dograh/deploy/helm/dograh/examples/values-k3s-prod.yaml

# Dograh — production values for k3s
# Hosted-AI only (no local models). All state on the node's local disk via
# k3s local-path StorageClass. TLS terminated at Cloudflare edge; re-encrypted
# to origin using the shared *.yourdomain.com Cloudflare Origin CA cert
# (secret `cloudflare-origin-tls`, copied from a neighboring namespace).
#
# HPA is enabled for web / workers / ui with min=1, max=5. Requires
# metrics-server in the cluster (k3s ships it by default).

image:
  tag: latest              # pin to a released tag once stable

# --- Bundled stateful deps (in-cluster, on local-path PVCs) -----------------
database: { mode: internal }
redis:    { mode: internal }
storage:  { mode: internalMinio }

# --- HTTP exposure ----------------------------------------------------------
exposure:
  mode: ingress
  ingress:
    className: traefik
    host: aicalling.yourdomain.com
    tls:
      enabled: true
      secretName: cloudflare-origin-tls

# --- Runtime config (rendered into the ConfigMap) --------------------------
config:
  environment: production
  logLevel: INFO
  backendApiEndpoint: https://aicalling.yourdomain.com   # kills the CF-tunnel fallback
  minioPublicEndpoint: https://aicalling.yourdomain.com  # browser fetches /voice-audio/ via Traefik
  enableSignup: false   # invite-only: 403 the public signup endpoint

# --- Workloads not needed for hosted-AI web-only calls ---------------------
ariManager:           { enabled: false }   # Asterisk SIP singleton
campaignOrchestrator: { enabled: false }   # scheduled outbound singleton
coturn:               { enabled: false }   # TURN relay

# --- Web tier (FastAPI + WebSocket signaling) ------------------------------
web:
  replicaCount: 1
  resources:
    requests: { cpu: 100m, memory: 384Mi }
    limits:   { cpu: "1",  memory: 1Gi }
  pdb: { enabled: false }

# --- ARQ background workers ------------------------------------------------
workers:
  replicaCount: 1
  resources:
    requests: { cpu: 50m,  memory: 128Mi }
    limits:   { cpu: 500m, memory: 512Mi }

# --- Next.js UI ------------------------------------------------------------
ui:
  replicaCount: 1
  resources:
    requests: { cpu: 50m,  memory: 256Mi }
    limits:   { cpu: 500m, memory: 512Mi }
  pdb: { enabled: false }

# --- Alembic migration Job (post-install / pre-upgrade hook) ---------------
# CPU request kept low so it schedules on a tight node; migrations are
# short-lived and don't need much headroom.
migrate:
  resources:
    requests: { cpu: 20m,  memory: 256Mi }
    limits:   { cpu: 500m, memory: 512Mi }

# --- HPA: 1 → 5 on CPU 70% only (memory HPA opt-in — see comments) ---------
# The chart ships all autoscaling blocks disabled; this file opts in for all
# three tiers. NOTE: CPU is a poor scale signal for the web tier (long-lived
# WebSockets don't move CPU much) and a coarse one for the IO-bound ARQ
# workers — see the autoscaling notes in values.yaml. Fine starting point for
# a single node; minReplicas=1 is why the web/ui PDBs are disabled above.
autoscaling:
  web:
    enabled: true
    minReplicas: 1
    maxReplicas: 5
    targetCPUUtilizationPercentage: 70
    targetMemoryUtilizationPercentage: null   # idle FastAPI already close to request; CPU HPA is enough
  workers:
    enabled: true
    minReplicas: 1
    maxReplicas: 5
    targetCPUUtilizationPercentage: 70
    targetMemoryUtilizationPercentage: null   # idle Python (ARQ) sits near the memory request; CPU HPA is enough
  ui:
    enabled: true
    minReplicas: 1
    maxReplicas: 5
    targetCPUUtilizationPercentage: 70
    targetMemoryUtilizationPercentage: null   # idle Node.js (Next.js SSR) sits near the memory request; CPU HPA is enough

# --- Internal Postgres (pgvector/pg17) -------------------------------------
postgresql:
  persistence: { size: 5Gi, storageClass: local-path }
  resources:
    requests: { cpu: 100m, memory: 256Mi }
    limits:   { cpu: "1",  memory: 1Gi }

# --- Internal Redis --------------------------------------------------------
redisinternal:
  persistence: { size: 1Gi, storageClass: local-path }
  resources:
    requests: { cpu: 50m,  memory: 64Mi }
    limits:   { cpu: 300m, memory: 256Mi }

# --- Internal MinIO (audio + artifacts on node disk) -----------------------
minio:
  persistence: { size: 10Gi, storageClass: local-path }
  resources:
    requests: { cpu: 50m,  memory: 128Mi }
    limits:   { cpu: 500m, memory: 512Mi }