anderson-ufrj
feat(monitoring): configure comprehensive Prometheus alerts and Alertmanager
2395a41
raw
history blame
1.2 kB
global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
monitor: 'cidadao-ai-monitor'
rule_files:
- "rules/*.yml"
- "alerts.yml"
scrape_configs:
# Cidadão.AI Backend Application Metrics
- job_name: 'cidadao-ai-backend'
static_configs:
- targets: ['cidadao-ai:8000', 'localhost:8000']
metrics_path: /api/v1/observability/metrics
scrape_interval: 10s
scrape_timeout: 5s
# Prometheus Self-Monitoring
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
scrape_interval: 30s
# Grafana Monitoring
- job_name: 'grafana'
static_configs:
- targets: ['grafana:3000']
scrape_interval: 30s
# System Metrics via Node Exporter
- job_name: 'node-exporter'
static_configs:
- targets: ['node_exporter:9100']
scrape_interval: 15s
# Container Metrics via cAdvisor
- job_name: 'cadvisor'
static_configs:
- targets: ['cadvisor:8080']
scrape_interval: 15s
# Alternative Health Check Endpoint
- job_name: 'cidadao-ai-health'
static_configs:
- targets: ['cidadao-ai:7860']
metrics_path: /health
scrape_interval: 30s
params:
format: ['json']