Latency, cost, tokens, errors — eBPF/HTTP ingest → Redpanda → ClickHouse → Grafana.

Active See latency, cost, tokens, errors, and volume across models and agents. LensAI is the observe layer — fleet SLOs and cost attribution via ingest → warehouse → Grafana, not a replacement for your APM.

When to use

You need p50/p95/p99 and $/task by tenant, agent, and model
Finance and platform must share one cost number
You want anomaly feeds that jump to TraceForge via trace_id

Ingest path

eBPF tracer  or  HTTP/SDK events
        ↓
  streaming ingest :8080
        ↓
     Redpanda
        ↓
    ClickHouse
        ↓
  Grafana :3000   ← dashboards

Run via lensai-integration (make build && make up && make smoke). Streaming stack: infra-ai-streaming; eBPF: ebpf-llm-tracer. A suite :4000 observe query API is Design target / not shipped.

Required labels

Label	Why
`tenant_id`	Cost attribution; reject if missing
`model_id`	Model mix and SLO by revision
`trace_id`	Join spike → TraceForge waterfall
`agent_id`	Per-agent burn and errors
`env`	Keep chaos/shadow out of prod SLO

Core metrics

lensai.latency.p50/p95/p99 — inference latency (ms)
lensai.tokens.input/output — finalize streams or under-count
lensai.cost.usd / cost.per_successful_task
lensai.errors.timeout, provider_5xx, rate_limit.429s
lensai.ingest.lag_ms, cardinality.active_series

Operator failure modes

ID	Problem	Next action
L08	Missing tenant_id → unattributed cost	Reject unlabeled at ingest
L09	Token under-count on streams	Hook stream-end events
L12	HTTP 200 with empty body	Treat empty as error class
L13	429 thrash burns retry cost	Respect Retry-After; jitter
L20	Fallback to strong model spikes bill	Budget caps in RouteIQ
L23	Cannot jump spike → trace	Require trace_id on events
L01	Cardinality explosion	Drop high-churn labels; aggregate
L18	Sampling hides rare errors	Always sample errors + slow

Config today

Use Compose/Helm env in lensai-integration and infra-ai-streaming — not a suite inferix.yaml. See Configuration.

Source

https://github.com/AkshantVats/lensai-integration

LensAI