# 0. Point at your Prometheus/Mimir. For Grafana Cloud, use the metrics endpoint
#    and add basic auth (-u "<metrics_user>:<token>") to each curl below.
PROM=http://localhost:9090   # or https://prometheus-prod-XX.grafana.net/api/prom

# 1. Sketch the query — for "5xx error rate per service":
EXPR='sum(rate(http_requests_total{status_code=~"5.."}[5m])) by (service)'

# 2. Validate syntax + that the metric/labels exist
curl -sG --data-urlencode "query=${EXPR}" \
  "$PROM/api/v1/query" | jq '.status, (.data.result|length)'
# Expect: "success" and result count > 0. If 0 — check label spelling and scrape activity:
curl -sG --data-urlencode "match[]=http_requests_total" "$PROM/api/v1/series" | jq '.data | length'

# 3. Sanity-check the magnitude — open Grafana Explore, paste the expr,
#    confirm the values look right against a known ground truth (k6 run, log count, etc.)

sum(rate(http_requests_total{job="api"}[5m])) by (status_code)

histogram_quantile(0.95,
  sum(rate(http_request_duration_seconds_bucket[5m])) by (le, service))

sum(rate(http_requests_total{status_code=~"5.."}[5m]))
  / (sum(rate(http_requests_total[5m])) > 0)

# 1. Pick the slow expression, give it a recording-rule name
groups:
  - name: http_request_rates
    interval: 1m
    rules:
      - record: job:http_request_duration_p95:rate5m
        expr: |
          histogram_quantile(0.95,
            sum(rate(http_request_duration_seconds_bucket[5m])) by (le, job))

# 2. After rules load, verify the new metric exists
curl -sG --data-urlencode "query=job:http_request_duration_p95:rate5m" \
  "$PROM/api/v1/query" | jq '.data.result | length'   # → > 0

# 3. Verify it matches the original expression for at least one sample window
# (Both queries should produce the same value at the same timestamp.)

# 4. Replace the dashboard panel expression with the recording-rule metric.