feat: update monitoring parameters for LiteLLM and Typesense, add notification prompts

Author: FabrizioCafolla

CHANGELOG.md

@@ -8,6 +8,18 @@ to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
 
+## [0.9.0] - 2025-12-15
+
+[Compare with previous version](https://github.com/sparkfabrik/terraform-google-services-monitoring/compare/0.8.0...0.9.0)
+
+### Added
+
+- Add `notification_prompts` param for LiteLLM and Typesense
+
+### Changed
+
+- Modify the default values of the pod restart alerts `duration` and `alignment_period`
+
 ## [0.8.0] - 2025-12-12
 
 [Compare with previous version](https://github.com/sparkfabrik/terraform-google-services-monitoring/compare/0.7.0...0.8.0)

README.md

@@ -38,11 +38,11 @@ Supported services:
 | <a name="input_cert_manager"></a> [cert\_manager](#input\_cert\_manager) | Configuration for cert-manager missing issuer log alert. Allows customization of project, cluster, namespace, notification channels, alert documentation, enablement, extra filters, auto-close timing, and notification rate limiting. | <pre>object({<br/>    enabled                          = optional(bool, true)<br/>    cluster_name                     = string<br/>    project_id                       = optional(string, null)<br/>    namespace                        = optional(string, "cert-manager")<br/>    notification_enabled             = optional(bool, true)<br/>    notification_channels            = optional(list(string), [])<br/>    logmatch_notification_rate_limit = optional(string, "300s")<br/>    alert_documentation              = optional(string, null)<br/>    auto_close_seconds               = optional(number, 3600)<br/>    filter_extra                     = optional(string, "")<br/>  })</pre> | n/a | yes |
 | <a name="input_cloud_sql"></a> [cloud\_sql](#input\_cloud\_sql) | Configuration for Cloud SQL monitoring alerts. Supports customization of project, auto-close timing, notification channels, and per-instance alert thresholds for CPU, memory, and disk utilization. | <pre>object({<br/>    project_id            = optional(string, null)<br/>    auto_close            = optional(string, "86400s") # default 24h<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    instances = optional(map(object({<br/>      cpu_utilization = optional(list(object({<br/>        severity         = optional(string, "WARNING"),<br/>        threshold        = optional(number, 0.90)<br/>        alignment_period = optional(string, "120s")<br/>        duration         = optional(string, "300s")<br/>        })), [<br/>        {<br/>          threshold = 0.85,<br/>          duration  = "1200s",<br/>        },<br/>        {<br/>          severity         = "CRITICAL",<br/>          threshold        = 1,<br/>          duration         = "300s",<br/>          alignment_period = "60s",<br/>        }<br/>      ])<br/>      memory_utilization = optional(list(object({<br/>        severity         = optional(string, "WARNING"),<br/>        threshold        = optional(number, 0.90)<br/>        alignment_period = optional(string, "300s")<br/>        duration         = optional(string, "300s")<br/>        })), [<br/>        {<br/>          severity = "WARNING",<br/>        },<br/>        {<br/>          severity  = "CRITICAL",<br/>          threshold = 0.95,<br/>        }<br/>      ])<br/>      disk_utilization = optional(list(object({<br/>        severity         = optional(string, "WARNING"),<br/>        threshold        = optional(number, 0.85)<br/>        alignment_period = optional(string, "300s")<br/>        duration         = optional(string, "600s")<br/>        })), [<br/>        {<br/>          severity = "WARNING",<br/>        },<br/>        {<br/>          severity  = "CRITICAL",<br/>          threshold = 0.95,<br/>        }<br/>      ])<br/>    })), {})<br/>  })</pre> | n/a | yes |
 | <a name="input_kyverno"></a> [kyverno](#input\_kyverno) | Configuration for Kyverno monitoring alerts. Allows customization of cluster name, project, notification channels, alert documentation, metric thresholds, auto-close timing, enablement, extra filters, and namespace. | <pre>object({<br/>    enabled               = optional(bool, true)<br/>    cluster_name          = string<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    # Rate limit for notifications, e.g. "300s" for 5 minutes, used only for log match alerts<br/>    logmatch_notification_rate_limit = optional(string, "300s")<br/>    alert_documentation              = optional(string, null)<br/>    auto_close_seconds               = optional(number, 3600)<br/>    filter_extra                     = optional(string, "")<br/>    namespace                        = optional(string, "kyverno")<br/>  })</pre> | n/a | yes |
-| <a name="input_litellm"></a> [litellm](#input\_litellm) | Configuration for LiteLLM monitoring alerts. Supports uptime checks for HTTP endpoints and container-level alerts (pod restarts) in GKE. Each app is identified by its name (map key). | <pre>object({<br/>    enabled               = optional(bool, false)<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    cluster_name          = optional(string, null)<br/><br/>    apps = optional(map(object({<br/>      uptime_check = optional(object({<br/>        enabled = optional(bool, true)<br/>        host    = string<br/>        path    = optional(string, "/health/readiness")<br/>      }), null)<br/><br/>      container_check = optional(object({<br/>        enabled   = optional(bool, true)<br/>        namespace = string<br/>        pod_restart = optional(object({<br/>          threshold          = optional(number, 0)<br/>          alignment_period   = optional(number, 60)<br/>          duration           = optional(number, 0)<br/>          auto_close_seconds = optional(number, 3600)<br/>        }), {})<br/>      }), null)<br/>    })), {})<br/>  })</pre> | `{}` | no |
+| <a name="input_litellm"></a> [litellm](#input\_litellm) | Configuration for LiteLLM monitoring alerts. Supports uptime checks for HTTP endpoints and container-level alerts (pod restarts) in GKE. Each app is identified by its name (map key). | <pre>object({<br/>    enabled               = optional(bool, false)<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    cluster_name          = optional(string, null)<br/><br/>    apps = optional(map(object({<br/>      uptime_check = optional(object({<br/>        enabled = optional(bool, true)<br/>        host    = string<br/>        path    = optional(string, "/health/readiness")<br/>      }), null)<br/><br/>      container_check = optional(object({<br/>        enabled   = optional(bool, true)<br/>        namespace = string<br/>        pod_restart = optional(object({<br/>          threshold          = optional(number, 0)<br/>          alignment_period   = optional(number, 60)<br/>          duration           = optional(number, 120)<br/>          auto_close_seconds = optional(number, 3600)<br/>          notification_prompts = optional(list(string), ["OPENED", "CLOSED"])<br/>        }), {})<br/>      }), null)<br/>    })), {})<br/>  })</pre> | `{}` | no |
 | <a name="input_notification_channels"></a> [notification\_channels](#input\_notification\_channels) | List of notification channel IDs to notify when an alert is triggered | `list(string)` | `[]` | no |
 | <a name="input_project_id"></a> [project\_id](#input\_project\_id) | The Google Cloud project ID where logging exclusions will be created | `string` | n/a | yes |
 | <a name="input_ssl_alert"></a> [ssl\_alert](#input\_ssl\_alert) | Configuration for SSL certificate expiration alerts. Allows customization of project, notification channels, alert thresholds, and user labels. | <pre>object({<br/>    enabled               = optional(bool, false)<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    threshold_days        = optional(list(number), [15, 7])<br/>    user_labels           = optional(map(string), {})<br/>  })</pre> | `{}` | no |
-| <a name="input_typesense"></a> [typesense](#input\_typesense) | Configuration for Typesense monitoring alerts. Supports uptime checks for HTTP endpoints and container-level alerts (pod restarts) in GKE. Each app is identified by its name (map key). | <pre>object({<br/>    enabled               = optional(bool, false)<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    cluster_name          = optional(string, null) # GKE cluster name for container checks<br/><br/>    # Apps configuration - map keyed by app_name<br/>    apps = optional(map(object({<br/>      # Uptime check configuration (optional)<br/>      uptime_check = optional(object({<br/>        enabled = optional(bool, true)<br/>        host    = string<br/>        path    = optional(string, "/readyz")<br/>      }), null)<br/><br/>      # Container check configuration for GKE (optional)<br/>      container_check = optional(object({<br/>        enabled   = optional(bool, true)<br/>        namespace = string<br/>        pod_restart = optional(object({<br/>          threshold          = optional(number, 0)<br/>          alignment_period   = optional(number, 60)<br/>          duration           = optional(number, 0)<br/>          auto_close_seconds = optional(number, 3600)<br/>        }), {})<br/>      }), null)<br/>    })), {})<br/>  })</pre> | `{}` | no |
+| <a name="input_typesense"></a> [typesense](#input\_typesense) | Configuration for Typesense monitoring alerts. Supports uptime checks for HTTP endpoints and container-level alerts (pod restarts) in GKE. Each app is identified by its name (map key). | <pre>object({<br/>    enabled               = optional(bool, false)<br/>    project_id            = optional(string, null)<br/>    notification_enabled  = optional(bool, true)<br/>    notification_channels = optional(list(string), [])<br/>    cluster_name          = optional(string, null)<br/><br/>    apps = optional(map(object({<br/>      uptime_check = optional(object({<br/>        enabled = optional(bool, true)<br/>        host    = string<br/>        path    = optional(string, "/readyz")<br/>      }), null)<br/><br/>      container_check = optional(object({<br/>        enabled   = optional(bool, true)<br/>        namespace = string<br/>        pod_restart = optional(object({<br/>          threshold          = optional(number, 0)<br/>          duration           = optional(number, 120)<br/>          auto_close_seconds = optional(number, 3600)<br/>          notification_prompts = optional(list(string), ["OPENED", "CLOSED"])<br/>        }), {})<br/>      }), null)<br/>    })), {})<br/>  })</pre> | `{}` | no |
 
 ## Outputs
 

lite_llm.tf

@@ -75,5 +75,6 @@ resource "google_monitoring_alert_policy" "litellm_pod_restart" {
 
   alert_strategy {
     auto_close = "${each.value.pod_restart.auto_close_seconds}s"
+    notification_prompts = each.value.pod_restart.notification_prompts
   }
 }

typesense.tf

@@ -75,5 +75,6 @@ resource "google_monitoring_alert_policy" "typesense_pod_restart" {
 
   alert_strategy {
     auto_close = "${each.value.pod_restart.auto_close_seconds}s"
+    notification_prompts = each.value.pod_restart.notification_prompts
   }
 }

variables.tf

@@ -107,26 +107,23 @@ variable "typesense" {
     project_id            = optional(string, null)
     notification_enabled  = optional(bool, true)
     notification_channels = optional(list(string), [])
-    cluster_name          = optional(string, null) # GKE cluster name for container checks
+    cluster_name          = optional(string, null)
 
-    # Apps configuration - map keyed by app_name
     apps = optional(map(object({
-      # Uptime check configuration (optional)
       uptime_check = optional(object({
         enabled = optional(bool, true)
         host    = string
         path    = optional(string, "/readyz")
       }), null)
 
-      # Container check configuration for GKE (optional)
       container_check = optional(object({
         enabled   = optional(bool, true)
         namespace = string
         pod_restart = optional(object({
           threshold          = optional(number, 0)
-          alignment_period   = optional(number, 60)
-          duration           = optional(number, 0)
+          duration           = optional(number, 120)
           auto_close_seconds = optional(number, 3600)
+          notification_prompts = optional(list(string), ["OPENED", "CLOSED"])
         }), {})
       }), null)
     })), {})
@@ -175,8 +172,9 @@ variable "litellm" {
         pod_restart = optional(object({
           threshold          = optional(number, 0)
           alignment_period   = optional(number, 60)
-          duration           = optional(number, 0)
+          duration           = optional(number, 120)
           auto_close_seconds = optional(number, 3600)
+          notification_prompts = optional(list(string), ["OPENED", "CLOSED"])
         }), {})
       }), null)
     })), {})