feat(updates): NetBird container image update management

- New image_service.py: Docker Hub digest check (no pull), local digest/ID
  comparison, pull_all_images, per-customer container image status, and
  update_customer_containers (docker compose up -d, data-safe)
- Monitoring endpoints: GET /images/check (hub vs local + per-customer
  needs_update), POST /images/pull (background), POST /customers/update-all
- Deployment endpoint: POST /{id}/update-images (single-customer update)
- Monitoring page: "NetBird Container Updates" card with Check / Pull / Update
  All buttons; image status table and per-customer update table with inline
  update buttons
- i18n: added keys in en.json and de.json

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/routers/deployments.py

@@ -7,8 +7,8 @@ from sqlalchemy.orm import Session
 
 from app.database import SessionLocal, get_db
 from app.dependencies import get_current_user
-from app.models import Customer, Deployment, User
-from app.services import docker_service, netbird_service
+from app.models import Customer, Deployment, SystemConfig, User
+from app.services import docker_service, image_service, netbird_service
 from app.utils.security import decrypt_value
 
 logger = logging.getLogger(__name__)
@@ -207,6 +207,50 @@ async def get_customer_credentials(
     }
 
 
+@router.post("/{customer_id}/update-images")
+async def update_customer_images(
+    customer_id: int,
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+):
+    """Recreate a customer's containers to pick up newly pulled images.
+
+    Images must already be pulled via POST /monitoring/images/pull.
+    Bind-mounted data is preserved — no data loss.
+    """
+    if current_user.role != "admin":
+        raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin only.")
+
+    customer = _require_customer(db, customer_id)
+    deployment = db.query(Deployment).filter(Deployment.customer_id == customer_id).first()
+    if not deployment:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="No deployment found for this customer.",
+        )
+
+    config = db.query(SystemConfig).filter(SystemConfig.id == 1).first()
+    if not config:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE, detail="System not configured."
+        )
+
+    instance_dir = f"{config.data_dir}/{customer.subdomain}"
+    result = await image_service.update_customer_containers(instance_dir, deployment.container_prefix)
+
+    if not result["success"]:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=result.get("error", "Failed to update containers."),
+        )
+
+    logger.info(
+        "Containers updated for customer '%s' (prefix: %s) by '%s'.",
+        customer.name, deployment.container_prefix, current_user.username,
+    )
+    return {"message": f"Containers updated for '{customer.name}'."}
+
+
 def _require_customer(db: Session, customer_id: int) -> Customer:
     """Helper to fetch a customer or raise 404.
 

app/routers/monitoring.py

@@ -5,13 +5,13 @@ import platform
 from typing import Any
 
 import psutil
-from fastapi import APIRouter, Depends
+from fastapi import APIRouter, BackgroundTasks, Depends, HTTPException, status
 from sqlalchemy.orm import Session
 
-from app.database import get_db
+from app.database import SessionLocal, get_db
 from app.dependencies import get_current_user
-from app.models import Customer, Deployment, User
-from app.services import docker_service
+from app.models import Customer, Deployment, SystemConfig, User
+from app.services import docker_service, image_service
 
 logger = logging.getLogger(__name__)
 router = APIRouter()
@@ -115,3 +115,137 @@ async def host_resources(
             "percent": disk.percent,
         },
     }
+
+
+@router.get("/images/check")
+async def check_image_updates(
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+) -> dict[str, Any]:
+    """Check all configured NetBird images for available updates on Docker Hub.
+
+    Compares local image digests against Docker Hub — no image is pulled.
+
+    Returns:
+        images: dict mapping image name to update status
+        any_update_available: bool
+        customer_status: list of per-customer container image status
+    """
+    config = db.query(SystemConfig).filter(SystemConfig.id == 1).first()
+    if not config:
+        raise HTTPException(status_code=status.HTTP_503_SERVICE_UNAVAILABLE, detail="System not configured.")
+
+    hub_status = await image_service.check_all_images(config)
+
+    # Per-customer local check (no network)
+    deployments = db.query(Deployment).all()
+    customer_status = []
+    for dep in deployments:
+        customer = dep.customer
+        cs = image_service.get_customer_container_image_status(dep.container_prefix, config)
+        customer_status.append({
+            "customer_id": customer.id,
+            "customer_name": customer.name,
+            "subdomain": customer.subdomain,
+            "container_prefix": dep.container_prefix,
+            "needs_update": cs["needs_update"],
+            "services": cs["services"],
+        })
+
+    return {**hub_status, "customer_status": customer_status}
+
+
+@router.post("/images/pull")
+async def pull_all_netbird_images(
+    background_tasks: BackgroundTasks,
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+) -> dict[str, Any]:
+    """Pull all configured NetBird images from Docker Hub.
+
+    Runs in the background — returns immediately. After pulling, re-check
+    customer status via GET /images/check to see which customers need updating.
+    """
+    if current_user.role != "admin":
+        raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin only.")
+
+    config = db.query(SystemConfig).filter(SystemConfig.id == 1).first()
+    if not config:
+        raise HTTPException(status_code=status.HTTP_503_SERVICE_UNAVAILABLE, detail="System not configured.")
+
+    # Snapshot image list before background task starts
+    images = [
+        config.netbird_management_image,
+        config.netbird_signal_image,
+        config.netbird_relay_image,
+        config.netbird_dashboard_image,
+    ]
+
+    async def _pull_bg() -> None:
+        bg_db = SessionLocal()
+        try:
+            cfg = bg_db.query(SystemConfig).filter(SystemConfig.id == 1).first()
+            if cfg:
+                await image_service.pull_all_images(cfg)
+        except Exception:
+            logger.exception("Background image pull failed")
+        finally:
+            bg_db.close()
+
+    background_tasks.add_task(_pull_bg)
+    return {"message": "Image pull started in background.", "images": images}
+
+
+@router.post("/customers/update-all")
+async def update_all_customers(
+    background_tasks: BackgroundTasks,
+    current_user: User = Depends(get_current_user),
+    db: Session = Depends(get_db),
+) -> dict[str, Any]:
+    """Recreate containers for all customers that have outdated images.
+
+    Only customers where at least one container runs an outdated image are updated.
+    Images must already be pulled. Data is preserved (bind mounts).
+    """
+    if current_user.role != "admin":
+        raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin only.")
+
+    config = db.query(SystemConfig).filter(SystemConfig.id == 1).first()
+    if not config:
+        raise HTTPException(status_code=status.HTTP_503_SERVICE_UNAVAILABLE, detail="System not configured.")
+
+    # Collect customers that need updating
+    deployments = db.query(Deployment).all()
+    to_update = []
+    for dep in deployments:
+        cs = image_service.get_customer_container_image_status(dep.container_prefix, config)
+        if cs["needs_update"]:
+            customer = dep.customer
+            instance_dir = str(dep.container_prefix).replace(
+                "netbird-", "", 1
+            )  # subdomain
+            to_update.append({
+                "instance_dir": f"{config.data_dir}/{customer.subdomain}",
+                "project_name": dep.container_prefix,
+                "customer_name": customer.name,
+            })
+
+    if not to_update:
+        return {"message": "All customers are already up to date.", "updated": 0}
+
+    async def _update_all_bg() -> None:
+        for entry in to_update:
+            try:
+                await image_service.update_customer_containers(
+                    entry["instance_dir"], entry["project_name"]
+                )
+                logger.info("Updated containers for %s", entry["project_name"])
+            except Exception:
+                logger.exception("Failed to update %s", entry["project_name"])
+
+    background_tasks.add_task(_update_all_bg)
+    names = [e["customer_name"] for e in to_update]
+    return {
+        "message": f"Updating {len(to_update)} customer(s) in background.",
+        "customers": names,
+    }