4914: adding support for prom rules

docs/resources/asserts_prom_rule_file.md

@@ -0,0 +1,314 @@
+---
+# generated by https://github.com/hashicorp/terraform-plugin-docs
+page_title: "grafana_asserts_prom_rule_file Resource - terraform-provider-grafana"
+subcategory: "Knowledge Graph"
+description: |-
+  Manages Prometheus Rules configurations through Grafana Asserts API. Allows creation and management of custom Prometheus recording and alerting rules.
+---
+
+# grafana_asserts_prom_rule_file (Resource)
+
+Manages Prometheus Rules configurations through Grafana Asserts API. Allows creation and management of custom Prometheus recording and alerting rules.
+
+## Example Usage
+
+```terraform
+# Basic recording rule for latency metrics
+resource "grafana_asserts_prom_rule_file" "latency_metrics" {
+  name   = "custom-latency-metrics"
+  active = true
+
+  group {
+    name     = "latency_recording_rules"
+    interval = "30s"
+
+    rule {
+      record = "custom:latency:p95"
+      expr   = "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))"
+      labels = {
+        source   = "custom_instrumentation"
+        severity = "info"
+      }
+    }
+
+    rule {
+      record = "custom:latency:p99"
+      expr   = "histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m]))"
+      labels = {
+        source   = "custom_instrumentation"
+        severity = "info"
+      }
+    }
+  }
+}
+
+# Alert rules for high latency
+resource "grafana_asserts_prom_rule_file" "latency_alerts" {
+  name   = "custom-latency-alerts"
+  active = true
+
+  group {
+    name     = "latency_alerting"
+    interval = "30s"
+
+    rule {
+      alert    = "HighLatency"
+      expr     = "histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m])) > 0.5"
+      duration = "5m"
+      labels = {
+        severity = "warning"
+        category = "Latency"
+      }
+      annotations = {
+        summary     = "High latency detected"
+        description = "P99 latency is above 500ms for 5 minutes"
+      }
+    }
+
+    rule {
+      alert    = "VeryHighLatency"
+      expr     = "histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m])) > 1.0"
+      duration = "2m"
+      labels = {
+        severity = "critical"
+        category = "Latency"
+      }
+      annotations = {
+        summary     = "Very high latency detected"
+        description = "P99 latency is above 1 second"
+      }
+    }
+  }
+}
+
+# Comprehensive monitoring rules with multiple groups
+resource "grafana_asserts_prom_rule_file" "comprehensive_monitoring" {
+  name   = "custom-comprehensive-monitoring"
+  active = true
+
+  # Latency monitoring
+  group {
+    name     = "latency_monitoring"
+    interval = "30s"
+
+    rule {
+      record = "custom:latency:p99"
+      expr   = "histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m]))"
+      labels = {
+        source = "custom"
+      }
+    }
+
+    rule {
+      alert    = "HighLatency"
+      expr     = "custom:latency:p99 > 0.5"
+      duration = "5m"
+      labels = {
+        severity = "warning"
+      }
+      annotations = {
+        summary = "High latency detected"
+      }
+    }
+  }
+
+  # Error rate monitoring
+  group {
+    name     = "error_monitoring"
+    interval = "1m"
+
+    rule {
+      record = "custom:error:rate"
+      expr   = "rate(http_requests_total{status=~\"5..\"}[5m])"
+      labels = {
+        source = "custom"
+      }
+    }
+
+    rule {
+      alert    = "HighErrorRate"
+      expr     = "custom:error:rate > 0.1"
+      duration = "10m"
+      labels = {
+        severity = "critical"
+        category = "Errors"
+      }
+      annotations = {
+        summary     = "High error rate detected"
+        description = "Error rate is above 10%"
+      }
+    }
+  }
+
+  # Throughput monitoring
+  group {
+    name     = "throughput_monitoring"
+    interval = "1m"
+
+    rule {
+      record = "custom:throughput:total"
+      expr   = "sum(rate(http_requests_total[5m]))"
+      labels = {
+        source = "custom"
+      }
+    }
+
+    rule {
+      alert    = "LowThroughput"
+      expr     = "custom:throughput:total < 10"
+      duration = "5m"
+      labels = {
+        severity = "warning"
+        category = "Throughput"
+      }
+      annotations = {
+        summary     = "Low throughput detected"
+        description = "Request throughput is below 10 requests/second"
+      }
+    }
+  }
+}
+
+# Rules with conditional enablement
+resource "grafana_asserts_prom_rule_file" "conditional_rules" {
+  name   = "custom-conditional-rules"
+  active = true
+
+  group {
+    name     = "environment_specific_rules"
+    interval = "30s"
+
+    rule {
+      alert    = "TestAlert"
+      expr     = "up == 0"
+      duration = "1m"
+      labels = {
+        severity = "info"
+      }
+      annotations = {
+        summary = "Test alert that is disabled in production"
+      }
+      # This rule will be disabled in the production group
+      disable_in_groups = ["production"]
+    }
+
+    rule {
+      alert    = "CriticalAlert"
+      expr     = "up == 0"
+      duration = "30s"
+      labels = {
+        severity = "critical"
+      }
+      annotations = {
+        summary = "Critical alert that fires in all environments"
+      }
+    }
+  }
+}
+
+# Inactive rules (for staging/testing)
+resource "grafana_asserts_prom_rule_file" "staging_rules" {
+  name   = "custom-staging-rules"
+  active = false # Rules file is inactive
+
+  group {
+    name     = "staging_tests"
+    interval = "1m"
+
+    rule {
+      record = "staging:test:metric"
+      expr   = "up"
+      labels = {
+        environment = "staging"
+      }
+    }
+  }
+}
+
+# SLO-based alerting
+resource "grafana_asserts_prom_rule_file" "slo_alerts" {
+  name   = "custom-slo-alerts"
+  active = true
+
+  group {
+    name     = "slo_monitoring"
+    interval = "1m"
+
+    rule {
+      record = "custom:slo:availability"
+      expr   = "sum(rate(http_requests_total{status!~\"5..\"}[5m])) / sum(rate(http_requests_total[5m]))"
+      labels = {
+        slo_type = "availability"
+      }
+    }
+
+    rule {
+      alert    = "SLOAvailabilityBreach"
+      expr     = "custom:slo:availability < 0.995"
+      duration = "5m"
+      labels = {
+        severity = "critical"
+        category = "SLO"
+      }
+      annotations = {
+        summary     = "SLO availability breach"
+        description = "Availability is below 99.5% SLO target"
+        runbook_url = "https://docs.example.com/runbooks/availability-breach"
+      }
+    }
+  }
+}
+```
+
+<!-- schema generated by tfplugindocs -->
+## Schema
+
+### Required
+
+- `group` (Block List, Min: 1) List of Prometheus rule groups. Each group contains one or more rules and can have its own evaluation interval. (see [below for nested schema](#nestedblock--group))
+- `name` (String) The name of the Prometheus rules file. This will be stored with a .custom extension. Must follow naming validation rules (alphanumeric, hyphens, underscores).
+
+### Optional
+
+- `active` (Boolean) Whether the rules file is active. Inactive rules are not evaluated. Defaults to `true`.
+
+### Read-Only
+
+- `id` (String) The ID of this resource.
+
+<a id="nestedblock--group"></a>
+### Nested Schema for `group`
+
+Required:
+
+- `name` (String) The name of the rule group (e.g., 'latency_monitoring').
+- `rule` (Block List, Min: 1) List of Prometheus rules in this group. (see [below for nested schema](#nestedblock--group--rule))
+
+Optional:
+
+- `interval` (String) Evaluation interval for this group (e.g., '30s', '1m'). If not specified, uses the global evaluation interval.
+
+<a id="nestedblock--group--rule"></a>
+### Nested Schema for `group.rule`
+
+Required:
+
+- `expr` (String) The PromQL expression to evaluate.
+
+Optional:
+
+- `active` (Boolean) Whether this specific rule is active. This field is read-only and controlled by the API.
+- `alert` (String) The name of the alert for alerting rules. Either 'record' or 'alert' must be specified, but not both.
+- `annotations` (Map of String) Annotations to add to alerts (e.g., summary, description).
+- `disable_in_groups` (Set of String) List of group names where this rule should be disabled. Useful for conditional rule enablement.
+- `duration` (String) How long the condition must be true before firing the alert (e.g., '5m'). Only applicable for alerting rules. Maps to 'for' in Prometheus.
+- `labels` (Map of String) Labels to attach to the resulting time series or alert.
+- `record` (String) The name of the time series to output for recording rules. Either 'record' or 'alert' must be specified, but not both.
+
+## Import
+
+Import is supported using the following syntax:
+
+```shell
+terraform import grafana_asserts_prom_rule_file.name "{{ name }}"
+```

examples/resources/grafana_asserts_prom_rule_file/import.sh

@@ -0,0 +1 @@
+terraform import grafana_asserts_prom_rule_file.name "{{ name }}"