App Observability

# 1. Set Cloud creds + start Alloy with config from references/apm.md
export GRAFANA_CLOUD_OTLP_ENDPOINT=https://otlp-gateway-prod-us-east-0.grafana.net/otlp
export GRAFANA_CLOUD_INSTANCE_ID=123456
export GRAFANA_CLOUD_API_KEY=glc_eyJ...
alloy fmt /etc/alloy/config.alloy   # syntax check
alloy run /etc/alloy/config.alloy

# 2. Verify Alloy is receiving + forwarding
curl -s http://localhost:12345/api/v0/web/components \
  | jq '.[] | select(.id|test("otelcol\\.exporter\\.otlphttp"))
        | {id, health:.health.state}'
# Expect health.state == "healthy"
curl -s http://localhost:12345/metrics \
  | grep -E 'otelcol_(receiver_accepted_spans|exporter_sent_spans)'

# 3. Point your app at Alloy (with required attributes!)
export OTEL_SERVICE_NAME="my-api"
export OTEL_RESOURCE_ATTRIBUTES="service.namespace=myteam,deployment.environment=production"
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
export OTEL_EXPORTER_OTLP_PROTOCOL=grpc

# 4. Verify spans landed in Tempo + spanmetrics generated
#    Tempo (TraceQL):  { resource.service.name = "my-api" }
#    Mimir (PromQL):   sum by (job) (rate(traces_spanmetrics_calls_total{service_name="my-api"}[5m]))
#    Expect > 0 within ~1 minute.

# 5. Verify it's wired to App Observability
#    Grafana → Application → Service Inventory: "my-api" should appear with RED metrics
#    Click into it → Service Map edges visible (requires span.kind on outbound calls)

# 1. Install
npm install @grafana/faro-react @grafana/faro-web-tracing

// 2. initializeFaro with TracingInstrumentation + ReactIntegration (see references/faro.md)
//    Push a smoketest event so we have a known signal:
faro.api.pushEvent('faro_smoketest', { ts: Date.now().toString() });

# 3. Verify in DevTools Network — POST to /collect returns 202
#    (401 → wrong app key; 404 → wrong url region)

# 4. Verify in Grafana Cloud
#    - Frontend Observability → your app → Sessions: your session appears
#    - LogQL on Loki: {kind="event"} |= "faro_smoketest"
#    - With TracingInstrumentation: open the session → the trace ID links to Tempo

pip install openlit==1.42.0

# At app startup
import openlit
openlit.init(application_name="my-ai-app", environment="production")
# Your existing OpenAI / Anthropic / Cohere calls now emit OTel spans + metrics.

# Env (same OTLP endpoint as APM)
export OTEL_SERVICE_NAME="my-ai-app"
export OTEL_EXPORTER_OTLP_ENDPOINT="https://otlp-gateway-<region>.grafana.net/otlp"
export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Basic $(echo -n $ID:$KEY | base64)"

# Verify after a few LLM calls:
#   PromQL: sum by (gen_ai_request_model) (rate(gen_ai_usage_input_tokens_total[5m]))
#   Dashboard: Grafana → AI Observability → "GenAI Observability" auto-populates