feat(open-webui): HA deployment with CNPG, PDB, and session persistence

- Switch from SQLite/PVC to CNPG PostgreSQL (3 instances, low-resource)
  with a transaction-mode PgBouncer pooler (2 instances)
- Raise open-webui replicas to 3 with priorityClassName: power
- Add PodDisruptionBudget (minAvailable: 1)
- Add Gateway API sessionPersistence (cookie) on the HTTPS HTTPRoute
  so WebSocket connections stick to the same backend pod
- Add postgres-credentials VaultStaticSecret; DATABASE_URL must be
  added to kv/kubernetes/namespace/open-webui/default/open-webui-credentials

.pre-commit-config.yaml

@@ -40,10 +40,3 @@ repos:
         entry: ci/validate-no-secrets.sh
         language: system
         pass_filenames: false
-      - id: conftest_policies
-        name: OPA policy checks (conftest)
-        entry: conftest test --policy policy/
-        language: system
-        types: [yaml]
-        exclude: ".*/charts/.*|.*/templates/.*|\\.woodpecker/.*"
-        pass_filenames: true

apps/base/artifactapi/resources/conf.d/remote-generic.yaml

@@ -36,6 +36,7 @@ remotes:
       - "neovim/neovim/.*/nvim-linux-x86_64.tar.gz$"
       - "nzbgetcom/nzbget/.*/nzbget-.*.x86_64.rpm$"
       - "onedr0p/exportarr/.*/exportarr_.*_linux_amd64.tar.gz$"
+      - "open-policy-agent/conftest/.*/conftest_.*_Linux_x86_64.tar.gz$"
       - "openbao/openbao-plugins/.*/openbao-plugin-secrets-consul_linux_amd64_.*.tar.gz$"
       - "openbao/openbao-plugins/.*/openbao-plugin-secrets-nomad_linux_amd64_.*.tar.gz$"
       - "prometheus-community/bind_exporter/.*/bind_exporter-.*.linux-amd64.tar.gz$"

apps/base/kanidm/README.md

@@ -0,0 +1,32 @@
+# kanidm
+
+Single-replica kanidm identity server deployment.
+
+## Initial setup
+
+After the pod starts for the first time, generate the admin and idm_admin credentials:
+
+```bash
+kubectl exec -n kanidm kanidm-0 -- /sbin/kanidmd recover-account admin
+kubectl exec -n kanidm kanidm-0 -- /sbin/kanidmd recover-account idm_admin
+```
+
+## Adding replication
+
+If replication is needed in the future:
+
+1. Scale the StatefulSet to 3 replicas and add `podAntiAffinity` to spread across nodes.
+2. Add a `[replication]` section to `configmap.yaml` per pod (origin is pod-specific:
+   `repl://kanidm-N.kanidm-headless.kanidm.svc.cluster.local:8444`).
+3. Add the replication port (8444) back to the StatefulSet container ports and headless service.
+4. Restore `rbac.yaml` for the cert-publisher sidecar, or exchange certificates manually:
+
+```bash
+# On each pod, get its replication certificate
+kubectl exec -n kanidm kanidm-0 -- /sbin/kanidmd renew-replication-certificate
+
+# Add each peer's certificate to the other pods' configs under:
+# [replication."repl://<peer-fqdn>:8444"]
+# type = "mutual-pull"
+# partner_cert = "<cert>"
+```

apps/base/kanidm/configmap.yaml

@@ -1,40 +0,0 @@
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: kanidm-config
-  namespace: kanidm
-  labels:
-    app.kubernetes.io/name: kanidm
-    app.kubernetes.io/instance: kanidm
-data:
-  server.toml: |
-    version = "2"
-
-    domain = "auth.unkin.net"
-    origin = "https://auth.unkin.net"
-    bindaddress = "[::]:8443"
-    db_path = "/data/kanidm.db"
-    db_arc_size = 2048
-    tls_chain = "/data/tls/tls.crt"
-    tls_key = "/data/tls/tls.key"
-    log_level = "info"
-
-    [online_backup]
-    path = "/data/backups/"
-    schedule = "0 22 * * *"
-    versions = 7
-
-    [replication]
-    origin = "__REPL_ORIGIN__"
-    bindaddress = "[::]:8444"
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: kanidm-repl-certs
-  namespace: kanidm
-  labels:
-    app.kubernetes.io/name: kanidm
-    app.kubernetes.io/instance: kanidm
-data: {}

apps/base/kanidm/kustomization.yaml

@@ -5,12 +5,23 @@ kind: Kustomization
 resources:
   - namespace.yaml
   - serviceaccount.yaml
-  - rbac.yaml
   - certificate.yaml
-  - configmap.yaml
   - service.yaml
   - statefulset.yaml
   - poddisruptionbudget.yaml
   - gateway.yaml
   - httproute.yaml
   - tlsroute.yaml
+
+configMapGenerator:
+  - name: kanidm-config
+    namespace: kanidm
+    options:
+      disableNameSuffixHash: true
+      labels:
+        app.kubernetes.io/name: kanidm
+        app.kubernetes.io/instance: kanidm
+    files:
+      - server-0.toml=resources/server-0.toml
+      - server-1.toml=resources/server-1.toml
+      - server-2.toml=resources/server-2.toml

apps/base/kanidm/resources/server-0.toml

@@ -0,0 +1,27 @@
+version = "2"
+
+domain = "auth.unkin.net"
+origin = "https://auth.unkin.net"
+bindaddress = "[::]:8443"
+db_path = "/data/kanidm.db"
+db_arc_size = 2048
+tls_chain = "/data/tls/tls.crt"
+tls_key = "/data/tls/tls.key"
+log_level = "info"
+
+[online_backup]
+path = "/data/backups/"
+schedule = "0 22 * * *"
+versions = 7
+
+[replication]
+origin = "repl://kanidm-0.kanidm-headless.kanidm.svc.cluster.local:8444"
+bindaddress = "[::]:8444"
+
+[replication."repl://kanidm-1.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-TCCAZ-gAwIBAgIRASqOpORz60wiv7wF_7oBOxQwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkMmE4ZWE0ZTQtNzNlYi00YzIyLWJmYmMtMDVmZmJhMDEzYjE0MRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMyODM5WhcNMzAwNTI1MTMyODM5WjBMMS0wKwYDVQQDDCQyYThlYTRlNC03M2ViLTRjMjItYmZiYy0wNWZmYmEwMTNiMTQxGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABFQP3zpFRt7TCOhzrUpOJBojn-sC2LmqZUub8P2ymVdIQbmoAyh4Q8Me0hNWJFyuFDnnqO06dt5I2iv0910-X6KjYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMS5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0gAMEUCIGjl58U6apcDjMEPIca8Wwg_JMfuMvV-uVcJI49Gl_9GAiEA2tFdb9rnFeBI7mwysScf5UsmY3ZziMD3UVm1vWN2IKs"
+
+[replication."repl://kanidm-2.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-TCCAZ-gAwIBAgIRAeFGUAJbCkJ2vzf_Vv4qjeUwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkZTE0NjUwMDItNWIwYS00Mjc2LWJmMzctZmY1NmZlMmE4ZGU1MRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMyOTEwWhcNMzAwNTI1MTMyOTEwWjBMMS0wKwYDVQQDDCRlMTQ2NTAwMi01YjBhLTQyNzYtYmYzNy1mZjU2ZmUyYThkZTUxGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABCrncHSbDNSV3_aOSZ14plbVfrvSXQQL9MOqvrDKlf_Q6WbcA8OrTUjs3Jt0Q2beWjC3Z5-5c9fGu8M_k2iVWf-jYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMi5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0gAMEUCIQDHY5Yl-bhDTuJaYnHSMSiSAEWPrDcRVzvfmOJukuJ1QQIgSwgyeSG3K0MY87DI1RDYAdZlpP1YOK3Yatj7-YSXPC0"

apps/base/kanidm/resources/server-1.toml

@@ -0,0 +1,27 @@
+version = "2"
+
+domain = "auth.unkin.net"
+origin = "https://auth.unkin.net"
+bindaddress = "[::]:8443"
+db_path = "/data/kanidm.db"
+db_arc_size = 2048
+tls_chain = "/data/tls/tls.crt"
+tls_key = "/data/tls/tls.key"
+log_level = "info"
+
+[online_backup]
+path = "/data/backups/"
+schedule = "0 22 * * *"
+versions = 7
+
+[replication]
+origin = "repl://kanidm-1.kanidm-headless.kanidm.svc.cluster.local:8444"
+bindaddress = "[::]:8444"
+
+[replication."repl://kanidm-0.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-jCCAZ-gAwIBAgIRAVKuoPDpF0IBnvFjCwdK41EwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkNTJhZWEwZjAtZTkxNy00MjAxLTllZjEtNjMwYjA3NGFlMzUxMRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMzNzQ5WhcNMzAwNTI1MTMzNzQ5WjBMMS0wKwYDVQQDDCQ1MmFlYTBmMC1lOTE3LTQyMDEtOWVmMS02MzBiMDc0YWUzNTExGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABGejqjk0Eet-RILHI236wHYqISdnPlebqnkuUTh4W2mCzkmqKibyjxGIUOs8LBrUeTR2DxVR1VV6H2rYQk2wdROjYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMC5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0kAMEYCIQCSkFj2A-KVWv2tKJLFzb18J5eWWKtsvWewZTn-FVnRnQIhAKJbt84IoZ9oXxgfp0VOLyVZiAgUgwMFS6JOfno3D-Nw"
+
+[replication."repl://kanidm-2.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-TCCAZ-gAwIBAgIRAeFGUAJbCkJ2vzf_Vv4qjeUwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkZTE0NjUwMDItNWIwYS00Mjc2LWJmMzctZmY1NmZlMmE4ZGU1MRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMyOTEwWhcNMzAwNTI1MTMyOTEwWjBMMS0wKwYDVQQDDCRlMTQ2NTAwMi01YjBhLTQyNzYtYmYzNy1mZjU2ZmUyYThkZTUxGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABCrncHSbDNSV3_aOSZ14plbVfrvSXQQL9MOqvrDKlf_Q6WbcA8OrTUjs3Jt0Q2beWjC3Z5-5c9fGu8M_k2iVWf-jYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMi5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0gAMEUCIQDHY5Yl-bhDTuJaYnHSMSiSAEWPrDcRVzvfmOJukuJ1QQIgSwgyeSG3K0MY87DI1RDYAdZlpP1YOK3Yatj7-YSXPC0"

apps/base/kanidm/resources/server-2.toml

@@ -0,0 +1,27 @@
+version = "2"
+
+domain = "auth.unkin.net"
+origin = "https://auth.unkin.net"
+bindaddress = "[::]:8443"
+db_path = "/data/kanidm.db"
+db_arc_size = 2048
+tls_chain = "/data/tls/tls.crt"
+tls_key = "/data/tls/tls.key"
+log_level = "info"
+
+[online_backup]
+path = "/data/backups/"
+schedule = "0 22 * * *"
+versions = 7
+
+[replication]
+origin = "repl://kanidm-2.kanidm-headless.kanidm.svc.cluster.local:8444"
+bindaddress = "[::]:8444"
+
+[replication."repl://kanidm-0.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-jCCAZ-gAwIBAgIRAVKuoPDpF0IBnvFjCwdK41EwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkNTJhZWEwZjAtZTkxNy00MjAxLTllZjEtNjMwYjA3NGFlMzUxMRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMzNzQ5WhcNMzAwNTI1MTMzNzQ5WjBMMS0wKwYDVQQDDCQ1MmFlYTBmMC1lOTE3LTQyMDEtOWVmMS02MzBiMDc0YWUzNTExGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABGejqjk0Eet-RILHI236wHYqISdnPlebqnkuUTh4W2mCzkmqKibyjxGIUOs8LBrUeTR2DxVR1VV6H2rYQk2wdROjYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMC5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0kAMEYCIQCSkFj2A-KVWv2tKJLFzb18J5eWWKtsvWewZTn-FVnRnQIhAKJbt84IoZ9oXxgfp0VOLyVZiAgUgwMFS6JOfno3D-Nw"
+
+[replication."repl://kanidm-1.kanidm-headless.kanidm.svc.cluster.local:8444"]
+type = "mutual-pull"
+partner_cert = "MIIB-TCCAZ-gAwIBAgIRASqOpORz60wiv7wF_7oBOxQwCgYIKoZIzj0EAwIwTDEtMCsGA1UEAwwkMmE4ZWE0ZTQtNzNlYi00YzIyLWJmYmMtMDVmZmJhMDEzYjE0MRswGQYDVQQKDBJLYW5pZG0gUmVwbGljYXRpb24wHhcNMjYwNTI1MTMyODM5WhcNMzAwNTI1MTMyODM5WjBMMS0wKwYDVQQDDCQyYThlYTRlNC03M2ViLTRjMjItYmZiYy0wNWZmYmEwMTNiMTQxGzAZBgNVBAoMEkthbmlkbSBSZXBsaWNhdGlvbjBZMBMGByqGSM49AgEGCCqGSM49AwEHA0IABFQP3zpFRt7TCOhzrUpOJBojn-sC2LmqZUub8P2ymVdIQbmoAyh4Q8Me0hNWJFyuFDnnqO06dt5I2iv0910-X6KjYjBgMCAGA1UdJQEB_wQWMBQGCCsGAQUFBwMCBggrBgEFBQcDATA8BgNVHREENTAzgjFrYW5pZG0tMS5rYW5pZG0taGVhZGxlc3Mua2FuaWRtLnN2Yy5jbHVzdGVyLmxvY2FsMAoGCCqGSM49BAMCA0gAMEUCIGjl58U6apcDjMEPIca8Wwg_JMfuMvV-uVcJI49Gl_9GAiEA2tFdb9rnFeBI7mwysScf5UsmY3ZziMD3UVm1vWN2IKs"

apps/base/kanidm/statefulset.yaml

@@ -36,24 +36,10 @@ spec:
         fsGroup: 1000
       initContainers:
         - name: config-init
-          image: kanidm/server:1.10.3
+          image: busybox:1.36
           command: ["/bin/sh", "-c"]
           args:
-            - |
+            - cp "/config-template/server-${POD_NAME##*-}.toml" /config/server.toml
-              set -e
-              REPL_ORIGIN="repl://${POD_NAME}.kanidm-headless.kanidm.svc.cluster.local:8444"
-              sed "s|__REPL_ORIGIN__|${REPL_ORIGIN}|g" /config-template/server.toml > /config/server.toml
-              for peer in kanidm-0 kanidm-1 kanidm-2; do
-                if [ "${peer}" = "${POD_NAME}" ]; then
-                  continue
-                fi
-                cert_file="/repl-certs/${peer}"
-                if [ -s "${cert_file}" ]; then
-                  fqdn="${peer}.kanidm-headless.kanidm.svc.cluster.local"
-                  printf '\n[replication."repl://%s:8444"]\ntype = "mutual-pull"\npartner_cert = "%s"\n' \
-                    "${fqdn}" "$(cat ${cert_file})" >> /config/server.toml
-                fi
-              done
           env:
             - name: POD_NAME
               valueFrom:
@@ -62,41 +48,12 @@ spec:
           volumeMounts:
             - name: config-template
               mountPath: /config-template
+              readOnly: true
             - name: config
               mountPath: /config
-            - name: repl-certs
-              mountPath: /repl-certs
-              readOnly: true
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true
-        - name: repl-cert-publisher
-          image: bitnami/kubectl:1.33
-          restartPolicy: Always
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              until kubectl exec "${POD_NAME}" -c kanidm -- /sbin/kanidmd renew-replication-certificate 2>/dev/null | grep -q '^# certificate:'; do
-                sleep 30
-              done
-              while true; do
-                cert=$(kubectl exec "${POD_NAME}" -c kanidm -- /sbin/kanidmd renew-replication-certificate 2>/dev/null \
-                  | grep '^# certificate:' | sed 's/^# certificate: "\(.*\)"$/\1/')
-                if [ -n "${cert}" ]; then
-                  kubectl patch configmap kanidm-repl-certs \
-                    --type=merge \
-                    -p "{\"data\":{\"${POD_NAME}\":\"${cert}\"}}"
-                fi
-                sleep 3600
-              done
-          env:
-            - name: POD_NAME
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.name
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: false
       containers:
         - name: kanidm
           image: kanidm/server:1.10.3
@@ -144,9 +101,6 @@ spec:
             name: kanidm-config
         - name: config
           emptyDir: {}
-        - name: repl-certs
-          configMap:
-            name: kanidm-repl-certs
         - name: tls
           secret:
             secretName: kanidm-tls

apps/base/kanidm/tlsroute.yaml

@@ -13,9 +13,14 @@ spec:
     - auth.unkin.net
     - au.auth.unkin.net
   parentRefs:
-    - name: kanidm
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: kanidm
       sectionName: https-passthrough
   rules:
     - backendRefs:
-        - name: kanidm
+        - group: ""
+          kind: Service
+          name: kanidm
           port: 8443
+          weight: 1

apps/base/open-webui/cnpg_cluster.yaml

@@ -0,0 +1,91 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: open-webui-postgres
+  namespace: open-webui
+spec:
+  affinity:
+    podAntiAffinityType: preferred
+  bootstrap:
+    initdb:
+      database: open-webui
+      encoding: UTF8
+      localeCType: C
+      localeCollate: C
+      owner: open-webui
+      secret:
+        name: postgres-credentials
+  enablePDB: true
+  enableSuperuserAccess: false
+  failoverDelay: 0
+  imageName: ghcr.io/cloudnative-pg/postgresql:17-minimal-trixie
+  instances: 3
+  logLevel: info
+  maxSyncReplicas: 0
+  minSyncReplicas: 0
+  monitoring:
+    customQueriesConfigMap:
+      - key: queries
+        name: cnpg-default-monitoring
+    disableDefaultQueries: false
+    enablePodMonitor: false
+  postgresql:
+    parameters:
+      archive_mode: "on"
+      archive_timeout: 5min
+      dynamic_shared_memory_type: posix
+      effective_cache_size: 128MB
+      full_page_writes: "on"
+      log_destination: csvlog
+      log_directory: /controller/log
+      log_filename: postgres
+      log_rotation_age: "0"
+      log_rotation_size: "0"
+      log_truncate_on_rotation: "false"
+      logging_collector: "on"
+      max_connections: "100"
+      max_parallel_workers: "4"
+      max_replication_slots: "16"
+      max_worker_processes: "4"
+      shared_buffers: 64MB
+      shared_memory_type: mmap
+      ssl_max_protocol_version: TLSv1.3
+      ssl_min_protocol_version: TLSv1.3
+      wal_keep_size: 128MB
+      wal_level: logical
+      wal_log_hints: "on"
+      wal_receiver_timeout: 5s
+      wal_sender_timeout: 5s
+    syncReplicaElectionConstraint:
+      enabled: false
+  primaryUpdateMethod: restart
+  primaryUpdateStrategy: unsupervised
+  probes:
+    liveness:
+      isolationCheck:
+        connectionTimeout: 1000
+        enabled: true
+        requestTimeout: 1000
+  replicationSlots:
+    highAvailability:
+      enabled: true
+      slotPrefix: _cnpg_
+    synchronizeReplicas:
+      enabled: true
+    updateInterval: 30
+  resources:
+    limits:
+      cpu: 500m
+      memory: 512Mi
+    requests:
+      cpu: 100m
+      memory: 256Mi
+  smartShutdownTimeout: 180
+  startDelay: 3600
+  stopDelay: 1800
+  storage:
+    resizeInUseVolumes: true
+    size: 5Gi
+    storageClass: cephrbd-fast-delete
+  switchoverDelay: 3600

apps/base/open-webui/cnpg_pooler.yaml

@@ -0,0 +1,33 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: Pooler
+metadata:
+  name: open-webui-postgres-pooler
+  namespace: open-webui
+spec:
+  cluster:
+    name: open-webui-postgres
+  instances: 2
+  pgbouncer:
+    parameters:
+      default_pool_size: "50"
+      max_client_conn: "200"
+    paused: false
+    poolMode: transaction
+  template:
+    metadata:
+      labels:
+        app: pooler
+    spec:
+      affinity:
+        podAntiAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            - labelSelector:
+                matchExpressions:
+                  - key: app
+                    operator: In
+                    values:
+                      - pooler
+              topologyKey: kubernetes.io/hostname
+      containers: []
+  type: rw

apps/base/open-webui/deployment.yaml

@@ -0,0 +1,61 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: open-webui
+  namespace: open-webui
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: open-webui
+  template:
+    metadata:
+      annotations:
+        reloader.stakater.com/auto: "true"
+      labels:
+        app: open-webui
+    spec:
+      priorityClassName: power
+      containers:
+        - name: open-webui
+          image: ghcr.io/open-webui/open-webui:main
+          imagePullPolicy: Always
+          ports:
+            - containerPort: 8080
+              name: http
+              protocol: TCP
+          env:
+            - name: OPENAI_API_BASE_URL
+              value: https://litellm.k8s.syd1.au.unkin.net
+            - name: WEBUI_URL
+              value: https://chat.k8s.syd1.au.unkin.net
+          envFrom:
+            - secretRef:
+                name: open-webui-credentials
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: 8080
+            failureThreshold: 3
+            initialDelaySeconds: 30
+            periodSeconds: 30
+            successThreshold: 1
+            timeoutSeconds: 5
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: 8080
+            failureThreshold: 3
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 5
+          resources:
+            limits:
+              cpu: "2"
+              memory: 4Gi
+            requests:
+              cpu: 250m
+              memory: 512Mi
+      restartPolicy: Always

apps/base/open-webui/gateway.yaml

@@ -0,0 +1,37 @@
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: Gateway
+metadata:
+  labels:
+    traefik.io/instance: internal
+  annotations:
+    cert-manager.io/cluster-issuer: vault-issuer
+    cert-manager.io/common-name: chat.k8s.syd1.au.unkin.net
+    cert-manager.io/private-key-size: "4096"
+    external-dns.alpha.kubernetes.io/hostname: chat.k8s.syd1.au.unkin.net
+    external-dns.alpha.kubernetes.io/target: 198.18.200.4
+  name: open-webui
+  namespace: open-webui
+spec:
+  gatewayClassName: traefik-internal
+  listeners:
+    - allowedRoutes:
+        namespaces:
+          from: Same
+      hostname: chat.k8s.syd1.au.unkin.net
+      name: http
+      port: 80
+      protocol: HTTP
+    - allowedRoutes:
+        namespaces:
+          from: Same
+      hostname: chat.k8s.syd1.au.unkin.net
+      name: https
+      port: 443
+      protocol: HTTPS
+      tls:
+        certificateRefs:
+          - group: ""
+            kind: Secret
+            name: open-webui-tls
+        mode: Terminate

apps/base/open-webui/httproute.yaml

@@ -0,0 +1,53 @@
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: HTTPRoute
+metadata:
+  name: open-webui-http-redirect
+  namespace: open-webui
+spec:
+  hostnames:
+    - chat.k8s.syd1.au.unkin.net
+  parentRefs:
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: open-webui
+      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: open-webui
+  namespace: open-webui
+spec:
+  hostnames:
+    - chat.k8s.syd1.au.unkin.net
+  parentRefs:
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: open-webui
+      sectionName: https
+  rules:
+    - backendRefs:
+        - group: ""
+          kind: Service
+          name: open-webui
+          port: 8080
+          weight: 1
+      matches:
+        - path:
+            type: PathPrefix
+            value: /
+      sessionPersistence:
+        type: Cookie
+        cookieName: open-webui-backend
+        absoluteTimeout: 24h0m0s

apps/base/open-webui/kustomization.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - namespace.yaml
+  - cnpg_cluster.yaml
+  - cnpg_pooler.yaml
+  - deployment.yaml
+  - pdb.yaml
+  - service.yaml
+  - gateway.yaml
+  - httproute.yaml
+  - vaultauth.yaml
+  - vaultstaticsecret.yaml

apps/base/open-webui/namespace.yaml

@@ -0,0 +1,5 @@
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: open-webui

apps/base/open-webui/pdb.yaml

@@ -0,0 +1,11 @@
+---
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: open-webui
+  namespace: open-webui
+spec:
+  minAvailable: 1
+  selector:
+    matchLabels:
+      app: open-webui

apps/base/open-webui/service.yaml

@@ -0,0 +1,17 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: open-webui
+  namespace: open-webui
+spec:
+  internalTrafficPolicy: Cluster
+  ports:
+    - name: http
+      port: 8080
+      protocol: TCP
+      targetPort: http
+  selector:
+    app: open-webui
+  sessionAffinity: None
+  type: ClusterIP

apps/base/open-webui/vaultauth.yaml

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

apps/base/open-webui/vaultstaticsecret.yaml

@@ -0,0 +1,34 @@
+---
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultStaticSecret
+metadata:
+  name: postgres-credentials
+  namespace: open-webui
+spec:
+  destination:
+    create: true
+    name: postgres-credentials
+    overwrite: true
+  hmacSecretData: true
+  mount: kv
+  path: kubernetes/namespace/open-webui/default/postgres-credentials
+  refreshAfter: 5m
+  type: kv-v2
+  vaultAuthRef: default
+---
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultStaticSecret
+metadata:
+  name: open-webui-credentials
+  namespace: open-webui
+spec:
+  destination:
+    create: true
+    name: open-webui-credentials
+    overwrite: true
+  hmacSecretData: true
+  mount: kv
+  path: kubernetes/namespace/open-webui/default/open-webui-credentials
+  refreshAfter: 5m
+  type: kv-v2
+  vaultAuthRef: default

apps/base/puppet/deployment_puppetboard.yaml

@@ -150,7 +150,7 @@ spec:
               memory: 350Mi
               cpu: 100m
             limits:
-              memory: 1Gi
+              memory: 1024Mi
               cpu: 500m
           securityContext:
             runAsNonRoot: true

apps/base/puppet/deployment_puppetdb.yaml

@@ -35,7 +35,7 @@ spec:
           imagePullPolicy: IfNotPresent
           resources:
             limits:
-              cpu: "1"
+              cpu: 1
               memory: 1536Mi
             requests:
               cpu: 250m

apps/base/puppet/deployment_puppetserver-compiler.yaml

@@ -31,11 +31,11 @@ spec:
         imagePullPolicy: IfNotPresent
         resources:
           limits:
-            cpu: "2"
+            cpu: 2
-            memory: 3Gi
+            memory: 3072Mi
           requests:
             cpu: 500m
-            memory: 1Gi
+            memory: 1024Mi
         ports:
         - containerPort: 8140
           name: puppetserver

apps/base/puppet/deployment_puppetserver-master.yaml

@@ -35,11 +35,11 @@ spec:
           imagePullPolicy: IfNotPresent
           resources:
             limits:
-              cpu: "2"
+              cpu: 2
               memory: 3500Mi
             requests:
               cpu: 250m
-              memory: 1Gi
+              memory: 1024Mi
           ports:
             - containerPort: 8140
               name: puppetserver

apps/base/puppet/service_puppetdb.yaml

@@ -9,7 +9,6 @@ metadata:
   name: puppetdb
   namespace: puppet
 spec:
-  clusterIP: null
   ports:
   - name: pdb-http
     port: 8080

apps/base/reposync/cronjob_reposync-almalinux9-appstream.yaml

@@ -53,7 +53,7 @@ spec:
                   cpu: 500m
                   memory: 1Gi
                 limits:
-                  cpu: "2"
+                  cpu: 2000m
                   memory: 4Gi
               volumeMounts:
                 - name: repodata

apps/base/reposync/cronjob_reposync-almalinux9-baseos.yaml

@@ -56,7 +56,7 @@ spec:
                   cpu: 500m
                   memory: 1Gi
                 limits:
-                  cpu: "2"
+                  cpu: 2000m
                   memory: 4Gi
               volumeMounts:
                 - name: repodata

apps/base/reposync/cronjob_reposync-epel9.yaml

@@ -53,7 +53,7 @@ spec:
                   cpu: 500m
                   memory: 1Gi
                 limits:
-                  cpu: "2"
+                  cpu: 2000m
                   memory: 4Gi
               volumeMounts:
                 - name: repodata

apps/base/reposync/cronjob_reposync-openvox7.yaml

@@ -52,7 +52,7 @@ spec:
                   cpu: 500m
                   memory: 1Gi
                 limits:
-                  cpu: "2"
+                  cpu: 2000m
                   memory: 4Gi
               volumeMounts:
                 - name: repodata

apps/overlays/au-syd1/consul/values.yaml

@@ -37,7 +37,7 @@ server:
       cpu: 100m
     limits:
       memory: 2Gi
-      cpu: 1000m
+      cpu: "1"
 
 client:
   enabled: false

apps/overlays/au-syd1/open-webui/kustomization.yaml

@@ -0,0 +1,6 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - ../../../base/open-webui

argocd/applicationsets/aitooling.yaml

@@ -11,6 +11,7 @@ spec:
       revision: HEAD
       directories:
       - path: apps/overlays/*/litellm
+      - path: apps/overlays/*/open-webui
       - path: apps/overlays/*/paperclip
   template:
     metadata:

argocd/projects/aitooling.yaml

@@ -11,6 +11,8 @@ spec:
   destinations:
     - namespace: 'litellm'
       server: https://kubernetes.default.svc
+    - namespace: 'open-webui'
+      server: https://kubernetes.default.svc
     - namespace: 'paperclip'
       server: https://kubernetes.default.svc
   clusterResourceWhitelist:

policy/gateway_api.rego

@@ -1,94 +0,0 @@
-package main
-
-# Gateway API resources require several fields to be set explicitly even though
-# the Gateway API controller defaults them. ArgoCD diffs desired vs live by
-# string comparison, so any field the controller defaults that is absent from
-# the git manifest causes a permanent OutOfSync.
-#
-# Affected resources:
-#   HTTPRoute / TLSRoute — parentRefs and backendRefs (see PR #162, #165)
-#   Gateway              — listeners[*].tls.certificateRefs (see PR #153)
-
-_route_kinds := {"HTTPRoute", "TLSRoute"}
-
-# ---- parentRefs: group must be "gateway.networking.k8s.io" ----
-
-deny contains msg if {
-    _route_kinds[input.kind]
-    ref := input.spec.parentRefs[i]
-    object.get(ref, "group", null) != "gateway.networking.k8s.io"
-    msg := sprintf(
-        "%s %s/%s parentRefs[%d]: add 'group: gateway.networking.k8s.io' — controller defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.kind, input.metadata.namespace, input.metadata.name, i],
-    )
-}
-
-# ---- parentRefs: kind must be "Gateway" ----
-
-deny contains msg if {
-    _route_kinds[input.kind]
-    ref := input.spec.parentRefs[i]
-    object.get(ref, "kind", null) != "Gateway"
-    msg := sprintf(
-        "%s %s/%s parentRefs[%d]: add 'kind: Gateway' — controller defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.kind, input.metadata.namespace, input.metadata.name, i],
-    )
-}
-
-# ---- backendRefs: group must be present (may be empty string "") ----
-
-deny contains msg if {
-    _route_kinds[input.kind]
-    rule := input.spec.rules[ri]
-    ref := rule.backendRefs[bi]
-    not _has_key(ref, "group")
-    msg := sprintf(
-        "%s %s/%s rules[%d].backendRefs[%d]: add 'group: \"\"' — controller defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.kind, input.metadata.namespace, input.metadata.name, ri, bi],
-    )
-}
-
-# ---- backendRefs: kind must be "Service" ----
-
-deny contains msg if {
-    _route_kinds[input.kind]
-    rule := input.spec.rules[ri]
-    ref := rule.backendRefs[bi]
-    object.get(ref, "kind", null) != "Service"
-    msg := sprintf(
-        "%s %s/%s rules[%d].backendRefs[%d]: add 'kind: Service' — controller defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.kind, input.metadata.namespace, input.metadata.name, ri, bi],
-    )
-}
-
-# ---- backendRefs: weight must be present ----
-
-deny contains msg if {
-    _route_kinds[input.kind]
-    rule := input.spec.rules[ri]
-    ref := rule.backendRefs[bi]
-    not _has_key(ref, "weight")
-    msg := sprintf(
-        "%s %s/%s rules[%d].backendRefs[%d]: add 'weight: 1' — controller defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.kind, input.metadata.namespace, input.metadata.name, ri, bi],
-    )
-}
-
-# ---- Gateway certificateRefs: group must be present (may be empty string "") ----
-
-deny contains msg if {
-    input.kind == "Gateway"
-    listener := input.spec.listeners[li]
-    ref := listener.tls.certificateRefs[ci]
-    not _has_key(ref, "group")
-    msg := sprintf(
-        "Gateway %s/%s listeners[%d].tls.certificateRefs[%d]: add 'group: \"\"' — admission webhook defaults this field, causing ArgoCD OutOfSync when omitted",
-        [input.metadata.namespace, input.metadata.name, li, ci],
-    )
-}
-
-# ---- Helper: key presence check (works for null, "", and any defined value) ----
-
-_has_key(obj, key) if {
-    _ = obj[key]
-}

policy/no_ingress.rego

@@ -1,13 +0,0 @@
-package main
-
-# Deny all Kubernetes Ingress resources.
-# This cluster uses Gateway API (HTTPRoute + Gateway) for ingress routing.
-# Ingress is the legacy API and must not be added.
-
-deny contains msg if {
-    input.kind == "Ingress"
-    msg := sprintf(
-        "%s/%s: Ingress resources are forbidden — use Gateway API HTTPRoute instead",
-        [input.metadata.namespace, input.metadata.name],
-    )
-}

policy/resource_normalization.rego

@@ -1,173 +0,0 @@
-package main
-
-# Kubernetes normalizes resource quantity values on write. ArgoCD diffs by
-# string comparison, so a non-canonical value in git will always differ from
-# the live object, causing permanent OutOfSync.
-#
-# Rules enforced here:
-#   CPU integers  — k8s converts integer 1 to string "1" (see PR #163)
-#   CPU milliCPU  — k8s converts 1000m → "1", 2000m → "2", etc. (PR #164)
-#   Memory Mi→Gi  — k8s converts 1024Mi → 1Gi, 2048Mi → 2Gi, etc. (PR #163)
-#   clusterIP null — k8s assigns a real IP; null in git always differs
-#                    from the live assigned value (see PR #166)
-
-# ---- Container helpers ----
-# Extracts containers from Deployment/StatefulSet/DaemonSet/Job/CronJob/Pod
-
-_containers contains c if { c := input.spec.template.spec.containers[_] }
-_containers contains c if { c := input.spec.template.spec.initContainers[_] }
-_containers contains c if { c := input.spec.containers[_] }
-_containers contains c if { c := input.spec.initContainers[_] }
-_containers contains c if { c := input.spec.jobTemplate.spec.template.spec.containers[_] }
-
-# ---- CPU: must not be an integer ----
-# YAML `cpu: 1` (unquoted) parses as JSON integer; k8s stores as string "1".
-
-deny contains msg if {
-    c := _containers[_]
-    cpu := c.resources.limits.cpu
-    is_number(cpu)
-    msg := sprintf(
-        "%s container %q: cpu limit %v is an unquoted integer — use \"%v\" (string) to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, cpu, cpu],
-    )
-}
-
-deny contains msg if {
-    c := _containers[_]
-    cpu := c.resources.requests.cpu
-    is_number(cpu)
-    msg := sprintf(
-        "%s container %q: cpu request %v is an unquoted integer — use \"%v\" (string) to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, cpu, cpu],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    cpu := input.spec.resources.limits.cpu
-    is_number(cpu)
-    msg := sprintf(
-        "Cluster %s/%s: cpu limit %v is an unquoted integer — use \"%v\" (string) to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, cpu, cpu],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    cpu := input.spec.resources.requests.cpu
-    is_number(cpu)
-    msg := sprintf(
-        "Cluster %s/%s: cpu request %v is an unquoted integer — use \"%v\" (string) to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, cpu, cpu],
-    )
-}
-
-# ---- CPU: milliCPU divisible by 1000 normalizes to a whole number ----
-# k8s converts 1000m → "1", 2000m → "2". Use the canonical whole-number form.
-
-_milli_whole(cpu) := n if {
-    is_string(cpu)
-    endswith(cpu, "m")
-    val := to_number(substring(cpu, 0, count(cpu) - 1))
-    val % 1000 == 0
-    val > 0
-    n := val / 1000
-}
-
-deny contains msg if {
-    c := _containers[_]
-    n := _milli_whole(c.resources.limits.cpu)
-    msg := sprintf(
-        "%s container %q: cpu limit %q normalizes to \"%v\" — use canonical form to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, c.resources.limits.cpu, n],
-    )
-}
-
-deny contains msg if {
-    c := _containers[_]
-    n := _milli_whole(c.resources.requests.cpu)
-    msg := sprintf(
-        "%s container %q: cpu request %q normalizes to \"%v\" — use canonical form to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, c.resources.requests.cpu, n],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    n := _milli_whole(input.spec.resources.limits.cpu)
-    msg := sprintf(
-        "Cluster %s/%s: cpu limit %q normalizes to \"%v\" — use canonical form to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, input.spec.resources.limits.cpu, n],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    n := _milli_whole(input.spec.resources.requests.cpu)
-    msg := sprintf(
-        "Cluster %s/%s: cpu request %q normalizes to \"%v\" — use canonical form to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, input.spec.resources.requests.cpu, n],
-    )
-}
-
-# ---- Memory: Mi values divisible by 1024 normalize to Gi ----
-# k8s converts 1024Mi → 1Gi, 2048Mi → 2Gi, etc.
-
-_mi_canonical(mem) := canonical if {
-    endswith(mem, "Mi")
-    val := to_number(substring(mem, 0, count(mem) - 2))
-    val % 1024 == 0
-    val > 0
-    canonical := sprintf("%vGi", [val / 1024])
-}
-
-deny contains msg if {
-    c := _containers[_]
-    canonical := _mi_canonical(c.resources.limits.memory)
-    msg := sprintf(
-        "%s container %q: memory limit %q normalizes to %q — use canonical form to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, c.resources.limits.memory, canonical],
-    )
-}
-
-deny contains msg if {
-    c := _containers[_]
-    canonical := _mi_canonical(c.resources.requests.memory)
-    msg := sprintf(
-        "%s container %q: memory request %q normalizes to %q — use canonical form to prevent ArgoCD OutOfSync",
-        [input.kind, c.name, c.resources.requests.memory, canonical],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    canonical := _mi_canonical(input.spec.resources.limits.memory)
-    msg := sprintf(
-        "Cluster %s/%s: memory limit %q normalizes to %q — use canonical form to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, input.spec.resources.limits.memory, canonical],
-    )
-}
-
-deny contains msg if {
-    input.kind == "Cluster"
-    canonical := _mi_canonical(input.spec.resources.requests.memory)
-    msg := sprintf(
-        "Cluster %s/%s: memory request %q normalizes to %q — use canonical form to prevent ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name, input.spec.resources.requests.memory, canonical],
-    )
-}
-
-# ---- Service: clusterIP must not be null ----
-# k8s assigns a real IP on creation; clusterIP is immutable afterward.
-# Setting null in git means desired=null vs live=10.x.x.x → permanent OutOfSync.
-# Remove the field and let k8s own it.
-
-deny contains msg if {
-    input.kind == "Service"
-    input.spec.clusterIP == null
-    msg := sprintf(
-        "Service %s/%s has 'clusterIP: null' — remove this field; Kubernetes assigns the IP on creation and it causes ArgoCD OutOfSync",
-        [input.metadata.namespace, input.metadata.name],
-    )
-}