Update dashboard manifests and add automation

- Updated deployment with correct Pi 3 tolerations
- Updated ingress for cloudflare-tunnel
- Added crontab example for systemd alternative
- Updated go.sum

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

automation/crontab.example

@@ -0,0 +1,18 @@
+# K8s Agent Scheduled Workflows
+# Install with: crontab /home/will/.claude/automation/crontab.example
+# Or add to existing: crontab -e
+
+# Environment
+SHELL=/bin/bash
+PATH=/usr/local/bin:/usr/bin:/bin
+CLAUDE_DIR=/home/will/.claude
+DASHBOARD_URL=http://k8s-agent-dashboard-k8s-agent.taildb3494.ts.net
+
+# Cluster health check - every 6 hours
+0 */6 * * * /home/will/.claude/automation/scheduler.sh cluster-health-check >> /home/will/.claude/logs/cron.log 2>&1
+
+# Daily cluster summary - 8am
+0 8 * * * /home/will/.claude/automation/scheduler.sh cluster-health-check >> /home/will/.claude/logs/cron.log 2>&1
+
+# Log rotation - weekly on Sunday at midnight
+0 0 * * 0 find /home/will/.claude/logs -name "*.log" -mtime +7 -delete

dashboard/deploy/deployment.yaml

@@ -18,12 +18,12 @@ spec:
     spec:
       # Target Pi 3 node (lightweight workload)
       tolerations:
-        - key: "node-type"
+        - key: "capacity"
           operator: "Equal"
-          value: "pi3"
+          value: "low"
-          effect: "NoSchedule"
+          effect: "NoExecute"
       nodeSelector:
-        kubernetes.io/arch: arm64
+        kubernetes.io/hostname: pi3
 
       # Security context
       securityContext:
@@ -33,7 +33,7 @@ spec:
 
       containers:
         - name: dashboard
-          image: ghcr.io/will/k8s-agent-dashboard:latest
+          image: gitea-http.taildb3494.ts.net/will/k8s-agent-dashboard:latest
           imagePullPolicy: Always
           ports:
             - name: http

dashboard/deploy/ingress.yaml

@@ -6,13 +6,10 @@ metadata:
   labels:
     app.kubernetes.io/name: k8s-agent-dashboard
     app.kubernetes.io/component: dashboard
-  annotations:
-    # Adjust annotations based on your ingress controller
-    # nginx.ingress.kubernetes.io/ssl-redirect: "false"
 spec:
-  ingressClassName: nginx  # or traefik, etc.
+  ingressClassName: cloudflare-tunnel
   rules:
-    - host: k8s-agent.local  # Adjust to your domain
+    - host: k8s-agent-dashboard-k8s-agent.taildb3494.ts.net
       http:
         paths:
           - path: /
@@ -22,8 +19,3 @@ spec:
                 name: k8s-agent-dashboard
                 port:
                   name: http
-  # Uncomment for TLS
-  # tls:
-  #   - hosts:
-  #       - k8s-agent.local
-  #     secretName: k8s-agent-dashboard-tls

dashboard/deploy/kustomization.yaml

@@ -15,5 +15,5 @@ commonLabels:
   app.kubernetes.io/managed-by: argocd
 
 images:
-  - name: ghcr.io/will/k8s-agent-dashboard
+  - name: gitea-http.taildb3494.ts.net/will/k8s-agent-dashboard
     newTag: latest

dashboard/deploy/pvc.yaml

@@ -9,8 +9,7 @@ metadata:
 spec:
   accessModes:
     - ReadWriteOnce
+  storageClassName: local-path
   resources:
     requests:
       storage: 100Mi
-  # Adjust storageClassName based on your cluster
-  # storageClassName: local-path

dashboard/go.sum

@@ -1,4 +1,4 @@
-github.com/go-chi/chi/v5 v5.0.11 h1/BnpYbFZ3T3S1WMpD79r7R5ThWX40TaFB7L31Y8xqSwA=
+github.com/go-chi/chi/v5 v5.0.11 h1:BnpYbFZ3T3S1WMpD79r7R5ThWX40TaFB7L31Y8xqSwA=
-github.com/go-chi/chi/v5 v5.0.11/go.mod h1/DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
+github.com/go-chi/chi/v5 v5.0.11/go.mod h1:DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
 github.com/go-chi/cors v1.2.1 h1:xEC8UT3Rlp2QuWNEr4Fs/c2EAGVKBwy/1vHx3bppil4=
-github.com/go-chi/cors v1.2.1/go.mod h1:sSbTewc+6wYHBBCW7ytsFSn3rn0gOeEOrPIsEDqiK+0=
+github.com/go-chi/cors v1.2.1/go.mod h1:sSbTewc+6wYHBBCW7ytsFSn836hqM7JxpglAy2Vzc58=

plans/pure-wishing-metcalfe.md

@@ -0,0 +1,34 @@
+# Cluster Issue Diagnosis Plan
+
+## Issues to Investigate
+
+1. **Critical Alerts** - KubeSchedulerDown, KubeControllerManagerDown
+   - Likely false positives (k0s bundles these in k0s-controller)
+   - Check if cluster is actually functional
+
+2. **CrashLooping Pod** - Find and diagnose
+   - Get pod status across all namespaces
+   - Check logs and events
+
+3. **Stuck Deployment** - Find and diagnose
+   - List deployments not at desired replica count
+   - Check events
+
+4. **Degraded kube-prometheus-stack**
+   - Check prometheus/alertmanager pods
+
+## Commands to Run
+
+```bash
+# Find crash looping pods
+kubectl get pods -A | grep -E 'CrashLoop|Error|ImagePull'
+
+# Find stuck deployments
+kubectl get deploy -A -o wide | grep -v '1/1\|2/2\|3/3\|4/4'
+
+# Check prometheus stack
+kubectl get pods -n monitoring
+
+# Check scheduler/controller (k0s specific)
+kubectl get pods -n kube-system
+```