The historic roof description conditions the cohort by form family 🟥

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

domain/epc_prediction/historic_conditioning.py

@@ -109,6 +109,7 @@ class HistoricConditioning:
     construction_age_band: Optional[str]
     main_fuel: Optional[int]
     total_floor_area_m2: Optional[float]
+    roof_form: Optional[str] = None
 
 
 def _wall_construction(description: str) -> Optional[int]:

domain/epc_prediction/prediction_target.py

@@ -40,6 +40,10 @@ class PredictionTarget:
     construction_age_band: Optional[str] = None
     main_fuel: Optional[int] = None
     total_floor_area_m2: Optional[float] = None
+    # The roof FORM family ("pitched" / "flat" / "dwelling_above" /
+    # "premises_above") — the API's roof_construction codes group by form,
+    # so the filter matches families, never exact codes (ADR-0054 amendment).
+    roof_form: Optional[str] = None
 
 
 @dataclass(frozen=True)

tests/domain/epc_prediction/test_comparable_properties.py

@@ -33,6 +33,7 @@ def _comparable(
     construction_age_band: Optional[str] = None,
     main_fuel: Optional[int] = None,
     total_floor_area_m2: Optional[float] = None,
+    roof_construction: Optional[int] = None,
 ) -> ComparableProperty:
     """A ComparableProperty carrying only the fields under test (opaque EpcPropertyData
     with property_type / built_form / main wall set — the partial-instance idiom)."""
@@ -44,6 +45,8 @@ def _comparable(
         main.wall_construction = wall_construction
     if construction_age_band is not None:
         main.construction_age_band = construction_age_band
+    if roof_construction is not None:
+        main.roof_construction = roof_construction
     epc.sap_building_parts = [main]
     if main_fuel is not None:
         detail: MainHeatingDetail = object.__new__(MainHeatingDetail)
@@ -306,6 +309,32 @@ def test_historic_age_band_conditions_within_one_band() -> None:
     }
 
 
+def test_historic_roof_form_conditions_the_cohort_by_family() -> None:
+    # Arrange — the expired cert observed a pitched roof. The API's
+    # roof_construction codes group into FORM families (empirical sweep:
+    # 4/5/8 = pitched, 1 = flat), so all pitched-family comparables match and
+    # the flat one drops (ADR-0054 as amended).
+    target = PredictionTarget(postcode="LS6 1AA", property_type="2", roof_form="pitched")
+    candidates = [
+        _comparable(property_type="2", roof_construction=4, certificate_number="P4a"),
+        _comparable(property_type="2", roof_construction=4, certificate_number="P4b"),
+        _comparable(property_type="2", roof_construction=5, certificate_number="P5"),
+        _comparable(property_type="2", roof_construction=8, certificate_number="P8"),
+        _comparable(property_type="2", roof_construction=4, certificate_number="P4c"),
+        _comparable(property_type="2", roof_construction=1, certificate_number="F1"),
+    ]
+
+    # Act
+    result: ComparableProperties = select_comparables(
+        target, candidates, minimum_cohort=5
+    )
+
+    # Assert — the whole pitched family survives; the flat roof drops.
+    assert {c.certificate_number for c in result.members} == {
+        "P4a", "P4b", "P4c", "P5", "P8"
+    }
+
+
 def test_floor_area_band_relaxes_when_too_few_match() -> None:
     # Arrange — only one comparable inside the ±5% band (< k=2): the band must
     # relax rather than starve the cohort (graceful degradation, ADR-0029).

tests/domain/epc_prediction/test_historic_conditioning.py

@@ -29,6 +29,7 @@ def test_resolves_stable_attributes_into_cohort_code_spaces():
         property_type="House",
         built_form="Semi-Detached",
         walls_description="Cavity wall, as built, no insulation (assumed)",
+        roof_description="Pitched, 100 mm loft insulation",
         construction_age_band="England and Wales: 1930-1949",
         main_fuel="mains gas (not community)",
         total_floor_area="84",
@@ -42,11 +43,37 @@ def test_resolves_stable_attributes_into_cohort_code_spaces():
     assert conditioning.property_type == "0"
     assert conditioning.built_form == "2"
     assert conditioning.wall_construction == 4
+    assert conditioning.roof_form == "pitched"
     assert conditioning.construction_age_band == "C"
     assert conditioning.main_fuel == 26
     assert conditioning.total_floor_area_m2 == 84.0
 
 
+def test_roof_descriptions_resolve_to_form_families():
+    # Arrange / Act / Assert — the FORM half of the description (before the
+    # comma) maps to a family, because the API's roof_construction codes group
+    # that way (7,974-cert co-occurrence sweep: 1=Flat 98%, 4/5/8=Pitched
+    # 88-99%, 3=another dwelling above 100%; 7/9=another premises above per
+    # the #1452 suppression fix). Insulation state is volatile and ignored.
+    cases = {
+        "Pitched, 250 mm loft insulation": "pitched",
+        "Pitched, no insulation (assumed)": "pitched",
+        "Flat, insulated (assumed)": "flat",
+        "(another dwelling above)": "dwelling_above",
+        "(another premises above)": "premises_above",
+    }
+    for text, family in cases.items():
+        record = _hist(roof_description=text)
+        assert conditioning_from_historic(record).roof_form == family, text
+    # Unpinned forms (roof rooms, thatched) must not guess.
+    assert conditioning_from_historic(
+        _hist(roof_description="Roof room(s), insulated")
+    ).roof_form is None
+    assert conditioning_from_historic(
+        _hist(roof_description="Thatched, with additional insulation")
+    ).roof_form is None
+
+
 def test_legacy_register_fuel_descriptions_resolve():
     # Arrange / Act / Assert — the old register lodged pre-RdSAP-17 fuels with
     # a "backwards compatibility" rider or a SAP-style prefix; they name the
@@ -84,6 +111,7 @@ def test_unresolvable_values_degrade_to_none():
     assert conditioning.property_type is None
     assert conditioning.built_form is None
     assert conditioning.wall_construction is None
+    assert conditioning.roof_form is None
     assert conditioning.construction_age_band is None
     assert conditioning.main_fuel is None
     assert conditioning.total_floor_area_m2 is None