Merge remote-tracking branch 'origin/main' into HEAD

# Conflicts:
#	tests/infrastructure/epc_client/test_sap_accuracy_corpus.py

.claude/skills/epc-to-elmhurst-rdsap-inputs/SKILL.md

@@ -115,6 +115,16 @@ one-line reason. Absent ≠ zero everywhere — note which.
 - **Water heating** 903 = Electric immersion off-peak → Elmhurst "Water Heater"
   category, not "Boiler Circulator" (901 = from main system).
 - **Windows** are synthesised from `glazed_area` band × TFA — not real geometry.
+- **Room height — give the RAW surveyed room height, NOT the engine's storey
+  height.** Elmhurst adds the RdSAP +0.25 m upper-storey (joist-void) allowance
+  itself. Our mapper already applies that +0.25 to upper floors
+  (`_UPPER_FLOOR_HEIGHT_ADD_M`), so `sap_floor_dimensions[*].room_height_m` for
+  a first floor is *already* `raw + 0.25`. Reading that value onto the sheet
+  makes Elmhurst add a SECOND 0.25 → storey height too tall → ~4-5 m² extra wall
+  + volume → **~1 SAP too low** (it under-scored 6 Barry Road 60→59 until the
+  first-floor height was corrected from 2.76 back to the raw 2.51). Pull heights
+  from the survey/raw `building_measurements`, not the transformed
+  `sap_floor_dimensions`; the ground/lowest floor takes the raw value either way.
 - **Age band — pick by construction YEAR, not the engine's band letter.** The
   live RdSAP-10 tool bands differently from `mapping.md`'s older table: it
   offers `…K 2007-2011`, **`L 2012-2022`**, **`M 2023 onwards`**. A 2020 build

.devcontainer/backend/Dockerfile

@@ -106,6 +106,12 @@ RUN git clone https://github.com/LazyVim/starter /home/${USER}/.config/nvim \
 RUN curl -fsSL https://claude.ai/install.sh | bash
 ENV PATH="/home/vscode/.local/bin:${PATH}"
 
+# Install herdr (terminal workspace manager for AI coding agents). Same pattern
+# as Claude Code above: the installer drops a self-contained static binary into
+# ~/.local/bin, which is now on PATH. Lets you run herdr from inside the
+# container. `herdr update` self-updates from herdr.dev thereafter.
+RUN curl -fsSL https://herdr.dev/install.sh | sh
+
 # Playwright chromium browser for the hyde Elmhurst automation. Run as the
 # vscode user so the download lands in /home/vscode/.cache/ms-playwright (the
 # OS deps were installed as root above). Headed chromium is required — the

.github/workflows/_deploy_lambda.yml

@@ -107,8 +107,6 @@ on:
         required: false
       TF_VAR_abri_relay_password:
         required: false
-      TF_VAR_abri_relay_default_resource:
-        required: false
       TF_VAR_test_abri_project_code_override:
         required: false
 jobs:
@@ -189,7 +187,6 @@ jobs:
           TF_VAR_abri_relay_url: ${{ secrets.TF_VAR_abri_relay_url }}
           TF_VAR_abri_relay_username: ${{ secrets.TF_VAR_abri_relay_username }}
           TF_VAR_abri_relay_password: ${{ secrets.TF_VAR_abri_relay_password }}
-          TF_VAR_abri_relay_default_resource: ${{ secrets.TF_VAR_abri_relay_default_resource }}
           TF_VAR_test_abri_project_code_override: ${{ secrets.TF_VAR_test_abri_project_code_override }}
         run: |
           ECR_REPO_URL_VAR=""
@@ -247,7 +244,6 @@ jobs:
           TF_VAR_abri_relay_url: ${{ secrets.TF_VAR_abri_relay_url }}
           TF_VAR_abri_relay_username: ${{ secrets.TF_VAR_abri_relay_username }}
           TF_VAR_abri_relay_password: ${{ secrets.TF_VAR_abri_relay_password }}
-          TF_VAR_abri_relay_default_resource: ${{ secrets.TF_VAR_abri_relay_default_resource }}
         run: |
           EXTRA_VARS=""
           if [[ -n "${{ inputs.ecr_repo }}" ]]; then

.github/workflows/deploy_terraform.yml

@@ -740,7 +740,6 @@ jobs:
       TF_VAR_abri_relay_url: ${{ secrets.ABRI_RELAY_URL }}
       TF_VAR_abri_relay_username: ${{ secrets.ABRI_RELAY_USERNAME }}
       TF_VAR_abri_relay_password: ${{ secrets.ABRI_RELAY_PASSWORD }}
-      TF_VAR_abri_relay_default_resource: ${{ secrets.ABRI_RELAY_DEFAULT_RESOURCE }}
 
   # ============================================================
   # Build Audit Generator image

CONTEXT.md

@@ -28,8 +28,8 @@ The date an EPC was lodged with the government register; used to identify the mo
 _Avoid_: assessment date, submission date
 
 **EPC Band**:
-A single letter A–G representing a property's current or potential energy efficiency rating.
-_Avoid_: energy rating, EPC grade, EPC score
+A single letter A–G representing a property's current or potential energy efficiency rating. A dwelling is in a band by its **published rating** — the continuous SAP rounded **half up** to the integer printed on the certificate (SAP 10.2 §13; Python's built-in `round` is half-to-*even* and must not be used for this). Anything holding a continuous score therefore judges band membership via `Epc.from_sap_continuous`, and any "has it reached band X?" test compares against `Epc.sap_lower_bound_continuous()` — the integer floor **less half a point** (C → 68.5), which is where the published rating enters the band. Comparing a continuous score against the raw integer floor makes a dwelling that already publishes in the band read as a fraction short (ADR-0064).
+_Avoid_: energy rating, EPC grade, EPC score; comparing a continuous SAP against `sap_lower_bound()`
 
 **Schema Type**:
 The versioned RdSAP or SAP schema that describes the structure of an EPC's raw data (e.g. `RdSAP-Schema-21.0.1`).
@@ -156,7 +156,7 @@ The SAP / EPC Band / carbon emissions / Primary Energy Intensity recorded on the
 _Avoid_: original performance, raw EPC values, recorded baseline
 
 **Effective Performance**:
-The SAP / EPC Band / carbon emissions / Primary Energy Intensity the modelling pipeline actually scored against — equal to Lodged Performance when no Rebaselining trigger fires, replaced by **SAP10 Calculation** output (the deterministic `Sap10Calculator`, which superseded the old ML-API rebaseliner; an ML residual head over the calculator is future — ADR-0009/0013) when triggered. The half of Baseline Performance that says "what we modelled".
+The SAP / EPC Band / carbon emissions / Primary Energy Intensity the modelling pipeline actually scored against — equal to Lodged Performance when no Rebaselining trigger fires, replaced by **SAP10 Calculation** output (the deterministic `Sap10Calculator`, which superseded the old ML-API rebaseliner; an ML residual head over the calculator is future — ADR-0009/0013) when triggered. The half of Baseline Performance that says "what we modelled". **Modelling does not read it**: it re-scores the Effective EPC itself (it needs a continuous score and a `SapResult` to bill from, and ADR-0011 forbids an in-memory hand-off between stages), then **asserts** its re-score agrees with this persisted figure and logs an error when it does not. The two are deliberately *not* reconciled — a divergence means the stages scored different pictures, and anchoring the Plan's SAP to this integer would leave it disagreeing with its own carbon, energy and bill figures (ADR-0066). Because a Plan's `post_*` are read against this figure, an unchecked divergence surfaces to the user as a gain nobody modelled.
 _Avoid_: modelled performance, rebaselined performance (only correct when rebaselining ran), scored values
 
 **Calculated SAP10 Performance**:
@@ -309,7 +309,7 @@ A "selecting A requires B" edge between **Recommendations**, for couplings that
 _Avoid_: best-practice measure (legacy term), forced measure
 
 **Optimised Package**:
-The subset of a Property's Recommendations selected by the Optimiser Service for installation. For an **Increasing EPC** goal the objective is **least-cost-to-target**: the cheapest package that reaches the goal band — so it **stops at the target and does not overshoot** into a higher band, leaving surplus budget unspent. When the target is **unreachable within budget**, it falls back to the **maximum improvement the budget buys** (best effort, below target). With **no budget** it is simply the cheapest package that reaches the target. Reaching the target is judged on the **true whole-package re-score** (ADR-0016), not on summed per-measure scores. (Other goals — Energy Savings, Reducing CO₂ — don't yet set a target and currently maximise improvement within budget; future work.)
+The subset of a Property's Recommendations selected by the Optimiser Service for installation. For an **Increasing EPC** goal the objective is **least-cost-to-target**: the cheapest package that reaches the goal band — so it **stops at the target and does not overshoot** into a higher band, leaving surplus budget unspent. When the target is **unreachable within budget**, it falls back to the **maximum improvement the budget buys** (best effort, below target). With **no budget** it is simply the cheapest package that reaches the target. Reaching the target is judged on the **true whole-package re-score** (ADR-0016), not on summed per-measure scores — and on the **published** band (see **EPC Band**): the target is the goal band's floor on the continuous scale, so a dwelling whose published baseline already meets the goal is **already at target** and gets an empty, £0 package rather than a marginal top-up (ADR-0064). (Other goals — Energy Savings, Reducing CO₂ — don't yet set a target and currently maximise improvement within budget; future work.)
 _Avoid_: selected measures, default measures, optimal solution, recommended bundle
 
 **Measure Type**:

applications/abri/abri_trigger_request.py

@@ -9,7 +9,7 @@ visibility surface.
 from datetime import date
 from typing import Dict, List, Literal, Optional, Tuple
 
-from pydantic import BaseModel, ConfigDict, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 AbriFlow = Literal["amend_job", "log_job", "sync_tenant_data", "abandon_job"]
 
@@ -19,8 +19,13 @@ AbriFlow = Literal["amend_job", "log_job", "sync_tenant_data", "abandon_job"]
 # alone would reject valid messages; the orchestrator fails the flow if a deal
 # carries neither. Its outcome is optional too, only feeding the reason seam.
 _FIELDS_BY_FLOW: Dict[AbriFlow, Tuple[str, ...]] = {
-    "amend_job": ("confirmed_survey_date",),
-    "log_job": ("place_ref", "deal_name", "confirmed_survey_date"),
+    "amend_job": ("confirmed_survey_date", "third_party_surveyor_identifier"),
+    "log_job": (
+        "place_ref",
+        "deal_name",
+        "confirmed_survey_date",
+        "third_party_surveyor_identifier",
+    ),
     "sync_tenant_data": ("place_ref",),
     "abandon_job": (),
 }
@@ -37,6 +42,18 @@ class AbriTriggerRequest(BaseModel):
     confirmed_survey_time: Optional[str] = None
     last_submission_date: Optional[date] = None
     outcome: Optional[str] = None
+    # OpenHousing's bookable resource for the survey; required by the log and
+    # amend flows. Empty string is also rejected by Abri, so not allowed here
+    third_party_surveyor_identifier: Optional[str] = None
+
+    @field_validator("third_party_surveyor_identifier")
+    @classmethod
+    def _blank_surveyor_identifier_is_missing(
+        cls, value: Optional[str]
+    ) -> Optional[str]:
+        if value is not None and not value.strip():
+            return None
+        return value
 
     @model_validator(mode="after")
     def _each_fired_flow_has_its_fields(self) -> "AbriTriggerRequest":

applications/abri/dispatch.py

@@ -81,13 +81,19 @@ def dispatch_abri_flows(
 
 
 def _run_amend(request: AbriTriggerRequest, flows: AbriFlows) -> str:
-    if request.confirmed_survey_date is None:
-        raise ValueError("amend_job fired without a confirmed_survey_date")
+    if (
+        request.confirmed_survey_date is None
+        or request.third_party_surveyor_identifier is None
+    ):
+        raise ValueError(
+            "amend_job fired without a confirmed_survey_date/surveyor identifier"
+        )
     outcome = flows.amend_job(
         AppointmentChange(
             deal_id=request.hubspot_deal_id,
             confirmed_survey_date=request.confirmed_survey_date,
             confirmed_survey_time=request.confirmed_survey_time,
+            third_party_surveyor_identifier=request.third_party_surveyor_identifier,
         )
     )
     if isinstance(outcome, AbriRequestRejected):
@@ -111,8 +117,12 @@ def _run_log(
         request.place_ref is None
         or request.deal_name is None
         or request.confirmed_survey_date is None
+        or request.third_party_surveyor_identifier is None
     ):
-        raise ValueError("log_job fired without place_ref/deal_name/survey date")
+        raise ValueError(
+            "log_job fired without place_ref/deal_name/survey date/"
+            "surveyor identifier"
+        )
     try:
         outcome = flows.log_job(
             ConfirmedSurveyBooking(
@@ -121,6 +131,9 @@ def _run_log(
                 deal_name=request.deal_name,
                 confirmed_survey_date=request.confirmed_survey_date,
                 confirmed_survey_time=request.confirmed_survey_time,
+                third_party_surveyor_identifier=(
+                    request.third_party_surveyor_identifier
+                ),
             )
         )
     except LogJobWriteBackError as error:

backend/app/db/models/hubspot_deal_data.py

@@ -67,6 +67,7 @@ class HubspotDealData(SQLModel, table=True):
     lodgement_date: Optional[datetime] = Field(default=None)
     expected_commencement_date: Optional[datetime] = Field(default=None)
     surveyor: Optional[str] = Field(default=None)
+    third_party_surveyor_identifier: Optional[str] = Field(default=None)
     confirmed_survey_date: Optional[datetime] = Field(default=None)
     confirmed_survey_time: Optional[str] = Field(default=None)
     surveyed_date: Optional[datetime] = Field(default=None)

backend/documents_parser/extractor.py

@@ -481,7 +481,9 @@ class PasHubRdSapSiteNotesExtractor:
 
     def extract_room_count_elements(self) -> RoomCountElements:
         rce_section = self._section("Room Count Elements", "Customer Response")
-        heated_rooms_raw = self._get_in(rce_section, "Number of heated rooms?")
+        heated_rooms_raw = self._get_in(
+            rce_section, "Please enter the number of HEATED rooms:"
+        )
         return RoomCountElements(
             number_of_habitable_rooms=int(
                 self._get_in(rce_section, "Number of habitable rooms?") or 0
@@ -518,6 +520,15 @@ class PasHubRdSapSiteNotesExtractor:
             number_of_fixed_cfl_bulbs=int(
                 self._get_in(rce_section, "Number of fixed CFL bulbs:") or 0
             ),
+            number_of_fixed_low_energy_lights=(
+                int(low_energy_raw)
+                if (
+                    low_energy_raw := self._get_in(
+                        rce_section, "Number of fixed low energy lights?"
+                    )
+                )
+                else None
+            ),
             waste_water_heat_recovery=self._get_in(
                 rce_section, "Are there any waste water heat recovery systems?"
             )
@@ -615,7 +626,11 @@ class PasHubRdSapSiteNotesExtractor:
             condensing=self._bool_in(data, "Condensing"),
             year=self._get_in(data, "Year") or "",
             mount=self._get_in(data, "Mount") or "",
-            open_flue=self._get_in(data, "Open Flue") or "",
+            # PCDF-Search "Open Flue" column wins; a Manual-Entry boiler instead
+            # lodges the flue under "Is there an open flue?" (Yes/No) (#1649 A).
+            open_flue=self._get_in(data, "Open Flue")
+            or self._get_in(data, "Is there an open flue?")
+            or "",
             fan_assist=self._bool_in(data, "Fan Assist"),
             status=self._get_in(data, "Status") or "",
             central_heating_pump_age=self._get_in(data, "Central heating pump age:")
@@ -627,6 +642,12 @@ class PasHubRdSapSiteNotesExtractor:
             weather_compensator=self._bool_in(data, "Is there a weather compensator?"),
             emitter=self._get_in(data, "Emitter:") or "",
             emitter_temperature=self._get_in(data, "Emitter Temperature:") or "",
+            # Manual-Entry boiler descriptor (blank on a PCDF-Search boiler):
+            # "Type of boiler:" and "Heating System (Boiler):" (the latter
+            # carries the pre/post-1998 age band) → the mapper's Table 4b
+            # efficiency lookup (#1649 A).
+            boiler_type=self._get_in(data, "Type of boiler:") or "",
+            boiler_age_band=self._get_in(data, "Heating System (Boiler):") or "",
         )
 
     def _parse_secondary_heating(self, data: List[str]) -> SecondaryHeating:
@@ -856,4 +877,9 @@ class PasHubRdSapSiteNotesExtractor:
             or "",
             wall_thickness_mm=self._wall_thickness_in(data),
             dry_lined=self._optional_bool_in(data, "Wall Dry-Lined?"),
+            # Surveyed alt-wall insulation thickness ("50 mm") → the mapper's
+            # §5.4 thickness input; dropped, the cascade assumes 100 mm (#1649 D).
+            insulation_thickness_mm=self._parse_insulation_thickness(
+                self._get_in(data, "Wall insulation thickness:")
+            )[0],
         )

backend/documents_parser/tests/fixtures/pashub_accuracy/manifest.json

@@ -1091,8 +1091,8 @@
     {
       "deal_id": "507639151845",
       "uprn": null,
-      "pre_sap_raw": "C80",
-      "pre_sap_score": 80,
+      "pre_sap_raw": "C76",
+      "pre_sap_score": 76,
       "pdf": "507639151845.pdf"
     },
     {