@checkstack/healthcheck-backend 0.16.4 → 0.17.0

package/CHANGELOG.md

@@ -1,5 +1,31 @@
 # @checkstack/healthcheck-backend
 
+## 0.17.0
+
+### Minor Changes
+
+- 298bf42: ### Notification System Optimizations
+
+  **System context in notifications**: All notification senders (healthcheck, incident, maintenance, dependency) now include the affected system name in the notification title and body. Users can immediately identify which system is affected without clicking through to the detail page.
+
+  **Upstream notification deduplication**: When an upstream dependency goes down affecting multiple downstream systems, the dependency notification sidecar now sends **one personalized notification per user** instead of one notification per affected system. Each user's notification lists only the systems they are subscribed to, with a link to the upstream root cause system. This prevents notification floods for users subscribed to groups containing many dependent systems.
+
+  **New catalog endpoint**: Added `getSystemGroupIds` S2S RPC endpoint on the catalog to resolve which catalog groups contain a given system, used by the dependency plugin for efficient subscriber resolution during batched notification dispatch.
+
+### Patch Changes
+
+- Updated dependencies [298bf42]
+  - @checkstack/catalog-common@1.5.0
+  - @checkstack/catalog-backend@0.6.0
+  - @checkstack/satellite-backend@0.2.14
+
+## 0.16.5
+
+### Patch Changes
+
+- 9a320fe: Fixed an issue where GitOps-provisioned health checks were not added to the background execution queue immediately upon association.
+  - @checkstack/satellite-backend@0.2.13
+
 ## 0.16.4
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@checkstack/healthcheck-backend",
-  "version": "0.16.4",
+  "version": "0.17.0",
   "type": "module",
   "main": "src/index.ts",
   "checkstack": {
@@ -14,18 +14,18 @@
   },
   "dependencies": {
     "@checkstack/backend-api": "0.12.0",
-    "@checkstack/catalog-backend": "0.5.1",
+    "@checkstack/catalog-backend": "0.5.4",
     "@checkstack/catalog-common": "1.4.1",
     "@checkstack/command-backend": "0.1.19",
     "@checkstack/common": "0.6.5",
-    "@checkstack/gitops-backend": "0.2.0",
+    "@checkstack/gitops-backend": "0.2.3",
     "@checkstack/gitops-common": "0.2.0",
     "@checkstack/healthcheck-common": "0.11.0",
     "@checkstack/incident-common": "0.4.7",
     "@checkstack/integration-backend": "0.1.19",
     "@checkstack/maintenance-common": "0.4.9",
     "@checkstack/queue-api": "0.2.13",
-    "@checkstack/satellite-backend": "0.2.9",
+    "@checkstack/satellite-backend": "0.2.13",
     "@checkstack/signal-common": "0.1.9",
     "@hono/zod-validator": "^0.7.6",
     "drizzle-orm": "^0.45.0",

package/src/healthcheck-gitops-kinds.test.ts

@@ -115,6 +115,10 @@ function createMockService() {
         })
         .filter(Boolean);
     }),
+    getConfiguration: mock(async (id: string) => {
+      const config = configs.find((c) => c.id === id);
+      return config as unknown as HealthCheckConfiguration | undefined;
+    }),
   };
 }
 
@@ -217,16 +221,13 @@ describe("Healthcheck GitOps Kind: Healthcheck", () => {
   });
 
   function buildKind() {
-    return buildHealthcheckKind({
-      createService: () =>
-        ({
-          createConfiguration: mockService.createConfiguration,
-          updateConfiguration: mockService.updateConfiguration,
-          deleteConfiguration: mockService.deleteConfiguration,
-        }) as never,
-      getHealthCheckRegistry: () => mockHCRegistry as never,
-      getCollectorRegistry: () => mockCollectorRegistry as never,
-    });
+    const mockDeps = {
+      createService: () => mockService as any,
+      getHealthCheckRegistry: () => mockHCRegistry as any,
+      getCollectorRegistry: () => mockCollectorRegistry as any,
+      getQueueManager: () => ({ getQueue: () => ({ scheduleRecurring: async () => "job-123" }) } as any),
+    };
+    return buildHealthcheckKind(mockDeps);
   }
 
   it("creates a new healthcheck configuration and returns entityId", async () => {
@@ -488,9 +489,11 @@ describe("Healthcheck GitOps Kind: System Extension", () => {
           associateSystem: mockService.associateSystem,
           disassociateSystem: mockService.disassociateSystem,
           getSystemConfigurations: mockService.getSystemConfigurations,
+          getConfiguration: mockService.getConfiguration,
         }) as never,
       getHealthCheckRegistry: () => createMockHealthCheckRegistry() as never,
       getCollectorRegistry: () => createMockCollectorRegistry() as never,
+      getQueueManager: () => ({ getQueue: () => ({ scheduleRecurring: async () => "job-123" }) } as any),
     });
   }
 

package/src/healthcheck-gitops-kinds.ts

@@ -22,6 +22,8 @@ import {
   arrayField,
   enumField,
 } from "@checkstack/backend-api";
+import type { QueueManager } from "@checkstack/queue-api";
+import { scheduleHealthCheck } from "./queue-executor";
 
 /**
  * Lazy accessor functions — populated during init(), consumed during reconcile.
@@ -32,6 +34,7 @@ interface HealthcheckGitOpsKindsDeps {
   createService: () => HealthCheckService;
   getHealthCheckRegistry: () => HealthCheckRegistry;
   getCollectorRegistry: () => CollectorRegistry;
+  getQueueManager: () => QueueManager;
 }
 
 // ─── Healthcheck Spec Schema ───────────────────────────────────────────────
@@ -323,8 +326,21 @@ export function buildSystemHealthcheckExtension(
           includeLocal: entry.includeLocal,
         });
 
+        // Retrieve config to get the interval for scheduling
+        const config = await service.getConfiguration(configId);
+        if (config) {
+          await scheduleHealthCheck({
+            queueManager: deps.getQueueManager(),
+            payload: {
+              configId,
+              systemId: systemEntityId,
+            },
+            intervalSeconds: config.intervalSeconds,
+          });
+        }
+
         context.logger.info(
-          `GitOps: associated ${entry.ref.kind} "${entry.ref.name}" (${configId}) with System "${entity.metadata.name}"`,
+          `GitOps: associated ${entry.ref.kind} "${entry.ref.name}" (${configId}) with System "${entity.metadata.name}" and scheduled execution`,
         );
       }
 

package/src/index.ts

@@ -19,6 +19,7 @@ import {
   type HealthCheckRegistry,
   type CollectorRegistry,
 } from "@checkstack/backend-api";
+import type { QueueManager } from "@checkstack/queue-api";
 import { integrationEventExtensionPoint } from "@checkstack/integration-backend";
 import { entityKindExtensionPoint } from "@checkstack/gitops-backend";
 import { z } from "zod";
@@ -99,6 +100,7 @@ export default createBackendPlugin({
     let gitopsDb: SafeDatabase<typeof schema> | undefined;
     let gitopsHealthCheckRegistry: HealthCheckRegistry | undefined;
     let gitopsCollectorRegistry: CollectorRegistry | undefined;
+    let gitopsQueueManager: QueueManager | undefined;
 
     const kindRegistry = env.getExtensionPoint(entityKindExtensionPoint);
     registerHealthcheckGitOpsKinds({
@@ -125,6 +127,11 @@ export default createBackendPlugin({
           throw new Error("CollectorRegistry not initialized");
         return gitopsCollectorRegistry;
       },
+      getQueueManager: () => {
+        if (!gitopsQueueManager)
+          throw new Error("QueueManager not initialized");
+        return gitopsQueueManager;
+      },
     });
 
     env.registerInit({
@@ -155,6 +162,7 @@ export default createBackendPlugin({
         gitopsDb = database;
         gitopsHealthCheckRegistry = healthCheckRegistry;
         gitopsCollectorRegistry = collectorRegistry;
+        gitopsQueueManager = queueManager;
 
         // Create catalog client for notification delegation
         const catalogClient = rpcClient.forPlugin(CatalogApi);

package/src/queue-executor.ts

@@ -101,6 +101,7 @@ export async function scheduleHealthCheck(props: {
  */
 async function notifyStateChange(props: {
   systemId: string;
+  systemName: string;
   previousStatus: HealthCheckStatus;
   newStatus: HealthCheckStatus;
   catalogClient: CatalogClient;
@@ -110,6 +111,7 @@ async function notifyStateChange(props: {
 }): Promise<void> {
   const {
     systemId,
+    systemName,
     previousStatus,
     newStatus,
     catalogClient,
@@ -168,18 +170,18 @@ async function notifyStateChange(props: {
   let importance: "info" | "warning" | "critical";
 
   if (isRecovery) {
-    title = "System health restored";
+    title = `System health restored: ${systemName}`;
     body =
-      "All health checks are now passing. The system has returned to normal operation.";
+      `All health checks for **${systemName}** are now passing. The system has returned to normal operation.`;
     importance = "info";
   } else if (isUnhealthy) {
-    title = "System health critical";
-    body = "Health checks indicate the system is unhealthy and may be down.";
+    title = `System health critical: ${systemName}`;
+    body = `Health checks indicate **${systemName}** is unhealthy and may be down.`;
     importance = "critical";
   } else if (isDegraded) {
-    title = "System health degraded";
+    title = `System health degraded: ${systemName}`;
     body =
-      "Some health checks are failing. The system may be experiencing issues.";
+      `Some health checks for **${systemName}** are failing. The system may be experiencing issues.`;
     importance = "warning";
   } else {
     // No notification for healthy → healthy (if somehow missed above)
@@ -535,6 +537,7 @@ async function executeHealthCheckJob(props: {
       if (newState.status !== previousStatus) {
         await notifyStateChange({
           systemId,
+          systemName,
           previousStatus,
           newStatus: newState.status,
           catalogClient,
@@ -615,6 +618,7 @@ async function executeHealthCheckJob(props: {
     if (newState.status !== previousStatus) {
       await notifyStateChange({
         systemId,
+        systemName,
         previousStatus,
         newStatus: newState.status,
         catalogClient,
@@ -732,6 +736,7 @@ async function executeHealthCheckJob(props: {
     if (newState.status !== previousStatus) {
       await notifyStateChange({
         systemId,
+        systemName,
         previousStatus,
         newStatus: newState.status,
         catalogClient,