junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-07-27 23:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Report missing baselines once per batch, and seed the harness's own 🟩

Browse source 
The modelling_e2e handler models one property per run_modelling call, so a
per-property "no persisted baseline" line would be one per property across a
whole re-model. The harness has no Baseline stage by design and cannot drift
from one, so it now establishes its own the way the Baseline orchestrator
would; the Postgres-backed lane is where the assertion has something to catch.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Khalim Conn-Kowlessar 2026-07-21 16:46:25 +00:00
parent 29157811e0
commit 223ef7c196
3 changed files with 74 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
harness/console.py
View file

@ -29,6 +29,10 @@ from domain.modelling.recommendation import Recommendation
from domain.modelling.scenario import Scenario
from domain.modelling.solar_potential import SolarPotential
from domain.property.property import Property, PropertyIdentity
from domain.property_baseline.performance import Performance
from domain.property_baseline.property_baseline_performance import (
PropertyBaselinePerformance,
)
from domain.property_baseline.rebaseliner import StubRebaseliner
from domain.sap10_calculator.calculator import Sap10Calculator
from harness.plan_table import format_plan_table
@ -49,6 +53,7 @@ from repositories.product.product_repository import ProductRepository
from tests.orchestration.fakes import (
FakeEpcRepo,
FakePlanRepository,
FakePropertyBaselineRepo,
FakePropertyRepo,
FakeScenarioRepository,
FakeSolarRepo,
@ -230,7 +235,26 @@ def run_modelling(
)
},
)
# The Baseline stage this harness has no database for. Modelling asserts its
# re-score agrees with the persisted Effective Performance (ADR-0066), so
# establish it here the way `PropertyBaselineOrchestrator` would — from the
# calculator on this same EPC. Drift is structurally impossible in this lane
# (one process, one code version, one picture), so the assertion is a no-op;
# seeding it keeps the check honest instead of reporting "no baseline" once
# per Property across a whole re-model batch. ~1% of a run_modelling call.
baseline_repo = FakePropertyBaselineRepo()
baseline_repo.save(
PropertyBaselinePerformance(
lodged=None,
effective=Performance.from_sap_result(Sap10Calculator().calculate(epc)),
rebaseline_reason="physical_state_changed",
space_heating_kwh=0.0,
water_heating_kwh=0.0,
),
_PROPERTY_ID,
)
unit = FakeUnitOfWork(
property_baseline=baseline_repo,
property=property_repo,
solar=FakeSolarRepo(
by_uprn={_UPRN: solar_insights}

44
orchestration/modelling_orchestrator.py
View file

@ -123,6 +123,11 @@ class ModellingOrchestrator:
# Resolve Fuel Rates once and reuse the BillDerivation across the batch,
# so every baseline/post bill is priced at the same snapshot (ADR-0014).
bill_derivation = BillDerivation(self._fuel_rates.get_current())
# Properties the Baseline stage never established. Collected and reported
# once at the end of the batch — a whole batch can legitimately have none
# (the database-free harness), and one line each would bury the real
# divergence errors under a duplicate per Property.
without_baseline: list[int] = []
with self._unit_of_work() as uow:
properties = uow.property.get_many(property_ids)
scenarios: list[Scenario] = uow.scenario.get_many(scenario_ids)
@ -154,11 +159,12 @@ class ModellingOrchestrator:
# baseline Score, which is already computed, rather than
# paying for another whole-dwelling re-score per Property.
if not checked_baseline:
_check_baseline_coherence(
if _check_baseline_coherence(
property_id,
plan.baseline.sap_continuous,
uow.property_baseline.get_for_property(property_id),
)
):
without_baseline.append(property_id)
checked_baseline = True
uow.plan.save(
plan,
@ -174,6 +180,14 @@ class ModellingOrchestrator:
uow.property.mark_modelled(
property_id, has_recommendations=has_recommendations
)
if without_baseline:
logger.warning(
"%s of %s properties had no persisted Baseline Performance "
"and were modelled against their own re-score; first ids: %s",
len(without_baseline),
len(property_ids),
without_baseline[:10],
)
uow.commit()
def _plan_for(
@ -517,7 +531,7 @@ def _check_baseline_coherence(
property_id: int,
modelled_baseline_sap: float,
persisted: Optional[PropertyBaselinePerformance],
) -> None:
) -> bool:
"""Assert that Modelling and the Baseline stage agree on what the Property
scores now, and say so loudly when they do not (ADR-0002, #1655).
@ -535,20 +549,21 @@ def _check_baseline_coherence(
a real defect upstream (see #1656) and should be investigated, not papered
over.
A missing row is a data gap, not a modelling fault: warn and carry on, so it
degrades one Property rather than aborting the batch (ADR-0012 reserves the
abort for a load-bearing calculator raise)."""
A missing row is a data gap, not a modelling fault, so it is **returned**
(``True``) for the caller to aggregate rather than logged here: it degrades
one Property instead of aborting the batch (ADR-0012 reserves the abort for a
load-bearing calculator raise), and an entire batch can legitimately have no
Baseline stage at all — the database-free harness the ``modelling_e2e``
handler runs on has none, so a per-Property line would bury the real errors
under one duplicate per Property.
A divergence stays per-Property: it is rare, and the Property is the thing
you need to go and look at."""
if persisted is None:
logger.warning(
"no persisted Baseline Performance for property_id=%s; modelling "
"against its own re-score (modelled_baseline_sap=%.2f)",
property_id,
modelled_baseline_sap,
)
return
return True
effective_sap: int = persisted.effective.sap_score
if abs(modelled_baseline_sap - effective_sap) <= _MAX_BASELINE_DIVERGENCE:
return
return False
logger.error(
"modelling baseline diverges from persisted Effective Performance for "
"property_id=%s: modelled=%.2f effective=%s (%s). Plan post_* figures "
@ -559,6 +574,7 @@ def _check_baseline_coherence(
effective_sap,
persisted.rebaseline_reason,
)
return False
def _target_sap(scenario: Scenario) -> Optional[float]:

27
tests/orchestration/test_modelling_baseline_coherence.py
View file

@ -81,18 +81,31 @@ def test_a_baseline_agreeing_within_rounding_is_silent(
assert caplog.records == []
def test_a_property_with_no_persisted_baseline_warns_rather_than_failing(
def test_a_property_with_no_persisted_baseline_is_reported_not_logged(
caplog: pytest.LogCaptureFixture,
) -> None:
# Arrange — the Property never went through the Baseline stage. A data gap
# should degrade one Property, not abort the batch (ADR-0012 reserves the
# abort for a load-bearing calculator raise).
# abort for a load-bearing calculator raise) — but it must not log per
# Property either: whole batches legitimately have no Baseline stage (the
# database-free harness the modelling_e2e handler runs on), and one line per
# Property buries the real errors in tens of thousands of duplicates.
# Act
with caplog.at_level(logging.WARNING):
_check_baseline_coherence(749719, 63.22, None)
missing = _check_baseline_coherence(749719, 63.22, None)
# Assert — visible, but not an error and not a raise.
assert "749719" in caplog.text
assert any(r.levelno == logging.WARNING for r in caplog.records)
assert not any(r.levelno >= logging.ERROR for r in caplog.records)
# Assert — reported back to the caller to aggregate, silent in itself.
assert missing is True
assert caplog.records == []
def test_a_property_with_a_baseline_is_not_reported_as_missing() -> None:
# Arrange
persisted: Optional[PropertyBaselinePerformance] = _persisted(63)
# Act
missing = _check_baseline_coherence(749719, 63.22, persisted)
# Assert
assert missing is False