Files
box/jobs/box-service-health.json
T

21 lines
1.0 KiB
JSON
Raw Normal View History

{
"agent": "646",
"chain_next": null,
"description": "Box service + data health — every 15 minutes (offset 7m)",
"followup": {
"escalate": "opm",
"expect_reply": true,
"nudges": 2,
"route": "box-health",
"timeout": "30m"
},
"name": "box-service-health",
"on_failure": "alert",
"prompt_template": "Box service health check.\nJob ID: {job_id}\nTime: {datetime}\n\nRun the Box service and data checks on the VM:\n ssh dev-operator-646@34.139.37.135 \"/srv/box/bin/box-health-check.sh services\"\n ssh dev-operator-646@34.139.37.135 \"/srv/box/bin/box-health-check.sh data\"\n(or run /srv/box/bin/box-health-check.sh via any VM access you have)\n\nExpected: board.service active, caddy active, sweeper timer firing,\n/srv/box writable. If any FAIL, investigate and include failure lines.\n\nReply with [RESULT {job_id}] OK or [RESULT {job_id}] FAIL <one-line summary>.",
"schedule": "7,22,37,52 * * * *",
"sidechat": {
"create": true,
"name_template": "box-service-health-{datetime}"
},
"timeout": 600
}