Sedata.AI Docs

The package exposes one knob for trace sampling: samplingRate. It maps directly to OpenTelemetry’s TraceIdRatioBasedSampler.

How it works

TraceIdRatioBasedSampler(rate) keeps a deterministic fraction of traces by hashing the trace id. Same trace → same decision across services, which keeps distributed traces consistent.

Rate	Kept
`1.0`	100% (default)
`0.5`	~50%
`0.1`	~10%
`0.01`	~1%
`0`	none (sampler off)

Setting it

const config: TelemetryConfig = {
  serverName: 'my-server',
  serverVersion: '1.0.0',
  exporterEndpoint: 'https://otel.sedata-ai.tech/v1',
  samplingRate: 0.1, // keep 10%
}

ConfigValidator rejects anything outside [0, 1]:

Error: samplingRate must be between 0 and 1

What gets sampled

Signal	Sampled by `samplingRate`?
Spans (traces)	✅
Metrics	❌ — metrics are aggregations, sampling doesn’t apply
Safety-check API calls	❌ — every call to a `safetyCheck`-wrapped handler hits the API

If you need to reduce safety-check load, you have to gate the wrapper itself (e.g. only wrap a few high-risk tools).

Recommended starting points

Local dev

samplingRate: 1.0 — see everything.

Staging

samplingRate: 1.0 — keep volume comparable to prod’s signal-to-noise.

Production

samplingRate: 0.1–0.25 — adjust by tool volume and storage budget.

Tail sampling instead?

samplingRate is head-based — the decision is made when the trace starts. If you want to keep all errored traces while dropping most successes, you’ll want tail sampling, which lives in an OpenTelemetry Collector, not the SDK. Point exporterEndpoint at a collector with the tail_sampling processor configured.

otel-collector.yaml

processors:
  tail_sampling:
    decision_wait: 5s
    policies:
      - name: errors
        type: status_code
        status_code: { status_codes: [ERROR] }
      - name: slow
        type: latency
        latency: { threshold_ms: 500 }
      - name: sample-rest
        type: probabilistic
        probabilistic: { sampling_percentage: 5 }

Then run @sedata-ai/mcp with samplingRate: 1.0 so the collector receives everything and makes the call.

Disabling tracing entirely

If you want metrics-only:

const config: TelemetryConfig = {
  // ...
  enableTracing: false,
}

This skips the trace exporter and sampler — no span allocations at all.

Telemetry pipeline

Where samplers fit in the broader export path.

Production deployment

Pre-flight checklist for prod.

Get started

Concepts

Guides

Metrics & traces

Examples

Help

Sampling

How it works

Setting it

What gets sampled

Recommended starting points

Local dev

Staging

Production

Tail sampling instead?

Disabling tracing entirely

Next

Telemetry pipeline

Production deployment

​How it works

​Setting it

​What gets sampled

​Recommended starting points

Local dev

Staging

Production

​Tail sampling instead?

​Disabling tracing entirely

​Next

Telemetry pipeline

Production deployment

How it works

Setting it

What gets sampled

Recommended starting points

Tail sampling instead?

Disabling tracing entirely

Next