initial containerapp codebundle

codebundles/azure-containerapps-health/.runwhen/generation-rules/azure-containerapps-health.yaml

@@ -0,0 +1,27 @@
+# apiVersion: runwhen.com/v1
+# kind: GenerationRules
+# spec:
+#   platform: azure
+#   generationRules:
+#     - resourceTypes:
+#         - azure_containerapps_container_apps
+#       matchRules:
+#         - type: pattern
+#           pattern: ".+"
+#           properties: [name]
+#           mode: substring
+#         - type: pattern
+#           pattern: "^app(?:,.*)?$"
+#           properties: [kind]
+#           mode: substring
+#       slxs:
+#         - baseName: az-containerapp-health
+#           qualifiers: ["resource", "resource_group"]
+#           baseTemplateName: azure-containerapps-health
+#           levelOfDetail: detailed
+#           outputItems:
+#             - type: slx
+#             - type: sli
+#             - type: runbook
+#               templateName: azure-containerapps-health-taskset.yaml
+#             - type: workflow 

codebundles/azure-containerapps-health/.runwhen/templates/azure-containerapps-health-sli.yaml

@@ -0,0 +1,65 @@
+apiVersion: runwhen.com/v1
+kind: ServiceLevelIndicator
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  displayUnitsLong: OK
+  displayUnitsShort: ok
+  locations:
+    - {{default_location}}
+  description: Measures the health of Azure Container App {{match_resource.resource.name}} in resource group {{resource_group.name}}
+  codeBundle:
+    {% if repo_url %}
+    repoUrl: {{repo_url}}
+    {% else %}
+    repoUrl: https://github.com/runwhen-contrib/rw-cli-codecollection.git
+    {% endif %}
+    {% if ref %}
+    ref: {{ref}}
+    {% else %}
+    ref: main
+    {% endif %}
+    pathToRobot: codebundles/azure-containerapps-health/sli.robot
+  intervalStrategy: intermezzo
+  intervalSeconds: 600
+  configProvided:
+    - name: AZ_RESOURCE_GROUP
+      value: {{resource_group.name}}
+    - name: CONTAINER_APP_NAME
+      value: {{match_resource.resource.name}}
+    - name: AZURE_RESOURCE_SUBSCRIPTION_ID
+      value: "{{ match_resource.subscription_id }}"
+    - name: SLI_TIME_PERIOD_MINUTES
+      value: "60"
+    - name: AZURE_SUBSCRIPTION_NAME
+      value: "{{ match_resource.subscription_name }}"
+    - name: AVAILABILITY_TARGET
+      value: "99.5"
+    - name: PERFORMANCE_TARGET_MS
+      value: "1000"
+    - name: ERROR_RATE_TARGET
+      value: "1.0"
+  secretsProvided:
+  {% if wb_version %}
+    {% include "azure-auth.yaml" ignore missing %}
+  {% else %}
+    - name: azure_credentials
+      workspaceKey: AUTH DETAILS NOT FOUND
+  {% endif %}
+  alerts:
+    warning:
+      operator: <
+      threshold: '1'
+      for: '20m'
+    ticket:
+      operator: <
+      threshold: '1'
+      for: '30m'
+    page:
+      operator: '=='
+      threshold: '0'
+      for: '' 

codebundles/azure-containerapps-health/.runwhen/templates/azure-containerapps-health-slx.yaml

@@ -0,0 +1,32 @@
+apiVersion: runwhen.com/v1
+kind: ServiceLevelX
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  imageURL: https://storage.googleapis.com/runwhen-nonprod-shared-images/icons/azure/container%20instances/10023-icon-service-Container-Instances.svg
+  alias: {{match_resource.resource.name}} Container App Health
+  asMeasuredBy: An aggregate score that is evaluated from configuration, metric, event or log issues. 
+  configProvided:
+  - name: AZ_RESOURCE_GROUP
+    value: {{resource_group.name}}
+  - name: CONTAINER_APP_NAME
+    value: {{match_resource.resource.name}}
+  owners:
+  - {{workspace.owner_email}}
+  statement: Container App {{match_resource.resource.name}} in resource group {{resource_group.name}} be available and healthy. 
+  additionalContext:
+    {% include "azure-hierarchy.yaml" ignore missing %}
+    qualified_name: "{{ match_resource.qualified_name }}"
+    containerapp_kind: "{{match_resource.resource.kind}}"
+  tags: 
+    {% include "azure-tags.yaml" ignore missing %}
+    - name: service
+      value: container_apps
+    - name: type
+      value: containerapp
+    - name: access
+      value: read-only 

codebundles/azure-containerapps-health/.runwhen/templates/azure-containerapps-health-taskset.yaml

@@ -0,0 +1,53 @@
+apiVersion: runwhen.com/v1
+kind: Runbook
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  location: {{default_location}}
+  description: Generates a report for Azure Container App {{match_resource.resource.name}} in resource group {{resource_group.name}}
+  codeBundle:
+    {% if repo_url %}
+    repoUrl: {{repo_url}}
+    {% else %}
+    repoUrl: https://github.com/runwhen-contrib/rw-cli-codecollection.git
+    {% endif %}
+    {% if ref %}
+    ref: {{ref}}
+    {% else %}
+    ref: main
+    {% endif %}
+    pathToRobot: codebundles/azure-containerapps-health/runbook.robot
+  configProvided:
+    - name: AZ_RESOURCE_GROUP
+      value: {{resource_group.name}}
+    - name: CONTAINER_APP_NAME
+      value: {{match_resource.resource.name}}
+    - name: AZURE_RESOURCE_SUBSCRIPTION_ID
+      value: "{{ match_resource.subscription_id }}"
+    - name: TIME_PERIOD_MINUTES
+      value: "10"
+    - name: AZURE_SUBSCRIPTION_NAME
+      value: "{{ match_resource.subscription_name }}"
+    - name: CPU_THRESHOLD
+      value: "80"
+    - name: MEMORY_THRESHOLD
+      value: "80"
+    - name: REPLICA_COUNT_MIN
+      value: "1"
+    - name: RESTART_COUNT_THRESHOLD
+      value: "5"
+    - name: REQUEST_COUNT_THRESHOLD
+      value: "1000"
+    - name: HTTP_ERROR_RATE_THRESHOLD
+      value: "5"
+  secretsProvided:
+  {% if wb_version %}
+    {% include "azure-auth.yaml" ignore missing %}
+  {% else %}
+    - name: azure_credentials
+      workspaceKey: AUTH DETAILS NOT FOUND
+  {% endif %} 

codebundles/azure-containerapps-health/.runwhen/templates/azure-containerapps-health-workflow.yaml

@@ -0,0 +1,25 @@
+apiVersion: runwhen.com/v1
+kind: Workflow
+metadata:
+  name: {{slx_name}}-{{ "Container App SLI Alert Workflow" | replace(" ", "-") | lower }}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  fromActivities:
+  - displayName: {{match_resource.resource.name}} Container App SLI Alert Workflow
+    description: Start RunSession with Eager Edgar when SLI is alerting for {{match_resource.resource.name}} Container App health
+    actions:
+    - tasks:
+        slx: {{slx_name.split('--')[1]}}
+        persona: eager-edgar
+        titles:
+          - '*'
+        sessionTTL: 20m
+    match:
+      activityVerbs:
+      - SLI_ALERTS_STARTED
+      slxs:
+      - {{slx_name.split('--')[1]}}
+    name: {{match_resource.resource.name}}-{{ "Container App SLI Alert Workflow" | replace(" ", "-") | lower }} 

codebundles/azure-containerapps-health/README.md

@@ -0,0 +1,88 @@
+# Azure Container Apps Health Monitoring
+
+Comprehensive health monitoring and triage for Azure Container Apps, checking application status, metrics, logs, configuration, and environment health to identify and resolve issues.
+
+## Features
+
+This codebundle provides comprehensive monitoring for Azure Container Apps including:
+
+- **Resource Health**: Azure platform-level health status monitoring
+- **Replica Health**: Container replica status and scaling analysis  
+- **Performance Metrics**: CPU, memory, request volume, and error rate monitoring
+- **Configuration Analysis**: Best practices validation and security assessment
+- **Revision Management**: Deployment health and traffic distribution monitoring
+- **Environment Health**: Infrastructure and networking status
+- **Log Analysis**: Intelligent error detection and pattern analysis
+
+## Configuration
+
+The TaskSet requires initialization to import necessary secrets, services, and user variables. The following variables should be set:
+
+### Required Variables
+- `CONTAINER_APP_NAME`: The name of the Azure Container App to monitor
+- `AZ_RESOURCE_GROUP`: The resource group containing the Container App
+- `azure_credentials`: Secret containing Azure service principal credentials
+
+### Optional Variables
+- `CONTAINER_APP_ENV_NAME`: Container Apps Environment name (auto-discovered if not provided)
+- `AZURE_RESOURCE_SUBSCRIPTION_ID`: Azure subscription ID (uses current subscription if not provided)
+- `TIME_PERIOD_MINUTES`: Time period for metrics and logs (default: 10 minutes)
+- `CPU_THRESHOLD`: CPU utilization threshold percentage (default: 80%)
+- `MEMORY_THRESHOLD`: Memory utilization threshold percentage (default: 80%)
+- `REPLICA_COUNT_MIN`: Minimum expected replica count (default: 1)
+- `RESTART_COUNT_THRESHOLD`: Restart count threshold for alerts (default: 5)
+- `REQUEST_COUNT_THRESHOLD`: Request count per minute threshold (default: 1000)
+- `HTTP_ERROR_RATE_THRESHOLD`: HTTP error rate percentage threshold (default: 5%)
+
+## Prerequisites
+
+- Azure CLI installed and authenticated
+- Service principal with appropriate permissions:
+  - `Container Apps Reader` role for Container Apps resources
+  - `Reader` role for metrics and monitoring
+  - `Log Analytics Reader` role for log analysis (if using Log Analytics)
+
+## Usage Examples
+
+### Basic Health Check
+```bash
+export CONTAINER_APP_NAME="my-app"
+export AZ_RESOURCE_GROUP="my-rg"
+# Run the health monitoring tasks
+```
+
+### Advanced Configuration
+```bash
+export CONTAINER_APP_NAME="production-app"
+export AZ_RESOURCE_GROUP="prod-rg"
+export CONTAINER_APP_ENV_NAME="prod-env"
+export CPU_THRESHOLD="90"
+export MEMORY_THRESHOLD="85"
+export TIME_PERIOD_MINUTES="30"
+```
+
+## Tasks Included
+
+1. **Resource Health Check**: Validates Azure platform health status
+2. **Replica Health Analysis**: Monitors replica count and status
+3. **Metrics Collection**: Gathers performance and utilization metrics
+4. **Log Retrieval**: Collects recent application logs
+5. **Configuration Review**: Analyzes Container App configuration
+6. **Revision Health**: Monitors deployment and traffic distribution
+7. **Environment Health**: Checks Container Apps Environment status
+8. **Log Analysis**: Performs intelligent error pattern detection
+
+## Notes
+
+- This codebundle assumes Azure service principal authentication flow
+- Requires Container Apps and related Azure resources to be properly configured
+- Log analysis works best when Log Analytics is configured for the Container Apps Environment
+- Some metrics may not be available for newly deployed Container Apps
+- Environment health checks will auto-discover the environment if not specified
+
+## Troubleshooting
+
+- Ensure Azure CLI is authenticated and has access to the subscription
+- Verify service principal has necessary permissions for Container Apps resources
+- Check that the Container App and resource group names are correct
+- For log analysis issues, verify Log Analytics configuration in the Container Apps Environment