ops: add production observability and recovery

This commit is contained in:
hailin
2026-07-27 19:06:34 +08:00
parent e69368a2f3
commit b02d18d3b9
33 changed files with 8832 additions and 1 deletions

View File

@@ -0,0 +1,21 @@
global:
scrape_interval: 30s
evaluation_interval: 30s
rule_files:
- /etc/prometheus/alerts.yml
alerting:
alertmanagers:
- static_configs:
- targets:
- alertmanager:9093
scrape_configs:
- job_name: ai-ticket-backend
metrics_path: /api/system/metrics
authorization:
credentials_file: /run/secrets/metrics_token
static_configs:
- targets:
- backend:8000