Add k8s-deployment-rollout-troubleshoot CodeBundle

codebundles/k8s-deployment-rollout-troubleshoot/.runwhen/generation-rules/k8s-deployment-rollout-troubleshoot.yaml

@@ -0,0 +1,22 @@
+apiVersion: runwhen.com/v1
+kind: GenerationRules
+spec:
+  generationRules:
+    - resourceTypes:
+        - deployment
+      matchRules:
+        - type: pattern
+          pattern: ".+"
+          properties: [name]
+          mode: substring
+      slxs:
+        - baseName: k8s-dep-rollout
+          shortenedBaseName: k8s-dep-rollout
+          qualifiers: ["resource", "namespace", "cluster"]
+          baseTemplateName: k8s-deployment-rollout-troubleshoot
+          levelOfDetail: basic
+          outputItems:
+            - type: slx
+            - type: sli
+            - type: runbook
+              templateName: k8s-deployment-rollout-troubleshoot-taskset.yaml

codebundles/k8s-deployment-rollout-troubleshoot/.runwhen/templates/k8s-deployment-rollout-troubleshoot-sli.yaml

@@ -0,0 +1,28 @@
+apiVersion: runwhen.com/v1
+kind: ServiceLevelIndicator
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  displayUnitsLong: Execution Status
+  displayUnitsShort: exe
+  locations:
+    - {{default_location}}
+  description: Periodically triggers k8s-deployment-rollout-troubleshoot runbook for deployment {{match_resource.resource.metadata.name}}.
+  codeBundle:
+    repoUrl: https://github.com/runwhen-contrib/rw-workspace-utils.git
+    ref: main
+    pathToRobot: codebundles/cron-scheduler-sli/sli.robot
+  intervalStrategy: intermezzo
+  intervalSeconds: 300
+  configProvided:
+    - name: CRON_SCHEDULE
+      value: "0 */6 * * *"
+    - name: TARGET_SLX
+      value: ""
+    - name: DRY_RUN
+      value: "false"
+  secretsProvided: []

codebundles/k8s-deployment-rollout-troubleshoot/.runwhen/templates/k8s-deployment-rollout-troubleshoot-slx.yaml

@@ -0,0 +1,25 @@
+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/kubernetes/resources/labeled/deploy.svg
+  alias: {{match_resource.resource.metadata.name}} Rollout Troubleshoot
+  asMeasuredBy: Periodic execution of rollout troubleshoot tasks when rollout health degrades.
+  configProvided:
+  - name: DEPLOYMENT_NAME
+    value: {{match_resource.resource.metadata.name}}
+  owners:
+  - {{workspace.owner_email}}
+  statement: Deployment {{match_resource.resource.metadata.name}} rollouts should complete successfully without stalled or failed revisions.
+  additionalContext:
+    {% include "kubernetes-hierarchy.yaml" ignore missing %}
+    qualified_name: "{{ match_resource.qualified_name }}"
+  tags:
+    {% include "kubernetes-tags.yaml" ignore missing %}
+    - name: access
+      value: read-only

codebundles/k8s-deployment-rollout-troubleshoot/.runwhen/templates/k8s-deployment-rollout-troubleshoot-taskset.yaml

@@ -0,0 +1,45 @@
+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: Read-only diagnostics for Kubernetes deployment rollout lifecycle failures.
+  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/k8s-deployment-rollout-troubleshoot/runbook.robot
+  configProvided:
+    - name: NAMESPACE
+      value: "{{match_resource.resource.metadata.namespace}}"
+    - name: CONTEXT
+      value: "{{context}}"
+    - name: DEPLOYMENT_NAME
+      value: "{{match_resource.resource.metadata.name}}"
+    - name: KUBERNETES_DISTRIBUTION_BINARY
+      value: "{{custom.kubernetes_distribution_binary | default('kubectl')}}"
+    - name: EVENT_AGE
+      value: "30m"
+    - name: ROLLOUT_STATUS_TIMEOUT
+      value: "30"
+    - name: STUCK_TERMINATING_THRESHOLD
+      value: "5"
+  secretsProvided:
+  {% if wb_version %}
+    {% include "kubernetes-auth.yaml" ignore missing %}
+  {% else %}
+    - name: kubeconfig
+      workspaceKey: {{custom.kubeconfig_secret_name | default("kubeconfig")}}
+  {% endif %}

codebundles/k8s-deployment-rollout-troubleshoot/.test/README.md

@@ -0,0 +1,15 @@
+# Test Infrastructure for k8s-deployment-rollout-troubleshoot
+
+Apply manifests with `task build-infra` to create test deployments covering rollout troubleshoot scenarios in the `test-rollout-troubleshoot` namespace.
+
+## Scenarios
+
+| Deployment | Scenario |
+|---|---|
+| `healthy-rollout` | Complete healthy rollout |
+| `progress-deadline-fail` | ProgressDeadlineExceeded via failing readiness probe |
+| `pdb-blocked-rollout` | PDB minAvailable blocks eviction during rollout |
+| `image-pull-fail` | ImagePullBackOff on bad image tag |
+| `stuck-terminating-seed` | Long preStop hook for terminating pod testing |
+
+Run `task default` after committing and pushing changes to validate generation rules via RunWhen Local discovery.

codebundles/k8s-deployment-rollout-troubleshoot/.test/Taskfile.yaml

@@ -0,0 +1,178 @@
+version: "3"
+
+tasks:
+  default:
+    desc: "Run/refresh config"
+    cmds:
+      - task: check-unpushed-commits
+      - task: generate-rwl-config
+      - task: run-rwl-discovery
+
+  clean:
+    desc: "Run cleanup tasks"
+    cmds:
+      - task: remove-kubernetes-objects
+      - task: delete-slxs
+      - task: clean-rwl-discovery
+
+  build-infra:
+    desc: "Build test infrastructure"
+    cmds:
+      - task: create-kubernetes-objects
+
+  create-kubernetes-objects:
+    desc: "Apply manifests from kubernetes directory using kubectl"
+    cmds:
+      - kubectl apply -f kubernetes/*
+    silent: true
+
+  remove-kubernetes-objects:
+    desc: "Delete kubernetes objects"
+    cmds:
+      - kubectl delete -f kubernetes/* --ignore-not-found
+    silent: true
+
+  check-unpushed-commits:
+    desc: Check if outstanding commits or file updates need to be pushed before testing.
+    vars:
+      BASE_DIR: "../"
+    cmds:
+      - |
+        echo "Checking for uncommitted changes in $BASE_DIR and $BASE_DIR.runwhen, excluding '.test'..."
+        UNCOMMITTED_FILES=$(git diff --name-only HEAD | grep -E "^${BASE_DIR}(\.runwhen|[^/]+)" | grep -v "/\.test/" || true)
+        if [ -n "$UNCOMMITTED_FILES" ]; then
+          echo "✗"
+          echo "Uncommitted changes found:"
+          echo "$UNCOMMITTED_FILES"
+          echo "Remember to commit & push changes before executing the run-rwl-discovery task."
+          echo "------------"
+          exit 1
+        else
+          echo "√"
+          echo "No uncommitted changes in specified directories."
+          echo "------------"
+        fi
+      - |
+        echo "Checking for unpushed commits in $BASE_DIR and $BASE_DIR.runwhen, excluding '.test'..."
+        git fetch origin
+        UNPUSHED_FILES=$(git diff --name-only origin/$(git rev-parse --abbrev-ref HEAD) HEAD | grep -E "^${BASE_DIR}(\.runwhen|[^/]+)" | grep -v "/\.test/" || true)
+        if [ -n "$UNPUSHED_FILES" ]; then
+          echo "✗"
+          echo "Unpushed commits found:"
+          echo "$UNPUSHED_FILES"
+          echo "Remember to push changes before executing the run-rwl-discovery task."
+          echo "------------"
+          exit 1
+        else
+          echo "√"
+          echo "No unpushed commits in specified directories."
+          echo "------------"
+        fi
+    silent: true
+
+  generate-rwl-config:
+    desc: "Generate RunWhen Local configuration (workspaceInfo.yaml)"
+    env:
+      RW_WORKSPACE: '{{.RW_WORKSPACE | default "my-workspace"}}'
+    cmds:
+      - |
+        repo_url=$(git config --get remote.origin.url)
+        branch_name=$(git rev-parse --abbrev-ref HEAD)
+        codebundle=$(basename "$(dirname "$PWD")")
+
+        namespace=$(yq e 'select(.kind == "Namespace") | .metadata.name' kubernetes/manifest.yaml -N)
+        cat <<EOF > workspaceInfo.yaml
+        workspaceName: "$RW_WORKSPACE"
+        workspaceOwnerEmail: authors@runwhen.com
+        defaultLocation: location-01
+        defaultLOD: none
+        cloudConfig:
+          kubernetes:
+            kubeconfigFile: /shared/kubeconfig
+            namespaceLODs:
+              $namespace: detailed
+            namespaces:
+              - $namespace
+        codeCollections:
+        - repoURL: "$repo_url"
+          branch: "$branch_name"
+          codeBundles: ["$codebundle"]
+        custom:
+          kubeconfig_secret_name: "kubeconfig"
+          kubernetes_distribution_binary: kubectl
+        EOF
+    silent: true
+
+  run-rwl-discovery:
+    desc: "Run RunWhen Local Discovery on test infrastructure"
+    cmds:
+      - |
+        CONTAINER_NAME="RunWhenLocal"
+        if docker ps -q --filter "name=$CONTAINER_NAME" | grep -q .; then
+          echo "Stopping and removing existing container $CONTAINER_NAME..."
+          docker stop $CONTAINER_NAME && docker rm $CONTAINER_NAME
+        elif docker ps -a -q --filter "name=$CONTAINER_NAME" | grep -q .; then
+          echo "Removing existing stopped container $CONTAINER_NAME..."
+          docker rm $CONTAINER_NAME
+        else
+          echo "No existing container named $CONTAINER_NAME found."
+        fi
+
+        echo "Cleaning up output directory..."
+        sudo rm -rf output || { echo "Failed to remove output directory"; exit 1; }
+        mkdir output && chmod 777 output || { echo "Failed to set permissions"; exit 1; }
+
+        echo "Starting new container $CONTAINER_NAME..."
+
+        kubeconfig=$(echo $RW_FROM_FILE | jq -r .kubeconfig)
+
+        docker run --name $CONTAINER_NAME -p 8081:8081 \
+          -v "$(pwd)":/shared \
+          -v $kubeconfig:/shared/kubeconfig \
+          -d ghcr.io/runwhen-contrib/runwhen-local:latest || {
+          echo "Failed to start container"; exit 1;
+        }
+
+        echo "Running workspace builder script in container..."
+        docker exec -w /workspace-builder $CONTAINER_NAME ./run.sh $1 --verbose || {
+          echo "Error executing script in container"; exit 1;
+        }
+
+        echo "Review generated config files under output/workspaces/"
+    silent: true
+
+  validate-generation-rules:
+    desc: "Validate YAML files in .runwhen/generation-rules"
+    cmds:
+      - |
+        for cmd in curl yq ajv; do
+          if ! command -v $cmd &> /dev/null; then
+            echo "Error: $cmd is required but not installed."
+            exit 1
+          fi
+        done
+
+        temp_dir=$(mktemp -d)
+        curl -s -o "$temp_dir/generation-rule-schema.json" \
+          https://raw.githubusercontent.com/runwhen-contrib/runwhen-local/refs/heads/main/src/generation-rule-schema.json
+
+        for yaml_file in ../.runwhen/generation-rules/*.yaml; do
+          echo "Validating $yaml_file"
+          json_file="$temp_dir/$(basename "${yaml_file%.*}.json")"
+          yq -o=json "$yaml_file" > "$json_file"
+          ajv validate -s "$temp_dir/generation-rule-schema.json" -d "$json_file" \
+            --spec=draft2020 --strict=false \
+          && echo "$yaml_file is valid." || echo "$yaml_file is invalid."
+        done
+
+        rm -rf "$temp_dir"
+    silent: true
+
+  clean-rwl-discovery:
+    desc: "Check and clean up RunWhen Local discovery output"
+    cmds:
+      - |
+        sudo rm -rf output
+        rm -f workspaceInfo.yaml
+        rm -f kubeconfig
+    silent: true