mirror of
https://github.com/Sea-Haven-Industries/procurement-ingest.git
synced 2026-09-30 17:43:14 +00:00
47fa35688d
Some checks are pending
Deploy / deploy (push) Waiting to run
The purchase-orders table was migrated to SSE-KMS (alias/seahaven-dynamodb, INFRA-95/M-3) out-of-band, but po_stack never declared the key, so grant_read_write_data did not propagate kms perms. po-email-processor failed ~99.6% of invocations with kms:Decrypt AccessDeniedException, a data-loss outage on the PO ingestion write path. - po_stack: declare encryption_key on purchase-orders (reconciles SSE drift; no-op against the already-encrypted live table) so the existing grants add kms:Decrypt/GenerateDataKey/DescribeKey to EmailProcessor, WebUI, SiteExtractor. - wo_stack: pre-emptive grant_encrypt_decrypt on the WO processor role ahead of the WorkOrders CMK migration (INFRA-6); tables left unencrypted, no table change. GPT-4.1 cross-review: no blockers.
220 lines
8.3 KiB
Python
220 lines
8.3 KiB
Python
"""CDK stack for the work order email ingestion pipeline."""
|
|
|
|
import aws_cdk as cdk
|
|
from aws_cdk import (
|
|
Duration,
|
|
RemovalPolicy,
|
|
Stack,
|
|
aws_cloudwatch as cloudwatch,
|
|
aws_cloudwatch_actions as cw_actions,
|
|
aws_dynamodb as dynamodb,
|
|
aws_kms as kms,
|
|
aws_lambda as lambda_,
|
|
aws_logs as logs,
|
|
aws_s3 as s3,
|
|
aws_s3_notifications as s3n,
|
|
aws_ses as ses,
|
|
aws_ses_actions as ses_actions,
|
|
aws_secretsmanager as secretsmanager,
|
|
aws_sns as sns,
|
|
aws_sqs as sqs,
|
|
aws_ssm as ssm,
|
|
)
|
|
from constructs import Construct
|
|
|
|
|
|
class WorkorderIngestStack(Stack):
|
|
def __init__(self, scope: Construct, construct_id: str, **kwargs):
|
|
super().__init__(scope, construct_id, **kwargs)
|
|
|
|
# --- S3 bucket for raw emails ---
|
|
email_bucket = s3.Bucket(
|
|
self,
|
|
"EmailBucket",
|
|
bucket_name=f"workorder-ingest-emails-{self.account}",
|
|
removal_policy=RemovalPolicy.RETAIN,
|
|
lifecycle_rules=[
|
|
s3.LifecycleRule(expiration=Duration.days(90)),
|
|
],
|
|
)
|
|
|
|
# --- DynamoDB tables ---
|
|
work_orders_table = dynamodb.Table(
|
|
self,
|
|
"WorkOrdersTable",
|
|
table_name="WorkOrders",
|
|
partition_key=dynamodb.Attribute(
|
|
name="work_order_id",
|
|
type=dynamodb.AttributeType.STRING,
|
|
),
|
|
billing_mode=dynamodb.BillingMode.PAY_PER_REQUEST,
|
|
removal_policy=RemovalPolicy.RETAIN,
|
|
)
|
|
# site-code-index and status-index GSIs removed 2026-06-03 (audit M-20):
|
|
# 0 reads in 30d against ~50k WCU each of write amplification. Re-add if
|
|
# a site-code or status query path ships.
|
|
|
|
comments_table = dynamodb.Table(
|
|
self,
|
|
"CommentsTable",
|
|
table_name="WorkOrderComments",
|
|
partition_key=dynamodb.Attribute(
|
|
name="work_order_id",
|
|
type=dynamodb.AttributeType.STRING,
|
|
),
|
|
sort_key=dynamodb.Attribute(
|
|
name="comment_id",
|
|
type=dynamodb.AttributeType.STRING,
|
|
),
|
|
billing_mode=dynamodb.BillingMode.PAY_PER_REQUEST,
|
|
removal_policy=RemovalPolicy.RETAIN,
|
|
)
|
|
|
|
# --- Secrets Manager for Anthropic API key ---
|
|
anthropic_secret = secretsmanager.Secret(
|
|
self,
|
|
"AnthropicApiKey",
|
|
secret_name="workorder-ingest/anthropic-api-key",
|
|
description="Anthropic API key for work order email parsing",
|
|
removal_policy=RemovalPolicy.RETAIN,
|
|
)
|
|
|
|
# --- DLQ for failed async invocations (INFRA-41 / audit H-8) ---
|
|
# SES → S3 → Lambda is async; without an OnFailure destination a failed
|
|
# parse (bad email, transient error) is silently dropped after Lambda's
|
|
# retries. CDK generates the queue name to avoid colliding with the
|
|
# interim CLI-created workorder-email-processor-dlq (removed post-deploy).
|
|
email_processor_dlq = sqs.Queue(
|
|
self,
|
|
"EmailProcessorDlq",
|
|
retention_period=Duration.days(14),
|
|
enforce_ssl=True,
|
|
)
|
|
|
|
# --- Lambda function ---
|
|
email_processor = lambda_.Function(
|
|
self,
|
|
"EmailProcessor",
|
|
function_name="workorder-email-processor",
|
|
runtime=lambda_.Runtime.PYTHON_3_12,
|
|
architecture=lambda_.Architecture.ARM_64,
|
|
handler="handler.handler",
|
|
code=lambda_.Code.from_asset(
|
|
"../lambdas/wo/email_processor",
|
|
bundling=cdk.BundlingOptions(
|
|
image=lambda_.Runtime.PYTHON_3_12.bundling_image,
|
|
command=[
|
|
"bash",
|
|
"-c",
|
|
"pip install --platform manylinux2014_aarch64 --only-binary=:all: "
|
|
"-r requirements.txt -t /asset-output && "
|
|
"cp -r . /asset-output/",
|
|
],
|
|
),
|
|
),
|
|
timeout=Duration.seconds(60),
|
|
memory_size=256,
|
|
log_retention=logs.RetentionDays.TWO_MONTHS,
|
|
dead_letter_queue=email_processor_dlq,
|
|
environment={
|
|
"WORK_ORDERS_TABLE": work_orders_table.table_name,
|
|
"COMMENTS_TABLE": comments_table.table_name,
|
|
"ANTHROPIC_API_KEY_SECRET_ARN": anthropic_secret.secret_arn,
|
|
},
|
|
)
|
|
|
|
# Grant permissions
|
|
email_bucket.grant_read(email_processor)
|
|
work_orders_table.grant_read_write_data(email_processor)
|
|
comments_table.grant_read_write_data(email_processor)
|
|
anthropic_secret.grant_read(email_processor)
|
|
|
|
# Pre-emptive KMS grant on the shared DynamoDB CMK (alias/seahaven-dynamodb,
|
|
# /seahaven/dynamodb/cmk-arn). The WorkOrders/WorkOrderComments tables are
|
|
# NOT yet SSE-KMS encrypted, so this grant is currently unused; it is added
|
|
# ahead of the CMK migration so the processor role does not hit AccessDenied
|
|
# the moment those tables are migrated. The actual table migration + kebab
|
|
# rename is tracked in INFRA-6 (and the set-aside wo_stack CMK WIP); fold the
|
|
# web-ui read grant in there.
|
|
dynamodb_cmk = kms.Key.from_key_arn(
|
|
self,
|
|
"DynamoDbCmk",
|
|
ssm.StringParameter.value_for_string_parameter(
|
|
self, "/seahaven/dynamodb/cmk-arn"
|
|
),
|
|
)
|
|
dynamodb_cmk.grant_encrypt_decrypt(email_processor)
|
|
|
|
# --- Errors alarm (INFRA-41 / audit H-8) ---
|
|
# ALARM-only (no OK action, per the CloudWatch-alarm preference) to the
|
|
# shared site-alerts topic (CMK alias/seahaven-alarm-topics lives on the
|
|
# topic). Any errored invocation in a 5-min window pages.
|
|
alarm_topic = sns.Topic.from_topic_arn(
|
|
self,
|
|
"SiteAlertsTopic",
|
|
f"arn:aws:sns:{self.region}:{self.account}:site-alerts",
|
|
)
|
|
email_processor.metric_errors(
|
|
period=Duration.minutes(5),
|
|
statistic="Sum",
|
|
).create_alarm(
|
|
self,
|
|
"EmailProcessorErrorsAlarm",
|
|
alarm_name="workorder-email-processor-errors",
|
|
alarm_description="workorder-email-processor async invocation errors",
|
|
threshold=0,
|
|
evaluation_periods=1,
|
|
comparison_operator=cloudwatch.ComparisonOperator.GREATER_THAN_THRESHOLD,
|
|
treat_missing_data=cloudwatch.TreatMissingData.NOT_BREACHING,
|
|
).add_alarm_action(cw_actions.SnsAction(alarm_topic))
|
|
|
|
# S3 event notification -> Lambda
|
|
email_bucket.add_event_notification(
|
|
s3.EventType.OBJECT_CREATED,
|
|
s3n.LambdaDestination(email_processor),
|
|
s3.NotificationKeyFilter(prefix="inbound/"),
|
|
)
|
|
|
|
# --- SES Receipt Rule ---
|
|
rule_set = ses.ReceiptRuleSet.from_receipt_rule_set_name(
|
|
self,
|
|
"ExistingRuleSet",
|
|
"INBOUND_MAIL",
|
|
)
|
|
|
|
rule_set.add_rule(
|
|
"WorkorderEmailRule",
|
|
recipients=["apm@int.seahaven.com"],
|
|
actions=[
|
|
ses_actions.S3(
|
|
bucket=email_bucket,
|
|
object_key_prefix="inbound/",
|
|
),
|
|
],
|
|
)
|
|
|
|
# --- Web UI Lambda ---
|
|
web_ui = lambda_.Function(
|
|
self,
|
|
"WebUI",
|
|
function_name="workorder-web-ui",
|
|
runtime=lambda_.Runtime.PYTHON_3_12,
|
|
architecture=lambda_.Architecture.ARM_64,
|
|
handler="handler.handler",
|
|
code=lambda_.Code.from_asset("../lambdas/wo/web_ui"),
|
|
timeout=Duration.seconds(15),
|
|
memory_size=128,
|
|
log_retention=logs.RetentionDays.TWO_MONTHS,
|
|
environment={
|
|
"WORK_ORDERS_TABLE": work_orders_table.table_name,
|
|
"COMMENTS_TABLE": comments_table.table_name,
|
|
},
|
|
)
|
|
|
|
work_orders_table.grant_read_data(web_ui)
|
|
comments_table.grant_read_data(web_ui)
|
|
|
|
# Public Function URL removed 2026-06-08 (INFRA-74 / audit C-5): the
|
|
# unauthenticated FunctionUrlAuthType.NONE URL was deleted out-of-band
|
|
# via CLI. Removing the construct (and its auto-generated Principal:*
|
|
# invoke permission) reconciles IaC with the live state.
|