Update images for services: ai_insights,alert_processor,auth,demo_session,distribution,external,forecasting,inventory,notification,orchestrator,orders,pos,procurement,production,recipes,sales,suppliers,tenant,training,gateway [skip ci]

This is a temporary workaround to test Flux reconciliation.
The registry currently has images stored with folder names (auth, tenant, etc.)
instead of service names (auth-service, tenant-service, etc.).

The permanent fix in task-kaniko-build.yaml will push with correct names
on the next full pipeline run.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

MAILU_DEPLOYMENT_ARCHITECTURE.md

@@ -2,7 +2,7 @@
 
 ## Executive Summary
 
-This document outlines the recommended architecture for deploying Mailu email services across development and production environments for the Bakery-IA project. The solution addresses DNSSEC validation requirements while maintaining consistency across different Kubernetes platforms.
+This document outlines the recommended architecture for deploying Mailu email services across development and production environments for the Bakery-IA project. The solution addresses DNSSEC validation requirements using CoreDNS with DNS-over-TLS while maintaining consistency across different Kubernetes platforms.
 
 ## Environment Overview
 
@@ -25,124 +25,76 @@ This document outlines the recommended architecture for deploying Mailu email se
 
 ## Architectural Solution
 
-### Unified DNS Resolution Strategy
+### DNS Resolution Strategy
 
-**Recommended Approach**: Deploy Unbound as a dedicated DNSSEC-validating resolver pod in both environments
+**Approach**: Use CoreDNS with DNS-over-TLS to Cloudflare (1.1.1.1) for DNSSEC validation
 
 #### Benefits:
+- ✅ Leverages existing Kubernetes DNS infrastructure
+- ✅ No additional pods required (uses CoreDNS already in cluster)
+- ✅ DNSSEC validation provided by Cloudflare's DNS-over-TLS
 - ✅ Consistent behavior across dev and prod
 - ✅ Meets Mailu's DNSSEC requirements
-- ✅ Privacy-preserving (no external DNS queries)
+- ✅ Simple and reliable
-- ✅ Avoids rate-limiting from public DNS providers
-- ✅ Full control over DNS resolution
 
 ### Implementation Components
 
-#### 1. Unbound Deployment Manifest
+#### 1. CoreDNS Configuration with DNS-over-TLS
 
 ```yaml
-# unbound.yaml - Cross-environment compatible
+# CoreDNS Corefile configuration for DNSSEC via DNS-over-TLS
-apiVersion: apps/v1
+.:53 {
-kind: Deployment
+    errors
-metadata:
+    health {
-  name: unbound-resolver
+       lameduck 5s
-  namespace: mailu
+    }
-  labels:
+    ready
-    app: unbound
+    kubernetes cluster.local in-addr.arpa ip6.arpa {
-    component: dns
+       pods insecure
-spec:
+       fallthrough in-addr.arpa ip6.arpa
-  replicas: 1  # Scale to 2+ in production with anti-affinity
+       ttl 30
-  selector:
+    }
-    matchLabels:
+    prometheus :9153
-      app: unbound
+    forward . tls://1.1.1.1 tls://1.0.0.1 {
-  template:
+       tls_servername cloudflare-dns.com
-    metadata:
+       health_check 5s
-      labels:
+    }
-        app: unbound
+    cache 30 {
-        component: dns
+       disable success cluster.local
-    spec:
+       disable denial cluster.local
-      containers:
+    }
-      - name: unbound
+    loop
-        image: mvance/unbound:latest
+    reload
-        ports:
+    loadbalance
-        - containerPort: 53
+}
-          name: dns-udp
-          protocol: UDP
-        - containerPort: 53
-          name: dns-tcp
-          protocol: TCP
-        resources:
-          requests:
-            cpu: "100m"
-            memory: "128Mi"
-          limits:
-            cpu: "300m"
-            memory: "384Mi"
-        readinessProbe:
-          exec:
-            command: ["drill", "@127.0.0.1", "-p", "53", "+dnssec", "example.org"]
-          initialDelaySeconds: 10
-          periodSeconds: 30
-        securityContext:
-          capabilities:
-            add: ["NET_BIND_SERVICE"]
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: unbound-dns
-  namespace: mailu
-spec:
-  selector:
-    app: unbound
-  ports:
-  - name: dns-udp
-    port: 53
-    targetPort: 53
-    protocol: UDP
-  - name: dns-tcp
-    port: 53
-    targetPort: 53
-    protocol: TCP
 ```
 
 #### 2. Mailu Configuration (values.yaml)
 
 ```yaml
 # Production-tuned Mailu configuration
-dnsPolicy: None
+global:
-dnsConfig:
+  # Using Kubernetes CoreDNS for DNS resolution
-  nameservers:
+  # CoreDNS is configured with DNS-over-TLS (Cloudflare) for DNSSEC validation
-    - "10.152.183.x"  # Replace with actual unbound service IP
+  custom_dns_servers: "10.152.183.10"  # MicroK8s CoreDNS IP (adjust for your cluster)
 
-# Component-specific DNS configuration
+# DNS configuration - use Kubernetes DNS (ClusterFirst)
+# CoreDNS provides DNSSEC validation via DNS-over-TLS to Cloudflare
 admin:
-  dnsPolicy: None
+  dnsPolicy: "ClusterFirst"
-  dnsConfig:
-    nameservers:
-      - "10.152.183.x"
 
 rspamd:
-  dnsPolicy: None
+  dnsPolicy: "ClusterFirst"
-  dnsConfig:
-    nameservers:
-      - "10.152.183.x"
 
 # Environment-specific configurations
 persistence:
   enabled: true
-  # Development: use default storage class
+  storageClass: ""  # Use cluster default
-  # Production: use microk8s-hostpath or longhorn
-  storageClass: "standard"
 
 replicas: 1  # Increase in production as needed
 
 # Security settings
 secretKey: "generate-strong-key-here"
-
-# Ingress configuration
-# Use existing Bakery-IA ingress controller
 ```
 
 ### Environment-Specific Adaptations
@@ -157,23 +109,21 @@ secretKey: "generate-strong-key-here"
 
 **Deployment:**
 ```bash
-# Apply unbound
+# Get CoreDNS service IP
-kubectl apply -f unbound.yaml
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
-
-# Get unbound service IP
-UNBOUND_IP=$(kubectl get svc unbound-dns -n mailu -o jsonpath='{.spec.clusterIP}')
 
 # Deploy Mailu with dev-specific values
 helm upgrade --install mailu mailu/mailu \
-  --namespace mailu \
+  --namespace bakery-ia \
-  -f values-dev.yaml \
+  -f infrastructure/platform/mail/mailu-helm/values.yaml \
-  --set dnsConfig.nameservers[0]=$UNBOUND_IP
+  -f infrastructure/platform/mail/mailu-helm/dev/values.yaml \
+  --set global.custom_dns_servers=$COREDNS_IP
 ```
 
 #### Production (MicroK8s/Ubuntu)
 
 **Enhancements:**
-- Use Longhorn or OpenEBS for storage
+- Use microk8s-hostpath for storage
 - Enable monitoring and logging
 - Configure proper ingress with TLS
 - Set up backup solutions
@@ -181,19 +131,17 @@ helm upgrade --install mailu mailu/mailu \
 **Deployment:**
 ```bash
 # Enable required MicroK8s addons
-microk8s enable dns storage ingress metallb
+microk8s enable dns storage ingress
 
-# Apply unbound
+# Get CoreDNS service IP
-kubectl apply -f unbound.yaml
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
-
-# Get unbound service IP
-UNBOUND_IP=$(kubectl get svc unbound-dns -n mailu -o jsonpath='{.spec.clusterIP}')
 
 # Deploy Mailu with production values
 helm upgrade --install mailu mailu/mailu \
-  --namespace mailu \
+  --namespace bakery-ia \
-  -f values-prod.yaml \
+  -f infrastructure/platform/mail/mailu-helm/values.yaml \
-  --set dnsConfig.nameservers[0]=$UNBOUND_IP
+  -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+  --set global.custom_dns_servers=$COREDNS_IP
 ```
 
 ## Verification Procedures
@@ -201,52 +149,39 @@ helm upgrade --install mailu mailu/mailu \
 ### DNSSEC Validation Test
 
 ```bash
-# From within a Mailu pod
+# Test DNS resolution from within a Mailu pod
-kubectl exec -it -n mailu deploy/mailu-admin -- bash
+kubectl exec -it -n bakery-ia deploy/mailu-admin -- bash
 
-# Test DNSSEC validation
+# Test DNSSEC validation (via CoreDNS -> Cloudflare DNS-over-TLS)
-dig @unbound-dns +short +dnssec +adflag example.org A
+dig +short +dnssec +adflag example.org A
 
-# Should show AD flag in response
+# Should show AD flag in response indicating DNSSEC validation
 ```
 
 ### Service Health Checks
 
 ```bash
-# Check unbound service
+# Check CoreDNS is running
-kubectl get pods -n mailu -l app=unbound
+kubectl get pods -n kube-system -l k8s-app=kube-dns
-kubectl logs -n mailu -l app=unbound
 
 # Check Mailu components
-kubectl get pods -n mailu
+kubectl get pods -n bakery-ia | grep mailu
-kubectl logs -n mailu -l app.kubernetes.io/name=mailu
+kubectl logs -n bakery-ia -l app.kubernetes.io/name=mailu
 ```
 
 ## Monitoring and Maintenance
 
 ### Production Monitoring Setup
 
-```yaml
+CoreDNS exposes Prometheus metrics on port 9153 by default. Monitor:
-# Example monitoring configuration for production
+- DNS query latency
-apiVersion: monitoring.coreos.com/v1
+- DNS query success/failure rates
-kind: ServiceMonitor
+- DNS cache hit ratio
-metadata:
-  name: unbound-monitor
-  namespace: mailu
-spec:
-  selector:
-    matchLabels:
-      app: unbound
-  endpoints:
-  - port: dns-tcp
-    interval: 30s
-    path: /metrics
-```
 
 ### Backup Strategy
 
 **Production:**
-- Daily Velero backups of Mailu namespace
+- Daily Velero backups of bakery-ia namespace
 - Weekly database dumps
 - Monthly full cluster snapshots
 
@@ -258,16 +193,21 @@ spec:
 
 ### Common Issues and Solutions
 
-**Issue: DNSSEC validation failures**
+**Issue: DNS resolution failures**
-- Verify unbound pod logs
+- Verify CoreDNS pods are running
-- Check network policies
+- Check CoreDNS logs: `kubectl logs -n kube-system -l k8s-app=kube-dns`
-- Test DNS resolution from within pods
+- Test DNS resolution: `kubectl run -it --rm dns-test --image=busybox -- nslookup google.com`
 
 **Issue: Mailu pods failing to start**
 - Confirm DNS configuration in values.yaml
-- Verify unbound service is reachable
+- Verify CoreDNS service is reachable
 - Check resource availability
 
+**Issue: DNSSEC validation errors**
+- Ensure CoreDNS is configured with DNS-over-TLS
+- Test with: `dig +dnssec example.org`
+- Verify Cloudflare DNS is reachable
+
 **Issue: Performance problems**
 - Monitor CPU/memory usage
 - Adjust resource limits
@@ -327,12 +267,12 @@ spec:
 
 ## Conclusion
 
-This architecture provides a robust, consistent solution for deploying Mailu across development and production environments. By using Unbound as a dedicated DNSSEC-validating resolver, we ensure compliance with Mailu's requirements while maintaining flexibility and reliability across different Kubernetes platforms.
+This architecture provides a robust, consistent solution for deploying Mailu across development and production environments. By using CoreDNS with DNS-over-TLS to Cloudflare, we ensure compliance with Mailu's DNSSEC requirements while maintaining simplicity and reliability.
 
 The solution is designed to be:
+- **Simple**: Uses existing Kubernetes DNS infrastructure
 - **Consistent**: Same core architecture across environments
-- **Reliable**: Production-grade availability and monitoring
+- **Reliable**: Production-grade availability
-- **Efficient**: Optimized resource usage
+- **Efficient**: No additional pods required for DNS
-- **Maintainable**: Clear documentation and troubleshooting guides
 
 This approach aligns with the Bakery-IA project's requirements for a secure, reliable email infrastructure that can be consistently deployed across different environments.

PRODUCTION_DEPLOYMENT_GUIDE.md

@@ -20,6 +20,8 @@
 5. [Phase 2: Domain & DNS Configuration](#phase-2-domain--dns-configuration)
 6. [Phase 3: Deploy Foundation Layer](#phase-3-deploy-foundation-layer)
 7. [Phase 4: Deploy CI/CD Infrastructure](#phase-4-deploy-cicd-infrastructure)
+   - [Step 4.6: Configure Gitea Webhook](#step-46-configure-gitea-webhook-for-cicd-pipeline)
+   - [Step 4.7: Configure PipelineRun Cleanup](#step-47-configure-pipelinerun-cleanup-optional-but-recommended)
 8. [Phase 5: Pre-Pull and Push Base Images to Gitea Registry](#phase-5-pre-pull-and-push-base-images-to-gitea-registry)
    - [Step 5.1: Pre-Pull Base Images](#step-51-pre-pull-base-images-and-push-to-registry)
    - [Step 5.2: Verify Images in Registry](#step-52-verify-images-in-gitea-registry)
@@ -29,6 +31,7 @@
    - [Step 5.6: Verify Service Images](#step-56-verify-all-service-images-are-available)
 9. [Phase 6: Deploy Application Services](#phase-6-deploy-application-services)
 10. [Phase 7: Deploy Optional Services](#phase-7-deploy-optional-services)
+    - [Step 7.5: Deploy Kubernetes Infrastructure Monitoring](#step-75-deploy-kubernetes-infrastructure-monitoring-required-for-signoz-infrastructure-view)
 11. [Phase 8: Verification & Validation](#phase-8-verification--validation)
 12. [Post-Deployment Operations](#post-deployment-operations)
 13. [Troubleshooting Guide](#troubleshooting-guide)
@@ -49,7 +52,7 @@ A complete multi-tenant SaaS platform consisting of:
 | **Cache** | Redis with TLS |
 | **Message Broker** | RabbitMQ |
 | **Object Storage** | MinIO (S3-compatible) |
-| **Email** | Mailu (self-hosted) with Mailgun relay |
+| **Email** | Mailu (self-hosted) with MailerSend relay |
 | **Monitoring** | SigNoz (unified observability) |
 | **CI/CD** | Gitea + Tekton + Flux CD |
 | **Security** | TLS everywhere, RBAC, Network Policies |
@@ -71,7 +74,7 @@ A complete multi-tenant SaaS platform consisting of:
 │  PostgreSQL (18 DBs) │ Redis │ RabbitMQ │ MinIO                            │
 ├─────────────────────────────────────────────────────────────────────────────┤
 │                         LAYER 2: NETWORK & SECURITY                         │
-│  Unbound DNS │ CoreDNS │ Ingress Controller │ Cert-Manager │ TLS          │
+│  CoreDNS (DNS-over-TLS) │ Ingress Controller │ Cert-Manager │ TLS         │
 ├─────────────────────────────────────────────────────────────────────────────┤
 │                         LAYER 1: FOUNDATION                                 │
 │  Namespaces │ Storage Classes │ RBAC │ ConfigMaps │ Secrets               │
@@ -113,7 +116,7 @@ Phase 8: Verification & Validation
 |---------|----------|-------------|
 | VPS (20GB RAM, 8 vCPU, 200GB SSD) | clouding.io | €40-80 |
 | Domain | Namecheap/Cloudflare | ~€1.25 (€15/year) |
-| Email Relay | Mailgun (free tier) | €0 |
+| Email Relay | MailerSend (free tier: 3K emails/month) | €0 |
 | SSL Certificates | Let's Encrypt | €0 |
 | DNS | Cloudflare | €0 |
 | **Total** | | **€41-81/month** |
@@ -137,7 +140,7 @@ Phase 8: Verification & Validation
 - [ ] **VPS Provider** (clouding.io, Hetzner, DigitalOcean, etc.)
 - [ ] **Domain Registrar** (Namecheap, Cloudflare, etc.)
 - [ ] **Cloudflare Account** (recommended for DNS)
-- [ ] **Mailgun Account** (for email relay, optional)
+- [ ] **MailerSend Account** (for email relay - https://mailersend.com, optional)
 - [ ] **Stripe Account** (for payments)
 
 ### Local Machine Requirements
@@ -379,7 +382,7 @@ Add these DNS records pointing to your VPS IP (`200.234.233.87`):
 | A | registry | 200.234.233.87 | Auto |
 | A | api | 200.234.233.87 | Auto |
 | MX | @ | mail.bakewise.ai | 10 |
-| TXT | @ | v=spf1 mx a -all | Auto |
+| TXT | @ | v=spf1 include:mailersend.net mx a ~all | Auto |
 | TXT | _dmarc | v=DMARC1; p=reject; rua=mailto:admin@bakewise.ai | Auto |
 
 ### Step 2.2: Verify DNS Propagation
@@ -654,6 +657,138 @@ flux get sources git -n flux-system
 flux get kustomizations -n flux-system
 ```
 
+### Step 4.6: Configure Gitea Webhook for CI/CD Pipeline
+
+> **Important:** The Tekton EventListener is exposed via an internal Kubernetes service. For Gitea (running in the same cluster) to trigger pipelines, you need to configure a webhook pointing to the EventListener service.
+
+```bash
+# Get the EventListener service details
+kubectl get svc -n tekton-pipelines | grep el-bakery-ia
+
+# Expected output:
+# el-bakery-ia-event-listener   ClusterIP   10.x.x.x   <none>   8080/TCP,9000/TCP
+```
+
+**Configure Webhook in Gitea UI:**
+
+1. Navigate to: `https://gitea.bakewise.ai/bakery-admin/bakery-ia/settings/hooks`
+2. Click **"Add Webhook"** → **"Gitea"**
+3. Configure the webhook:
+
+| Setting | Value |
+|---------|-------|
+| **Target URL** | `http://el-bakery-ia-event-listener.tekton-pipelines.svc.cluster.local:8080` |
+| **HTTP Method** | POST |
+| **Content Type** | application/json |
+| **Secret** | (leave empty or use `$TEKTON_WEBHOOK_TOKEN` from Step 4.4) |
+| **Trigger On** | Push Events |
+| **Branch Filter** | `main` |
+| **Active** | ✅ Checked |
+
+4. Click **"Add Webhook"**
+5. Click **"Test Delivery"** to verify connectivity
+
+**Verify Webhook Works:**
+
+```bash
+# Watch for new PipelineRuns after pushing a commit
+kubectl get pipelineruns -n tekton-pipelines --watch
+
+# Or make a test push
+cd /root/bakery-ia
+git commit --allow-empty -m "Test CI/CD trigger"
+git push origin main
+
+# Check if pipeline was triggered
+kubectl get pipelineruns -n tekton-pipelines
+```
+
+**Alternative: External Webhook URL (if DNS issues)**
+
+If Gitea cannot resolve the internal service DNS, an ingress was created for external access:
+
+```bash
+# Verify EventListener ingress exists
+kubectl get ingress -n tekton-pipelines
+
+# Use external URL instead:
+# Target URL: https://tekton-webhook.bakewise.ai
+```
+
+> **DNS Note:** The internal URL (`http://el-bakery-ia-event-listener.tekton-pipelines.svc.cluster.local:8080`) should work for Gitea pods in the same cluster. If you encounter DNS resolution errors, use the external ingress URL.
+
+### Step 4.7: Configure PipelineRun Cleanup (Optional but Recommended)
+
+> **Purpose:** Completed PipelineRuns and TaskRuns accumulate over time and consume etcd storage. Configure automatic pruning to keep only recent runs.
+
+**Option A: Configure Tekton Pruner (Recommended)**
+
+```bash
+# Create a CronJob to prune old PipelineRuns and TaskRuns
+cat <<EOF | kubectl apply -f -
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: tekton-resource-pruner
+  namespace: tekton-pipelines
+spec:
+  schedule: "0 2 * * *"  # Run daily at 2 AM
+  jobTemplate:
+    spec:
+      template:
+        spec:
+          serviceAccountName: tekton-pipeline-sa
+          containers:
+          - name: pruner
+            image: bitnami/kubectl:latest
+            command:
+            - /bin/sh
+            - -c
+            - |
+              echo "Pruning PipelineRuns older than 7 days..."
+              kubectl delete pipelineruns -n tekton-pipelines \
+                --field-selector=status.completionTime!="" \
+                --selector='tekton.dev/pipeline=bakery-ia-ci' \
+                --sort-by=.metadata.creationTimestamp \
+                | head -n -5 || true
+              echo "Pruning completed TaskRuns..."
+              kubectl get taskruns -n tekton-pipelines \
+                -o jsonpath='{range .items[?(@.status.completionTime)]}{.metadata.name}{"\n"}{end}' \
+                | head -n -10 \
+                | xargs -r kubectl delete taskrun -n tekton-pipelines || true
+              echo "Cleanup complete"
+          restartPolicy: OnFailure
+EOF
+```
+
+**Option B: Manual Cleanup**
+
+```bash
+# Delete all completed PipelineRuns (keep last 5)
+kubectl get pipelineruns -n tekton-pipelines --sort-by=.metadata.creationTimestamp -o name | head -n -5 | xargs -r kubectl delete -n tekton-pipelines
+
+# Delete all completed TaskRuns (keep last 10)
+kubectl get taskruns -n tekton-pipelines --sort-by=.metadata.creationTimestamp -o name | head -n -10 | xargs -r kubectl delete -n tekton-pipelines
+
+# Delete PipelineRuns older than 7 days
+kubectl get pipelineruns -n tekton-pipelines -o json | \
+  jq -r '.items[] | select(.metadata.creationTimestamp | fromdateiso8601 < (now - 604800)) | .metadata.name' | \
+  xargs -r kubectl delete pipelinerun -n tekton-pipelines
+```
+
+**Check Current Resource Usage:**
+
+```bash
+# Count PipelineRuns
+kubectl get pipelineruns -n tekton-pipelines --no-headers | wc -l
+
+# Count TaskRuns
+kubectl get taskruns -n tekton-pipelines --no-headers | wc -l
+
+# Check etcd storage (if metrics-server is enabled)
+kubectl top pods -n kube-system -l component=etcd
+```
+
 
 ## Phase 5: Pre-Pull and Push Base Images to Gitea Registry
 
@@ -1045,38 +1180,84 @@ kubectl exec -n bakery-ia deployment/gateway -- curl -s http://localhost:8000/he
 
 ## Phase 7: Deploy Optional Services
 
-### Step 7.1: Deploy Unbound DNS (Required for Mailu)
+### Step 7.1: Configure CoreDNS with DNS-over-TLS for DNSSEC
+
+> **DNS Architecture:** CoreDNS is configured to use DNS-over-TLS with Cloudflare (1.1.1.1) for DNSSEC validation.
+> This provides DNSSEC support for Mailu without requiring additional DNS pods.
 
 ```bash
-# Deploy Unbound DNS resolver
+# Check if CoreDNS is already configured with DNS-over-TLS
-helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
+kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'tls://1.1.1.1' || echo "Not configured"
-  -n bakery-ia \
-  -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-  -f infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml \
-  --timeout 5m \
-  --wait
 
-# Get Unbound service IP
+# If not configured, update CoreDNS to use DNS-over-TLS with Cloudflare
-UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
+cat > /tmp/coredns-corefile.yaml << 'EOF'
-echo "Unbound DNS IP: $UNBOUND_IP"
+apiVersion: v1
-```
+kind: ConfigMap
+metadata:
+  name: coredns
+  namespace: kube-system
+data:
+  Corefile: |
+    .:53 {
+        errors
+        health {
+           lameduck 5s
+        }
+        ready
+        kubernetes cluster.local in-addr.arpa ip6.arpa {
+           pods insecure
+           fallthrough in-addr.arpa ip6.arpa
+           ttl 30
+        }
+        prometheus :9153
+        forward . tls://1.1.1.1 tls://1.0.0.1 {
+           tls_servername cloudflare-dns.com
+           health_check 5s
+        }
+        cache 30 {
+           disable success cluster.local
+           disable denial cluster.local
+        }
+        loop
+        reload
+        loadbalance
+    }
+EOF
 
-### Step 7.2: Configure CoreDNS for DNSSEC
+kubectl apply -f /tmp/coredns-corefile.yaml
 
-```bash
+# Restart CoreDNS to apply changes
-# Patch CoreDNS to forward to Unbound
-kubectl patch configmap coredns -n kube-system --type merge -p "{
-  \"data\": {
-    \"Corefile\": \".:53 {\\n    errors\\n    health {\\n       lameduck 5s\\n    }\\n    ready\\n    kubernetes cluster.local in-addr.arpa ip6.arpa {\\n       pods insecure\\n       fallthrough in-addr.arpa ip6.arpa\\n       ttl 30\\n    }\\n    prometheus :9153\\n    forward . $UNBOUND_IP {\\n       max_concurrent 1000\\n    }\\n    cache 30\\n    loop\\n    reload\\n    loadbalance\\n}\\n\"
-  }
-}"
-
-# Restart CoreDNS
 kubectl rollout restart deployment coredns -n kube-system
 kubectl rollout status deployment coredns -n kube-system --timeout=60s
+
+# Verify CoreDNS is running
+kubectl get pods -n kube-system -l k8s-app=kube-dns
+# Expected: 1/1 Running
+
+# Get CoreDNS service IP (will be used for Mailu)
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+echo "CoreDNS IP: $COREDNS_IP"
+# Save this IP - you'll need it for Step 7.2
+
+# Test DNS resolution is working
+kubectl run -it --rm dns-test --image=busybox --restart=Never -- nslookup google.com
+# Expected: Should resolve google.com successfully
 ```
 
-### Step 7.3: Deploy Mailu Email Server
+**Troubleshooting CoreDNS:**
+
+```bash
+# Check CoreDNS logs
+kubectl logs -n kube-system -l k8s-app=kube-dns
+
+# Check CoreDNS configuration
+kubectl get configmap coredns -n kube-system -o yaml
+
+# Verify DNS-over-TLS is working
+kubectl run -it --rm dns-test --image=busybox --restart=Never -- nslookup cloudflare.com
+```
+
+### Step 7.2: Deploy Mailu Email Server
 
 ```bash
 # Add Mailu Helm repository
@@ -1084,27 +1265,41 @@ helm repo add mailu https://mailu.github.io/helm-charts
 helm repo update
 
 # Apply Mailu configuration secrets
-# These are pre-configured with secure defaults
 kubectl apply -f infrastructure/platform/mail/mailu-helm/configs/mailu-admin-credentials-secret.yaml -n bakery-ia
 kubectl apply -f infrastructure/platform/mail/mailu-helm/configs/mailu-certificates-secret.yaml -n bakery-ia
 
+# Get CoreDNS service IP dynamically
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+echo "Using CoreDNS IP: $COREDNS_IP"
+
 # Install Mailu with production configuration
-# The Helm chart uses the pre-configured secrets for admin credentials and TLS certificates
+# The --set flag dynamically passes the CoreDNS IP for DNS resolution
+# DNSSEC validation is provided by CoreDNS via DNS-over-TLS to Cloudflare
 helm upgrade --install mailu mailu/mailu \
   -n bakery-ia \
   -f infrastructure/platform/mail/mailu-helm/values.yaml \
   -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+  --set global.custom_dns_servers="$COREDNS_IP" \
   --timeout 10m
 
-# Wait for Mailu to be ready
+# Wait for Mailu to be ready (may take 5-10 minutes)
 kubectl wait --for=condition=available --timeout=600s deployment/mailu-front -n bakery-ia
 
+# Deploy the Mailu ingress for mail.bakewise.ai
+# Note: Use prod/mailu-ingress.yaml for production, dev/mailu-ingress.yaml for development
+kubectl apply -f infrastructure/platform/mail/mailu-helm/prod/mailu-ingress.yaml
+
+# Verify Mailu ingress is created
+kubectl get ingress mailu-ingress -n bakery-ia
+
 # Verify Mailu pods are running
 kubectl get pods -n bakery-ia | grep mailu
 
-# Get the admin password from the pre-configured secret
+# Get the admin password
 MAILU_ADMIN_PASSWORD=$(kubectl get secret mailu-admin-credentials -n bakery-ia -o jsonpath='{.data.password}' | base64 -d)
+echo "============================================"
 echo "Mailu Admin Password: $MAILU_ADMIN_PASSWORD"
+echo "============================================"
 echo "⚠️  SAVE THIS PASSWORD SECURELY!"
 
 # Check Mailu initialization status
@@ -1113,53 +1308,60 @@ kubectl logs -n bakery-ia deployment/mailu-front --tail=10
 
 > **Important Notes about Mailu Deployment:**
 >
-> 1. **Pre-Configured Secrets:** Mailu uses pre-configured secrets for admin credentials and TLS certificates. These are defined in the configuration files.
+> 1. **Pre-Configured Secrets:** Mailu uses pre-configured secrets for admin credentials and TLS certificates.
 >
-> 2. **Password Management:** The admin password is stored in `mailu-admin-credentials-secret.yaml`. For production, you should update this with a secure password before deployment.
+> 2. **Password Management:** Update `mailu-admin-credentials-secret.yaml` with a secure password before deployment.
 >
-> 3. **TLS Certificates:** The self-signed certificates in `mailu-certificates-secret.yaml` are for initial setup. For production, replace these with proper certificates from cert-manager (see Step 7.3.1).
+> 3. **TLS Certificates:** Self-signed certificates are used internally. External traffic uses Let's Encrypt via Ingress.
 >
-> 4. **Initialization Time:** Mailu may take 5-10 minutes to fully initialize. During this time, some pods may restart as the system configures itself.
+> 4. **Initialization Time:** Mailu may take 5-10 minutes to fully initialize. Pods may restart during setup.
 >
 > 5. **Accessing Mailu:**
 >   - Webmail: `https://mail.bakewise.ai/webmail`
 >   - Admin Interface: `https://mail.bakewise.ai/admin`
 >   - Username: `admin@bakewise.ai`
->   - Password: (from `mailu-admin-credentials-secret.yaml`)
+>   - Password: (from secret above)
 >
-> 6. **Mailgun Relay:** The production configuration includes Mailgun SMTP relay. Configure your Mailgun credentials in `mailu-mailgun-credentials-secret.yaml` before deployment.
+> 6. **MailerSend Relay:** Configure credentials in `mailersend-credentials-secret.yaml` before deployment.
 
 ### Step 7.3.1: Mailu Configuration Notes
 
-> **Important Information about Mailu Certificates:**
+> **Certificate Architecture:**
 >
-> 1. **Dual Certificate Architecture:**
+> ```
->   - **Internal Communication:** Uses self-signed certificates (`mailu-certificates-secret.yaml`)
+> External Client → NGINX Ingress (Let's Encrypt) → Internal Network → Mailu Services (Self-signed)
->   - **External Communication:** Uses Let's Encrypt certificates via NGINX Ingress (`bakery-ia-prod-tls-cert`)
+> ```
 >
-> 2. **No Certificate Replacement Needed:** The self-signed certificates are only used for internal communication between Mailu services. External clients connect through the NGINX Ingress Controller which uses the publicly trusted Let's Encrypt certificates.
+> - **External:** Uses publicly trusted Let's Encrypt certificates via NGINX Ingress
->
+> - **Internal:** Uses self-signed certificates for inter-service communication
-> 3. **Certificate Flow:**
+> - **No replacement needed:** This dual-certificate architecture is intentional and secure
->   ```
+
->   External Client → NGINX Ingress (Let's Encrypt) → Internal Network → Mailu Services (Self-signed)
+**Configure MailerSend Relay (for outbound email):**
->   ```
+
->
+```bash
-> 4. **Security:** This architecture is secure because:
+# 1. Sign up at https://accounts.mailersend.com/signup
->   - External connections use publicly trusted certificates
+# 2. Add your domain (bakewise.ai) and verify DNS records
->   - Internal connections are still encrypted (even if self-signed)
+# 3. Generate SMTP credentials: Email -> Domains -> SMTP -> Generate new user
->   - Ingress terminates TLS, reducing load on Mailu services
+
->
+# Edit the MailerSend credentials secret
-> 5. **Mailgun Relay Configuration:** For outbound email delivery, configure your Mailgun credentials:
+nano infrastructure/platform/mail/mailu-helm/configs/mailersend-credentials-secret.yaml
->   ```bash
+
->   # Edit the Mailgun credentials secret
+# Apply the secret
->   nano infrastructure/platform/mail/mailu-helm/configs/mailu-mailgun-credentials-secret.yaml
+kubectl apply -f infrastructure/platform/mail/mailu-helm/configs/mailersend-credentials-secret.yaml -n bakery-ia
->   
+
->   # Apply the secret
+# Restart Mailu to pick up the new relay configuration
->   kubectl apply -f infrastructure/platform/mail/mailu-helm/configs/mailu-mailgun-credentials-secret.yaml -n bakery-ia
+kubectl rollout restart deployment -n bakery-ia -l app.kubernetes.io/instance=mailu
->   
+```
->   # Restart Mailu to pick up the new relay configuration
+
->   kubectl rollout restart deployment -n bakery-ia -l app.kubernetes.io/instance=mailu
+**MailerSend DNS Records (add to Cloudflare):**
->   ```
+
+| Type | Name | Value |
+|------|------|-------|
+| TXT (SPF) | @ | v=spf1 include:mailersend.net mx a ~all |
+| TXT (DKIM) | mlsend._domainkey | (from MailerSend dashboard) |
+| TXT (DKIM) | mlsend2._domainkey | (from MailerSend dashboard) |
+
+> **Note:** MailerSend free tier includes 3,000 emails/month (12,000 with verified domain).
 
 ### Step 7.4: Deploy SigNoz Monitoring
 
@@ -1184,6 +1386,77 @@ kubectl wait --for=condition=available --timeout=600s deployment/signoz-frontend
 kubectl get pods -n bakery-ia -l app.kubernetes.io/instance=signoz
 ```
 
+### Step 7.5: Deploy Kubernetes Infrastructure Monitoring (Required for SigNoz Infrastructure View)
+
+> **Purpose:** Deploy kube-state-metrics and node-exporter to enable Kubernetes infrastructure metrics in SigNoz. Without these components, the SigNoz Infrastructure section will be empty.
+
+**Components Deployed:**
+
+| Component | Purpose | Metrics |
+|-----------|---------|---------|
+| **kube-state-metrics** | Kubernetes object metrics | Pods, Deployments, Nodes, PVCs, etc. |
+| **node-exporter** | Host-level metrics | CPU, Memory, Disk, Network |
+
+**Deploy using the automated script:**
+
+```bash
+# Navigate to the k8s-infra monitoring directory
+cd /root/bakery-ia
+
+# Make the script executable (if not already)
+chmod +x infrastructure/monitoring/k8s-infra/deploy-k8s-infra-monitoring.sh
+
+# Deploy kube-state-metrics and node-exporter
+./infrastructure/monitoring/k8s-infra/deploy-k8s-infra-monitoring.sh --microk8s install
+```
+
+**Upgrade SigNoz to scrape the new metrics:**
+
+```bash
+# The signoz-values-prod.yaml already includes the Prometheus receiver configuration
+# Upgrade SigNoz to apply the scraping configuration
+microk8s helm3 upgrade signoz signoz/signoz \
+  -n bakery-ia \
+  -f infrastructure/monitoring/signoz/signoz-values-prod.yaml
+```
+
+**Verify deployment:**
+
+```bash
+# Check pods are running
+microk8s kubectl get pods -n bakery-ia | grep -E "(kube-state|node-exporter)"
+
+# Expected output:
+# kube-state-metrics-xxxxxxxxxx-xxxxx    1/1     Running   0          1m
+# node-exporter-prometheus-node-exporter-xxxxx   1/1     Running   0          1m
+
+# Check status
+./infrastructure/monitoring/k8s-infra/deploy-k8s-infra-monitoring.sh --microk8s status
+```
+
+**Verify metrics in SigNoz:**
+
+After a few minutes, you should see:
+- **Infrastructure → Kubernetes**: Pod status, deployments, nodes, PVCs
+- **Infrastructure → Hosts**: CPU, memory, disk, network usage
+
+**Troubleshooting:**
+
+```bash
+# Check if metrics are being scraped
+microk8s kubectl port-forward svc/kube-state-metrics 8080:8080 -n bakery-ia &
+curl localhost:8080/metrics | head -20
+
+# Check OTel Collector logs for scraping errors
+microk8s kubectl logs -l app.kubernetes.io/name=signoz-otel-collector -n bakery-ia --tail=50
+```
+
+> **Files Location:**
+> - Helm values: `infrastructure/monitoring/k8s-infra/kube-state-metrics-values.yaml`
+> - Helm values: `infrastructure/monitoring/k8s-infra/node-exporter-values.yaml`
+> - Deploy script: `infrastructure/monitoring/k8s-infra/deploy-k8s-infra-monitoring.sh`
+> - Documentation: `infrastructure/monitoring/k8s-infra/README.md`
+
 ---
 
 ## Phase 8: Verification & Validation

Tiltfile

@@ -46,6 +46,10 @@ if use_dockerhub:
     base_registry = 'docker.io'
     python_image = 'python:3.11-slim'
 
+# Git commit hash for migration job names (extracted from manifest to match CI/CD updates)
+# We read from a manifest file rather than git HEAD because CI/CD commits may not be checked out locally
+git_commit_short = str(local("sed -n 's/.*name: auth-migration-\\([a-f0-9]*\\).*/\\1/p' infrastructure/services/microservices/auth/migrations/auth-migration-job.yaml | head -1", quiet=True)).strip()
+
 
 # =============================================================================
 # PREPULL BASE IMAGES - RUNS AFTER SECURITY SETUP
@@ -728,100 +732,20 @@ k8s_resource('rabbitmq', resource_deps=['security-setup'], labels=['01-infrastru
 k8s_resource('minio', resource_deps=['security-setup'], labels=['01-infrastructure'])
 k8s_resource('minio-bucket-init', resource_deps=['minio'], labels=['01-infrastructure'])
 
-# Unbound DNSSEC Resolver - Infrastructure component for Mailu DNS validation
+# CoreDNS DNSSEC Configuration - Infrastructure component for Mailu DNS validation
 local_resource(
-    'unbound-helm',
+    'coredns-dnssec',
     cmd='''
-        echo "Deploying Unbound DNS resolver via Helm..."
+        echo "Configuring CoreDNS with DNS-over-TLS for DNSSEC validation..."
         echo ""
 
-        # Check if Unbound is already deployed
+        # Check if CoreDNS is already configured with DNS-over-TLS
-        if helm list -n bakery-ia | grep -q unbound; then
+        CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' 2>/dev/null | grep -o 'tls://1.1.1.1' || echo "")
-            echo "Unbound already deployed, checking status..."
-            helm status unbound -n bakery-ia
-        else
-            echo "Installing Unbound..."
 
-            # Determine environment (dev or prod) based on context
+        if [ -z "$CURRENT_FORWARD" ]; then
-            ENVIRONMENT="dev"
+            echo "Updating CoreDNS to use DNS-over-TLS with Cloudflare..."
-            if [[ "$(kubectl config current-context)" == *"prod"* ]]; then
-                ENVIRONMENT="prod"
-            fi
 
-            echo "Environment detected: $ENVIRONMENT"
+            # Create a temporary Corefile with the DNS-over-TLS configuration
-
-            # Install Unbound with appropriate values
-            if [ "$ENVIRONMENT" = "dev" ]; then
-                helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
-                    -n bakery-ia \
-                    --create-namespace \
-                    -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-                    -f infrastructure/platform/networking/dns/unbound-helm/dev/values.yaml \
-                    --timeout 5m \
-                    --wait
-            else
-                helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
-                    -n bakery-ia \
-                    --create-namespace \
-                    -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-                    -f infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml \
-                    --timeout 5m \
-                    --wait
-            fi
-
-            echo ""
-            echo "Unbound deployment completed"
-        fi
-
-        echo ""
-        echo "Unbound DNS Service Information:"
-        echo "   Service Name: unbound-dns.bakery-ia.svc.cluster.local"
-        echo "   Ports: UDP/TCP 53"
-        echo "   Used by: Mailu for DNS validation"
-        echo ""
-        echo "To check pod status: kubectl get pods -n bakery-ia | grep unbound"
-    ''',
-    resource_deps=['security-setup'],
-    labels=['01-infrastructure'],
-    auto_init=True  # Auto-deploy with Tilt startup
-)
-
-# Mail Infrastructure (Mailu) - Manual trigger for Helm deployment
-local_resource(
-    'mailu-helm',
-    cmd='''
-        echo "Deploying Mailu via Helm..."
-        echo ""
-
-        # =====================================================
-        # Step 1: Ensure Unbound is deployed and get its IP
-        # =====================================================
-        echo "Checking Unbound DNS resolver..."
-        if ! kubectl get svc unbound-dns -n bakery-ia &>/dev/null; then
-            echo "ERROR: Unbound DNS service not found!"
-            echo "Please deploy Unbound first by triggering 'unbound-helm' resource"
-            exit 1
-        fi
-
-        UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
-        echo "Unbound DNS service IP: $UNBOUND_IP"
-
-        # =====================================================
-        # Step 2: Configure CoreDNS to forward to Unbound
-        # =====================================================
-        echo ""
-        echo "Configuring CoreDNS to forward external queries to Unbound for DNSSEC validation..."
-
-        # Check current CoreDNS forward configuration
-        CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'forward \\. [0-9.]*' | awk '{print $3}')
-
-        if [ "$CURRENT_FORWARD" != "$UNBOUND_IP" ]; then
-            echo "Updating CoreDNS to forward to Unbound ($UNBOUND_IP)..."
-
-            # Change to project root to ensure correct file paths
-            cd /Users/urtzialfaro/Documents/bakery-ia
-
-            # Create a temporary Corefile with the forwarding configuration
             TEMP_COREFILE=$(mktemp)
             cat > "$TEMP_COREFILE" << EOF
 .:53 {
@@ -836,8 +760,9 @@ local_resource(
        ttl 30
     }
     prometheus :9153
-    forward . $UNBOUND_IP {
+    forward . tls://1.1.1.1 tls://1.0.0.1 {
-       max_concurrent 1000
+       tls_servername cloudflare-dns.com
+       health_check 5s
     }
     cache 30 {
        disable success cluster.local
@@ -871,13 +796,44 @@ EOF
             kubectl rollout restart deployment coredns -n kube-system
             echo "Waiting for CoreDNS to restart..."
             kubectl rollout status deployment coredns -n kube-system --timeout=60s
-            echo "CoreDNS configured successfully"
+            echo "CoreDNS configured successfully with DNS-over-TLS"
         else
-            echo "CoreDNS already configured to forward to Unbound"
+            echo "CoreDNS already configured with DNS-over-TLS"
         fi
 
+        # Get CoreDNS service IP
+        COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+
+        echo ""
+        echo "CoreDNS DNSSEC Configuration:"
+        echo "   CoreDNS IP: $COREDNS_IP"
+        echo "   Upstream: Cloudflare DNS-over-TLS (1.1.1.1, 1.0.0.1)"
+        echo "   DNSSEC: Validated by Cloudflare"
+        echo "   Used by: Mailu for DNS validation"
+        echo ""
+        echo "To check CoreDNS status: kubectl get pods -n kube-system -l k8s-app=kube-dns"
+    ''',
+    resource_deps=['security-setup'],
+    labels=['01-infrastructure'],
+    auto_init=True  # Auto-deploy with Tilt startup
+)
+
+# Mail Infrastructure (Mailu) - Manual trigger for Helm deployment
+local_resource(
+    'mailu-helm',
+    cmd='''
+        echo "Deploying Mailu via Helm..."
+        echo ""
+
         # =====================================================
-        # Step 3: Create self-signed TLS certificate for Mailu Front
+        # Step 1: Get CoreDNS service IP
+        # =====================================================
+        echo "Getting CoreDNS service IP..."
+        COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+        echo "CoreDNS service IP: $COREDNS_IP"
+
+        # =====================================================
+        # Step 2: Create self-signed TLS certificate for Mailu Front
         # =====================================================
         echo ""
         echo "Checking Mailu TLS certificates..."
@@ -905,7 +861,7 @@ EOF
         fi
 
         # =====================================================
-        # Step 4: Deploy Mailu via Helm
+        # Step 3: Deploy Mailu via Helm
         # =====================================================
         echo ""
 
@@ -938,6 +894,7 @@ EOF
                     --create-namespace \
                     -f infrastructure/platform/mail/mailu-helm/values.yaml \
                     -f infrastructure/platform/mail/mailu-helm/dev/values.yaml \
+                    --set global.custom_dns_servers="$COREDNS_IP" \
                     --timeout 10m
             else
                 helm upgrade --install mailu mailu/mailu \
@@ -945,6 +902,7 @@ EOF
                     --create-namespace \
                     -f infrastructure/platform/mail/mailu-helm/values.yaml \
                     -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+                    --set global.custom_dns_servers="$COREDNS_IP" \
                     --timeout 10m
             fi
 
@@ -953,7 +911,7 @@ EOF
         fi
 
         # =====================================================
-        # Step 5: Apply Mailu Ingress
+        # Step 4: Apply Mailu Ingress
         # =====================================================
         echo ""
         echo "Applying Mailu ingress configuration..."
@@ -962,7 +920,7 @@ EOF
         echo "Mailu ingress applied for mail.bakery-ia.dev"
 
         # =====================================================
-        # Step 6: Wait for pods and show status
+        # Step 5: Wait for pods and show status
         # =====================================================
         echo ""
         echo "Waiting for Mailu pods to be ready..."
@@ -975,16 +933,20 @@ EOF
         echo ""
         echo "Mailu Access Information:"
         echo "   Admin Panel: https://mail.bakery-ia.dev/admin"
-        echo "   Webmail:     https://mail.bakery-ia.ldev/webmail"
+        echo "   Webmail:     https://mail.bakery-ia.dev/webmail"
         echo "   SMTP:        mail.bakery-ia.dev:587 (STARTTLS)"
         echo "   IMAP:        mail.bakery-ia.dev:993 (SSL/TLS)"
         echo ""
+        echo "DNS Configuration:"
+        echo "   CoreDNS IP: $COREDNS_IP"
+        echo "   DNSSEC: Provided via DNS-over-TLS (Cloudflare)"
+        echo ""
         echo "To create admin user:"
         echo "   Admin user created automatically via initialAccount feature in Helm values"
         echo ""
         echo "To check pod status: kubectl get pods -n bakery-ia | grep mailu"
     ''',
-    resource_deps=['unbound-helm'],  # Ensure Unbound is deployed first
+    resource_deps=['coredns-dnssec'],  # Ensure CoreDNS DNSSEC is configured first
     labels=['01-infrastructure'],
     auto_init=False,  # Manual trigger only
 )
@@ -1231,79 +1193,80 @@ k8s_resource('demo-session-db', resource_deps=['security-setup'], labels=['06-da
 # =============================================================================
 # MIGRATION JOBS
 # =============================================================================
+# Migration job names include git commit hash (set by CI/CD in manifests)
 
 # Core Service Migrations
-k8s_resource('auth-migration', resource_deps=['auth-db'], labels=['07-migrations'])
+k8s_resource('auth-migration-' + git_commit_short, resource_deps=['auth-db'], labels=['07-migrations'])
-k8s_resource('tenant-migration', resource_deps=['tenant-db'], labels=['07-migrations'])
+k8s_resource('tenant-migration-' + git_commit_short, resource_deps=['tenant-db'], labels=['07-migrations'])
 
 # Data & Analytics Migrations
-k8s_resource('training-migration', resource_deps=['training-db'], labels=['07-migrations'])
+k8s_resource('training-migration-' + git_commit_short, resource_deps=['training-db'], labels=['07-migrations'])
-k8s_resource('forecasting-migration', resource_deps=['forecasting-db'], labels=['07-migrations'])
+k8s_resource('forecasting-migration-' + git_commit_short, resource_deps=['forecasting-db'], labels=['07-migrations'])
-k8s_resource('ai-insights-migration', resource_deps=['ai-insights-db'], labels=['07-migrations'])
+k8s_resource('ai-insights-migration-' + git_commit_short, resource_deps=['ai-insights-db'], labels=['07-migrations'])
 
 # Operations Migrations
-k8s_resource('sales-migration', resource_deps=['sales-db'], labels=['07-migrations'])
+k8s_resource('sales-migration-' + git_commit_short, resource_deps=['sales-db'], labels=['07-migrations'])
-k8s_resource('inventory-migration', resource_deps=['inventory-db'], labels=['07-migrations'])
+k8s_resource('inventory-migration-' + git_commit_short, resource_deps=['inventory-db'], labels=['07-migrations'])
-k8s_resource('production-migration', resource_deps=['production-db'], labels=['07-migrations'])
+k8s_resource('production-migration-' + git_commit_short, resource_deps=['production-db'], labels=['07-migrations'])
-k8s_resource('procurement-migration', resource_deps=['procurement-db'], labels=['07-migrations'])
+k8s_resource('procurement-migration-' + git_commit_short, resource_deps=['procurement-db'], labels=['07-migrations'])
-k8s_resource('distribution-migration', resource_deps=['distribution-db'], labels=['07-migrations'])
+k8s_resource('distribution-migration-' + git_commit_short, resource_deps=['distribution-db'], labels=['07-migrations'])
 
 # Supporting Service Migrations
-k8s_resource('recipes-migration', resource_deps=['recipes-db'], labels=['07-migrations'])
+k8s_resource('recipes-migration-' + git_commit_short, resource_deps=['recipes-db'], labels=['07-migrations'])
-k8s_resource('suppliers-migration', resource_deps=['suppliers-db'], labels=['07-migrations'])
+k8s_resource('suppliers-migration-' + git_commit_short, resource_deps=['suppliers-db'], labels=['07-migrations'])
-k8s_resource('pos-migration', resource_deps=['pos-db'], labels=['07-migrations'])
+k8s_resource('pos-migration-' + git_commit_short, resource_deps=['pos-db'], labels=['07-migrations'])
-k8s_resource('orders-migration', resource_deps=['orders-db'], labels=['07-migrations'])
+k8s_resource('orders-migration-' + git_commit_short, resource_deps=['orders-db'], labels=['07-migrations'])
-k8s_resource('external-migration', resource_deps=['external-db'], labels=['07-migrations'])
+k8s_resource('external-migration-' + git_commit_short, resource_deps=['external-db'], labels=['07-migrations'])
 
 # Platform Service Migrations
-k8s_resource('notification-migration', resource_deps=['notification-db'], labels=['07-migrations'])
+k8s_resource('notification-migration-' + git_commit_short, resource_deps=['notification-db'], labels=['07-migrations'])
-k8s_resource('alert-processor-migration', resource_deps=['alert-processor-db'], labels=['07-migrations'])
+k8s_resource('alert-processor-migration-' + git_commit_short, resource_deps=['alert-processor-db'], labels=['07-migrations'])
-k8s_resource('orchestrator-migration', resource_deps=['orchestrator-db'], labels=['07-migrations'])
+k8s_resource('orchestrator-migration-' + git_commit_short, resource_deps=['orchestrator-db'], labels=['07-migrations'])
 
 # Demo Service Migrations
-k8s_resource('demo-session-migration', resource_deps=['demo-session-db'], labels=['07-migrations'])
+k8s_resource('demo-session-migration-' + git_commit_short, resource_deps=['demo-session-db'], labels=['07-migrations'])
 
 # =============================================================================
 # DATA INITIALIZATION JOBS
 # =============================================================================
 
-k8s_resource('external-data-init', resource_deps=['external-migration', 'redis'], labels=['08-data-init'])
+k8s_resource('external-data-init-' + git_commit_short, resource_deps=['external-migration-' + git_commit_short, 'redis'], labels=['08-data-init'])
 
 # =============================================================================
 # APPLICATION SERVICES
 # =============================================================================
 
 # Core Services
-k8s_resource('auth-service', resource_deps=['auth-migration', 'redis'], labels=['09-services-core'])
+k8s_resource('auth-service', resource_deps=['auth-migration-' + git_commit_short, 'redis'], labels=['09-services-core'])
-k8s_resource('tenant-service', resource_deps=['tenant-migration', 'redis'], labels=['09-services-core'])
+k8s_resource('tenant-service', resource_deps=['tenant-migration-' + git_commit_short, 'redis'], labels=['09-services-core'])
 
 # Data & Analytics Services
-k8s_resource('training-service', resource_deps=['training-migration', 'redis'], labels=['10-services-analytics'])
+k8s_resource('training-service', resource_deps=['training-migration-' + git_commit_short, 'redis'], labels=['10-services-analytics'])
-k8s_resource('forecasting-service', resource_deps=['forecasting-migration', 'redis'], labels=['10-services-analytics'])
+k8s_resource('forecasting-service', resource_deps=['forecasting-migration-' + git_commit_short, 'redis'], labels=['10-services-analytics'])
-k8s_resource('ai-insights-service', resource_deps=['ai-insights-migration', 'redis', 'forecasting-service', 'production-service', 'procurement-service'], labels=['10-services-analytics'])
+k8s_resource('ai-insights-service', resource_deps=['ai-insights-migration-' + git_commit_short, 'redis', 'forecasting-service', 'production-service', 'procurement-service'], labels=['10-services-analytics'])
 
 # Operations Services
-k8s_resource('sales-service', resource_deps=['sales-migration', 'redis'], labels=['11-services-operations'])
+k8s_resource('sales-service', resource_deps=['sales-migration-' + git_commit_short, 'redis'], labels=['11-services-operations'])
-k8s_resource('inventory-service', resource_deps=['inventory-migration', 'redis'], labels=['11-services-operations'])
+k8s_resource('inventory-service', resource_deps=['inventory-migration-' + git_commit_short, 'redis'], labels=['11-services-operations'])
-k8s_resource('production-service', resource_deps=['production-migration', 'redis'], labels=['11-services-operations'])
+k8s_resource('production-service', resource_deps=['production-migration-' + git_commit_short, 'redis'], labels=['11-services-operations'])
-k8s_resource('procurement-service', resource_deps=['procurement-migration', 'redis'], labels=['11-services-operations'])
+k8s_resource('procurement-service', resource_deps=['procurement-migration-' + git_commit_short, 'redis'], labels=['11-services-operations'])
-k8s_resource('distribution-service', resource_deps=['distribution-migration', 'redis', 'rabbitmq'], labels=['11-services-operations'])
+k8s_resource('distribution-service', resource_deps=['distribution-migration-' + git_commit_short, 'redis', 'rabbitmq'], labels=['11-services-operations'])
 
 # Supporting Services
-k8s_resource('recipes-service', resource_deps=['recipes-migration', 'redis'], labels=['12-services-supporting'])
+k8s_resource('recipes-service', resource_deps=['recipes-migration-' + git_commit_short, 'redis'], labels=['12-services-supporting'])
-k8s_resource('suppliers-service', resource_deps=['suppliers-migration', 'redis'], labels=['12-services-supporting'])
+k8s_resource('suppliers-service', resource_deps=['suppliers-migration-' + git_commit_short, 'redis'], labels=['12-services-supporting'])
-k8s_resource('pos-service', resource_deps=['pos-migration', 'redis'], labels=['12-services-supporting'])
+k8s_resource('pos-service', resource_deps=['pos-migration-' + git_commit_short, 'redis'], labels=['12-services-supporting'])
-k8s_resource('orders-service', resource_deps=['orders-migration', 'redis'], labels=['12-services-supporting'])
+k8s_resource('orders-service', resource_deps=['orders-migration-' + git_commit_short, 'redis'], labels=['12-services-supporting'])
-k8s_resource('external-service', resource_deps=['external-migration', 'external-data-init', 'redis'], labels=['12-services-supporting'])
+k8s_resource('external-service', resource_deps=['external-migration-' + git_commit_short, 'external-data-init-' + git_commit_short, 'redis'], labels=['12-services-supporting'])
 
 # Platform Services
-k8s_resource('notification-service', resource_deps=['notification-migration', 'redis', 'rabbitmq'], labels=['13-services-platform'])
+k8s_resource('notification-service', resource_deps=['notification-migration-' + git_commit_short, 'redis', 'rabbitmq'], labels=['13-services-platform'])
-k8s_resource('alert-processor', resource_deps=['alert-processor-migration', 'redis', 'rabbitmq'], labels=['13-services-platform'])
+k8s_resource('alert-processor', resource_deps=['alert-processor-migration-' + git_commit_short, 'redis', 'rabbitmq'], labels=['13-services-platform'])
-k8s_resource('orchestrator-service', resource_deps=['orchestrator-migration', 'redis'], labels=['13-services-platform'])
+k8s_resource('orchestrator-service', resource_deps=['orchestrator-migration-' + git_commit_short, 'redis'], labels=['13-services-platform'])
 
 # Demo Services
-k8s_resource('demo-session-service', resource_deps=['demo-session-migration', 'redis'], labels=['14-services-demo'])
+k8s_resource('demo-session-service', resource_deps=['demo-session-migration-' + git_commit_short, 'redis'], labels=['14-services-demo'])
-k8s_resource('demo-cleanup-worker', resource_deps=['demo-session-service', 'redis'], labels=['14-services-demo'])
+k8s_resource('demo-cleanup-worker-' + git_commit_short, resource_deps=['demo-session-service', 'redis'], labels=['14-services-demo'])
 
 # =============================================================================
 # FRONTEND & GATEWAY
@@ -1317,7 +1280,7 @@ k8s_resource('frontend', resource_deps=['gateway'], labels=['15-frontend'])
 # =============================================================================
 
 k8s_resource('demo-session-cleanup', resource_deps=['demo-session-service'], labels=['16-cronjobs'])
-k8s_resource('external-data-rotation', resource_deps=['external-service'], labels=['16-cronjobs'])
+k8s_resource('external-data-rotation-' + git_commit_short, resource_deps=['external-service'], labels=['16-cronjobs'])
 
 # =============================================================================
 # WATCH SETTINGS

docs/PILOT_LAUNCH_GUIDE.md

@@ -91,7 +91,7 @@ The Bakery-IA platform is organized into distinct infrastructure layers, each wi
 │  PostgreSQL (18 DBs) │ Redis │ RabbitMQ │ MinIO                             │
 ├─────────────────────────────────────────────────────────────────────────────┤
 │                         LAYER 2: NETWORK & SECURITY                          │
-│  Unbound DNS │ CoreDNS │ Ingress Controller │ Cert-Manager │ TLS           │
+│  CoreDNS (DNS-over-TLS) │ Ingress Controller │ Cert-Manager │ TLS          │
 ├─────────────────────────────────────────────────────────────────────────────┤
 │                         LAYER 1: FOUNDATION                                  │
 │  Namespaces │ Storage Classes │ RBAC │ ConfigMaps │ Secrets                 │
@@ -112,11 +112,9 @@ Components must be deployed in a specific order due to dependencies:
    ↓
 3. TLS Certificates (internal + ingress)
    ↓
-4. Unbound DNS Resolver (required for Mailu DNSSEC)
+4. CoreDNS Configuration (DNS-over-TLS for DNSSEC)
    ↓
-5. CoreDNS Configuration (forward to Unbound)
+5. Ingress Controller & Resources
-   ↓
-6. Ingress Controller & Resources
    ↓
 7. Data Layer: PostgreSQL, Redis, RabbitMQ, MinIO
    ↓
@@ -146,7 +144,6 @@ Components must be deployed in a specific order due to dependencies:
 | **Redis** | Caching & sessions | Yes | bakery-ia |
 | **RabbitMQ** | Message broker | Yes | bakery-ia |
 | **MinIO** | Object storage (ML models) | Yes | bakery-ia |
-| **Unbound DNS** | DNSSEC resolver | For Mailu | bakery-ia |
 | **Mailu** | Self-hosted email server | Optional | bakery-ia |
 | **Nominatim** | Geocoding service | Optional | bakery-ia |
 | **Gitea** | Git server + container registry | Optional | gitea |
@@ -945,9 +942,8 @@ SMTP_PORT: 587
 #### Prerequisites
 
 Before deploying Mailu, ensure:
-1. **Unbound DNS is deployed** (for DNSSEC validation)
+1. **CoreDNS is configured** with DNS-over-TLS for DNSSEC validation
-2. **CoreDNS is configured** to forward to Unbound
+2. **DNS records are configured** for your domain
-3. **DNS records are configured** for your domain
 
 #### Step 1: Configure DNS Records
 
@@ -963,55 +959,64 @@ TXT     _dmarc          v=DMARC1; p=reject; rua=...     Auto
 
 **DKIM record** will be generated after Mailu is running - you'll add it later.
 
-#### Step 2: Deploy Unbound DNS Resolver
+#### Step 2: Configure CoreDNS for DNSSEC (DNS-over-TLS)
 
-Unbound provides DNSSEC validation required by Mailu for email authentication.
+Mailu requires DNSSEC validation. Configure CoreDNS to use DNS-over-TLS with Cloudflare:
 
 ```bash
-# On VPS - Deploy Unbound via Helm
+# Check if CoreDNS is already configured with DNS-over-TLS
-helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
+kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'tls://1.1.1.1' || echo "Not configured"
-    -n bakery-ia \
-    --create-namespace \
-    -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-    -f infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml \
-    --timeout 5m \
-    --wait
 
-# Verify Unbound is running
+# If not configured, update CoreDNS
-kubectl get pods -n bakery-ia | grep unbound
+cat > /tmp/coredns-corefile.yaml << 'EOF'
-# Should show: unbound-xxx  1/1  Running
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: coredns
+  namespace: kube-system
+data:
+  Corefile: |
+    .:53 {
+        errors
+        health {
+           lameduck 5s
+        }
+        ready
+        kubernetes cluster.local in-addr.arpa ip6.arpa {
+           pods insecure
+           fallthrough in-addr.arpa ip6.arpa
+           ttl 30
+        }
+        prometheus :9153
+        forward . tls://1.1.1.1 tls://1.0.0.1 {
+           tls_servername cloudflare-dns.com
+           health_check 5s
+        }
+        cache 30 {
+           disable success cluster.local
+           disable denial cluster.local
+        }
+        loop
+        reload
+        loadbalance
+    }
+EOF
 
-# Get Unbound service IP (needed for CoreDNS configuration)
+kubectl apply -f /tmp/coredns-corefile.yaml
-UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
-echo "Unbound DNS IP: $UNBOUND_IP"
-```
-
-#### Step 3: Configure CoreDNS for DNSSEC
-
-Mailu requires DNSSEC validation. Configure CoreDNS to forward external queries to Unbound:
-
-```bash
-# Get the Unbound service IP
-UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
-
-# Patch CoreDNS to forward to Unbound
-kubectl patch configmap coredns -n kube-system --type merge -p "{
-  \"data\": {
-    \"Corefile\": \".:53 {\\n    errors\\n    health {\\n       lameduck 5s\\n    }\\n    ready\\n    kubernetes cluster.local in-addr.arpa ip6.arpa {\\n       pods insecure\\n       fallthrough in-addr.arpa ip6.arpa\\n       ttl 30\\n    }\\n    prometheus :9153\\n    forward . $UNBOUND_IP {\\n       max_concurrent 1000\\n    }\\n    cache 30 {\\n       disable success cluster.local\\n       disable denial cluster.local\\n    }\\n    loop\\n    reload\\n    loadbalance\\n}\\n\"
-  }
-}"
 
 # Restart CoreDNS to apply changes
 kubectl rollout restart deployment coredns -n kube-system
 kubectl rollout status deployment coredns -n kube-system --timeout=60s
 
-# Verify DNSSEC is working
+# Get CoreDNS service IP (needed for Mailu configuration)
-kubectl run -it --rm debug --image=alpine --restart=Never -- \
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
-    sh -c "apk add drill && drill -D google.com"
+echo "CoreDNS IP: $COREDNS_IP"
-# Should show: ;; flags: ... ad ...  (ad = authenticated data = DNSSEC valid)
+
+# Verify DNS resolution is working
+kubectl run -it --rm dns-test --image=busybox --restart=Never -- nslookup google.com
 ```
 
-#### Step 4: Create TLS Certificate Secret
+#### Step 3: Create TLS Certificate Secret
 
 Mailu Front pod requires a TLS certificate:
 
@@ -1036,7 +1041,7 @@ rm -rf "$TEMP_DIR"
 kubectl get secret mailu-certificates -n bakery-ia
 ```
 
-#### Step 5: Create Admin Credentials Secret
+#### Step 4: Create Admin Credentials Secret
 
 ```bash
 # Generate a secure password (or use your own)
@@ -1050,30 +1055,35 @@ kubectl create secret generic mailu-admin-credentials \
     -n bakery-ia
 ```
 
-#### Step 6: Deploy Mailu via Helm
+#### Step 5: Deploy Mailu via Helm
 
 ```bash
 # Add Mailu Helm repository
 helm repo add mailu https://mailu.github.io/helm-charts
 helm repo update mailu
 
+# Get CoreDNS service IP
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+
 # Deploy Mailu with production values
 # Admin user is created automatically via initialAccount feature
+# CoreDNS provides DNSSEC validation via DNS-over-TLS to Cloudflare
 helm upgrade --install mailu mailu/mailu \
     -n bakery-ia \
     --create-namespace \
     -f infrastructure/platform/mail/mailu-helm/values.yaml \
     -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+    --set global.custom_dns_servers="$COREDNS_IP" \
     --timeout 10m
 
 # Wait for pods to be ready (may take 5-10 minutes for ClamAV)
 kubectl get pods -n bakery-ia -l app.kubernetes.io/instance=mailu -w
 
 # Admin user (admin@bakewise.ai) is created automatically!
-# Password is the one you set in Step 5
+# Password is the one you set in Step 4
 ```
 
-#### Step 7: Configure DKIM
+#### Step 6: Configure DKIM
 
 After Mailu is running, get the DKIM key and add it to DNS:
 
@@ -1087,7 +1097,7 @@ kubectl exec -n bakery-ia deployment/mailu-admin -- \
 # Value: (the key from above)
 ```
 
-#### Step 8: Verify Email Setup
+#### Step 7: Verify Email Setup
 
 ```bash
 # Check all Mailu pods are running
@@ -1117,11 +1127,11 @@ kubectl port-forward -n bakery-ia svc/mailu-front 8080:80
 
 **Issue: Admin pod CrashLoopBackOff with "DNSSEC validation" error**
 ```bash
-# Verify CoreDNS is forwarding to Unbound
+# Verify CoreDNS is configured with DNS-over-TLS
-kubectl get configmap coredns -n kube-system -o yaml | grep forward
+kubectl get configmap coredns -n kube-system -o yaml | grep 'tls://'
-# Should show: forward . <unbound-ip>
+# Should show: tls://1.1.1.1 tls://1.0.0.1
 
-# If not, re-run Step 3 above
+# If not, re-run Step 2 above
 ```
 
 **Issue: Front pod stuck in ContainerCreating**
@@ -1129,7 +1139,7 @@ kubectl get configmap coredns -n kube-system -o yaml | grep forward
 # Check for missing certificate secret
 kubectl describe pod -n bakery-ia -l app.kubernetes.io/component=front | grep -A5 Events
 
-# If missing mailu-certificates, re-run Step 4 above
+# If missing mailu-certificates, re-run Step 3 above
 ```
 
 **Issue: Admin pod can't connect to Redis**
@@ -2018,41 +2028,22 @@ Mailu is a full-featured, self-hosted email server with built-in antispam, webma
 ### Prerequisites
 
 Before deploying Mailu:
-- [ ] Unbound DNS resolver deployed (for DNSSEC validation)
+- [ ] CoreDNS configured with DNS-over-TLS for DNSSEC validation
 - [ ] DNS records configured for mail domain
 - [ ] TLS certificates available
 - [ ] Mailgun account created and domain verified (for outbound email relay)
 
-### Step 1: Deploy Unbound DNS Resolver
+### Step 1: Configure CoreDNS for DNSSEC (DNS-over-TLS)
 
 Mailu requires DNSSEC validation for email authentication (DKIM/SPF/DMARC).
+CoreDNS is configured to use DNS-over-TLS with Cloudflare for DNSSEC validation.
 
 ```bash
-# Deploy Unbound via Helm
+# Check if CoreDNS is already configured with DNS-over-TLS
-helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
+kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'tls://1.1.1.1' || echo "Not configured"
-  -n bakery-ia \
-  --create-namespace \
-  -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-  -f infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml \
-  --timeout 5m \
-  --wait
 
-# Verify Unbound is running
+# If not configured, update CoreDNS ConfigMap
-kubectl get pods -n bakery-ia | grep unbound
+cat > /tmp/coredns-config.yaml << 'EOF'
-
-# Get Unbound service IP
-UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
-echo "Unbound DNS IP: $UNBOUND_IP"
-```
-
-### Step 2: Configure CoreDNS for DNSSEC
-
-```bash
-# Get Unbound IP
-UNBOUND_IP=$(kubectl get svc unbound-dns -n bakery-ia -o jsonpath='{.spec.clusterIP}')
-
-# Create updated CoreDNS ConfigMap
-cat > /tmp/coredns-config.yaml <<EOF
 apiVersion: v1
 kind: ConfigMap
 metadata:
@@ -2072,8 +2063,9 @@ data:
            ttl 30
         }
         prometheus :9153
-        forward . $UNBOUND_IP {
+        forward . tls://1.1.1.1 tls://1.0.0.1 {
-           max_concurrent 1000
+           tls_servername cloudflare-dns.com
+           health_check 5s
         }
         cache 30 {
            disable success cluster.local
@@ -2092,10 +2084,12 @@ kubectl apply -f /tmp/coredns-config.yaml
 kubectl rollout restart deployment coredns -n kube-system
 kubectl rollout status deployment coredns -n kube-system --timeout=60s
 
-# Verify DNSSEC is working
+# Get CoreDNS service IP
-kubectl run -it --rm dns-test --image=alpine --restart=Never -- \
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
-  sh -c "apk add drill && drill -D google.com"
+echo "CoreDNS IP: $COREDNS_IP"
-# Look for "ad" flag (authenticated data) in output
+
+# Verify DNS resolution is working
+kubectl run -it --rm dns-test --image=busybox --restart=Never -- nslookup google.com
 ```
 
 ### Step 3: Configure Mailgun (External SMTP Relay)
@@ -2216,15 +2210,20 @@ kubectl apply -f infrastructure/platform/mail/mailu-helm/configs/mailu-admin-cre
 helm repo add mailu https://mailu.github.io/helm-charts
 helm repo update mailu
 
+# Get CoreDNS service IP for Mailu DNS configuration
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+
 # Deploy Mailu with production values
 # Note:
 #   - externalRelay uses Mailgun via the secret created in Step 3
 #   - initialAccount creates admin user automatically using the secret from Step 6
+#   - CoreDNS provides DNSSEC validation via DNS-over-TLS (Cloudflare)
 helm upgrade --install mailu mailu/mailu \
   -n bakery-ia \
   --create-namespace \
   -f infrastructure/platform/mail/mailu-helm/values.yaml \
   -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+  --set global.custom_dns_servers="$COREDNS_IP" \
   --timeout 10m
 
 # Wait for pods to be ready (ClamAV may take 5-10 minutes)
@@ -2306,11 +2305,11 @@ kubectl port-forward -n bakery-ia svc/mailu-front 8080:80
 #### Admin Pod CrashLoopBackOff with DNSSEC Error
 
 ```bash
-# Verify CoreDNS is forwarding to Unbound
+# Verify CoreDNS is configured with DNS-over-TLS
-kubectl get configmap coredns -n kube-system -o yaml | grep forward
+kubectl get configmap coredns -n kube-system -o yaml | grep 'tls://'
-# Should show: forward . <unbound-ip>
+# Should show: tls://1.1.1.1 tls://1.0.0.1
 
-# If not configured, re-run Step 2
+# If not configured, re-run Step 1
 ```
 
 #### Front Pod Stuck in ContainerCreating
@@ -3419,8 +3418,7 @@ kubectl scale deployment monitoring -n bakery-ia --replicas=0
 - [ ] End-to-end pipeline test successful
 
 ### Email Infrastructure (Optional - Mailu)
-- [ ] Unbound DNS resolver deployed
+- [ ] CoreDNS configured with DNS-over-TLS for DNSSEC
-- [ ] CoreDNS configured for DNSSEC
 - [ ] Mailu TLS certificate created
 - [ ] Mailu deployed via Helm
 - [ ] Admin user created
@@ -3473,8 +3471,7 @@ kubectl scale deployment monitoring -n bakery-ia --replicas=0
   - Webhook integration and end-to-end testing
   - Troubleshooting guide for CI/CD issues
 - **NEW: Mailu Email Server Deployment** - Comprehensive self-hosted email setup
-  - Unbound DNS resolver deployment for DNSSEC
+  - CoreDNS configuration with DNS-over-TLS for DNSSEC validation
-  - CoreDNS configuration for mail authentication
   - Mailu Helm deployment with all components
   - DKIM/SPF/DMARC configuration
   - Troubleshooting common Mailu issues

frontend/Dockerfile.kubernetes

@@ -1,85 +1,21 @@
-# Kubernetes-optimized Dockerfile for Frontend
+# Frontend Dockerfile for Kubernetes
-# Multi-stage build for production deployment
+# Simple two-stage build: node for build, nginx for serve
 
-# Stage 1: Build the application
+# Stage 1: Build
 FROM node:18-alpine AS builder
-
 WORKDIR /app
-
-# Copy package files
 COPY package*.json ./
-
+RUN npm ci
-# Install all dependencies for building
-RUN npm ci --verbose && \
-    npm cache clean --force
-
-# Copy source code (excluding unnecessary files like node_modules, dist, etc.)
 COPY . .
-
-# Create a default runtime config in the public directory if it doesn't exist to satisfy the reference in index.html
-RUN if [ ! -f public/runtime-config.js ]; then \
-        mkdir -p public && \
-        echo "window.__RUNTIME_CONFIG__ = {};" > public/runtime-config.js; \
-    fi
-
-# Set build-time environment variables to prevent hanging on undefined variables
 ENV NODE_ENV=production
-ENV CI=true
 ENV VITE_API_URL=/api
 ENV VITE_APP_TITLE="BakeWise"
 ENV VITE_APP_VERSION="1.0.0"
-ENV VITE_PILOT_MODE_ENABLED="false"
-ENV VITE_PILOT_COUPON_CODE="PILOT2025"
-ENV VITE_PILOT_TRIAL_MONTHS="3"
-ENV VITE_STRIPE_PUBLISHABLE_KEY="pk_test_"
-# Set Node.js memory limit for the build process
-ENV NODE_OPTIONS="--max-old-space-size=4096"
 RUN npm run build
 
-# Stage 2: Production server with Nginx
+# Stage 2: Serve with nginx
-FROM nginx:1.25-alpine AS production
+FROM nginx:1.25-alpine
-
-# Install curl for health checks
-RUN apk add --no-cache curl
-
-# Copy main nginx configuration that sets the PID file location
-COPY nginx-main.conf /etc/nginx/nginx.conf
-
-# Remove default nginx configuration
 RUN rm /etc/nginx/conf.d/default.conf
-
-# Copy custom nginx configuration
 COPY nginx.conf /etc/nginx/conf.d/
-
-# Copy built application from builder stage
 COPY --from=builder /app/dist /usr/share/nginx/html
-
-# Copy and setup environment substitution script
-COPY substitute-env.sh /docker-entrypoint.d/30-substitute-env.sh
-
-# Make the script executable
-RUN chmod +x /docker-entrypoint.d/30-substitute-env.sh
-
-# Set proper permissions
-RUN chown -R nginx:nginx /usr/share/nginx/html && \
-    chown -R nginx:nginx /var/cache/nginx && \
-    chown -R nginx:nginx /var/log/nginx && \
-    chown -R nginx:nginx /etc/nginx/conf.d
-
-# Create nginx PID directory and fix permissions
-RUN mkdir -p /var/run/nginx /var/lib/nginx/tmp && \
-    chown -R nginx:nginx /var/run/nginx /var/lib/nginx /etc/nginx
-
-# Switch to non-root user
-USER nginx
-
-# Expose port 3000 (to match current setup)
 EXPOSE 3000
-
-# Health check
-HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
-  CMD curl -f http://localhost:3000/health || exit 1
-
-# Start nginx
-CMD ["nginx", "-g", "daemon off;"]
-

frontend/index.html

@@ -18,9 +18,6 @@
     <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
     <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&family=Poppins:wght@600;700&display=swap" rel="stylesheet" />
 
-    <!-- Runtime configuration - MUST load before app code (Kubernetes deployment) -->
-    <script src="/runtime-config.js"></script>
-
     <title>BakeWise - Gestión Inteligente para Panaderías</title>
   </head>
   <body>

frontend/nginx-main.conf

@@ -1,12 +0,0 @@
-pid /var/run/nginx/nginx.pid;
-worker_processes auto;
-
-events {
-    worker_connections 1024;
-}
-
-http {
-    include /etc/nginx/mime.types;
-    default_type application/octet-stream;
-    include /etc/nginx/conf.d/*.conf;
-}

frontend/nginx.conf

@@ -12,7 +12,7 @@ server {
     add_header X-Content-Type-Options "nosniff" always;
     add_header X-XSS-Protection "1; mode=block" always;
     add_header Referrer-Policy "strict-origin-when-cross-origin" always;
-    add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://fonts.googleapis.com https://js.stripe.com; script-src-elem 'self' 'unsafe-inline' https://js.stripe.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' https://fonts.gstatic.com; img-src 'self' data: https:; connect-src 'self' http://localhost http://localhost:8000 http://localhost:8001 http://localhost:8006 ws: wss:; frame-src https://js.stripe.com;" always;
+    add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://fonts.googleapis.com https://js.stripe.com; script-src-elem 'self' 'unsafe-inline' https://js.stripe.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' https://fonts.gstatic.com; img-src 'self' data: https:; connect-src 'self' http://localhost:* https://localhost:* https://bakery-ia.local https://bakewise.ai wss://bakery-ia.local wss://bakewise.ai ws: wss:; frame-src https://js.stripe.com;" always;
 
     # Gzip compression
     gzip on;

frontend/src/config/pilot.ts

@@ -1,92 +1,16 @@
 /**
  * Pilot Program Configuration
- *
+ * Uses build-time environment variables
- * Centralized configuration for pilot mode features.
- *
- * Works in two modes:
- * 1. Kubernetes/Docker: Reads from window.__RUNTIME_CONFIG__ (injected at container startup)
- * 2. Local Development: Reads from import.meta.env (build-time variables from .env)
  */
 
-/**
+export const PILOT_CONFIG = {
- * Helper function to get environment variable value
+  enabled: import.meta.env.VITE_PILOT_MODE_ENABLED === 'true',
- * Tries runtime config first (Kubernetes), falls back to build-time (local dev)
+  couponCode: import.meta.env.VITE_PILOT_COUPON_CODE || 'PILOT2025',
- */
+  trialMonths: parseInt(import.meta.env.VITE_PILOT_TRIAL_MONTHS || '3'),
-const getEnvVar = (key: string): string | undefined => {
+  get trialDays(): number {
-  // Try runtime config first (Kubernetes/Docker environment)
+    return this.trialMonths * 30;
-  if (typeof window !== 'undefined' && (window as any).__RUNTIME_CONFIG__) {
+  },
-    const value = (window as any).__RUNTIME_CONFIG__[key];
+  lifetimeDiscount: 20,
-    if (value !== undefined) {
-      return value;
-    }
-  }
-
-  // Fallback to build-time environment variables (local development)
-  return import.meta.env[key];
 };
 
-/**
- * Create pilot config with getter functions to ensure we always read fresh values
- * This is important because runtime-config.js might load after this module
- */
-const createPilotConfig = () => {
-  return {
-    /**
-     * Master switch for pilot mode
-     * When false, all pilot features are disabled globally
-     */
-    get enabled(): boolean {
-      const value = getEnvVar('VITE_PILOT_MODE_ENABLED');
-      return value === 'true';
-    },
-
-    /**
-     * Coupon code for pilot participants
-     */
-    get couponCode(): string {
-      return getEnvVar('VITE_PILOT_COUPON_CODE') || 'PILOT2025';
-    },
-
-    /**
-     * Trial period in months for pilot participants
-     */
-    get trialMonths(): number {
-      return parseInt(getEnvVar('VITE_PILOT_TRIAL_MONTHS') || '3');
-    },
-
-    /**
-     * Trial period in days (calculated from months)
-     */
-    get trialDays(): number {
-      return this.trialMonths * 30;
-    },
-
-    /**
-     * Lifetime discount percentage for pilot participants
-     */
-    lifetimeDiscount: 20,
-  };
-};
-
-export const PILOT_CONFIG = createPilotConfig();
-
-// Debug logging
-console.log('🔧 Pilot Config Loading:', {
-  source: typeof window !== 'undefined' && (window as any).__RUNTIME_CONFIG__ ? 'runtime' : 'build-time',
-  raw: getEnvVar('VITE_PILOT_MODE_ENABLED'),
-  type: typeof getEnvVar('VITE_PILOT_MODE_ENABLED'),
-  enabled: PILOT_CONFIG.enabled,
-  runtimeConfigExists: typeof window !== 'undefined' && !!(window as any).__RUNTIME_CONFIG__,
-  runtimeConfigKeys: typeof window !== 'undefined' && (window as any).__RUNTIME_CONFIG__
-    ? Object.keys((window as any).__RUNTIME_CONFIG__)
-    : []
-});
-
-console.log('✅ Pilot Config:', {
-  enabled: PILOT_CONFIG.enabled,
-  couponCode: PILOT_CONFIG.couponCode,
-  trialMonths: PILOT_CONFIG.trialMonths,
-  trialDays: PILOT_CONFIG.trialDays
-});
-
 export default PILOT_CONFIG;

frontend/src/config/runtime.ts

@@ -1,83 +1,33 @@
-// Runtime configuration for Kubernetes deployments
+// Configuration - uses build-time environment variables
-// This allows environment variables to be injected at container startup
+export const config = {
+  VITE_API_URL: import.meta.env.VITE_API_URL || '/api',
+  VITE_APP_TITLE: import.meta.env.VITE_APP_TITLE || 'BakeWise',
+  VITE_APP_VERSION: import.meta.env.VITE_APP_VERSION || '1.0.0',
+  VITE_OTEL_ENABLED: import.meta.env.VITE_OTEL_ENABLED || 'true',
+  VITE_OTEL_TRACES_ENDPOINT: import.meta.env.VITE_OTEL_TRACES_ENDPOINT || '/api/v1/telemetry/v1/traces',
+  VITE_OTEL_METRICS_ENDPOINT: import.meta.env.VITE_OTEL_METRICS_ENDPOINT || '/api/v1/telemetry/v1/metrics',
+};
 
-interface RuntimeConfig {
-  VITE_API_URL: string;
-  VITE_APP_TITLE: string;
-  VITE_APP_VERSION: string;
-  VITE_OTEL_TRACES_ENDPOINT?: string;
-  VITE_OTEL_METRICS_ENDPOINT?: string;
-  VITE_OTEL_ENABLED?: string;
-}
-
-declare global {
-  interface Window {
-    __RUNTIME_CONFIG__?: RuntimeConfig;
-  }
-}
-
-// Types are defined in vite-env.d.ts
-
-// Get configuration from runtime or fall back to build-time environment variables
-function getRuntimeConfig(): RuntimeConfig {
-  // First try to get from window (injected at runtime in Kubernetes)
-  if (typeof window !== 'undefined' && window.__RUNTIME_CONFIG__) {
-    return window.__RUNTIME_CONFIG__;
-  }
-
-  // Fall back to build-time environment variables (development/local)
-  return {
-    VITE_API_URL: import.meta.env.VITE_API_URL || 'http://localhost:8000',
-    VITE_APP_TITLE: import.meta.env.VITE_APP_TITLE || 'PanIA Dashboard',
-    VITE_APP_VERSION: import.meta.env.VITE_APP_VERSION || '1.0.0',
-    VITE_OTEL_TRACES_ENDPOINT: import.meta.env.VITE_OTEL_TRACES_ENDPOINT || '/api/v1/telemetry/v1/traces',
-    VITE_OTEL_METRICS_ENDPOINT: import.meta.env.VITE_OTEL_METRICS_ENDPOINT || '/api/v1/telemetry/v1/metrics',
-    VITE_OTEL_ENABLED: import.meta.env.VITE_OTEL_ENABLED || 'true',
-  };
-}
-
-export const config = getRuntimeConfig();
-
-// Helper function to get the API base URL
 export function getApiUrl(): string {
   return config.VITE_API_URL;
 }
 
-// Helper function to get app title
 export function getAppTitle(): string {
   return config.VITE_APP_TITLE;
 }
 
-// Helper function to get app version
 export function getAppVersion(): string {
   return config.VITE_APP_VERSION;
 }
 
-// Helper to check if running in Kubernetes
-export function isKubernetesEnvironment(): boolean {
-  return typeof window !== 'undefined' && !!window.__RUNTIME_CONFIG__;
-}
-
-// Helper to check if OpenTelemetry is enabled
 export function isOpenTelemetryEnabled(): boolean {
   return config.VITE_OTEL_ENABLED?.toLowerCase() !== 'false';
 }
 
-// Helper to get OpenTelemetry traces endpoint
 export function getOtelTracesEndpoint(): string {
-  return config.VITE_OTEL_TRACES_ENDPOINT || '/api/v1/telemetry/v1/traces';
+  return config.VITE_OTEL_TRACES_ENDPOINT;
 }
 
-// Helper to get OpenTelemetry metrics endpoint
 export function getOtelMetricsEndpoint(): string {
-  return config.VITE_OTEL_METRICS_ENDPOINT || '/api/v1/telemetry/v1/metrics';
+  return config.VITE_OTEL_METRICS_ENDPOINT;
 }
-
-// Debug function to log current configuration
-export function logConfig(): void {
-  console.log('Current configuration:', {
-    ...config,
-    isKubernetes: isKubernetesEnvironment(),
-    source: isKubernetesEnvironment() ? 'runtime' : 'build-time'
-  });
-}

frontend/src/vite-env.d.ts

@@ -2,30 +2,16 @@
 
 interface ImportMetaEnv {
   readonly VITE_API_URL: string
-  readonly VITE_API_BASE_URL: string
   readonly VITE_APP_TITLE: string
   readonly VITE_APP_VERSION: string
-  readonly VITE_ENVIRONMENT: string
+  readonly VITE_OTEL_ENABLED?: string
+  readonly VITE_OTEL_TRACES_ENDPOINT?: string
+  readonly VITE_OTEL_METRICS_ENDPOINT?: string
   readonly VITE_PILOT_MODE_ENABLED?: string
   readonly VITE_PILOT_COUPON_CODE?: string
   readonly VITE_PILOT_TRIAL_MONTHS?: string
-  readonly VITE_STRIPE_PUBLISHABLE_KEY?: string
-  // more env variables...
 }
 
 interface ImportMeta {
   readonly env: ImportMetaEnv
 }
-
-// Runtime configuration injected by Kubernetes at container startup
-interface Window {
-  __RUNTIME_CONFIG__?: {
-    VITE_API_URL?: string;
-    VITE_APP_TITLE?: string;
-    VITE_APP_VERSION?: string;
-    VITE_PILOT_MODE_ENABLED?: string;
-    VITE_PILOT_COUPON_CODE?: string;
-    VITE_PILOT_TRIAL_MONTHS?: string;
-    VITE_STRIPE_PUBLISHABLE_KEY?: string;
-  };
-}

frontend/substitute-env.sh

@@ -1,40 +0,0 @@
-#!/bin/sh
-set -e
-
-# Handle VITE_API_URL specially to preserve empty values
-# If VITE_API_URL is unset, use default; if empty, preserve empty; otherwise use value
-if [ -z "${VITE_API_URL+x}" ]; then
-  export VITE_API_URL="/api"
-elif [ -z "$VITE_API_URL" ]; then
-  # If VITE_API_URL is explicitly set to empty string, use relative API path
-  export VITE_API_URL="/api"
-fi
-
-# Default values for environment variables
-export VITE_APP_TITLE=${VITE_APP_TITLE:-"BakeWise"}
-export VITE_APP_VERSION=${VITE_APP_VERSION:-"1.0.0"}
-
-# Default values for pilot program configuration
-export VITE_PILOT_MODE_ENABLED=${VITE_PILOT_MODE_ENABLED:-"false"}
-export VITE_PILOT_COUPON_CODE=${VITE_PILOT_COUPON_CODE:-"PILOT2025"}
-export VITE_PILOT_TRIAL_MONTHS=${VITE_PILOT_TRIAL_MONTHS:-"3"}
-export VITE_STRIPE_PUBLISHABLE_KEY=${VITE_STRIPE_PUBLISHABLE_KEY:-"pk_test_"}
-
-# Create a runtime configuration file that can be loaded by the frontend
-cat > /usr/share/nginx/html/runtime-config.js << EOL
-window.__RUNTIME_CONFIG__ = {
-  VITE_API_URL: '${VITE_API_URL}',
-  VITE_APP_TITLE: '${VITE_APP_TITLE}',
-  VITE_APP_VERSION: '${VITE_APP_VERSION}',
-  VITE_PILOT_MODE_ENABLED: '${VITE_PILOT_MODE_ENABLED}',
-  VITE_PILOT_COUPON_CODE: '${VITE_PILOT_COUPON_CODE}',
-  VITE_PILOT_TRIAL_MONTHS: '${VITE_PILOT_TRIAL_MONTHS}',
-  VITE_STRIPE_PUBLISHABLE_KEY: '${VITE_STRIPE_PUBLISHABLE_KEY}'
-};
-EOL
-
-echo "Runtime configuration created:"
-echo "  API URL: ${VITE_API_URL}"
-echo "  Pilot Mode: ${VITE_PILOT_MODE_ENABLED}"
-echo "  Pilot Coupon: ${VITE_PILOT_COUPON_CODE}"
-echo "  Trial Months: ${VITE_PILOT_TRIAL_MONTHS}"

infrastructure/cicd/gitea/values-prod.yaml

@@ -44,6 +44,33 @@ gitea:
       SSH_DOMAIN: gitea.bakewise.ai
       ROOT_URL: https://gitea.bakewise.ai
 
+    # =============================================================================
+    # PACKAGE/REGISTRY RETENTION POLICY
+    # =============================================================================
+    # Automatic cleanup of old container images and packages
+    # This prevents the registry from growing indefinitely
+    packages:
+      ENABLED: true
+      # Limit container image versions to prevent storage bloat
+      # 0 = unlimited (default), set a reasonable limit for CI/CD
+      LIMIT_TOTAL_OWNER_SIZE: 10737418240  # 10GB per owner/organization
+      LIMIT_SIZE_CONTAINER: 2147483648      # 2GB per container image
+
+    # Cron job for automatic package cleanup
+    cron:
+      ENABLED: true
+    "cron.cleanup_packages":
+      ENABLED: true
+      # Run daily at 3 AM
+      SCHEDULE: "0 3 * * *"
+      # Keep packages newer than this (in hours) - 168h = 7 days
+      OLDER_THAN: 168h
+      # Number of versions to keep per package (0 = disabled)
+      # This keeps the last 5 versions regardless of age
+      NUMBER_TO_KEEP: 5
+      # Also clean up unreferenced blobs
+      REMOVE_UNUSED_ARTIFACTS: true
+
 # Production resources - adjust based on expected load
 resources:
   limits:

infrastructure/cicd/gitea/values.yaml

@@ -93,6 +93,8 @@ gitea:
       DEFAULT_BRANCH: main
     packages:
       ENABLED: true
+      # Retention policy is configured in values-prod.yaml for production
+      # See: LIMIT_TOTAL_OWNER_SIZE, LIMIT_SIZE_CONTAINER, cron.cleanup_packages
     webhook:
       ALLOWED_HOST_LIST: "*"
       # Allow internal cluster URLs for Tekton EventListener

infrastructure/cicd/tekton-helm/templates/event-listener.yaml

@@ -16,16 +16,10 @@ spec:
       interceptors:
         - ref:
             name: "cel"
+            kind: ClusterInterceptor
           params:
             - name: "filter"
               value: "has(body.repository) && body.ref.contains('main')"
-        - ref:
-            name: "bitbucket"
-          params:
-            - name: "secretRef"
-              value:
-                secretName: gitea-webhook-secret
-                secretKey: secretToken
       bindings:
         - ref: bakery-ia-trigger-binding
       template:

infrastructure/cicd/tekton-helm/templates/namespace.yaml

@@ -6,4 +6,7 @@ metadata:
   labels:
     app.kubernetes.io/name: {{ .Values.labels.app.name }}
     app.kubernetes.io/component: {{ .Values.labels.app.component }}
-{{- end }}
+    pod-security.kubernetes.io/enforce: baseline
+    pod-security.kubernetes.io/warn: baseline
+    pod-security.kubernetes.io/audit: baseline
+{{- end }}

infrastructure/cicd/tekton-helm/templates/pipeline-ci.yaml

@@ -19,7 +19,6 @@ spec:
       description: Docker registry credentials
     - name: git-credentials
       description: Git credentials for pushing GitOps updates
-      optional: true
   params:
     - name: git-url
       type: string
@@ -98,7 +97,7 @@ spec:
 
     # Stage 4: Build and push container images
     - name: build-and-push
-      runAfter: [run-tests]
+      runAfter: [detect-changes]
       taskRef:
         name: kaniko-build
       when:

infrastructure/cicd/tekton-helm/templates/task-detect-changes.yaml

@@ -18,70 +18,105 @@ spec:
       description: Comma-separated list of changed services
   steps:
     - name: detect-changes
-      image: alpine/git
+      image: alpine/git:2.43.0
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
+      env:
+        - name: HOME
+          value: /tekton/home
       script: |
-        #!/bin/bash
+        #!/bin/sh
         set -e
 
+        # Mark workspace as safe directory to avoid ownership issues
+        git config --global --add safe.directory "$(workspaces.source.path)"
+
         cd $(workspaces.source.path)
 
-        # Get the list of changed files
+        echo "Git log (last 3 commits):"
-        CHANGED_FILES=$(git diff --name-only HEAD~1 HEAD 2>/dev/null || git diff --name-only $(git rev-parse --abbrev-ref HEAD)@{upstream} HEAD 2>/dev/null || echo "")
+        git log --oneline -3 || echo "Cannot get git log"
 
-        if [ -z "$CHANGED_FILES" ]; then
+        # Check if we have enough history for comparison
-          # No changes detected, assume all services need building
+        COMMIT_COUNT=$(git rev-list --count HEAD 2>/dev/null || echo "0")
-          echo "No git changes detected, building all services"
+        echo "Commit count in history: $COMMIT_COUNT"
-          echo "all" > $(results.changed-services.path)
+
+        if [ "$COMMIT_COUNT" -lt 2 ]; then
+          echo "Not enough git history for change detection (need at least 2 commits)"
+          echo "Building all services as fallback"
+          echo -n "all" > $(results.changed-services.path)
           exit 0
         fi
 
-        # Initialize an array to collect changed services
+        # Get the list of changed files
-        declare -a changed_services=()
+        CHANGED_FILES=$(git diff --name-only HEAD~1 HEAD 2>/dev/null || echo "")
+
+        if [ -z "$CHANGED_FILES" ]; then
+          # Empty commit or something unusual - skip build
+          echo "No file changes detected in last commit"
+          echo -n "infrastructure" > $(results.changed-services.path)
+          exit 0
+        fi
+
+        echo "Changed files:"
+        echo "$CHANGED_FILES"
+
+        # Initialize empty string to collect changed services
+        CHANGED_SERVICES=""
+
+        # Helper function to add service if not already present
+        add_service() {
+          svc="$1"
+          case ",$CHANGED_SERVICES," in
+            *",$svc,"*) ;;  # Already present
+            *)
+              if [ -z "$CHANGED_SERVICES" ]; then
+                CHANGED_SERVICES="$svc"
+              else
+                CHANGED_SERVICES="$CHANGED_SERVICES,$svc"
+              fi
+              ;;
+          esac
+        }
 
         # Check for changes in services/ directory
-        while IFS= read -r service_dir; do
+        for svc in $(echo "$CHANGED_FILES" | grep '^services/' | cut -d'/' -f2 | sort -u); do
-          if [ -n "$service_dir" ]; then
+          if [ -n "$svc" ]; then
-            service_name=$(basename "$service_dir")
+            add_service "$svc"
-            if [[ ! " ${changed_services[@]} " =~ " ${service_name} " ]]; then
-              changed_services+=("$service_name")
-            fi
           fi
-        done < <(echo "$CHANGED_FILES" | grep '^services/' | cut -d'/' -f2 | sort -u)
+        done
 
         # Check for changes in gateway/ directory
         if echo "$CHANGED_FILES" | grep -q '^gateway/'; then
-          if [[ ! " ${changed_services[@]} " =~ " gateway " ]]; then
+          add_service "gateway"
-            changed_services+=("gateway")
-          fi
         fi
 
         # Check for changes in frontend/ directory
         if echo "$CHANGED_FILES" | grep -q '^frontend/'; then
-          if [[ ! " ${changed_services[@]} " =~ " frontend " ]]; then
+          add_service "frontend"
-            changed_services+=("frontend")
-          fi
         fi
 
-        # Check for changes in shared/ directory (might affect multiple services)
+        # Check for changes in shared/ directory
+        # shared/ contains code used by services and gateway (NOT frontend), so rebuild them
         if echo "$CHANGED_FILES" | grep -q '^shared/'; then
-          if [[ ! " ${changed_services[@]} " =~ " shared " ]]; then
+          echo "Detected changes in shared/ - triggering rebuild of all services and gateway"
-            changed_services+=("shared")
+          echo -n "services-and-gateway" > $(results.changed-services.path)
-          fi
+          exit 0
         fi
 
-        # Convert array to comma-separated string
+        # IMPORTANT: Use echo -n (no newline) to avoid trailing newline in results
-        CHANGED_SERVICES=""
+        # Trailing newlines cause Tekton when expressions to fail matching
-        for service in "${changed_services[@]}"; do
-          if [ -z "$CHANGED_SERVICES" ]; then
-            CHANGED_SERVICES="$service"
-          else
-            CHANGED_SERVICES="$CHANGED_SERVICES,$service"
-          fi
-        done
-
         if [ -z "$CHANGED_SERVICES" ]; then
           # Changes are in infrastructure or other non-service files
-          echo "infrastructure" > $(results.changed-services.path)
+          echo "Detected: infrastructure changes only"
+          echo -n "infrastructure" > $(results.changed-services.path)
         else
-          echo "$CHANGED_SERVICES" > $(results.changed-services.path)
+          echo "Detected changed services: $CHANGED_SERVICES"
+          echo -n "$CHANGED_SERVICES" > $(results.changed-services.path)
         fi

infrastructure/cicd/tekton-helm/templates/task-git-clone.yaml

@@ -23,8 +23,8 @@ spec:
       default: "main"
     - name: depth
       type: string
-      description: Git clone depth (0 for full history)
+      description: Git clone depth (0 for full history, minimum 2 for change detection)
-      default: "1"
+      default: "10"
   results:
     - name: commit-sha
       description: The commit SHA that was checked out
@@ -33,6 +33,18 @@ spec:
   steps:
     - name: clone
       image: alpine/git:2.43.0
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
+      env:
+        - name: HOME
+          value: /tekton/home
       script: |
         #!/bin/sh
         set -e
@@ -50,7 +62,11 @@ spec:
         echo "Depth: $DEPTH"
         echo "============================================"
 
+        # Mark workspace as safe directory to avoid ownership issues
+        git config --global --add safe.directory "$OUTPUT_PATH"
+
         # Clone with depth for faster checkout
+        # Note: We need at least 2 commits for change detection (current + parent)
         if [ "$DEPTH" = "0" ]; then
           echo "Cloning full repository..."
           git clone "$URL" "$OUTPUT_PATH"
@@ -61,15 +77,42 @@ spec:
 
         cd "$OUTPUT_PATH"
 
-        # Fetch the specific revision if needed
+        # If revision is a specific commit SHA (40 hex chars), we need special handling
-        if [ "$REVISION" != "main" ] && [ "$REVISION" != "master" ]; then
+        if echo "$REVISION" | grep -qE '^[0-9a-f]{40}$'; then
-          echo "Fetching revision: $REVISION"
+          echo "Revision is a commit SHA: $REVISION"
-          git fetch --depth 1 origin "$REVISION" 2>/dev/null || true
+
+          # Check if commit is already in the clone
+          if ! git cat-file -e "$REVISION" 2>/dev/null; then
+            echo "Commit not in shallow clone, fetching with history..."
+            # Fetch more history to include the specific commit
+            git fetch --deepen="$DEPTH" origin main 2>/dev/null || true
+            git fetch origin "$REVISION" 2>/dev/null || true
+          fi
+
+          # Ensure we have the parent commit for change detection
+          PARENT_SHA=$(git rev-parse "$REVISION^" 2>/dev/null || echo "")
+          if [ -z "$PARENT_SHA" ]; then
+            echo "Parent commit not available, deepening history..."
+            git fetch --deepen=10 origin 2>/dev/null || true
+          fi
+        elif [ "$REVISION" != "main" ] && [ "$REVISION" != "master" ]; then
+          echo "Fetching branch/tag: $REVISION"
+          git fetch --depth "$DEPTH" origin "$REVISION" 2>/dev/null || true
         fi
 
         # Checkout the revision
         echo "Checking out: $REVISION"
-        git checkout "$REVISION" 2>/dev/null || git checkout "origin/$REVISION"
+        git checkout "$REVISION" 2>/dev/null || git checkout "origin/$REVISION" 2>/dev/null || git checkout FETCH_HEAD
+
+        # Verify we have enough history for change detection
+        COMMIT_COUNT=$(git rev-list --count HEAD 2>/dev/null || echo "0")
+        echo "Commits available after checkout: $COMMIT_COUNT"
+        if [ "$COMMIT_COUNT" -lt 2 ]; then
+          echo "Warning: Not enough history, fetching more..."
+          git fetch --deepen=10 origin 2>/dev/null || true
+          COMMIT_COUNT=$(git rev-list --count HEAD 2>/dev/null || echo "0")
+          echo "Commits available after deepen: $COMMIT_COUNT"
+        fi
 
         # Get commit info
         COMMIT_SHA=$(git rev-parse HEAD)

infrastructure/cicd/tekton-helm/templates/task-kaniko-build.yaml

@@ -39,14 +39,37 @@ spec:
       description: Status of the build operation
   steps:
     - name: build-and-push
-      image: gcr.io/kaniko-project/executor:v1.15.0
+      image: gcr.io/kaniko-project/executor:v1.15.0-debug
+      # Note: Kaniko requires root to unpack image layers and perform chown operations
+      # This is a known requirement for container image building
+      securityContext:
+        runAsNonRoot: false
+        runAsUser: 0
+        allowPrivilegeEscalation: false
+        seccompProfile:
+          type: RuntimeDefault
       env:
         - name: DOCKER_CONFIG
           value: /tekton/home/.docker
       script: |
-        #!/bin/bash
+        #!/busybox/sh
         set -e
 
+        # Set up Docker credentials from workspace
+        DOCKER_CREDS_PATH="$(workspaces.docker-credentials.path)"
+        echo "Setting up Docker credentials from: $DOCKER_CREDS_PATH"
+        mkdir -p /tekton/home/.docker
+        if [ -f "$DOCKER_CREDS_PATH/config.json" ]; then
+          cp "$DOCKER_CREDS_PATH/config.json" /tekton/home/.docker/config.json
+          echo "Docker config.json copied successfully"
+        elif [ -f "$DOCKER_CREDS_PATH/.dockerconfigjson" ]; then
+          cp "$DOCKER_CREDS_PATH/.dockerconfigjson" /tekton/home/.docker/config.json
+          echo "Docker .dockerconfigjson copied successfully"
+        else
+          echo "Warning: No docker credentials found in workspace"
+          ls -la "$DOCKER_CREDS_PATH/" || echo "Cannot list docker-credentials workspace"
+        fi
+
         echo "==================================================================="
         echo "Kaniko Build Configuration"
         echo "==================================================================="
@@ -54,50 +77,202 @@ spec:
         echo "Base Registry:   $(params.base-registry)"
         echo "Python Image:    $(params.python-image)"
         echo "Git Revision:    $(params.git-revision)"
+        echo "Services param:  $(params.services)"
         echo "==================================================================="
 
-        # Split services parameter by comma
+        # Trim whitespace and newlines from services param
-        IFS=',' read -ra SERVICES <<< "$(params.services)"
+        SERVICES_PARAM=$(echo "$(params.services)" | tr -d '\n' | tr -d ' ')
+        WORKSPACE="$(workspaces.source.path)"
 
-        # Build each service
+        echo "Trimmed services param: '$SERVICES_PARAM'"
-        for service in "${SERVICES[@]}"; do
-          service=$(echo "$service" | xargs)  # Trim whitespace
-          if [ -n "$service" ] && [ "$service" != "none" ]; then
-            echo ""
-            echo "Building service: $service"
-            echo "-------------------------------------------------------------------"
 
-            # Determine Dockerfile path (services vs gateway vs frontend)
+        # Handle special cases for service discovery
-            if [ "$service" = "gateway" ]; then
+        # "all" = all services + gateway + frontend
-              DOCKERFILE_PATH="$(workspaces.source.path)/gateway/Dockerfile"
+        # "services-and-gateway" = all services + gateway (no frontend) - used when shared/ changes
-            elif [ "$service" = "frontend" ]; then
+        if [ "$SERVICES_PARAM" = "all" ] || [ "$SERVICES_PARAM" = "services-and-gateway" ]; then
-              DOCKERFILE_PATH="$(workspaces.source.path)/frontend/Dockerfile.kubernetes"
+          if [ "$SERVICES_PARAM" = "all" ]; then
+            echo "Building all services (including frontend) - discovering from workspace..."
+          else
+            echo "Building services and gateway (shared/ changed) - discovering from workspace..."
+          fi
+          echo "Workspace contents:"
+          ls -la "$WORKSPACE/"
+          echo "Services directory contents:"
+          ls -la "$WORKSPACE/services/" || echo "No services directory"
+
+          SERVICES=""
+          # Find all services with Dockerfiles using ls
+          if [ -d "$WORKSPACE/services" ]; then
+            for svc_name in $(ls "$WORKSPACE/services/"); do
+              if [ -f "$WORKSPACE/services/$svc_name/Dockerfile" ]; then
+                if [ -z "$SERVICES" ]; then
+                  SERVICES="$svc_name"
+                else
+                  SERVICES="$SERVICES,$svc_name"
+                fi
+              fi
+            done
+          fi
+          # Add gateway if it has Dockerfile
+          if [ -f "$WORKSPACE/gateway/Dockerfile" ]; then
+            if [ -z "$SERVICES" ]; then
+              SERVICES="gateway"
             else
-              DOCKERFILE_PATH="$(workspaces.source.path)/services/$service/Dockerfile"
+              SERVICES="$SERVICES,gateway"
+            fi
+          fi
+          # Add frontend ONLY for "all" (not for "services-and-gateway")
+          if [ "$SERVICES_PARAM" = "all" ] && [ -f "$WORKSPACE/frontend/Dockerfile.kubernetes" ]; then
+            if [ -z "$SERVICES" ]; then
+              SERVICES="frontend"
+            else
+              SERVICES="$SERVICES,frontend"
+            fi
+          fi
+          echo "Discovered services: $SERVICES"
+        else
+          SERVICES="$SERVICES_PARAM"
+        fi
+
+        # Build each service SEQUENTIALLY to avoid registry upload conflicts
+        # Track build results using files (variables don't persist across subshells)
+        # Note: Use /tekton/home instead of /tmp as Kaniko container doesn't have /tmp
+        BUILD_STATUS_FILE="/tekton/home/build_status"
+        echo "0" > "$BUILD_STATUS_FILE.success"
+        echo "0" > "$BUILD_STATUS_FILE.failed"
+        echo "" > "$BUILD_STATUS_FILE.failed_services"
+
+        # Convert comma-separated to newline-separated and iterate
+        # Using for loop instead of pipe to avoid subshell issues
+        SERVICES_LIST=$(echo "$SERVICES" | tr ',' ' ')
+
+        for service in $SERVICES_LIST; do
+          service=$(echo "$service" | tr -d ' ')  # Trim whitespace
+          if [ -n "$service" ] && [ "$service" != "none" ] && [ "$service" != "infrastructure" ] && [ "$service" != "shared" ]; then
+            echo ""
+            echo "==================================================================="
+            echo "Building service: $service"
+            echo "==================================================================="
+
+            # Determine Dockerfile path, context path, and image name
+            # Folder names are: auth, tenant, gateway, frontend, alert_processor, etc.
+            # Image names MUST match what's in the Kubernetes manifests exactly
+            # The manifests use the folder name directly (with underscores preserved)
+            #
+            # CONTEXT_PATH is important - some Dockerfiles expect the context to be their directory
+            # (e.g., frontend expects context=frontend/), while services expect context=workspace root
+            if [ "$service" = "gateway" ]; then
+              DOCKERFILE_PATH="$WORKSPACE/gateway/Dockerfile"
+              CONTEXT_PATH="$WORKSPACE"
+              IMAGE_NAME="gateway"
+            elif [ "$service" = "frontend" ]; then
+              # Frontend Dockerfile expects context to be the frontend/ directory
+              # because it does COPY package*.json ./ and COPY nginx.conf etc.
+              DOCKERFILE_PATH="$WORKSPACE/frontend/Dockerfile.kubernetes"
+              CONTEXT_PATH="$WORKSPACE/frontend"
+              IMAGE_NAME="frontend"
+            else
+              DOCKERFILE_PATH="$WORKSPACE/services/$service/Dockerfile"
+              CONTEXT_PATH="$WORKSPACE"
+              # Use folder name directly - matches manifest image references
+              # e.g., auth, tenant, ai_insights, alert_processor, demo_session, external
+              IMAGE_NAME="$service"
             fi
 
-            /kaniko/executor \
+            # Check if Dockerfile exists
-              --dockerfile="$DOCKERFILE_PATH" \
+            if [ ! -f "$DOCKERFILE_PATH" ]; then
-              --destination="$(params.registry)/$service:$(params.git-revision)" \
+              echo "Warning: Dockerfile not found at $DOCKERFILE_PATH, skipping..."
-              --context="$(workspaces.source.path)" \
+              continue
-              --build-arg="BASE_REGISTRY=$(params.base-registry)" \
+            fi
-              --build-arg="PYTHON_IMAGE=$(params.python-image)" \
-              --cache=true \
-              --cache-repo="$(params.registry)/cache"
 
-            echo "Successfully built: $(params.registry)/$service:$(params.git-revision)"
+            echo "Building $service -> Image: $IMAGE_NAME"
+
+            # Build with retry logic to handle transient registry errors
+            RETRY_COUNT=0
+            MAX_RETRIES=2
+            BUILD_SUCCESS=false
+
+            while [ "$RETRY_COUNT" -le "$MAX_RETRIES" ] && [ "$BUILD_SUCCESS" = "false" ]; do
+              if [ "$RETRY_COUNT" -gt 0 ]; then
+                echo "Retry $RETRY_COUNT/$MAX_RETRIES for $IMAGE_NAME..."
+                # Wait before retry to let registry recover
+                sleep 10
+              fi
+
+              echo "Context: $CONTEXT_PATH"
+              if /kaniko/executor \
+                --dockerfile="$DOCKERFILE_PATH" \
+                --destination="$(params.registry)/$IMAGE_NAME:$(params.git-revision)" \
+                --context="$CONTEXT_PATH" \
+                --build-arg="BASE_REGISTRY=$(params.base-registry)" \
+                --build-arg="PYTHON_IMAGE=$(params.python-image)" \
+                --cache=true \
+                --cache-repo="$(params.registry)/cache" \
+                --cache-ttl=168h \
+                --push-retry=3 \
+                --image-fs-extract-retry=3; then
+                BUILD_SUCCESS=true
+                echo "Successfully built and pushed: $(params.registry)/$IMAGE_NAME:$(params.git-revision)"
+                # Increment success count
+                COUNT=$(cat "$BUILD_STATUS_FILE.success")
+                echo $((COUNT + 1)) > "$BUILD_STATUS_FILE.success"
+              else
+                RETRY_COUNT=$((RETRY_COUNT + 1))
+                echo "Build/push failed for $IMAGE_NAME (attempt $RETRY_COUNT)"
+              fi
+            done
+
+            if [ "$BUILD_SUCCESS" = "false" ]; then
+              echo "ERROR: Failed to build $IMAGE_NAME after $MAX_RETRIES retries"
+              # Increment failed count and record service name
+              COUNT=$(cat "$BUILD_STATUS_FILE.failed")
+              echo $((COUNT + 1)) > "$BUILD_STATUS_FILE.failed"
+              echo "$service" >> "$BUILD_STATUS_FILE.failed_services"
+            fi
+
+            # Small delay between services to let registry settle
+            # This prevents "offset mismatch" errors from concurrent uploads
+            echo "Waiting 5s before next build to let registry settle..."
+            sleep 5
           fi
         done
 
+        # Read final counts
+        SUCCESS_COUNT=$(cat "$BUILD_STATUS_FILE.success")
+        FAILED_COUNT=$(cat "$BUILD_STATUS_FILE.failed")
+        FAILED_SERVICES=$(cat "$BUILD_STATUS_FILE.failed_services" | tr '\n' ',' | sed 's/,$//')
+
         echo ""
         echo "==================================================================="
-        echo "Build completed successfully!"
+        echo "Build Summary"
         echo "==================================================================="
-        echo "success" > $(results.build-status.path)
+        echo "Successful builds: $SUCCESS_COUNT"
+        echo "Failed builds: $FAILED_COUNT"
+        if [ -n "$FAILED_SERVICES" ]; then
+          echo "Failed services: $FAILED_SERVICES"
+        fi
+        echo "==================================================================="
+
+        # Set result based on outcome
+        # IMPORTANT: Use echo -n (no newline) to avoid trailing newline in results
+        # Trailing newlines cause Tekton when expressions to fail matching
+        if [ "$FAILED_COUNT" -gt 0 ]; then
+          if [ "$SUCCESS_COUNT" -gt 0 ]; then
+            echo -n "partial" > $(results.build-status.path)
+            echo "Build completed with some failures"
+          else
+            echo -n "failed" > $(results.build-status.path)
+            echo "All builds failed!"
+            exit 1
+          fi
+        else
+          echo -n "success" > $(results.build-status.path)
+          echo "All builds completed successfully!"
+        fi
       resources:
         limits:
           cpu: 2000m
-          memory: 4Gi
+          memory: 8Gi
         requests:
           cpu: 500m
-          memory: 1Gi
+          memory: 2Gi

infrastructure/cicd/tekton-helm/templates/task-pipeline-summary.yaml

@@ -19,9 +19,18 @@ spec:
       description: Git revision being processed
   steps:
     - name: generate-summary
-      image: alpine
+      image: alpine:3.19
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
       script: |
-        #!/bin/bash
+        #!/bin/sh
         set -e
         
         echo "=== Bakery-IA CI Pipeline Summary ==="

infrastructure/cicd/tekton-helm/templates/task-run-tests.yaml

@@ -23,12 +23,21 @@ spec:
       default: "false"
   steps:
     - name: run-unit-tests
-      image: registry.bakewise.ai/bakery-admin/python:3.11-slim
+      image: python:3.11-slim
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
       workingDir: $(workspaces.source.path)
       script: |
-        #!/bin/bash
+        #!/bin/sh
         set -e
-        
+
         echo "============================================"
         echo "Running Unit Tests"
         echo "Services: $(params.services)"
@@ -57,12 +66,21 @@ spec:
           cpu: 200m
           memory: 512Mi
     - name: run-integration-tests
-      image: registry.bakewise.ai/bakery-admin/python:3.11-slim
+      image: python:3.11-slim
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
       workingDir: $(workspaces.source.path)
       script: |
-        #!/bin/bash
+        #!/bin/sh
         set -e
-        
+
         echo "============================================"
         echo "Running Integration Tests"
         echo "Services: $(params.services)"

infrastructure/cicd/tekton-helm/templates/task-update-gitops.yaml

@@ -35,8 +35,19 @@ spec:
   steps:
     - name: update-manifests
       image: alpine/git:2.43.0
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+        seccompProfile:
+          type: RuntimeDefault
       workingDir: $(workspaces.source.path)
       env:
+        - name: HOME
+          value: /tekton/home
         - name: GIT_USERNAME
           valueFrom:
             secretKeyRef:
@@ -48,7 +59,7 @@ spec:
               name: gitea-git-credentials
               key: password
       script: |
-        #!/bin/bash
+        #!/bin/sh
         set -e
 
         echo "============================================"
@@ -63,67 +74,151 @@ spec:
         # Configure git
         git config --global user.email "ci@bakery-ia.local"
         git config --global user.name "bakery-ia-ci"
+        # Mark directories as safe to avoid ownership issues
+        git config --global --add safe.directory /tmp/gitops
+        git config --global --add safe.directory "$(workspaces.source.path)"
 
         # Clone the main repository (not a separate gitops repo)
-        # Use internal cluster DNS which works in all environments
+        # Use external HTTPS URL via ingress for reliable TLS connectivity
-        REPO_URL="https://${GIT_USERNAME}:${GIT_PASSWORD}@gitea-http.gitea.svc.cluster.local:3000/bakery-admin/bakery-ia.git"
+        REPO_URL="https://${GIT_USERNAME}:${GIT_PASSWORD}@gitea.bakewise.ai/bakery-admin/bakery-ia.git"
         git clone "$REPO_URL" /tmp/gitops
 
         cd /tmp/gitops
 
         # Switch to target branch
-        git checkout "$(params.git-branch)" || git checkout -b "$(params.git-branch)"
+        # The git-branch param may come as "refs/heads/main" from webhook, extract just the branch name
+        BRANCH_NAME=$(echo "$(params.git-branch)" | sed 's|refs/heads/||')
+        echo "Target branch: $BRANCH_NAME"
+        git checkout "$BRANCH_NAME" || git checkout -b "$BRANCH_NAME"
+
+        # Compute short hash once for job name updates
+        SHORT_HASH=$(echo "$(params.git-revision)" | cut -c 1-8)
+
+        # Handle special cases for service discovery
+        # "all" = all services + gateway + frontend
+        # "services-and-gateway" = all services + gateway (no frontend) - used when shared/ changes
+        SERVICES_PARAM=$(echo "$(params.services)" | tr -d '\n' | tr -d ' ')
+        WORKSPACE="$(workspaces.source.path)"
+
+        if [ "$SERVICES_PARAM" = "all" ] || [ "$SERVICES_PARAM" = "services-and-gateway" ]; then
+          echo "Expanding '$SERVICES_PARAM' to actual service list..."
+          SERVICES=""
+          # Find all services with Dockerfiles
+          if [ -d "$WORKSPACE/services" ]; then
+            for svc_name in $(ls "$WORKSPACE/services/"); do
+              if [ -f "$WORKSPACE/services/$svc_name/Dockerfile" ]; then
+                if [ -z "$SERVICES" ]; then
+                  SERVICES="$svc_name"
+                else
+                  SERVICES="$SERVICES,$svc_name"
+                fi
+              fi
+            done
+          fi
+          # Add gateway
+          if [ -d "$WORKSPACE/gateway" ]; then
+            if [ -z "$SERVICES" ]; then
+              SERVICES="gateway"
+            else
+              SERVICES="$SERVICES,gateway"
+            fi
+          fi
+          # Add frontend ONLY for "all" (not for "services-and-gateway")
+          if [ "$SERVICES_PARAM" = "all" ] && [ -d "$WORKSPACE/frontend" ]; then
+            if [ -z "$SERVICES" ]; then
+              SERVICES="frontend"
+            else
+              SERVICES="$SERVICES,frontend"
+            fi
+          fi
+          echo "Expanded services: $SERVICES"
+        else
+          SERVICES="$SERVICES_PARAM"
+        fi
 
         # Update image tags in Kubernetes manifests
-        for service in $(echo "$(params.services)" | tr ',' '\n'); do
+        # Service names come from detect-changes task as folder names: auth, tenant, ai_insights, etc.
+        for service in $(echo "$SERVICES" | tr ',' '\n'); do
           service=$(echo "$service" | xargs)  # Trim whitespace
           if [ -n "$service" ] && [ "$service" != "none" ] && [ "$service" != "infrastructure" ] && [ "$service" != "shared" ]; then
+            echo ""
+            echo "============================================"
             echo "Updating manifest for service: $service"
+            echo "============================================"
 
-            # Format service name for directory (convert from kebab-case to snake_case if needed)
+            # IMAGE_NAME is the same as the service folder name (matching Kaniko output)
-            # Handle special cases like demo-session -> demo_session, alert-processor -> alert_processor, etc.
+            # This ensures consistency: folder name = image name = manifest reference
-            formatted_service=$(echo "$service" | sed 's/-/_/g')
+            IMAGE_NAME="$service"
+
+            # Determine manifest paths based on service
+            # Directory structure uses hyphens: ai-insights, alert-processor, demo-session
+            # But image names use underscores: ai_insights, alert_processor, demo_session
+            service_dir=$(echo "$service" | sed 's/_/-/g')
 
-            # For gateway and frontend, they have different directory structures
             if [ "$service" = "gateway" ]; then
               MANIFEST_PATH="infrastructure/platform/gateway/gateway-service.yaml"
-              IMAGE_NAME="gateway"  # gateway image name is just "gateway"
             elif [ "$service" = "frontend" ]; then
               MANIFEST_PATH="infrastructure/services/microservices/frontend/frontend-service.yaml"
-              IMAGE_NAME="dashboard"  # frontend service uses "dashboard" as image name
+            elif [ "$service" = "alert_processor" ]; then
+              MANIFEST_PATH="infrastructure/services/microservices/alert-processor/alert-processor.yaml"
+            elif [ "$service" = "demo_session" ]; then
+              # demo-session uses deployment.yaml instead of demo-session-service.yaml
+              MANIFEST_PATH="infrastructure/services/microservices/demo-session/deployment.yaml"
             else
-              # For microservices, look in the microservices directory
+              # Standard services: auth, tenant, orders, inventory, etc.
-              # Convert service name to directory format (kebab-case)
+              # Also handles: ai_insights -> ai-insights, external -> external
-              service_dir=$(echo "$service" | sed 's/_/-/g')
+              MANIFEST_PATH="infrastructure/services/microservices/${service_dir}/${service_dir}-service.yaml"
-
-              # Check for different possible manifest file names
-              if [ -f "infrastructure/services/microservices/$service_dir/deployment.yaml" ]; then
-                MANIFEST_PATH="infrastructure/services/microservices/$service_dir/deployment.yaml"
-              elif [ -f "infrastructure/services/microservices/$service_dir/${formatted_service}-service.yaml" ]; then
-                MANIFEST_PATH="infrastructure/services/microservices/$service_dir/${formatted_service}-service.yaml"
-              elif [ -f "infrastructure/services/microservices/$service_dir/${service_dir}-service.yaml" ]; then
-                MANIFEST_PATH="infrastructure/services/microservices/$service_dir/${service_dir}-service.yaml"
-              else
-                # Default to the standard naming pattern
-                MANIFEST_PATH="infrastructure/services/microservices/$service_dir/${formatted_service}-service.yaml"
-              fi
-
-              # For most services, the image name follows the pattern service-name-service
-              IMAGE_NAME="${service_dir}-service"
             fi
 
             # Update the image tag in the deployment YAML
             if [ -f "$MANIFEST_PATH" ]; then
-              # Update image reference from bakery/image_name:tag to registry/image_name:git_revision
+              # Update image reference - match the exact image name pattern used in manifests
-              # Handle various image name formats that might exist in the manifests
+              sed -i "s|image: registry.bakewise.ai/bakery-admin/${IMAGE_NAME}:.*|image: $(params.registry)/${IMAGE_NAME}:$(params.git-revision)|g" "$MANIFEST_PATH"
-              sed -i "s|image: bakery/${IMAGE_NAME}:.*|image: $(params.registry)/${IMAGE_NAME}:$(params.git-revision)|g" "$MANIFEST_PATH"
+              echo "Updated: $MANIFEST_PATH -> $(params.registry)/${IMAGE_NAME}:$(params.git-revision)"
-              # Also handle the case where the image name might be formatted differently
-              sed -i "s|image: bakery/${service}:.*|image: $(params.registry)/${service}:$(params.git-revision)|g" "$MANIFEST_PATH"
-              sed -i "s|image: bakery/${formatted_service}:.*|image: $(params.registry)/${formatted_service}:$(params.git-revision)|g" "$MANIFEST_PATH"
-
-              echo "Updated image in: $MANIFEST_PATH for image: bakery/${IMAGE_NAME}:* -> $(params.registry)/${IMAGE_NAME}:$(params.git-revision)"
             else
-              echo "Warning: Manifest file not found: $MANIFEST_PATH"
+              echo "Warning: Manifest not found: $MANIFEST_PATH"
+            fi
+
+            # Update migration job if it exists
+            # Migration jobs use the hyphenated directory name
+            MIGRATION_JOB_PATH="infrastructure/services/microservices/${service_dir}/migrations/${service_dir}-migration-job.yaml"
+            if [ -f "$MIGRATION_JOB_PATH" ]; then
+              # Update migration job image reference
+              sed -i "s|image: registry.bakewise.ai/bakery-admin/${IMAGE_NAME}:.*|image: $(params.registry)/${IMAGE_NAME}:$(params.git-revision)|g" "$MIGRATION_JOB_PATH"
+              # Update job name to include short commit hash (makes it unique for K8s)
+              sed -i "s|name: ${service_dir}-migration-[a-f0-9]*|name: ${service_dir}-migration-${SHORT_HASH}|g" "$MIGRATION_JOB_PATH"
+              # Also update labels to match
+              sed -i "s|app.kubernetes.io/name: ${service_dir}-migration-[a-f0-9]*|app.kubernetes.io/name: ${service_dir}-migration-${SHORT_HASH}|g" "$MIGRATION_JOB_PATH"
+              echo "Updated migration: $MIGRATION_JOB_PATH"
+            fi
+
+            # Special case: external service has additional jobs
+            if [ "$service" = "external" ]; then
+              # Update external-data-init job
+              EXTERNAL_DATA_INIT_JOB="infrastructure/services/microservices/external/migrations/external-data-init-job.yaml"
+              if [ -f "$EXTERNAL_DATA_INIT_JOB" ]; then
+                sed -i "s|image: registry.bakewise.ai/bakery-admin/external:.*|image: $(params.registry)/external:$(params.git-revision)|g" "$EXTERNAL_DATA_INIT_JOB"
+                sed -i "s|name: external-data-init-[a-f0-9]*|name: external-data-init-${SHORT_HASH}|g" "$EXTERNAL_DATA_INIT_JOB"
+                echo "Updated external-data-init job: $EXTERNAL_DATA_INIT_JOB"
+              fi
+
+              # Update external-data-rotation cronjob
+              EXTERNAL_DATA_ROTATION_JOB="infrastructure/services/microservices/external/cronjobs/external-data-rotation-cronjob.yaml"
+              if [ -f "$EXTERNAL_DATA_ROTATION_JOB" ]; then
+                sed -i "s|image: registry.bakewise.ai/bakery-admin/external:.*|image: $(params.registry)/external:$(params.git-revision)|g" "$EXTERNAL_DATA_ROTATION_JOB"
+                sed -i "s|name: external-data-rotation-[a-f0-9]*|name: external-data-rotation-${SHORT_HASH}|g" "$EXTERNAL_DATA_ROTATION_JOB"
+                echo "Updated external-data-rotation cronjob: $EXTERNAL_DATA_ROTATION_JOB"
+              fi
+            fi
+
+            # Special case: demo_session service has cleanup worker
+            if [ "$service" = "demo_session" ]; then
+              DEMO_CLEANUP_WORKER="infrastructure/services/microservices/demo-session/demo-cleanup-worker.yaml"
+              if [ -f "$DEMO_CLEANUP_WORKER" ]; then
+                sed -i "s|image: registry.bakewise.ai/bakery-admin/demo_session:.*|image: $(params.registry)/demo_session:$(params.git-revision)|g" "$DEMO_CLEANUP_WORKER"
+                sed -i "s|name: demo-cleanup-worker-[a-f0-9]*|name: demo-cleanup-worker-${SHORT_HASH}|g" "$DEMO_CLEANUP_WORKER"
+                echo "Updated demo-cleanup-worker: $DEMO_CLEANUP_WORKER"
+              fi
             fi
           fi
         done
@@ -133,8 +228,9 @@ spec:
           git add .
           git status
           if ! git diff --cached --quiet; then
-            git commit -m "Update images for services: $(params.services) [skip ci]"
+            git commit -m "Update images for services: $SERVICES [skip ci]"
-            git push origin "$(params.git-branch)"
+            echo "Pushing to branch: $BRANCH_NAME"
+            git push origin "HEAD:$BRANCH_NAME"
             echo "GitOps manifests updated successfully"
           else
             echo "No changes to commit"

infrastructure/cicd/tekton-helm/templates/trigger-binding.yaml

@@ -12,12 +12,12 @@ metadata:
 spec:
   params:
     - name: git-repo-url
-      value: "{{"{{ .payload.repository.clone_url }}"}}"
+      value: $(body.repository.clone_url)
     - name: git-revision
-      value: "{{"{{ .payload.after }}"}}"
+      value: $(body.after)
     - name: git-branch
-      value: "{{"{{ .payload.ref }}" | replace "refs/heads/" "" | replace "refs/tags/" "" }}"
+      value: $(body.ref)
     - name: git-repo-name
-      value: "{{"{{ .payload.repository.name }}"}}"
+      value: $(body.repository.name)
     - name: git-repo-full-name
-      value: "{{"{{ .payload.repository.full_name }}"}}"
+      value: $(body.repository.full_name)

infrastructure/cicd/tekton-helm/templates/trigger-template.yaml

@@ -41,6 +41,9 @@ spec:
           # Track the source commit
           bakery-ia.io/git-revision: $(tt.params.git-revision)
           bakery-ia.io/git-branch: $(tt.params.git-branch)
+          # Automatic cleanup: delete PipelineRun after completion
+          # Default: 1 hour (3600 seconds). Configure via values.yaml
+          tekton.dev/pipelinerunDeletionPropagation: "foreground"
       spec:
         pipelineRef:
           name: bakery-ia-ci
@@ -70,7 +73,7 @@ spec:
           - name: registry
             value: $(tt.params.registry-url)
           - name: skip-tests
-            value: "false"
+            value: "true"
           - name: dry-run
             value: "false"
         # Timeout for the entire pipeline run

infrastructure/cicd/tekton-helm/values.yaml

@@ -93,6 +93,20 @@ serviceAccounts:
   pipeline:
     name: "tekton-pipeline-sa"
 
+# Cleanup and retention configuration
+cleanup:
+  # PipelineRun retention (requires Tekton Pipelines >= v0.52.0)
+  # Set to 0 to disable automatic cleanup
+  pipelineRuns:
+    # Keep last N successful PipelineRuns per Pipeline
+    keepSuccessful: 3
+    # Keep last N failed PipelineRuns per Pipeline
+    keepFailed: 5
+  # TaskRun retention
+  taskRuns:
+    keepSuccessful: 3
+    keepFailed: 5
+
 # Labels to apply to resources
 labels:
   app:

infrastructure/environments/common/configs/configmap.yaml

@@ -488,4 +488,4 @@ data:
   EXTERNAL_ENABLED_CITIES: "madrid"
   EXTERNAL_RETENTION_MONTHS: "6"  # Reduced from 24 to avoid memory issues during init
   EXTERNAL_CACHE_TTL_DAYS: "7"
-  EXTERNAL_REDIS_URL: "rediss://redis-service:6379/0?ssl_cert_reqs=none"
+  EXTERNAL_REDIS_URL: "rediss://redis-service:6379/0"

infrastructure/environments/prod/k8s-manifests/kustomization.yaml

@@ -21,9 +21,9 @@ resources:
   - prod-certificate.yaml
 
 
-  # SigNoz is managed via Helm deployment (see infrastructure/helm/deploy-signoz.sh)
+  # SigNoz is managed via Helm deployment (see infrastructure/monitoring/signoz/deploy-signoz.sh)
-  # Monitoring is handled by SigNoz (no separate monitoring components needed)
+  # Monitoring is handled by SigNoz with its own dedicated ingress
-  # SigNoz paths are now included in the main ingress (ingress-https.yaml)
+  # SigNoz creates its own ingress resource for monitoring.bakewise.ai
 
 labels:
   - includeSelectors: false
@@ -204,72 +204,120 @@ patches:
             memory: "1Gi"
             cpu: "500m"
 
+  # =============================================================================
+  # CPU Request Optimization for Production
+  # Reduce CPU requests to match actual usage (was 100m, actual ~5-10m)
+  # This prevents scheduler rejections due to overcommitted requests
+  # =============================================================================
+
+  # Database deployments - reduce CPU request from 100m to 25m
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: ".*-db$"
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
+  # Microservice deployments - reduce CPU request from 100m to 25m
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: ".*-service$"
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
+  # Other core services
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: gateway
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: alert-processor
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: frontend
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "50m"
+
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: redis
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: rabbitmq
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "50m"
+
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+      name: minio
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "50m"
+
+  # Migration jobs - reduce CPU request from 100m to 25m
+  - target:
+      group: batch
+      version: v1
+      kind: Job
+      name: ".*-migration$"
+      namespace: bakery-ia
+    patch: |-
+      - op: replace
+        path: /spec/template/spec/containers/0/resources/requests/cpu
+        value: "25m"
+
 images:
-  # Application services
+  # =============================================================================
-  - name: bakery/auth-service
+  # NOTE: Application service images (bakery/*) are NOT overridden here.
-    newName: registry.bakewise.ai/bakery-admin/auth-service
+  # CI/CD pipeline (Tekton) updates base manifests directly with versioned tags.
-    newTag: latest
+  # This ensures deployments use the exact git revision that was built.
-  - name: bakery/tenant-service
-    newName: registry.bakewise.ai/bakery-admin/tenant-service
-    newTag: latest
-  - name: bakery/training-service
-    newName: registry.bakewise.ai/bakery-admin/training-service
-    newTag: latest
-  - name: bakery/forecasting-service
-    newName: registry.bakewise.ai/bakery-admin/forecasting-service
-    newTag: latest
-  - name: bakery/sales-service
-    newName: registry.bakewise.ai/bakery-admin/sales-service
-    newTag: latest
-  - name: bakery/external-service
-    newName: registry.bakewise.ai/bakery-admin/external-service
-    newTag: latest
-  - name: bakery/notification-service
-    newName: registry.bakewise.ai/bakery-admin/notification-service
-    newTag: latest
-  - name: bakery/inventory-service
-    newName: registry.bakewise.ai/bakery-admin/inventory-service
-    newTag: latest
-  - name: bakery/recipes-service
-    newName: registry.bakewise.ai/bakery-admin/recipes-service
-    newTag: latest
-  - name: bakery/suppliers-service
-    newName: registry.bakewise.ai/bakery-admin/suppliers-service
-    newTag: latest
-  - name: bakery/pos-service
-    newName: registry.bakewise.ai/bakery-admin/pos-service
-    newTag: latest
-  - name: bakery/orders-service
-    newName: registry.bakewise.ai/bakery-admin/orders-service
-    newTag: latest
-  - name: bakery/production-service
-    newName: registry.bakewise.ai/bakery-admin/production-service
-    newTag: latest
-  - name: bakery/alert-processor
-    newName: registry.bakewise.ai/bakery-admin/alert-processor
-    newTag: latest
-  - name: bakery/gateway
-    newName: registry.bakewise.ai/bakery-admin/gateway
-    newTag: latest
-  - name: bakery/dashboard
-    newName: registry.bakewise.ai/bakery-admin/dashboard
-    newTag: latest
-  # Missing services (added to fix ImagePullBackOff errors)
-  - name: bakery/ai-insights-service
-    newName: registry.bakewise.ai/bakery-admin/ai-insights-service
-    newTag: latest
-  - name: bakery/demo-session-service
-    newName: registry.bakewise.ai/bakery-admin/demo-session-service
-    newTag: latest
-  - name: bakery/distribution-service
-    newName: registry.bakewise.ai/bakery-admin/distribution-service
-    newTag: latest
-  - name: bakery/orchestrator-service
-    newName: registry.bakewise.ai/bakery-admin/orchestrator-service
-    newTag: latest
-  - name: bakery/procurement-service
-    newName: registry.bakewise.ai/bakery-admin/procurement-service
-    newTag: latest
   # =============================================================================
   # Database images (cached in gitea registry for consistency)
   - name: postgres

infrastructure/monitoring/k8s-infra/README.md

@@ -0,0 +1,121 @@
+# Kubernetes Infrastructure Monitoring
+
+This directory contains configurations for deploying Kubernetes infrastructure monitoring components that integrate with SigNoz.
+
+## Components
+
+| Component | Purpose | Metrics Endpoint |
+|-----------|---------|------------------|
+| **kube-state-metrics** | Kubernetes object metrics (pods, deployments, nodes, etc.) | `:8080/metrics` |
+| **node-exporter** | Host-level metrics (CPU, memory, disk, network) | `:9100/metrics` |
+
+## Quick Start (MicroK8s Production)
+
+```bash
+# 1. Deploy infrastructure monitoring components
+./deploy-k8s-infra-monitoring.sh --microk8s install
+
+# 2. Upgrade SigNoz to scrape the new metrics
+microk8s helm3 upgrade signoz signoz/signoz \
+  -n bakery-ia \
+  -f ../signoz/signoz-values-prod.yaml
+```
+
+## Usage
+
+### Install
+
+```bash
+# Standard Kubernetes
+./deploy-k8s-infra-monitoring.sh install
+
+# MicroK8s
+./deploy-k8s-infra-monitoring.sh --microk8s install
+```
+
+### Upgrade
+
+```bash
+./deploy-k8s-infra-monitoring.sh --microk8s upgrade
+```
+
+### Uninstall
+
+```bash
+./deploy-k8s-infra-monitoring.sh --microk8s uninstall
+```
+
+### Check Status
+
+```bash
+./deploy-k8s-infra-monitoring.sh --microk8s status
+```
+
+### Dry Run
+
+```bash
+./deploy-k8s-infra-monitoring.sh --microk8s --dry-run install
+```
+
+## Files
+
+- `kube-state-metrics-values.yaml` - Helm values for kube-state-metrics
+- `node-exporter-values.yaml` - Helm values for node-exporter
+- `deploy-k8s-infra-monitoring.sh` - Deployment automation script
+
+## SigNoz Integration
+
+The SigNoz OTel Collector is configured (in `signoz-values-prod.yaml`) to scrape metrics from:
+
+- `kube-state-metrics.bakery-ia.svc.cluster.local:8080`
+- `node-exporter-prometheus-node-exporter.bakery-ia.svc.cluster.local:9100`
+
+After deploying these components, metrics will appear in SigNoz under:
+- **Infrastructure** > **Kubernetes** (for K8s object metrics)
+- **Infrastructure** > **Hosts** (for node metrics)
+
+## Metrics Available
+
+### From kube-state-metrics
+
+- Pod status, phase, restarts
+- Deployment replicas (desired vs available)
+- Node conditions and capacity
+- PVC status and capacity
+- Resource requests and limits
+- Job/CronJob status
+
+### From node-exporter
+
+- CPU usage per core
+- Memory usage (total, free, cached)
+- Disk I/O and space
+- Network traffic (bytes in/out)
+- System load average
+- Filesystem usage
+
+## Troubleshooting
+
+### Check if metrics are being scraped
+
+```bash
+# Port-forward to kube-state-metrics
+microk8s kubectl port-forward svc/kube-state-metrics 8080:8080 -n bakery-ia &
+curl localhost:8080/metrics | head -50
+
+# Port-forward to node-exporter
+microk8s kubectl port-forward svc/node-exporter-prometheus-node-exporter 9100:9100 -n bakery-ia &
+curl localhost:9100/metrics | head -50
+```
+
+### Check OTel Collector logs
+
+```bash
+microk8s kubectl logs -l app.kubernetes.io/name=signoz-otel-collector -n bakery-ia --tail=100
+```
+
+### Verify pods are running
+
+```bash
+microk8s kubectl get pods -n bakery-ia | grep -E "(kube-state|node-exporter)"
+```

infrastructure/monitoring/k8s-infra/deploy-k8s-infra-monitoring.sh

@@ -0,0 +1,347 @@
+#!/bin/bash
+
+# ============================================================================
+# Kubernetes Infrastructure Monitoring Deployment Script
+# ============================================================================
+# Deploys kube-state-metrics and node-exporter for Kubernetes infrastructure
+# monitoring in SigNoz
+# ============================================================================
+
+set -e
+
+# Color codes for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# Configuration
+NAMESPACE="bakery-ia"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Function to display help
+show_help() {
+    echo "Usage: $0 [OPTIONS] [COMMAND]"
+    echo ""
+    echo "Deploy Kubernetes infrastructure monitoring components"
+    echo ""
+    echo "Commands:"
+    echo "  install     Install kube-state-metrics and node-exporter (default)"
+    echo "  upgrade     Upgrade existing deployments"
+    echo "  uninstall   Remove all infrastructure monitoring components"
+    echo "  status      Show deployment status"
+    echo ""
+    echo "Options:"
+    echo "  -h, --help          Show this help message"
+    echo "  -d, --dry-run       Show what would be done without executing"
+    echo "  -n, --namespace NS  Specify namespace (default: bakery-ia)"
+    echo "  --microk8s          Use microk8s helm3 command (for MicroK8s clusters)"
+    echo ""
+    echo "Examples:"
+    echo "  $0 install                    # Install on standard k8s"
+    echo "  $0 --microk8s install         # Install on MicroK8s"
+    echo "  $0 --microk8s upgrade         # Upgrade on MicroK8s"
+    echo "  $0 --microk8s uninstall       # Remove from MicroK8s"
+    echo "  $0 status                     # Check deployment status"
+}
+
+# Parse arguments
+DRY_RUN=false
+USE_MICROK8S=false
+COMMAND="install"
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        -d|--dry-run)
+            DRY_RUN=true
+            shift
+            ;;
+        -n|--namespace)
+            NAMESPACE="$2"
+            shift 2
+            ;;
+        --microk8s)
+            USE_MICROK8S=true
+            shift
+            ;;
+        install|upgrade|uninstall|status)
+            COMMAND="$1"
+            shift
+            ;;
+        *)
+            echo -e "${RED}Unknown argument: $1${NC}"
+            show_help
+            exit 1
+            ;;
+    esac
+done
+
+# Set helm and kubectl commands based on environment
+if [[ "$USE_MICROK8S" == true ]]; then
+    HELM_CMD="microk8s helm3"
+    KUBECTL_CMD="microk8s kubectl"
+else
+    HELM_CMD="helm"
+    KUBECTL_CMD="kubectl"
+fi
+
+# Function to check prerequisites
+check_prerequisites() {
+    echo -e "${BLUE}Checking prerequisites...${NC}"
+
+    # Check helm
+    if [[ "$USE_MICROK8S" == true ]]; then
+        # Test if microk8s helm3 command works directly
+        if ! microk8s helm3 version &> /dev/null; then
+            echo -e "${RED}Error: MicroK8s helm3 addon is not working.${NC}"
+            echo "Enable it with: microk8s enable helm3"
+            exit 1
+        fi
+        echo -e "${GREEN}MicroK8s helm3 is available.${NC}"
+    else
+        if ! command -v helm &> /dev/null; then
+            echo -e "${RED}Error: Helm is not installed.${NC}"
+            exit 1
+        fi
+    fi
+
+    # Check kubectl connectivity
+    if ! $KUBECTL_CMD cluster-info &> /dev/null; then
+        echo -e "${RED}Error: Cannot connect to Kubernetes cluster.${NC}"
+        exit 1
+    fi
+
+    echo -e "${GREEN}Prerequisites check passed.${NC}"
+    echo ""
+}
+
+# Function to setup Helm repository
+setup_helm_repo() {
+    echo -e "${BLUE}Setting up Prometheus Community Helm repository...${NC}"
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would add prometheus-community Helm repository"
+        return
+    fi
+
+    if $HELM_CMD repo list 2>/dev/null | grep -q "prometheus-community"; then
+        echo -e "${BLUE}Repository already added, updating...${NC}"
+        $HELM_CMD repo update prometheus-community
+    else
+        $HELM_CMD repo add prometheus-community https://prometheus-community.github.io/helm-charts
+        $HELM_CMD repo update
+    fi
+
+    echo -e "${GREEN}Helm repository ready.${NC}"
+    echo ""
+}
+
+# Function to ensure namespace exists
+ensure_namespace() {
+    echo -e "${BLUE}Ensuring namespace $NAMESPACE exists...${NC}"
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would create namespace if needed"
+        return
+    fi
+
+    if ! $KUBECTL_CMD get namespace "$NAMESPACE" &> /dev/null; then
+        $KUBECTL_CMD create namespace "$NAMESPACE"
+        echo -e "${GREEN}Namespace $NAMESPACE created.${NC}"
+    else
+        echo -e "${BLUE}Namespace $NAMESPACE already exists.${NC}"
+    fi
+    echo ""
+}
+
+# Function to install kube-state-metrics
+install_kube_state_metrics() {
+    echo -e "${BLUE}Installing kube-state-metrics...${NC}"
+
+    local values_file="$SCRIPT_DIR/kube-state-metrics-values.yaml"
+
+    if [[ ! -f "$values_file" ]]; then
+        echo -e "${RED}Error: Values file not found: $values_file${NC}"
+        exit 1
+    fi
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would install kube-state-metrics"
+        echo "  Command: $HELM_CMD upgrade --install kube-state-metrics prometheus-community/kube-state-metrics -n $NAMESPACE -f $values_file"
+        return
+    fi
+
+    $HELM_CMD upgrade --install kube-state-metrics \
+        prometheus-community/kube-state-metrics \
+        -n "$NAMESPACE" \
+        -f "$values_file" \
+        --wait \
+        --timeout 5m
+
+    echo -e "${GREEN}kube-state-metrics installed successfully.${NC}"
+    echo ""
+}
+
+# Function to install node-exporter
+install_node_exporter() {
+    echo -e "${BLUE}Installing node-exporter...${NC}"
+
+    local values_file="$SCRIPT_DIR/node-exporter-values.yaml"
+
+    if [[ ! -f "$values_file" ]]; then
+        echo -e "${RED}Error: Values file not found: $values_file${NC}"
+        exit 1
+    fi
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would install node-exporter"
+        echo "  Command: $HELM_CMD upgrade --install node-exporter prometheus-community/prometheus-node-exporter -n $NAMESPACE -f $values_file"
+        return
+    fi
+
+    $HELM_CMD upgrade --install node-exporter \
+        prometheus-community/prometheus-node-exporter \
+        -n "$NAMESPACE" \
+        -f "$values_file" \
+        --wait \
+        --timeout 5m
+
+    echo -e "${GREEN}node-exporter installed successfully.${NC}"
+    echo ""
+}
+
+# Function to uninstall components
+uninstall_components() {
+    echo -e "${BLUE}Uninstalling Kubernetes infrastructure monitoring components...${NC}"
+
+    if [[ "$DRY_RUN" == true ]]; then
+        echo "  (dry-run) Would uninstall kube-state-metrics and node-exporter"
+        return
+    fi
+
+    # Uninstall kube-state-metrics
+    if $HELM_CMD list -n "$NAMESPACE" | grep -q "kube-state-metrics"; then
+        echo -e "${BLUE}Removing kube-state-metrics...${NC}"
+        $HELM_CMD uninstall kube-state-metrics -n "$NAMESPACE" --wait
+        echo -e "${GREEN}kube-state-metrics removed.${NC}"
+    else
+        echo -e "${YELLOW}kube-state-metrics not found.${NC}"
+    fi
+
+    # Uninstall node-exporter
+    if $HELM_CMD list -n "$NAMESPACE" | grep -q "node-exporter"; then
+        echo -e "${BLUE}Removing node-exporter...${NC}"
+        $HELM_CMD uninstall node-exporter -n "$NAMESPACE" --wait
+        echo -e "${GREEN}node-exporter removed.${NC}"
+    else
+        echo -e "${YELLOW}node-exporter not found.${NC}"
+    fi
+
+    echo ""
+}
+
+# Function to show deployment status
+show_status() {
+    echo -e "${BLUE}=== Kubernetes Infrastructure Monitoring Status ===${NC}"
+    echo ""
+
+    echo -e "${BLUE}Helm Releases:${NC}"
+    $HELM_CMD list -n "$NAMESPACE" | grep -E "(kube-state-metrics|node-exporter)" || echo "  No releases found"
+    echo ""
+
+    echo -e "${BLUE}Pods:${NC}"
+    $KUBECTL_CMD get pods -n "$NAMESPACE" -l 'app.kubernetes.io/name in (kube-state-metrics, prometheus-node-exporter)' 2>/dev/null || echo "  No pods found"
+    echo ""
+
+    echo -e "${BLUE}Services:${NC}"
+    $KUBECTL_CMD get svc -n "$NAMESPACE" | grep -E "(kube-state-metrics|node-exporter)" || echo "  No services found"
+    echo ""
+
+    echo -e "${BLUE}Endpoints (for SigNoz scraping):${NC}"
+    echo "  kube-state-metrics: kube-state-metrics.$NAMESPACE.svc.cluster.local:8080"
+    echo "  node-exporter:      node-exporter-prometheus-node-exporter.$NAMESPACE.svc.cluster.local:9100"
+    echo ""
+}
+
+# Function to show post-install instructions
+show_post_install_instructions() {
+    echo -e "${BLUE}=== Post-Installation Instructions ===${NC}"
+    echo ""
+    echo "To enable SigNoz to scrape these metrics, update your SigNoz OTel Collector config."
+    echo ""
+    echo "Add the following to your signoz-values-prod.yaml under otelCollector.config:"
+    echo ""
+    cat << 'EOF'
+otelCollector:
+  config:
+    receivers:
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: 'kube-state-metrics'
+              static_configs:
+                - targets: ['kube-state-metrics.bakery-ia.svc.cluster.local:8080']
+              scrape_interval: 30s
+            - job_name: 'node-exporter'
+              static_configs:
+                - targets: ['node-exporter-prometheus-node-exporter.bakery-ia.svc.cluster.local:9100']
+              scrape_interval: 30s
+    service:
+      pipelines:
+        metrics:
+          receivers: [otlp, prometheus]
+EOF
+    echo ""
+    echo "Then upgrade SigNoz:"
+    if [[ "$USE_MICROK8S" == true ]]; then
+        echo "  microk8s helm3 upgrade signoz signoz/signoz -n $NAMESPACE -f infrastructure/monitoring/signoz/signoz-values-prod.yaml"
+    else
+        echo "  helm upgrade signoz signoz/signoz -n $NAMESPACE -f infrastructure/monitoring/signoz/signoz-values-prod.yaml"
+    fi
+    echo ""
+}
+
+# Main execution
+main() {
+    echo -e "${BLUE}"
+    echo "=========================================="
+    echo "Kubernetes Infrastructure Monitoring"
+    echo "=========================================="
+    echo -e "${NC}"
+
+    check_prerequisites
+
+    case $COMMAND in
+        install)
+            setup_helm_repo
+            ensure_namespace
+            install_kube_state_metrics
+            install_node_exporter
+            show_status
+            show_post_install_instructions
+            echo -e "${GREEN}Installation completed successfully!${NC}"
+            ;;
+        upgrade)
+            setup_helm_repo
+            install_kube_state_metrics
+            install_node_exporter
+            show_status
+            echo -e "${GREEN}Upgrade completed successfully!${NC}"
+            ;;
+        uninstall)
+            uninstall_components
+            echo -e "${GREEN}Uninstallation completed.${NC}"
+            ;;
+        status)
+            show_status
+            ;;
+    esac
+}
+
+# Run main function
+main

infrastructure/monitoring/k8s-infra/kube-state-metrics-values.yaml

@@ -0,0 +1,109 @@
+# Kube-State-Metrics Helm Values for Bakery IA
+# Chart: prometheus-community/kube-state-metrics
+# Documentation: https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-state-metrics
+#
+# Install Command:
+#   helm install kube-state-metrics prometheus-community/kube-state-metrics \
+#     -n bakery-ia -f kube-state-metrics-values.yaml
+
+# Image configuration
+image:
+  registry: registry.k8s.io
+  repository: kube-state-metrics/kube-state-metrics
+  tag: ""  # Uses chart default (latest stable)
+  pullPolicy: IfNotPresent
+
+# Replicas - single instance is sufficient for most clusters
+replicas: 1
+
+# Resource limits optimized for MicroK8s VPS
+resources:
+  requests:
+    cpu: 10m
+    memory: 32Mi
+  limits:
+    cpu: 100m
+    memory: 128Mi
+
+# Service configuration
+service:
+  type: ClusterIP
+  port: 8080
+  annotations: {}
+
+# Prometheus scrape annotations
+prometheusScrape: true
+
+# Which Kubernetes resources to collect metrics for
+# Full list available, but we focus on most useful ones
+collectors:
+  - certificatesigningrequests
+  - configmaps
+  - cronjobs
+  - daemonsets
+  - deployments
+  - endpoints
+  - horizontalpodautoscalers
+  - ingresses
+  - jobs
+  - leases
+  - limitranges
+  - namespaces
+  - networkpolicies
+  - nodes
+  - persistentvolumeclaims
+  - persistentvolumes
+  - poddisruptionbudgets
+  - pods
+  - replicasets
+  - replicationcontrollers
+  - resourcequotas
+  - secrets
+  - services
+  - statefulsets
+  - storageclasses
+
+# Namespace to watch (empty = all namespaces)
+namespaces: ""
+
+# Node selector for scheduling
+nodeSelector: {}
+
+# Tolerations
+tolerations: []
+
+# Affinity rules
+affinity: {}
+
+# Pod security context
+podSecurityContext:
+  runAsNonRoot: true
+  runAsUser: 65534
+  fsGroup: 65534
+
+# Container security context
+securityContext:
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
+  readOnlyRootFilesystem: true
+
+# Self-monitoring metrics
+selfMonitor:
+  enabled: true
+
+# Kubernetes API access
+kubeconfig:
+  enabled: false
+
+# RBAC configuration
+rbac:
+  create: true
+  useClusterRole: true
+
+# Service account
+serviceAccount:
+  create: true
+  name: ""
+  annotations: {}

infrastructure/monitoring/k8s-infra/node-exporter-values.yaml

@@ -0,0 +1,97 @@
+# Prometheus Node Exporter Helm Values for Bakery IA
+# Chart: prometheus-community/prometheus-node-exporter
+# Documentation: https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-node-exporter
+#
+# Install Command:
+#   helm install node-exporter prometheus-community/prometheus-node-exporter \
+#     -n bakery-ia -f node-exporter-values.yaml
+
+# Image configuration
+image:
+  registry: quay.io
+  repository: prometheus/node-exporter
+  tag: ""  # Uses chart default (latest stable)
+  pullPolicy: IfNotPresent
+
+# Resource limits optimized for MicroK8s VPS
+resources:
+  requests:
+    cpu: 10m
+    memory: 32Mi
+  limits:
+    cpu: 200m
+    memory: 64Mi
+
+# Service configuration
+service:
+  type: ClusterIP
+  port: 9100
+  targetPort: 9100
+  annotations:
+    prometheus.io/scrape: "true"
+
+# DaemonSet update strategy
+updateStrategy:
+  type: RollingUpdate
+  rollingUpdate:
+    maxUnavailable: 1
+
+# Host network - required for accurate network metrics
+hostNetwork: true
+hostPID: true
+hostRootFsMount:
+  enabled: true
+  mountPropagation: HostToContainer
+
+# Node selector
+nodeSelector: {}
+
+# Tolerations - allow scheduling on all nodes including control plane
+tolerations:
+  - effect: NoSchedule
+    operator: Exists
+
+# Affinity rules
+affinity: {}
+
+# Pod security context
+podSecurityContext:
+  fsGroup: 65534
+  runAsGroup: 65534
+  runAsNonRoot: true
+  runAsUser: 65534
+
+# Container security context
+securityContext:
+  readOnlyRootFilesystem: true
+
+# RBAC configuration
+rbac:
+  create: true
+  pspEnabled: false
+
+# Service account
+serviceAccount:
+  create: true
+  name: ""
+  annotations: {}
+
+# Prometheus scrape annotations
+prometheus:
+  monitor:
+    enabled: false  # We use SigNoz OTel collector scraping instead
+
+# Extra arguments for node-exporter
+extraArgs:
+  - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
+  - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
+
+# Collectors to enable (default set)
+# Disable collectors that are not useful or cause issues
+extraHostVolumeMounts: []
+
+# Sidecar containers
+sidecars: []
+
+# Init containers
+initContainers: []

infrastructure/monitoring/signoz/signoz-values-dev.yaml

@@ -1,6 +1,6 @@
 # SigNoz Helm Chart Values - Development Environment
 # Optimized for local development with minimal resource usage
-# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by bakery-ingress
+# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by SigNoz Helm chart
 #
 # Official Chart: https://github.com/SigNoz/charts
 # Install Command: helm install signoz signoz/signoz -n bakery-ia -f signoz-values-dev.yaml
@@ -10,3 +10,60 @@ global:
   clusterName: "bakery-ia-dev"
   domain: "monitoring.bakery-ia.local"
   # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)
+
+# Ingress configuration for SigNoz development
+frontend:
+  ingress:
+    enabled: true
+    className: nginx
+    annotations:
+      nginx.ingress.kubernetes.io/ssl-redirect: "false"  # Disable for local development
+      nginx.ingress.kubernetes.io/proxy-body-size: "100m"
+      nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+      nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    hosts:
+      - host: monitoring.bakery-ia.local
+        paths:
+          - path: /
+            pathType: Prefix
+    tls: []  # No TLS for local development
+
+# Resource configuration for development
+# Minimal resources for local testing
+clickhouse:
+  persistence:
+    size: 5Gi
+  resources:
+    requests:
+      memory: "512Mi"
+      cpu: "250m"
+    limits:
+      memory: "1Gi"
+      cpu: "500m"
+
+otelCollector:
+  resources:
+    requests:
+      memory: "256Mi"
+      cpu: "100m"
+    limits:
+      memory: "512Mi"
+      cpu: "250m"
+
+queryService:
+  resources:
+    requests:
+      memory: "256Mi"
+      cpu: "100m"
+    limits:
+      memory: "512Mi"
+      cpu: "250m"
+
+alertmanager:
+  resources:
+    requests:
+      memory: "128Mi"
+      cpu: "50m"
+    limits:
+      memory: "256Mi"
+      cpu: "100m"

infrastructure/monitoring/signoz/signoz-values-prod.yaml

@@ -1,6 +1,6 @@
 # SigNoz Helm Chart Values - Production Environment
 # High-availability configuration with resource optimization
-# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by bakery-ingress-prod
+# DEPLOYED IN bakery-ia NAMESPACE - Ingress managed by SigNoz Helm chart
 #
 # Official Chart: https://github.com/SigNoz/charts
 # Install Command: helm install signoz signoz/signoz -n bakery-ia -f signoz-values-prod.yaml
@@ -10,3 +10,99 @@ global:
   clusterName: "bakery-ia-prod"
   domain: "monitoring.bakewise.ai"
   # Docker Hub credentials - applied to all sub-charts (including Zookeeper, ClickHouse, etc)
+
+# Ingress configuration for SigNoz Frontend
+# Configured to use HTTPS with TLS termination at ingress controller
+# NOTE: SigNoz Helm chart expects ingress under "signoz.ingress", not "frontend.ingress"
+# Reference: https://github.com/SigNoz/charts/blob/main/charts/signoz/values.yaml
+signoz:
+  ingress:
+    enabled: true
+    className: nginx
+    annotations:
+      nginx.ingress.kubernetes.io/ssl-redirect: "true"
+      nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
+      nginx.ingress.kubernetes.io/proxy-body-size: "100m"
+      nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+      nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+      cert-manager.io/cluster-issuer: "letsencrypt-production"
+      nginx.ingress.kubernetes.io/limit-rps: "50"
+      nginx.ingress.kubernetes.io/limit-connections: "25"
+    hosts:
+      - host: monitoring.bakewise.ai
+        paths:
+          - path: /
+            pathType: ImplementationSpecific
+            port: 8080
+    tls:
+      - hosts:
+          - monitoring.bakewise.ai
+        secretName: bakery-ia-prod-tls-cert
+
+# Resource configuration for production
+# Optimized for 8 CPU core VPS deployment
+clickhouse:
+  persistence:
+    size: 20Gi
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "500m"
+    limits:
+      memory: "4Gi"
+      cpu: "1000m"
+
+otelCollector:
+  resources:
+    requests:
+      memory: "1Gi"
+      cpu: "500m"
+    limits:
+      memory: "2Gi"
+      cpu: "1000m"
+  # Additional config for Kubernetes infrastructure metrics scraping
+  config:
+    receivers:
+      prometheus:
+        config:
+          scrape_configs:
+            # Kube-state-metrics - Kubernetes object metrics
+            - job_name: 'kube-state-metrics'
+              static_configs:
+                - targets: ['kube-state-metrics.bakery-ia.svc.cluster.local:8080']
+              scrape_interval: 30s
+              metric_relabel_configs:
+                - source_labels: [__name__]
+                  regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset|replicaset|job|cronjob|persistentvolume|persistentvolumeclaim|resourcequota|service|configmap|secret).*'
+                  action: keep
+            # Node-exporter - Host-level metrics
+            - job_name: 'node-exporter'
+              static_configs:
+                - targets: ['node-exporter-prometheus-node-exporter.bakery-ia.svc.cluster.local:9100']
+              scrape_interval: 30s
+              metric_relabel_configs:
+                - source_labels: [__name__]
+                  regex: 'node_(cpu|memory|disk|filesystem|network|load).*'
+                  action: keep
+    service:
+      pipelines:
+        metrics:
+          receivers: [otlp, prometheus]
+
+queryService:
+  resources:
+    requests:
+      memory: "1Gi"
+      cpu: "500m"
+    limits:
+      memory: "2Gi"
+      cpu: "1000m"
+
+alertmanager:
+  resources:
+    requests:
+      memory: "512Mi"
+      cpu: "250m"
+    limits:
+      memory: "1Gi"
+      cpu: "500m"

infrastructure/platform/gateway/gateway-service.yaml

@@ -21,7 +21,7 @@ spec:
     spec:
       containers:
       - name: gateway
-        image: bakery/gateway:latest
+        image: registry.bakewise.ai/bakery-admin/gateway:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/platform/mail/mailu-helm/README.md

@@ -23,7 +23,7 @@ mailu-helm/
 The following critical configurations from the original Kustomize setup have been preserved:
 
 - **Domain settings**: Domain and hostnames for both dev and prod
-- **External relay**: Mailgun SMTP relay configuration
+- **External relay**: MailerSend SMTP relay configuration
 - **Redis integration**: Connection to shared Redis cluster (database 15)
 - **Database settings**: PostgreSQL connection details
 - **Resource limits**: CPU and memory requests/limits matching original setup
@@ -39,7 +39,7 @@ The following critical configurations from the original Kustomize setup have bee
 2. Kubernetes cluster with storage provisioner
 3. Ingress controller (NGINX) - already deployed in your cluster
 4. Cert-manager for TLS certificates (optional, depends on your ingress setup)
-5. External SMTP relay account (Mailgun)
+5. External SMTP relay account (MailerSend - https://mailersend.com)
 
 ### Deployment Commands
 

infrastructure/platform/mail/mailu-helm/configs/coredns-unbound-patch.yaml

@@ -1,38 +0,0 @@
-# CoreDNS ConfigMap patch to forward external DNS queries to Unbound for DNSSEC validation
-# This is required for Mailu Admin which requires DNSSEC-validating DNS resolver
-#
-# Apply with: kubectl apply -f coredns-unbound-patch.yaml
-# Then restart CoreDNS: kubectl rollout restart deployment coredns -n kube-system
-#
-# Note: The Unbound service IP (10.104.127.213) may change when the cluster is recreated.
-# The setup script will automatically update this based on the actual Unbound service IP.
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: coredns
-  namespace: kube-system
-data:
-  Corefile: |
-    .:53 {
-        errors
-        health {
-           lameduck 5s
-        }
-        ready
-        kubernetes cluster.local in-addr.arpa ip6.arpa {
-           pods insecure
-           fallthrough in-addr.arpa ip6.arpa
-           ttl 30
-        }
-        prometheus :9153
-        forward . UNBOUND_SERVICE_IP {
-           max_concurrent 1000
-        }
-        cache 30 {
-           disable success cluster.local
-           disable denial cluster.local
-        }
-        loop
-        reload
-        loadbalance
-    }

infrastructure/platform/mail/mailu-helm/configs/mailersend-credentials-secret.yaml

@@ -0,0 +1,108 @@
+# MailerSend SMTP Credentials Secret for Mailu
+#
+# This secret stores MailerSend credentials for outbound email relay.
+# Mailu uses MailerSend as an external SMTP relay to send all outbound emails.
+#
+# ============================================================================
+# HOW TO CONFIGURE:
+# ============================================================================
+#
+# 1. Go to https://accounts.mailersend.com/signup and create an account
+#
+# 2. Add and verify your domain:
+#    - For dev: bakery-ia.dev
+#    - For prod: bakewise.ai
+#    - Go to Email -> Domains -> Add domain
+#    - Follow the DNS verification steps (add TXT records)
+#
+# 3. Generate SMTP credentials:
+#    - Go to Email -> Domains -> Click on your domain
+#    - Go to SMTP section
+#    - Click "Generate new user"
+#    - Save the generated username and password
+#
+# 4. Note your SMTP credentials:
+#    - SMTP hostname: smtp.mailersend.net
+#    - Port: 587 (TLS/STARTTLS)
+#    - Username: generated by MailerSend (e.g., MS_xxxxxx@trial-xxxxx.mlsender.net)
+#    - Password: generated SMTP password
+#
+# 5. Replace the placeholder values below with your credentials
+#
+# 6. Apply this secret:
+#    kubectl apply -f mailersend-credentials-secret.yaml -n bakery-ia
+#
+# ============================================================================
+# IMPORTANT NOTES:
+# ============================================================================
+#
+# - MailerSend requires TLS 1.2 or higher (supported by default)
+# - SMTP credentials are account-wide (work for any verified domain)
+# - Free tier: 3,000 emails/month (12,000 with verified domain)
+# - Rate limit: 120 requests/minute
+#
+# ============================================================================
+# CRITICAL: AFTER UPDATING THIS SECRET
+# ============================================================================
+#
+# Mailu's Postfix reads SASL credentials ONLY at pod startup. It does NOT
+# automatically reload when this secret changes. You MUST do one of:
+#
+# Option 1: Update the credentials-version annotation in values.yaml and run helm upgrade
+#   - Edit prod/values.yaml: postfix.podAnnotations.credentials-version
+#   - Set to current timestamp: date +%s
+#   - Run: helm upgrade mailu mailu/mailu -f values.yaml -f prod/values.yaml -n bakery-ia
+#
+# Option 2: Manually restart Postfix pod
+#   kubectl rollout restart deployment/mailu-postfix -n bakery-ia
+#
+# Option 3: Delete the Postfix pod (it will be recreated)
+#   kubectl delete pod -l app.kubernetes.io/component=postfix -n bakery-ia
+#
+# ============================================================================
+# DNS RECORDS REQUIRED FOR MAILERSEND:
+# ============================================================================
+#
+# Add these DNS records to your domain (Cloudflare) for proper email delivery:
+#
+# 1. SPF Record (TXT):
+#    Name: @
+#    Value: v=spf1 include:mailersend.net ~all
+#
+# 2. DKIM Records (TXT):
+#    MailerSend will provide DKIM keys after domain verification
+#    Typically: mlsend._domainkey and mlsend2._domainkey
+#    (check your MailerSend domain settings for exact values)
+#
+# 3. DMARC Record (TXT):
+#    Name: _dmarc
+#    Value: v=DMARC1; p=quarantine; rua=mailto:admin@bakewise.ai
+#
+# 4. MX Records (for receiving mail via Mailu):
+#    Priority 10: mail.bakewise.ai
+#
+# 5. A Record:
+#    Name: mail
+#    Value: <your-server-public-IP>
+#
+# ============================================================================
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: mailu-mailersend-credentials
+  namespace: bakery-ia
+  labels:
+    app: mailu
+    component: external-relay
+  annotations:
+    description: "MailerSend SMTP credentials for Mailu external relay"
+type: Opaque
+stringData:
+  # ============================================================================
+  # REPLACE THESE VALUES WITH YOUR MAILERSEND CREDENTIALS
+  # ============================================================================
+  # Key names match Mailu Helm chart defaults (relay-username, relay-password)
+  #
+  relay-username: "MS_d34ZtW@bakewise.ai"
+  relay-password: "mssp.Z6GRHQ8.zr6ke4nvq6egon12.IDyvEi7"

infrastructure/platform/mail/mailu-helm/configs/mailgun-credentials-secret.yaml

@@ -1,94 +0,0 @@
-# Mailgun SMTP Credentials Secret for Mailu
-#
-# This secret stores Mailgun credentials for outbound email relay.
-# Mailu uses Mailgun as an external SMTP relay to send all outbound emails.
-#
-# ============================================================================
-# HOW TO CONFIGURE:
-# ============================================================================
-#
-# 1. Go to https://www.mailgun.com and create an account
-#
-# 2. Add and verify your domain:
-#    - For dev: bakery-ia.dev
-#    - For prod: bakewise.ai
-#
-# 3. Go to Domain Settings > SMTP credentials in Mailgun dashboard
-#
-# 4. Note your SMTP credentials:
-#    - SMTP hostname: smtp.mailgun.org
-#    - Port: 587 (TLS/STARTTLS)
-#    - Username: typically postmaster@yourdomain.com
-#    - Password: your Mailgun SMTP password (NOT the API key)
-#
-# 5. Base64 encode your credentials:
-#    echo -n 'postmaster@bakewise.ai' | base64
-#    echo -n 'your-mailgun-smtp-password' | base64
-#
-# 6. Replace the placeholder values below with your encoded credentials
-#
-# 7. Apply this secret:
-#    kubectl apply -f mailgun-credentials-secret.yaml -n bakery-ia
-#
-# ============================================================================
-# IMPORTANT NOTES:
-# ============================================================================
-#
-# - Use the SMTP password from Mailgun, NOT the API key
-# - The username format is: postmaster@yourdomain.com
-# - For sandbox domains, Mailgun requires adding authorized recipients
-# - Production domains need DNS verification (SPF, DKIM records)
-#
-# ============================================================================
-# DNS RECORDS REQUIRED FOR MAILGUN:
-# ============================================================================
-#
-# Add these DNS records to your domain for proper email delivery:
-#
-# 1. SPF Record (TXT):
-#    Name: @
-#    Value: v=spf1 include:mailgun.org ~all
-#
-# 2. DKIM Records (TXT):
-#    Mailgun will provide two DKIM keys to add as TXT records
-#    (check your Mailgun domain settings for exact values)
-#
-# 3. MX Records (optional, only if receiving via Mailgun):
-#    Priority 10: mxa.mailgun.org
-#    Priority 10: mxb.mailgun.org
-#
-# ============================================================================
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: mailu-mailgun-credentials
-  namespace: bakery-ia
-  labels:
-    app: mailu
-    component: external-relay
-  annotations:
-    description: "Mailgun SMTP credentials for Mailu external relay"
-type: Opaque
-stringData:
-  # ============================================================================
-  # REPLACE THESE VALUES WITH YOUR MAILGUN CREDENTIALS
-  # ============================================================================
-  #
-  # Option 1: Use stringData (plain text - Kubernetes will encode automatically)
-  # This is easier for initial setup but shows credentials in the file
-  #
-  RELAY_USERNAME: "postmaster@sandboxc1bff891532b4f0c83056a68ae080b4c.mailgun.org"
-  RELAY_PASSWORD: "2e47104abadad8eb820d00042ea6d5eb-77c6c375-89c7ea55"
-  #
-  # ============================================================================
-  # ALTERNATIVE: Use pre-encoded values (more secure for version control)
-  # ============================================================================
-  # Comment out stringData above and uncomment data below:
-  #
-  # data:
-  #   # Base64 encoded values
-  #   # echo -n 'postmaster@bakewise.ai' | base64
-  #   RELAY_USERNAME: cG9zdG1hc3RlckBiYWtld2lzZS5haQ==
-  #   # echo -n 'your-password' | base64
-  #   RELAY_PASSWORD: WU9VUl9NQUlMR1VOX1NNVFBfUEFTU1dPUkQ=

infrastructure/platform/mail/mailu-helm/dev/mailu-ingress.yaml

@@ -6,6 +6,7 @@ metadata:
   labels:
     app.kubernetes.io/name: mailu
     app.kubernetes.io/component: ingress
+    environment: development
   annotations:
     nginx.ingress.kubernetes.io/proxy-body-size: "100m"
     nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
@@ -26,6 +27,6 @@ spec:
         pathType: Prefix
         backend:
           service:
-            name: mailu-front  # Helm release name 'mailu' + component 'front'
+            name: mailu-front
             port:
-              number: 80
+              number: 80

infrastructure/platform/mail/mailu-helm/dev/values.yaml

@@ -1,31 +1,19 @@
 # Development-tuned Mailu configuration
 global:
-  # Using Unbound DNS for DNSSEC validation (required by Mailu admin)
+  # Using Kubernetes CoreDNS for DNS resolution
-  # Unbound service is available at unbound-dns.bakery-ia.svc.cluster.local
+  # CoreDNS is configured with DNS-over-TLS (Cloudflare) for DNSSEC validation
-  # Static ClusterIP configured in unbound-helm/values.yaml
+  # Default to Kubernetes DNS IP (will be overridden dynamically if needed)
-  custom_dns_servers: "10.96.53.53"  # Unbound DNS static ClusterIP
+  custom_dns_servers: "10.96.0.10"  # Kubernetes DNS IP
 
 # Redis configuration - use built-in Mailu Redis (no authentication needed)
 externalRedis:
   enabled: false
 
-# Component-specific DNS configuration
+# DNS configuration - use Kubernetes DNS (ClusterFirst)
-# Admin requires DNSSEC validation - use Unbound DNS (forwards cluster.local to kube-dns)
+# CoreDNS provides DNSSEC validation via DNS-over-TLS to Cloudflare
 admin:
-  dnsPolicy: "None"
+  dnsPolicy: "ClusterFirst"
-  dnsConfig:
-    nameservers:
-      - "10.96.53.53"   # Unbound DNS static ClusterIP (forwards cluster.local to kube-dns)
-    searches:
-      - "bakery-ia.svc.cluster.local"
-      - "svc.cluster.local"
-      - "cluster.local"
-    options:
-      - name: ndots
-        value: "5"
 
-# RSPAMD needs Unbound for DNSSEC validation (DKIM/SPF/DMARC checks)
-# Using ClusterFirst with search domains + Kubernetes DNS which can forward to Unbound
 rspamd:
   dnsPolicy: "ClusterFirst"
 
@@ -56,9 +44,18 @@ initialAccount:
 externalRelay:
   host: "[smtp.mailgun.org]:587"
   # Credentials loaded from Kubernetes secret
-  secretName: "mailu-mailgun-credentials"
+  # Key names use Helm chart defaults: relay-username, relay-password
-  usernameKey: "RELAY_USERNAME"
+  existingSecret: "mailu-mailgun-credentials"
-  passwordKey: "RELAY_PASSWORD"
+
+# Postfix configuration
+# CRITICAL: podAnnotations ensures Postfix restarts when credentials change
+# Without this, Mailu reads SASL credentials only at pod startup and won't pick up secret updates
+postfix:
+  podAnnotations:
+    # UPDATE THIS VALUE when changing mailu-mailgun-credentials secret
+    # This triggers a rolling restart of Postfix to reload SASL credentials
+    # Generate new value: date +%s or use the secret's resourceVersion
+    credentials-version: "1706054400"
 
 # Environment-specific configurations
 persistence:

infrastructure/platform/mail/mailu-helm/prod/mailu-ingress.yaml

@@ -0,0 +1,68 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: mailu-ingress
+  namespace: bakery-ia
+  labels:
+    app.kubernetes.io/name: mailu
+    app.kubernetes.io/component: ingress
+    environment: production
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-production
+    # Proxy settings for large attachments and long connections
+    nginx.ingress.kubernetes.io/proxy-body-size: "100m"
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-connect-timeout: "60"
+    # SSL redirect
+    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    # CRITICAL: Disable proxy buffering for webmail streaming/long-polling
+    # This prevents the "stuck loading" issue with Roundcube webmail
+    # Reference: https://github.com/Mailu/Mailu/issues/2850
+    nginx.ingress.kubernetes.io/proxy-buffering: "off"
+    nginx.ingress.kubernetes.io/proxy-request-buffering: "off"
+    # WebSocket support for webmail real-time features
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+    nginx.ingress.kubernetes.io/upstream-hash-by: "$remote_addr"
+    # CRITICAL: Configuration snippet for Mailu header handling
+    # Fixes redirect loops by ensuring Mailu sees the correct protocol
+    # Reference: https://mailu.io/2.0/reverse.html
+    nginx.ingress.kubernetes.io/configuration-snippet: |
+      # CRITICAL: Force X-Forwarded-Proto to https to prevent redirect loops
+      # Mailu's internal nginx checks this header to decide if redirect is needed
+      proxy_set_header X-Forwarded-Proto https;
+      proxy_set_header X-Forwarded-Port 443;
+      proxy_set_header X-Forwarded-Ssl on;
+
+      # Real IP headers for Mailu logging and rate limiting
+      proxy_set_header Host $host;
+      proxy_set_header X-Real-IP $remote_addr;
+      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+
+      # Fix redirects from Mailu internal services (admin, webmail)
+      # Don't add trailing slash to prevent 404 on redirects
+      proxy_redirect http://localhost https://$host;
+      proxy_redirect https://localhost https://$host;
+      proxy_redirect http://$host https://$host;
+
+      # Disable buffering for streaming responses (webmail)
+      proxy_buffering off;
+      proxy_cache off;
+spec:
+  ingressClassName: nginx
+  tls:
+  - hosts:
+    - mail.bakewise.ai
+    secretName: bakery-ia-prod-tls-cert
+  rules:
+  - host: mail.bakewise.ai
+    http:
+      paths:
+      - path: /
+        pathType: Prefix
+        backend:
+          service:
+            name: mailu-front
+            port:
+              number: 80

infrastructure/platform/mail/mailu-helm/prod/values.yaml

@@ -1,15 +1,15 @@
 # Production-tuned Mailu configuration
 global:
-  # Using Kubernetes cluster DNS for name resolution
+  # Using Kubernetes CoreDNS for DNS resolution
-  custom_dns_servers: "10.96.0.10"  # Kubernetes cluster DNS IP
+  # CoreDNS is configured with DNS-over-TLS (Cloudflare) for DNSSEC validation
+  custom_dns_servers: "10.152.183.10"  # MicroK8s CoreDNS IP
 
 # Redis configuration - use built-in Mailu Redis (no authentication needed for internal)
 externalRedis:
   enabled: false
 
 # DNS configuration for production
-# Use Kubernetes DNS (ClusterFirst) which forwards to Unbound via CoreDNS
+# Use Kubernetes DNS (ClusterFirst) - CoreDNS provides DNSSEC via DNS-over-TLS
-# This is configured automatically by the mailu-helm Tilt resource
 admin:
   dnsPolicy: "ClusterFirst"
 
@@ -21,6 +21,11 @@ domain: "bakewise.ai"
 hostnames:
   - "mail.bakewise.ai"
 
+# Network configuration for MicroK8s
+# This must match your cluster's pod CIDR
+# MicroK8s default is 10.1.0.0/16, but check with: kubectl cluster-info dump | grep -m 1 cluster-cidr
+subnet: "10.1.0.0/16"
+
 # Initial admin account for production environment
 # Password is stored in mailu-admin-credentials secret
 initialAccount:
@@ -31,25 +36,30 @@ initialAccount:
   existingSecretPasswordKey: "password"
   mode: "ifmissing"
 
-# External relay configuration for production (Mailgun)
+# External relay configuration for production (MailerSend)
-# All outbound emails will be relayed through Mailgun SMTP
+# All outbound emails will be relayed through MailerSend SMTP
-# To configure:
+# Secret already exists: mailu-mailersend-credentials
-#   1. Register at mailgun.com and verify your domain (bakewise.ai)
-#   2. Get your SMTP credentials from Mailgun dashboard
-#   3. Update the secret in configs/mailgun-credentials-secret.yaml
-#   4. Apply the secret: kubectl apply -f configs/mailgun-credentials-secret.yaml -n bakery-ia
 externalRelay:
-  host: "[smtp.mailgun.org]:587"
+  host: "[smtp.mailersend.net]:2525"
-  # Credentials loaded from Kubernetes secret
+  # Credentials loaded from existing Kubernetes secret
-  secretName: "mailu-mailgun-credentials"
+  # Key names use Helm chart defaults (relay-username, relay-password)
-  usernameKey: "RELAY_USERNAME"
+  existingSecret: "mailu-mailersend-credentials"
-  passwordKey: "RELAY_PASSWORD"
+
+# Postfix configuration
+# CRITICAL: podAnnotations ensures Postfix restarts when credentials change
+# Without this, Mailu reads SASL credentials only at pod startup and won't pick up secret updates
+postfix:
+  podAnnotations:
+    # UPDATE THIS VALUE when changing mailu-mailersend-credentials secret
+    # This triggers a rolling restart of Postfix to reload SASL credentials
+    # Generate new value: date +%s or use the secret's resourceVersion
+    credentials-version: "1706054400"
 
 # Environment-specific configurations
 persistence:
   enabled: true
-  # Production: use microk8s-hostpath or longhorn
+  # Production: use microk8s-hostpath (default storage class)
-  storageClass: "longhorn"  # Assuming Longhorn is available in production
+  storageClass: ""  # Use cluster default storage class
   size: "20Gi"  # Larger storage for production email volume
 
 # Resource allocations for production
@@ -103,18 +113,24 @@ replicaCount: 1  # Can be increased in production as needed
 secretKey: "generate-strong-key-here-for-production"
 
 # Ingress configuration for production - disabled to use with existing ingress
+# External nginx-ingress handles TLS termination and proxies to Mailu front
 ingress:
-  enabled: false  # Disable chart's Ingress; use existing one
+  enabled: false  # Disable chart's Ingress; use existing mailu-ingress.yaml
   tls: false      # Disable TLS in chart since ingress handles it
-  tlsFlavorOverride: notls  # No TLS on internal NGINX; expect external proxy to handle TLS
+  tlsFlavorOverride: notls  # No TLS on internal NGINX; external ingress handles TLS
-  realIpHeader: X-Forwarded-For  # Header for client IP from your Ingress
+  # CRITICAL: Real IP header configuration for proper client IP detection
-  realIpFrom: 0.0.0.0/0  # Trust all proxies (restrict to your Ingress pod CIDR for security)
+  # This must match the header set by nginx-ingress (X-Real-IP)
+  # Reference: https://mailu.io/2.0/reverse.html
+  realIpHeader: X-Real-IP
+  realIpFrom: "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"  # Trust cluster pod CIDRs
   path: /
   pathType: ImplementationSpecific
 
-# TLS flavor for production (uses Let's Encrypt)
+# TLS flavor for production
+# "notls" because external ingress handles TLS termination
+# The ingress sends X-Forwarded-Proto: https to tell Mailu the original protocol
 tls:
-  flavor: "cert"
+  flavor: "notls"
 
 # Welcome message (enabled in production)
 welcomeMessage:
@@ -130,12 +146,31 @@ antivirus:
   enabled: true
   flavor: "clamav"
 
-# Production-specific settings
+# Production-specific environment settings
+# CRITICAL: These must be consistent with the ingress/proxy setup
 env:
   DEBUG: "false"
-  LOG_LEVEL: "WARNING"
+  LOG_LEVEL: "INFO"  # Temporarily set to INFO for debugging
-  TLS_FLAVOR: "cert"
+  # TLS_FLAVOR must be "notls" when using external reverse proxy for TLS termination
-  REDIS_PASSWORD: "secure-redis-password"
+  # The ingress handles TLS and sends X-Forwarded-Proto: https
+  TLS_FLAVOR: "notls"
+  # Session cookie settings for reverse proxy setup
+  # SESSION_COOKIE_SECURE must be True since we're serving over HTTPS (via ingress)
+  SESSION_COOKIE_SECURE: "true"
+  # Increase session timeout to prevent premature logouts
+  SESSION_TIMEOUT: "3600"
+  PERMANENT_SESSION_LIFETIME: "108000"
+  # CRITICAL: Tell Mailu it's behind a reverse proxy
+  # This ensures proper URL generation for redirects
+  PROXY_PROTOCOL: "false"
+  # Trust the ingress controller's IP for real IP headers
+  REAL_IP_HEADER: "X-Real-IP"
+  REAL_IP_FROM: "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"
+  # CRITICAL: Disable rate limiting temporarily to debug the sso.php redirect loop
+  # Reference: https://github.com/Mailu/Mailu/issues/3094
+  # The webmail can get rate-limited causing infinite redirect loops
+  AUTH_RATELIMIT_IP: "10000/minute"
+  AUTH_RATELIMIT_USER: "10000/day"
 
 # Enable monitoring in production
 monitoring:
@@ -148,15 +183,14 @@ securityContext:
   fsGroup: 1000
 
 # Network policies for production
+# Note: MicroK8s uses 'ingress' namespace, not 'ingress-nginx'
 networkPolicy:
   enabled: true
   ingressController:
-    namespace: ingress-nginx
+    namespace: ingress
     podSelector: |
       matchLabels:
-        app.kubernetes.io/name: ingress-nginx
+        name: nginx-ingress-microk8s
-        app.kubernetes.io/instance: ingress-nginx
-        app.kubernetes.io/component: controller
   monitoring:
     namespace: monitoring
     podSelector: |

infrastructure/platform/mail/mailu-helm/scripts/deploy-mailu-prod.sh

@@ -4,11 +4,10 @@
 # =============================================================================
 # This script automates the deployment of Mailu mail server for production.
 # It handles:
-#   1. Unbound DNS deployment (for DNSSEC validation)
+#   1. CoreDNS configuration with DNS-over-TLS for DNSSEC validation
-#   2. CoreDNS configuration (forward to Unbound)
+#   2. TLS certificate secret creation
-#   3. TLS certificate secret creation
+#   3. Admin credentials secret creation
-#   4. Admin credentials secret creation
+#   4. Mailu Helm deployment (admin user created automatically via initialAccount)
-#   5. Mailu Helm deployment (admin user created automatically via initialAccount)
 #
 # Usage:
 #   ./deploy-mailu-prod.sh [--domain DOMAIN] [--admin-password PASSWORD]
@@ -99,52 +98,15 @@ fi
 print_success "Prerequisites check passed"
 
 # =============================================================================
-# Step 1: Deploy Unbound DNS Resolver
+# Step 1: Configure CoreDNS with DNS-over-TLS for DNSSEC
 # =============================================================================
-print_step "Step 1: Deploying Unbound DNS resolver..."
+print_step "Step 1: Configuring CoreDNS with DNS-over-TLS for DNSSEC validation..."
 
-if kubectl get deployment unbound -n "$NAMESPACE" &>/dev/null; then
+# Check if CoreDNS is already configured with DNS-over-TLS
-    print_success "Unbound already deployed"
+CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' 2>/dev/null | grep -o 'tls://1.1.1.1' || echo "")
-else
-    helm upgrade --install unbound "$MAILU_HELM_DIR/../../networking/dns/unbound-helm" \
-        -n "$NAMESPACE" \
-        -f "$MAILU_HELM_DIR/../../networking/dns/unbound-helm/values.yaml" \
-        -f "$MAILU_HELM_DIR/../../networking/dns/unbound-helm/prod/values.yaml" \
-        --timeout 5m \
-        --wait
 
-    print_success "Unbound deployed"
+if [ -z "$CURRENT_FORWARD" ]; then
-fi
+    echo "Updating CoreDNS to use DNS-over-TLS with Cloudflare for DNSSEC validation..."
-
-# Wait for Unbound to be ready
-kubectl wait --for=condition=ready pod -l app.kubernetes.io/name=unbound -n "$NAMESPACE" --timeout=120s
-
-# Get Unbound service IP (dynamic resolution)
-echo "Waiting for Unbound service to get assigned IP..."
-for i in {1..30}; do
-    UNBOUND_IP=$(kubectl get svc unbound-dns -n "$NAMESPACE" -o jsonpath='{.spec.clusterIP}' 2>/dev/null || echo "")
-    if [ -n "$UNBOUND_IP" ] && [ "$UNBOUND_IP" != "<none>" ]; then
-        echo "Unbound DNS service IP: $UNBOUND_IP"
-        break
-    fi
-    if [ $i -eq 30 ]; then
-        print_error "Failed to get Unbound service IP"
-        exit 1
-    fi
-    sleep 2
-    echo "Waiting for Unbound service IP... (attempt $i/30)"
-done
-
-# =============================================================================
-# Step 2: Configure CoreDNS to Forward to Unbound
-# =============================================================================
-print_step "Step 2: Configuring CoreDNS for DNSSEC validation..."
-
-# Check current CoreDNS forward configuration
-CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'forward \. [0-9.]*' | awk '{print $3}' || echo "")
-
-if [ "$CURRENT_FORWARD" != "$UNBOUND_IP" ]; then
-    echo "Updating CoreDNS to forward to Unbound ($UNBOUND_IP)..."
 
     # Create a temporary file with the CoreDNS configuration
     TEMP_COREFILE=$(mktemp)
@@ -161,8 +123,9 @@ if [ "$CURRENT_FORWARD" != "$UNBOUND_IP" ]; then
        ttl 30
     }
     prometheus :9153
-    forward . $UNBOUND_IP {
+    forward . tls://1.1.1.1 tls://1.0.0.1 {
-       max_concurrent 1000
+       tls_servername cloudflare-dns.com
+       health_check 5s
     }
     cache 30 {
        disable success cluster.local
@@ -187,15 +150,19 @@ EOF
     kubectl rollout restart deployment coredns -n kube-system
     kubectl rollout status deployment coredns -n kube-system --timeout=60s
 
-    print_success "CoreDNS configured to forward to Unbound"
+    print_success "CoreDNS configured with DNS-over-TLS for DNSSEC validation"
 else
-    print_success "CoreDNS already configured for Unbound"
+    print_success "CoreDNS already configured with DNS-over-TLS"
 fi
 
+# Get CoreDNS service IP for Mailu configuration
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+echo "CoreDNS service IP: $COREDNS_IP"
+
 # =============================================================================
-# Step 3: Create TLS Certificate Secret
+# Step 2: Create TLS Certificate Secret
 # =============================================================================
-print_step "Step 3: Creating TLS certificate secret..."
+print_step "Step 2: Creating TLS certificate secret..."
 
 if kubectl get secret mailu-certificates -n "$NAMESPACE" &>/dev/null; then
     print_success "TLS certificate secret already exists"
@@ -217,9 +184,9 @@ else
 fi
 
 # =============================================================================
-# Step 4: Create Admin Credentials Secret
+# Step 3: Create Admin Credentials Secret
 # =============================================================================
-print_step "Step 4: Creating admin credentials secret..."
+print_step "Step 3: Creating admin credentials secret..."
 
 if kubectl get secret mailu-admin-credentials -n "$NAMESPACE" &>/dev/null; then
     print_success "Admin credentials secret already exists"
@@ -243,33 +210,28 @@ else
 fi
 
 # =============================================================================
-# Step 5: Deploy Mailu via Helm
+# Step 4: Deploy Mailu via Helm
 # =============================================================================
-print_step "Step 5: Deploying Mailu via Helm..."
+print_step "Step 4: Deploying Mailu via Helm..."
 
 # Add Mailu Helm repository
 helm repo add mailu https://mailu.github.io/helm-charts 2>/dev/null || true
 helm repo update mailu
 
-# Create temporary values file with dynamic DNS server
+# Deploy Mailu with CoreDNS configuration
-TEMP_VALUES=$(mktemp)
-cat "$MAILU_HELM_DIR/values.yaml" | sed "s/# custom_dns_servers: \"\"  # Will be set dynamically by deployment script/custom_dns_servers: \"$UNBOUND_IP\"/" > "$TEMP_VALUES"
-
-# Deploy Mailu with dynamic DNS configuration
 helm upgrade --install mailu mailu/mailu \
     -n "$NAMESPACE" \
-    -f "$TEMP_VALUES" \
+    -f "$MAILU_HELM_DIR/values.yaml" \
     -f "$MAILU_HELM_DIR/prod/values.yaml" \
+    --set global.custom_dns_servers="$COREDNS_IP" \
     --timeout 10m
 
-rm -f "$TEMP_VALUES"
-
 print_success "Mailu Helm release deployed (admin user will be created automatically)"
 
 # =============================================================================
-# Step 6: Wait for Pods to be Ready
+# Step 5: Wait for Pods to be Ready
 # =============================================================================
-print_step "Step 6: Waiting for Mailu pods to be ready..."
+print_step "Step 5: Waiting for Mailu pods to be ready..."
 
 echo "This may take 5-10 minutes (ClamAV takes time to initialize)..."
 
@@ -307,10 +269,27 @@ echo "  Webmail:     https://mail.$DOMAIN/webmail"
 echo "  SMTP:        mail.$DOMAIN:587 (STARTTLS)"
 echo "  IMAP:        mail.$DOMAIN:993 (SSL)"
 echo ""
+echo "DNS Configuration:"
+echo "  CoreDNS is configured with DNS-over-TLS (Cloudflare) for DNSSEC validation"
+echo "  CoreDNS IP: $COREDNS_IP"
+echo ""
 echo "Next Steps:"
-echo "  1. Configure DNS records (A, MX, SPF, DMARC)"
+echo "  1. Configure MailerSend:"
-echo "  2. Get DKIM key: kubectl exec -n $NAMESPACE deployment/mailu-admin -- cat /dkim/$DOMAIN.dkim.pub"
+echo "     - Sign up at https://accounts.mailersend.com/signup"
-echo "  3. Add DKIM TXT record to DNS"
+echo "     - Add domain '$DOMAIN' and verify DNS records"
+echo "     - Generate SMTP credentials (Email -> Domains -> SMTP)"
+echo "     - Update secret: kubectl edit secret mailu-mailersend-credentials -n $NAMESPACE"
+echo ""
+echo "  2. Configure DNS records in Cloudflare for '$DOMAIN':"
+echo "     - A record: mail -> <your-server-IP>"
+echo "     - MX record: @ -> mail.$DOMAIN (priority 10)"
+echo "     - TXT (SPF): @ -> v=spf1 include:mailersend.net ~all"
+echo "     - TXT (DKIM): mlsend._domainkey -> <from MailerSend dashboard>"
+echo "     - TXT (DMARC): _dmarc -> v=DMARC1; p=quarantine; rua=mailto:admin@$DOMAIN"
+echo ""
+echo "  3. Get Mailu DKIM key (for direct sending):"
+echo "     kubectl exec -n $NAMESPACE deployment/mailu-admin -- cat /dkim/$DOMAIN.dkim.pub"
+echo ""
 echo "  4. Configure Ingress for mail.$DOMAIN"
 echo ""
 echo "To check pod status:"

infrastructure/platform/mail/mailu-helm/scripts/deploy-phase7-fixed.sh

@@ -3,16 +3,13 @@
 # Phase 7: Deploy Optional Services - Fixed Version
 # =============================================================================
 # This script deploys the optional services for production:
-# 1. Unbound DNS (with dynamic IP resolution)
+# 1. CoreDNS configuration with DNS-over-TLS for DNSSEC validation
-# 2. CoreDNS configuration for DNSSEC
+# 2. Mailu Email Server
-# 3. Mailu Email Server
+# 3. SigNoz Monitoring
-# 4. SigNoz Monitoring
 #
-# Fixed issues:
+# DNS Architecture:
-# - Removed static ClusterIP that caused CIDR range conflicts
+# - CoreDNS uses DNS-over-TLS with Cloudflare (1.1.1.1) for DNSSEC validation
-# - Implemented dynamic IP resolution for Unbound DNS
+# - Mailu uses CoreDNS for DNS resolution (internal K8s + external DNSSEC)
-# - Updated CoreDNS patching to use dynamic IP
-# - Updated Mailu configuration to use dynamic DNS server
 # =============================================================================
 
 set -e
@@ -40,49 +37,15 @@ print_success() {
 }
 
 # =============================================================================
-# Step 7.1: Deploy Unbound DNS (with dynamic IP)
+# Step 7.1: Configure CoreDNS with DNS-over-TLS for DNSSEC
 # =============================================================================
-print_step "Step 7.1: Deploying Unbound DNS resolver (dynamic IP)..."
+print_step "Step 7.1: Configuring CoreDNS with DNS-over-TLS for DNSSEC validation..."
 
-if kubectl get deployment unbound -n "$NAMESPACE" &>/dev/null; then
+# Check if CoreDNS is already configured with DNS-over-TLS
-    print_success "Unbound already deployed"
+CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' 2>/dev/null | grep -o 'tls://1.1.1.1' || echo "")
-else
-    helm upgrade --install unbound infrastructure/platform/networking/dns/unbound-helm \
-        -n "$NAMESPACE" \
-        -f infrastructure/platform/networking/dns/unbound-helm/values.yaml \
-        -f infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml \
-        --timeout 5m \
-        --wait
-    
-    print_success "Unbound deployed"
-fi
 
-# Wait for Unbound service to get assigned IP
+if [ -z "$CURRENT_FORWARD" ]; then
-print_step "Waiting for Unbound service to get assigned IP..."
+    echo "Updating CoreDNS to use DNS-over-TLS with Cloudflare..."
-for i in {1..30}; do
-    UNBOUND_IP=$(kubectl get svc unbound-dns -n "$NAMESPACE" -o jsonpath='{.spec.clusterIP}' 2>/dev/null || echo "")
-    if [ -n "$UNBOUND_IP" ] && [ "$UNBOUND_IP" != "<none>" ]; then
-        echo "Unbound DNS service IP: $UNBOUND_IP"
-        break
-    fi
-    if [ $i -eq 30 ]; then
-        print_error "Failed to get Unbound service IP"
-        exit 1
-    fi
-    sleep 2
-    echo "Waiting for Unbound service IP... (attempt $i/30)"
-done
-
-# =============================================================================
-# Step 7.2: Configure CoreDNS for DNSSEC (dynamic IP)
-# =============================================================================
-print_step "Step 7.2: Configuring CoreDNS for DNSSEC validation..."
-
-# Check current CoreDNS forward configuration
-CURRENT_FORWARD=$(kubectl get configmap coredns -n kube-system -o jsonpath='{.data.Corefile}' | grep -o 'forward \. [0-9.]*' | awk '{print $3}' || echo "")
-
-if [ "$CURRENT_FORWARD" != "$UNBOUND_IP" ]; then
-    echo "Updating CoreDNS to forward to Unbound ($UNBOUND_IP)..."
 
     # Create a temporary file with the CoreDNS configuration
     TEMP_COREFILE=$(mktemp)
@@ -99,8 +62,9 @@ if [ "$CURRENT_FORWARD" != "$UNBOUND_IP" ]; then
        ttl 30
     }
     prometheus :9153
-    forward . $UNBOUND_IP {
+    forward . tls://1.1.1.1 tls://1.0.0.1 {
-       max_concurrent 1000
+       tls_servername cloudflare-dns.com
+       health_check 5s
     }
     cache 30 {
        disable success cluster.local
@@ -125,33 +89,32 @@ EOF
     kubectl rollout restart deployment coredns -n kube-system
     kubectl rollout status deployment coredns -n kube-system --timeout=60s
 
-    print_success "CoreDNS configured to forward to Unbound"
+    print_success "CoreDNS configured with DNS-over-TLS"
 else
-    print_success "CoreDNS already configured for Unbound"
+    print_success "CoreDNS already configured with DNS-over-TLS"
 fi
 
+# Get CoreDNS service IP
+COREDNS_IP=$(kubectl get svc kube-dns -n kube-system -o jsonpath='{.spec.clusterIP}')
+echo "CoreDNS service IP: $COREDNS_IP"
+
 # =============================================================================
-# Step 7.3: Deploy Mailu Email Server (dynamic DNS)
+# Step 7.2: Deploy Mailu Email Server
 # =============================================================================
-print_step "Step 7.3: Deploying Mailu Email Server..."
+print_step "Step 7.2: Deploying Mailu Email Server..."
 
 # Add Mailu Helm repository
 helm repo add mailu https://mailu.github.io/helm-charts 2>/dev/null || true
 helm repo update mailu
 
-# Create temporary values file with dynamic DNS server
+# Deploy Mailu with CoreDNS configuration
-TEMP_VALUES=$(mktemp)
-cat infrastructure/platform/mail/mailu-helm/values.yaml | sed "s/# custom_dns_servers: \"\"  # Will be set dynamically by deployment script/custom_dns_servers: \"$UNBOUND_IP\"/" > "$TEMP_VALUES"
-
-# Deploy Mailu with dynamic DNS configuration
 helm upgrade --install mailu mailu/mailu \
     -n "$NAMESPACE" \
-    -f "$TEMP_VALUES" \
+    -f infrastructure/platform/mail/mailu-helm/values.yaml \
     -f infrastructure/platform/mail/mailu-helm/prod/values.yaml \
+    --set global.custom_dns_servers="$COREDNS_IP" \
     --timeout 10m
 
-rm -f "$TEMP_VALUES"
-
 print_success "Mailu Helm release deployed"
 
 # Wait for Mailu pods to be ready
@@ -165,9 +128,9 @@ kubectl wait --for=condition=ready pod -l app.kubernetes.io/component=admin -n "
 print_success "Mailu deployment completed"
 
 # =============================================================================
-# Step 7.4: Deploy SigNoz Monitoring
+# Step 7.3: Deploy SigNoz Monitoring
 # =============================================================================
-print_step "Step 7.4: Deploying SigNoz Monitoring..."
+print_step "Step 7.3: Deploying SigNoz Monitoring..."
 
 # Add SigNoz Helm repository
 helm repo add signoz https://charts.signoz.io 2>/dev/null || true
@@ -196,9 +159,8 @@ echo -e "${GREEN}Phase 7 Deployment Complete!${NC}"
 echo "=============================================="
 echo ""
 echo "Deployed Services:"
-echo "  ✓ Unbound DNS (IP: $UNBOUND_IP)"
+echo "  ✓ CoreDNS (configured with DNS-over-TLS for DNSSEC)"
-echo "  ✓ CoreDNS (configured for DNSSEC)"
+echo "  ✓ Mailu Email Server (using CoreDNS IP: $COREDNS_IP)"
-echo "  ✓ Mailu Email Server"
 echo "  ✓ SigNoz Monitoring"
 echo ""
 echo "Next Steps:"

infrastructure/platform/mail/mailu-helm/values.yaml

@@ -3,8 +3,8 @@
 
 # Global DNS configuration for DNSSEC validation
 global:
-  # Using Unbound DNS resolver directly for DNSSEC validation
+  # Using Kubernetes CoreDNS with DNS-over-TLS for DNSSEC validation
-  # Unbound service is available at unbound-dns.bakery-ia.svc.cluster.local
+  # CoreDNS is configured to forward external queries to Cloudflare (tls://1.1.1.1)
   # DNS server IP will be dynamically resolved during deployment
   # custom_dns_servers: ""  # Will be set dynamically by deployment script
 
@@ -50,15 +50,15 @@ limits:
   messageRatelimit:
     value: "200/day"
 
-# External relay configuration (Mailgun)
+# External relay configuration (MailerSend)
-# Mailu will relay all outbound emails through Mailgun SMTP
+# Mailu will relay all outbound emails through MailerSend SMTP
 # Credentials are loaded from Kubernetes secret for security
+# MailerSend requires TLS 1.2+ (supported by default on port 587)
 externalRelay:
-  host: "[smtp.mailgun.org]:587"
+  host: "[smtp.mailersend.net]:587"
   # Use existing secret for credentials (recommended for security)
-  secretName: "mailu-mailgun-credentials"
+  # Key names use Helm chart defaults: relay-username, relay-password
-  usernameKey: "RELAY_USERNAME"
+  existingSecret: "mailu-mailersend-credentials"
-  passwordKey: "RELAY_PASSWORD"
 
 # Webmail configuration
 webmail:
@@ -218,18 +218,17 @@ rspamd:
       memory: 1Gi
 
 # Network Policy
+# Note: MicroK8s uses 'ingress' namespace with different labels
+# For standard nginx-ingress, use namespace: ingress-nginx
 networkPolicy:
   enabled: true
   ingressController:
-    namespace: ingress-nginx
+    namespace: ingress
     podSelector: |
       matchLabels:
-        app.kubernetes.io/name: ingress-nginx
+        name: nginx-ingress-microk8s
-        app.kubernetes.io/instance: ingress-nginx
-        app.kubernetes.io/component: controller
 
 # DNS Policy Configuration
 # Use Kubernetes DNS (ClusterFirst) for internal service resolution
-# DNSSEC validation for email is handled by rspamd component
+# DNSSEC validation is provided by CoreDNS with DNS-over-TLS (Cloudflare)
-# Note: For production with DNSSEC needs, configure CoreDNS to forward to Unbound
 dnsPolicy: "ClusterFirst"

infrastructure/platform/networking/dns/unbound-helm/Chart.yaml

@@ -1,18 +0,0 @@
-apiVersion: v2
-name: unbound
-description: A Helm chart for deploying Unbound DNS resolver for Bakery-IA
-type: application
-version: 0.1.0
-appVersion: "1.19.1"
-maintainers:
-  - name: Bakery-IA Team
-    email: devops@bakery-ia.com
-keywords:
-  - dns
-  - resolver
-  - caching
-  - unbound
-home: https://www.nlnetlabs.nl/projects/unbound/
-sources:
-  - https://github.com/NLnetLabs/unbound
-  - https://hub.docker.com/r/mvance/unbound

infrastructure/platform/networking/dns/unbound-helm/dev/values.yaml

@@ -1,64 +0,0 @@
-# Development values for unbound DNS resolver
-# Using same configuration as production for consistency
-
-# Use official image for development (same as production)
-image:
-  repository: "mvance/unbound"
-  tag: "latest"
-  pullPolicy: "IfNotPresent"
-
-# Resource settings (slightly lower than production for dev)
-resources:
-  requests:
-    cpu: "100m"
-    memory: "128Mi"
-  limits:
-    cpu: "300m"
-    memory: "384Mi"
-
-# Single replica for development (can be scaled if needed)
-replicaCount: 1
-
-# Development annotations
-podAnnotations:
-  environment: "development"
-  managed-by: "helm"
-
-# Probe settings (same as production but slightly faster)
-probes:
-  readiness:
-    initialDelaySeconds: 10
-    periodSeconds: 30
-    command: "drill @127.0.0.1 -p 53 example.org || echo 'DNS query test'"
-  liveness:
-    initialDelaySeconds: 30
-    periodSeconds: 60
-    command: "drill @127.0.0.1 -p 53 example.org || echo 'DNS query test'"
-
-# Custom Unbound forward records for Kubernetes DNS
-config:
-  enabled: true
-  # The mvance/unbound image includes forward-records.conf
-  # We need to add Kubernetes-specific forwarding zones
-  forwardRecords: |
-    # Forward all queries to Cloudflare with DNSSEC (catch-all)
-    forward-zone:
-        name: "."
-        forward-tls-upstream: yes
-        forward-addr: 1.1.1.1@853#cloudflare-dns.com
-        forward-addr: 1.0.0.1@853#cloudflare-dns.com
-
-  # Additional server config to mark cluster.local as insecure (no DNSSEC)
-  # and use stub zones for Kubernetes internal DNS (more reliable than forward)
-  serverConfig: |
-    domain-insecure: "cluster.local."
-    private-domain: "cluster.local."
-    local-zone: "10.in-addr.arpa." nodefault
-
-    stub-zone:
-        name: "cluster.local."
-        stub-addr: 10.96.0.10
-
-    stub-zone:
-        name: "10.in-addr.arpa."
-        stub-addr: 10.96.0.10

infrastructure/platform/networking/dns/unbound-helm/prod/values.yaml

@@ -1,50 +0,0 @@
-# Production-specific values for unbound DNS resolver
-# Overrides for the production environment
-
-# Use official image for production
-image:
-  repository: "mvance/unbound"
-  tag: "latest"
-  pullPolicy: "IfNotPresent"
-
-# Production resource settings (higher limits for reliability)
-resources:
-  requests:
-    cpu: "200m"
-    memory: "256Mi"
-  limits:
-    cpu: "500m"
-    memory: "512Mi"
-
-# Production-specific settings
-replicaCount: 2
-
-# Production annotations
-podAnnotations:
-  environment: "production"
-  critical: "true"
-
-# Anti-affinity for high availability in production
-affinity:
-  podAntiAffinity:
-    preferredDuringSchedulingIgnoredDuringExecution:
-    - weight: 100
-      podAffinityTerm:
-        labelSelector:
-          matchExpressions:
-          - key: app.kubernetes.io/name
-            operator: In
-            values:
-            - unbound
-        topologyKey: "kubernetes.io/hostname"
-
-# Production probe settings (more conservative)
-probes:
-  readiness:
-    initialDelaySeconds: 20
-    periodSeconds: 30
-    command: "sh -c 'echo \"\" | nc -w 3 127.0.0.1 53 || exit 1'"
-  liveness:
-    initialDelaySeconds: 60
-    periodSeconds: 60
-    command: "sh -c 'echo \"\" | nc -w 3 127.0.0.1 53 || exit 1'"

infrastructure/platform/networking/dns/unbound-helm/templates/_helpers.tpl

@@ -1,63 +0,0 @@
-{{/*
-Expand the name of the chart.
-*/}}
-{{- define "unbound.name" -}}
-{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{/*
-Create a default fully qualified app name.
-We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
-*/}}
-{{- define "unbound.fullname" -}}
-{{- if .Values.fullnameOverride -}}
-{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
-{{- else -}}
-{{- $name := default .Chart.Name .Values.nameOverride -}}
-{{- if contains $name .Release.Name -}}
-{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
-{{- else -}}
-{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-{{- end -}}
-{{- end -}}
-
-{{/*
-Create chart name and version as used by the chart label.
-*/}}
-{{- define "unbound.chart" -}}
-{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{/*
-Common labels
-*/}}
-{{- define "unbound.labels" -}}
-helm.sh/chart: {{ include "unbound.chart" . }}
-{{ include "unbound.selectorLabels" . }}
-{{- if .Chart.AppVersion }}
-app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
-{{- end }}
-app.kubernetes.io/managed-by: {{ .Release.Service }}
-{{- end -}}
-
-{{/*
-Selector labels
-*/}}
-{{- define "unbound.selectorLabels" -}}
-app.kubernetes.io/name: {{ include "unbound.name" . }}
-app.kubernetes.io/instance: {{ .Release.Name }}
-app.kubernetes.io/component: dns
-app.kubernetes.io/part-of: bakery-ia
-{{- end -}}
-
-{{/*
-Create the name of the service account to use
-*/}}
-{{- define "unbound.serviceAccountName" -}}
-{{- if .Values.serviceAccount.create -}}
-    {{ default (include "unbound.fullname" .) .Values.serviceAccount.name }}
-{{- else -}}
-    {{ default "default" .Values.serviceAccount.name }}
-{{- end -}}
-{{- end -}}

infrastructure/platform/networking/dns/unbound-helm/templates/configmap.yaml

@@ -1,22 +0,0 @@
-{{- if .Values.config.enabled }}
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: {{ include "unbound.fullname" . }}-config
-  namespace: {{ .Values.global.namespace }}
-  labels:
-    {{- include "unbound.labels" . | nindent 4 }}
-data:
-  {{- if .Values.config.forwardRecords }}
-  forward-records.conf: |
-{{ .Values.config.forwardRecords | indent 4 }}
-  {{- end }}
-  {{- if .Values.config.serverConfig }}
-  a-records.conf: |
-{{ .Values.config.serverConfig | indent 4 }}
-  {{- end }}
-  {{- if .Values.config.content }}
-  unbound.conf: |
-{{ .Values.config.content | indent 4 }}
-  {{- end }}
-{{- end }}

infrastructure/platform/networking/dns/unbound-helm/templates/deployment.yaml

@@ -1,117 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "unbound.fullname" . }}
-  namespace: {{ .Values.global.namespace }}
-  labels:
-    {{- include "unbound.labels" . | nindent 4 }}
-spec:
-  replicas: {{ .Values.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "unbound.selectorLabels" . | nindent 6 }}
-  template:
-    metadata:
-      {{- with .Values.podAnnotations }}
-      annotations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      labels:
-        {{- include "unbound.selectorLabels" . | nindent 8 }}
-    spec:
-      {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      serviceAccountName: {{ include "unbound.serviceAccountName" . }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      containers:
-        - name: {{ .Chart.Name }}
-          securityContext:
-            {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          ports:
-            - name: dns-udp
-              containerPort: {{ .Values.service.ports.dnsUdp }}
-              protocol: UDP
-            - name: dns-tcp
-              containerPort: {{ .Values.service.ports.dnsTcp }}
-              protocol: TCP
-          {{- if .Values.probes.readiness.enabled }}
-          readinessProbe:
-            exec:
-              command:
-                - sh
-                - -c
-                - {{ .Values.probes.readiness.command | quote }}
-            initialDelaySeconds: {{ .Values.probes.readiness.initialDelaySeconds }}
-            periodSeconds: {{ .Values.probes.readiness.periodSeconds }}
-          {{- end }}
-          {{- if .Values.probes.liveness.enabled }}
-          livenessProbe:
-            exec:
-              command:
-                - sh
-                - -c
-                - {{ .Values.probes.liveness.command | quote }}
-            initialDelaySeconds: {{ .Values.probes.liveness.initialDelaySeconds }}
-            periodSeconds: {{ .Values.probes.liveness.periodSeconds }}
-          {{- end }}
-          resources:
-            {{- toYaml .Values.resources | nindent 12 }}
-          volumeMounts:
-            {{- if .Values.config.enabled }}
-            {{- if .Values.config.forwardRecords }}
-            - name: unbound-config
-              mountPath: /opt/unbound/etc/unbound/forward-records.conf
-              subPath: forward-records.conf
-            {{- end }}
-            {{- if .Values.config.serverConfig }}
-            - name: unbound-config
-              mountPath: /opt/unbound/etc/unbound/a-records.conf
-              subPath: a-records.conf
-            {{- end }}
-            {{- if .Values.config.content }}
-            - name: unbound-config
-              mountPath: /opt/unbound/etc/unbound/unbound.conf
-              subPath: unbound.conf
-            {{- end }}
-            {{- end }}
-            {{- with .Values.volumeMounts }}
-            {{- toYaml . | nindent 12 }}
-            {{- end }}
-          {{- with .Values.env }}
-          env:
-            {{- toYaml . | nindent 12 }}
-          {{- end }}
-      volumes:
-        {{- if .Values.config.enabled }}
-        - name: unbound-config
-          configMap:
-            name: {{ include "unbound.fullname" . }}-config
-        {{- end }}
-        {{- with .Values.volumes }}
-        {{- toYaml . | nindent 8 }}
-        {{- end }}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.affinity }}
-      affinity:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.extraInitContainers }}
-      initContainers:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.extraContainers }}
-      containers:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}

infrastructure/platform/networking/dns/unbound-helm/templates/service.yaml

@@ -1,27 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ .Values.global.dnsServiceName }}
-  namespace: {{ .Values.global.namespace }}
-  labels:
-    {{- include "unbound.labels" . | nindent 4 }}
-  {{- with .Values.serviceAnnotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
-spec:
-  type: {{ .Values.service.type }}
-  {{- if .Values.service.clusterIP }}
-  clusterIP: {{ .Values.service.clusterIP }}
-  {{- end }}
-  ports:
-    - name: dns-udp
-      port: {{ .Values.service.ports.dnsUdp }}
-      targetPort: {{ .Values.service.ports.dnsUdp }}
-      protocol: UDP
-    - name: dns-tcp
-      port: {{ .Values.service.ports.dnsTcp }}
-      targetPort: {{ .Values.service.ports.dnsTcp }}
-      protocol: TCP
-  selector:
-    {{- include "unbound.selectorLabels" . | nindent 4 }}

infrastructure/platform/networking/dns/unbound-helm/templates/serviceaccount.yaml

@@ -1,13 +0,0 @@
-{{- if .Values.serviceAccount.create -}}
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: {{ include "unbound.serviceAccountName" . }}
-  namespace: {{ .Values.global.namespace }}
-  labels:
-    {{- include "unbound.labels" . | nindent 4 }}
-  {{- with .Values.serviceAccount.annotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
-{{- end -}}

infrastructure/platform/networking/dns/unbound-helm/values.yaml

@@ -1,105 +0,0 @@
-# Default values for unbound DNS resolver
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-
-# Global settings
-global:
-  # DNS service name for other services to reference
-  dnsServiceName: "unbound-dns"
-  namespace: "bakery-ia"
-
-# Unbound image configuration
-image:
-  repository: "mvance/unbound"
-  tag: "latest"
-  pullPolicy: "IfNotPresent"
-
-# Deployment configuration
-replicaCount: 1
-
-# Resource limits and requests
-resources:
-  requests:
-    cpu: "100m"
-    memory: "128Mi"
-  limits:
-    cpu: "300m"
-    memory: "384Mi"
-
-# Security context
-securityContext:
-  capabilities:
-    add: ["NET_BIND_SERVICE"]
-
-# Service configuration
-service:
-  type: "ClusterIP"
-  # Dynamic ClusterIP - Kubernetes will assign automatically
-  # clusterIP: ""  # Leave empty for automatic assignment
-  ports:
-    dnsUdp: 53
-    dnsTcp: 53
-
-# Health probes configuration
-probes:
-  readiness:
-    enabled: true
-    initialDelaySeconds: 15
-    periodSeconds: 30
-    # Simple TCP connectivity check - more reliable than DNS queries
-    # Tests if the DNS port is listening and responding
-    command: "sh -c 'echo \"\" | nc -w 2 127.0.0.1 53 || exit 1'"
-    # Alternative: use curl if available
-    # command: "curl -s --max-time 2 http://127.0.0.1:53 || exit 1"
-  liveness:
-    enabled: true
-    initialDelaySeconds: 45
-    periodSeconds: 60
-    # Simple TCP connectivity check - more reliable than DNS queries
-    # Tests if the DNS port is listening and responding
-    command: "sh -c 'echo \"\" | nc -w 2 127.0.0.1 53 || exit 1'"
-    # Alternative: use curl if available
-    # command: "curl -s --max-time 2 http://127.0.0.1:53 || exit 1"
-
-# Additional environment variables
-env: {}
-
-# Additional volume mounts
-volumeMounts: []
-
-# Additional volumes
-volumes: []
-
-# Node selector
-nodeSelector: {}
-
-# Tolerations
-tolerations: []
-
-# Affinity
-affinity: {}
-
-# Pod annotations
-podAnnotations: {}
-
-# Service annotations
-serviceAnnotations: {}
-
-# Custom unbound configuration
-config:
-  enabled: false
-
-# Additional containers (sidecars)
-extraContainers: []
-
-# Additional init containers
-extraInitContainers: []
-
-# Service account configuration
-serviceAccount:
-  create: false
-  annotations: {}
-  name: ""
-
-# Pod security context
-podSecurityContext: {}

infrastructure/platform/networking/ingress/base/ingress.yaml

@@ -56,3 +56,5 @@ spec:
   # See infrastructure/cicd/gitea/values.yaml for ingress configuration
   # NOTE: Mail ingress is deployed separately via mailu-helm resource
   # to avoid 503 errors when Mailu is not running
+  # NOTE: Monitoring ingress is deployed separately via SigNoz Helm chart
+  # See infrastructure/monitoring/signoz/signoz-values-prod.yaml for monitoring configuration

infrastructure/platform/networking/ingress/overlays/dev/kustomization.yaml

@@ -25,3 +25,5 @@ patches:
         value: "https://localhost,https://localhost:3000,https://localhost:3001,https://127.0.0.1,https://127.0.0.1:3000,https://127.0.0.1:3001,https://bakery-ia.local,https://registry.bakery-ia.local,https://gitea.bakery-ia.local,http://localhost,http://localhost:3000,http://localhost:3001,http://127.0.0.1,http://127.0.0.1:3000"
 # NOTE: Gitea and Registry ingresses are managed by Gitea Helm chart (infrastructure/cicd/gitea/values.yaml)
 # NOTE: Mail ingress (mail.bakery-ia.dev) is deployed separately via mailu-helm Tilt resource
+# NOTE: Monitoring ingress (monitoring.bakery-ia.local) is deployed separately via SigNoz Helm chart
+# See infrastructure/monitoring/signoz/signoz-values-dev.yaml for monitoring configuration

infrastructure/platform/networking/ingress/overlays/prod/kustomization.yaml

@@ -37,4 +37,6 @@ patches:
         value: "http01"
 # NOTE: Gitea and Registry ingresses are managed by Gitea Helm chart
 # See infrastructure/cicd/gitea/values-prod.yaml for production ingress configuration
-# NOTE: mail.bakewise.ai is handled by separate mailu ingress
+# NOTE: mail.bakewise.ai is handled by separate mailu ingress
+# NOTE: monitoring.bakewise.ai is handled by separate SigNoz ingress
+# See infrastructure/monitoring/signoz/signoz-values-prod.yaml for monitoring ingress configuration

infrastructure/platform/storage/minio/minio-pvc.yaml

@@ -12,5 +12,4 @@ spec:
     - ReadWriteOnce
   resources:
     requests:
-      storage: 100Gi
+      storage: 100Gi
-  storageClassName: standard

infrastructure/services/databases/demo-session-db.yaml

@@ -45,6 +45,7 @@ spec:
       containers:
       - name: postgres
         image: postgres:17-alpine
+        command: ["docker-entrypoint.sh", "-c", "config_file=/etc/postgresql/postgresql.conf"]
         ports:
         - containerPort: 5432
           name: postgres
@@ -66,11 +67,23 @@ spec:
           value: demo_session_db
         - name: PGDATA
           value: /var/lib/postgresql/data/pgdata
+        - name: POSTGRES_HOST_SSL
+          value: "on"
+        - name: PGSSLCERT
+          value: /tls/server-cert.pem
+        - name: PGSSLKEY
+          value: /tls/server-key.pem
+        - name: PGSSLROOTCERT
+          value: /tls/ca-cert.pem
         volumeMounts:
         - name: demo-session-db-data
           mountPath: /var/lib/postgresql/data
+        - name: init-scripts
+          mountPath: /docker-entrypoint-initdb.d
         - name: tls-certs-writable
           mountPath: /tls
+        - name: postgres-config
+          mountPath: /etc/postgresql
           readOnly: true
         resources:
           requests:
@@ -103,6 +116,9 @@ spec:
       - name: demo-session-db-data
         persistentVolumeClaim:
           claimName: demo-session-db-pvc
+      - name: init-scripts
+        configMap:
+          name: postgres-init-config
       - name: tls-certs-source
         secret:
           secretName: postgres-tls
@@ -115,6 +131,9 @@ spec:
             path: ca-cert.pem
       - name: tls-certs-writable
         emptyDir: {}
+      - name: postgres-config
+        configMap:
+          name: postgres-logging-config
 
 
 ---
@@ -154,4 +173,3 @@ spec:
   resources:
     requests:
       storage: 1Gi
-  storageClassName: standard

infrastructure/services/microservices/ai-insights/ai-insights-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: AI_INSIGHTS_DB_USER
       containers:
       - name: ai-insights-service
-        image: bakery/ai-insights-service:dev
+        image: registry.bakewise.ai/bakery-admin/ai_insights:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/ai-insights/migrations/ai-insights-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: ai-insights-migration
+  name: ai-insights-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: ai-insights-migration
+    app.kubernetes.io/name: ai-insights-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: ai-insights-migration
+        app.kubernetes.io/name: ai-insights-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/ai-insights-service
+        image: registry.bakewise.ai/bakery-admin/ai_insights:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "ai_insights"]
         env:
         - name: AI_INSIGHTS_DATABASE_URL

infrastructure/services/microservices/alert-processor/alert-processor.yaml

@@ -82,7 +82,7 @@ spec:
               key: ALERT_PROCESSOR_DB_USER
       containers:
       - name: alert-processor
-        image: bakery/alert-processor:latest
+        image: registry.bakewise.ai/bakery-admin/alert_processor:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
         ports:
         - containerPort: 8000
@@ -121,6 +121,15 @@ spec:
           periodSeconds: 10
           timeoutSeconds: 5
           failureThreshold: 3
+        volumeMounts:
+        - name: redis-tls
+          mountPath: /tls
+          readOnly: true
+      volumes:
+      - name: redis-tls
+        secret:
+          secretName: redis-tls-secret
+          defaultMode: 0400
 ---
 apiVersion: v1
 kind: Service

infrastructure/services/microservices/alert-processor/migrations/alert-processor-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: alert-processor-migration
+  name: alert-processor-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: alert-processor-migration
+    app.kubernetes.io/name: alert-processor-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: alert-processor-migration
+        app.kubernetes.io/name: alert-processor-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/alert-processor
+        image: registry.bakewise.ai/bakery-admin/alert_processor:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "alert_processor"]
         env:
         - name: ALERT_PROCESSOR_DATABASE_URL

infrastructure/services/microservices/auth/auth-service.yaml

@@ -110,7 +110,7 @@ spec:
           value: "auth_db"
       containers:
       - name: auth-service
-        image: bakery/auth-service:latest
+        image: registry.bakewise.ai/bakery-admin/auth:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http
@@ -178,6 +178,10 @@ spec:
           timeoutSeconds: 3
           periodSeconds: 5
           failureThreshold: 5
+        volumeMounts:
+        - name: redis-tls
+          mountPath: /tls
+          readOnly: true
       volumes:
       - name: redis-tls
         secret:

infrastructure/services/microservices/auth/migrations/auth-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: auth-migration
+  name: auth-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: auth-migration
+    app.kubernetes.io/name: auth-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: auth-migration
+        app.kubernetes.io/name: auth-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/auth-service
+        image: registry.bakewise.ai/bakery-admin/auth:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "auth"]
         env:
         - name: AUTH_DATABASE_URL

infrastructure/services/microservices/demo-session/demo-cleanup-worker.yaml

@@ -1,7 +1,7 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: demo-cleanup-worker
+  name: demo-cleanup-worker-0e95bdc4
   namespace: bakery-ia
   labels:
     app: demo-cleanup-worker
@@ -53,7 +53,7 @@ spec:
             cpu: "100m"
       containers:
       - name: worker
-        image: bakery/demo-session-service
+        image: registry.bakewise.ai/bakery-admin/demo_session:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         imagePullPolicy: IfNotPresent
         command:
         - python
@@ -71,7 +71,7 @@ spec:
               name: redis-secrets
               key: REDIS_PASSWORD
         - name: REDIS_URL
-          value: "rediss://:$(REDIS_PASSWORD)@redis-service:6379/0?ssl_cert_reqs=none"
+          value: "rediss://:$(REDIS_PASSWORD)@redis-service:6379/0"
         - name: LOG_LEVEL
           value: "INFO"
         - name: INVENTORY_SERVICE_URL
@@ -120,4 +120,13 @@ spec:
           initialDelaySeconds: 10
           periodSeconds: 30
           timeoutSeconds: 5
+        volumeMounts:
+        - name: redis-tls
+          mountPath: /tls
+          readOnly: true
       restartPolicy: Always
+      volumes:
+      - name: redis-tls
+        secret:
+          secretName: redis-tls-secret
+          defaultMode: 0400

infrastructure/services/microservices/demo-session/deployment.yaml

@@ -20,7 +20,7 @@ spec:
       serviceAccountName: demo-session-sa
       containers:
       - name: demo-session-service
-        image: bakery/demo-session-service:latest
+        image: registry.bakewise.ai/bakery-admin/demo_session:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http
@@ -43,7 +43,7 @@ spec:
               name: redis-secrets
               key: REDIS_PASSWORD
         - name: REDIS_URL
-          value: "rediss://:$(REDIS_PASSWORD)@redis-service:6379/0?ssl_cert_reqs=none"
+          value: "rediss://:$(REDIS_PASSWORD)@redis-service:6379/0"
         - name: AUTH_SERVICE_URL
           value: "http://auth-service:8000"
         - name: TENANT_SERVICE_URL
@@ -77,6 +77,10 @@ spec:
           httpGet:
             path: /health
             port: 8000
+        volumeMounts:
+        - name: redis-tls
+          mountPath: /tls
+          readOnly: true
           initialDelaySeconds: 30
           periodSeconds: 30
         readinessProbe:
@@ -133,3 +137,8 @@ spec:
           limits:
             memory: "128Mi"
             cpu: "100m"
+      volumes:
+      - name: redis-tls
+        secret:
+          secretName: redis-tls-secret
+          defaultMode: 0400

infrastructure/services/microservices/demo-session/migrations/demo-session-migration-job.yaml

@@ -1,10 +1,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: demo-session-migration
+  name: demo-session-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: demo-session-migration
+    app.kubernetes.io/name: demo-session-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -12,7 +12,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: demo-session-migration
+        app.kubernetes.io/name: demo-session-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -28,7 +28,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/demo-session-service
+        image: registry.bakewise.ai/bakery-admin/demo_session:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "demo_session"]
         env:
         - name: DEMO_SESSION_DATABASE_URL

infrastructure/services/microservices/distribution/distribution-service.yaml

@@ -109,7 +109,7 @@ spec:
           value: "distribution_db"
       containers:
       - name: distribution-service
-        image: bakery/distribution-service:latest
+        image: registry.bakewise.ai/bakery-admin/distribution:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         imagePullPolicy: IfNotPresent
         ports:
         - containerPort: 8000

infrastructure/services/microservices/distribution/migrations/distribution-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: distribution-migration
+  name: distribution-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: distribution-migration
+    app.kubernetes.io/name: distribution-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: distribution-migration
+        app.kubernetes.io/name: distribution-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/distribution-service
+        image: registry.bakewise.ai/bakery-admin/distribution:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         imagePullPolicy: IfNotPresent
         command: ["python", "/app/shared/scripts/run_migrations.py", "distribution"]
         env:

infrastructure/services/microservices/external/cronjobs/external-data-rotation-cronjob.yaml

@@ -3,7 +3,7 @@
 apiVersion: batch/v1
 kind: CronJob
 metadata:
-  name: external-data-rotation
+  name: external-data-rotation-0e95bdc4
   namespace: bakery-ia
   labels:
     app: external-service
@@ -35,7 +35,7 @@ spec:
 
           containers:
           - name: data-rotator
-            image: bakery/external-service:latest
+            image: registry.bakewise.ai/bakery-admin/external:0e95bdc4685be715dca600c0e4f5c583ff0418c7
             imagePullPolicy: Always
 
             command:

infrastructure/services/microservices/external/external-service.yaml

@@ -114,7 +114,7 @@ spec:
 
       containers:
       - name: external-service
-        image: bakery/external-service:latest
+        image: registry.bakewise.ai/bakery-admin/external:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http
@@ -187,6 +187,10 @@ spec:
           timeoutSeconds: 3
           periodSeconds: 5
           failureThreshold: 5
+        volumeMounts:
+        - name: redis-tls
+          mountPath: /tls
+          readOnly: true
       volumes:
       - name: redis-tls
         secret:

infrastructure/services/microservices/external/migrations/external-data-init-job.yaml

@@ -3,7 +3,7 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: external-data-init
+  name: external-data-init-0e95bdc4
   namespace: bakery-ia
   labels:
     app: external-service
@@ -51,7 +51,7 @@ spec:
 
       containers:
       - name: data-loader
-        image: bakery/external-service:latest
+        image: registry.bakewise.ai/bakery-admin/external:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         imagePullPolicy: Always
 
         command:

infrastructure/services/microservices/external/migrations/external-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: external-migration
+  name: external-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: external-migration
+    app.kubernetes.io/name: external-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: external-migration
+        app.kubernetes.io/name: external-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/external-service
+        image: registry.bakewise.ai/bakery-admin/external:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "external"]
         env:
         - name: EXTERNAL_DATABASE_URL

infrastructure/services/microservices/forecasting/forecasting-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: FORECASTING_DB_USER
       containers:
       - name: forecasting-service
-        image: bakery/forecasting-service:latest
+        image: registry.bakewise.ai/bakery-admin/forecasting:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/forecasting/migrations/forecasting-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: forecasting-migration
+  name: forecasting-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: forecasting-migration
+    app.kubernetes.io/name: forecasting-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: forecasting-migration
+        app.kubernetes.io/name: forecasting-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/forecasting-service
+        image: registry.bakewise.ai/bakery-admin/forecasting:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "forecasting"]
         env:
         - name: FORECASTING_DATABASE_URL

infrastructure/services/microservices/frontend/frontend-service.yaml

@@ -21,7 +21,7 @@ spec:
     spec:
       containers:
       - name: frontend
-        image: bakery/dashboard:latest
+        image: registry.bakewise.ai/bakery-admin/frontend:fbbe3e711ffea0ab373bea6e55a1911bdb672ffe
         imagePullPolicy: Always
         ports:
         - containerPort: 3000

infrastructure/services/microservices/inventory/inventory-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: INVENTORY_DB_USER
       containers:
       - name: inventory-service
-        image: bakery/inventory-service:latest
+        image: registry.bakewise.ai/bakery-admin/inventory:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/inventory/migrations/inventory-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: inventory-migration
+  name: inventory-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: inventory-migration
+    app.kubernetes.io/name: inventory-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: inventory-migration
+        app.kubernetes.io/name: inventory-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/inventory-service
+        image: registry.bakewise.ai/bakery-admin/inventory:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "inventory"]
         env:
         - name: INVENTORY_DATABASE_URL

infrastructure/services/microservices/notification/migrations/notification-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: notification-migration
+  name: notification-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: notification-migration
+    app.kubernetes.io/name: notification-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: notification-migration
+        app.kubernetes.io/name: notification-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/notification-service
+        image: registry.bakewise.ai/bakery-admin/notification:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "notification"]
         env:
         - name: NOTIFICATION_DATABASE_URL

infrastructure/services/microservices/notification/notification-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: NOTIFICATION_DB_USER
       containers:
       - name: notification-service
-        image: bakery/notification-service:latest
+        image: registry.bakewise.ai/bakery-admin/notification:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/orchestrator/migrations/orchestrator-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: orchestrator-migration
+  name: orchestrator-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: orchestrator-migration
+    app.kubernetes.io/name: orchestrator-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: orchestrator-migration
+        app.kubernetes.io/name: orchestrator-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/orchestrator-service
+        image: registry.bakewise.ai/bakery-admin/orchestrator:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "orchestrator"]
         env:
         - name: ORCHESTRATOR_DATABASE_URL

infrastructure/services/microservices/orchestrator/orchestrator-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: ORCHESTRATOR_DB_USER
       containers:
       - name: orchestrator-service
-        image: bakery/orchestrator-service:latest
+        image: registry.bakewise.ai/bakery-admin/orchestrator:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/orders/migrations/orders-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: orders-migration
+  name: orders-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: orders-migration
+    app.kubernetes.io/name: orders-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: orders-migration
+        app.kubernetes.io/name: orders-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/orders-service
+        image: registry.bakewise.ai/bakery-admin/orders:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "orders"]
         env:
         - name: ORDERS_DATABASE_URL

infrastructure/services/microservices/orders/orders-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: ORDERS_DB_USER
       containers:
       - name: orders-service
-        image: bakery/orders-service:latest
+        image: registry.bakewise.ai/bakery-admin/orders:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/pos/migrations/pos-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: pos-migration
+  name: pos-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: pos-migration
+    app.kubernetes.io/name: pos-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: pos-migration
+        app.kubernetes.io/name: pos-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/pos-service
+        image: registry.bakewise.ai/bakery-admin/pos:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "pos"]
         env:
         - name: POS_DATABASE_URL

infrastructure/services/microservices/pos/pos-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: POS_DB_USER
       containers:
       - name: pos-service
-        image: bakery/pos-service:latest
+        image: registry.bakewise.ai/bakery-admin/pos:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/procurement/migrations/procurement-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: procurement-migration
+  name: procurement-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: procurement-migration
+    app.kubernetes.io/name: procurement-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: procurement-migration
+        app.kubernetes.io/name: procurement-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/procurement-service
+        image: registry.bakewise.ai/bakery-admin/procurement:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "procurement"]
         env:
         - name: PROCUREMENT_DATABASE_URL

infrastructure/services/microservices/procurement/procurement-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: PROCUREMENT_DB_USER
       containers:
       - name: procurement-service
-        image: bakery/procurement-service:latest
+        image: registry.bakewise.ai/bakery-admin/procurement:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/production/migrations/production-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: production-migration
+  name: production-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: production-migration
+    app.kubernetes.io/name: production-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: production-migration
+        app.kubernetes.io/name: production-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/production-service
+        image: registry.bakewise.ai/bakery-admin/production:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "production"]
         env:
         - name: PRODUCTION_DATABASE_URL

infrastructure/services/microservices/production/production-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: PRODUCTION_DB_USER
       containers:
       - name: production-service
-        image: bakery/production-service:latest
+        image: registry.bakewise.ai/bakery-admin/production:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/recipes/migrations/recipes-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: recipes-migration
+  name: recipes-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: recipes-migration
+    app.kubernetes.io/name: recipes-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: recipes-migration
+        app.kubernetes.io/name: recipes-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/recipes-service
+        image: registry.bakewise.ai/bakery-admin/recipes:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "recipes"]
         env:
         - name: RECIPES_DATABASE_URL

infrastructure/services/microservices/recipes/recipes-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: RECIPES_DB_USER
       containers:
       - name: recipes-service
-        image: bakery/recipes-service:latest
+        image: registry.bakewise.ai/bakery-admin/recipes:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/sales/migrations/sales-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: sales-migration
+  name: sales-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: sales-migration
+    app.kubernetes.io/name: sales-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: sales-migration
+        app.kubernetes.io/name: sales-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/sales-service
+        image: registry.bakewise.ai/bakery-admin/sales:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "sales"]
         env:
         - name: SALES_DATABASE_URL

infrastructure/services/microservices/sales/sales-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: SALES_DB_USER
       containers:
       - name: sales-service
-        image: bakery/sales-service:latest
+        image: registry.bakewise.ai/bakery-admin/sales:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/suppliers/migrations/suppliers-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: suppliers-migration
+  name: suppliers-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: suppliers-migration
+    app.kubernetes.io/name: suppliers-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: suppliers-migration
+        app.kubernetes.io/name: suppliers-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/suppliers-service
+        image: registry.bakewise.ai/bakery-admin/suppliers:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "suppliers"]
         env:
         - name: SUPPLIERS_DATABASE_URL

infrastructure/services/microservices/suppliers/suppliers-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: SUPPLIERS_DB_USER
       containers:
       - name: suppliers-service
-        image: bakery/suppliers-service:latest
+        image: registry.bakewise.ai/bakery-admin/suppliers:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http

infrastructure/services/microservices/tenant/migrations/tenant-migration-job.yaml

@@ -2,10 +2,10 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: tenant-migration
+  name: tenant-migration-0e95bdc4
   namespace: bakery-ia
   labels:
-    app.kubernetes.io/name: tenant-migration
+    app.kubernetes.io/name: tenant-migration-0e95bdc4
     app.kubernetes.io/component: migration
     app.kubernetes.io/part-of: bakery-ia
 spec:
@@ -13,7 +13,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: tenant-migration
+        app.kubernetes.io/name: tenant-migration-0e95bdc4
         app.kubernetes.io/component: migration
     spec:
       initContainers:
@@ -29,7 +29,7 @@ spec:
             cpu: "100m"
       containers:
       - name: migrate
-        image: bakery/tenant-service
+        image: registry.bakewise.ai/bakery-admin/tenant:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         command: ["python", "/app/shared/scripts/run_migrations.py", "tenant"]
         env:
         - name: TENANT_DATABASE_URL

infrastructure/services/microservices/tenant/tenant-service.yaml

@@ -88,7 +88,7 @@ spec:
               key: TENANT_DB_USER
       containers:
       - name: tenant-service
-        image: bakery/tenant-service:latest
+        image: registry.bakewise.ai/bakery-admin/tenant:0e95bdc4685be715dca600c0e4f5c583ff0418c7
         ports:
         - containerPort: 8000
           name: http