bundle with no ``cost-baseline.json``. Anchoring is opt-in per bundle, so every pre-S4.0 bundle (including the commons-owned goldens) runs byte-identically to before.""" 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(_reply(_FAKE_CODE, 1.0, 300000.0, 90000.0)), store=fresh_store, ) assert isinstance(result.outcome, ValidatedProposal) # --- Arm 5: F8 — method caps keyed by config, not the literal measure string ---------------------- def test_method_cap_is_keyed_by_config_not_a_hardcoded_string() -> None: """F8: the method-specific cap comes from a REGISTRY the caller can supply. A caller-configured cap for a measure with no built-in entry rejects a proposal the generic P90 stage passes — so the rule is keyed by configuration, not by the ``energy_efficiency`` literal.""" proposal = SavingsProposal( project_id="P-ASFALT", measure="asfalt_reduction", affected_items=[AffectedItem(code="05.2", quantity=100000, unit_cost=1.0)], claimed_saving_nok=20000, assumptions={}, ) assert isinstance(validate_proposal(proposal), ValidatedProposal) # generic P90 = 30000 capped = validate_proposal(proposal, method_caps={"asfalt_reduction": 0.10}) assert isinstance(capped, Rejection) assert "method cap" in capped.reason