Per-window assignment from a landlord aggregate is strictly worse than the cert's
existing per-window sap_windows, so a mixed override always defers — the proportion
comparison only fed a 'flag when far' branch not worth a new schema field. Realized
decision: a GlazingType.MIXED sentinel (LLM classifies mixes to it) resolves to no
overlay, preserving the cert glazing; uniform assertions still apply.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ADR-0041: flat roofs ARE scored by insulation thickness via RdSAP Table 16
col (1) ('joists at ceiling level and flat roof'); the RoofType taxonomy lacks
flat-thickness members so the depth is discarded — fix needs new FLAT_*MM members
(FE-owned pgEnum). ADR-0042: a landlord glazing override reconciles against the
cert's per-window sap_windows composition rather than flattening every window to
one type; mixed-and-close defers to the cert, mixed-and-far is flagged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Specifies the ALTER ... DROP NOT NULL on the four lodged_* columns (#1361) and
the ordering constraint: it must land before the backend writes NULL or runs the
backfill, else the predicted-Property INSERT aborts the batch.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Amends ADR-0004's both-halves-always-populated invariant: EPC Prediction
borrows a neighbour's recorded figures, so a predicted Property has no Lodged
Performance — its lodged half is absent (NULL), only the Effective half is
persisted. Sharpens the CONTEXT.md glossary for Lodged / Baseline Performance.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Solid fuel is ambiguous across coal/wood/smokeless/pellets, so the overlay
defaults to house coal (33, the most common) when no main_fuel override is
given; a specific solid-fuel override still wins by last-wins composition.
Updates the ADR-0041 natural-fuel amendment accordingly (every archetype drags
a natural fuel; solid defaults to coal).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Record the natural-fuel drag-along rule the overlay now implements: drag a fuel
only where the archetype is unambiguous (electric/gas), leave ambiguous
solid/oil room heaters to the main_fuel override, let a present main_fuel
override win by last-wins composition, and LOG (not raise) a landlord fuel that
contradicts the archetype's natural fuel.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
grill-with-docs output for PRD #1361 Class A. The band-G baselines are not a
fabric/rebaseline bug (walls are correct — landlord asserted as-built); they are
a target-vocabulary gap in the landlord-description heating classifier. The LLM
maps unbounded free-text onto a closed internal taxonomy, but that taxonomy had
9 archetypes vs ~13 RdSAP families, so it overflowed into "Gas CPSU"/storage
(the "convector" collision sent direct-acting room heaters to off-peak storage
403 → SAP ~10).
- ADR-0041: fix the taxonomy not the mapper; unmapped input -> None (keep lodged
EPC, surface to user), never a forced archetype; heat pumps modellable via a
default Table 4a code (no PCDB id); community heating via codes 301/302/304
with a documented DLF-1.50 / boiler-source default.
- CONTEXT.md: sharpen Landlord-Description Classification and the four distinct
vocabularies (landlord / recognised-internal / lodged / SAP code).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Record the two load-bearing decisions and correct the CONTEXT.md
'Calculated SAP10 Performance' entry: the lodged figure is kept at >=10.2
only for a pristine lodged cert; overrides/prediction adopt the calculator.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document Slice 2 in the persistence-fidelity migration log, plus the 7
calculator-read nested gaps the recursive guard newly surfaced (tracked
follow-up).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A Landlord heating-system override was applied as a sparse patch, so the
replaced system's fields bled through. A storage flat reclassified as a gas
combi (property 728513) kept mains_gas=False, heating category 7, the 2401
storage charge control, a Dual meter and an electric-immersion cylinder — an
incoherent record that gated out the gas-boiler-upgrade Measure and made the
heating Generator read the dwelling as off-gas (offering HHRSH storage).
Extend the ADR-0035 drag-along to gas boilers (Table 4b 102/104/120): the
overlay now sets the whole coherent companion set — mains_gas, gas main fuel,
heating category 2, fanned flue, full modern controls (2106), a single-rate
meter, and hot water from the main system with the cylinder set from the boiler
type (combi → none, regular/CPSU → cylinder). The main_fuel overlay also flips
mains_gas=True for a "mains gas" fuel. Non-off-peak archetypes now drag an
explicit Single meter so a system switch never leaves a stale Dual.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ADR-0026 sized PV at 0.70 x Google maxArrayPanelsCount, assuming Google's roof
is the dwelling's. Medium-imagery footprint conflation (semi-detached/terraced)
returns the whole building's roof -> oversized arrays (property 742003: 55m2
bungalow -> ~16 kWp -> effective E/49.7 -> A/92.4 on solar alone). ADR-0038
bounds the array to the dwelling's own usable roof (roof_area-based budget,
proximity segment selection anchored on the dwelling), subsuming the legacy
GoogleSolarApi guards the rewrite dropped. CONTEXT: add Footprint Conflation +
Dwelling-Roof Cap, extend Solar Potential (per-segment centre + area).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Captures the calc-facing ventilation-type gap (older RdSAP mappers drop
mechanical_ventilation_kind), the FE-side Main Fuel display, the sweep survivor
clusters, and the predicted-property display path — all separate from ADR-0037.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Captures the grill-with-docs decisions for the full-SAP-17.1 mapper completion:
rebaseline-to-10.2 (restores Rebaselining trigger (a)), calc-affecting fields
coupled with the sap_version flip, and growing Elmhurst-anchored validation.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolves the ADR-0014 off-peak deferral: off-peak is a property of the
meter (every electric end use splits day/night by its own High-Rate
Fraction, a calculator output), not a per-end-use fuel. Adds the
Off-Peak Meter and High-Rate Fraction glossary terms.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
CONTEXT.md gains Non-Separated / Separated Conservatory glossary terms; ADR-0036
records the mapper-owned §6.1 split + 1:1 persistence + round-trip contract; the
migration note lists the five new epc_property columns for the FE schema repo.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A dwelling's heating is one conceptual system, but its fields are scattered
across EpcPropertyData (a gov-API schema mirror): the cluster on sap_heating, the
electricity tariff on sap_energy_source.meter_type, hot-water flags loose at top
level. Three places synthesise a heating system — Measure Options, Landlord
Overrides, EPC Prediction's donor — and each hand-copied a different ad-hoc
subset. The override and donor both dropped meter_type, so an electric-storage
system landed on the template's single-rate meter and billed overnight heat at
the peak rate: property 713406 scored SAP 13 (G) vs ~50 (E), inflating the HHRSH
measure to +45.8 and overshooting the plan to band A.
Establish a single Coherent Heating System boundary (CONTEXT.md) that every
synthesiser must cover, with a source-appropriate fill policy (ADR-0035):
- Override overlay *completes* the partial system the landlord named. Companion
fields are now DERIVED from the SAP code, not hand-attached per archetype: the
off-peak meter from the calculator's single off-peak classification (new
OFF_PEAK_IMPLYING_HEATING_CODES = SAP §12 Rules 1-2), and an unobserved storage
charge control defaults to the conservative manual control (Table 4e 2401). So
adding a heating archetype is just adding its code — companions can't be
forgotten. A contract test guards it (every off-peak code drags a Dual meter).
- Prediction's heating donor now *carries* the donor's meter_type alongside its
sap_heating cluster — the donor is already coherent.
Coherence is a synthesis-time obligation only; the calculator still scores a real
lodged cert exactly as lodged.
Verified on 713406: baseline 13 -> 47.8 (E), matching its recorded rating; the
phantom HHRSH recommendation is gone and the plan no longer overshoots to A.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Closes out the cohort-broadening work with its decision record and consolidates
the retry plumbing.
ADR-0034 documents broadening the EPC-Prediction cohort to the real unit
postcodes nearest the target (via postcodes.io) when its own postcode holds no
same-type comparable — extending ADR-0031 decision 5. Records why postcodes.io
was chosen over council[] (whole-LA, no property_type in rows), a bulk Code-Point
Open / ONSPD dataset, and the OS Places radius API, and the lazy / nearest-first
early-stop / soft-fail policy. Broadening-specific docstrings now cite 0034.
Retry consolidation: extract the EPC client's call_with_retry into a shared
infrastructure/http_retry.py keyed off a generic TransientHttpError marker, so
the mechanism (exponential backoff, Retry-After) is shared while each client
keeps its own transient policy. EpcRateLimitError now subclasses TransientHttpError
(still an EpcApiError); PostcodesIoClient routes through the same helper, raising
TransientHttpError on 429/5xx and soft-failing to the seed once exhausted (the EPC
client propagates instead). Direct tests for the shared helper; EPC + postcodes.io
suites repointed at the shared sleep.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Routes run_modelling through prop.effective_epc and dumps each target's
property_overrides before the run, so a landlord wall override moves the
calculated SAP. Records the overlay design in ADR-0032.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
build_first_run_pipeline now constructs epc_prediction=EpcPrediction() and accepts
comparables_repo + prediction_attributes_reader as optional params, threading them
into IngestionOrchestrator (ADR-0031). The on-switch is now just supplying those
two arguments — no orchestrator/handler edits — once they exist: the cohort repo
(its EPC client is the source client pending #1136) and the property_overrides
attributes reader (built separately). Both default None, so the feature stays OFF
and ingestion is unchanged until they're passed.
The epc_property.source migration is live, so the predicted-EPC persistence slot
(slice-5c) now works against the real DB. Handover updated to reflect the simpler
composition-root step.
pyright strict clean; handler + pipeline + ingestion-prediction tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The gap-fill is wired end-to-end (slices 5a-5e) behind seams; this note is what's
left to switch it on in production: (1) implement the PredictionTargetAttributesReader
stub over property_overrides — with the override-value → API-code mapping
select_comparables needs; (2) run the epc_property.source Drizzle migration; (3)
pass the three optional collaborators at the IngestionOrchestrator composition
root. Plus the open Validation-Cohort exclusion (no code path exists yet — exclude
on source_path == "predicted" when one is built) and the anomaly dual-use pointer.
No code change: the validation exclusion has no consumer to attach to today, and
the structural signal (source_path == "predicted") already exists from slice-5a.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add a `source` discriminator (lodged | predicted) to the EPC store so a Property
holds a lodged EPC and a predicted one (EPC Prediction gap-fill) at once
(ADR-0031). EpcRepository.save gains source="lodged"; idempotent delete is now
per-source (a predicted save no longer wipes lodged, and vice versa);
get_for_property/get_for_properties filter lodged; new get_predicted_for_property
/ get_predicted_for_properties read predicted. PropertyPostgresRepository.get +
get_many hydrate Property.predicted_epc, so the predicted picture reaches the
modelling read (both load via get_many). FakeEpcRepo mirrors the dual slot.
EpcPropertyModel gains `source` (default "lodged"); the test DB builds from the
SQLModel mirror so this is exercised without the prod migration. The matching
Drizzle change (column + per-(property_id,source) uniqueness) is the team's to
action before merge — docs/MIGRATION_NOTE_predicted_epc_source.md.
3 store tests (coexist, idempotent predicted re-save leaves lodged, lodged-only
has no predicted) + property-repo wiring; 85 pass across affected suites; new
code pyright-clean (2 pre-existing wwhrs errors in epc_property_table untouched).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Resolve the slice-5 design tree (grill-with-docs): estimation runs in Ingestion
(refines ADR-0029 dec-3; drops the #1227 "shift to Modelling" — no surviving
rationale, and stages communicate only via persisted state); predicted EPC is
persisted in a DISTINCT slot (EPC table + source discriminator) so lodged +
predicted coexist (enables EPC Anomaly Flags); provenance is structural (the
slot), not a field on EpcPropertyData; effective_epc/source_path gain a
"predicted" branch; slice-5 is gap-fill only; property_type is a REQUIRED input
(hard cohort filter) from Landlord Overrides, and Properties with unknown type
are gated out (no national defaults). OS postcode_search as a broader type
source is a noted follow-on. CONTEXT EPC Prediction entry gains the gating rule.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Strategy/context companion to the validate-cert-sap-accuracy skill: the
per-cert loop, how to read the gov-API-vs-Elmhurst comparison, the code->value
gotchas (immersion/cylinder/party-wall/baths/off-peak), known mapper gaps to
chase (alt-wall drop), cert-selection for coverage, guardrails (corpus gauge,
no tuning to one cert, no tolerance widening), and the current corpus state.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Tier-2 (full national bulk streaming) is deferred. The near-term scale
validation is a Tier-1.5: a few-thousand-cert anonymised corpus stored in
S3 (too large to commit, far more stable than the 36-target gate fixture),
pulled to a temp dir and run through the same load_corpus +
evaluate_component_accuracy. Reuses the committed-fixture machinery wholesale
— only the data source differs. One scorer, three data sources (committed
fixture / S3 corpus / bulk stream).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Records the grilling-session decisions amending ADR-0029's validation:
- Source cohort keeps all cert vintages (components are agnostic of the SAP
methodology that rated them); only the held-out validation TARGET is
restricted to SAP 10.2. Amends ADR-0029 decision 5 ("pre-SAP10 dropped").
- Component Accuracy (predicted vs API actual components) is the primary,
calculator-independent signal. calc(predicted) vs calc(actual) rejected
(circular ground truth, hides calculator error); neighbour-mean-lodged-SAP
baseline rejected (mixes SAP versions). calc(predicted) vs API-lodged
SAP/carbon/PE kept as a secondary, calculator-floored guard.
- Two tiers: committed anonymized fixture (ratcheting CI gate) + bulk-export
national battle-test on harness/epc_bulk.py + harness/cohort.py, emitting
accuracy + a failure taxonomy, re-baselining the gate floors.
CONTEXT.md: Comparable Properties corrected to all-vintage source; new
Component Accuracy term. ADR-0029 Validation section marked superseded.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
