Compare commits

...

9 commits

Author SHA1 Message Date
Daniel Roth
8a7be50eae
Merge 3dc14480e9 into 133190f093 2026-03-23 10:31:35 +00:00
Daniel Roth
3dc14480e9 rename evidence file getter method 2026-03-23 10:31:30 +00:00
Daniel Roth
cd514b6e5d add and implement cotality_client 2026-03-23 10:29:42 +00:00
Daniel Roth
b8c0c9ea65 move playwright process to separate file 2026-03-23 09:56:53 +00:00
Daniel Roth
4d641af0c1 extract token from localStorage after logging in 2026-03-23 09:36:57 +00:00
Daniel Roth
defce34263 Merge branch 'main' into feature/pashub-to-ara 2026-03-23 09:28:02 +00:00
KhalimCK
133190f093
Merge pull request #914 from Hestia-Homes/feature/ml-prediction-buckets
Feature/ml prediction buckets
2026-03-20 13:00:22 +00:00
Khalim Conn-Kowlessar
b64ce2c7fe added new buckets for carbon and heat to terraform 2026-03-20 12:55:33 +00:00
Khalim Conn-Kowlessar
639f46df09 created predictions buckets for carbon and heat, added iam permissions 2026-03-20 09:59:19 +00:00
7 changed files with 144 additions and 70 deletions

View file

@ -77,6 +77,9 @@ jobs:
echo "::set-output name=hotwater_kwh_predictions_bucket::${{ secrets[format('{0}_HOTWATER_KWH_PREDICTIONS_BUCKET', github.ref_name)] }}"
echo "::set-output name=energy_asessments_bucket::${{ secrets[format('{0}_ENERGY_ASSESSMENTS_BUCKET', github.ref_name)] }}"
echo "::set-output name=google_solar_api_key::${{ secrets[format('{0}_GOOGLE_SOLAR_API_KEY', github.ref_name)] }}"
echo "::set-output name=sap_baseline_predictions_bucket::${{ secrets[format('{0}_SAP_BASELINE_PREDICTIONS_BUCKET', github.ref_name)] }}"
echo "::set-output name=carbon_baseline_predictions_bucket::${{ secrets[format('{0}_CARBON_BASELINE_PREDICTIONS_BUCKET', github.ref_name)] }}"
echo "::set-output name=heat_baseline_predictions_bucket::${{ secrets[format('{0}_HEAT_BASELINE_PREDICTIONS_BUCKET', github.ref_name)] }}"
- name: Setup Docker
uses: docker/setup-buildx-action@v1
@ -129,6 +132,9 @@ jobs:
DB_NAME: ${{ steps.set_db_credentials.outputs.db_name }}
ECR_URI: ${{ steps.set_ecr_credentials.outputs.ecr_uri }}
GITHUB_SHA: ${{ github.sha }}
SAP_BASELINE_PREDICTIONS_BUCKET: ${{ steps.set_api_secrets.outputs.sap_baseline_predictions_bucket }}
CARBON_BASELINE_PREDICTIONS_BUCKET: ${{ steps.set_api_secrets.outputs.carbon_baseline_predictions_bucket }}
HEAT_BASELINE_PREDICTIONS_BUCKET: ${{ steps.set_api_secrets.outputs.heat_baseline_predictions_bucket }}
run: |
# Fetch database credentials from AWS Secrets Manager
SECRET_VALUE=$(aws secretsmanager get-secret-value --secret-id ${{ github.ref_name }}/assessment_model/db_credentials --query SecretString)

View file

@ -1,54 +1,26 @@
from typing import Any, Dict, Mapping
from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
from typing import Any, List, Mapping
from backend.pashub_fetcher.cotality_client import CotalityClient
from backend.pashub_fetcher.token_getter import get_token_from_local_storage
from utils.logger import setup_logger
logger = setup_logger()
def handler(event: Mapping[str, Any], context: Any) -> Dict[str, str]:
logger.info("Starting Playwright flow")
def handler(event: Mapping[str, Any], context: Any) -> None:
pas_hub_email = "random@test.com"
pas_hub_password = "my_fake_password"
email = "random@test.com"
password = "my_fake_password"
try:
token: str = get_token_from_local_storage(pas_hub_email, pas_hub_password)
logger.info(f"Token extracted successfully: {token}")
except:
logger.error("Error getting auth token from Pas Hub")
raise
with sync_playwright() as p:
browser = p.chromium.launch(
headless=True,
args=["--no-sandbox", "--disable-dev-shm-usage"],
)
page = browser.new_page()
client = CotalityClient(token=token)
uprn = "100061885568" # TODO: get from request body
try:
logger.info("Navigating to site...")
page.goto("https://pashub.net/", timeout=30000)
logger.info("Filling login form...")
page.fill("#email", email)
page.fill("#password", password)
logger.info("Submitting login...")
page.click("#btn-login")
page.wait_for_timeout(3000)
if "login" in page.url.lower():
logger.error("Login failed (still on login page)")
return {"status": "error", "message": "Login failed"}
logger.info(f"Login likely successful. URL: {page.url}")
return {"status": "ok"}
except PlaywrightTimeoutError as e:
logger.error(f"Timeout during login flow: {str(e)}")
return {"status": "error", "message": "Timeout during login"}
except Exception as e:
logger.error(f"Unexpected error: {str(e)}")
return {"status": "error", "message": str(e)}
finally:
browser.close()
saved_files: List[str] = client.get_evidence_files_by_uprn(uprn=uprn)
print(f"saved {len(saved_files)} files")

View file

@ -0,0 +1,54 @@
from playwright.sync_api import sync_playwright, TimeoutError as PlaywrightTimeoutError
from utils.logger import setup_logger
logger = setup_logger()
def get_token_from_local_storage(email: str, password: str) -> str:
logger.info("Starting Playwright flow")
with sync_playwright() as p:
browser = p.chromium.launch(
headless=True,
args=["--no-sandbox", "--disable-dev-shm-usage"],
)
page = browser.new_page()
try:
logger.info("Navigating to site...")
page.goto("https://pashub.net/", timeout=30000)
logger.info("Filling login form...")
page.fill("#email", email)
page.fill("#password", password)
logger.info("Submitting login...")
page.click("#btn-login")
page.wait_for_timeout(3000)
if "login" in page.url.lower():
raise Exception("Login failed (still on login page)")
logger.info(f"Login likely successful. URL: {page.url}")
token = page.evaluate(
"""() => {
return localStorage.getItem('token');
}"""
)
if not token:
raise Exception("Login succeeded but no token found")
return token
except PlaywrightTimeoutError as e:
raise Exception(f"Timeout during login flow: {str(e)}")
except Exception as e:
raise Exception(f"Unexpected error: {str(e)}")
finally:
browser.close()

View file

@ -5,7 +5,7 @@ data "terraform_remote_state" "shared" {
backend = "s3"
config = {
bucket = "assessment-model-terraform-state"
key = "env:/${var.stage}/terraform.tfstate"
key = "env:/${var.stage}/terraform.tfstate"
region = "eu-west-2"
}
}
@ -14,7 +14,7 @@ data "terraform_remote_state" "engine" {
backend = "s3"
config = {
bucket = "ara-engine-terraform-state",
key = "env:/${var.stage}/terraform.tfstate"
key = "env:/${var.stage}/terraform.tfstate"
region = "eu-west-2"
}
}
@ -23,7 +23,7 @@ data "terraform_remote_state" "categorisation" {
backend = "s3"
config = {
bucket = "categorisation-terraform-state",
key = "env:/${var.stage}/terraform.tfstate"
key = "env:/${var.stage}/terraform.tfstate"
region = "eu-west-2"
}
}
@ -43,26 +43,26 @@ locals {
# FastAPI Lambda + API Gateway
############################################
module "fastapi" {
source = "../../modules/lambda_with_api_gateway"
source = "../../modules/lambda_with_api_gateway"
name = "fastapi"
stage = var.stage
source_dir = "${path.root}/../../../../"
handler = "backend.app.main.handler"
runtime = "python3.11"
timeout = 600
memory_size = 512
artifact_bucket = data.terraform_remote_state.shared.outputs.ara_fast_api_state_bucket
name = "fastapi"
stage = var.stage
source_dir = "${path.root}/../../../../"
handler = "backend.app.main.handler"
runtime = "python3.11"
timeout = 600
memory_size = 512
artifact_bucket = data.terraform_remote_state.shared.outputs.ara_fast_api_state_bucket
requirements_file = "${path.root}/../../../../backend/app/requirements/requirements.txt"
domain_name = "api.${var.domain_name}"
environment = {
ENVIRONMENT = var.stage
API_KEY = var.api_key
SECRET_KEY = var.secret_key
ENVIRONMENT = var.stage
API_KEY = var.api_key
SECRET_KEY = var.secret_key
# DOMAIN_NAME = var.domain_name
EPC_AUTH_TOKEN = var.epc_auth_token
EPC_AUTH_TOKEN = var.epc_auth_token
GOOGLE_SOLAR_API_KEY = var.google_solar_api_key
DB_HOST = var.db_host
@ -71,14 +71,17 @@ module "fastapi" {
DB_USERNAME = local.db_credentials.db_assessment_model_username
DB_PASSWORD = local.db_credentials.db_assessment_model_password
PLAN_TRIGGER_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_plan_trigger_bucket_name
DATA_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_sap_data_bucket_name
SAP_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_sap_predictions_bucket_name
CARBON_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_carbon_predictions_bucket_name
HEAT_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_heat_predictions_bucket_name
HEATING_KWH_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_heating_kwh_predictions_bucket_name
HOTWATER_KWH_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_hotwater_kwh_predictions_bucket_name
ENERGY_ASSESSMENTS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_energy_assessments_bucket_name
PLAN_TRIGGER_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_plan_trigger_bucket_name
DATA_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_sap_data_bucket_name
SAP_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_sap_predictions_bucket_name
CARBON_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_carbon_predictions_bucket_name
HEAT_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_heat_predictions_bucket_name
HEATING_KWH_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_heating_kwh_predictions_bucket_name
HOTWATER_KWH_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_hotwater_kwh_predictions_bucket_name
ENERGY_ASSESSMENTS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_energy_assessments_bucket_name
SAP_BASELINE_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_sap_baseline_predictions_bucket_name
CARBON_BASELINE_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_carbon_baseline_predictions_bucket_name
HEAT_BASELINE_PREDICTIONS_BUCKET = data.terraform_remote_state.shared.outputs.retrofit_heat_baseline_predictions_bucket_name
ENGINE_SQS_URL = data.terraform_remote_state.engine.outputs.ara_engine_queue_url
CATEGORISATION_SQS_URL = data.terraform_remote_state.categorisation.outputs.categorisation_queue_url
@ -121,4 +124,4 @@ resource "aws_iam_role_policy_attachment" "fastapi_sqs_send" {
resource "aws_iam_role_policy_attachment" "fastapi_s3_read_and_write" {
role = module.fastapi.role_name
policy_arn = data.terraform_remote_state.shared.outputs.fast_api_s3_read_and_write_arn
}
}

View file

@ -239,6 +239,33 @@ module "retrofit_sap_baseline_predictions" {
allowed_origins = var.allowed_origins
}
output "retrofit_sap_baseline_predictions_bucket_name" {
value = module.retrofit_sap_baseline_predictions.bucket_name
description = "Name of the retrofit SAP baseline predictions bucket"
}
module "retrofit_carbon_baseline_predictions" {
source = "../modules/s3"
bucketname = "retrofit-carbon-baseline-predictions-${var.stage}"
allowed_origins = var.allowed_origins
}
output "retrofit_carbon_baseline_predictions_bucket_name" {
value = module.retrofit_carbon_baseline_predictions.bucket_name
description = "Name of the retrofit carbon baseline predictions bucket"
}
module "retrofit_heat_baseline_predictions" {
source = "../modules/s3"
bucketname = "retrofit-heat-baseline-predictions-${var.stage}"
allowed_origins = var.allowed_origins
}
output "retrofit_heat_baseline_predictions_bucket_name" {
value = module.retrofit_heat_baseline_predictions.bucket_name
description = "Name of the retrofit heat baseline predictions bucket"
}
// We make this bucket presignable, because we want to generate download links for the frontend
module "retrofit_energy_assessments" {
source = "../modules/s3_presignable_bucket"
@ -526,7 +553,10 @@ module "engine_s3_read_and_write" {
"arn:aws:s3:::${module.retrofit_heat_predictions.bucket_name}",
"arn:aws:s3:::${module.retrofit_heating_kwh_predictions.bucket_name}",
"arn:aws:s3:::${module.retrofit_hotwater_kwh_predictions.bucket_name}",
"arn:aws:s3:::${module.retrofit_energy_assessments.bucket_name}"
"arn:aws:s3:::${module.retrofit_energy_assessments.bucket_name}",
"arn:aws:s3:::${module.retrofit_sap_baseline_predictions.bucket_name}",
"arn:aws:s3:::${module.retrofit_carbon_baseline_predictions.bucket_name}",
"arn:aws:s3:::${module.retrofit_heat_baseline_predictions.bucket_name}"
]
actions = ["s3:*"]
resource_paths = ["/*"]

View file

@ -28,6 +28,9 @@ provider:
HOTWATER_KWH_PREDICTIONS_BUCKET: ${env:HOTWATER_KWH_PREDICTIONS_BUCKET}
ENERGY_ASSESSMENTS_BUCKET: ${env:ENERGY_ASSESSMENTS_BUCKET}
GOOGLE_SOLAR_API_KEY: ${env:GOOGLE_SOLAR_API_KEY}
SAP_BASELINE_PREDICTIONS_BUCKET: ${env:SAP_BASELINE_PREDICTIONS_BUCKET}
CARBON_BASELINE_PREDICTIONS_BUCKET: ${env:CARBON_BASELINE_PREDICTIONS_BUCKET}
HEAT_BASELINE_PREDICTIONS_BUCKET: ${env:HEAT_BASELINE_PREDICTIONS_BUCKET}
ENGINE_SQS_URL:
Ref: EngineQueue
# hardcode the categorisation queue for now as it's created in terraform
@ -177,3 +180,9 @@ resources:
- arn:aws:s3:::${env:HEATING_KWH_PREDICTIONS_BUCKET}/*
- arn:aws:s3:::${env:HOTWATER_KWH_PREDICTIONS_BUCKET}
- arn:aws:s3:::${env:HOTWATER_KWH_PREDICTIONS_BUCKET}/*
- arn:aws:s3:::${env:SAP_BASELINE_PREDICTIONS_BUCKET}
- arn:aws:s3:::${env:SAP_BASELINE_PREDICTIONS_BUCKET}/*
- arn:aws:s3:::${env:CARBON_BASELINE_PREDICTIONS_BUCKET}
- arn:aws:s3:::${env:CARBON_BASELINE_PREDICTIONS_BUCKET}/*
- arn:aws:s3:::${env:HEAT_BASELINE_PREDICTIONS_BUCKET}
- arn:aws:s3:::${env:HEAT_BASELINE_PREDICTIONS_BUCKET}/*