Cluster Health Status #4750

	name: Cluster Health Status
	on:
	schedule:
	- cron: '0 * * * *'
	push:
	paths:
	- .github/workflows/*
	workflow_dispatch:
	jobs:
	health-check:
	name: Monitor Cluster Endpoints
	runs-on: ubuntu-latest
	steps:
	- name: Check endpoints
	run: \|
	ENDPOINTS="${{ secrets.CLUSTER_ENDPOINTS }}"

	# Validate input
	if [[ -z "$ENDPOINTS" ]]; then
	echo "❌ No endpoints found in CLUSTER_ENDPOINTS secret"
	exit 1
	fi

	# Initialize counters
	total=0
	failed=0

	# Function to check endpoint with retries
	check_endpoint() {
	local url="$1"
	local max_attempts=3
	local attempt=1

	while [[ $attempt -le $max_attempts ]]; do
	if [[ $attempt -gt 1 ]]; then
	echo " Retry $((attempt - 1))/$((max_attempts - 1))..."
	sleep 2 # Wait 2 seconds between retries
	fi

	if curl -sfLI --max-time 10 "$url" >/dev/null 2>&1; then
	if [[ $attempt -gt 1 ]]; then
	echo "✅ OK (succeeded on attempt $attempt)"
	else
	echo "✅ OK"
	fi
	return 0
	fi

	attempt=$((attempt + 1))
	done

	echo "❌ FAILED (all $max_attempts attempts failed)"
	return 1
	}

	# Process each endpoint
	while IFS= read -r url; do
	# Skip empty lines and comments
	[[ -z "$url" \|\| "$url" =~ ^[[:space:]]*# ]] && continue
	url=$(echo "$url" \| xargs)
	[[ -z "$url" ]] && continue

	total=$((total + 1))
	echo "Testing: $url"

	if ! check_endpoint "$url"; then
	failed=$((failed + 1))
	fi
	echo ""

	done <<< "$ENDPOINTS"

	# Summary
	echo "📊 Summary: $((total - failed))/$total endpoints OK"

	# Exit with error if any failed
	if [[ $failed -gt 0 ]]; then
	echo "💥 $failed endpoint(s) failed!"
	exit 1
	else
	echo "🎉 All endpoints healthy!"
	fi

Provide feedback