correction: credential-forward + unified graph; activate SOPS (author-first)

Operator directive: don't diverge architecture to avoid asking for credentials;
provision them upfront via SOPS and keep the existing (unified) graph.

Roadmap reconciliation: Phase 2 = Network/Storage/TLS/DNS/Ingress, so
cert-manager/externaldns/gateway (the credential-gated pieces) ARE Phase 2;
monitoring is Phase 4. Earlier A2/rollout scope was inverted by credential-avoidance.

Reverts (credential-driven): remove clusters/dev/rollout/ + the $patch:delete's;
restore unified base graph (dev = ../base + cluster-vars + SOPS decryption,
R-ENV-02 intact); restore monitoring files (Phase 4). Kept non-credential
improvements: tofu for_each/rejoin, Kyverno parametrization + webhook excludes.

platform/kustomization.yaml now phased (single shared list): Phase-2 set =
kyverno, cilium, longhorn, cert-manager, externaldns, gateway; later components
commented with phase markers.

SOPS activated: .sops.yaml at repo root; bootstrap/sops/secret-templates/*.yaml.example
for all secrets (cloudflare x2, grafana, alertmanager-smtp, keycloak, oauth2-proxy, pia);
bootstrap/sops/CREDENTIALS.md checklist; pre-wired commented cloudflare-api-token lines
in cert-manager + externaldns; filled non-secret ACME email. Agents never touch real
secret values (operator encrypts).

Validated: kubectl kustomize dev(unified)/prod/platform(Phase-2 only), templates inert,
make -C ci gate PASS.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

platform/monitoring/kube-prometheus-stack.yaml

@@ -62,7 +62,7 @@ spec:
         storageSpec:
           volumeClaimTemplate:
             spec:
-              storageClassName: ${MONITORING_STORAGE_CLASS}   # replicated tier (ADR-0003); cluster-vars knob
+              storageClassName: longhorn                  # replicated tier (ADR-0003)
               accessModes: ["ReadWriteOnce"]
               resources:
                 requests:
@@ -80,24 +80,22 @@ spec:
             memory: 32Mi
           limits:
             memory: 96Mi
-        # SMTP is an OPERATOR HAND-OFF DEFERRED to Phase 4 — no creds yet, and the by-name
-        # `alertmanager-smtp` Secret does NOT exist. Mounting a missing Secret wedges Alertmanager
-        # in ContainerCreating, so the mount is DISABLED until the hand-off. Re-enable verbatim
-        # (uncomment) when the SOPS `alertmanager-smtp` Secret is delivered. TODO(Phase-4 SMTP).
-        # secrets:
-        #   - alertmanager-smtp
-      # Routing stays live; RECEIVERS ARE NULL until the SMTP hand-off (alerts still fire, route,
-      # and show in the Alertmanager UI + Grafana — they just aren't emailed). The smtp_* globals
-      # and email_configs are retained below, commented, so re-enabling is a pure uncomment.
+        # SMTP credentials are an OPERATOR HAND-OFF: a SOPS-encrypted Secret, referenced BY NAME
+        # only (docs/07). Mounted at /etc/alertmanager/secrets/<name>/ so the config below can read
+        # the password from a file (never inline plaintext).
+        secrets:
+          - alertmanager-smtp
+      # Routing/receivers. Non-secret SMTP endpoint fields (smarthost/from/to/username) are
+      # operator-supplied placeholders (REPLACE-ME, same convention as velero); the PASSWORD is
+      # read from the mounted SOPS secret via *_file. Both severities email; subject/route differ.
       config:
         global:
           resolve_timeout: 5m
-          # TODO(Phase-4 SMTP hand-off): uncomment together with the alertmanager-smtp Secret mount.
-          # smtp_smarthost: "smtp.example.com:587"
-          # smtp_from: "[email protected]"
-          # smtp_auth_username: "<smtp-login>"
-          # smtp_auth_password_file: /etc/alertmanager/secrets/alertmanager-smtp/smtp-password
-          # smtp_require_tls: true
+          smtp_smarthost: "REPLACE-ME:587"          # operator hand-off (e.g. smtp.gmail.com:587)
+          smtp_from: "REPLACE-ME"                    # operator hand-off (From: address)
+          smtp_auth_username: "REPLACE-ME"           # operator hand-off (SMTP login)
+          smtp_auth_password_file: /etc/alertmanager/secrets/alertmanager-smtp/smtp-password
+          smtp_require_tls: true
         route:
           group_by: ["alertname", "namespace"]
           group_wait: 30s
@@ -111,29 +109,25 @@ spec:
               group_wait: 10s
               repeat_interval: 1h
         receivers:
-          # NULL receivers until Phase-4 SMTP. email_configs retained (commented) for verbatim re-enable.
           - name: email-warning
-            # email_configs:
-            #   - to: "<alert-inbox>"
-            #     send_resolved: true
-            #     headers:
-            #       subject: '[WARNING] {{ .CommonLabels.alertname }} ({{ .CommonLabels.namespace }})'
+            email_configs:
+              - to: "REPLACE-ME"                     # operator hand-off (alert inbox)
+                send_resolved: true
+                headers:
+                  subject: '[WARNING] {{ .CommonLabels.alertname }} ({{ .CommonLabels.namespace }})'
           - name: email-critical
-            # email_configs:
-            #   - to: "<alert-inbox>"
-            #     send_resolved: true
-            #     headers:
-            #       subject: '[CRITICAL] {{ .CommonLabels.alertname }} ({{ .CommonLabels.namespace }})'
+            email_configs:
+              - to: "REPLACE-ME"                     # operator hand-off (alert inbox)
+                send_resolved: true
+                headers:
+                  subject: '[CRITICAL] {{ .CommonLabels.alertname }} ({{ .CommonLabels.namespace }})'
 
     # --- Grafana: dashboards (R-OBS-03), surfaced in the C2 UI (docs/12) behind Keycloak SSO ---
     grafana:
       enabled: true
       # Admin bootstrap + (later) OIDC client are SOPS secrets referenced BY NAME (WS-SEC/ADR-0014).
-      # cluster-vars knob: prod = the SOPS `grafana-admin-credentials` Secret; dev = "" (empty),
-      # which makes the chart fall back to its default admin password (dev-only, NAT-isolated) so
-      # Grafana starts without an operator secret. TODO: supply a dev Secret if wider dev access.
       admin:
-        existingSecret: ${GRAFANA_ADMIN_SECRET}
+        existingSecret: grafana-admin-credentials
         userKey: admin-user
         passwordKey: admin-password
       # DEV TRIM: emptyDir (default). Dashboards are provisioned from ConfigMaps (sidecar), so no

platform/monitoring/loki.yaml

@@ -60,7 +60,7 @@ spec:
       replicas: 1
       persistence:
         enabled: true
-        storageClass: ${MONITORING_STORAGE_CLASS}   # replicated tier (ADR-0003); cluster-vars knob
+        storageClass: longhorn          # replicated tier (ADR-0003)
         size: ${MONITORING_LOKI_PVC_SIZE}   # overlay knob (dev 5Gi / prod large)
       resources:
         requests: