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 10:07:36.
› →|
updated 1d 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 11 endpoints

Endpoint-level X-ray over the last 3d — 497 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
2d ago
automated · 40d07ba1
Neo4j footprint
325
0.6 per request · 3 slow
owner · on-call
Sambasiva Bandarupalli
backup Ahmed Aburaed · CODEOWNERS /data-science/
Endpoint Calls ▾ Avg latency Max Err %
GET /api/v1/threads 216 71 ms 271 ms 0.0%
POST /api/v1/chat/:id/runs/stream 104 — — 0.0%
GET /api/v1/chat/:id/state 60 95 ms 710 ms 0.0%
GET /api/v1/threads/:id 41 63 ms 161 ms 0.0%
POST /api/v1/threads 29 70 ms 158 ms 0.0%
GET /api/v1/chat/:id/runs/:id/stream 20 6.33 s 2.1 min 40.0%
POST /api/v1/chat/:id/runs/:id/resume 14 24.84 s 1.3 min 0.0%
GET /api/v1/projects 10 50 ms 103 ms 0.0%
GET /api/v1/artifacts/art_95ebb5474bb8 1 73 ms 73 ms 0.0%
GET /api/v1/artifacts/art_95ebb5474bb8/html 1 63 ms 63 ms 0.0%
POST /api/v1/chat/:id/runs/:id/cancel 1 134 ms 134 ms 0.0%

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.