feat(P0/P1/P2): Add E2E agent prober, version pinning, prometheus fixes

scripts/node1/verify_agents.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+# Verify Agents Script - checks that agents are responding
+# Usage: ./verify_agents.sh
+
+set -e
+
+echo "=== AGENT E2E VERIFICATION ==="
+echo ""
+
+# 1. Check prober metrics
+echo "1. Checking prober metrics..."
+PROBER_METRICS=$(curl -s http://localhost:9108/metrics 2>/dev/null || echo "FAIL")
+if echo "$PROBER_METRICS" | grep -q "agent_e2e_success"; then
+    echo "   ✅ Prober metrics available"
+    echo "$PROBER_METRICS" | grep "agent_e2e_success" | head -3
+else
+    echo "   ❌ Prober metrics NOT available (prober may not be running)"
+fi
+
+echo ""
+
+# 2. Check Prometheus targets
+echo "2. Checking Prometheus targets..."
+PROM_TARGETS=$(curl -s http://localhost:9090/api/v1/targets 2>/dev/null || echo "FAIL")
+if echo "$PROM_TARGETS" | grep -q "prober"; then
+    echo "   ✅ Prober found in Prometheus targets"
+else
+    echo "   ⚠️ Prober not in Prometheus targets yet"
+fi
+
+echo ""
+
+# 3. Direct agent ping test
+echo "3. Testing /debug/agent_ping..."
+PING_RESULT=$(curl -s -X POST http://localhost:9300/debug/agent_ping -H "Content-Type: application/json" -d '{}' 2>/dev/null || echo '{"error":"connection failed"}')
+echo "   $PING_RESULT"
+
+echo ""
+
+# 4. Gateway health
+echo "4. Gateway health..."
+HEALTH=$(curl -s http://localhost:9300/health 2>/dev/null || echo '{"status":"error"}')
+if echo "$HEALTH" | grep -q "healthy"; then
+    echo "   ✅ Gateway healthy"
+    echo "   $HEALTH" | head -c 200
+else
+    echo "   ❌ Gateway unhealthy: $HEALTH"
+fi
+
+echo ""
+echo ""
+
+# 5. Webhook test
+echo "5. Testing webhook (Helion)..."
+WEBHOOK=$(curl -s -X POST http://localhost:9300/helion/telegram/webhook \
+    -H "Content-Type: application/json" \
+    -d '{"update_id":1}' 2>/dev/null || echo '{"error":"failed"}')
+echo "   $WEBHOOK"
+
+echo ""
+echo "=== VERIFICATION COMPLETE ==="