Xray
hourly rollups 1h 6h 24h 48h 3d 5d 7d 14d 30d ‹
Last 3 days▾
Ends now. Anything up to this cluster's 30-day retention.
Start and end times
Cancel
Interpreted in UTC (change it at the right of this bar). Earliest available: 2026-10-20 12:23:06.
› →|
updated 2d ago
Sample data. This database was generated by scripts/seed_dev_db.py — every service, deploy, person and figure on this page is synthetic. Names are sample.*@seed.invalid and image tags are prefixed SEED-. Nothing here happened.
← all services

chat-agent 6 endpoints

Endpoint-level X-ray over the last 3d — 137 API calls. Endpoints are derived from the request logs and templatized (:id). Click one for its Neo4j fan-out, traces, and logs (fetched live).
See the raw calls: all API calls · failing (5xx) →
What it costs: its bill · namespace tilda · requests vs use · its LLM calls · AI spend by org

error budget
healthy
99.90% derived · 0.0× burn
p95 vs normal
—
no baseline yet
last deploy
—
no ArgoCD sync recorded
Neo4j footprint
229
1.1 per request · 4 slow
owner · on-call
Sambasiva Bandarupalli
backup Ahmed Aburaed · CODEOWNERS /data-science/
Endpoint Calls ▾ Avg latency Max Err %
POST /api/v1/chat/:id/runs/stream 51 — — 0.0%
POST /api/v1/chat/:id/runs/:id/resume 31 7.46 s 39.43 s 0.0%
POST /api/v1/threads 29 165 ms 2.62 s 0.0%
GET /api/v1/threads 17 144 ms 401 ms 0.0%
GET /api/v1/chat/:id/state 8 136 ms 328 ms 0.0%
POST /api/v1/chat/:id/runs/:id/cancel 1 102 ms 102 ms 100.0%

Per-endpoint Neo4j fan-out (and N+1 detection) is one click away on each endpoint's Queries tab — fetched live by sampling that endpoint's recent traces.