Get trace health summary

Get project check status and per-check failure rates among evaluated traces. Health checks use time-based sampling; counts and rates do not cover all ingested traces, and status is no_data when no traces were evaluated in the range. Read sampling_interval_seconds for the configured cooldown. Get results for a time range of at most 31 days, by default the last 24 hours. Each call checks one category: trace_health (default) for instrumentation health or conversation_view for Conversation View compatibility.

GET/v1/projects/{projectId}/trace-health/summary

Authorization

AuthorizationPersonal API key · headerrequired

Your personal API key from Settings > Personal API Keys, sent as Bearer <key>.

X-Organization-IdOrganization ID · headerrequired

The organization to act in. Copy it with Copy organization ID in the organization menu or the settings sidebar.

Path parameters

projectIdstringrequired

Query parameters

categorystring

Choose instrumentation health or Conversation View compatibility checks

default: "trace_health"

Allowed:trace_healthconversation_view

start_timestring<date-time>

Inclusive ISO 8601 start timestamp with UTC offset; defaults to 24 hours before end_time

end_timestring<date-time>

Exclusive ISO 8601 end timestamp with UTC offset; defaults to now

Responses

200

Response for status 200

summaryobjectrequired

Show properties

start_timestringrequired

end_timestringrequired

sampling_interval_secondsnumberrequired

Minimum cooldown between newly selected traces per project. Selected traces can be rechecked; reconciliation can also evaluate never-finalized traces.

statusstringrequired

Health among evaluated traces, excluding muted checks. Healthy does not prove all ingested traces were evaluated. no_data means no traces were checked in this time range; then latest_trace_at is the project's newest trace start, null if none

Allowed:healthyunhealthyno_data

latest_trace_atstring | null

checksobject[]required

Show properties

Array of object

check_idstringrequired

is_mutedbooleanrequired

Muted checks do not affect project health

check_versionnumberrequired

scopestringrequired

Allowed:tracespan

labelstringrequired

failure_labelstringrequired

descriptionstringrequired

remediationstringrequired

applicabilitystringrequired

impact_reasonsobjectrequired

Show properties

conversation viewstring

evalsstring

trace structure for eval contextstring

cost trackingstring

evaluated_trace_countnumberrequired

Evaluated traces, not total ingested traces.

applicable_trace_countnumberrequired

Evaluated traces to which this check applies.

affected_trace_countnumberrequired

Known failing evaluated traces, not an exhaustive count across all ingested traces.

failure_ratenumber | nullrequired

Failure rate among applicable evaluated traces, not a population estimate.

Try it

Server

Base URLCustom base URLOverrides the selected server when set.

Authorization

Personal API keyOrganization IDRemember on this deviceInclude my values in samples

Parameters

projectIdpath*categoryqueryChoose instrumentation health or Conversation View compatibility checksstart_timequeryInclusive ISO 8601 start timestamp with UTC offset; defaults to 24 hours before end_timeend_timequeryExclusive ISO 8601 end timestamp with UTC offset; defaults to now

Request

curl -X GET 'https://api.judgmentlabs.ai/v1/projects/YOUR_PROJECT_ID/trace-health/summary' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'X-Organization-Id: YOUR_ORGANIZATION_ID' \
  -H 'Accept: application/json'

const response = await fetch("https://api.judgmentlabs.ai/v1/projects/YOUR_PROJECT_ID/trace-health/summary", {
  method: "GET",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "X-Organization-Id": "YOUR_ORGANIZATION_ID",
    "Accept": "application/json"
  }
});

import requests

response = requests.get(
    "https://api.judgmentlabs.ai/v1/projects/YOUR_PROJECT_ID/trace-health/summary",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "X-Organization-Id": "YOUR_ORGANIZATION_ID",
        "Accept": "application/json"
    },
)

Response

{
  "summary": {
    "start_time": "string",
    "end_time": "string",
    "sampling_interval_seconds": 0,
    "status": "healthy",
    "latest_trace_at": "string",
    "checks": [
      {
        "check_id": "string",
        "is_muted": true,
        "check_version": 0,
        "scope": "trace",
        "label": "string",
        "failure_label": "string",
        "description": "string",
        "remediation": "string",
        "applicability": "string",
        "impact_reasons": {
          "conversation view": "string",
          "evals": "string",
          "trace structure for eval context": "string",
          "cost tracking": "string"
        },
        "evaluated_trace_count": 0,
        "applicable_trace_count": 0,
        "affected_trace_count": 0,
        "failure_rate": 0
      }
    ]
  }
}