feat(hub): configure durable audit intake

charts/hub/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.138.0
+version: 0.139.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

charts/hub/README.md

@@ -310,11 +310,16 @@ Below all configuration options and parameters are listed.
 | `kerberoshub.audit.enabled` | Deploy the Hub audit service. Its first responsibility is forwarding canonical MongoDB `audit_events` to configured destinations. | `false` |
 | `kerberoshub.audit.repository` | Hub audit service container image repository. | `"ghcr.io/uug-ai/hub-audit"` |
 | `kerberoshub.audit.pullPolicy` | Hub audit service image pull policy. | `"IfNotPresent"` |
-| `kerberoshub.audit.tag` | Hub audit service image tag. | `"v1.0.0"` |
+| `kerberoshub.audit.tag` | Hub audit service image tag. | `"v1.1.0"` |
 | `kerberoshub.audit.replicas` | Number of audit service replicas. Per-destination MongoDB leases prevent concurrent delivery. | `1` |
 | `kerberoshub.audit.dispatchInterval` | How often the mounted destination configuration is reloaded and eligible destinations are polled. | `"5s"` |
 | `kerberoshub.audit.leaseDuration` | Per-destination lease duration. It must exceed every destination timeout by at least 30 seconds. | `"2m"` |
 | `kerberoshub.audit.terminationGracePeriodSeconds` | Pod termination grace period. Keep this longer than `leaseDuration` so an in-flight cycle can finish. | `150` |
+| `kerberoshub.audit.intake.queue` | Durable RabbitMQ queue receiving normalized audit events from producers. | `"hub-audit-events"` |
+| `kerberoshub.audit.intake.deadletterQueue` | RabbitMQ queue for invalid audit events and exhausted persistence retries. | `"hub-audit-dead-letter"` |
+| `kerberoshub.audit.intake.maxRetries` | Maximum MongoDB persistence retries before an intake event is dead-lettered. | `10` |
+| `kerberoshub.audit.intake.prefetchCount` | Maximum unacknowledged intake events per audit replica. | `20` |
+| `kerberoshub.audit.intake.persistTimeout` | Timeout for one MongoDB persistence attempt. | `"10s"` |
 | `kerberoshub.audit.destinations` | Webhook destinations. Each entry supports `id`, `enabled`, `url`, delivery limits, filters, public `headers`, `bearerTokenSecret`, and arbitrary `secretHeaders`. Destination IDs retain independent checkpoints. | `[]` |
 | `kerberoshub.audit.serviceMonitor.enabled` | Create a Prometheus `ServiceMonitor` for audit service metrics. | `true` |
 | `kerberoshub.audit.serviceMonitor.interval` | Audit service metrics scrape interval. | `"15s"` |

charts/hub/templates/configmap-hub-audit.yaml

@@ -1,4 +1,4 @@
-{{- if and (or (eq .Values.mode "all") (eq .Values.mode "ui")) .Values.kerberoshub.audit.enabled -}}
+{{- if .Values.kerberoshub.audit.enabled -}}
 {{- $destinations := list -}}
 {{- $destinationIDs := dict -}}
 {{- range $index, $destination := .Values.kerberoshub.audit.destinations -}}

charts/hub/templates/kerberos-hub/hub-audit-servicemonitor.yaml

@@ -1,4 +1,4 @@
-{{- if and (or (eq .Values.mode "all") (eq .Values.mode "ui")) .Values.kerberoshub.audit.enabled .Values.kerberoshub.audit.serviceMonitor.enabled -}}
+{{- if and .Values.kerberoshub.audit.enabled .Values.kerberoshub.audit.serviceMonitor.enabled -}}
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:

charts/hub/templates/kerberos-hub/hub-audit.yaml

@@ -1,4 +1,7 @@
-{{- if and (or (eq .Values.mode "all") (eq .Values.mode "ui")) .Values.kerberoshub.audit.enabled -}}
+{{- if .Values.kerberoshub.audit.enabled -}}
+{{- if ne (upper .Values.queueProvider) "RABBITMQ" -}}
+{{- fail "kerberoshub.audit currently requires queueProvider=RABBITMQ" -}}
+{{- end -}}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -111,6 +114,24 @@ spec:
             - configMapRef:
                 name: mongodb-config
           env:
+            - name: RABBITMQ_HOST
+              value: {{ .Values.rabbitmq.host | quote }}
+            - name: RABBITMQ_EXCHANGE
+              value: {{ .Values.rabbitmq.exchange | quote }}
+            - name: RABBITMQ_USERNAME
+              value: {{ .Values.rabbitmq.username | quote }}
+            - name: RABBITMQ_PASSWORD
+              value: {{ .Values.rabbitmq.password | quote }}
+            - name: AUDIT_QUEUE
+              value: {{ .Values.kerberoshub.audit.intake.queue | quote }}
+            - name: AUDIT_DEADLETTER_QUEUE
+              value: {{ .Values.kerberoshub.audit.intake.deadletterQueue | quote }}
+            - name: AUDIT_MAX_RETRIES
+              value: {{ .Values.kerberoshub.audit.intake.maxRetries | quote }}
+            - name: AUDIT_PREFETCH_COUNT
+              value: {{ .Values.kerberoshub.audit.intake.prefetchCount | quote }}
+            - name: AUDIT_PERSIST_TIMEOUT
+              value: {{ .Values.kerberoshub.audit.intake.persistTimeout | quote }}
             - name: DISPATCH_INTERVAL
               value: {{ .Values.kerberoshub.audit.dispatchInterval | quote }}
             - name: LEASE_DURATION

charts/hub/values.yaml

@@ -705,11 +705,17 @@ kerberoshub:
     enabled: false
     repository: ghcr.io/uug-ai/hub-audit
     pullPolicy: IfNotPresent
-    tag: "v1.0.0"
+    tag: "v1.1.0"
     replicas: 1
     dispatchInterval: "5s"
     leaseDuration: "2m"
     terminationGracePeriodSeconds: 150 # Keep above leaseDuration so an in-flight cycle can finish.
+    intake:
+      queue: "hub-audit-events"
+      deadletterQueue: "hub-audit-dead-letter"
+      maxRetries: 10
+      prefetchCount: 20
+      persistTimeout: "10s"
     topologySpreadConstraints: []
     volumes: []
     volumeMounts: []