fix(zabbix): bump web probe timeouts 5s→15s + add failureThreshold

zabbix-web nginx+PHP-FPM container serves / at ~3-5s baseline with
occasional 6-7s spikes (probe path renders full dashboard via PHP).
kube-probe was killing the container after 3 consecutive 5s-timeout
499s, producing CrashLoopBackOff alert noise even though the app
was serving real traffic fine.

15s timeout absorbs the natural variance; explicit failureThreshold=3
documents the policy (was implicit default).

Closes the firing PodCrashLoopBackOff (zabbix-web) + pending
HTTPServiceSlow/HTTPServiceDegraded alerts. zabbix.iamworkin.lan
remains slow at the application layer (separate work — PHP-FPM
warm-up + Zabbix server "host not found" agent lookup spam need
their own fixes) but the pod restart loop stops.

apps/github-runner/github-runner.yaml

@@ -0,0 +1,196 @@
+# GitHub Actions self-hosted Linux runner — Phase 2 K8s deployment
+#
+# Phase 1 (current): BLUEJAY-WS registered manually as a Windows runner
+#   with label "fc-build-windows" via config.cmd (see docs/infrastructure/
+#   self-hosted-runner-fleet.md §WPF Build Runner).
+#
+# Phase 2 (this file): ephemeral Linux runner in RKE2 for non-WPF builds
+#   (Blazor Server, class libraries, operators, integration tests). Reduces
+#   billing for ubuntu-24.04 jobs that run on GitHub-hosted runners today.
+#
+# Runner image: myoung34/github-runner:latest
+#   EPHEMERAL=true — each pod runs exactly one job then exits; the
+#   Deployment controller immediately recreates it and re-registers.
+#   Prevents job queue starvation when two jobs overlap.
+#
+# NuGet cache: 5Gi Longhorn RWO PVC mounted at /home/runner/.nuget/packages
+#   Persists NuGet packages across ephemeral pod restarts (not shared across
+#   simultaneous runner pods; single-replica constraint below).
+#
+# Credentials:
+#   OnePasswordItem "GitHub Runner Registration Token" → Secret
+#   github-runner-token with field "credential" used as RUNNER_TOKEN.
+#   Operator must create/rotate the 1P item manually; registration tokens
+#   expire after 1h — use a fine-grained PAT with admin:org_hook scope
+#   or a re-registration script. See docs/infrastructure/
+#   self-hosted-runner-fleet.md §Security.
+#
+# Security model:
+#   - No ClusterRole / ClusterRoleBinding — runner has no K8s API access.
+#   - securityContext: runAsNonRoot with read-only root filesystem where
+#     possible (runner image needs /tmp and /home/runner writable).
+#   - Fork pull-request approval required on the GitHub repo settings.
+#   - RUNNER_ALLOW_RUNASROOT=false is the default.
+#
+# Cost: Phase 2 eliminates GitHub-hosted ubuntu-24.04 billing; break-even
+#   vs electricity is ~1 000 min/month at current TOU rates.
+#
+# Node placement: rke2-server (10.0.56.11) only — Longhorn RWO PVC must
+#   land on the same node as the volume, and the server node has the most
+#   spare capacity for burst CI workloads.
+#
+# Designs: docs/infrastructure/self-hosted-runner-fleet.md
+# Questions: Q-CI-1..5 (all Recommended defaults)
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: github-runner
+  labels:
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+---
+# 1Password secret sync — creates github-runner-token K8s Secret.
+# Fields expected in the 1Password item:
+#   credential — GitHub runner registration token (or PAT for re-reg script)
+# Item path: IAmWorkin vault > "GitHub Runner Registration Token"
+# Operator MUST create this item before the Deployment will start cleanly.
+apiVersion: onepassword.com/v1
+kind: OnePasswordItem
+metadata:
+  name: github-runner-token
+  namespace: github-runner
+  labels:
+    app.kubernetes.io/component: credentials
+    app.kubernetes.io/part-of: flowercore
+spec:
+  itemPath: vaults/IAmWorkin/items/GitHub Runner Registration Token
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: github-runner-nuget-cache
+  namespace: github-runner
+  labels:
+    app.kubernetes.io/component: cache
+    app.kubernetes.io/part-of: flowercore
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 5Gi
+  volumeMode: Filesystem
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: github-runner
+  namespace: github-runner
+  labels:
+    app.kubernetes.io/component: runner
+    app.kubernetes.io/part-of: flowercore
+# No ClusterRole or ClusterRoleBinding — runner has zero K8s API privileges.
+# CI jobs that need kubectl must supply their own kubeconfig via a secret
+# injected at the job level, not via this service account.
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: github-runner
+  namespace: github-runner
+  labels:
+    app.kubernetes.io/name: github-runner
+    app.kubernetes.io/component: runner
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/created-by: argocd
+spec:
+  # Single replica enforced: the Longhorn RWO PVC can only be mounted by
+  # one pod at a time. Each pod re-registers as an ephemeral runner after
+  # completing a job (EPHEMERAL=true restarts the container, not the pod,
+  # so the PVC stays attached between jobs).
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: github-runner
+  # Use Recreate to avoid the Multi-Attach RWO error during rollouts.
+  strategy:
+    type: Recreate
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: github-runner
+        app.kubernetes.io/component: runner
+        app.kubernetes.io/part-of: flowercore
+        flowercore.io/created-by: argocd
+    spec:
+      serviceAccountName: github-runner
+      # Pin to rke2-server so the Longhorn RWO volume is always on the same node.
+      nodeSelector:
+        kubernetes.io/hostname: rke2-server
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 1001
+        runAsGroup: 1001
+        fsGroup: 1001
+      containers:
+        - name: runner
+          image: myoung34/github-runner:latest
+          imagePullPolicy: Always
+          env:
+            # GitHub org/repo targeting.
+            # Set REPO_URL for a repo-scoped runner (cheaper, simpler).
+            # Switch to ORG_NAME + empty REPO_URL for an org-scoped runner.
+            - name: REPO_URL
+              value: "https://github.com/astoltz/FlowerCore.Common"
+            - name: RUNNER_NAME_PREFIX
+              value: "rke2-linux"
+            - name: RUNNER_WORKDIR
+              value: "/tmp/runner/work"
+            # EPHEMERAL=true: runner deregisters after one job; container
+            # exits with code 0; Deployment controller restarts it and a
+            # fresh registration occurs. Prevents stale runner accumulation.
+            - name: EPHEMERAL
+              value: "true"
+            # Labels used by workflow files: runs-on: [self-hosted, linux, fc-build-linux]
+            - name: LABELS
+              value: "self-hosted,linux,fc-build-linux"
+            # Registration token injected from 1Password via OnePasswordItem CRD.
+            - name: RUNNER_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: github-runner-token
+                  key: credential
+          resources:
+            requests:
+              cpu: "500m"
+              memory: "1Gi"
+            limits:
+              cpu: "2000m"
+              memory: "4Gi"
+          volumeMounts:
+            - name: nuget-cache
+              mountPath: /home/runner/.nuget/packages
+            - name: tmp
+              mountPath: /tmp
+          # Liveness: runner process is alive.
+          livenessProbe:
+            exec:
+              command:
+                - /bin/sh
+                - -c
+                - "pgrep -f Runner.Listener > /dev/null"
+            initialDelaySeconds: 30
+            periodSeconds: 30
+            failureThreshold: 3
+      volumes:
+        - name: nuget-cache
+          persistentVolumeClaim:
+            claimName: github-runner-nuget-cache
+        - name: tmp
+          emptyDir: {}
+      # Restart policy: Always — the Deployment controller handles
+      # re-registration after each ephemeral job completes.
+      restartPolicy: Always

apps/zabbix/zabbix.yaml

@@ -305,15 +305,17 @@ spec:
               path: /
               port: 8080
             initialDelaySeconds: 60
-            timeoutSeconds: 5
+            timeoutSeconds: 15
             periodSeconds: 10
+            failureThreshold: 3
           readinessProbe:
             httpGet:
               path: /
               port: 8080
             initialDelaySeconds: 30
             periodSeconds: 5
-            timeoutSeconds: 5
+            timeoutSeconds: 15
+            failureThreshold: 3
 ---
 apiVersion: v1
 kind: Service