.dockerignore

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

.github/workflows/_build_image.yml

@@ -40,8 +40,6 @@ on:
         required: false
       EPC_AUTH_TOKEN:
         required: false
-      OPEN_EPC_API_TOKEN:
-        required: false
 
 jobs:
   build:
@@ -52,7 +50,6 @@ 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: deployment/terraform/shared
+        working-directory: infrastructure/terraform/shared
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: deployment/terraform/shared
+        working-directory: infrastructure/terraform/shared
         run: terraform workspace select ${STAGE} || terraform workspace new ${STAGE}
 
       - name: Terraform Plan
-        working-directory: deployment/terraform/shared
+        working-directory: infrastructure/terraform/shared
         run: terraform plan -var-file=${STAGE}.tfvars -out=tfplan
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: deployment/terraform/shared
+        working-directory: infrastructure/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: deployment/terraform/lambda/engine
+      lambda_path: infrastructure/terraform/lambda/engine
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: engine-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.ara_engine_image.outputs.image_digest }}
@@ -133,7 +133,6 @@ jobs:
         DEV_DB_PORT=$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 }}
@@ -142,7 +141,6 @@ 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
@@ -152,7 +150,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: address2uprn
-      lambda_path: deployment/terraform/lambda/address2UPRN
+      lambda_path: infrastructure/terraform/lambda/address2UPRN
       stage: ${{ needs.determine_stage.outputs.stage }}
       ecr_repo: address2uprn-${{ needs.determine_stage.outputs.stage }}
       image_digest: ${{ needs.address2uprn_image.outputs.image_digest }}
@@ -171,7 +169,7 @@ jobs:
     uses: ./.github/workflows/_build_image.yml
     with:
       ecr_repo: postcode_splitter-${{ needs.determine_stage.outputs.stage }}
-      dockerfile_path: applications/postcode_splitter/Dockerfile
+      dockerfile_path: backend/postcode_splitter/handler/Dockerfile
       build_context: .
       build_args: |
         DEV_DB_HOST=$DEV_DB_HOST
@@ -193,7 +191,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: postcodeSplitter
-      lambda_path: deployment/terraform/lambda/postcodeSplitter
+      lambda_path: infrastructure/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 }}
@@ -233,7 +231,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: bulk_address2uprn_combiner
-      lambda_path: deployment/terraform/lambda/bulk_address2uprn_combiner
+      lambda_path: infrastructure/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 }}
@@ -273,7 +271,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: condition-etl
-      lambda_path: deployment/terraform/lambda/condition-etl
+      lambda_path: infrastructure/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 }}
@@ -313,7 +311,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: categorisation
-      lambda_path: deployment/terraform/lambda/categorisation
+      lambda_path: infrastructure/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 }}
@@ -353,7 +351,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: ordnanceSurvey
-      lambda_path: deployment/terraform/lambda/ordnanceSurvey
+      lambda_path: infrastructure/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 }}
@@ -388,7 +386,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: pashub_to_ara
-      lambda_path: deployment/terraform/lambda/pashub_to_ara
+      lambda_path: infrastructure/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 }}
@@ -421,7 +419,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: ara_fast_api
-      lambda_path: deployment/terraform/lambda/fast-api
+      lambda_path: infrastructure/terraform/lambda/fast-api
       stage: ${{ needs.determine_stage.outputs.stage }}
       terraform_apply: ${{ needs.determine_stage.outputs.terraform_apply }}
     secrets:
@@ -460,17 +458,17 @@ jobs:
       - uses: hashicorp/setup-terraform@v3
 
       - name: Terraform Init
-        working-directory: deployment/terraform/cdn_certificate
+        working-directory: infrastructure/terraform/cdn_certificate
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: deployment/terraform/cdn_certificate
+        working-directory: infrastructure/terraform/cdn_certificate
         run: |
           terraform workspace select $STAGE \
             || terraform workspace new $STAGE
 
       - name: Terraform Plan
-        working-directory: deployment/terraform/cdn_certificate
+        working-directory: infrastructure/terraform/cdn_certificate
         run: |
           terraform plan \
             -var="stage=${STAGE}" \
@@ -478,7 +476,7 @@ jobs:
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: deployment/terraform/cdn_certificate
+        working-directory: infrastructure/terraform/cdn_certificate
         run: terraform apply -auto-approve tfplan
 
 
@@ -505,17 +503,17 @@ jobs:
       - uses: hashicorp/setup-terraform@v3
 
       - name: Terraform Init
-        working-directory: deployment/terraform/cdn
+        working-directory: infrastructure/terraform/cdn
         run: terraform init -reconfigure
 
       - name: Terraform Workspace
-        working-directory: deployment/terraform/cdn
+        working-directory: infrastructure/terraform/cdn
         run: |
           terraform workspace select $STAGE \
             || terraform workspace new $STAGE
 
       - name: Terraform Plan
-        working-directory: deployment/terraform/cdn
+        working-directory: infrastructure/terraform/cdn
         run: |
           terraform plan \
             -var="stage=${STAGE}" \
@@ -523,7 +521,7 @@ jobs:
 
       - name: Terraform Apply
         if: env.TERRAFORM_APPLY == 'true'
-        working-directory: deployment/terraform/cdn
+        working-directory: infrastructure/terraform/cdn
         run: terraform apply -auto-approve tfplan
 
   # ============================================================
@@ -564,7 +562,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: magic_plan
-      lambda_path: deployment/terraform/lambda/magic_plan
+      lambda_path: infrastructure/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 }}
@@ -587,7 +585,7 @@ jobs:
     uses: ./.github/workflows/_deploy_lambda.yml
     with:
       lambda_name: hubspot-etl-to-ara
-      lambda_path: deployment/terraform/lambda/hubspot_deal_etl
+      lambda_path: infrastructure/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

@@ -36,13 +36,6 @@ 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

@@ -60,15 +60,3 @@ 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

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

AGENTS.md

@@ -0,0 +1,29 @@
+
+<!-- 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

@@ -1,4 +1,33 @@
 
+<!-- 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
-deployment/
+infrastructure/
 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 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" |
+| **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" |
 | **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, 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.
+- **"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".
 - **"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

@@ -1,34 +0,0 @@
-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

@@ -1,52 +0,0 @@
-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

@@ -1,34 +0,0 @@
-# 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

@@ -1,9 +0,0 @@
-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

@@ -1,28 +0,0 @@
-#!/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": "f4b3332f-c0cc-481f-96a5-d39860a647cf",
-                    "sub_task_id": "14c042de-40c4-473b-8cd8-72c983a94a8d",
-                    "s3_uri": "s3://retrofit-data-dev/ara_raw_inputs/calico/Calico Homes Full list EPC Properties(Sheet2) (1) (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

@@ -1,12 +0,0 @@
-#!/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

@@ -1,11 +0,0 @@
-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

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

asset_list/app.py

@@ -79,23 +79,23 @@ def app():
     """
 
     data_folder = "/workspaces/model/asset_list"
-    data_filename = "lincs_address_list.xlsx"
-    sheet_name = "Sheet1"
-    postcode_column = "Postcode"
-    address1_column = "Deal Name"
+    data_filename = "input.xlsx"
+    sheet_name = "Handovers"
+    postcode_column = "POSTCODE"
+    address1_column = "Full Addres"
     address1_method = None
-    fulladdress_column = "Deal Name"
+    fulladdress_column = "Full Addres"
     address_cols_to_concat = []
     missing_postcodes_method = None
     landlord_year_built = None
-    landlord_os_uprn = None
-    landlord_property_type = None  # Good to include if landlord gave
-    landlord_built_form = None  # Good to include if landlord gave
+    landlord_os_uprn = "domna_found_uprn"
+    landlord_property_type = "PROPERTY TYPE"  # Good to include if landlord gave
+    landlord_built_form = "Type Description"  # 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 = "landlord_id"
+    landlord_property_id = "PROP REF"
     landlord_sap = None
     outcomes_filename = None
     outcomes_sheetname = None
@@ -468,3 +468,9 @@ def app():
                 asset_list.duplicated_addresses.to_excel(
                     writer, sheet_name="Duplicate Properties", index=False
                 )
+
+
+
+
+for key,value in dict.items():
+    lsakjfldsa

backend/address2UPRN/handler/Dockerfile

@@ -6,13 +6,11 @@ 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

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

domain/addresses/postcode_batching.py

@@ -1,51 +0,0 @@
-from __future__ import annotations
-
-from collections.abc import Iterable, Iterator
-
-from domain.addresses.user_address import UserAddress
-from domain.postcode import Postcode
-
-
-def iter_postcode_grouped_batches(
-    addresses: Iterable[UserAddress],
-    *,
-    max_batch_size: int = 500,
-) -> Iterator[list[UserAddress]]:
-    if max_batch_size < 1:
-        raise ValueError("max_batch_size must be >= 1")
-
-    groups = _group_by_postcode_in_order(addresses)
-
-    buffer: list[UserAddress] = []
-    for group in groups.values():
-        group_len = len(group)
-
-        # Oversize single-Postcode group: flush buffer first, then dispatch
-        # the group as its own batch. Mirrors the legacy
-        # ``if group_len >= batch_size`` branch.
-        if group_len >= max_batch_size:
-            if buffer:
-                yield buffer
-                buffer = []
-            yield group
-            continue
-
-        # Adding this group would overflow: flush buffer before appending.
-        if len(buffer) + group_len > max_batch_size:
-            yield buffer
-            buffer = []
-
-        buffer.extend(group)
-
-    # Final flush.
-    if buffer:
-        yield buffer
-
-
-def _group_by_postcode_in_order(
-    addresses: Iterable[UserAddress],
-) -> dict[Postcode, list[UserAddress]]:
-    groups: dict[Postcode, list[UserAddress]] = {}
-    for address in addresses:
-        groups.setdefault(address.postcode, []).append(address)
-    return groups

domain/addresses/user_address.py

@@ -1,18 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from typing import Optional
-
-from domain.postcode import Postcode
-
-
-def _empty_source_row() -> dict[str, str]:
-    return {}
-
-
-@dataclass(frozen=True)
-class UserAddress:
-    user_address: str
-    postcode: Postcode
-    internal_reference: Optional[str] = None
-    source_row: dict[str, str] = field(default_factory=_empty_source_row, compare=False)

domain/postcode.py

@@ -1,15 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-
-
-@dataclass(frozen=True)
-class Postcode:
-    value: str
-
-    def __post_init__(self) -> None:
-        # Frozen dataclass: bypass the descriptor with object.__setattr__.
-        object.__setattr__(self, "value", "".join(self.value.split()).upper())
-
-    def __str__(self) -> str:
-        return self.value

domain/tasks/subtasks.py

@@ -1,55 +0,0 @@
-from dataclasses import dataclass
-from datetime import datetime, timezone
-from enum import Enum
-from typing import Any, Optional
-from uuid import UUID, uuid4
-
-
-class SubTaskStatus(str, Enum):
-    WAITING = "waiting"
-    IN_PROGRESS = "in progress"
-    COMPLETE = "complete"
-    FAILED = "failed"
-
-
-@dataclass
-class SubTask:
-    id: UUID
-    task_id: UUID
-    status: SubTaskStatus = SubTaskStatus.WAITING
-    inputs: Optional[dict[str, Any]] = None
-    outputs: Optional[dict[str, Any]] = None
-    cloud_logs_url: Optional[str] = None
-    job_started: Optional[datetime] = None
-    job_completed: Optional[datetime] = None
-
-    @classmethod
-    def create(
-        cls, *, task_id: UUID, inputs: Optional[dict[str, Any]] = None
-    ) -> "SubTask":
-        return cls(
-            id=uuid4(),
-            task_id=task_id,
-            status=SubTaskStatus.WAITING,
-            inputs=inputs,
-        )
-
-    def start(self, cloud_logs_url: Optional[str] = None) -> None:
-        if self.status not in (SubTaskStatus.WAITING, SubTaskStatus.IN_PROGRESS):
-            raise ValueError(f"cannot start subtask in status {self.status}")
-        if self.job_started is None:
-            self.job_started = datetime.now(timezone.utc)
-        self.status = SubTaskStatus.IN_PROGRESS
-        if cloud_logs_url is not None:
-            self.cloud_logs_url = cloud_logs_url
-
-    def complete(self, result: Any = None) -> None:
-        self.status = SubTaskStatus.COMPLETE
-        self.job_completed = datetime.now(timezone.utc)
-        if result is not None:
-            self.outputs = {"result": result}
-
-    def fail(self, error: BaseException) -> None:
-        self.status = SubTaskStatus.FAILED
-        self.job_completed = datetime.now(timezone.utc)
-        self.outputs = {"error": str(error)}

domain/tasks/tasks.py

@@ -1,94 +0,0 @@
-from dataclasses import dataclass
-from datetime import datetime, timezone
-from enum import Enum
-from typing import Optional
-from uuid import UUID, uuid4
-
-from domain.tasks.subtasks import SubTaskStatus
-
-
-class TaskStatus(str, Enum):
-    WAITING = "waiting"
-    IN_PROGRESS = "in progress"
-    COMPLETE = "complete"
-    FAILED = "failed"
-
-
-class Source(str, Enum):
-    PORTFOLIO = "portfolio_id"
-    HUBSPOT_DEAL = "hubspot_deal_id"
-
-
-@dataclass
-class Task:
-    id: UUID
-    task_source: str
-    status: TaskStatus = TaskStatus.WAITING
-    service: Optional[str] = None
-    source: Optional[Source] = None
-    source_id: Optional[str] = None
-    job_started: Optional[datetime] = None
-    job_completed: Optional[datetime] = None
-
-    @classmethod
-    def create(
-        cls,
-        *,
-        task_source: str,
-        service: Optional[str] = None,
-        source: Optional[Source] = None,
-        source_id: Optional[str] = None,
-    ) -> "Task":
-        if not task_source.strip():
-            raise ValueError("task_source must be non-empty")
-        return cls(
-            id=uuid4(),
-            task_source=task_source,
-            service=service,
-            source=source,
-            source_id=source_id,
-            status=TaskStatus.WAITING,
-            job_started=datetime.now(timezone.utc),
-        )
-
-    def start(self) -> None:
-        if self.status not in (TaskStatus.WAITING, TaskStatus.IN_PROGRESS):
-            raise ValueError(f"cannot start task in status {self.status}")
-        if self.job_started is None:
-            self.job_started = datetime.now(timezone.utc)
-        self.status = TaskStatus.IN_PROGRESS
-
-    def complete(self) -> None:
-        self.status = TaskStatus.COMPLETE
-        self.job_completed = datetime.now(timezone.utc)
-
-    def fail(self) -> None:
-        self.status = TaskStatus.FAILED
-        self.job_completed = datetime.now(timezone.utc)
-
-    def recalculate_from_subtasks(self, statuses: list[SubTaskStatus]) -> None:
-        """Recompute Task.status from its SubTasks' statuses.
-
-        Rule (preserved from legacy _update_task_progress):
-          - any FAILED       → FAILED
-          - all COMPLETE     → COMPLETE
-          - any IN_PROGRESS  → IN_PROGRESS
-          - otherwise        → WAITING
-
-        Empty list is a no-op (newly-created task with no subtasks).
-        """
-        if not statuses:
-            return
-        now = datetime.now(timezone.utc)
-        if SubTaskStatus.FAILED in statuses:
-            self.status = TaskStatus.FAILED
-            self.job_completed = now
-        elif all(s is SubTaskStatus.COMPLETE for s in statuses):
-            self.status = TaskStatus.COMPLETE
-            self.job_completed = now
-        elif SubTaskStatus.IN_PROGRESS in statuses:
-            self.status = TaskStatus.IN_PROGRESS
-            self.job_completed = None
-        else:
-            self.status = TaskStatus.WAITING
-            self.job_completed = None

infrastructure/address2uprn_queue_client.py

@@ -1,20 +0,0 @@
-from uuid import UUID
-
-from infrastructure.sqs_client import SqsClient
-
-
-class Address2UprnQueueClient(SqsClient):
-    def publish(
-        self,
-        *,
-        parent_task_id: UUID,
-        child_subtask_id: UUID,
-        s3_uri: str,
-    ) -> str:
-        return self.send(
-            {
-                "task_id": str(parent_task_id),
-                "sub_task_id": str(child_subtask_id),
-                "s3_uri": s3_uri,
-            }
-        )

infrastructure/csv_s3_client.py

@@ -1,28 +0,0 @@
-import csv
-from io import StringIO
-
-from infrastructure.s3_client import S3Client
-from infrastructure.s3_uri import parse_s3_uri
-
-
-class CsvS3Client(S3Client):
-    def read_rows(self, s3_uri: str) -> list[dict[str, str]]:
-        bucket, key = parse_s3_uri(s3_uri)
-        if bucket != self.bucket:
-            raise ValueError(
-                f"s3_uri bucket {bucket!r} does not match client bucket {self.bucket!r}"
-            )
-        raw = self.get_object(key)
-        text = raw.decode("utf-8-sig")
-        reader = csv.DictReader(StringIO(text))
-        return [dict(row) for row in reader]
-
-    def save_rows(self, rows: list[dict[str, str]], key: str) -> str:
-        if not rows:
-            raise ValueError("Cannot save an empty rows list: header is unknown")
-        buffer = StringIO()
-        fieldnames = list(rows[0].keys())
-        writer = csv.DictWriter(buffer, fieldnames=fieldnames)
-        writer.writeheader()
-        writer.writerows(rows)
-        return self.put_object(key, buffer.getvalue().encode("utf-8"))

infrastructure/postgres/config.py

@@ -1,33 +0,0 @@
-from dataclasses import dataclass
-from typing import Mapping
-
-
-@dataclass(frozen=True)
-class PostgresConfig:
-    host: str
-    port: int
-    username: str
-    password: str
-    database: str
-    driver: str = "psycopg2"
-    pool_size: int = 3
-    max_overflow: int = 5
-    pool_pre_ping: bool = True
-    pool_recycle: int = 300
-
-    def url(self) -> str:
-        return (
-            f"postgresql+{self.driver}://"
-            f"{self.username}:{self.password}@{self.host}:{self.port}/{self.database}"
-        )
-
-    @classmethod
-    def from_env(cls, env: Mapping[str, str]) -> "PostgresConfig":
-        return cls(
-            host=env["POSTGRES_HOST"],
-            port=int(env["POSTGRES_PORT"]),
-            username=env["POSTGRES_USERNAME"],
-            password=env["POSTGRES_PASSWORD"],
-            database=env["POSTGRES_DATABASE"],
-            driver=env.get("POSTGRES_DRIVER", "psycopg2"),
-        )

infrastructure/postgres/engine.py

@@ -1,18 +0,0 @@
-from sqlalchemy.engine import Engine
-from sqlmodel import Session, create_engine
-
-from infrastructure.postgres.config import PostgresConfig
-
-
-def make_engine(config: PostgresConfig) -> Engine:
-    return create_engine(
-        config.url(),
-        pool_size=config.pool_size,
-        max_overflow=config.max_overflow,
-        pool_pre_ping=config.pool_pre_ping,
-        pool_recycle=config.pool_recycle,
-    )
-
-
-def make_session(engine: Engine) -> Session:
-    return Session(engine)

infrastructure/postgres/subtask_table.py

@@ -1,21 +0,0 @@
-from datetime import datetime, timezone
-from typing import ClassVar, Optional
-from uuid import UUID, uuid4
-
-from sqlmodel import Field, SQLModel
-
-
-class SubTaskRow(SQLModel, table=True):
-    __tablename__: ClassVar[str] = "sub_task"  # pyright: ignore[reportIncompatibleVariableOverride]
-
-    id: UUID = Field(default_factory=uuid4, primary_key=True, index=True)
-    task_id: UUID = Field(foreign_key="tasks.id")
-    job_started: Optional[datetime] = None
-    job_completed: Optional[datetime] = None
-    status: str = Field(default="waiting")
-    inputs: Optional[str] = None
-    outputs: Optional[str] = None
-    cloud_logs_url: Optional[str] = None
-    updated_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc)
-    )

infrastructure/postgres/task_table.py

@@ -1,36 +0,0 @@
-from datetime import datetime, timezone
-from typing import ClassVar, Optional
-from uuid import UUID, uuid4
-
-from sqlalchemy import Column
-from sqlalchemy import Enum as SAEnum
-from sqlmodel import Field, SQLModel
-
-from domain.tasks.tasks import Source
-
-
-class TaskRow(SQLModel, table=True):
-    __tablename__: ClassVar[str] = "tasks"  # pyright: ignore[reportIncompatibleVariableOverride]
-
-    id: UUID = Field(default_factory=uuid4, primary_key=True, index=True)
-    task_source: str
-    job_started: Optional[datetime] = None
-    job_completed: Optional[datetime] = None
-    status: str = Field(default="waiting")
-    service: Optional[str] = None
-    updated_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc)
-    )
-
-    source: Optional[Source] = Field(
-        default=None,
-        sa_column=Column(
-            SAEnum(
-                Source,
-                name="source",
-                values_callable=lambda cls: [m.value for m in cls],  # pyright: ignore[reportUnknownLambdaType, reportUnknownMemberType, reportUnknownVariableType]
-            ),
-            nullable=True,
-        ),
-    )
-    source_id: Optional[str] = None

infrastructure/s3_client.py

@@ -1,22 +0,0 @@
-from typing import Any
-
-
-class S3Client:
-    def __init__(self, boto_s3_client: Any, bucket: str) -> None:
-        self._client = boto_s3_client
-        self._bucket = bucket
-
-    @property
-    def bucket(self) -> str:
-        return self._bucket
-
-    def get_object(self, key: str) -> bytes:
-        response: dict[str, Any] = self._client.get_object(
-            Bucket=self._bucket, Key=key
-        )
-        body: bytes = response["Body"].read()
-        return body
-
-    def put_object(self, key: str, body: bytes) -> str:
-        self._client.put_object(Bucket=self._bucket, Key=key, Body=body)
-        return f"s3://{self._bucket}/{key}"

infrastructure/s3_uri.py

@@ -1,25 +0,0 @@
-from urllib.parse import unquote
-
-
-def parse_s3_uri(s3_uri: str) -> tuple[str, str]:
-    if s3_uri.startswith("s3://"):
-        parts = s3_uri[len("s3://") :].split("/", 1)
-        if len(parts) < 2 or not parts[0] or not parts[1]:
-            raise ValueError("S3 URI must include both a bucket and a key")
-        return parts[0], parts[1]
-
-    if "?" not in s3_uri:
-        raise ValueError(f"Not an s3:// URI and has no query string: {s3_uri!r}")
-    base, query = s3_uri.split("?", 1)
-
-    if "/s3/object/" not in base:
-        raise ValueError(f"Console URL has no '/s3/object/' segment: {s3_uri!r}")
-    bucket = base.split("/s3/object/", 1)[1]
-
-    params: dict[str, str] = {}
-    for item in query.split("&"):
-        if "=" in item:
-            name, value = item.split("=", 1)
-            params[name] = value
-    key = unquote(params.get("prefix", ""))
-    return bucket, key

infrastructure/sqs_client.py

@@ -1,20 +0,0 @@
-import json
-from typing import Any
-
-
-class SqsClient:
-    def __init__(self, boto_sqs_client: Any, queue_url: str) -> None:
-        self._client = boto_sqs_client
-        self._queue_url = queue_url
-
-    @property
-    def queue_url(self) -> str:
-        return self._queue_url
-
-    def send(self, body: dict[str, Any]) -> str:
-        response: dict[str, Any] = self._client.send_message(
-            QueueUrl=self._queue_url,
-            MessageBody=json.dumps(body),
-        )
-        message_id: str = response["MessageId"]
-        return message_id

infrastructure/terraform/lambda/_template/README.md

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

infrastructure/terraform/lambda/postcodeSplitter/main.tf

@@ -38,8 +38,22 @@ module "lambda" {
     {
       STAGE     = var.stage
       LOG_LEVEL = "info"
-      POSTGRES_USERNAME = local.db_credentials.db_assessment_model_username
-      POSTGRES_PASSWORD = local.db_credentials.db_assessment_model_password
+      DB_USERNAME = local.db_credentials.db_assessment_model_username
+      DB_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
     },