fix(cdk): explicit Lambda LogGroups replace log_retention (INFRA-114) (#126)

First seahaven-prod deploy failed CREATE on the sender-auth MetricFilter:
it imported /aws/lambda/<fn> by name, which pre-existed in mgmt but not in
a fresh account. All 5 functions now get an explicit logs.LogGroup
(TWO_MONTHS, RETAIN) via common.make_function_log_group, and the metric
filter takes the construct so CFN orders it after the group exists.

Also removes the deprecated LogRetention custom resource and its
wildcard logs:PutRetentionPolicy role (CKV_AWS_111). Function roles keep
AWSLambdaBasicExecutionRole (verified in the synthesized template), so
log-write permissions are unchanged; cross-review's grant_write FIX was
a false positive on that basis. Supersedes PR #84, which hardcoded the
mgmt logs-CMK ARN and predates the common.py refactor.

mgmt collision note: these CREATEs would collide with the pre-existing
groups in mgmt; acceptable because the deploy secret now targets prod
and mgmt is frozen pending decommission.

cdk/common.py

@@ -73,7 +73,36 @@ def add_ddb_alarms(scope, id_prefix, table, alarm_name_prefix, alarm_topic):
     ).add_alarm_action(cw_actions.SnsAction(alarm_topic))
 
 
-def add_sender_auth_rejected_alarm(scope, id_prefix, function_name, alarm_topic):
+def make_function_log_group(scope, id_prefix, function_name):
+    """Explicit log group for a Lambda, replacing the deprecated
+    ``log_retention`` prop (INFRA-114).
+
+    Making the group a real stack resource (a) drops the LogRetention custom
+    resource whose role carried wildcard ``logs:PutRetentionPolicy`` (checkov
+    CKV_AWS_111), and (b) makes the group an orderable CFN dependency:
+    consumers like the sender-auth metric filter now deploy AFTER the group
+    exists. The previous by-name import raced group creation in a fresh
+    account and failed the first seahaven-prod deploy (the mgmt account
+    masked this because its groups predated the filter).
+
+    RETAIN matches the repo convention for stateful resources and mirrors the
+    old behavior (LogRetention never deleted groups on stack delete). NOTE:
+    in an account where ``/aws/lambda/<fn>`` already exists out-of-band
+    (mgmt), deploying this CREATE would collide -- acceptable because mgmt is
+    frozen post-migration and never redeployed from main.
+    """
+    return logs.LogGroup(
+        scope,
+        f"{id_prefix}LogGroup",
+        log_group_name=f"/aws/lambda/{function_name}",
+        retention=logs.RetentionDays.TWO_MONTHS,
+        removal_policy=RemovalPolicy.RETAIN,
+    )
+
+
+def add_sender_auth_rejected_alarm(
+    scope, id_prefix, function_name, alarm_topic, log_group
+):
     """Metric-filter + alarm on ``sender_auth_rejected`` warnings (INFRA-107).
 
     A rejected inbound email is skipped without erroring the invocation, so it
@@ -84,21 +113,18 @@ def add_sender_auth_rejected_alarm(scope, id_prefix, function_name, alarm_topic)
     mail while the pipeline reports healthy.
 
     ALARM-only SnsAction to site-alerts; no OK action. The metric filter reads
-    the function's own log group (imported by the deterministic
+    the function's own log group, passed in as the EXPLICIT LogGroup construct
-    ``/aws/lambda/<fn>`` name, created by the function's log_retention). A plain
+    (from ``make_function_log_group``) so CFN orders the filter after the
-    substring pattern is used because Lambda prefixes each line with its own
+    group exists -- a by-name import here failed the first fresh-account
-    level/timestamp/request-id, so the JSON payload is not a standalone JSON
+    deploy. A plain substring pattern is used because Lambda prefixes each
-    log event a `{$.event=...}` pattern could match.
+    line with its own level/timestamp/request-id, so the JSON payload is not
+    a standalone JSON log event a `{$.event=...}` pattern could match.
     """
     metric_name = f"{function_name}-sender-auth-rejected"
     logs.MetricFilter(
         scope,
         f"{id_prefix}SenderAuthRejectedFilter",
-        log_group=logs.LogGroup.from_log_group_name(
+        log_group=log_group,
-            scope,
-            f"{id_prefix}LogGroup",
-            f"/aws/lambda/{function_name}",
-        ),
         filter_pattern=logs.FilterPattern.literal('"sender_auth_rejected"'),
         metric_namespace=_SENDER_AUTH_METRIC_NAMESPACE,
         metric_name=metric_name,

cdk/po_stack.py

@@ -11,7 +11,6 @@ from aws_cdk import (
     aws_kms as kms,
     aws_lambda as lambda_,
     aws_lambda_event_sources as lambda_event_sources,
-    aws_logs as logs,
     aws_s3 as s3,
     aws_s3_notifications as s3n,
     aws_ses as ses,
@@ -91,6 +90,9 @@ class PoIngestStack(Stack):
         email_processor_dlq = common.make_processor_dlq(self, "EmailProcessorDlq")
 
         # --- Lambda function ---
+        email_processor_log_group = common.make_function_log_group(
+            self, "EmailProcessor", "po-email-processor"
+        )
         email_processor = lambda_.Function(
             self,
             "EmailProcessor",
@@ -134,7 +136,7 @@ class PoIngestStack(Stack):
             ),
             timeout=Duration.seconds(60),
             memory_size=256,
-            log_retention=logs.RetentionDays.TWO_MONTHS,
+            log_group=email_processor_log_group,
             dead_letter_queue=email_processor_dlq,
             environment={
                 "PO_TABLE": "purchase-orders",
@@ -196,7 +198,11 @@ class PoIngestStack(Stack):
         # false-reject storm pages instead of vanishing. default_value=0 keeps the
         # series populated (alarm stays OK, never INSUFFICIENT_DATA) between events.
         common.add_sender_auth_rejected_alarm(
-            self, "EmailProcessor", "po-email-processor", alarm_topic
+            self,
+            "EmailProcessor",
+            "po-email-processor",
+            alarm_topic,
+            email_processor_log_group,
         )
 
         # --- Template fallback-rate alarm: po-email-processor ---
@@ -372,6 +378,7 @@ class PoIngestStack(Stack):
         )
 
         # --- Web UI Lambda ---
+        web_ui_log_group = common.make_function_log_group(self, "WebUI", "po-web-ui")
         web_ui = lambda_.Function(
             self,
             "WebUI",
@@ -409,7 +416,7 @@ class PoIngestStack(Stack):
             ),
             timeout=Duration.seconds(60),
             memory_size=256,
-            log_retention=logs.RetentionDays.TWO_MONTHS,
+            log_group=web_ui_log_group,
             environment={
                 "PO_TABLE": "purchase-orders",
                 # Defense-in-depth shared secret for the web UI handler. The
@@ -464,6 +471,9 @@ class PoIngestStack(Stack):
         # 518 WCU of write amplification. Re-add if a state-level query path ships.
 
         # --- Site extractor Lambda (DynamoDB Streams → verified-sites) ---
+        site_extractor_log_group = common.make_function_log_group(
+            self, "SiteExtractor", "po-ingest-site-extractor"
+        )
         site_extractor = lambda_.Function(
             self,
             "SiteExtractor",
@@ -483,7 +493,7 @@ class PoIngestStack(Stack):
             ),
             timeout=Duration.seconds(60),
             memory_size=256,
-            log_retention=logs.RetentionDays.TWO_MONTHS,
+            log_group=site_extractor_log_group,
             environment={
                 "VERIFIED_SITES_TABLE": verified_sites_table.table_name,
                 "PENDING_REVIEW_TABLE": "pending-site-review",

cdk/wo_stack.py

@@ -9,7 +9,6 @@ from aws_cdk import (
     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,
@@ -89,6 +88,9 @@ class WorkorderIngestStack(Stack):
         email_processor_dlq = common.make_processor_dlq(self, "EmailProcessorDlq")
 
         # --- Lambda function ---
+        email_processor_log_group = common.make_function_log_group(
+            self, "EmailProcessor", "workorder-email-processor"
+        )
         email_processor = lambda_.Function(
             self,
             "EmailProcessor",
@@ -119,7 +121,7 @@ class WorkorderIngestStack(Stack):
             ),
             timeout=Duration.seconds(60),
             memory_size=256,
-            log_retention=logs.RetentionDays.TWO_MONTHS,
+            log_group=email_processor_log_group,
             dead_letter_queue=email_processor_dlq,
             environment={
                 "WORK_ORDERS_TABLE": work_orders_table.table_name,
@@ -194,7 +196,11 @@ class WorkorderIngestStack(Stack):
         # 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
+            self,
+            "EmailProcessor",
+            "workorder-email-processor",
+            alarm_topic,
+            email_processor_log_group,
         )
 
         # --- Template fallback-rate alarm: workorder-email-processor ---
@@ -304,6 +310,9 @@ class WorkorderIngestStack(Stack):
         )
 
         # --- Web UI Lambda ---
+        web_ui_log_group = common.make_function_log_group(
+            self, "WebUI", "workorder-web-ui"
+        )
         web_ui = lambda_.Function(
             self,
             "WebUI",
@@ -340,7 +349,7 @@ class WorkorderIngestStack(Stack):
             ),
             timeout=Duration.seconds(15),
             memory_size=128,
-            log_retention=logs.RetentionDays.TWO_MONTHS,
+            log_group=web_ui_log_group,
             environment={
                 "WORK_ORDERS_TABLE": work_orders_table.table_name,
                 "COMMENTS_TABLE": comments_table.table_name,