mirror of
https://github.com/Sea-Haven-Industries/procurement-ingest.git
synced 2026-09-30 16:33:14 +00:00
Adam Moussa
447b0619ad
The From header and any raw-MIME Authentication-Results copies are attacker-forgeable, so a forged email to apm@int.seahaven.com or amazon_po@int.seahaven.com could create or mutate a WO/PO (INFRA-107, CRITICAL). Both S3-triggered email processors now authenticate the sender against the Authentication-Results header SES itself prepends at delivery: only the topmost header is consulted, its authserv-id must be amazonses.com, and it must carry dkim=pass for a domain in the per-pipeline ALLOWED_DKIM_DOMAINS env var (comma-separated, set in CDK so ops can adjust without code changes). Allowlists come from live traffic observed 2026-07-15 on both ingest buckets: WO mail arrives via the apm@ Google Groups forward, which re-signs as seahaven.com (the hxgnsmartcloud.com signature does not survive the forward); PO mail passes for amazon.coupahost.com. amazonses.com also passes on PO mail but is deliberately excluded -- every SES customer's outbound mail passes for it. Every failure path (env var unset, header missing or unparseable, verdict fail, unaligned domain) rejects the email: a structured warning with the reason and S3 key is logged and the record skipped without erroring the invocation, so rejected mail causes no Lambda retries or DLQ messages. Handler signatures and event sources are unchanged. Refs: INFRA-107
360 lines
15 KiB
Python
360 lines
15 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
|
|
|
|
# Operations these tables actually issue (PutItem/UpdateItem/DeleteItem writes,
|
|
# GetItem/Query/BatchGetItem reads). DynamoDB emits ThrottledRequests/SystemErrors
|
|
# keyed by TableName + Operation only, so the CDK *_for_operations helpers (which
|
|
# render a SUM MathExpression across these per-operation metrics) are the correct,
|
|
# non-deprecated way to roll a table up to a single alarmable series.
|
|
_DDB_ALARM_OPERATIONS = [
|
|
dynamodb.Operation.GET_ITEM,
|
|
dynamodb.Operation.BATCH_GET_ITEM,
|
|
dynamodb.Operation.QUERY,
|
|
dynamodb.Operation.SCAN,
|
|
dynamodb.Operation.PUT_ITEM,
|
|
dynamodb.Operation.UPDATE_ITEM,
|
|
dynamodb.Operation.DELETE_ITEM,
|
|
dynamodb.Operation.BATCH_WRITE_ITEM,
|
|
]
|
|
|
|
|
|
def _add_ddb_alarms(scope, id_prefix, table, alarm_name_prefix, alarm_topic):
|
|
"""Add throttle + system-error alarms for a DynamoDB table.
|
|
|
|
Both fire on any non-zero datapoint in a 5-min window. ALARM-only SnsAction
|
|
to site-alerts (no OK action); TreatMissingData NOT_BREACHING.
|
|
"""
|
|
table.metric_throttled_requests_for_operations(
|
|
operations=_DDB_ALARM_OPERATIONS,
|
|
period=Duration.minutes(5),
|
|
statistic="Sum",
|
|
).create_alarm(
|
|
scope,
|
|
f"{id_prefix}ThrottlesAlarm",
|
|
alarm_name=f"{alarm_name_prefix}-throttles",
|
|
alarm_description=f"{alarm_name_prefix} DynamoDB throttled requests",
|
|
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))
|
|
|
|
table.metric_system_errors_for_operations(
|
|
operations=_DDB_ALARM_OPERATIONS,
|
|
period=Duration.minutes(5),
|
|
statistic="Sum",
|
|
).create_alarm(
|
|
scope,
|
|
f"{id_prefix}SystemErrorsAlarm",
|
|
alarm_name=f"{alarm_name_prefix}-system-errors",
|
|
alarm_description=f"{alarm_name_prefix} DynamoDB server-side (5xx) 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))
|
|
|
|
|
|
class WorkorderIngestStack(Stack):
|
|
def __init__(self, scope: Construct, construct_id: str, **kwargs):
|
|
super().__init__(scope, construct_id, **kwargs)
|
|
|
|
# --- Shared alarm SNS topic (site-alerts) ---
|
|
# Imported once near the top so every alarm in this stack reuses the same
|
|
# Topic construct instance (avoids duplicate logical IDs). ALARM-only
|
|
# SnsAction; no OK action, per the CloudWatch-alarm preference. The
|
|
# topic's CMK (alias/seahaven-alarm-topics) lives on the topic itself.
|
|
alarm_topic = sns.Topic.from_topic_arn(
|
|
self,
|
|
"SiteAlertsTopic",
|
|
f"arn:aws:sns:{self.region}:{self.account}:site-alerts",
|
|
)
|
|
|
|
# --- S3 bucket for raw emails ---
|
|
email_bucket = s3.Bucket(
|
|
self,
|
|
"EmailBucket",
|
|
bucket_name=f"workorder-ingest-emails-{self.account}",
|
|
block_public_access=s3.BlockPublicAccess.BLOCK_ALL,
|
|
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,
|
|
# Fail-closed sender auth (INFRA-107): the handler only
|
|
# accepts mail whose SES-stamped Authentication-Results
|
|
# header carries dkim=pass for one of these domains. APM
|
|
# mail arrives via the apm@ Google Groups forward, which
|
|
# re-signs as seahaven.com (observed on live traffic
|
|
# 2026-07-15: "dkim=pass header.i=@seahaven.com"; the
|
|
# original hxgnsmartcloud.com signature does not survive
|
|
# the forward). Unset/empty ⇒ the handler rejects all mail.
|
|
"ALLOWED_DKIM_DOMAINS": "seahaven.com",
|
|
},
|
|
)
|
|
|
|
# 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. Any errored invocation in a 5-min window pages.
|
|
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))
|
|
|
|
# --- Throttles alarm: workorder-email-processor ---
|
|
# Any throttled invocation (concurrency cap hit) in a 5-min window pages.
|
|
# ALARM-only to site-alerts; no OK action; NOT_BREACHING when no data.
|
|
email_processor.metric_throttles(
|
|
period=Duration.minutes(5),
|
|
statistic="Sum",
|
|
).create_alarm(
|
|
self,
|
|
"EmailProcessorThrottlesAlarm",
|
|
alarm_name="workorder-email-processor-throttles",
|
|
alarm_description="workorder-email-processor invocation throttles",
|
|
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))
|
|
|
|
# --- Duration alarm: workorder-email-processor (orphan adoption) ---
|
|
# Adopts the orphaned CLI alarm Lambda-Duration-workorder-email-processor
|
|
# under the repo's <fn>-duration naming (NEW logical name → no deploy
|
|
# collision; delete the orphan post-deploy). p95 /
|
|
# 45000 ms (75% of the 60s timeout) / eval 3 of which 2 datapoints —
|
|
# tighter than the orphan's Maximum>=48000 / 1-of-1.
|
|
email_processor.metric_duration(
|
|
period=Duration.minutes(5),
|
|
statistic="p95",
|
|
).create_alarm(
|
|
self,
|
|
"EmailProcessorDurationAlarm",
|
|
alarm_name="workorder-email-processor-duration",
|
|
alarm_description="workorder-email-processor p95 duration approaching the 60s timeout",
|
|
threshold=45000,
|
|
evaluation_periods=3,
|
|
datapoints_to_alarm=2,
|
|
comparison_operator=cloudwatch.ComparisonOperator.GREATER_THAN_OR_EQUAL_TO_THRESHOLD,
|
|
treat_missing_data=cloudwatch.TreatMissingData.NOT_BREACHING,
|
|
).add_alarm_action(cw_actions.SnsAction(alarm_topic))
|
|
|
|
# --- DLQ messages-present alarm (INFRA-41 / audit H-8) ---
|
|
# The errors alarm above fires on any errored invocation, but a message
|
|
# only lands in the DLQ after Lambda exhausts its async retries and gives
|
|
# up — i.e. a genuinely dropped email. ALARM-only (no OK action) to the
|
|
# same shared site-alerts topic. MAXIMUM over a 5-min window so a single
|
|
# visible message pages even if it is later consumed/redriven.
|
|
email_processor_dlq.metric_approximate_number_of_messages_visible(
|
|
period=Duration.minutes(5),
|
|
statistic="Maximum",
|
|
).create_alarm(
|
|
self,
|
|
"EmailProcessorDlqMessagesAlarm",
|
|
alarm_name="workorder-email-processor-dlq-messages",
|
|
alarm_description="workorder-email-processor DLQ has visible messages (dropped emails)",
|
|
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)
|
|
|
|
# --- DynamoDB throttle + system-error alarms ---
|
|
# ThrottledRequests / SystemErrors emit at TableName + Operation only
|
|
# (verified against live CloudWatch: no TableName-only rollup exists, and
|
|
# metric_throttled_requests is deprecated/invalid in aws-cdk-lib 2.259.0).
|
|
# Each table currently has zero throttle/error datapoints, so the series
|
|
# only materialise on first occurrence — NOT_BREACHING keeps them OK until
|
|
# then.
|
|
_add_ddb_alarms(
|
|
self, "WorkOrdersTable", work_orders_table, "WorkOrders", alarm_topic
|
|
)
|
|
_add_ddb_alarms(
|
|
self, "WorkOrderComments", comments_table, "WorkOrderComments", alarm_topic
|
|
)
|
|
|
|
# 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.
|