fix: repair kill-instance scope action slug and add instance_id parameter

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 - Fix: triggering a scheduled task job on a scope that is not deployed now fails with a clear "deploy the scope first" message instead of an opaque error
+- Add "Kill instance" action to scheduled task scopes to terminate an individual running job instance
 
 ## [1.13.0] - 2026-07-10
 - Add support to get AWS credentials via assume role

azure-aro/specs/actions/kill-instance.json.tpl

@@ -0,0 +1,36 @@
+{
+  "name": "Kill instance",
+  "type": "custom",
+  "icon": "material-symbols:delete-outline",
+  "results": {
+    "schema": { "type": "object", "required": [], "properties": {} },
+    "values": {}
+  },
+  "service_specification_id": "{{ env.Getenv "SERVICE_SPECIFICATION_ID" }}",
+  "parameters": {
+    "schema": {
+      "type": "object",
+      "required": [
+        "instance_id",
+        "scope_id",
+        "deployment_id"
+      ],
+      "properties": {
+        "scope_id": {
+          "type": "string"
+        },
+        "instance_id": {
+          "type": "string"
+        },
+        "deployment_id": {
+          "type": "string"
+        }
+      }
+    },
+    "values": {}
+  },
+  "annotations": {
+    "show_on": ["performance"],
+    "runs_over": "scope"
+  }
+}

azure/specs/actions/kill-instance.json.tpl

@@ -0,0 +1,36 @@
+{
+  "name": "Kill instance",
+  "type": "custom",
+  "icon": "material-symbols:delete-outline",
+  "results": {
+    "schema": { "type": "object", "required": [], "properties": {} },
+    "values": {}
+  },
+  "service_specification_id": "{{ env.Getenv "SERVICE_SPECIFICATION_ID" }}",
+  "parameters": {
+    "schema": {
+      "type": "object",
+      "required": [
+        "instance_id",
+        "scope_id",
+        "deployment_id"
+      ],
+      "properties": {
+        "scope_id": {
+          "type": "string"
+        },
+        "instance_id": {
+          "type": "string"
+        },
+        "deployment_id": {
+          "type": "string"
+        }
+      }
+    },
+    "values": {}
+  },
+  "annotations": {
+    "show_on": ["performance"],
+    "runs_over": "scope"
+  }
+}

k8s/deployment/kill_instances → k8s/deployment/kill_instance

@@ -6,14 +6,14 @@ set -euo pipefail
 log debug "🔍 Starting instance kill operation..."
 
 DEPLOYMENT_ID=$(echo "$CONTEXT" | jq -r '.parameters.deployment_id // .notification.parameters.deployment_id // empty')
-INSTANCE_NAME=$(echo "$CONTEXT" | jq -r '.parameters.instance_name // .notification.parameters.instance_name // empty')
+INSTANCE_ID=$(echo "$CONTEXT" | jq -r '.parameters.instance_id // .notification.parameters.instance_id // empty')
 
 if [[ -z "$DEPLOYMENT_ID" ]] && [[ -n "${NP_ACTION_CONTEXT:-}" ]]; then
     DEPLOYMENT_ID=$(echo "$NP_ACTION_CONTEXT" | jq -r '.notification.parameters.deployment_id // empty')
 fi
 
-if [[ -z "$INSTANCE_NAME" ]] && [[ -n "${NP_ACTION_CONTEXT:-}" ]]; then
-    INSTANCE_NAME=$(echo "$NP_ACTION_CONTEXT" | jq -r '.notification.parameters.instance_name // empty')
+if [[ -z "$INSTANCE_ID" ]] && [[ -n "${NP_ACTION_CONTEXT:-}" ]]; then
+    INSTANCE_ID=$(echo "$NP_ACTION_CONTEXT" | jq -r '.notification.parameters.instance_id // empty')
 fi
 
 if [[ -z "$DEPLOYMENT_ID" ]]; then
@@ -26,18 +26,18 @@ if [[ -z "$DEPLOYMENT_ID" ]]; then
     exit 1
 fi
 
-if [[ -z "$INSTANCE_NAME" ]]; then
-    log error "❌ instance_name parameter not found"
+if [[ -z "$INSTANCE_ID" ]]; then
+    log error "❌ instance_id parameter not found"
     log error "💡 Possible causes:"
     log error "   - Parameter not provided in action request"
     log error "   - Context structure is different than expected"
     log error "🔧 How to fix:"
-    log error "   - Ensure instance_name is passed in the action parameters"
+    log error "   - Ensure instance_id is passed in the action parameters"
     exit 1
 fi
 
 log debug "📋 Deployment ID: $DEPLOYMENT_ID"
-log debug "📋 Instance name: $INSTANCE_NAME"
+log debug "📋 Instance name: $INSTANCE_ID"
 
 SCOPE_ID=$(echo "$CONTEXT" | jq -r '.tags.scope_id // .scope.id // .notification.tags.scope_id // empty')
 
@@ -63,8 +63,8 @@ log debug "📋 Scope ID: $SCOPE_ID"
 log debug "📋 Namespace: $K8S_NAMESPACE"
 
 log debug "🔍 Verifying pod exists..."
-if ! kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" >/dev/null 2>&1; then
-    log error "❌ Pod $INSTANCE_NAME not found in namespace $K8S_NAMESPACE"
+if ! kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" >/dev/null 2>&1; then
+    log error "❌ Pod $INSTANCE_ID not found in namespace $K8S_NAMESPACE"
     log error "💡 Possible causes:"
     log error "   - Pod was already terminated"
     log error "   - Pod name is incorrect"
@@ -75,15 +75,15 @@ if ! kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" >/dev/null 2>&1; then
 fi
 
 log debug "📋 Fetching pod details..."
-POD_STATUS=$(kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" -o jsonpath='{.status.phase}')
-POD_NODE=$(kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" -o jsonpath='{.spec.nodeName}')
-POD_START_TIME=$(kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" -o jsonpath='{.status.startTime}')
+POD_STATUS=$(kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" -o jsonpath='{.status.phase}')
+POD_NODE=$(kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" -o jsonpath='{.spec.nodeName}')
+POD_START_TIME=$(kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" -o jsonpath='{.status.startTime}')
 
-log debug "📋 Pod: $INSTANCE_NAME | Status: $POD_STATUS | Node: $POD_NODE | Started: $POD_START_TIME"
+log debug "📋 Pod: $INSTANCE_ID | Status: $POD_STATUS | Node: $POD_NODE | Started: $POD_START_TIME"
 
 DEPLOYMENT_NAME="d-$SCOPE_ID-$DEPLOYMENT_ID"
 
-POD_DEPLOYMENT=$(kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" -o jsonpath='{.metadata.ownerReferences[0].name}' 2>/dev/null || echo "")
+POD_DEPLOYMENT=$(kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" -o jsonpath='{.metadata.ownerReferences[0].name}' 2>/dev/null || echo "")
 if [[ -n "$POD_DEPLOYMENT" ]]; then
     REPLICASET_DEPLOYMENT=$(kubectl get replicaset "$POD_DEPLOYMENT" -n "$K8S_NAMESPACE" -o jsonpath='{.metadata.ownerReferences[0].name}' 2>/dev/null || echo "")
     log debug "📋 Pod ownership: ReplicaSet=$POD_DEPLOYMENT -> Deployment=$REPLICASET_DEPLOYMENT"
@@ -95,14 +95,14 @@ else
     log warn "⚠️  Could not verify pod ownership"
 fi
 
-log debug "📝 Deleting pod $INSTANCE_NAME with 30s grace period..."
-kubectl delete pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" --grace-period=30
+log debug "📝 Deleting pod $INSTANCE_ID with 30s grace period..."
+kubectl delete pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" --grace-period=30
 
 log debug "📝 Waiting for pod termination..."
-kubectl wait --for=delete pod/"$INSTANCE_NAME" -n "$K8S_NAMESPACE" --timeout=60s || log warn "⚠️  Pod deletion timeout reached"
+kubectl wait --for=delete pod/"$INSTANCE_ID" -n "$K8S_NAMESPACE" --timeout=60s || log warn "⚠️  Pod deletion timeout reached"
 
-if kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" >/dev/null 2>&1; then
-    POD_STATUS_AFTER=$(kubectl get pod "$INSTANCE_NAME" -n "$K8S_NAMESPACE" -o jsonpath='{.status.phase}')
+if kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" >/dev/null 2>&1; then
+    POD_STATUS_AFTER=$(kubectl get pod "$INSTANCE_ID" -n "$K8S_NAMESPACE" -o jsonpath='{.status.phase}')
     log warn "⚠️  Pod still exists after deletion attempt (status: $POD_STATUS_AFTER)"
 else
     log info "✅ Pod successfully terminated and removed"
@@ -123,4 +123,4 @@ else
     log warn "⚠️  Deployment $DEPLOYMENT_NAME not found"
 fi
 
-log info "✨ Instance kill operation completed for $INSTANCE_NAME"
+log info "✨ Instance kill operation completed for $INSTANCE_ID"

k8s/deployment/tests/kill_instances.bats → k8s/deployment/tests/kill_instance.bats

@@ -1,6 +1,6 @@
 #!/usr/bin/env bats
 # =============================================================================
-# Unit tests for deployment/kill_instances - pod termination
+# Unit tests for deployment/kill_instance - pod termination
 # =============================================================================
 
 setup() {
@@ -15,7 +15,7 @@ setup() {
   export CONTEXT='{
     "parameters": {
       "deployment_id": "deploy-456",
-      "instance_name": "my-pod-abc123"
+      "instance_id": "my-pod-abc123"
     },
     "tags": {
       "scope_id": "scope-123"
@@ -84,8 +84,8 @@ teardown() {
 # =============================================================================
 # Success Case
 # =============================================================================
-@test "kill_instances: successfully kills pod with correct logging" {
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+@test "kill_instance: successfully kills pod with correct logging" {
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 0 ]
   # Start message
@@ -110,14 +110,14 @@ teardown() {
 # =============================================================================
 # Error Cases
 # =============================================================================
-@test "kill_instances: fails with troubleshooting when deployment_id missing" {
+@test "kill_instance: fails with troubleshooting when deployment_id missing" {
   export CONTEXT='{
     "parameters": {
-      "instance_name": "my-pod-abc123"
+      "instance_id": "my-pod-abc123"
     }
   }'
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 1 ]
   assert_contains "$output" "❌ deployment_id parameter not found"
@@ -127,32 +127,32 @@ teardown() {
   assert_contains "$output" "Ensure deployment_id is passed in the action parameters"
 }
 
-@test "kill_instances: fails with troubleshooting when instance_name missing" {
+@test "kill_instance: fails with troubleshooting when instance_id missing" {
   export CONTEXT='{
     "parameters": {
       "deployment_id": "deploy-456"
     }
   }'
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 1 ]
-  assert_contains "$output" "❌ instance_name parameter not found"
+  assert_contains "$output" "❌ instance_id parameter not found"
   assert_contains "$output" "💡 Possible causes:"
   assert_contains "$output" "Parameter not provided in action request"
   assert_contains "$output" "🔧 How to fix:"
-  assert_contains "$output" "Ensure instance_name is passed in the action parameters"
+  assert_contains "$output" "Ensure instance_id is passed in the action parameters"
 }
 
-@test "kill_instances: fails with troubleshooting when scope_id missing" {
+@test "kill_instance: fails with troubleshooting when scope_id missing" {
   export CONTEXT='{
     "parameters": {
       "deployment_id": "deploy-456",
-      "instance_name": "my-pod-abc123"
+      "instance_id": "my-pod-abc123"
     }
   }'
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 1 ]
   assert_contains "$output" "❌ scope_id not found in context"
@@ -162,7 +162,7 @@ teardown() {
   assert_contains "$output" "Verify the action is invoked with proper scope context"
 }
 
-@test "kill_instances: fails with troubleshooting when pod not found" {
+@test "kill_instance: fails with troubleshooting when pod not found" {
   kubectl() {
     case "$1" in
       get)
@@ -175,7 +175,7 @@ teardown() {
   }
   export -f kubectl
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 1 ]
   assert_contains "$output" "❌ Pod my-pod-abc123 not found in namespace test-namespace"
@@ -188,7 +188,7 @@ teardown() {
 # =============================================================================
 # Warning Cases
 # =============================================================================
-@test "kill_instances: warns when pod belongs to different deployment" {
+@test "kill_instance: warns when pod belongs to different deployment" {
   kubectl() {
     case "$1" in
       get)
@@ -230,13 +230,13 @@ teardown() {
   }
   export -f kubectl
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 0 ]
   assert_contains "$output" "⚠️  Pod does not belong to expected deployment d-scope-123-deploy-456"
 }
 
-@test "kill_instances: warns when pod still exists after deletion" {
+@test "kill_instance: warns when pod still exists after deletion" {
   local delete_called=0
   kubectl() {
     case "$1" in
@@ -279,7 +279,7 @@ teardown() {
   }
   export -f kubectl
 
-  run bash "$BATS_TEST_DIRNAME/../kill_instances"
+  run bash "$BATS_TEST_DIRNAME/../kill_instance"
 
   [ "$status" -eq 0 ]
   assert_contains "$output" "⚠️  Pod deletion timeout reached"

k8s/deployment/workflows/kill_instances.yaml → k8s/deployment/workflows/kill_instance.yaml

@@ -10,6 +10,6 @@ steps:
         parameters:
           level: string
           message: string
-  - name: kill instances
+  - name: kill instance
     type: script
-    file: "$SERVICE_PATH/deployment/kill_instances"
+    file: "$SERVICE_PATH/deployment/kill_instance"