Add staffing timing to the integration harness and commit the verified run: small train 171ms, forecast train 3.6s, SSE propagation 15ms, 120/120 clients for 300s with 0 drops and p95 5.6ms, 20 heartbeats at 15s, FastAPI-down fallback from the snapshot, and recovery in 1.6s.
20 lines
564 B
JSON
20 lines
564 B
JSON
{
|
|
"fastapi_down": {
|
|
"cache_failures": 1,
|
|
"last_error": "ml: /bootstrap: Get \"http://127.0.0.1:18000/bootstrap\": dial tcp 127.0.0.1:18000: connect: connection refused",
|
|
"next_retry_at": "2026-11-14T05:34:31Z",
|
|
"last_success_at": "2026-11-14T05:34:20Z",
|
|
"forecast_cached": true,
|
|
"staffing_cached": true,
|
|
"readyz": 200,
|
|
"sensors": 8
|
|
},
|
|
"recovery": {
|
|
"after_ms": 1622,
|
|
"last_success_before": "2026-11-14T05:34:20Z",
|
|
"last_success_after": "2026-11-14T05:34:33Z",
|
|
"forecast_cached": false,
|
|
"failures": 0
|
|
}
|
|
}
|