# story-crater-backend.descriptor.yaml
# Build input for generating svc-story-crater-backend.yaml dashboard ConfigMap
# and svc-story-crater-backend-rules.yaml PrometheusRule.
# NOT applied to cluster — this is a reference for Claude's mechanical dashboard generation.

service: story-crater-backend
display_name: "Story Crater Backend"
namespace: story-crater-backend
service_type: message-worker
folder: "Story Crater Backend"

jobs:
  - agent-worker
  - check
  - edit-collab
  - canary

metrics:
  prefix: story_crater
  up_selector: 'job=~"agent-worker|check|edit-collab|canary"'

  rate:
    metric: story_crater_messages_handled_total
    labels: [agent, queue, status]  # status: succeeded | failed

  duration:
    metric: story_crater_message_handle_duration_ms
    type: histogram
    unit: ms

  error:
    metric: story_crater_app_metric_total
    filter: 'severity="error"'

  domain:
    - metric: story_crater_queue_depth
      kind: gauge
      group_by: [queue]
    - metric: story_crater_dedup_redeliveries_total
      kind: counter
      group_by: [agent, queue]
    - metric: story_crater_outbox_publish_lag_ms
      kind: histogram
    - metric: story_crater_llm_tokens_used_total
      kind: counter
      group_by: [agent, kind]
    - metric: story_crater_llm_call_duration_seconds
      kind: histogram
      group_by: [agent, model_provider]
    - metric: story_crater_check_latency_ms
      kind: histogram
      slo_ms: 1200
    - metric: story_crater_degrade_state
      kind: gauge
      group_by: [service]

correlation_ids: [session_id, trace_id, tenant]

logs:
  loki_namespace_selector: 'namespace="story-crater-backend"'

alerts:
  - name: HighErrorRate
    expr_template: rate_error_ratio
    threshold: 0.05
    for: 10m
    severity: warning
  - name: CheckLatencySLOBreach
    expr_template: histogram_quantile_over_threshold
    metric: story_crater_check_latency_ms
    quantile: 0.95
    threshold: 1200
    for: 10m
    severity: critical