mirror of
https://github.com/Sea-Haven-Industries/procurement-ingest.git
synced 2026-09-30 11:53:13 +00:00
f8eb18f02b
Some checks are pending
Deploy / deploy (push) Waiting to run
The ~379 lines po_stack.py and wo_stack.py defined identically (DynamoDB alarms, the sender-auth-rejected metric filter + alarm, the standard per-Lambda alarm set, the Bedrock InvokeModel grant, the raw-email bucket, the async DLQ, the template-fallback-rate math alarm) move into cdk/common.py. Every helper is a PLAIN function taking (scope, id, ...), called with each stack's own Stack as scope and the exact literal construct ids used inline before, so every synthesized logical ID is byte-stable. A Construct subclass would reparent the tree and make CloudFormation attempt to replace the RETAIN-protected purchase-orders/WorkOrders tables and named buckets -- data loss -- so it is forbidden. Per-function alarm variance (PO p99 vs WO p95 duration, po-web-ui throttles+duration only, site-extractor no DLQ alarm, workorder-web-ui zero alarms) is preserved through call-site arguments, not baked into the helpers. make_bedrock_invoke_statement derives the inference-profile and us-east-1 foundation-model ARNs from Stack.of(scope).account/.region instead of the hardcoded 328440206208/us-east-1 literals. The environment stays account-agnostic (region-only), so the account resolves to the AWS::AccountId pseudo-parameter: the derived ARN resolves at deploy to the same ARN the literal named in-account (a benign in-place IAM policy update, never a replacement) and is account-portable rather than pinned to the frozen management account. The account= pin evaluated for cdk.Environment was deliberately NOT added: resolving every account-derived value (bucket names, Lambda::Permission source account, SNS action ARN) to literals makes CloudFormation flag the RETAIN email buckets as requiring replacement against the deployed account-agnostic templates -- a data-loss risk that outranks the pin, which buys nothing (the resolved values are unchanged). Also: net-new CfnOutputs for the five Lambda function ARNs and the owned/consumed table names, exact-pin constructs==10.6.0, and fix the stale aws-cdk-lib 2.259.0 -> 2.261.0 version comment. The common.py extraction is zero-cdk-diff on both stacks (byte-stable logical IDs, no asset/property change); the only deltas versus deployed are the intended benign Bedrock IAM in-place update and the additive CfnOutputs. Mandatory GPT-4.1 cross-family review ran on the Bedrock IAM move; its BLOCK was a verified false positive (it read AWS::AccountId as a wildcard -- it is a deploy-time-resolved concrete value naming one account and one inference-profile, region is pinned us-east-1, and the grant is strictly more least-privilege-correct than the hardcoded literal).
403 lines
19 KiB
Python
403 lines
19 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_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,
|
|
)
|
|
from constructs import Construct
|
|
|
|
import common
|
|
|
|
|
|
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 = common.make_email_bucket(
|
|
self, "EmailBucket", "workorder-ingest-emails"
|
|
)
|
|
|
|
# --- 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,
|
|
)
|
|
|
|
# --- Anthropic API key secret removed (Bedrock migration) ---
|
|
# Parsing moved from the Anthropic API to the Bedrock inference profile
|
|
# us.anthropic.claude-haiku-4-5-20251001-v1:0, so no provider API key is
|
|
# needed. The old secret "workorder-ingest/anthropic-api-key" had
|
|
# RemovalPolicy.RETAIN, so it is ORPHANED (not deleted) by this change:
|
|
# delete it manually post-deploy and revoke the stored key at Anthropic.
|
|
|
|
# --- 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 = common.make_processor_dlq(self, "EmailProcessorDlq")
|
|
|
|
# --- 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",
|
|
exclude=["**/__pycache__/**", "**/tests/**", "**/package/**"],
|
|
bundling=cdk.BundlingOptions(
|
|
image=lambda_.Runtime.PYTHON_3_12.bundling_image,
|
|
command=[
|
|
"bash",
|
|
"-c",
|
|
# pip step removed in Phase 7: requirements.txt is now empty
|
|
# (boto3 comes from the Lambda runtime), so nothing is installed
|
|
# and the manylinux pin has nothing to pin. cp-only is safe.
|
|
# shared/*.py ships the four modules extracted to
|
|
# lambdas/shared/ (Phase 3): ses_auth, web_ui_auth,
|
|
# email_parsing, emf. Flat cp keeps the bare-name
|
|
# imports (e.g. `from ses_auth import ...`) resolving
|
|
# unchanged in /asset-output.
|
|
"cp wo/email_processor/*.py /asset-output/ && "
|
|
"cp shared/*.py /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,
|
|
"BEDROCK_MODEL_ID": "us.anthropic.claude-haiku-4-5-20251001-v1:0",
|
|
# 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)
|
|
|
|
# --- Bedrock InvokeModel grant ---
|
|
# The us.* inference profile can route cross-region, so the grant MUST
|
|
# cover both the inference-profile ARN AND the per-region foundation-model
|
|
# ARNs (empty account field) for every region the profile can reach
|
|
# (us-east-1/us-east-2/us-west-2). A profile-only grant AccessDenies at
|
|
# runtime whenever the profile routes to a region whose foundation-model
|
|
# ARN is not allowed.
|
|
email_processor.add_to_role_policy(common.make_bedrock_invoke_statement(self))
|
|
|
|
# NOTE: The pre-emptive grant_encrypt_decrypt on the shared DynamoDB CMK
|
|
# (alias/seahaven-dynamodb) was removed (security sweep 2026-06-17). The
|
|
# WorkOrders/WorkOrderComments tables are NOT SSE-KMS encrypted with that
|
|
# CMK, so the grant was unused for these tables yet handed
|
|
# wo-email-processor kms:Decrypt on the CMK that also protects the
|
|
# purchase-orders table (cross-stack decrypt reach). Re-add this grant only
|
|
# as part of the actual CMK migration of these tables (INFRA-6), at which
|
|
# point grant_read_write_data on the (then encrypted) tables would propagate
|
|
# the needed key permissions automatically.
|
|
|
|
# --- Standard per-Lambda alarms: workorder-email-processor ---
|
|
# errors (INFRA-41 / audit H-8), throttles, DLQ-visible-messages (dropped
|
|
# emails), and a p95 duration alarm (orphan adoption of the CLI
|
|
# Lambda-Duration-workorder-email-processor under <fn>-duration naming,
|
|
# 45000 ms = 75% of the 60s timeout, eval 3 / dp 2). p95 (NOT p99) is the
|
|
# WO-specific duration statistic. All ALARM-only to site-alerts.
|
|
common.add_standard_lambda_alarms(
|
|
self,
|
|
"EmailProcessor",
|
|
email_processor,
|
|
"workorder-email-processor",
|
|
alarm_topic,
|
|
duration_statistic="p95",
|
|
errors=True,
|
|
dlq=email_processor_dlq,
|
|
descriptions={
|
|
"errors": "workorder-email-processor async invocation errors",
|
|
"throttles": "workorder-email-processor invocation throttles",
|
|
"dlq": "workorder-email-processor DLQ has visible messages (dropped emails)",
|
|
"duration": "workorder-email-processor p95 duration approaching the 60s timeout",
|
|
},
|
|
)
|
|
|
|
# --- Sender-auth rejection alarm (INFRA-107) ---
|
|
# A rejected email (bad/unaligned DKIM verdict) returns normally, so it
|
|
# produces NO Lambda error, NO DLQ message and NO retry -- only a
|
|
# `sender_auth_rejected` warning log. The WO allowlist trusts dkim=pass
|
|
# for seahaven.com on the assumption the apm@ forward re-signs there; if
|
|
# that assumption is wrong (e.g. a Gmail auto-forward re-signs under a
|
|
# different domain), 100% of legitimate work-order mail is silently
|
|
# dropped. This metric filter + alarm turns those warnings into a paging
|
|
# signal so a false-reject storm surfaces instead of a silent outage.
|
|
common.add_sender_auth_rejected_alarm(
|
|
self, "EmailProcessor", "workorder-email-processor", alarm_topic
|
|
)
|
|
|
|
# --- Template fallback-rate alarm: workorder-email-processor ---
|
|
# The processor tries a deterministic template parse first and only calls
|
|
# the Bedrock AI extractor on a miss/invalid. A sustained rise in the
|
|
# ai_fallback share signals Hexagon template drift (coverage collapse).
|
|
# EMF metric Seahaven/WorkorderIngest/ParseOutcome, dimensioned by
|
|
# ParseMethod (template|ai_fallback). 15-min periods (deliberate deviation
|
|
# from the 5-min house style) accumulate a stable denominator at the low
|
|
# ~760/day volume; FILL(0) + a >=10-sample volume floor prevent
|
|
# low-volume false pages and INSUFFICIENT_DATA. ALARM-only SnsAction to
|
|
# site-alerts, no OK action, NOT_BREACHING -- matching the stack idiom.
|
|
# rejected_included=True: the WO expression folds ai_fallback_rejected
|
|
# (rej) into BOTH numerator and denominator -- a drift outage whose AI
|
|
# output also fails the gate must still count as fallback, otherwise it
|
|
# would LOWER the observed rate while silently dropping mail. (Contrast
|
|
# PO, which excludes rej to avoid a pre-call double-count.)
|
|
common.make_fallback_rate_alarm(
|
|
self,
|
|
"EmailProcessorTemplateFallbackRateAlarm",
|
|
namespace="Seahaven/WorkorderIngest",
|
|
alarm_topic=alarm_topic,
|
|
alarm_name="workorder-email-processor-template-fallback-rate",
|
|
alarm_description=(
|
|
"workorder-email-processor deterministic-template coverage "
|
|
"collapse: >15% of parses fell back to the Bedrock AI extractor"
|
|
),
|
|
rejected_included=True,
|
|
period=Duration.minutes(15),
|
|
threshold=15,
|
|
floor=10,
|
|
evaluation_periods=3,
|
|
datapoints_to_alarm=2,
|
|
)
|
|
|
|
# --- AI-fallback rejected alarm: workorder-email-processor ---
|
|
# A parse rejected by the validate_ai_fallback gate is dropped without
|
|
# error/retry/DLQ (fail closed), so like sender-auth rejections it
|
|
# needs its own pager or a sustained rejection condition (prompt-
|
|
# injection probing, or template drift whose AI output fails the gate)
|
|
# stays silent. Same sparse-arrival idiom as the sender-auth-rejected
|
|
# alarm: >=1 rejection per 5-min period, 2 of the last 6 periods (30
|
|
# min), so a lone probe self-clears but a burst pages within ~10 min.
|
|
# Coverage residual (matching the sender-auth-rejected sibling and
|
|
# knowingly accepted): rejections spaced >~25-30 min apart never place
|
|
# two breaching datapoints in one 30-min window, and the fallback-rate
|
|
# alarm dilutes them below 15% against normal template volume, so a
|
|
# *very* sparse silent-drop trickle is not paged by either alarm.
|
|
# EMF emits no datapoint in quiet periods (no metric-filter
|
|
# default_value here); NOT_BREACHING treats those gaps as OK.
|
|
cloudwatch.Metric(
|
|
namespace="Seahaven/WorkorderIngest",
|
|
metric_name="ParseOutcome",
|
|
dimensions_map={"ParseMethod": "ai_fallback_rejected"},
|
|
statistic="Sum",
|
|
period=Duration.minutes(5),
|
|
).create_alarm(
|
|
self,
|
|
"EmailProcessorAiFallbackRejectedAlarm",
|
|
alarm_name="workorder-email-processor-ai-fallback-rejected",
|
|
alarm_description=(
|
|
"workorder-email-processor is rejecting Bedrock AI-fallback "
|
|
"output at the validation gate (possible prompt-injection "
|
|
"probing or template drift silently dropping real mail)"
|
|
),
|
|
threshold=1,
|
|
evaluation_periods=6,
|
|
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))
|
|
|
|
# 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 auth token secret ---
|
|
# Shared secret for the web UI auth gate, stored in Secrets Manager and
|
|
# resolved at runtime so the token never appears in CloudFormation templates
|
|
# or Lambda environment variables. Create this secret before deploying
|
|
# either stack; both PO and WO stacks reference it by name.
|
|
web_ui_auth_secret = secretsmanager.Secret.from_secret_name_v2(
|
|
self,
|
|
"WebUiAuthToken",
|
|
"procurement-ingest/web-ui-auth-token",
|
|
)
|
|
|
|
# --- 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",
|
|
exclude=["**/__pycache__/**"],
|
|
bundling=cdk.BundlingOptions(
|
|
image=lambda_.Runtime.PYTHON_3_12.bundling_image,
|
|
command=[
|
|
"bash",
|
|
"-c",
|
|
# web_ui_auth.py is shared (lambdas/shared) and must land
|
|
# FLAT beside handler.py so
|
|
# `from web_ui_auth import is_authenticated` resolves at
|
|
# runtime. Only web_ui_auth is copied from shared/. WO
|
|
# baseline keeps __init__.py and requirements.txt, so the
|
|
# whole web_ui dir is copied; deployed file list becomes
|
|
# {__init__, handler, requirements.txt, web_ui_auth}.
|
|
# NOTE: the top-level `exclude=` on from_asset only
|
|
# filters the asset-hash fingerprint, NOT the directory
|
|
# Docker bundling actually mounts, so a local
|
|
# __pycache__ on disk at synth time WOULD otherwise leak
|
|
# into the bundled zip -- strip it explicitly post-cp
|
|
# instead of relying on exclude.
|
|
"cp -r wo/web_ui/. /asset-output/ && "
|
|
"cp shared/web_ui_auth.py /asset-output/ && "
|
|
"rm -rf /asset-output/__pycache__",
|
|
],
|
|
),
|
|
),
|
|
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,
|
|
# Defense-in-depth shared secret for the web UI handler. The
|
|
# handler fails closed if this ARN is unset or the secret is
|
|
# missing, so any future invocation path cannot re-expose the
|
|
# WO DB unauthenticated. The secret value is fetched at runtime
|
|
# from Secrets Manager (not embedded in env vars or template).
|
|
"WEB_UI_AUTH_TOKEN_SECRET_ARN": web_ui_auth_secret.secret_arn,
|
|
},
|
|
)
|
|
|
|
work_orders_table.grant_read_data(web_ui)
|
|
comments_table.grant_read_data(web_ui)
|
|
web_ui_auth_secret.grant_read(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 2.261.0).
|
|
# Each table currently has zero throttle/error datapoints, so the series
|
|
# only materialise on first occurrence — NOT_BREACHING keeps them OK until
|
|
# then.
|
|
common.add_ddb_alarms(
|
|
self, "WorkOrdersTable", work_orders_table, "WorkOrders", alarm_topic
|
|
)
|
|
common.add_ddb_alarms(
|
|
self, "WorkOrderComments", comments_table, "WorkOrderComments", alarm_topic
|
|
)
|
|
|
|
# --- Function ARN + consumed-table-name outputs (Phase 4, additive) ---
|
|
cdk.CfnOutput(
|
|
self,
|
|
"EmailProcessorFunctionArn",
|
|
value=email_processor.function_arn,
|
|
description="ARN of the workorder-email-processor Lambda",
|
|
)
|
|
cdk.CfnOutput(
|
|
self,
|
|
"WebUiFunctionArn",
|
|
value=web_ui.function_arn,
|
|
description="ARN of the workorder-web-ui Lambda",
|
|
)
|
|
cdk.CfnOutput(
|
|
self,
|
|
"WorkOrdersTableName",
|
|
value=work_orders_table.table_name,
|
|
description="WorkOrders DynamoDB table",
|
|
)
|
|
cdk.CfnOutput(
|
|
self,
|
|
"WorkOrderCommentsTableName",
|
|
value=comments_table.table_name,
|
|
description="WorkOrderComments DynamoDB table",
|
|
)
|
|
|
|
# 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.
|