Fix validate-except syntax: trailing semicolon after last entry

named requires every entry in the list to be semicolon-terminated,
including the last one before the closing brace; without it named fails
config parse (missing ';' before '}') and crash-loops.

.woodpecker/vector-test.yaml

@@ -1,29 +0,0 @@
-when:
-  - event: pull_request
-
-steps:
-  - name: vector-test
-    image: artifactapi.k8s.syd1.au.unkin.net/dockerhub/timberio/vector:0.57.0-debian
-    commands:
-      # Dummy creds + writable dirs so the full topologies build; the unit tests
-      # only exercise the transforms (sources are not started).
-      - export CLICKHOUSE_USER=ci CLICKHOUSE_PASSWORD=ci
-      - export NATS_PRODUCER_PASSWORD=ci NATS_CONSUMER_PASSWORD=ci
-      - mkdir -p /vector-data-dir /etc/vault-ca
-      - cp /etc/ssl/certs/ca-certificates.crt /etc/vault-ca/ca.crt
-      # Transform tier + VM ingest: unit-tested transforms.
-      - vector test apps/base/logging/vector/aggregator.yaml apps/base/logging/vector/aggregator-tests.yaml
-      - vector test apps/base/logging/vector/vm-ingest.yaml apps/base/logging/vector/vm-ingest-tests.yaml
-      # Agent has no transforms to unit-test; validate it builds. (The archiver
-      # leg is now the logarchiver service, not a Vector pipeline.)
-      - vector validate --no-environment apps/base/logging/vector/agent.yaml
-    backend_options:
-      kubernetes:
-        serviceAccountName: default
-        resources:
-          requests:
-            memory: 256Mi
-            cpu: 250m
-          limits:
-            memory: 1Gi
-            cpu: 1

apps/base/age-api/deployment.yaml

@@ -12,13 +12,13 @@ spec:
   template:
     metadata:
       annotations:
-        configmap.reloader.stakater.com/auto: "true"
+        reloader.stakater.com/auto: "true"
       labels:
         app: age-api
     spec:
       containers:
         - name: age-api
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/age-api:v0.1.0
+          image: git.unkin.net/unkin/age-api:v0.1.0
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 8080

apps/base/age-api/kustomization.yaml

@@ -8,7 +8,6 @@ resources:
   - httproute.yaml
   - namespace.yaml
   - service.yaml
-  - vpa.yaml
 
 configMapGenerator:
   - name: age-api-config

apps/base/age-api/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: age-api-vpa
-  namespace: age-api
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: age-api
-  updatePolicy:
-    updateMode: "Off"

apps/base/artifactapi/api-deployment.yaml

@@ -5,8 +5,7 @@ metadata:
   name: api
   namespace: artifactapi
   annotations:
-    configmap.reloader.stakater.com/auto: "true"
-    secret.reloader.stakater.com/reload: "vault-ca-cert"
+    reloader.stakater.com/auto: "true"
 spec:
   selector:
     matchLabels:
@@ -36,7 +35,7 @@ spec:
               mountPath: /combined-certs
       containers:
         - name: api
-          image: git.unkin.net/unkin/artifactapi:v3.7.7
+          image: git.unkin.net/unkin/artifactapi:v3.7.6
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 8000

apps/base/artifactapi/cnpg_backup.yaml

@@ -1,56 +0,0 @@
----
-# Ceph RGW (S3) backup target for the artifactapi CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster:
-# cephrgw CRs are namespace-scoped and CNPG reads its S3 credential Secret from
-# its own namespace, so backups are per-database rather than one shared bucket.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-artifactapi-backup
-  namespace: artifactapi
-spec:
-  displayName: "CNPG backup owner (artifactapi)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-artifactapi-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-artifactapi-backup-s3
-  # Keep the RGW user (and thus the keys) if this CR is ever deleted, so an
-  # in-flight restore can still reach the archive.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-artifactapi
-  namespace: artifactapi
-spec:
-  placementTarget: ec
-  bucketName: cnpg-artifactapi
-  # The owner user has full control of its own bucket (read + write), which is
-  # all the backup/restore identity needs — no extra BucketAccess grant.
-  ownerRef: cnpg-artifactapi-backup
-  versioning: false
-  tags:
-    app: artifactapi
-    purpose: cnpg-backup
-  # Never drop the backups if the CR is removed; retire buckets by hand.
-  retainOnDelete: true
----
-# Nightly base backup. Continuous WAL archiving is always-on via the Cluster's
-# spec.backup.barmanObjectStore; this schedules the periodic full backup that
-# WAL is layered on top of. Schedules are staggered across clusters so the 8
-# base backups do not hit RGW at once (CNPG cron is 6-field, seconds first).
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-artifactapi-nightly
-  namespace: artifactapi
-spec:
-  schedule: "0 40 1 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: postgres

apps/base/artifactapi/cnpg_cluster.yaml

@@ -7,35 +7,6 @@ metadata:
 spec:
   affinity:
     podAntiAffinityType: preferred
-  backup:
-    # 30-day retention (DEFAULT — adjust per cluster if needed). Enforced by CNPG
-    # against the object store on each successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-artifactapi
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-artifactapi-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-artifactapi-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: artifactapi
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
   bootstrap:
     initdb:
       database: artifacts

apps/base/artifactapi/httproute.yaml

@@ -1,6 +1,30 @@
 ---
 apiVersion: gateway.networking.k8s.io/v1
 kind: HTTPRoute
+metadata:
+  name: http-redirect
+  namespace: artifactapi
+spec:
+  hostnames:
+    - artifactapi.k8s.syd1.au.unkin.net
+  parentRefs:
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: artifactapi
+      sectionName: http
+  rules:
+    - filters:
+        - type: RequestRedirect
+          requestRedirect:
+            scheme: https
+            statusCode: 301
+      matches:
+        - path:
+            type: PathPrefix
+            value: /
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: HTTPRoute
 metadata:
   name: api-route
   namespace: artifactapi
@@ -8,12 +32,6 @@ spec:
   hostnames:
     - artifactapi.k8s.syd1.au.unkin.net
   parentRefs:
-    # Early-boot clients (anaconda/kickstart, yum in %post, PXE) need plain HTTP
-    # for the rpm repos; serve the app directly on port 80 instead of redirecting.
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: artifactapi
-      sectionName: http
     - group: gateway.networking.k8s.io
       kind: Gateway
       name: artifactapi

apps/base/artifactapi/kustomization.yaml

@@ -7,7 +7,6 @@ resources:
   - api-hpa.yaml
   - configmap.yaml
   - cnpg_cluster.yaml
-  - cnpg_backup.yaml
   - cnpg_pooler.yaml
   - gateway.yaml
   - httproute.yaml
@@ -18,4 +17,3 @@ resources:
   - ui-hpa.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml
-  - vpa.yaml

apps/base/artifactapi/ui-deployment.yaml

@@ -5,7 +5,7 @@ metadata:
   name: ui
   namespace: artifactapi
   annotations:
-    configmap.reloader.stakater.com/auto: "true"
+    reloader.stakater.com/auto: "true"
 spec:
   selector:
     matchLabels:
@@ -22,7 +22,7 @@ spec:
       automountServiceAccountToken: true
       containers:
         - name: ui
-          image: git.unkin.net/unkin/artifactapi-ui:v3.7.7
+          image: git.unkin.net/unkin/artifactapi-ui:v3.7.6
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 80

apps/base/artifactapi/vpa.yaml

@@ -1,45 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: api-vpa
-  namespace: artifactapi
-  # NOTE: this workload also has an HPA. updateMode Off is recommendation-only
-  # and does not act, so there is no HPA/VPA conflict today. Do not flip to Auto/
-  # Initial without first moving the HPA off CPU/memory (VPA owns those under Auto).
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: api
-  updatePolicy:
-    updateMode: "Off"
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: redis-vpa
-  namespace: artifactapi
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: redis
-  updatePolicy:
-    updateMode: "Off"
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: ui-vpa
-  namespace: artifactapi
-  # NOTE: this workload also has an HPA. updateMode Off is recommendation-only
-  # and does not act, so there is no HPA/VPA conflict today. Do not flip to Auto/
-  # Initial without first moving the HPA off CPU/memory (VPA owns those under Auto).
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: ui
-  updatePolicy:
-    updateMode: "Off"

apps/base/authentik/cnpg_backup.yaml

@@ -1,56 +0,0 @@
----
-# Ceph RGW (S3) backup target for the authentik CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster:
-# cephrgw CRs are namespace-scoped and CNPG reads its S3 credential Secret from
-# its own namespace, so backups are per-database rather than one shared bucket.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-authentik-backup
-  namespace: authentik
-spec:
-  displayName: "CNPG backup owner (authentik)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-authentik-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-authentik-backup-s3
-  # Keep the RGW user (and thus the keys) if this CR is ever deleted, so an
-  # in-flight restore can still reach the archive.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-authentik
-  namespace: authentik
-spec:
-  placementTarget: ec
-  bucketName: cnpg-authentik
-  # The owner user has full control of its own bucket (read + write), which is
-  # all the backup/restore identity needs — no extra BucketAccess grant.
-  ownerRef: cnpg-authentik-backup
-  versioning: false
-  tags:
-    app: authentik
-    purpose: cnpg-backup
-  # Never drop the backups if the CR is removed; retire buckets by hand.
-  retainOnDelete: true
----
-# Nightly base backup. Continuous WAL archiving is always-on via the Cluster's
-# spec.backup.barmanObjectStore; this schedules the periodic full backup that
-# WAL is layered on top of. Schedules are staggered across clusters so the 8
-# base backups do not hit RGW at once (CNPG cron is 6-field, seconds first).
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-authentik-nightly
-  namespace: authentik
-spec:
-  schedule: "0 0 1 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: postgres

apps/base/authentik/cnpg_cluster.yaml

@@ -7,35 +7,6 @@ metadata:
 spec:
   affinity:
     podAntiAffinityType: preferred
-  backup:
-    # 30-day retention (DEFAULT — adjust per cluster if needed). Enforced by CNPG
-    # against the object store on each successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-authentik
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-authentik-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-authentik-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: authentik
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
   bootstrap:
     initdb:
       database: authentik
@@ -106,12 +77,10 @@ spec:
   resources:
     limits:
       cpu: 500m
-      # 512Mi OOMKilled replicas under load (shared_buffers 128MB +
-      # max_connections 200 leave no headroom) — see incident 2026-07-28.
-      memory: 1Gi
+      memory: 512Mi
     requests:
       cpu: 50m
-      memory: 512Mi
+      memory: 256Mi
   smartShutdownTimeout: 180
   startDelay: 3600
   stopDelay: 1800

apps/base/authentik/kustomization.yaml

@@ -4,7 +4,6 @@ kind: Kustomization
 
 resources:
   - cnpg_cluster.yaml
-  - cnpg_backup.yaml
   - cnpg_pooler.yaml
   - gateway.yaml
   - httproute.yaml
@@ -18,4 +17,3 @@ resources:
   - redis-service.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml
-  - vpa.yaml

apps/base/authentik/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: redis-vpa
-  namespace: authentik
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: redis
-  updatePolicy:
-    updateMode: "Off"

apps/base/bind-external/agent-dns-rolebinding.yaml

@@ -1,16 +0,0 @@
----
-# Confines the agent-dns service account (in bind-system) to the agent-dns
-# ClusterRole within this namespace.
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: agent-dns
-  namespace: bind-external
-subjects:
-  - kind: ServiceAccount
-    name: agent-dns
-    namespace: bind-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: agent-dns

apps/base/bind-external/cluster.yaml

@@ -1,52 +0,0 @@
----
-# Externally-reachable authoritative BIND for zones we delegate to ourselves.
-# First tenant: acme.unkin.net, the DNS-01 challenge zone Let's Encrypt validates
-# via a one-time _acme-challenge.unkin.net CNAME. Authoritative-only, recursion
-# off, no forwarding, no open transfers -- the primaryService is the single
-# dmz-pinned LoadBalancer that public NAT targets and that cert-manager writes to.
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindCluster
-metadata:
-  name: bind-external
-  namespace: bind-external
-spec:
-  mode: authoritative
-  recursion: false
-  replicas: 2
-  storageClassName: cephrbd-fast-delete
-  storageSize: 1Gi
-  # Public server: answer queries from anywhere (Let's Encrypt validates over the
-  # internet), deny recursion and open zone transfers. localhost + pod net are
-  # implied by "any" and cover in-pod nsupdate and secondary SOA refresh; per-zone
-  # allow-transfer (catalog + acme zone) still permits key-authenticated AXFR.
-  extraOptions:
-    - "allow-query { any; }"
-    - "allow-transfer { none; }"
-  service:
-    type: ClusterIP
-  primaryService:
-    type: LoadBalancer
-    externalTrafficPolicy: Local
-    annotations:
-      purelb.io/service-group: dmz
-      purelb.io/addresses: 198.18.199.53
-      external-dns.alpha.kubernetes.io/hostname: bind-external-primary.k8s.syd1.au.unkin.net
-  resources:
-    requests:
-      cpu: 20m
-      memory: 128Mi
-    limits:
-      cpu: "1"
-      memory: 512Mi
----
-# Catalog zone so the acme zone replicates onto the secondary (AXFR/IXFR keyed
-# with the certmanager TSIG key, reused here as the transfer key).
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindCatalogZone
-metadata:
-  name: bind-external-catalog
-  namespace: bind-external
-spec:
-  clusterRef: bind-external
-  zoneName: catalog.external
-  transferKeyRef: certmanager

apps/base/bind-external/kustomization.yaml

@@ -1,10 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml
-  - cluster.yaml
-  - tsigkey.yaml
-  - zones.yaml
-  - agent-dns-rolebinding.yaml

apps/base/bind-external/namespace.yaml

@@ -1,5 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: bind-external

apps/base/bind-external/tsigkey.yaml

@@ -1,20 +0,0 @@
----
-# TSIG key cert-manager uses to send RFC2136 dynamic updates (the DNS-01 TXT
-# records) to the primary, and that the secondary reuses for AXFR. The operator
-# generates the material into Secret certmanager-tsig in this namespace;
-# secretTemplate stamps emberstack reflector hints so the Secret is mirrored into
-# the cert-manager namespace, where the rfc2136 solver reads its "secret" key.
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindTSIGKey
-metadata:
-  name: certmanager
-  namespace: bind-external
-spec:
-  clusterRef: bind-external
-  algorithm: hmac-sha256
-  secretTemplate:
-    annotations:
-      reflector.v1.k8s.emberstack.com/reflection-allowed: "true"
-      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "cert-manager"
-      reflector.v1.k8s.emberstack.com/reflection-auto-enabled: "true"
-      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "cert-manager"

apps/base/bind-external/zones.yaml

@@ -1,19 +0,0 @@
----
-# Self-delegated ACME challenge zone. Google Cloud DNS holds a one-time
-# _acme-challenge.unkin.net CNAME -> _acme-challenge.acme.unkin.net and an
-# acme.unkin.net NS delegation pointing here; cert-manager writes the challenge
-# TXT records via RFC2136 authenticated with the certmanager key.
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindZone
-metadata:
-  name: acme-unkin-net
-  namespace: bind-external
-spec:
-  clusterRef: bind-external
-  zoneName: acme.unkin.net
-  type: primary
-  defaultTTL: 60
-  dynamicUpdate: true
-  updateKeyRef: certmanager
-  allowTransfer:
-    - key certmanager

apps/base/bind-internal/agent-dns-rolebinding.yaml

@@ -1,16 +0,0 @@
----
-# Confines the agent-dns service account (in bind-system) to the agent-dns
-# ClusterRole within this namespace.
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: agent-dns
-  namespace: bind-internal
-subjects:
-  - kind: ServiceAccount
-    name: agent-dns
-    namespace: bind-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: agent-dns

apps/base/bind-internal/authoritative/acls.yaml

@@ -24,6 +24,3 @@ spec:
     - 198.18.27.0/24
     - 198.18.28.0/24
     - 198.18.29.0/24
-    # Admin/management access (individual hosts, not whole subnets)
-    - 10.10.12.200/32   # benvin workstation (wireguard)
-    - 198.18.21.160/32  # benvin router

apps/base/bind-internal/authoritative/cluster.yaml

@@ -13,14 +13,9 @@ spec:
   storageSize: 2Gi
   # Restrict queries to internal networks (puppet acl-main.unkin.net).
   # 10.42.0.0/16 (pod net) is required so secondaries can SOA-refresh
-  # from the primary during catalog replication. localhost is required so the
-  # operator's in-pod `nsupdate` (sent to 127.0.0.1) passes query-authorization;
-  # without it every dynamic update is "denied due to allow-query".
+  # from the primary during catalog replication.
   extraOptions:
-    - "allow-query { localhost; auth-acl-main; 10.42.0.0/16; }"
-    # Enable query logging for the Tier-2 vector bind_query pipeline (see the
-    # resolvers cluster for the routing rationale).
-    - "querylog yes"
+    - "allow-query { auth-acl-main; 10.42.0.0/16; }"
   service:
     type: LoadBalancer
     externalTrafficPolicy: Local

apps/base/bind-internal/authoritative/kustomization.yaml

@@ -6,5 +6,4 @@ resources:
   - cluster.yaml
   - tsigkey.yaml
   - zones.yaml
-  - records.yaml
   - acls.yaml

apps/base/bind-internal/authoritative/records.yaml

@@ -1,90 +0,0 @@
-# Individually-managed authoritative records for the unkin.net zone.
-# DNSRecords must live in the same namespace as their BindZone (the operator
-# resolves zoneRef/clusterRef/updateKeyRef within the record's namespace), so
-# these sit alongside the zone in bind-internal, not in the app namespace.
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  # "internal" in the name distinguishes this from the external DNS that
-  # Authentik will manage its own records from later.
-  name: identity-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: identity
-  type: A
-  ttl: 600
-  values:
-    # traefik-internal gateway VIP; the authentik Gateway serves the
-    # identity.unkin.net hostname there.
-    - 198.18.200.4
----
-# PRODUCTION CUTOVER RECORD — intentionally commented out.
-# git.unkin.net currently resolves to the LIVE VM forge (HAProxy VRRP VIP
-# 198.18.19.17), which holds every repo the estate depends on. Uncommenting this
-# repoints the whole org's git.unkin.net at the new k8s Gitea gateway VIP, so it
-# is the FINAL step of the forge migration — gated on the data migration (gitea
-# dump/restore + SECRET_KEY copy) in argocd-apps docs/gitea-migration.md.
-# NOTE: the live git.unkin.net answer is served by the puppet DNS master today
-# (profiles::dns::master, records from PuppetDB); this k8s apex zone holds only
-# SOA+NS + a few DNSRecords so far. Confirm the k8s bind cluster is the live
-# authority for unkin.net (or update the puppet record instead) before relying
-# on this CR at cutover.
-# ---
-# apiVersion: bind.unkin.net/v1alpha1
-# kind: DNSRecord
-# metadata:
-#   name: git-dns-internal
-#   namespace: bind-internal
-# spec:
-#   zoneRef: unkin-net
-#   name: git
-#   type: A
-#   ttl: 600
-#   values:
-#     # traefik-internal gateway VIP; the gitea Gateway serves git.unkin.net there.
-#     - 198.18.200.4
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: s3-ceph-cname
-  namespace: bind-internal
-spec:
-  zoneRef: ceph-unkin-net
-  name: s3
-  type: CNAME
-  ttl: 600
-  values:
-    # radosgw S3 endpoint. Points at the Consul service for now; the real
-    # target will be changed later.
-    - radosgw.service.consul.
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: dashboard-ceph-cname
-  namespace: bind-internal
-spec:
-  zoneRef: ceph-unkin-net
-  name: dashboard
-  type: CNAME
-  ttl: 600
-  values:
-    # Ceph mgr dashboard, reached via lb1. Lets in-cluster clients (the
-    # cephrgw-operator) resolve dashboard.ceph.unkin.net.
-    - lb1.unkin.net.
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: lb1-unkin-net
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: lb1
-  type: A
-  ttl: 600
-  values:
-    - 103.216.191.185

apps/base/bind-internal/authoritative/zones.yaml

@@ -31,22 +31,6 @@ spec:
   dynamicUpdate: true
   updateKeyRef: client-update
 ---
-# ceph.unkin.net: the ceph host (ausyd1nxvm2069/halb) publishes
-# dashboard.ceph.unkin.net via nsupdate; puppet targets a dedicated
-# `zone ceph.unkin.net.`, so it must exist here or the update gets NOTZONE.
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindZone
-metadata:
-  name: ceph-unkin-net
-  namespace: bind-internal
-spec:
-  clusterRef: bind-authoritative
-  zoneName: ceph.unkin.net
-  type: primary
-  defaultTTL: 600
-  dynamicUpdate: true
-  updateKeyRef: client-update
----
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
 metadata:

apps/base/bind-internal/externaldns/tsigkey.yaml

@@ -1,10 +1,6 @@
 ---
 # Key that external-dns (and DNSRecord objects) use to send RFC2136 dynamic
-# updates to the primary. The operator generates the material into a Secret
-# (externaldns-key-tsig) in this namespace. secretTemplate stamps emberstack
-# reflector hints onto that Secret so it is mirrored into the externaldns
-# namespace, where the external-dns controller reads it -- guaranteeing
-# external-dns presents exactly the key the primary's allow-update accepts.
+# updates to the primary. The operator generates the material into a Secret.
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindTSIGKey
 metadata:
@@ -13,9 +9,3 @@ metadata:
 spec:
   clusterRef: bind-externaldns
   algorithm: hmac-sha256
-  secretTemplate:
-    annotations:
-      reflector.v1.k8s.emberstack.com/reflection-allowed: "true"
-      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "externaldns"
-      reflector.v1.k8s.emberstack.com/reflection-auto-enabled: "true"
-      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "externaldns"

apps/base/bind-internal/kustomization.yaml

@@ -8,4 +8,3 @@ resources:
   - resolvers
   - externaldns
   - tsig-api
-  - agent-dns-rolebinding.yaml

apps/base/bind-internal/resolvers/acls.yaml

@@ -8,15 +8,11 @@ metadata:
 spec:
   clusterRef: bind-resolvers
   entries:
-    - 10.42.0.0/16   # k8s pod network (kube-proxy masquerades node-originated LB queries)
     - 198.18.1.10/32
     - 198.18.2.160/27
     - 198.18.21.160/27
     - 198.18.2.192/27
     - 198.18.21.192/27
-    # Admin/management access
-    - 10.10.12.200/32   # benvin workstation (wireguard)
-    - 198.18.21.160/32  # benvin router (also within 198.18.21.160/27 above)
     - 198.18.13.0/24
     - 198.18.14.0/24
     - 198.18.15.0/24

apps/base/bind-internal/resolvers/cluster.yaml

@@ -30,11 +30,6 @@ spec:
   # (incl. k8s.syd1.au.unkin.net); 18.198.in-addr.arpa covers every reverse zone.
   extraOptions:
     - "validate-except { unkin.net; 18.198.in-addr.arpa; consul; }"
-    # Enable query logging so the Tier-2 vector bind_query pipeline can parse
-    # client/qname/qtype. Routes to the `queries` category which, with no explicit
-    # logging{} clause, follows the default category to the named foreground
-    # stderr channel -> pod stdout -> vector (subject logs.k8s.bind-internal.*).
-    - "querylog yes"
   resources:
     requests:
       cpu: 20m

apps/base/bind-internal/resolvers/forward-zones.yaml

@@ -1,9 +1,6 @@
 # Conditional forward zones, from the puppet openforwarder view.
-# Upstreams: unkin authoritative 198.18.200.6, consul 198.18.19.14,
-#   k8s 198.18.200.8 (in-cluster bind-externaldns VIP).
-# k8s -> in-cluster bind-externaldns 198.18.200.8 for both the forward zone
-#   k8s.syd1.au.unkin.net and the reverse zone 200.18.198.in-addr.arpa, which
-#   external-dns now publishes to (see the external-dns migration PRs).
+# Upstreams: unkin authoritative 198.18.200.6, consul 198.18.19.14, k8s 198.18.200.8.
+# k8s -> in-cluster bind-externaldns 198.18.200.8.
 # (Zones that forwarded to 10.10.16.x were dropped; consul left as-is.)
 ---
 apiVersion: bind.unkin.net/v1alpha1
@@ -64,22 +61,6 @@ spec:
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
-metadata:
-  name: fwd-200-18-198-in-addr-arpa
-  namespace: bind-internal
-spec:
-  clusterRef: bind-resolvers
-  viewRef: openforwarder
-  zoneName: 200.18.198.in-addr.arpa
-  type: forward
-  catalog: false
-  forwarders:
-    # Reverse zone for the k8s LB range, published by external-dns to the
-    # in-cluster bind-externaldns alongside k8s.syd1.au.unkin.net.
-    - 198.18.200.8
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: BindZone
 metadata:
   name: fwd-13-18-198-in-addr-arpa
   namespace: bind-internal

apps/base/bind-internal/tsig-api/tsig-api.yaml

@@ -13,7 +13,7 @@ metadata:
   name: bind-tsig-api
   namespace: bind-internal
 spec:
-  image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/bind-tsig-api:v0.2.3
+  image: git.unkin.net/unkin/bind-tsig-api:v0.2.1
   replicas: 1
   port: 8443
   # targetNamespace defaults to this resource's namespace (bind-internal), where

apps/base/bind-system/agent-dns-rbac.yaml

@@ -1,38 +0,0 @@
----
-# Static service account that Vault's kubernetes secret engine mints scoped
-# tokens for (agent-dns role). RBAC is confined to the bind namespaces via the
-# per-namespace RoleBindings below, not a ClusterRoleBinding.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: agent-dns
-  namespace: bind-system
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: agent-dns
-rules:
-  - apiGroups: ["bind.unkin.net"]
-    resources: ["*"]
-    verbs: ["*"]
-  - apiGroups: [""]
-    resources: ["pods", "services", "configmaps", "events"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: [""]
-    resources: ["pods/log"]
-    verbs: ["get"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: agent-dns
-  namespace: bind-system
-subjects:
-  - kind: ServiceAccount
-    name: agent-dns
-    namespace: bind-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: agent-dns

apps/base/bind-system/deployment.yaml

@@ -21,7 +21,7 @@ spec:
         runAsNonRoot: true
       containers:
         - name: operator
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/bind-operator:v0.2.6
+          image: git.unkin.net/unkin/bind-operator:v0.2.1
           args:
             - --metrics-bind-address=:8080
             - --health-probe-bind-address=:8081

apps/base/bind-system/kustomization.yaml

@@ -6,8 +6,6 @@ resources:
   - namespace.yaml
   # CRDs are pulled from the bind-operator repo at the matching tag rather than
   # vendored here, so they never drift from the operator.
-  - https://git.unkin.net/unkin/bind-operator/raw/tag/v0.2.6/config/crd/install.yaml
+  - https://git.unkin.net/unkin/bind-operator/raw/tag/v0.2.1/config/crd/install.yaml
   - rbac.yaml
-  - agent-dns-rbac.yaml
   - deployment.yaml
-  - vpa.yaml

apps/base/bind-system/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: bind-operator-vpa
-  namespace: bind-system
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: bind-operator
-  updatePolicy:
-    updateMode: "Off"

apps/base/cephrgw-system/deployment.yaml

@@ -1,84 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: cephrgw-operator
-  namespace: cephrgw-system
-  labels:
-    app.kubernetes.io/name: cephrgw-operator
-  annotations:
-    # Restart on internal CA rotation only; cephrgw-credentials is Vault-rotated
-    # (VSO) and deliberately excluded so routine key rotation causes no restart.
-    configmap.reloader.stakater.com/auto: "true"
-    secret.reloader.stakater.com/reload: "vault-ca-cert"
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: cephrgw-operator
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: cephrgw-operator
-    spec:
-      serviceAccountName: cephrgw-operator
-      securityContext:
-        runAsNonRoot: true
-      containers:
-        - name: operator
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/cephrgw-operator:v0.4.0
-          args:
-            - --metrics-bind-address=:8080
-            - --health-probe-bind-address=:8081
-            - --leader-elect
-          envFrom:
-            # Provides CEPH_RGW_ACCESS_KEY/SECRET_KEY and the endpoints
-            # (CEPH_RGW_ENDPOINT / CEPH_RGW_ADMIN_ENDPOINT), plus optional
-            # CEPH_RGW_REGION / CEPH_RGW_CA / CEPH_RGW_INSECURE. Rendered from
-            # Vault per docs/ceph-setup.md; not managed in GitOps.
-            - secretRef:
-                name: cephrgw-credentials
-          env:
-            # Trust the internal unkin.net (Vault PKI) CA so the operator can
-            # verify radosgw's TLS cert. vault-ca-cert is reflected into every
-            # namespace from the certificates namespace.
-            - name: CEPH_RGW_CA_FILE
-              value: /etc/vault-ca/ca.crt
-          volumeMounts:
-            - name: vault-ca-cert
-              mountPath: /etc/vault-ca/ca.crt
-              subPath: ca.crt
-              readOnly: true
-          ports:
-            - containerPort: 8080
-              name: metrics
-            - containerPort: 8081
-              name: health
-          readinessProbe:
-            httpGet:
-              path: /readyz
-              port: 8081
-            initialDelaySeconds: 5
-            periodSeconds: 10
-          livenessProbe:
-            httpGet:
-              path: /healthz
-              port: 8081
-            initialDelaySeconds: 15
-            periodSeconds: 20
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop: ["ALL"]
-          resources:
-            requests:
-              cpu: 50m
-              memory: 64Mi
-            limits:
-              cpu: 500m
-              memory: 256Mi
-      volumes:
-        - name: vault-ca-cert
-          secret:
-            secretName: vault-ca-cert

apps/base/cephrgw-system/kustomization.yaml

@@ -1,14 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml
-  # CRDs are pulled from the cephrgw-operator repo at the matching tag rather
-  # than vendored here, so they never drift from the operator.
-  - https://git.unkin.net/unkin/cephrgw-operator/raw/tag/v0.4.0/config/crd/install.yaml
-  - rbac.yaml
-  - deployment.yaml
-  - vaultauth.yaml
-  - vaultstaticsecret.yaml
-  - vpa.yaml

apps/base/cephrgw-system/namespace.yaml

@@ -1,5 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: cephrgw-system

apps/base/cephrgw-system/rbac.yaml

@@ -1,42 +0,0 @@
----
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: cephrgw-operator
-  namespace: cephrgw-system
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: cephrgw-operator
-rules:
-  - apiGroups: ["ceph.unkin.net"]
-    resources: ["*"]
-    verbs: ["*"]
-  # The operator delivers RGW access/secret keys into Secrets.
-  - apiGroups: [""]
-    resources: ["secrets"]
-    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
-  - apiGroups: [""]
-    resources: ["events"]
-    verbs: ["create", "patch"]
-  - apiGroups: ["coordination.k8s.io"]
-    resources: ["leases"]
-    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
-  # v0.3.1 startup check reads its own CRDs to warn if they are stale/missing.
-  - apiGroups: ["apiextensions.k8s.io"]
-    resources: ["customresourcedefinitions"]
-    verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: cephrgw-operator
-subjects:
-  - kind: ServiceAccount
-    name: cephrgw-operator
-    namespace: cephrgw-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: cephrgw-operator

apps/base/cephrgw-system/vaultauth.yaml

@@ -1,21 +0,0 @@
----
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultAuth
-metadata:
-  name: default
-  namespace: cephrgw-system
-spec:
-  method: kubernetes
-  mount: k8s/au/syd1
-  vaultConnectionRef: vso-system/default
-  allowedNamespaces:
-    - cephrgw-system
-  kubernetes:
-    # Shared "default" role: binds the namespace's default ServiceAccount and
-    # grants the templated kv/kubernetes/namespace/<ns>/<sa>/* read policy, so
-    # no per-app terraform-vault change is needed.
-    role: default
-    serviceAccount: default
-    audiences:
-      - vault
-    tokenExpirationSeconds: 600

apps/base/cephrgw-system/vaultstaticsecret.yaml

@@ -1,30 +0,0 @@
----
-# Renders the radosgw credentials from Vault into the cephrgw-credentials
-# Secret the operator Deployment consumes via envFrom. The KV secret's keys
-# (CEPH_RGW_ACCESS_KEY/SECRET_KEY, CEPH_RGW_ENDPOINT, optional
-# CEPH_RGW_ADMIN_ENDPOINT/REGION/CA) are copied verbatim, so they land as the
-# matching env vars.
-#
-# The path sits under the templated default policy
-# (kv/data/kubernetes/namespace/<ns>/<sa>/*), so it needs no dedicated Vault
-# role or policy. Seed the values with:
-#   vault kv put kv/kubernetes/namespace/cephrgw-system/default/cephrgw-credentials \
-#     CEPH_RGW_ENDPOINT=https://s3.ceph.unkin.net \
-#     CEPH_RGW_ADMIN_ENDPOINT=https://radosgw.service.consul:443 \
-#     CEPH_RGW_ACCESS_KEY=... CEPH_RGW_SECRET_KEY=...
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: cephrgw-credentials
-  namespace: cephrgw-system
-spec:
-  vaultAuthRef: default
-  mount: kv
-  type: kv-v2
-  path: kubernetes/namespace/cephrgw-system/default/cephrgw-credentials
-  refreshAfter: 5m
-  hmacSecretData: true
-  destination:
-    name: cephrgw-credentials
-    create: true
-    overwrite: true

apps/base/cephrgw-system/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: cephrgw-operator-vpa
-  namespace: cephrgw-system
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: cephrgw-operator
-  updatePolicy:
-    updateMode: "Off"

apps/base/cert-manager/clusterissuer_letsencrypt-staging.yaml

@@ -1,21 +0,0 @@
----
-apiVersion: cert-manager.io/v1
-kind: ClusterIssuer
-metadata:
-  name: letsencrypt-staging
-spec:
-  acme:
-    server: https://acme-staging-v02.api.letsencrypt.org/directory
-    email: admin@unkin.net
-    privateKeySecretRef:
-      name: letsencrypt-staging-account-key
-    solvers:
-      - dns01:
-          cnameStrategy: Follow
-          rfc2136:
-            nameserver: "198.18.199.53:53"
-            tsigKeyName: certmanager
-            tsigAlgorithm: HMACSHA256
-            tsigSecretSecretRef:
-              name: certmanager-tsig
-              key: secret

apps/base/cert-manager/clusterissuer_letsencrypt.yaml

@@ -1,21 +0,0 @@
----
-apiVersion: cert-manager.io/v1
-kind: ClusterIssuer
-metadata:
-  name: letsencrypt
-spec:
-  acme:
-    server: https://acme-v02.api.letsencrypt.org/directory
-    email: admin@unkin.net
-    privateKeySecretRef:
-      name: letsencrypt-account-key
-    solvers:
-      - dns01:
-          cnameStrategy: Follow
-          rfc2136:
-            nameserver: "198.18.199.53:53"
-            tsigKeyName: certmanager
-            tsigAlgorithm: HMACSHA256
-            tsigSecretSecretRef:
-              name: certmanager-tsig
-              key: secret

apps/base/cert-manager/clusterissuer_vault-issuer.yaml

@@ -1,27 +0,0 @@
----
-apiVersion: cert-manager.io/v1
-kind: ClusterIssuer
-metadata:
-  name: vault-issuer
-  labels:
-    app.kubernetes.io/instance: cert-manager-config
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/name: cert-manager-config
-  annotations:
-    meta.helm.sh/release-name: cert-manager-clusterissuer
-    meta.helm.sh/release-namespace: cert-manager
-spec:
-  vault:
-    server: https://vault.service.consul:8200
-    path: pki_int/sign/servers_default
-    caBundleSecretRef:
-      key: ca.crt
-      name: vault-ca-cert
-    auth:
-      kubernetes:
-        mountPath: /v1/auth/k8s/au/syd1
-        role: cert_manager_issuer
-        serviceAccountRef:
-          name: cert-manager-vault-issuer
-          audiences:
-            - vault

apps/base/cert-manager/kustomization.yaml

@@ -7,7 +7,4 @@ resources:
   - serviceaccount.yaml
   - clusterrole.yaml
   - clusterrolebinding.yaml
-  - clusterissuer_vault-issuer.yaml
   - vmservicescrape.yaml
-  - clusterissuer_letsencrypt.yaml
-  - clusterissuer_letsencrypt-staging.yaml

apps/base/certificates/vault-ca-cert.yaml

@@ -1,6 +1,4 @@
 ---
-# pre-commit: allow-plain-secret -- public CA bundle; this secret bootstraps
-# trust in Vault itself and therefore cannot be Vault-sourced.
 apiVersion: v1
 kind: Secret
 metadata:
@@ -30,7 +28,7 @@ stringData:
     mitItX+RAgMBAAGjgewwgekwDgYDVR0PAQH/BAQDAgEGMA8GA1UdEwEB/wQFMAMB
     Af8wHQYDVR0OBBYEFEp/+grAdVqRSeb9xJjSeZYNW32MMB8GA1UdIwQYMBaAFBqc
     v6Y+hfHt4EjgKa/uoQGEHTknMEcGCCsGAQUFBwEBBDswOTA3BggrBgEFBQcwAoYr
-    aHR0cHM6Ly92YXVsdC5zZXJ2dWNlLmNvbnN1bC92MS9wa2lfcm9vdC9jYTA9BgNV
+    aHR0cHM6Ly92YXVsdC5zZXJ2aWNlLmNvbnN1bC92MS9wa2lfcm9vdC9jYTA9BgNV
     HR8ENjA0MDKgMKAuhixodHRwczovL3ZhdWx0LnNlcnZpY2UuY29uc3VsL3YxL3Br
     aV9yb290L2NybDANBgkqhkiG9w0BAQsFAAOCAQEAM0FS8tscZe7yly/gM7jO6lx5
     muMFusifjUIrcQGnZBkoECeuUVPNTs3e/Th+XaxjCnmSpqSNT3z9Irr6Hhxf7n03

apps/base/clickhouse-system/kustomization.yaml

@@ -1,6 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml

apps/base/clickhouse-system/namespace.yaml

@@ -1,7 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  labels:
-    app.kubernetes.io/name: clickhouse-system
-  name: clickhouse-system

apps/base/consul/README.md

@@ -1,30 +0,0 @@
-# consul (k8s)
-
-Consul server cluster (DC `au-syd1`), deployed via the HashiCorp helm chart with
-ACLs enabled (`default_policy: deny`, parity with the VM cluster).
-
-## API access (ACL auth)
-
-The HTTP API and UI are served on port 8500 behind the gateway at
-`https://consul.k8s.syd1.au.unkin.net` (and `https://consul.service.consul`).
-With ACLs enabled, requests beyond the anonymous policy require a token:
-
-```bash
-# management (bootstrap) token — seeded from Vault, synced by VSO into the
-# consul-bootstrap-acl-token secret; same value as the VM cluster's
-# initial_management token:
-CONSUL_HTTP_TOKEN=$(vault kv get -field=token kv/kubernetes/namespace/consul/default/bootstrap-acl-token)
-
-curl -H "X-Consul-Token: $CONSUL_HTTP_TOKEN" https://consul.k8s.syd1.au.unkin.net/v1/status/leader
-
-# consul CLI:
-CONSUL_HTTP_ADDR=https://consul.k8s.syd1.au.unkin.net CONSUL_HTTP_TOKEN=$CONSUL_HTTP_TOKEN consul members
-```
-
-The UI at the same hostname exposes an ACL login (top right) — paste a token.
-Anonymous requests get the anonymous-token policy only (reads for DNS/service
-discovery; no writes, no ACL/token APIs).
-
-Prefer short-lived tokens minted by Vault's consul secrets engine over the
-management token for day-to-day use; the terraform-* CI roles already work this
-way.

apps/base/consul/httproute.yaml

@@ -46,8 +46,8 @@ spec:
     - backendRefs:
         - group: ""
           kind: Service
-          name: consul-http
-          port: 8500
+          name: consul-ui
+          port: 80
           weight: 1
       matches:
         - path:
@@ -74,8 +74,8 @@ spec:
     - backendRefs:
         - group: ""
           kind: Service
-          name: consul-http
-          port: 8500
+          name: consul-ui
+          port: 80
           weight: 1
       matches:
         - path:

apps/base/consul/kustomization.yaml

@@ -6,6 +6,3 @@ resources:
   - namespace.yaml
   - gateway.yaml
   - httproute.yaml
-  - service.yaml
-  - vaultauth.yaml
-  - vaultstaticsecret.yaml

apps/base/consul/service.yaml

@@ -1,25 +0,0 @@
----
-# ClusterIP service targeting the consul server pods' HTTP API (8500).
-# The HashiCorp chart only ships consul-ui (also 8500 via the server pods)
-# and the headless consul-server; this named service gives the Gateway a
-# stable API backend. Consul serves both the HTTP API and the UI (at /ui/)
-# on this same port, so routing the API hostname here preserves the UI too.
-apiVersion: v1
-kind: Service
-metadata:
-  name: consul-http
-  namespace: consul
-  labels:
-    app.kubernetes.io/name: consul
-    app.kubernetes.io/instance: consul
-spec:
-  type: ClusterIP
-  selector:
-    app: consul
-    component: server
-    release: consul
-  ports:
-    - name: http
-      port: 8500
-      protocol: TCP
-      targetPort: 8500

apps/base/consul/vaultauth.yaml

@@ -1,18 +0,0 @@
----
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultAuth
-metadata:
-  name: default
-  namespace: consul
-spec:
-  allowedNamespaces:
-    - consul
-  kubernetes:
-    audiences:
-      - vault
-    role: default
-    serviceAccount: default
-    tokenExpirationSeconds: 600
-  method: kubernetes
-  mount: k8s/au/syd1
-  vaultConnectionRef: vso-system/default

apps/base/consul/vaultstaticsecret.yaml

@@ -1,17 +0,0 @@
----
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: bootstrap-acl-token
-  namespace: consul
-spec:
-  destination:
-    create: true
-    name: consul-bootstrap-acl-token
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/consul/default/bootstrap-acl-token
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default

apps/base/dhcp-system/cr/keaapi.yaml

@@ -1,25 +0,0 @@
----
-# Terraform-friendly REST API for KeaSubnet/KeaClientClass CRUD. The bearer
-# token Secret is generated by the operator when absent (no plain Secret is
-# committed here); it can later be pre-seeded from Vault under the same name.
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaAPI
-metadata:
-  name: kea-api
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  replicas: 1
-  image: git.unkin.net/unkin/kea-api:v0.1.2
-  tokenSecretName: kea-api-token
-  service:
-    type: ClusterIP
-    port: 8080
-  resources:
-    requests:
-      cpu: 100m
-      memory: 64Mi
-    limits:
-      cpu: "1"
-      memory: 256Mi

apps/base/dhcp-system/cr/keaclientclasses.yaml

@@ -1,27 +0,0 @@
-# PXE boot classes matching client architecture (option 93), replacing the
-# legacy dhcpd "Legacy" and "UEFI-64" classes. Object names are lowercased to
-# satisfy RFC1123 (the operator renders the kea class name from metadata.name).
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaClientClass
-metadata:
-  name: legacy
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  archHex: ["0x0000"]
-  bootFileName: /undionly.kpxe
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaClientClass
-metadata:
-  name: uefi-64
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  archHex: ["0x0007", "0x0009"]
-  bootFileName: /ipxe.efi

apps/base/dhcp-system/cr/keacluster.yaml

@@ -1,35 +0,0 @@
----
-# HA pair fronted by a PureLB anycast Service on a NEW, unused common-pool IP
-# (198.18.200.10). This is intentionally NOT the current isc-dhcpd anycast
-# address (198.18.19.18) -- the production cutover is a separate later task.
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaCluster
-metadata:
-  name: kea
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  replicas: 2
-  image: git.unkin.net/unkin/kea:v0.1.2
-  domainName: main.unkin.net
-  defaultLeaseTime: 1200
-  maxLeaseTime: 86400
-  # No ntpServers: DHCP option 42 (ntp-servers) carries IPv4 addresses only, so
-  # the rotating AU pool.ntp.org hostnames cannot be delivered this way (kea
-  # rejects them at config load). Add concrete NTP server IPs here if needed.
-  ha:
-    mode: hot-standby
-  service:
-    type: LoadBalancer
-    ipAddressPool: common
-    loadBalancerIP: 198.18.200.10
-    annotations:
-      purelb.io/addresses: 198.18.200.10
-  resources:
-    requests:
-      cpu: 100m
-      memory: 128Mi
-    limits:
-      cpu: "1"
-      memory: 512Mi

apps/base/dhcp-system/cr/keasubnets.yaml

@@ -1,90 +0,0 @@
-# Translation of the legacy ISC dhcpd pools (puppet
-# roles/infra/dhcp/server.yaml): 198.18.13-17.0/24, each a .200-.220 pool,
-# next-server 198.18.19.19. Gateways per the original config:
-# .13/.14/.15/.16 -> .254, .17 -> .1. DNS points at the in-cluster
-# bind-resolvers PureLB IP (198.18.200.7), not the legacy 198.18.19.15.
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaSubnet
-metadata:
-  name: net-198-18-13
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  subnet: 198.18.13.0/24
-  pools:
-    - 198.18.13.200 - 198.18.13.220
-  routers: [198.18.13.254]
-  dnsServers: [198.18.200.7]
-  domainName: main.unkin.net
-  nextServer: 198.18.19.19
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaSubnet
-metadata:
-  name: net-198-18-14
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  subnet: 198.18.14.0/24
-  pools:
-    - 198.18.14.200 - 198.18.14.220
-  routers: [198.18.14.254]
-  dnsServers: [198.18.200.7]
-  domainName: main.unkin.net
-  nextServer: 198.18.19.19
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaSubnet
-metadata:
-  name: net-198-18-15
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  subnet: 198.18.15.0/24
-  pools:
-    - 198.18.15.200 - 198.18.15.220
-  routers: [198.18.15.254]
-  dnsServers: [198.18.200.7]
-  domainName: main.unkin.net
-  nextServer: 198.18.19.19
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaSubnet
-metadata:
-  name: net-198-18-16
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  subnet: 198.18.16.0/24
-  pools:
-    - 198.18.16.200 - 198.18.16.220
-  routers: [198.18.16.254]
-  dnsServers: [198.18.200.7]
-  domainName: main.unkin.net
-  nextServer: 198.18.19.19
----
-apiVersion: kea.unkin.net/v1alpha1
-kind: KeaSubnet
-metadata:
-  name: net-198-18-17
-  namespace: dhcp-system
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  clusterRef: kea
-  subnet: 198.18.17.0/24
-  pools:
-    - 198.18.17.200 - 198.18.17.220
-  routers: [198.18.17.1]
-  dnsServers: [198.18.200.7]
-  domainName: main.unkin.net
-  nextServer: 198.18.19.19

apps/base/dhcp-system/deployment.yaml

@@ -1,56 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: kea-operator
-  namespace: dhcp-system
-  labels:
-    app.kubernetes.io/name: kea-operator
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: kea-operator
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: kea-operator
-    spec:
-      serviceAccountName: kea-operator
-      securityContext:
-        runAsNonRoot: true
-      containers:
-        - name: operator
-          image: git.unkin.net/unkin/kea-operator:v0.1.2
-          args:
-            - --metrics-bind-address=:8080
-            - --health-probe-bind-address=:8081
-          ports:
-            - containerPort: 8080
-              name: metrics
-            - containerPort: 8081
-              name: health
-          readinessProbe:
-            httpGet:
-              path: /readyz
-              port: 8081
-            initialDelaySeconds: 5
-            periodSeconds: 10
-          livenessProbe:
-            httpGet:
-              path: /healthz
-              port: 8081
-            initialDelaySeconds: 15
-            periodSeconds: 20
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop: ["ALL"]
-          resources:
-            requests:
-              cpu: 50m
-              memory: 64Mi
-            limits:
-              cpu: 500m
-              memory: 256Mi

apps/base/dhcp-system/kustomization.yaml

@@ -1,17 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml
-  # CRDs are pulled from the kea-operator repo at the matching tag rather than
-  # vendored here, so they never drift from the operator.
-  - https://git.unkin.net/unkin/kea-operator/raw/tag/v0.1.0/config/crd/install.yaml
-  - rbac.yaml
-  - deployment.yaml
-  - vpa.yaml
-  # CRs (sync-wave 1) reconcile after the operator + CRDs are established.
-  - cr/keacluster.yaml
-  - cr/keasubnets.yaml
-  - cr/keaclientclasses.yaml
-  - cr/keaapi.yaml

apps/base/dhcp-system/namespace.yaml

@@ -1,5 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: dhcp-system

apps/base/dhcp-system/rbac.yaml

@@ -1,46 +0,0 @@
----
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: kea-operator
-  namespace: dhcp-system
----
-# Sourced from the kea-operator repo config/rbac/role.yaml (v0.1.0). Leader
-# election is disabled so no coordination.k8s.io/leases grant is needed.
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: kea-operator
-rules:
-  - apiGroups: [""]
-    resources: ["configmaps", "secrets", "serviceaccounts", "services"]
-    verbs: ["create", "delete", "get", "list", "patch", "update", "watch"]
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: ["apps"]
-    resources: ["deployments", "statefulsets"]
-    verbs: ["create", "delete", "get", "list", "patch", "update", "watch"]
-  - apiGroups: ["kea.unkin.net"]
-    resources: ["keaapis", "keaclientclasses", "keaclusters", "keasubnets"]
-    verbs: ["create", "delete", "get", "list", "patch", "update", "watch"]
-  - apiGroups: ["kea.unkin.net"]
-    resources:
-      ["keaapis/status", "keaclientclasses/status", "keaclusters/status", "keasubnets/status"]
-    verbs: ["get", "patch", "update"]
-  - apiGroups: ["rbac.authorization.k8s.io"]
-    resources: ["rolebindings", "roles"]
-    verbs: ["create", "delete", "get", "list", "patch", "update", "watch"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: kea-operator
-subjects:
-  - kind: ServiceAccount
-    name: kea-operator
-    namespace: dhcp-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: kea-operator

apps/base/dhcp-system/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: kea-operator-vpa
-  namespace: dhcp-system
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: kea-operator
-  updatePolicy:
-    updateMode: "Off"

apps/base/encapi/cnpg_backup.yaml

@@ -1,56 +0,0 @@
----
-# Ceph RGW (S3) backup target for the encapi CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster:
-# cephrgw CRs are namespace-scoped and CNPG reads its S3 credential Secret from
-# its own namespace, so backups are per-database rather than one shared bucket.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-encapi-backup
-  namespace: encapi
-spec:
-  displayName: "CNPG backup owner (encapi)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-encapi-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-encapi-backup-s3
-  # Keep the RGW user (and thus the keys) if this CR is ever deleted, so an
-  # in-flight restore can still reach the archive.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-encapi
-  namespace: encapi
-spec:
-  placementTarget: ec
-  bucketName: cnpg-encapi
-  # The owner user has full control of its own bucket (read + write), which is
-  # all the backup/restore identity needs — no extra BucketAccess grant.
-  ownerRef: cnpg-encapi-backup
-  versioning: false
-  tags:
-    app: encapi
-    purpose: cnpg-backup
-  # Never drop the backups if the CR is removed; retire buckets by hand.
-  retainOnDelete: true
----
-# Nightly base backup. Continuous WAL archiving is always-on via the Cluster's
-# spec.backup.barmanObjectStore; this schedules the periodic full backup that
-# WAL is layered on top of. Schedules are staggered across clusters so the 8
-# base backups do not hit RGW at once (CNPG cron is 6-field, seconds first).
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-encapi-nightly
-  namespace: encapi
-spec:
-  schedule: "0 40 2 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: postgres

apps/base/encapi/cnpg_cluster.yaml

@@ -7,35 +7,6 @@ metadata:
 spec:
   affinity:
     podAntiAffinityType: preferred
-  backup:
-    # 30-day retention (DEFAULT — adjust per cluster if needed). Enforced by CNPG
-    # against the object store on each successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-encapi
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-encapi-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-encapi-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: encapi
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
   bootstrap:
     initdb:
       database: encapi

apps/base/encapi/deployment.yaml

@@ -5,7 +5,7 @@ metadata:
   name: encapi
   namespace: encapi
   annotations:
-    configmap.reloader.stakater.com/auto: "true"
+    reloader.stakater.com/auto: "true"
 spec:
   replicas: 2
   selector:
@@ -23,7 +23,7 @@ spec:
       automountServiceAccountToken: true
       containers:
         - name: encapi
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/encapi:v0.1.1
+          image: git.unkin.net/unkin/encapi:v0.1.1
           imagePullPolicy: IfNotPresent
           ports:
             - containerPort: 8000

apps/base/encapi/kustomization.yaml

@@ -10,8 +10,6 @@ resources:
   - gateway.yaml
   - httproute.yaml
   - cnpg_cluster.yaml
-  - cnpg_backup.yaml
   - cnpg_pooler.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml
-  - vpa.yaml

apps/base/encapi/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: encapi-vpa
-  namespace: encapi
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: encapi
-  updatePolicy:
-    updateMode: "Off"

apps/base/externaldns/agent-dns-rolebinding.yaml

@@ -1,16 +0,0 @@
----
-# Confines the agent-dns service account (in bind-system) to the agent-dns
-# ClusterRole within this namespace.
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: agent-dns
-  namespace: externaldns
-subjects:
-  - kind: ServiceAccount
-    name: agent-dns
-    namespace: bind-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: agent-dns

apps/base/externaldns/kustomization.yaml

@@ -6,4 +6,3 @@ resources:
   - namespace.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml
-  - agent-dns-rolebinding.yaml

apps/base/gitea/cnpg_backup.yaml

@@ -1,46 +0,0 @@
----
-# Ceph RGW (S3) backup target for the gitea CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-gitea-backup
-  namespace: gitea
-spec:
-  displayName: "CNPG backup owner (gitea)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-gitea-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-gitea-backup-s3
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-gitea
-  namespace: gitea
-spec:
-  bucketName: cnpg-gitea
-  ownerRef: cnpg-gitea-backup
-  versioning: false
-  tags:
-    app: gitea
-    purpose: cnpg-backup
-  retainOnDelete: true
----
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-gitea-nightly
-  namespace: gitea
-spec:
-  # 6-field CNPG cron (seconds first). 04:00 — next free slot after netbox
-  # (03:40), keeping the estate's 20-minute stagger.
-  schedule: "0 0 4 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: gitea-postgres

apps/base/gitea/cnpg_cluster.yaml

@@ -1,90 +0,0 @@
----
-# Postgres for the k8s Gitea (replaces the Patroni-shared DB the VM uses). Gitea
-# already runs on Postgres, so cutover is a plain pg dump/restore (no engine
-# conversion). App-user creds come from the postgres-credentials Vault secret.
-apiVersion: postgresql.cnpg.io/v1
-kind: Cluster
-metadata:
-  name: gitea-postgres
-  namespace: gitea
-spec:
-  affinity:
-    podAntiAffinityType: preferred
-  backup:
-    # 30-day retention. Enforced by CNPG against the object store on each
-    # successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-gitea
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-gitea-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-gitea-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: gitea
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
-  bootstrap:
-    initdb:
-      database: gitea
-      encoding: UTF8
-      localeCType: C
-      localeCollate: C
-      owner: gitea
-      secret:
-        name: postgres-credentials
-  enablePDB: true
-  enableSuperuserAccess: false
-  failoverDelay: 0
-  imageName: ghcr.io/cloudnative-pg/postgresql:18.1-system-trixie
-  instances: 2
-  logLevel: info
-  monitoring:
-    customQueriesConfigMap:
-      - key: queries
-        name: cnpg-default-monitoring
-    disableDefaultQueries: false
-    enablePodMonitor: false
-  postgresql:
-    parameters:
-      max_connections: "200"
-      shared_buffers: 256MB
-  primaryUpdateMethod: restart
-  primaryUpdateStrategy: unsupervised
-  replicationSlots:
-    highAvailability:
-      enabled: true
-      slotPrefix: _cnpg_
-    synchronizeReplicas:
-      enabled: true
-    updateInterval: 30
-  resources:
-    limits:
-      cpu: "2"
-      memory: 2Gi
-    requests:
-      cpu: 250m
-      memory: 512Mi
-  smartShutdownTimeout: 180
-  startDelay: 3600
-  stopDelay: 1800
-  storage:
-    resizeInUseVolumes: true
-    size: 20Gi
-    storageClass: cephrbd-fast-delete
-  switchoverDelay: 3600

apps/base/gitea/cnpg_pooler.yaml

@@ -1,36 +0,0 @@
----
-# pgbouncer in front of the primary. Gitea opens a connection per request and
-# benefits from pooling under multiple app replicas. Session mode keeps Gitea's
-# occasional session-scoped state (advisory locks, LISTEN/NOTIFY) working.
-apiVersion: postgresql.cnpg.io/v1
-kind: Pooler
-metadata:
-  name: gitea-postgres-pooler-rw
-  namespace: gitea
-spec:
-  cluster:
-    name: gitea-postgres
-  instances: 2
-  pgbouncer:
-    parameters:
-      default_pool_size: "50"
-      max_client_conn: "200"
-    paused: false
-    poolMode: session
-  template:
-    metadata:
-      labels:
-        app: pooler-rw
-    spec:
-      affinity:
-        podAntiAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            - labelSelector:
-                matchExpressions:
-                  - key: app
-                    operator: In
-                    values:
-                      - pooler-rw
-              topologyKey: kubernetes.io/hostname
-      containers: []
-  type: rw

apps/base/gitea/gateway.yaml

@@ -1,69 +0,0 @@
----
-# HTTPS front for the k8s Gitea, served on two names:
-#   git.unkin.net              — canonical/production (apex, bind-operator zone;
-#                                DNS flip is the gated cutover step, see the doc)
-#   git.k8s.syd1.au.unkin.net  — admin/backup route (external-dns k8s.syd1 zone),
-#                                same dual-name pattern as identity.unkin.net.
-# The cert-manager Certificate (vault-issuer) takes CN git.unkin.net and gets a
-# DNS SAN for each TLS listener hostname automatically.
-apiVersion: gateway.networking.k8s.io/v1
-kind: Gateway
-metadata:
-  name: gitea
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-    app.kubernetes.io/instance: gitea
-    traefik.io/instance: internal
-  annotations:
-    cert-manager.io/cluster-issuer: vault-issuer
-    cert-manager.io/common-name: git.unkin.net
-    cert-manager.io/private-key-size: "4096"
-    # Only the k8s admin route is published by external-dns (it owns just the
-    # k8s.syd1.au.unkin.net zone). git.unkin.net lives in the apex zone and is
-    # flipped at cutover — NOT managed here.
-    external-dns.alpha.kubernetes.io/hostname: git.k8s.syd1.au.unkin.net
-    external-dns.alpha.kubernetes.io/target: 198.18.200.4
-spec:
-  gatewayClassName: traefik-internal
-  listeners:
-    - name: http-primary
-      port: 80
-      protocol: HTTP
-      hostname: git.unkin.net
-      allowedRoutes:
-        namespaces:
-          from: Same
-    - name: https-primary
-      port: 443
-      protocol: HTTPS
-      hostname: git.unkin.net
-      allowedRoutes:
-        namespaces:
-          from: Same
-      tls:
-        mode: Terminate
-        certificateRefs:
-          - group: ""
-            kind: Secret
-            name: gitea-tls
-    - name: http-admin
-      port: 80
-      protocol: HTTP
-      hostname: git.k8s.syd1.au.unkin.net
-      allowedRoutes:
-        namespaces:
-          from: Same
-    - name: https-admin
-      port: 443
-      protocol: HTTPS
-      hostname: git.k8s.syd1.au.unkin.net
-      allowedRoutes:
-        namespaces:
-          from: Same
-      tls:
-        mode: Terminate
-        certificateRefs:
-          - group: ""
-            kind: Secret
-            name: gitea-tls

apps/base/gitea/httproute.yaml

@@ -1,65 +0,0 @@
----
-apiVersion: gateway.networking.k8s.io/v1
-kind: HTTPRoute
-metadata:
-  name: gitea-http-redirect
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-    app.kubernetes.io/instance: gitea
-spec:
-  hostnames:
-    - git.unkin.net
-    - git.k8s.syd1.au.unkin.net
-  parentRefs:
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: gitea
-      sectionName: http-primary
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: gitea
-      sectionName: http-admin
-  rules:
-    - filters:
-        - type: RequestRedirect
-          requestRedirect:
-            scheme: https
-            statusCode: 301
-      matches:
-        - path:
-            type: PathPrefix
-            value: /
----
-apiVersion: gateway.networking.k8s.io/v1
-kind: HTTPRoute
-metadata:
-  name: gitea
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-    app.kubernetes.io/instance: gitea
-spec:
-  hostnames:
-    - git.unkin.net
-    - git.k8s.syd1.au.unkin.net
-  parentRefs:
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: gitea
-      sectionName: https-primary
-    - group: gateway.networking.k8s.io
-      kind: Gateway
-      name: gitea
-      sectionName: https-admin
-  rules:
-    - backendRefs:
-        - group: ""
-          kind: Service
-          name: gitea-http
-          port: 3000
-          weight: 1
-      matches:
-        - path:
-            type: PathPrefix
-            value: /

apps/base/gitea/kustomization.yaml

@@ -1,16 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml
-  - cnpg_cluster.yaml
-  - cnpg_backup.yaml
-  - cnpg_pooler.yaml
-  - valkey-deployment.yaml
-  - valkey-pvc.yaml
-  - valkey-service.yaml
-  - vaultauth.yaml
-  - vaultstaticsecret.yaml
-  - gateway.yaml
-  - httproute.yaml

apps/base/gitea/namespace.yaml

@@ -1,7 +0,0 @@
----
-apiVersion: v1
-kind: Namespace
-metadata:
-  labels:
-    app.kubernetes.io/name: gitea
-  name: gitea

apps/base/gitea/valkey-deployment.yaml

@@ -1,89 +0,0 @@
----
-# Standalone Valkey (Redis-compatible) for Gitea's session store, cache and
-# queue. The Gitea chart bundles a redis-cluster subchart, but we run our own
-# standalone Valkey here: it keeps image control in-estate (valkey/valkey,
-# already allowlisted through the artifactapi dockerhub mirror) and matches the
-# standalone-cache pattern used by litellm/netbox. One instance serves three
-# logical DBs: DB 0 = session, DB 1 = cache, DB 2 = queue. AOF persistence is
-# enabled so queued actions/webhook deliveries survive a restart.
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: gitea-valkey
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-    app.kubernetes.io/component: valkey
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: gitea-valkey
-  strategy:
-    type: Recreate
-  template:
-    metadata:
-      labels:
-        app: gitea-valkey
-        app.kubernetes.io/name: gitea
-        app.kubernetes.io/component: valkey
-    spec:
-      securityContext:
-        fsGroup: 999
-      containers:
-        - name: valkey
-          image: valkey/valkey:8-alpine
-          imagePullPolicy: IfNotPresent
-          command:
-            - valkey-server
-            - --appendonly
-            - "yes"
-            - --save
-            - "60"
-            - "1"
-          ports:
-            - containerPort: 6379
-              name: valkey
-              protocol: TCP
-          securityContext:
-            allowPrivilegeEscalation: false
-            runAsNonRoot: true
-            runAsUser: 999
-            capabilities:
-              drop:
-                - ALL
-          livenessProbe:
-            exec:
-              command:
-                - valkey-cli
-                - ping
-            failureThreshold: 3
-            initialDelaySeconds: 30
-            periodSeconds: 30
-            successThreshold: 1
-            timeoutSeconds: 5
-          readinessProbe:
-            exec:
-              command:
-                - valkey-cli
-                - ping
-            failureThreshold: 3
-            initialDelaySeconds: 5
-            periodSeconds: 10
-            successThreshold: 1
-            timeoutSeconds: 5
-          resources:
-            limits:
-              cpu: 500m
-              memory: 512Mi
-            requests:
-              cpu: 50m
-              memory: 128Mi
-          volumeMounts:
-            - mountPath: /data
-              name: data
-      restartPolicy: Always
-      volumes:
-        - name: data
-          persistentVolumeClaim:
-            claimName: gitea-valkey-data

apps/base/gitea/valkey-pvc.yaml

@@ -1,14 +0,0 @@
----
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: gitea-valkey-data
-  namespace: gitea
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 5Gi
-  storageClassName: cephrbd-fast-delete
-  volumeMode: Filesystem

apps/base/gitea/valkey-service.yaml

@@ -1,20 +0,0 @@
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: gitea-valkey
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-    app.kubernetes.io/component: valkey
-spec:
-  internalTrafficPolicy: Cluster
-  ports:
-    - name: valkey
-      port: 6379
-      protocol: TCP
-      targetPort: valkey
-  selector:
-    app: gitea-valkey
-  sessionAffinity: None
-  type: ClusterIP

apps/base/gitea/vaultauth.yaml

@@ -1,18 +0,0 @@
----
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultAuth
-metadata:
-  name: default
-  namespace: gitea
-spec:
-  allowedNamespaces:
-    - gitea
-  kubernetes:
-    audiences:
-      - vault
-    role: default
-    serviceAccount: default
-    tokenExpirationSeconds: 600
-  method: kubernetes
-  mount: k8s/au/syd1
-  vaultConnectionRef: vso-system/default

apps/base/gitea/vaultstaticsecret.yaml

@@ -1,83 +0,0 @@
----
-# CNPG app-user credentials (keys: username, password). Consumed by the Cluster
-# bootstrap (initdb.secret) AND by Gitea (gitea.config.database.PASSWD via the
-# chart's existingSecret wiring). One-time Vault seed — see the PR description.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: postgres-credentials
-  namespace: gitea
-spec:
-  destination:
-    create: true
-    name: postgres-credentials
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/gitea/default/postgres-credentials
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-# Initial Gitea admin (keys: username, password, email). Applied by the chart's
-# init job on first boot (gitea.admin.existingSecret). Local fallback account
-# that survives the Authentik OIDC cutover. One-time Vault seed.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: gitea-admin
-  namespace: gitea
-spec:
-  destination:
-    create: true
-    name: gitea-admin
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/gitea/default/gitea-admin
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-# Gitea internal secrets (keys: SECRET_KEY, INTERNAL_TOKEN). Pinned here rather
-# than chart-generated so all replicas share identical values AND so the data
-# cutover can replace them with the VM's app.ini values (SECRET_KEY encrypts
-# 2FA/mirror/oauth secrets in the DB — it MUST match the restored database).
-# One-time Vault seed.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: gitea-inner
-  namespace: gitea
-spec:
-  destination:
-    create: true
-    name: gitea-inner
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/gitea/default/gitea-inner
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-# Authentik OIDC client secret (key: client_secret). Read by the
-# terraform-authentik provider runner (policy already grants
-# kv/.../namespace/+/default/oauth-credentials) AND mounted into Gitea to
-# register the OIDC login source. One-time Vault seed.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: oauth-credentials
-  namespace: gitea
-spec:
-  destination:
-    create: true
-    name: oauth-credentials
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/gitea/default/oauth-credentials
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default

apps/base/grafana/cnpg_backup.yaml

@@ -1,56 +0,0 @@
----
-# Ceph RGW (S3) backup target for the grafana CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster:
-# cephrgw CRs are namespace-scoped and CNPG reads its S3 credential Secret from
-# its own namespace, so backups are per-database rather than one shared bucket.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-grafana-backup
-  namespace: grafana
-spec:
-  displayName: "CNPG backup owner (grafana)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-grafana-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-grafana-backup-s3
-  # Keep the RGW user (and thus the keys) if this CR is ever deleted, so an
-  # in-flight restore can still reach the archive.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-grafana
-  namespace: grafana
-spec:
-  placementTarget: ec
-  bucketName: cnpg-grafana
-  # The owner user has full control of its own bucket (read + write), which is
-  # all the backup/restore identity needs — no extra BucketAccess grant.
-  ownerRef: cnpg-grafana-backup
-  versioning: false
-  tags:
-    app: grafana
-    purpose: cnpg-backup
-  # Never drop the backups if the CR is removed; retire buckets by hand.
-  retainOnDelete: true
----
-# Nightly base backup. Continuous WAL archiving is always-on via the Cluster's
-# spec.backup.barmanObjectStore; this schedules the periodic full backup that
-# WAL is layered on top of. Schedules are staggered across clusters so the 8
-# base backups do not hit RGW at once (CNPG cron is 6-field, seconds first).
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-grafana-nightly
-  namespace: grafana
-spec:
-  schedule: "0 20 3 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: postgres

apps/base/grafana/cnpg_cluster.yaml

@@ -7,35 +7,6 @@ metadata:
 spec:
   affinity:
     podAntiAffinityType: preferred
-  backup:
-    # 30-day retention (DEFAULT — adjust per cluster if needed). Enforced by CNPG
-    # against the object store on each successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-grafana
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-grafana-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-grafana-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: grafana
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
   bootstrap:
     initdb:
       database: grafana

apps/base/grafana/grafana.yaml

@@ -26,13 +26,6 @@ spec:
                     secretKeyRef:
                       name: oauth-credentials
                       key: client_secret
-              # identity.unkin.net is served by the internal unkin.net CA, which
-              # the stock Grafana image doesn't trust. Mount the reflected
-              # vault-ca-cert and point generic_oauth's tls_client_ca at it.
-              volumeMounts:
-                - name: vault-ca-cert
-                  mountPath: /etc/grafana/vault-ca
-                  readOnly: true
               resources:
                 requests:
                   cpu: 100m
@@ -40,13 +33,6 @@ spec:
                 limits:
                   cpu: "1"
                   memory: 1Gi
-          volumes:
-            - name: vault-ca-cert
-              secret:
-                secretName: vault-ca-cert
-                items:
-                  - key: ca.crt
-                    path: ca.crt
   config:
     server:
       root_url: "https://grafana.k8s.syd1.au.unkin.net"
@@ -65,16 +51,10 @@ spec:
       allow_sign_up: "true"
       use_pkce: "true"
       client_id: "grafana"
-      # ak_groups = hierarchical group claim from terraform-authentik (carries
-      # permission groups inherited via role groups).
-      scopes: "openid email profile ak_groups"
+      scopes: "openid email profile"
       auth_url: "https://identity.unkin.net/application/o/authorize/"
       token_url: "https://identity.unkin.net/application/o/token/"
       api_url: "https://identity.unkin.net/application/o/userinfo/"
-      # Trust the internal unkin.net CA that signs identity.unkin.net's cert
-      # (mounted from the reflected vault-ca-cert Secret).
-      tls_client_ca: "/etc/grafana/vault-ca/ca.crt"
-      # Authentik permission groups -> Grafana roles. akP-grafana-admin is granted
-      # to akR-global-admin members (and direct members) via terraform-authentik.
-      role_attribute_path: "contains(ak_groups[*], 'akP-grafana-admin') && 'Admin' || 'Viewer'"
+      # Authentik groups -> Grafana roles (adjust group name as needed).
+      role_attribute_path: "contains(groups[*], 'grafana-admins') && 'Admin' || 'Viewer'"
       role_attribute_strict: "false"

apps/base/grafana/kustomization.yaml

@@ -5,7 +5,6 @@ kind: Kustomization
 resources:
   - namespace.yaml
   - cnpg_cluster.yaml
-  - cnpg_backup.yaml
   - cnpg_pooler.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml

apps/base/kanidm/kustomization.yaml

@@ -14,7 +14,6 @@ resources:
   - gateway.yaml
   - httproute.yaml
   - tlsroute.yaml
-  - vpa.yaml
 
 configMapGenerator:
   - name: kanidm-config

apps/base/kanidm/statefulset.yaml

@@ -5,8 +5,7 @@ metadata:
   name: kanidm
   namespace: kanidm
   annotations:
-    configmap.reloader.stakater.com/auto: "true"
-    secret.reloader.stakater.com/reload: "kanidm-tls"
+    reloader.stakater.com/auto: "true"
   labels:
     app.kubernetes.io/name: kanidm
     app.kubernetes.io/instance: kanidm

apps/base/kanidm/vpa.yaml

@@ -1,13 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: kanidm-vpa
-  namespace: kanidm
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: StatefulSet
-    name: kanidm
-  updatePolicy:
-    updateMode: "Off"

apps/base/litellm/cnpg_backup.yaml

@@ -1,56 +0,0 @@
----
-# Ceph RGW (S3) backup target for the litellm CNPG cluster, provisioned by the
-# in-estate cephrgw-operator. One dedicated bucket + owner user per cluster:
-# cephrgw CRs are namespace-scoped and CNPG reads its S3 credential Secret from
-# its own namespace, so backups are per-database rather than one shared bucket.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: cnpg-litellm-backup
-  namespace: litellm
-spec:
-  displayName: "CNPG backup owner (litellm)"
-  # RGW users are global; keep the uid namespace-qualified so it never collides.
-  uid: cnpg-litellm-backup
-  maxBuckets: 5
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT) into this Secret; the Cluster's barmanObjectStore consumes it.
-  secretName: cnpg-litellm-backup-s3
-  # Keep the RGW user (and thus the keys) if this CR is ever deleted, so an
-  # in-flight restore can still reach the archive.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: cnpg-litellm
-  namespace: litellm
-spec:
-  placementTarget: ec
-  bucketName: cnpg-litellm
-  # The owner user has full control of its own bucket (read + write), which is
-  # all the backup/restore identity needs — no extra BucketAccess grant.
-  ownerRef: cnpg-litellm-backup
-  versioning: false
-  tags:
-    app: litellm
-    purpose: cnpg-backup
-  # Never drop the backups if the CR is removed; retire buckets by hand.
-  retainOnDelete: true
----
-# Nightly base backup. Continuous WAL archiving is always-on via the Cluster's
-# spec.backup.barmanObjectStore; this schedules the periodic full backup that
-# WAL is layered on top of. Schedules are staggered across clusters so the 8
-# base backups do not hit RGW at once (CNPG cron is 6-field, seconds first).
-apiVersion: postgresql.cnpg.io/v1
-kind: ScheduledBackup
-metadata:
-  name: cnpg-litellm-nightly
-  namespace: litellm
-spec:
-  schedule: "0 20 1 * * *"
-  immediate: false
-  backupOwnerReference: self
-  method: barmanObjectStore
-  cluster:
-    name: litellm-postgres

apps/base/litellm/cnpg_cluster.yaml

@@ -7,35 +7,6 @@ metadata:
 spec:
   affinity:
     podAntiAffinityType: preferred
-  backup:
-    # 30-day retention (DEFAULT — adjust per cluster if needed). Enforced by CNPG
-    # against the object store on each successful base backup.
-    retentionPolicy: 30d
-    barmanObjectStore:
-      # Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
-      destinationPath: s3://cnpg-litellm
-      endpointURL: https://s3.ceph.unkin.net
-      # radosgw serves a Vault-PKI cert; trust the internal CA (reflected into
-      # every namespace as the vault-ca-cert Secret).
-      endpointCA:
-        name: vault-ca-cert
-        key: ca.crt
-      # Keys minted by the ObjectStoreUser in cnpg_backup.yaml; never hardcoded.
-      s3Credentials:
-        accessKeyId:
-          name: cnpg-litellm-backup-s3
-          key: AWS_ACCESS_KEY_ID
-        secretAccessKey:
-          name: cnpg-litellm-backup-s3
-          key: AWS_SECRET_ACCESS_KEY
-      # Path prefix within the bucket; keep stable across restores (see docs).
-      serverName: litellm
-      data:
-        compression: bzip2
-        jobs: 2
-      wal:
-        compression: zstd
-        maxParallel: 2
   bootstrap:
     initdb:
       database: litellm
@@ -48,7 +19,7 @@ spec:
   enablePDB: true
   enableSuperuserAccess: false
   failoverDelay: 0
-  imageName: ghcr.io/cloudnative-pg/postgresql:17-system-trixie
+  imageName: ghcr.io/cloudnative-pg/postgresql:17-minimal-trixie
   instances: 3
   logLevel: info
   maxSyncReplicas: 0

apps/base/litellm/deployment.yaml

@@ -11,28 +11,10 @@ spec:
   template:
     metadata:
       annotations:
-        configmap.reloader.stakater.com/auto: "true"
-        secret.reloader.stakater.com/reload: "vault-ca-cert"
+        reloader.stakater.com/auto: "true"
       labels:
         app: litellm
     spec:
-      # LiteLLM's SSO client reaches identity.unkin.net, whose cert is signed by
-      # the internal unkin.net CA. Combine the image's public roots with the
-      # reflected vault-ca-cert into one bundle (SSL_CERT_FILE/REQUESTS_CA_BUNDLE
-      # in litellm-env point at it) so internal OIDC and public HTTPS both work.
-      initContainers:
-        - name: combine-certs
-          image: alpine:3
-          command:
-            - sh
-            - -c
-            - cat /etc/ssl/certs/ca-certificates.crt /custom-ca/ca.crt > /combined-certs/ca-certificates.crt
-          volumeMounts:
-            - name: vault-ca-cert
-              mountPath: /custom-ca
-              readOnly: true
-            - name: combined-certs
-              mountPath: /combined-certs
       containers:
         - name: litellm
           image: docker.litellm.ai/berriai/litellm-database:main-stable
@@ -48,14 +30,6 @@ spec:
             - containerPort: 4000
               name: http
               protocol: TCP
-          env:
-            # Authentik OIDC client secret (SSO); non-secret SSO config is in the
-            # litellm-env ConfigMap.
-            - name: GENERIC_CLIENT_SECRET
-              valueFrom:
-                secretKeyRef:
-                  name: oauth-credentials
-                  key: client_secret
           envFrom:
             - secretRef:
                 name: litellm-credentials
@@ -90,19 +64,8 @@ spec:
             - mountPath: /app/config.yaml
               name: config
               subPath: config.yaml
-            - name: combined-certs
-              mountPath: /etc/ssl/combined
-              readOnly: true
       restartPolicy: Always
       volumes:
         - name: config
           configMap:
             name: litellm-config
-        - name: vault-ca-cert
-          secret:
-            secretName: vault-ca-cert
-            items:
-              - key: ca.crt
-                path: ca.crt
-        - name: combined-certs
-          emptyDir: {}

apps/base/litellm/kustomization.yaml

@@ -4,7 +4,6 @@ kind: Kustomization
 
 resources:
   - cnpg_cluster.yaml
-  - cnpg_backup.yaml
   - cnpg_pooler.yaml
   - deployment.yaml
   - hpa.yaml
@@ -16,7 +15,6 @@ resources:
   - services.yaml
   - vaultauth.yaml
   - vaultstaticsecret.yaml
-  - vpa.yaml
 
 configMapGenerator:
   - name: litellm-config
@@ -27,24 +25,5 @@ configMapGenerator:
   - name: litellm-env
     literals:
       - STORE_MODEL_IN_DB=True
-      # Emit structured JSON logs so the Tier-2 vector litellm pipeline can parse
-      # model/tokens/latency/key/status (logs.k8s.litellm.*).
-      - JSON_LOGS=True
-      # Authentik OIDC SSO (generic). Client secret is injected from the
-      # oauth-credentials Secret in the Deployment; endpoints match the other
-      # apps (identity.unkin.net). PROXY_BASE_URL is required for SSO.
-      - GENERIC_CLIENT_ID=litellm
-      - GENERIC_AUTHORIZATION_ENDPOINT=https://identity.unkin.net/application/o/authorize/
-      - GENERIC_TOKEN_ENDPOINT=https://identity.unkin.net/application/o/token/
-      - GENERIC_USERINFO_ENDPOINT=https://identity.unkin.net/application/o/userinfo/
-      # litellm_role scope carries the Authentik-computed role claim; LiteLLM
-      # reads it via GENERIC_USER_ROLE_ATTRIBUTE and maps to proxy_admin/etc.
-      - GENERIC_SCOPE=openid email profile litellm_role
-      - GENERIC_USER_ROLE_ATTRIBUTE=litellm_role
-      - PROXY_BASE_URL=https://litellm.k8s.syd1.au.unkin.net
-      # Trust the internal unkin.net CA (identity.unkin.net) via the combined
-      # bundle assembled by the combine-certs init container.
-      - SSL_CERT_FILE=/etc/ssl/combined/ca-certificates.crt
-      - REQUESTS_CA_BUNDLE=/etc/ssl/combined/ca-certificates.crt
     options:
       disableNameSuffixHash: true

apps/base/litellm/vaultstaticsecret.yaml

@@ -18,24 +18,6 @@ spec:
 ---
 apiVersion: secrets.hashicorp.com/v1beta1
 kind: VaultStaticSecret
-metadata:
-  name: oauth-credentials
-  namespace: litellm
-spec:
-  destination:
-    create: true
-    name: oauth-credentials
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  # Same secret Authentik sets on the litellm OAuth2 provider (key: client_secret).
-  path: kubernetes/namespace/litellm/default/oauth-credentials
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
 metadata:
   name: litellm-credentials
   namespace: litellm

apps/base/litellm/vpa.yaml

@@ -1,29 +0,0 @@
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: litellm-vpa
-  namespace: litellm
-  # NOTE: this workload also has an HPA. updateMode Off is recommendation-only
-  # and does not act, so there is no HPA/VPA conflict today. Do not flip to Auto/
-  # Initial without first moving the HPA off CPU/memory (VPA owns those under Auto).
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: litellm
-  updatePolicy:
-    updateMode: "Off"
----
-apiVersion: autoscaling.k8s.io/v1
-kind: VerticalPodAutoscaler
-metadata:
-  name: redis-vpa
-  namespace: litellm
-spec:
-  targetRef:
-    apiVersion: apps/v1
-    kind: Deployment
-    name: redis
-  updatePolicy:
-    updateMode: "Off"

apps/base/logging/cephrgw.yaml

@@ -1,43 +0,0 @@
----
-# S3 bucket (Ceph RGW) for the long-term raw-log archive, provisioned by the
-# in-estate cephrgw-operator. The archiver Vector deployment writes here.
-apiVersion: ceph.unkin.net/v1alpha1
-kind: ObjectStoreUser
-metadata:
-  name: logs-archive-owner
-  namespace: logging
-spec:
-  displayName: "Logging raw-archive bucket owner"
-  maxBuckets: 5
-  quota:
-    enabled: true
-    # 5 TiB soft cap; real retention is enforced RGW-side by a bucket lifecycle
-    # policy (see PR notes) — the operator does not manage lifecycle.
-    maxSizeBytes: 5497558138880
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: Bucket
-metadata:
-  name: logs-archive
-  namespace: logging
-spec:
-  bucketName: logs-archive
-  ownerRef: logs-archive-owner
-  versioning: false
-  tags:
-    app: logging
-    purpose: raw-log-archive
-  # Keep the bucket (and its objects) if this CR is ever deleted.
-  retainOnDelete: true
----
-apiVersion: ceph.unkin.net/v1alpha1
-kind: BucketAccess
-metadata:
-  name: logs-archive-writer
-  namespace: logging
-spec:
-  bucketRef: logs-archive
-  level: read-write
-  # Operator writes AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY (+ RGW_UID,
-  # S3_ENDPOINT, BUCKET_NAME) into this Secret; the archiver consumes it.
-  secretName: logs-archive-s3

apps/base/logging/clickhouseinstallation.yaml

@@ -1,80 +0,0 @@
----
-apiVersion: clickhouse.altinity.com/v1
-kind: ClickHouseInstallation
-metadata:
-  name: logs
-  namespace: logging
-spec:
-  defaults:
-    templates:
-      dataVolumeClaimTemplate: data-volume
-      serviceTemplate: chi-service
-      podTemplate: clickhouse
-  configuration:
-    users:
-      # Password hash is sourced from the Vault-synced clickhouse-credentials
-      # Secret; the plaintext never lands in git or the ClickHouse config.
-      vector/password_sha256_hex:
-        valueFrom:
-          secretKeyRef:
-            name: clickhouse-credentials
-            key: password_sha256_hex
-      vector/networks/ip:
-        - "::/0"
-      vector/profile: default
-      vector/quota: default
-      # Allow the vector user to create the logs database/table (bootstrap Job)
-      # and to INSERT. Restrict the built-in default user to loopback only.
-      vector/access_management: "1"
-      default/networks/ip:
-        - "127.0.0.1"
-        - "::1"
-    profiles:
-      default/max_memory_usage: "10000000000"
-      default/max_execution_time: "120"
-    clusters:
-      - name: logs
-        layout:
-          shardsCount: 1
-          replicasCount: 1
-  templates:
-    volumeClaimTemplates:
-      - name: data-volume
-        spec:
-          storageClassName: cephrbd-fast-delete
-          accessModes:
-            - ReadWriteOnce
-          resources:
-            requests:
-              # 3d TTL on logs.raw. At ~130 GiB/day raw, ClickHouse LZ4/ZSTD
-              # (~6x on log text) stores ~20-25 GiB/day => ~60-75 GiB/3d, plus
-              # merge headroom (~2x peak). logs.raw is the only table. 150Gi
-              # gives comfortable headroom; long-term data lives in S3, not here.
-              storage: 150Gi
-    serviceTemplates:
-      - name: chi-service
-        generateName: "clickhouse-{chi}"
-        spec:
-          type: ClusterIP
-          ports:
-            - name: http
-              port: 8123
-            - name: tcp
-              port: 9000
-    podTemplates:
-      - name: clickhouse
-        spec:
-          securityContext:
-            fsGroup: 101
-            runAsUser: 101
-            runAsGroup: 101
-          containers:
-            - name: clickhouse
-              image: artifactapi.k8s.syd1.au.unkin.net/dockerhub/clickhouse/clickhouse-server:24.8
-              resources:
-                requests:
-                  cpu: 500m
-                  memory: 2Gi
-                limits:
-                  cpu: "2"
-                  memory: 8Gi