feat: Claude Code Monitor — lanes, pipelines and a merged workspace

Internal SmartGift build of a Claude Code monitoring dashboard. Lanes: a durable unit of parallel agent work, one per working directory, tracked across session restarts. Managed lanes are git worktrees the dashboard provisions and can reset or remove behind a three-check destroy guard and a counted preflight; adopted lanes are directories you already own and are never destroyable. Pipelines: a lane moves through pipeline stages. A stage the agent declares with evidence renders green; a stage inferred from the tool-event stream renders dashed amber and never counts as done. Detection is forward-only within a 30-minute window, and never writes the declared stage. Workspace: one page at /run with a lane grid, the selected lane's pipeline, and a full Claude console behind a disclosure.
2026-07-29 17:07:45 +07:00
commit 57dc91585d
783 changed files with 221743 additions and 0 deletions
@@ -0,0 +1,18 @@
+# Patterns to ignore when building packages.
+.DS_Store
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+.project
+.idea/
+*.tmproj
+.vscode/
@@ -0,0 +1,28 @@
+apiVersion: v2
+name: agent-monitor
+description: Claude Code Agent Monitor - Real-time dashboard for tracking Claude Code agent activity
+type: application
+version: 1.0.0
+appVersion: "1.0.0"
+
+home: https://git.smartgift.io.vn/Smartgift-AI/Claude-Code-Monitor
+sources:
+  - https://git.smartgift.io.vn/Smartgift-AI/Claude-Code-Monitor
+
+keywords:
+  - claude
+  - agent
+  - monitor
+  - dashboard
+  - ai
+  - devtools
+  - observability
+
+maintainers:
+  - name: David Nguyen
+    url: https://git.smartgift.io.vn/Smartgift-AI
+
+icon: https://git.smartgift.io.vn/Smartgift-AI/Claude-Code-Monitor/raw/branch/master/favicon.svg
+
+annotations:
+  artifacthub.io/category: monitoring-logging
@@ -0,0 +1,79 @@
+╔══════════════════════════════════════════════════════════════════════╗
+║           Claude Code Agent Monitor - Deployment Notes              ║
+╚══════════════════════════════════════════════════════════════════════╝
+
+{{- $fullName := include "agent-monitor.fullname" . -}}
+
+🎉 {{ $fullName }} has been deployed to namespace "{{ .Release.Namespace }}"!
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+📡 Accessing the Dashboard:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+
+  URL: http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+
+  export NODE_PORT=$(kubectl get -n {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ $fullName }})
+  export NODE_IP=$(kubectl get nodes -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo "Dashboard URL: http://$NODE_IP:$NODE_PORT"
+
+{{- else if contains "LoadBalancer" .Values.service.type }}
+
+  NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+  Watch status with:
+    kubectl get -n {{ .Release.Namespace }} svc {{ $fullName }} -w
+
+  export SERVICE_IP=$(kubectl get svc -n {{ .Release.Namespace }} {{ $fullName }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
+  echo "Dashboard URL: http://$SERVICE_IP:{{ .Values.service.port }}"
+
+{{- else }}
+
+  Port-forward to access locally:
+    kubectl port-forward -n {{ .Release.Namespace }} svc/{{ $fullName }} 4820:{{ .Values.service.port }}
+
+  Then open: http://localhost:4820
+
+{{- end }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+🔍 Health Check:
+  kubectl exec -n {{ .Release.Namespace }} deploy/{{ $fullName }} -- wget -qO- http://localhost:{{ .Values.service.targetPort }}/api/health
+
+🧪 Run Tests:
+  helm test {{ .Release.Name }} -n {{ .Release.Namespace }}
+
+📊 View Logs:
+  kubectl logs -n {{ .Release.Namespace }} -l app.kubernetes.io/name={{ include "agent-monitor.name" . }} -f
+
+📈 Check Pods:
+  kubectl get pods -n {{ .Release.Namespace }} -l app.kubernetes.io/name={{ include "agent-monitor.name" . }}
+
+{{- if .Values.persistence.enabled }}
+
+💾 Persistent Storage:
+  SQLite data is stored on PVC: {{ $fullName }}-data ({{ .Values.persistence.size }})
+{{- end }}
+
+{{- if .Values.mcp.enabled }}
+
+🔌 MCP Sidecar:
+  MCP server is running on port {{ .Values.mcp.port }}
+  Access via: kubectl port-forward -n {{ .Release.Namespace }} svc/{{ $fullName }} {{ .Values.mcp.port }}:{{ .Values.mcp.port }}
+{{- end }}
+
+{{- if .Values.autoscaling.enabled }}
+
+📐 Autoscaling:
+  Min replicas: {{ .Values.autoscaling.minReplicas }}
+  Max replicas: {{ .Values.autoscaling.maxReplicas }}
+  CPU target:   {{ .Values.autoscaling.targetCPUUtilizationPercentage }}%
+  Memory target: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}%
+{{- end }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -0,0 +1,88 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "agent-monitor.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this
+(by the DNS naming spec). If release name contains the chart name it will be used
+as a full name.
+*/}}
+{{- define "agent-monitor.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "agent-monitor.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "agent-monitor.labels" -}}
+helm.sh/chart: {{ include "agent-monitor.chart" . }}
+{{ include "agent-monitor.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+app.kubernetes.io/part-of: claude-code-agent-monitor
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "agent-monitor.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "agent-monitor.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "agent-monitor.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "agent-monitor.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
+
+{{/*
+Return the container image string
+*/}}
+{{- define "agent-monitor.image" -}}
+{{- $tag := default .Chart.AppVersion .Values.image.tag -}}
+{{- if .Values.image.registry -}}
+{{- printf "%s/%s:%s" .Values.image.registry .Values.image.repository $tag -}}
+{{- else -}}
+{{- printf "%s:%s" .Values.image.repository $tag -}}
+{{- end -}}
+{{- end }}
+
+{{/*
+Return the MCP sidecar container image string
+*/}}
+{{- define "agent-monitor.mcpImage" -}}
+{{- $tag := default .Chart.AppVersion .Values.mcp.image.tag -}}
+{{- if .Values.mcp.image.registry -}}
+{{- printf "%s/%s:%s" .Values.mcp.image.registry .Values.mcp.image.repository $tag -}}
+{{- else -}}
+{{- printf "%s:%s" .Values.mcp.image.repository $tag -}}
+{{- end -}}
+{{- end }}
@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}-config
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+data:
+  {{- range $key, $value := .Values.env }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}
+  {{- range $key, $value := .Values.extraEnv }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}
@@ -0,0 +1,159 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  revisionHistoryLimit: {{ .Values.deployment.revisionHistoryLimit | default 5 }}
+  {{- with .Values.deployment.strategy }}
+  strategy:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "agent-monitor.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        {{- with .Values.podAnnotations }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+      labels:
+        {{- include "agent-monitor.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "agent-monitor.serviceAccountName" . }}
+      automountServiceAccountToken: false
+      {{- with .Values.podSecurityContext }}
+      securityContext:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      containers:
+        # ── Main application container ────────────────────────────────────
+        - name: {{ .Chart.Name }}
+          {{- with .Values.securityContext }}
+          securityContext:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          image: {{ include "agent-monitor.image" . }}
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.targetPort }}
+              protocol: TCP
+          {{- with .Values.livenessProbe }}
+          livenessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.readinessProbe }}
+          readinessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.startupProbe }}
+          startupProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          envFrom:
+            - configMapRef:
+                name: {{ include "agent-monitor.fullname" . }}-config
+            {{- with .Values.extraEnvFrom }}
+            {{- toYaml . | nindent 12 }}
+            {{- end }}
+          {{- with .Values.resources }}
+          resources:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          lifecycle:
+            preStop:
+              exec:
+                # Allow in-flight requests (including WebSockets) to drain before SIGTERM
+                command: ["sh", "-c", "sleep 5"]
+          volumeMounts:
+            - name: data
+              mountPath: /app/data
+            - name: tmp
+              mountPath: /tmp
+          {{- if .Values.mcp.enabled }}
+        # ── MCP sidecar container ─────────────────────────────────────────
+        - name: mcp
+          {{- with .Values.mcp.securityContext }}
+          securityContext:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          image: {{ include "agent-monitor.mcpImage" . }}
+          imagePullPolicy: {{ .Values.mcp.image.pullPolicy }}
+          ports:
+            - name: mcp
+              containerPort: {{ .Values.mcp.port }}
+              protocol: TCP
+          env:
+            {{- range $key, $value := .Values.mcp.env }}
+            - name: {{ $key }}
+              value: {{ $value | quote }}
+            {{- end }}
+          startupProbe:
+            tcpSocket:
+              port: mcp
+            failureThreshold: 30
+            periodSeconds: 2
+          livenessProbe:
+            tcpSocket:
+              port: mcp
+            initialDelaySeconds: 15
+            periodSeconds: 20
+            timeoutSeconds: 3
+            failureThreshold: 3
+          readinessProbe:
+            tcpSocket:
+              port: mcp
+            initialDelaySeconds: 5
+            periodSeconds: 10
+            timeoutSeconds: 3
+            failureThreshold: 3
+          {{- with .Values.mcp.resources }}
+          resources:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+          {{- end }}
+      volumes:
+        - name: data
+          {{- if .Values.persistence.enabled }}
+          persistentVolumeClaim:
+            claimName: {{ .Values.persistence.existingClaim | default (printf "%s-data" (include "agent-monitor.fullname" .)) }}
+          {{- else }}
+          emptyDir: {}
+          {{- end }}
+        - name: tmp
+          emptyDir:
+            sizeLimit: 100Mi
+      terminationGracePeriodSeconds: 30
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.topologySpreadConstraints }}
+      topologySpreadConstraints:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
@@ -0,0 +1,53 @@
+{{- if .Values.autoscaling.enabled -}}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "agent-monitor.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+  behavior:
+    scaleDown:
+      stabilizationWindowSeconds: {{ .Values.autoscaling.scaleDownStabilizationWindowSeconds | default 300 }}
+      policies:
+        - type: Pods
+          value: 1
+          periodSeconds: 60
+        - type: Percent
+          value: 10
+          periodSeconds: 60
+      selectPolicy: Min
+    scaleUp:
+      stabilizationWindowSeconds: 30
+      policies:
+        - type: Pods
+          value: 2
+          periodSeconds: 60
+        - type: Percent
+          value: 50
+          periodSeconds: 60
+      selectPolicy: Max
+{{- end }}
@@ -0,0 +1,41 @@
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if .Values.ingress.className }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            pathType: {{ .pathType }}
+            backend:
+              service:
+                name: {{ include "agent-monitor.fullname" $ }}
+                port:
+                  name: http
+          {{- end }}
+    {{- end }}
+{{- end }}
@@ -0,0 +1,46 @@
+{{- if .Values.networkPolicy.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+spec:
+  podSelector:
+    matchLabels:
+      {{- include "agent-monitor.selectorLabels" . | nindent 6 }}
+  policyTypes:
+    - Ingress
+    - Egress
+  ingress:
+    # Allow HTTP traffic to the application port from any pod (ingress controllers, etc.)
+    - ports:
+        - port: {{ .Values.service.targetPort }}
+          protocol: TCP
+      {{- if .Values.mcp.enabled }}
+    # Allow MCP traffic when sidecar is enabled
+    - ports:
+        - port: {{ .Values.mcp.port }}
+          protocol: TCP
+      {{- end }}
+    {{- with .Values.networkPolicy.additionalIngressRules }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+  egress:
+    # Allow DNS resolution
+    - ports:
+        - port: 53
+          protocol: UDP
+        - port: 53
+          protocol: TCP
+    # Allow outbound HTTPS (for external API calls)
+    - ports:
+        - port: 443
+          protocol: TCP
+    # Allow internal communication within the cluster
+    - to:
+        - podSelector: {}
+    {{- with .Values.networkPolicy.additionalEgressRules }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+{{- end }}
@@ -0,0 +1,18 @@
+{{- if .Values.podDisruptionBudget.enabled -}}
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+spec:
+  {{- if .Values.podDisruptionBudget.minAvailable }}
+  minAvailable: {{ .Values.podDisruptionBudget.minAvailable }}
+  {{- end }}
+  {{- if .Values.podDisruptionBudget.maxUnavailable }}
+  maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "agent-monitor.selectorLabels" . | nindent 6 }}
+{{- end }}
@@ -0,0 +1,23 @@
+{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) -}}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}-data
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+  {{- with .Values.persistence.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  accessModes:
+    {{- range .Values.persistence.accessModes }}
+    - {{ . }}
+    {{- end }}
+  {{- if .Values.persistence.storageClass }}
+  storageClassName: {{ .Values.persistence.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.size }}
+{{- end }}
@@ -0,0 +1,33 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+  {{- with .Values.service.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  type: {{ .Values.service.type }}
+  # Sticky sessions for WebSocket connections
+  sessionAffinity: ClientIP
+  sessionAffinityConfig:
+    clientIP:
+      timeoutSeconds: 10800
+  ports:
+    - name: http
+      port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      {{- if and (eq .Values.service.type "NodePort") .Values.service.nodePort }}
+      nodePort: {{ .Values.service.nodePort }}
+      {{- end }}
+    {{- if .Values.mcp.enabled }}
+    - name: mcp
+      port: {{ .Values.mcp.port }}
+      targetPort: mcp
+      protocol: TCP
+    {{- end }}
+  selector:
+    {{- include "agent-monitor.selectorLabels" . | nindent 4 }}
@@ -0,0 +1,13 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "agent-monitor.serviceAccountName" . }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken | default false }}
+{{- end }}
@@ -0,0 +1,29 @@
+{{- if and .Values.monitoring.enabled .Values.monitoring.serviceMonitor.enabled -}}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "agent-monitor.fullname" . }}
+  {{- if .Values.monitoring.serviceMonitor.namespace }}
+  namespace: {{ .Values.monitoring.serviceMonitor.namespace }}
+  {{- end }}
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+    {{- with .Values.monitoring.serviceMonitor.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "agent-monitor.selectorLabels" . | nindent 6 }}
+  {{- if .Values.monitoring.serviceMonitor.namespace }}
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace }}
+  {{- end }}
+  endpoints:
+    - port: http
+      path: {{ .Values.monitoring.serviceMonitor.path | default "/api/metrics" }}
+      interval: {{ .Values.monitoring.serviceMonitor.interval | default "30s" }}
+      scrapeTimeout: {{ .Values.monitoring.serviceMonitor.scrapeTimeout | default "10s" }}
+      honorLabels: {{ .Values.monitoring.serviceMonitor.honorLabels | default false }}
+{{- end }}
@@ -0,0 +1,34 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "agent-monitor.fullname" . }}-test-connection"
+  labels:
+    {{- include "agent-monitor.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+    "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
+spec:
+  restartPolicy: Never
+  securityContext:
+    runAsNonRoot: true
+    runAsUser: 65534
+    runAsGroup: 65534
+    seccompProfile:
+      type: RuntimeDefault
+  containers:
+    - name: wget
+      image: busybox:1.36
+      command: ['wget']
+      args:
+        - '--timeout=10'
+        - '--tries=3'
+        - '-qO-'
+        - 'http://{{ include "agent-monitor.fullname" . }}:{{ .Values.service.port }}/api/health'
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65534
+        readOnlyRootFilesystem: true
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
@@ -0,0 +1,50 @@
+# =============================================================================
+# Development Environment Overrides
+# =============================================================================
+# Usage: helm install agent-monitor ./agent-monitor -f values-dev.yaml
+
+replicaCount: 1
+
+image:
+  pullPolicy: Always
+
+env:
+  NODE_ENV: development
+  DASHBOARD_PORT: "4820"
+  LOG_LEVEL: debug
+
+resources:
+  requests:
+    cpu: 50m
+    memory: 64Mi
+  limits:
+    cpu: 250m
+    memory: 256Mi
+
+autoscaling:
+  enabled: false
+
+persistence:
+  enabled: true
+  size: 1Gi
+
+podDisruptionBudget:
+  enabled: false
+
+networkPolicy:
+  enabled: false
+
+monitoring:
+  enabled: false
+
+ingress:
+  enabled: false
+
+# Relax security for dev debugging
+securityContext:
+  readOnlyRootFilesystem: false
+  runAsNonRoot: true
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
@@ -0,0 +1,117 @@
+# =============================================================================
+# Production Environment Overrides
+# =============================================================================
+# Usage: helm install agent-monitor ./agent-monitor -f values-production.yaml
+
+replicaCount: 3
+
+env:
+  NODE_ENV: production
+  DASHBOARD_PORT: "4820"
+  LOG_LEVEL: warn
+
+resources:
+  requests:
+    cpu: 250m
+    memory: 256Mi
+  limits:
+    cpu: "1"
+    memory: "1Gi"
+
+autoscaling:
+  enabled: true
+  minReplicas: 3
+  maxReplicas: 20
+  targetCPUUtilizationPercentage: 70
+  targetMemoryUtilizationPercentage: 80
+  scaleDownStabilizationWindowSeconds: 600
+
+deployment:
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
+
+persistence:
+  enabled: true
+  size: 20Gi
+  storageClass: gp3
+
+podDisruptionBudget:
+  enabled: true
+  minAvailable: 2
+
+networkPolicy:
+  enabled: true
+
+# -- Spread pods across nodes (required) and zones (preferred) for high availability
+affinity:
+  podAntiAffinity:
+    requiredDuringSchedulingIgnoredDuringExecution:
+      - labelSelector:
+          matchExpressions:
+            - key: app.kubernetes.io/name
+              operator: In
+              values:
+                - agent-monitor
+        topologyKey: kubernetes.io/hostname
+    preferredDuringSchedulingIgnoredDuringExecution:
+      - weight: 50
+        podAffinityTerm:
+          labelSelector:
+            matchExpressions:
+              - key: app.kubernetes.io/name
+                operator: In
+                values:
+                  - agent-monitor
+          topologyKey: topology.kubernetes.io/zone
+
+topologySpreadConstraints:
+  - maxSkew: 1
+    topologyKey: topology.kubernetes.io/zone
+    whenUnsatisfiable: ScheduleAnyway
+    labelSelector:
+      matchLabels:
+        app.kubernetes.io/name: agent-monitor
+
+ingress:
+  enabled: true
+  className: nginx
+  annotations:
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    nginx.ingress.kubernetes.io/upstream-hash-by: "$remote_addr"
+    nginx.ingress.kubernetes.io/configuration-snippet: |
+      proxy_set_header Upgrade $http_upgrade;
+      proxy_set_header Connection "upgrade";
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
+    cert-manager.io/cluster-issuer: letsencrypt-prod
+  hosts:
+    - host: agent-monitor.example.com
+      paths:
+        - path: /
+          pathType: Prefix
+  tls:
+    - secretName: agent-monitor-production-tls
+      hosts:
+        - agent-monitor.example.com
+
+monitoring:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    interval: 15s
+    scrapeTimeout: 10s
+
+mcp:
+  enabled: true
+  resources:
+    requests:
+      cpu: 100m
+      memory: 128Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
@@ -0,0 +1,65 @@
+# =============================================================================
+# Staging Environment Overrides
+# =============================================================================
+# Usage: helm install agent-monitor ./agent-monitor -f values-staging.yaml
+
+replicaCount: 2
+
+env:
+  NODE_ENV: production
+  DASHBOARD_PORT: "4820"
+  LOG_LEVEL: info
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+autoscaling:
+  enabled: true
+  minReplicas: 2
+  maxReplicas: 5
+  targetCPUUtilizationPercentage: 75
+  targetMemoryUtilizationPercentage: 80
+  scaleDownStabilizationWindowSeconds: 180
+
+persistence:
+  enabled: true
+  size: 5Gi
+
+podDisruptionBudget:
+  enabled: true
+  minAvailable: 1
+
+networkPolicy:
+  enabled: true
+
+ingress:
+  enabled: true
+  className: nginx
+  annotations:
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    nginx.ingress.kubernetes.io/upstream-hash-by: "$remote_addr"
+    nginx.ingress.kubernetes.io/configuration-snippet: |
+      proxy_set_header Upgrade $http_upgrade;
+      proxy_set_header Connection "upgrade";
+  hosts:
+    - host: agent-monitor.staging.internal
+      paths:
+        - path: /
+          pathType: Prefix
+  tls:
+    - secretName: agent-monitor-staging-tls
+      hosts:
+        - agent-monitor.staging.internal
+
+monitoring:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    interval: 30s
@@ -0,0 +1,312 @@
+# =============================================================================
+# Claude Code Agent Monitor - Default Helm Values
+# =============================================================================
+# Override these values per environment using values-dev.yaml, values-staging.yaml,
+# or values-production.yaml.
+
+# -- Number of pod replicas
+replicaCount: 2
+
+# -- Container image configuration
+image:
+  registry: ghcr.io
+  repository: smartgift/claude-code-monitor
+  tag: "" # Defaults to .Chart.AppVersion if empty
+  pullPolicy: IfNotPresent
+
+# -- Image pull secrets for private registries
+imagePullSecrets: []
+
+# -- Override the release name
+nameOverride: ""
+# -- Override the full release name
+fullnameOverride: ""
+
+# =============================================================================
+# Service Account
+# =============================================================================
+serviceAccount:
+  # -- Whether to create a ServiceAccount
+  create: true
+  # -- Annotations to add to the ServiceAccount
+  annotations: {}
+  # -- The name of the ServiceAccount (auto-generated if empty)
+  name: ""
+  # -- Automount API credentials
+  automountServiceAccountToken: false
+
+# =============================================================================
+# Pod Configuration
+# =============================================================================
+
+# -- Annotations to add to pods
+podAnnotations: {}
+
+# -- Labels to add to pods
+podLabels: {}
+
+# -- Pod-level security context
+podSecurityContext:
+  runAsNonRoot: true
+  runAsUser: 1000
+  runAsGroup: 1000
+  fsGroup: 1000
+  fsGroupChangePolicy: OnRootMismatch
+  seccompProfile:
+    type: RuntimeDefault
+
+# -- Container-level security context
+securityContext:
+  runAsNonRoot: true
+  readOnlyRootFilesystem: true
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
+
+# =============================================================================
+# Deployment Strategy
+# =============================================================================
+deployment:
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
+
+# =============================================================================
+# Service
+# =============================================================================
+service:
+  # -- Service type (ClusterIP, NodePort, LoadBalancer)
+  type: ClusterIP
+  # -- Service port (external)
+  port: 80
+  # -- Container port the application listens on
+  targetPort: 4820
+  # -- Node port (only used when type is NodePort)
+  nodePort: ""
+  # -- Additional service annotations
+  annotations: {}
+
+# =============================================================================
+# Ingress
+# =============================================================================
+ingress:
+  # -- Enable ingress resource
+  enabled: false
+  # -- Ingress class name (e.g. nginx, traefik, alb)
+  className: ""
+  # -- Ingress annotations
+  annotations: {}
+    # nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+    # nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    # nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    # nginx.ingress.kubernetes.io/proxy-set-headers: "Upgrade=$http_upgrade,Connection=upgrade"
+  # -- Ingress host definitions
+  hosts:
+    - host: agent-monitor.local
+      paths:
+        - path: /
+          pathType: Prefix
+  # -- TLS configuration
+  tls: []
+  #  - secretName: agent-monitor-tls
+  #    hosts:
+  #      - agent-monitor.local
+
+# =============================================================================
+# Resource Limits
+# =============================================================================
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+# =============================================================================
+# Autoscaling (HPA)
+# =============================================================================
+autoscaling:
+  # -- Enable Horizontal Pod Autoscaler
+  enabled: true
+  # -- Minimum number of replicas
+  minReplicas: 2
+  # -- Maximum number of replicas
+  maxReplicas: 10
+  # -- Target CPU utilization percentage
+  targetCPUUtilizationPercentage: 70
+  # -- Target memory utilization percentage
+  targetMemoryUtilizationPercentage: 80
+  # -- Scale-down stabilization window (seconds)
+  scaleDownStabilizationWindowSeconds: 300
+
+# =============================================================================
+# Persistence (SQLite database)
+# =============================================================================
+persistence:
+  # -- Enable persistent storage for SQLite data
+  enabled: true
+  # -- Storage class name (empty string uses default)
+  storageClass: ""
+  # -- Access modes for the PVC
+  accessModes:
+    - ReadWriteOnce
+  # -- Size of the persistent volume
+  size: 10Gi
+  # -- Annotations for the PVC
+  annotations: {}
+  # -- Use an existing PVC instead of creating one
+  existingClaim: ""
+
+# =============================================================================
+# Scheduling
+# =============================================================================
+
+# -- Node selector for pod placement
+nodeSelector: {}
+
+# -- Tolerations for pod placement
+tolerations: []
+
+# -- Affinity rules for pod placement
+affinity: {}
+
+# -- Topology spread constraints
+topologySpreadConstraints: []
+
+# =============================================================================
+# Environment Variables
+# =============================================================================
+env:
+  # -- Node.js environment
+  NODE_ENV: production
+  # -- Port the dashboard server listens on (must match service.targetPort)
+  DASHBOARD_PORT: "4820"
+  # -- Log level (debug, info, warn, error)
+  LOG_LEVEL: info
+
+# -- Additional environment variables as key-value pairs
+extraEnv: {}
+  # MY_CUSTOM_VAR: my-value
+
+# -- Extra environment variables from secrets or configmaps
+extraEnvFrom: []
+  # - secretRef:
+  #     name: my-secret
+  # - configMapRef:
+  #     name: my-configmap
+
+# =============================================================================
+# Health Probes
+# =============================================================================
+livenessProbe:
+  httpGet:
+    path: /api/health
+    port: http
+  initialDelaySeconds: 30
+  periodSeconds: 15
+  timeoutSeconds: 5
+  failureThreshold: 3
+  successThreshold: 1
+
+readinessProbe:
+  httpGet:
+    path: /api/health
+    port: http
+  initialDelaySeconds: 5
+  periodSeconds: 10
+  timeoutSeconds: 3
+  failureThreshold: 3
+  successThreshold: 1
+
+startupProbe:
+  httpGet:
+    path: /api/health
+    port: http
+  initialDelaySeconds: 5
+  periodSeconds: 5
+  timeoutSeconds: 3
+  failureThreshold: 30
+  successThreshold: 1
+
+# =============================================================================
+# Pod Disruption Budget
+# =============================================================================
+podDisruptionBudget:
+  # -- Enable PodDisruptionBudget
+  enabled: true
+  # -- Minimum available pods during voluntary disruptions
+  minAvailable: 1
+  # -- Maximum unavailable pods (alternative to minAvailable)
+  # maxUnavailable: 1
+
+# =============================================================================
+# Network Policy
+# =============================================================================
+networkPolicy:
+  # -- Enable NetworkPolicy
+  enabled: true
+  # -- Additional ingress rules
+  additionalIngressRules: []
+  # -- Additional egress rules
+  additionalEgressRules: []
+
+# =============================================================================
+# MCP Sidecar (Model Context Protocol server)
+# =============================================================================
+mcp:
+  # -- Enable MCP sidecar container
+  enabled: false
+  image:
+    registry: ghcr.io
+    repository: smartgift/claude-code-monitor-mcp
+    tag: "" # Defaults to .Chart.AppVersion if empty
+    pullPolicy: IfNotPresent
+  # -- MCP HTTP transport port
+  port: 8819
+  # -- Resource limits for MCP sidecar
+  resources:
+    requests:
+      cpu: 50m
+      memory: 64Mi
+    limits:
+      cpu: 200m
+      memory: 256Mi
+  # -- MCP environment variables
+  env:
+    MCP_TRANSPORT: http
+    MCP_PORT: "8819"
+    DASHBOARD_URL: "http://localhost:4820"
+  # -- Container security context for MCP
+  securityContext:
+    runAsNonRoot: true
+    readOnlyRootFilesystem: true
+    allowPrivilegeEscalation: false
+    capabilities:
+      drop:
+        - ALL
+
+# =============================================================================
+# Monitoring
+# =============================================================================
+monitoring:
+  # -- Enable Prometheus monitoring
+  enabled: false
+  serviceMonitor:
+    # -- Enable ServiceMonitor resource (requires Prometheus Operator)
+    enabled: false
+    # -- Namespace for the ServiceMonitor (defaults to release namespace)
+    namespace: ""
+    # -- Additional labels for the ServiceMonitor
+    labels: {}
+    # -- Scrape interval
+    interval: 30s
+    # -- Scrape timeout
+    scrapeTimeout: 10s
+    # -- Metric path
+    path: /api/metrics
+    # -- Honor labels from the target
+    honorLabels: false