Collect pod logs with VLAgent, retire the NATS/ClickHouse chain (#506)

The vector -> JetStream -> ClickHouse chain duplicated storage the in-cluster VictoriaLogs already provides, and its NATS StatefulSet keeps the logging Application from syncing.

- collect pod logs with a VLAgent DaemonSet remote-writing to vlinsert-logs
- delete vector, NATS, ClickHouse, logarchiver and logviewer
- drop clickhouse-system from the logging ApplicationSet

---------

Co-authored-by: BenVincent <benvin@main.unkin.net>
Reviewed-on: #506
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>

.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

AGENTS.md

@@ -22,10 +22,10 @@ make kubeconform
 make clean
 
 # Quick build + inspect without persisting output
-kustomize build --enable-helm --helm-kube-version "$(cat ci/kube-version)" apps/overlays/au-syd1/<app-name>
+kustomize build --enable-helm apps/overlays/au-syd1/<app-name>
 
 # Check all resource kinds produced by an overlay
-kustomize build --enable-helm --helm-kube-version "$(cat ci/kube-version)" apps/overlays/au-syd1/<app-name> | grep "^kind:" | sort | uniq -c
+kustomize build --enable-helm apps/overlays/au-syd1/<app-name> | grep "^kind:" | sort | uniq -c
 
 # Run pre-commit checks against all files
 uvx pre-commit run --all-files
@@ -118,7 +118,7 @@ In `argocd/projects/platform.yaml` (or `storage.yaml`):
 
 ### 5. Validate
 ```bash
-kustomize build --enable-helm --helm-kube-version "$(cat ci/kube-version)" apps/overlays/au-syd1/<app-name>
+kustomize build --enable-helm apps/overlays/au-syd1/<app-name>
 make kubeconform
 ```
 
@@ -215,7 +215,7 @@ Examples:
 
 Some overlays vendor Helm charts locally under `apps/overlays/au-syd1/<app-name>/charts/<chart-name>/`. When a chart is vendored, the overlay's `kustomization.yaml` references the local path. When not vendored, it references the OCI or HTTP repo directly.
 
-The Kubernetes target version lives in `ci/kube-version`; the Makefile and CI scripts read it for both the Helm capabilities version and kubeconform.
+Current Kubernetes target version: **1.33.7** (used by kubeconform in CI).
 
 ---
 

Makefile

@@ -3,11 +3,8 @@
 # Build a kustomization path to manifests directory
 # Usage: make build clusters/au-syd1/bootstrap
 build:
-	@kube_version="$$(cat ci/kube-version)"; \
+	@mkdir -p manifests/$(filter-out $@,$(MAKECMDGOALS))
-	if [ -z "$$kube_version" ]; then echo "cannot read ci/kube-version" >&2; exit 1; fi; \
+	@kustomize build --enable-helm $(filter-out $@,$(MAKECMDGOALS)) --output manifests/$(filter-out $@,$(MAKECMDGOALS))
-	target="$(filter-out $@,$(MAKECMDGOALS))"; \
-	mkdir -p "manifests/$$target"; \
-	kustomize build --enable-helm --helm-kube-version "$$kube_version" "$$target" --output "manifests/$$target"
 
 # Generate JSON schemas from CRDs and Kubernetes swagger spec (run manually, results committed)
 schemas:

apps/base/bind-external/acme-unkin-net/a/kustomization.yaml

@@ -3,4 +3,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 
 resources:
-  - namespace.yaml
+  - ns1.yaml

apps/base/bind-external/acme-unkin-net/a/ns1.yaml

@@ -0,0 +1,16 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: acme-ns1-a
+  namespace: bind-external
+spec:
+  zoneRef: acme-unkin-net
+  name: ns1
+  type: A
+  ttl: 3600
+  values:
+    # Public address of this cluster's external BIND, same target as
+    # acme-ns1.unkin.net. Resolvers that cached the seeded ns1.acme.unkin.net
+    # NS name must still reach the zone.
+    - 103.216.191.185

apps/base/bind-external/acme-unkin-net/kustomization.yaml

@@ -0,0 +1,11 @@
+---
+# Authoritative delegation records for acme.unkin.net. Without these the zone
+# only holds the operator's seed apex (NS ns1.acme.unkin.net glued to the
+# primary pod IP), which is unroutable off-cluster and goes stale on
+# reschedule. DNSRecords must live in the same namespace as their BindZone.
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - ns
+  - a

apps/base/bind-external/acme-unkin-net/ns/apex.yaml

@@ -0,0 +1,16 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: acme-apex-ns
+  namespace: bind-external
+spec:
+  zoneRef: acme-unkin-net
+  # "@" is the zone apex.
+  name: "@"
+  type: NS
+  ttl: 3600
+  values:
+    # Matches the parent delegation in Google Cloud DNS. Out of zone, so the
+    # child needs no glue of its own.
+    - acme-ns1.unkin.net.

apps/base/bind-external/acme-unkin-net/ns/kustomization.yaml

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

apps/base/bind-external/kustomization.yaml

@@ -7,4 +7,5 @@ resources:
   - cluster.yaml
   - tsigkey.yaml
   - zones.yaml
+  - acme-unkin-net
   - agent-dns-rolebinding.yaml

apps/base/bind-external/zones.yaml

@@ -17,3 +17,14 @@ spec:
   updateKeyRef: certmanager
   allowTransfer:
     - key certmanager
+  # Published apex NS. acme-ns1 is what the parent delegates to and glues; ns1 is
+  # in-zone, so its address is declared below or a reseed would glue it to the
+  # primary pod IP.
+  nameservers:
+    - acme-ns1.unkin.net.
+    - ns1.acme.unkin.net.
+  records:
+    - name: ns1
+      type: A
+      ttl: 3600
+      values: ["103.216.191.185"]

apps/base/bind-internal/authoritative/ceph-unkin-net/cname/dashboard.yaml

@@ -0,0 +1,15 @@
+---
+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.

apps/base/bind-internal/authoritative/ceph-unkin-net/cname/kustomization.yaml

@@ -0,0 +1,7 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - dashboard.yaml
+  - s3.yaml

apps/base/bind-internal/authoritative/ceph-unkin-net/cname/s3.yaml

@@ -0,0 +1,15 @@
+---
+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.

apps/base/bind-internal/authoritative/ceph-unkin-net/kustomization.yaml

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

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

@@ -2,9 +2,14 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 
+# Individually-managed authoritative records live under <zone>/<type>/<record>.yaml.
+# 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.
 resources:
   - cluster.yaml
   - tsigkey.yaml
   - zones.yaml
-  - records.yaml
+  - unkin-net
+  - ceph-unkin-net
   - acls.yaml

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

@@ -1,164 +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-EXTERNAL (DMZ) gateway VIP; the authentik Gateway serves the
-    # identity.unkin.net hostname there.
-    - 198.18.199.0
----
-# 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
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: ghp-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: ghp
-  type: A
-  ttl: 600
-  values:
-    # traefik-internal gateway VIP; the ghp Gateway serves ghp.unkin.net there.
-    - 198.18.200.4
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: arrstack-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: arrstack
-  type: A
-  ttl: 600
-  values:
-    # traefik-EXTERNAL (DMZ) gateway VIP; the arrproxy Gateway serves the
-    # arrstack.unkin.net front door (oauth2-proxy) there.
-    - 198.18.199.0
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: logviewer-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: logviewer
-  type: A
-  ttl: 600
-  values:
-    # traefik-internal gateway VIP; the logviewer Gateway serves
-    # logviewer.unkin.net there.
-    - 198.18.200.4
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: cheeztv-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: cheeztv
-  type: A
-  ttl: 600
-  values:
-    # traefik-internal gateway VIP; the cheeztv Gateway serves cheeztv.unkin.net
-    # there.
-    - 198.18.200.4
----
-apiVersion: bind.unkin.net/v1alpha1
-kind: DNSRecord
-metadata:
-  name: watchstate-dns-internal
-  namespace: bind-internal
-spec:
-  zoneRef: unkin-net
-  name: watchstate
-  type: A
-  ttl: 600
-  values:
-    # traefik-EXTERNAL (DMZ) gateway VIP; the watchstate-external Gateway serves
-    # the watchstate.unkin.net front door (oauth2-proxy) there.
-    - 198.18.199.0

apps/base/bind-internal/authoritative/unkin-net/a/arrstack.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: arrstack-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: arrstack
+  type: A
+  ttl: 600
+  values:
+    # traefik-EXTERNAL (DMZ) gateway VIP; the arrproxy Gateway serves the
+    # arrstack.unkin.net front door (oauth2-proxy) there.
+    - 198.18.199.0

apps/base/bind-internal/authoritative/unkin-net/a/cheeztv.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: cheeztv-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: cheeztv
+  type: A
+  ttl: 600
+  values:
+    # traefik-internal gateway VIP; the cheeztv Gateway serves cheeztv.unkin.net
+    # there.
+    - 198.18.200.4

apps/base/bind-internal/authoritative/unkin-net/a/ghp.yaml

@@ -0,0 +1,14 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: ghp-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: ghp
+  type: A
+  ttl: 600
+  values:
+    # traefik-internal gateway VIP; the ghp Gateway serves ghp.unkin.net there.
+    - 198.18.200.4

apps/base/bind-internal/authoritative/unkin-net/a/git.yaml

@@ -0,0 +1,27 @@
+---
+# 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.
+# Uncomment this record AND its entry in kustomization.yaml to activate it.
+# ---
+# 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

apps/base/bind-internal/authoritative/unkin-net/a/identity.yaml

@@ -0,0 +1,17 @@
+---
+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-EXTERNAL (DMZ) gateway VIP; the authentik Gateway serves the
+    # identity.unkin.net hostname there.
+    - 198.18.199.0

apps/base/bind-internal/authoritative/unkin-net/a/kustomization.yaml

@@ -0,0 +1,16 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - arrstack.yaml
+  - cheeztv.yaml
+  # PRODUCTION CUTOVER RECORD — see git.yaml. Uncomment together with the
+  # record itself.
+  # - git.yaml
+  - ghp.yaml
+  - identity.yaml
+  - lb1.yaml
+  - logviewer.yaml
+  - vlogs.yaml
+  - watchstate.yaml

apps/base/bind-internal/authoritative/unkin-net/a/lb1.yaml

@@ -0,0 +1,13 @@
+---
+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/unkin-net/a/logviewer.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: logviewer-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: logviewer
+  type: A
+  ttl: 600
+  values:
+    # traefik-internal gateway VIP; the logviewer Gateway serves
+    # logviewer.unkin.net there.
+    - 198.18.200.4

apps/base/bind-internal/authoritative/unkin-net/a/vlogs.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: vlogs-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: vlogs
+  type: A
+  ttl: 600
+  values:
+    # traefik-EXTERNAL (DMZ) gateway VIP; the vlogs-external Gateway serves the
+    # vlogs.unkin.net front door (oauth2-proxy) there.
+    - 198.18.199.0

apps/base/bind-internal/authoritative/unkin-net/a/watchstate.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bind.unkin.net/v1alpha1
+kind: DNSRecord
+metadata:
+  name: watchstate-dns-internal
+  namespace: bind-internal
+spec:
+  zoneRef: unkin-net
+  name: watchstate
+  type: A
+  ttl: 600
+  values:
+    # traefik-EXTERNAL (DMZ) gateway VIP; the watchstate-external Gateway serves
+    # the watchstate.unkin.net front door (oauth2-proxy) there.
+    - 198.18.199.0

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

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

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:v0.2.7
+          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/bind-operator:v0.3.1
           args:
             - --metrics-bind-address=:8080
             - --health-probe-bind-address=:8081

apps/base/bind-system/kustomization.yaml

@@ -6,7 +6,7 @@ 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/v0.2.7/config/crd/install.yaml
+  - https://git.unkin.net/unkin/bind-operator/raw/tag/v0.3.1/config/crd/install.yaml
   - rbac.yaml
   - agent-dns-rbac.yaml
   - deployment.yaml

apps/base/cert-manager/certificate_wildcard-ceph-unkin-net.yaml

@@ -0,0 +1,26 @@
+---
+# Let's Encrypt *.ceph.unkin.net wildcard for the haproxy edge (ceph dashboard).
+# DNS-01 needs the delegated _acme-challenge.ceph.unkin.net CNAME in the public
+# unkin.net zone.
+# _acme-challenge.ceph.unkin.net. CNAME _acme-challenge.ceph.acme.unkin.net.
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: wildcard-ceph-unkin-net
+  namespace: cert-manager
+spec:
+  secretName: wildcard-ceph-unkin-net-tls
+  secretTemplate:
+    annotations:
+      reflector.v1.k8s.emberstack.com/reflection-allowed: "true"
+      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "haproxy"
+      reflector.v1.k8s.emberstack.com/reflection-auto-enabled: "true"
+      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "haproxy"
+  privateKey:
+    size: 4096
+  dnsNames:
+    - "*.ceph.unkin.net"
+  issuerRef:
+    name: letsencrypt
+    kind: ClusterIssuer
+    group: cert-manager.io

apps/base/cert-manager/certificate_wildcard-main-unkin-net.yaml

@@ -0,0 +1,26 @@
+---
+# Let's Encrypt *.main.unkin.net wildcard for the haproxy edge (pve, arr stack,
+# jellyfin, stalwart webadmin/autoconfig). DNS-01 needs the delegated
+# _acme-challenge.main.unkin.net CNAME in the public unkin.net zone.
+# _acme-challenge.main.unkin.net. CNAME _acme-challenge.main.acme.unkin.net.
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: wildcard-main-unkin-net
+  namespace: cert-manager
+spec:
+  secretName: wildcard-main-unkin-net-tls
+  secretTemplate:
+    annotations:
+      reflector.v1.k8s.emberstack.com/reflection-allowed: "true"
+      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "haproxy"
+      reflector.v1.k8s.emberstack.com/reflection-auto-enabled: "true"
+      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "haproxy"
+  privateKey:
+    size: 4096
+  dnsNames:
+    - "*.main.unkin.net"
+  issuerRef:
+    name: letsencrypt
+    kind: ClusterIssuer
+    group: cert-manager.io

apps/base/cert-manager/certificate_wildcard-unkin-net.yaml

@@ -14,9 +14,9 @@ spec:
   secretTemplate:
     annotations:
       reflector.v1.k8s.emberstack.com/reflection-allowed: "true"
-      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "cheeztv,arrstack,authentik,gitea,watchstate,mediamark,repospawner"
+      reflector.v1.k8s.emberstack.com/reflection-allowed-namespaces: "cheeztv,arrstack,authentik,gitea,watchstate,mediamark,repospawner,haproxy,logging"
       reflector.v1.k8s.emberstack.com/reflection-auto-enabled: "true"
-      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "cheeztv,arrstack,authentik,gitea,watchstate,mediamark,repospawner"
+      reflector.v1.k8s.emberstack.com/reflection-auto-namespaces: "cheeztv,arrstack,authentik,gitea,watchstate,mediamark,repospawner,haproxy,logging"
   privateKey:
     size: 4096
   dnsNames:

apps/base/cert-manager/kustomization.yaml

@@ -12,3 +12,5 @@ resources:
   - clusterissuer_letsencrypt.yaml
   - clusterissuer_letsencrypt-staging.yaml
   - certificate_wildcard-unkin-net.yaml
+  - certificate_wildcard-main-unkin-net.yaml
+  - certificate_wildcard-ceph-unkin-net.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/grafana/grafanadatasource.yaml

@@ -20,3 +20,22 @@ spec:
     jsonData:
       timeInterval: "15s"
       httpMethod: "POST"
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDatasource
+metadata:
+  name: victorialogs
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  plugins:
+    - name: victoriametrics-logs-datasource
+      version: 0.32.0
+  datasource:
+    name: "VictoriaLogs"
+    type: "victoriametrics-logs-datasource"
+    uid: "victorialogs"
+    access: "proxy"
+    url: "http://vlselect-logs.logging.svc.cluster.local:9471"

apps/base/haproxy/configmap.yaml

@@ -0,0 +1,274 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: haproxy-config
+  namespace: haproxy
+data:
+  certificate.list: |
+    # First entry is the default cert for non-matching SNI.
+    /etc/haproxy/certs/unkin-net/tls.crt
+    /etc/haproxy/certs/main-unkin-net/tls.crt
+    /etc/haproxy/certs/ceph-unkin-net/tls.crt
+
+  fe_https.map: |
+    sonarr.main.unkin.net be_sonarr
+    radarr.main.unkin.net be_radarr
+    lidarr.main.unkin.net be_lidarr
+    readarr.main.unkin.net be_readarr
+    prowlarr.main.unkin.net be_prowlarr
+    nzbget.main.unkin.net be_nzbget
+    jellyfin.main.unkin.net be_jellyfin
+    fafflix.unkin.net be_jellyfin
+    git.unkin.net be_gitea
+    grafana.unkin.net be_grafana
+    dashboard.ceph.unkin.net be_ceph_dashboard
+    auth.unkin.net be_k8s_kanidm
+
+  haproxy.cfg: |
+    global
+      log stdout format raw local0
+      log stdout format raw local1 notice
+      maxconn  4000
+      hard-stop-after  2m
+      ssl-default-bind-ciphers  EECDH+AESGCM:EDH+AESGCM:AES256+EECDH:AES256+EDH
+      ssl-default-bind-options  ssl-min-ver TLSv1.2 ssl-max-ver TLSv1.3
+      ssl-default-server-ciphers  kEECDH+aRSA+AES:kRSA+AES:+AES256:RC4-SHA:!kEDH:!LOW:!EXP:!MD5:!aNULL:!eNULL
+      ssl-default-server-options  no-sslv3
+      stats  timeout 30s
+      stats  socket /var/lib/haproxy/stats
+      stats  socket /var/lib/haproxy/admin.sock mode 660 level admin
+      tune.ssl.default-dh-param  2048
+
+    defaults
+      log  global
+      maxconn  5000
+      mode  http
+      option  httplog
+      option  dontlognull
+      option  http-server-close
+      option  forwardfor except 127.0.0.0/8
+      option  redispatch
+      retries  3
+      stats  enable
+      timeout  http-request 10s
+      timeout  queue 1m
+      timeout  connect 10s
+      timeout  client 5m
+      timeout  server 5m
+      timeout  http-keep-alive 10s
+      timeout  check 10s
+
+    frontend fe_https
+      bind 0.0.0.0:443 ssl crt-list /usr/local/etc/haproxy/certificate.list ciphers EECDH+AESGCM:EDH+AESGCM:AES256+EECDH:AES256+EDH force-tlsv12
+      mode http
+      description Global HTTPS Frontend
+      http-request set-header X-Forwarded-Proto https
+      http-request set-header X-Real-IP %[src]
+      http-response set-header X-Content-Type-Options nosniff
+      http-response set-header X-XSS-Protection 1;mode=block
+      use_backend %[req.hdr(host),lower,map(/usr/local/etc/haproxy/fe_https.map,be_default)]
+
+    frontend fe_metrics
+      bind 0.0.0.0:8405
+      mode http
+      description Metrics Frontend
+      http-request set-header X-Forwarded-Proto https
+      http-request set-header X-Real-IP %[src]
+      http-request use-service prometheus-exporter if { path /metrics }
+
+    backend be_ceph_dashboard
+      description Backend for Ceph Dashboard from Mgr instances
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-check expect status 200
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 9443 }
+      http-reuse always
+      option httpchk GET /
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      stick-table type ip size 200k expire 30m
+      server prodnxsr0009 198.18.23.9:9443 check cookie prodnxsr0009 fall 2 inter 2s rise 3 ssl verify none
+      server prodnxsr0010 198.18.23.10:9443 check cookie prodnxsr0010 fall 2 inter 2s rise 3 ssl verify none
+      server prodnxsr0011 198.18.23.11:9443 check cookie prodnxsr0011 fall 2 inter 2s rise 3 ssl verify none
+      server prodnxsr0012 198.18.23.12:9443 check cookie prodnxsr0012 fall 2 inter 2s rise 3 ssl verify none
+      server prodnxsr0013 198.18.23.13:9443 check cookie prodnxsr0013 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_default
+      description Backend for unmatched HTTP traffic
+      balance roundrobin
+      cookie SRVNAME insert
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      option httpchk GET /
+      option forwardfor
+
+    backend be_gitea
+      description Backend for gitea cluster
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      stick on src
+      stick-table type ip size 200k expire 30m
+      server ausyd1nxvm2080 198.18.26.18:443 check cookie ausyd1nxvm2080 fall 2 inter 2s rise 3 ssl verify none
+      server ausyd1nxvm2081 198.18.27.117:443 check cookie ausyd1nxvm2081 fall 2 inter 2s rise 3 ssl verify none
+      server ausyd1nxvm2082 198.18.28.71:443 check cookie ausyd1nxvm2082 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_grafana
+      description Backend for grafana nodes
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      stick on src
+      stick-table type ip size 200k expire 30m
+      server ausyd1nxvm2015 198.18.27.2:443 check cookie ausyd1nxvm2015 fall 2 inter 2s rise 3 ssl verify none
+      server ausyd1nxvm2016 198.18.28.189:443 check cookie ausyd1nxvm2016 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_jellyfin
+      description Backend for au-syd1 jellyfin
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2051 198.18.25.164:443 check cookie ausyd1nxvm2051 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_k8s_kanidm
+      description Backend for Kanidm (auth.unkin.net via Kubernetes internal Traefik)
+      balance roundrobin
+      http-reuse always
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      redirect scheme https if !{ ssl_fc }
+      option httpchk
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      http-check connect ssl sni auth.unkin.net
+      http-check send meth GET uri /status ver HTTP/1.1 hdr Host auth.unkin.net
+      http-check expect status 200
+      server k8s-traefik-internal 198.18.200.4:443 ssl verify none check inter 2s rise 3 fall 2 sni str(auth.unkin.net)
+
+    backend be_lidarr
+      description Backend for au-syd1 lidarr
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2048 198.18.28.165:443 check cookie ausyd1nxvm2048 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_nzbget
+      description Backend for au-syd1 nzbget
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2045 198.18.25.44:443 check cookie ausyd1nxvm2045 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_prowlarr
+      description Backend for au-syd1 prowlarr
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2050 198.18.25.66:443 check cookie ausyd1nxvm2050 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_radarr
+      description Backend for au-syd1 radarr
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2047 198.18.27.131:443 check cookie ausyd1nxvm2047 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_readarr
+      description Backend for au-syd1 readarr
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2049 198.18.29.32:443 check cookie ausyd1nxvm2049 fall 2 inter 2s rise 3 ssl verify none
+
+    backend be_sonarr
+      description Backend for au-syd1 sonarr
+      balance roundrobin
+      cookie SRVNAME insert indirect nocache
+      http-request set-header X-Forwarded-Port %[dst_port]
+      http-request add-header X-Forwarded-Proto https if { dst_port 443 }
+      http-reuse always
+      option httpchk GET /consul/health
+      option forwardfor
+      option http-keep-alive
+      option prefer-last-server
+      redirect scheme https if !{ ssl_fc }
+      server ausyd1nxvm2046 198.18.26.161:443 check cookie ausyd1nxvm2046 fall 2 inter 2s rise 3 ssl verify none
+
+    # The `peers au-syd1-prod` section is dropped: peer names must be static and a
+    # Deployment cannot provide them. Behind the external Traefik's TLS
+    # passthrough `src` is a Traefik pod, so X-Real-IP, forwardfor and the
+    # `stick on src` tables all key on that; the SRVNAME cookie carries real
+    # session persistence. Traefik cannot emit PROXY protocol to a TLSRoute
+    # backend, so there is nothing to bind `accept-proxy` to.
+
+    listen health
+      bind 0.0.0.0:8404
+      mode http
+      monitor-uri /healthz
+
+    listen stats
+      bind 127.0.0.1:9090
+      mode http
+      stats uri /
+      stats auth admin:admin

apps/base/haproxy/deployment.yaml

@@ -0,0 +1,148 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: haproxy
+  namespace: haproxy
+  annotations:
+    reloader.stakater.com/auto: "true"
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: haproxy
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  template:
+    metadata:
+      labels:
+        app: haproxy
+    spec:
+      automountServiceAccountToken: false
+      terminationGracePeriodSeconds: 150
+      affinity:
+        podAntiAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            - labelSelector:
+                matchLabels:
+                  app: haproxy
+              topologyKey: kubernetes.io/hostname
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 99
+        runAsGroup: 99
+        seccompProfile:
+          type: RuntimeDefault
+      containers:
+        - name: haproxy
+          image: haproxy:3.2.24-alpine
+          imagePullPolicy: IfNotPresent
+          command:
+            - haproxy
+            - -W
+            - -db
+            - -f
+            - /usr/local/etc/haproxy/haproxy.cfg
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop: [ALL]
+              # fe_https binds the privileged port 443 as uid 99, and the
+              # dst_port ACLs need the real port.
+              add: [NET_BIND_SERVICE]
+          ports:
+            - name: https
+              containerPort: 443
+              protocol: TCP
+            - name: health
+              containerPort: 8404
+              protocol: TCP
+            - name: metrics
+              containerPort: 8405
+              protocol: TCP
+            - name: stats
+              containerPort: 9090
+              protocol: TCP
+          lifecycle:
+            preStop:
+              exec:
+                # SIGUSR1 to the master soft-stops the workers; hard-stop-after
+                # caps the drain. Wait so kubelet holds SIGTERM until it is done.
+                command:
+                  - /bin/sh
+                  - -c
+                  - kill -s USR1 1; while kill -0 1 2>/dev/null; do sleep 1; done
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: health
+            initialDelaySeconds: 15
+            periodSeconds: 30
+            timeoutSeconds: 5
+            failureThreshold: 3
+          readinessProbe:
+            httpGet:
+              path: /healthz
+              port: health
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            timeoutSeconds: 5
+            failureThreshold: 3
+          resources:
+            requests:
+              cpu: 200m
+              memory: 256Mi
+            limits:
+              cpu: 2
+              memory: 1Gi
+          volumeMounts:
+            - name: config
+              mountPath: /usr/local/etc/haproxy
+              readOnly: true
+            - name: cert-unkin-net
+              mountPath: /etc/haproxy/certs/unkin-net
+              readOnly: true
+            - name: cert-main-unkin-net
+              mountPath: /etc/haproxy/certs/main-unkin-net
+              readOnly: true
+            - name: cert-ceph-unkin-net
+              mountPath: /etc/haproxy/certs/ceph-unkin-net
+              readOnly: true
+            - name: run
+              mountPath: /var/lib/haproxy
+      volumes:
+        - name: config
+          configMap:
+            name: haproxy-config
+        # ssl-load-extra-files loads <crtfile>.key by default, so the key is
+        # projected next to the cert as tls.crt.key.
+        - name: cert-unkin-net
+          secret:
+            secretName: wildcard-unkin-net-tls
+            items:
+              - key: tls.crt
+                path: tls.crt
+              - key: tls.key
+                path: tls.crt.key
+        - name: cert-main-unkin-net
+          secret:
+            secretName: wildcard-main-unkin-net-tls
+            items:
+              - key: tls.crt
+                path: tls.crt
+              - key: tls.key
+                path: tls.crt.key
+        - name: cert-ceph-unkin-net
+          secret:
+            secretName: wildcard-ceph-unkin-net-tls
+            items:
+              - key: tls.crt
+                path: tls.crt
+              - key: tls.key
+                path: tls.crt.key
+        - name: run
+          emptyDir: {}
+      restartPolicy: Always

apps/base/haproxy/gateway.yaml

@@ -0,0 +1,31 @@
+---
+# External (DMZ) front for the haproxy edge on the traefik-external LB VIP
+# 198.18.199.0. The :443 listener is TLS Passthrough: haproxy owns the three
+# wildcard certs and terminates behind Traefik, so there are no certificateRefs
+# here. Listener hostnames are deliberately unset and the routes carry the
+# explicit hostname list instead; allowedRoutes Same keeps other namespaces off
+# these listeners.
+apiVersion: gateway.networking.k8s.io/v1
+kind: Gateway
+metadata:
+  name: haproxy
+  namespace: haproxy
+  labels:
+    traefik.io/instance: external
+spec:
+  gatewayClassName: traefik-external
+  listeners:
+    - name: http
+      port: 80
+      protocol: HTTP
+      allowedRoutes:
+        namespaces:
+          from: Same
+    - name: https-passthrough
+      port: 443
+      protocol: TLS
+      tls:
+        mode: Passthrough
+      allowedRoutes:
+        namespaces:
+          from: Same

apps/base/haproxy/httproute.yaml

@@ -0,0 +1,37 @@
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: HTTPRoute
+metadata:
+  name: haproxy-http-redirect
+  namespace: haproxy
+  labels:
+    app: haproxy
+spec:
+  hostnames:
+    - sonarr.main.unkin.net
+    - radarr.main.unkin.net
+    - lidarr.main.unkin.net
+    - readarr.main.unkin.net
+    - prowlarr.main.unkin.net
+    - nzbget.main.unkin.net
+    - jellyfin.main.unkin.net
+    - fafflix.unkin.net
+    - git.unkin.net
+    - grafana.unkin.net
+    - dashboard.ceph.unkin.net
+    - auth.unkin.net
+  parentRefs:
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: haproxy
+      sectionName: http
+  rules:
+    - filters:
+        - type: RequestRedirect
+          requestRedirect:
+            scheme: https
+            statusCode: 301
+      matches:
+        - path:
+            type: PathPrefix
+            value: /

apps/base/haproxy/kustomization.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - namespace.yaml
+  - configmap.yaml
+  - deployment.yaml
+  - service.yaml
+  - gateway.yaml
+  - tlsroute.yaml
+  - httproute.yaml
+  - pdb.yaml
+  - vpa.yaml
+  - vmpodscrape.yaml

apps/base/haproxy/namespace.yaml

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

apps/base/haproxy/pdb.yaml

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

apps/base/haproxy/service.yaml

@@ -0,0 +1,19 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: haproxy
+  namespace: haproxy
+spec:
+  type: ClusterIP
+  # Reached only by the external Traefik's TLS-passthrough TLSRoute, so the
+  # peer address here is a Traefik pod, not the client. sessionAffinity is
+  # deliberately absent: keyed on ClientIP it would pin whole Traefik pods,
+  # not clients. Backend persistence rests on the per-backend SRVNAME cookie.
+  selector:
+    app: haproxy
+  ports:
+    - name: https
+      port: 443
+      protocol: TCP
+      targetPort: https

apps/base/haproxy/tlsroute.yaml

@@ -0,0 +1,34 @@
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: TLSRoute
+metadata:
+  name: haproxy
+  namespace: haproxy
+  labels:
+    app: haproxy
+spec:
+  hostnames:
+    - sonarr.main.unkin.net
+    - radarr.main.unkin.net
+    - lidarr.main.unkin.net
+    - readarr.main.unkin.net
+    - prowlarr.main.unkin.net
+    - nzbget.main.unkin.net
+    - jellyfin.main.unkin.net
+    - fafflix.unkin.net
+    - git.unkin.net
+    - grafana.unkin.net
+    - dashboard.ceph.unkin.net
+    - auth.unkin.net
+  parentRefs:
+    - group: gateway.networking.k8s.io
+      kind: Gateway
+      name: haproxy
+      sectionName: https-passthrough
+  rules:
+    - backendRefs:
+        - group: ""
+          kind: Service
+          name: haproxy
+          port: 443
+          weight: 1

apps/base/haproxy/vmpodscrape.yaml

@@ -0,0 +1,13 @@
+---
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMPodScrape
+metadata:
+  name: haproxy
+  namespace: haproxy
+spec:
+  selector:
+    matchLabels:
+      app: haproxy
+  podMetricsEndpoints:
+    - port: metrics
+      path: /metrics

apps/base/haproxy/vpa.yaml

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

@@ -1,97 +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"
-      # Read-only user for CLI tools + the logviewer UI. Hash sourced from the
-      # Vault-synced clickhouse-logreader Secret, same mechanism as vector.
-      # Scoped to the logs database only (unlike vector, which bootstraps it).
-      logreader/password_sha256_hex:
-        valueFrom:
-          secretKeyRef:
-            name: clickhouse-logreader
-            key: password_sha256_hex
-      logreader/networks/ip:
-        - "::/0"
-      logreader/profile: readonly
-      logreader/quota: default
-      logreader/allow_databases/database:
-        - "logs"
-    profiles:
-      default/max_memory_usage: "10000000000"
-      default/max_execution_time: "120"
-      readonly/readonly: "2"
-      readonly/max_memory_usage: "10000000000"
-      readonly/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: docker.io/clickhouse/clickhouse-server:24.8
-              resources:
-                requests:
-                  cpu: 500m
-                  memory: 2Gi
-                limits:
-                  cpu: "2"
-                  memory: 8Gi

apps/base/logging/configmap_logarchiver.yaml

@@ -1,40 +0,0 @@
----
-# logarchiver non-secret config. Secrets (NATS/S3/ClickHouse creds) and the
-# subject filter come from env; everything else uses the binary's built-in
-# defaults, which already target this stack. ack_wait MUST exceed batch.max_age
-# so unacked messages in an open batch are not redelivered mid-batch.
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: logarchiver-config
-  namespace: logging
-data:
-  config.yaml: |
-    nats:
-      ack_wait: 5m
-      fetch_batch: 512
-    batch:
-      max_bytes: 67108864
-      max_events: 200000
-      max_age: 2m
-    # Pin the proven RGW endpoint/bucket; ignore the secret's S3_ENDPOINT/BUCKET_NAME
-    # (AWS creds still come from the secret env). endpoint_env/bucket_env off.
-    s3:
-      endpoint: "https://s3.ceph.unkin.net"
-      bucket: "logs-archive"
-      region: "us-east-1"
-      path_style: true
-      ca_file: /etc/vault-ca/ca.crt
-      endpoint_env: ""
-      bucket_env: ""
-    crypto:
-      key_name: logarchive
-      pubkey_source: vault
-      vault:
-        address: "https://vault.service.consul:8200"
-        mount: gpg
-        auth_method: kubernetes
-        k8s_mount: k8s/au/syd1
-        k8s_role: logging_logarchiver
-        k8s_jwt_path: /var/run/secrets/vault/token
-        ca_file: /etc/vault-ca/ca.crt

apps/base/logging/deployment_logarchiver.yaml

@@ -1,134 +0,0 @@
----
-# logarchiver — replaces the vector-archiver leg. Independent JetStream durable
-# consumer (archiver) that seals raw logs to S3 as zstd + OpenPGP objects and
-# indexes each object in ClickHouse (logs.archive_index). Acks only after the
-# object is in S3 AND indexed. Reuses the same NATS/S3/CA wiring the Vector
-# archiver used; the OpenPGP public key is delivered as a mounted file.
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: logarchiver
-  namespace: logging
-  annotations:
-    configmap.reloader.stakater.com/auto: "true"
-    secret.reloader.stakater.com/reload: "vault-ca-cert"
-  labels:
-    app.kubernetes.io/name: logarchiver
-    app.kubernetes.io/component: archiver
-spec:
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: logarchiver
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: logarchiver
-        vector.dev/exclude: "true"
-    spec:
-      # Dedicated SA whose projected vault-audience token authenticates the
-      # k8s-auth login used to fetch the logarchive public key from the gpg engine.
-      serviceAccountName: logarchiver
-      automountServiceAccountToken: false
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65532
-        runAsGroup: 65532
-        seccompProfile:
-          type: RuntimeDefault
-      containers:
-        - name: logarchiver
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/logarchiver:v0.1.0
-          imagePullPolicy: IfNotPresent
-          args: ["run"]
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop:
-                - ALL
-          ports:
-            - containerPort: 9090
-              name: metrics
-              protocol: TCP
-          env:
-            - name: LOGARCHIVER_CONFIG
-              value: /etc/logarchiver/config.yaml
-            # Server-side subject filter; must match the archiver consumer's filter.
-            - name: ARCHIVE_SUBJECTS
-              value: "logs.k8s.vault.>"
-            - name: NATS_CONSUMER_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: nats-auth
-                  key: consumer_password
-            - name: CLICKHOUSE_USER
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-credentials
-                  key: username
-            - name: CLICKHOUSE_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-credentials
-                  key: password
-          # S3 creds + S3_ENDPOINT + BUCKET_NAME from the cephrgw BucketAccess Secret.
-          envFrom:
-            - secretRef:
-                name: logs-archive-s3
-          livenessProbe:
-            httpGet:
-              path: /healthz
-              port: metrics
-            initialDelaySeconds: 15
-            periodSeconds: 30
-            timeoutSeconds: 5
-            failureThreshold: 3
-          readinessProbe:
-            httpGet:
-              path: /healthz
-              port: metrics
-            initialDelaySeconds: 5
-            periodSeconds: 10
-            timeoutSeconds: 5
-            failureThreshold: 3
-          resources:
-            requests:
-              cpu: 100m
-              memory: 256Mi
-            limits:
-              cpu: "1"
-              memory: 1Gi
-          volumeMounts:
-            - name: config
-              mountPath: /etc/logarchiver/config.yaml
-              subPath: config.yaml
-              readOnly: true
-            - name: vault-token
-              mountPath: /var/run/secrets/vault
-              readOnly: true
-            - name: vault-ca-cert
-              mountPath: /etc/vault-ca/ca.crt
-              subPath: ca.crt
-              readOnly: true
-            - name: tmp
-              mountPath: /tmp
-      volumes:
-        - name: config
-          configMap:
-            name: logarchiver-config
-        # Projected SA token with audience "vault" for the gpg-engine k8s login.
-        - name: vault-token
-          projected:
-            sources:
-              - serviceAccountToken:
-                  path: token
-                  audience: vault
-                  expirationSeconds: 600
-        - name: vault-ca-cert
-          secret:
-            secretName: vault-ca-cert
-        - name: tmp
-          emptyDir: {}

apps/base/logging/gateway.yaml

@@ -1,16 +1,13 @@
 ---
-# Log ingestion endpoint for puppet-managed VMs (and any non-k8s client).
+# Log ingestion endpoint for puppet-managed VMs (and any non-k8s client):
-# Reuses the internal Traefik gateway + cert-manager + external-dns pattern so
+# fronts the VLCluster vlinsert service over TLS at a name VMs can resolve.
-# VMs reach the Vector aggregator's HTTP source over TLS at a DNS name they can
-# resolve. The puppet-side Vector rollout ships NDJSON to
-# https://logs-ingest.k8s.syd1.au.unkin.net/ (a later task).
 apiVersion: gateway.networking.k8s.io/v1
 kind: Gateway
 metadata:
   name: logs-ingest
   namespace: logging
   labels:
-    app.kubernetes.io/name: vector-aggregator
+    app.kubernetes.io/name: victorialogs
     app.kubernetes.io/component: ingest
     traefik.io/instance: internal
   annotations:

apps/base/logging/httproute.yaml

@@ -5,7 +5,7 @@ metadata:
   name: logs-ingest-http-redirect
   namespace: logging
   labels:
-    app.kubernetes.io/name: vector-aggregator
+    app.kubernetes.io/name: victorialogs
     app.kubernetes.io/component: ingest
 spec:
   hostnames:
@@ -32,7 +32,7 @@ metadata:
   name: logs-ingest
   namespace: logging
   labels:
-    app.kubernetes.io/name: vector-aggregator
+    app.kubernetes.io/name: victorialogs
     app.kubernetes.io/component: ingest
 spec:
   hostnames:
@@ -46,8 +46,8 @@ spec:
     - backendRefs:
         - group: ""
           kind: Service
-          name: vector-vm-ingest
+          name: vlinsert-logs
-          port: 8080
+          port: 9481
           weight: 1
       matches:
         - path:

apps/base/logging/job_clickhouse-schema.yaml

@@ -1,131 +0,0 @@
----
-# Declarative ClickHouse schema bootstrap. Runs as an ArgoCD PostSync hook so it
-# executes after the ClickHouseInstallation is reconciled, and re-runs on every
-# sync (idempotent CREATE ... IF NOT EXISTS). Edit the DDL here to evolve the
-# schema; the Vector aggregator writes to logs.raw with skip_unknown_fields, so
-# adding columns is backward-compatible.
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: clickhouse-schema
-  namespace: logging
-  annotations:
-    argocd.argoproj.io/hook: PostSync
-    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation
-  labels:
-    app.kubernetes.io/name: clickhouse-schema
-    app.kubernetes.io/component: bootstrap
-spec:
-  backoffLimit: 20
-  activeDeadlineSeconds: 1800
-  ttlSecondsAfterFinished: 3600
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: clickhouse-schema
-        vector.dev/exclude: "true"
-    spec:
-      restartPolicy: OnFailure
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 101
-        runAsGroup: 101
-      containers:
-        - name: clickhouse-schema
-          image: docker.io/clickhouse/clickhouse-server:24.8
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop:
-                - ALL
-          env:
-            - name: HOME
-              value: /tmp
-            - name: CLICKHOUSE_USER
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-credentials
-                  key: username
-            - name: CLICKHOUSE_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-credentials
-                  key: password
-          command:
-            - /bin/bash
-            - -ec
-            - |
-              host=clickhouse-logs.logging.svc.cluster.local
-              echo "Waiting for ClickHouse at ${host}:9000 ..."
-              until clickhouse-client --host "$host" --port 9000 \
-                  --user "$CLICKHOUSE_USER" --password "$CLICKHOUSE_PASSWORD" \
-                  --query "SELECT 1" >/dev/null 2>&1; do
-                echo "  not ready, retrying in 5s"; sleep 5
-              done
-              echo "Applying schema ..."
-              clickhouse-client --host "$host" --port 9000 \
-                --user "$CLICKHOUSE_USER" --password "$CLICKHOUSE_PASSWORD" \
-                --multiquery <<'EOSQL'
-              CREATE DATABASE IF NOT EXISTS logs;
-
-              CREATE TABLE IF NOT EXISTS logs.raw
-              (
-                  timestamp  DateTime64(3)           DEFAULT now64(3),
-                  host       LowCardinality(String)  DEFAULT '',
-                  source     LowCardinality(String)  DEFAULT '',
-                  namespace  LowCardinality(String)  DEFAULT '',
-                  pod        String                  DEFAULT '',
-                  container  LowCardinality(String)  DEFAULT '',
-                  stream     LowCardinality(String)  DEFAULT '',
-                  severity   LowCardinality(String)  DEFAULT '',
-                  message    String                  DEFAULT '',
-                  labels     Map(LowCardinality(String), String),
-                  fields     Map(LowCardinality(String), String)
-              )
-              ENGINE = MergeTree
-              PARTITION BY toDate(timestamp)
-              ORDER BY (source, namespace, host, timestamp)
-              TTL toDateTime(timestamp) + INTERVAL 3 DAY
-              SETTINGS index_granularity = 8192;
-
-              -- One row per archived S3 object (written by logarchiver). No TTL:
-              -- the index must outlive logs.raw so the long-term S3 archive stays
-              -- searchable. Keep in sync with logarchiver internal/index/ddl.go.
-              CREATE TABLE IF NOT EXISTS logs.archive_index
-              (
-                  object_key       String,
-                  bucket           LowCardinality(String),
-                  subject          LowCardinality(String),
-                  hosts            Array(LowCardinality(String)),
-                  min_ts           DateTime64(3),
-                  max_ts           DateTime64(3),
-                  event_count      UInt64,
-                  raw_bytes        UInt64,
-                  stored_bytes     UInt64,
-                  compression      LowCardinality(String),
-                  cipher           LowCardinality(String),
-                  container_format LowCardinality(String),
-                  key_name         LowCardinality(String),
-                  key_fingerprint  String,
-                  created_at       DateTime64(3) DEFAULT now64(3),
-                  INDEX idx_hosts hosts TYPE bloom_filter GRANULARITY 1
-              )
-              ENGINE = MergeTree
-              PARTITION BY toYYYYMM(min_ts)
-              ORDER BY (subject, min_ts, object_key);
-              EOSQL
-              echo "Schema applied."
-          resources:
-            requests:
-              cpu: 50m
-              memory: 128Mi
-            limits:
-              cpu: 500m
-              memory: 512Mi
-          volumeMounts:
-            - name: tmp
-              mountPath: /tmp
-      volumes:
-        - name: tmp
-          emptyDir: {}

apps/base/logging/kustomization.yaml

@@ -5,46 +5,8 @@ kind: Kustomization
 resources:
   - namespace.yaml
   - vaultauth.yaml
-  - vaultstaticsecret.yaml
+  - vlcluster.yaml
-  - clickhouseinstallation.yaml
+  - vlagent.yaml
-  - job_clickhouse-schema.yaml
-  - nats-bootstrap-job.yaml
-  - cephrgw.yaml
   - gateway.yaml
   - httproute.yaml
-  - serviceaccount_logarchiver.yaml
+  - vlogs
-  - configmap_logarchiver.yaml
-  - deployment_logarchiver.yaml
-  - logviewer
-
-# Vector pipelines are the single source of truth (also validated by
-# `vector test` in CI). Mounted into each tier via `existingConfigMaps`.
-configMapGenerator:
-  # Tunable JetStream stream limits (the nats-bootstrap Job reads these and does
-  # create-or-update). Hash suffix is INTENTIONALLY left on: editing a value
-  # renames the ConfigMap, which rewrites the Job's env reference, which changes
-  # the PostSync hook Job's spec and forces Argo to re-run it -> new limits apply.
-  # Sizing assumes ~1500 events/s avg @ ~1 KiB/event with S2 compression (~4x):
-  # ~33 GiB/day compressed -> ~100 GiB/3d per replica. max_bytes 130 GiB sits
-  # under the 180Gi/node PVC (see values-nats.yaml). Raising retention beyond the
-  # PVC requires bumping BOTH max_bytes here and fileStore PVC size in values.
-  - name: nats-stream-limits
-    literals:
-      - max_age=72h
-      - max_bytes=139586437120
-      - dupe_window=2m
-  - name: vector-agent-config
-    files:
-      - agent.yaml=vector/agent.yaml
-    options:
-      disableNameSuffixHash: true
-  - name: vector-aggregator-config
-    files:
-      - aggregator.yaml=vector/aggregator.yaml
-    options:
-      disableNameSuffixHash: true
-  - name: vector-vm-ingest-config
-    files:
-      - vm-ingest.yaml=vector/vm-ingest.yaml
-    options:
-      disableNameSuffixHash: true

apps/base/logging/logviewer/deployment.yaml

@@ -1,80 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: logviewer
-  namespace: logging
-  annotations:
-    secret.reloader.stakater.com/reload: "clickhouse-logreader"
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: logviewer
-  strategy:
-    type: Recreate
-  template:
-    metadata:
-      labels:
-        app: logviewer
-    spec:
-      serviceAccountName: default
-      automountServiceAccountToken: false
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65532
-        runAsGroup: 65532
-        fsGroup: 65532
-        seccompProfile:
-          type: RuntimeDefault
-      containers:
-        - name: logviewer
-          image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/logviewer:v0.1.0
-          imagePullPolicy: IfNotPresent
-          ports:
-            - containerPort: 8080
-              name: http
-              protocol: TCP
-          env:
-            - name: CH_URL
-              value: http://clickhouse-logs.logging.svc.cluster.local:8123
-            - name: CH_USER
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-logreader
-                  key: username
-            - name: CH_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: clickhouse-logreader
-                  key: password
-          livenessProbe:
-            httpGet:
-              path: /healthz
-              port: http
-            initialDelaySeconds: 10
-            periodSeconds: 30
-            timeoutSeconds: 5
-            failureThreshold: 3
-          readinessProbe:
-            httpGet:
-              path: /healthz
-              port: http
-            initialDelaySeconds: 5
-            periodSeconds: 10
-            timeoutSeconds: 5
-            failureThreshold: 3
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop:
-                - ALL
-          resources:
-            requests:
-              cpu: 100m
-              memory: 128Mi
-            limits:
-              cpu: 500m
-              memory: 512Mi
-      restartPolicy: Always

apps/base/logging/logviewer/gateway.yaml

@@ -1,38 +0,0 @@
----
-# Internal front for the logviewer UI (cf. mediamover/pdbmux).
-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: logviewer.unkin.net
-    cert-manager.io/private-key-size: "4096"
-    external-dns.alpha.kubernetes.io/hostname: logviewer.unkin.net
-    external-dns.alpha.kubernetes.io/target: 198.18.200.4
-  name: logviewer
-  namespace: logging
-spec:
-  gatewayClassName: traefik-internal
-  listeners:
-    - allowedRoutes:
-        namespaces:
-          from: Same
-      hostname: logviewer.unkin.net
-      name: http
-      port: 80
-      protocol: HTTP
-    - allowedRoutes:
-        namespaces:
-          from: Same
-      hostname: logviewer.unkin.net
-      name: https
-      port: 443
-      protocol: HTTPS
-      tls:
-        certificateRefs:
-          - group: ""
-            kind: Secret
-            name: logviewer-tls
-        mode: Terminate

apps/base/logging/logviewer/service.yaml

@@ -1,36 +0,0 @@
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: logviewer
-  namespace: logging
-spec:
-  internalTrafficPolicy: Cluster
-  ports:
-    - name: http
-      port: 8080
-      protocol: TCP
-      targetPort: http
-  selector:
-    app: logviewer
-  sessionAffinity: None
-  type: ClusterIP
----
-# Front-door entry Service: the HTTPRoute for logviewer.unkin.net targets this;
-# all traffic enters via oauth2-proxy.
-apiVersion: v1
-kind: Service
-metadata:
-  name: logviewer-oauth2
-  namespace: logging
-spec:
-  internalTrafficPolicy: Cluster
-  ports:
-    - name: http
-      port: 80
-      protocol: TCP
-      targetPort: http
-  selector:
-    app: logviewer-oauth2
-  sessionAffinity: None
-  type: ClusterIP

apps/base/logging/logviewer/vaultstaticsecret.yaml

@@ -1,21 +0,0 @@
----
-# Authentik OIDC client for logviewer (client_id, client_secret, cookie_secret)
-# seeded at kv/kubernetes/namespace/logging/default/oauth-credentials; the
-# logging/default templated policy already grants read, so no terraform-vault
-# change is needed.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: logviewer-oauth-credentials
-  namespace: logging
-spec:
-  destination:
-    create: true
-    name: logviewer-oauth-credentials
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/logging/default/oauth-credentials
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default

apps/base/logging/nats-bootstrap-job.yaml

@@ -1,158 +0,0 @@
----
-# Declarative JetStream provisioning: the LOGS stream + durable consumers.
-# ArgoCD PostSync hook, idempotent create-or-UPDATE, re-runs each sync.
-#
-# Stream LOGS: file storage, 3 replicas, retention=limits (NOT workqueue) so the
-# transform tier AND the archiver each independently see every message — reading
-# never deletes; only max-age/max-bytes do. S2 compression is on (logs compress
-# well). Replay window = max-age (3d default). Beyond that, the S3 archive is the
-# ONLY long-term source — everything else is gone after 3 days (accepted design).
-#
-# TUNABLE LIMITS LIVE IN A CONFIGMAP (nats-stream-limits): max_age, max_bytes,
-# dupe_window. Change the ConfigMap and re-sync — this Job re-runs and applies
-# the new limits via `nats stream edit` (no manual surgery). The ConfigMap is
-# generated with a content-hash suffix (kustomize), so editing it changes both
-# the ConfigMap name AND this Job's env reference → the PostSync hook Job's spec
-# changes and Argo re-runs it (belt-and-suspenders on top of hooks running each
-# sync; hook-delete-policy=BeforeHookCreation recreates it every time).
-#
-# Consumers (independent offsets = true fan-out):
-#   transform  -> whole log stream, feeds the ClickHouse transform tier
-#   archiver   -> configurable security-relevant subset, feeds the S3 archiver.
-#                 Default filter is Vault audit (logs.k8s.vault.>); ADD subjects
-#                 by editing ARCHIVE_SUBJECTS (space-separated -> repeated
-#                 --filter). Exact default set is an open decision for Ben.
-#
-# Runbook (replay):
-#   (a) reprocess from JetStream (within max-age, 3d): scale the transform tier
-#       to 0, then `nats consumer rm LOGS transform` and re-run this Job
-#       (recreates at DeliverAll), or `nats consumer edit`/`--replay` from a
-#       start seq/time.
-#   (b) long-horizon (beyond JetStream): re-ingest S3 archive objects back
-#       through the transform tier (vector aws_s3 source or a one-shot Job).
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: nats-bootstrap
-  namespace: logging
-  annotations:
-    argocd.argoproj.io/hook: PostSync
-    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation
-  labels:
-    app.kubernetes.io/name: nats-bootstrap
-    app.kubernetes.io/component: bootstrap
-spec:
-  backoffLimit: 20
-  activeDeadlineSeconds: 1800
-  ttlSecondsAfterFinished: 3600
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: nats-bootstrap
-        vector.dev/exclude: "true"
-    spec:
-      restartPolicy: OnFailure
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 1000
-        runAsGroup: 1000
-      containers:
-        - name: nats-bootstrap
-          image: docker.io/natsio/nats-box:0.18.0
-          # nats CLI stats the working directory when loading its response
-          # schemas; under readOnlyRootFilesystem + runAsUser 1000 the image's
-          # default WORKDIR is not accessible ("stat .: permission denied"), so
-          # run from the writable /tmp emptyDir.
-          workingDir: /tmp
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop:
-                - ALL
-          env:
-            - name: HOME
-              value: /tmp
-            - name: NATS_URL
-              value: "nats://nats.logging.svc.cluster.local:4222"
-            - name: NATS_ADMIN_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: nats-auth
-                  key: admin_password
-            # Tunable stream limits — sourced from the ConfigMap.
-            - name: MAX_AGE
-              valueFrom:
-                configMapKeyRef:
-                  name: nats-stream-limits
-                  key: max_age
-            - name: MAX_BYTES
-              valueFrom:
-                configMapKeyRef:
-                  name: nats-stream-limits
-                  key: max_bytes
-            - name: DUPE_WINDOW
-              valueFrom:
-                configMapKeyRef:
-                  name: nats-stream-limits
-                  key: dupe_window
-            # Space-separated subject filters for the archiver consumer.
-            - name: ARCHIVE_SUBJECTS
-              value: "logs.k8s.vault.>"
-          command:
-            - /bin/sh
-            - -ec
-            - |
-              export NATS_USER=log-admin NATS_PASSWORD="$NATS_ADMIN_PASSWORD"
-              echo "Waiting for NATS + JetStream ..."
-              until nats --server "$NATS_URL" account info >/dev/null 2>&1; do
-                echo "  not ready, retry in 5s"; sleep 5
-              done
-
-              echo "Ensuring stream LOGS (max_age=$MAX_AGE max_bytes=$MAX_BYTES dupe=$DUPE_WINDOW) ..."
-              # Create if absent; otherwise converge the mutable limits from the
-              # ConfigMap. (storage/retention/replicas are immutable, set only on
-              # create.)
-              nats stream add LOGS \
-                --subjects='logs.>' --storage=file --replicas=3 \
-                --retention=limits --discard=old --compression=s2 \
-                --max-age="$MAX_AGE" --max-bytes="$MAX_BYTES" \
-                --max-msgs=-1 --max-msgs-per-subject=-1 --max-msg-size=-1 \
-                --max-consumers=-1 --dupe-window="$DUPE_WINDOW" --defaults 2>/dev/null \
-              && echo "  created" \
-              || nats stream edit -f LOGS \
-                --subjects='logs.>' --discard=old --compression=s2 \
-                --max-age="$MAX_AGE" --max-bytes="$MAX_BYTES" \
-                --max-msgs=-1 --max-msgs-per-subject=-1 --max-msg-size=-1 \
-                --max-consumers=-1 --dupe-window="$DUPE_WINDOW"
-
-              echo "Ensuring consumer transform ..."
-              nats consumer add LOGS transform \
-                --pull --filter='logs.>' --deliver=all --ack=explicit \
-                --max-deliver=-1 --replay=instant --defaults 2>/dev/null \
-              || echo "  transform already exists"
-
-              echo "Ensuring consumer archiver (filters: $ARCHIVE_SUBJECTS) ..."
-              filter_args=""
-              for s in $ARCHIVE_SUBJECTS; do filter_args="$filter_args --filter=$s"; done
-              # shellcheck disable=SC2086
-              nats consumer add LOGS archiver \
-                --pull $filter_args --deliver=all --ack=explicit \
-                --max-deliver=-1 --replay=instant --defaults 2>/dev/null \
-              || echo "  archiver already exists"
-
-              echo "Done."
-              nats stream info LOGS
-          resources:
-            requests:
-              cpu: 50m
-              memory: 64Mi
-            limits:
-              cpu: 500m
-              memory: 256Mi
-          volumeMounts:
-            - name: tmp
-              mountPath: /tmp
-      volumes:
-        - name: tmp
-          emptyDir: {}

apps/base/logging/serviceaccount_logarchiver.yaml

@@ -1,9 +0,0 @@
----
-# Dedicated SA for logarchiver's Vault k8s-auth login (role logging_logarchiver,
-# terraform-vault). Only used to fetch the logarchive public key.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: logarchiver
-  namespace: logging
-automountServiceAccountToken: false

apps/base/logging/vaultstaticsecret.yaml

@@ -1,73 +0,0 @@
----
-# ClickHouse credentials for the `vector` user.
-#
-# Seed the Vault KV entry once (values are NOT stored in git), e.g.:
-#   PW=$(openssl rand -base64 24)
-#   HASH=$(printf '%s' "$PW" | sha256sum | cut -d' ' -f1)
-#   vault kv put kv/kubernetes/namespace/logging/default/clickhouse-credentials \
-#     username=vector password="$PW" password_sha256_hex="$HASH"
-#
-# The `logging/default` ServiceAccount reads this path via the templated
-# `policies/kv/kubernetes/default.yaml` policy (k8s auth role `default`), so no
-# terraform-vault change is required — only the value above must be written.
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: clickhouse-credentials
-  namespace: logging
-spec:
-  destination:
-    create: true
-    name: clickhouse-credentials
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/logging/default/clickhouse-credentials
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-# ClickHouse credentials for the read-only `logreader` user (CLI tools +
-# logviewer UI). Seeded the same way as clickhouse-credentials above:
-#   PW=$(openssl rand -hex 24)
-#   HASH=$(printf '%s' "$PW" | sha256sum | cut -d' ' -f1)
-#   vault kv put kv/kubernetes/namespace/logging/default/clickhouse-logreader \
-#     username=logreader password="$PW" password_sha256_hex="$HASH"
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: clickhouse-logreader
-  namespace: logging
-spec:
-  destination:
-    create: true
-    name: clickhouse-logreader
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/logging/default/clickhouse-logreader
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default
----
-# NATS JetStream auth. Distinct passwords for the producer (edge), consumer
-# (transform tier + archiver) and admin (bootstrap Job) users. Seed once:
-#   for k in admin producer consumer; do declare P_$k=$(openssl rand -base64 24); done
-#   vault kv put kv/kubernetes/namespace/logging/default/nats-auth \
-#     admin_password="$P_admin" producer_password="$P_producer" consumer_password="$P_consumer"
-apiVersion: secrets.hashicorp.com/v1beta1
-kind: VaultStaticSecret
-metadata:
-  name: nats-auth
-  namespace: logging
-spec:
-  destination:
-    create: true
-    name: nats-auth
-    overwrite: true
-  hmacSecretData: true
-  mount: kv
-  path: kubernetes/namespace/logging/default/nats-auth
-  refreshAfter: 5m
-  type: kv-v2
-  vaultAuthRef: default

apps/base/logging/vector/agent.yaml

@@ -1,43 +0,0 @@
----
-# Vector EDGE agent pipeline (DaemonSet) — thin publisher, single source of
-# truth. Mounted via existingConfigMaps (NOT the chart's customConfig, whose
-# Helm `tpl` pass collides with Vector's own {{ }} / ${ } syntax). Tails all pod
-# logs, attaches only routing tokens, publishes to JetStream. No parsing.
-data_dir: /vector-data-dir
-
-api:
-  enabled: false
-
-sources:
-  kubernetes_logs:
-    type: kubernetes_logs
-
-transforms:
-  # Routing metadata only: NATS-subject-safe namespace + container tokens.
-  keymeta:
-    type: remap
-    inputs:
-      - kubernetes_logs
-    source: |
-      ns = to_string(.kubernetes.pod_namespace || "unknown") ?? "unknown"
-      .ns_token = replace(ns, r'[^a-zA-Z0-9_-]', "_")
-      cont = to_string(.kubernetes.container_name || "unknown") ?? "unknown"
-      .cont_token = replace(cont, r'[^a-zA-Z0-9_-]', "_")
-
-sinks:
-  to_jetstream:
-    type: nats
-    inputs:
-      - keymeta
-    url: nats://nats.logging.svc.cluster.local:4222
-    connection_name: vector-agent
-    subject: "logs.k8s.{{ ns_token }}.{{ cont_token }}"
-    jetstream:
-      enabled: true
-    auth:
-      strategy: user_password
-      user_password:
-        user: log-producer
-        password: ${NATS_PRODUCER_PASSWORD}
-    encoding:
-      codec: json

apps/base/logging/vector/aggregator-tests.yaml

@@ -1,668 +0,0 @@
----
-# `vector test` unit tests for the aggregator transforms. Merged with
-# aggregator.yaml in CI (.woodpecker/vector-test.yaml). This is the pattern the
-# per-app parsing follow-ups extend: add a test per new transform here.
-tests:
-  - name: subject_routes_k8s_vs_vm
-    inputs:
-      - insert_at: route
-        type: log
-        log_fields:
-          subject: "logs.k8s.shop.web"
-          message: "routed"
-    outputs:
-      - extract_from: route.k8s
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.message, "routed")
-
-  - name: k8s_log_is_normalised
-    inputs:
-      - insert_at: k8s_shape
-        type: log
-        log_fields:
-          message: "hello from pod"
-          stream: "stdout"
-          timestamp: "2026-07-27T00:00:00Z"
-          kubernetes.pod_name: "web-abc"
-          kubernetes.pod_namespace: "shop"
-          kubernetes.container_name: "web"
-          kubernetes.pod_node_name: "node-1"
-    outputs:
-      - extract_from: k8s_shape
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "shop")
-              assert_eq!(.pod, "web-abc")
-              assert_eq!(.container, "web")
-              assert_eq!(.host, "node-1")
-              assert_eq!(.stream, "stdout")
-              assert_eq!(.message, "hello from pod")
-
-  - name: vm_log_is_normalised
-    inputs:
-      - insert_at: vm_shape
-        type: log
-        log_fields:
-          message: "sshd started"
-          host: "vm-db-1"
-          severity: "info"
-          role: "database"
-    outputs:
-      - extract_from: vm_shape
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.host, "vm-db-1")
-              assert_eq!(.severity, "info")
-              assert_eq!(.message, "sshd started")
-              assert_eq!(.labels.role, "database")
-
-  # --- catch-all preservation: an unclaimed k8s event still flows app_route ->
-  # generic route -> k8s_shape (proves the two-stage chain keeps the fallback) ---
-  - name: unclaimed_k8s_falls_through_to_generic
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.shop.web"
-          message: "plain app log"
-    outputs:
-      - extract_from: route.k8s
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.message, "plain app log")
-
-  # --- Tier-1: Authentik SSO (k8s, LIVE NOW) ---
-  - name: authentik_routes_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.authentik.server"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.authentik
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: authentik_parse_extracts_event
-    inputs:
-      - insert_at: authentik_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.authentik.server"
-          stream: "stdout"
-          kubernetes.pod_namespace: "authentik"
-          kubernetes.container_name: "server"
-          kubernetes.pod_node_name: "node-2"
-          message: '{"event":"login","action":"login","user":"alice","client_ip":"203.0.113.9","result":"success","level":"info","logger":"authentik.events","timestamp":"2026-07-27T00:00:00Z"}'
-    outputs:
-      - extract_from: authentik_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "authentik")
-              assert_eq!(.container, "server")
-              assert_eq!(.severity, "info")
-              assert_eq!(.message, "login")
-              assert_eq!(.labels.app, "authentik")
-              assert_eq!(.fields.event, "login")
-              assert_eq!(.fields.action, "login")
-              assert_eq!(.fields.user, "alice")
-              assert_eq!(.fields.client_ip, "203.0.113.9")
-              assert_eq!(.fields.result, "success")
-
-  # --- Tier-1: Traefik ingress (k8s, JSON access logs) ---
-  - name: traefik_routes_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.traefik-system.traefik"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.traefik
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: traefik_parse_extracts_access_fields
-    inputs:
-      - insert_at: traefik_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.traefik-system.traefik"
-          kubernetes.pod_namespace: "traefik-system"
-          kubernetes.container_name: "traefik"
-          kubernetes.pod_node_name: "node-3"
-          message: '{"RouterName":"web@kubernetes","ServiceName":"shop-svc@kubernetes","RequestMethod":"GET","RequestPath":"/api","RequestHost":"shop.example.net","RequestProtocol":"HTTP/1.1","DownstreamStatus":200,"Duration":5000000,"ClientHost":"203.0.113.5","StartUTC":"2026-07-27T00:00:00Z"}'
-    outputs:
-      - extract_from: traefik_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "traefik-system")
-              assert_eq!(.labels.app, "traefik")
-              assert_eq!(.message, "GET /api 200")
-              assert_eq!(.fields.route, "web@kubernetes")
-              assert_eq!(.fields.service, "shop-svc@kubernetes")
-              assert_eq!(.fields.method, "GET")
-              assert_eq!(.fields.path, "/api")
-              assert_eq!(.fields.host, "shop.example.net")
-              assert_eq!(.fields.status, "200")
-              assert_eq!(.fields.duration_ms, "5")
-              assert_eq!(.fields.client_ip, "203.0.113.5")
-
-  # --- Tier-1: Vault/OpenBao file audit (VM, awaiting VM vector) ---
-  - name: vault_routes_by_file
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.vault1_syd1"
-          file: "/var/log/vault_audit.log"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.vault
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: vault_parse_extracts_request
-    inputs:
-      - insert_at: vault_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.vault1_syd1"
-          host: "vault1"
-          file: "/var/log/vault_audit.log"
-          message: '{"time":"2026-07-27T00:00:00Z","type":"response","auth":{"display_name":"token"},"request":{"operation":"read","path":"secret/data/app","remote_address":"10.0.0.9"},"error":""}'
-    outputs:
-      - extract_from: vault_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.host, "vault1")
-              assert_eq!(.labels.app, "vault")
-              assert_eq!(.message, "read secret/data/app")
-              assert_eq!(.fields.type, "response")
-              assert_eq!(.fields.display_name, "token")
-              assert_eq!(.fields.operation, "read")
-              assert_eq!(.fields.path, "secret/data/app")
-              assert_eq!(.fields.remote_address, "10.0.0.9")
-
-  # --- Tier-1: nginx access (VM, awaiting VM vector) ---
-  - name: nginx_access_routes_by_file
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.web1_syd1"
-          file: "/var/log/nginx/shop_access.log"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.nginx_access
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: nginx_access_parse_extracts_combined
-    inputs:
-      - insert_at: nginx_access_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.web1_syd1"
-          host: "web1"
-          file: "/var/log/nginx/shop_access.log"
-          message: '192.0.2.10 - - [27/Jul/2026:00:00:00 +0000] "GET /index.html HTTP/1.1" 200 1024 "https://ref.example/" "Mozilla/5.0" 0.012'
-    outputs:
-      - extract_from: nginx_access_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.stream, "access")
-              assert_eq!(.labels.log_type, "access")
-              assert_eq!(.fields.client_ip, "192.0.2.10")
-              assert_eq!(.fields.method, "GET")
-              assert_eq!(.fields.path, "/index.html")
-              assert_eq!(.fields.status, "200")
-              assert_eq!(.fields.bytes, "1024")
-              assert_eq!(.fields.referer, "https://ref.example/")
-              assert_eq!(.fields.user_agent, "Mozilla/5.0")
-              assert_eq!(.fields.request_time, "0.012")
-
-  # --- Tier-1: nginx error (VM, awaiting VM vector) ---
-  - name: nginx_error_routes_by_file
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.web1_syd1"
-          file: "/var/log/nginx/shop_error.log"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.nginx_error
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: nginx_error_parse_extracts_fields
-    inputs:
-      - insert_at: nginx_error_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.web1_syd1"
-          host: "web1"
-          file: "/var/log/nginx/shop_error.log"
-          message: '2026/07/27 00:00:00 [error] 1234#0: *5 open() "/var/www/x" failed (2: No such file or directory), client: 192.0.2.20, server: shop, request: "GET / HTTP/1.1", host: "shop"'
-    outputs:
-      - extract_from: nginx_error_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.stream, "error")
-              assert_eq!(.severity, "error")
-              assert_eq!(.labels.log_type, "error")
-              assert_eq!(.fields.level, "error")
-              assert_eq!(.fields.pid, "1234")
-              assert_eq!(.fields.cid, "5")
-              assert_eq!(.fields.client_ip, "192.0.2.20")
-
-  # --- Tier-1: HAProxy httplog (VM journald, awaiting VM vector) ---
-  - name: haproxy_routes_by_identifier
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.halb1_syd1"
-          SYSLOG_IDENTIFIER: "haproxy"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.haproxy
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: haproxy_parse_extracts_timers
-    inputs:
-      - insert_at: haproxy_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.halb1_syd1"
-          host: "halb1"
-          SYSLOG_IDENTIFIER: "haproxy"
-          message: '192.0.2.30:54321 [27/Jul/2026:00:00:00.123] fe_http be_app/app1 10/0/1/2/13 200 512 - - ---- 5/4/3/2/0 0/0 "GET /health HTTP/1.1"'
-    outputs:
-      - extract_from: haproxy_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.labels.app, "haproxy")
-              assert_eq!(.fields.client_ip, "192.0.2.30")
-              assert_eq!(.fields.frontend, "fe_http")
-              assert_eq!(.fields.backend, "be_app")
-              assert_eq!(.fields.server, "app1")
-              assert_eq!(.fields.tq, "10")
-              assert_eq!(.fields.tw, "0")
-              assert_eq!(.fields.tc, "1")
-              assert_eq!(.fields.tr, "2")
-              assert_eq!(.fields.tt, "13")
-              assert_eq!(.fields.termination_state, "----")
-              assert_eq!(.fields.retries, "0")
-              assert_eq!(.fields.status, "200")
-              assert_eq!(.fields.bytes, "512")
-
-  # --- Tier-1: glauth LDAP (VM, awaiting VM vector) ---
-  - name: glauth_routes_by_identifier
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.ldap1_syd1"
-          SYSLOG_IDENTIFIER: "glauth"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.glauth
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: glauth_parse_extracts_bind
-    inputs:
-      - insert_at: glauth_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.ldap1_syd1"
-          host: "ldap1"
-          SYSLOG_IDENTIFIER: "glauth"
-          message: '{"level":"info","msg":"Bind success as user","bindDN":"cn=admin,dc=example,dc=com","src":"192.0.2.40:1234","time":"2026-07-27T00:00:00Z"}'
-    outputs:
-      - extract_from: glauth_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.host, "ldap1")
-              assert_eq!(.severity, "info")
-              assert_eq!(.labels.app, "glauth")
-              assert_eq!(.fields.bindDN, "cn=admin,dc=example,dc=com")
-              assert_eq!(.fields.remote, "192.0.2.40:1234")
-              assert_eq!(.fields.success, "true")
-
-  # ================= Tier-2 (stacks on #318) =================
-
-  # --- BIND query logs (k8s bind-* + VM named) ---
-  - name: bind_routes_k8s_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.bind-internal.named"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.bind_query
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: bind_routes_vm_by_identifier
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.dns1_syd1"
-          SYSLOG_IDENTIFIER: "named"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.bind_query
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: bind_parse_extracts_query
-    inputs:
-      - insert_at: bind_query_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.bind-internal.named"
-          kubernetes.pod_namespace: "bind-internal"
-          kubernetes.container_name: "named"
-          kubernetes.pod_node_name: "node-4"
-          message: '02-Aug-2026 00:00:00.123 client @0x7f 192.0.2.1#40426 (www.example.com): view internal: query: www.example.com IN A +E(0)K (198.18.200.7)'
-    outputs:
-      - extract_from: bind_query_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "bind-internal")
-              assert_eq!(.labels.app, "bind")
-              assert_eq!(.message, "query www.example.com A")
-              assert_eq!(.fields.client_ip, "192.0.2.1")
-              assert_eq!(.fields.qname, "www.example.com")
-              assert_eq!(.fields.qclass, "IN")
-              assert_eq!(.fields.qtype, "A")
-              assert_eq!(.fields.view, "internal")
-
-  # --- Rancher audit (k8s, cattle-system sidecar) ---
-  - name: rancher_routes_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.cattle-system.rancher-audit-log"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.rancher_audit
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: rancher_parse_extracts_audit
-    inputs:
-      - insert_at: rancher_audit_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.cattle-system.rancher-audit-log"
-          kubernetes.pod_namespace: "cattle-system"
-          kubernetes.container_name: "rancher-audit-log"
-          kubernetes.pod_node_name: "node-5"
-          message: '{"auditID":"abc-123","requestURI":"/v3/tokens","user":{"name":"u-alice","group":["admins"]},"method":"GET","remoteAddr":"10.42.0.9:1234","responseCode":200,"requestTimestamp":"2026-08-01T00:00:00Z"}'
-    outputs:
-      - extract_from: rancher_audit_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "cattle-system")
-              assert_eq!(.labels.app, "rancher")
-              assert_eq!(.labels.log_type, "audit")
-              assert_eq!(.message, "GET /v3/tokens 200")
-              assert_eq!(.fields.user, "u-alice")
-              assert_eq!(.fields.verb, "GET")
-              assert_eq!(.fields.uri, "/v3/tokens")
-              assert_eq!(.fields.status, "200")
-
-  # --- CNPG Postgres (ONE transform, all clusters) ---
-  - name: cnpg_routes_by_postgres_container
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.litellm.postgres"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.cnpg_pg
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  # mutual exclusivity: an app-namespace CNPG pod (authentik) is claimed by
-  # cnpg_pg, NOT the authentik app route (which now carves out .postgres).
-  - name: cnpg_authentik_postgres_routes_to_cnpg
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.authentik.postgres"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.cnpg_pg
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: cnpg_parse_extracts_record
-    inputs:
-      - insert_at: cnpg_pg_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.litellm.postgres"
-          kubernetes.pod_namespace: "litellm"
-          kubernetes.container_name: "postgres"
-          kubernetes.pod_node_name: "node-6"
-          kubernetes.pod_labels."cnpg.io/cluster": "litellm-postgres"
-          message: '{"level":"info","ts":"2026-08-01T00:00:00Z","logger":"postgres","msg":"record","record":{"user_name":"litellm","database_name":"litellm","error_severity":"LOG","message":"duration: 12.345 ms  statement: SELECT 1","query":""}}'
-    outputs:
-      - extract_from: cnpg_pg_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "litellm")
-              assert_eq!(.severity, "LOG")
-              assert_eq!(.labels.app, "cnpg")
-              assert_eq!(.labels.cluster, "litellm-postgres")
-              assert_eq!(.fields.error_severity, "LOG")
-              assert_eq!(.fields.duration_ms, "12.345")
-              assert_eq!(.fields.user, "litellm")
-              assert_eq!(.fields.database, "litellm")
-
-  # --- Gitea router/access (k8s + VM) ---
-  - name: gitea_routes_k8s_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.gitea.gitea"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.gitea
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: gitea_parse_router_line
-    inputs:
-      - insert_at: gitea_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.gitea.gitea"
-          kubernetes.pod_namespace: "gitea"
-          kubernetes.container_name: "gitea"
-          kubernetes.pod_node_name: "node-7"
-          message: '2026/08/01 00:00:00 .../router.go:100:func() [I] router: completed GET /user/login for 10.0.0.1:0, 200 OK in 12.3ms @ web/base.go:1'
-    outputs:
-      - extract_from: gitea_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "gitea")
-              assert_eq!(.labels.app, "gitea")
-              assert_eq!(.message, "GET /user/login 200")
-              assert_eq!(.fields.method, "GET")
-              assert_eq!(.fields.path, "/user/login")
-              assert_eq!(.fields.status, "200")
-              assert_eq!(.fields.latency, "12.3ms")
-  - name: gitea_parse_access_line
-    inputs:
-      - insert_at: gitea_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.gitea.gitea"
-          kubernetes.pod_namespace: "gitea"
-          kubernetes.container_name: "gitea"
-          message: '10.0.0.5 - alice [01/Aug/2026:00:00:00 +0000] "POST /repo/foo HTTP/1.1" 201 512 "-" "git/2.0"'
-    outputs:
-      - extract_from: gitea_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.fields.method, "POST")
-              assert_eq!(.fields.path, "/repo/foo")
-              assert_eq!(.fields.status, "201")
-              assert_eq!(.fields.user, "alice")
-              assert_eq!(.fields.client_ip, "10.0.0.5")
-
-  # --- PuppetServer / PuppetDB (k8s stdout) ---
-  - name: puppet_routes_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.puppet.puppetserver"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.puppet
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: puppet_parse_logback_line
-    inputs:
-      - insert_at: puppet_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.puppet.puppetserver"
-          kubernetes.pod_namespace: "puppet"
-          kubernetes.container_name: "puppetserver"
-          kubernetes.pod_node_name: "node-8"
-          message: '2026-08-01 00:00:00,123 INFO  [qtp123-45] [puppetserver] Compiled catalog for web01.unkin.net in environment production in 1.23 seconds'
-    outputs:
-      - extract_from: puppet_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "puppet")
-              assert_eq!(.severity, "INFO")
-              assert_eq!(.labels.app, "puppet")
-              assert_eq!(.fields.level, "INFO")
-              assert_eq!(.fields.logger, "puppetserver")
-              assert_eq!(.fields.node, "web01.unkin.net")
-
-  # --- LiteLLM request logs (k8s JSON) ---
-  - name: litellm_routes_by_subject
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.k8s.litellm.litellm"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.litellm
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: litellm_parse_extracts_request
-    inputs:
-      - insert_at: litellm_parse
-        type: log
-        log_fields:
-          subject: "logs.k8s.litellm.litellm"
-          kubernetes.pod_namespace: "litellm"
-          kubernetes.container_name: "litellm"
-          kubernetes.pod_node_name: "node-9"
-          message: '{"message":"Request completed","level":"info","model":"gpt-4o","total_tokens":1234,"response_time":0.532,"api_key":"sk-abc","status":"success","timestamp":"2026-08-01T00:00:00Z"}'
-    outputs:
-      - extract_from: litellm_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "k8s")
-              assert_eq!(.namespace, "litellm")
-              assert_eq!(.severity, "info")
-              assert_eq!(.message, "Request completed")
-              assert_eq!(.labels.app, "litellm")
-              assert_eq!(.fields.model, "gpt-4o")
-              assert_eq!(.fields.tokens, "1234")
-              assert_eq!(.fields.latency, "0.532")
-              assert_eq!(.fields.key, "sk-abc")
-              assert_eq!(.fields.status, "success")
-
-  # --- Postfix maillog (VM, per-line best-effort) ---
-  - name: postfix_routes_by_identifier
-    inputs:
-      - insert_at: app_route
-        type: log
-        log_fields:
-          subject: "logs.vm.mail1_syd1"
-          SYSLOG_IDENTIFIER: "postfix/qmgr"
-          message: "routed"
-    outputs:
-      - extract_from: app_route.postfix
-        conditions:
-          - type: vrl
-            source: 'assert_eq!(.message, "routed")'
-  - name: postfix_parse_extracts_line
-    inputs:
-      - insert_at: postfix_parse
-        type: log
-        log_fields:
-          subject: "logs.vm.mail1_syd1"
-          host: "mail1"
-          SYSLOG_IDENTIFIER: "postfix/smtp"
-          message: 'ABC123DEF: to=<rcpt@example.com>, relay=mx.example.com[1.2.3.4]:25, delay=1.2, delays=0.1/0/0.5/0.6, dsn=2.0.0, status=sent (250 OK)'
-    outputs:
-      - extract_from: postfix_parse
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.source, "vm")
-              assert_eq!(.host, "mail1")
-              assert_eq!(.labels.app, "postfix")
-              assert_eq!(.fields.qid, "ABC123DEF")
-              assert_eq!(.fields.to, "rcpt@example.com")
-              assert_eq!(.fields.relay, "mx.example.com[1.2.3.4]:25")
-              assert_eq!(.fields.delay, "1.2")
-              assert_eq!(.fields.status, "sent")
-              assert_eq!(.fields.program, "postfix/smtp")

apps/base/logging/vector/aggregator.yaml

@@ -1,900 +0,0 @@
----
-# Vector TRANSFORM tier (the "brain") — single source of truth, also validated
-# by `vector test` in CI. Consumes the whole log stream from JetStream via the
-# durable `transform` consumer (at-least-once; durable offsets tracked by
-# JetStream), routes by subject, normalises into the logs.raw columns, and is
-# the ONLY ClickHouse writer.
-#
-# Routing model (two stages):
-#   1. app_route — peels off Tier-1 per-app streams by subject / source tag and
-#      hands each to a dedicated parse transform that emits the full logs.raw
-#      shape plus structured .fields. Conditions are MUTUALLY EXCLUSIVE, so an
-#      event is claimed by at most one app (no double-insert).
-#   2. route (generic catch-all) — everything app_route did NOT claim
-#      (app_route._unmatched) is split k8s/vm and shaped generically. This is the
-#      fallback for all un-parsed traffic and MUST stay intact.
-# Add a new per-app pipeline by appending a mutually-exclusive route to
-# app_route, a parse transform, and its id to the clickhouse sink `inputs`.
-#
-# Structured fields go into the logs.raw `fields Map(String,String)` column — no
-# DDL change is needed (values are stringified; empties are compacted away).
-#
-# VM source-tag convention (the puppet-side vector rollout MUST follow it so
-# these transforms light up): file sources set `.file` (absolute log path);
-# journald sources set `.SYSLOG_IDENTIFIER` (falls back to `.program`/`.appname`).
-#
-# Durability model: JetStream (3d / 130 GiB, S2-compressed) is the SOLE
-# durability layer and the replay window. This
-# tier is stateless (no PVC, memory buffer). If ClickHouse is down the sink
-# blocks (when_full=block); back-pressure stops the source pulling, so unpulled
-# messages stay in JetStream and are redelivered. NB: Vector's NATS source has
-# no end-to-end acks (acks on receipt), so a pod killed mid-outage can lose the
-# in-memory buffer's worth of already-pulled events — accepted for a stateless,
-# autoscalable tier.
-data_dir: /vector-data-dir
-
-api:
-  enabled: true
-  address: 0.0.0.0:8686
-
-sources:
-  js_in:
-    type: nats
-    url: nats://nats.logging.svc.cluster.local:4222
-    connection_name: vector-transform
-    subject: "logs.>"
-    jetstream:
-      stream: LOGS
-      consumer: transform
-    auth:
-      strategy: user_password
-      user_password:
-        user: log-consumer
-        password: ${NATS_CONSUMER_PASSWORD}
-    decoding:
-      codec: json
-
-transforms:
-  # Stage 1: peel off Tier-1 per-app streams. Mutually exclusive conditions;
-  # anything unmatched falls through to the generic `route` below.
-  app_route:
-    type: route
-    inputs:
-      - js_in
-    route:
-      # k8s: authentik SSO — structlog JSON on stdout. The `.postgres` container
-      # is the authentik-namespace CNPG cluster; carve it out so it is claimed by
-      # the single `cnpg_pg` route below (keeps app_route mutually exclusive).
-      authentik: 'starts_with(to_string(.subject) ?? "", "logs.k8s.authentik.") && !ends_with(to_string(.subject) ?? "", ".postgres")'
-      # k8s: Traefik ingress — JSON access logs (requires logs.access.format=json,
-      # flipped in the traefik-system overlay values in this same change).
-      traefik: 'starts_with(to_string(.subject) ?? "", "logs.k8s.traefik-system.")'
-      # VM: Vault/OpenBao file audit device (/var/log/vault_audit.log), JSON.
-      vault: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && contains(to_string(.file) ?? "", "vault_audit")'
-      # VM: nginx combined access log (/var/log/nginx/<vhost>_access.log).
-      nginx_access: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && contains(to_string(.file) ?? "", "nginx") && ends_with(to_string(.file) ?? "", "access.log")'
-      # VM: nginx error log (/var/log/nginx/<vhost>_error.log).
-      nginx_error: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && contains(to_string(.file) ?? "", "nginx") && ends_with(to_string(.file) ?? "", "error.log")'
-      # VM: HAProxy httplog via journald.
-      haproxy: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && ((to_string(.SYSLOG_IDENTIFIER) ?? "") == "haproxy" || (to_string(.program) ?? "") == "haproxy" || (to_string(.appname) ?? "") == "haproxy")'
-      # VM: glauth LDAP — structuredlog (logrus) JSON.
-      glauth: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && (contains(to_string(.file) ?? "", "glauth") || (to_string(.SYSLOG_IDENTIFIER) ?? "") == "glauth" || (to_string(.program) ?? "") == "glauth" || (to_string(.appname) ?? "") == "glauth")'
-
-      # --- Tier-2 (stacks on #318) ---
-      # BIND query logs, k8s + VM. k8s: any bind-* namespace (bind-internal DNS
-      # servers, bind-system operator) — query logging enabled via `querylog yes`
-      # in the BindCluster extraOptions in this change. VM: puppet-managed named
-      # (file /var/log/named/*.log or journald `named`) — puppet-side enable is a
-      # required follow-up (profiles/dns/server.pp).
-      bind_query: 'starts_with(to_string(.subject) ?? "", "logs.k8s.bind") || (starts_with(to_string(.subject) ?? "", "logs.vm.") && (contains(to_string(.file) ?? "", "named") || (to_string(.SYSLOG_IDENTIFIER) ?? "") == "named" || (to_string(.program) ?? "") == "named" || (to_string(.appname) ?? "") == "named"))'
-      # k8s: Rancher audit log — JSON, emitted by the `rancher-audit-log` sidecar
-      # (auditLog.enabled level 1, already on in the cattle-system overlay).
-      rancher_audit: 'starts_with(to_string(.subject) ?? "", "logs.k8s.cattle-system.rancher-audit-log")'
-      # k8s: CNPG Postgres — ONE route for ALL clusters. The CNPG main container is
-      # always named `postgres`, so logs.k8s.<ns>.postgres uniquely identifies every
-      # cluster across all namespaces (authentik/litellm/artifactapi/woodpecker/
-      # puppet/paperclip/grafana/netbox/gitea/encapi). Mutually exclusive because the
-      # app routes above/below carve out `.postgres`.
-      cnpg_pg: 'starts_with(to_string(.subject) ?? "", "logs.k8s.") && ends_with(to_string(.subject) ?? "", ".postgres")'
-      # Gitea router/access logs. k8s: the new k8s gitea (ns gitea) with router +
-      # access logging enabled in the overlay values in this change — carve out
-      # `.postgres` (gitea-namespace CNPG). VM: puppet-managed gitea (file or
-      # journald `gitea`) — puppet-side log-format enable is a follow-up.
-      gitea: '(starts_with(to_string(.subject) ?? "", "logs.k8s.gitea.") && !ends_with(to_string(.subject) ?? "", ".postgres")) || (starts_with(to_string(.subject) ?? "", "logs.vm.") && (contains(to_string(.file) ?? "", "gitea") || (to_string(.SYSLOG_IDENTIFIER) ?? "") == "gitea" || (to_string(.program) ?? "") == "gitea" || (to_string(.appname) ?? "") == "gitea"))'
-      # PuppetServer / PuppetDB. k8s: openvoxserver/openvoxdb stdout (ns puppet) —
-      # carve out `.postgres` (puppet-namespace CNPG). VM file logs (multiline
-      # logback + puppetserver-access.log) are a puppet-side vector concern (the
-      # multiline join must happen at the edge) — follow-up.
-      puppet: 'starts_with(to_string(.subject) ?? "", "logs.k8s.puppet.") && !ends_with(to_string(.subject) ?? "", ".postgres")'
-      # k8s: LiteLLM request logs — JSON once JSON_LOGS=True (flipped in the litellm
-      # env in this change). Carve out `.postgres` (litellm-namespace CNPG).
-      litellm: 'starts_with(to_string(.subject) ?? "", "logs.k8s.litellm.") && !ends_with(to_string(.subject) ?? "", ".postgres")'
-      # VM: Postfix maillog — journald (SYSLOG_IDENTIFIER postfix/*) or file maillog.
-      postfix: 'starts_with(to_string(.subject) ?? "", "logs.vm.") && (starts_with(to_string(.SYSLOG_IDENTIFIER) ?? "", "postfix") || starts_with(to_string(.program) ?? "", "postfix") || starts_with(to_string(.appname) ?? "", "postfix") || contains(to_string(.file) ?? "", "maillog"))'
-
-  # Stage 2: generic catch-all for everything app_route did not claim.
-  route:
-    type: route
-    inputs:
-      - app_route._unmatched
-    route:
-      k8s: 'starts_with(to_string(.subject) ?? "", "logs.k8s.")'
-      vm: 'starts_with(to_string(.subject) ?? "", "logs.vm.")'
-
-  k8s_shape:
-    type: remap
-    inputs:
-      - route.k8s
-    source: |
-      ts = .timestamp || now()
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      ns = to_string(.kubernetes.pod_namespace || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      msg = to_string(.message || "") ?? ""
-      lbls = object(.kubernetes.pod_labels) ?? {}
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": ns,
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": "",
-        "message": msg,
-        "labels": lbls,
-        "fields": {}
-      }
-
-  vm_shape:
-    type: remap
-    inputs:
-      - route.vm
-    source: |
-      ts = .timestamp || .ts || now()
-      host = to_string(.host || .hostname || "") ?? ""
-      msg = to_string(.message || .msg || "") ?? ""
-      sev = to_string(.severity || .level || "") ?? ""
-      role = to_string(.role || "") ?? ""
-      lbls = {}
-      if role != "" {
-        lbls = {"role": role}
-      }
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "",
-        "severity": sev,
-        "message": msg,
-        "labels": lbls,
-        "fields": {}
-      }
-
-  # --- Tier-1 per-app parse transforms (each emits the full logs.raw shape) ---
-
-  # Authentik SSO (k8s, ns authentik) — structlog JSON on stdout.
-  # LIVE NOW: authentik pods already stream to logs.k8s.authentik.*.
-  authentik_parse:
-    type: remap
-    inputs:
-      - app_route.authentik
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.timestamp || .timestamp || now()
-      user = ""
-      if is_string(ev.user) {
-        user = to_string(ev.user) ?? ""
-      } else if is_object(ev.user) {
-        user = to_string(ev.user.username) ?? ""
-      }
-      fields = compact({
-        "event": to_string(ev.event) ?? "",
-        "action": to_string(ev.action) ?? "",
-        "user": user,
-        "client_ip": to_string(ev.client_ip) ?? "",
-        "result": to_string(ev.result) ?? "",
-        "logger": to_string(ev.logger) ?? ""
-      }, string: true)
-      sev = to_string(ev.level) ?? ""
-      msg = raw
-      if ev.event != null {
-        msg = to_string(ev.event) ?? raw
-      }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": "authentik",
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": sev,
-        "message": msg,
-        "labels": {"app": "authentik"},
-        "fields": fields
-      }
-
-  # Traefik ingress (k8s, ns traefik-system) — JSON access logs. Non-access
-  # traefik lines (app logs) simply parse to no access fields and keep .message.
-  # geoip on client_ip is a PREREQUISITE (no enrichment table yet — see PR note).
-  traefik_parse:
-    type: remap
-    inputs:
-      - app_route.traefik
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.StartUTC || ev.time || .timestamp || now()
-      status = ""
-      if ev.DownstreamStatus != null {
-        status = to_string(ev.DownstreamStatus) ?? ""
-      }
-      dur_ns = to_int(ev.Duration) ?? 0
-      dur_ms = ""
-      if dur_ns > 0 {
-        dur_ms = to_string(dur_ns / 1000000)
-      }
-      method = to_string(ev.RequestMethod) ?? ""
-      path = to_string(ev.RequestPath) ?? ""
-      fields = compact({
-        "route": to_string(ev.RouterName) ?? "",
-        "service": to_string(ev.ServiceName) ?? "",
-        "method": method,
-        "path": path,
-        "host": to_string(ev.RequestHost) ?? "",
-        "status": status,
-        "duration_ms": dur_ms,
-        "client_ip": to_string(ev.ClientHost) ?? "",
-        "protocol": to_string(ev.RequestProtocol) ?? ""
-      }, string: true)
-      msg = raw
-      if method != "" {
-        msg = method + " " + path + " " + status
-      }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": "traefik-system",
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": "",
-        "message": msg,
-        "labels": {"app": "traefik"},
-        "fields": fields
-      }
-
-  # Vault/OpenBao file audit device (VM, /var/log/vault_audit.log) — JSON, one
-  # object per request/response. AWAITING VM VECTOR (in-cluster vault is quiet;
-  # lights up when the puppet vector rollout ships logs.vm.* with .file set).
-  vault_parse:
-    type: remap
-    inputs:
-      - app_route.vault
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.time || .timestamp || .ts || now()
-      auth = object(ev.auth) ?? {}
-      req = object(ev.request) ?? {}
-      fields = compact({
-        "type": to_string(ev.type) ?? "",
-        "display_name": to_string(auth.display_name) ?? "",
-        "operation": to_string(req.operation) ?? "",
-        "path": to_string(req.path) ?? "",
-        "remote_address": to_string(req.remote_address) ?? "",
-        "error": to_string(ev.error) ?? ""
-      }, string: true)
-      op = to_string(req.operation) ?? ""
-      pth = to_string(req.path) ?? ""
-      msg = raw
-      if op != "" || pth != "" {
-        msg = op + " " + pth
-      }
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "",
-        "severity": "",
-        "message": msg,
-        "labels": {"app": "vault"},
-        "fields": fields
-      }
-
-  # nginx access log (VM) — combined/CLF + optional trailing request_time.
-  # AWAITING VM VECTOR. geoip on client_ip is a PREREQUISITE (see PR note).
-  nginx_access_parse:
-    type: remap
-    inputs:
-      - app_route.nginx_access
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      m = parse_regex(raw, r'^(?P<client_ip>\S+) \S+ (?P<user>\S+) \[(?P<time_local>[^\]]+)\] "(?P<method>\S+) (?P<path>\S+) (?P<protocol>[^"]*)" (?P<status>\d{3}) (?P<bytes>\d+|-) "(?P<referer>[^"]*)" "(?P<user_agent>[^"]*)"(?: (?P<request_time>[\d.]+))?') ?? {}
-      fields = compact({
-        "client_ip": to_string(m.client_ip),
-        "method": to_string(m.method),
-        "path": to_string(m.path),
-        "status": to_string(m.status),
-        "bytes": to_string(m.bytes),
-        "referer": to_string(m.referer),
-        "user_agent": to_string(m.user_agent),
-        "request_time": to_string(m.request_time)
-      }, string: true)
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "access",
-        "severity": "",
-        "message": raw,
-        "labels": {"app": "nginx", "log_type": "access"},
-        "fields": fields
-      }
-
-  # nginx error log (VM). AWAITING VM VECTOR.
-  nginx_error_parse:
-    type: remap
-    inputs:
-      - app_route.nginx_error
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      m = parse_regex(raw, r'^(?P<time_local>\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2}) \[(?P<level>\w+)\] (?P<pid>\d+)#(?P<tid>\d+): (?:\*(?P<cid>\d+) )?(?P<err>.*)$') ?? {}
-      c = parse_regex(raw, r'client: (?P<client_ip>[0-9a-fA-F:.]+)') ?? {}
-      lvl = to_string(m.level)
-      err = to_string(m.err)
-      fields = compact({
-        "level": lvl,
-        "pid": to_string(m.pid),
-        "cid": to_string(m.cid),
-        "client_ip": to_string(c.client_ip),
-        "error": err
-      }, string: true)
-      msg = raw
-      if err != "" {
-        msg = err
-      }
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "error",
-        "severity": lvl,
-        "message": msg,
-        "labels": {"app": "nginx", "log_type": "error"},
-        "fields": fields
-      }
-
-  # HAProxy httplog (VM, journald). AWAITING VM VECTOR.
-  # httplog: %ci:%cp [%tr] %ft %b/%s %Tq/%Tw/%Tc/%Tr/%Tt %ST %B %CC %CS %tsc
-  #          %ac/%fc/%bc/%sc/%rc %sq/%bq {hdrs} "%r"
-  haproxy_parse:
-    type: remap
-    inputs:
-      - app_route.haproxy
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      m = parse_regex(raw, r'(?P<client_ip>\d{1,3}(?:\.\d{1,3}){3}):(?P<client_port>\d+) \[(?P<accept_date>[^\]]+)\] (?P<frontend>\S+) (?P<backend>[^/ ]+)/(?P<server>\S+) (?P<tq>-?\d+)/(?P<tw>-?\d+)/(?P<tc>-?\d+)/(?P<tr>-?\d+)/(?P<tt>[+-]?\d+) (?P<status>\d{3}) (?P<bytes>\d+) \S+ \S+ (?P<termination_state>\S{4}) (?P<actconn>\d+)/(?P<feconn>\d+)/(?P<beconn>\d+)/(?P<srvconn>\d+)/(?P<retries>\d+) (?P<srv_queue>\d+)/(?P<backend_queue>\d+)') ?? {}
-      fields = compact({
-        "client_ip": to_string(m.client_ip),
-        "frontend": to_string(m.frontend),
-        "backend": to_string(m.backend),
-        "server": to_string(m.server),
-        "tq": to_string(m.tq),
-        "tw": to_string(m.tw),
-        "tc": to_string(m.tc),
-        "tr": to_string(m.tr),
-        "tt": to_string(m.tt),
-        "termination_state": to_string(m.termination_state),
-        "retries": to_string(m.retries),
-        "status": to_string(m.status),
-        "bytes": to_string(m.bytes)
-      }, string: true)
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "",
-        "severity": "",
-        "message": raw,
-        "labels": {"app": "haproxy"},
-        "fields": fields
-      }
-
-  # glauth LDAP (VM) — structuredlog (logrus) JSON. AWAITING VM VECTOR.
-  glauth_parse:
-    type: remap
-    inputs:
-      - app_route.glauth
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.time || .timestamp || .ts || now()
-      binddn = to_string(ev.bindDN) ?? ""
-      if binddn == "" {
-        binddn = to_string(ev.binddn) ?? ""
-      }
-      remote = to_string(ev.src) ?? ""
-      if remote == "" {
-        remote = to_string(ev.remoteAddr) ?? ""
-      }
-      lvl = to_string(ev.level) ?? ""
-      gmsg = to_string(ev.msg) ?? ""
-      success = "false"
-      if contains(downcase(gmsg), "success") || (lvl == "info" && contains(downcase(gmsg), "bind")) {
-        success = "true"
-      }
-      fields = compact({
-        "bindDN": binddn,
-        "remote": remote,
-        "success": success,
-        "level": lvl,
-        "msg": gmsg
-      }, string: true)
-      msg = gmsg
-      if msg == "" {
-        msg = raw
-      }
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "",
-        "severity": lvl,
-        "message": msg,
-        "labels": {"app": "glauth"},
-        "fields": fields
-      }
-
-  # --- Tier-2 per-app parse transforms (stacks on #318) ---
-
-  # BIND query logs (k8s bind-* namespaces + VM named). LIVE on k8s once the
-  # `querylog yes` extraOptions (this change) roll out; VM AWAITS the puppet-side
-  # enable (profiles/dns/server.pp). rcode is NOT present in standard query-log
-  # lines (that needs response logging / dnstap) — extracted only if a
-  # response-style `status:` line is seen. Non-query lines keep .message.
-  bind_query_parse:
-    type: remap
-    inputs:
-      - app_route.bind_query
-    source: |
-      subj = to_string(.subject) ?? ""
-      is_k8s = starts_with(subj, "logs.k8s.")
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      node = ""
-      ns = ""
-      pod = ""
-      container = ""
-      strm = ""
-      hostv = ""
-      src = "vm"
-      if is_k8s {
-        src = "k8s"
-        node = to_string(.kubernetes.pod_node_name || "") ?? ""
-        ns = to_string(.kubernetes.pod_namespace || "") ?? ""
-        pod = to_string(.kubernetes.pod_name || "") ?? ""
-        container = to_string(.kubernetes.container_name || "") ?? ""
-        strm = to_string(.stream || "") ?? ""
-        hostv = node
-      } else {
-        hostv = to_string(.host || .hostname || "") ?? ""
-      }
-      m = parse_regex(raw, r'client\s+(?:@\S+\s+)?(?P<client_ip>[0-9a-fA-F:.]+)#(?P<port>\d+)(?:\s+\([^)]*\))?:\s+(?:view\s+(?P<view>\S+):\s+)?query:\s+(?P<qname>\S+)\s+(?P<qclass>\S+)\s+(?P<qtype>\S+)(?:\s+(?P<flags>\S+))?') ?? {}
-      rc = parse_regex(raw, r'status:\s+(?P<rcode>\w+)') ?? {}
-      fields = compact({
-        "client_ip": to_string(m.client_ip),
-        "qname": to_string(m.qname),
-        "qtype": to_string(m.qtype),
-        "qclass": to_string(m.qclass),
-        "view": to_string(m.view),
-        "flags": to_string(m.flags),
-        "rcode": to_string(rc.rcode)
-      }, string: true)
-      qn = to_string(m.qname)
-      msg = raw
-      if qn != "" {
-        msg = "query " + qn + " " + to_string(m.qtype)
-      }
-      . = {
-        "timestamp": ts,
-        "host": hostv,
-        "source": src,
-        "namespace": ns,
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": "",
-        "message": msg,
-        "labels": {"app": "bind"},
-        "fields": fields
-      }
-
-  # Rancher audit log (k8s, cattle-system rancher-audit-log sidecar) — JSON,
-  # auditLog level 1 (already enabled in the overlay). LIVE NOW.
-  rancher_audit_parse:
-    type: remap
-    inputs:
-      - app_route.rancher_audit
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.requestTimestamp || ev.time || .timestamp || now()
-      user = ""
-      if is_object(ev.user) {
-        user = to_string(ev.user.name) ?? ""
-      } else if is_string(ev.user) {
-        user = to_string(ev.user) ?? ""
-      }
-      verb = to_string(ev.method) ?? ""
-      if verb == "" { verb = to_string(ev.verb) ?? "" }
-      uri = to_string(ev.requestURI) ?? ""
-      if uri == "" { uri = to_string(ev.uri) ?? "" }
-      status = ""
-      if ev.responseCode != null { status = to_string(ev.responseCode) ?? "" }
-      if status == "" && is_object(ev.responseStatus) { status = to_string(ev.responseStatus.code) ?? "" }
-      fields = compact({
-        "user": user,
-        "verb": verb,
-        "uri": uri,
-        "status": status,
-        "auditID": to_string(ev.auditID) ?? "",
-        "remote_addr": to_string(ev.remoteAddr) ?? ""
-      }, string: true)
-      msg = raw
-      if verb != "" || uri != "" {
-        msg = verb + " " + uri + " " + status
-      }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": "cattle-system",
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": "",
-        "message": msg,
-        "labels": {"app": "rancher", "log_type": "audit"},
-        "fields": fields
-      }
-
-  # CNPG Postgres — ONE transform for ALL clusters (10 namespaces). The instance
-  # manager wraps postgres logs as JSON on stdout; the postgres CSV columns nest
-  # under `.record` (logger == "postgres"). Non-postgres lines (instance-manager
-  # operator logs) keep .message and set no PG fields. LIVE NOW.
-  cnpg_pg_parse:
-    type: remap
-    inputs:
-      - app_route.cnpg_pg
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      ns = to_string(.kubernetes.pod_namespace || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      cluster = to_string(.kubernetes.pod_labels."cnpg.io/cluster" || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = .timestamp || now()
-      rec = object(ev.record) ?? {}
-      logger = to_string(ev.logger) ?? ""
-      sev = ""
-      pgmsg = ""
-      fields = {}
-      if logger == "postgres" {
-        sev = to_string(rec.error_severity) ?? ""
-        pgmsg = to_string(rec.message) ?? ""
-        dm = parse_regex(pgmsg, r'duration:\s+(?P<ms>[0-9.]+)\s+ms') ?? {}
-        fields = compact({
-          "error_severity": sev,
-          "message": pgmsg,
-          "query": to_string(rec.query) ?? "",
-          "duration_ms": to_string(dm.ms),
-          "user": to_string(rec.user_name) ?? "",
-          "database": to_string(rec.database_name) ?? ""
-        }, string: true)
-      }
-      lbls = {"app": "cnpg"}
-      if cluster != "" {
-        lbls = {"app": "cnpg", "cluster": cluster}
-      }
-      msg = raw
-      if pgmsg != "" { msg = pgmsg }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": ns,
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": sev,
-        "message": msg,
-        "labels": lbls,
-        "fields": fields
-      }
-
-  # Gitea router/access logs (k8s gitea + VM gitea). Router "completed" lines give
-  # method/path/status/latency; NCSA access lines give method/path/status/user.
-  # k8s LIVE once the overlay log config (this change) rolls out; VM AWAITS the
-  # puppet-side log-format enable.
-  gitea_parse:
-    type: remap
-    inputs:
-      - app_route.gitea
-    source: |
-      subj = to_string(.subject) ?? ""
-      is_k8s = starts_with(subj, "logs.k8s.")
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      node = ""
-      ns = ""
-      pod = ""
-      container = ""
-      strm = ""
-      hostv = ""
-      src = "vm"
-      if is_k8s {
-        src = "k8s"
-        node = to_string(.kubernetes.pod_node_name || "") ?? ""
-        ns = to_string(.kubernetes.pod_namespace || "") ?? ""
-        pod = to_string(.kubernetes.pod_name || "") ?? ""
-        container = to_string(.kubernetes.container_name || "") ?? ""
-        strm = to_string(.stream || "") ?? ""
-        hostv = node
-      } else {
-        hostv = to_string(.host || .hostname || "") ?? ""
-      }
-      r = parse_regex(raw, r'completed (?P<method>\S+) (?P<path>\S+) for (?P<client>\S+), (?P<status>\d{3}) [^ ]+ in (?P<latency>[0-9.]+\w+)') ?? {}
-      a = parse_regex(raw, r'^(?P<client_ip>\S+) \S+ (?P<user>\S+) \[[^\]]+\] "(?P<method>\S+) (?P<path>\S+) [^"]*" (?P<status>\d{3})') ?? {}
-      method = to_string(r.method)
-      if method == "" { method = to_string(a.method) }
-      path = to_string(r.path)
-      if path == "" { path = to_string(a.path) }
-      status = to_string(r.status)
-      if status == "" { status = to_string(a.status) }
-      user = to_string(a.user)
-      if user == "-" { user = "" }
-      fields = compact({
-        "method": method,
-        "path": path,
-        "status": status,
-        "latency": to_string(r.latency),
-        "user": user,
-        "client_ip": to_string(a.client_ip)
-      }, string: true)
-      msg = raw
-      if method != "" {
-        msg = method + " " + path + " " + status
-      }
-      . = {
-        "timestamp": ts,
-        "host": hostv,
-        "source": src,
-        "namespace": ns,
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": "",
-        "message": msg,
-        "labels": {"app": "gitea"},
-        "fields": fields
-      }
-
-  # PuppetServer / PuppetDB (k8s openvoxserver/openvoxdb stdout, ns puppet). Per
-  # line logback parse (level/logger/message + node) and an access-log line
-  # (method/status/node) where present. VM multiline stacktrace join +
-  # puppetserver-access.log are a puppet-side edge concern (follow-up). LIVE NOW.
-  puppet_parse:
-    type: remap
-    inputs:
-      - app_route.puppet
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      ts = .timestamp || now()
-      lb = parse_regex(raw, r'^(?P<ts>\d{4}-\d{2}-\d{2}[ T]\d{2}:\d{2}:\d{2}[,.]\d+)\s+(?P<level>[A-Z]+)\s+\[(?P<thread>[^\]]*)\]\s+\[(?P<logger>[^\]]*)\]\s+(?P<msg>.*)$') ?? {}
-      ac = parse_regex(raw, r'^(?P<client_ip>\S+) \S+ \S+ \[[^\]]+\] "(?P<method>\S+) (?P<path>\S+) [^"]*" (?P<status>\d{3})') ?? {}
-      nd = parse_regex(raw, r'(?:catalog for|for node)\s+(?P<node>[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+)') ?? {}
-      lvl = to_string(lb.level)
-      pmsg = to_string(lb.msg)
-      err = ""
-      if lvl == "ERROR" { err = pmsg }
-      fields = compact({
-        "level": lvl,
-        "logger": to_string(lb.logger),
-        "node": to_string(nd.node),
-        "method": to_string(ac.method),
-        "status": to_string(ac.status),
-        "path": to_string(ac.path),
-        "client_ip": to_string(ac.client_ip),
-        "error": err
-      }, string: true)
-      msg = raw
-      if pmsg != "" { msg = pmsg }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": "puppet",
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": lvl,
-        "message": msg,
-        "labels": {"app": "puppet"},
-        "fields": fields
-      }
-
-  # LiteLLM request logs (k8s) — JSON once JSON_LOGS=True (flipped in the litellm
-  # env this change). parse_json -> model/tokens/latency/key/status (best-effort
-  # against litellm's JSON schema); non-JSON lines keep .message. Field keys light
-  # up once the env flip rolls out.
-  litellm_parse:
-    type: remap
-    inputs:
-      - app_route.litellm
-    source: |
-      node = to_string(.kubernetes.pod_node_name || "") ?? ""
-      pod = to_string(.kubernetes.pod_name || "") ?? ""
-      container = to_string(.kubernetes.container_name || "") ?? ""
-      strm = to_string(.stream || "") ?? ""
-      raw = to_string(.message || "") ?? ""
-      ev = object(parse_json(raw) ?? {}) ?? {}
-      ts = ev.timestamp || .timestamp || now()
-      sev = to_string(ev.level) ?? ""
-      lmsg = to_string(ev.message) ?? ""
-      fields = compact({
-        "model": to_string(ev.model) ?? "",
-        "tokens": to_string(ev.total_tokens) ?? "",
-        "latency": to_string(ev.response_time) ?? "",
-        "key": to_string(ev.api_key) ?? "",
-        "status": to_string(ev.status) ?? "",
-        "user": to_string(ev.user) ?? ""
-      }, string: true)
-      msg = raw
-      if lmsg != "" { msg = lmsg }
-      . = {
-        "timestamp": ts,
-        "host": node,
-        "source": "k8s",
-        "namespace": "litellm",
-        "pod": pod,
-        "container": container,
-        "stream": strm,
-        "severity": sev,
-        "message": msg,
-        "labels": {"app": "litellm"},
-        "fields": fields
-      }
-
-  # Postfix maillog (VM) — best-effort PER-LINE parse (qid + from/to/status/relay/
-  # delay). Full qid-lifecycle correlation is a query-time GROUP BY qid in
-  # ClickHouse, NOT a stateless-aggregator job (stitching the multi-line lifecycle
-  # needs a stateful reduce). AWAITS VM VECTOR.
-  postfix_parse:
-    type: remap
-    inputs:
-      - app_route.postfix
-    source: |
-      host = to_string(.host || .hostname || "") ?? ""
-      raw = to_string(.message || .msg || "") ?? ""
-      ts = .timestamp || .ts || now()
-      prog = to_string(.SYSLOG_IDENTIFIER || .program || .appname || "") ?? ""
-      q = parse_regex(raw, r'^(?P<qid>[0-9A-F]{6,}):') ?? {}
-      frm = parse_regex(raw, r'from=<(?P<from>[^>]*)>') ?? {}
-      rcpt = parse_regex(raw, r'to=<(?P<to>[^>]*)>') ?? {}
-      st = parse_regex(raw, r'status=(?P<status>\w+)') ?? {}
-      rel = parse_regex(raw, r'relay=(?P<relay>[^,]+)') ?? {}
-      dly = parse_regex(raw, r'delay=(?P<delay>[0-9.]+)') ?? {}
-      fields = compact({
-        "qid": to_string(q.qid),
-        "from": to_string(frm.from),
-        "to": to_string(rcpt.to),
-        "status": to_string(st.status),
-        "relay": to_string(rel.relay),
-        "delay": to_string(dly.delay),
-        "program": prog
-      }, string: true)
-      . = {
-        "timestamp": ts,
-        "host": host,
-        "source": "vm",
-        "namespace": "",
-        "pod": "",
-        "container": "",
-        "stream": "",
-        "severity": "",
-        "message": raw,
-        "labels": {"app": "postfix"},
-        "fields": fields
-      }
-
-sinks:
-  clickhouse:
-    type: clickhouse
-    inputs:
-      - k8s_shape
-      - vm_shape
-      - authentik_parse
-      - traefik_parse
-      - vault_parse
-      - nginx_access_parse
-      - nginx_error_parse
-      - haproxy_parse
-      - glauth_parse
-      - bind_query_parse
-      - rancher_audit_parse
-      - cnpg_pg_parse
-      - gitea_parse
-      - puppet_parse
-      - litellm_parse
-      - postfix_parse
-    endpoint: http://clickhouse-logs.logging.svc.cluster.local:8123
-    database: logs
-    table: raw
-    skip_unknown_fields: true
-    date_time_best_effort: true
-    auth:
-      strategy: basic
-      user: "${CLICKHOUSE_USER}"
-      password: "${CLICKHOUSE_PASSWORD}"
-    batch:
-      max_events: 500000
-      max_bytes: 134217728
-      timeout_secs: 10
-    # Stateless: in-memory buffer, block on full so back-pressure reaches the
-    # JetStream pull source (which then stops acking). JetStream is durability.
-    buffer:
-      type: memory
-      max_events: 2000
-      when_full: block
-    healthcheck:
-      enabled: true

apps/base/logging/vector/vm-ingest-tests.yaml

@@ -1,29 +0,0 @@
----
-# `vector test` unit tests for the VM-ingest routing transform.
-tests:
-  - name: host_token_is_subject_safe
-    inputs:
-      - insert_at: tag
-        type: log
-        log_fields:
-          host: "db1.syd1.example.net"
-          message: "sshd accepted"
-    outputs:
-      - extract_from: tag
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.host_token, "db1_syd1_example_net")
-
-  - name: missing_host_defaults_to_unknown
-    inputs:
-      - insert_at: tag
-        type: log
-        log_fields:
-          message: "no host field"
-    outputs:
-      - extract_from: tag
-        conditions:
-          - type: vrl
-            source: |
-              assert_eq!(.host_token, "unknown")

apps/base/logging/vector/vm-ingest.yaml

@@ -1,50 +0,0 @@
----
-# Vector VM-INGEST tier — the VM front door. Thin: accepts NDJSON over HTTPS
-# (behind the logs-ingest Gateway) from puppet-managed VMs, attaches only a
-# routing token, and publishes into JetStream (subject logs.vm.<host>). No
-# parsing here — shaping happens in the transform tier after JetStream, so VM
-# logs get the same durability/replay/fan-out as k8s logs.
-data_dir: /vector-data-dir
-
-api:
-  enabled: true
-  address: 0.0.0.0:8686
-
-sources:
-  vm_http:
-    type: http_server
-    address: 0.0.0.0:8080
-    path: /
-    method: POST
-    decoding:
-      codec: json
-    framing:
-      method: newline_delimited
-
-transforms:
-  # Routing metadata only: derive a NATS-subject-safe host token.
-  tag:
-    type: remap
-    inputs:
-      - vm_http
-    source: |
-      host = to_string(.host || .hostname || "unknown") ?? "unknown"
-      .host_token = replace(host, r'[^a-zA-Z0-9_-]', "_")
-
-sinks:
-  to_jetstream:
-    type: nats
-    inputs:
-      - tag
-    url: nats://nats.logging.svc.cluster.local:4222
-    connection_name: vector-vm-ingest
-    subject: "logs.vm.{{ host_token }}"
-    jetstream:
-      enabled: true
-    auth:
-      strategy: user_password
-      user_password:
-        user: log-producer
-        password: ${NATS_PRODUCER_PASSWORD}
-    encoding:
-      codec: json

apps/base/logging/vlagent.yaml

@@ -0,0 +1,26 @@
+---
+apiVersion: operator.victoriametrics.com/v1
+kind: VLAgent
+metadata:
+  name: logs
+  namespace: logging
+spec:
+  componentVersion: v1.52.0
+  k8sCollector:
+    enabled: true
+  remoteWrite:
+    # vlagent appends ?version=v1 itself; the path must be the native endpoint
+    - url: http://vlinsert-logs.logging.svc.cluster.local:9481/insert/native
+  remoteWriteSettings:
+    # collector mode buffers to the node's /var/lib/vlagent-data, so cap it:
+    # a vlinsert outage must not fill the host disk (500MB chunks)
+    maxDiskUsagePerURL: 2GiB
+  tolerations:
+    - operator: Exists
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: "1"
+      memory: 1Gi

apps/base/logging/vlcluster.yaml

@@ -0,0 +1,47 @@
+---
+apiVersion: operator.victoriametrics.com/v1
+kind: VLCluster
+metadata:
+  name: logs
+  namespace: logging
+spec:
+  clusterVersion: v1.52.0
+  vlinsert:
+    replicaCount: 2
+    resources:
+      requests:
+        cpu: 500m
+        memory: 1Gi
+      limits:
+        cpu: "2"
+        memory: 4Gi
+  vlselect:
+    replicaCount: 2
+    resources:
+      requests:
+        cpu: 500m
+        memory: 1Gi
+      limits:
+        cpu: "2"
+        memory: 4Gi
+  vlstorage:
+    replicaCount: 3
+    retentionPeriod: 180d
+    # ~3 GiB/day measured; 220GiB/node cap keeps 180d time-based, not disk-bound
+    retentionMaxDiskSpaceUsageBytes: 220GiB
+    storage:
+      volumeClaimTemplate:
+        spec:
+          accessModes:
+            - ReadWriteOnce
+          storageClassName: cephrbd-fast-delete
+          resources:
+            requests:
+              storage: 250Gi
+    resources:
+      requests:
+        cpu: "1"
+        memory: 2Gi
+      limits:
+        cpu: "4"
+        memory: 8Gi

apps/base/logging/vlogs/gateway.yaml

@@ -0,0 +1,38 @@
+---
+# External (DMZ) front for the VictoriaLogs UI on vlogs.unkin.net via the
+# external Traefik (LB VIP 198.18.199.0). TLS terminates with the real Let's
+# Encrypt *.unkin.net wildcard (Certificate wildcard-unkin-net in cert-manager,
+# reflected into this namespace as wildcard-unkin-net-tls by the emberstack
+# reflector), so there is no cert-manager annotation here. The apex
+# vlogs.unkin.net A record lives in the bind-operator unkin.net zone, NOT
+# external-dns, so no external-dns annotation either. oauth2-proxy fronts it.
+apiVersion: gateway.networking.k8s.io/v1
+kind: Gateway
+metadata:
+  labels:
+    traefik.io/instance: external
+  name: vlogs-external
+  namespace: logging
+spec:
+  gatewayClassName: traefik-external
+  listeners:
+    - allowedRoutes:
+        namespaces:
+          from: Same
+      hostname: vlogs.unkin.net
+      name: http
+      port: 80
+      protocol: HTTP
+    - allowedRoutes:
+        namespaces:
+          from: Same
+      hostname: vlogs.unkin.net
+      name: https
+      port: 443
+      protocol: HTTPS
+      tls:
+        certificateRefs:
+          - group: ""
+            kind: Secret
+            name: wildcard-unkin-net-tls
+        mode: Terminate

apps/base/logging/vlogs/httproute.yaml

@@ -2,15 +2,15 @@
 apiVersion: gateway.networking.k8s.io/v1
 kind: HTTPRoute
 metadata:
-  name: logviewer-http-redirect
+  name: vlogs-http-redirect
   namespace: logging
 spec:
   hostnames:
-    - logviewer.unkin.net
+    - vlogs.unkin.net
   parentRefs:
     - group: gateway.networking.k8s.io
       kind: Gateway
-      name: logviewer
+      name: vlogs-external
       sectionName: http
   rules:
     - filters:
@@ -26,21 +26,33 @@ spec:
 apiVersion: gateway.networking.k8s.io/v1
 kind: HTTPRoute
 metadata:
-  name: logviewer
+  name: vlogs
   namespace: logging
 spec:
   hostnames:
-    - logviewer.unkin.net
+    - vlogs.unkin.net
   parentRefs:
     - group: gateway.networking.k8s.io
       kind: Gateway
-      name: logviewer
+      name: vlogs-external
       sectionName: https
   rules:
+    # Exact / outranks the PathPrefix catch-all; target needs the trailing slash
+    - filters:
+        - type: RequestRedirect
+          requestRedirect:
+            path:
+              type: ReplaceFullPath
+              replaceFullPath: /select/vmui/
+            statusCode: 302
+      matches:
+        - path:
+            type: Exact
+            value: /
     - backendRefs:
         - group: ""
           kind: Service
-          name: logviewer-oauth2
+          name: vlogs-oauth2
           port: 80
           weight: 1
       matches:

apps/base/logging/vlogs/kustomization.yaml

@@ -4,7 +4,6 @@ kind: Kustomization
 
 resources:
   - vaultstaticsecret.yaml
-  - deployment.yaml
   - oauth2-proxy-configmap.yaml
   - oauth2-proxy-deployment.yaml
   - service.yaml

apps/base/logging/vlogs/oauth2-proxy-configmap.yaml

@@ -1,31 +1,27 @@
 ---
-# Non-secret oauth2-proxy configuration (client_id/secret/cookie_secret come
-# from the logviewer-oauth-credentials Secret). Single auth front for the
-# logviewer UI: everything requires an Authentik session in akP-logviewer-admin.
 apiVersion: v1
 kind: ConfigMap
 metadata:
-  name: logviewer-oauth2-env
+  name: vlogs-oauth2-env
   namespace: logging
 data:
   OAUTH2_PROXY_HTTP_ADDRESS: "0.0.0.0:4180"
   OAUTH2_PROXY_PROVIDER: "oidc"
-  # Authentik logviewer app discovery issuer (terraform-authentik PR #21).
+  OAUTH2_PROXY_OIDC_ISSUER_URL: "https://identity.unkin.net/application/o/vlogs/"
-  OAUTH2_PROXY_OIDC_ISSUER_URL: "https://identity.unkin.net/application/o/logviewer/"
+  OAUTH2_PROXY_REDIRECT_URL: "https://vlogs.unkin.net/oauth2/callback"
-  OAUTH2_PROXY_REDIRECT_URL: "https://logviewer.unkin.net/oauth2/callback"
+  OAUTH2_PROXY_UPSTREAMS: "http://vlselect-logs.logging.svc.cluster.local:9471/"
-  OAUTH2_PROXY_UPSTREAMS: "http://logviewer.logging.svc.cluster.local:8080/"
   OAUTH2_PROXY_SCOPE: "openid email profile ak_groups"
   # Populate session.Groups from the Authentik ak_groups claim.
   OAUTH2_PROXY_OIDC_GROUPS_CLAIM: "ak_groups"
-  OAUTH2_PROXY_ALLOWED_GROUPS: "akP-logviewer-admin"
+  OAUTH2_PROXY_ALLOWED_GROUPS: "akP-vlogs-admin"
   OAUTH2_PROXY_PASS_USER_HEADERS: "true"
   OAUTH2_PROXY_EMAIL_DOMAINS: "*"
   # Authentik hardcodes email_verified=false in the id_token; authorization is
   # enforced via ak_groups, so accepting the unverified email is safe.
   OAUTH2_PROXY_INSECURE_OIDC_ALLOW_UNVERIFIED_EMAIL: "true"
   OAUTH2_PROXY_COOKIE_SECURE: "true"
-  OAUTH2_PROXY_COOKIE_DOMAINS: "logviewer.unkin.net"
+  OAUTH2_PROXY_COOKIE_DOMAINS: "vlogs.unkin.net"
-  OAUTH2_PROXY_WHITELIST_DOMAINS: "logviewer.unkin.net"
+  OAUTH2_PROXY_WHITELIST_DOMAINS: "vlogs.unkin.net"
   OAUTH2_PROXY_REVERSE_PROXY: "true"
   OAUTH2_PROXY_PROVIDER_CA_FILES: "/etc/ssl/combined/ca-certificates.crt"
   OAUTH2_PROXY_CODE_CHALLENGE_METHOD: "S256"

apps/base/logging/vlogs/oauth2-proxy-deployment.yaml

@@ -2,16 +2,16 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: logviewer-oauth2
+  name: vlogs-oauth2
   namespace: logging
   annotations:
     configmap.reloader.stakater.com/auto: "true"
-    secret.reloader.stakater.com/reload: "logviewer-oauth-credentials,vault-ca-cert"
+    secret.reloader.stakater.com/reload: "vlogs-oauth-credentials,vault-ca-cert"
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app: logviewer-oauth2
+      app: vlogs-oauth2
   strategy:
     rollingUpdate:
       maxUnavailable: 1
@@ -19,7 +19,7 @@ spec:
   template:
     metadata:
       labels:
-        app: logviewer-oauth2
+        app: vlogs-oauth2
     spec:
       serviceAccountName: default
       automountServiceAccountToken: false
@@ -69,23 +69,23 @@ spec:
               protocol: TCP
           envFrom:
             - configMapRef:
-                name: logviewer-oauth2-env
+                name: vlogs-oauth2-env
                 optional: false
           env:
             - name: OAUTH2_PROXY_CLIENT_ID
               valueFrom:
                 secretKeyRef:
-                  name: logviewer-oauth-credentials
+                  name: vlogs-oauth-credentials
                   key: client_id
             - name: OAUTH2_PROXY_CLIENT_SECRET
               valueFrom:
                 secretKeyRef:
-                  name: logviewer-oauth-credentials
+                  name: vlogs-oauth-credentials
                   key: client_secret
             - name: OAUTH2_PROXY_COOKIE_SECRET
               valueFrom:
                 secretKeyRef:
-                  name: logviewer-oauth-credentials
+                  name: vlogs-oauth-credentials
                   key: cookie_secret
           volumeMounts:
             - name: combined-certs

apps/base/logging/vlogs/service.yaml

@@ -0,0 +1,19 @@
+---
+# Front-door entry Service: the HTTPRoute for vlogs.unkin.net targets this, so
+# all traffic enters via oauth2-proxy.
+apiVersion: v1
+kind: Service
+metadata:
+  name: vlogs-oauth2
+  namespace: logging
+spec:
+  internalTrafficPolicy: Cluster
+  ports:
+    - name: http
+      port: 80
+      protocol: TCP
+      targetPort: http
+  selector:
+    app: vlogs-oauth2
+  sessionAffinity: None
+  type: ClusterIP

apps/base/logging/vlogs/vaultstaticsecret.yaml

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

apps/base/puppet/cronjob_g10k-code.yaml

@@ -11,11 +11,13 @@ metadata:
   namespace: puppet
 spec:
   schedule: "*/1 * * * *"
+  startingDeadlineSeconds: 200
   concurrencyPolicy: Forbid
   successfulJobsHistoryLimit: 3
   failedJobsHistoryLimit: 3
   jobTemplate:
     spec:
+      activeDeadlineSeconds: 300
       template:
         metadata:
           labels:

apps/base/woodpecker/gocache_bucket.yaml

@@ -0,0 +1,33 @@
+---
+# Shared Go build cache (GOCACHEPROG) for CI and developer laptops. Lives in the
+# woodpecker namespace because CI is the primary consumer and reads the Secret here.
+apiVersion: ceph.unkin.net/v1alpha1
+kind: ObjectStoreUser
+metadata:
+  name: gocache
+  namespace: woodpecker
+spec:
+  displayName: "Go build cache owner"
+  uid: gocache
+  maxBuckets: 1
+  secretName: gocache-s3
+  retainOnDelete: false
+---
+apiVersion: ceph.unkin.net/v1alpha1
+kind: Bucket
+metadata:
+  name: gocache
+  namespace: woodpecker
+spec:
+  bucketName: gocache
+  ownerRef: gocache
+  versioning: false
+  # No placementTarget: default (replicated) placement, not the ec target the
+  # backup buckets use — a build cache is millions of small objects.
+  tags:
+    app: gocache
+    purpose: go-build-cache
+  retainOnDelete: false
+  # A cache bucket is never empty, and the operator refuses to delete a
+  # non-empty bucket without this, wedging the finalizer.
+  purgeOnDelete: true

apps/base/woodpecker/kustomization.yaml

@@ -7,6 +7,7 @@ resources:
   - cnpg_cluster.yaml
   - cnpg_backup.yaml
   - cnpg_pooler.yaml
+  - gocache_bucket.yaml
   - serviceaccount_arrproxy_ci.yaml
   - serviceaccount_autobackup_operator_ci.yaml
   - serviceaccount_ghp.yaml

apps/overlays/au-syd1/clickhouse-system/kustomization.yaml

@@ -1,16 +0,0 @@
----
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-namespace: clickhouse-system
-
-resources:
-  - ../../../base/clickhouse-system
-
-helmCharts:
-  - name: altinity-clickhouse-operator
-    repo: https://helm.altinity.com
-    version: "0.27.2"
-    releaseName: clickhouse-operator
-    namespace: clickhouse-system
-    valuesFile: values.yaml

apps/overlays/au-syd1/clickhouse-system/values.yaml

@@ -1,45 +0,0 @@
-# Altinity ClickHouse operator. Cluster-scoped: watches ClickHouseInstallation
-# resources in all namespaces (the logs cluster lives in the `logging` namespace).
-# CRDs are installed at runtime by the chart's crdHook Job.
-#
-# Upstream official images; no Docker Hardened Image variant is adopted (DHI is
-# subscription-gated and served from a private org namespace not reachable via
-# the anonymous artifactapi dockerhub proxy).
-#
-# Watch the logging namespace where the ClickHouseInstallation lives. The chart
-# default (watchNamespaces: []) makes the operator watch ONLY its own namespace
-# (clickhouse-system), so the logs CHI was never reconciled — set it explicitly.
-watchNamespaces:
-  - logging
-crdHook:
-  image:
-    repository: docker.io/bitnami/kubectl
-  resources:
-    requests:
-      cpu: 50m
-      memory: 64Mi
-    limits:
-      cpu: 250m
-      memory: 128Mi
-
-operator:
-  image:
-    repository: docker.io/altinity/clickhouse-operator
-  resources:
-    requests:
-      cpu: 100m
-      memory: 256Mi
-    limits:
-      cpu: 500m
-      memory: 512Mi
-
-metrics:
-  image:
-    repository: docker.io/altinity/metrics-exporter
-  resources:
-    requests:
-      cpu: 50m
-      memory: 64Mi
-    limits:
-      cpu: 250m
-      memory: 256Mi

apps/overlays/au-syd1/haproxy/kustomization.yaml

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

apps/overlays/au-syd1/logging/kustomization.yaml

@@ -6,34 +6,3 @@ namespace: logging
 
 resources:
   - ../../../base/logging
-
-helmCharts:
-  # Dedicated JetStream NATS cluster — the durable log bus.
-  - name: nats
-    repo: https://nats-io.github.io/k8s/helm/charts
-    version: "2.14.2"
-    releaseName: nats
-    namespace: logging
-    valuesFile: values-nats.yaml
-  # Edge agent (DaemonSet): tails every pod's logs, publishes to JetStream.
-  - name: vector
-    repo: https://helm.vector.dev
-    version: "0.57.0"
-    releaseName: vector-agent
-    namespace: logging
-    valuesFile: values-vector-agent.yaml
-  # VM ingest (Deployment): HTTP NDJSON front door -> JetStream.
-  - name: vector
-    repo: https://helm.vector.dev
-    version: "0.57.0"
-    releaseName: vector-vm-ingest
-    namespace: logging
-    valuesFile: values-vector-vm-ingest.yaml
-  # Transform tier (StatefulSet): JetStream consumer -> shape -> ClickHouse.
-  - name: vector
-    repo: https://helm.vector.dev
-    version: "0.57.0"
-    releaseName: vector-aggregator
-    namespace: logging
-    valuesFile: values-vector-aggregator.yaml
-  # Archiver: replaced by the logarchiver Deployment (apps/base/logging).

apps/overlays/au-syd1/logging/values-nats.yaml

@@ -1,103 +0,0 @@
-# Dedicated JetStream-enabled NATS cluster for the log bus. Deliberately NOT
-# shared with app messaging (streamstack et al. run their own NATS in their own
-# repo) — a separate cluster isolates logging blast-radius from app messaging
-# and lets us size retention/storage purely for the log outage-buffer + replay
-# use-case.
-fullnameOverride: nats
-
-config:
-  cluster:
-    enabled: true
-    replicas: 3
-  jetstream:
-    enabled: true
-    fileStore:
-      pvc:
-        # Sized for 3d retention: ~100 GiB/3d compressed (see
-        # nats-stream-limits ConfigMap) + file-store WAL/index/overhead, kept
-        # safely above the 130 GiB max_bytes cap. 3 replicas => ~0.5 TiB total
-        # provisioned on cephrbd-fast-delete. NB: this is the honest number for
-        # the assumed ~1500 events/s; higher real volume needs a bigger PVC +
-        # max_bytes together, else discard=old truncates retention below 3d.
-        size: 180Gi
-        storageClassName: cephrbd-fast-delete
-  # Per-user auth with publish/subscribe separation. Passwords are injected as
-  # env vars from the Vault-synced nats-auth Secret. The `<< $VAR >>` wrapping is
-  # REQUIRED by this chart: it renders the value UNQUOTED in nats.conf so the
-  # NATS server expands the env var. A plain `$VAR` is JSON-quoted ("$VAR") and
-  # NATS then treats it as a literal string — which broke auth for every client.
-  merge:
-    authorization:
-      users:
-        # Bootstrap Job (stream/consumer management) — full JetStream API.
-        - user: log-admin
-          password: << $NATS_ADMIN_PASSWORD >>
-        # Edge publishers (k8s DaemonSet + VM ingest) — publish only.
-        - user: log-producer
-          password: << $NATS_PRODUCER_PASSWORD >>
-          permissions:
-            publish:
-              allow:
-                - "logs.>"
-            subscribe:
-              allow:
-                - "_INBOX.>"
-        # Consumers (transform tier + archiver) — pull + ack only, no publish
-        # to log subjects.
-        - user: log-consumer
-          password: << $NATS_CONSUMER_PASSWORD >>
-          permissions:
-            publish:
-              allow:
-                - "$JS.API.CONSUMER.>"
-                - "$JS.API.STREAM.INFO.>"
-                - "$JS.ACK.LOGS.>"
-            subscribe:
-              allow:
-                - "_INBOX.>"
-
-container:
-  # Upstream official nats; no DHI variant available.
-  image:
-    repository: docker.io/library/nats
-    tag: 2.14.2-alpine
-  env:
-    NATS_ADMIN_PASSWORD:
-      valueFrom:
-        secretKeyRef:
-          name: nats-auth
-          key: admin_password
-    NATS_PRODUCER_PASSWORD:
-      valueFrom:
-        secretKeyRef:
-          name: nats-auth
-          key: producer_password
-    NATS_CONSUMER_PASSWORD:
-      valueFrom:
-        secretKeyRef:
-          name: nats-auth
-          key: consumer_password
-  resources:
-    requests:
-      cpu: 250m
-      memory: 512Mi
-    limits:
-      cpu: "2"
-      memory: 4Gi
-
-# Roll the StatefulSet on config changes only; nats-auth is Vault-rotated (VSO)
-# so it is deliberately not watched here (no restart on routine key rotation).
-podTemplate:
-  merge:
-    metadata:
-      annotations:
-        configmap.reloader.stakater.com/auto: "true"
-
-# Config-reloader sidecar image.
-reloader:
-  image:
-    repository: docker.io/natsio/nats-server-config-reloader
-    tag: "0.23.0"
-
-natsBox:
-  enabled: false

apps/overlays/au-syd1/logging/values-vector-agent.yaml

@@ -1,53 +0,0 @@
-# Vector EDGE agent (DaemonSet) — thin publisher. Tails every node's pod logs
-# (incl. control-plane via the blanket toleration) and publishes them into
-# JetStream over the Vector NATS sink. No parsing; only a routing subject token
-# is attached. Shaping happens in the transform tier after JetStream.
-role: Agent
-fullnameOverride: vector-agent
-
-# distroless-libc (no DHI — subscription-gated/private-namespace, not reachable
-# via the anon proxy).
-image:
-  repository: docker.io/timberio/vector
-  tag: 0.57.0-distroless-libc
-
-rbac:
-  create: true
-serviceAccount:
-  create: true
-
-podLabels:
-  vector.dev/exclude: "true"
-
-tolerations:
-  - operator: Exists
-
-env:
-  # Vector 0.57 disables ${VAR} config interpolation by default; auth needs it.
-  - name: VECTOR_DANGEROUSLY_ALLOW_ENV_VAR_INTERPOLATION
-    value: "true"
-  - name: NATS_PRODUCER_PASSWORD
-    valueFrom:
-      secretKeyRef:
-        name: nats-auth
-        key: producer_password
-
-resources:
-  requests:
-    cpu: 100m
-    memory: 256Mi
-  limits:
-    cpu: "1"
-    memory: 1Gi
-
-service:
-  enabled: false
-
-# Pipeline is the single source of truth in apps/base/logging/vector/agent.yaml,
-# mounted via existingConfigMaps (avoids the chart's customConfig Helm-tpl pass).
-dataDir: /vector-data-dir
-existingConfigMaps:
-  - vector-agent-config
-
-workloadResourceAnnotations:
-  configmap.reloader.stakater.com/auto: "true"

apps/overlays/au-syd1/logging/values-vector-aggregator.yaml

@@ -1,84 +0,0 @@
-# Vector TRANSFORM tier (STATELESS Deployment) — the "brain": sole ClickHouse
-# writer, owns all transforms, holds the only ClickHouse + NATS-consumer creds.
-#
-# Stateless by design: a JetStream pull consumer with NO PVC and NO disk buffer.
-# JetStream is the sole durability layer. On a ClickHouse outage the clickhouse
-# sink blocks (buffer when_full=block), back-pressure stops the source pulling,
-# and unpulled messages stay in JetStream for redelivery. Because Vector's NATS
-# source does NOT support end-to-end acknowledgements (it acks on receipt, not
-# after the sink), the only at-risk window is the in-memory buffer's worth of
-# already-pulled events if a pod is killed mid-outage — the accepted trade for a
-# horizontally-autoscalable stateless tier. Multiple replicas share the one
-# durable consumer `transform` (JetStream pull consumers distribute work), so
-# HPA is safe.
-role: Stateless-Aggregator
-fullnameOverride: vector-aggregator
-
-image:
-  repository: docker.io/timberio/vector
-  tag: 0.57.0-distroless-libc
-
-# Horizontal autoscaling on CPU — safe with N replicas on one durable consumer.
-autoscaling:
-  enabled: true
-  minReplicas: 2
-  maxReplicas: 8
-  targetCPUUtilizationPercentage: 70
-
-workloadResourceAnnotations:
-  configmap.reloader.stakater.com/auto: "true"
-
-podLabels:
-  vector.dev/exclude: "true"
-
-# Pipeline is the single source of truth in apps/base/logging/vector/
-# aggregator.yaml (unit-tested by `vector test` in CI), mounted via
-# existingConfigMaps. No persistence — stateless.
-dataDir: /vector-data-dir
-existingConfigMaps:
-  - vector-aggregator-config
-
-# The ONLY place ClickHouse + NATS-consumer creds are consumed.
-env:
-  # Vector 0.57 disables ${VAR} config interpolation by default; the pipeline's
-  # auth (${CLICKHOUSE_*}, ${NATS_CONSUMER_PASSWORD}) needs it enabled.
-  - name: VECTOR_DANGEROUSLY_ALLOW_ENV_VAR_INTERPOLATION
-    value: "true"
-  - name: CLICKHOUSE_USER
-    valueFrom:
-      secretKeyRef:
-        name: clickhouse-credentials
-        key: username
-  - name: CLICKHOUSE_PASSWORD
-    valueFrom:
-      secretKeyRef:
-        name: clickhouse-credentials
-        key: password
-  - name: NATS_CONSUMER_PASSWORD
-    valueFrom:
-      secretKeyRef:
-        name: nats-auth
-        key: consumer_password
-
-# Pure consumer: expose only the Vector API for debugging.
-containerPorts:
-  - name: api
-    containerPort: 8686
-    protocol: TCP
-
-service:
-  enabled: true
-  type: ClusterIP
-  ports:
-    - name: api
-      port: 8686
-      targetPort: 8686
-      protocol: TCP
-
-resources:
-  requests:
-    cpu: 250m
-    memory: 512Mi
-  limits:
-    cpu: "2"
-    memory: 2Gi

apps/overlays/au-syd1/logging/values-vector-vm-ingest.yaml

@@ -1,59 +0,0 @@
-# Vector VM-INGEST tier (Deployment) — VM front door. HTTP NDJSON in (behind the
-# logs-ingest Gateway), publishes into JetStream. Stateless publisher.
-# Pipeline: apps/base/logging/vector/vm-ingest.yaml (unit-tested in CI).
-role: Stateless-Aggregator
-fullnameOverride: vector-vm-ingest
-replicas: 2
-
-image:
-  repository: docker.io/timberio/vector
-  tag: 0.57.0-distroless-libc
-
-workloadResourceAnnotations:
-  configmap.reloader.stakater.com/auto: "true"
-
-podLabels:
-  vector.dev/exclude: "true"
-
-dataDir: /vector-data-dir
-existingConfigMaps:
-  - vector-vm-ingest-config
-
-env:
-  # Vector 0.57 disables ${VAR} config interpolation by default; auth needs it.
-  - name: VECTOR_DANGEROUSLY_ALLOW_ENV_VAR_INTERPOLATION
-    value: "true"
-  - name: NATS_PRODUCER_PASSWORD
-    valueFrom:
-      secretKeyRef:
-        name: nats-auth
-        key: producer_password
-
-containerPorts:
-  - name: http-ingest
-    containerPort: 8080
-    protocol: TCP
-  - name: api
-    containerPort: 8686
-    protocol: TCP
-
-service:
-  enabled: true
-  type: ClusterIP
-  ports:
-    - name: http-ingest
-      port: 8080
-      targetPort: 8080
-      protocol: TCP
-    - name: api
-      port: 8686
-      targetPort: 8686
-      protocol: TCP
-
-resources:
-  requests:
-    cpu: 100m
-    memory: 256Mi
-  limits:
-    cpu: "1"
-    memory: 1Gi

apps/overlays/au-syd1/vm-system/kustomization.yaml

@@ -10,7 +10,7 @@ resources:
 helmCharts:
   - name: victoria-metrics-operator
     repo: https://victoriametrics.github.io/helm-charts/
-    version: "0.57.1"
+    version: "0.67.3"
     releaseName: victoria-metrics-operator
     namespace: vm-system
     valuesFile: values.yaml

argocd/applicationsets/logging.yaml

@@ -10,7 +10,6 @@ spec:
         repoURL: https://git.unkin.net/unkin/argocd-apps
         revision: HEAD
         directories:
-          - path: apps/overlays/*/clickhouse-system
           - path: apps/overlays/*/logging
   template:
     metadata:

argocd/applicationsets/platform.yaml

@@ -29,6 +29,7 @@ spec:
       - path: apps/overlays/*/ghp
       - path: apps/overlays/*/gitea
       - path: apps/overlays/*/grafana-system
+      - path: apps/overlays/*/haproxy
       - path: apps/overlays/*/inteldeviceplugins-system
       - path: apps/overlays/*/jfrog
       - path: apps/overlays/*/k8up-system

argocd/projects/platform.yaml

@@ -43,6 +43,8 @@ spec:
       server: https://kubernetes.default.svc
     - namespace: 'gitea'
       server: https://kubernetes.default.svc
+    - namespace: 'haproxy'
+      server: https://kubernetes.default.svc
     - namespace: 'jfrog'
       server: https://kubernetes.default.svc
     - namespace: 'kanidm'

ci/kube-version

@@ -1 +0,0 @@
-1.33.13

ci/validate-apps.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-KUBE_VERSION="$(cat ci/kube-version)"
+KUBE_VERSION="1.33.7"
 
 SCHEMA_DIR="${SCHEMA_DIR:-schemas}"
 
@@ -15,7 +15,7 @@ while IFS= read -r -d "" k; do
   dir="$(dirname "$k")"
   echo "==> kubeconform: $dir" >&2
 
-  kustomize build --enable-helm --helm-kube-version "$KUBE_VERSION" "$dir" \
+  kustomize build --enable-helm "$dir" \
     | kubeconform \
         -kubernetes-version "$KUBE_VERSION" \
         -summary \

ci/validate-clusters.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-KUBE_VERSION="$(cat ci/kube-version)"
+KUBE_VERSION="1.33.7"
 
 SCHEMA_DIR="${SCHEMA_DIR:-schemas}"
 
@@ -15,7 +15,7 @@ while IFS= read -r -d "" k; do
   dir="$(dirname "$k")"
   echo "==> kubeconform: $dir" >&2
 
-  kustomize build --enable-helm --helm-kube-version "$KUBE_VERSION" "$dir" \
+  kustomize build --enable-helm "$dir" \
     | kubeconform \
         -kubernetes-version "$KUBE_VERSION" \
         -summary \

migration.md

@@ -49,8 +49,8 @@
 - Use existing patterns like `apps/overlays/*/csi-*` or `apps/overlays/*/<app-name>`
 
 ### 9. Validation
-- Run `kustomize build --enable-helm --helm-kube-version "$(cat ci/kube-version)" apps/overlays/au-syd1/<app-name>` to generate all resources
+- Run `kustomize build --enable-helm apps/overlays/au-syd1/<app-name>` to generate all resources
-- Check resource types: `kustomize build --enable-helm --helm-kube-version "$(cat ci/kube-version)" apps/overlays/au-syd1/<app-name> | grep "^kind:" | sort | uniq -c`
+- Check resource types: `kustomize build --enable-helm apps/overlays/au-syd1/<app-name> | grep "^kind:" | sort | uniq -c`
 - Verify all resource types are permitted in the target project's `clusterResourceWhitelist` and `namespaceResourceWhitelist`
 - Run `make kubeconform` to validate all resources
 - Fix any validation errors