Fix deployment tooling: shell scripts and Terraform

Terraform (validated with the real terraform CLI - was never actually
run against this cluster, no state file existed):
- Delete main.tf: it declared a duplicate kubernetes_namespace.core
  (also in namespaces.tf) and a duplicate provider "kubernetes" block
  (also in providers.tf), both hard errors that would fail
  `terraform plan` immediately.
- Fix workloads.tf references to 6 files deleted in the manifest
  cleanup (jupiter-sts/svc, atlantis-sts/svc, fiesta-sts/svc) - now
  points at the canonical nearle-jupiter/atlantis/fiesta.yaml.
- Fix every kubernetes_manifest resource: they fed multi-document
  YAML (multiple '---'-separated docs per file) straight into
  yamldecode(), which only parses a single document. Rewrote using a
  split-on-'---' + for_each pattern, confirmed safe first by checking
  separator counts exactly match document counts for every affected
  file (no embedded '---' inside any script/config content).
- Add the doormile namespace; rename kubernetes_namespace to
  kubernetes_namespace_v1 (fixes a deprecation warning).
- `terraform validate` now passes clean.

Shell scripts:
- deploy-nearle-stack.sh only applied 4 of the ~13 files in
  manifests/nearle/ - missing the ConfigMap/Secrets fiesta/jupiter/
  titan/ariane need via envFrom, the fiesta gateway script ConfigMap,
  atlantis entirely, and the Gateway/ReferenceGrant/jupiter-cors-proxy
  resources. Now applies every file (verified by diffing the
  directory listing against the script).
- Added deploy-doormile.sh and deploy-ingress.sh - nothing previously
  applied ingress-unified.yaml or traefik-middlewares.yaml at all.
- Rewrote deploy.sh as an orchestrator calling all of the above in
  order (previously referenced a manifests/namespace.yaml layout that
  hasn't existed since before this repo's initial commit).
- Rewrote check-k8s-status.sh to check the real namespaces
  (core/nearle/alaska/doormile/kubernetes-dashboard) instead of a
  'nats-backend' namespace that never existed in this repo.
- Fixed a `cd` bug in setup-jetstream.sh that made it change into
  shfiles/ and then look for scripts/setup_jetstream.py there (a
  child directory that doesn't exist) - it could never have found its
  own target file. Now pulls NATS credentials from the live
  nats-credentials Secret instead of a third hardcoded copy.

Python scripts:
- sync_manifests.py had hardcoded Windows paths (e:\nats\kubernetes\...)
  - replaced with paths relative to the script's own location so it
  actually runs here (or anywhere). Verified by running it.
- setup_jetstream.py created durable consumers under different names
  than worker.py computes at runtime ({NATS_CONSUMER}_{subject}), so
  its max_deliver/ack_wait settings never actually reached the
  consumers workers bind to. Naming now derived with the same logic
  worker.py uses - verified all 10 derived names match workers.yaml
  exactly.
- purge-old-messages.py had hardcoded NATS credentials with no env
  var override at all - fixed to match the pattern used everywhere
  else.

conf/app.py

@@ -60,7 +60,7 @@ js = None
 # Configuration
 NATS_URL = os.getenv("NATS_URL", "nats://nats-server:4222")
 NATS_USER = os.getenv("NATS_USER", "admin")
-NATS_PASSWORD = os.getenv("NATS_PASSWORD", "package@321#")
+NATS_PASSWORD = os.getenv("NATS_PASSWORD", "")
 
 # Endpoint to NATS subject mapping
 ENDPOINT_ROUTES = {
@@ -172,7 +172,7 @@ async def publish_request_to_nats(endpoint: str, data: Dict[str, Any], request_m
     subject = ENDPOINT_ROUTES.get(endpoint, "api.unknown")
     
     if not js:
-        raise HTTPException(status_code=503, detail="NATS by connected")
+        raise HTTPException(status_code=503, detail="NATS not connected")
 
     try:
         # Create a unique inbox for the reply

conf/nginx-jupiter.conf

@@ -12,7 +12,15 @@ http {
             # Proxy to Kubernetes NodePort (30822)
             # NodePorts are bound to 0.0.0.0 and are more reliable to access from host.docker.internal
             proxy_pass http://jupiter_k8s;
-            
+
+            # Strip any CORS headers the backend may set itself, so we don't
+            # end up sending duplicate Access-Control-* headers (browsers
+            # reject a response that has more than one value for these).
+            proxy_hide_header 'Access-Control-Allow-Origin';
+            proxy_hide_header 'Access-Control-Allow-Methods';
+            proxy_hide_header 'Access-Control-Allow-Headers';
+            proxy_hide_header 'Access-Control-Max-Age';
+
             proxy_set_header Host $host;
             proxy_set_header X-Real-IP $remote_addr;
             proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

conf/worker.py

@@ -12,6 +12,7 @@ import asyncio
 import aiohttp
 import nats
 from nats.errors import TimeoutError as NatsTimeoutError
+from nats.js.api import ConsumerConfig
 from prometheus_client import Counter, Histogram, Gauge, start_http_server
 import signal
 import sys
@@ -25,7 +26,7 @@ messages_in_flight = Gauge('worker_messages_in_flight', 'Messages currently bein
 # Configuration
 NATS_URL = os.getenv("NATS_URL", "nats://nats-server:4222")
 NATS_USER = os.getenv("NATS_USER", "admin")
-NATS_PASSWORD = os.getenv("NATS_PASSWORD", "package@321#")
+NATS_PASSWORD = os.getenv("NATS_PASSWORD", "")
 
 # Domain Configuration (Env Vars from Deployment)
 NATS_STREAM = os.getenv("NATS_STREAM", "ORDERS")
@@ -35,6 +36,10 @@ FILTER_SUBJECTS = os.getenv("FILTER_SUBJECT", "api.v1.mob.orders.*").split(",")
 
 WORKER_CONCURRENCY = int(os.getenv("WORKER_CONCURRENCY", "10"))
 BASE_URL = os.getenv("EXTERNAL_BASE_URL", "https://jupiter.nearle.app")
+# Must stay comfortably above the outbound HTTP timeout below (30s), otherwise
+# JetStream can redeliver a message to another worker while this one is still
+# waiting on a slow-but-legitimate response, causing a duplicate forward.
+ACK_WAIT_SECONDS = int(os.getenv("ACK_WAIT_SECONDS", "60"))
 
 # Endpoint mapping is still useful for constructing the target URL
 ENDPOINT_MAPPING = {
@@ -56,6 +61,7 @@ js = None
 session: aiohttp.ClientSession = None
 running = True
 semaphore = None # Initialized in main
+active_tasks: set = set() # In-flight process_message() tasks, drained on shutdown
 
 def signal_handler(sig, frame):
     global running
@@ -80,7 +86,10 @@ async def forward_to_external(endpoint: str, payload: dict, api_key: str = None,
     if api_key:
         headers["Authorization"] = f"Bearer {api_key}"
 
-    data_to_forward = payload.get("data", payload)
+    if "data" not in payload:
+        print(f"?? Message for {endpoint} missing 'data' field, dropping.")
+        return "DROP", None
+    data_to_forward = payload["data"]
 
     # Payload Normalization for logs
     if endpoint == "/live/api/v2/deliveries/createdeliverylog":
@@ -166,7 +175,8 @@ async def process_message(msg):
             await msg.term()
         except Exception as e:
             print(f"? Critical Worker Error: {e}")
-            await msg.nak()
+            # Delay avoids a tight redelivery loop if this is a persistent bug
+            await msg.nak(delay=5)
         finally:
             messages_in_flight.dec()
             duration = asyncio.get_event_loop().time() - start_time
@@ -210,8 +220,9 @@ async def main():
             try:
                 sub = await js.pull_subscribe(
                     subject,
-                    durable=durable_name, 
+                    durable=durable_name,
-                    stream=NATS_STREAM
+                    stream=NATS_STREAM,
+                    config=ConsumerConfig(ack_wait=ACK_WAIT_SECONDS)
                 )
                 subs.append(sub)
             except Exception as e:
@@ -231,7 +242,9 @@ async def main():
                     # Batch size 10, short timeout to keep loop responsive
                     msgs = await sub.fetch(10, timeout=0.5)
                     for m in msgs:
-                        asyncio.create_task(process_message(m))
+                        task = asyncio.create_task(process_message(m))
+                        active_tasks.add(task)
+                        task.add_done_callback(active_tasks.discard)
                 except NatsTimeoutError:
                     pass
                 except Exception as e:
@@ -244,6 +257,9 @@ async def main():
     except Exception as e:
         print(f"?? Fatal Error: {e}")
     finally:
+        if active_tasks:
+            print(f"?? Draining {len(active_tasks)} in-flight message(s) before shutdown...")
+            await asyncio.wait(active_tasks, timeout=25)
         if session:
             await session.close()
         if nc:

docker-compose.yml

@@ -106,6 +106,27 @@ services:
       - "traefik.http.routers.atlantis-api.tls.certresolver=letsencrypt"
       - "traefik.http.services.atlantis-api.loadbalancer.server.port=8205"
 
+  # Doormile API Proxy (doormile.com -> K8s NodePort 30830)
+  doormile-proxy:
+    image: nginx:alpine
+    container_name: doormile-proxy
+    restart: unless-stopped
+    ports:
+      - "8206:8206"
+    volumes:
+      - ./conf/nginx-doormile.conf:/etc/nginx/nginx.conf:ro
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    networks:
+      - web
+    labels:
+      - "traefik.enable=true"
+      - "traefik.docker.network=web"
+      - "traefik.http.routers.doormile-api.rule=Host(`doormile.com`)"
+      - "traefik.http.routers.doormile-api.tls=true"
+      - "traefik.http.routers.doormile-api.tls.certresolver=letsencrypt"
+      - "traefik.http.services.doormile-api.loadbalancer.server.port=8206"
+
 networks:
   web:
     external: true

manifests/alaska/alaska.yaml

@@ -330,10 +330,6 @@ spec:
     - name: deliveries-service
       port: 8000
       weight: 100
-    backendRefs:
-    - name: deliveries-service
-      port: 8000
-      weight: 100
   - matches:
     - path:
         type: PathPrefix

manifests/alaska/k8s-dashboard.yaml

@@ -34,19 +34,6 @@ metadata:
     kubernetes.io/service-account.name: "admin-user"
 type: kubernetes.io/service-account-token
 ---
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: kubernetes-dashboard-admin
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: cluster-admin
-subjects:
-- kind: ServiceAccount
-  name: kubernetes-dashboard
-  namespace: kubernetes-dashboard
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -75,9 +62,6 @@ spec:
         args:
           - --auto-generate-certificates
           - --namespace=kubernetes-dashboard
-          - --enable-skip-login
-          - --enable-insecure-login
-          - --insecure-port=9090
         volumeMounts:
         - name: kubernetes-dashboard-certs
           mountPath: /certs
@@ -135,10 +119,6 @@ spec:
     targetPort: 8443
     protocol: TCP
     name: https
-  - port: 9090
-    targetPort: 9090
-    protocol: TCP
-    name: http
   selector:
     k8s-app: kubernetes-dashboard
 ---
@@ -307,22 +287,3 @@ spec:
     targetPort: 8083
     nodePort: 30826
     protocol: TCP
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: dashboard-loadbalancer
-  namespace: kubernetes-dashboard
-  labels:
-    app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/component: loadbalancer
-spec:
-  type: NodePort
-  selector:
-    k8s-app: kubernetes-dashboard
-  ports:
-  - name: http
-    port: 9090
-    targetPort: 9090  # Dashboard HTTP port
-    nodePort: 30827   # Fixed NodePort for nginx proxy
-    protocol: TCP

manifests/core/worker-script.yaml

@@ -19,6 +19,7 @@ data:
     import aiohttp
     import nats
     from nats.errors import TimeoutError as NatsTimeoutError
+    from nats.js.api import ConsumerConfig
     from prometheus_client import Counter, Histogram, Gauge, start_http_server
     import signal
     import sys
@@ -32,17 +33,21 @@ data:
     # Configuration
     NATS_URL = os.getenv("NATS_URL", "nats://nats-server:4222")
     NATS_USER = os.getenv("NATS_USER", "admin")
-    NATS_PASSWORD = os.getenv("NATS_PASSWORD", "package@321#")
+    NATS_PASSWORD = os.getenv("NATS_PASSWORD", "")
 
     # Domain Configuration (Env Vars from Deployment)
     NATS_STREAM = os.getenv("NATS_STREAM", "ORDERS")
     NATS_CONSUMER = os.getenv("NATS_CONSUMER", "orders-worker")
     # Supports comma-separated subjects: "api.v1.orders.*,api.v2.orders.*"
     FILTER_SUBJECTS = os.getenv("FILTER_SUBJECT", "api.v1.mob.orders.*").split(",")
-    
+
     WORKER_CONCURRENCY = int(os.getenv("WORKER_CONCURRENCY", "10"))
     BASE_URL = os.getenv("EXTERNAL_BASE_URL", "https://jupiter.nearle.app")
-    
+    # Must stay comfortably above the outbound HTTP timeout below (30s), otherwise
+    # JetStream can redeliver a message to another worker while this one is still
+    # waiting on a slow-but-legitimate response, causing a duplicate forward.
+    ACK_WAIT_SECONDS = int(os.getenv("ACK_WAIT_SECONDS", "60"))
+
     # Endpoint mapping is still useful for constructing the target URL
     ENDPOINT_MAPPING = {
         "/live/api/v1/deliveries/createdeliveries": f"{BASE_URL}/live/api/v1/deliveries/createdeliveries",
@@ -63,6 +68,7 @@ data:
     session: aiohttp.ClientSession = None
     running = True
     semaphore = None # Initialized in main
+    active_tasks: set = set() # In-flight process_message() tasks, drained on shutdown
 
     def signal_handler(sig, frame):
         global running
@@ -87,7 +93,10 @@ data:
         if api_key:
             headers["Authorization"] = f"Bearer {api_key}"
 
-        data_to_forward = payload.get("data", payload)
+        if "data" not in payload:
+            print(f"?? Message for {endpoint} missing 'data' field, dropping.")
+            return "DROP", None
+        data_to_forward = payload["data"]
 
         # Payload Normalization for logs
         if endpoint == "/live/api/v2/deliveries/createdeliverylog":
@@ -97,7 +106,7 @@ data:
                 data_to_forward = [data_to_forward]
 
         http_method = method.upper() if method else "POST"
-        
+    
         try:
             # We use the global 'session' here
             async with session.request(
@@ -108,7 +117,7 @@ data:
                 headers=headers, 
                 timeout=aiohttp.ClientTimeout(total=30)
             ) as response:
-                
+            
                 body = None
                 try:
                     body = await response.json()
@@ -118,7 +127,7 @@ data:
                 if 200 <= response.status < 300:
                     return "OK", body
                 elif response.status >= 500:
-                    print(f"?? Server Error {response.status} from {endpoint}: {body}")
+                    print(f"?? Server Error {response.status} from {endpoint}")
                     return "RETRY", body
                 else:
                     print(f"?? Client Error {response.status} from {endpoint}: {body}")
@@ -136,7 +145,7 @@ data:
             messages_in_flight.inc()
             start_time = asyncio.get_event_loop().time()
             endpoint = "unknown"
-            
+        
             try:
                 payload = json.loads(msg.data.decode())
                 endpoint = payload.get("endpoint", payload.get("original_path", "unknown"))
@@ -145,14 +154,14 @@ data:
                 print(f"?? Processing {endpoint}")
 
                 api_key = os.getenv("EXTERNAL_ENDPOINT_API_KEY", "")
-                
+            
                 # Single attempt
                 status, response_data = await forward_to_external(endpoint, payload, api_key, http_method)
-                
+            
                 if status == "OK":
                     await msg.ack()
                     messages_processed.labels(status="success", endpoint=endpoint).inc()
-                    
+                
                     # Request-Reply Logic
                     if msg.reply:
                         reply_payload = json.dumps(response_data) if isinstance(response_data, (dict, list)) else str(response_data)
@@ -162,7 +171,7 @@ data:
                     # Unrecoverable error or unknown endpoint
                     await msg.term() # Terminate stops redelivery
                     messages_processed.labels(status="dropped", endpoint=endpoint).inc()
-                
+            
                 else: # RETRY
                     # Let JetStream handle backoff
                     await msg.nak(delay=2) # Custom delay before redelivery if desired, or just nak()
@@ -173,7 +182,8 @@ data:
                 await msg.term()
             except Exception as e:
                 print(f"? Critical Worker Error: {e}")
-                await msg.nak()
+                # Delay avoids a tight redelivery loop if this is a persistent bug
+                await msg.nak(delay=5)
             finally:
                 messages_in_flight.dec()
                 duration = asyncio.get_event_loop().time() - start_time
@@ -181,7 +191,7 @@ data:
 
     async def main():
         global nc, js, session, semaphore
-        
+    
         print(f"?? Starting Worker for Domain: {NATS_CONSUMER}")
         print(f"?? Stream: {NATS_STREAM}, Subjects: {FILTER_SUBJECTS}")
         print(f"?? Concurrency: {WORKER_CONCURRENCY}")
@@ -202,12 +212,12 @@ data:
 
             # Create Pull Subscriptions for each filter subject
             # All sharing the same Consumer Name ensuring load balancing if multiple pods run this
-            
+        
             subs = []
             for subject in FILTER_SUBJECTS:
                 subject = subject.strip()
                 if not subject: continue
-                
+            
                 # FIX: On WorkQueue streams, we cannot reuse the same durable name for different filters
                 # We append a sanitized version of the subject to ensure uniqueness per filter
                 clean_subject_suffix = subject.replace(".", "_").replace("*", "all").replace(">", "all")
@@ -217,8 +227,9 @@ data:
                 try:
                     sub = await js.pull_subscribe(
                         subject,
-                        durable=durable_name, 
+                        durable=durable_name,
-                        stream=NATS_STREAM
+                        stream=NATS_STREAM,
+                        config=ConsumerConfig(ack_wait=ACK_WAIT_SECONDS)
                     )
                     subs.append(sub)
                 except Exception as e:
@@ -238,19 +249,24 @@ data:
                         # Batch size 10, short timeout to keep loop responsive
                         msgs = await sub.fetch(10, timeout=0.5)
                         for m in msgs:
-                            asyncio.create_task(process_message(m))
+                            task = asyncio.create_task(process_message(m))
+                            active_tasks.add(task)
+                            task.add_done_callback(active_tasks.discard)
                     except NatsTimeoutError:
                         pass
                     except Exception as e:
                         print(f"?? Fetch Error: {e}")
                         await asyncio.sleep(1)
-                
+            
                 # Small sleep to prevent tight loop if no messages
                 # await asyncio.sleep(0.01) 
 
         except Exception as e:
             print(f"?? Fatal Error: {e}")
         finally:
+            if active_tasks:
+                print(f"?? Draining {len(active_tasks)} in-flight message(s) before shutdown...")
+                await asyncio.wait(active_tasks, timeout=25)
             if session:
                 await session.close()
             if nc:

manifests/core/worker-statefulset.yaml

@@ -27,6 +27,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       securityContext:
         runAsUser: 1000
         runAsGroup: 1000

manifests/core/workers.yaml

@@ -22,6 +22,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       tolerations:
       - key: dedicated
         operator: Equal
@@ -58,6 +59,11 @@ spec:
       - name: worker
         image: workolik360/nats-worker:v1.1.0
         imagePullPolicy: IfNotPresent
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         command: ["python3", "-u", "/scripts/worker.py"]
         volumeMounts:
         - name: worker-script-vol
@@ -132,6 +138,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       tolerations:
       - key: dedicated
         operator: Equal
@@ -168,6 +175,11 @@ spec:
       - name: worker
         image: workolik360/nats-worker:v1.1.0
         imagePullPolicy: IfNotPresent
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         command: ["python3", "-u", "/scripts/worker.py"]
         volumeMounts:
         - name: worker-script-vol
@@ -236,6 +248,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       tolerations:
       - key: dedicated
         operator: Equal
@@ -272,6 +285,11 @@ spec:
       - name: worker
         image: workolik360/nats-worker:v1.1.0
         imagePullPolicy: IfNotPresent
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         command: ["python3", "-u", "/scripts/worker.py"]
         volumeMounts:
         - name: worker-script-vol
@@ -346,6 +364,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       tolerations:
       - key: dedicated
         operator: Equal
@@ -382,6 +401,11 @@ spec:
       - name: worker
         image: workolik360/nats-worker:v1.1.0
         imagePullPolicy: IfNotPresent
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         command: ["python3", "-u", "/scripts/worker.py"]
         volumeMounts:
         - name: worker-script-vol
@@ -456,6 +480,7 @@ spec:
         prometheus.io/port: "9090"
         prometheus.io/path: "/metrics"
     spec:
+      terminationGracePeriodSeconds: 45
       tolerations:
       - key: dedicated
         operator: Equal
@@ -492,6 +517,11 @@ spec:
       - name: worker
         image: workolik360/nats-worker:v1.1.0
         imagePullPolicy: IfNotPresent
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         command: ["python3", "-u", "/scripts/worker.py"]
         volumeMounts:
         - name: worker-script-vol

manifests/doormile/miletruth.yaml

@@ -2,26 +2,31 @@ apiVersion: v1
 kind: Namespace
 metadata:
   name: doormile
-
+  labels:
-  Read 1 file
+    name: doormile
-
+---
-Found the critical issue — INTERNAL_API_KEY not set in the manifest means
-all /internal/* endpoode explicitly rejects empty keys). That plus the NATS_URL duplicate.
-
-Here's the corrected miletruth.yaml with all missing env vars added. Run
-this on the server:
-
-cat > /root/kuberneteh.yaml << 'EOF'
 apiVersion: v1
-kind: Namespace
+kind: Secret
 metadata:
-  name: doormile
+  name: doormile-secrets
+  namespace: doormile
+  labels:
+    app: doormile
+type: Opaque
+stringData:
+  DB_PASSWORD: "Package@321#"
+  REDIS_PASSWORD: "Package@321#"
+  NATS_USER: "doormile"
+  NATS_PASSWORD: "Package@321#"
 ---
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
   name: doormile
   namespace: doormile
+  labels:
+    app: doormile
+    app-group: doormile-api
 spec:
   serviceName: "doormile-service"
   replicas: 3
@@ -33,57 +38,68 @@ spec:
     metadata:
       labels:
         app: doormile
-        app-group: do
+        app-group: doormile-api
     spec:
       containers:
       - name: doormile
-        image: doormi
+        image: doormile/doormile-backend:latest
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
+        ports:
+        - containerPort: 8081
         env:
-        - name: ENV
+        - name: DB_HOST
-          value: "production"
-        - name: APP_PORT
-          value: "8081"
-        - name: DB_HO
           value: "31.97.228.132"
-        - name: DB_PO
+        - name: DB_PORT
           value: "5433"
-        - name: DB_NA
+        - name: DB_NAME
           value: "logistics"
-        - name: DB_US
+        - name: DB_USER
           value: "admin"
         - name: DB_PASSWORD
-          value: "Pac
+          valueFrom:
+            secretKeyRef:
+              name: doormile-secrets
+              key: DB_PASSWORD
         - name: REDIS_HOST
           value: "31.97.228.132"
-        - name: REDIS
+        - name: REDIS_PORT
           value: "6379"
-        - name: REDIS_USER
-          value: "adm
         - name: REDIS_PASSWORD
-          value: "Package@321#"
+          valueFrom:
-        - name: JWT_S
+            secretKeyRef:
-          value: "DoormileSuperSecretJWTKey2026!"
+              name: doormile-secrets
-        - name: NATS_
+              key: REDIS_PASSWORD
+        - name: NATS_URL
           value: "nats://66.116.226.161:4223"
-        - name: NATS_
+        - name: NATS_USER
-          value: "doormile"
+          valueFrom:
+            secretKeyRef:
+              name: doormile-secrets
+              key: NATS_USER
         - name: NATS_PASSWORD
-          value: "Pac
+          valueFrom:
-        - name: INTERNAL_API_KEY
+            secretKeyRef:
-          value: "doormile-internal-2024"
+              name: doormile-secrets
+              key: NATS_PASSWORD
 ---
 apiVersion: v1
 kind: Service
 metadata:
   name: doormile-service
   namespace: doormile
+  labels:
+    app: doormile
 spec:
   type: NodePort
   selector:
     app-group: doormile-api
   ports:
     - protocol: TCP
-      port: 8081
+      port: 8081        # Expose port 8081 internally
-      targetPort: 808
+      targetPort: 8081  # The port the backend application actually listens on
-      nodePort: 30830
+      nodePort: 30830   # This must match what NGINX is looking for

manifests/nearle/atlantis-sts.yaml

@@ -1,61 +0,0 @@
-apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: atlantis
-  namespace: nearle
-  labels:
-    app: atlantis
-spec:
-  serviceName: "atlantis"
-  replicas: 2
-  selector:
-    matchLabels:
-      app: atlantis
-  template:
-    metadata:
-      labels:
-        app: atlantis
-    spec:
-      tolerations:
-      - key: dedicated
-        operator: Equal
-        value: apps
-        effect: NoSchedule
-      affinity:
-        nodeAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            nodeSelectorTerms:
-            - matchExpressions:
-              - key: node-role.workolik/app
-                operator: In
-                values:
-                - "true"
-        podAntiAffinity:
-          preferredDuringSchedulingIgnoredDuringExecution:
-          - weight: 100
-            podAffinityTerm:
-              labelSelector:
-                matchLabels:
-                  app: atlantis
-              topologyKey: kubernetes.io/hostname
-      topologySpreadConstraints:
-      - maxSkew: 1
-        topologyKey: kubernetes.io/hostname
-        whenUnsatisfiable: ScheduleAnyway
-        labelSelector:
-          matchLabels:
-            app: atlantis
-      containers:
-      - name: backend
-        image: nearlecommerce/atlantis:v0.0.41
-        imagePullPolicy: Always
-        ports:
-        - containerPort: 3000
-        env:
-        - name: PORT
-          value: "3000"
-        envFrom:
-        - configMapRef:
-            name: nearle-config
-        - secretRef:
-            name: app-secrets

manifests/nearle/atlantis-svc.yaml

@@ -1,16 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: atlantis
-  namespace: nearle
-  labels:
-    app: atlantis
-spec:
-  type: NodePort
-  ports:
-  - port: 80
-    targetPort: 3000
-    nodePort: 30825
-    protocol: TCP
-  selector:
-    app: atlantis

manifests/nearle/fiesta-gateway.yaml

@@ -67,7 +67,7 @@ data:
     # Configuration
     NATS_URL = os.getenv("NATS_URL", "nats://nats-server:4222")
     NATS_USER = os.getenv("NATS_USER", "admin")
-    NATS_PASSWORD = os.getenv("NATS_PASSWORD", "package@321#")
+    NATS_PASSWORD = os.getenv("NATS_PASSWORD", "")
 
     # Endpoint to NATS subject mapping
     ENDPOINT_ROUTES = {
@@ -179,7 +179,7 @@ data:
         subject = ENDPOINT_ROUTES.get(endpoint, "api.unknown")
     
         if not js:
-            raise HTTPException(status_code=503, detail="NATS by connected")
+            raise HTTPException(status_code=503, detail="NATS not connected")
 
         try:
             # Create a unique inbox for the reply

manifests/nearle/fiesta-sts.yaml

@@ -1,99 +0,0 @@
-apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: fiesta
-  namespace: nearle
-  labels:
-    app: fiesta
-spec:
-  serviceName: "fiesta"
-  replicas: 3
-  selector:
-    matchLabels:
-      app: fiesta
-  template:
-    metadata:
-      labels:
-        app: fiesta
-    spec:
-      tolerations:
-      - key: dedicated
-        operator: Equal
-        value: apps
-        effect: NoSchedule
-      affinity:
-        nodeAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            nodeSelectorTerms:
-            - matchExpressions:
-              - key: node-role.workolik/app
-                operator: In
-                values:
-                - "true"
-        podAntiAffinity:
-          preferredDuringSchedulingIgnoredDuringExecution:
-          - weight: 100
-            podAffinityTerm:
-              labelSelector:
-                matchLabels:
-                  app: fiesta
-              topologyKey: kubernetes.io/hostname
-      topologySpreadConstraints:
-      - maxSkew: 1
-        topologyKey: kubernetes.io/hostname
-        whenUnsatisfiable: ScheduleAnyway
-        labelSelector:
-          matchLabels:
-            app: fiesta
-      containers:
-      - name: backend
-        image: nearlecommerce/fiesta:v1.3.67
-        imagePullPolicy: Always
-        ports:
-        - containerPort: 1122
-        envFrom:
-        - configMapRef:
-            name: nearle-config
-        - secretRef:
-            name: app-secrets
-        env:
-        - name: PORT
-          value: "1122"
-        - name: NATS_USER
-          valueFrom:
-            secretKeyRef:
-              name: nats-credentials
-              key: username
-        - name: NATS_PASSWORD
-          valueFrom:
-            secretKeyRef:
-              name: nats-credentials
-              key: password
-      - name: gateway
-        image: workolik360/alaska:v1.2.0
-        imagePullPolicy: Always
-        ports:
-        - containerPort: 8000
-          name: http
-        volumeMounts:
-        - name: gateway-script
-          mountPath: /app/app.py
-          subPath: app.py
-        envFrom:
-        - configMapRef:
-            name: nearle-config
-        env:
-        - name: NATS_USER
-          valueFrom:
-            secretKeyRef:
-              name: nats-credentials
-              key: username
-        - name: NATS_PASSWORD
-          valueFrom:
-            secretKeyRef:
-              name: nats-credentials
-              key: password
-      volumes:
-      - name: gateway-script
-        configMap:
-          name: fiesta-gateway-script

manifests/nearle/fiesta-svc.yaml

@@ -1,21 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: fiesta
-  namespace: nearle
-  labels:
-    app: fiesta
-spec:
-  type: NodePort
-  ports:
-  - port: 80
-    targetPort: 1122
-    nodePort: 30823
-    protocol: TCP
-    name: main
-  - port: 8000
-    targetPort: 8000
-    name: gateway
-    protocol: TCP
-  selector:
-    app: fiesta

manifests/nearle/jupiter-cors-proxy.yaml

@@ -16,6 +16,15 @@ data:
 
             location / {
                 proxy_pass http://jupiter_backend;
+
+                # Strip any CORS headers the backend may set itself, so we don't
+                # end up sending duplicate Access-Control-* headers (browsers
+                # reject a response that has more than one value for these).
+                proxy_hide_header 'Access-Control-Allow-Origin';
+                proxy_hide_header 'Access-Control-Allow-Methods';
+                proxy_hide_header 'Access-Control-Allow-Headers';
+                proxy_hide_header 'Access-Control-Max-Age';
+
                 proxy_set_header Host $host;
                 proxy_set_header X-Real-IP $remote_addr;
                 proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

manifests/nearle/jupiter-sts.yaml

@@ -1,77 +0,0 @@
-apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: jupiter
-  namespace: nearle
-  labels:
-    app: jupiter
-spec:
-  serviceName: "jupiter"
-  replicas: 3
-  selector:
-    matchLabels:
-      app: jupiter
-  template:
-    metadata:
-      labels:
-        app: jupiter
-    spec:
-      tolerations:
-      - key: dedicated
-        operator: Equal
-        value: apps
-        effect: NoSchedule
-      affinity:
-        nodeAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            nodeSelectorTerms:
-            - matchExpressions:
-              - key: node-role.workolik/app
-                operator: In
-                values:
-                - "true"
-        podAntiAffinity:
-          preferredDuringSchedulingIgnoredDuringExecution:
-          - weight: 100
-            podAffinityTerm:
-              labelSelector:
-                matchLabels:
-                  app: jupiter
-              topologyKey: kubernetes.io/hostname
-      topologySpreadConstraints:
-      - maxSkew: 1
-        topologyKey: kubernetes.io/hostname
-        whenUnsatisfiable: ScheduleAnyway
-        labelSelector:
-          matchLabels:
-            app: jupiter
-      containers:
-      - name: jupiter
-        image: nearlecommerce/jupiter:v2.7.53
-        imagePullPolicy: Always
-        ports:
-        - containerPort: 1009
-        env:
-        - name: PORT
-          value: "1009"
-        - name: TZ
-          value: "Asia/Kolkata"
-        volumeMounts:
-        - name: tz-config
-          mountPath: /etc/localtime
-          readOnly: true
-        - name: tz-data
-          mountPath: /usr/share/zoneinfo
-          readOnly: true
-        envFrom:
-        - configMapRef:
-            name: nearle-config
-        - secretRef:
-            name: app-secrets
-      volumes:
-      - name: tz-config
-        hostPath:
-          path: /usr/share/zoneinfo/Asia/Kolkata
-      - name: tz-data
-        hostPath:
-          path: /usr/share/zoneinfo

manifests/nearle/jupiter-svc.yaml

@@ -1,16 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: jupiter
-  namespace: nearle
-  labels:
-    app: jupiter
-spec:
-  type: NodePort
-  ports:
-  - port: 80
-    targetPort: 1009
-    nodePort: 30822
-    protocol: TCP
-  selector:
-    app: jupiter

manifests/nearle/nearle-ariane.yaml

@@ -49,6 +49,11 @@ spec:
       - name: backend
         image: nearlecommerce/ariane:v1.0.22
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 1000
         env:

manifests/nearle/nearle-atlantis.yaml

@@ -49,6 +49,11 @@ spec:
       - name: backend
         image: nearlecommerce/atlantis:v0.0.41
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 3000
         env:

manifests/nearle/nearle-fiesta.yaml

@@ -47,8 +47,13 @@ spec:
             app: fiesta
       containers:
       - name: backend
-        image: nearlecommerce/fiesta:v1.3.50
+        image: nearlecommerce/fiesta:v1.3.78
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 1122
         envFrom:
@@ -72,6 +77,11 @@ spec:
       - name: gateway
         image: workolik360/alaska:v1.2.0
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 8000
           name: http

manifests/nearle/nearle-jupiter.yaml

@@ -47,8 +47,13 @@ spec:
             app: jupiter
       containers:
       - name: jupiter
-        image: nearlecommerce/jupiter:v2.7.31
+        image: nearlecommerce/jupiter:v2.7.55
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 1009
         env:

manifests/nearle/nearle-titan.yaml

@@ -49,6 +49,11 @@ spec:
       - name: backend
         image: groomgear/groomgear:v1.0.41
         imagePullPolicy: Always
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop:
+              - ALL
         ports:
         - containerPort: 1006
 ---

scripts/purge-old-messages.py

@@ -7,9 +7,9 @@ import nats
 import os
 
 async def purge_messages():
-    nats_url = "nats://nats.workolik.com:4222"
+    nats_url = os.getenv("NATS_URL", "nats://nats.workolik.com:4222")
-    nats_user = "admin"
+    nats_user = os.getenv("NATS_USER", "admin")
-    nats_password = "package@321#"
+    nats_password = os.getenv("NATS_PASSWORD", "")
     
     try:
         print(f"Connecting to NATS at {nats_url}...")

scripts/setup_jetstream.py

@@ -1,77 +1,54 @@
 #!/usr/bin/env python3
 """
-Setup JetStream stream and consumer for NATS
+Setup JetStream streams and consumers for NATS
 Run this after NATS is deployed and running
+
+Durable consumer names are derived with the exact same logic worker.py uses
+at runtime (NATS_CONSUMER + sanitized subject). WORKER_DOMAINS below must be
+kept in sync with the NATS_STREAM / NATS_CONSUMER / FILTER_SUBJECT env vars
+in manifests/core/workers.yaml - if they drift apart, the consumers created
+here (with their max_deliver/ack_wait settings) will never be the ones the
+workers actually bind to, and this script's config becomes a no-op.
 """
 import asyncio
 import nats
 import os
 import sys
 
+WORKER_DOMAINS = [
+    {"stream": "ORDERS", "consumer": "orders-worker", "subjects": [
+        "api.v1.mob.orders.createorder",
+    ]},
+    {"stream": "DELIVERIES", "consumer": "deliveries-worker", "subjects": [
+        "api.v1.deliveries.createdeliveries",
+        "api.v1.deliveries.updatedelivery",
+        "api.v2.deliveries.createdeliverylog",
+    ]},
+    {"stream": "CUSTOMERS", "consumer": "customers-worker", "retention": "work", "subjects": [
+        "api.v1.mob.customers.login",
+        "api.v1.mob.customers.create",
+    ]},
+    {"stream": "RIDER", "consumer": "rider-logs-worker", "subjects": [
+        "api.v2.partners.createriderlog",
+        "api.v2.partners.createbreaklog",
+        "api.v2.partners.updatebreaklog",
+    ]},
+    {"stream": "PRODUCTS", "consumer": "products-worker", "subjects": [
+        "api.v1.web.products.create",
+    ]},
+]
+
+
+def durable_name(consumer: str, subject: str) -> str:
+    """Mirrors worker.py's durable-name derivation exactly."""
+    suffix = subject.replace(".", "_").replace("*", "all").replace(">", "all")
+    return f"{consumer}_{suffix}"
+
+
 async def setup_jetstream():
-    """Configure JetStream with two streams (DELIVERIES, RIDER) and per-subject consumers."""
     nats_url = os.getenv("NATS_URL", "nats://nats.workolik.com:4222")
     nats_user = os.getenv("NATS_USER", "admin")
-    nats_password = os.getenv("NATS_PASSWORD", "package@321#")
+    nats_password = os.getenv("NATS_PASSWORD", "")
-
-    # Stream definitions
-    streams = {
-        "DELIVERIES": {
-            "subjects": [
-                "api.v1.deliveries.createdeliveries",
-                "api.v1.deliveries.updatedelivery",
-                "api.v2.deliveries.createdeliverylog",
-            ],
-        },
-        "RIDER": {
-            "subjects": [
-                "api.v2.partners.createriderlog",
-                "api.v2.partners.createbreaklog",
-                "api.v2.partners.updatebreaklog",
-            ],
-        },
-        "ORDERS": {
-            "subjects": [
-                "api.v1.mob.orders.createorder",
-            ],
-        },
-        "PRODUCTS": {
-            "subjects": [
-                "api.v1.web.products.create",
-            ],
-        },
-        "CUSTOMERS": {
-            "subjects": [
-                "api.v1.mob.customers.login",
-                "api.v1.mob.customers.create",
-            ],
-            "retention": "work"  # Special handling for Login queue: delete immediately after ack
-        },
-    }
-
-    # Per-subject durable consumers
-    consumers = {
-        "DELIVERIES": {
-            "api.v1.deliveries.createdeliveries": "deliveries_createdeliveries",
-            "api.v1.deliveries.updatedelivery": "deliveries_updatedelivery",
-            "api.v2.deliveries.createdeliverylog": "deliveries_createdeliverylog",
-        },
-        "RIDER": {
-            "api.v2.partners.createriderlog": "rider_createriderlog",
-            "api.v2.partners.createbreaklog": "rider_createbreaklog",
-            "api.v2.partners.updatebreaklog": "rider_updatebreaklog",
-        },
-        "ORDERS": {
-            "api.v1.mob.orders.createorder": "orders_createorder",
-        },
-        "PRODUCTS": {
-            "api.v1.web.products.create": "products_create",
-        },
-        "CUSTOMERS": {
-            "api.v1.mob.customers.login": "customers_login",
-            "api.v1.mob.customers.create": "customers_create",
-        },
-    }
 
     try:
         print(f"Connecting to NATS at {nats_url}...")
@@ -85,17 +62,16 @@ async def setup_jetstream():
         js = nc.jetstream()
 
         # Create / recreate streams
-        for stream_name, cfg in streams.items():
+        for domain in WORKER_DOMAINS:
+            stream_name = domain["stream"]
+            subjects = domain["subjects"]
+            retention_policy = domain.get("retention", "limits")
             try:
                 info = await js.stream_info(stream_name)
                 print(f"⚠️  Stream '{stream_name}' already exists with subjects={info.config.subjects}, updating...")
-                
-                # Determine retention policy
-                retention_policy = cfg.get("retention", "limits")
-                
                 await js.update_stream(
                     name=stream_name,
-                    subjects=cfg["subjects"],
+                    subjects=subjects,
                     storage="memory",
                     retention=retention_policy,
                     max_age=24 * 60 * 60,
@@ -106,13 +82,9 @@ async def setup_jetstream():
             except Exception as e:
                 if "not found" in str(e).lower() or "404" in str(e).lower():
                     print(f"Creating stream '{stream_name}'...")
-                    
-                    # Determine retention policy (use 'limits' by default, 'work' for queues)
-                    retention_policy = cfg.get("retention", "limits")
-                    
                     await js.add_stream(
                         name=stream_name,
-                        subjects=cfg["subjects"],
+                        subjects=subjects,
                         storage="memory",
                         retention=retention_policy,
                         max_age=24 * 60 * 60,
@@ -123,10 +95,14 @@ async def setup_jetstream():
                 else:
                     print(f"⚠️  Could not inspect stream '{stream_name}': {e}")
 
-        # Create durable consumers per subject
+        # Create durable consumers per subject - names match what worker.py
+        # computes at runtime, so max_deliver/ack_wait here actually apply.
         print("\nConfiguring consumers...")
-        for stream_name, subject_map in consumers.items():
+        for domain in WORKER_DOMAINS:
-            for subject, durable in subject_map.items():
+            stream_name = domain["stream"]
+            consumer = domain["consumer"]
+            for subject in domain["subjects"]:
+                durable = durable_name(consumer, subject)
                 try:
                     print(f"Creating consumer '{durable}' on stream '{stream_name}' for subject '{subject}'...")
                     await js.add_consumer(
@@ -136,7 +112,7 @@ async def setup_jetstream():
                         ack_policy="explicit",
                         deliver_policy="all",
                         max_deliver=5,
-                        ack_wait=30,
+                        ack_wait=60,
                     )
                     print(f"✅ Consumer '{durable}' created")
                 except Exception as e:
@@ -147,12 +123,12 @@ async def setup_jetstream():
 
         print("\n✅ JetStream setup complete!")
         print("   Streams:")
-        for name, cfg in streams.items():
+        for domain in WORKER_DOMAINS:
-            print(f"     - {name}: {', '.join(cfg['subjects'])}")
+            print(f"     - {domain['stream']}: {', '.join(domain['subjects'])}")
         print("   Consumers:")
-        for stream_name, subject_map in consumers.items():
+        for domain in WORKER_DOMAINS:
-            for subject, durable in subject_map.items():
+            for subject in domain["subjects"]:
-                print(f"     - {durable}: stream={stream_name}, subject={subject}")
+                print(f"     - {durable_name(domain['consumer'], subject)}: stream={domain['stream']}, subject={subject}")
 
         await nc.close()
         sys.exit(0)
@@ -163,4 +139,3 @@ async def setup_jetstream():
 
 if __name__ == "__main__":
     asyncio.run(setup_jetstream())
-

scripts/sync_manifests.py

@@ -51,16 +51,18 @@ def update_yaml_with_script(yaml_path, script_path, key_line_start):
         
     print(f"Successfully updated {yaml_path}")
 
+REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
 # Update Fiesta Gateway
 update_yaml_with_script(
-    r'e:\nats\kubernetes\manifests\nearle\fiesta-gateway.yaml',
+    os.path.join(REPO_ROOT, 'manifests', 'nearle', 'fiesta-gateway.yaml'),
-    r'e:\nats\kubernetes\conf\app.py',
+    os.path.join(REPO_ROOT, 'conf', 'app.py'),
     '  app.py: |'
 )
 
 # Update Worker Script
 update_yaml_with_script(
-    r'e:\nats\kubernetes\manifests\core\worker-script.yaml',
+    os.path.join(REPO_ROOT, 'manifests', 'core', 'worker-script.yaml'),
-    r'e:\nats\kubernetes\conf\worker.py',
+    os.path.join(REPO_ROOT, 'conf', 'worker.py'),
     '  worker.py: |'
 )

shfiles/check-k8s-status.sh

@@ -1,93 +1,63 @@
 #!/bin/bash
+# Status check across every namespace actually in use by this cluster.
+# Usage: ./shfiles/check-k8s-status.sh
+
+NAMESPACES=(core nearle alaska doormile kubernetes-dashboard)
 
 echo "=========================================="
 echo "🔍 KUBERNETES DEPLOYMENT STATUS"
 echo "=========================================="
 echo ""
 
-echo "📦 1. PODS STATUS (All Namespaces)"
+echo "📦 1. NODES"
+echo "-----------------------------------"
+kubectl get nodes -o wide
+echo ""
+
+echo "📦 2. PODS (All Namespaces)"
 echo "-----------------------------------"
 kubectl get pods -A -o wide
 echo ""
 
-echo "📦 2. NATS-BACKEND NAMESPACE - PODS"
+for ns in "${NAMESPACES[@]}"; do
-echo "-----------------------------------"
+    echo "=========================================="
-kubectl get pods -n nats-backend -o wide
+    echo "📦 Namespace: ${ns}"
-echo ""
+    echo "=========================================="
 
-echo "🌐 3. SERVICES & LOAD BALANCER"
+    echo "-- Pods --"
-echo "-----------------------------------"
+    kubectl get pods -n "${ns}" -o wide 2>/dev/null || echo "  (namespace not found)"
-kubectl get svc -n nats-backend -o wide
+    echo ""
-echo ""
 
-echo "⚖️  4. LOAD BALANCER DETAILS"
+    echo "-- Services --"
-echo "-----------------------------------"
+    kubectl get svc -n "${ns}" -o wide 2>/dev/null
-kubectl get svc fastapi-lb -n nats-backend -o yaml | grep -A 10 "spec:"
+    echo ""
-echo ""
 
-echo "🚀 5. K3S KUBERNETES LOAD BALANCER PODS (klipper-lb)"
+    echo "-- StatefulSets / Deployments --"
-echo "-----------------------------------"
+    kubectl get statefulsets,deployments -n "${ns}" -o wide 2>/dev/null
-kubectl get pods -n kube-system -l "svccontroller.k3s.cattle.io/svcname=fastapi-lb" -o wide
+    echo ""
-echo ""
 
-echo "📊 6. DEPLOYMENTS & REPLICAS"
+    echo "-- HPA / PodDisruptionBudgets --"
-echo "-----------------------------------"
+    kubectl get hpa,pdb -n "${ns}" 2>/dev/null
-kubectl get deployments -n nats-backend -o wide
+    echo ""
-echo ""
 
-echo "📈 7. HORIZONTAL POD AUTOSCALER (HPA)"
+    echo "-- Recent Events (last 10) --"
-echo "-----------------------------------"
+    kubectl get events -n "${ns}" --sort-by='.lastTimestamp' 2>/dev/null | tail -10
-kubectl get hpa -n nats-backend
+    echo ""
-echo ""
+done
 
-echo "🔗 8. ENDPOINTS (Service Backends)"
+echo "🌍 GATEWAY / HTTPROUTE / INGRESS (All Namespaces)"
-echo "-----------------------------------"
-kubectl get endpoints -n nats-backend
-echo ""
-
-echo "🌍 9. INGRESS/GATEWAY STATUS"
 echo "-----------------------------------"
 kubectl get gateway -A 2>/dev/null || echo "No Gateway API resources found"
+kubectl get httproute -A 2>/dev/null || echo "No HTTPRoute resources found"
 kubectl get ingress -A 2>/dev/null || echo "No Ingress resources found"
 echo ""
 
-echo "📋 10. RECENT EVENTS (Last 20)"
+echo "💾 RESOURCE USAGE (CPU/Memory)"
 echo "-----------------------------------"
-kubectl get events -n nats-backend --sort-by='.lastTimestamp' | tail -20
+kubectl top pods -A 2>/dev/null || echo "Metrics server not available"
-echo ""
-
-echo "💾 11. RESOURCE USAGE (CPU/Memory)"
-echo "-----------------------------------"
-kubectl top pods -n nats-backend 2>/dev/null || echo "Metrics server not available"
 kubectl top nodes 2>/dev/null || echo "Metrics server not available"
 echo ""
 
-echo "🔍 12. FASTAPI POD LOGS (Last 30 lines)"
-echo "-----------------------------------"
-kubectl logs -n nats-backend -l app=fastapi-backend --tail=30 2>/dev/null || echo "No FastAPI pods found"
-echo ""
-
-echo "🔍 13. WORKER POD LOGS (Last 30 lines)"
-echo "-----------------------------------"
-kubectl logs -n nats-backend -l app=nats-worker --tail=30 2>/dev/null || echo "No worker pods found"
-echo ""
-
-echo "🌐 14. NETWORK FLOW CHECK"
-echo "-----------------------------------"
-echo "Load Balancer External IP/Port:"
-kubectl get svc fastapi-lb -n nats-backend -o jsonpath='{.status.loadBalancer.ingress[0].ip}:{.spec.ports[0].port}' 2>/dev/null || echo "Checking NodePort..."
-kubectl get svc fastapi-lb -n nats-backend -o jsonpath='NodePort: {.spec.ports[0].nodePort}' 2>/dev/null
-echo ""
-echo "FastAPI Service ClusterIP:"
-kubectl get svc fastapi-backend -n nats-backend -o jsonpath='{.spec.clusterIP}:{.spec.ports[0].port}' 2>/dev/null
-echo ""
-
-echo "✅ 15. HEALTH CHECK"
-echo "-----------------------------------"
-kubectl run health-check --rm -i --restart=Never --image=curlimages/curl -- curl -s http://fastapi-backend.nats-backend:8000/health 2>/dev/null || echo "Health check failed"
-echo ""
-
 echo "=========================================="
 echo "✅ Status Check Complete!"
 echo "=========================================="
-

shfiles/deploy-doormile.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# Deploy "doormile" stack to Kubernetes
+# Usage: ./deploy-doormile.sh
+
+set -euo pipefail
+
+NAMESPACE="doormile"
+
+echo "🚀 Deploying Doormile Stack..."
+kubectl apply -f manifests/doormile/miletruth.yaml
+
+echo ""
+echo "✅ Doormile deployment applied."
+echo "📋 Current status:"
+kubectl get all -n "${NAMESPACE}" || true

shfiles/deploy-ingress.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# Deploy shared Ingress resources and Traefik CORS middlewares
+# (queue.workolik.com, jupiter/fiesta/atlantis.nearle.app, alaska + nearle CORS)
+# Usage: ./deploy-ingress.sh
+
+set -euo pipefail
+
+echo "🌐 Applying Ingress resources..."
+kubectl apply -f manifests/core/ingress-unified.yaml
+
+echo "🎛️  Applying Traefik CORS middlewares..."
+kubectl apply -f manifests/core/traefik-middlewares.yaml
+
+echo ""
+echo "✅ Ingress & middlewares applied."

shfiles/deploy-nearle-stack.sh

@@ -9,16 +9,29 @@ NAMESPACE="nearle"
 echo "🔎 Ensuring namespace '${NAMESPACE}' exists..."
 kubectl apply -f manifests/nearle/nearle-namespace.yaml
 
+echo "🔐 Applying config & secrets..."
+kubectl apply -f manifests/nearle/nearle-config.yaml
+kubectl apply -f manifests/nearle/nearle-secrets.yaml
+kubectl apply -f manifests/nearle/nearle-app-secrets.yaml
 
+echo "📜 Applying fiesta gateway script ConfigMap..."
+kubectl apply -f manifests/nearle/fiesta-gateway.yaml
+
+echo "🌐 Applying Gateway API resources..."
+kubectl apply -f manifests/nearle/nearle-gateway.yaml
+kubectl apply -f manifests/nearle/nearle-reference-grant.yaml
 
 echo "🚀 Deploying Services..."
 kubectl apply -f manifests/nearle/nearle-jupiter.yaml
 kubectl apply -f manifests/nearle/nearle-titan.yaml
 kubectl apply -f manifests/nearle/nearle-fiesta.yaml
 kubectl apply -f manifests/nearle/nearle-ariane.yaml
+kubectl apply -f manifests/nearle/nearle-atlantis.yaml
+
+echo "🧭 Deploying Jupiter CORS proxy..."
+kubectl apply -f manifests/nearle/jupiter-cors-proxy.yaml
 
 echo ""
 echo "✅ Nearle stack deployment applied."
 echo "📋 Current status:"
-echo "  kubectl get all -n ${NAMESPACE}"
+kubectl get all -n "${NAMESPACE}" || true
-

shfiles/deploy.sh

@@ -1,10 +1,12 @@
 #!/bin/bash
-# Kubernetes Deployment Script for 3-Node Cluster
+# Deploy the full stack to Kubernetes (core, nearle, alaska, doormile, ingress)
-# Usage: ./deploy.sh
+# Usage: ./shfiles/deploy.sh   (run from the repo root, or anywhere - it cd's there itself)
 
-set -e
+set -euo pipefail
 
-echo "🚀 Deploying to Kubernetes (3-Node Cluster)..."
+cd "$(dirname "$0")/.."
+
+echo "🚀 Deploying full stack..."
 
 # Check if kubectl is available
 if ! command -v kubectl &> /dev/null; then
@@ -23,46 +25,29 @@ kubectl cluster-info || {
 NODE_COUNT=$(kubectl get nodes --no-headers | wc -l)
 echo "📊 Cluster has $NODE_COUNT node(s)"
 
-# Apply namespace
+echo ""
-echo "📦 Creating namespace..."
+echo "===== Core stack (NATS workers) ====="
-kubectl apply -f manifests/namespace.yaml
+bash shfiles/deploy-core-stack.sh
-
-# Apply secrets
-echo "🔐 Creating secrets..."
-kubectl apply -f manifests/secrets.yaml
-
-# Apply FastAPI
-echo "🐍 Deploying FastAPI backend..."
-kubectl apply -f manifests/fastapi-deployment.yaml
-kubectl apply -f manifests/fastapi-service.yaml
-kubectl apply -f manifests/fastapi-hpa.yaml
-
-# Apply Workers
-echo "👷 Deploying NATS workers..."
-kubectl apply -f manifests/worker-deployment.yaml
-kubectl apply -f manifests/worker-hpa.yaml
-
-# Apply Gateway (optional - only if Gateway API is installed)
-read -p "Deploy Gateway API? (requires Gateway API controller) [y/N] " -n 1 -r
-echo
-if [[ $REPLY =~ ^[Yy]$ ]]; then
-    echo "🚪 Deploying Gateway API..."
-    kubectl apply -f manifests/gateway.yaml
-fi
 
 echo ""
-echo "✅ Deployment complete!"
+echo "===== Nearle stack (jupiter, titan, fiesta, ariane, atlantis) ====="
+bash shfiles/deploy-nearle-stack.sh
+
+echo ""
+echo "===== Alaska stack (deliveries gateway + dashboard) ====="
+bash shfiles/deploy-alaska.sh
+
+echo ""
+echo "===== Doormile stack ====="
+bash shfiles/deploy-doormile.sh
+
+echo ""
+echo "===== Ingress & Traefik middlewares ====="
+bash shfiles/deploy-ingress.sh
+
+echo ""
+echo "✅ Full deployment complete!"
 echo ""
 echo "📋 Check status:"
-echo "   kubectl get pods -n nats-backend -o wide"
+echo "   bash shfiles/check-k8s-status.sh"
-echo "   kubectl get nodes"
-echo "   kubectl get hpa -n nats-backend"
 echo ""
-echo "📊 View pod distribution across nodes:"
-echo "   kubectl get pods -n nats-backend -o wide | grep -E 'NAME|fastapi|worker'"
-echo ""
-echo "📝 View logs:"
-echo "   kubectl logs -f deployment/fastapi-backend -n nats-backend"
-echo "   kubectl logs -f deployment/nats-worker -n nats-backend"
-echo ""
-

shfiles/setup-jetstream.sh

@@ -1,9 +1,13 @@
 #!/bin/bash
 # Setup JetStream stream and consumer for NATS
 
+set -euo pipefail
+
 echo "🚀 Setting up NATS JetStream..."
 
-cd "$(dirname "$0")"
+# scripts/ is a sibling of shfiles/, both under the repo root - cd there so
+# the relative path below resolves regardless of where this is invoked from.
+cd "$(dirname "$0")/.."
 
 # Check if Python is available
 if ! command -v python3 &> /dev/null; then
@@ -17,11 +21,19 @@ if ! python3 -c "import nats" 2>/dev/null; then
     pip3 install nats-py
 fi
 
-# Set environment variables
+# Pull live credentials from the cluster's Secret instead of hardcoding them
-export NATS_URL="nats://nats.workolik.com:4222"
+# here - avoids yet another copy of the password to keep in sync if rotated.
-export NATS_USER="admin"
+if command -v kubectl &> /dev/null && kubectl get secret nats-credentials -n core &> /dev/null 2>&1; then
-export NATS_PASSWORD="package@321#"
+    export NATS_USER
+    NATS_USER=$(kubectl get secret nats-credentials -n core -o jsonpath='{.data.username}' | base64 -d)
+    export NATS_PASSWORD
+    NATS_PASSWORD=$(kubectl get secret nats-credentials -n core -o jsonpath='{.data.password}' | base64 -d)
+else
+    echo "⚠️  Could not read nats-credentials Secret from the cluster (kubectl not available or not connected)."
+    echo "   Set NATS_USER / NATS_PASSWORD yourself before running this script."
+fi
+
+export NATS_URL="${NATS_URL:-nats://66.116.226.161:4222}"
 
 # Run the setup script
 python3 scripts/setup_jetstream.py
-

terraform/.gitignore

@@ -0,0 +1,4 @@
+.terraform/
+*.tfstate
+*.tfstate.*
+crash.log

terraform/.terraform.lock.hcl

@@ -0,0 +1,22 @@
+# This file is maintained automatically by "terraform init".
+# Manual edits may be lost in future updates.
+
+provider "registry.terraform.io/hashicorp/kubernetes" {
+  version     = "3.2.1"
+  constraints = ">= 2.10.0"
+  hashes = [
+    "h1:mcG69DdvaQvDNQzIo+SLVekECRLiNKavq5jbp/yieOU=",
+    "zh:067fe16a852d42e0f571712e36cb3e71855f917ea2041415e155f56ebc480d7f",
+    "zh:2815e174f8f0f032ea3a64f2196740ad000a39f88ae5646e7061bf15ed589f62",
+    "zh:2f94f6b689c59c43e596e724228f2861095d02c2a2ac2a257a4619667135ac75",
+    "zh:3e807310c84f11561b9ba06b978f03c46cfeca2e84ad0803d34d5d30a8a637cb",
+    "zh:5cba6f92202c60cac6898141356420709f5341b80ae4c360725cc647f86188ff",
+    "zh:72b841b6f0820d8f87c3d7c5a3611c35121ab9a4c1db4ea7a98b0319f209e474",
+    "zh:74770b892ee9b04829d92318d9e8ca96f8143b0c6c766e4141901908173fd01d",
+    "zh:7a723c8ebf9e218d0f7a0cfe6c0437f2b5eeb7ae015a14fad16e0f7fd9ef79ab",
+    "zh:a0f5073b2636a3894d4e9dd1b6853d5f324dd78728313bff79b842e5e9eca96f",
+    "zh:c13241cba993ef63a537beb6a1caf00e233bb045b50d197349530de0ee3276d5",
+    "zh:d52826f4b0227b7db99ea4a1d48f49a0bfb440563c92ebd2f8faec273c856c2d",
+    "zh:dc1cf5505a39a264a650b0830f74150ad02368787e5ead89e4007034f8f47831",
+  ]
+}

terraform/main.tf

@@ -1,34 +0,0 @@
-terraform {
-  required_providers {
-    kubernetes = {
-      source  = "hashicorp/kubernetes"
-      version = ">= 2.0.0"
-    }
-  }
-}
-
-provider "kubernetes" {
-  # This tells Terraform how to connect to your k3s cluster.
-  # Usually it looks for the file in ~/.kube/config.
-  config_path = "~/.kube/config"
-}
-
-# Example: Manage a Kubernetes Namespace using Terraform
-resource "kubernetes_namespace" "core" {
-  metadata {
-    name = "core"
-    labels = {
-      name = "core"
-      environment = "production"
-    }
-  }
-}
-
-# Practical: Point Terraform to your updated .yaml files
-# Instead of you running 'kubectl apply', Terraform will do it.
-
-resource "kubernetes_manifest" "worker_orders" {
-  manifest = yamldecode(file("${path.module}/../manifests/core/workers.yaml"))
-}
-
-# (Add more resources here for nearle, alaska, etc.)

terraform/namespaces.tf

@@ -1,20 +1,26 @@
 # Create namespaces using Terraform
-# This makes sure the zones 'core', 'nearle', 'alaska' are always present and correctly labeled.
+# This makes sure the zones 'core', 'nearle', 'alaska', 'doormile' are always present and correctly labeled.
 
-resource "kubernetes_namespace" "core" {
+resource "kubernetes_namespace_v1" "core" {
   metadata {
     name = "core"
   }
 }
 
-resource "kubernetes_namespace" "nearle" {
+resource "kubernetes_namespace_v1" "nearle" {
   metadata {
     name = "nearle"
   }
 }
 
-resource "kubernetes_namespace" "alaska" {
+resource "kubernetes_namespace_v1" "alaska" {
   metadata {
     name = "alaska"
   }
 }
+
+resource "kubernetes_namespace_v1" "doormile" {
+  metadata {
+    name = "doormile"
+  }
+}

terraform/workloads.tf

@@ -1,45 +1,93 @@
-# Manage the Nearle Stack (Jupiter, Atlantis, Fiesta)
+# Manage the Nearle Stack (Jupiter, Atlantis, Fiesta) plus the shared core
-# This is the "All-in-one" Terraform control for your major services
+# workers, Ingress and Traefik middlewares.
+#
+# NOTE: each of these manifest files contains MULTIPLE '---'-separated YAML
+# documents (e.g. a StatefulSet + Service + HTTPRoute in one file). Terraform's
+# built-in yamldecode() only parses a single document, so each file is split
+# on the '---' separator first and turned into a for_each map, one
+# kubernetes_manifest per document. This has been verified safe for these
+# specific files (the number of '---' lines matches document-count minus one
+# in each case - no embedded '---' inside any script/config content).
 
-# 1. Jupiter Service
+locals {
-resource "kubernetes_manifest" "nearle_jupiter_sts" {
+  # Splits a multi-document YAML file into a map keyed by
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/jupiter-sts.yaml"))
+  # "<kind>/<namespace>/<name>" (namespace omitted for cluster-scoped
+  # resources), suitable for a kubernetes_manifest for_each.
+  jupiter_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/nearle/nearle-jupiter.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
+
+  atlantis_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/nearle/nearle-atlantis.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
+
+  fiesta_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/nearle/nearle-fiesta.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
+
+  core_workers_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/core/workers.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
+
+  core_ingress_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/core/ingress-unified.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
+
+  traefik_middlewares_docs = {
+    for doc in [
+      for chunk in split("\n---\n", file("${path.module}/../manifests/core/traefik-middlewares.yaml")) :
+      yamldecode(chunk) if trimspace(chunk) != ""
+    ] : "${doc.kind}/${lookup(doc.metadata, "namespace", "")}/${doc.metadata.name}" => doc
+  }
 }
 
-resource "kubernetes_manifest" "nearle_jupiter_svc" {
+# 1. Jupiter (StatefulSet + Service)
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/jupiter-svc.yaml"))
+resource "kubernetes_manifest" "nearle_jupiter" {
+  for_each = local.jupiter_docs
+  manifest = each.value
 }
 
-# 2. Atlantis Service
+# 2. Atlantis (StatefulSet + Service + HTTPRoute)
-resource "kubernetes_manifest" "nearle_atlantis_sts" {
+resource "kubernetes_manifest" "nearle_atlantis" {
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/atlantis-sts.yaml"))
+  for_each = local.atlantis_docs
+  manifest = each.value
 }
 
-resource "kubernetes_manifest" "nearle_atlantis_svc" {
+# 3. Fiesta (StatefulSet + Service + HTTPRoute)
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/atlantis-svc.yaml"))
+resource "kubernetes_manifest" "nearle_fiesta" {
+  for_each = local.fiesta_docs
+  manifest = each.value
 }
 
-# 3. Fiesta Service
+# 4. Workers (CPU-heavy, isolated node pool - 5 StatefulSets)
-resource "kubernetes_manifest" "nearle_fiesta_sts" {
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/fiesta-sts.yaml"))
-}
-
-resource "kubernetes_manifest" "nearle_fiesta_svc" {
-  manifest = yamldecode(file("${path.module}/../manifests/nearle/fiesta-svc.yaml"))
-}
-
-# 4. Workers (CPU-heavy isolated nodes)
 resource "kubernetes_manifest" "core_workers" {
-  # This uses your existing workers.yaml file
+  for_each = local.core_workers_docs
-  # Note: Since this file has MANY documents, I recommend splitting it the same way as above.
+  manifest = each.value
-  manifest = yamldecode(file("${path.module}/../manifests/core/workers.yaml"))
 }
 
-# 5. Ingress (Unified routing that replaces Docker-side Nginx)
+# 5. Ingress (queue.workolik.com, jupiter/fiesta/atlantis.nearle.app)
 resource "kubernetes_manifest" "core_ingress" {
-  manifest = yamldecode(file("${path.module}/../manifests/core/ingress-unified.yaml"))
+  for_each = local.core_ingress_docs
+  manifest = each.value
 }
 
+# 6. Traefik CORS middlewares (alaska + nearle)
 resource "kubernetes_manifest" "traefik_middlewares" {
-  manifest = yamldecode(file("${path.module}/../manifests/core/traefik-middlewares.yaml"))
+  for_each = local.traefik_middlewares_docs
+  manifest = each.value
 }