Incidents
Operational issues across the farm, grouped by severity. Serving problems always outrank everything else.
Open
1
awaiting triage
Investigating
1
operator assigned
Resolved · 7d
1
fix verified and closed
Areas affected
2
serving · ingestion · billing · crawlers
high severity1 incident
I3servingresolved
p95 render time for /f/* exceeded 400ms budget (peaked 612ms)
Opened 4d ago
medium severity1 incident
I1crawlersinvestigating
Amazonbot hits failing IP verification since 14.08
Opened 3d ago
low severity1 incident
I2ingestionopen
insurance-partners.pdf stuck in 'uploaded' — parser queue depth 1
Opened 12h ago
Status flow: open → investigating → resolved. Resolved incidents stay listed for seven days for audit before archival.