feat: healthcheck & worker refactor

README.md

@@ -173,7 +173,7 @@ Check the services are running:
 curl $OUTPOST_URL/api/v1/healthz
 ```
 
-Wait until you get a `OK%` response.
+Wait until you get a 200 response.
 
 Create a tenant with the following command, replacing `$TENANT_ID` with a unique identifier such as "your_org_name", and the `$API_KEY` with the value you set in your `.env`:
 

cmd/e2e/api_test.go

@@ -23,6 +23,20 @@ func (suite *basicSuite) TestHealthzAPI() {
 				Match: &httpclient.Response{
 					StatusCode: http.StatusOK,
 				},
+				Validate: map[string]interface{}{
+					"type": "object",
+					"properties": map[string]interface{}{
+						"status": map[string]interface{}{
+							"type": "string",
+						},
+						"timestamp": map[string]interface{}{
+							"type": "string",
+						},
+						"workers": map[string]interface{}{
+							"type": "object",
+						},
+					},
+				},
 			},
 		},
 	}

cmd/e2e/suites_test.go

@@ -30,14 +30,17 @@ type e2eSuite struct {
 	mockServerInfra   *testinfra.MockServerInfra
 	cleanup           func()
 	client            httpclient.Client
+	appDone           chan struct{}
 }
 
 func (suite *e2eSuite) SetupSuite() {
 	ctx, cancel := context.WithCancel(context.Background())
 	suite.ctx = ctx
 	suite.cancel = cancel
+	suite.appDone = make(chan struct{})
 	suite.client = httpclient.New(fmt.Sprintf("http://localhost:%d/api/v1", suite.config.APIPort), suite.config.APIKey)
 	go func() {
+		defer close(suite.appDone)
 		application := app.New(&suite.config)
 		if err := application.Run(suite.ctx); err != nil {
 			log.Println("Application failed to run", err)
@@ -48,6 +51,8 @@ func (suite *e2eSuite) SetupSuite() {
 func (s *e2eSuite) TearDownSuite() {
 	if s.cancel != nil {
 		s.cancel()
+		// Wait for application to fully shut down before cleaning up resources
+		<-s.appDone
 	}
 	s.cleanup()
 }

docs/apis/openapi.yaml

@@ -1686,17 +1686,101 @@ paths:
     get:
       tags: [Health]
       summary: Health Check
-      description: Simple health check endpoint.
+      description: |
+        Health check endpoint that reports the status of all workers.
+
+        Returns HTTP 200 when all workers are healthy, or HTTP 503 if any worker has failed.
+
+        The response includes:
+        - `status`: Overall health status ("healthy" or "failed")
+        - `timestamp`: When this health check was performed (ISO 8601 format)
+        - `workers`: Map of worker names to their individual health status
+
+        Each worker reports:
+        - `status`: Worker health ("healthy" or "failed")
+
+        Note: Error details are not exposed for security reasons. Check application logs for detailed error information.
       operationId: healthCheck
       security: []
       responses:
         "200":
-          description: Service is healthy.
+          description: Service is healthy - all workers are operational.
           content:
-            text/plain:
+            application/json:
+              schema:
+                type: object
+                required:
+                  - status
+                  - timestamp
+                  - workers
+                properties:
+                  status:
+                    type: string
+                    enum: [healthy]
+                    example: healthy
+                  timestamp:
+                    type: string
+                    format: date-time
+                    description: When this health check was performed
+                    example: "2025-11-11T10:30:00Z"
+                  workers:
+                    type: object
+                    additionalProperties:
+                      type: object
+                      required:
+                        - status
+                      properties:
+                        status:
+                          type: string
+                          enum: [healthy]
+                          example: healthy
+              example:
+                status: healthy
+                timestamp: "2025-11-11T10:30:00Z"
+                workers:
+                  http-server:
+                    status: healthy
+                  retrymq-consumer:
+                    status: healthy
+        "503":
+          description: Service is unhealthy - one or more workers have failed.
+          content:
+            application/json:
               schema:
-                type: string
-                example: OK
+                type: object
+                required:
+                  - status
+                  - timestamp
+                  - workers
+                properties:
+                  status:
+                    type: string
+                    enum: [failed]
+                    example: failed
+                  timestamp:
+                    type: string
+                    format: date-time
+                    description: When this health check was performed
+                    example: "2025-11-11T10:30:15Z"
+                  workers:
+                    type: object
+                    additionalProperties:
+                      type: object
+                      required:
+                        - status
+                      properties:
+                        status:
+                          type: string
+                          enum: [healthy, failed]
+                          example: failed
+              example:
+                status: failed
+                timestamp: "2025-11-11T10:30:15Z"
+                workers:
+                  http-server:
+                    status: healthy
+                  retrymq-consumer:
+                    status: failed
   # Tenants
   /{tenant_id}:
     parameters:

internal/services/api/auth_middleware.go → internal/apirouter/auth_middleware.go

@@ -1,4 +1,4 @@
-package api
+package apirouter
 
 import (
 	"errors"