version: 1
source: docs/reference/09-dashboards-alerts-slos.md#12-slos
slos:
  - id: observability-export
    name: Observability Export SLO
    objective: 99% of observed telemetry events are not locally dropped over 30 days.
    target: ">= 0.99"
    window: 30d
    measurement_source: Prometheus metrics emitted by ObservMe.
    indicator:
      type: promql
      expr: >-
        1 - ((sum(rate(observme_telemetry_dropped_total[30d])) or vector(0)) / clamp_min(sum(rate(observme_events_observed_total[30d])), 1e-9))
  - id: agent-lineage
    name: Agent Lineage SLO
    objective: 99% of known subagent spawns produce either propagated trace context or parent/child lineage attributes.
    target: ">= 0.99"
    window: 30d
    measurement_source: Prometheus metrics emitted by ObservMe lineage and subagent instrumentation.
    indicator:
      type: promql
      expr: >-
        clamp_min(1 - (((sum(rate(observme_subagent_spawn_failures_total[30d])) or vector(0)) + (sum(rate(observme_orphan_agents_total[30d])) or vector(0)) + (sum(rate(observme_trace_context_propagation_failures_total[30d])) or vector(0))) / clamp_min(sum(rate(observme_subagents_spawned_total[30d])), 1e-9)), 0)
  - id: workflow-completion
    name: Workflow Completion SLO
    objective: 99% of started workflows complete or explicitly fail with terminal telemetry over 30 days.
    target: ">= 0.99"
    window: 30d
    measurement_source: Prometheus workflow lifecycle counters emitted by ObservMe.
    indicator:
      type: promql
      expr: >-
        clamp_max(((sum(rate(observme_workflows_completed_total[30d])) or vector(0)) + (sum(rate(observme_workflow_errors_total[30d])) or vector(0))) / clamp_min(sum(rate(observme_workflows_started_total[30d])), 1e-9), 1)
  - id: instrumentation-overhead
    name: Instrumentation Overhead SLO
    objective: 99% of event handlers complete in under 10ms.
    target: "99% < 10ms"
    window: 30d
    measurement_source: Prometheus histogram metric observme_handler_duration_ms emitted by ObservMe handlers.
    indicator:
      type: metric
      metric: observme_handler_duration_ms
      threshold_ms: 10
      percentile: 0.99
      suggested_promql: >-
        histogram_quantile(0.99, sum(rate(observme_handler_duration_ms_bucket[30d])) by (le)) < bool 10
  - id: redaction
    name: Redaction SLO
    objective: 100% of configured secret test patterns are redacted in CI.
    target: "100%"
    measurement_source: CI redaction test corpus for configured secret patterns.
    indicator:
      type: ci_test
      ci_test_time: true
      runtime_only: false
      description: This is a test SLO, not runtime-only.