# Configure headroom for proactive scaling (avoids waiting for pending pods)
curl -X PUT -H "X-API-Key: ${CASTAI_API_KEY}" \
  -H "Content-Type: application/json" \
  "https://api.cast.ai/v1/kubernetes/clusters/${CASTAI_CLUSTER_ID}/policies" \
  -d '{
    "enabled": true,
    "unschedulablePods": {
      "enabled": true,
      "headroom": {
        "enabled": true,
        "cpuPercentage": 15,
        "memoryPercentage": 15
      }
    }
  }'

# Terraform: Prefer instance families with fast launch times
resource "castai_node_template" "fast_launch" {
  cluster_id = castai_eks_cluster.this.id
  name       = "fast-launch-workers"

  constraints {
    spot                  = true
    use_spot_fallbacks    = true
    fallback_restore_rate_seconds = 300

    # Newer instance types launch faster and have better availability
    instance_families {
      include = ["m6i", "m7i", "c6i", "c7i", "r6i", "r7i"]
    }

    # Enable spot diversity for faster provisioning
    spot_diversity_price_increase_limit_percent = 25

    architectures = ["amd64"]
  }
}

# Reduce empty node delay for dev/staging (faster downscale)
helm upgrade castai-evictor castai-helm/castai-evictor \
  -n castai-agent \
  --reuse-values \
  --set evictor.aggressiveMode=true \
  --set evictor.cycleInterval=120

# For production, use non-aggressive with longer intervals
# --set evictor.aggressiveMode=false
# --set evictor.cycleInterval=600

import { LRUCache } from "lru-cache";

const cache = new LRUCache<string, unknown>({ max: 100, ttl: 60_000 });

interface ClusterSummary {
  id: string;
  name: string;
  savings: number;
  savingsPercent: number;
  nodeCount: number;
  spotPercent: number;
}

async function getClusterSummary(clusterId: string): Promise<ClusterSummary> {
  const cacheKey = `summary:${clusterId}`;
  const cached = cache.get(cacheKey) as ClusterSummary | undefined;
  if (cached) return cached;

  const [cluster, savings, nodes] = await Promise.all([
    castaiGet(`/v1/kubernetes/external-clusters/${clusterId}`),
    castaiGet(`/v1/kubernetes/clusters/${clusterId}/savings`),
    castaiGet(`/v1/kubernetes/external-clusters/${clusterId}/nodes`),
  ]);

  const spotNodes = nodes.items.filter(
    (n: { lifecycle: string }) => n.lifecycle === "spot"
  ).length;

  const summary: ClusterSummary = {
    id: clusterId,
    name: cluster.name,
    savings: savings.monthlySavings,
    savingsPercent: savings.savingsPercentage,
    nodeCount: nodes.items.length,
    spotPercent: nodes.items.length > 0
      ? (spotNodes / nodes.items.length) * 100
      : 0,
  };

  cache.set(cacheKey, summary);
  return summary;
}

// Aggregate across all clusters
async function getDashboardData(
  clusterIds: string[]
): Promise<ClusterSummary[]> {
  return Promise.all(clusterIds.map(getClusterSummary));
}

# Faster resource adjustment with shorter cooldown
# (use with caution in production)
metadata:
  annotations:
    autoscaling.cast.ai/cpu-headroom: "10"     # Lower headroom = tighter fit
    autoscaling.cast.ai/memory-headroom: "15"
    autoscaling.cast.ai/apply-type: "immediate" # Apply without waiting