nntrivi2001
57dc91585d
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.
118 lines
2.8 KiB
YAML
118 lines
2.8 KiB
YAML
# =============================================================================
|
|
# 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
|