← all services
chat-agent 8 endpoints
Endpoint-level X-ray over the last 48h — 246 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
1d ago
automated ·
40d07ba1Neo4j footprint
143
0.6 per request · 2 slow
owner · on-call
Sambasiva Bandarupalli
backup Ahmed Aburaed · CODEOWNERS /data-science/
| Endpoint | Calls ▾ | Avg latency | Max | Err % |
|---|---|---|---|---|
| GET /api/v1/threads | 105 | 67 ms | 271 ms | 0.0% |
| POST /api/v1/chat/:id/runs/stream | 67 | — | — | 0.0% |
| GET /api/v1/chat/:id/state | 25 | 95 ms | 310 ms | 0.0% |
| POST /api/v1/threads | 16 | 67 ms | 82 ms | 0.0% |
| POST /api/v1/chat/:id/runs/:id/resume | 13 | 26.04 s | 1.3 min | 0.0% |
| GET /api/v1/threads/:id | 12 | 46 ms | 112 ms | 0.0% |
| GET /api/v1/chat/:id/runs/:id/stream | 6 | 86 ms | 116 ms | 16.7% |
| GET /api/v1/projects | 2 | 46 ms | 51 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.