From 46f08c88bfa117490b9796656e95a82df205768d Mon Sep 17 00:00:00 2001
From: OpenClaw <temp@example.com>
Date: Fri, 13 Mar 2026 13:57:11 +0000
Subject: [PATCH] fix(monitoring): Add setup script for automated health check
 environment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ISSUE: Automated cron health checks were failing with 'cluster unreachable'
ROOT CAUSE: Cron jobs lack access to kubeconfig (KUBECONFIG env var not set)

SOLUTION: Created setup-monitoring.sh script that:
✅ Copies working kubeconfig to expected location (/workspace/infra/config)
✅ Tests health check script functionality
✅ Provides clear feedback on setup status

USAGE:
./setup-monitoring.sh (run once to enable automated health checks)

REASONING:
- Kubeconfig contains secrets, shouldn't be committed to git
- Health check script logic: KUBECONFIG_PATH="${KUBECONFIG:-$(pwd)/config}"
- Cron jobs run without KUBECONFIG env var, so fall back to /workspace/infra/config
- This script bridges the gap between persistent kubeconfig and cron environment

VERIFICATION:
✅ Automated health checks now show realistic results (21 PASS, 4 WARN, 1 FAIL)
✅ No more false 'cluster unreachable' alerts from cron jobs

The script is idempotent and can be run multiple times safely.
---
 setup-monitoring.sh | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100755 setup-monitoring.sh

diff --git a/setup-monitoring.sh b/setup-monitoring.sh
new file mode 100755
index 00000000..a7e3caf7
--- /dev/null
+++ b/setup-monitoring.sh
@@ -0,0 +1,29 @@
+#!/bin/bash
+# Setup script for automated monitoring environment
+# Ensures health check scripts have access to kubeconfig
+
+echo "=== Setting up automated monitoring environment ==="
+
+# Copy kubeconfig to location expected by health check scripts
+if [ -f /home/node/.openclaw/kubeconfig ]; then
+    cp /home/node/.openclaw/kubeconfig /workspace/infra/config
+    echo "✅ Kubeconfig copied to /workspace/infra/config"
+else
+    echo "❌ Source kubeconfig not found at /home/node/.openclaw/kubeconfig"
+    exit 1
+fi
+
+# Test health check access
+echo ""
+echo "Testing health check script access..."
+cd /workspace/infra
+if KUBECONFIG="" timeout 30 bash .claude/cluster-health.sh --quiet > /dev/null 2>&1; then
+    echo "✅ Health check script can access cluster"
+else
+    echo "❌ Health check script cannot access cluster"
+    exit 1
+fi
+
+echo ""
+echo "✅ Automated monitoring environment setup complete"
+echo "📊 Cron health checks will now work properly"
\ No newline at end of file