monitoring: mirror Sprint 60 probe coverage

Sprint 58 Cx-12. Rebased over OIDC GitOps main; YAML parse and focused bluejay-infra lint tests passed.

apps/fc-distribution/fc-distribution.yaml

@@ -109,6 +109,7 @@ spec:
         prometheus.io/scrape: "true"
         prometheus.io/port: "8080"
         prometheus.io/path: "/metrics"
+        flowercore.io/healthz-auth-policy: "allow-anonymous"
     spec:
       # Synology NFS export `/volume1/kubernetes` ACL only allows rke2-server
       # (10.0.56.11) right now. Until the ACL is widened in DSM (admin only),
@@ -126,7 +127,7 @@ spec:
           #   dotnet.exe publish -c Release -o deploy/app \
           #     src/FlowerCore.Distribution.Web/FlowerCore.Distribution.Web.csproj
           #   podman build -t localhost/fc-distribution:v<tag> -f deploy/Dockerfile.deploy deploy
-          image: localhost/fc-distribution:v202605061948
+          image: localhost/fc-distribution:v20260604-oidc-root-anon
           imagePullPolicy: Never
           ports:
             - containerPort: 8080

apps/fc-dns/fc-dns.yaml

@@ -101,6 +101,7 @@ spec:
         prometheus.io/scrape: "true"
         prometheus.io/port: "5320"
         prometheus.io/path: "/metrics/prometheus"
+        flowercore.io/healthz-auth-policy: "allow-anonymous"
     spec:
       serviceAccountName: dns-web
       securityContext:

apps/fc-media/fc-media.yaml

@@ -131,6 +131,7 @@ spec:
         prometheus.io/scrape: "true"
         prometheus.io/port: "5200"
         prometheus.io/path: "/metrics"
+        flowercore.io/healthz-auth-policy: "allow-anonymous"
     spec:
       nodeSelector:
         kubernetes.io/hostname: rke2-server

apps/knowledge/knowledge.yaml

@@ -93,6 +93,7 @@ spec:
         prometheus.io/scrape: "true"
         prometheus.io/port: "8080"
         prometheus.io/path: "/metrics"
+        flowercore.io/healthz-auth-policy: "allow-anonymous"
     spec:
       securityContext:
         runAsNonRoot: true
@@ -123,9 +124,9 @@ spec:
               value: "Production"
             - name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
               value: "false"
-            # AuthentiK/OIDC is wired but not enforced until the
+            # AuthentiK/OIDC is enforced. /healthz stays anonymous by contract;
-            # knowledge-oidc-client Secret is provisioned and
+            # see flowercore.io/healthz-auth-policy above and the Sprint 58
-            # FlowerCore__Auth__Enabled is flipped to true.
+            # OIDC readiness probe audit.
             - name: FlowerCore__Auth__Enabled
               value: "true"
             - name: FlowerCore__Auth__Oidc__Enabled

apps/monitoring/noc-monitoring.yaml

@@ -216,19 +216,24 @@ data:
       - job_name: "pimanager-app"
         scrape_interval: 15s
         metrics_path: /metrics
+        scheme: https
+        tls_config:
+          insecure_skip_verify: true
         static_configs:
-          - targets: ["10.0.58.25:5000"]
+          - targets: ["piez.iamworkin.lan"]
             labels:
               instance: "piez"
-              service: "pimanager"
+              service: "signalcontrol"
               vlan: "home"
               device: "pi4-ezconnect"
-          - targets: ["10.0.58.113:5200"]
+              rig: "signal-b"
+          - targets: ["pirelay.iamworkin.lan"]
             labels:
               instance: "pirelay"
-              service: "pimanager"
+              service: "signalcontrol"
               vlan: "home"
               device: "pi3-ks0212"
+              rig: "signal-a"
 
       # Epson ET-3750 EcoTank Printer SNMP
       - job_name: "snmp-printer"
@@ -481,22 +486,31 @@ data:
               - "https://intranet.iamworkin.lan/"
               - "https://signage.iamworkin.lan/healthz"   # root 401 auth-gated 2026-06-01; /healthz anon 200
               - "https://kiosk.iamworkin.lan/"
-              - "https://media.iamworkin.lan/healthz"   # root auth-gated by OIDC; /healthz anon 200
+              - "https://media.iamworkin.lan/healthz"    # root auth-gated by OIDC; /healthz anonymous 200
               - "https://mysql.iamworkin.lan/healthz"   # root 401 auth-gated 2026-06-01; /healthz anon 200
               - "https://php.iamworkin.lan/healthz"     # root 401 auth-gated 2026-06-01; /healthz anon 200
               - "https://zabbix.iamworkin.lan/"
               - "https://desktop.iamworkin.lan/"
-              - "https://print.iamworkin.lan/"
+              - "https://print.iamworkin.lan/healthz"    # root 401 behind API key auth; /healthz anonymous 200
-              - "https://dns.iamworkin.lan/healthz"     # root auth-gated by OIDC; /healthz anon 200
+              - "https://dns.iamworkin.lan/healthz"      # root auth-gated by OIDC; /healthz anonymous 200
-              - "https://chat.iamworkin.lan/"
+              - "https://signalcontrol.iamworkin.lan/health" # FlowerCore.SignalControl Pi control plane
-              - "https://dist.iamworkin.lan/healthz"    # root/admin auth-gated by OIDC; /healthz anon 200
+              - "https://flowercore.iamworkin.lan/healthz"    # FlowerCore landing
-              - "https://dms.iamworkin.lan/"
+              - "https://replay.iamworkin.lan/healthz"        # FlowerCore.Signage replay surface
+              - "https://worldbuilder.iamworkin.lan/healthz"  # FlowerCore.WorldBuilder
+              - "https://updates.iamworkin.lan/api/v1/manifests/_schema" # UpdateCenter plural LAN alias
+              - "https://updatecenter-internal.iamworkin.lan/api/v1/manifests/_schema" # internal UC schema route
+              - "https://chat.iamworkin.lan/healthz"     # OIDC staged; keep blackbox off root before enforcement flips
+              - "https://dist.iamworkin.lan/healthz"     # root/admin auth-gated by OIDC; /healthz anonymous 200
+              - "https://dms.iamworkin.lan/healthz"      # future OIDC posture; health route is already anonymous/live
               - "https://menuboard.iamworkin.lan/"
               - "https://messageboard.iamworkin.lan/"
               - "https://presentations.iamworkin.lan/"
               - "https://retail.iamworkin.lan/"
               - "https://ttsreader.iamworkin.lan/"
               # Explicit healthcheck paths
+              - "https://library.iamworkin.lan/health"
+              - "https://aistation.iamworkin.lan/healthz"
+              - "https://knowledge.iamworkin.lan/healthz"
               - "https://fc-llm-bridge.iamworkin.lan/healthz"
               - "https://acme.iamworkin.lan/health"
               # NOTE: services intentionally NOT in this probe surface
@@ -908,12 +922,13 @@ data:
           # of idle and SNMP times out, so 5m for: would page nightly. A
           # genuine printer outage (jam, disconnected) lasts well over 30m.
           - alert: EpsonPrinterDown
-            expr: up{job="snmp-printer"} == 0
+            expr: (max_over_time(up{job="snmp-printer"}[35m]) == bool 0) == 1 and (hour() >= 13 or hour() < 1)
             for: 30m
             labels:
-              severity: warning
+              severity: info
+              alert_channel: irc
             annotations:
-              summary: "Epson ET-3750 SNMP unreachable for >30m (likely actual fault, not sleep)"
+              summary: "Epson ET-3750 SNMP unreachable during waking hours (30m)"
 
           - alert: SynologyDiskLow
             expr: hrStorageUsed{job="snmp-nas"} / hrStorageSize{job="snmp-nas"} * 100 > 85
@@ -1020,7 +1035,12 @@ data:
       - name: kubernetes-state
         rules:
           - alert: KubeContainerRestartingFrequently
-            expr: increase(kube_pod_container_status_restarts_total[1h]) > 5
+            # Exclude github-runner: ephemeral runners register, run one job,
+            # exit cleanly, and restart by design. Also require kube_pod_info so
+            # deleted rollout pods do not keep firing from retained restart series.
+            expr: |
+              increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[1h]) > 5
+              and on(namespace, pod) kube_pod_info
             for: 15m
             labels:
               severity: warning
@@ -1029,7 +1049,12 @@ data:
               description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has restarted {{ $value | printf \"%.0f\" }} times in the last hour. Check 'kubectl describe pod' + last-state termination reason."
 
           - alert: KubeContainerCrashLooping
-            expr: increase(kube_pod_container_status_restarts_total[15m]) > 3
+            # Same github-runner/delete-retention exclusions as the hourly
+            # restart rule above; real runner failures are covered by the
+            # dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts.
+            expr: |
+              increase(kube_pod_container_status_restarts_total{namespace!="github-runner"}[15m]) > 3
+              and on(namespace, pod) kube_pod_info
             for: 5m
             labels:
               severity: critical
@@ -1057,7 +1082,10 @@ data:
               description: "Pod can't pull image. Check the image ref (often a stale tag or unreachable registry) and clean up if it's an orphan."
 
           - alert: KubeDeploymentReplicasMismatch
-            expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available
+            # github-runner has explicit runner-offline alerts; the generic
+            # replica-mismatch rule should not page on intentionally ephemeral
+            # 0/1 runner churn between CI jobs.
+            expr: kube_deployment_spec_replicas{namespace!="github-runner"} != kube_deployment_status_replicas_available{namespace!="github-runner"}
             for: 15m
             labels:
               severity: warning

tests/bluejay-infra-lint/FleetManifestLintTests.cs

@@ -423,6 +423,82 @@ public sealed class FleetManifestLintTests
         monitoring.Should().Contain("alert_channel: irc");
     }
 
+    [Fact]
+    public void Monitoring_GenericKubernetesAlerts_MustExcludeEphemeralGithubRunnerNamespace()
+    {
+        var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
+
+        monitoring.Should().Contain("kube_pod_container_status_restarts_total{namespace!=\"github-runner\"}");
+        monitoring.Should().Contain("and on(namespace, pod) kube_pod_info");
+        monitoring.Should().Contain("kube_deployment_spec_replicas{namespace!=\"github-runner\"} != kube_deployment_status_replicas_available{namespace!=\"github-runner\"}");
+        monitoring.Should().Contain("dedicated LinuxRunnerOffline/MacMiniRunnerOffline alerts");
+    }
+
+    [Fact]
+    public void Monitoring_BlackboxTargetsForOidcSensitiveServices_MustUseAnonymousHealthRoutesWhenAvailable()
+    {
+        var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
+
+        monitoring.Should().Contain("https://chat.iamworkin.lan/healthz");
+        monitoring.Should().Contain("https://dist.iamworkin.lan/healthz");
+        monitoring.Should().Contain("https://dms.iamworkin.lan/healthz");
+        monitoring.Should().Contain("https://print.iamworkin.lan/healthz");
+        monitoring.Should().Contain("https://knowledge.iamworkin.lan/healthz");
+        monitoring.Should().Contain("https://library.iamworkin.lan/health");
+        monitoring.Should().Contain("https://aistation.iamworkin.lan/healthz");
+        monitoring.Should().NotContain("https://print.iamworkin.lan/\"");
+    }
+
+    [Fact]
+    public void OidcEnforcedDeployments_WithHttpHealthzProbes_MustDeclareAnonymousHealthzContract()
+    {
+        var violations = Inventory.Documents
+            .Where(document => document.Kind == "Deployment")
+            .SelectMany(document => document.MainContainerMappings()
+                .Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
+                .Where(container => string.Equals(EnvValue(container, "FlowerCore__Auth__Oidc__Enabled"), "true", StringComparison.OrdinalIgnoreCase))
+                .Where(container => ProbeHttpGetPath(container, "readinessProbe") == "/healthz"
+                    || ProbeHttpGetPath(container, "startupProbe") == "/healthz")
+                .Where(_ => !string.Equals(
+                    PodAnnotation(document, "flowercore.io/healthz-auth-policy"),
+                    "allow-anonymous",
+                    StringComparison.Ordinal))
+                .Select(container =>
+                {
+                    var containerName = ManifestNodeExtensions.Scalar(container, "name") ?? "<unnamed>";
+                    return $"{document.Descriptor} container '{containerName}' enforces OIDC while probing /healthz but lacks flowercore.io/healthz-auth-policy: allow-anonymous.";
+                }))
+            .ToList();
+
+        violations.Should().BeEmpty();
+    }
+
+    [Fact]
+    public void Knowledge_OidcEnforcement_MustKeepHealthzAnonymousContractVisibleInManifest()
+    {
+        var knowledge = Inventory.Documents
+            .Single(document => document.Kind == "Deployment" && document.Namespace == "knowledge" && document.Name == "knowledge-web");
+        var container = knowledge.MainContainerMappings().Should().ContainSingle().Subject;
+
+        EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("true");
+        EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
+        ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
+        PodAnnotation(knowledge, "flowercore.io/healthz-auth-policy").Should().Be("allow-anonymous");
+    }
+
+    [Fact]
+    public void Distribution_OidcEnforcement_MustKeepHealthzAnonymousContractVisibleInManifest()
+    {
+        var distribution = Inventory.Documents
+            .Single(document => document.Kind == "Deployment" && document.Namespace == "fc-distribution" && document.Name == "fc-distribution");
+        var container = distribution.MainContainerMappings().Should().ContainSingle().Subject;
+
+        EnvValue(container, "FlowerCore__Auth__Oidc__Enabled").Should().Be("true");
+        EnvValue(container, "FlowerCore__Auth__Enabled").Should().Be("true");
+        ProbeHttpGetPath(container, "readinessProbe").Should().Be("/healthz");
+        PodAnnotation(distribution, "flowercore.io/healthz-auth-policy").Should().Be("allow-anonymous");
+    }
+
     [Fact]
     public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
     {
@@ -790,6 +866,12 @@ public sealed class FleetManifestLintTests
             "/volume1/kubernetes/fc-media-inbox",
             "/volume1/video",
         });
+
+        var distributionDeployment = AppDocuments("fc-distribution")
+            .Single(document => document.Kind == "Deployment" && document.Name == "fc-distribution");
+        var distributionContainer = distributionDeployment.MainContainerMappings().Should().ContainSingle().Subject;
+
+        ManifestNodeExtensions.Scalar(distributionContainer, "image").Should().Be("localhost/fc-distribution:v20260604-oidc-root-anon");
     }
 
     [Fact]
@@ -920,6 +1002,19 @@ public sealed class FleetManifestLintTests
             .SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
     }
 
+    private static string? PodAnnotation(ManifestDocument document, string name)
+    {
+        return document.Scalar("spec", "template", "metadata", "annotations", name);
+    }
+
+    private static string? ProbeHttpGetPath(YamlMappingNode container, string probeKey)
+    {
+        return ManifestNodeExtensions.TryGetMapping(container, probeKey, out var probe)
+            && ManifestNodeExtensions.TryGetMapping(probe, "httpGet", out var httpGet)
+            ? ManifestNodeExtensions.Scalar(httpGet, "path")
+            : null;
+    }
+
     private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
     {
         return Inventory.Documents