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 +1,69 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: agent-monitor
+  namespace: agent-monitor
+spec:
+  template:
+    spec:
+      containers:
+        - name: mcp-sidecar
+          image: ${IMAGE_REGISTRY}/agent-monitor-mcp:${IMAGE_TAG}
+          imagePullPolicy: IfNotPresent
+
+          ports:
+            - name: mcp
+              containerPort: 8819
+              protocol: TCP
+
+          env:
+            - name: MCP_TRANSPORT
+              value: "http"
+            - name: MCP_DASHBOARD_BASE_URL
+              value: "http://localhost:4820"
+            - name: MCP_PORT
+              value: "8819"
+
+          resources:
+            requests:
+              memory: "64Mi"
+              cpu: "50m"
+            limits:
+              memory: "256Mi"
+              cpu: "250m"
+
+          startupProbe:
+            tcpSocket:
+              port: mcp
+            failureThreshold: 30
+            periodSeconds: 2
+
+          readinessProbe:
+            tcpSocket:
+              port: mcp
+            initialDelaySeconds: 5
+            periodSeconds: 10
+            timeoutSeconds: 3
+            failureThreshold: 3
+
+          livenessProbe:
+            tcpSocket:
+              port: mcp
+            initialDelaySeconds: 10
+            periodSeconds: 30
+            timeoutSeconds: 5
+            failureThreshold: 3
+
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 1000
+            runAsGroup: 1000
+            readOnlyRootFilesystem: true
+            allowPrivilegeEscalation: false
+            capabilities:
+              drop:
+                - ALL
+
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
@@ -0,0 +1,11 @@
+apiVersion: kustomize.config.k8s.io/v1alpha1
+kind: Component
+
+metadata:
+  name: mcp-sidecar
+
+patches:
+  - path: deployment-patch.yaml
+    target:
+      kind: Deployment
+      name: agent-monitor
@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1alpha1
+kind: Component
+
+metadata:
+  name: monitoring
+
+resources:
+  - servicemonitor.yaml
@@ -0,0 +1,31 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: agent-monitor
+  namespace: agent-monitor
+  labels:
+    app.kubernetes.io/name: agent-monitor
+    app.kubernetes.io/instance: agent-monitor
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/component: monitoring
+    app.kubernetes.io/managed-by: kustomize
+    # Common label for Prometheus Operator discovery
+    release: prometheus
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: agent-monitor
+      app.kubernetes.io/instance: agent-monitor
+  namespaceSelector:
+    matchNames:
+      - agent-monitor
+  endpoints:
+    - port: http
+      path: /api/health
+      interval: 30s
+      scrapeTimeout: 10s
+      honorLabels: true
+      metricRelabelings:
+        - sourceLabels: [__name__]
+          regex: "(http_requests_total|http_request_duration_.*|nodejs_.*|process_.*)"
+          action: keep