a46a70c014
- docker-compose.node1.yml: Add network aliases (router, gateway,
memory-service, qdrant, nats, neo4j) to eliminate manual
`docker network connect --alias` commands
- docker-compose.node1.yml: ROUTER_URL now uses env variable with
fallback: ${ROUTER_URL:-http://router:8000}
- docker-compose.node1.yml: Increase router healthcheck start_period
to 30s and retries to 5
- .gitignore: Add noda1-credentials.local.mdc (local-only SSH creds)
- scripts/node1/verify_agents.sh: Improved output with agent list
- docs: Add NODA1-AGENT-VERIFICATION.md, NODA1-AGENT-ARCHITECTURE.md,
NODA1-VERIFICATION-REPORT-2026-02-03.md
- config/README.md: How to add new agents
- .cursor/rules/, .cursor/skills/: NODA1 operations skill for Cursor
Root cause fixed: Gateway could not resolve 'router' DNS name when
Router container was named 'dagi-staging-router' without alias.
Co-authored-by: Cursor <cursoragent@cursor.com>
70 lines
2.3 KiB
Bash
70 lines
2.3 KiB
Bash
#!/bin/bash
|
||
# Verify Agents Script - checks that agents are responding
|
||
# Usage: ./verify_agents.sh
|
||
|
||
set -e
|
||
|
||
echo "=== AGENT E2E VERIFICATION ==="
|
||
echo ""
|
||
|
||
# 1. Check prober metrics
|
||
echo "1. Checking prober metrics..."
|
||
PROBER_METRICS=$(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 " $PING_RESULT"
|
||
|
||
echo ""
|
||
|
||
# 4. Gateway health та список агентів
|
||
echo "4. Gateway health та агенти..."
|
||
HEALTH=$(curl -s http://localhost:9300/health 2>/dev/null || echo '{"status":"error"}')
|
||
if echo "$HEALTH" | grep -q "healthy"; then
|
||
echo " ✅ Gateway healthy"
|
||
AGENTS_COUNT=$(echo "$HEALTH" | grep -o '"agents_count":[0-9]*' | cut -d: -f2)
|
||
echo " Агентів у реєстрі: ${AGENTS_COUNT:-?}"
|
||
if command -v jq >/dev/null 2>&1; then
|
||
echo " Агенти (prompt | telegram token):"
|
||
echo "$HEALTH" | jq -r '.agents | to_entries[] | " - \(.key): prompt=\(.value.prompt_loaded) token=\(.value.telegram_token_configured)"' 2>/dev/null || echo "$HEALTH" | head -c 400
|
||
else
|
||
echo " (встановіть jq для детального виводу: .agents)"
|
||
echo "$HEALTH" | head -c 400
|
||
fi
|
||
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 ==="
|