Merge branch 'main' into feature/script-to-rename-sharepoint-files

.dockerignore

@@ -6,7 +6,7 @@ backend/.idea/*
 backend/.env
 recommendations/tests/*
 model_data/tests/*
-infrastructure/*
+deployment/*
 data_collection/*
 node_modules/*
 conservation_areas/*

.github/workflows/_build_image.yml

@@ -40,6 +40,8 @@ on:
         required: false
       EPC_AUTH_TOKEN:
         required: false
+      OPEN_EPC_API_TOKEN:
+        required: false
 
 jobs:
   build:
@@ -50,6 +52,7 @@ jobs:
       DEV_DB_PORT: ${{ secrets.DEV_DB_PORT }}
       DEV_DB_NAME: ${{ secrets.DEV_DB_NAME }}
       EPC_AUTH_TOKEN: ${{ secrets.EPC_AUTH_TOKEN }}
+      OPEN_EPC_API_TOKEN: ${{ secrets.OPEN_EPC_API_TOKEN }}
 
     outputs:
       image_digest: ${{ steps.digest.outputs.image_digest }}

.github/workflows/deploy_terraform.yml

@@ -62,20 +62,20 @@ jobs:
       - uses: hashicorp/setup-terraform@v3
 
       - name: Terraform Init
-        working-directory: infrastructure/terraform/shared
+        working-directory: deployment/terraform/shared
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: infrastructure/terraform/shared
+        working-directory: deployment/terraform/shared
         run: terraform workspace select ${STAGE} || terraform workspace new ${STAGE}
 
       - name: Terraform Plan
-        working-directory: infrastructure/terraform/shared
+        working-directory: deployment/terraform/shared
         run: terraform plan -var-file=${STAGE}.tfvars -out=tfplan
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: infrastructure/terraform/shared
+        working-directory: deployment/terraform/shared
         run: terraform apply -auto-approve tfplan
 
   # ============================================================
@@ -101,7 +101,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: ara_engine
-      lambda_path: infrastructure/terraform/lambda/engine
+      lambda_path: deployment/terraform/lambda/engine
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: engine-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.ara_engine_image.outputs.image_digest }}
@@ -133,6 +133,7 @@ jobs:
         DEV_DB_PORT=$DEV_DB_PORT
         DEV_DB_NAME=$DEV_DB_NAME
         EPC_AUTH_TOKEN=$EPC_AUTH_TOKEN
+        OPEN_EPC_API_TOKEN=$OPEN_EPC_API_TOKEN
     secrets:
       AWS_ACCESS_KEY_ID: ${{ secrets.DEV_AWS_ACCESS_KEY_ID }}
       AWS_SECRET_ACCESS_KEY: ${{ secrets.DEV_AWS_SECRET_ACCESS_KEY }}
@@ -141,6 +142,7 @@ jobs:
       DEV_DB_PORT: ${{ secrets.DEV_DB_PORT }}
       DEV_DB_NAME: ${{ secrets.DEV_DB_NAME }}
       EPC_AUTH_TOKEN: ${{ secrets.DEV_EPC_AUTH_TOKEN }}
+      OPEN_EPC_API_TOKEN: ${{ secrets.DEV_OPEN_EPC_API_TOKEN }}
 
   # ============================================================
   # Deploy Address 2 UPRN Lambda
@@ -150,7 +152,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: address2uprn
-      lambda_path: infrastructure/terraform/lambda/address2UPRN
+      lambda_path: deployment/terraform/lambda/address2UPRN
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: address2uprn-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.address2uprn_image.outputs.image_digest }}
@@ -169,7 +171,7 @@ jobs:
     uses: ./.github/workflows/_build_image.yml
     with:
       ecr_repo: postcode_splitter-${{ needs.determine_stage.outputs.stage }}
-      dockerfile_path: backend/postcode_splitter/handler/Dockerfile
+      dockerfile_path: applications/postcode_splitter/Dockerfile
       build_context: .
       build_args: |
         DEV_DB_HOST=$DEV_DB_HOST
@@ -191,7 +193,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: postcodeSplitter
-      lambda_path: infrastructure/terraform/lambda/postcodeSplitter
+      lambda_path: deployment/terraform/lambda/postcodeSplitter
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: postcode_splitter-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.postcodeSplitter_image.outputs.image_digest }}
@@ -231,7 +233,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: bulk_address2uprn_combiner
-      lambda_path: infrastructure/terraform/lambda/bulk_address2uprn_combiner
+      lambda_path: deployment/terraform/lambda/bulk_address2uprn_combiner
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: bulk_address2uprn_combiner-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.bulk_address2uprn_combiner_image.outputs.image_digest }}
@@ -271,7 +273,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: condition-etl
-      lambda_path: infrastructure/terraform/lambda/condition-etl
+      lambda_path: deployment/terraform/lambda/condition-etl
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: condition-etl-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.condition_etl_image.outputs.image_digest }}
@@ -311,7 +313,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: categorisation
-      lambda_path: infrastructure/terraform/lambda/categorisation
+      lambda_path: deployment/terraform/lambda/categorisation
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: categorisation-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.categorisation_image.outputs.image_digest }}
@@ -351,7 +353,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: ordnanceSurvey
-      lambda_path: infrastructure/terraform/lambda/ordnanceSurvey
+      lambda_path: deployment/terraform/lambda/ordnanceSurvey
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: ordnance-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.ordnanceSurvey_image.outputs.image_digest }}
@@ -386,7 +388,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: pashub_to_ara
-      lambda_path: infrastructure/terraform/lambda/pashub_to_ara
+      lambda_path: deployment/terraform/lambda/pashub_to_ara
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: pashub_to_ara-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.pashub_to_ara_image.outputs.image_digest }}
@@ -419,7 +421,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: ara_fast_api
-      lambda_path: infrastructure/terraform/lambda/fast-api
+      lambda_path: deployment/terraform/lambda/fast-api
       stage: ${{ needs.determine_stage.outputs.stage }}
       terraform_apply: ${{ needs.determine_stage.outputs.terraform_apply }}
     secrets:
@@ -458,17 +460,17 @@ jobs:
       - uses: hashicorp/setup-terraform@v3
 
       - name: Terraform Init
-        working-directory: infrastructure/terraform/cdn_certificate
+        working-directory: deployment/terraform/cdn_certificate
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: infrastructure/terraform/cdn_certificate
+        working-directory: deployment/terraform/cdn_certificate
         run: |
           terraform workspace select $STAGE \
             || terraform workspace new $STAGE
 
       - name: Terraform Plan
-        working-directory: infrastructure/terraform/cdn_certificate
+        working-directory: deployment/terraform/cdn_certificate
         run: |
           terraform plan \
             -var="stage=${STAGE}" \
@@ -476,7 +478,7 @@ jobs:
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: infrastructure/terraform/cdn_certificate
+        working-directory: deployment/terraform/cdn_certificate
         run: terraform apply -auto-approve tfplan
 
 
@@ -503,17 +505,17 @@ jobs:
       - uses: hashicorp/setup-terraform@v3
 
       - name: Terraform Init
-        working-directory: infrastructure/terraform/cdn
+        working-directory: deployment/terraform/cdn
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: infrastructure/terraform/cdn
+        working-directory: deployment/terraform/cdn
         run: |
           terraform workspace select $STAGE \
             || terraform workspace new $STAGE
 
       - name: Terraform Plan
-        working-directory: infrastructure/terraform/cdn
+        working-directory: deployment/terraform/cdn
         run: |
           terraform plan \
             -var="stage=${STAGE}" \
@@ -521,7 +523,7 @@ jobs:
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: infrastructure/terraform/cdn
+        working-directory: deployment/terraform/cdn
         run: terraform apply -auto-approve tfplan
 
   # ============================================================
@@ -562,7 +564,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: magic_plan
-      lambda_path: infrastructure/terraform/lambda/magic_plan
+      lambda_path: deployment/terraform/lambda/magic_plan
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: magic-plan-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.magic_plan_image.outputs.image_digest }}
@@ -585,7 +587,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: hubspot-etl-to-ara
-      lambda_path: infrastructure/terraform/lambda/hubspot_deal_etl
+      lambda_path: deployment/terraform/lambda/hubspot_deal_etl
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: hubspot-etl-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.hubspot_etl_image.outputs.image_digest }}

.github/workflows/lambda_smoke_tests.yml

@@ -36,6 +36,13 @@ jobs:
       build_context: .
       service_name: postcode-splitter
 
+  postcode_splitter_ddd_smoke_test:
+    uses: ./.github/workflows/_smoke_test_lambda.yml
+    with:
+      dockerfile_path: applications/postcode_splitter/Dockerfile
+      build_context: .
+      service_name: postcode-splitter-ddd
+
   # ============================================================
   # Bulk Address2UPRN Combiner
   # ============================================================

.github/workflows/unit_tests.yml

@@ -60,3 +60,15 @@ jobs:
             -e DB_PASSWORD=test \
             -e DB_PORT=5432 \
             model-test pytest -vv -m 'not integration'
+
+      # The DDD rewrite (tests/) defines SQLModel table classes that map to the
+      # same physical tables as the legacy backend models. Both sets share the
+      # one global SQLModel.metadata, so they cannot be imported into the same
+      # pytest process. It runs as a separate invocation until the legacy
+      # models are retired. Its DB is spawned in-process by pytest-postgresql,
+      # so no DB service or env is required.
+      - name: Run DDD tests
+        run: |
+          docker run --rm \
+            --network host \
+            model-test pytest -vv tests/

.gitignore

@@ -121,6 +121,7 @@ celerybeat.pid
 
 # Environments
 .env
+.env.local
 .venv
 env/
 venv/

AGENTS.md

@@ -1,29 +0,0 @@
-
-<!-- BACKLOG.MD MCP GUIDELINES START -->
-
-<CRITICAL_INSTRUCTION>
-
-## BACKLOG WORKFLOW INSTRUCTIONS
-
-This project uses Backlog.md MCP for all task and project management activities.
-
-**CRITICAL GUIDANCE**
-
-- If your client supports MCP resources, read `backlog://workflow/overview` to understand when and how to use Backlog for this project.
-- If your client only supports tools or the above request fails, call `backlog.get_backlog_instructions()` to load the tool-oriented overview. Use the `instruction` selector when you need `task-creation`, `task-execution`, or `task-finalization`.
-
-- **First time working here?** Read the overview resource IMMEDIATELY to learn the workflow
-- **Already familiar?** You should have the overview cached ("## Backlog.md Overview (MCP)")
-- **When to read it**: BEFORE creating tasks, or when you're unsure whether to track work
-
-These guides cover:
-- Decision framework for when to create tasks
-- Search-first workflow to avoid duplicates
-- Links to detailed guides for task creation, execution, and finalization
-- MCP tools reference
-
-You MUST read the overview resource to understand the complete workflow. The information is NOT summarized here.
-
-</CRITICAL_INSTRUCTION>
-
-<!-- BACKLOG.MD MCP GUIDELINES END -->

CLAUDE.md

@@ -1,33 +1,4 @@
 
-<!-- BACKLOG.MD MCP GUIDELINES START -->
-
-<CRITICAL_INSTRUCTION>
-
-## BACKLOG WORKFLOW INSTRUCTIONS
-
-This project uses Backlog.md MCP for all task and project management activities.
-
-**CRITICAL GUIDANCE**
-
-- If your client supports MCP resources, read `backlog://workflow/overview` to understand when and how to use Backlog for this project.
-- If your client only supports tools or the above request fails, call `backlog.get_backlog_instructions()` to load the tool-oriented overview. Use the `instruction` selector when you need `task-creation`, `task-execution`, or `task-finalization`.
-
-- **First time working here?** Read the overview resource IMMEDIATELY to learn the workflow
-- **Already familiar?** You should have the overview cached ("## Backlog.md Overview (MCP)")
-- **When to read it**: BEFORE creating tasks, or when you're unsure whether to track work
-
-These guides cover:
-- Decision framework for when to create tasks
-- Search-first workflow to avoid duplicates
-- Links to detailed guides for task creation, execution, and finalization
-- MCP tools reference
-
-You MUST read the overview resource to understand the complete workflow. The information is NOT summarized here.
-
-</CRITICAL_INSTRUCTION>
-
-<!-- BACKLOG.MD MCP GUIDELINES END -->
-
 ## Available Skills
 
 Five Claude Code skills are installed in this repo's dev container. Each maps to a phase of the feature lifecycle.

Dockerfile.test.dockerignore

@@ -4,7 +4,7 @@ model_data/local_data/
 backend/node_modules/
 backend/.idea/
 backend/.env
-infrastructure/
+deployment/
 data_collection/
 node_modules/
 conservation_areas/

UBIQUITOUS_LANGUAGE.md

@@ -23,7 +23,7 @@ Invoke `/ubiquitous-language` in any session to extract new terms from the conve
 |------|------------|------------------|
 | **UPRN** | Unique Property Reference Number — the government-issued permanent identifier for a physical address in the UK. | "property ID", "address ID", "code" |
 | **Postcode** | A UK postal code used to group nearby addresses; the primary search key for finding EPC records. | "zip code", "postal code" |
-| **User Address** | A free-text address string provided by a user or imported from a customer dataset, before any normalisation or matching. | "user input", "raw address", "user_inputed_address" |
+| **User Address** | A structured dataclass (`domain.addresses.user_address.UserAddress`) capturing a customer-supplied address: a free-text `user_address` line, a canonical `postcode` (sanitised on construction), and an optional `internal_reference`. The bare string sense -- the raw free-text address line as it arrives from upstream ingestion, before being wrapped -- remains valid when discussing CSV columns, API payloads, or other upstream contexts; in domain code, prefer the dataclass. | "user input", "raw address", "user_inputed_address" |
 | **Dwelling** | A single residential unit that can hold an EPC — a house, flat, or maisonette. | "property", "unit", "home" |
 
 ## Address Matching
@@ -72,7 +72,7 @@ Invoke `/ubiquitous-language` in any session to extract new terms from the conve
 
 ## Flagged ambiguities
 
-- **"address"** appears as both the raw **User Address** (free-text from customer data) and a structured field on an **EPC Search Result** (normalised address lines). Always qualify: "user address" vs "EPC address" or "address line 1".
+- **"address"** appears as both the raw **User Address** (free-text from customer data, or the structured `UserAddress` dataclass that wraps it) and a structured field on an **EPC Search Result** (normalised address lines). Always qualify: "user address" vs "EPC address" or "address line 1". Within `domain/`, **User Address** specifically means the `UserAddress` dataclass; in upstream ingestion contexts (CSV columns, SQS payloads) it can still mean the raw string sense.
 - **"score"** is used for the `AddressMatch.score()` function output, the `lexiscore` DataFrame column, and informally in conversation. Prefer **Lexiscore** in domain discussions; reserve "score" for method-level code comments.
 - **"user_inputed_address"** in `backend/address2UPRN/main.py` is a misspelling and a synonym for **User Address** — the canonical term. New code should use `user_address`.
 - **"EPC"** is overloaded as both the document (an Energy Performance Certificate) and the rating band letter. Use **EPC** for the document and **EPC Band** for the letter.

applications/postcode_splitter/Dockerfile

@@ -0,0 +1,34 @@
+FROM public.ecr.aws/lambda/python:3.11
+
+# Postgres host/port/database are baked into the image at build time from
+# the deploy workflow's --build-arg values (GitHub Actions DEV_DB_* secrets),
+# mirroring backend/postcode_splitter/handler/Dockerfile. They map onto the
+# POSTGRES_* names PostgresConfig.from_env reads. Username/password are NOT
+# baked in -- Terraform injects those as Lambda env vars from Secrets Manager.
+ARG DEV_DB_HOST
+ARG DEV_DB_PORT
+ARG DEV_DB_NAME
+
+ENV POSTGRES_HOST=${DEV_DB_HOST}
+ENV POSTGRES_PORT=${DEV_DB_PORT}
+ENV POSTGRES_DATABASE=${DEV_DB_NAME}
+
+WORKDIR /var/task
+
+COPY applications/postcode_splitter/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the layered source the handler imports from. The new splitter pulls
+# only DDD-shaped packages — no pandas, no legacy backend/.
+COPY domain/ domain/
+COPY infrastructure/ infrastructure/
+COPY orchestration/ orchestration/
+COPY repositories/ repositories/
+COPY utilities/ utilities/
+COPY applications/ applications/
+
+# Place the handler at the Lambda task root so the runtime can resolve
+# ``main.handler`` without an extra package prefix.
+COPY applications/postcode_splitter/handler.py /var/task/main.py
+
+CMD ["main.handler"]

applications/postcode_splitter/handler.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+import os
+from typing import Any
+
+import boto3
+
+from applications.postcode_splitter.postcode_splitter_trigger_body import (
+    PostcodeSplitterTriggerBody,
+)
+from infrastructure.address2uprn_queue_client import Address2UprnQueueClient
+from infrastructure.csv_s3_client import CsvS3Client
+from orchestration.postcode_splitter_orchestrator import PostcodeSplitterOrchestrator
+from orchestration.task_orchestrator import TaskOrchestrator
+from repositories.user_address.user_address_csv_s3_repository import (
+    UserAddressCsvS3Repository,
+)
+from utilities.aws_lambda.subtask_handler import subtask_handler
+
+
+@subtask_handler()
+def handler(
+    body: dict[str, Any], context: Any, task_orchestrator: TaskOrchestrator
+) -> dict[str, list[str]]:
+    trigger = PostcodeSplitterTriggerBody.model_validate(body)
+
+    bucket = os.environ["S3_BUCKET_NAME"]
+    queue_url = os.environ["ADDRESS2UPRN_QUEUE_URL"]
+
+    # boto3.client is overloaded per-service in the installed stubs; cast
+    # to Any so the strict-mode checker treats it as opaque.
+    boto3_client: Any = boto3.client  # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType]
+    boto_s3: Any = boto3_client("s3")
+    boto_sqs: Any = boto3_client("sqs")
+
+    csv_client = CsvS3Client(boto_s3, bucket)
+    user_address_repo = UserAddressCsvS3Repository(csv_client, bucket)
+    queue_client = Address2UprnQueueClient(boto_sqs, queue_url)
+
+    splitter = PostcodeSplitterOrchestrator(
+        task_orchestrator=task_orchestrator,
+        user_address_repo=user_address_repo,
+        queue_client=queue_client,
+    )
+
+    child_ids = splitter.split_and_dispatch(
+        parent_task_id=trigger.task_id,
+        parent_subtask_id=trigger.sub_task_id,
+        input_s3_uri=trigger.s3_uri,
+    )
+
+    return {"child_subtask_ids": [str(cid) for cid in child_ids]}

applications/postcode_splitter/local_handler/.env.local.example

@@ -0,0 +1,34 @@
+# Local-test environment for the postcode_splitter Lambda.
+#
+#   cp .env.local.example .env.local   then fill in the values below.
+#
+# .env.local is gitignored. The container hits REAL AWS and a REAL Postgres,
+# so every value here points at infrastructure that actually exists.
+#
+# NOTE: the new DDD code uses different env var names than the repo root
+# .env. The mapping (root .env name -> var here) is given per section.
+# Keep comments on their own lines — docker-compose's env_file parser folds a
+# trailing "# ..." into the value.
+
+# --- Postgres (orchestration/default_orchestrator -> PostgresConfig.from_env) ---
+# POSTGRES_HOST <- DB_HOST, PORT <- DB_PORT, USERNAME <- DB_USERNAME,
+# PASSWORD <- DB_PASSWORD, DATABASE <- DB_NAME.
+POSTGRES_HOST=
+POSTGRES_PORT=5432
+POSTGRES_USERNAME=
+POSTGRES_PASSWORD=
+POSTGRES_DATABASE=
+# POSTGRES_DRIVER=psycopg2   (optional; defaults to psycopg2)
+
+# --- Handler config (applications/postcode_splitter/handler.py) ---
+# S3_BUCKET_NAME: bucket holding the input address CSV (root .env: DATA_BUCKET).
+# ADDRESS2UPRN_QUEUE_URL: SQS queue the splitter fans batches out to; not in
+# the root .env (Terraform sets it in prod).
+S3_BUCKET_NAME=
+ADDRESS2UPRN_QUEUE_URL=
+
+# --- AWS credentials for boto3 (S3 + SQS clients) ---
+AWS_ACCESS_KEY_ID=
+AWS_SECRET_ACCESS_KEY=
+AWS_DEFAULT_REGION=eu-west-2
+# AWS_SESSION_TOKEN=   (only if using temporary/SSO credentials)

applications/postcode_splitter/local_handler/docker-compose.yml

@@ -0,0 +1,9 @@
+services:
+  postcode-splitter:
+    build:
+      context: ../../../
+      dockerfile: applications/postcode_splitter/Dockerfile
+    ports:
+      - "9001:8080"
+    env_file:
+      - .env.local

applications/postcode_splitter/local_handler/invoke_local_lambda.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+import json
+import requests
+
+HOST = "localhost"
+PORT = "9001"
+
+LAMBDA_URL = f"http://{HOST}:{PORT}/2015-03-31/functions/function/invocations"
+
+payload = {
+    "Records": [
+        {
+            "body": json.dumps(
+                {
+                    "task_id": "e295d89b-a7c5-4a9a-8b4e-b405fab1f298",
+                    "sub_task_id": "f4a9944f-41f0-4a33-8669-5016ec574068",
+                    "s3_uri": "s3://retrofit-data-dev/bulk_onboarding_inputs/hyde2 (1).csv",
+                }
+            )
+        }
+    ]
+}
+
+response = requests.post(LAMBDA_URL, json=payload)
+
+print("Status code:", response.status_code)
+print("Response:")
+print(response.text)

applications/postcode_splitter/local_handler/run_local.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")"
+
+if [ ! -f .env.local ]; then
+  cp .env.local.example .env.local
+  echo "Created .env.local from the template — fill it in, then re-run." >&2
+  exit 1
+fi
+
+docker compose build --no-cache
+docker compose up --force-recreate

applications/postcode_splitter/postcode_splitter_trigger_body.py

@@ -0,0 +1,11 @@
+from uuid import UUID
+
+from pydantic import BaseModel, ConfigDict
+
+
+class PostcodeSplitterTriggerBody(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
+    task_id: UUID
+    sub_task_id: UUID
+    s3_uri: str

applications/postcode_splitter/requirements.txt

@@ -0,0 +1,4 @@
+boto3
+pydantic
+sqlmodel
+psycopg2-binary

asset_list/app.py

@@ -79,23 +79,23 @@ def app():
     """
 
     data_folder = "/workspaces/model/asset_list"
-    data_filename = "input.xlsx"
+    data_filename = "hyde.xlsx"
-    sheet_name = "Handovers"
+    sheet_name = "AddressProfilingResults"
-    postcode_column = "POSTCODE"
+    postcode_column = "Postcode"
-    address1_column = "Full Addres"
+    address1_column = "Address"
     address1_method = None
-    fulladdress_column = "Full Addres"
+    fulladdress_column = "Postcode"
     address_cols_to_concat = []
     missing_postcodes_method = None
     landlord_year_built = None
-    landlord_os_uprn = "domna_found_uprn"
+    landlord_os_uprn = None
-    landlord_property_type = "PROPERTY TYPE"  # Good to include if landlord gave
+    landlord_property_type = "Property Type"  # Good to include if landlord gave
-    landlord_built_form = "Type Description"  # Good to include if landlord gave
+    landlord_built_form = None  # Good to include if landlord gave
     landlord_wall_construction = None
     landlord_roof_construction = None
     landlord_heating_system = None
     landlord_existing_pv = None
-    landlord_property_id = "PROP REF"
+    landlord_property_id = "Organisation Reference"
     landlord_sap = None
     outcomes_filename = None
     outcomes_sheetname = None
@@ -469,8 +469,3 @@ def app():
                     writer, sheet_name="Duplicate Properties", index=False
                 )
 
-
-
-
-for key,value in dict.items():
-    lsakjfldsa

backend/address2UPRN/handler/Dockerfile

@@ -6,11 +6,13 @@ ARG DEV_DB_HOST
 ARG DEV_DB_PORT
 ARG DEV_DB_NAME
 ARG EPC_AUTH_TOKEN
+ARG OPEN_EPC_API_TOKEN
 
 ENV DB_HOST=${DEV_DB_HOST}
 ENV DB_PORT=${DEV_DB_PORT}
 ENV DB_NAME=${DEV_DB_NAME}
 ENV EPC_AUTH_TOKEN=${EPC_AUTH_TOKEN}
+ENV OPEN_EPC_API_TOKEN=${OPEN_EPC_API_TOKEN}
 
 
 # Set working directory (Lambda task root)

backend/address2UPRN/handler/requirements.txt

@@ -8,4 +8,5 @@ boto3==1.35.44
 sqlmodel
 sqlalchemy==2.0.36
 psycopg2-binary==2.9.10
-pydantic-settings==2.6.0
+pydantic-settings==2.6.0
+httpx

backend/epc_client/epc_client_service.py

@@ -47,8 +47,14 @@ class EpcClientService:
         latest = max(results, key=lambda r: r.registration_date)
         return self.get_by_certificate_number(latest.certificate_number)
 
+    @staticmethod
+    def _normalise_postcode(postcode: str) -> str:
+        """Return the postcode with all spaces removed and uppercased."""
+        return postcode.replace(" ", "").upper()
+
     def search_by_postcode(self, postcode: str) -> list[EpcSearchResult]:
-        return call_with_retry(lambda: self._search(postcode=postcode))
+        normalised = self._normalise_postcode(postcode)
+        return call_with_retry(lambda: self._search(postcode=normalised))
 
     # ------------------------------------------------------------------
     # Private helperEpcRateLimpolarss

deployment/terraform/lambda/_template/README.md

@@ -10,7 +10,7 @@
 ### 2. Add infrastructure prerequisites (shared stack)
 - Add a new ECR repository in:
 
-  infrastructure/terraform/shared/main.tf
+  deployment/terraform/shared/main.tf
 
 - Create a PR to deploy this to main then dev in order to deploy the shared stack
 

deployment/terraform/lambda/postcodeSplitter/main.tf

@@ -38,22 +38,8 @@ module "lambda" {
     {
       STAGE     = var.stage
       LOG_LEVEL = "info"
-      DB_USERNAME = local.db_credentials.db_assessment_model_username
+      POSTGRES_USERNAME = local.db_credentials.db_assessment_model_username
-      DB_PASSWORD = local.db_credentials.db_assessment_model_password
+      POSTGRES_PASSWORD = local.db_credentials.db_assessment_model_password
-      GOOGLE_SOLAR_API_KEY = "test"
-      SAP_PREDICTIONS_BUCKET = "test"
-      CARBON_PREDICTIONS_BUCKET = "test"
-      HEAT_PREDICTIONS_BUCKET = "test"
-      HEATING_KWH_PREDICTIONS_BUCKET = "test"
-      HOTWATER_KWH_PREDICTIONS_BUCKET = "test"
-      API_KEY = "test"
-      ENVIRONMENT = "test"
-      SECRET_KEY = "test"
-      PLAN_TRIGGER_BUCKET = "test"
-      DATA_BUCKET = "test"
-      EPC_AUTH_TOKEN = "test"
-      ENGINE_SQS_URL = "test"
-      ENERGY_ASSESSMENTS_BUCKET = "test"
       ADDRESS2UPRN_QUEUE_URL = data.terraform_remote_state.address2uprn.outputs.address2uprn_queue_url
       S3_BUCKET_NAME = data.terraform_remote_state.shared.outputs.retrofit_sap_data_bucket_name
     },