Stabilize CI Kaniko tag and keep Harbor free of egress proxy.

Use the seeded kaniko v1.27.6-debug image, retry npm ci, and push via harbor-core without HTTP_PROXY so Harbor UI metadata and blob uploads keep working.

Co-authored-by: Cursor <cursoragent@cursor.com>

.gitea/workflows/build-deploy.yaml

@@ -0,0 +1,291 @@
+name: Build and Deploy Platform
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+      - "**.md"
+  workflow_dispatch:
+
+# Serialize builds so parallel pushes don't race on the GitOps values update.
+concurrency:
+  group: build-deploy-platform
+  cancel-in-progress: false
+
+env:
+  # PULL_REGISTRY: kubelet pulls via k3s mirror → harbor-core (matches registry-pull-secret)
+  PULL_REGISTRY: registry.abrban.com
+  # PUSH_REGISTRY: kaniko pushes via harbor-core (Harbor UI metadata + blob storage)
+  PUSH_REGISTRY: harbor-core.cloudhost.svc.cluster.local
+  PROJECT: abrban
+  BUILD_NS: cloudhost-builds
+  GITEA_HOST: gitea-http.gitea.svc.cluster.local:3000
+  # PAT of the "ci" user, stored as repo secret CI_TOKEN (names starting with GITEA_ are reserved)
+  GITEA_TOKEN: ${{ secrets.CI_TOKEN }}
+  REPO_PATH: abrban/cloud-host.git
+  GITOPS_REPO_PATH: abrban/cloud-host-gitops.git
+
+jobs:
+  build-and-deploy:
+    runs-on: abrban-builder
+    steps:
+      - name: Checkout
+        shell: sh
+        run: |
+          git clone --depth=1 --branch main "http://oauth2:${GITEA_TOKEN}@${GITEA_HOST}/${REPO_PATH}" workspace
+          cd workspace
+          echo "Checked out $(git rev-parse --short HEAD)"
+
+      - name: Set image tag
+        shell: sh
+        run: |
+          cd workspace
+          SHA="$(git rev-parse --short HEAD)"
+          TAG="$(date +%Y%m%d-%H%M)-${SHA}"
+          echo "IMAGE_TAG=${TAG}" >> "$GITHUB_ENV"
+          echo "Build tag: ${TAG}"
+
+      - name: Define job waiter
+        shell: sh
+        run: |
+          # wait_for_job <name>: exit 0 on Complete, exit 1 (with kaniko logs) on Failed/timeout
+          cat > wait_for_job.sh <<'ENDSCRIPT'
+          #!/bin/sh
+          JOB="$1"
+          DEADLINE=$(( $(date +%s) + 2400 ))
+          while :; do
+            CONDS="$(kubectl -n ${BUILD_NS} get job/${JOB} -o jsonpath='{range .status.conditions[*]}{.type}={.status} {end}' 2>/dev/null)"
+            case "$CONDS" in
+              *Complete=True*) echo "Job ${JOB} completed"; exit 0 ;;
+              *Failed=True*)
+                echo "Job ${JOB} FAILED — kaniko logs:"
+                kubectl -n ${BUILD_NS} logs job/${JOB} -c kaniko --tail=100 || true
+                exit 1 ;;
+            esac
+            if [ "$(date +%s)" -gt "$DEADLINE" ]; then
+              echo "Timed out waiting for job ${JOB} — kaniko logs:"
+              kubectl -n ${BUILD_NS} logs job/${JOB} -c kaniko --tail=100 || true
+              exit 1
+            fi
+            sleep 15
+          done
+          ENDSCRIPT
+          chmod +x wait_for_job.sh
+
+      - name: Run backend tests (Job)
+        shell: sh
+        run: |
+          JOB_NAME="test-be-$(echo $IMAGE_TAG | tr '.:' '-' | cut -c1-50)"
+          cat <<ENDJOB | kubectl apply -f -
+          apiVersion: batch/v1
+          kind: Job
+          metadata:
+            name: ${JOB_NAME}
+            namespace: ${BUILD_NS}
+          spec:
+            ttlSecondsAfterFinished: 3600
+            backoffLimit: 0
+            template:
+              spec:
+                restartPolicy: Never
+                imagePullSecrets:
+                  - name: registry-pull-secret
+                containers:
+                  - name: test
+                    image: ${PULL_REGISTRY}/${PROJECT}/node:24-alpine
+                    envFrom:
+                      - secretRef:
+                          name: registry-egress-proxy
+                    command:
+                      - sh
+                      - -c
+                      - |
+                        apk add --no-cache git &&
+                        git clone --depth=1 --branch main http://oauth2:${GITEA_TOKEN}@${GITEA_HOST}/${REPO_PATH} /workspace &&
+                        cd /workspace/backend &&
+                        npm config set fetch-retries 5 &&
+                        npm config set fetch-retry-mintimeout 20000 &&
+                        npm config set fetch-retry-maxtimeout 120000 &&
+                        (npm ci --legacy-peer-deps || (echo 'npm ci failed, retrying...' && sleep 5 && npm ci --legacy-peer-deps) || (echo 'npm ci failed again, retrying...' && sleep 10 && npm ci --legacy-peer-deps)) &&
+                        npm run test -- --ci --runInBand
+                    resources:
+                      requests: { cpu: 500m, memory: 1Gi }
+                      limits: { cpu: "2", memory: 3Gi }
+          ENDJOB
+          echo "Waiting for backend test job: ${JOB_NAME}"
+          # Reuse the waiter but read logs from the "test" container on failure
+          DEADLINE=$(( $(date +%s) + 1800 ))
+          while :; do
+            CONDS="$(kubectl -n ${BUILD_NS} get job/${JOB_NAME} -o jsonpath='{range .status.conditions[*]}{.type}={.status} {end}' 2>/dev/null)"
+            case "$CONDS" in
+              *Complete=True*) echo "Tests passed"; break ;;
+              *Failed=True*)
+                echo "Tests FAILED — logs:"
+                kubectl -n ${BUILD_NS} logs job/${JOB_NAME} -c test --tail=200 || true
+                exit 1 ;;
+            esac
+            if [ "$(date +%s)" -gt "$DEADLINE" ]; then
+              echo "Timed out waiting for tests — logs:"
+              kubectl -n ${BUILD_NS} logs job/${JOB_NAME} -c test --tail=200 || true
+              exit 1
+            fi
+            sleep 15
+          done
+
+      - name: Build backend image (Kaniko Job)
+        shell: sh
+        run: |
+          JOB_NAME="build-be-$(echo $IMAGE_TAG | tr '.:' '-' | cut -c1-50)"
+          cat <<ENDJOB | kubectl apply -f -
+          apiVersion: batch/v1
+          kind: Job
+          metadata:
+            name: ${JOB_NAME}
+            namespace: ${BUILD_NS}
+          spec:
+            ttlSecondsAfterFinished: 3600
+            backoffLimit: 2
+            template:
+              spec:
+                restartPolicy: Never
+                imagePullSecrets:
+                  - name: registry-pull-secret
+                initContainers:
+                  - name: clone
+                    # alpine/git ships git — no flaky apk install at build time
+                    image: ${PULL_REGISTRY}/${PROJECT}/alpine-git:2.43.0
+                    command:
+                      - sh
+                      - -c
+                      - git clone --depth=1 --branch main http://oauth2:${GITEA_TOKEN}@${GITEA_HOST}/${REPO_PATH} /workspace
+                    volumeMounts:
+                      - name: ws
+                        mountPath: /workspace
+                containers:
+                  - name: kaniko
+                    image: ${PULL_REGISTRY}/${PROJECT}/kaniko-executor:v1.27.6-debug
+                    # Base image (node:24-alpine) is seeded in Harbor abrban/ — avoids
+                    # flaky direct pulls from docker.io through the egress proxy.
+                    envFrom:
+                      - secretRef:
+                          name: registry-egress-proxy
+                    args:
+                      - --dockerfile=/workspace/backend/Dockerfile
+                      - --context=dir:///workspace/backend
+                      - --build-arg=BASE_IMAGE=${PUSH_REGISTRY}/${PROJECT}/node:24-alpine
+                      - --destination=${PUSH_REGISTRY}/${PROJECT}/cloudhost-backend:${IMAGE_TAG}
+                      - --insecure
+                      - --insecure-pull
+                      - --insecure-registry=${PUSH_REGISTRY}
+                      - --skip-tls-verify
+                      - --push-retry=2
+                    volumeMounts:
+                      - name: ws
+                        mountPath: /workspace
+                      - name: docker-config
+                        mountPath: /kaniko/.docker
+                volumes:
+                  - name: ws
+                    emptyDir: {}
+                  - name: docker-config
+                    secret:
+                      secretName: kaniko-harbor-auth
+                      items:
+                        - key: .dockerconfigjson
+                          path: config.json
+          ENDJOB
+          echo "Waiting for backend build job: ${JOB_NAME}"
+          ./wait_for_job.sh "${JOB_NAME}"
+          echo "Backend build done"
+
+      - name: Build frontend image (Kaniko Job)
+        shell: sh
+        run: |
+          JOB_NAME="build-fe-$(echo $IMAGE_TAG | tr '.:' '-' | cut -c1-50)"
+          cat <<ENDJOB | kubectl apply -f -
+          apiVersion: batch/v1
+          kind: Job
+          metadata:
+            name: ${JOB_NAME}
+            namespace: ${BUILD_NS}
+          spec:
+            ttlSecondsAfterFinished: 3600
+            backoffLimit: 2
+            template:
+              spec:
+                restartPolicy: Never
+                imagePullSecrets:
+                  - name: registry-pull-secret
+                initContainers:
+                  - name: clone
+                    image: ${PULL_REGISTRY}/${PROJECT}/alpine-git:2.43.0
+                    command:
+                      - sh
+                      - -c
+                      - git clone --depth=1 --branch main http://oauth2:${GITEA_TOKEN}@${GITEA_HOST}/${REPO_PATH} /workspace
+                    volumeMounts:
+                      - name: ws
+                        mountPath: /workspace
+                containers:
+                  - name: kaniko
+                    image: ${PULL_REGISTRY}/${PROJECT}/kaniko-executor:v1.27.6-debug
+                    envFrom:
+                      - secretRef:
+                          name: registry-egress-proxy
+                    args:
+                      - --dockerfile=/workspace/frontend/Dockerfile
+                      - --context=dir:///workspace/frontend
+                      - --build-arg=BASE_IMAGE=${PUSH_REGISTRY}/${PROJECT}/node:24-alpine
+                      - --build-arg=NEXT_PUBLIC_API_URL=https://api.abrban.com
+                      - --destination=${PUSH_REGISTRY}/${PROJECT}/cloudhost-frontend:${IMAGE_TAG}
+                      - --insecure
+                      - --insecure-pull
+                      - --insecure-registry=${PUSH_REGISTRY}
+                      - --skip-tls-verify
+                      - --push-retry=2
+                    volumeMounts:
+                      - name: ws
+                        mountPath: /workspace
+                      - name: docker-config
+                        mountPath: /kaniko/.docker
+                volumes:
+                  - name: ws
+                    emptyDir: {}
+                  - name: docker-config
+                    secret:
+                      secretName: kaniko-harbor-auth
+                      items:
+                        - key: .dockerconfigjson
+                          path: config.json
+          ENDJOB
+          echo "Waiting for frontend build job: ${JOB_NAME}"
+          ./wait_for_job.sh "${JOB_NAME}"
+          echo "Frontend build done"
+
+      - name: Update GitOps repo and push
+        shell: sh
+        run: |
+          git clone --depth=1 --branch main "http://oauth2:${GITEA_TOKEN}@${GITEA_HOST}/${GITOPS_REPO_PATH}" gitops-repo
+          cd gitops-repo
+          VALUES=platform/values-abrban.yaml
+          if command -v yq >/dev/null 2>&1; then
+            IMAGE_TAG="${IMAGE_TAG}" yq -i '.images.backend.tag = strenv(IMAGE_TAG) | .images.frontend.tag = strenv(IMAGE_TAG)' "${VALUES}"
+          else
+            # Only touch the tag line directly below each cloudhost-* repository line.
+            sed -i "/repository: .*cloudhost-backend/{n;s|tag: \".*\"|tag: \"${IMAGE_TAG}\"|;}" "${VALUES}"
+            sed -i "/repository: .*cloudhost-frontend/{n;s|tag: \".*\"|tag: \"${IMAGE_TAG}\"|;}" "${VALUES}"
+          fi
+          git config user.email "ci@abrban.com"
+          git config user.name "Gitea Actions"
+          git add "${VALUES}"
+          if ! git diff --cached --quiet; then
+            git commit -m "ci: deploy platform ${IMAGE_TAG}"
+            # Retry with rebase — another pipeline may have pushed meanwhile.
+            for attempt in 1 2 3; do
+              if git push origin HEAD:main; then
+                break
+              fi
+              echo "Push rejected (attempt ${attempt}) — rebasing on latest main"
+              git pull --rebase origin main
+              [ "$attempt" = "3" ] && { echo "Giving up after 3 attempts"; exit 1; }
+            done
+          fi

.github/workflows/ci.yml

@@ -0,0 +1,68 @@
+name: CI
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+jobs:
+  backend:
+    name: Backend
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: backend
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '24'
+          cache: npm
+          cache-dependency-path: backend/package-lock.json
+      - run: npm ci
+      - run: npm run typecheck
+      - run: npm run lint:check
+      - run: npm test -- --passWithNoTests
+      - run: npm run test:e2e
+      - name: Verify Helm migration ConfigMap is in sync
+        run: |
+          npm run sync:migrations
+          if ! git diff --quiet -- helm/cloudhost-platform/migrations; then
+            echo "::error::helm/cloudhost-platform/migrations is out of sync with backend/migrations. Run 'npm run sync:migrations' and commit."
+            git --no-pager diff --stat -- helm/cloudhost-platform/migrations
+            exit 1
+          fi
+
+  frontend:
+    name: Frontend
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: frontend
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '24'
+          cache: npm
+          cache-dependency-path: frontend/package-lock.json
+      - run: npm ci
+      - run: npm run typecheck
+      - run: npm run lint
+      - run: npm test
+      - run: npm run build
+        env:
+          NEXT_PUBLIC_API_URL: http://localhost:4000
+
+  helm:
+    name: Helm Charts
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: azure/setup-helm@v4
+        with:
+          version: v3.15.4
+      - run: helm lint backend/helm/cloudhost-platform
+      - run: helm lint backend/helm/cloudhost-app
+      - run: helm lint backend/helm/cloudhost-logging

ARCHITECTURE.md

@@ -2,7 +2,14 @@
 
 ## Overview
 
-CloudHost is a self-service PaaS platform that enables users to deploy **Node.js**, **Laravel**, and **WordPress** applications onto Kubernetes clusters managed by a super admin. It includes a full billing/wallet system, automated lifecycle management, and Helm-based deployments.
+CloudHost is a self-service PaaS that lets users deploy applications onto Kubernetes
+clusters managed by a super admin. Source code (uploaded archive or git repo) is turned
+into a container image **inside the cluster** with Kaniko, then rolled out via Helm. It
+includes a full billing/wallet system, automated lifecycle management, managed
+databases/services, Elasticsearch-backed logging, and a bilingual (Persian/English) panel.
+
+Supported runtimes — each built from a platform-maintained `Dockerfile` template:
+**Node.js, Laravel, Go, PHP, Python, Django, .NET**, and **WordPress** (official image).
 
 ---
 
@@ -10,42 +17,34 @@ CloudHost is a self-service PaaS platform that enables users to deploy **Node.js
 
 ```
 ┌─────────────────────────────────────────────────────────────────┐
-│                        USERS / ADMINS                           │
+│                        USERS / ADMINS  (Browser)                 │
-│                     (Browser / CLI)                              │
 └──────────────────────────┬──────────────────────────────────────┘
                            │ HTTPS
                            ▼
 ┌─────────────────────────────────────────────────────────────────┐
-│                     FRONTEND (Next.js 14)                       │
+│              FRONTEND — Next.js 16 (App Router, bilingual)       │
-│  ┌──────────┐  ┌───────────────┐  ┌──────────┐  ┌───────────┐  │
+│   Landing │ Auth (OTP) │ Deploy Wizard │ Dashboard │ Admin Panel │
-│  │  Auth UI │  │ Deploy Wizard │  │ Dashboard│  │Admin Panel│  │
-│  └──────────┘  └───────────────┘  └──────────┘  └───────────┘  │
 └──────────────────────────┬──────────────────────────────────────┘
-                           │ REST API (JSON)
+                           │ REST /api/v1 (JSON)
                            ▼
 ┌─────────────────────────────────────────────────────────────────┐
-│                    BACKEND (NestJS 10)                           │
+│                     BACKEND — NestJS 11                          │
-│                                                                 │
+│  Auth · Users · Admin · Applications · Deployments · Clusters    │
-│  ┌──────────┐  ┌──────────────┐  ┌────────────┐  ┌──────────┐  │
+│  Build · Billing · Lifecycle · Snapshots · Tickets · Access ·    │
-│  │Auth      │  │Applications  │  │Deployments │  │Clusters  │  │
+│  Notifications · Kubernetes/Helm/Registry                        │
-│  │Module    │  │Module        │  │Module      │  │Module    │  │
+└───┬───────────┬───────────────────┬───────────────┬─────────────┘
-│  └──────────┘  └──────────────┘  └────────────┘  └──────────┘  │
+    │           │                   │               │
-│                                                                 │
+    ▼           ▼                   ▼               ▼
-│  ┌──────────┐  ┌──────────────┐  ┌────────────┐  ┌──────────┐  │
+┌────────┐ ┌────────┐         ┌──────────┐ ┌──────────────────┐
-│  │Billing   │  │Lifecycle     │  │Snapshots   │  │Tickets   │  │
+│Postgres│ │ Redis  │         │ Registry │ │   Kubernetes     │
-│  │Module    │  │Module        │  │Module      │  │Module    │  │
+│  16    │ │(cache/ │         │  (:2)    │ │   Cluster(s)     │
-│  └──────────┘  └──────────────┘  └────────────┘  └──────────┘  │
+│        │ │ Bull)  │         └──────────┘ │  ┌────────────┐  │
-│                                                                 │
+└────────┘ └────────┘                      │  │ Build Jobs │  │
-│  ┌──────────────────┐  ┌──────────────┐  ┌──────────────────┐   │
+                                           │  │  (Kaniko)  │  │
-│  │ Kubernetes       │  │ Helm         │  │ Build            │   │
+                                           │  └────────────┘  │
-│  │ Service          │  │ Service      │  │ Service          │   │
+                                           │  Helm releases   │
-│  └────────┬─────────┘  └──────┬───────┘  └──────┬───────────┘   │
+                                           │  (user apps)     │
-└───────────┼───────────────────┼──────────────────┼───────────────┘
+                                           └──────────────────┘
-            │                   │                  │
-    ┌───────▼────────┐  ┌──────▼────────┐  ┌──────▼────────┐
-    │  Kubernetes    │  │  Helm CLI     │  │  Kaniko       │
-    │  Cluster(s)   │  │  (v3)         │  │  (in-cluster) │
-    └───────────────┘  └───────────────┘  └───────────────┘
 ```
 
 ---
@@ -54,110 +53,118 @@ CloudHost is a self-service PaaS platform that enables users to deploy **Node.js
 
 | Module | Purpose |
 |--------|---------|
-| **Auth** | JWT access/refresh tokens, Passport strategies, role guards |
+| **Auth** | Mobile-number + OTP (SMS) and password login; JWT access/refresh; Passport strategies; role guards |
-| **Users** | User CRUD, admin activate/deactivate, profile management |
+| **Users** | User CRUD, profile, phone verification |
-| **Applications** | App CRUD, code upload (zip), metadata, runtime detection |
+| **Admin** | Super-admin user-detail dashboard and operations |
-| **Build** | Kaniko-based image builds via BullMQ queue; auto-detects Node.js/Laravel/WordPress |
+| **Applications** | App CRUD, code upload (→ disk), git config, runtime/version metadata |
-| **Kubernetes** | K8s API interactions — namespace, scale, delete, pod logs, build pods |
+| **Application-migrations** | Import / migrate existing applications (Bull queue) |
-| **Helm** | Helm CLI wrapper — install/upgrade, rollback, uninstall, history |
+| **Build** | `build.service` — runtime detection + per-runtime Dockerfile generation, Kaniko image builds inside K8s |
-| **Deployments** | Deployment lifecycle orchestration, history, stop/restart |
+| **Deployments** | Deploy orchestration (build → Helm), history, stop/restart |
-| **Clusters** | Multi-cluster management, kubeconfig storage, default cluster selection |
+| **Kubernetes** | K8s API wrapper, Helm CLI wrapper, registry service |
-| **Billing** | Wallet system (deposit/deduct), transaction ledger, plan cost calculation |
+| **Clusters** | Multi-cluster management, kubeconfig storage, default cluster |
-| **Lifecycle** | Cron-based scanner: auto-suspend expired apps, auto-delete after grace period |
+| **Billing** | Wallet (deposit/deduct), transaction ledger, invoices, pricing catalog, coupons/discounts |
-| **Snapshots** | Application snapshot/backup management |
+| **Lifecycle** | Interval scanner: auto-suspend expired apps, auto-delete after grace period |
-| **Tickets** | Support ticket system for users |
+| **Snapshots** | Application snapshot/backup & restore |
+| **Tickets** | Support ticket system (technical/sales departments) |
+| **Access** | Time-limited external access to app services via temporary NodePort grants (Bull queue) |
+| **Notifications** | User-facing notifications |
+| **Common / Config** | Shared enums, guards, decorators; env & TypeORM config |
 
 ---
 
 ## 🔧 Tech Stack
 
-### Frontend: Next.js 14 (App Router) + Tailwind CSS
+### Frontend: Next.js 16 (App Router) + Tailwind CSS v4
 
 | Reason | Detail |
 |--------|--------|
-| **SSR & SEO** | Server-side rendering for fast initial loads |
+| **SSR & SEO** | Server-side rendering for fast initial loads and a public landing/blog |
-| **App Router** | React Server Components, layouts, loading states |
+| **App Router** | React Server Components, layouts, locale routing under `app/[lang]/` |
-| **Tailwind CSS** | Rapid UI development, consistent design system |
+| **Bilingual** | `fa-IR` (default) + `en-US`; `middleware.ts` also splits landing vs authenticated panel |
-| **TypeScript** | End-to-end type safety with shared types |
+| **React Query** | Server state, caching, polling for live build/deploy status |
-| **React Query** | Server state management, caching, polling for live status |
+| **Zustand** | Lightweight client auth store |
-| **Zustand** | Lightweight client state management (auth store) |
+| **TypeScript** | End-to-end type safety |
 
-### Backend: NestJS 10 (Node.js)
+### Backend: NestJS 11 (Node.js 20)
 
 | Reason | Detail |
 |--------|--------|
-| **Modular architecture** | Each domain is a self-contained module |
+| **Modular** | Each domain is a self-contained module |
-| **TypeScript native** | Full type safety, shared interfaces with frontend |
+| **@kubernetes/client-node** | Direct K8s API interaction (Jobs, Deployments, logs, scale) |
-| **@kubernetes/client-node** | Official K8s client for direct API interaction |
+| **Helm CLI** | Shell-out to helm for chart-based app deployments |
-| **Helm CLI** | Shell-out to helm for chart-based deployments |
+| **Bull (Redis)** | Async queues for service-access grants and application migrations |
-| **Bull/BullMQ** | Redis-backed job queues for async build pipelines |
+| **TypeORM** | PostgreSQL ORM. `synchronize` is **development-only**; production schema changes ship as idempotent SQL migrations / `ALTER ... IF NOT EXISTS` |
-| **TypeORM** | PostgreSQL ORM with entity-based schema |
 
 ### Build System: Kaniko (in-cluster)
 
 | Reason | Detail |
 |--------|--------|
-| **No Docker daemon** | Builds inside K8s pods — no Docker-in-Docker |
+| **No Docker daemon** | Builds run as unprivileged K8s Jobs in `cloudhost-builds` |
-| **Runtime detection** | Auto-detects Node.js, Laravel, WordPress from source files |
+| **Runtime detection** | `detectRuntime()` infers Node.js / Laravel / WordPress from source files; the app may also pin a runtime explicitly |
-| **WordPress support** | Custom entrypoint script for wp-content merging |
+| **Per-runtime Dockerfiles** | `generateDockerfile()` emits a tailored Dockerfile for Node.js, Laravel, WordPress, Go, PHP, Python, Django, or .NET |
-| **Registry push** | Native push to insecure or authenticated registries |
+| **WordPress** | Templated Dockerfile + custom entrypoint that merges `wp-content` |
+| **Source ingestion** | Uploaded archives saved to disk and streamed into a per-build PVC (helper pod + `kubectl cp`); git repos cloned in-pod |
+| **Registry push** | Native push to the in-cluster (insecure) registry |
 
 ### Deployment: Helm v3 Charts
 
 | Reason | Detail |
 |--------|--------|
-| **Templated manifests** | Single chart handles Node.js, Laravel, WordPress |
+| **Templated manifests** | One `cloudhost-app` chart handles all runtimes + attached services |
-| **Rollback support** | Built-in revision history and rollback |
+| **Rollback** | Built-in revision history |
-| **Resource policies** | PVCs and secrets persist across helm uninstall |
+| **Persistence** | DB/app PVCs and secrets use keep policies so they survive helm uninstall |
-| **Registry pull secrets** | Auto-created per namespace for insecure registries |
+| **Ingress** | Traefik by default (k3s); `INGRESS_CLASS=nginx` for ingress-nginx |
+
+---
+
+## 🔄 Build & Deploy Flow
+
+```
+User triggers deploy (panel)
+    │
+    ▼
+Backend runs the build-and-deploy pipeline, creating a Kubernetes Job in `cloudhost-builds`:
+
+  ┌─ init: prepare source  (uploaded zip → disk → helper pod + `kubectl cp` → build PVC) ─┐
+  │      …or…                                                                              │  → /workspace/source
+  └─ init: git-clone       (clone repo; token injected into the URL for private repos) ───┘
+                                   │
+                                   ▼
+  The platform detects the runtime and generates a Dockerfile for it
+  (Node.js / Laravel / WordPress / Go / PHP / Python / Django / .NET)
+                                   │
+                                   ▼
+  container: kaniko        → build image (cache per user) → push to in-cluster registry
+                                   │
+                                   ▼
+        HelmService install/upgrade `cloudhost-app`
+                                   │
+                                   ▼
+        Helm creates: Namespace, Deployment, Service, Ingress (+TLS), per-app
+        DB/Redis/RabbitMQ, PVCs, Secrets, registry pull secret, log shipper
+                                   │
+                                   ▼
+                 App live at https://<subdomain>.<PLATFORM_DOMAIN>
+```
+
+Notes:
+- The build runs **inline** within the deploy request (it is not queued); build
+  progress/logs are tracked in memory and polled by the frontend. This assumes a single
+  active backend replica for an in-flight build.
+- Bull/Redis queues are used by other subsystems (service-access grants, application
+  migrations), not by the image build.
 
 ---
 
 ## 🔐 Security Architecture
 
-- JWT Authentication (access + refresh tokens)
+- Mobile-OTP + password authentication; JWT access + refresh
-- Role-Based Access Control (User / Admin)
+- **Live** role/active-status enforcement — `JwtStrategy` reads the user from the DB each request
-- K8s Namespace Isolation per user
+- Role-Based Access Control (`user` / `admin` / `technical` / `sales`)
-- K8s RBAC — scoped ServiceAccounts
+- K8s namespace isolation per user; scoped ServiceAccounts
-- Network Policies between namespaces
+- Resource quotas & limit ranges; expandable per-app storage
-- Resource Quotas & Limit Ranges
+- Secrets stored as K8s Secrets (env vars, DB creds)
-- Secrets encryption (K8s Secrets)
+- Input validation (class-validator), Helmet headers, Bcrypt password hashing
-- Input validation (class-validator on all DTOs)
-- Helmet HTTP security headers
-- Bcrypt password hashing (12 rounds)
-
----
-
-## 🔄 Deployment Flow
-
-```
-User uploads code (zip)
-    │
-    ▼
-API stores file + metadata in PostgreSQL
-    │
-    ▼
-BullMQ build job queued
-    │
-    ▼
-detectRuntime() → nodejs | laravel | wordpress
-    │
-    ▼
-Generate Dockerfile per runtime
-    │
-    ▼
-Kaniko Pod builds image → pushes to registry
-    │
-    ▼
-HelmService.installOrUpgrade() with cloudhost-app chart
-    │
-    ▼
-Helm creates: Namespace, Deployment, Service, Ingress,
-  DB, PVC, Secrets, Registry Pull Secret, TLS cert
-    │
-    ▼
-App live at https://<subdomain>.apps.cloudhost.ir
-```
 
 ---
 
@@ -168,95 +175,100 @@ ACTIVE ──(expires)──► SUSPENDED ──(grace)──► PENDING_DELETIO
   ▲                       │                        │
   └────── payment ────────┘                        │
   └────── payment (within grace) ──────────────────┘
+
+DOCKED ── user removed the service; data retained until the plan expires
 ```
 
-- **Billing Cycles**: HOURLY | MONTHLY | YEARLY
+- **Billing cycles**: HOURLY | MONTHLY | YEARLY
-- **Hourly plans**: auto-renew from wallet each hour
+- **Wallet**: deposits, deductions, refunds, gateway payments; invoices with coupons/discounts
-- **Grace periods**: admin-configurable via PlatformSettings table
+- **Grace periods**: admin-configurable via the PlatformSettings entity (per cycle)
-- **Lifecycle Scanner**: runs every 60s (configurable)
+- **Lifecycle scanner**: runs on an interval (default 60s); suspends expired apps (scale to 0,
+  data retained) and deletes them after the grace period
+
+> ⚠️ The lifecycle scanner and other interval jobs assume a **single backend replica** —
+> guard them (e.g. a Redis lock) before scaling the control plane horizontally.
 
 ---
 
-## Helm Chart: cloudhost-platform
+## 📦 Helm Charts
 
-Chart at `backend/helm/cloudhost-platform/` deploys the **control plane** (NestJS API, Next.js UI, PostgreSQL, Redis) into a dedicated namespace (default `cloudhost`).
+### cloudhost-platform — control plane
 
-| Value | Purpose |
+Deploys the API, UI, PostgreSQL, and Redis into a namespace (default `cloudhost`).
-|-------|---------|
-| `ingress.enabled` | Create Ingress (default `true`) |
-| `ingress.tls.enabled` | cert-manager TLS via `clusterIssuer` |
-| `ingress.frontend.host` / `ingress.api.host` | Public hostnames |
-| `postgres.password` / `secrets.jwtSecret` | Credentials (auto-generated if empty on first install) |
-| `migrations.enabled` | Post-install SQL migration Job |
-
----
-
-## 🚀 Helm Chart: cloudhost-app
-
-Single chart at `backend/helm/cloudhost-app/` handles all runtimes:
 
 | Template | Purpose |
 |----------|---------|
-| `deployment.yaml` | App pod with imagePullSecrets, probes, WordPress volumes |
+| `backend-deployment.yaml` / `backend-service.yaml` / `backend-pvc.yaml` | NestJS API + uploads PVC |
-| `service.yaml` | ClusterIP (port 80 → app port) |
+| `frontend-deployment.yaml` / `frontend-service.yaml` | Next.js UI |
-| `ingress.yaml` | Nginx ingress with cert-manager TLS |
+| `postgres-*.yaml` / `redis-*.yaml` | Control-plane database & queue |
-| `secret.yaml` | User env vars as K8s Secret |
+| `ingress.yaml` | Frontend / API / panel host rules (+ TLS) |
-| `db-deployment.yaml` | PostgreSQL or MySQL with health probes |
+| `secret.yaml` | JWT, DB, registry, SMS and other platform secrets |
-| `db-service.yaml` | Database ClusterIP service |
+| `migrations-configmap.yaml` / `migrations-job.yaml` | Optional SQL migration Job (`migrations.enabled`) |
-| `db-pvc.yaml` | Database storage (resource-policy: keep) |
+| `namespace.yaml` / `_helpers.tpl` / `NOTES.txt` | Namespace + chart helpers |
-| `db-secret.yaml` | Database credentials (resource-policy: keep) |
+
-| `wp-pvc.yaml` | WordPress wp-content PVC (resource-policy: keep) |
+Key values: `ingress.enabled`, `ingress.tls.*`, `ingress.frontend.host` / `ingress.api.host`,
-| `registry-pull-secret.yaml` | imagePullSecret for insecure registry |
+`postgres.password`, `secrets.jwtSecret`, `migrations.enabled`.
+
+### cloudhost-app — a single user application
+
+| Template | Purpose |
+|----------|---------|
+| `deployment.yaml` | App pod (imagePullSecret, probes, WordPress volumes, env) |
+| `service.yaml` / `ingress.yaml` | ClusterIP + ingress with TLS |
+| `secret.yaml` | User env vars as a K8s Secret |
+| `db-deployment.yaml` / `db-service.yaml` / `db-pvc.yaml` / `db-secret.yaml` | Optional managed PostgreSQL/MySQL/MariaDB/MongoDB |
+| `redis-deployment.yaml` / `rabbitmq-deployment.yaml` | Optional attached services |
+| `app-storage-pvc.yaml` | App persistent storage |
+| `storageclass.yaml` | Expandable StorageClass (created on demand) |
+| `registry-pull-secret.yaml` | imagePullSecret for the in-cluster registry |
+| `fluent-bit-configmap.yaml` / `log-shipper-configmap.yaml` / `_log-shipper.tpl` / `elasticsearch-credentials-secret.yaml` | Per-app log shipping to Elasticsearch |
+
+### cloudhost-logging — observability
+
+Elasticsearch / Kibana / Fluent-bit stack for centralized build and runtime logs
+(also see `backend/k8s/logging/`).
 
 ---
 
 ## 📁 Project Structure
 
 ```
-host/
+cloud-host/
-├── ARCHITECTURE.md
+├── ARCHITECTURE.md  README.md  RUNBOOK.fa.md  CHANGELOG.md  CONTRIBUTING.md
-├── README.md
+├── UPGRADE.md  UPGRADE.en.md   docker-compose.yml
-├── CHANGELOG.md
+├── backend/                         # NestJS 11 API
-├── CONTRIBUTING.md
-├── docker-compose.yml
-├── backend/
 │   ├── Dockerfile
-│   ├── package.json
+│   ├── helm/{cloudhost-platform, cloudhost-app, cloudhost-logging}/
-│   ├── helm/cloudhost-platform/  # Helm chart for control plane
+│   ├── k8s/{logging, mail}/         # standalone manifests
-│   ├── helm/cloudhost-app/       # Helm chart for user apps
+│   ├── migrations/                  # SQL migrations (one-off Jobs in prod)
-│   ├── src/
-│   │   ├── main.ts / app.module.ts
-│   │   ├── auth/                 # JWT + Passport
-│   │   ├── users/                # User management
-│   │   ├── applications/         # App CRUD + upload
-│   │   ├── deployments/          # Deploy orchestration
-│   │   ├── clusters/             # Multi-cluster (admin)
-│   │   ├── kubernetes/           # K8s client + Helm service
-│   │   ├── build/                # Kaniko builds (BullMQ)
-│   │   ├── billing/              # Wallet + transactions
-│   │   ├── lifecycle/            # Auto-suspend/delete
-│   │   ├── snapshots/            # App snapshots
-│   │   └── tickets/              # Support tickets
-│   └── templates/                # Legacy Handlebars (deprecated)
-├── frontend/
-│   ├── Dockerfile
-│   ├── package.json
 │   └── src/
-│       ├── app/dashboard/        # Apps, deploy, admin pages
+│       ├── main.ts / app.module.ts
-│       ├── components/
+│       ├── auth/  users/  admin/    # OTP auth, users, super-admin dashboard
-│       ├── lib/                  # API client, auth store
+│       ├── applications/  application-migrations/
-│       └── types/                # Shared TS interfaces
+│       ├── deployments/             # orchestration (build → Helm)
-└── uploads/                      # User-uploaded code archives
+│       ├── build/                   # build.service: runtime detection + per-runtime Dockerfiles + Kaniko
+│       ├── kubernetes/              # K8s client, Helm, registry
+│       ├── clusters/                # multi-cluster management
+│       ├── billing/  lifecycle/  snapshots/  tickets/  access/  notifications/
+│       ├── common/                  # enums, guards, decorators
+│       └── config/                  # env + TypeORM config
+└── frontend/                        # Next.js 16 (App Router, fa-IR / en-US)
+    ├── Dockerfile                   # ARG NEXT_PUBLIC_API_URL
+    └── src/
+        ├── middleware.ts            # locale routing + landing/panel split
+        ├── app/[lang]/{page, login, register, blog, dashboard/*}
+        ├── components/  hooks/  lib/  types/
+        └── i18n/                    # dictionaries, provider, switcher
 ```
 
 ---
 
 ## 🔮 Future Considerations
 
-1. Custom domains with auto TLS via cert-manager
+1. Per-app horizontal autoscaling (HPA) based on CPU/memory
-2. Horizontal Pod Autoscaler based on CPU/memory
+2. WebSocket/SSE for real-time build log streaming (currently polled)
-3. WebSocket/SSE for real-time build log streaming
+3. A Redis-backed build queue (so builds survive a replica restart and the control plane can scale out)
-4. GitOps integration (ArgoCD)
+4. In-cluster image vulnerability scanning (report-only)
-5. Additional runtimes (Python, Go, Rust)
+5. GitOps integration (e.g. ArgoCD) and git-push-to-deploy
-6. App marketplace with pre-built templates
+6. Automated control-plane database backups (scheduled `pg_dump` + retention)
-7. Per-app resource consumption dashboards
+7. App marketplace with pre-built templates

AUDIT-STATUS.fa.md

@@ -0,0 +1,172 @@
+# وضعیت رفع یافته‌های گزارش ممیزی CloudHost
+
+> مرجع: `AUDIT-REPORT.fa.pdf` / `scripts/audit-report.fa.html`  
+> آخرین به‌روزرسانی: ۳ تیر ۱۴۰۴ (3 Jul 2026)
+
+| نماد | معنی |
+|------|------|
+| ✅ | رفع شده |
+| ⚠️ | جزئی / نیاز به پیکربندی محیط |
+| 🔜 | عمداً به تعویق افتاده (اسکوپ بزرگ یا trade-off) |
+
+---
+
+## خلاصه
+
+| دسته | تعداد | ✅ | ⚠️ | 🔜 |
+|------|-------|----|----|-----|
+| بلاکرهای پروداکشن | 8 | 8 | 0 | 0 |
+| بیلد و Kaniko | 10 | 9 | 0 | 1 |
+| دیپلوی و پیش‌نمایش | 6 | 6 | 0 | 0 |
+| دیتابیس / سرویس اختیاری | 9 | 8 | 0 | 1 |
+| Migration / اسکیما | 4 | 4 | 0 | 0 |
+| بیلینگ و امنیت مالی | 5 | 5 | 0 | 0 |
+| GitOps / CI-CD | 4 | 4 | 0 | 0 |
+| امنیت اپ / auth | 6 | 3 | 0 | 3 |
+| بهبود / زیرساخت | 5 | 2 | 1 | 2 |
+
+**نتیجه:** همه بلاکرهای پروداکشن و تقریباً همه باگ‌های قطعی رفع شده‌اند. موارد باقی‌مانده عمدتاً پیکربندی آینه رجیستری، JWT در localStorage، و پاک‌سازی PVC یتیم هستند.
+
+---
+
+## ۱. بلاکرهای پروداکشن (اولویت ۱–۸)
+
+| # | یافته | وضعیت | اقدام |
+|---|--------|--------|-------|
+| 1 | شارژ رایگان کیف پول (`POST /billing/wallet/charge`) | ✅ | HMAC + گارد production در `billing-wallet.controller.ts` |
+| 2 | دیپلوی بدون پرداخت | ✅ | گارد بیلینگ در `triggerDeployment`, `startDeployment`, `PATCH resources` |
+| 3 | namespace از ۸ کاراکتر UUID | ✅ | `userIdSlug` / `userNamespace` با UUID کامل |
+| 4 | migration بدون ردیابی نسخه | ✅ | `schema_migrations` + `000_base_schema.sql` + pre-upgrade hook |
+| 5 | `015` ستون `user_id` / `001` بدون گارد TYPE | ✅ | اصلاح نام ستون + `IF NOT EXISTS` |
+| 6 | workflow Gitea بدون تست | ✅ | job تست + rebase در `.gitea/workflows/build-deploy.yaml` |
+| 7 | رمز هاردکد Elasticsearch | ✅ | حذف از git + SealedSecret |
+| 8 | COPY گو / `\|\| echo` Node | ✅ | اصلاح در `build.service.ts` |
+
+---
+
+## ۲. بیلد (Kaniko + Dockerfile)
+
+| یافته | وضعیت | یادداشت |
+|--------|--------|---------|
+| Go COPY نامعتبر | ✅ | |
+| Node build failure نادیده | ✅ | `npm ci` + fail-on-build |
+| Laravel extensions | ✅ | mbstring, xml, bcmath, zip, fileinfo, tokenizer |
+| Python pyproject.toml | ✅ | تشخیص + نصب poetry/pdm |
+| Kaniko 4Gi / PVC بدون SC | ✅ | limits قابل تنظیم + `BUILD_PVC_STORAGE_CLASS` |
+| Git token در spec / branch injection / SSRF | ✅ | GIT_ASKPASS + Secret + validation |
+| Zip slip در unzip | ✅ | اعتبارسنجی مسیر قبل و بعد از extract |
+| state بیلد در حافظه | ✅ | Redis session + startup recovery |
+| دیپلوی هم‌زمان بدون قفل | ✅ | in-flight guard در `triggerDeployment` |
+| Base image بدون آینه | ✅ | `build.images` در Helm values + پیش‌فرض Harbor در configuration |
+| zip bomb (۱۰GiB) | 🔜 | سقف آپلود موجود؛ محدودیت تعداد entry در archive پیشنهاد می‌شود |
+
+---
+
+## ۳. دیپلوی و پیش‌نمایش
+
+| یافته | وضعیت | یادداشت |
+|--------|--------|---------|
+| حذف preview با custom domain pending | ✅ | `hasVerifiedCustomDomain()` در k8s + deployments |
+| getPreviewInfo پچ NodePort | ✅ | فقط خواندن؛ ingressUrl اولویت دارد |
+| fallback بین‌کلاستری → ImagePullBackOff | ✅ | `CLUSTER_DEPLOY_FALLBACK_ENABLED=true` برای fallback |
+| NodePort host از API server | ⚠️ | `getClusterHostIp` همچنان fallback؛ ingressUrl مسیر اصلی |
+| suspend NodePort revoke | ✅ | `deleteTemporaryAccessServicesForApp` در suspend |
+
+---
+
+## ۴. دیتابیس و سرویس‌های اختیاری
+
+| یافته | وضعیت | یادداشت |
+|--------|--------|---------|
+| Redis/RabbitMQ randAlphaNum | ✅ | الگوی `lookup` در helm templates |
+| probe بدون auth | ✅ | redis-cli `-a` / mongo با credential |
+| RWO بدون Recreate | ✅ | `strategy: Recreate` |
+| dbPassword fallback هر deploy | ✅ | generate + persist در DB |
+| Mongo snapshot/restore | ✅ | |
+| WordPress MySQL اجباری | ✅ | |
+| wp-content restore از PVC | ✅ | |
+| PVC یتیم بعد از suspend/delete | 🔜 | نیاز به job پاک‌سازی دوره‌ای |
+| ایمیج DB از Docker Hub | ⚠️ | آینه در `values.yaml`؛ پیکربندی per-cluster |
+
+---
+
+## ۵. Migration / اسکیما
+
+| یافته | وضعیت |
+|--------|--------|
+| Job دوباره همه SQL | ✅ |
+| post-upgrade → pre-upgrade | ✅ |
+| نبود base schema | ✅ |
+| 015 user_id | ✅ |
+
+---
+
+## ۶. بیلینگ
+
+| یافته | وضعیت |
+|--------|--------|
+| wallet charge بدون درگاه | ✅ |
+| proration اشتباه | ✅ |
+| race در wallet | ✅ | pessimistic lock |
+| auto-renew دو بار بین replicas | ✅ | lock روی Application در transaction |
+| دیپلوی بدون پرداخت | ✅ |
+
+---
+
+## ۷. GitOps / CI-CD
+
+| یافته | وضعیت |
+|--------|--------|
+| workflow بدون تست | ✅ |
+| elastic password در git | ✅ |
+| platform Redis requirepass | ✅ |
+| backend RollingUpdate + limits + postgres backup | ✅ |
+| Swagger در production | ✅ |
+| RUNBOOK-DEPLOY portable | ✅ | commit `6d9cd89` |
+
+---
+
+## ۸. امنیت اپلیکیشن
+
+| یافته | وضعیت | یادداشت |
+|--------|--------|---------|
+| gitToken / dbPassword در API | ✅ | `@Exclude` + `hasDbPassword` / `hasGitToken` |
+| Elasticsearch log isolation | ✅ | namespace کامل |
+| OTP Math.random | ✅ | `crypto.randomInt` |
+| OTP consume race | ✅ | pessimistic lock در transaction |
+| JWT در localStorage | 🔜 | نیاز به httpOnly cookie + CSRF — اسکوپ frontend بزرگ |
+| refresh token rotation | 🔜 | |
+| secret پیش‌فرض dev | ⚠️ | `validate-production-config` در production fail می‌کند |
+| docker compose NODE_ENV=production | ✅ | `NODE_ENV: development` برای dev محلی |
+
+---
+
+## ۹. بهبود / زیرساخت
+
+| یافته | وضعیت |
+|--------|--------|
+| Backend Dockerfile helm/kubectl از اینترنت | 🔜 | mirror یا COPY از stage |
+| orphan PVC cleanup | 🔜 |
+| zip bomb hard limit | 🔜 |
+
+---
+
+## متغیرهای محیطی جدید (مرجع deploy)
+
+| متغیر | پیش‌فرض | توضیح |
+|--------|---------|-------|
+| `CLUSTER_DEPLOY_FALLBACK_ENABLED` | `false` | fallback بین کلاستر |
+| `CLUSTER_DEPLOY_FALLBACK_ATTEMPTS` | `3` | فقط وقتی fallback فعال |
+| `BASE_IMAGE_REGISTRY` | `registry.abrban.com/proxy-dockerhub/library` | آینه base imageهای بیلد (یا از `build` در Helm values) |
+| `KANIKO_IMAGE` | `registry.abrban.com/proxy-gcr/...` | Kaniko executor (یا `build.images.kaniko` در values) |
+| `BUILD_PVC_STORAGE_CLASS` | — | StorageClass برای PVC بیلد |
+| `BILLING_WALLET_HMAC_SECRET` | — | اجباری در production |
+| `PAYMENT_GATEWAY_*` | — | اجباری برای charge واقعی |
+
+---
+
+## commitهای مرتبط
+
+- `22359be` — fix(platform): apply production hardening from audit plan
+- `6d9cd89` — docs: add portable from-zero deploy runbook and GitOps templates
+- *(uncommitted)* — رفع موارد باقی‌مانده این سند (preview، OTP، zip slip، auto-renew lock، docker-compose)

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 CloudHost
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,303 +1,331 @@
 # ☁️ CloudHost — Self-Service PaaS Platform
 
-A self-service Platform-as-a-Service (PaaS) that lets developers deploy **Node.js**, **Laravel**, and **WordPress** applications onto Kubernetes with zero DevOps overhead. Includes wallet-based billing, automated lifecycle management, and Helm-based deployments.
+A self-service Platform-as-a-Service (PaaS) that lets developers deploy applications
+onto Kubernetes with zero DevOps overhead. Source code is turned into a container
+image **inside the cluster** with Kaniko (no Docker daemon), then rolled out with Helm —
+complete with managed databases, wallet-based billing, automated lifecycle management,
+live logs, and a bilingual (Persian/English) panel.
+
+Supported runtimes — each built from a platform-maintained `Dockerfile` template:
+**Node.js, Laravel, Go, PHP, Python, Django, .NET**, and **WordPress** (official image +
+custom `wp-content` entrypoint).
+
+> 🇮🇷 Production deployment on the `abrban.com` k3s cluster — including all the
+> Iran-network workarounds — is documented step-by-step in **[RUNBOOK.fa.md](RUNBOOK.fa.md)** (Persian).
+
+> 🔄 **CI/CD (Gitea Actions → Kaniko → Harbor → Argo CD):** see **[RUNBOOK-CICD.fa.md](RUNBOOK-CICD.fa.md)** (Persian) and **[gitops/README.md](gitops/README.md)** for bootstrap (`seed-ci-images`, Sealed Secrets, two-repo GitOps layout).
+>
+> 🚀 **Deploy from zero (any cluster):** **[RUNBOOK-DEPLOY.fa.md](RUNBOOK-DEPLOY.fa.md)** — server checklist, values, secrets, logging, greenfield reset.
 
 ---
 
 ## Architecture Overview
 
 ```
-┌─────────────┐          ┌─────────────────┐        ┌──────────────┐
+┌──────────────┐   REST    ┌──────────────────┐   K8s API   ┌──────────────┐
-│  Next.js 16  │  REST   │   NestJS API     │  K8s   │  Kubernetes  │
+│  Next.js 16   │ /api/v1   │   NestJS 11 API   │  + Helm     │  Kubernetes  │
-│  Frontend    │◄───────►│   Backend        │◄──────►│  Cluster(s)  │
+│  Frontend     │◄─────────►│   Backend         │◄───────────►│  Cluster(s)  │
-└─────────────┘          └────────┬────────┘        └──────────────┘
+└──────────────┘           └────────┬─────────┘             └──────┬───────┘
-                                  │
+                                    │                                │ build Jobs
-                       ┌──────────┼──────────┐
+                  ┌─────────────────┼─────────────────┐             ▼
-                       ▼          ▼          ▼
+                  ▼                 ▼                 ▼         ┌──────────┐
-                  PostgreSQL    Redis     Container
+              PostgreSQL          Redis           Registry     │  Kaniko  │
-                                (Bull)    Registry
+                16            (cache + Bull)        (:2)        └──────────┘
 ```
 
 | Layer            | Technology                                                        |
-| ------------ | ------------------------------------------------------- |
+| ---------------- | ----------------------------------------------------------------- |
-| Frontend     | Next.js 16, Tailwind CSS v4, React Query, Zustand       |
+| Frontend         | Next.js 16 (App Router, SSR), React 19, Tailwind CSS v4, React Query, Zustand |
 | Backend API      | NestJS 11, TypeORM, Passport JWT, Bull (Redis)                    |
-| Build Engine | Kaniko (in-cluster, daemon-less Docker builds)          |
+| Build engine     | **Kaniko** (daemon-less in-cluster builds) with platform-generated per-runtime Dockerfiles |
-| Deployment   | Helm v3 charts, @kubernetes/client-node                 |
+| Source ingestion | Uploaded archive (zip/tar.gz) streamed into a build PVC, **or** git clone |
-| Database     | PostgreSQL 16                                           |
+| Deployment       | Helm v3 charts, `@kubernetes/client-node`                        |
-| Queue        | Redis 7 + BullMQ                                        |
+| Database         | PostgreSQL 16 (control plane); per-app MySQL/MariaDB/PostgreSQL/MongoDB |
+| Queue / cache    | Redis 7 + Bull (service-access grants, app migrations)           |
+| Registry         | In-cluster `registry:2`                                          |
+| Auth             | Mobile number + **OTP** (SMS) and password, JWT access/refresh   |
 
-> 📖 See [ARCHITECTURE.md](ARCHITECTURE.md) for detailed system design.
+> 📖 See **[ARCHITECTURE.md](ARCHITECTURE.md)** for detailed system design.
-> 🔼 See [UPGRADE.en.md](UPGRADE.en.md) ([فارسی](UPGRADE.md)) for the latest dependency-upgrade notes (React 19, Next 16, NestJS 11, Tailwind 4, k8s-client v1).
+> 🔼 See [UPGRADE.en.md](UPGRADE.en.md) ([فارسی](UPGRADE.md)) for dependency-upgrade notes.
+> 📋 See [RUNBOOK.en.md](RUNBOOK.en.md) ([فارسی](RUNBOOK.fa.md)) for operations.
 
 ---
 
 ## Features
 
 ### For Developers
-- 🚀 **One-click deploys** from uploaded code archive (zip)
+- 🚀 **Deploy from a code archive (zip/tar.gz) _or_ a git URL** (public or private via token)
-- 🟢 **Node.js** — auto-detected via `package.json` (npm build & start)
+- 🟢 **Multi-runtime** — Node.js, Laravel, Go, PHP, Python, Django, .NET, each built from a maintained Dockerfile template
-- 🟣 **Laravel** — PHP 8.x + Nginx + Supervisor (auto-detected via `artisan`)
+- 🔵 **WordPress** — official image + custom entrypoint that merges your `wp-content`
-- 🔵 **WordPress** — official image + custom entrypoint for wp-content merging
+- 🗄️ **Managed databases & services** — PostgreSQL, MySQL, MariaDB, MongoDB, Redis, RabbitMQ provisioned via Helm
-- 🗄️ **Managed databases** — PostgreSQL or MySQL provisioned via Helm
+- 💰 **Wallet system** — deposit funds, pay per plan (hourly / monthly / yearly), coupons & discounts
-- 💰 **Wallet system** — deposit funds, pay for plans (hourly/monthly/yearly)
+- 📊 **Live build & runtime logs** (Elasticsearch-backed) + deployment history with rollback
-- 📊 **Live logs** & deployment history with rollback
+- 🔒 **Environment variables** stored as Kubernetes Secrets
-- 🔒 **Environment variables** managed as Kubernetes Secrets
+- ⚙️ **Resource controls** — CPU, memory, replicas, expandable disk
-- ⚙️ **Resource controls** — CPU, memory, replica count
+- 🌐 **Custom domains** with automatic TLS
-- 📸 **Snapshots** — backup and restore application state
+- 📸 **Snapshots** — backup & restore application state
-- 🎫 **Support tickets** — in-app support system
+- 🎫 **Support tickets** with technical/sales departments
 
 ### For Super Admins
-- 🖥️ **Multi-cluster management** — register/remove Kubernetes clusters
+- 🖥️ **Multi-cluster management** — register/remove Kubernetes clusters (kubeconfig stored encrypted)
-- 👥 **User management** — activate, deactivate, change roles
+- 👥 **User management** — activate, deactivate, change roles, per-user detail dashboard
-- 📈 **Quotas** — per-cluster limits (CPU, memory, max apps)
+- 📈 **Quotas & pricing** — per-cluster limits and a configurable pricing catalog
-- 💳 **Billing oversight** — view all transactions, manage wallet deposits
+- 💳 **Billing oversight** — transactions, invoices, wallet deposits, global discount
-- ⏱️ **Lifecycle settings** — configure grace periods per billing cycle
+- ⏱️ **Lifecycle settings** — grace periods per billing cycle
-- 🔐 **RBAC** — role-based guards on every endpoint
+- 🔐 **RBAC** — role-based guards on every endpoint (`user` / `admin` / `technical` / `sales`)
+
+---
+
+## How the Build & Deploy Pipeline Works
+
+When a user triggers a deploy, the backend runs the build-and-deploy pipeline and creates
+the build as a **Kubernetes Job** in the `cloudhost-builds` namespace:
+
+```
+1. SOURCE
+   ├─ uploaded archive → saved to disk (UPLOAD_DIR) → streamed into a per-build PVC
+   │   via a short-lived helper pod + `kubectl cp`, then unpacked   (init: prepare source)
+   └─ git URL → cloned in-pod; private repos inject the token into the clone URL  (init: git-clone)
+
+2. DOCKERFILE
+   The platform detects the runtime (or uses the app's selected runtime) and generates a
+   Dockerfile for it — Node.js, Laravel, WordPress, Go, PHP, Python, Django, or .NET.
+
+3. BUILD  (container: kaniko)
+   Kaniko builds the image (layer cache per user) and pushes it to the in-cluster
+   registry — no Docker daemon, no privileged pod.
+
+4. DEPLOY
+   Helm installs/upgrades the `cloudhost-app` chart → Deployment, Service, Ingress,
+   per-app DB/Redis/RabbitMQ, PVCs, Secrets, log shipper. App goes live at its subdomain.
+```
+
+The build runs inline within the deploy request and its progress/logs are tracked in
+memory, then polled by the frontend. (Bull/Redis queues are used elsewhere — service-access
+grants and application migrations — but not for image builds.)
 
 ---
 
 ## Project Structure
 
 ```
-host/
+cloud-host/
-├── ARCHITECTURE.md          # Detailed architecture document
 ├── README.md                 # This file
-├── CHANGELOG.md             # Version history
+├── ARCHITECTURE.md           # Detailed system design
-├── CONTRIBUTING.md          # Development workflow & conventions
+├── RUNBOOK.fa.md             # Persian runbook: local dev + abrban/k3s production deploy
-├── docker-compose.yml       # Local dev / production compose
+├── RUNBOOK-DEPLOY.fa.md      # Deploy platform from zero (any cluster): values, secrets, health checks
+├── RUNBOOK-CICD.fa.md        # CI/CD pipeline: Gitea Actions → Kaniko → Argo CD
+├── CHANGELOG.md / CONTRIBUTING.md / UPGRADE.md / UPGRADE.en.md
+├── docker-compose.yml        # Local dev stack (Postgres + Redis + API + UI)
 │
-├── backend/                 # NestJS API
+├── backend/                  # NestJS 11 API (REST under /api/v1)
 │   ├── Dockerfile
-│   ├── package.json
 │   ├── helm/
-│   │   ├── cloudhost-platform/  # Helm chart (control plane)
+│   │   ├── cloudhost-platform/   # Helm chart — control plane (API, UI, Postgres, Redis)
-│   │   └── cloudhost-app/       # Helm chart (user apps)
+│   │   ├── cloudhost-app/        # Helm chart — a single user application + its services
-│   │       ├── Chart.yaml
+│   │   └── cloudhost-logging/    # Helm chart — Elasticsearch / Kibana / Fluent-bit
-│   │       ├── values.yaml
+│   ├── k8s/                  # Standalone manifests (logging, mail)
-│   │       └── templates/   # K8s manifest templates
+│   ├── migrations/           # SQL migrations (applied via one-off Jobs in prod)
-│   ├── src/
-│   │   ├── main.ts / app.module.ts
-│   │   ├── auth/            # JWT auth (register, login, refresh)
-│   │   ├── users/           # User CRUD + admin ops
-│   │   ├── applications/    # Application CRUD + code upload
-│   │   ├── deployments/     # Deployment pipeline orchestration
-│   │   ├── clusters/        # Cluster management (admin)
-│   │   ├── kubernetes/      # K8s client + Helm service
-│   │   ├── build/           # Kaniko build jobs (Bull queue)
-│   │   ├── billing/         # Wallet, transactions, plan costs
-│   │   ├── lifecycle/       # Auto-suspend/delete scanner
-│   │   ├── snapshots/       # App snapshot management
-│   │   ├── tickets/         # Support ticket system
-│   │   ├── common/          # Enums, decorators, guards
-│   │   └── config/          # Env configuration loader
-│   └── templates/           # Legacy Handlebars templates (deprecated)
-│
-├── frontend/                # Next.js 14 App Router
-│   ├── Dockerfile
-│   ├── package.json
 │   └── src/
-│       ├── app/
+│       ├── main.ts / app.module.ts
-│       │   ├── login/ & register/
+│       ├── auth/             # Mobile-OTP + password login, JWT strategies, role guards
-│       │   └── dashboard/
+│       ├── users/            # User CRUD, profile, phone verification
-│       │       ├── apps/    # App list + detail (lifecycle status)
+│       ├── admin/            # Super-admin user-detail dashboard & ops
-│       │       ├── deploy/  # Multi-step deploy wizard
+│       ├── applications/     # App CRUD, code upload (→ disk), git config
-│       │       └── admin/   # Admin: users, clusters, billing, apps
+│       ├── application-migrations/  # Import/migrate existing apps (Bull queue)
-│       ├── components/
+│       ├── deployments/      # Deploy orchestration, history, stop/restart
-│       ├── lib/             # API client, auth store
+│       ├── build/            # Kaniko build (build.service): per-runtime Dockerfile generation
-│       ├── hooks/
+│       ├── kubernetes/       # K8s client, Helm wrapper, registry service
-│       └── types/           # TypeScript interfaces
+│       ├── clusters/         # Multi-cluster management, kubeconfig storage
+│       ├── billing/          # Wallet, transactions, invoices, pricing catalog, coupons
+│       ├── lifecycle/        # Scanner: auto-suspend/delete expired apps
+│       ├── snapshots/        # App snapshot/restore
+│       ├── tickets/          # Support tickets
+│       ├── notifications/    # User notifications
+│       ├── access/           # Time-limited external service access (NodePort grants, Bull queue)
+│       ├── common/           # Enums, guards, decorators
+│       └── config/           # Env configuration loader + TypeORM config
 │
-└── uploads/                 # User-uploaded code archives
+├── frontend/                 # Next.js 16 App Router (bilingual fa-IR / en-US)
+│   ├── Dockerfile            # ARG NEXT_PUBLIC_API_URL baked at build time
+│   └── src/
+│       ├── middleware.ts     # Locale routing + landing (abrban.com) vs panel split
+│       ├── app/[lang]/
+│       │   ├── page.tsx      # Landing
+│       │   ├── login/ register/
+│       │   ├── blog/
+│       │   └── dashboard/    # apps, deploy, logs, invoices, wallet, services,
+│       │       │             #   tickets, account, staff, admin
+│       │       └── ...
+│       ├── components/  hooks/  lib/ (API client, auth store)  types/
+│       └── i18n/             # Dictionaries, provider, language switcher
 ```
 
 ---
 
-## Quick Start
+## Quick Start (Local Development)
 
-### Prerequisites
+**Prerequisites:** Node.js ≥ 20, Docker & Docker Compose, and (for actually building/deploying
+user apps) a Kubernetes cluster reachable via kubeconfig.
 
-| Tool            | Version |
+> ℹ️ The API and UI run fine locally against Postgres + Redis. The **build/deploy pipeline
-| --------------- | ------- |
+> itself runs as Kubernetes Jobs**, so triggering a real user-app build requires a cluster
-| Node.js         | ≥ 20    |
+> (with the in-cluster registry). For pure UI/API development you don't need one.
-| Docker & Compose| ≥ 24    |
-| PostgreSQL      | 16      |
-| Redis           | 7       |
-| Helm            | ≥ 3.12  |
 
-### 1. Clone & Install
+### 1. Clone & install
 
 ```bash
-git clone <repo-url> host && cd host
+git clone <repo-url> cloud-host && cd cloud-host
 cd backend && npm install && cd ..
 cd frontend && npm install && cd ..
 ```
 
-### 2. Environment Variables
+### 2. Environment variables
 
 ```bash
 cp backend/.env.example backend/.env
 cp frontend/.env.local.example frontend/.env.local
-# Edit both files with your DB, JWT, Redis, and registry settings
+# Edit both — at minimum DB, JWT, Redis. See the Configuration table below.
 ```
 
-### 3. Run with Docker Compose
+### 3. Start Postgres + Redis
 
 ```bash
-docker compose up --build
+docker compose up -d postgres redis
 ```
 
-Backend at port 4000, Frontend at port 3000.
+### 4. Run the apps
-
-### 4. Deploy Platform on Kubernetes (Helm)
-
-Prerequisites: NGINX Ingress, cert-manager (if TLS enabled), StorageClass for PVCs.
 
 ```bash
-# Build images (set API URL to match ingress.api.host when TLS is on)
+# Terminal 1 — Backend (http://localhost:4000, prefix /api/v1, Swagger at /docs)
-export REG=your-registry.example.com
-docker build -t $REG/cloudhost-backend:latest ./backend
-docker build -t $REG/cloudhost-frontend:latest \
-  --build-arg NEXT_PUBLIC_API_URL=https://api.platform.example.com ./frontend
-docker push $REG/cloudhost-backend:latest $REG/cloudhost-frontend:latest
-
-# Install (copy and edit values-production.example.yaml first)
-helm upgrade --install cloudhost ./backend/helm/cloudhost-platform \
-  -n cloudhost --create-namespace \
-  -f backend/helm/cloudhost-platform/values-production.example.yaml
-```
-
-Key values: `ingress.enabled`, `ingress.tls.enabled`, `ingress.frontend.host`, `ingress.api.host`, `postgres.password`, `secrets.jwtSecret`.
-
-See chart defaults in `backend/helm/cloudhost-platform/values.yaml` and post-install notes via `helm get notes cloudhost -n cloudhost`.
-
-### 5. Run Locally (development)
-
-```bash
-# Terminal 1 — Backend
 cd backend && npm run start:dev
 
-# Terminal 2 — Frontend
+# Terminal 2 — Frontend (http://localhost:3000)
 cd frontend && npm run dev
 ```
 
----
+In development `NODE_ENV=development`, so TypeORM `synchronize` builds the schema
+automatically and the pricing catalog self-seeds. Set `frontend` `NEXT_PUBLIC_API_URL`
+to the backend URL.
 
-## API Endpoints
+> To run the **whole** stack (API + UI + Postgres + Redis) in containers instead:
-
+> `docker compose up --build` (backend on `:4000`, frontend on `:3000`).
-All endpoints prefixed with `/api/v1`. Full Swagger docs at `http://localhost:4000/docs`.
-
-### Auth
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /auth/register | Create account |
-| POST | /auth/login | Get JWT tokens |
-| POST | /auth/refresh | Refresh access token |
-
-### Applications
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /applications | Create app |
-| GET | /applications | List user's apps |
-| GET | /applications/:id | App details |
-| PATCH | /applications/:id | Update app |
-| DELETE | /applications/:id | Delete app + K8s resources |
-
-### Deployments
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /applications/:appId/deployments | Trigger deploy |
-| GET | /applications/:appId/deployments | List deployments |
-| GET | /deployments/:id | Deployment detail |
-| GET | /deployments/:id/logs | Pod logs |
-| POST | /deployments/:id/stop | Stop deployment |
-| POST | /deployments/:id/restart | Restart deployment |
-
-### Billing
-| Method | Path | Description |
-|--------|------|-------------|
-| GET | /billing/balance | Get wallet balance |
-| POST | /billing/deposit | Add funds to wallet |
-| GET | /billing/transactions | Transaction history |
-| POST | /billing/pay/:appId | Pay for app plan |
-
-### Lifecycle (Admin)
-| Method | Path | Description |
-|--------|------|-------------|
-| GET | /lifecycle/settings | Get retention periods |
-| PATCH | /lifecycle/settings | Update retention periods |
-
-### Snapshots
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /snapshots | Create snapshot |
-| GET | /snapshots | List snapshots |
-| POST | /snapshots/:id/restore | Restore snapshot |
-
-### Tickets
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /tickets | Create ticket |
-| GET | /tickets | List tickets |
-| PATCH | /tickets/:id | Update ticket |
-
-### Users
-| Method | Path | Description |
-|--------|------|-------------|
-| GET | /users/me | Current user |
-| PATCH | /users/me | Update profile |
-
-### Admin — Users
-| Method | Path | Description |
-|--------|------|-------------|
-| GET | /users | List all users |
-| PATCH | /users/:id/activate | Activate user |
-| PATCH | /users/:id/deactivate | Deactivate user |
-| PATCH | /users/:id/role | Change role |
-
-### Admin — Clusters
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | /clusters | Add cluster |
-| GET | /clusters | List clusters |
-| GET | /clusters/:id | Cluster details |
-| PATCH | /clusters/:id | Update cluster |
-| DELETE | /clusters/:id | Remove cluster |
 
 ---
 
-## Configuration
+## Deploy on Kubernetes (Helm)
+
+> **Production GitOps (from zero):** [`RUNBOOK-DEPLOY.fa.md`](RUNBOOK-DEPLOY.fa.md) — variable table, values, Sealed Secrets, logging, health checks.
+>
+> **Production abrban.com specifics:** [`RUNBOOK.fa.md`](RUNBOOK.fa.md) — Iran network, Ceph, Harbor details.
+>
+> **CI/CD pipeline:** [`RUNBOOK-CICD.fa.md`](RUNBOOK-CICD.fa.md).
+
+This section is the **generic Helm-only** path (Path B in RUNBOOK-DEPLOY) without Gitea/Argo.
+
+**Prerequisites:** a Kubernetes cluster, an Ingress controller (Traefik on k3s by default,
+or set `INGRESS_CLASS=nginx`), a default StorageClass for PVCs, and a container registry
+reachable by the cluster.
+
+### 1. Build & push the platform images
+
+```bash
+export REG=your-registry.example.com
+docker build -t $REG/cloudhost-backend:1.0.0 ./backend
+docker build -t $REG/cloudhost-frontend:1.0.0 \
+  --build-arg NEXT_PUBLIC_API_URL=https://api.platform.example.com ./frontend
+docker push $REG/cloudhost-backend:1.0.0
+docker push $REG/cloudhost-frontend:1.0.0
+```
+
+### 2. Install the control plane
+
+```bash
+cp backend/helm/cloudhost-platform/values-production.example.yaml my-values.yaml
+# Edit my-values.yaml: image tags, ingress hosts, postgres password, jwtSecret, registry, SMS/OTP
+
+helm upgrade --install cloudhost ./backend/helm/cloudhost-platform \
+  -n cloudhost --create-namespace \
+  -f my-values.yaml \
+  --set images.backend.tag=1.0.0 \
+  --set images.frontend.tag=1.0.0
+```
+
+Key values: `ingress.enabled`, `ingress.tls.*`, `ingress.frontend.host`, `ingress.api.host`,
+`postgres.password`, `secrets.jwtSecret`, `migrations.enabled`. Chart defaults live in
+`backend/helm/cloudhost-platform/values.yaml`; post-install notes via
+`helm get notes cloudhost -n cloudhost`.
+
+### 3. Cluster-side prerequisites for the build pipeline
+
+Ensure the `cloudhost-builds` namespace has:
+
+- the in-cluster **registry** (`registry:2`) reachable at `REGISTRY_URL`,
+- a `kaniko-builder` ServiceAccount with an `imagePullSecret` for the registry,
+- enough ephemeral storage for the per-build source PVC + helper pod.
+
+### 4. Verify
+
+```bash
+kubectl get deploy -n cloudhost            # backend & frontend 1/1
+helm status cloudhost -n cloudhost         # STATUS: deployed
+curl -s -o /dev/null -w '%{http_code}\n' https://<frontend.host>
+```
+
+---
+
+## Configuration (key env vars)
 
 | Variable | Description | Default |
 |----------|-------------|---------|
 | `PORT` | Backend port | `4000` |
-| `DB_HOST` | PostgreSQL host | `localhost` |
+| `DB_HOST` / `DB_PORT` / `DB_USERNAME` / `DB_PASSWORD` / `DB_DATABASE` | PostgreSQL connection | `localhost` / `5432` / `cloudhost` / — / `cloudhost` |
-| `DB_PORT` | PostgreSQL port | `5432` |
+| `JWT_SECRET` / `JWT_EXPIRES_IN` | Access token secret + TTL | — / `1h` |
-| `DB_USERNAME` | Database user | `cloudhost` |
+| `JWT_REFRESH_SECRET` / `JWT_REFRESH_EXPIRES_IN` | Refresh token secret + TTL | — / `7d` |
-| `DB_PASSWORD` | Database password | — |
+| `REDIS_HOST` / `REDIS_PORT` | Redis (cache + Bull queues) | `localhost` / `6379` |
-| `DB_NAME` | Database name | `cloudhost` |
+| `SMS_PROVIDER` | OTP provider (`mizbansms` \| `kavenegar`) | `mizbansms` |
-| `JWT_SECRET` | JWT signing secret | — |
+| `MIZBANSMS_USERNAME` / `MIZBANSMS_PASSWORD` / `MIZBANSMS_FROM` | OTP SMS credentials (required or OTP send 503s) | — |
-| `JWT_EXPIRES_IN` | Access token TTL | `15m` |
+| `REGISTRY_URL` / `REGISTRY_PULL_URL` | In-cluster registry (push / pull) | `registry.cloudhost-builds.svc.cluster.local:5000` |
-| `REDIS_HOST` | Redis host | `localhost` |
+| `BUILD_NAMESPACE` / `BUILD_SERVICE_ACCOUNT` | Build Jobs namespace + SA | `cloudhost-builds` / `kaniko-builder` |
-| `REDIS_PORT` | Redis port | `6379` |
+| `KANIKO_IMAGE` | Kaniko executor image | `registry.abrban.com/proxy-gcr/kaniko-project/executor:v1.23.2` |
-| `REGISTRY_URL` | Container registry URL | `localhost:30500` |
+| `BUILD_ALPINE_IMAGE` | Alpine image for build init/helper pods | `registry.abrban.com/proxy-dockerhub/library/alpine:3.19` |
-| `PLATFORM_DOMAIN` | Base domain for app subdomains | `apps.cloudhost.ir` |
+| `BUILD_ALPINE_GIT_IMAGE` | Git-clone init container image | `registry.abrban.com/proxy-dockerhub/alpine/git:2.43.0` |
-| `LIFECYCLE_SCAN_INTERVAL_MS` | Lifecycle scanner interval | `60000` |
+| `BASE_IMAGE_REGISTRY` | Harbor prefix for Docker Hub images in generated Dockerfiles | `registry.abrban.com/proxy-dockerhub/library` |
-| `LIFECYCLE_HOURLY_DELETE_AFTER_MS` | Hourly plan grace period | `3600000` (1h) |
+| `UPLOAD_DIR` | Disk path for uploaded source archives | `./uploads` |
-| `LIFECYCLE_MONTHLY_DELETE_AFTER_MS` | Monthly plan grace period | `259200000` (3d) |
+| `INGRESS_CLASS` | Ingress controller for app Ingress objects | `traefik` |
-| `LIFECYCLE_YEARLY_DELETE_AFTER_MS` | Yearly plan grace period | `604800000` (7d) |
+| `PLATFORM_DOMAIN` / `PREVIEW_BASE_DOMAIN` | Base domain for app subdomains / previews | `apps.cloudhost.local` / — |
+| `PLATFORM_STORAGE_CLASS` | StorageClass for new PVCs (needs volume expansion) | `cloudhost-expandable` |
+| `ELASTICSEARCH_HOST` / `ELASTICSEARCH_PORT` | Log search backend | cluster DNS / `9200` |
+| `LIFECYCLE_SCAN_INTERVAL_MS` | Lifecycle scanner tick | `60000` |
+
+---
+
+## Authentication
+
+Login is **mobile-number based**: the user receives a one-time SMS code (OTP) and can also
+set a password. On every request `JwtStrategy` re-reads the user's **role and active status
+from the database** (not from the token), so promotions/deactivations take effect immediately.
+Tokens: JWT access (`JWT_EXPIRES_IN`, default 1h) + refresh (7d).
+
+---
+
+## API
+
+All endpoints are prefixed with `/api/v1`. Interactive Swagger docs at
+`http://localhost:4000/api/docs`. Major route groups: `auth` (OTP request/verify, login,
+refresh), `applications`, `deployments`, `clusters`, `billing` (wallet, invoices,
+transactions, pricing), `snapshots`, `tickets`, `users`, `admin`, `notifications`.
 
 ---
 
 ## Security
 
-- **JWT** access + refresh tokens with configurable expiry
+- **JWT** access + refresh tokens; live role/active-status enforcement from DB
-- **Bcrypt** password hashing (12 rounds)
+- **Bcrypt** password hashing
-- **Helmet** HTTP security headers
+- **Helmet** HTTP security headers, **class-validator** on all DTOs
-- **RBAC** role-based route guards (`@Roles(UserRole.ADMIN)`)
+- **RBAC** role-based route guards (`@Roles(...)`)
-- **Namespace isolation** — each user deploys to their own K8s namespace
+- **Namespace isolation** — each user deploys to their own Kubernetes namespace
-- **Secrets** — env vars stored as K8s Secrets, never in plain manifests
+- **Secrets** — env vars stored as K8s Secrets
-- **Input validation** — `class-validator` on all DTOs
 
 ---
 

RUNBOOK-CEPH.fa.md

@@ -0,0 +1,346 @@
+# راهنمای Ceph برای ابربان (Rook)
+
+این سند نصب، معماری واقعی روی کلاستر **abr**، مدیریت روزمره و عیب‌یابی **Rook-Ceph** را پوشش می‌دهد.
+
+- چارت و اسکریپت‌ها: [`backend/helm/cloudhost-ceph/`](backend/helm/cloudhost-ceph/)
+- README انگلیسی: [`backend/helm/cloudhost-ceph/README.md`](backend/helm/cloudhost-ceph/README.md)
+- رجیستری: [`RUNBOOK-HARBOR.fa.md`](RUNBOOK-HARBOR.fa.md)
+
+---
+
+## چرا Ceph؟
+
+| نیاز | راه‌حل Ceph |
+|------|-------------|
+| PVC اپ/دیتابیس با **resize** | Block pool → StorageClass `rook-ceph-block` |
+| آپلود **zip** سورس کاربر | Object store (RGW) → StorageClass `rook-ceph-bucket` |
+
+یک کلاستر Ceph هر دو را پوشش می‌دهد؛ zip را روی PVC نگه ندارید — از **bucket** استفاده کنید.
+
+---
+
+## معماری روی abr (single-node)
+
+```
+registry.abrban.com
+  ├── rook/ceph:v1.20.1              → Rook operator
+  └── proxy-dockerhub/ceph/ceph:v19.2 → Ceph daemon (Squid)
+
+Node abr
+  ├── /dev/loop6 (15Gi) → OSD (bluestore raw)
+  ├── mon-a, mgr-a, osd-0, rgw → rook-ceph namespace
+  └── RGW: rook-ceph-rgw-ceph-objectstore.rook-ceph.svc:80
+```
+
+| محدودیت | توضیح |
+|---------|--------|
+| **۱ OSD** | replication=1؛ بدون HA |
+| **loop device** | دیسک خام نداریم؛ `/dev/loop6` از فایل `osd-loopback.img` |
+| **HEALTH_WARN** | طبیعی: `OSD count 1 < default size 3`، mon low space |
+| **ایمیج‌ها** | باید از قبل در Harbor mirror شده باشند (kubelet به docker.io دسترسی ندارد) |
+
+---
+
+## پیش‌نیازها
+
+### پروفایل `single-node` (کلاستر فعلی abr)
+
+- Kubernetes 1.28+ (k3s + Traefik)
+- Harbor بالا و ایمیج‌های `rook/ceph` + `ceph/ceph` mirror شده
+- حداقل **۱۵ گیگ** فضا برای loop OSD (`/var/lib/rook/osd-loopback.img`)
+- `helm` 3.x و `kubectl` با دسترسی cluster-admin
+- Secret `registry-pull-secret` در `rook-ceph` با `harbor_registry_user`
+
+### پروفایل `multi-node` (production)
+
+- حداقل **۳ نود** + دیسک خام (raw)
+- فایل values: `values-rook-cluster-multi-node.yaml`
+
+---
+
+## نصب (اولین بار — abr)
+
+### ۱. آماده‌سازی loop device برای OSD
+
+روی نود تک‌دیسک، Rook به دیسک خام نیاز دارد. یک loop device بسازید:
+
+```bash
+# روی نود (یا Job privileged — یک‌بار)
+truncate -s 15G /var/lib/rook/osd-loopback.img
+losetup --find --show /var/lib/rook/osd-loopback.img   # → /dev/loop6
+```
+
+### ۲. فعال‌سازی loop در Rook operator
+
+```bash
+kubectl -n rook-ceph patch cm rook-ceph-operator-config --type merge \
+  -p '{"data":{"ROOK_CEPH_ALLOW_LOOP_DEVICES":"true"}}'
+kubectl -n rook-ceph rollout restart deploy/rook-ceph-operator
+```
+
+### ۳. mirror ایمیج‌ها (قبل از نصب cluster)
+
+| ایمیج | مسیر pull |
+|-------|-----------|
+| `rook/ceph:v1.20.1` | `registry.abrban.com/rook/ceph:v1.20.1` |
+| `quay.io/ceph/ceph:v19.2` | `registry.abrban.com/proxy-dockerhub/ceph/ceph:v19.2` |
+
+جزئیات mirror: [`RUNBOOK-HARBOR.fa.md`](RUNBOOK-HARBOR.fa.md)
+
+### ۴. نصب operator
+
+```bash
+helm repo add rook-release https://charts.rook.io/release
+helm repo update rook-release
+
+helm upgrade --install rook-ceph rook-release/rook-ceph \
+  -n rook-ceph --create-namespace \
+  --set image.repository=registry.abrban.com/rook/ceph \
+  --set image.tag=v1.20.1 \
+  --set imagePullSecrets[0].name=registry-pull-secret
+```
+
+### ۵. نصب cluster
+
+```bash
+cd backend/helm/cloudhost-ceph
+
+helm upgrade --install rook-ceph-cluster rook-release/rook-ceph-cluster \
+  -n rook-ceph \
+  -f values-rook-cluster-single-node.yaml \
+  --set cephClusterSpec.cephVersion.image=registry.abrban.com/proxy-dockerhub/ceph/ceph:v19.2
+```
+
+> **توجه:** `values-rook-cluster-single-node.yaml` از `devices: [{name: "/dev/loop6"}]` استفاده می‌کند (نه directory — در Rook v1.20 حذف شده).
+
+### ۶. extras (bucket + secret)
+
+```bash
+kubectl create namespace cloudhost-builds 2>/dev/null || true
+helm upgrade --install cloudhost-ceph . \
+  -n cloudhost-builds -f values.yaml --no-hooks
+```
+
+اگر Job `bucket-sync` به‌خاطر `bitnami/kubectl` گیر کرد، secret را دستی بسازید:
+
+```bash
+kubectl -n cloudhost-builds get secret app-sources -o yaml
+kubectl -n cloudhost-builds get cm app-sources -o yaml   # BUCKET_NAME
+# → secret ceph-app-sources-credentials (کلیدهای SOURCE_STORAGE_*)
+```
+
+### ۷. یکپارچه‌سازی backend
+
+```bash
+# کپی secret به namespace پلتفرم (یک‌بار)
+kubectl -n cloudhost-builds get secret ceph-app-sources-credentials -o yaml \
+  | sed 's/namespace: cloudhost-builds/namespace: cloudhost/' \
+  | kubectl apply -f -
+
+# یا با Helm (پیشنهادی):
+helm upgrade cloudhost ./backend/helm/cloudhost-platform -n cloudhost \
+  --set backend.sourceStorage.enabled=true \
+  --set backend.env.PLATFORM_STORAGE_CLASS=rook-ceph-block \
+  --set backend.env.PLATFORM_CREATE_STORAGE_CLASS=false \
+  --set backend.env.PLATFORM_STORAGE_PROVISIONER=rook-ceph.rbd.csi.ceph.com
+```
+
+بدون Helm می‌توانید دستی patch کنید:
+
+```bash
+kubectl -n cloudhost set env deploy/cloudhost-backend \
+  PLATFORM_STORAGE_CLASS=rook-ceph-block \
+  PLATFORM_CREATE_STORAGE_CLASS=false \
+  PLATFORM_STORAGE_PROVISIONER=rook-ceph.rbd.csi.ceph.com
+
+kubectl -n cloudhost patch deploy cloudhost-backend --type=json \
+  -p '[{"op":"add","path":"/spec/template/spec/containers/0/envFrom","value":[{"secretRef":{"name":"ceph-app-sources-credentials"}}]}]'
+```
+
+---
+
+## اسکریپت `install.sh` (نصب تمیز)
+
+برای نصب از صفر (بعد از آماده‌سازی loop + mirror):
+
+```bash
+cd backend/helm/cloudhost-ceph
+./scripts/install.sh single-node
+./scripts/verify.sh
+```
+
+اسکریپت operator + cluster + extras را نصب می‌کند. روی abr حتماً **قبلش** loop device و mirror ایمیج را انجام دهید.
+
+---
+
+## خروجی‌های مهم
+
+### StorageClassها
+
+| نام | کاربرد |
+|-----|--------|
+| `rook-ceph-block` | PVC اپ، DB، Redis، … |
+| `rook-ceph-bucket` | claim کردن bucket برای zip |
+
+### Secret پلتفرم
+
+```bash
+kubectl -n cloudhost-builds get secret ceph-app-sources-credentials -o yaml
+kubectl -n cloudhost get secret ceph-app-sources-credentials -o yaml   # کپی در cloudhost
+```
+
+کلیدها: `SOURCE_STORAGE_ENDPOINT`, `SOURCE_STORAGE_BUCKET`, `SOURCE_STORAGE_ACCESS_KEY`, `SOURCE_STORAGE_SECRET_KEY`
+
+### RGW endpoint
+
+```
+http://rook-ceph-rgw-ceph-objectstore.rook-ceph.svc.cluster.local:80
+```
+
+---
+
+## مدیریت روزمره
+
+### سلامت کلاستر
+
+```bash
+kubectl -n rook-ceph get cephcluster
+kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph status
+kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph osd tree
+kubectl get sc | grep rook-ceph
+kubectl -n rook-ceph get pods
+```
+
+### Dashboard
+
+```bash
+kubectl -n rook-ceph get secret rook-ceph-dashboard-password -o jsonpath='{.data.password}' | base64 -d
+kubectl -n rook-ceph port-forward svc/rook-ceph-mgr-dashboard 8443:8443
+# https://localhost:8443
+```
+
+### bucket و OBC
+
+```bash
+kubectl -n cloudhost-builds get obc app-sources
+kubectl -n cloudhost-builds get cm app-sources
+```
+
+### PVC جدید با Ceph
+
+```yaml
+storageClassName: rook-ceph-block
+```
+
+فقط **اپ‌های جدید** (یا بعد از migration) از این StorageClass استفاده می‌کنند. PVCهای قدیمی روی `local-path` / `cloudhost-expandable` خودکار منتقل نمی‌شوند.
+
+---
+
+## راه‌اندازی مجدد (reinstall)
+
+### ۱. حذف Helm
+
+```bash
+cd backend/helm/cloudhost-ceph
+./scripts/uninstall.sh
+# تایپ: delete-ceph
+```
+
+### ۲. پاک‌سازی روی نود
+
+```bash
+sudo losetup -d /dev/loop6 2>/dev/null || true
+sudo rm -f /var/lib/rook/osd-loopback.img
+sudo rm -rf /var/lib/rook
+```
+
+### ۳. نصب مجدد
+
+loop device + mirror + `./scripts/install.sh single-node`
+
+---
+
+## عیب‌یابی
+
+### CephCluster در `Progressing` / Detecting version
+
+```bash
+kubectl -n rook-ceph get pods | grep detect-version
+kubectl -n rook-ceph describe pod -l job-name=rook-ceph-detect-version
+```
+
+| خطا | راه‌حل |
+|-----|--------|
+| `ceph/ceph:v19.2 not found` | mirror از quay.io؛ tag صحیح `v19.2` نه `v19.2.1` |
+| pull timeout | اولین pull بزرگ است (~500MB)؛ صبر یا image را از قبل روی نود بکشید |
+| Job `detect-version` Terminating گیر کرد | `kubectl -n rook-ceph delete job rook-ceph-detect-version --force --grace-period=0` |
+
+### OSD بالا نمی‌آید (OSD count 0)
+
+```bash
+kubectl -n rook-ceph logs -l app=rook-ceph-osd-prepare --tail=50
+```
+
+| خطا | راه‌حل |
+|-----|--------|
+| `unsupported diskType loop` | `ROOK_CEPH_ALLOW_LOOP_DEVICES=true` |
+| `not picked by deviceFilter` | از `devices: [{name: "/dev/loop6"}]` استفاده کنید نه `deviceFilter` |
+| `no devices matched` | `losetup -a` روی نود؛ loop6 وجود دارد؟ |
+| `directories` در values | در Rook v1.20 کار نمی‌کند — loop یا raw disk |
+
+### Volume mount روی rook-ceph-tools
+
+`rook-ceph-mon-endpoints` و `rook-ceph-mon` تا قبل از بالا آمدن mon ساخته نمی‌شوند — طبیعی است؛ بعد از Ready برطرف می‌شود.
+
+### Helm timeout روی apiserver
+
+اگر `failed to download openapi` دیدید، بدون `--wait` نصب کنید و با `kubectl get cephcluster` پیگیری کنید.
+
+### resize PVC
+
+```bash
+kubectl get storageclass rook-ceph-block -o yaml | grep allowVolumeExpansion
+kubectl patch pvc <name> -n <ns> --type merge \
+  -p '{"spec":{"resources":{"requests":{"storage":"5Gi"}}}}'
+```
+
+---
+
+## ارتقا (upgrade)
+
+```bash
+helm repo update rook-release
+
+helm upgrade rook-ceph rook-release/rook-ceph -n rook-ceph \
+  --reuse-values --timeout 10m
+
+helm upgrade rook-ceph-cluster rook-release/rook-ceph-cluster \
+  -n rook-ceph \
+  -f values-rook-cluster-single-node.yaml \
+  --set cephClusterSpec.cephVersion.image=registry.abrban.com/proxy-dockerhub/ceph/ceph:v19.2
+
+helm upgrade cloudhost-ceph . -n cloudhost-builds -f values.yaml
+```
+
+قبل از upgrade در production: [Rook upgrade guide](https://rook.io/docs/rook/latest/Upgrade/ceph-upgrade/) و snapshot.
+
+---
+
+## نکات امنیتی
+
+- RGW داخل کلاستر HTTP است — برای دسترسی خارجی ingress + TLS اضافه کنید.
+- Secret `ceph-app-sources-credentials` را فقط به backend بدهید.
+- `single-node` + ۱ OSD فقط staging است؛ production نیاز به ۳+ نود و دیسک جدا دارد.
+
+---
+
+## چک‌لیست بعد از نصب
+
+- [ ] `ceph status` — mon/mgr/osd/rgw up
+- [ ] `rook-ceph-block` و `rook-ceph-bucket` در `kubectl get sc`
+- [ ] `ceph-app-sources-credentials` در `cloudhost-builds` و `cloudhost`
+- [ ] env بک‌اند: `PLATFORM_STORAGE_CLASS=rook-ceph-block`
+- [x] `SOURCE_STORAGE_*` در backend از secret خوانده می‌شود (`backend.sourceStorage.enabled=true` در Helm)
+- [ ] اپ تست: آپلود zip و deploy با bucket فعال
+- [ ] اپ تست با PVC جدید deploy شده
+- [ ] ایمیج‌های Rook در Harbor موجود و pull تست شده

RUNBOOK-CICD.fa.md

@@ -0,0 +1,321 @@
+# RUNBOOK — خط CI/CD (Gitea Actions → Kaniko → Harbor → Argo CD)
+
+این مستند جریان کامل Build و Deploy پلتفرم را توضیح می‌دهد: از Push شدن کد روی `main` تا استقرار خودکار روی Kubernetes.
+
+> **استقرار از صفر روی سرور جدید:** [`RUNBOOK-DEPLOY.fa.md`](RUNBOOK-DEPLOY.fa.md) — شامل جدول متغیرها، seal کردن Secretها، logging stack، greenfield reset، و چک‌لیست سلامت.
+
+---
+
+## معماری و جریان کلی
+
+```mermaid
+flowchart TD
+    Dev[Developer] -->|git push main| AppRepo["Gitea: abrban/cloud-host (کد + چارت)"]
+    AppRepo -->|trigger workflow| Runner["Act Runner (namespace: gitea)"]
+    Runner -->|"checkout با CI_TOKEN"| AppRepo
+    Runner -->|kubectl apply Job| Kaniko["Kaniko Job (namespace: cloudhost-builds)"]
+    Kaniko -->|"push با harbor_registry_user"| Harbor["Harbor (harbor-registry:5000)"]
+    Runner -->|"آپدیت image.tag + commit/push"| GitOpsRepo["Gitea: abrban/cloud-host-gitops (state)"]
+    GitOpsRepo -->|"poll (پیش‌فرض هر ۳ دقیقه)"| Argo["Argo CD (automated sync)"]
+    AppRepo -->|"Helm Chart (source دوم)"| Argo
+    Argo -->|"helm render + apply"| K8s["Kubernetes (namespace: cloudhost)"]
+    Harbor -->|"pull از طریق mirror در k3s"| K8s
+    Rollback["Rollback: git revert در cloud-host-gitops"] -.-> GitOpsRepo
+```
+
+مراحل به ترتیب:
+
+1. Developer روی شاخهٔ `main` در ریپوی اپلیکیشن (`git.abrban.com/abrban/cloud-host`) push می‌کند.
+2. Workflow در [`.gitea/workflows/build-deploy.yaml`](.gitea/workflows/build-deploy.yaml) روی Runner با لیبل `abrban-builder` اجرا می‌شود.
+3. Runner کد را با توکن CI کلون می‌کند و تگ ایمیج (`YYYYMMDD-HHMM-<sha>`) را می‌سازد.
+4. **Job تست بک‌اند** در namespace `cloudhost-builds` اجرا می‌شود (`npm ci` + `jest --ci`) — در صورت fail، بیلد ایمیج شروع نمی‌شود.
+5. برای هر ایمیج (backend و frontend) یک Kaniko Job در namespace `cloudhost-builds` ساخته می‌شود که کد را کلون، ایمیج را build و به Harbor push می‌کند.
+6. بعد از موفقیت هر دو Build، همان Runner ریپوی **`cloud-host-gitops`** را کلون می‌کند، مقدار `images.backend.tag` و `images.frontend.tag` را در `platform/values-abrban.yaml` عوض و commit/push می‌کند (با retry و `git pull --rebase` در صورت race).
+7. Argo CD (Application به نام `abrban-platform` با sync خودکار) تغییر را تشخیص می‌دهد و نسخهٔ جدید را در namespace `cloudhost` مستقر می‌کند.
+
+> **جلوگیری از حلقهٔ CI:** کامیتِ Pipeline به ریپوی جدا (`cloud-host-gitops`) می‌رود که هیچ Workflowای ندارد؛ بنابراین Build دوباره trigger نمی‌شود.
+
+**زمان تقریبی یک Pipeline کامل:** ۱۵–۲۵ دقیقه (backend سنگین‌تر است؛ شامل دانلود npm، helm و kubectl داخل Dockerfile).
+
+---
+
+## Bootstrap — پیش‌نیازهای یک‌بار (کلاستر تازه)
+
+قبل از اولین push به `main`، این موارد باید در کلاستر آماده باشند:
+
+| # | کار | دستور / فایل |
+|---|-----|--------------|
+| 1 | Mirror k3s → Harbor | `./scripts/apply-k3s-registries.sh` |
+| 2 | Secretهای TLS و registry در nsهای `gitea`, `cloudhost-builds`, `argocd` | [`gitops/README.md`](gitops/README.md) گام ۴ |
+| 3 | پروکسی egress در `gitea` و `cloudhost-builds` | همان گام ۴ — برای npm/helm/kubectl داخل build و دانلود kubectl توسط Runner |
+| 4 | **Seed ایمیج‌های CI** در Harbor `abrban/` | [`gitops/jobs/seed-ci-images.yaml`](gitops/jobs/seed-ci-images.yaml) |
+| 5 | Sealed Secrets controller | `helm upgrade --install sealed-secrets ... -f gitops/sealed-secrets/values.yaml` |
+| 6 | SealedSecretها از ریپوی gitops | `kubectl apply -f` روی `cloud-host-gitops/sealed-secrets/` |
+| 7 | Gitea Runner + Secret `CI_TOKEN` در ریپو | [`gitops/gitea/act-runner.yaml`](gitops/gitea/act-runner.yaml) |
+| 8 | ریپوی `cloud-host-gitops` + Argo Application | [`gitops/argocd/application-platform.yaml`](gitops/argocd/application-platform.yaml) |
+
+### Seed ایمیج‌های CI (الزامی)
+
+kubelet و Kaniko نمی‌توانند reliably از proxy-cache هاربر برای همهٔ ایمیج‌ها استفاده کنند. این ایمیج‌ها باید **یک‌بار** با skopeo در پروژهٔ `abrban/` کپی شوند:
+
+| ایمیج در Harbor | منبع upstream | مصرف |
+|-----------------|---------------|------|
+| `abrban/act-runner:0.2.11` | docker.io/gitea/act_runner | Gitea Actions runner |
+| `abrban/alpine-git:2.43.0` | docker.io/alpine/git | initContainer کلون در Kaniko Job |
+| `abrban/node:24-alpine` | docker.io/library/node | **BASE_IMAGE** در Dockerfile (هر stage) |
+| `abrban/kaniko-executor:v1.27.6-debug` | gcr.io/kaniko-project/executor | Kaniko Job |
+
+```bash
+# پیش‌نیاز: secret registry-egress-proxy و registry-pull-secret در ns cloudhost
+kubectl apply -f gitops/jobs/seed-ci-images.yaml
+kubectl -n cloudhost wait --for=condition=complete job/seed-ci-images --timeout=15m
+kubectl -n cloudhost logs job/seed-ci-images --tail=5
+# انتظار: SEED_OK
+```
+
+بررسی:
+
+```bash
+kubectl -n cloudhost run tags --rm -i --restart=Never \
+  --image=registry.abrban.com/abrban/alpine:3 \
+  --overrides='{"spec":{"imagePullSecrets":[{"name":"registry-pull-secret"}]}}' \
+  -- sh -c 'H="harbor_registry_user:$(kubectl -n cloudhost get secret harbor-core -o jsonpath="{.data.REGISTRY_CREDENTIAL_PASSWORD}" | base64 -d)@harbor-registry.cloudhost.svc.cluster.local:5000"; for r in act-runner kaniko-executor alpine-git node; do wget -qO- "http://${H}/v2/abrban/${r}/tags/list"; echo; done'
+```
+
+> بعد از bootstrap، Pipeline با push به `main` خودکار اجرا می‌شود؛ نیازی به `./scripts/trigger-platform-build.sh` برای جریان عادی نیست (فقط برای دیباگ دستی).
+
+---
+
+## ساختار Repository (دو ریپو)
+
+### `abrban/cloud-host` — Application Repo
+
+| مسیر | نقش |
+|------|-----|
+| `backend/`, `frontend/` | کد اپلیکیشن + Dockerfile |
+| `backend/helm/cloudhost-platform/` | Helm Chart پلتفرم |
+| `.gitea/workflows/build-deploy.yaml` | Pipeline (Build + آپدیت GitOps) |
+| `gitops/` | نصب زیرساخت (Argo CD، Gitea، Sealed Secrets، k3s و…) |
+
+### `abrban/cloud-host-gitops` — GitOps Repo (منبع حقیقت Argo CD)
+
+| مسیر | نقش |
+|------|-----|
+| `platform/values-abrban.yaml` | مقادیر Production — تنها فایلی که CI آپدیت می‌کند |
+| `argocd/application-platform.yaml` | تعریف Application (نسخهٔ mirror آن در `gitops/argocd/` ریپوی اپ هم هست) |
+| `sealed-secrets/*.yaml` | SealedSecretهای CI — رمزشده و قابل کامیت |
+
+Application در Argo CD به‌صورت **multi-source** تعریف شده: چارت از `cloud-host` و values از `cloud-host-gitops`:
+
+```yaml
+sources:
+  - repoURL: https://git.abrban.com/abrban/cloud-host.git
+    path: backend/helm/cloudhost-platform
+    helm:
+      valueFiles:
+        - $values/platform/values-abrban.yaml
+  - repoURL: https://git.abrban.com/abrban/cloud-host-gitops.git
+    ref: values
+```
+
+مزیت این جداسازی: history تمیز، دسترسی نوشتن CI محدود به ریپوی state، و امکان دیدن کل تاریخچهٔ Deployها با `git log` یک ریپوی کوچک.
+
+---
+
+## احراز هویت‌ها (چه کسی با چه چیزی به کجا وصل می‌شود)
+
+| مسیر | مکانیزم | محل نگهداری |
+|------|---------|--------------|
+| Runner → Gitea (ثبت) | Registration Token | SealedSecret `gitea-act-runner-token` (ns `gitea`) در ریپوی gitops |
+| Workflow → Gitea (clone/push هر دو ریپو) | PAT کاربر `ci` | Secret ریپوی `cloud-host` در Gitea با نام **`CI_TOKEN`** (نام‌های `GITEA_*` رزرو هستند) |
+| Kaniko → Harbor (push) | `harbor_registry_user` | SealedSecret `kaniko-harbor-auth` (ns `cloudhost-builds`) در ریپوی gitops |
+| kubelet → Harbor (pull) | user `cloudhost` | Secret `registry-pull-secret` + mirror در `gitops/k3s/registries.yaml` |
+| Argo CD → `cloud-host` (read) | repo credential | Secret `gitea-repo-creds` (ns `argocd`) |
+| Argo CD → `cloud-host-gitops` (read) | PAT کاربر `ci` | SealedSecret `gitea-gitops-repo-creds` (ns `argocd`) در ریپوی gitops |
+
+### توکن CI برای Gitea (`CI_TOKEN`)
+
+کاربر `ci` در Gitea ساخته شده و روی هر دو ریپو دسترسی write دارد. PAT آن با scope `read:repository, write:repository` به‌عنوان Secret با نام `CI_TOKEN` در **Settings → Actions → Secrets** ریپوی `cloud-host` ثبت شده است.
+
+برای rotate: در Gitea با کاربر `ci` توکن جدید بسازید (یا از API ادمین: `POST /api/v1/users/ci/tokens`)، مقدار Secret را در تنظیمات ریپو آپدیت کنید و SealedSecret `gitea-gitops-repo-creds` را هم دوباره seal کنید.
+
+### احراز هویت Kaniko به Harbor
+
+Kaniko به endpoint داخلی `harbor-registry.cloudhost.svc.cluster.local:5000` push می‌کند که **مستقیم به کامپوننت registry** می‌رود و harbor-core را دور می‌زند. نکتهٔ مهم:
+
+- **Robot Accountهای Harbor اینجا کار نمی‌کنند** — توکن آن‌ها را harbor-core صادر می‌کند و endpoint داخلی به سرویس توکن دسترسی ندارد.
+- credential درست، کاربر داخلی `harbor_registry_user` است با پسورد `REGISTRY_CREDENTIAL_PASSWORD` از Secret `harbor-core`:
+
+```bash
+REG_PASS="$(kubectl -n cloudhost get secret harbor-core \
+  -o jsonpath='{.data.REGISTRY_CREDENTIAL_PASSWORD}' | base64 -d)"
+kubectl -n cloudhost-builds create secret docker-registry kaniko-harbor-auth \
+  --docker-server=harbor-registry.cloudhost.svc.cluster.local:5000 \
+  --docker-username=harbor_registry_user \
+  --docker-password="${REG_PASS}"
+```
+
+نمونهٔ manifest: [`gitops/jobs/kaniko-harbor-auth.example.yaml`](gitops/jobs/kaniko-harbor-auth.example.yaml) — نسخهٔ واقعی به‌صورت SealedSecret در ریپوی gitops است.
+
+ورک‌فلو این Secret را در مسیر `/kaniko/.docker/config.json` هر دو Kaniko Job مانت می‌کند. چون push/pull داخلی و بدون TLS است، این فلگ‌ها لازم‌اند:
+
+- `--insecure` / `--skip-tls-verify` — push
+- `--insecure-pull` / `--insecure-registry=${PUSH_REGISTRY}` — pull ایمیج پایه از `harbor-registry:5000`
+
+ایمیج پایه (`node:24-alpine`) از endpoint داخلی کشیده می‌شود، نه از `registry.abrban.com`:
+
+```yaml
+# در .gitea/workflows/build-deploy.yaml
+--build-arg=BASE_IMAGE=harbor-registry.cloudhost.svc.cluster.local:5000/abrban/node:24-alpine
+```
+
+Dockerfileها از `ARG BASE_IMAGE=node:24-alpine` استفاده می‌کنند (build محلی بدون تغییر).
+
+> **پروکسی egress** (`registry-egress-proxy` در ns `cloudhost-builds`) هنوز لازم است برای `npm ci` و دانلود helm/kubectl **داخل** مراحل RUN در Dockerfile — فقط pull ایمیج پایه از docker.io حذف شده است.
+
+> **عارضهٔ جانبی push مستقیم به :5000** — Harbor DB از این ایمیج‌ها بی‌خبر می‌ماند؛ در UI هاربر دیده نمی‌شوند ولی pull به‌درستی کار می‌کند. برای دیدن تگ‌ها از registry API استفاده کنید (بخش عیب‌یابی).
+
+### ارتباط Runner با Harbor
+
+Runner خودش با Harbor حرف نمی‌زند؛ فقط Job می‌سازد. دو مسیر Harbor:
+
+- **Push (داخلی):** `harbor-registry.cloudhost.svc.cluster.local:5000` — بدون عبور از Traefik.
+- **Pull (kubelet):** `registry.abrban.com` — از طریق mirror در k3s (`scripts/apply-k3s-registries.sh`) به harbor-core route می‌شود.
+
+---
+
+## Versioning ایمیج‌ها
+
+**استاندارد فعلی:** `YYYYMMDD-HHMM-<git-sha-short>` (مثلاً `20260702-1230-a1b2c3d`)
+
+- **Immutable** است — هیچ‌وقت یک تگ بازنویسی نمی‌شود (برخلاف `latest`).
+- **قابل ردیابی** است — از روی تگ ایمیجِ در حال اجرا مستقیماً به کامیت می‌رسید.
+- **مرتب‌شونده** است — به‌ترتیب زمانی دیده می‌شود.
+
+از `latest` هرگز برای Deploy استفاده نکنید؛ هم قابلیت Rollback را از بین می‌برد و هم Argo CD تغییری برای sync نمی‌بیند.
+
+**SemVer برای Releaseها (اختیاری):** روی کامیت release یک Git Tag مثل `v1.4.0` بزنید و همان ایمیج را با `skopeo copy` تگ اضافه بزنید (rebuild لازم نیست). تگ SemVer برای انسان‌هاست؛ منبع حقیقتِ Deploy همان تگ SHA-دار در values است.
+
+---
+
+## آپدیت خودکار Helm Values
+
+مرحلهٔ آخر Workflow ریپوی `cloud-host-gitops` را کلون می‌کند و فقط دو مقدار را در `platform/values-abrban.yaml` عوض می‌کند:
+
+```yaml
+images:
+  backend:
+    repository: registry.abrban.com/abrban/cloudhost-backend
+    tag: "20260702-1230-a1b2c3d"   # ← CI این را آپدیت می‌کند
+  frontend:
+    repository: registry.abrban.com/abrban/cloudhost-frontend
+    tag: "20260702-1230-a1b2c3d"   # ← CI این را آپدیت می‌کند
+```
+
+اگر `yq` روی Runner موجود باشد از آن استفاده می‌شود، وگرنه `sed` هدفمند (فقط خطِ `tag:` بلافاصله بعد از `repository: ...cloudhost-*`) اجرا می‌شود.
+
+جایگزین بررسی‌شده و کنارگذاشته‌شده: **Argo CD Image Updater** — با روش فعلی هم‌پوشانی دارد و شفافیت کامیتِ صریح از CI را ندارد.
+
+---
+
+## Rollback
+
+چون Deploy فقط از Git انجام می‌شود، Rollback هم یک عملیات Git است — این بار در ریپوی `cloud-host-gitops`:
+
+```bash
+git clone https://git.abrban.com/abrban/cloud-host-gitops.git && cd cloud-host-gitops
+
+# 1. پیدا کردن کامیت deploy مشکل‌دار
+git log --oneline -- platform/values-abrban.yaml
+
+# 2. برگرداندن آن (تگ ایمیج به نسخهٔ قبلی برمی‌گردد)
+git revert <commit-sha>
+git push origin main
+
+# 3. Argo CD به‌صورت خودکار به نسخهٔ قبلی sync می‌کند (ایمیج قبلی هنوز در Harbor هست)
+```
+
+نکته‌ها:
+
+- `git revert` (نه `reset --force`) — history حفظ می‌شود و مشخص است چه چیزی چرا برگشت.
+- **Rollback اضطراری** (وقتی Git در دسترس نیست): `argocd app rollback abrban-platform` یا Sync به revision قبلی در UI. **هشدار:** چون `selfHeal: true` فعال است، Argo در sync بعدی دوباره به HEAD گیت برمی‌گردد — rollback اضطراری موقتی است و باید بلافاصله با `git revert` دائمی شود.
+- اگر Deployment جدید خراب باشد (CrashLoopBackOff)، به‌خاطر `RollingUpdate` نسخهٔ قبلی تا آماده‌شدن نسخهٔ جدید بالا می‌ماند.
+
+---
+
+## مدیریت Secretها (Sealed Secrets)
+
+کنترلر **Sealed Secrets** در `kube-system` نصب است (values در [`gitops/sealed-secrets/values.yaml`](gitops/sealed-secrets/values.yaml)؛ ایمیج آن از `ghcr.io/bitnami` به پروژهٔ `abrban/` هاربر seed شده). Secretهای CI به‌صورت **SealedSecret** در ریپوی `cloud-host-gitops` (پوشهٔ `sealed-secrets/`) نگهداری می‌شوند — رمزشده با کلید عمومی کلاستر؛ فقط کنترلرِ داخل کلاستر می‌تواند رمزگشایی کند، پس کامیت‌کردنشان امن است.
+
+| SealedSecret | Namespace | محتوا |
+|--------------|-----------|-------|
+| `gitea-act-runner-token` | `gitea` | توکن ثبت Runner |
+| `kaniko-harbor-auth` | `cloudhost-builds` | dockerconfig کاربر `harbor_registry_user` |
+| `gitea-gitops-repo-creds` | `argocd` | repo credential ریپوی gitops (کاربر `ci`) |
+| `abrban-platform-secrets` | `cloudhost` | postgres-password، jwt-secret، jwt-refresh-secret، **cluster-kubeconfig-key**، **redis-password** |
+| `elasticsearch-credentials` | `logging` | ELASTIC_PASSWORD، FLUENTBIT_PASSWORD (خارج از چارت پلتفرم — [`elasticsearch-credentials.example.yaml`](gitops/sealed-secrets/elasticsearch-credentials.example.yaml)) |
+
+چارت Helm با `secrets.existingSecret: abrban-platform-secrets` در `platform/values-abrban.yaml` (ریپوی gitops) از Secret ازپیش‌ساخته استفاده می‌کند — Argo CD با `helm template` نمی‌تواند Secret تصادفی بسازد (lookup خالی است و هر sync مقادیر JWT/Redis را عوض می‌کند).
+
+نمونهٔ کامل values: [`gitops/platform/values-abrban.example.yaml`](gitops/platform/values-abrban.example.yaml) — شامل mirror ایمیج postgres/redis، `BASE_IMAGE_REGISTRY`، و envهای Elastic.
+
+### Greenfield / ارتقا از نسخهٔ قدیم
+
+اگر کلاستر قبلاً با schema یا namespace قدیمی بالا آمده، قبل از deploy جدید **reset دیتابیس** لازم است. مراحل کامل (با متغیرهای قابل‌تنظیم برای هر محیط) در **[`RUNBOOK-DEPLOY.fa.md` — فاز ۶](RUNBOOK-DEPLOY.fa.md#فاز-۶--greenfield--ارتقا-از-نسخهٔ-قدیم)**.
+
+### ساخت/به‌روزرسانی یک SealedSecret
+
+```bash
+brew install kubeseal   # فقط بار اول
+
+kubectl -n <ns> create secret generic <name> --from-literal=key=value --dry-run=client -o json \
+  | kubeseal --controller-name=sealed-secrets-controller --controller-namespace=kube-system --format yaml \
+  > sealed-secrets/<name>.yaml
+# سپس commit/push در ریپوی cloud-host-gitops و kubectl apply (یا sync توسط Argo در آینده)
+```
+
+> اگر Secret از قبل در کلاستر وجود دارد و می‌خواهید کنترلر آن را تصاحب کند، اول annotate کنید:
+> `kubectl -n <ns> annotate secret <name> sealedsecrets.bitnami.com/managed="true"`
+
+Secretهایی که هنوز دستی‌اند (خارج از چرخهٔ CI): `abrban-wildcard-tls`، `registry-pull-secret`، `registry-egress-proxy`، `harbor-core` (ساختهٔ Helm) — می‌توانند به‌تدریج seal شوند.
+
+> **نکتهٔ امنیتی:** توکن ثبت Runner و پسورد پروکسی که قبلاً در history گیت افشا شده بودند rotate شده‌اند (توکن Runner جدید صادر و Runner دوباره ثبت شد). پسورد کاربر پروکسی (`builder`) روی سرور پروکسی هنوز باید توسط ادمین عوض شود؛ بعد از تغییر، Secret `registry-egress-proxy` را در namespaceهای `cloudhost` و `gitea` آپدیت کنید.
+
+---
+
+## Best Practiceهای GitOps در این استک (چک‌لیست)
+
+- [x] **Git تنها منبع حقیقت** — Argo CD با `automated + prune + selfHeal`؛ تغییر دستی با `kubectl edit` برگردانده می‌شود.
+- [x] **جداسازی App Repo از GitOps Repo** — history تمیز و دسترسی حداقلی CI.
+- [x] **تگ Immutable به‌جای `latest`** — هر Build تگ یکتا دارد.
+- [x] **جلوگیری از CI Loop** — کامیت CI به ریپوی جدا می‌رود که Workflow ندارد.
+- [x] **Build بدون Docker Daemon** — Kaniko داخل Job، بدون `docker.sock` و بدون privileged.
+- [x] **جداسازی push/pull هاربر** — push داخلی بدون عبور از Ingress؛ pull از طریق mirror k3s.
+- [x] **Concurrency در Workflow** — دو push پشت‌سرهم روی آپدیت values با هم race نمی‌کنند.
+- [x] **Secretهای GitOps-شده** — Sealed Secrets نصب و secretهای CI رمزشده در Git.
+- [ ] **محیط Staging** — با `platform/values-staging.yaml` و Application دوم قابل اضافه‌شدن است.
+- [ ] **Notification** — Argo CD Notifications برای اطلاع از Sync موفق/ناموفق.
+
+---
+
+## عیب‌یابی سریع
+
+| علامت | بررسی |
+|-------|-------|
+| Workflow اجرا نمی‌شود | `kubectl -n gitea logs deploy/gitea-act-runner` — ثبت Runner و لیبل `abrban-builder` |
+| Build fail — clone | معتبربودن Secret `CI_TOKEN` در تنظیمات ریپوی `cloud-host` |
+| Build fail — pull ایمیج پایه | `node:24-alpine` باید seed شده باشد؛ Workflow باید `BASE_IMAGE=harbor-registry.../abrban/node:24-alpine` + `--insecure-pull` داشته باشد؛ نه pull مستقیم از docker.io |
+| Build fail — UNAUTHORIZED روی registry.abrban.com | BASE_IMAGE نباید `registry.abrban.com/...` باشد — credential کانیکو فقط برای `harbor-registry:5000` است |
+| Build fail — HTTP response to HTTPS client | `--insecure-pull` و `--insecure-registry=harbor-registry.cloudhost.svc.cluster.local:5000` در Kaniko args |
+| Build fail — timeout npm/helm/kubectl | `registry-egress-proxy` در ns `cloudhost-builds` و سلامت پروکسی egress |
+| Build fail — push به Harbor | `kubectl -n cloudhost-builds get secret kaniko-harbor-auth`؛ پسورد باید با `REGISTRY_CREDENTIAL_PASSWORD` هاربر یکی باشد |
+| کامیت values push نمی‌شود | دسترسی write کاربر `ci` روی `cloud-host-gitops` |
+| Argo sync نمی‌کند | `kubectl -n argocd get app abrban-platform`؛ هر دو repo credential (`gitea-repo-creds` و `gitea-gitops-repo-creds`) |
+| Pod ایمیج را pull نمی‌کند | `registry-pull-secret` در ns `cloudhost` و mirror k3s (`scripts/apply-k3s-registries.sh`) |
+| دیدن تگ‌های موجود در registry | از داخل کلاستر: `wget -qO- "http://harbor_registry_user:<REG_PASS>@harbor-registry.cloudhost.svc.cluster.local:5000/v2/abrban/cloudhost-backend/tags/list"` |
+| Backend CrashLoop — CLUSTER_KUBECONFIG_KEY | Secret `abrban-platform-secrets` باید کلید `cluster-kubeconfig-key` داشته باشد و در values: `secrets.existingSecret: abrban-platform-secrets` |
+| Backend CrashLoop — DB auth | پسورد postgres در Secret با DB واقعی هم‌خوان باشد (`ALTER USER ... WITH PASSWORD` در صورت rotate شدن Secret) |
+| Backend CrashLoop — Redis auth | Secret `abrban-platform-secrets` باید کلید `redis-password` داشته باشد؛ backend و Redis پلتفرم هر دو از آن استفاده می‌کنند |
+| Backend CrashLoop — ELASTIC_PASSWORD | در production مقدار پیش‌فرض رد می‌شود — env در values-abrban.yaml باید رمز rotate‌شده داشته باشد |
+| Workflow fail — tests | Job `test-be-*` در ns `cloudhost-builds` — `kubectl logs job/... -c test` |
+| SealedSecret باز نمی‌شود | `kubectl get sealedsecrets -A` (ستون SYNCED) و لاگ `kubectl -n kube-system logs deploy/sealed-secrets-controller` |

RUNBOOK-DEPLOY.fa.md

@@ -0,0 +1,426 @@
+# RUNBOOK — استقرار پلتفرم CloudHost از صفر
+
+این سند **کارهایی را که روی سرور/کلاستر باید انجام دهید** مرحله‌به‌مرحله توضیح می‌دهد — از bootstrap زیرساخت تا اولین deploy موفق پس از hardening.
+
+> **برای چه کسی است:** هر کسی که می‌خواهد CloudHost را روی یک کلاستر Kubernetes تازه (یا کلاستر دیگری غیر از abrban) بالا بیاورد.
+>
+> **چه چیزی اینجا نیست:** جزئیات معماری اپ → [`RUNBOOK.fa.md`](RUNBOOK.fa.md)؛ جزئیات pipeline CI → [`RUNBOOK-CICD.fa.md`](RUNBOOK-CICD.fa.md).
+
+---
+
+## قبل از شروع — جدول متغیرها
+
+همهٔ دستورات زیر از این متغیرها استفاده می‌کنند. **یک‌بار** آن‌ها را برای محیط خودتان پر کنید:
+
+| متغیر | توضیح | مثال abrban | مثال محیط جدید |
+|-------|--------|-------------|----------------|
+| `PLATFORM_NS` | namespace پلتفرم | `cloudhost` | `cloudhost` |
+| `BUILD_NS` | namespace بیلد Kaniko | `cloudhost-builds` | `cloudhost-builds` |
+| `LOGGING_NS` | namespace Elasticsearch | `logging` | `logging` |
+| `REGISTRY_HOST` | آدرس pull ایمیج (Ingress/registry عمومی) | `registry.abrban.com` | `registry.example.com` |
+| `REGISTRY_PROJECT` | پروژه Harbor برای ایمیج‌های platform | `abrban` | `cloudhost` |
+| `REGISTRY_PUSH` | endpoint داخلی push (بدون TLS) | `harbor-registry.cloudhost.svc.cluster.local:5000` | `registry.registry.svc:5000` |
+| `GIT_HOST` | URL گیت (Gitea/GitHub) | `git.abrban.com` | `git.example.com` |
+| `APP_REPO` | ریپوی کد + چارت | `abrban/cloud-host` | `org/cloud-host` |
+| `GITOPS_REPO` | ریپوی state (values + sealed secrets) | `abrban/cloud-host-gitops` | `org/cloud-host-gitops` |
+| `VALUES_FILE` | فایل values در gitops | `platform/values-abrban.yaml` | `platform/values-production.yaml` |
+| `PLATFORM_SECRET` | Secret پلتفرم (JWT, DB, Redis, …) | `abrban-platform-secrets` | `cloudhost-platform-secrets` |
+| `ARGO_APP` | نام Application در Argo CD | `abrban-platform` | `cloudhost-platform` |
+| `DOMAIN_LANDING` | لندینگ | `abrban.com` | `example.com` |
+| `DOMAIN_PANEL` | پنل | `panel.abrban.com` | `panel.example.com` |
+| `DOMAIN_API` | API | `api.abrban.com` | `api.example.com` |
+| `DOMAIN_APPS` | دامنهٔ اپ‌های کاربر | `apps.abrban.com` | `apps.example.com` |
+| `STORAGE_CLASS` | StorageClass PVCها | `local-path` | `standard` |
+| `INGRESS_CLASS` | Ingress controller | `traefik` | `nginx` |
+
+```bash
+# نمونه — قبل از اجرای دستورات export کنید:
+export PLATFORM_NS=cloudhost
+export BUILD_NS=cloudhost-builds
+export LOGGING_NS=logging
+export REGISTRY_HOST=registry.example.com
+export REGISTRY_PROJECT=cloudhost
+export REGISTRY_PUSH=harbor-registry.cloudhost.svc.cluster.local:5000
+export GIT_HOST=git.example.com
+export APP_REPO=org/cloud-host
+export GITOPS_REPO=org/cloud-host-gitops
+export VALUES_FILE=platform/values-production.yaml
+export PLATFORM_SECRET=cloudhost-platform-secrets
+export ARGO_APP=cloudhost-platform
+export DOMAIN_LANDING=example.com
+export DOMAIN_PANEL=panel.example.com
+export DOMAIN_API=api.example.com
+export DOMAIN_APPS=apps.example.com
+export STORAGE_CLASS=standard
+export INGRESS_CLASS=nginx
+```
+
+---
+
+## دو مسیر استقرار
+
+| | **مسیر A — GitOps (توصیه Production)** | **مسیر B — Helm مستقیم** |
+|---|--------------------------------------|---------------------------|
+| CI/CD | Gitea Actions → Kaniko → Argo CD | build/push دستی + `helm upgrade` |
+| Values | ریپوی جدا `GITOPS_REPO` | فایل محلی `my-values.yaml` |
+| Secretها | Sealed Secrets در gitops | inline در values یا Secret دستی |
+| مستند | **همین سند +** [`RUNBOOK-CICD.fa.md`](RUNBOOK-CICD.fa.md) | [`README.md`](README.md) بخش Deploy |
+
+بقیهٔ این سند **مسیر A** را پوشش می‌دهد. برای مسیر B به انتهای سند بروید.
+
+---
+
+## مسیر A — GitOps: فاز ۰ تا ۷
+
+### فاز ۰ — پیش‌نیازهای سخت‌افزاری و شبکه
+
+- [ ] کلاستر Kubernetes (k3s یا دیگر) با kubectl از ماشین admin
+- [ ] DNS: رکوردهای A/CNAME برای `$DOMAIN_LANDING`, `$DOMAIN_PANEL`, `$DOMAIN_API`, `$REGISTRY_HOST`, `$GIT_HOST`, Argo CD
+- [ ] گواهی TLS (wildcard یا cert-manager + `clusterIssuer`)
+- [ ] دسترسی `kubectl` به کلاستر
+- [ ] `helm`, `kubeseal` (برای Sealed Secrets) روی ماشین admin
+- [ ] دو ریپوی Git: `$APP_REPO` (کد) و `$GITOPS_REPO` (خالی یا با skeleton)
+
+---
+
+### فاز ۱ — Bootstrap زیرساخت (یک‌بار per cluster)
+
+این مراحل در [`gitops/README.md`](gitops/README.md) هم هست؛ خلاصه:
+
+```bash
+cd cloud-host   # ریپوی اپلیکیشن
+
+# 1) mirror رجیستری k3s → Harbor (یا registry خودتان)
+./scripts/apply-k3s-registries.sh   # در صورت k3s؛ برای کلاستر دیگر mirror معادل تنظیم کنید
+
+# 2) Argo CD
+helm upgrade --install argocd argo/argo-cd -n argocd --create-namespace \
+  -f gitops/argocd/values-bootstrap.yaml --timeout 15m --wait
+
+# 3) Gitea (یا GitHub/GitLab — workflow را متناسب تنظیم کنید)
+helm upgrade --install gitea gitea-charts/gitea -n gitea --create-namespace \
+  -f gitops/gitea/values.yaml --timeout 15m --wait
+
+# 4) Secretهای TLS + registry-pull + egress در nsهای لازم
+#    (wildcard TLS و registry-pull-secret را یک‌بار در $PLATFORM_NS بسازید، سپس کپی)
+for ns in argocd gitea $BUILD_NS; do
+  kubectl -n $PLATFORM_NS get secret <wildcard-tls-secret> -o yaml \
+    | sed "s/namespace: ${PLATFORM_NS}/namespace: ${ns}/" | kubectl apply -f -
+  kubectl -n $PLATFORM_NS get secret registry-pull-secret -o yaml \
+    | sed "s/namespace: ${PLATFORM_NS}/namespace: ${ns}/" | kubectl apply -f -
+done
+
+# 5) Seed ایمیج‌های CI (act-runner, alpine-git, node, kaniko) — فایل را برای REGISTRY_* خودتان ویرایش کنید
+kubectl apply -f gitops/jobs/seed-ci-images.yaml
+kubectl -n $PLATFORM_NS wait --for=condition=complete job/seed-ci-images --timeout=15m
+
+# 6) Sealed Secrets controller
+helm repo add sealed-secrets https://bitnami.github.io/sealed-secrets
+helm upgrade --install sealed-secrets sealed-secrets/sealed-secrets \
+  -n kube-system -f gitops/sealed-secrets/values.yaml --timeout 10m --wait
+
+# 7) Gitea Actions runner + Secret CI_TOKEN در ریپوی app
+kubectl apply -f gitops/gitea/act-runner.yaml
+# در Gitea: Settings → Actions → Secrets → CI_TOKEN = PAT کاربر ci
+
+# 8) Argo CD Application (chart از app repo، values از gitops repo)
+#    قبل از apply: repoURLها در gitops/argocd/application-platform.yaml را با GIT_HOST/APP_REPO/GITOPS_REPO هم‌خوان کنید
+kubectl apply -f gitops/argocd/application-platform.yaml
+```
+
+**بررسی فاز ۱:**
+
+```bash
+kubectl get nodes
+kubectl -n argocd get pods
+kubectl -n gitea get pods
+kubectl -n kube-system get pods -l app.kubernetes.io/name=sealed-secrets
+```
+
+---
+
+### فاز ۲ — آماده‌سازی ریپوی GitOps (values)
+
+```bash
+# کلون ریپوی gitops (کنار ریپوی app یا هر مسیر دلخواه)
+git clone "https://${GIT_HOST}/${GITOPS_REPO}.git" cloud-host-gitops
+cd cloud-host-gitops
+
+# کپی template values از ریپوی app
+cp ../cloud-host/gitops/platform/values-abrban.example.yaml "${VALUES_FILE}"
+```
+
+**فایل values را برای محیط خودتان ویرایش کنید** — حداقل این فیلدها:
+
+| بخش | چه چیزی عوض شود |
+|-----|------------------|
+| `images.postgres/redis/busybox` | مسیر mirror در `$REGISTRY_HOST` (مثلاً `proxy-dockerhub/library/postgres:16-alpine`) |
+| `images.backend/frontend.repository` | `$REGISTRY_HOST/$REGISTRY_PROJECT/cloudhost-backend` |
+| `secrets.existingSecret` | `$PLATFORM_SECRET` |
+| `ingress.*.host` | `$DOMAIN_LANDING`, `$DOMAIN_PANEL`, `$DOMAIN_API` |
+| `ingress.className` | `$INGRESS_CLASS` |
+| `global.storageClass` | `$STORAGE_CLASS` |
+| `backend.env.PLATFORM_DOMAIN` | `$DOMAIN_APPS` |
+| `backend.env.FRONTEND_URL` | `https://${DOMAIN_PANEL},https://${DOMAIN_LANDING}` |
+| `backend.env.REGISTRY_URL` | push داخلی: `$REGISTRY_PUSH/$REGISTRY_PROJECT` |
+| `backend.env.REGISTRY_PULL_URL` | `$REGISTRY_HOST/$REGISTRY_PROJECT` |
+| `backend.env.BASE_IMAGE_REGISTRY` | prefix mirror برای Dockerfileهای کاربر |
+| `backend.env.ELASTIC_*` | بعد از فاز ۴ پر می‌شود |
+| `postgres/redis.imagePullSecrets` | `[{ name: registry-pull-secret }]` |
+
+```bash
+git add "${VALUES_FILE}"
+git commit -m "chore: initial platform values for $(hostname -s 2>/dev/null || echo production)"
+git push origin main
+```
+
+> **نکته:** CI فقط `images.backend.tag` و `images.frontend.tag` را عوض می‌کند — بقیهٔ فایل دست شماست.
+
+---
+
+### فاز ۳ — Secretهای پلتفرم (Sealed Secrets)
+
+Secret پلتفرم **نباید** در values به‌صورت plaintext commit شود. از SealedSecret استفاده کنید.
+
+**کلیدهای الزامی** در `$PLATFORM_SECRET`:
+
+| کلید | کاربرد |
+|------|--------|
+| `postgres-password` | Postgres پلتفرم + migration Job |
+| `jwt-secret` | JWT access (حداقل ۳۲ کاراکتر تصادفی) |
+| `jwt-refresh-secret` | JWT refresh |
+| `cluster-kubeconfig-key` | رمزگذاری kubeconfig کلاسترها (۶۴ hex یا passphrase قوی) |
+| `redis-password` | Redis پلتفرم + backend (Bull queues) |
+
+```bash
+cd cloud-host-gitops
+
+# تولید رمزهای تصادفی (یا خودتان مقدار قوی بگذارید)
+PG_PASS="$(openssl rand -base64 24)"
+JWT="$(openssl rand -base64 32)"
+JWT_REFRESH="$(openssl rand -base64 32)"
+KUBE_KEY="$(openssl rand -hex 32)"
+REDIS_PASS="$(openssl rand -base64 24)"
+
+kubectl -n $PLATFORM_NS create secret generic "$PLATFORM_SECRET" \
+  --from-literal=postgres-password="$PG_PASS" \
+  --from-literal=jwt-secret="$JWT" \
+  --from-literal=jwt-refresh-secret="$JWT_REFRESH" \
+  --from-literal=cluster-kubeconfig-key="$KUBE_KEY" \
+  --from-literal=redis-password="$REDIS_PASS" \
+  --dry-run=client -o json \
+| kubeseal \
+    --controller-name=sealed-secrets-controller \
+    --controller-namespace=kube-system \
+    --format yaml \
+> "sealed-secrets/${PLATFORM_SECRET}.yaml"
+
+kubectl apply -f "sealed-secrets/${PLATFORM_SECRET}.yaml"
+git add "sealed-secrets/${PLATFORM_SECRET}.yaml"
+git commit -m "chore: seal platform secrets"
+git push origin main
+```
+
+**بررسی:**
+
+```bash
+kubectl -n $PLATFORM_NS get secret "$PLATFORM_SECRET"
+kubectl get sealedsecrets -A | grep "$PLATFORM_SECRET"
+```
+
+SealedSecretهای CI دیگر (kaniko، runner، repo creds) را طبق [`RUNBOOK-CICD.fa.md`](RUNBOOK-CICD.fa.md) بسازید.
+
+---
+
+### فاز ۴ — Logging stack + Secret Elasticsearch
+
+```bash
+cd cloud-host
+
+# 1) namespace logging (اگر در manifest نیست)
+kubectl create namespace $LOGGING_NS --dry-run=client -o yaml | kubectl apply -f -
+
+# 2) Secret elasticsearch — خارج از git (plaintext commit ممنوع)
+ELASTIC_PASS="$(openssl rand -base64 24)"
+FLUENT_PASS="$(openssl rand -base64 24)"
+
+kubectl -n $LOGGING_NS create secret generic elasticsearch-credentials \
+  --from-literal=ELASTIC_PASSWORD="$ELASTIC_PASS" \
+  --from-literal=FLUENTBIT_PASSWORD="$FLUENT_PASS"
+
+# یا seal کنید:
+kubectl -n $LOGGING_NS create secret generic elasticsearch-credentials \
+  --from-literal=ELASTIC_PASSWORD="$ELASTIC_PASS" \
+  --from-literal=FLUENTBIT_PASSWORD="$FLUENT_PASS" \
+  --dry-run=client -o json \
+| kubeseal --controller-name=sealed-secrets-controller \
+    --controller-namespace=kube-system --format yaml \
+> ../cloud-host-gitops/sealed-secrets/elasticsearch-credentials.yaml
+
+# 3) deploy stack (بدون Secret inline — manifest فقط ConfigMap/Deployment دارد)
+kubectl apply -f backend/k8s/logging/elasticsearch-stack.yaml
+
+# 4) همان مقادیر را در values پلتفرم بگذارید (backend.env)
+#    ELASTIC_PASSWORD, FLUENTBIT_PASSWORD, KIBANA_SYSTEM_PASSWORD
+#    سپس commit/push در gitops repo
+```
+
+> backend در production بدون `ELASTIC_PASSWORD` معتبر **بالا نمی‌آید** (`validate-production-config`).
+
+---
+
+### فاز ۵ — اولین Deploy
+
+**روش ۱ — CI (توصیه):** push به `main` در `$APP_REPO` → workflow تست + Kaniko + آپدیت tag در gitops → Argo sync.
+
+```bash
+cd cloud-host
+git push origin main   # یا push به Gitea remote
+# پیگیری: Gitea Actions UI یا kubectl -n $BUILD_NS get jobs -w
+```
+
+**روش ۲ — دستی (bootstrap / بدون CI):**
+
+```bash
+# build ایمیج‌ها (روی ماشینی که به registry دسترسی دارد) یا trigger-platform-build.sh
+TAG="$(date +%Y%m%d-%H%M)-manual"
+VALUES="../cloud-host-gitops/${VALUES_FILE}"
+./scripts/gitops-deploy.sh TAG="$TAG" VALUES="$VALUES"
+```
+
+**بررسی Argo:**
+
+```bash
+kubectl -n argocd get app "$ARGO_APP"
+argocd app sync "$ARGO_APP"   # در صورت sync خودکار غیرفعال
+kubectl -n $PLATFORM_NS get pods
+kubectl -n $PLATFORM_NS rollout status deploy/cloudhost-backend --timeout=300s
+kubectl -n $PLATFORM_NS rollout status deploy/cloudhost-frontend --timeout=300s
+```
+
+---
+
+### فاز ۶ — Greenfield / ارتقا از نسخهٔ قدیم
+
+اگر کلاستر **قبلاً** با نسخهٔ قدیمی CloudHost بالا آمده (namespace کوتاه UUID، migration بدون `schema_migrations`)، **قبل از deploy جدید** دیتابیس را reset کنید.
+
+> ⚠️ **فقط greenfield / بدون دادهٔ واقعی.** در production با داده، اول backup بگیرید.
+
+```bash
+# 1) backend را متوقف کنید
+kubectl -n $PLATFORM_NS scale deploy/cloudhost-backend --replicas=0
+
+# 2) schema را از نو بسازید
+kubectl -n $PLATFORM_NS exec deploy/cloudhost-postgres -- \
+  psql -U cloudhost -c 'DROP SCHEMA public CASCADE; CREATE SCHEMA public;'
+
+# 3) Argo sync — migration Job (pre-upgrade hook) base schema + migrations را اجرا می‌کند
+argocd app sync "$ARGO_APP"
+
+# 4) backend را بالا بیاورید
+kubectl -n $PLATFORM_NS scale deploy/cloudhost-backend --replicas=1
+```
+
+**تغییرات breaking که reset می‌خواهند:**
+
+| تغییر | اثر |
+|-------|-----|
+| namespace کاربر `user-<uuid-32>` به‌جای `user-<8char>` | namespaceهای قدیمی دیگر استفاده نمی‌شوند — اپ‌ها redeploy |
+| `000_base_schema.sql` + `schema_migrations` | DB باید از نو migrate شود |
+| `redis-password` جدید | Secret + restart Redis و backend |
+
+---
+
+### فاز ۷ — چک‌لیست تأیید سلامت
+
+```bash
+# Podها
+kubectl -n $PLATFORM_NS get deploy,pods
+kubectl -n $LOGGING_NS get pods
+
+# API
+curl -sf "https://${DOMAIN_API}/api/v1/health" && echo OK
+curl -sf "https://${DOMAIN_API}/api/v1/ready" && echo OK
+
+# Frontend
+curl -sf -o /dev/null -w '%{http_code}\n' "https://${DOMAIN_LANDING}"
+curl -sf -o /dev/null -w '%{http_code}\n' "https://${DOMAIN_PANEL}"
+
+# Migration
+kubectl -n $PLATFORM_NS logs job/$(kubectl -n $PLATFORM_NS get jobs -o name | grep migration | tail -1 | cut -d/ -f2) 2>/dev/null || true
+
+# Redis auth
+kubectl -n $PLATFORM_NS exec deploy/cloudhost-redis -- redis-cli ping
+
+# Backup CronJob (اگر enabled)
+kubectl -n $PLATFORM_NS get cronjobs
+```
+
+| علامت | اقدام |
+|-------|-------|
+| Backend CrashLoop — JWT/DB/Redis | Secret `$PLATFORM_SECRET` و keys — [`RUNBOOK-CICD.fa.md`](RUNBOOK-CICD.fa.md) عیب‌یابی |
+| Backend CrashLoop — ELASTIC_PASSWORD | env در values + Secret logging |
+| Migration fail | `kubectl logs` روی migration Job؛ `schema_migrations` و فایل‌های `backend/migrations/` |
+| Argo OutOfSync | `argocd app diff $ARGO_APP` |
+
+---
+
+## مسیر B — Helm مستقیم (بدون GitOps)
+
+برای lab، staging، یا کلاستری **بدون** Gitea/Argo:
+
+```bash
+cp backend/helm/cloudhost-platform/values-production.example.yaml my-values.yaml
+# ویرایش: hosts, registry, secrets (jwtSecret, postgres.password, redis.password), ingress
+
+docker build -t $REG/cloudhost-backend:1.0.0 ./backend
+docker build -t $REG/cloudhost-frontend:1.0.0 \
+  --build-arg NEXT_PUBLIC_API_URL=https://${DOMAIN_API} ./frontend
+docker push $REG/cloudhost-backend:1.0.0
+docker push $REG/cloudhost-frontend:1.0.0
+
+helm upgrade --install cloudhost ./backend/helm/cloudhost-platform \
+  -n $PLATFORM_NS --create-namespace \
+  -f my-values.yaml \
+  --set images.backend.repository=$REG/cloudhost-backend \
+  --set images.frontend.repository=$REG/cloudhost-frontend \
+  --set images.backend.tag=1.0.0 \
+  --set images.frontend.tag=1.0.0 \
+  --set global.storageClass=$STORAGE_CLASS
+```
+
+> در این مسیر `secrets.existingSecret` خالی بماند تا Helm Secret بسازد — **برای production با Argo CD توصیه نمی‌شود** (lookup در `helm template` خالی است).
+
+---
+
+## فایل‌های مرجع در ریپو
+
+| فایل | نقش |
+|------|-----|
+| [`gitops/platform/values-abrban.example.yaml`](gitops/platform/values-abrban.example.yaml) | Template values — کپی و rename برای محیط جدید |
+| [`gitops/sealed-secrets/abrban-platform-secrets.example.yaml`](gitops/sealed-secrets/abrban-platform-secrets.example.yaml) | دستور seal Secret پلتفرم |
+| [`gitops/sealed-secrets/elasticsearch-credentials.example.yaml`](gitops/sealed-secrets/elasticsearch-credentials.example.yaml) | دستور seal Secret logging |
+| [`backend/helm/cloudhost-platform/values-production.example.yaml`](backend/helm/cloudhost-platform/values-production.example.yaml) | Template برای مسیر B |
+| [`scripts/gitops-deploy.sh`](scripts/gitops-deploy.sh) | deploy دستی با Helm + values از gitops |
+
+---
+
+## خلاصهٔ ترتیب (Quick reference)
+
+```
+فاز ۰  DNS + kubectl + helm + kubeseal + دو ریپو
+  ↓
+فاز ۱  Argo + Gitea + registry + sealed-secrets + runner + Application
+  ↓
+فاز ۲  کپی values template → ویرایش → push gitops
+  ↓
+فاز ۳  seal platform secrets → push gitops
+  ↓
+فاز ۴  elasticsearch stack + secret + env در values
+  ↓
+فاز ۵  push main (CI) یا gitops-deploy.sh (دستی)
+  ↓
+فاز ۶  (در صورت upgrade) reset DB
+  ↓
+فاز ۷  health check
+```

RUNBOOK-HARBOR.fa.md

@@ -0,0 +1,195 @@
+# راهنمای Harbor — `registry.abrban.com`
+
+این سند معماری فعلی، نصب، مدیریت روزمره و عیب‌یابی **Harbor** روی کلاستر abr را پوشش می‌دهد.
+
+- چارت/values: [`backend/helm/cloudhost-harbor/`](backend/helm/cloudhost-harbor/)
+- اسکریپت نصب: [`backend/helm/cloudhost-harbor/scripts/install-harbor-registry.sh`](backend/helm/cloudhost-harbor/scripts/install-harbor-registry.sh)
+
+---
+
+## معماری فعلی (خلاصه)
+
+```
+registry.abrban.com (Traefik + TLS wildcard)
+├── /                    → harbor-portal   (UI)
+├── /api/, /service/, /c/ → harbor-core   (API + auth)
+├── /v2/proxy-dockerhub/ → harbor-registry (ایمیج‌های mirror‌شده Ceph/Rook)
+├── /v2/rook/            → harbor-registry
+└── /v2/*                → registry قدیمی (ایمیج‌های platform: backend, nixpacks, …)
+```
+
+| کامپوننت | نقش |
+|----------|-----|
+| **Harbor** | UI، proxy-cache، ذخیره ایمیج‌های جدید |
+| **registry قدیمی** (`Deployment/registry`) | هنوز بالاست؛ ایمیج‌های platform قبل از Harbor اینجاست |
+| **registry-egress-proxy** | secret با `HTTP_PROXY` / `HTTPS_PROXY` برای pull از docker.io/quay از داخل کلاستر |
+| **registry-pull-secret** | auth kubelet برای pull از `registry.abrban.com` |
+
+> Harbor و registry قدیمی **هم‌زمان** روی یک hostname هستند؛ مسیر `/v2/` با Ingress split می‌شود.
+
+---
+
+## پیش‌نیازها
+
+- Secret `abrban-wildcard-tls` در namespace `cloudhost`
+- Secret `registry-egress-proxy` در namespace `cloudhost` (پروکسی egress)
+- Helm repo: `helm repo add harbor https://helm.goharbor.io`
+
+---
+
+## نصب / ارتقا
+
+```bash
+cd backend/helm/cloudhost-harbor
+./scripts/install-harbor-registry.sh
+```
+
+اسکریپت:
+1. Harbor را با values + proxy از `registry-egress-proxy` نصب می‌کند
+2. Ingress قدیمی `registry` را حذف می‌کند (بعد از نصب باید دستی دوباره route شود — بخش Ingress)
+3. `Deployment/registry` را scale به 0 می‌کند (برای rollback نگه داشته می‌شود)
+
+### Ingress بعد از نصب (الزامی)
+
+Harbor به **چند مسیر** نیاز دارد. Ingress نهایی باید شبیه این باشد:
+
+| Path | Service | Port |
+|------|---------|------|
+| `/` | `harbor-portal` | 80 |
+| `/api/`, `/service/`, `/c/`, `/chartrepo/` | `harbor-core` | 80 |
+| `/v2/proxy-dockerhub/`, `/v2/rook/` | `harbor-registry` | 5000 |
+| `/v2/` (بقیه) | `registry` (قدیمی) | 5000 |
+
+بدون split روی `/v2/`، یا UI 404 می‌دهد یا kubelet ایمیج platform را پیدا نمی‌کند.
+
+---
+
+## دسترسی و credentialها
+
+| کاربرد | کاربر | منبع |
+|--------|-------|------|
+| UI / API مدیریت | `admin` | `kubectl -n cloudhost get secret harbor-core -o jsonpath='{.data.HARBOR_ADMIN_PASSWORD}' \| base64 -d` |
+| push/pull داخلی به harbor-registry | `harbor_registry_user` | secret `harbor-core` → `REGISTRY_CREDENTIAL_PASSWORD` |
+| pull kubelet (ایمیج‌های platform) | `cloudhost` | secret `registry-pull-secret` (namespace `cloudhost`) |
+| pull kubelet (ایمیج‌های Rook/Ceph) | `harbor_registry_user` | secret `registry-pull-secret` (namespace `rook-ceph`) |
+
+URL: https://registry.abrban.com/
+
+---
+
+## پروژه‌های proxy-cache
+
+| پروژه | upstream | کاربرد |
+|-------|----------|--------|
+| `proxy-dockerhub` | docker.io | Rook، Ceph، bitnami، … |
+| `proxy-quay` | quay.io | cephcsi و … |
+| `proxy-k8s` | registry.k8s.io | CSI sidecarها |
+
+ایجاد از UI: **Administration → Registries → New Endpoint** سپس **Projects → New Project** با نوع Proxy Cache.
+
+> health check بعضی endpointها (مثلاً quay) از UI timeout می‌خورد؛ از داخل `harbor-core` با curl و proxy ممکن است OK باشد. در صورت نیاز endpoint را با type `docker-registry` بسازید.
+
+### proxy در Harbor
+
+پروکسی از secret `registry-egress-proxy` در ConfigMapهای `harbor-core` و `harbor-jobservice-env` تزریق می‌شود.
+
+**مهم:** Go (harbor-core/jobservice) به `http_proxy` / `https_proxy` **lowercase** هم نیاز دارد. اگر health check upstream `unhealthy` ماند، هر دو حالت uppercase و lowercase را در ConfigMap بگذارید و podها را restart کنید:
+
+```bash
+kubectl -n cloudhost rollout restart deploy/harbor-core deploy/harbor-jobservice
+```
+
+---
+
+## mirror دستی ایمیج (وقتی proxy-cache کار نمی‌کند)
+
+روی abr، pull مستقیم از docker.io/quay از kubelet ممکن نیست. ایمیج‌های حیاتی را با Job داخل کلاستر mirror کنید:
+
+**مقصد push:** `harbor-registry.cloudhost.svc.cluster.local:5000` (HTTP، با `harbor_registry_user`)
+
+**مثال مسیرها در registry:**
+
+| ایمیج upstream | مسیر در registry |
+|----------------|------------------|
+| `rook/ceph:v1.20.1` | `rook/ceph:v1.20.1` |
+| `quay.io/ceph/ceph:v19.2` | `proxy-dockerhub/ceph/ceph:v19.2` |
+
+```bash
+# لیست ایمیج‌های داخل harbor-registry
+kubectl -n cloudhost exec deploy/harbor-portal -- \
+  curl -s -u "harbor_registry_user:$(kubectl -n cloudhost get secret harbor-core -o jsonpath='{.data.REGISTRY_CREDENTIAL_PASSWORD}' | base64 -d)" \
+  http://harbor-registry:5000/v2/_catalog
+```
+
+> push مستقیم به `harbor-registry:5000` metadata در Harbor UI را به‌روز نمی‌کند؛ برای kubelet کافی است چون `/v2/` به harbor-registry route شده.
+
+---
+
+## مدیریت روزمره
+
+### وضعیت
+
+```bash
+kubectl -n cloudhost get pods | grep harbor
+kubectl -n cloudhost get ingress registry -o yaml | grep -A3 'path:'
+curl -sk -o /dev/null -w "%{http_code}\n" https://registry.abrban.com/
+curl -sk -u admin:<pass> https://registry.abrban.com/api/v2.0/systeminfo
+```
+
+### لاگ‌ها
+
+```bash
+kubectl -n cloudhost logs deploy/harbor-core --tail=50
+kubectl -n cloudhost logs deploy/harbor-jobservice --tail=50
+kubectl -n cloudhost logs deploy/harbor-registry -c registry --tail=50
+```
+
+### ارتقا Harbor
+
+```bash
+helm repo update harbor
+./scripts/install-harbor-registry.sh
+# Ingress split را دوباره تأیید کنید
+```
+
+### rollback به registry قدیمی
+
+```bash
+kubectl -n cloudhost scale deploy/registry --replicas=1
+# Ingress را فقط به service registry:5000 برگردانید
+helm uninstall harbor -n cloudhost
+```
+
+---
+
+## عیب‌یابی
+
+| علامت | علت محتمل | اقدام |
+|-------|-----------|--------|
+| `https://registry.abrban.com/` → 404 | Ingress فقط به `harbor-core` وصل است | `/` → `harbor-portal` |
+| `ImagePullBackOff` برای `cloudhost-backend` | `/v2/` به Harbor رفته، ایمیج platform آنجا نیست | `/v2/` (عمومی) → `registry` قدیمی |
+| `not found` برای `proxy-dockerhub/...` | ایمیج mirror نشده | Job skopeo یا proxy-cache |
+| push با 499/503 | Traefik timeout | push از داخل کلاستر به `harbor-registry:5000` |
+| registry endpoint `unhealthy` | proxy lowercase یا timeout health check | patch ConfigMap + restart؛ یا mirror دستی |
+| `authentication required` روی pull | pull secret اشتباه namespace | `cloudhost` vs `harbor_registry_user` در `rook-ceph` |
+
+### تست pull
+
+```bash
+# platform (cloudhost user)
+curl -sk -u "cloudhost:<pass>" https://registry.abrban.com/v2/cloudhost-backend/tags/list
+
+# rook/ceph (harbor_registry_user)
+curl -sk -u "harbor_registry_user:<pass>" https://registry.abrban.com/v2/rook/ceph/tags/list
+```
+
+---
+
+## چک‌لیست بعد از نصب
+
+- [ ] Portal روی `/` پاسخ 200
+- [ ] `/api/v2.0/systeminfo` پاسخ JSON
+- [ ] Ingress split `/v2/` درست است
+- [ ] پروژه‌های `proxy-dockerhub`, `proxy-k8s`, `proxy-quay` ساخته شده
+- [ ] `registry-pull-secret` در `cloudhost` و `rook-ceph` به‌روز است
+- [ ] ایمیج‌های Rook/Ceph mirror شده و pull تست شده

RUNBOOK.en.md

@@ -0,0 +1,69 @@
+# CloudHost — Operations Runbook (English)
+
+Short operational guide. For architecture details see [ARCHITECTURE.md](ARCHITECTURE.md). For Persian production deploy steps see [RUNBOOK.fa.md](RUNBOOK.fa.md).
+
+## Stack
+
+- **Frontend:** Next.js 16 (`/fa-IR`, `/en-US` routes)
+- **Backend:** NestJS 11 (`/api/v1`, Swagger at `/api/docs`)
+- **Data:** PostgreSQL 16, Redis 7
+- **Build:** Kaniko in-cluster (`cloudhost-builds` namespace)
+- **Deploy:** Helm charts (`cloudhost-platform`, `cloudhost-app`, `cloudhost-logging`)
+
+## Health checks
+
+| Endpoint | Purpose |
+|----------|---------|
+| `GET /api/v1/health` | Liveness |
+| `GET /api/v1/ready` | Readiness (DB ping) |
+
+## Local development
+
+```bash
+docker compose up -d postgres redis
+cd backend && cp .env.example .env && npm run start:dev
+cd frontend && cp .env.local.example .env.local && npm run dev
+```
+
+## SQL migrations
+
+1. Add file under `backend/migrations/`
+2. Run `cd backend && npm run sync:migrations` (copies into Helm chart)
+3. Helm post-install Job applies migrations on upgrade
+
+## Build namespace bootstrap
+
+```bash
+kubectl apply -f backend/k8s/builds/cloudhost-builds-bootstrap.yaml
+```
+
+Configure `REGISTRY_URL`, `BUILD_NAMESPACE`, and `CLUSTER_KUBECONFIG_KEY` in backend env.
+
+## Backups (optional Helm)
+
+Enable in `values.yaml`:
+
+```yaml
+backups:
+  postgres:
+    enabled: true
+    schedule: "0 3 * * *"
+    storageSize: 10Gi
+```
+
+Restore: `gunzip -c backup.sql.gz | psql` against the control-plane database.
+
+## Monitoring (optional)
+
+Enable Prometheus ServiceMonitor:
+
+```yaml
+monitoring:
+  enabled: true
+```
+
+Requires `kube-prometheus-stack` or compatible Prometheus Operator in the cluster.
+
+## CI
+
+GitHub Actions runs backend/frontend tests, typecheck, build, and `helm lint` on push/PR.

RUNBOOK.fa.md

@@ -0,0 +1,232 @@
+# CloudHost — راهنمای معماری و اجرای وبسایت (Runbook)
+
+این سند دو بخش دارد:
+1. **اپلیکیشن چطور کار می‌کند** — معماری و جریان‌ها.
+2. **اجرای وبسایت، مرحله‌به‌مرحله** — هم برای توسعه‌ی محلی، هم برای استقرار (deploy) روی کلاستر k3s سرور (abrban) به‌همراه راه‌حل‌های مخصوص شبکه‌ی ایران.
+
+> اصطلاح‌ها: «پنل» = اپ احرازشده (`panel.abrban.com`)، «لندینگ» = صفحه‌ی معرفی (`abrban.com`)، «اپ کاربر» = اپلیکیشنی که مشتری روی CloudHost دیپلوی می‌کند.
+
+> **به‌روزرسانی ۲۰۲۶:** pipeline بیلد فعلی از **Kaniko** + Dockerfileهای نگهداری‌شده توسط پلتفرم استفاده می‌کند (نه Nixpacks/MinIO). آرشیو سورس روی دیسک/PVC آپلود می‌شود. manifest بوت‌استرپ namespace بیلد: [`backend/k8s/builds/cloudhost-builds-bootstrap.yaml`](backend/k8s/builds/cloudhost-builds-bootstrap.yaml).
+
+> **استقرار از صفر روی سرور:** [`RUNBOOK-DEPLOY.fa.md`](RUNBOOK-DEPLOY.fa.md) — مراحل values، Secretها، deploy، greenfield reset.
+
+---
+
+### ۱.۱ CloudHost چیست
+یک **PaaS خودسرویس** برای بازار ایران: کاربر کد/ریپوی خودش را می‌دهد و CloudHost آن را build و روی Kubernetes اجرا می‌کند، با مدیریت دامنه، دیتابیس، لاگ، فاکتور و کیف پول.
+
+### ۱.۲ اجزای اصلی
+
+| جزء | تکنولوژی | نقش |
+|---|---|---|
+| **Frontend** | Next.js (App Router, SSR) | لندینگ + پنل کاربری/ادمین |
+| **Backend** | NestJS (REST `/api/v1`) | منطق کسب‌وکار، ساخت اپ، احراز هویت |
+| **Postgres** | postgres:16 | دیتابیس اصلی (کاربر، اپ، فاکتور، …) |
+| **Redis** | redis:7 | کش، صف Bull (مهاجرت اپ، دسترسی موقت)، پیشرفت بیلد |
+| **Registry داخلی** | Harbor + registry:2 (legacy) | ایمیج‌های build و platform؛ جزئیات: [`RUNBOOK-HARBOR.fa.md`](RUNBOOK-HARBOR.fa.md) |
+| **Storage (Ceph)** | Rook-Ceph | PVC (`rook-ceph-block`) + bucket zip (`rook-ceph-bucket`)؛ جزئیات: [`RUNBOOK-CEPH.fa.md`](RUNBOOK-CEPH.fa.md) |
+| **Build pipeline** | Kaniko | تبدیل سورس به ایمیج Docker داخل کلاستر (بدون Docker daemon) |
+| **Kubernetes** | k3s (تک‌نود) | اجرای همه‌ی موارد بالا + اپ‌های کاربر |
+
+### ۱.۳ دامنه‌ها (همه روی `78.157.39.52`، HTTPS با wildcard cert)
+- `abrban.com` → لندینگ
+- `panel.abrban.com` → پنل احرازشده
+- `api.abrban.com` → بک‌اند
+- `registry.abrban.com` → Harbor (UI + proxy-cache) + registry قدیمی برای ایمیج‌های platform — [`RUNBOOK-HARBOR.fa.md`](RUNBOOK-HARBOR.fa.md)
+- `apps.abrban.com` → دامنه‌ی پیش‌فرض اپ‌های کاربر
+
+### ۱.۴ جریان احراز هویت
+- ورود مبتنی بر **موبایل + OTP** (پیامک از طریق MizbanSMS) یا رمز عبور.
+- توکن **JWT** (access ~15m، refresh ~7d).
+- `JwtStrategy` در هر درخواست نقش و فعال‌بودن کاربر را **از دیتابیس** می‌خواند (نه از توکن) تا تغییر نقش/غیرفعال‌سازی بلافاصله اثر کند.
+
+### ۱.۵ جریان دیپلویِ «اپ کاربر» (مهم‌ترین بخش)
+وقتی کاربر یک اپ را build/redeploy می‌کند:
+
+```
+کاربر (پنل)
+   │  آپلود zip  ──────────────►  MinIO (bucket: app-sources)   ┐
+   │  یا git URL                                                  │ منبع سورس
+   ▼                                                              │
+Backend: یک job در صف Bull («app-deploy») می‌گذارد              │
+   ▼                                                              │
+ساخت یک Kubernetes Job در namespace «cloudhost-builds»:         │
+   1) init: fetch-source (دانلود از MinIO) یا git-clone  ◄───────┘
+   2) init: nixpacks-prepare
+        • اگر سورس Dockerfile دارد → همان (BYO)
+        • وگرنه → با Nixpacks یک Dockerfile می‌سازد
+   3) container: Kaniko  → build ایمیج → push به registry داخلی
+   ▼
+(غیرمسدودکننده) اسکن Trivy → خلاصه‌ی آسیب‌پذیری
+   ▼
+Backend با Helm، اپ را روی کلاستر بالا می‌آورد (Deployment + Service + Ingress)
+   ▼
+GC رجیستری: روزانه فقط N نسخه‌ی آخر هر اپ را نگه می‌دارد
+```
+
+- پیشرفت بیلد در Redis نگه‌داری می‌شود؛ فرانت هر ۱.۵ ثانیه `build-progress`/`build-logs` را poll می‌کند.
+- توکن git در یک Secret موقتِ هر بیلد می‌نشیند و در `finally` پاک می‌شود (در manifest درج نمی‌شود).
+
+---
+
+## بخش ۲ — اجرای محلی (Local Dev)
+
+پیش‌نیاز: Node 20، Docker، Docker Compose.
+
+```bash
+# ۱) دیتابیس و Redis
+docker compose up -d            # از docker-compose.yml ریشه‌ی پروژه
+
+# ۲) بک‌اند
+cd backend
+cp .env.example .env            # مقادیر را پر کن (DB، JWT، SMS، …)
+npm install
+npm run start:dev               # روی http://localhost:4000  (پیشوند /api/v1)
+
+# ۳) فرانت
+cd ../frontend
+npm install
+npm run dev                     # روی http://localhost:3000
+```
+
+- در حالت dev، TypeORM `synchronize` روشن است و جدول‌ها خودکار ساخته می‌شوند.
+- `NEXT_PUBLIC_API_URL` فرانت باید به آدرس بک‌اند اشاره کند.
+
+---
+
+## بخش ۳ — استقرار روی کلاستر (abrban / k3s)
+
+> این بخش فرض می‌کند کلاستر k3s و wildcard cert از قبل آماده‌اند. context کوبه: `default`.
+
+### ۳.۰ ثابت‌های محیط
+| | مقدار |
+|---|---|
+| namespace اپ | `cloudhost` |
+| namespace بیلد | `cloudhost-builds` |
+| Helm release | `cloudhost` |
+| چارت | `backend/helm/cloudhost-platform` |
+| values | `/tmp/abrban/values-abrban.yaml` |
+| رجیستری (push داخلی) | `registry.cloudhost.svc.cluster.local:5000` (HTTP, insecure) |
+| رجیستری (pull توسط kubelet) | `registry.abrban.com` (HTTPS, wildcard cert) — همان storage |
+| پروکسی build | `http://builder:<pw>@45.129.38.203:9911` |
+
+### ۳.۱ نکات شبکه‌ی ایران (چرا کارها این‌شکلی‌اند)
+- کلاستر به **Let's Encrypt، github، docker.io، ghcr.io، gcr.io** مستقیم نمی‌رسد (یا خیلی کند).
+- **gTLS/cert**: دستی، secret `abrban-wildcard-tls` (نه cert-manager).
+- **npm**: از `registry.npmmirror.com` مستقیم (نه پروکسی).
+- **ایمیج‌های پایه**: اول داخل رجیستری داخلی **mirror** می‌شوند، بعد استفاده.
+- **دانلودهای build (apk/nix/pip/…)**: از طریق پروکسی بالا.
+
+### ۳.۲ گام‌های استقرار
+
+**گام ۱ — بررسی دسترسی کلاستر**
+```bash
+kubectl config current-context          # باید default باشد
+kubectl get nodes
+```
+
+**گام ۲ — mirror کردن ایمیج‌های پایه به رجیستری داخلی**
+ایمیج‌هایی که کلاستر مستقیم نمی‌تواند pull کند را با یک Job داخل کلاستر کپی کن.
+- برای ایمیج‌های **کوچک**: `crane copy <src> registry.cloudhost.svc.cluster.local:5000/<dst> --insecure`
+- برای ایمیج‌های **بزرگ** (مثل nixpacks): از **skopeo** استفاده کن — چون بلاب را با PUT یکجا آپلود می‌کند و گیر `PROTOCOL_ERROR` آپلود تکه‌ای crane را ندارد:
+  ```
+  skopeo copy --override-os linux --override-arch amd64 --dest-tls-verify=false \
+    docker://<src> docker://registry.cloudhost.svc.cluster.local:5000/<dst>
+  ```
+  (با `REGISTRY_AUTH_FILE` از secret `kaniko-docker-config` و env پروکسی.)
+
+ایمیج‌های لازم: `minio/minio`, `railwayapp/nixpacks`, `library/alpine:3.19`, `library/postgres`, `library/redis`, و base ای که Nixpacks تولید می‌کند.
+
+**گام ۳ — MinIO (ذخیره‌ی سورس اپ‌ها)**
+به‌طور خودکار فقط هنگام **ثبت کلاستر جدید** ساخته می‌شود؛ روی کلاستر موجود دستی بساز: secret `minio-credentials` (`accesskey`/`secretkey`) + PVC ۲۰Gi + Deployment (`registry.abrban.com/minio/minio:latest`) + Service، همه در `cloudhost-builds`. کردنشال پیش‌فرض با config بک‌اند می‌خواند.
+
+**گام ۴ — pull-secret برای namespace بیلد**
+```bash
+# کپی pull-secret رجیستری به ns بیلد
+kubectl get secret registry-pull-secret -n cloudhost -o json \
+ | jq '.metadata.namespace="cloudhost-builds" | del(.metadata.uid,.metadata.resourceVersion,.metadata.creationTimestamp)' \
+ | kubectl apply -f -
+# وصل به هر دو ServiceAccount که pod بیلد ممکن است از آن‌ها استفاده کند
+kubectl patch sa default        -n cloudhost-builds -p '{"imagePullSecrets":[{"name":"registry-pull-secret"}]}'
+kubectl patch sa kaniko-builder -n cloudhost-builds -p '{"imagePullSecrets":[{"name":"registry-pull-secret"}]}'
+```
+> ⚠️ `kaniko-builder` حتماً لازم است: pod بیلد با همین SA اجرا می‌شود و init container نیکس‌پکس ایمیجش را از `registry.abrban.com` می‌کشد.
+
+**گام ۵ — build ایمیج‌های frontend/backend (Kaniko)**
+سورس را در PVC بیلد (`build-src`) از طریق pod `srcsync` قرار بده، سپس Job‌های Kaniko را اجرا کن.
+```bash
+# سینک سورس (از working tree؛ tsbuildinfo و dist را حذف کن!)
+cd <repo>
+tar czf - --exclude=node_modules --exclude=.next --exclude=.git frontend \
+  | kubectl exec -i srcsync -n cloudhost -- sh -c 'rm -rf /workspace/frontend && tar xzf - -C /workspace'
+rm -f backend/tsconfig.tsbuildinfo      # ← مهم
+tar czf - --exclude=node_modules --exclude=dist --exclude=.git backend \
+  | kubectl exec -i srcsync -n cloudhost -- sh -c 'rm -rf /workspace/backend && tar xzf - -C /workspace'
+
+# build (manifestهای kaniko-*.yaml: registry-mirror + proxy + npmmirror)
+kubectl apply -f /tmp/abrban/kaniko-frontend-<tag>.yaml
+kubectl apply -f /tmp/abrban/kaniko-backend-<tag>.yaml
+```
+
+**گام ۶ — استقرار با Helm**
+```bash
+helm upgrade cloudhost backend/helm/cloudhost-platform \
+  -n cloudhost -f /tmp/abrban/values-abrban.yaml \
+  --set images.backend.tag=<tag> \
+  --set images.frontend.tag=<tag> \
+  --set migrations.enabled=false        # ← مهاجرت‌ها روی DB زنده تداخل دارند
+```
+> بدون `--wait` اجرا کن (وگرنه به‌خاطر کندیِ pull، status اشتباهاً `failed` می‌شود درحالی‌که rollout موفق است).
+
+**گام ۷ — bootstrap اسکیمای دیتابیس (فقط روی DB تازه)**
+در پروداکشن `synchronize` خاموش است. روی DB کاملاً تازه: موقتاً `NODE_ENV=development` کن تا synchronize جدول‌ها را بسازد و pricing خودش seed شود، بعد به `production` برگردان. روی DB موجود، فقط مهاجرت‌های idempotent جدید را با یک Job جدا اعمال کن (نه helm hook).
+
+**گام ۸ — تأیید**
+```bash
+kubectl get deploy -n cloudhost                       # backend/frontend 1/1
+helm status cloudhost -n cloudhost                    # STATUS: deployed
+curl -s -o /dev/null -w '%{http_code}\n' https://panel.abrban.com   # 307
+curl -s -X POST https://api.abrban.com/api/v1/auth/otp/request \
+  -H 'Content-Type: application/json' -d '{"phone":"09xxxxxxxxx"}'  # {"sent":true}
+```
+
+---
+
+## بخش ۴ — env‌های کلیدی build pipeline (روی بک‌اند)
+این‌ها در `backend.env` فایل values ست می‌شوند:
+
+| env | مقدار/توضیح |
+|---|---|
+| `MINIO_SECRET_KEY` | کلید MinIO (هماهنگ با secret) |
+| `NIXPACKS_IMAGE` | `registry.abrban.com/railwayapp/nixpacks:latest` (mirror) |
+| `NIXPACKS_BUILD_ENV` | `NPM_CONFIG_REGISTRY=https://registry.npmmirror.com` |
+| `BUILD_HTTP_PROXY` | پروکسی build (تزریق به Kaniko + init containerها) |
+| `BUILD_REGISTRY_MIRROR` | `registry.cloudhost.svc.cluster.local:5000` (pull پایه از mirror) |
+| `BUILD_SCAN_ENABLED` | `false` تا وقتی ایمیج Trivy mirror شود |
+| `SMS_PROVIDER` + `MIZBANSMS_*` | بدون این‌ها ارسال OTP خطای 503 می‌دهد |
+
+---
+
+## بخش ۵ — عیب‌یابی رایج
+
+| نشانه | علت | راه‌حل |
+|---|---|---|
+| backend کرش: `Cannot find module '/app/dist/main.js'` | `tsconfig.tsbuildinfo` کهنه در سورس → tsc فایل‌ها را دوباره emit نمی‌کند | قبل از build، `tsconfig.tsbuildinfo` را حذف کن |
+| init container بیلد: `no basic auth credentials` | SA `kaniko-builder` بدون pull-secret | گام ۴ را اجرا کن |
+| pull ایمیج: `not found` با اینکه push شده | crane در آپلود تکه‌ایِ بلاب بزرگ شکست خورده (tag ناقص) | با **skopeo** دوباره mirror کن |
+| pull از docker.io: `TLS handshake timeout` | docker.io از کلاستر بسته است | ایمیج را mirror کن |
+| `nixpacks: not found` در init | باینری نیکس‌پکس روی PATH پیش‌فرض نیست | command را با مسیر/ENTRYPOINT درست صدا بزن |
+| helm: `no template "...namespace"` یا `nil pointer redis.enabled` | فایل‌های چارت (`_helpers.tpl`/`values.yaml`) از `/tmp` پاک شده‌اند | از سورس اصلی بازیابی + ادیت‌های deploy را دوباره اعمال کن |
+| OTP خطای 503 | env پیامک ست نیست | `SMS_PROVIDER`/`MIZBANSMS_*` را ست کن |
+
+> ⚠️ پوشه‌ی `/tmp` در macOS فایل‌های قدیمی‌تر از ~۳ روز را پاک می‌کند؛ درخت کاری deploy در `/tmp` ممکن است فایل از دست بدهد — قبل از build بررسی کن.
+
+---
+
+## بخش ۶ — به‌روزرسانی نسخه (خلاصه)
+1. تغییرات کد را در سورس اعمال کن (`tsc --noEmit` بگیر).
+2. tag جدید انتخاب کن.
+3. سورس را در `srcsync` سینک کن (با حذف `tsbuildinfo`).
+4. Job Kaniko را با tag جدید بساز.
+5. `helm upgrade ... --set images.*.tag=<tag> --set migrations.enabled=false` (بدون `--wait`).
+6. تأیید کن: podها 1/1، helm `deployed`، endpoint‌ها سالم.

backend/.env.example

@@ -20,6 +20,13 @@ JWT_REFRESH_EXPIRES_IN=7d
 REDIS_HOST=localhost
 REDIS_PORT=6379
 
+# Multi-cluster: AES-256-GCM key for encrypting kubeconfigs at rest (required in production).
+# Generate with: openssl rand -hex 32
+CLUSTER_KUBECONFIG_KEY=
+
+# Stub payment gateway (dev/staging only — disabled in production unless explicitly enabled)
+# PAYMENT_GATEWAY_STUB_ENABLED=true
+
 # ─── OTP SMS ────────────────────────────────────────────────────────────────
 # Pick the provider. Without valid credentials, OTP codes are logged to the API
 # console in development only; in production a missing config makes OTP send fail
@@ -68,6 +75,11 @@ REGISTRY_PASSWORD=registry_secret
 # Build
 BUILD_NAMESPACE=cloudhost-builds
 BUILD_SERVICE_ACCOUNT=kaniko-builder
+# Kaniko job images — defaults pull from Harbor proxy-cache when unset.
+# KANIKO_IMAGE=registry.abrban.com/proxy-gcr/kaniko-project/executor:v1.23.2
+# BUILD_ALPINE_IMAGE=registry.abrban.com/proxy-dockerhub/library/alpine:3.19
+# BUILD_ALPINE_GIT_IMAGE=registry.abrban.com/proxy-dockerhub/alpine/git:2.43.0
+# BASE_IMAGE_REGISTRY=registry.abrban.com/proxy-dockerhub/library
 
 # Platform
 # Public URL(s) of the frontend — used for CORS and to derive the platform/preview

backend/Dockerfile

@@ -1,5 +1,6 @@
 # ---- Stage 1: Build ----
-FROM node:24-alpine AS builder
+ARG BASE_IMAGE=node:24-alpine
+FROM ${BASE_IMAGE} AS builder
 
 WORKDIR /app
 
@@ -10,7 +11,7 @@ COPY . .
 RUN npm run build
 
 # ---- Stage 2: Production ----
-FROM node:24-alpine AS production
+FROM ${BASE_IMAGE} AS production
 
 RUN apk add --no-cache dumb-init curl bash \
  && curl -fsSL https://get.helm.sh/helm-v3.15.4-linux-amd64.tar.gz | tar xz -C /tmp \

backend/eslint.config.mjs

@@ -0,0 +1,28 @@
+import tsPlugin from '@typescript-eslint/eslint-plugin';
+import tsParser from '@typescript-eslint/parser';
+
+/** @type {import('eslint').Linter.Config[]} */
+export default [
+  {
+    ignores: ['dist/**', 'node_modules/**', 'coverage/**'],
+  },
+  {
+    files: ['src/**/*.ts', 'test/**/*.ts'],
+    languageOptions: {
+      parser: tsParser,
+      parserOptions: {
+        ecmaVersion: 'latest',
+        sourceType: 'module',
+      },
+    },
+    plugins: {
+      '@typescript-eslint': tsPlugin,
+    },
+    rules: {
+      ...tsPlugin.configs.recommended.rules,
+      '@typescript-eslint/no-explicit-any': 'off',
+      '@typescript-eslint/no-require-imports': 'off',
+      '@typescript-eslint/no-unused-vars': ['warn', { argsIgnorePattern: '^_' }],
+    },
+  },
+];

backend/helm/cloudhost-app/templates/_helpers.tpl

@@ -46,6 +46,16 @@ Database deployment name
 {{- printf "%s-db" .Values.app.name }}
 {{- end }}
 
+{{/*
+Optional mirror registry prefix for Docker Hub images.
+Usage: {{ include "cloudhost-app.baseImage" (dict "root" $ "image" "redis:7.2-alpine") }}
+*/}}
+{{- define "cloudhost-app.baseImage" -}}
+{{- $reg := "" -}}
+{{- with .root.Values.images -}}{{- $reg = .baseRegistry | default "" -}}{{- end -}}
+{{- if $reg -}}{{ printf "%s/%s" $reg .image }}{{- else -}}{{ .image }}{{- end -}}
+{{- end }}
+
 {{/*
 Database image — auto-computed from type + version if not explicitly set
 */}}
@@ -53,13 +63,13 @@ Database image — auto-computed from type + version if not explicitly set
 {{- if .Values.database.image }}
   {{- .Values.database.image }}
 {{- else if eq .Values.database.type "postgresql" }}
-  {{- printf "postgres:%s-alpine" .Values.database.version }}
+  {{- include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "postgres:%s-alpine" .Values.database.version)) }}
 {{- else if eq .Values.database.type "mariadb" }}
-  {{- printf "mariadb:%s" .Values.database.version }}
+  {{- include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "mariadb:%s" .Values.database.version)) }}
 {{- else if eq .Values.database.type "mongodb" }}
-  {{- printf "mongo:%s" .Values.database.version }}
+  {{- include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "mongo:%s" .Values.database.version)) }}
 {{- else }}
-  {{- printf "mysql:%s" .Values.database.version }}
+  {{- include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "mysql:%s" .Values.database.version)) }}
 {{- end }}
 {{- end }}
 

backend/helm/cloudhost-app/templates/_log-shipper.tpl

@@ -5,7 +5,7 @@
 {{- define "cloudhost-app.logShipperContainers" -}}
 {{- if .root.Values.elasticsearch.enabled }}
 - name: log-shipper
-  image: fluent/fluent-bit:2.2
+  image: {{ include "cloudhost-app.baseImage" (dict "root" .root "image" "fluent/fluent-bit:2.2") }}
   resources:
     requests:
       cpu: "10m"

backend/helm/cloudhost-app/templates/db-deployment.yaml

@@ -16,6 +16,10 @@ metadata:
     {{- include "cloudhost-app.labels" . | nindent 4 }}
 spec:
   replicas: 1
+  # RWO volume + single replica: recreate the old pod before starting the new
+  # one — a rolling update would deadlock on the attached PVC.
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       app: {{ $dbName }}
@@ -114,7 +118,7 @@ spec:
               command: ["healthcheck.sh", "--connect", "--innodb_initialized"]
             {{- else if eq .Values.database.type "mongodb" }}
             exec:
-              command: ["mongosh", "--eval", "db.adminCommand('ping')"]
+              command: ["sh", "-c", "mongosh --quiet -u \"$MONGO_INITDB_ROOT_USERNAME\" -p \"$MONGO_INITDB_ROOT_PASSWORD\" --eval \"db.adminCommand('ping')\""]
             {{- else }}
             exec:
               command: ["mysqladmin", "ping", "-h", "127.0.0.1"]
@@ -131,7 +135,7 @@ spec:
               command: ["healthcheck.sh", "--connect", "--innodb_initialized"]
             {{- else if eq .Values.database.type "mongodb" }}
             exec:
-              command: ["mongosh", "--eval", "db.adminCommand('ping')"]
+              command: ["sh", "-c", "mongosh --quiet -u \"$MONGO_INITDB_ROOT_USERNAME\" -p \"$MONGO_INITDB_ROOT_PASSWORD\" --eval \"db.adminCommand('ping')\""]
             {{- else }}
             exec:
               command: ["mysqladmin", "ping", "-h", "127.0.0.1"]

backend/helm/cloudhost-app/templates/deployment.yaml

@@ -217,7 +217,7 @@ spec:
             {{- end }}
         {{- if .Values.elasticsearch.enabled }}
         - name: fluent-bit
-          image: fluent/fluent-bit:2.2
+          image: {{ include "cloudhost-app.baseImage" (dict "root" $ "image" "fluent/fluent-bit:2.2") }}
           resources:
             requests:
               cpu: "10m"

backend/helm/cloudhost-app/templates/elasticsearch-credentials-secret.yaml

@@ -1,4 +1,7 @@
 {{- if .Values.elasticsearch.enabled }}
+{{- if not .Values.elasticsearch.fluentbitPassword }}
+{{- fail "elasticsearch.fluentbitPassword is required when elasticsearch.enabled=true — no hardcoded default is shipped" }}
+{{- end }}
 apiVersion: v1
 kind: Secret
 metadata:
@@ -8,7 +11,7 @@ metadata:
     {{- include "cloudhost-app.labels" . | nindent 4 }}
 type: Opaque
 stringData:
-  ELASTIC_PASSWORD: {{ .Values.elasticsearch.elasticPassword | default "CloudHost2024!Secure" | quote }}
+  ELASTIC_PASSWORD: {{ .Values.elasticsearch.elasticPassword | quote }}
-  FLUENTBIT_PASSWORD: {{ .Values.elasticsearch.fluentbitPassword | default "FluentBit2024!Writer" | quote }}
+  FLUENTBIT_PASSWORD: {{ .Values.elasticsearch.fluentbitPassword | quote }}
-  KIBANA_SYSTEM_PASSWORD: {{ .Values.elasticsearch.kibanaPassword | default "Kibana2024!System" | quote }}
+  KIBANA_SYSTEM_PASSWORD: {{ .Values.elasticsearch.kibanaPassword | quote }}
 {{- end }}

backend/helm/cloudhost-app/templates/rabbitmq-deployment.yaml

@@ -2,11 +2,22 @@
 {{- $name       := include "cloudhost-app.name" . -}}
 {{- $ns         := include "cloudhost-app.namespace" . -}}
 {{- $rabbitName := printf "%s-rabbitmq" $name -}}
+{{- /* Preserve the existing password across upgrades — RabbitMQ only applies
+       RABBITMQ_DEFAULT_PASS on first boot, so a regenerated secret would
+       diverge from the credentials stored in the persisted volume. */ -}}
+{{- $rabbitSecretName := printf "%s-secret" $rabbitName -}}
+{{- $existingRabbit := lookup "v1" "Secret" $ns $rabbitSecretName -}}
+{{- $rabbitPass := "" -}}
+{{- if and $existingRabbit $existingRabbit.data (index $existingRabbit.data "password") -}}
+{{- $rabbitPass = index $existingRabbit.data "password" | b64dec -}}
+{{- else -}}
+{{- $rabbitPass = randAlphaNum 16 -}}
+{{- end -}}
 ---
 apiVersion: v1
 kind: Secret
 metadata:
-  name: {{ $rabbitName }}-secret
+  name: {{ $rabbitSecretName }}
   namespace: {{ $ns }}
   labels:
     app: {{ $rabbitName }}
@@ -16,7 +27,7 @@ metadata:
 type: Opaque
 data:
   username: {{ "appuser" | b64enc | quote }}
-  password: {{ randAlphaNum 16 | b64enc | quote }}
+  password: {{ $rabbitPass | b64enc | quote }}
 ---
 apiVersion: v1
 kind: PersistentVolumeClaim
@@ -48,6 +59,9 @@ metadata:
     {{- include "cloudhost-app.labels" . | nindent 4 }}
 spec:
   replicas: 1
+  # RWO volume + single replica: recreate instead of rolling update.
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       app: {{ $rabbitName }}
@@ -58,7 +72,7 @@ spec:
     spec:
       containers:
         - name: rabbitmq
-          image: {{ printf "rabbitmq:%s-management-alpine" (.Values.rabbitmq.version | default "3.13") }}
+          image: {{ include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "rabbitmq:%s-management-alpine" (.Values.rabbitmq.version | default "3.13"))) }}
           ports:
             - containerPort: 5672
               name: amqp
@@ -68,12 +82,12 @@ spec:
             - name: RABBITMQ_DEFAULT_USER
               valueFrom:
                 secretKeyRef:
-                  name: {{ $rabbitName }}-secret
+                  name: {{ $rabbitSecretName }}
                   key: username
             - name: RABBITMQ_DEFAULT_PASS
               valueFrom:
                 secretKeyRef:
-                  name: {{ $rabbitName }}-secret
+                  name: {{ $rabbitSecretName }}
                   key: password
           volumeMounts:
             - name: rabbitmq-data

backend/helm/cloudhost-app/templates/redis-deployment.yaml

@@ -2,11 +2,21 @@
 {{- $name    := include "cloudhost-app.name" . -}}
 {{- $ns      := include "cloudhost-app.namespace" . -}}
 {{- $redisName := printf "%s-redis" $name -}}
+{{- /* Preserve the existing password across upgrades — regenerating it every
+       upgrade would break app↔Redis auth against the persisted volume. */ -}}
+{{- $redisSecretName := printf "%s-secret" $redisName -}}
+{{- $existingRedis := lookup "v1" "Secret" $ns $redisSecretName -}}
+{{- $redisPass := "" -}}
+{{- if and $existingRedis $existingRedis.data (index $existingRedis.data "password") -}}
+{{- $redisPass = index $existingRedis.data "password" | b64dec -}}
+{{- else -}}
+{{- $redisPass = randAlphaNum 16 -}}
+{{- end -}}
 ---
 apiVersion: v1
 kind: Secret
 metadata:
-  name: {{ $redisName }}-secret
+  name: {{ $redisSecretName }}
   namespace: {{ $ns }}
   labels:
     app: {{ $redisName }}
@@ -15,7 +25,7 @@ metadata:
     "helm.sh/resource-policy": keep
 type: Opaque
 data:
-  password: {{ randAlphaNum 16 | b64enc | quote }}
+  password: {{ $redisPass | b64enc | quote }}
 ---
 apiVersion: v1
 kind: PersistentVolumeClaim
@@ -47,6 +57,10 @@ metadata:
     {{- include "cloudhost-app.labels" . | nindent 4 }}
 spec:
   replicas: 1
+  # RWO volume + single replica: recreate the old pod before starting the new
+  # one, otherwise a rolling update deadlocks on the attached PVC.
+  strategy:
+    type: Recreate
   selector:
     matchLabels:
       app: {{ $redisName }}
@@ -57,7 +71,7 @@ spec:
     spec:
       containers:
         - name: redis
-          image: {{ printf "redis:%s-alpine" (.Values.redis.version | default "7.2") }}
+          image: {{ include "cloudhost-app.baseImage" (dict "root" $ "image" (printf "redis:%s-alpine" (.Values.redis.version | default "7.2"))) }}
           args: ["--requirepass", "$(REDIS_PASSWORD)"]
           ports:
             - containerPort: 6379
@@ -65,7 +79,14 @@ spec:
             - name: REDIS_PASSWORD
               valueFrom:
                 secretKeyRef:
-                  name: {{ $redisName }}-secret
+                  name: {{ $redisSecretName }}
+                  key: password
+            # redis-cli in the probes auto-authenticates from REDISCLI_AUTH,
+            # so `redis-cli ping` works even with --requirepass set.
+            - name: REDISCLI_AUTH
+              valueFrom:
+                secretKeyRef:
+                  name: {{ $redisSecretName }}
                   key: password
           volumeMounts:
             - name: redis-data

backend/helm/cloudhost-app/values.yaml

@@ -101,3 +101,9 @@ changeCause: ""
 # ── Registry (for imagePullSecret) ──────────────────────
 registry:
   url: "localhost:30500"
+
+# ── Base images ──────────────────────────────────────────
+images:
+  # Optional mirror registry prefix for Docker Hub images (postgres, mysql,
+  # redis, rabbitmq, fluent-bit, …), e.g. "mirror.example.com".
+  baseRegistry: ""

backend/helm/cloudhost-ceph/.helmignore

@@ -0,0 +1,3 @@
+.rook-cluster-values-ref.yaml
+*.md
+scripts/

backend/helm/cloudhost-ceph/.rook-cluster-values-ref.yaml

@@ -0,0 +1,758 @@
+# Default values for a single rook-ceph cluster
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+# -- Namespace of the main rook operator
+operatorNamespace: rook-ceph
+
+# -- The metadata.name of the CephCluster CR
+# @default -- The same as the namespace
+clusterName:
+
+# -- Optional override of the target kubernetes version
+kubeVersion:
+
+# -- Cluster ceph.conf override
+configOverride:
+# configOverride: |
+#   [global]
+#   mon_allow_pool_delete = true
+#   osd_pool_default_size = 3
+#   osd_pool_default_min_size = 2
+
+# Installs a debugging toolbox deployment
+toolbox:
+  # -- Enable Ceph debugging pod deployment. See [toolbox](../Troubleshooting/ceph-toolbox.md)
+  enabled: false
+  # -- Toolbox image, defaults to the image used by the Ceph cluster
+  image: #quay.io/ceph/ceph:v20.2.1
+  # -- Toolbox tolerations
+  tolerations: []
+  # -- Toolbox affinity
+  affinity: {}
+  # -- Toolbox labels
+  labels: {}
+  # -- Toolbox container security context
+  containerSecurityContext:
+    runAsNonRoot: true
+    runAsUser: 2016
+    runAsGroup: 2016
+    capabilities:
+      drop: ["ALL"]
+  # -- Toolbox resources
+  resources:
+    limits:
+      memory: "1Gi"
+    requests:
+      cpu: "100m"
+      memory: "128Mi"
+  # -- Set the priority class for the toolbox if desired
+  priorityClassName:
+
+monitoring:
+  # -- Enable Prometheus integration, will also create necessary RBAC rules to allow Operator to create ServiceMonitors.
+  # Monitoring requires Prometheus to be pre-installed
+  enabled: false
+  # -- Whether to disable the metrics reported by Ceph. If false, the prometheus mgr module and Ceph exporter are enabled
+  metricsDisabled: false
+  # -- Whether to create the Prometheus rules for Ceph alerts
+  createPrometheusRules: false
+  # -- Edit Prometheus rules for Ceph alerts
+  prometheusRuleOverrides: {}
+    # CephHealthWarning:
+    #   disabled: true
+    # NVMeoFHighWriteLatency:
+    #   for: 3m
+    #   labels:
+    #     severity: critical
+  # -- The namespace in which to create the prometheus rules, if different from the rook cluster namespace.
+  # If you have multiple rook-ceph clusters in the same k8s cluster, choose the same namespace (ideally, namespace with prometheus
+  # deployed) to set rulesNamespaceOverride for all the clusters. Otherwise, you will get duplicate alerts with multiple alert definitions.
+  rulesNamespaceOverride:
+  # Monitoring settings for external clusters:
+  # externalMgrEndpoints: <list of endpoints>
+  # externalMgrPrometheusPort: <port>
+  # Scrape interval for prometheus
+  # interval: 10s
+  # allow adding custom labels and annotations to the prometheus rule
+  prometheusRule:
+    # -- Labels applied to PrometheusRule
+    labels: {}
+    # -- Annotations applied to PrometheusRule
+    annotations: {}
+
+# imagePullSecrets option allow to pull docker images from private docker registry. Option will be passed to all service accounts.
+# imagePullSecrets:
+# - name: my-registry-secret
+
+# Labels and annotations to add to the CephCluster CR
+cephClusterMetadata:
+  annotations: {}
+  labels: {}
+
+# Specify these values to override the Ceph image in the cephClusterSpec below.
+# If specifying these values, do not include the cephVersion section in the cephClusterSpec.
+cephImage:
+  # The repository from which to pull the ceph image
+  repository: quay.io/ceph/ceph
+  # In production, use a specific version tag instead of the general v20 flag, which pulls the latest release and could result in different
+  # versions running within the cluster. See tags available at https://hub.docker.com/r/ceph/ceph/tags/.
+  # To be more precise, you can always use a timestamp tag such as quay.io/ceph/ceph:v20.2.1-20260402
+  tag: v20.2.1
+  # Whether to allow unsupported versions of Ceph. Currently Squid and Tentacle are supported.
+  # Future versions would require this to be set to `true`.
+  # Do not set to true in production.
+  allowUnsupported: false
+  # The image pull policy for pulling the ceph image in the ceph daemon pods, defaults to IfNotPresent
+  # imagePullPolicy: IfNotPresent
+
+# All values below are taken from the CephCluster CRD
+# -- Cluster configuration.
+# @default -- See [below](#ceph-cluster-spec)
+cephClusterSpec:
+  # This cluster spec example is for a converged cluster where all the Ceph daemons are running locally,
+  # as in the host-based example (cluster.yaml). For a different configuration such as a
+  # PVC-based cluster (cluster-on-pvc.yaml), external cluster (cluster-external.yaml),
+  # or stretch cluster (cluster-stretched.yaml), replace this entire `cephClusterSpec`
+  # with the specs from those examples.
+  # For more details, check https://rook.io/docs/rook/v1.10/CRDs/Cluster/ceph-cluster-crd/
+
+  # The path on the host where configuration files will be persisted. Must be specified. If there are multiple clusters, the directory must be unique for each cluster.
+  # Important: if you reinstall the cluster, make sure you delete this directory from each host or else the mons will fail to start on the new cluster.
+  # In Minikube, the '/data' directory is configured to persist across reboots. Use "/data/rook" in Minikube environment.
+  dataDirHostPath: /var/lib/rook
+
+  # Whether or not upgrade should continue even if a check fails
+  # This means Ceph's status could be degraded and we don't recommend upgrading but you might decide otherwise
+  # Use at your OWN risk
+  # To understand Rook's upgrade process of Ceph, read https://rook.io/docs/rook/v1.10/Upgrade/ceph-upgrade/
+  skipUpgradeChecks: false
+
+  # Whether or not continue if PGs are not clean during an upgrade
+  continueUpgradeAfterChecksEvenIfNotHealthy: false
+
+  # WaitTimeoutForHealthyOSDInMinutes defines the time (in minutes) the operator would wait before an OSD can be stopped for upgrade or restart.
+  # If the timeout exceeds and OSD is not ok to stop, then the operator would skip upgrade for the current OSD and proceed with the next one
+  # if `continueUpgradeAfterChecksEvenIfNotHealthy` is `false`. If `continueUpgradeAfterChecksEvenIfNotHealthy` is `true`, then operator would
+  # continue with the upgrade of an OSD even if its not ok to stop after the timeout. This timeout won't be applied if `skipUpgradeChecks` is `true`.
+  # The default wait timeout is 10 minutes.
+  waitTimeoutForHealthyOSDInMinutes: 10
+
+  # Whether or not requires PGs are clean before an OSD upgrade. If set to `true` OSD upgrade process won't start until PGs are healthy.
+  # This configuration will be ignored if `skipUpgradeChecks` is `true`.
+  # Default is false.
+  upgradeOSDRequiresHealthyPGs: false
+
+  mon:
+    # Set the number of mons to be started. Generally recommended to be 3.
+    # For highest availability, an odd number of mons should be specified.
+    count: 3
+    # The mons should be on unique nodes. For production, at least 3 nodes are recommended for this reason.
+    # Mons should only be allowed on the same node for test environments where data loss is acceptable.
+    allowMultiplePerNode: false
+
+  mgr:
+    # When higher availability of the mgr is needed, increase the count to 2.
+    # In that case, one mgr will be active and one in standby. When Ceph updates which
+    # mgr is active, Rook will update the mgr services to match the active mgr.
+    count: 2
+    allowMultiplePerNode: false
+    modules:
+      # List of modules to optionally enable or disable.
+      # Note the "dashboard" and "monitoring" modules are already configured by other settings in the cluster CR.
+      # - name: rook
+      #   enabled: true
+
+  # enable the ceph dashboard for viewing cluster status
+  dashboard:
+    enabled: true
+    # serve the dashboard under a subpath (useful when you are accessing the dashboard via a reverse proxy)
+    # urlPrefix: /ceph-dashboard
+    # serve the dashboard at the given port.
+    # port: 8443
+    # Serve the dashboard using SSL (if using ingress to expose the dashboard and `ssl: true` you need to set
+    # the corresponding "backend protocol" annotation(s) for your ingress controller of choice)
+    ssl: true
+
+  # Network configuration, see: https://github.com/rook/rook/blob/master/Documentation/CRDs/Cluster/ceph-cluster-crd.md#network-configuration-settings
+  network:
+    connections:
+      # Whether to encrypt the data in transit across the wire to prevent eavesdropping the data on the network.
+      # The default is false. When encryption is enabled, all communication between clients and Ceph daemons, or between Ceph daemons will be encrypted.
+      # When encryption is not enabled, clients still establish a strong initial authentication and data integrity is still validated with a crc check.
+      # IMPORTANT: Encryption requires the 5.11 kernel for the latest nbd and cephfs drivers. Alternatively for testing only,
+      # you can set the "mounter: rbd-nbd" in the rbd storage class, or "mounter: fuse" in the cephfs storage class.
+      # The nbd and fuse drivers are *not* recommended in production since restarting the csi driver pod will disconnect the volumes.
+      encryption:
+        enabled: false
+      # Whether to compress the data in transit across the wire. The default is false.
+      # The kernel requirements above for encryption also apply to compression.
+      compression:
+        enabled: false
+      # Whether to require communication over msgr2. If true, the msgr v1 port (6789) will be disabled
+      # and clients will be required to connect to the Ceph cluster with the v2 port (3300).
+      # Requires a kernel that supports msgr v2 (kernel 5.11 or CentOS 8.4 or newer).
+      requireMsgr2: false
+  #   # enable host networking
+  #   provider: host
+  #   # EXPERIMENTAL: enable the Multus network provider
+  #   provider: multus
+  #   selectors:
+  #     # The selector keys are required to be `public` and `cluster`.
+  #     # Based on the configuration, the operator will do the following:
+  #     #   1. if only the `public` selector key is specified both public_network and cluster_network Ceph settings will listen on that interface
+  #     #   2. if both `public` and `cluster` selector keys are specified the first one will point to 'public_network' flag and the second one to 'cluster_network'
+  #     #
+  #     # In order to work, each selector value must match a NetworkAttachmentDefinition object in Multus
+  #     #
+  #     # public: public-conf --> NetworkAttachmentDefinition object name in Multus
+  #     # cluster: cluster-conf --> NetworkAttachmentDefinition object name in Multus
+  #   # Provide internet protocol version. IPv6, IPv4 or empty string are valid options. Empty string would mean IPv4
+  #   ipFamily: "IPv6"
+  #   # Ceph daemons to listen on both IPv4 and Ipv6 networks
+  #   dualStack: false
+
+  # enable the crash collector for ceph daemon crash collection
+  crashCollector:
+    disable: false
+    # Uncomment daysToRetain to prune ceph crash entries older than the
+    # specified number of days.
+    # daysToRetain: 30
+
+  # enable log collector, daemons will log on files and rotate
+  logCollector:
+    enabled: true
+    periodicity: daily # one of: hourly, daily, weekly, monthly
+    maxLogSize: 500M # SUFFIX may be 'M' or 'G'. Must be at least 1M.
+
+  # automate [data cleanup process](https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/ceph-teardown.md#delete-the-data-on-hosts) in cluster destruction.
+  cleanupPolicy:
+    # Since cluster cleanup is destructive to data, confirmation is required.
+    # To destroy all Rook data on hosts during uninstall, confirmation must be set to "yes-really-destroy-data".
+    # This value should only be set when the cluster is about to be deleted. After the confirmation is set,
+    # Rook will immediately stop configuring the cluster and only wait for the delete command.
+    # If the empty string is set, Rook will not destroy any data on hosts during uninstall.
+    confirmation: ""
+    # sanitizeDisks represents settings for sanitizing OSD disks on cluster deletion
+    sanitizeDisks:
+      # method indicates if the entire disk should be sanitized or simply ceph's metadata
+      # in both case, re-install is possible
+      # possible choices are 'complete' or 'quick' (default)
+      method: quick
+      # dataSource indicate where to get random bytes from to write on the disk
+      # possible choices are 'zero' (default) or 'random'
+      # using random sources will consume entropy from the system and will take much more time then the zero source
+      dataSource: zero
+      # iteration overwrite N times instead of the default (1)
+      # takes an integer value
+      iteration: 1
+    # allowUninstallWithVolumes defines how the uninstall should be performed
+    # If set to true, cephCluster deletion does not wait for the PVs to be deleted.
+    allowUninstallWithVolumes: false
+
+  # To control where various services will be scheduled by kubernetes, use the placement configuration sections below.
+  # The example under 'all' would have all services scheduled on kubernetes nodes labeled with 'role=storage-node' and
+  # tolerate taints with a key of 'storage-node'.
+  # placement:
+  #   all:
+  #     nodeAffinity:
+  #       requiredDuringSchedulingIgnoredDuringExecution:
+  #         nodeSelectorTerms:
+  #           - matchExpressions:
+  #             - key: role
+  #               operator: In
+  #               values:
+  #               - storage-node
+  #     podAffinity:
+  #     podAntiAffinity:
+  #     topologySpreadConstraints:
+  #     tolerations:
+  #     - key: storage-node
+  #       operator: Exists
+  #   # The above placement information can also be specified for mon, osd, and mgr components
+  #   mon:
+  #   # Monitor deployments may contain an anti-affinity rule for avoiding monitor
+  #   # collocation on the same node. This is a required rule when host network is used
+  #   # or when AllowMultiplePerNode is false. Otherwise this anti-affinity rule is a
+  #   # preferred rule with weight: 50.
+  #   osd:
+  #   mgr:
+  #   cleanup:
+
+  # annotations:
+  #   all:
+  #   mon:
+  #   osd:
+  #   cleanup:
+  #   prepareosd:
+  #   # If no mgr annotations are set, prometheus scrape annotations will be set by default.
+  #   mgr:
+  #   dashboard:
+
+  # labels:
+  #   all:
+  #   mon:
+  #   osd:
+  #   cleanup:
+  #   mgr:
+  #   prepareosd:
+  #   # monitoring is a list of key-value pairs. It is injected into all the monitoring resources created by operator.
+  #   # These labels can be passed as LabelSelector to Prometheus
+  #   monitoring:
+  #   dashboard:
+
+  resources:
+    mgr:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "500m"
+        memory: "512Mi"
+    mon:
+      limits:
+        memory: "2Gi"
+      requests:
+        cpu: "1000m"
+        memory: "1Gi"
+    osd:
+      limits:
+        memory: "4Gi"
+      requests:
+        cpu: "1000m"
+        memory: "4Gi"
+    prepareosd:
+      # limits: It is not recommended to set limits on the OSD prepare job
+      #         since it's a one-time burst for memory that must be allowed to
+      #         complete without an OOM kill.  Note however that if a k8s
+      #         limitRange guardrail is defined external to Rook, the lack of
+      #         a limit here may result in a sync failure, in which case a
+      #         limit should be added.  1200Mi may suffice for up to 15Ti
+      #         OSDs ; for larger devices 2Gi may be required.
+      #         cf. https://github.com/rook/rook/pull/11103
+      requests:
+        cpu: "500m"
+        memory: "50Mi"
+    mgr-sidecar:
+      limits:
+        memory: "100Mi"
+      requests:
+        cpu: "100m"
+        memory: "40Mi"
+    crashcollector:
+      limits:
+        memory: "60Mi"
+      requests:
+        cpu: "100m"
+        memory: "60Mi"
+    logcollector:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "100m"
+        memory: "100Mi"
+    cleanup:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "500m"
+        memory: "100Mi"
+    exporter:
+      limits:
+        memory: "128Mi"
+      requests:
+        cpu: "50m"
+        memory: "50Mi"
+    cmd-reporter:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "500m"
+        memory: "100Mi"
+
+  # The option to automatically remove OSDs that are out and are safe to destroy.
+  removeOSDsIfOutAndSafeToRemove: false
+
+  # priority classes to apply to ceph resources
+  priorityClassNames:
+    mon: system-node-critical
+    osd: system-node-critical
+    mgr: system-cluster-critical
+
+  storage: # cluster level storage configuration and selection
+    useAllNodes: true
+    useAllDevices: true
+    # deviceFilter:
+    # config:
+    #   crushRoot: "custom-root" # specify a non-default root label for the CRUSH map
+    #   metadataDevice: "md0" # specify a non-rotational storage so ceph-volume will use it as block db device of bluestore.
+    #   databaseSizeMB: "1024" # uncomment if the disks are smaller than 100 GB
+    #   osdsPerDevice: "1" # this value can be overridden at the node or device level
+    #   encryptedDevice: "true" # the default value for this option is "false"
+    # # Individual nodes and their config can be specified as well, but 'useAllNodes' above must be set to false. Then, only the named
+    # # nodes below will be used as storage resources. Each node's 'name' field should match their 'kubernetes.io/hostname' label.
+    # nodes:
+    #   - name: "172.17.4.201"
+    #     devices: # specific devices to use for storage can be specified for each node
+    #       - name: "sdb"
+    #       - name: "nvme01" # multiple osds can be created on high performance devices
+    #         config:
+    #           osdsPerDevice: "5"
+    #       - name: "/dev/disk/by-id/ata-ST4000DM004-XXXX" # devices can be specified using full udev paths
+    #     config: # configuration can be specified at the node level which overrides the cluster level config
+    #   - name: "172.17.4.301"
+    #     deviceFilter: "^sd."
+
+  # The section for configuring management of daemon disruptions during upgrade or fencing.
+  disruptionManagement:
+    # If true, the operator will create and manage PodDisruptionBudgets for OSD, Mon, RGW, and MDS daemons. OSD PDBs are managed dynamically
+    # via the strategy outlined in the [design](https://github.com/rook/rook/blob/master/design/ceph/ceph-managed-disruptionbudgets.md). The operator will
+    # block eviction of OSDs by default and unblock them safely when drains are detected.
+    managePodBudgets: true
+    # A duration in minutes that determines how long an entire failureDomain like `region/zone/host` will be held in `noout` (in addition to the
+    # default DOWN/OUT interval) when it is draining. This is only relevant when  `managePodBudgets` is `true`. The default value is `30` minutes.
+    osdMaintenanceTimeout: 30
+
+  # Configure the healthcheck and liveness probes for ceph pods.
+  # Valid values for daemons are 'mon', 'osd', 'status'
+  healthCheck:
+    daemonHealth:
+      mon:
+        disabled: false
+        interval: 45s
+      osd:
+        disabled: false
+        interval: 60s
+      status:
+        disabled: false
+        interval: 60s
+    # Change pod liveness probe, it works for all mon, mgr, and osd pods.
+    livenessProbe:
+      mon:
+        disabled: false
+      mgr:
+        disabled: false
+      osd:
+        disabled: false
+
+ingress:
+  # -- Enable an ingress for the ceph-dashboard
+  dashboard: {}
+    # labels:
+    #   external-dns/private: "true"
+    # annotations:
+    #   external-dns.alpha.kubernetes.io/hostname: dashboard.example.com
+    #   nginx.ingress.kubernetes.io/rewrite-target: /ceph-dashboard/$2
+    # If the dashboard has ssl: true the following will make sure the NGINX Ingress controller can expose the dashboard correctly
+    #   nginx.ingress.kubernetes.io/backend-protocol: "HTTPS"
+    #   nginx.ingress.kubernetes.io/server-snippet: |
+    #     proxy_ssl_verify off;
+    # host:
+    #   name: dashboard.example.com
+    #   path: "/ceph-dashboard(/|$)(.*)"
+    #   pathType: Prefix
+    # tls:
+    # - hosts:
+    #     - dashboard.example.com
+    #   secretName: testsecret-tls
+    ## Note: Only one of ingress class annotation or the `ingressClassName:` can be used at a time
+    ## to set the ingress class
+    # ingressClassName: nginx
+
+route:
+  # -- Enable an HTTPRoute for the ceph-dashboard
+  dashboard: {}
+    # labels:
+    #   external-dns/private: "true"
+    # annotations:
+    #   external-dns.alpha.kubernetes.io/hostname: dashboard.example.com
+    #   nginx.ingress.kubernetes.io/rewrite-target: /ceph-dashboard/$2
+    # host:
+    #   name: dashboard.example.com
+    #   path: "/"
+    #   pathType: PathPrefix
+    # parentRefs:
+    #   - name: internal
+    #     namespace: kube-system
+    #     sectionName: https
+
+# -- A list of CephBlockPool configurations to deploy
+# @default -- See [below](#ceph-block-pools)
+cephBlockPools:
+  - name: ceph-blockpool
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Block-Storage/ceph-block-pool-crd.md#spec for available configuration
+    spec:
+      failureDomain: host
+      replicated:
+        size: 3
+      # Enables collecting RBD per-image IO statistics by enabling dynamic OSD performance counters. Defaults to false.
+      # For reference: https://docs.ceph.com/docs/latest/mgr/prometheus/#rbd-io-statistics
+      # enableRBDStats: true
+    storageClass:
+      enabled: true
+      name: ceph-block
+      annotations: {}
+      labels: {}
+      isDefault: true
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: "Immediate"
+      mountOptions: []
+      # see https://kubernetes.io/docs/concepts/storage/storage-classes/#allowed-topologies
+      allowedTopologies: []
+      #        - matchLabelExpressions:
+      #            - key: rook-ceph-role
+      #              values:
+      #                - storage-node
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Block-Storage-RBD/block-storage.md#provision-storage for available configuration
+      parameters:
+        # (optional) mapOptions is a comma-separated list of map options.
+        # For krbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+        # For nbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+        # mapOptions: lock_on_read,queue_depth=1024
+
+        # (optional) unmapOptions is a comma-separated list of unmap options.
+        # For krbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+        # For nbd options refer
+        # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+        # unmapOptions: force
+
+        # RBD image format. Defaults to "2".
+        imageFormat: "2"
+
+        # RBD image features, equivalent to OR'd bitfield value: 63
+        # Available for imageFormat: "2". Older releases of CSI RBD
+        # support only the `layering` feature. The Linux kernel (KRBD) supports the
+        # full feature complement as of 5.4
+        imageFeatures: layering
+
+        # These secrets contain Ceph admin credentials.
+        csi.storage.k8s.io/provisioner-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/provisioner-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-expand-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/controller-expand-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-publish-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/controller-publish-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/node-stage-secret-name: rook-csi-rbd-node
+        csi.storage.k8s.io/node-stage-secret-namespace: "{{ .Release.Namespace }}"
+        # Specify the filesystem type of the volume. If not specified, csi-provisioner
+        # will set default as `ext4`. Note that `xfs` is not recommended due to potential deadlock
+        # in hyperconverged settings where the volume is mounted on the same node as the osds.
+        csi.storage.k8s.io/fstype: ext4
+
+# -- A list of CephFileSystem configurations to deploy
+# @default -- See [below](#ceph-file-systems)
+cephFileSystems:
+  - name: ceph-filesystem
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Shared-Filesystem/ceph-filesystem-crd.md#filesystem-settings for available configuration
+    spec:
+      metadataPool:
+        replicated:
+          size: 3
+      dataPools:
+        - failureDomain: host
+          replicated:
+            size: 3
+          # Optional and highly recommended, 'data0' by default, see https://github.com/rook/rook/blob/master/Documentation/CRDs/Shared-Filesystem/ceph-filesystem-crd.md#pools
+          name: data0
+      metadataServer:
+        activeCount: 1
+        activeStandby: true
+        resources:
+          limits:
+            memory: "4Gi"
+          requests:
+            cpu: "1000m"
+            memory: "4Gi"
+        priorityClassName: system-cluster-critical
+    storageClass:
+      enabled: true
+      isDefault: false
+      name: ceph-filesystem
+      # (Optional) specify a data pool to use, must be the name of one of the data pools above, 'data0' by default
+      pool: data0
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: "Immediate"
+      annotations: {}
+      labels: {}
+      mountOptions: []
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Shared-Filesystem-CephFS/filesystem-storage.md#provision-storage for available configuration
+      parameters:
+        # The secrets contain Ceph admin credentials.
+        csi.storage.k8s.io/provisioner-secret-name: rook-csi-cephfs-provisioner
+        csi.storage.k8s.io/provisioner-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-expand-secret-name: rook-csi-cephfs-provisioner
+        csi.storage.k8s.io/controller-expand-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/controller-publish-secret-name: rook-csi-cephfs-provisioner
+        csi.storage.k8s.io/controller-publish-secret-namespace: "{{ .Release.Namespace }}"
+        csi.storage.k8s.io/node-stage-secret-name: rook-csi-cephfs-node
+        csi.storage.k8s.io/node-stage-secret-namespace: "{{ .Release.Namespace }}"
+        # Specify the filesystem type of the volume. If not specified, csi-provisioner
+        # will set default as `ext4`. Note that `xfs` is not recommended due to potential deadlock
+        # in hyperconverged settings where the volume is mounted on the same node as the osds.
+        csi.storage.k8s.io/fstype: ext4
+
+# -- Settings for the filesystem snapshot class
+# @default -- See [CephFS Snapshots](../Storage-Configuration/Ceph-CSI/ceph-csi-snapshot.md#cephfs-snapshots)
+cephFileSystemVolumeSnapshotClass:
+  enabled: false
+  name: ceph-filesystem
+  isDefault: true
+  deletionPolicy: Delete
+  annotations: {}
+  labels: {}
+  # see https://rook.io/docs/rook/v1.10/Storage-Configuration/Ceph-CSI/ceph-csi-snapshot/#cephfs-snapshots for available configuration
+  parameters: {}
+
+# -- Settings for the block pool snapshot class
+# @default -- See [RBD Snapshots](../Storage-Configuration/Ceph-CSI/ceph-csi-snapshot.md#rbd-snapshots)
+cephBlockPoolsVolumeSnapshotClass:
+  enabled: false
+  name: ceph-block
+  isDefault: false
+  deletionPolicy: Delete
+  annotations: {}
+  labels: {}
+  # see https://rook.io/docs/rook/v1.10/Storage-Configuration/Ceph-CSI/ceph-csi-snapshot/#rbd-snapshots for available configuration
+  parameters: {}
+
+# -- A list of CephObjectStore configurations to deploy
+# @default -- See [below](#ceph-object-stores)
+cephObjectStores:
+  - name: ceph-objectstore
+    # see https://github.com/rook/rook/blob/master/Documentation/CRDs/Object-Storage/ceph-object-store-crd.md#object-store-settings for available configuration
+    spec:
+      metadataPool:
+        failureDomain: host
+        replicated:
+          size: 3
+      dataPool:
+        failureDomain: host
+        erasureCoded:
+          dataChunks: 2
+          codingChunks: 1
+        parameters:
+          bulk: "true"
+      preservePoolsOnDelete: true
+      gateway:
+        port: 80
+        resources:
+          limits:
+            memory: "2Gi"
+          requests:
+            cpu: "1000m"
+            memory: "1Gi"
+        # securePort: 443
+        # sslCertificateRef:
+        instances: 1
+        priorityClassName: system-cluster-critical
+        # opsLogSidecar:
+        #   resources:
+        #     limits:
+        #       memory: "100Mi"
+        #     requests:
+        #       cpu: "100m"
+        #       memory: "40Mi"
+    storageClass:
+      enabled: true
+      name: ceph-bucket
+      reclaimPolicy: Delete
+      volumeBindingMode: "Immediate"
+      annotations: {}
+      labels: {}
+      # see https://github.com/rook/rook/blob/master/Documentation/Storage-Configuration/Object-Storage-RGW/ceph-object-bucket-claim.md#storageclass for available configuration
+      parameters:
+        # note: objectStoreNamespace and objectStoreName are configured by the chart
+        region: us-east-1
+    ingress:
+      # Enable an ingress for the ceph-objectstore
+      enabled: false
+      # The ingress port by default will be the object store's "securePort" (if set), or the gateway "port".
+      # To override those defaults, set this ingress port to the desired port.
+      # port: 80
+      # annotations: {}
+      # host:
+      #   name: objectstore.example.com
+      #   path: /
+      #   pathType: Prefix
+      # tls:
+      # - hosts:
+      #     - objectstore.example.com
+      #   secretName: ceph-objectstore-tls
+      # ingressClassName: nginx
+    route:
+      # Enable an ingress for the ceph-objectstore
+      enabled: false
+      # The ingress port by default will be the object store's "securePort" (if set), or the gateway "port".
+      # To override those defaults, set this ingress port to the desired port.
+      # port: 80
+      # annotations: {}
+      # host:
+      #   name: objectstore.example.com
+      #   path: /
+      #   pathType: PathPrefix
+      # parentRefs:
+      #   - name: internal
+      #     namespace: kube-system
+      #     sectionName: https
+## cephECBlockPools are disabled by default, please remove the comments and set desired values to enable it
+## For erasure coded a replicated metadata pool is required.
+## https://rook.io/docs/rook/latest/CRDs/Shared-Filesystem/ceph-filesystem-crd/#erasure-coded
+#cephECBlockPools:
+#  - name: ec-pool
+#    spec:
+#      metadataPool:
+#        replicated:
+#          size: 2
+#      dataPool:
+#        failureDomain: osd
+#        erasureCoded:
+#          dataChunks: 2
+#          codingChunks: 1
+#        deviceClass: hdd
+#
+#    parameters:
+#      # clusterID is the namespace where the rook cluster is running
+#      # If you change this namespace, also change the namespace below where the secret namespaces are defined
+#      clusterID: rook-ceph # namespace:cluster
+#      # (optional) mapOptions is a comma-separated list of map options.
+#      # For krbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+#      # For nbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+#      # mapOptions: lock_on_read,queue_depth=1024
+#
+#      # (optional) unmapOptions is a comma-separated list of unmap options.
+#      # For krbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd/#kernel-rbd-krbd-options
+#      # For nbd options refer
+#      # https://docs.ceph.com/docs/latest/man/8/rbd-nbd/#options
+#      # unmapOptions: force
+#
+#      # RBD image format. Defaults to "2".
+#      imageFormat: "2"
+#
+#      # RBD image features, equivalent to OR'd bitfield value: 63
+#      # Available for imageFormat: "2". Older releases of CSI RBD
+#      # support only the `layering` feature. The Linux kernel (KRBD) supports the
+#      # full feature complement as of 5.4
+#      # imageFeatures: layering,fast-diff,object-map,deep-flatten,exclusive-lock
+#      imageFeatures: layering
+#
+#    storageClass:
+#      provisioner: rook-ceph.rbd.csi.ceph.com # csi-provisioner-name
+#      enabled: true
+#      name: rook-ceph-block
+#      isDefault: false
+#      annotations: { }
+#      labels: { }
+#      allowVolumeExpansion: true
+#      reclaimPolicy: Delete
+
+# -- CSI driver name prefix for cephfs, rbd and nfs.
+# @default -- `namespace name where rook-ceph operator is deployed`
+csiDriverNamePrefix:
+

backend/helm/cloudhost-ceph/Chart.yaml

@@ -0,0 +1,13 @@
+apiVersion: v2
+name: cloudhost-ceph
+description: CloudHost extras on top of Rook-Ceph (app source bucket, platform integration secrets)
+type: application
+version: 0.1.0
+appVersion: "1.0.0"
+keywords:
+  - ceph
+  - rook
+  - storage
+  - s3
+maintainers:
+  - name: CloudHost

backend/helm/cloudhost-ceph/README.md

@@ -0,0 +1,140 @@
+# CloudHost Ceph (Rook)
+
+Helm chart and install scripts for **Rook-Ceph** on CloudHost clusters:
+
+| Layer | Purpose |
+|-------|---------|
+| **rook-ceph-block** | Expandable PVCs for apps, databases, registry |
+| **rook-ceph-bucket** | S3-compatible storage for uploaded source zip archives |
+
+The chart does **not** vendor Rook itself — it installs the official [`rook-release`](https://charts.rook.io/release) charts and adds CloudHost-specific **ObjectBucketClaim** + credential sync.
+
+---
+
+## Quick install
+
+```bash
+cd backend/helm/cloudhost-ceph
+./scripts/install.sh single-node   # one-node k3s (current abr cluster)
+# or
+./scripts/install.sh multi-node    # production, 3+ nodes + raw disks
+```
+
+Verify:
+
+```bash
+./scripts/verify.sh
+```
+
+---
+
+## Profiles
+
+### `single-node`
+
+- OSD on **loop device** `/dev/loop6` (15Gi file at `/var/lib/rook/osd-loopback.img`) — no spare raw disk required
+- Requires `ROOK_CEPH_ALLOW_LOOP_DEVICES=true` on the operator
+- Replication **size: 1** (no HA)
+- Suitable for **staging / single k3s node**
+- Images must be pre-mirrored to `registry.abrban.com` (see `RUNBOOK-HARBOR.fa.md`)
+
+### `multi-node`
+
+- OSD on **raw devices** (`useAllDevices: true`)
+- Replication **size: 3** for block + object metadata
+- Erasure-coded object data pool
+- Requires **3+ nodes** and dedicated disks
+
+---
+
+## What gets installed
+
+| Step | Release | Namespace |
+|------|---------|-----------|
+| 1 | `rook-ceph` (operator) | `rook-ceph` |
+| 2 | `rook-ceph-cluster` | `rook-ceph` |
+| 3 | `cloudhost-ceph` (OBC + secrets) | `cloudhost-builds` |
+
+### StorageClasses (from Rook)
+
+| Name | Use |
+|------|-----|
+| `rook-ceph-block` | App PVC, DB PVC, Redis, registry, … |
+| `rook-ceph-bucket` | `ObjectBucketClaim` → S3 bucket + credentials |
+
+### CloudHost extras
+
+| Resource | Description |
+|----------|-------------|
+| `ObjectBucketClaim/app-sources` | Bucket for user zip uploads |
+| `Secret/ceph-app-sources-credentials` | Stable S3 credentials for backend |
+| `ConfigMap/cloudhost-ceph-integration` | Suggested `PLATFORM_*` env values |
+
+---
+
+## Platform integration
+
+After install, configure the **backend**:
+
+```env
+PLATFORM_STORAGE_CLASS=rook-ceph-block
+PLATFORM_CREATE_STORAGE_CLASS=false
+PLATFORM_STORAGE_PROVISIONER=rook-ceph.rbd.csi.ceph.com
+```
+
+Mount or env-from secret `cloudhost-builds/ceph-app-sources-credentials`:
+
+```env
+SOURCE_STORAGE_ENDPOINT=http://rook-ceph-rgw-ceph-objectstore.rook-ceph.svc.cluster.local:80
+SOURCE_STORAGE_REGION=us-east-1
+SOURCE_STORAGE_BUCKET=<from secret>
+SOURCE_STORAGE_ACCESS_KEY=<from secret>
+SOURCE_STORAGE_SECRET_KEY=<from secret>
+```
+
+> **Note:** Existing PVCs on `local-path` / `cloudhost-expandable` are **not** migrated automatically. New apps use `rook-ceph-block` once the backend env is updated. Plan migration per workload (see `RUNBOOK-CEPH.fa.md`).
+
+---
+
+## Uninstall (destructive)
+
+```bash
+./scripts/uninstall.sh
+# then on each node:
+sudo rm -rf /var/lib/rook /var/lib/rook/osd
+```
+
+---
+
+## Troubleshooting
+
+```bash
+# Cluster health
+kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph status
+
+# OSD pods
+kubectl -n rook-ceph get pods -l app=rook-ceph-osd
+
+# RGW (object store)
+kubectl -n rook-ceph get pods -l app=rook-ceph-rgw
+
+# Bucket sync job
+kubectl -n cloudhost-builds logs job -l job-name=cloudhost-ceph-bucket-sync --tail=50
+```
+
+Full operational guide (Persian): [`../../../RUNBOOK-CEPH.fa.md`](../../../RUNBOOK-CEPH.fa.md)
+
+Registry / Harbor (Persian): [`../../../RUNBOOK-HARBOR.fa.md`](../../../RUNBOOK-HARBOR.fa.md)
+
+---
+
+## Files
+
+| File | Role |
+|------|------|
+| `values-rook-cluster-single-node.yaml` | Rook cluster values (1 node) |
+| `values-rook-cluster-multi-node.yaml` | Rook cluster values (production) |
+| `values.yaml` | CloudHost OBC / secret sync |
+| `scripts/install.sh` | Full install |
+| `scripts/verify.sh` | Health check |
+| `scripts/uninstall.sh` | Tear down |

backend/helm/cloudhost-ceph/scripts/install.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+# Install Rook-Ceph operator + cluster + CloudHost bucket extras.
+# Usage: ./scripts/install.sh [single-node|multi-node]
+set -euo pipefail
+
+PROFILE="${1:-single-node}"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+CHART_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+ROOK_NS="rook-ceph"
+EXTRAS_NS="cloudhost-builds"
+CLUSTER_VALUES="${CHART_DIR}/values-rook-cluster-${PROFILE}.yaml"
+
+if [[ ! -f "${CLUSTER_VALUES}" ]]; then
+  echo "Unknown profile: ${PROFILE} (missing ${CLUSTER_VALUES})" >&2
+  exit 1
+fi
+
+echo "==> Profile: ${PROFILE}"
+echo "==> Adding rook-release helm repo"
+helm repo add rook-release https://charts.rook.io/release 2>/dev/null || true
+helm repo update rook-release
+
+echo "==> [1/4] Installing Rook operator in ${ROOK_NS}"
+helm upgrade --install rook-ceph rook-release/rook-ceph \
+  --namespace "${ROOK_NS}" \
+  --create-namespace \
+  --wait \
+  --timeout 10m
+
+echo "==> [2/4] Waiting for Rook operator deployment"
+kubectl -n "${ROOK_NS}" rollout status deploy/rook-ceph-operator --timeout=300s
+
+echo "==> [3/4] Installing Ceph cluster (${CLUSTER_VALUES})"
+helm upgrade --install rook-ceph-cluster rook-release/rook-ceph-cluster \
+  --namespace "${ROOK_NS}" \
+  -f "${CLUSTER_VALUES}" \
+  --wait \
+  --timeout 25m
+
+echo "==> Waiting for CephCluster phase = Ready (up to 20 min)"
+"${SCRIPT_DIR}/wait-ceph-ready.sh" 1200
+
+echo "==> [4/4] Installing CloudHost Ceph extras (ObjectBucketClaim) in ${EXTRAS_NS}"
+kubectl create namespace "${EXTRAS_NS}" 2>/dev/null || true
+helm upgrade --install cloudhost-ceph "${CHART_DIR}" \
+  --namespace "${EXTRAS_NS}" \
+  -f "${CHART_DIR}/values.yaml" \
+  --wait \
+  --timeout 15m
+
+echo ""
+echo "==> Done. Run ./scripts/verify.sh to confirm health and print integration hints."

backend/helm/cloudhost-ceph/scripts/uninstall.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# Remove CloudHost extras + Rook cluster + operator (DATA LOSS).
+set -euo pipefail
+
+read -r -p "This deletes ALL Ceph data. Type 'delete-ceph' to continue: " CONFIRM
+if [[ "${CONFIRM}" != "delete-ceph" ]]; then
+  echo "Aborted."
+  exit 1
+fi
+
+helm uninstall cloudhost-ceph -n cloudhost-builds 2>/dev/null || true
+helm uninstall rook-ceph-cluster -n rook-ceph 2>/dev/null || true
+helm uninstall rook-ceph -n rook-ceph 2>/dev/null || true
+
+echo "Waiting for Rook resources to terminate..."
+sleep 15
+kubectl -n rook-ceph get pods 2>/dev/null || true
+
+cat <<'EOF'
+
+IMPORTANT: On each node, wipe Rook state before reinstalling:
+  sudo rm -rf /var/lib/rook
+  sudo rm -rf /var/lib/rook/osd
+
+For raw-disk OSDs also zap disks (see RUNBOOK-CEPH.fa.md).
+EOF

backend/helm/cloudhost-ceph/scripts/verify.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOK_NS="rook-ceph"
+EXTRAS_NS="cloudhost-builds"
+
+echo "=== StorageClasses ==="
+kubectl get storageclass | grep -E 'NAME|rook-ceph' || true
+
+echo ""
+echo "=== Ceph status ==="
+kubectl -n "${ROOK_NS}" exec deploy/rook-ceph-tools -- ceph status 2>/dev/null || echo "(tools pod not ready yet)"
+
+echo ""
+echo "=== OSD / MON pods ==="
+kubectl -n "${ROOK_NS}" get pods -l app=rook-ceph-osd 2>/dev/null || kubectl -n "${ROOK_NS}" get pods | grep -E 'osd|mon|mgr|rgw' || true
+
+echo ""
+echo "=== Object bucket claim ==="
+kubectl -n "${EXTRAS_NS}" get obc,app-sources 2>/dev/null || kubectl -n "${EXTRAS_NS}" get obc 2>/dev/null || true
+
+echo ""
+echo "=== Platform credentials secret ==="
+if kubectl -n "${EXTRAS_NS}" get secret ceph-app-sources-credentials >/dev/null 2>&1; then
+  echo "Secret ceph-app-sources-credentials exists"
+  kubectl -n "${EXTRAS_NS}" get secret ceph-app-sources-credentials -o jsonpath='{.data.SOURCE_STORAGE_BUCKET}' | base64 -d
+  echo ""
+else
+  echo "Secret ceph-app-sources-credentials not ready — check bucket sync job:"
+  kubectl -n "${EXTRAS_NS}" get jobs,pods | grep bucket-sync || true
+fi
+
+echo ""
+echo "=== Suggested backend env ==="
+kubectl -n "${EXTRAS_NS}" get configmap cloudhost-ceph-integration -o yaml 2>/dev/null | sed -n '/PLATFORM_/p;/SOURCE_STORAGE_ENDPOINT/p' || true

backend/helm/cloudhost-ceph/scripts/wait-ceph-ready.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# Wait until Ceph reports HEALTH_OK or HEALTH_WARN (single-node often stays WARN).
+set -euo pipefail
+
+TIMEOUT="${1:-900}"
+ROOK_NS="rook-ceph"
+START=$(date +%s)
+
+echo "Waiting for rook-ceph-tools deployment..."
+for _ in $(seq 1 60); do
+  if kubectl -n "${ROOK_NS}" get deploy rook-ceph-tools >/dev/null 2>&1; then
+    if kubectl -n "${ROOK_NS}" rollout status deploy/rook-ceph-tools --timeout=120s 2>/dev/null; then
+      break
+    fi
+  fi
+  sleep 5
+done
+
+while true; do
+  NOW=$(date +%s)
+  if (( NOW - START > TIMEOUT )); then
+    echo "Timed out after ${TIMEOUT}s waiting for Ceph health" >&2
+    kubectl -n "${ROOK_NS}" get cephcluster,pod -o wide || true
+    exit 1
+  fi
+
+  if kubectl -n "${ROOK_NS}" get deploy rook-ceph-tools >/dev/null 2>&1; then
+    HEALTH=$(kubectl -n "${ROOK_NS}" exec deploy/rook-ceph-tools -- ceph health 2>/dev/null || echo "unknown")
+    echo "Ceph health: ${HEALTH}"
+    if [[ "${HEALTH}" == "HEALTH_OK" || "${HEALTH}" == HEALTH_WARN* ]]; then
+      PHASE=$(kubectl -n "${ROOK_NS}" get cephcluster rook-ceph -o jsonpath='{.status.phase}' 2>/dev/null || echo "")
+      echo "CephCluster phase: ${PHASE}"
+      if [[ "${PHASE}" == "Ready" ]]; then
+        exit 0
+      fi
+    fi
+  fi
+  sleep 15
+done

backend/helm/cloudhost-ceph/templates/NOTES.txt

@@ -0,0 +1,23 @@
+CloudHost Ceph storage is ready (or still initializing).
+
+Profiles
+  single-node  Directory OSD on /var/lib/rook/osd — for one-node k3s (no HA)
+  multi-node   Raw disk OSDs with replication=3 — production
+
+StorageClasses created by Rook
+  rook-ceph-block   Block volumes (app PVC, DB, registry, …)
+  rook-ceph-bucket  S3-compatible buckets via ObjectBucketClaim
+
+Verify cluster health
+  kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph status
+  kubectl get storageclass | grep rook-ceph
+  kubectl -n cloudhost-builds get obc,secret | grep -E 'app-sources|ceph-app-sources'
+
+Platform backend (after bucket sync Job completes)
+  PLATFORM_STORAGE_CLASS=rook-ceph-block
+  PLATFORM_CREATE_STORAGE_CLASS=false
+  PLATFORM_STORAGE_PROVISIONER=rook-ceph.rbd.csi.ceph.com
+
+  Mount secret cloudhost-builds/ceph-app-sources-credentials for zip upload S3 settings.
+
+Full guide: backend/helm/cloudhost-ceph/README.md and RUNBOOK-CEPH.fa.md

backend/helm/cloudhost-ceph/templates/_helpers.tpl

@@ -0,0 +1,27 @@
+{{/*
+CloudHost Ceph chart helpers
+*/}}
+{{- define "cloudhost-ceph.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{- define "cloudhost-ceph.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 }}
+
+{{- define "cloudhost-ceph.labels" -}}
+helm.sh/chart: {{ include "cloudhost-ceph.name" . }}-{{ .Chart.Version }}
+app.kubernetes.io/name: {{ include "cloudhost-ceph.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+app.kubernetes.io/part-of: cloudhost
+{{- end }}

backend/helm/cloudhost-ceph/templates/integration-configmap.yaml

@@ -0,0 +1,20 @@
+{{- if .Values.integration.createConfigMap }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ .Values.integration.configMapName }}
+  namespace: {{ .Values.namespace }}
+  labels:
+    {{- include "cloudhost-ceph.labels" . | nindent 4 }}
+data:
+  PLATFORM_STORAGE_CLASS: rook-ceph-block
+  PLATFORM_CREATE_STORAGE_CLASS: "false"
+  PLATFORM_STORAGE_PROVISIONER: rook-ceph.rbd.csi.ceph.com
+  SOURCE_STORAGE_ENDPOINT: {{ .Values.platform.endpoint | quote }}
+  SOURCE_STORAGE_REGION: {{ .Values.platform.region | quote }}
+  SOURCE_STORAGE_CREDENTIALS_SECRET: {{ .Values.platform.credentialsSecretName | quote }}
+  README: |
+    Block PVCs: set PLATFORM_STORAGE_CLASS=rook-ceph-block on the backend.
+    New app PVCs use rook-ceph-block; existing local-path PVCs are NOT auto-migrated.
+    Object storage credentials: secret {{ .Values.platform.credentialsSecretName }} in {{ .Values.namespace }}.
+{{- end }}

backend/helm/cloudhost-ceph/templates/objectbucketclaim-app-sources.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.objectStore.claimName }}
+apiVersion: objectbucket.io/v1alpha1
+kind: ObjectBucketClaim
+metadata:
+  name: {{ .Values.objectStore.claimName }}
+  namespace: {{ .Values.namespace }}
+  labels:
+    {{- include "cloudhost-ceph.labels" . | nindent 4 }}
+  annotations:
+    helm.sh/hook: post-install,post-upgrade
+    helm.sh/hook-weight: "5"
+spec:
+  storageClassName: {{ .Values.objectStore.bucketStorageClass | quote }}
+  generateBucketName: {{ .Values.objectStore.generateBucketName | quote }}
+{{- end }}

backend/helm/cloudhost-ceph/templates/platform-bucket-credentials-job.yaml

@@ -0,0 +1,113 @@
+{{- if and .Values.platform.createCredentialsSecret .Values.objectStore.claimName }}
+# Stable secret name for platform workers. Populated by a post-install Job once the OBC secret exists.
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+  namespace: {{ .Values.namespace }}
+  labels:
+    {{- include "cloudhost-ceph.labels" . | nindent 4 }}
+  annotations:
+    helm.sh/hook: post-install,post-upgrade
+    helm.sh/hook-weight: "1"
+    helm.sh/hook-delete-policy: before-hook-creation
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+  namespace: {{ .Values.namespace }}
+  annotations:
+    helm.sh/hook: post-install,post-upgrade
+    helm.sh/hook-weight: "1"
+    helm.sh/hook-delete-policy: before-hook-creation
+rules:
+  - apiGroups: [""]
+    resources: ["secrets"]
+    verbs: ["get", "list", "create", "patch", "update"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+  namespace: {{ .Values.namespace }}
+  annotations:
+    helm.sh/hook: post-install,post-upgrade
+    helm.sh/hook-weight: "1"
+    helm.sh/hook-delete-policy: before-hook-creation
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+subjects:
+  - kind: ServiceAccount
+    name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+    namespace: {{ .Values.namespace }}
+---
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+  namespace: {{ .Values.namespace }}
+  labels:
+    {{- include "cloudhost-ceph.labels" . | nindent 4 }}
+  annotations:
+    helm.sh/hook: post-install,post-upgrade
+    helm.sh/hook-weight: "10"
+    helm.sh/hook-delete-policy: before-hook-creation
+spec:
+  backoffLimit: 30
+  template:
+    spec:
+      serviceAccountName: {{ include "cloudhost-ceph.fullname" . }}-bucket-sync
+      restartPolicy: OnFailure
+      containers:
+        - name: sync
+          image: registry.abrban.com/proxy-dockerhub/bitnami/kubectl:1.32
+          imagePullPolicy: IfNotPresent
+          env:
+            - name: OBC_SECRET
+              value: {{ printf "obc-%s-%s" .Values.namespace .Values.objectStore.claimName | quote }}
+            - name: TARGET_SECRET
+              value: {{ .Values.platform.credentialsSecretName | quote }}
+            - name: NAMESPACE
+              value: {{ .Values.namespace | quote }}
+            - name: ENDPOINT
+              value: {{ .Values.platform.endpoint | quote }}
+            - name: REGION
+              value: {{ .Values.platform.region | quote }}
+          command:
+            - /bin/bash
+            - -ec
+            - |
+              echo "Waiting for OBC secret ${OBC_SECRET} in ${NAMESPACE}..."
+              for i in $(seq 1 120); do
+                if kubectl get secret -n "${NAMESPACE}" "${OBC_SECRET}" >/dev/null 2>&1; then
+                  break
+                fi
+                sleep 10
+              done
+              kubectl get secret -n "${NAMESPACE}" "${OBC_SECRET}" >/dev/null
+
+              BUCKET=$(kubectl get secret -n "${NAMESPACE}" "${OBC_SECRET}" -o jsonpath='{.data.BUCKET_NAME}' | base64 -d)
+              ACCESS=$(kubectl get secret -n "${NAMESPACE}" "${OBC_SECRET}" -o jsonpath='{.data.AWS_ACCESS_KEY_ID}' | base64 -d)
+              SECRET=$(kubectl get secret -n "${NAMESPACE}" "${OBC_SECRET}" -o jsonpath='{.data.AWS_SECRET_ACCESS_KEY}' | base64 -d)
+
+              cat <<EOF | kubectl apply -f -
+              apiVersion: v1
+              kind: Secret
+              metadata:
+                name: ${TARGET_SECRET}
+                namespace: ${NAMESPACE}
+                labels:
+                  app.kubernetes.io/part-of: cloudhost
+              type: Opaque
+              stringData:
+                SOURCE_STORAGE_ENDPOINT: "${ENDPOINT}"
+                SOURCE_STORAGE_REGION: "${REGION}"
+                SOURCE_STORAGE_BUCKET: "${BUCKET}"
+                SOURCE_STORAGE_ACCESS_KEY: "${ACCESS}"
+                SOURCE_STORAGE_SECRET_KEY: "${SECRET}"
+              EOF
+              echo "Synced bucket credentials to secret ${TARGET_SECRET} (bucket=${BUCKET})"
+{{- end }}

backend/helm/cloudhost-ceph/values-rook-cluster-multi-node.yaml

@@ -0,0 +1,83 @@
+# Rook-Ceph cluster values — MULTI NODE (production).
+# Install: scripts/install.sh multi-node
+#
+# Prerequisites:
+# - At least 3 worker nodes (odd mon count)
+# - Raw disks available (useAllDevices) OR dedicated devices per node
+# - Taint-free nodes labeled rook-ceph-role=storage-node (optional)
+
+operatorNamespace: rook-ceph
+
+toolbox:
+  enabled: true
+
+cephClusterSpec:
+  dataDirHostPath: /var/lib/rook
+
+  mon:
+    count: 3
+    allowMultiplePerNode: false
+
+  mgr:
+    count: 2
+    allowMultiplePerNode: false
+
+  dashboard:
+    enabled: true
+    ssl: true
+
+  storage:
+    useAllNodes: false
+    useAllDevices: true
+    # Example: pin OSDs to storage nodes only
+    # nodes:
+    #   - name: "node-1"
+    #   - name: "node-2"
+    #   - name: "node-3"
+
+cephFileSystems: []
+
+cephBlockPools:
+  - name: ceph-blockpool
+    spec:
+      failureDomain: host
+      replicated:
+        size: 3
+    storageClass:
+      enabled: true
+      name: rook-ceph-block
+      isDefault: false
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: WaitForFirstConsumer
+
+cephObjectStores:
+  - name: ceph-objectstore
+    spec:
+      metadataPool:
+        failureDomain: host
+        replicated:
+          size: 3
+      dataPool:
+        failureDomain: host
+        erasureCoded:
+          dataChunks: 2
+          codingChunks: 1
+      preservePoolsOnDelete: true
+      gateway:
+        port: 80
+        instances: 2
+        resources:
+          limits:
+            memory: "2Gi"
+          requests:
+            cpu: "500m"
+            memory: "1Gi"
+    storageClass:
+      enabled: true
+      name: rook-ceph-bucket
+      reclaimPolicy: Delete
+      parameters:
+        region: us-east-1
+    ingress:
+      enabled: false

backend/helm/cloudhost-ceph/values-rook-cluster-single-node.yaml

@@ -0,0 +1,102 @@
+# Rook-Ceph cluster values — SINGLE NODE (k3s dev/staging).
+# Install: scripts/install.sh single-node
+#
+# Uses loop device /dev/loop6 (15Gi) on single-node clusters without a spare raw disk.
+# Replication factor = 1 (no HA). For production multi-node use values-rook-cluster-multi-node.yaml.
+# See RUNBOOK-CEPH.fa.md for loop setup and image mirroring prerequisites.
+
+operatorNamespace: rook-ceph
+
+toolbox:
+  enabled: true
+
+cephClusterSpec:
+  dataDirHostPath: /var/lib/rook
+  skipUpgradeChecks: true
+  continueUpgradeAfterChecksEvenIfNotHealthy: true
+
+  mon:
+    count: 1
+    allowMultiplePerNode: true
+
+  mgr:
+    count: 1
+    allowMultiplePerNode: true
+
+  dashboard:
+    enabled: true
+    ssl: false
+
+  resources:
+    mon:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "200m"
+        memory: "512Mi"
+    mgr:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "200m"
+        memory: "512Mi"
+    osd:
+      limits:
+        memory: "2Gi"
+      requests:
+        cpu: "500m"
+        memory: "1Gi"
+
+  storage:
+    useAllNodes: true
+    useAllDevices: false
+    devices:
+      - name: "/dev/loop6"
+
+# Disable CephFS to save RAM on single-node clusters.
+cephFileSystems: []
+
+cephBlockPools:
+  - name: ceph-blockpool
+    spec:
+      failureDomain: osd
+      replicated:
+        size: 1
+    storageClass:
+      enabled: true
+      name: rook-ceph-block
+      isDefault: false
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: WaitForFirstConsumer
+
+cephObjectStores:
+  - name: ceph-objectstore
+    spec:
+      metadataPool:
+        failureDomain: osd
+        replicated:
+          size: 1
+      dataPool:
+        failureDomain: osd
+        replicated:
+          size: 1
+      preservePoolsOnDelete: true
+      gateway:
+        port: 80
+        instances: 1
+        resources:
+          limits:
+            memory: "1Gi"
+          requests:
+            cpu: "250m"
+            memory: "512Mi"
+    storageClass:
+      enabled: true
+      name: rook-ceph-bucket
+      reclaimPolicy: Delete
+      volumeBindingMode: Immediate
+      parameters:
+        region: us-east-1
+    ingress:
+      enabled: false

backend/helm/cloudhost-ceph/values.yaml

@@ -0,0 +1,25 @@
+# CloudHost Ceph extras (ObjectBucketClaim for zip uploads).
+# Rook operator + CephCluster are installed via scripts/install.sh using official rook-release charts.
+
+namespace: cloudhost-builds
+
+objectStore:
+  # Must match rook-ceph-cluster cephObjectStores[].storageClass.name
+  bucketStorageClass: rook-ceph-bucket
+  # Claim name; Rook generates bucket + credentials secret
+  claimName: app-sources
+  # Prefix for generated bucket name (Rook appends random suffix)
+  generateBucketName: cloudhost-app-sources
+
+platform:
+  # Copy S3 credentials into a stable secret name for backend/workers
+  createCredentialsSecret: true
+  credentialsSecretName: ceph-app-sources-credentials
+  # In-cluster RGW endpoint (adjust if ingress is enabled on object store)
+  endpoint: http://rook-ceph-rgw-ceph-objectstore.rook-ceph.svc.cluster.local:80
+  region: us-east-1
+
+integration:
+  # Emit a ConfigMap with suggested backend env vars (non-secret)
+  createConfigMap: true
+  configMapName: cloudhost-ceph-integration

backend/helm/cloudhost-harbor/scripts/install-harbor-registry.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Replaces registry.abrban.com docker distribution with Harbor.
+# WARNING: This will delete the existing `Ingress/registry` routing. The old
+# `Deployment/registry` and its PVC are left in place for rollback.
+
+VALUES_FILE="${1:-/Users/keyhan/Documents/keyhan-project/cloud-host/backend/helm/cloudhost-harbor/values-registry.abrban.com.yaml}"
+
+echo "==> Ensuring harbor repo"
+helm repo add harbor https://helm.goharbor.io 2>/dev/null || true
+helm repo update harbor
+
+echo "==> [0/4] Preflight"
+kubectl -n cloudhost get secret abrban-wildcard-tls >/dev/null
+kubectl -n cloudhost get secret registry-egress-proxy >/dev/null
+
+echo "==> [1/4] Disabling old registry ingress (host registry.abrban.com)"
+kubectl -n cloudhost delete ingress registry --ignore-not-found
+
+echo "==> [2/4] Scaling old registry deployment down (rollback-friendly)"
+kubectl -n cloudhost scale deploy/registry --replicas=0 || true
+
+echo "==> [3/4] Installing Harbor"
+# IMPORTANT: do NOT set HTTP(S)_PROXY on harbor-core for in-cluster registry
+# traffic. Egress proxy on core causes 502 on blob uploads via harbor-core
+# (Kaniko/skopeo push fails; Harbor UI metadata never appears).
+# Keep proxy empty here; Harbor proxy-cache projects can still use project-level
+# proxy settings when needed. Expand noProxy for safety if proxy is re-enabled.
+TMP_PROXY_VALUES="$(mktemp)"
+cat > "${TMP_PROXY_VALUES}" <<EOF
+proxy:
+  httpProxy: ""
+  httpsProxy: ""
+  noProxy: "harbor-core,harbor-jobservice,harbor-database,harbor-registry,harbor-portal,.svc,.cluster.local,10.43.0.0/16,127.0.0.1,localhost,registry.abrban.com"
+EOF
+
+helm upgrade --install harbor harbor/harbor \
+  -n cloudhost \
+  -f "$VALUES_FILE" \
+  -f "${TMP_PROXY_VALUES}" \
+  --wait \
+  --timeout 20m
+
+rm -f "${TMP_PROXY_VALUES}" || true
+
+echo "==> [4/4] Apply registry ingress path split (proxy-* → harbor-core)"
+kubectl apply -f "$(dirname "$0")/../../../gitops/harbor/registry-ingress.yaml"
+
+echo "==> Done"
+kubectl -n cloudhost get ingress | grep -n registry || true
+

backend/helm/cloudhost-harbor/values-registry.abrban.com.yaml

@@ -0,0 +1,75 @@
+## Harbor values to REPLACE registry.abrban.com
+## Ingress controller on this cluster is Traefik (k3s).
+##
+## Install:
+##   helm upgrade --install harbor harbor/harbor -n cloudhost -f backend/helm/cloudhost-harbor/values-registry.abrban.com.yaml
+##
+externalURL: http://registry.abrban.com
+
+proxy:
+  # Values are injected by install script from `cloudhost/registry-egress-proxy`.
+  httpProxy: ""
+  httpsProxy: ""
+  noProxy: ""
+
+expose:
+  type: ingress
+  tls:
+    enabled: true
+    certSource: secret
+    secret:
+      secretName: abrban-wildcard-tls
+  ingress:
+    className: traefik
+    hosts:
+      core: registry.abrban.com
+    annotations:
+      traefik.ingress.kubernetes.io/router.entrypoints: websecure
+      # Increase timeouts for large pushes (skopeo/registry blobs)
+      traefik.ingress.kubernetes.io/router.tls: "true"
+
+# Disable components we don't need for now to reduce resources
+trivy:
+  enabled: false
+notary:
+  enabled: false
+chartmuseum:
+  enabled: false
+
+# Single-node staging: keep resource usage modest
+core:
+  replicas: 1
+jobservice:
+  replicas: 1
+registry:
+  replicas: 1
+
+persistence:
+  enabled: true
+  persistentVolumeClaim:
+    # Use existing default storage (local-path) until Ceph is ready.
+    # After Ceph, switch to rook-ceph-block for Harbor's PVCs.
+    registry:
+      storageClass: local-path
+      size: 50Gi
+    jobservice:
+      storageClass: local-path
+      size: 5Gi
+    database:
+      storageClass: local-path
+      size: 10Gi
+    redis:
+      storageClass: local-path
+      size: 5Gi
+
+database:
+  type: internal
+
+redis:
+  type: internal
+
+portal:
+  replicas: 1
+
+# We will create proxy-cache projects after install (todo: configure-proxy-cache)
+

backend/helm/cloudhost-logging/templates/elasticsearch-statefulset.yaml

@@ -1,4 +1,3 @@
-{{- $auth := printf "elastic:%s" .Values.elasticPassword | b64enc }}
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
@@ -74,22 +73,20 @@ spec:
             - name: es-data
               mountPath: /usr/share/elasticsearch/data
           readinessProbe:
-            httpGet:
+            exec:
-              path: /_cluster/health?local=true
+              command:
-              port: 9200
+                - sh
-              httpHeaders:
+                - -c
-                - name: Authorization
+                - curl -sf -u "elastic:${ELASTIC_PASSWORD}" http://127.0.0.1:9200/_cluster/health?local=true
-                  value: Basic {{ $auth }}
             initialDelaySeconds: 30
             periodSeconds: 10
             timeoutSeconds: 5
           livenessProbe:
-            httpGet:
+            exec:
-              path: /_cluster/health?local=true
+              command:
-              port: 9200
+                - sh
-              httpHeaders:
+                - -c
-                - name: Authorization
+                - curl -sf -u "elastic:${ELASTIC_PASSWORD}" http://127.0.0.1:9200/_cluster/health?local=true
-                  value: Basic {{ $auth }}
             initialDelaySeconds: 60
             periodSeconds: 30
             timeoutSeconds: 10

backend/helm/cloudhost-platform/migrations/001_service_access_grants.sql

@@ -1,16 +1,20 @@
 -- Temporary external access grants (Redis, RabbitMQ, database)
-CREATE TYPE service_access_target AS ENUM (
+DO $$ BEGIN
+  CREATE TYPE service_access_target AS ENUM (
     'database',
     'redis',
     'rabbitmq_amqp',
     'rabbitmq_management'
-);
+  );
+EXCEPTION WHEN duplicate_object THEN null; END $$;
 
-CREATE TYPE service_access_grant_status AS ENUM (
+DO $$ BEGIN
+  CREATE TYPE service_access_grant_status AS ENUM (
     'active',
     'expired',
     'revoked'
-);
+  );
+EXCEPTION WHEN duplicate_object THEN null; END $$;
 
 CREATE TABLE IF NOT EXISTS service_access_grants (
   id UUID PRIMARY KEY DEFAULT gen_random_uuid(),

backend/helm/cloudhost-platform/migrations/015_application_product_type.sql

@@ -3,7 +3,7 @@ ALTER TABLE applications
   ADD COLUMN IF NOT EXISTS product_type VARCHAR(32) NOT NULL DEFAULT 'application';
 
 CREATE INDEX IF NOT EXISTS idx_applications_user_product_type
-  ON applications (user_id, product_type);
+  ON applications ("userId", product_type);
 
 ALTER TABLE resource_credits
   ADD COLUMN IF NOT EXISTS product_type VARCHAR(32) NOT NULL DEFAULT 'application';

backend/helm/cloudhost-platform/migrations/018_user_phone_and_verification.sql

@@ -0,0 +1,33 @@
+-- Mobile-first auth: phone is the login identifier, email becomes an optional
+-- contact field, plus a table of short-lived one-time SMS codes for verifying
+-- a phone (registration/login completion and number changes).
+
+-- Email becomes optional (login no longer uses it). Postgres treats NULLs as
+-- distinct, so the existing UNIQUE constraint keeps working for users without one.
+ALTER TABLE users ALTER COLUMN email DROP NOT NULL;
+
+ALTER TABLE users ADD COLUMN IF NOT EXISTS phone VARCHAR;
+ALTER TABLE users ADD COLUMN IF NOT EXISTS "phoneVerified" BOOLEAN NOT NULL DEFAULT FALSE;
+
+-- Unique per non-null phone (NULLs allowed for legacy email-only staff accounts).
+CREATE UNIQUE INDEX IF NOT EXISTS users_phone_unique ON users (phone) WHERE phone IS NOT NULL;
+
+-- One-time SMS verification codes (hashed).
+DO $$ BEGIN
+  CREATE TYPE verification_codes_purpose_enum AS ENUM ('login', 'change_phone');
+EXCEPTION WHEN duplicate_object THEN null; END $$;
+
+CREATE TABLE IF NOT EXISTS verification_codes (
+  id          UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  "userId"    UUID NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+  purpose     verification_codes_purpose_enum NOT NULL,
+  destination VARCHAR NOT NULL,
+  "codeHash"  VARCHAR NOT NULL,
+  "expiresAt" TIMESTAMPTZ NOT NULL,
+  attempts    INT NOT NULL DEFAULT 0,
+  "consumedAt" TIMESTAMPTZ,
+  "createdAt" TIMESTAMPTZ NOT NULL DEFAULT now()
+);
+
+CREATE INDEX IF NOT EXISTS verification_codes_user_purpose_idx
+  ON verification_codes ("userId", purpose);

backend/helm/cloudhost-platform/templates/_helpers.tpl

@@ -46,8 +46,12 @@ app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end }}
 
 {{- define "cloudhost-platform.secretName" -}}
+{{- if .Values.secrets.existingSecret }}
+{{- .Values.secrets.existingSecret }}
+{{- else }}
 {{- printf "%s-secrets" (include "cloudhost-platform.fullname" .) }}
 {{- end }}
+{{- end }}
 
 {{- define "cloudhost-platform.tlsSecretName" -}}
 {{- if .Values.ingress.tls.secretName }}
@@ -109,3 +113,18 @@ PLATFORM_DOMAIN / preview domain from the first entry only. The panel host
 {{- define "cloudhost-platform.frontendImage" -}}
 {{- printf "%s:%s" .Values.images.frontend.repository .Values.images.frontend.tag }}
 {{- end }}
+
+{{- define "cloudhost-platform.buildEnv" -}}
+- name: KANIKO_IMAGE
+  value: {{ .Values.build.images.kaniko | quote }}
+- name: BUILD_ALPINE_IMAGE
+  value: {{ .Values.build.images.alpine | quote }}
+- name: BUILD_ALPINE_GIT_IMAGE
+  value: {{ .Values.build.images.alpineGit | quote }}
+- name: BASE_IMAGE_REGISTRY
+  value: {{ .Values.build.baseImageRegistry | quote }}
+{{- if .Values.build.egressProxySecret }}
+- name: BUILD_EGRESS_PROXY_SECRET
+  value: {{ .Values.build.egressProxySecret | quote }}
+{{- end }}
+{{- end }}

backend/helm/cloudhost-platform/templates/backend-deployment.yaml

@@ -9,8 +9,14 @@ metadata:
     {{- include "cloudhost-platform.labels" . | nindent 4 }}
 spec:
   replicas: {{ .Values.backend.replicas }}
+  # Zero-downtime rollouts: DB migrations run in a pre-upgrade hook Job, so the
+  # new pod only starts against a ready schema. The uploads PVC is RWO but
+  # local-path volumes pin pods to the same node, so surge pods can attach.
   strategy:
-    type: Recreate
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
   selector:
     matchLabels:
       app: {{ include "cloudhost-platform.backend.fullname" . }}
@@ -19,6 +25,10 @@ spec:
       labels:
         app: {{ include "cloudhost-platform.backend.fullname" . }}
     spec:
+      {{- with .Values.backend.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       initContainers:
         {{- if .Values.postgres.enabled }}
         - name: wait-postgres
@@ -68,6 +78,11 @@ spec:
               value: {{ include "cloudhost-platform.redis.fullname" . }}
             - name: REDIS_PORT
               value: "6379"
+            - name: REDIS_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: redis-password
             - name: JWT_SECRET
               valueFrom:
                 secretKeyRef:
@@ -78,8 +93,48 @@ spec:
                 secretKeyRef:
                   name: {{ include "cloudhost-platform.secretName" . }}
                   key: jwt-refresh-secret
+            - name: CLUSTER_KUBECONFIG_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: cluster-kubeconfig-key
+            - name: ELASTIC_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: elastic-password
             - name: FRONTEND_URL
               value: {{ include "cloudhost-platform.corsOrigins" . | quote }}
+            {{- if .Values.backend.sms.enabled }}
+            - name: SMS_PROVIDER
+              value: {{ .Values.backend.sms.provider | default "mizbansms" | quote }}
+            - name: MIZBANSMS_FROM
+              value: {{ .Values.backend.sms.from | default "5000467254" | quote }}
+            - name: MIZBANSMS_API
+              value: {{ .Values.backend.sms.api | default "2016" | quote }}
+            - name: MIZBANSMS_USERTYPE
+              value: {{ .Values.backend.sms.userType | default "2" | quote }}
+            - name: MIZBANSMS_USERNAME
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: mizbansms-username
+            - name: MIZBANSMS_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: mizbansms-password
+            {{- end }}
+            {{- if .Values.registry.credentialsSecret }}
+            - name: REGISTRY_USERNAME
+              value: {{ .Values.registry.username | default "harbor_registry_user" | quote }}
+            - name: REGISTRY_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: {{ .Values.registry.credentialsSecret | quote }}
+                  key: {{ .Values.registry.credentialsPasswordKey | default "REGISTRY_CREDENTIAL_PASSWORD" | quote }}
+            {{- end }}
+            {{- include "cloudhost-platform.buildEnv" . | nindent 12 }}
             {{- range $key, $val := .Values.backend.env }}
             - name: {{ $key }}
               value: {{ $val | quote }}
@@ -88,19 +143,24 @@ spec:
             - name: {{ $key }}
               value: {{ $val | quote }}
             {{- end }}
+          {{- if .Values.backend.sourceStorage.enabled }}
+          envFrom:
+            - secretRef:
+                name: {{ .Values.backend.sourceStorage.existingSecret }}
+          {{- end }}
           volumeMounts:
             - name: uploads
               mountPath: /app/uploads
           livenessProbe:
             httpGet:
-              path: /api/docs
+              path: /api/v1/health
               port: 4000
             initialDelaySeconds: 60
             periodSeconds: 15
             timeoutSeconds: 5
           readinessProbe:
             httpGet:
-              path: /api/docs
+              path: /api/v1/ready
               port: 4000
             initialDelaySeconds: 20
             periodSeconds: 10

backend/helm/cloudhost-platform/templates/frontend-deployment.yaml

@@ -17,6 +17,10 @@ spec:
       labels:
         app: {{ include "cloudhost-platform.frontend.fullname" . }}
     spec:
+      {{- with .Values.frontend.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - name: frontend
           image: {{ include "cloudhost-platform.frontendImage" . | quote }}

backend/helm/cloudhost-platform/templates/ingress.yaml

@@ -7,7 +7,7 @@ metadata:
   labels:
     {{- include "cloudhost-platform.labels" . | nindent 4 }}
   annotations:
-    {{- if .Values.ingress.tls.enabled }}
+    {{- if and .Values.ingress.tls.enabled (not .Values.ingress.tls.secretName) }}
     cert-manager.io/cluster-issuer: {{ .Values.ingress.tls.clusterIssuer | quote }}
     {{- end }}
     {{- if and .Values.ingress.singleHost.enabled .Values.ingress.singleHost.apiPath }}

backend/helm/cloudhost-platform/templates/migrations-job.yaml

@@ -7,7 +7,9 @@ metadata:
   labels:
     {{- include "cloudhost-platform.labels" . | nindent 4 }}
   annotations:
-    helm.sh/hook: post-install,post-upgrade
+    # Run BEFORE the backend rolls out so schema-dependent code never starts
+    # against an unmigrated database.
+    helm.sh/hook: pre-install,pre-upgrade
     helm.sh/hook-weight: "5"
     helm.sh/hook-delete-policy: before-hook-creation,hook-succeeded
 spec:
@@ -47,9 +49,20 @@ spec:
             - -c
             - |
               set -e
+              # Track applied migrations so each file runs exactly once — the
+              # loop is idempotent across every helm upgrade.
+              psql -v ON_ERROR_STOP=1 -c "CREATE TABLE IF NOT EXISTS schema_migrations (filename TEXT PRIMARY KEY, applied_at TIMESTAMPTZ NOT NULL DEFAULT NOW());"
               for f in $(ls /migrations/*.sql | sort); do
-                echo ">>> Applying $f"
+                name=$(basename "$f")
-                psql -v ON_ERROR_STOP=1 -f "$f"
+                applied=$(psql -tA -c "SELECT 1 FROM schema_migrations WHERE filename = '$name';")
+                if [ "$applied" = "1" ]; then
+                  echo ">>> Skipping $name (already applied)"
+                  continue
+                fi
+                echo ">>> Applying $name"
+                psql -v ON_ERROR_STOP=1 --single-transaction \
+                  -f "$f" \
+                  -c "INSERT INTO schema_migrations (filename) VALUES ('$name');"
               done
               echo ">>> All migrations applied"
           volumeMounts:

backend/helm/cloudhost-platform/templates/monitoring.yaml

@@ -0,0 +1,35 @@
+{{- if .Values.monitoring.enabled }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "cloudhost-platform.fullname" . }}-backend-metrics
+  namespace: {{ include "cloudhost-platform.namespace" . }}
+  labels:
+    {{- include "cloudhost-platform.labels" . | nindent 4 }}
+    app.kubernetes.io/component: backend
+spec:
+  type: ClusterIP
+  ports:
+    - name: http
+      port: 4000
+      targetPort: 4000
+  selector:
+    app: {{ include "cloudhost-platform.backend.fullname" . }}
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "cloudhost-platform.fullname" . }}-backend
+  namespace: {{ include "cloudhost-platform.namespace" . }}
+  labels:
+    {{- include "cloudhost-platform.labels" . | nindent 4 }}
+    release: prometheus
+spec:
+  selector:
+    matchLabels:
+      app: {{ include "cloudhost-platform.backend.fullname" . }}
+  endpoints:
+    - port: http
+      path: /api/v1/health
+      interval: 30s
+{{- end }}

backend/helm/cloudhost-platform/templates/postgres-backup.yaml

@@ -0,0 +1,64 @@
+{{- if .Values.backups.postgres.enabled }}
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: {{ include "cloudhost-platform.fullname" . }}-postgres-backup
+  namespace: {{ include "cloudhost-platform.namespace" . }}
+  labels:
+    {{- include "cloudhost-platform.labels" . | nindent 4 }}
+spec:
+  schedule: {{ .Values.backups.postgres.schedule | quote }}
+  successfulJobsHistoryLimit: 3
+  failedJobsHistoryLimit: 1
+  jobTemplate:
+    spec:
+      template:
+        spec:
+          restartPolicy: OnFailure
+          containers:
+            - name: backup
+              image: {{ .Values.images.postgres | quote }}
+              env:
+                - name: PGHOST
+                  value: {{ include "cloudhost-platform.postgres.fullname" . }}
+                - name: PGPORT
+                  value: "5432"
+                - name: PGDATABASE
+                  value: {{ .Values.postgres.database | quote }}
+                - name: PGUSER
+                  value: {{ .Values.postgres.username | quote }}
+                - name: PGPASSWORD
+                  valueFrom:
+                    secretKeyRef:
+                      name: {{ include "cloudhost-platform.secretName" . }}
+                      key: postgres-password
+              command:
+                - sh
+                - -c
+                - |
+                  set -e
+                  STAMP=$(date +%Y%m%d-%H%M%S)
+                  FILE="/backup/cloudhost-${STAMP}.sql.gz"
+                  pg_dump | gzip > "$FILE"
+                  echo "Backup written to $FILE"
+                  # Retention: keep the last {{ .Values.backups.postgres.retentionDays | default 7 }} days
+                  find /backup -name 'cloudhost-*.sql.gz' -mtime +{{ .Values.backups.postgres.retentionDays | default 7 }} -delete
+              volumeMounts:
+                - name: backup
+                  mountPath: /backup
+          volumes:
+            - name: backup
+              persistentVolumeClaim:
+                claimName: {{ include "cloudhost-platform.fullname" . }}-postgres-backup
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "cloudhost-platform.fullname" . }}-postgres-backup
+  namespace: {{ include "cloudhost-platform.namespace" . }}
+spec:
+  accessModes: [ReadWriteOnce]
+  resources:
+    requests:
+      storage: {{ .Values.backups.postgres.storageSize }}
+{{- end }}

backend/helm/cloudhost-platform/templates/postgres-deployment.yaml

@@ -19,6 +19,10 @@ spec:
       labels:
         app: {{ include "cloudhost-platform.postgres.fullname" . }}
     spec:
+      {{- with .Values.postgres.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - name: postgres
           image: {{ .Values.images.postgres | quote }}

backend/helm/cloudhost-platform/templates/redis-deployment.yaml

@@ -19,9 +19,26 @@ spec:
       labels:
         app: {{ include "cloudhost-platform.redis.fullname" . }}
     spec:
+      {{- with .Values.redis.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - name: redis
           image: {{ .Values.images.redis | quote }}
+          args: ["--requirepass", "$(REDIS_PASSWORD)"]
+          env:
+            - name: REDIS_PASSWORD
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: redis-password
+            # redis-cli reads REDISCLI_AUTH so authenticated probes need no -a flag
+            - name: REDISCLI_AUTH
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "cloudhost-platform.secretName" . }}
+                  key: redis-password
           ports:
             - containerPort: 6379
           volumeMounts:

backend/helm/cloudhost-platform/templates/secret.yaml

@@ -1,3 +1,10 @@
+{{- if not .Values.secrets.existingSecret }}
+{{/*
+NOTE: lookup only works with `helm install/upgrade` (CLI). Argo CD renders with
+`helm template` where lookup is always empty, so values would be regenerated on
+every sync. For GitOps deployments set secrets.existingSecret and manage the
+Secret out-of-band (e.g. SealedSecret in the gitops repo).
+*/}}
 {{- $existing := lookup "v1" "Secret" (include "cloudhost-platform.namespace" .) (include "cloudhost-platform.secretName" .) }}
 {{- $pgPass := .Values.postgres.password }}
 {{- if not $pgPass }}
@@ -11,6 +18,14 @@
 {{- if not $jwtRefresh }}
 {{- if $existing }}{{- $jwtRefresh = index $existing.data "jwt-refresh-secret" | b64dec }}{{- else }}{{- $jwtRefresh = randAlphaNum 32 }}{{- end }}
 {{- end }}
+{{- $kubeconfigKey := .Values.secrets.clusterKubeconfigKey }}
+{{- if not $kubeconfigKey }}
+{{- if and $existing (hasKey $existing.data "cluster-kubeconfig-key") }}{{- $kubeconfigKey = index $existing.data "cluster-kubeconfig-key" | b64dec }}{{- else }}{{- $kubeconfigKey = randAlphaNum 32 }}{{- end }}
+{{- end }}
+{{- $redisPass := .Values.redis.password }}
+{{- if not $redisPass }}
+{{- if and $existing (hasKey $existing.data "redis-password") }}{{- $redisPass = index $existing.data "redis-password" | b64dec }}{{- else }}{{- $redisPass = randAlphaNum 24 }}{{- end }}
+{{- end }}
 apiVersion: v1
 kind: Secret
 metadata:
@@ -23,3 +38,6 @@ stringData:
   postgres-password: {{ $pgPass | quote }}
   jwt-secret: {{ $jwt | quote }}
   jwt-refresh-secret: {{ $jwtRefresh | quote }}
+  cluster-kubeconfig-key: {{ $kubeconfigKey | quote }}
+  redis-password: {{ $redisPass | quote }}
+{{- end }}

backend/helm/cloudhost-platform/values-production.example.yaml

@@ -8,6 +8,11 @@ global:
   storageClass: local-path   # k3s example
 
 images:
+  # Mirror Docker Hub images through your private registry so cluster nodes
+  # never pull from docker.io directly (matches the kaniko/Harbor setup).
+  postgres: registry.example.com/mirror/postgres:16-alpine
+  redis: registry.example.com/mirror/redis:7-alpine
+  busybox: registry.example.com/mirror/busybox:1.36
   backend:
     repository: registry.example.com/cloudhost-backend
     tag: "1.0.0"
@@ -17,8 +22,25 @@ images:
     tag: "1.0.0"
     pullPolicy: Always
 
+# Build job images — override for clusters without Harbor proxy-cache.
+build:
+  images:
+    kaniko: registry.example.com/proxy-gcr/kaniko-project/executor:v1.23.2
+    alpine: registry.example.com/proxy-dockerhub/library/alpine:3.19
+    alpineGit: registry.example.com/proxy-dockerhub/alpine/git:2.43.0
+  baseImageRegistry: registry.example.com/proxy-dockerhub/library
+
 postgres:
   password: "CHANGE_ME_STRONG_POSTGRES_PASSWORD"
+  # Pull secret for the mirrored postgres image
+  imagePullSecrets:
+    - name: registry-pull-secret
+
+redis:
+  # Auto-generated and persisted in the platform Secret when left empty.
+  password: ""
+  imagePullSecrets:
+    - name: registry-pull-secret
 
 secrets:
   jwtSecret: "CHANGE_ME_LONG_JWT_SECRET"
@@ -36,10 +58,26 @@ ingress:
     clusterIssuer: letsencrypt-prod
 
 backend:
+  # Enable after copying ceph-app-sources-credentials secret into the cloudhost namespace
+  sourceStorage:
+    enabled: false
+    existingSecret: ceph-app-sources-credentials
   env:
     PLATFORM_DOMAIN: apps.example.com
     REGISTRY_URL: registry.cloudhost-builds.svc.cluster.local:5000
     REGISTRY_PULL_URL: registry.cloudhost-builds.svc.cluster.local:5000
+    # Elastic log-stack credentials (must match the logging namespace Secret)
+    ELASTIC_PASSWORD: "CHANGE_ME_ELASTIC_PASSWORD"
+    FLUENTBIT_PASSWORD: "CHANGE_ME_FLUENTBIT_PASSWORD"
+    KIBANA_SYSTEM_PASSWORD: "CHANGE_ME_KIBANA_PASSWORD"
+    # Swagger stays off in production; set SWAGGER_ENABLED: "true" to expose it
 
 migrations:
   enabled: true
+
+backups:
+  postgres:
+    enabled: true
+    schedule: "0 3 * * *"
+    storageSize: 10Gi
+    retentionDays: 7

backend/helm/cloudhost-platform/values.yaml

@@ -12,6 +12,9 @@ createNamespace: true
 global:
   storageClass: ""
 
+# For clusters without direct docker.io access, point these at your mirror,
+# e.g. registry.abrban.com/abrban/postgres:16-alpine, and set
+# postgres.imagePullSecrets / redis.imagePullSecrets accordingly.
 images:
   postgres: postgres:16-alpine
   redis: redis:7-alpine
@@ -25,6 +28,26 @@ images:
     tag: "1.0.0"
     pullPolicy: IfNotPresent
 
+# Kaniko push credentials — harbor_registry_user for harbor-registry:5000 (Harbor production).
+registry:
+  credentialsSecret: ""
+  credentialsPasswordKey: REGISTRY_CREDENTIAL_PASSWORD
+  username: harbor_registry_user
+
+# Kaniko job images — defaults pull from Harbor proxy-cache.
+# Override any line for a different registry/tag.
+build:
+  images:
+    # Seeded into abrban/ via gitops/jobs/seed-ci-images.yaml — avoid flaky proxy-gcr pulls.
+    kaniko: registry.abrban.com/abrban/kaniko-executor:v1.27.6-debug
+    alpine: registry.abrban.com/abrban/alpine:3.19
+    alpineGit: registry.abrban.com/abrban/alpine-git:2.43.0
+  # Seeded base images (gitops/jobs/seed-ci-images.yaml) — proxy-dockerhub cache can be corrupt on first pull.
+  baseImageRegistry: registry.abrban.com/abrban
+  # Secret with HTTP_PROXY/HTTPS_PROXY for Kaniko build jobs (npm, apk, git clone).
+  # Set to registry-egress-proxy in production; leave empty when nodes have direct egress.
+  egressProxySecret: ""
+
 postgres:
   enabled: true
   database: cloudhost
@@ -32,20 +55,57 @@ postgres:
   # Leave empty to auto-generate on first install (stored in Secret)
   password: ""
   storage: 10Gi
-  resources: {}
+  # Needed when images.postgres points at a private mirror
+  imagePullSecrets: []
+  resources:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: "2"
+      memory: 2Gi
 
 redis:
   enabled: true
   storage: 1Gi
-  resources: {}
+  # Leave empty to auto-generate on first install (stored in Secret as redis-password).
+  # With secrets.existingSecret, that Secret must also contain a redis-password key.
+  password: ""
+  # Needed when images.redis points at a private mirror
+  imagePullSecrets: []
+  resources:
+    requests:
+      cpu: 50m
+      memory: 64Mi
+    limits:
+      cpu: 500m
+      memory: 512Mi
 
 backend:
   enabled: true
   replicas: 1
+  imagePullSecrets:
+    - name: registry-pull-secret
   uploads:
     size: 20Gi
-  resources: {}
+  sourceStorage:
+    enabled: false
+    existingSecret: ceph-app-sources-credentials
+  resources:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: "2"
+      memory: 2Gi
   extraEnv: {}
+  # OTP SMS — credentials live in the platform Secret (mizbansms-username/password).
+  sms:
+    enabled: false
+    provider: mizbansms
+    from: "5000467254"
+    api: "2016"
+    userType: "2"
   env:
     NODE_ENV: production
     PORT: "4000"
@@ -66,12 +126,27 @@ backend:
 frontend:
   enabled: true
   replicas: 1
-  resources: {}
+  imagePullSecrets:
+    - name: registry-pull-secret
+  resources:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: "1"
+      memory: 1Gi
 
 # JWT secrets — set in production (values-production.example.yaml)
 secrets:
+  # Use a pre-created Secret instead of chart-managed one. Required for GitOps
+  # (Argo CD renders with `helm template`, so lookup/randAlphaNum regenerate on
+  # every sync). Secret must contain keys: postgres-password, jwt-secret,
+  # jwt-refresh-secret, cluster-kubeconfig-key, redis-password, elastic-password.
+  existingSecret: ""
   jwtSecret: ""
   jwtRefreshSecret: ""
+  # AES key for encrypting stored kubeconfigs (64 hex chars or any passphrase)
+  clusterKubeconfigKey: ""
 
 ingress:
   enabled: true
@@ -97,3 +172,13 @@ ingress:
 migrations:
   enabled: true
   image: postgres:16-alpine
+
+monitoring:
+  enabled: false
+
+backups:
+  postgres:
+    enabled: true
+    schedule: "0 3 * * *"
+    storageSize: 10Gi
+    retentionDays: 7

backend/k8s/builds/cloudhost-builds-bootstrap.yaml

@@ -0,0 +1,77 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: cloudhost-builds
+  labels:
+    app.kubernetes.io/part-of: cloudhost
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kaniko-builder
+  namespace: cloudhost-builds
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: kaniko-builder
+  namespace: cloudhost-builds
+rules:
+  - apiGroups: ['']
+    resources: ['pods', 'pods/log', 'secrets', 'configmaps', 'persistentvolumeclaims']
+    verbs: ['create', 'get', 'list', 'watch', 'delete', 'patch', 'update']
+  - apiGroups: ['batch']
+    resources: ['jobs']
+    verbs: ['create', 'get', 'list', 'watch', 'delete']
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: kaniko-builder
+  namespace: cloudhost-builds
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: kaniko-builder
+subjects:
+  - kind: ServiceAccount
+    name: kaniko-builder
+    namespace: cloudhost-builds
+---
+# In-cluster registry for Kaniko push + app image pull (HTTP — add TLS in production).
+apiVersion: v1
+kind: Service
+metadata:
+  name: registry
+  namespace: cloudhost-builds
+spec:
+  type: ClusterIP
+  ports:
+    - port: 5000
+      targetPort: 5000
+  selector:
+    app: registry
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: registry
+  namespace: cloudhost-builds
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: registry
+  template:
+    metadata:
+      labels:
+        app: registry
+    spec:
+      containers:
+        - name: registry
+          image: registry:2
+          ports:
+            - containerPort: 5000
+          env:
+            - name: REGISTRY_HTTP_ADDR
+              value: ':5000'

backend/k8s/logging/elasticsearch-stack.yaml

@@ -9,18 +9,16 @@ metadata:
   labels:
     app.kubernetes.io/managed-by: cloudhost
 ---
-# Elasticsearch credentials secret
+# Elasticsearch credentials — managed OUT-OF-BAND, never committed to git.
-apiVersion: v1
+# Create the Secret before applying this manifest (or use a SealedSecret in
-kind: Secret
+# the GitOps repo):
-metadata:
+#
-  name: elasticsearch-credentials
+#   kubectl -n logging create secret generic elasticsearch-credentials \
-  namespace: logging
+#     --from-literal=ELASTIC_PASSWORD="$(openssl rand -base64 24)" \
-type: Opaque
+#     --from-literal=FLUENTBIT_PASSWORD="$(openssl rand -base64 24)"
-stringData:
+#
-  # Admin credentials - change in production!
+# The backend reads the same values from ELASTIC_PASSWORD / FLUENTBIT_PASSWORD
-  ELASTIC_PASSWORD: "CloudHost2024!Secure"
+# env vars (see cloudhost-platform values: backend.extraEnv or an extra Secret).
-  # For Fluent Bit to send logs
-  FLUENTBIT_PASSWORD: "FluentBit2024!Writer"
 ---
 # ConfigMap for Elasticsearch configuration
 apiVersion: v1
@@ -183,24 +181,20 @@ spec:
             - name: data
               mountPath: /usr/share/elasticsearch/data
           readinessProbe:
-            httpGet:
+            exec:
-              path: /_cluster/health?local=true
+              command:
-              port: 9200
+                - sh
-              scheme: HTTP
+                - -c
-              httpHeaders:
+                - curl -sf -u "elastic:${ELASTIC_PASSWORD}" http://127.0.0.1:9200/_cluster/health?local=true
-                - name: Authorization
-                  value: "Basic ZWxhc3RpYzpDbG91ZEhvc3QyMDI0IVNlY3VyZQ=="
             initialDelaySeconds: 30
             periodSeconds: 10
             timeoutSeconds: 5
           livenessProbe:
-            httpGet:
+            exec:
-              path: /_cluster/health?local=true
+              command:
-              port: 9200
+                - sh
-              scheme: HTTP
+                - -c
-              httpHeaders:
+                - curl -sf -u "elastic:${ELASTIC_PASSWORD}" http://127.0.0.1:9200/_cluster/health?local=true
-                - name: Authorization
-                  value: "Basic ZWxhc3RpYzpDbG91ZEhvc3QyMDI0IVNlY3VyZQ=="
             initialDelaySeconds: 60
             periodSeconds: 30
             timeoutSeconds: 10

backend/k8s/mail/maddy.yaml

@@ -0,0 +1,248 @@
+# Maddy mail server — lightweight full mail server (SMTP + IMAP + DKIM)
+# Namespace: mail   |   Host: mail.abrban.com   |   Primary domain: abrban.com
+#
+# Exposed on node IP 78.157.39.52 via k3s servicelb (klipper).
+# TLS uses the *.abrban.com wildcard cert (secret abrban-wildcard-tls, copied into ns mail).
+#
+# NOTE (Iran/IP reputation): inbound mail (receiving) works; outbound delivery to
+# Gmail/Outlook may be blocked or land in spam, and outbound port 25 may be filtered
+# by the ISP. Use a smarthost relay if real external delivery is required.
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: maddy-config
+  namespace: mail
+data:
+  maddy.conf: |
+    ## Maddy Mail Server - configuration (mail.abrban.com)
+
+    $(hostname) = mail.abrban.com
+    $(primary_domain) = abrban.com
+    $(local_domains) = $(primary_domain)
+
+    tls file /etc/maddy/tls/tls.crt /etc/maddy/tls/tls.key
+
+    # ---- Local storage & authentication ----
+    storage.imapsql local_mailboxes {
+        driver sqlite3
+        dsn imapsql.db
+    }
+
+    auth.pass_table local_authdb {
+        table sql_table {
+            driver sqlite3
+            dsn credentials.db
+            table_name passwords
+        }
+    }
+
+    # ---- Routing ----
+    hostname $(hostname)
+
+    table.chain local_rewrites {
+        optional_step regexp "(.+)\+(.+)@(.+)" "$1@$3"
+        optional_step static {
+            entry postmaster postmaster@$(primary_domain)
+        }
+        optional_step file /data/aliases
+    }
+
+    msgpipeline local_routing {
+        destination postmaster $(local_domains) {
+            modify {
+                replace_rcpt &local_rewrites
+            }
+            deliver_to &local_mailboxes
+        }
+        default_destination {
+            reject 550 5.1.1 "User doesn't exist"
+        }
+    }
+
+    # ---- Inbound SMTP (port 25) ----
+    smtp tcp://0.0.0.0:25 {
+        limits {
+            all rate 20 1s
+            all concurrency 10
+        }
+        dmarc yes
+        check {
+            require_mx_record
+            dkim
+            spf
+        }
+        source $(local_domains) {
+            reject 501 5.1.8 "Use Submission for outgoing SMTP"
+        }
+        default_source {
+            destination postmaster $(local_domains) {
+                deliver_to &local_routing
+            }
+            default_destination {
+                reject 550 5.1.1 "User doesn't exist"
+            }
+        }
+    }
+
+    # ---- Submission (ports 465 implicit-TLS, 587 STARTTLS) ----
+    submission tls://0.0.0.0:465 tcp://0.0.0.0:587 {
+        limits {
+            all rate 50 1s
+        }
+        auth &local_authdb
+        source $(local_domains) {
+            check {
+                authorize_sender {
+                    prepare_email &local_rewrites
+                    user_to_email identity
+                }
+            }
+            destination postmaster $(local_domains) {
+                deliver_to &local_routing
+            }
+            default_destination {
+                modify {
+                    dkim $(primary_domain) $(hostname) default
+                }
+                deliver_to &remote_queue
+            }
+        }
+        default_source {
+            reject 501 5.1.8 "Non-local sender domain"
+        }
+    }
+
+    # ---- Outbound delivery queue ----
+    target.remote outbound_delivery {
+        limits {
+            destination rate 20 1s
+            destination concurrency 10
+        }
+        mx_auth {
+            dane
+            mtasts {
+                cache fs
+                fs_dir mtasts_cache/
+            }
+            local_policy {
+                min_tls_level encrypted
+                min_mx_level none
+            }
+        }
+    }
+
+    target.queue remote_queue {
+        target &outbound_delivery
+        autogenerated_msg_domain $(primary_domain)
+        bounce {
+            destination postmaster $(local_domains) {
+                deliver_to &local_routing
+            }
+            default_destination {
+                reject 550 5.0.0 "Refusing to send DSNs to non-local addresses"
+            }
+        }
+    }
+
+    # ---- IMAP (993 implicit-TLS, 143 STARTTLS) ----
+    imap tls://0.0.0.0:993 tcp://0.0.0.0:143 {
+        auth &local_authdb
+        storage &local_mailboxes
+    }
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: maddy-data
+  namespace: mail
+spec:
+  accessModes: ["ReadWriteOnce"]
+  storageClassName: local-path
+  resources:
+    requests:
+      storage: 5Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: maddy
+  namespace: mail
+  labels:
+    app: maddy
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: maddy
+  template:
+    metadata:
+      labels:
+        app: maddy
+    spec:
+      containers:
+        - name: maddy
+          image: foxcpp/maddy:0.7
+          imagePullPolicy: IfNotPresent
+          env:
+            - name: MADDY_HOSTNAME
+              value: mail.abrban.com
+            - name: MADDY_DOMAIN
+              value: abrban.com
+          ports:
+            - { name: smtp,       containerPort: 25 }
+            - { name: submission, containerPort: 587 }
+            - { name: smtps,      containerPort: 465 }
+            - { name: imap,       containerPort: 143 }
+            - { name: imaps,      containerPort: 993 }
+          volumeMounts:
+            - name: data
+              mountPath: /data
+            - name: config
+              mountPath: /data/maddy.conf
+              subPath: maddy.conf
+            - name: tls
+              mountPath: /etc/maddy/tls
+              readOnly: true
+          resources:
+            requests:
+              cpu: 50m
+              memory: 64Mi
+            limits:
+              cpu: "1"
+              memory: 256Mi
+          livenessProbe:
+            tcpSocket: { port: 25 }
+            initialDelaySeconds: 15
+            periodSeconds: 30
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: maddy-data
+        - name: config
+          configMap:
+            name: maddy-config
+        - name: tls
+          secret:
+            secretName: abrban-wildcard-tls
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: maddy
+  namespace: mail
+  labels:
+    app: maddy
+spec:
+  type: LoadBalancer
+  externalTrafficPolicy: Local   # preserve client source IP (needed for SPF/spam checks)
+  selector:
+    app: maddy
+  ports:
+    - { name: smtp,       port: 25,  targetPort: 25 }
+    - { name: submission, port: 587, targetPort: 587 }
+    - { name: smtps,      port: 465, targetPort: 465 }
+    - { name: imap,       port: 143, targetPort: 143 }
+    - { name: imaps,      port: 993, targetPort: 993 }

backend/k8s/nixpacks-spike/nixpacks-spike.yaml

@@ -1,212 +0,0 @@
-# ─────────────────────────────────────────────────────────────────────────────
-# فاز ۰ — Spike ریسک Nixpacks روی شبکه‌ی ایران (abrban / cloudhost-builds)
-#
-# هدف: قبل از مهاجرت سیستم بیلد به Nixpacks (فاز ۲)، مطمئن شویم زنجیره‌ی
-#   nixpacks (تولید Dockerfile)  →  kaniko (build واقعی + نصب وابستگی‌ها)
-# پشت شبکه‌ی ایران کار می‌کند و کشف کنیم چه mirror/proxy لازم است.
-#
-# چرا این ساختار: `nixpacks build --out` فقط Dockerfile می‌سازد و دانلودی ندارد؛
-# دانلود سنگین (nixpkgs + npm/go modules) داخل مرحله‌ی Docker build اتفاق می‌افتد.
-# پس برای تست واقعی شبکه باید kaniko همان Dockerfile تولیدی را build کند.
-# با --no-push نیازی به رجیستری/کردنشال نیست — فقط build تست می‌شود.
-#
-# اجرا:
-#   kubectl apply -f nixpacks-spike.yaml
-#   kubectl -n cloudhost-builds logs -f job/nixpacks-spike-node
-#   kubectl -n cloudhost-builds logs -f job/nixpacks-spike-go
-#   # بعد از اتمام:
-#   kubectl -n cloudhost-builds delete -f nixpacks-spike.yaml
-#
-# اگر kaniko سرِ `RUN ... npm install` یا fetch nixpkgs گیر کرد → شبکه‌ی ایران
-# مانع است؛ env های mirror را (بخش «نکات mirror» پایین فایل) فعال/تنظیم کنید و
-# دوباره اجرا کنید. نتیجه را برای تصمیم فاز ۲ مستند کنید.
-# ─────────────────────────────────────────────────────────────────────────────
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: nixpacks-spike-node-src
-  namespace: cloudhost-builds
-data:
-  package.json: |
-    {
-      "name": "nixpacks-spike",
-      "version": "1.0.0",
-      "private": true,
-      "scripts": { "start": "node index.js" },
-      "dependencies": { "express": "^4.18.2" }
-    }
-  index.js: |
-    const express = require('express');
-    const app = express();
-    app.get('/', (_req, res) => res.send('nixpacks spike ok'));
-    app.listen(process.env.PORT || 3000, () => console.log('up'));
----
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: nixpacks-spike-node
-  namespace: cloudhost-builds
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 1800
-  template:
-    spec:
-      restartPolicy: Never
-      volumes:
-        - name: workspace
-          emptyDir: {}
-        - name: src
-          configMap:
-            name: nixpacks-spike-node-src
-      initContainers:
-        # 1) staging سورس نمونه از ConfigMap به workspace
-        - name: stage-source
-          image: alpine:3.19
-          imagePullPolicy: IfNotPresent
-          command:
-            - sh
-            - -c
-            - |
-              set -e
-              mkdir -p /workspace/source
-              cp /src/package.json /workspace/source/package.json
-              cp /src/index.js /workspace/source/index.js
-              echo ">>> staged source:" && ls -la /workspace/source
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-            - { name: src, mountPath: /src }
-        # 2) Nixpacks: تولید Dockerfile در /workspace/source/.nixpacks/Dockerfile
-        - name: nixpacks-plan
-          image: ghcr.io/railwayapp/nixpacks:latest
-          imagePullPolicy: IfNotPresent
-          # نگاشت همان تنظیماتی که فاز ۲ پاس می‌دهد (نسخه‌ی Node و PORT)
-          env:
-            - { name: NIXPACKS_NODE_VERSION, value: "20" }
-            # - { name: NPM_CONFIG_REGISTRY, value: "https://registry.npmmirror.com" }  # ← در صورت نیاز
-          command:
-            - nixpacks
-            - build
-            - /workspace/source
-            - --out
-            - /workspace/source
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-      containers:
-        # 3) Kaniko: build واقعی Dockerfile تولیدی (تست دانلود وابستگی‌ها). بدون push.
-        - name: kaniko
-          image: gcr.io/kaniko-project/executor:v1.23.2
-          imagePullPolicy: IfNotPresent
-          args:
-            - --dockerfile=/workspace/source/.nixpacks/Dockerfile
-            - --context=dir:///workspace/source
-            - --no-push
-            - --verbosity=info
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-          resources:
-            requests: { cpu: "500m", memory: "1Gi" }
-            limits: { cpu: "2", memory: "4Gi" }
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: nixpacks-spike-go-src
-  namespace: cloudhost-builds
-data:
-  go.mod: |
-    module nixpacksspike
-
-    go 1.22
-  main.go: |
-    package main
-
-    import (
-      "fmt"
-      "net/http"
-      "os"
-    )
-
-    func main() {
-      http.HandleFunc("/", func(w http.ResponseWriter, _ *http.Request) {
-        fmt.Fprintln(w, "nixpacks spike ok")
-      })
-      port := os.Getenv("PORT")
-      if port == "" {
-        port = "8080"
-      }
-      http.ListenAndServe(":"+port, nil)
-    }
----
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: nixpacks-spike-go
-  namespace: cloudhost-builds
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 1800
-  template:
-    spec:
-      restartPolicy: Never
-      volumes:
-        - name: workspace
-          emptyDir: {}
-        - name: src
-          configMap:
-            name: nixpacks-spike-go-src
-      initContainers:
-        - name: stage-source
-          image: alpine:3.19
-          imagePullPolicy: IfNotPresent
-          command:
-            - sh
-            - -c
-            - |
-              set -e
-              mkdir -p /workspace/source
-              cp /src/go.mod /workspace/source/go.mod
-              cp /src/main.go /workspace/source/main.go
-              echo ">>> staged source:" && ls -la /workspace/source
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-            - { name: src, mountPath: /src }
-        - name: nixpacks-plan
-          image: ghcr.io/railwayapp/nixpacks:latest
-          imagePullPolicy: IfNotPresent
-          env:
-            # - { name: GOPROXY, value: "https://goproxy.cn,direct" }  # ← در صورت نیاز (mirror چین)
-          command:
-            - nixpacks
-            - build
-            - /workspace/source
-            - --out
-            - /workspace/source
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-      containers:
-        - name: kaniko
-          image: gcr.io/kaniko-project/executor:v1.23.2
-          imagePullPolicy: IfNotPresent
-          args:
-            - --dockerfile=/workspace/source/.nixpacks/Dockerfile
-            - --context=dir:///workspace/source
-            - --no-push
-            - --verbosity=info
-          volumeMounts:
-            - { name: workspace, mountPath: /workspace }
-          resources:
-            requests: { cpu: "500m", memory: "1Gi" }
-            limits: { cpu: "2", memory: "4Gi" }
-# ─────────────────────────────────────────────────────────────────────────────
-# نکات mirror (اگر build گیر کرد، uncomment/تنظیم و دوباره اجرا کنید):
-#   • npm:   NPM_CONFIG_REGISTRY=https://registry.npmmirror.com  (روی container kaniko
-#            اثر ندارد چون Dockerfile تولیدی است؛ بهتر است در فاز ۲ به‌صورت ARG/ENV
-#            داخل مرحله‌ی نصب تزریق شود — اینجا فقط برای nixpacks-plan گذاشته شده.)
-#   • nix:   اگر دانلود nixpkgs (https://github.com/NixOS/...) شکست خورد، احتمال نیاز به
-#            HTTP(S)_PROXY روی container kaniko یا آینه‌سازی nixpkgs. در لاگ kaniko دنبال
-#            خطوط fetch tarball بگردید.
-#   • go:    GOPROXY=https://goproxy.cn,direct  یا proxy داخلی.
-#   • اگر pull از ghcr.io/gcr.io خود مشکل داشت → image ها را به رجیستری داخلی mirror کنید
-#     (همان الگوی LOGGING_*_IMAGE در configuration.ts).
-# ─────────────────────────────────────────────────────────────────────────────

backend/migrations/001_service_access_grants.sql

@@ -1,16 +1,20 @@
 -- Temporary external access grants (Redis, RabbitMQ, database)
-CREATE TYPE service_access_target AS ENUM (
+DO $$ BEGIN
+  CREATE TYPE service_access_target AS ENUM (
     'database',
     'redis',
     'rabbitmq_amqp',
     'rabbitmq_management'
-);
+  );
+EXCEPTION WHEN duplicate_object THEN null; END $$;
 
-CREATE TYPE service_access_grant_status AS ENUM (
+DO $$ BEGIN
+  CREATE TYPE service_access_grant_status AS ENUM (
     'active',
     'expired',
     'revoked'
-);
+  );
+EXCEPTION WHEN duplicate_object THEN null; END $$;
 
 CREATE TABLE IF NOT EXISTS service_access_grants (
   id UUID PRIMARY KEY DEFAULT gen_random_uuid(),

backend/migrations/015_application_product_type.sql

@@ -3,7 +3,7 @@ ALTER TABLE applications
   ADD COLUMN IF NOT EXISTS product_type VARCHAR(32) NOT NULL DEFAULT 'application';
 
 CREATE INDEX IF NOT EXISTS idx_applications_user_product_type
-  ON applications (user_id, product_type);
+  ON applications ("userId", product_type);
 
 ALTER TABLE resource_credits
   ADD COLUMN IF NOT EXISTS product_type VARCHAR(32) NOT NULL DEFAULT 'application';

backend/package.json

@@ -1,5 +1,5 @@
 {
-  "name": "cloudhost-backend",
+  "name": "abrban-backend",
   "version": "1.0.0",
   "description": "CloudHost PaaS Backend API",
   "private": true,
@@ -9,7 +9,9 @@
     "start:dev": "nest start --watch",
     "start:debug": "nest start --debug --watch",
     "start:prod": "node dist/main",
-    "lint": "eslint \"{src,apps,libs,test}/**/*.ts\" --fix",
+    "lint": "eslint \"src/**/*.ts\" --fix",
+    "lint:check": "eslint \"src/**/*.ts\"",
+    "typecheck": "tsc --noEmit",
     "format": "prettier --write \"src/**/*.ts\" \"test/**/*.ts\"",
     "test": "jest",
     "test:watch": "jest --watch",
@@ -18,9 +20,11 @@
     "migration:generate": "npm run typeorm -- migration:generate -d src/config/typeorm.config.ts",
     "migration:run": "npm run typeorm -- migration:run -d src/config/typeorm.config.ts",
     "migration:revert": "npm run typeorm -- migration:revert -d src/config/typeorm.config.ts",
-    "seed": "ts-node -r tsconfig-paths/register src/seed.ts"
+    "seed": "ts-node -r tsconfig-paths/register src/seed.ts",
+    "sync:migrations": "node scripts/sync-helm-migrations.mjs"
   },
   "dependencies": {
+    "@aws-sdk/client-s3": "^3.1077.0",
     "@kubernetes/client-node": "^1.4.0",
     "@nestjs/bull": "^11.0.4",
     "@nestjs/common": "^11.1.24",
@@ -30,6 +34,7 @@
     "@nestjs/passport": "^11.0.5",
     "@nestjs/platform-express": "^11.1.26",
     "@nestjs/swagger": "^11.4.4",
+    "@nestjs/throttler": "^6.5.0",
     "@nestjs/typeorm": "^11.0.1",
     "bcrypt": "^6.0.0",
     "bull": "^4.12.0",
@@ -37,8 +42,8 @@
     "class-validator": "^0.15.1",
     "handlebars": "^4.7.8",
     "helmet": "^8.2.0",
+    "ioredis": "^5.11.1",
     "js-yaml": "^4.2.0",
-    "minio": "^8.0.7",
     "multer": "^2.1.1",
     "passport": "^0.7.0",
     "passport-jwt": "^4.0.1",
@@ -46,7 +51,8 @@
     "reflect-metadata": "^0.2.1",
     "rxjs": "^7.8.2",
     "typeorm": "^1.0.0",
-    "uuid": "^14.0.0"
+    "uuid": "^14.0.0",
+    "yauzl": "^3.4.0"
   },
   "devDependencies": {
     "@nestjs/cli": "^11.0.23",
@@ -59,6 +65,7 @@
     "@types/multer": "^2.1.0",
     "@types/node": "^24.0.0",
     "@types/passport-jwt": "^4.0.0",
+    "@types/yauzl": "^3.4.0",
     "@typescript-eslint/eslint-plugin": "^8.61.0",
     "@typescript-eslint/parser": "^8.61.0",
     "eslint": "^9.0.0",
@@ -84,6 +91,9 @@
       "**/*.(t|j)s"
     ],
     "coverageDirectory": "../coverage",
-    "testEnvironment": "node"
+    "testEnvironment": "node",
+    "setupFilesAfterEnv": [
+      "<rootDir>/test-setup.ts"
+    ]
   }
 }

backend/scripts/generate-base-schema.mjs

@@ -0,0 +1,94 @@
+#!/usr/bin/env node
+/**
+ * Generate the greenfield base schema (000_base_schema.sql) by letting TypeORM
+ * `synchronize` build every table from the entities against a throwaway
+ * Postgres, then dumping the schema. Run when entities change materially:
+ *
+ *   docker run -d --name ch-schemagen -e POSTGRES_PASSWORD=pass \
+ *     -e POSTGRES_USER=cloudhost -e POSTGRES_DB=cloudhost \
+ *     -p 55432:5432 postgres:16-alpine
+ *   node scripts/generate-base-schema.mjs
+ *
+ * The output is wrapped so it is safe to run on an already-populated database
+ * (every statement uses IF NOT EXISTS / duplicate_object guards where possible;
+ * the migration runner also records it in schema_migrations so it runs once).
+ */
+import 'reflect-metadata';
+import { DataSource } from 'typeorm';
+import { execFileSync } from 'node:child_process';
+import fs from 'node:fs';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const backendRoot = path.resolve(__dirname, '..');
+const outPath = path.join(backendRoot, 'migrations', '000_base_schema.sql');
+
+// Use the COMPILED entities (run `npm run build` first) — union-typed columns
+// only carry correct decorator metadata through the project's tsc build.
+const ds = new DataSource({
+  type: 'postgres',
+  host: process.env.SCHEMA_DB_HOST || '127.0.0.1',
+  port: parseInt(process.env.SCHEMA_DB_PORT || '55432', 10),
+  username: 'cloudhost',
+  password: 'pass',
+  database: 'cloudhost',
+  entities: [path.join(backendRoot, 'dist/**/*.entity.js')],
+  synchronize: true,
+});
+
+await ds.initialize();
+await ds.destroy();
+
+// Dump schema-only from the container, then strip owner/ACL noise.
+const dumped = execFileSync('docker', [
+  'exec', 'ch-schemagen',
+  'pg_dump', '-U', 'cloudhost', '-d', 'cloudhost',
+  '--schema-only', '--no-owner', '--no-privileges',
+], { maxBuffer: 32 * 1024 * 1024 }).toString();
+
+// Strip:
+//  - psql client meta-commands that are version-specific (\restrict is
+//    pg_dump 16.13+ only) and would break on the migrations image's psql;
+//  - the `search_path = ''` reset, which otherwise persists into the trailing
+//    `INSERT INTO schema_migrations` the runner appends (unqualified) and the
+//    footer below, causing "no schema has been selected to create in".
+const raw = dumped
+  .split('\n')
+  .filter(
+    (line) =>
+      !/^\\(restrict|unrestrict)\b/.test(line) &&
+      !/set_config\('search_path'/.test(line),
+  )
+  .join('\n');
+
+const header = `-- 000_base_schema.sql — greenfield base schema (generated from TypeORM entities).
+-- Auto-generated by scripts/generate-base-schema.mjs. Do not edit by hand.
+-- Incremental migrations (001+) run afterwards on top of this schema.
+
+`;
+
+// The legacy pricing-catalog migrations (004-009) target a superseded
+// snake_case pricing schema that is incompatible with the current entities.
+// On greenfield the base schema already creates the entity-shaped pricing
+// tables and the app self-seeds their rows (PricingCatalogService.ensureDefaults
+// on boot), so mark those migrations as already applied to skip them.
+const supersededPricingMigrations = [
+  '004_pricing_catalog.sql',
+  '005_pricing_catalog_all_runtimes.sql',
+  '006_addon_rate_resources.sql',
+  '007_optional_service_pricing_matrix.sql',
+  '008_application_optional_service_resources.sql',
+  '009_optional_service_deploy_defaults.sql',
+];
+const footer = `
+
+-- Mark superseded legacy pricing migrations as applied (see generator note).
+CREATE TABLE IF NOT EXISTS schema_migrations (filename TEXT PRIMARY KEY, applied_at TIMESTAMPTZ NOT NULL DEFAULT NOW());
+INSERT INTO schema_migrations (filename) VALUES
+${supersededPricingMigrations.map((m) => `  ('${m}')`).join(',\n')}
+ON CONFLICT (filename) DO NOTHING;
+`;
+
+fs.writeFileSync(outPath, header + raw + footer);
+console.log(`Wrote ${outPath} (${raw.length} bytes)`);

backend/scripts/sync-helm-migrations.mjs

@@ -0,0 +1,33 @@
+#!/usr/bin/env node
+/**
+ * Copy SQL migrations from backend/migrations/ into the Helm chart ConfigMap source.
+ * Run after adding or editing migration files: npm run sync:migrations
+ */
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const sourceDir = path.resolve(__dirname, '../migrations');
+const targetDir = path.resolve(__dirname, '../helm/cloudhost-platform/migrations');
+
+if (!fs.existsSync(sourceDir)) {
+  console.error(`Source not found: ${sourceDir}`);
+  process.exit(1);
+}
+
+fs.mkdirSync(targetDir, { recursive: true });
+
+const files = fs.readdirSync(sourceDir).filter((f) => f.endsWith('.sql')).sort();
+for (const file of files) {
+  fs.copyFileSync(path.join(sourceDir, file), path.join(targetDir, file));
+}
+
+// Remove stale SQL files no longer in source
+for (const existing of fs.readdirSync(targetDir)) {
+  if (existing.endsWith('.sql') && !files.includes(existing)) {
+    fs.unlinkSync(path.join(targetDir, existing));
+  }
+}
+
+console.log(`Synced ${files.length} migration(s) to ${targetDir}`);

backend/src/app.module.ts

@@ -2,6 +2,8 @@ import { Module } from '@nestjs/common';
 import { ConfigModule, ConfigService } from '@nestjs/config';
 import { TypeOrmModule } from '@nestjs/typeorm';
 import { BullModule } from '@nestjs/bull';
+import { ThrottlerModule, ThrottlerGuard } from '@nestjs/throttler';
+import { APP_GUARD } from '@nestjs/core';
 import { AuthModule } from './auth/auth.module';
 import { UsersModule } from './users/users.module';
 import { ApplicationsModule } from './applications/applications.module';
@@ -15,8 +17,8 @@ import { SnapshotsModule } from './snapshots/snapshots.module';
 import { LifecycleModule } from './lifecycle/lifecycle.module';
 import { ApplicationMigrationsModule } from './application-migrations/application-migrations.module';
 import { AdminModule } from './admin/admin.module';
-import { RedisModule } from './common/redis/redis.module';
+import { HealthModule } from './health/health.module';
-import { StorageModule } from './common/storage/storage.module';
+import { StorageModule } from './storage/storage.module';
 import configuration from './config/configuration';
 
 @Module({
@@ -51,18 +53,22 @@ import configuration from './config/configuration';
         redis: {
           host: configService.get('redis.host'),
           port: configService.get('redis.port'),
+          password: configService.get('redis.password'),
         },
       }),
       inject: [ConfigService],
     }),
 
-    // Shared Redis client (build state across replicas)
+    ThrottlerModule.forRoot([
-    RedisModule,
+      {
-
+        name: 'default',
-    // Shared MinIO storage (application source archives)
+        ttl: 60_000,
-    StorageModule,
+        limit: 120,
+      },
+    ]),
 
     // Feature modules
+    StorageModule,
     AuthModule,
     UsersModule,
     ApplicationsModule,
@@ -76,6 +82,13 @@ import configuration from './config/configuration';
     LifecycleModule,
     ApplicationMigrationsModule,
     AdminModule,
+    HealthModule,
+  ],
+  providers: [
+    {
+      provide: APP_GUARD,
+      useClass: ThrottlerGuard,
+    },
   ],
 })
 export class AppModule {}

backend/src/applications/applications.controller.ts

@@ -18,7 +18,8 @@ import {
 } from '@nestjs/common';
 import { AuthGuard } from '@nestjs/passport';
 import { FileInterceptor } from '@nestjs/platform-express';
-import { ApiTags, ApiOperation, ApiBearerAuth, ApiConsumes } from '@nestjs/swagger';
+import { ApiTags, ApiOperation, ApiBearerAuth, ApiConsumes, ApiBadRequestResponse } from '@nestjs/swagger';
+import { Throttle } from '@nestjs/throttler';
 import { ApplicationsService } from './applications.service';
 import { DomainService } from './domain.service';
 import { CreateApplicationDto, UpdateApplicationDto, ScaleResourcesDto, SetCustomDomainDto, CheckDnsDto } from './dto/application.dto';
@@ -67,7 +68,20 @@ export class ApplicationsController {
   }
 
   @Post(':id/upload')
+  @Throttle({ default: { limit: 10, ttl: 60_000 } })
   @ApiOperation({ summary: 'Upload application code (zip file)' })
+  @ApiBadRequestResponse({
+    description: 'Runtime mismatch between selected app type and archive contents',
+    schema: {
+      example: {
+        statusCode: 400,
+        message: 'Selected runtime "nodejs" does not match the uploaded source (detected "go").',
+        configured: 'nodejs',
+        detected: 'go',
+        signals: ['go.mod'],
+      },
+    },
+  })
   @ApiConsumes('multipart/form-data')
   @UseInterceptors(FileInterceptor('file', {
     limits: { fileSize: 10 * 1024 * 1024 * 1024 }, // 10 GiB max application archive
@@ -373,6 +387,29 @@ export class ApplicationsController {
       throw new BadRequestException('Replicas can only be changed for the main application workload.');
     }
 
+    // Non-staff users must go through the billed upgrade flow for any change
+    // that increases cost — direct PATCH must not bypass payment.
+    if (!isStaff) {
+      const upgradeDto =
+        workload === 'app'
+          ? {
+              cpuLimit: dto.cpuLimit,
+              memoryLimit: dto.memoryLimit,
+              replicas: dto.replicas,
+            }
+          : workload === 'database'
+            ? { databaseResources: { cpuLimit: dto.cpuLimit, memoryLimit: dto.memoryLimit } }
+            : workload === 'redis'
+              ? { redisResources: { cpuLimit: dto.cpuLimit, memoryLimit: dto.memoryLimit } }
+              : { rabbitmqResources: { cpuLimit: dto.cpuLimit, memoryLimit: dto.memoryLimit } };
+      const cost = await this.billingService.calculateUpgradeCost(app, upgradeDto as any);
+      if (cost.proratedAmount > 0) {
+        throw new BadRequestException(
+          'This change increases the plan cost. Use the resource upgrade flow (with invoice payment) instead.',
+        );
+      }
+    }
+
     // Update in K8s (live)
     await this.kubernetesService.updateResources(app, dto, workload);
 

backend/src/applications/applications.service.ts

@@ -17,7 +17,13 @@ import {
 } from '../common/enums';
 import { ensureAppUrlEnv } from './app-url.util';
 import { normalizeCreateApplicationDto } from './managed-service.util';
-import { StorageService } from '../common/storage/storage.service';
+import {
+  assertRuntimeMatch,
+  detectRuntimeFromArchive,
+} from '../build/runtime-detector';
+import { SourceStorageService } from '../storage/source-storage.service';
+import { userIdSlug } from '../kubernetes/k8s-workload.util';
+import * as os from 'os';
 
 @Injectable()
 export class ApplicationsService {
@@ -28,7 +34,7 @@ export class ApplicationsService {
     private appsRepository: Repository<Application>,
     private clustersService: ClustersService,
     private configService: ConfigService,
-    private storageService: StorageService,
+    private sourceStorage: SourceStorageService,
   ) {}
 
   private toDnsLabel(value: string): string {
@@ -62,6 +68,18 @@ export class ApplicationsService {
     dto = normalizeCreateApplicationDto(dto);
     const productType = dto.productType ?? ProductType.APPLICATION;
 
+    // WordPress only runs on MySQL/MariaDB — reject PostgreSQL/Mongo/none up
+    // front instead of failing at runtime inside the WordPress container.
+    if (dto.runtime === AppRuntime.WORDPRESS) {
+      if (!dto.databaseType || dto.databaseType === DatabaseType.NONE) {
+        dto.databaseType = DatabaseType.MYSQL;
+      } else if (![DatabaseType.MYSQL, DatabaseType.MARIADB].includes(dto.databaseType)) {
+        throw new BadRequestException(
+          `WordPress requires a MySQL or MariaDB database — "${dto.databaseType}" is not supported.`,
+        );
+      }
+    }
+
     // Placement is always decided automatically by the allocator.
     const allocation = await this.clustersService.selectClusterForApplication(dto, userId);
     const clusterId = allocation.cluster.id;
@@ -91,7 +109,7 @@ export class ApplicationsService {
 
     const baseLabel = dto.name;
     const subdomain = customDomain
-      ? `${this.toDnsLabel(baseLabel)}-${this.toDnsLabel(userId.split('-')[0])}`
+      ? `${this.toDnsLabel(baseLabel)}-${this.toDnsLabel(userIdSlug(userId).slice(0, 12))}`
       : await this.generateRandomSubdomain(baseLabel);
     const platformDomain = this.configService.get('platform.domain') || 'apps.cloudhost.ir';
 
@@ -206,20 +224,13 @@ export class ApplicationsService {
   async delete(id: string, userId: string): Promise<Application> {
     const app = await this.findOne(id, userId);
 
-    // Delete the uploaded source archive from object storage.
+    // Delete uploaded source files
     if (app.codePath) {
-      await this.storageService.removeSource(app.codePath);
-    }
-    // Remove any legacy on-disk dump/source dir (db dumps are still stored locally).
       try {
-      const uploadDir = this.configService.get<string>('platform.uploadDir') || './uploads';
+        await this.sourceStorage.deleteSource(app.userId, app.id, app.codePath);
-      const appDir = path.join(uploadDir, app.userId, app.id);
-      if (fs.existsSync(appDir)) {
-        fs.rmSync(appDir, { recursive: true, force: true });
-        this.logger.log(`Deleted upload directory: ${appDir}`);
-      }
       } catch (e: any) {
-      this.logger.warn(`Failed to delete upload dir for ${app.name}: ${e.message}`);
+        this.logger.warn(`Failed to delete source for ${app.name}: ${e.message}`);
+      }
     }
 
     await this.appsRepository.remove(app);
@@ -265,15 +276,38 @@ export class ApplicationsService {
     }
 
     const app = await this.findOne(id, userId);
+    const tempPath = path.join(os.tmpdir(), `upload-${app.id}-${Date.now()}.zip`);
+    fs.writeFileSync(tempPath, file.buffer);
 
-    // Stream the archive to MinIO; codePath stores the object key (build pods
+    try {
-    // pull it via a presigned URL — no local disk, no PVC, no kubectl cp).
+      const detected = await detectRuntimeFromArchive(tempPath);
-    const key = await this.storageService.putSource(app.userId, app.id, file.buffer);
+      assertRuntimeMatch(app.runtime, detected);
-    app.codePath = key;
+
+      const storedPath = await this.sourceStorage.putSource(app.userId, app.id, file.buffer);
+      app.codePath = storedPath;
       const saved = await this.appsRepository.save(app);
 
-    this.logger.log(`Uploaded code for ${app.name} → ${key} (${(file.size / 1024).toFixed(1)} KB)`);
+      if (detected.confidence === 'low') {
+        Object.assign(saved, {
+          runtimeWarning:
+            'Could not determine the project type from the archive with high confidence. Build may fail if the selected runtime is wrong.',
+        });
+      }
+
+      this.logger.log(`Uploaded code for ${app.name} → ${storedPath} (${(file.size / 1024).toFixed(1)} KB)`);
       return saved;
+    } catch (err) {
+      try {
+        await this.sourceStorage.deleteSource(app.userId, app.id);
+      } catch {
+        // ignore rollback errors
+      }
+      throw err;
+    } finally {
+      if (fs.existsSync(tempPath)) {
+        fs.unlinkSync(tempPath);
+      }
+    }
   }
 
   async uploadDbDump(id: string, userId: string, file: Express.Multer.File): Promise<Application> {

backend/src/applications/entities/application.entity.ts

@@ -16,6 +16,7 @@ import {
   CustomDomainStatus,
   ProductType,
 } from '../../common/enums';
+import { Exclude, Expose } from 'class-transformer';
 import { User } from '../../users/entities/user.entity';
 import { Deployment } from '../../deployments/entities/deployment.entity';
 
@@ -51,9 +52,16 @@ export class Application {
   @Column({ nullable: true })
   dbUsername: string;
 
+  /** Never expose raw DB password in API responses — use hasDbPassword for UI. */
+  @Exclude({ toPlainOnly: true })
   @Column({ nullable: true })
   dbPassword: string;
 
+  @Expose()
+  get hasDbPassword(): boolean {
+    return !!this.dbPassword;
+  }
+
   @Column({ nullable: true, default: '1Gi' })
   dbStorageSize: string; // PVC storage size for database (e.g. '1Gi', '5Gi', '10Gi')
 
@@ -111,8 +119,19 @@ export class Application {
   @Column({ nullable: true })
   gitUrl: string;
 
+  /**
+   * Personal access token for private repos. Never serialized into API
+   * responses (see hasGitToken) — it is a credential to an external system.
+   */
+  @Exclude({ toPlainOnly: true })
   @Column({ nullable: true })
-  gitToken: string; // Personal access token for private repos
+  gitToken: string;
+
+  /** Whether a git token is configured (safe indicator for the UI). */
+  @Expose()
+  get hasGitToken(): boolean {
+    return !!this.gitToken;
+  }
 
   @Column({ nullable: true })
   gitBranch: string; // Branch to clone (default: main)

backend/src/auth/auth.controller.ts

@@ -1,5 +1,6 @@
 import { Controller, Post, Body, HttpCode, HttpStatus } from '@nestjs/common';
 import { ApiTags, ApiOperation, ApiResponse } from '@nestjs/swagger';
+import { Throttle } from '@nestjs/throttler';
 import { AuthService } from './auth.service';
 import { RegisterDto } from './dto/register.dto';
 import { LoginDto } from './dto/login.dto';
@@ -7,6 +8,7 @@ import { OtpRequestDto, OtpVerifyDto } from './dto/otp.dto';
 import { RefreshTokenDto } from './dto/refresh-token.dto';
 
 @ApiTags('Authentication')
+@Throttle({ default: { limit: 20, ttl: 60_000 } })
 @Controller('auth')
 export class AuthController {
   constructor(private readonly authService: AuthService) {}

backend/src/billing/billing-invoices.controller.ts

@@ -0,0 +1,149 @@
+import {
+  Controller,
+  Get,
+  Post,
+  Patch,
+  Body,
+  Param,
+  Query,
+  UseGuards,
+  Request,
+} from '@nestjs/common';
+import { AuthGuard } from '@nestjs/passport';
+import { ApiTags, ApiOperation, ApiBearerAuth } from '@nestjs/swagger';
+import { BillingService } from './billing.service';
+import { BillingOpsService } from './billing-ops.service';
+import { assertStubGatewayAllowed } from './payment-gateway.util';
+import {
+  ChargeWalletDto,
+  InitiateInvoicePaymentDto,
+  VerifyInvoiceGatewayDto,
+  UpdateInvoiceStatusDto,
+} from './dto/billing.dto';
+import { RolesGuard } from '../common/guards/roles.guard';
+import { Roles } from '../common/decorators/roles.decorator';
+import { UserRole, InvoiceStatus, PaymentMethod } from '../common/enums';
+
+@ApiTags('Billing')
+@ApiBearerAuth()
+@Controller('billing')
+@UseGuards(AuthGuard('jwt'), RolesGuard)
+export class BillingInvoicesController {
+  constructor(
+    private readonly billingService: BillingService,
+    private readonly billingOpsService: BillingOpsService,
+  ) {}
+
+  // ─── Invoices ─────────────────────────────────────────────────────
+
+  @Get('invoices')
+  @ApiOperation({ summary: 'List my invoices' })
+  async listMyInvoices(
+    @Request() req: any,
+    @Query('status') status?: InvoiceStatus,
+    @Query('applicationId') applicationId?: string,
+    @Query('limit') limit?: string,
+  ) {
+    return this.billingService.listInvoices(req.user, {
+      status,
+      applicationId,
+      limit: limit ? parseInt(limit, 10) : undefined,
+    });
+  }
+
+  @Get('invoices/:id')
+  @ApiOperation({ summary: 'Get one invoice with line items and transactions' })
+  async getInvoice(@Request() req: any, @Param('id') id: string) {
+    return this.billingService.getInvoiceForUser(id, req.user);
+  }
+
+  @Post('invoices/:id/pay/mixed')
+  @ApiOperation({ summary: 'Pay invoice with wallet first, then gateway for the remaining amount' })
+  async initiateInvoiceMixed(
+    @Request() req: any,
+    @Param('id') id: string,
+    @Body() dto: InitiateInvoicePaymentDto,
+  ) {
+    const result = await this.billingService.initiateInvoiceMixedPayment(id, req.user, dto.callbackUrl);
+    const effect = await this.billingOpsService.completePaidInvoiceEffect(result.invoice);
+    return { ...result, effect };
+  }
+
+  @Post('invoices/:id/gateway/verify')
+  @ApiOperation({ summary: 'Verify invoice gateway payment' })
+  async verifyInvoiceGateway(
+    @Request() req: any,
+    @Param('id') id: string,
+    @Body() dto: VerifyInvoiceGatewayDto,
+  ) {
+    assertStubGatewayAllowed();
+    const result = await this.billingService.verifyInvoiceGatewayPayment(
+      id,
+      req.user,
+      dto.trackingCode,
+      dto.amount,
+    );
+    const effect = await this.billingOpsService.completePaidInvoiceEffect(result.invoice);
+    return { ...result, effect };
+  }
+
+  // ─── Invoice Admin ────────────────────────────────────────────────
+
+  @Get('admin/invoices')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'List all invoices (Admin)' })
+  async listAdminInvoices(
+    @Request() req: any,
+    @Query('status') status?: InvoiceStatus,
+    @Query('userId') userId?: string,
+    @Query('applicationId') applicationId?: string,
+    @Query('paymentMethod') paymentMethod?: PaymentMethod,
+    @Query('search') search?: string,
+    @Query('limit') limit?: string,
+  ) {
+    return this.billingService.listInvoices(req.user, {
+      status,
+      userId,
+      applicationId,
+      paymentMethod,
+      search,
+      limit: limit ? parseInt(limit, 10) : undefined,
+    });
+  }
+
+  @Get('admin/invoices/:id')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'Get invoice details (Admin)' })
+  async getAdminInvoice(@Request() req: any, @Param('id') id: string) {
+    return this.billingService.getInvoiceForUser(id, req.user);
+  }
+
+  @Patch('admin/invoices/:id/status')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'Update invoice status with reason (Admin)' })
+  async updateAdminInvoiceStatus(
+    @Param('id') id: string,
+    @Body() dto: UpdateInvoiceStatusDto,
+  ) {
+    return this.billingService.updateInvoiceStatus(id, dto.status, dto.reason);
+  }
+
+  // ─── Wallet Admin ─────────────────────────────────────────────────
+
+  @Get('admin/wallets')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'List all wallets (Admin)' })
+  async getAllWallets() {
+    return this.billingService.getAllWallets();
+  }
+
+  @Post('admin/wallets/:userId/charge')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'Charge a user\'s wallet (Admin)' })
+  async adminChargeWallet(
+    @Param('userId') userId: string,
+    @Body() dto: ChargeWalletDto,
+  ) {
+    return this.billingService.adminChargeWallet(userId, dto.amount, dto.description);
+  }
+}

backend/src/billing/billing-ops.service.ts

@@ -0,0 +1,258 @@
+import { BadRequestException, Inject, Injectable, forwardRef } from '@nestjs/common';
+import { BillingService } from './billing.service';
+import { AppLifecycleService } from '../lifecycle/app-lifecycle.service';
+import { ApplicationsService } from '../applications/applications.service';
+import { KubernetesService } from '../kubernetes/kubernetes.service';
+import { UpgradeResourcesDto } from './dto/billing.dto';
+import {
+  BillingCycle,
+  InvoiceStatus,
+  ProductType,
+  DatabaseType,
+  UserRole,
+} from '../common/enums';
+import { Application } from '../applications/entities/application.entity';
+
+@Injectable()
+export class BillingOpsService {
+  constructor(
+    private readonly billingService: BillingService,
+    @Inject(forwardRef(() => AppLifecycleService))
+    private readonly lifecycleService: AppLifecycleService,
+    @Inject(forwardRef(() => ApplicationsService))
+    private readonly applicationsService: ApplicationsService,
+    @Inject(forwardRef(() => KubernetesService))
+    private readonly kubernetesService: KubernetesService,
+  ) {}
+
+  async completePaidInvoiceEffect(invoice: any) {
+    if (invoice.status !== InvoiceStatus.PAID) return null;
+    if (invoice.metadata?.completedAt) return invoice.metadata.completionResult || null;
+
+    const action = invoice.metadata?.action;
+    if (!action || !invoice.applicationId) return null;
+
+    if (action === 'renew' || action === 'activate') {
+      const cycle = invoice.metadata?.cycle as BillingCycle;
+      if (!Object.values(BillingCycle).includes(cycle)) return null;
+
+      const activated = await this.lifecycleService.activateApp(invoice.applicationId, cycle);
+      const result = {
+        action,
+        application: {
+          id: activated.id,
+          name: activated.name,
+          lifecycleStatus: activated.lifecycleStatus,
+          planExpiresAt: activated.planExpiresAt,
+          billingCycle: activated.billingCycle,
+        },
+      };
+      await this.billingService.markInvoiceEffectCompleted(invoice.id, result);
+      return result;
+    }
+
+    if (action === 'upgrade') {
+      const app = await this.applicationsService.findOne(invoice.applicationId);
+      const resources = (invoice.metadata?.resources || {}) as UpgradeResourcesDto;
+      const updatedApp = await this.applicationsService.update(
+        app.id,
+        app.userId,
+        this.buildUpgradeEntityPatch(app, resources),
+      );
+
+      try {
+        await this.applyUpgradeToKubernetes(updatedApp, resources, app);
+      } catch (e: any) {
+        console.warn(`K8s resource update failed for ${app.name}: ${e.message}`);
+      }
+
+      const result = {
+        action,
+        application: {
+          id: updatedApp.id,
+          name: updatedApp.name,
+          cpuRequest: updatedApp.cpuRequest,
+          cpuLimit: updatedApp.cpuLimit,
+          memoryRequest: updatedApp.memoryRequest,
+          memoryLimit: updatedApp.memoryLimit,
+          replicas: updatedApp.replicas,
+        },
+      };
+      await this.billingService.markInvoiceEffectCompleted(invoice.id, result);
+      return result;
+    }
+
+    return null;
+  }
+
+  buildUpgradeEntityPatch(app: Application, dto: UpgradeResourcesDto): Partial<Application> {
+    const pt = app.productType ?? ProductType.APPLICATION;
+
+    if (dto.redisResources) {
+      return {
+        optionalServiceResources: {
+          ...app.optionalServiceResources,
+          redis: {
+            ...app.optionalServiceResources?.redis,
+            ...dto.redisResources,
+            storageGi:
+              dto.redisResources.storageGi ?? app.optionalServiceResources?.redis?.storageGi ?? 1,
+          },
+        },
+      };
+    }
+
+    if (dto.rabbitmqResources) {
+      return {
+        optionalServiceResources: {
+          ...app.optionalServiceResources,
+          rabbitmq: {
+            ...app.optionalServiceResources?.rabbitmq,
+            ...dto.rabbitmqResources,
+            storageGi:
+              dto.rabbitmqResources.storageGi ??
+              app.optionalServiceResources?.rabbitmq?.storageGi ??
+              2,
+          },
+        },
+      };
+    }
+
+    if (pt === ProductType.MANAGED_REDIS || pt === ProductType.MANAGED_RABBITMQ) {
+      return {};
+    }
+
+    return {
+      cpuRequest: dto.cpuRequest || app.cpuRequest,
+      cpuLimit: dto.cpuLimit || app.cpuLimit,
+      memoryRequest: dto.memoryRequest || app.memoryRequest,
+      memoryLimit: dto.memoryLimit || app.memoryLimit,
+      replicas: dto.replicas ?? app.replicas,
+      dbStorageSize: dto.dbStorageSize || app.dbStorageSize,
+      appStorageSize: dto.appStorageSize || app.appStorageSize,
+    };
+  }
+
+  async applyUpgradeToKubernetes(
+    app: Application,
+    dto: UpgradeResourcesDto,
+    previous: Application,
+  ): Promise<void> {
+    const pt = app.productType ?? ProductType.APPLICATION;
+
+    if (pt === ProductType.MANAGED_DATABASE) {
+      await this.kubernetesService.updateResources(
+        app,
+        {
+          cpuRequest: dto.cpuRequest,
+          cpuLimit: dto.cpuLimit,
+          memoryRequest: dto.memoryRequest,
+          memoryLimit: dto.memoryLimit,
+        },
+        'database',
+      );
+      if (dto.dbStorageSize && dto.dbStorageSize !== previous.dbStorageSize) {
+        const resize = await this.kubernetesService.resizeDatabasePvc(app, dto.dbStorageSize);
+        if (!resize.success) {
+          throw new BadRequestException(resize.message);
+        }
+      }
+      return;
+    }
+
+    if (pt === ProductType.MANAGED_REDIS) {
+      await this.applyOptionalServiceUpgrade(app, dto, previous, 'redis');
+      return;
+    }
+
+    if (pt === ProductType.MANAGED_RABBITMQ) {
+      await this.applyOptionalServiceUpgrade(app, dto, previous, 'rabbitmq');
+      return;
+    }
+
+    if (dto.redisResources && app.enableRedis) {
+      await this.applyOptionalServiceUpgrade(app, dto, previous, 'redis');
+    }
+
+    if (dto.rabbitmqResources && app.enableRabbitmq) {
+      await this.applyOptionalServiceUpgrade(app, dto, previous, 'rabbitmq');
+    }
+
+    const touchesAppWorkload =
+      dto.cpuRequest !== undefined ||
+      dto.cpuLimit !== undefined ||
+      dto.memoryRequest !== undefined ||
+      dto.memoryLimit !== undefined ||
+      dto.replicas !== undefined;
+
+    if (touchesAppWorkload) {
+      await this.kubernetesService.updateResources(app, {
+        cpuRequest: dto.cpuRequest,
+        cpuLimit: dto.cpuLimit,
+        memoryRequest: dto.memoryRequest,
+        memoryLimit: dto.memoryLimit,
+        replicas: dto.replicas,
+      });
+    }
+
+    if (dto.appStorageSize && dto.appStorageSize !== previous.appStorageSize) {
+      await this.kubernetesService.resizeAppStoragePvc(app, dto.appStorageSize);
+    }
+
+    if (
+      dto.dbStorageSize &&
+      dto.dbStorageSize !== previous.dbStorageSize &&
+      previous.databaseType &&
+      previous.databaseType !== DatabaseType.NONE
+    ) {
+      const resize = await this.kubernetesService.resizeDatabasePvc(app, dto.dbStorageSize);
+      if (!resize.success) {
+        throw new BadRequestException(resize.message);
+      }
+    }
+  }
+
+  async applyOptionalServiceUpgrade(
+    app: Application,
+    dto: UpgradeResourcesDto,
+    previous: Application,
+    service: 'redis' | 'rabbitmq',
+  ): Promise<void> {
+    const res = app.optionalServiceResources?.[service];
+    const dtoRes = service === 'redis' ? dto.redisResources : dto.rabbitmqResources;
+    if (res) {
+      await this.kubernetesService.updateResources(
+        app,
+        {
+          cpuRequest: res.cpuRequest,
+          cpuLimit: res.cpuLimit,
+          memoryRequest: res.memoryRequest,
+          memoryLimit: res.memoryLimit,
+        },
+        service,
+      );
+    }
+    const prevGi =
+      previous.optionalServiceResources?.[service]?.storageGi ?? (service === 'redis' ? 1 : 2);
+    const nextGi = dtoRes?.storageGi;
+    if (nextGi != null && nextGi > prevGi) {
+      const resize =
+        service === 'redis'
+          ? await this.kubernetesService.resizeRedisStoragePvc(app, `${nextGi}Gi`)
+          : await this.kubernetesService.resizeRabbitmqStoragePvc(app, `${nextGi}Gi`);
+      if (!resize.success) {
+        throw new BadRequestException(resize.message);
+      }
+    }
+  }
+
+  async getAppWithAccess(user: any, applicationId: string) {
+    const isAdminOrSales = user.role === UserRole.ADMIN || user.role === UserRole.SALES;
+
+    if (isAdminOrSales) {
+      return this.applicationsService.findOne(applicationId);
+    }
+
+    return this.applicationsService.findOne(applicationId, user.id);
+  }
+}

backend/src/billing/billing-wallet.controller.ts

@@ -0,0 +1,199 @@
+import {
+  Controller,
+  Get,
+  Post,
+  Body,
+  Param,
+  Query,
+  UseGuards,
+  Request,
+  BadRequestException,
+  Inject,
+  forwardRef,
+} from '@nestjs/common';
+import { AuthGuard } from '@nestjs/passport';
+import { ApiTags, ApiOperation, ApiBearerAuth } from '@nestjs/swagger';
+import { BillingService } from './billing.service';
+import {
+  assertStubGatewayAllowed,
+  issueGatewayTrackingCode,
+  assertGatewayTrackingCodeValid,
+} from './payment-gateway.util';
+import { AppLifecycleService } from '../lifecycle/app-lifecycle.service';
+import { ApplicationsService } from '../applications/applications.service';
+import { ChargeWalletDto, PayApplicationDto } from './dto/billing.dto';
+import { RolesGuard } from '../common/guards/roles.guard';
+import { BillingCycle, InvoiceReason } from '../common/enums';
+
+@ApiTags('Billing')
+@ApiBearerAuth()
+@Controller('billing')
+@UseGuards(AuthGuard('jwt'), RolesGuard)
+export class BillingWalletController {
+  constructor(
+    private readonly billingService: BillingService,
+    @Inject(forwardRef(() => AppLifecycleService))
+    private readonly lifecycleService: AppLifecycleService,
+    @Inject(forwardRef(() => ApplicationsService))
+    private readonly applicationsService: ApplicationsService,
+  ) {}
+
+  // ─── Wallet (User) ───────────────────────────────────────────────
+
+  @Get('wallet')
+  @ApiOperation({ summary: 'Get my wallet balance' })
+  async getBalance(@Request() req: any) {
+    return this.billingService.getBalance(req.user.id);
+  }
+
+  @Post('wallet/charge')
+  @ApiOperation({ summary: 'Charge my wallet (self top-up — stub gateway, dev/staging only)' })
+  async chargeMyWallet(@Request() req: any, @Body() dto: ChargeWalletDto) {
+    // Direct self-credit is only for environments with the stub gateway enabled.
+    // In production a real payment gateway must credit wallets.
+    assertStubGatewayAllowed();
+    return this.billingService.chargeWallet(req.user.id, dto.amount, dto.description || 'Self top-up');
+  }
+
+  @Get('wallet/transactions')
+  @ApiOperation({ summary: 'Get my wallet transactions' })
+  async getTransactions(@Request() req: any, @Query('limit') limit?: string) {
+    return this.billingService.getTransactions(req.user.id, limit ? parseInt(limit, 10) : 50);
+  }
+
+  @Get('resource-credits')
+  @ApiOperation({ summary: 'List active prepaid resource credits (from deleted apps)' })
+  async getResourceCredits(@Request() req: any) {
+    const credits = await this.billingService.getActiveCredits(req.user.id);
+    return credits.map((c) => this.billingService.formatCreditForApi(c));
+  }
+
+  @Post('wallet/pay/:applicationId')
+  @ApiOperation({ summary: 'Pay for an application plan from wallet — activates/renews the app' })
+  async payForApplication(
+    @Request() req: any,
+    @Param('applicationId') applicationId: string,
+    @Body() body: PayApplicationDto,
+  ) {
+    const cycle = body.cycle as BillingCycle;
+    if (!Object.values(BillingCycle).includes(cycle)) {
+      throw new BadRequestException(`Invalid billing cycle: ${body.cycle}`);
+    }
+
+    const app = await this.applicationsService.findOne(applicationId, req.user.id);
+
+    const payment = await this.billingService.resolveAppPayment(
+      req.user.id,
+      app,
+      cycle,
+    );
+
+    const coupon = await this.billingService.resolveCoupon(
+      req.user.id,
+      body.couponCode,
+      await this.billingService.getAppChargeBreakdown(app),
+      cycle,
+      payment.amountDue,
+    );
+
+    let invoice = null;
+    if (payment.amountDue > 0) {
+      invoice = await this.billingService.createInvoice({
+        userId: req.user.id,
+        applicationId: app.id,
+        reason: InvoiceReason.DEPLOY,
+        lines: [
+          {
+            label: `Application payment: ${app.name}`,
+            description: `Billing cycle: ${cycle}`,
+            amount: payment.amountDue,
+            metadata: {
+              cycle,
+              waivedAmount: payment.waivedAmount,
+              creditApplied: payment.creditId || null,
+            },
+          },
+        ],
+        metadata: {
+          action: 'activate',
+          cycle,
+        },
+        discount: coupon ?? undefined,
+      });
+    }
+
+    let tx = null;
+    if (invoice) {
+      const paid = await this.billingService.payInvoiceWithWallet(invoice.id, req.user);
+      tx = paid.transaction;
+      invoice = paid.invoice;
+    }
+
+    const activated = await this.lifecycleService.activateApp(
+      applicationId,
+      cycle,
+    );
+
+    return {
+      transaction: tx,
+      invoice,
+      creditApplied: payment.creditId || null,
+      waivedAmount: payment.waivedAmount,
+      discountAmount: coupon?.amount ?? 0,
+      discountCode: coupon?.code ?? null,
+      paidAmount: invoice ? Number(invoice.total) : 0,
+      application: {
+        id: activated.id,
+        name: activated.name,
+        lifecycleStatus: activated.lifecycleStatus,
+        planExpiresAt: activated.planExpiresAt,
+      },
+      message: payment.waivedAmount > 0
+        ? payment.amountDue > 0
+          ? `Application "${activated.name}" activated — prepaid credit applied; you paid ${payment.amountDue} Toman for additional services.`
+          : `Application "${activated.name}" activated using your prepaid resource credit (no charge).`
+        : payment.amountDue > 0
+          ? `Application "${activated.name}" activated until ${activated.planExpiresAt?.toISOString()}`
+          : `Application "${activated.name}" activated`,
+    };
+  }
+
+  // ─── Payment Gateway ─────────────────────────────────────────────
+
+  @Post('gateway/initiate')
+  @ApiOperation({ summary: 'Initiate a payment gateway transaction' })
+  async initiateGateway(
+    @Request() req: any,
+    @Body() body: { amount: number; description?: string; callbackUrl: string },
+  ) {
+    assertStubGatewayAllowed();
+    const trackingCode = issueGatewayTrackingCode(req.user.id, body.amount);
+    return {
+      success: true,
+      trackingCode,
+      gatewayUrl: `${body.callbackUrl}?trackingCode=${trackingCode}&amount=${body.amount}&status=success`,
+      message: 'Redirect user to gatewayUrl to complete payment',
+    };
+  }
+
+  @Post('gateway/verify')
+  @ApiOperation({ summary: 'Verify a payment gateway transaction and charge wallet' })
+  async verifyGateway(
+    @Request() req: any,
+    @Body() body: { trackingCode: string; amount: number },
+  ) {
+    assertStubGatewayAllowed();
+    // The tracking code binds user + amount at initiate time; reject tampered amounts.
+    assertGatewayTrackingCodeValid(body.trackingCode, req.user.id, body.amount);
+    await this.billingService.chargeWallet(
+      req.user.id,
+      body.amount,
+      `Payment gateway: ${body.trackingCode}`,
+    );
+    return {
+      success: true,
+      message: 'Payment verified and wallet charged',
+      trackingCode: body.trackingCode,
+    };
+  }
+}

backend/src/billing/billing.controller.ts

@@ -3,35 +3,27 @@ import {
   Get,
   Post,
   Patch,
-  Delete,
   Body,
   Param,
-  Query,
   UseGuards,
   Request,
   BadRequestException,
   Inject,
   forwardRef,
-  ForbiddenException,
 } from '@nestjs/common';
 import { AuthGuard } from '@nestjs/passport';
 import { ApiTags, ApiOperation, ApiBearerAuth } from '@nestjs/swagger';
 import { BillingService } from './billing.service';
+import { BillingOpsService } from './billing-ops.service';
 import { AppLifecycleService } from '../lifecycle/app-lifecycle.service';
 import { ApplicationsService } from '../applications/applications.service';
-import { KubernetesService } from '../kubernetes/kubernetes.service';
 import {
-  ChargeWalletDto,
   CalculateCostDto,
   CalculateDeployCostDto,
   SetOptionalServicesPricingDto,
   RenewApplicationDto,
   UpgradeResourcesDto,
   CalculateUpgradeCostDto,
-  InitiateInvoicePaymentDto,
-  VerifyInvoiceGatewayDto,
-  UpdateInvoiceStatusDto,
-  PayApplicationDto,
 } from './dto/billing.dto';
 import { UpdatePricingCatalogDto } from './dto/pricing-catalog.dto';
 import { RolesGuard } from '../common/guards/roles.guard';
@@ -41,12 +33,7 @@ import {
   BillingCycle,
   AppLifecycleStatus,
   InvoiceReason,
-  InvoiceStatus,
-  PaymentMethod,
-  ProductType,
-  DatabaseType,
 } from '../common/enums';
-import { Application } from '../applications/entities/application.entity';
 
 @ApiTags('Billing')
 @ApiBearerAuth()
@@ -55,12 +42,11 @@ import { Application } from '../applications/entities/application.entity';
 export class BillingController {
   constructor(
     private readonly billingService: BillingService,
+    private readonly billingOpsService: BillingOpsService,
     @Inject(forwardRef(() => AppLifecycleService))
     private readonly lifecycleService: AppLifecycleService,
     @Inject(forwardRef(() => ApplicationsService))
     private readonly applicationsService: ApplicationsService,
-    @Inject(forwardRef(() => KubernetesService))
-    private readonly kubernetesService: KubernetesService,
   ) {}
 
   // ─── Pricing catalog (Admin) ──────────────────────────────────────
@@ -98,6 +84,29 @@ export class BillingController {
     return this.billingService.calculateDeployPayment(req.user.id, dto, dto.cycle, dto.couponCode);
   }
 
+  // ─── Global discount (platform-wide) ───────────────────────────
+
+  @Get('settings/global-discount')
+  @ApiOperation({ summary: 'Get the platform-wide discount percentage' })
+  async getGlobalDiscount() {
+    return this.billingService.getGlobalDiscount();
+  }
+
+  @Patch('settings/global-discount')
+  @Roles(UserRole.ADMIN)
+  @ApiOperation({ summary: 'Set the platform-wide discount percentage (Admin)' })
+  async setGlobalDiscount(@Body() body: { percentOff: number }) {
+    if (
+      body.percentOff === undefined ||
+      typeof body.percentOff !== 'number' ||
+      body.percentOff < 0 ||
+      body.percentOff > 100
+    ) {
+      throw new BadRequestException('percentOff must be a number between 0 and 100');
+    }
+    return this.billingService.setGlobalDiscount(body.percentOff);
+  }
+
   // ─── Custom Domain Pricing ─────────────────────────────────────
 
   @Get('settings/custom-domain-price')
@@ -129,274 +138,6 @@ export class BillingController {
     return this.billingService.setOptionalServicesPricing(dto);
   }
 
-  // ─── Wallet (User) ───────────────────────────────────────────────
-
-  @Get('wallet')
-  @ApiOperation({ summary: 'Get my wallet balance' })
-  async getBalance(@Request() req: any) {
-    return this.billingService.getBalance(req.user.id);
-  }
-
-  @Post('wallet/charge')
-  @ApiOperation({ summary: 'Charge my wallet (self top-up)' })
-  async chargeMyWallet(@Request() req: any, @Body() dto: ChargeWalletDto) {
-    return this.billingService.chargeWallet(req.user.id, dto.amount, dto.description || 'Self top-up');
-  }
-
-  @Get('wallet/transactions')
-  @ApiOperation({ summary: 'Get my wallet transactions' })
-  async getTransactions(@Request() req: any, @Query('limit') limit?: string) {
-    return this.billingService.getTransactions(req.user.id, limit ? parseInt(limit, 10) : 50);
-  }
-
-  @Get('resource-credits')
-  @ApiOperation({ summary: 'List active prepaid resource credits (from deleted apps)' })
-  async getResourceCredits(@Request() req: any) {
-    const credits = await this.billingService.getActiveCredits(req.user.id);
-    return credits.map((c) => this.billingService.formatCreditForApi(c));
-  }
-
-  // ─── Invoices ─────────────────────────────────────────────────────
-
-  @Get('invoices')
-  @ApiOperation({ summary: 'List my invoices' })
-  async listMyInvoices(
-    @Request() req: any,
-    @Query('status') status?: InvoiceStatus,
-    @Query('applicationId') applicationId?: string,
-    @Query('limit') limit?: string,
-  ) {
-    return this.billingService.listInvoices(req.user, {
-      status,
-      applicationId,
-      limit: limit ? parseInt(limit, 10) : undefined,
-    });
-  }
-
-  @Get('invoices/:id')
-  @ApiOperation({ summary: 'Get one invoice with line items and transactions' })
-  async getInvoice(@Request() req: any, @Param('id') id: string) {
-    return this.billingService.getInvoiceForUser(id, req.user);
-  }
-
-  @Post('invoices/:id/pay/mixed')
-  @ApiOperation({ summary: 'Pay invoice with wallet first, then gateway for the remaining amount' })
-  async initiateInvoiceMixed(
-    @Request() req: any,
-    @Param('id') id: string,
-    @Body() dto: InitiateInvoicePaymentDto,
-  ) {
-    const result = await this.billingService.initiateInvoiceMixedPayment(id, req.user, dto.callbackUrl);
-    const effect = await this.completePaidInvoiceEffect(result.invoice);
-    return { ...result, effect };
-  }
-
-  @Post('invoices/:id/gateway/verify')
-  @ApiOperation({ summary: 'Verify invoice gateway payment' })
-  async verifyInvoiceGateway(
-    @Request() req: any,
-    @Param('id') id: string,
-    @Body() dto: VerifyInvoiceGatewayDto,
-  ) {
-    const result = await this.billingService.verifyInvoiceGatewayPayment(
-      id,
-      req.user,
-      dto.trackingCode,
-      dto.amount,
-    );
-    const effect = await this.completePaidInvoiceEffect(result.invoice);
-    return { ...result, effect };
-  }
-
-  @Post('wallet/pay/:applicationId')
-  @ApiOperation({ summary: 'Pay for an application plan from wallet — activates/renews the app' })
-  async payForApplication(
-    @Request() req: any,
-    @Param('applicationId') applicationId: string,
-    @Body() body: PayApplicationDto,
-  ) {
-    const cycle = body.cycle as BillingCycle;
-    if (!Object.values(BillingCycle).includes(cycle)) {
-      throw new BadRequestException(`Invalid billing cycle: ${body.cycle}`);
-    }
-
-    const app = await this.applicationsService.findOne(applicationId, req.user.id);
-
-    const payment = await this.billingService.resolveAppPayment(
-      req.user.id,
-      app,
-      cycle,
-    );
-
-    const coupon = await this.billingService.resolveCoupon(
-      req.user.id,
-      body.couponCode,
-      await this.billingService.getAppChargeBreakdown(app),
-      cycle,
-      payment.amountDue,
-    );
-
-    let invoice = null;
-    if (payment.amountDue > 0) {
-      invoice = await this.billingService.createInvoice({
-        userId: req.user.id,
-        applicationId: app.id,
-        reason: InvoiceReason.DEPLOY,
-        lines: [
-          {
-            label: `Application payment: ${app.name}`,
-            description: `Billing cycle: ${cycle}`,
-            amount: payment.amountDue,
-            metadata: {
-              cycle,
-              waivedAmount: payment.waivedAmount,
-              creditApplied: payment.creditId || null,
-            },
-          },
-        ],
-        metadata: {
-          action: 'activate',
-          cycle,
-        },
-        discount: coupon ?? undefined,
-      });
-    }
-
-    let tx = null;
-    if (invoice) {
-      const paid = await this.billingService.payInvoiceWithWallet(invoice.id, req.user);
-      tx = paid.transaction;
-      invoice = paid.invoice;
-    }
-
-    const activated = await this.lifecycleService.activateApp(
-      applicationId,
-      cycle,
-    );
-
-    return {
-      transaction: tx,
-      invoice,
-      creditApplied: payment.creditId || null,
-      waivedAmount: payment.waivedAmount,
-      discountAmount: coupon?.amount ?? 0,
-      discountCode: coupon?.code ?? null,
-      paidAmount: invoice ? Number(invoice.total) : 0,
-      application: {
-        id: activated.id,
-        name: activated.name,
-        lifecycleStatus: activated.lifecycleStatus,
-        planExpiresAt: activated.planExpiresAt,
-      },
-      message: payment.waivedAmount > 0
-        ? payment.amountDue > 0
-          ? `Application "${activated.name}" activated — prepaid credit applied; you paid ${payment.amountDue} Toman for additional services.`
-          : `Application "${activated.name}" activated using your prepaid resource credit (no charge).`
-        : payment.amountDue > 0
-          ? `Application "${activated.name}" activated until ${activated.planExpiresAt?.toISOString()}`
-          : `Application "${activated.name}" activated`,
-    };
-  }
-
-  // ─── Payment Gateway ─────────────────────────────────────────────
-
-  @Post('gateway/initiate')
-  @ApiOperation({ summary: 'Initiate a payment gateway transaction' })
-  async initiateGateway(
-    @Request() req: any,
-    @Body() body: { amount: number; description?: string; callbackUrl: string },
-  ) {
-    // In production, integrate with Zarinpal/IDPay/etc.
-    // For now, simulate a gateway redirect URL.
-    const trackingCode = `PAY-${Date.now()}-${Math.random().toString(36).substring(2, 8).toUpperCase()}`;
-    return {
-      success: true,
-      trackingCode,
-      gatewayUrl: `${body.callbackUrl}?trackingCode=${trackingCode}&amount=${body.amount}&status=success`,
-      message: 'Redirect user to gatewayUrl to complete payment',
-    };
-  }
-
-  @Post('gateway/verify')
-  @ApiOperation({ summary: 'Verify a payment gateway transaction and charge wallet' })
-  async verifyGateway(
-    @Request() req: any,
-    @Body() body: { trackingCode: string; amount: number },
-  ) {
-    // In production, verify with the gateway provider.
-    // For now, auto-approve and charge the wallet.
-    await this.billingService.chargeWallet(
-      req.user.id,
-      body.amount,
-      `Payment gateway: ${body.trackingCode}`,
-    );
-    return {
-      success: true,
-      message: 'Payment verified and wallet charged',
-      trackingCode: body.trackingCode,
-    };
-  }
-
-  // ─── Invoice Admin ────────────────────────────────────────────────
-
-  @Get('admin/invoices')
-  @Roles(UserRole.ADMIN)
-  @ApiOperation({ summary: 'List all invoices (Admin)' })
-  async listAdminInvoices(
-    @Request() req: any,
-    @Query('status') status?: InvoiceStatus,
-    @Query('userId') userId?: string,
-    @Query('applicationId') applicationId?: string,
-    @Query('paymentMethod') paymentMethod?: PaymentMethod,
-    @Query('search') search?: string,
-    @Query('limit') limit?: string,
-  ) {
-    return this.billingService.listInvoices(req.user, {
-      status,
-      userId,
-      applicationId,
-      paymentMethod,
-      search,
-      limit: limit ? parseInt(limit, 10) : undefined,
-    });
-  }
-
-  @Get('admin/invoices/:id')
-  @Roles(UserRole.ADMIN)
-  @ApiOperation({ summary: 'Get invoice details (Admin)' })
-  async getAdminInvoice(@Request() req: any, @Param('id') id: string) {
-    return this.billingService.getInvoiceForUser(id, req.user);
-  }
-
-  @Patch('admin/invoices/:id/status')
-  @Roles(UserRole.ADMIN)
-  @ApiOperation({ summary: 'Update invoice status with reason (Admin)' })
-  async updateAdminInvoiceStatus(
-    @Param('id') id: string,
-    @Body() dto: UpdateInvoiceStatusDto,
-  ) {
-    return this.billingService.updateInvoiceStatus(id, dto.status, dto.reason);
-  }
-
-  // ─── Wallet Admin ─────────────────────────────────────────────────
-
-  @Get('admin/wallets')
-  @Roles(UserRole.ADMIN)
-  @ApiOperation({ summary: 'List all wallets (Admin)' })
-  async getAllWallets() {
-    return this.billingService.getAllWallets();
-  }
-
-  @Post('admin/wallets/:userId/charge')
-  @Roles(UserRole.ADMIN)
-  @ApiOperation({ summary: 'Charge a user\'s wallet (Admin)' })
-  async adminChargeWallet(
-    @Param('userId') userId: string,
-    @Body() dto: ChargeWalletDto,
-  ) {
-    return this.billingService.adminChargeWallet(userId, dto.amount, dto.description);
-  }
-
   // ─── Application Renewal ──────────────────────────────────────────
 
   @Get('applications/:applicationId/renewal-cost')
@@ -405,8 +146,7 @@ export class BillingController {
     @Request() req: any,
     @Param('applicationId') applicationId: string,
   ) {
-    // User can only view their own app, admin/sales can view any
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
-    const app = await this.getAppWithAccess(req.user, applicationId);
     const costs = await this.billingService.calculateRenewalCost(app);
     return {
       applicationId: app.id,
@@ -425,7 +165,7 @@ export class BillingController {
     @Param('applicationId') applicationId: string,
     @Body() dto: RenewApplicationDto,
   ) {
-    const app = await this.getAppWithAccess(req.user, applicationId);
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
     const costs = await this.billingService.calculateRenewalCost(app);
     const amount = dto.cycle === BillingCycle.HOURLY ? costs.hourly
       : dto.cycle === BillingCycle.MONTHLY ? costs.monthly
@@ -467,10 +207,8 @@ export class BillingController {
     @Param('applicationId') applicationId: string,
     @Body() dto: RenewApplicationDto,
   ) {
-    // User can only renew their own app, admin/sales can renew any
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
-    const app = await this.getAppWithAccess(req.user, applicationId);
 
-    // Calculate cost for the selected cycle
     const costs = await this.billingService.calculateRenewalCost(app);
     const amount = dto.cycle === BillingCycle.HOURLY ? costs.hourly
       : dto.cycle === BillingCycle.MONTHLY ? costs.monthly
@@ -510,7 +248,6 @@ export class BillingController {
 
     const paid = await this.billingService.payInvoiceWithWallet(invoice.id, req.user);
 
-    // Activate the application
     const renewedApp = await this.lifecycleService.activateApp(app.id, dto.cycle);
 
     return {
@@ -544,7 +281,6 @@ export class BillingController {
     }
 
     if (body.bypassPayment) {
-      // Direct activation without payment (for special cases, support, etc.)
       const renewedApp = await this.lifecycleService.activateApp(app.id, cycle);
       return {
         success: true,
@@ -560,7 +296,6 @@ export class BillingController {
       };
     }
 
-    // Normal renewal - deduct from app owner's wallet
     const costs = await this.billingService.calculateRenewalCost(app);
     const amount = cycle === BillingCycle.HOURLY ? costs.hourly
       : cycle === BillingCycle.MONTHLY ? costs.monthly
@@ -617,7 +352,7 @@ export class BillingController {
     @Param('applicationId') applicationId: string,
     @Body() dto: CalculateUpgradeCostDto,
   ) {
-    const app = await this.getAppWithAccess(req.user, applicationId);
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
     const result = await this.billingService.calculateUpgradeCost(app, dto);
 
     return {
@@ -652,7 +387,7 @@ export class BillingController {
     @Param('applicationId') applicationId: string,
     @Body() dto: UpgradeResourcesDto,
   ) {
-    const app = await this.getAppWithAccess(req.user, applicationId);
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
     if (app.lifecycleStatus !== AppLifecycleStatus.ACTIVE) {
       throw new BadRequestException(
         `Cannot upgrade resources for ${app.lifecycleStatus} application. Please renew first.`,
@@ -704,20 +439,17 @@ export class BillingController {
     @Param('applicationId') applicationId: string,
     @Body() dto: UpgradeResourcesDto,
   ) {
-    const app = await this.getAppWithAccess(req.user, applicationId);
+    const app = await this.billingOpsService.getAppWithAccess(req.user, applicationId);
 
-    // Application must be active to upgrade
     if (app.lifecycleStatus !== AppLifecycleStatus.ACTIVE) {
       throw new BadRequestException(
         `Cannot upgrade resources for ${app.lifecycleStatus} application. Please renew first.`
       );
     }
 
-    // Calculate upgrade cost
     const costResult = await this.billingService.calculateUpgradeCost(app, dto);
     let paidInvoice = null;
 
-    // If upgrading (positive difference), require payment
     if (costResult.proratedAmount > 0) {
       const walletUserId = req.user.role === UserRole.ADMIN || req.user.role === UserRole.SALES
         ? app.userId
@@ -761,11 +493,11 @@ export class BillingController {
     const updatedApp = await this.applicationsService.update(
       app.id,
       app.userId,
-      this.buildUpgradeEntityPatch(app, dto),
+      this.billingOpsService.buildUpgradeEntityPatch(app, dto),
     );
 
     try {
-      await this.applyUpgradeToKubernetes(updatedApp, dto, app);
+      await this.billingOpsService.applyUpgradeToKubernetes(updatedApp, dto, app);
     } catch (e: any) {
       console.warn(`K8s resource update failed for ${app.name}: ${e.message}`);
     }
@@ -790,238 +522,4 @@ export class BillingController {
         : 'Resources updated (downgrade or no cost change).',
     };
   }
-
-  // ─── Helper Methods ───────────────────────────────────────────────
-
-  private async completePaidInvoiceEffect(invoice: any) {
-    if (invoice.status !== InvoiceStatus.PAID) return null;
-    if (invoice.metadata?.completedAt) return invoice.metadata.completionResult || null;
-
-    const action = invoice.metadata?.action;
-    if (!action || !invoice.applicationId) return null;
-
-    if (action === 'renew' || action === 'activate') {
-      const cycle = invoice.metadata?.cycle as BillingCycle;
-      if (!Object.values(BillingCycle).includes(cycle)) return null;
-
-      const activated = await this.lifecycleService.activateApp(invoice.applicationId, cycle);
-      const result = {
-        action,
-        application: {
-          id: activated.id,
-          name: activated.name,
-          lifecycleStatus: activated.lifecycleStatus,
-          planExpiresAt: activated.planExpiresAt,
-          billingCycle: activated.billingCycle,
-        },
-      };
-      await this.billingService.markInvoiceEffectCompleted(invoice.id, result);
-      return result;
-    }
-
-    if (action === 'upgrade') {
-      const app = await this.applicationsService.findOne(invoice.applicationId);
-      const resources = (invoice.metadata?.resources || {}) as UpgradeResourcesDto;
-      const updatedApp = await this.applicationsService.update(
-        app.id,
-        app.userId,
-        this.buildUpgradeEntityPatch(app, resources),
-      );
-
-      try {
-        await this.applyUpgradeToKubernetes(updatedApp, resources, app);
-      } catch (e: any) {
-        console.warn(`K8s resource update failed for ${app.name}: ${e.message}`);
-      }
-
-      const result = {
-        action,
-        application: {
-          id: updatedApp.id,
-          name: updatedApp.name,
-          cpuRequest: updatedApp.cpuRequest,
-          cpuLimit: updatedApp.cpuLimit,
-          memoryRequest: updatedApp.memoryRequest,
-          memoryLimit: updatedApp.memoryLimit,
-          replicas: updatedApp.replicas,
-        },
-      };
-      await this.billingService.markInvoiceEffectCompleted(invoice.id, result);
-      return result;
-    }
-
-    return null;
-  }
-
-  private buildUpgradeEntityPatch(app: Application, dto: UpgradeResourcesDto): Partial<Application> {
-    const pt = app.productType ?? ProductType.APPLICATION;
-
-    if (dto.redisResources) {
-      return {
-        optionalServiceResources: {
-          ...app.optionalServiceResources,
-          redis: {
-            ...app.optionalServiceResources?.redis,
-            ...dto.redisResources,
-            storageGi:
-              dto.redisResources.storageGi ?? app.optionalServiceResources?.redis?.storageGi ?? 1,
-          },
-        },
-      };
-    }
-
-    if (dto.rabbitmqResources) {
-      return {
-        optionalServiceResources: {
-          ...app.optionalServiceResources,
-          rabbitmq: {
-            ...app.optionalServiceResources?.rabbitmq,
-            ...dto.rabbitmqResources,
-            storageGi:
-              dto.rabbitmqResources.storageGi ??
-              app.optionalServiceResources?.rabbitmq?.storageGi ??
-              2,
-          },
-        },
-      };
-    }
-
-    if (pt === ProductType.MANAGED_REDIS || pt === ProductType.MANAGED_RABBITMQ) {
-      return {};
-    }
-
-    return {
-      cpuRequest: dto.cpuRequest || app.cpuRequest,
-      cpuLimit: dto.cpuLimit || app.cpuLimit,
-      memoryRequest: dto.memoryRequest || app.memoryRequest,
-      memoryLimit: dto.memoryLimit || app.memoryLimit,
-      replicas: dto.replicas ?? app.replicas,
-      dbStorageSize: dto.dbStorageSize || app.dbStorageSize,
-      appStorageSize: dto.appStorageSize || app.appStorageSize,
-    };
-  }
-
-  private async applyUpgradeToKubernetes(
-    app: Application,
-    dto: UpgradeResourcesDto,
-    previous: Application,
-  ): Promise<void> {
-    const pt = app.productType ?? ProductType.APPLICATION;
-
-    if (pt === ProductType.MANAGED_DATABASE) {
-      await this.kubernetesService.updateResources(
-        app,
-        {
-          cpuRequest: dto.cpuRequest,
-          cpuLimit: dto.cpuLimit,
-          memoryRequest: dto.memoryRequest,
-          memoryLimit: dto.memoryLimit,
-        },
-        'database',
-      );
-      if (dto.dbStorageSize && dto.dbStorageSize !== previous.dbStorageSize) {
-        const resize = await this.kubernetesService.resizeDatabasePvc(app, dto.dbStorageSize);
-        if (!resize.success) {
-          throw new BadRequestException(resize.message);
-        }
-      }
-      return;
-    }
-
-    if (pt === ProductType.MANAGED_REDIS) {
-      await this.applyOptionalServiceUpgrade(app, dto, previous, 'redis');
-      return;
-    }
-
-    if (pt === ProductType.MANAGED_RABBITMQ) {
-      await this.applyOptionalServiceUpgrade(app, dto, previous, 'rabbitmq');
-      return;
-    }
-
-    if (dto.redisResources && app.enableRedis) {
-      await this.applyOptionalServiceUpgrade(app, dto, previous, 'redis');
-    }
-
-    if (dto.rabbitmqResources && app.enableRabbitmq) {
-      await this.applyOptionalServiceUpgrade(app, dto, previous, 'rabbitmq');
-    }
-
-    const touchesAppWorkload =
-      dto.cpuRequest !== undefined ||
-      dto.cpuLimit !== undefined ||
-      dto.memoryRequest !== undefined ||
-      dto.memoryLimit !== undefined ||
-      dto.replicas !== undefined;
-
-    if (touchesAppWorkload) {
-      await this.kubernetesService.updateResources(app, {
-        cpuRequest: dto.cpuRequest,
-        cpuLimit: dto.cpuLimit,
-        memoryRequest: dto.memoryRequest,
-        memoryLimit: dto.memoryLimit,
-        replicas: dto.replicas,
-      });
-    }
-
-    if (dto.appStorageSize && dto.appStorageSize !== previous.appStorageSize) {
-      await this.kubernetesService.resizeAppStoragePvc(app, dto.appStorageSize);
-    }
-
-    if (
-      dto.dbStorageSize &&
-      dto.dbStorageSize !== previous.dbStorageSize &&
-      previous.databaseType &&
-      previous.databaseType !== DatabaseType.NONE
-    ) {
-      const resize = await this.kubernetesService.resizeDatabasePvc(app, dto.dbStorageSize);
-      if (!resize.success) {
-        throw new BadRequestException(resize.message);
-      }
-    }
-  }
-
-  private async applyOptionalServiceUpgrade(
-    app: Application,
-    dto: UpgradeResourcesDto,
-    previous: Application,
-    service: 'redis' | 'rabbitmq',
-  ): Promise<void> {
-    const res = app.optionalServiceResources?.[service];
-    const dtoRes = service === 'redis' ? dto.redisResources : dto.rabbitmqResources;
-    if (res) {
-      await this.kubernetesService.updateResources(
-        app,
-        {
-          cpuRequest: res.cpuRequest,
-          cpuLimit: res.cpuLimit,
-          memoryRequest: res.memoryRequest,
-          memoryLimit: res.memoryLimit,
-        },
-        service,
-      );
-    }
-    const prevGi =
-      previous.optionalServiceResources?.[service]?.storageGi ?? (service === 'redis' ? 1 : 2);
-    const nextGi = dtoRes?.storageGi;
-    if (nextGi != null && nextGi > prevGi) {
-      const resize =
-        service === 'redis'
-          ? await this.kubernetesService.resizeRedisStoragePvc(app, `${nextGi}Gi`)
-          : await this.kubernetesService.resizeRabbitmqStoragePvc(app, `${nextGi}Gi`);
-      if (!resize.success) {
-        throw new BadRequestException(resize.message);
-      }
-    }
-  }
-
-  private async getAppWithAccess(user: any, applicationId: string) {
-    const isAdminOrSales = user.role === UserRole.ADMIN || user.role === UserRole.SALES;
-    
-    if (isAdminOrSales) {
-      return this.applicationsService.findOne(applicationId);
-    }
-    
-    // Regular user - must own the app
-    return this.applicationsService.findOne(applicationId, user.id);
-  }
 }

backend/src/billing/billing.module.ts

@@ -1,7 +1,11 @@
 import { Module, forwardRef } from '@nestjs/common';
 import { TypeOrmModule } from '@nestjs/typeorm';
 import { BillingService } from './billing.service';
+import { BillingOpsService } from './billing-ops.service';
 import { BillingController } from './billing.controller';
+import { BillingWalletController } from './billing-wallet.controller';
+import { BillingInvoicesController } from './billing-invoices.controller';
+import { PublicPricingController } from './public-pricing.controller';
 import { DiscountController } from './discount.controller';
 import { DiscountService } from './discount.service';
 import { PricingCatalogService } from './pricing-catalog.service';
@@ -9,6 +13,7 @@ import { PricingRate } from './entities/pricing-rate.entity';
 import { AddonRate } from './entities/addon-rate.entity';
 import { OptionalServiceProfile } from './entities/optional-service-profile.entity';
 import { OptionalServiceRate } from './entities/optional-service-rate.entity';
+import { PlatformSetting } from './entities/platform-setting.entity';
 import { Wallet } from './entities/wallet.entity';
 import { WalletTransaction } from './entities/wallet-transaction.entity';
 import { ResourceCredit } from './entities/resource-credit.entity';
@@ -34,13 +39,20 @@ import { KubernetesModule } from '../kubernetes/kubernetes.module';
       InvoiceLine,
       Discount,
       DiscountRedemption,
+      PlatformSetting,
     ]),
     forwardRef(() => LifecycleModule),
     forwardRef(() => ApplicationsModule),
     forwardRef(() => KubernetesModule),
   ],
-  controllers: [BillingController, DiscountController],
+  controllers: [
-  providers: [BillingService, PricingCatalogService, DiscountService],
+    BillingController,
-  exports: [BillingService, PricingCatalogService, DiscountService],
+    BillingWalletController,
+    BillingInvoicesController,
+    PublicPricingController,
+    DiscountController,
+  ],
+  providers: [BillingService, BillingOpsService, PricingCatalogService, DiscountService],
+  exports: [BillingService, BillingOpsService, PricingCatalogService, DiscountService],
 })
 export class BillingModule {}

backend/src/billing/billing.service.ts

@@ -1,6 +1,6 @@
 import { Injectable, Logger, BadRequestException, NotFoundException, ForbiddenException } from '@nestjs/common';
 import { InjectRepository } from '@nestjs/typeorm';
-import { Repository, IsNull, MoreThan, FindOptionsWhere } from 'typeorm';
+import { Repository, IsNull, MoreThan, FindOptionsWhere, EntityManager } from 'typeorm';
 import { Wallet } from './entities/wallet.entity';
 import { WalletTransaction } from './entities/wallet-transaction.entity';
 import { Invoice } from './entities/invoice.entity';
@@ -48,6 +48,18 @@ export class BillingService {
     return this.pricingCatalog.updateCatalog(dto);
   }
 
+  // ─── Global (platform-wide) discount ──────────────────────────────
+
+  /** Current platform-wide discount percentage (0–100). */
+  async getGlobalDiscount(): Promise<{ percentOff: number }> {
+    return { percentOff: await this.pricingCatalog.getGlobalDiscountPercent(true) };
+  }
+
+  /** Set the platform-wide discount percentage (Admin). */
+  async setGlobalDiscount(percentOff: number): Promise<{ percentOff: number }> {
+    return { percentOff: await this.pricingCatalog.setGlobalDiscountPercent(percentOff) };
+  }
+
   // ─── Cost Calculation ─────────────────────────────────────────────
 
   /**
@@ -160,6 +172,32 @@ export class BillingService {
     return { balance: Number(wallet.balance) };
   }
 
+  /**
+   * Load the user's wallet inside a transaction with a row-level lock
+   * (SELECT ... FOR UPDATE) so concurrent charge/deduct operations serialize
+   * instead of racing on read-modify-write.
+   */
+  private async lockWallet(em: EntityManager, userId: string): Promise<Wallet> {
+    let wallet = await em.getRepository(Wallet).findOne({
+      where: { userId },
+      lock: { mode: 'pessimistic_write' },
+    });
+    if (!wallet) {
+      // First-time wallet creation may race; the unique userId column makes
+      // one insert win — re-read with the lock afterwards.
+      try {
+        await em.getRepository(Wallet).insert({ userId, balance: 0 });
+      } catch {
+        /* concurrent insert won — fall through to locked re-read */
+      }
+      wallet = await em.getRepository(Wallet).findOneOrFail({
+        where: { userId },
+        lock: { mode: 'pessimistic_write' },
+      });
+    }
+    return wallet;
+  }
+
   async chargeWallet(
     userId: string,
     amount: number,
@@ -168,11 +206,12 @@ export class BillingService {
   ): Promise<WalletTransaction> {
     if (amount <= 0) throw new BadRequestException('Amount must be positive');
 
-    const wallet = await this.getOrCreateWallet(userId);
+    const saved = await this.walletRepo.manager.transaction(async (em) => {
+      const wallet = await this.lockWallet(em, userId);
       wallet.balance = Number(wallet.balance) + amount;
-    await this.walletRepo.save(wallet);
+      await em.getRepository(Wallet).save(wallet);
 
-    const tx = this.txRepo.create({
+      const tx = em.getRepository(WalletTransaction).create({
         walletId: wallet.id,
         type: TransactionType.CHARGE,
         amount,
@@ -180,9 +219,10 @@ export class BillingService {
         description: description || 'Wallet charge',
         invoiceId,
       });
-    const saved = await this.txRepo.save(tx);
+      return em.getRepository(WalletTransaction).save(tx);
+    });
 
-    this.logger.log(`Charged wallet of user ${userId}: +${amount} Toman → balance: ${wallet.balance}`);
+    this.logger.log(`Charged wallet of user ${userId}: +${amount} Toman → balance: ${saved.balanceAfter}`);
     return saved;
   }
 
@@ -195,15 +235,16 @@ export class BillingService {
   ): Promise<WalletTransaction> {
     if (amount <= 0) throw new BadRequestException('Amount must be positive');
 
-    const wallet = await this.getOrCreateWallet(userId);
+    const saved = await this.walletRepo.manager.transaction(async (em) => {
+      const wallet = await this.lockWallet(em, userId);
       if (Number(wallet.balance) < amount) {
         throw new BadRequestException('Insufficient wallet balance');
       }
 
       wallet.balance = Number(wallet.balance) - amount;
-    await this.walletRepo.save(wallet);
+      await em.getRepository(Wallet).save(wallet);
 
-    const tx = this.txRepo.create({
+      const tx = em.getRepository(WalletTransaction).create({
         walletId: wallet.id,
         type: TransactionType.DEDUCTION,
         amount,
@@ -212,9 +253,10 @@ export class BillingService {
         applicationId,
         invoiceId,
       });
-    const saved = await this.txRepo.save(tx);
+      return em.getRepository(WalletTransaction).save(tx);
+    });
 
-    this.logger.log(`Deducted from wallet of user ${userId}: -${amount} Toman → balance: ${wallet.balance}`);
+    this.logger.log(`Deducted from wallet of user ${userId}: -${amount} Toman → balance: ${saved.balanceAfter}`);
     return saved;
   }
 
@@ -731,7 +773,9 @@ export class BillingService {
       yearly: newCost.yearly - currentCost.yearly,
     };
 
-    // Calculate prorated amount based on remaining time in billing period
+    // Calculate prorated amount based on remaining time in billing period.
+    // Use the price difference of the app's own billing cycle scaled by the
+    // fraction of the cycle that remains — not the hourly rate for all cycles.
     let proratedAmount = 0;
     let remainingHours = 0;
 
@@ -740,9 +784,18 @@ export class BillingService {
       const expiresAt = new Date(app.planExpiresAt);
       remainingHours = Math.max(0, (expiresAt.getTime() - now.getTime()) / (1000 * 60 * 60));
 
+      const cycleDifference = this.amountForCycle(difference, app.billingCycle);
+      const cycleHours =
+        app.billingCycle === BillingCycle.HOURLY
+          ? 1
+          : app.billingCycle === BillingCycle.MONTHLY
+            ? 30 * 24
+            : 365 * 24;
+
       // Only charge difference if upgrading (not downgrading)
-      if (difference.hourly > 0) {
+      if (cycleDifference > 0) {
-        proratedAmount = Math.ceil(difference.hourly * remainingHours);
+        const remainingFraction = Math.min(1, remainingHours / cycleHours);
+        proratedAmount = Math.ceil(cycleDifference * remainingFraction);
       }
     }
 

backend/src/billing/payment-gateway.util.spec.ts

@@ -0,0 +1,32 @@
+import { ForbiddenException } from '@nestjs/common';
+import { assertStubGatewayAllowed } from './payment-gateway.util';
+
+describe('assertStubGatewayAllowed', () => {
+  const env = process.env;
+
+  beforeEach(() => {
+    process.env = { ...env };
+  });
+
+  afterAll(() => {
+    process.env = env;
+  });
+
+  it('allows in development', () => {
+    process.env.NODE_ENV = 'development';
+    delete process.env.PAYMENT_GATEWAY_STUB_ENABLED;
+    expect(() => assertStubGatewayAllowed()).not.toThrow();
+  });
+
+  it('blocks in production by default', () => {
+    process.env.NODE_ENV = 'production';
+    delete process.env.PAYMENT_GATEWAY_STUB_ENABLED;
+    expect(() => assertStubGatewayAllowed()).toThrow(ForbiddenException);
+  });
+
+  it('allows in production when explicitly enabled for staging', () => {
+    process.env.NODE_ENV = 'production';
+    process.env.PAYMENT_GATEWAY_STUB_ENABLED = 'true';
+    expect(() => assertStubGatewayAllowed()).not.toThrow();
+  });
+});

backend/src/billing/payment-gateway.util.ts

@@ -0,0 +1,61 @@
+import { BadRequestException, ForbiddenException } from '@nestjs/common';
+import { createHmac, timingSafeEqual } from 'node:crypto';
+
+/**
+ * Stub gateway endpoints auto-approve payments without a real provider.
+ * Disabled in production unless PAYMENT_GATEWAY_STUB_ENABLED=true (staging only).
+ */
+export function assertStubGatewayAllowed(): void {
+  if (
+    process.env.NODE_ENV === 'production' &&
+    process.env.PAYMENT_GATEWAY_STUB_ENABLED !== 'true'
+  ) {
+    throw new ForbiddenException('Payment gateway is not configured');
+  }
+}
+
+function gatewaySigningSecret(): string {
+  return (
+    process.env.PAYMENT_GATEWAY_SIGNING_SECRET ||
+    process.env.JWT_SECRET ||
+    'default-jwt-secret'
+  );
+}
+
+function hmacSignature(payload: string): string {
+  return createHmac('sha256', gatewaySigningSecret()).update(payload).digest('hex').slice(0, 24);
+}
+
+/**
+ * Issue a tracking code that cryptographically binds the initiating user and
+ * amount, so `verify` cannot be replayed with a different (larger) amount.
+ * Format: PAY-<ts>-<rand>-<hmac(userId|amount|ts|rand)>
+ */
+export function issueGatewayTrackingCode(userId: string, amount: number): string {
+  const ts = Date.now().toString(36);
+  const rand = Math.random().toString(36).substring(2, 8).toUpperCase();
+  const sig = hmacSignature(`${userId}|${amount}|${ts}|${rand}`);
+  return `PAY-${ts}-${rand}-${sig}`;
+}
+
+/**
+ * Validate a tracking code issued by {@link issueGatewayTrackingCode} against
+ * the calling user and the amount being credited. Throws on any mismatch.
+ */
+export function assertGatewayTrackingCodeValid(
+  trackingCode: string,
+  userId: string,
+  amount: number,
+): void {
+  const parts = String(trackingCode || '').split('-');
+  if (parts.length !== 4 || parts[0] !== 'PAY') {
+    throw new BadRequestException('Invalid gateway tracking code');
+  }
+  const [, ts, rand, sig] = parts;
+  const expected = hmacSignature(`${userId}|${amount}|${ts}|${rand}`);
+  const a = Buffer.from(sig);
+  const b = Buffer.from(expected);
+  if (a.length !== b.length || !timingSafeEqual(a, b)) {
+    throw new BadRequestException('Gateway tracking code does not match the payment details');
+  }
+}

backend/src/billing/pricing-catalog.service.spec.ts

@@ -5,6 +5,7 @@ import { PricingRate } from './entities/pricing-rate.entity';
 import { AddonRate } from './entities/addon-rate.entity';
 import { OptionalServiceProfile } from './entities/optional-service-profile.entity';
 import { OptionalServiceRate } from './entities/optional-service-rate.entity';
+import { PlatformSetting } from './entities/platform-setting.entity';
 import {
   AppRuntime,
   BillingCycle,
@@ -47,6 +48,13 @@ describe('PricingCatalogService', () => {
     create: jest.fn().mockImplementation((x) => x),
   };
 
+  const settingsRepo = {
+    find: jest.fn().mockResolvedValue([]),
+    findOne: jest.fn().mockResolvedValue(null),
+    save: jest.fn().mockImplementation((x) => Promise.resolve(x)),
+    create: jest.fn().mockImplementation((x) => x),
+  };
+
   beforeEach(async () => {
     jest.clearAllMocks();
     const module: TestingModule = await Test.createTestingModule({
@@ -56,6 +64,7 @@ describe('PricingCatalogService', () => {
         { provide: getRepositoryToken(AddonRate), useValue: addonRepo },
         { provide: getRepositoryToken(OptionalServiceProfile), useValue: optionalProfileRepo },
         { provide: getRepositoryToken(OptionalServiceRate), useValue: optionalRateRepo },
+        { provide: getRepositoryToken(PlatformSetting), useValue: settingsRepo },
       ],
     }).compile();
 

backend/src/billing/pricing-catalog.service.ts

@@ -5,6 +5,7 @@ import { PricingRate } from './entities/pricing-rate.entity';
 import { AddonRate } from './entities/addon-rate.entity';
 import { OptionalServiceProfile } from './entities/optional-service-profile.entity';
 import { OptionalServiceRate } from './entities/optional-service-rate.entity';
+import { PlatformSetting } from './entities/platform-setting.entity';
 import {
   AppRuntime,
   BillingCycle,
@@ -39,12 +40,22 @@ import {
 } from './dto/pricing-catalog.dto';
 import { OptionalServiceResourcesDto } from './dto/optional-service-resources.dto';
 
+/** PlatformSetting key holding the platform-wide discount percentage (0–100). */
+export const GLOBAL_DISCOUNT_SETTING_KEY = 'global_discount_percent';
+
 export interface CyclePrices {
   hourly: number;
   monthly: number;
   yearly: number;
 }
 
+export interface CostTotals {
+  hourly: number;
+  monthly: number;
+  yearly: number;
+  breakdown: CostBreakdownLine[];
+}
+
 export interface PricingRateRow {
   resourceType: PricingResourceType;
   hourlyPrice: number;
@@ -129,10 +140,18 @@ export class PricingCatalogService implements OnModuleInit {
     private readonly optionalProfileRepo: Repository<OptionalServiceProfile>,
     @InjectRepository(OptionalServiceRate)
     private readonly optionalRateRepo: Repository<OptionalServiceRate>,
+    @InjectRepository(PlatformSetting)
+    private readonly settingsRepo: Repository<PlatformSetting>,
   ) {}
 
+  /** In-memory cache of the global discount % (TTL-refreshed; single-replica safe). */
+  private cachedGlobalDiscountPct = 0;
+  private cachedGlobalDiscountAt = 0;
+  private static readonly GLOBAL_DISCOUNT_TTL_MS = 30_000;
+
   async onModuleInit() {
     await this.ensureDefaults();
+    await this.getGlobalDiscountPercent(true);
   }
 
   async ensureDefaults() {
@@ -337,13 +356,89 @@ export class PricingCatalogService implements OnModuleInit {
     };
   }
 
-  async computeTotalsFromDb(dto: CalculateCostDto) {
+  /** Raw totals straight from the catalog, before any platform-wide discount. */
+  async computeTotalsRawFromDb(dto: CalculateCostDto): Promise<CostTotals> {
     const runtime = dto.runtime as AppRuntime;
     const rates = await this.getRatesForRuntime(runtime);
     const optional = await this.getOptionalBillingContext();
     return this.computeTotalsWithRates(dto, rates, optional);
   }
 
+  /**
+   * Totals with the platform-wide discount applied. This is the single choke
+   * point every real charge funnels through (calculateCost → invoices), so the
+   * discount automatically reaches previews, deploys, renewals and upgrades.
+   */
+  async computeTotalsFromDb(dto: CalculateCostDto): Promise<CostTotals> {
+    const raw = await this.computeTotalsRawFromDb(dto);
+    const pct = await this.getGlobalDiscountPercent();
+    return this.applyGlobalDiscount(raw, pct);
+  }
+
+  /** Scale totals (and each breakdown line) by the platform-wide discount. */
+  applyGlobalDiscount(totals: CostTotals, percentOff: number): CostTotals {
+    const pct = Math.min(100, Math.max(0, percentOff || 0));
+    if (pct <= 0) return totals;
+    const factor = 1 - pct / 100;
+    const scale = (n: number) => Math.round(n * factor);
+    return {
+      hourly: scale(totals.hourly),
+      monthly: scale(totals.monthly),
+      yearly: scale(totals.yearly),
+      breakdown: totals.breakdown.map((line) => ({
+        ...line,
+        hourly: scale(line.hourly),
+        monthly: scale(line.monthly),
+        yearly: scale(line.yearly),
+      })),
+    };
+  }
+
+  /** Platform-wide discount percentage (0–100), cached with a short TTL. */
+  async getGlobalDiscountPercent(force = false): Promise<number> {
+    const now = Date.now();
+    if (
+      !force &&
+      now - this.cachedGlobalDiscountAt < PricingCatalogService.GLOBAL_DISCOUNT_TTL_MS
+    ) {
+      return this.cachedGlobalDiscountPct;
+    }
+    try {
+      const setting = await this.settingsRepo.findOne({
+        where: { key: GLOBAL_DISCOUNT_SETTING_KEY },
+      });
+      const parsed = setting ? parseInt(setting.value, 10) : 0;
+      this.cachedGlobalDiscountPct = Number.isFinite(parsed)
+        ? Math.min(100, Math.max(0, parsed))
+        : 0;
+      this.cachedGlobalDiscountAt = now;
+    } catch (e: any) {
+      this.logger.warn(`Failed to read global discount setting: ${e?.message}`);
+    }
+    return this.cachedGlobalDiscountPct;
+  }
+
+  /** Persist the platform-wide discount percentage (Admin) and refresh the cache. */
+  async setGlobalDiscountPercent(percentOff: number): Promise<number> {
+    const clamped = Math.min(100, Math.max(0, Math.round(percentOff || 0)));
+    let setting = await this.settingsRepo.findOne({
+      where: { key: GLOBAL_DISCOUNT_SETTING_KEY },
+    });
+    if (!setting) {
+      setting = this.settingsRepo.create({
+        key: GLOBAL_DISCOUNT_SETTING_KEY,
+        value: String(clamped),
+        description: 'Platform-wide discount percentage applied to all pricing',
+      });
+    } else {
+      setting.value = String(clamped);
+    }
+    await this.settingsRepo.save(setting);
+    this.cachedGlobalDiscountPct = clamped;
+    this.cachedGlobalDiscountAt = Date.now();
+    return clamped;
+  }
+
   computeTotalsWithRates(
     dto: CalculateCostDto,
     rates: PricingRate[],
@@ -739,13 +834,16 @@ export class PricingCatalogService implements OnModuleInit {
       cpuQty += this.parseCpuToCores(dto.databaseResources.cpuLimit);
       memoryQty += this.parseMemoryToGb(dto.databaseResources.memoryLimit);
     }
-    const storageQty =
+    // App resources (CPU/RAM/storage) bill per replica — each replica is a full
-      (dto.dbStorageSize
+    // copy of the user-selected footprint. The database is a single-replica
+    // workload, so its storage is billed once regardless of app replicas.
+    const dbStorage = dto.dbStorageSize
       ? parseFloat(String(dto.dbStorageSize).replace(/Gi$/i, '')) || 0
-        : 0) +
+      : 0;
-      (dto.appStorageSize
+    const appStorage = dto.appStorageSize
       ? parseFloat(String(dto.appStorageSize).replace(/Gi$/i, '')) || 0
-        : 0);
+      : 0;
+    const storageQty = dbStorage + appStorage * replicas;
 
     const map = new Map<PricingResourceType, number>();
     map.set(PricingResourceType.BASE_FEE, 1);

backend/src/billing/public-pricing.controller.ts

@@ -0,0 +1,41 @@
+import { Body, Controller, Get, Post } from '@nestjs/common';
+import { ApiOperation, ApiTags } from '@nestjs/swagger';
+import { PricingCatalogService } from './pricing-catalog.service';
+import { CalculateCostDto } from './dto/billing.dto';
+
+/**
+ * Unauthenticated pricing endpoints for the public landing page. Exposes the
+ * read-only pricing catalog and a cost estimator, both annotated with the
+ * platform-wide discount so the marketing site can show before/after prices.
+ */
+@ApiTags('Public Pricing')
+@Controller('public/pricing')
+export class PublicPricingController {
+  constructor(private readonly pricingCatalog: PricingCatalogService) {}
+
+  @Get('catalog')
+  @ApiOperation({ summary: 'Public pricing catalog + platform-wide discount' })
+  async getCatalog() {
+    const [catalog, globalDiscountPercent] = await Promise.all([
+      this.pricingCatalog.getCatalog(),
+      this.pricingCatalog.getGlobalDiscountPercent(),
+    ]);
+    return { ...catalog, globalDiscountPercent };
+  }
+
+  @Post('calculate')
+  @ApiOperation({ summary: 'Estimate cost for a configuration (gross + discounted)' })
+  async calculate(@Body() dto: CalculateCostDto) {
+    const [gross, globalDiscountPercent] = await Promise.all([
+      this.pricingCatalog.computeTotalsRawFromDb(dto),
+      this.pricingCatalog.getGlobalDiscountPercent(),
+    ]);
+    const net = this.pricingCatalog.applyGlobalDiscount(gross, globalDiscountPercent);
+    return {
+      gross: { hourly: gross.hourly, monthly: gross.monthly, yearly: gross.yearly },
+      net: { hourly: net.hourly, monthly: net.monthly, yearly: net.yearly },
+      breakdown: net.breakdown,
+      globalDiscountPercent,
+    };
+  }
+}

backend/src/build/build-progress.store.ts

@@ -0,0 +1,105 @@
+import { Injectable, OnModuleDestroy } from '@nestjs/common';
+import { ConfigService } from '@nestjs/config';
+import Redis from 'ioredis';
+import type { BuildProgress } from './build.service';
+
+const KEY_PREFIX = 'build:progress:';
+const SESSION_KEY_PREFIX = 'build:session:';
+const TTL_SECONDS = 3600;
+
+/**
+ * Serializable subset of an active build session, persisted to Redis so that
+ * after a backend restart the orphaned cluster resources (job, PVC, secret,
+ * helper pod) of interrupted builds can still be located and cleaned up.
+ */
+export interface PersistedBuildSession {
+  deploymentId: string;
+  applicationId?: string;
+  namespace?: string;
+  buildPodName?: string;
+  sourcePvcName?: string;
+  helperPodName?: string;
+  gitSecretName?: string;
+}
+
+@Injectable()
+export class BuildProgressStore implements OnModuleDestroy {
+  private readonly redis: Redis;
+
+  constructor(private readonly configService: ConfigService) {
+    this.redis = new Redis({
+      host: this.configService.get<string>('redis.host'),
+      port: this.configService.get<number>('redis.port'),
+      password: this.configService.get<string>('redis.password'),
+      lazyConnect: true,
+      maxRetriesPerRequest: 1,
+    });
+    this.redis.connect().catch(() => {
+      // Redis may be unavailable in local unit tests — in-memory fallback remains in BuildService.
+    });
+  }
+
+  async get(deploymentId: string): Promise<BuildProgress | null> {
+    try {
+      const raw = await this.redis.get(`${KEY_PREFIX}${deploymentId}`);
+      return raw ? (JSON.parse(raw) as BuildProgress) : null;
+    } catch {
+      return null;
+    }
+  }
+
+  async set(deploymentId: string, progress: BuildProgress): Promise<void> {
+    try {
+      await this.redis.set(
+        `${KEY_PREFIX}${deploymentId}`,
+        JSON.stringify(progress),
+        'EX',
+        TTL_SECONDS,
+      );
+    } catch {
+      // Best-effort — local map still holds progress for this replica.
+    }
+  }
+
+  async clear(deploymentId: string): Promise<void> {
+    try {
+      await this.redis.del(`${KEY_PREFIX}${deploymentId}`);
+    } catch {
+      // ignore
+    }
+  }
+
+  async setSession(session: PersistedBuildSession): Promise<void> {
+    try {
+      await this.redis.set(
+        `${SESSION_KEY_PREFIX}${session.deploymentId}`,
+        JSON.stringify(session),
+        'EX',
+        TTL_SECONDS,
+      );
+    } catch {
+      // Best-effort — cleanup falls back to prefix-based resource scan.
+    }
+  }
+
+  async getSession(deploymentId: string): Promise<PersistedBuildSession | null> {
+    try {
+      const raw = await this.redis.get(`${SESSION_KEY_PREFIX}${deploymentId}`);
+      return raw ? (JSON.parse(raw) as PersistedBuildSession) : null;
+    } catch {
+      return null;
+    }
+  }
+
+  async clearSession(deploymentId: string): Promise<void> {
+    try {
+      await this.redis.del(`${SESSION_KEY_PREFIX}${deploymentId}`);
+    } catch {
+      // ignore
+    }
+  }
+
+  onModuleDestroy(): void {
+    this.redis.disconnect();
+  }
+}

backend/src/build/build.module.ts

@@ -1,6 +1,6 @@
 import { Module, forwardRef } from '@nestjs/common';
 import { BuildService } from './build.service';
-import { ScanService } from './scan.service';
+import { BuildProgressStore } from './build-progress.store';
 import { KubernetesModule } from '../kubernetes/kubernetes.module';
 import { ClustersModule } from '../clusters/clusters.module';
 
@@ -9,7 +9,7 @@ import { ClustersModule } from '../clusters/clusters.module';
     forwardRef(() => KubernetesModule),
     ClustersModule,
   ],
-  providers: [BuildService, ScanService],
+  providers: [BuildService, BuildProgressStore],
-  exports: [BuildService, ScanService],
+  exports: [BuildService],
 })
 export class BuildModule {}

backend/src/build/build.service.spec.ts

@@ -1,259 +1,247 @@
+import { Test, TestingModule } from '@nestjs/testing';
+import { ConfigService } from '@nestjs/config';
+import * as path from 'path';
+import { BuildService } from './build.service';
+import { Application } from '../applications/entities/application.entity';
 import { AppRuntime } from '../common/enums';
+import { ClustersService } from '../clusters/clusters.service';
+import { RegistryService } from '../kubernetes/registry.service';
+import { BuildProgressStore } from './build-progress.store';
+import { SourceStorageService } from '../storage/source-storage.service';
 
-/**
+describe('BuildService', () => {
- * Tests for build service:
+  let service: BuildService;
- *  • Nixpacks build preparation (BYO Dockerfile vs generated) for code runtimes
- *  • WordPress templated Dockerfile + helper-pod / entrypoint / zip-structure logic
- *
- * NOTE: like the rest of this file, the Nixpacks tests reproduce the pure logic
- * locally instead of importing BuildService — the service pulls in the ESM
- * `@kubernetes/client-node`, which this project's Jest config does not transform.
- * Keep these copies in sync with nixpacksPrepareInitContainer in build.service.ts.
- */
 
-/**
+  beforeEach(async () => {
- * Tests for the WordPress build flow — specifically:
+    const module: TestingModule = await Test.createTestingModule({
- * 1. Helper pod PVC race condition (must wait for termination)
+      providers: [
- * 2. WordPress Dockerfile generation correctness
+        BuildService,
- * 3. Entrypoint should use ENTRYPOINT not CMD to avoid double docker-entrypoint.sh execution
+        {
- */
+          provide: ConfigService,
-
+          useValue: {
-describe('WordPress Dockerfile generation', () => {
+            get: jest.fn((key: string) => {
-  // Reproduce the wordpressDockerfile logic from build.service.ts
+              const map: Record<string, string> = {
-  function wordpressDockerfile(app: {
+                'build.namespace': 'cloudhost-builds',
-    runtimeVersion?: string;
+                'build.serviceAccount': 'kaniko-builder',
-    phpVersion?: string;
+                'registry.url': 'registry.local:5000',
-    codePath?: string;
-    port?: number;
-  }): string {
-    const wpVersion = app.runtimeVersion || '6.7';
-    const phpVersion = app.phpVersion || '8.3';
-    const hasUploadedCode = !!app.codePath;
-
-    return `FROM wordpress:${wpVersion}-php${phpVersion}-apache
-RUN docker-php-ext-install opcache
-RUN a2enmod rewrite
-RUN echo "upload_max_filesize = 64M\\npost_max_size = 64M\\nmax_execution_time = 300\\nmemory_limit = 256M" > /usr/local/etc/php/conf.d/uploads.ini
-${hasUploadedCode ? `COPY . /tmp/user-content
-RUN mkdir -p /usr/src/wordpress-user
-ENTRYPOINT ["cloudhost-entrypoint.sh"]
-CMD []` : `CMD ["apache2-foreground"]`}
-EXPOSE 80
-`;
-  }
-
-  it('should use ENTRYPOINT (not CMD) when user uploaded code', () => {
-    const df = wordpressDockerfile({ codePath: '/some/path/source.zip' });
-    expect(df).toContain('ENTRYPOINT ["cloudhost-entrypoint.sh"]');
-    expect(df).not.toContain('CMD ["cloudhost-entrypoint.sh"]');
-  });
-
-  it('should use CMD apache2-foreground for fresh install (no code)', () => {
-    const df = wordpressDockerfile({});
-    expect(df).toContain('CMD ["apache2-foreground"]');
-    expect(df).not.toContain('ENTRYPOINT');
-  });
-
-  it('should use correct WordPress and PHP versions', () => {
-    const df = wordpressDockerfile({ runtimeVersion: '6.4', phpVersion: '8.2' });
-    expect(df).toContain('FROM wordpress:6.4-php8.2-apache');
-  });
-
-  it('should default to WP 6.7 and PHP 8.3', () => {
-    const df = wordpressDockerfile({});
-    expect(df).toContain('FROM wordpress:6.7-php8.3-apache');
-  });
-
-  it('should COPY user content when codePath exists', () => {
-    const df = wordpressDockerfile({ codePath: '/tmp/source.zip' });
-    expect(df).toContain('COPY . /tmp/user-content');
-  });
-
-  it('should NOT copy user content for fresh install', () => {
-    const df = wordpressDockerfile({});
-    expect(df).not.toContain('COPY . /tmp/user-content');
-  });
-});
-
-describe('Helper pod PVC race condition', () => {
-  it('should wait for pod deletion (not just fire-and-forget)', () => {
-    // Simulate the fix: after deleteNamespacedPod, poll readNamespacedPod until 404
-    const deletionSteps = [
-      { exists: true },   // pod still terminating
-      { exists: true },   // still terminating
-      { exists: false },  // gone (404)
-    ];
-
-    let pollCount = 0;
-    let fullyTerminated = false;
-
-    for (const step of deletionSteps) {
-      pollCount++;
-      if (!step.exists) {
-        fullyTerminated = true;
-        break;
-      }
-    }
-
-    expect(fullyTerminated).toBe(true);
-    expect(pollCount).toBe(3);
-  });
-
-  it('should time out if pod never terminates', () => {
-    const maxPolls = 30; // e.g. 60s / 2s interval
-    let pollCount = 0;
-    let timedOut = false;
-
-    while (pollCount < maxPolls) {
-      pollCount++;
-      // Pod always exists (simulating stuck termination)
-      const exists = true;
-      if (!exists) break;
-    }
-
-    if (pollCount >= maxPolls) {
-      timedOut = true;
-    }
-
-    expect(timedOut).toBe(true);
-  });
-});
-
-describe('WordPress entrypoint script', () => {
-  const entrypointScript = `#!/bin/bash
-set -e
-
-# Merge user wp-content into PVC
-if [ -d /usr/src/wordpress-user/wp-content ]; then
-  mkdir -p /var/www/html/wp-content
-  cp -a /usr/src/wordpress-user/wp-content/. /var/www/html/wp-content/
-  chown -R www-data:www-data /var/www/html/wp-content
-fi
-
-exec docker-entrypoint.sh apache2-foreground`;
-
-  it('should call docker-entrypoint.sh exactly once (via exec)', () => {
-    const matches = entrypointScript.match(/docker-entrypoint\.sh/g);
-    expect(matches).toHaveLength(1);
-  });
-
-  it('should use exec to replace process', () => {
-    expect(entrypointScript).toContain('exec docker-entrypoint.sh apache2-foreground');
-  });
-
-  it('should merge wp-content on every start when staged content exists', () => {
-    expect(entrypointScript).toContain('/usr/src/wordpress-user/wp-content');
-    expect(entrypointScript).not.toContain('.user-content-merged');
-  });
-
-  it('should not copy user wp-config.php (credentials come from env vars)', () => {
-    expect(entrypointScript).not.toContain('wp-config.php');
-  });
-
-  it('should set proper ownership after merging wp-content', () => {
-    expect(entrypointScript).toContain('chown -R www-data:www-data /var/www/html/wp-content');
-  });
-});
-
-describe('WordPress zip structure handling', () => {
-  // The unzip init container handles single-subfolder flattening
-  it('should flatten single subfolder (public_html/) to root', () => {
-    // Simulate: zip contains only public_html/
-    const extractedItems = ['public_html'];
-    const count = extractedItems.length;
-    const firstItem = extractedItems[0];
-
-    let flattenedToRoot = false;
-    if (count === 1 && firstItem === 'public_html') {
-      // cp -a /tmp/extract/public_html/. /workspace-out/source/
-      flattenedToRoot = true;
-    }
-
-    expect(flattenedToRoot).toBe(true);
-  });
-
-  it('should copy as-is when multiple items exist', () => {
-    // Simulate: zip contains multiple items at root
-    const extractedItems = ['wp-admin', 'wp-content', 'wp-includes', 'index.php'];
-    const count = extractedItems.length;
-
-    let copiedAsIs = false;
-    if (count !== 1) {
-      copiedAsIs = true;
-    }
-
-    expect(copiedAsIs).toBe(true);
-  });
-});
-
-describe('Nixpacks build preparation', () => {
-  // Local copies of the pure logic in build.service.ts (see NOTE at top of file).
-  function shellQuote(value: string): string {
-    return `'${value.replace(/'/g, `'\\''`)}'`;
-  }
-
-  function nixpacksPlanEnv(app: { runtime: AppRuntime; runtimeVersion?: string }): { name: string; value: string }[] {
-    const env: { name: string; value: string }[] = [];
-    if (app.runtime === AppRuntime.NODEJS && app.runtimeVersion) {
-      env.push({ name: 'NIXPACKS_NODE_VERSION', value: String(app.runtimeVersion) });
-    }
-    if ((app.runtime === AppRuntime.PYTHON || app.runtime === AppRuntime.DJANGO) && app.runtimeVersion) {
-      env.push({ name: 'NIXPACKS_PYTHON_VERSION', value: String(app.runtimeVersion) });
-    }
-    return env;
-  }
-
-  function nixpacksPrepareInitContainer(
-    app: { runtime: AppRuntime; runtimeVersion?: string },
-    config: { nixpacksImage?: string; nixpacksBuildEnv?: string[] } = {},
-  ): any {
-    const image = config.nixpacksImage || 'ghcr.io/railwayapp/nixpacks:latest';
-    const buildEnv = config.nixpacksBuildEnv || [];
-    const envFlags = buildEnv.map((kv) => `--env ${shellQuote(kv)}`).join(' ');
-    const planEnv = nixpacksPlanEnv(app);
-    return {
-      name: 'nixpacks-prepare',
-      image,
-      env: planEnv.length ? planEnv : undefined,
-      command: [
-        'sh',
-        '-c',
-        `if [ -f source/Dockerfile ]; then cp source/Dockerfile /workspace/Dockerfile; ` +
-          `else nixpacks build source --out source ${envFlags} && cp source/.nixpacks/Dockerfile /workspace/Dockerfile; fi`,
-      ],
-      volumeMounts: [{ name: 'workspace', mountPath: '/workspace' }],
               };
-  }
+              return map[key];
+            }),
+          },
+        },
+        { provide: ClustersService, useValue: {} },
+        {
+          provide: BuildProgressStore,
+          useValue: { get: jest.fn(), set: jest.fn(), clear: jest.fn() },
+        },
+        { provide: RegistryService, useValue: {} },
+        {
+          provide: SourceStorageService,
+          useValue: {
+            isObjectStorage: () => false,
+            materializeToTempFile: jest.fn(),
+            getSize: jest.fn(),
+          },
+        },
+      ],
+    }).compile();
 
-  it('prefers a user-provided Dockerfile (BYO), falling back to Nixpacks', () => {
+    service = module.get(BuildService);
-    const script = nixpacksPrepareInitContainer({ runtime: AppRuntime.NODEJS }).command[2] as string;
-    expect(script).toContain('if [ -f source/Dockerfile ]');
-    expect(script).toContain('cp source/Dockerfile /workspace/Dockerfile');
-    expect(script).toContain('nixpacks build source --out source');
-    expect(script).toContain('cp source/.nixpacks/Dockerfile /workspace/Dockerfile');
   });
 
-  it('uses the configured Nixpacks image (default when unset)', () => {
+  describe('baseImage', () => {
-    expect(nixpacksPrepareInitContainer({ runtime: AppRuntime.GO }).image).toBe('ghcr.io/railwayapp/nixpacks:latest');
+    it('prefixes Docker Hub library images (tag colon must not block mirroring)', () => {
-    expect(
+      const config = (service as any).configService as { get: jest.Mock };
-      nixpacksPrepareInitContainer({ runtime: AppRuntime.GO }, { nixpacksImage: 'registry.local/nixpacks:1.2.3' }).image,
+      config.get.mockImplementation((key: string) => {
-    ).toBe('registry.local/nixpacks:1.2.3');
+        if (key === 'build.baseImageRegistry') return 'registry.abrban.com/abrban';
+        return undefined;
       });
 
-  it('bakes build-time mirror env into the build via --env flags', () => {
+      expect((service as any).baseImage('node:20-alpine')).toBe(
-    const script = nixpacksPrepareInitContainer(
+        'registry.abrban.com/abrban/node:20-alpine',
-      { runtime: AppRuntime.NODEJS },
+      );
-      { nixpacksBuildEnv: ['NPM_CONFIG_REGISTRY=https://registry.npmmirror.com'] },
+      expect((service as any).baseImage('alpine:3.19')).toBe(
-    ).command[2] as string;
+        'registry.abrban.com/abrban/alpine:3.19',
-    expect(script).toContain(`--env 'NPM_CONFIG_REGISTRY=https://registry.npmmirror.com'`);
+      );
     });
 
-  it('maps the selected Node version to NIXPACKS_NODE_VERSION', () => {
+    it('leaves images that already reference an external registry unchanged', () => {
-    const c = nixpacksPrepareInitContainer({ runtime: AppRuntime.NODEJS, runtimeVersion: '20' });
+      const config = (service as any).configService as { get: jest.Mock };
-    expect(c.env).toContainEqual({ name: 'NIXPACKS_NODE_VERSION', value: '20' });
+      config.get.mockImplementation((key: string) => {
+        if (key === 'build.baseImageRegistry') return 'registry.abrban.com/abrban';
+        return undefined;
       });
 
-  it('shellQuote escapes embedded single quotes safely', () => {
+      expect((service as any).baseImage('mcr.microsoft.com/dotnet/sdk:8.0')).toBe(
-    expect(shellQuote("a'b")).toBe("'a'\\''b'");
+        'mcr.microsoft.com/dotnet/sdk:8.0',
+      );
+      expect((service as any).baseImage('registry.abrban.com/abrban/node:20-alpine')).toBe(
+        'registry.abrban.com/abrban/node:20-alpine',
+      );
+      expect((service as any).baseImage('localhost:5000/myapp:latest')).toBe(
+        'localhost:5000/myapp:latest',
+      );
+    });
+  });
+
+  describe('generateDockerfile', () => {
+    it('generates Go Dockerfile with requested runtime version', () => {
+      const app = {
+        runtime: AppRuntime.GO,
+        runtimeVersion: '1.22',
+        port: 8080,
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app) as string;
+
+      expect(dockerfile).toContain('FROM golang:1.22-alpine');
+      expect(dockerfile).toContain('EXPOSE 8080');
+    });
+
+    it('generates Go Dockerfile with cmd package when present in archive entries', () => {
+      const app = {
+        runtime: AppRuntime.GO,
+        runtimeVersion: '1.22',
+        port: 8080,
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app, [
+        'go.mod',
+        'cmd/server/main.go',
+      ]) as string;
+
+      expect(dockerfile).toContain('go build -a -installsuffix cgo -ldflags="-w -s" -o main ./cmd/server');
+    });
+
+    it('generates Node.js Dockerfile with mirrored base images when registry prefix is set', async () => {
+      const module = await Test.createTestingModule({
+        providers: [
+          BuildService,
+          {
+            provide: ConfigService,
+            useValue: {
+              get: jest.fn((key: string) => {
+                const map: Record<string, string> = {
+                  'build.namespace': 'cloudhost-builds',
+                  'build.serviceAccount': 'kaniko-builder',
+                  'build.baseImageRegistry': 'registry.abrban.com/abrban',
+                  'registry.url': 'registry.local:5000',
+                };
+                return map[key];
+              }),
+            },
+          },
+          { provide: ClustersService, useValue: {} },
+          {
+            provide: BuildProgressStore,
+            useValue: { get: jest.fn(), set: jest.fn(), clear: jest.fn() },
+          },
+          { provide: RegistryService, useValue: {} },
+          {
+            provide: SourceStorageService,
+            useValue: {
+              isObjectStorage: () => false,
+              materializeToTempFile: jest.fn(),
+              getSize: jest.fn(),
+            },
+          },
+        ],
+      }).compile();
+
+      const mirrored = module.get(BuildService);
+      const app = {
+        runtime: AppRuntime.NODEJS,
+        runtimeVersion: '20',
+      } as Application;
+
+      const dockerfile = (mirrored as any).generateDockerfile(app) as string;
+
+      expect(dockerfile).toContain('FROM registry.abrban.com/abrban/node:20-alpine');
+      expect(dockerfile).toContain('EXPOSE 3000');
+    });
+
+    it('generates Node.js Dockerfile with default port', () => {
+      const app = {
+        runtime: AppRuntime.NODEJS,
+        runtimeVersion: '20',
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app) as string;
+
+      expect(dockerfile).toContain('FROM node:20');
+      expect(dockerfile).toContain('EXPOSE 3000');
+    });
+
+    it('generates Laravel Dockerfile with artisan migrate', () => {
+      const app = {
+        runtime: AppRuntime.LARAVEL,
+        phpVersion: '8.3',
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app) as string;
+
+      expect(dockerfile).toContain('php:8.3');
+      expect(dockerfile).toContain('artisan migrate');
+    });
+
+    it('generates WordPress Dockerfile with official image', () => {
+      const app = {
+        runtime: AppRuntime.WORDPRESS,
+        runtimeVersion: '6.4',
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app) as string;
+
+      expect(dockerfile).toContain('wordpress:6.4');
+    });
+
+    it('generates Django Dockerfile with detected settings module', () => {
+      const app = {
+        runtime: AppRuntime.DJANGO,
+        runtimeVersion: '3.12',
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app, ['myproject/settings.py']) as string;
+
+      expect(dockerfile).toContain('DJANGO_SETTINGS_MODULE=myproject.settings');
+      expect(dockerfile).toContain('gunicorn');
+    });
+
+    it('generates .NET Dockerfile that restores nested csproj', () => {
+      const app = {
+        runtime: AppRuntime.DOTNET,
+        runtimeVersion: '8.0',
+      } as Application;
+
+      const dockerfile = (service as any).generateDockerfile(app, ['src/App/App.csproj']) as string;
+
+      expect(dockerfile).toContain('CSPROJ="src/App/App.csproj"');
+      expect(dockerfile).toContain('dotnet publish "$CSPROJ"');
+    });
+  });
+
+  describe('egressProxyEnvFrom', () => {
+    it('returns secretRef when BUILD_EGRESS_PROXY_SECRET is set', () => {
+      const config = (service as any).configService as { get: jest.Mock };
+      config.get.mockImplementation((key: string) => {
+        if (key === 'build.egressProxySecret') return 'registry-egress-proxy';
+        return undefined;
+      });
+
+      expect((service as any).egressProxyEnvFrom()).toEqual([
+        { secretRef: { name: 'registry-egress-proxy' } },
+      ]);
+    });
+
+    it('returns undefined when egress proxy is disabled', () => {
+      const config = (service as any).configService as { get: jest.Mock };
+      config.get.mockImplementation((key: string) => {
+        if (key === 'build.egressProxySecret') return '';
+        return undefined;
+      });
+
+      expect((service as any).egressProxyEnvFrom()).toBeUndefined();
+      expect((service as any).withEgressProxy({ name: 'kaniko' })).toEqual({ name: 'kaniko' });
+    });
   });
 });

backend/src/build/runtime-detector.spec.ts

@@ -0,0 +1,141 @@
+import * as path from 'path';
+import { BadRequestException } from '@nestjs/common';
+import { AppRuntime } from '../common/enums';
+import {
+  assertRuntimeMatch,
+  detectDjangoSettingsModule,
+  detectGoBuildTarget,
+  detectRuntimeFromArchive,
+  detectRuntimeFromEntries,
+  listArchiveEntries,
+  normalizeEntryPath,
+  stripCommonRootPrefix,
+} from './runtime-detector';
+
+const fixturesDir = path.join(__dirname, 'fixtures');
+
+describe('runtime-detector', () => {
+  describe('normalizeEntryPath / stripCommonRootPrefix', () => {
+    it('strips a single root folder prefix', () => {
+      const entries = ['myapp/package.json', 'myapp/src/index.js'];
+      expect(stripCommonRootPrefix(entries)).toEqual(['package.json', 'src/index.js']);
+    });
+
+    it('normalizes leading ./ segments', () => {
+      expect(normalizeEntryPath('./package.json')).toBe('package.json');
+    });
+  });
+
+  describe('detectRuntimeFromEntries', () => {
+    it('detects nodejs in nested layout', () => {
+      const result = detectRuntimeFromEntries(['myapp/package.json']);
+      expect(result).toMatchObject({ runtime: AppRuntime.NODEJS, confidence: 'high' });
+    });
+
+    it('detects go from go.mod', () => {
+      const result = detectRuntimeFromEntries(['go.mod', 'main.go']);
+      expect(result).toMatchObject({ runtime: AppRuntime.GO, confidence: 'high' });
+    });
+
+    it('detects laravel from artisan + composer.json', () => {
+      const result = detectRuntimeFromEntries(['artisan', 'composer.json']);
+      expect(result).toMatchObject({ runtime: AppRuntime.LARAVEL, confidence: 'high' });
+    });
+
+    it('detects php from composer.json without artisan', () => {
+      const result = detectRuntimeFromEntries(['composer.json', 'index.php']);
+      expect(result).toMatchObject({ runtime: AppRuntime.PHP, confidence: 'high' });
+    });
+
+    it('detects django from manage.py', () => {
+      const result = detectRuntimeFromEntries(['manage.py', 'requirements.txt']);
+      expect(result).toMatchObject({ runtime: AppRuntime.DJANGO, confidence: 'high' });
+    });
+
+    it('detects python from requirements.txt', () => {
+      const result = detectRuntimeFromEntries(['requirements.txt', 'app.py']);
+      expect(result).toMatchObject({ runtime: AppRuntime.PYTHON, confidence: 'high' });
+    });
+
+    it('detects dotnet from shallow csproj', () => {
+      const result = detectRuntimeFromEntries(['src/App/App.csproj']);
+      expect(result).toMatchObject({ runtime: AppRuntime.DOTNET, confidence: 'high' });
+    });
+
+    it('detects wordpress wp-content migrate layout', () => {
+      const result = detectRuntimeFromEntries(['themes/twenty/style.css', 'plugins/hello/hello.php']);
+      expect(result).toMatchObject({ runtime: AppRuntime.WORDPRESS, confidence: 'high' });
+    });
+
+    it('returns low confidence when package.json and composer.json coexist', () => {
+      const result = detectRuntimeFromEntries(['package.json', 'composer.json']);
+      expect(result).toMatchObject({ runtime: null, confidence: 'low' });
+    });
+  });
+
+  describe('assertRuntimeMatch', () => {
+    it('passes when configured runtime matches detection', () => {
+      expect(() =>
+        assertRuntimeMatch(AppRuntime.GO, {
+          runtime: AppRuntime.GO,
+          confidence: 'high',
+          signals: ['go.mod'],
+        }),
+      ).not.toThrow();
+    });
+
+    it('throws BadRequestException on high-confidence mismatch', () => {
+      expect(() =>
+        assertRuntimeMatch(AppRuntime.NODEJS, {
+          runtime: AppRuntime.GO,
+          confidence: 'high',
+          signals: ['go.mod'],
+        }),
+      ).toThrow(BadRequestException);
+    });
+
+    it('allows upload when confidence is low', () => {
+      expect(() =>
+        assertRuntimeMatch(AppRuntime.NODEJS, {
+          runtime: null,
+          confidence: 'low',
+          signals: [],
+        }),
+      ).not.toThrow();
+    });
+  });
+
+  describe('listArchiveEntries + detectRuntimeFromArchive', () => {
+    it.each([
+      ['nodejs-nested.zip', AppRuntime.NODEJS],
+      ['go-mod.zip', AppRuntime.GO],
+      ['laravel.zip', AppRuntime.LARAVEL],
+      ['php-composer.zip', AppRuntime.PHP],
+      ['django.zip', AppRuntime.DJANGO],
+      ['wordpress-wp-content.zip', AppRuntime.WORDPRESS],
+    ] as const)('reads %s as %s', async (fixture, runtime) => {
+      const zipPath = path.join(fixturesDir, fixture);
+      const entries = await listArchiveEntries(zipPath);
+      expect(entries.length).toBeGreaterThan(0);
+      const detected = await detectRuntimeFromArchive(zipPath);
+      expect(detected.runtime).toBe(runtime);
+      expect(detected.confidence).toBe('high');
+    });
+
+    it('detects go inside a single nested root folder', async () => {
+      const zipPath = path.join(fixturesDir, 'go-nested-root.zip');
+      const detected = await detectRuntimeFromArchive(zipPath);
+      expect(detected.runtime).toBe(AppRuntime.GO);
+    });
+  });
+
+  describe('dockerfile helpers', () => {
+    it('prefers cmd/*/main.go for go build target', () => {
+      expect(detectGoBuildTarget(['go.mod', 'cmd/server/main.go'])).toBe('./cmd/server');
+    });
+
+    it('infers django settings module from project layout', () => {
+      expect(detectDjangoSettingsModule(['myproject/settings.py'])).toBe('myproject.settings');
+    });
+  });
+});