feat(customers): sortable table columns + default ascending ID order

- Customer list now defaults to ascending ID order instead of newest-first,
  so the table starts at customer #1 instead of the highest ID
- Add sort_by/sort_order query params to GET /customers (whitelisted column
  map to prevent SQL injection via arbitrary column names)
- Make ID/Name/Subdomain/Status/Devices/Created column headers clickable,
  toggling asc/desc with a visual arrow indicator

Co-Authored-By: Claude Sonnet 5 <[email protected]>

app/main.py

@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)
 app = FastAPI(
     title="NetBird MSP Appliance",
     description="Multi-tenant NetBird management platform for MSPs",
-    version="1.0.0",
+    version="1.2.0",
     docs_url="/api/docs",
     redoc_url="/api/redoc",
     openapi_url="/api/openapi.json",

app/routers/customers.py

@@ -78,22 +78,36 @@ async def create_customer(
     return response
 
 
+SORTABLE_CUSTOMER_COLUMNS = {
+    "id": Customer.id,
+    "name": Customer.name,
+    "subdomain": Customer.subdomain,
+    "status": Customer.status,
+    "max_devices": Customer.max_devices,
+    "created_at": Customer.created_at,
+}
+
+
 @router.get("")
 async def list_customers(
     page: int = Query(default=1, ge=1),
     per_page: int = Query(default=25, ge=1, le=100),
     search: Optional[str] = Query(default=None),
     status_filter: Optional[str] = Query(default=None, alias="status"),
+    sort_by: str = Query(default="id"),
+    sort_order: str = Query(default="asc", pattern="^(asc|desc)$"),
     current_user: User = Depends(get_current_user),
     db: Session = Depends(get_db),
 ):
-    """List customers with pagination, search, and status filter.
+    """List customers with pagination, search, status filter, and sorting.
 
     Args:
         page: Page number (1-indexed).
         per_page: Items per page.
         search: Search in name, subdomain, email.
         status_filter: Filter by status.
+        sort_by: Column to sort by — one of SORTABLE_CUSTOMER_COLUMNS.
+        sort_order: "asc" or "desc".
 
     Returns:
         Paginated customer list with metadata.
@@ -113,8 +127,11 @@ async def list_customers(
         query = query.filter(Customer.status == status_filter)
 
     total = query.count()
+
+    sort_column = SORTABLE_CUSTOMER_COLUMNS.get(sort_by, Customer.id)
+    sort_expr = sort_column.desc() if sort_order == "desc" else sort_column.asc()
     customers = (
-        query.order_by(Customer.created_at.desc())
+        query.order_by(sort_expr, Customer.id.asc())
         .offset((page - 1) * per_page)
         .limit(per_page)
         .all()

app/routers/monitoring.py

@@ -1,7 +1,9 @@
 """Monitoring API — system overview, customer statuses, host resources."""
 
+import asyncio
 import logging
 import platform
+import time
 from typing import Any
 
 import psutil
@@ -16,6 +18,13 @@ from app.services import docker_service, image_service
 logger = logging.getLogger(__name__)
 router = APIRouter()
 
+# Short-lived cache for the local update-status badges. This endpoint is
+# triggered on every customer-table render (i.e. every search keystroke), but
+# the underlying data (which images are outdated) only changes after an image
+# pull + container recreate, so a few seconds of staleness is harmless.
+_update_status_cache: dict[str, Any] = {"data": None, "expires": 0.0}
+_UPDATE_STATUS_TTL_SECONDS = 20
+
 
 @router.get("/status")
 async def system_status(
@@ -58,8 +67,7 @@ async def all_customers_status(
         .all()
     )
 
-    results: list[dict[str, Any]] = []
-    for c in customers:
+    async def _build_entry(c: Customer) -> dict[str, Any]:
         entry: dict[str, Any] = {
             "id": c.id,
             "name": c.name,
@@ -67,7 +75,7 @@ async def all_customers_status(
             "status": c.status,
         }
         if c.deployment:
-            containers = docker_service.get_container_status(c.deployment.container_prefix)
+            containers = await docker_service.get_container_status_async(c.deployment.container_prefix)
             entry["deployment_status"] = c.deployment.deployment_status
             entry["containers"] = containers
             entry["relay_udp_port"] = c.deployment.relay_udp_port
@@ -76,9 +84,11 @@ async def all_customers_status(
         else:
             entry["deployment_status"] = None
             entry["containers"] = []
-        results.append(entry)
+        return entry
 
-    return results
+    # Fetch container status for all customers concurrently instead of one
+    # blocking Docker SDK call at a time.
+    return await asyncio.gather(*[_build_entry(c) for c in customers])
 
 
 @router.get("/resources")
@@ -205,15 +215,28 @@ async def customers_local_update_status(
 
     Compares running container image IDs against locally stored images.
     No network call — safe to call on every dashboard load.
+
+    Results are cached for a few seconds since this is triggered on every
+    customer-table render (including every search keystroke) but the
+    underlying data rarely changes.
     """
+    now = time.monotonic()
+    if _update_status_cache["data"] is not None and now < _update_status_cache["expires"]:
+        return _update_status_cache["data"]
+
     config = db.query(SystemConfig).filter(SystemConfig.id == 1).first()
     if not config:
         return []
     deployments = db.query(Deployment).all()
-    results = []
-    for dep in deployments:
-        cs = image_service.get_customer_container_image_status(dep.container_prefix, config)
-        results.append({"customer_id": dep.customer_id, "needs_update": cs["needs_update"]})
+
+    async def _check(dep: Deployment) -> dict[str, Any]:
+        cs = await image_service.get_customer_container_image_status_async(dep.container_prefix, config)
+        return {"customer_id": dep.customer_id, "needs_update": cs["needs_update"]}
+
+    results = await asyncio.gather(*[_check(dep) for dep in deployments])
+    results = list(results)
+    _update_status_cache["data"] = results
+    _update_status_cache["expires"] = now + _UPDATE_STATUS_TTL_SECONDS
     return results
 
 

app/routers/settings.py

@@ -4,6 +4,7 @@ There is no .env file. Every setting lives in the ``system_config`` table
 (singleton row with id=1) and is editable via the Web UI settings page.
 """
 
+import asyncio
 import logging
 import os
 import shutil
@@ -358,13 +359,15 @@ async def trigger_update(
     current_user: User = Depends(get_current_user),
     db: Session = Depends(get_db),
 ):
-    """Backup the database, git pull the latest code, and rebuild the container.
+    """Kick off backup + git pull + container rebuild in the background.
+
+    Returns immediately — the actual work (which can take several minutes,
+    especially the ``--no-cache`` image build) runs in a background thread so
+    it doesn't block this request or any other user's requests while it
+    runs. Progress can be polled via GET /settings/update/status until the
+    container restarts with the new version.
 
-    The rebuild is fire-and-forget — the app will restart in ~60 seconds.
     Only admin users may trigger an update.
-
-    Returns:
-        Dict with ok, message, and backup path.
     """
     if getattr(current_user, "role", "admin") != "admin":
         raise HTTPException(
@@ -383,11 +386,37 @@ async def trigger_update(
             detail="git_repo_url is not configured in settings.",
         )
 
-    result = update_service.trigger_update(config, DATABASE_PATH)
-    if not result.get("ok"):
+    current_status = update_service.get_update_status()
+    if current_status.get("state") == "running":
         raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=result.get("message", "Update failed."),
+            status_code=status.HTTP_409_CONFLICT,
+            detail="An update is already in progress.",
         )
+
+    # Snapshot the only fields trigger_update() needs — avoids passing a
+    # SQLAlchemy instance into a background thread after this request's
+    # session may already be closed.
+    class _ConfigSnapshot:
+        git_repo_url = config.git_repo_url
+        git_branch = config.git_branch
+        git_token = config.git_token
+
+    asyncio.create_task(asyncio.to_thread(update_service.trigger_update, _ConfigSnapshot(), DATABASE_PATH))
     logger.info("Update triggered by %s.", current_user.username)
-    return result
+    return {
+        "ok": True,
+        "message": "Update gestartet. Dies kann mehrere Minuten dauern — Fortschritt via Status sichtbar.",
+    }
+
+
+@router.get("/update/status")
+async def update_status(
+    current_user: User = Depends(get_current_user),
+):
+    """Return progress of the currently running (or last) update.
+
+    Note: once the container restarts mid-update, this endpoint stops
+    responding for a few seconds — that itself is a signal the swap is
+    happening. The frontend falls back to polling for the app coming back up.
+    """
+    return update_service.get_update_status()

app/services/docker_service.py

@@ -27,13 +27,24 @@ async def _run_cmd(cmd: list[str], timeout: int = 120) -> subprocess.CompletedPr
     )
 
 
+_client: Optional[docker.DockerClient] = None
+
+
 def _get_client() -> docker.DockerClient:
-    """Return a Docker client connected via the Unix socket.
+    """Return a shared Docker client connected via the Unix socket.
+
+    The client is created once and reused — creating a new client per call
+    (as `docker.from_env()` does) re-negotiates the API version and opens a
+    fresh connection every time, which is wasteful when called once per
+    customer in a loop.
 
     Returns:
         docker.DockerClient instance.
     """
-    return docker.from_env()
+    global _client
+    if _client is None:
+        _client = docker.from_env()
+    return _client
 
 
 async def compose_up(
@@ -212,6 +223,16 @@ def get_container_status(container_prefix: str) -> list[dict[str, Any]]:
     return results
 
 
+async def get_container_status_async(container_prefix: str) -> list[dict[str, Any]]:
+    """Thread-offloaded wrapper around get_container_status().
+
+    Use this when checking status for multiple customers so the Docker SDK
+    calls run in the thread pool instead of blocking the event loop.
+    """
+    loop = asyncio.get_event_loop()
+    return await loop.run_in_executor(None, get_container_status, container_prefix)
+
+
 def get_container_logs(container_name: str, tail: int = 200) -> str:
     """Retrieve recent logs from a container.
 

app/services/image_service.py

@@ -211,6 +211,44 @@ async def pull_all_images(config) -> dict[str, Any]:
     }
 
 
+async def get_customer_container_image_status_async(container_prefix: str, config) -> dict[str, Any]:
+    """Async, thread-offloaded version of get_customer_container_image_status().
+
+    Runs the per-service `docker inspect` subprocess calls concurrently in the
+    thread pool instead of sequentially blocking the event loop — use this
+    whenever checking status for multiple customers (e.g. dashboard/search
+    badge refresh, monitoring overview).
+
+    Returns:
+        services: dict mapping service name to status info
+        needs_update: True if any service has a different image ID than locally stored
+    """
+    service_images = {
+        "management": config.netbird_management_image,
+        "signal": config.netbird_signal_image,
+        "relay": config.netbird_relay_image,
+        "dashboard": config.netbird_dashboard_image,
+    }
+    loop = asyncio.get_event_loop()
+
+    async def _check(svc: str, image: str) -> tuple[str, dict[str, Any]]:
+        container_name = f"{container_prefix}-{svc}"
+        container_id, local_id = await asyncio.gather(
+            loop.run_in_executor(None, get_container_image_id, container_name),
+            loop.run_in_executor(None, get_local_image_id, image),
+        )
+        if container_id and local_id:
+            up_to_date = container_id == local_id
+        else:
+            up_to_date = None  # container not running or image not pulled
+        return svc, {"container": container_name, "image": image, "up_to_date": up_to_date}
+
+    pairs = await asyncio.gather(*[_check(svc, image) for svc, image in service_images.items()])
+    services = dict(pairs)
+    needs_update = any(s["up_to_date"] is False for s in services.values())
+    return {"services": services, "needs_update": needs_update}
+
+
 def get_customer_container_image_status(container_prefix: str, config) -> dict[str, Any]:
     """Check which service containers are running outdated local images.
 

app/services/npm_service.py

@@ -12,9 +12,12 @@ Let's Encrypt SSL certificates.
 Also manages NPM streams for STUN/TURN relay UDP ports.
 """
 
+import base64
+import json
 import logging
 import os
 import socket
+import time
 from typing import Any
 
 import httpx
@@ -24,6 +27,14 @@ logger = logging.getLogger(__name__)
 # Timeout for NPM API calls (seconds)
 NPM_TIMEOUT = 30
 
+# Cached JWTs, keyed by (api_url, email). NPM issues a token that stays valid
+# for a while (per its 'exp' claim), so re-logging in on every single API
+# call — as this module used to do — adds a full extra round-trip per action
+# for no reason.
+_token_cache: dict[tuple[str, str], dict[str, Any]] = {}
+_TOKEN_SAFETY_MARGIN = 60  # refresh this many seconds before actual expiry
+_DEFAULT_TOKEN_TTL = 3600  # fallback if the 'exp' claim can't be parsed
+
 
 def _get_forward_host() -> str:
     """Get the host machine's real IP address for NPM forwarding.
@@ -90,6 +101,61 @@ async def _npm_login(client: httpx.AsyncClient, api_url: str, email: str, passwo
     )
 
 
+def _decode_jwt_exp(token: str) -> float | None:
+    """Best-effort decode of a JWT's 'exp' claim, without verifying the signature.
+
+    We only use this to size our own cache TTL — NPM itself still enforces
+    the real expiry server-side, so an inaccurate read here is harmless.
+    """
+    try:
+        payload_b64 = token.split(".")[1]
+        padding = "=" * (-len(payload_b64) % 4)
+        payload = json.loads(base64.urlsafe_b64decode(payload_b64 + padding))
+        return payload.get("exp")
+    except Exception:
+        return None
+
+
+async def _get_token(
+    client: httpx.AsyncClient, api_url: str, email: str, password: str, force_refresh: bool = False
+) -> str:
+    """Return a cached NPM JWT if still valid, otherwise log in and cache it."""
+    cache_key = (api_url, email)
+    if not force_refresh:
+        cached = _token_cache.get(cache_key)
+        if cached and time.time() < cached["expires_at"]:
+            return cached["token"]
+
+    token = await _npm_login(client, api_url, email, password)
+    exp = _decode_jwt_exp(token)
+    expires_at = (exp - _TOKEN_SAFETY_MARGIN) if exp else (time.time() + _DEFAULT_TOKEN_TTL)
+    _token_cache[cache_key] = {"token": token, "expires_at": expires_at}
+    return token
+
+
+async def _request_with_reauth(
+    client: httpx.AsyncClient,
+    method: str,
+    api_url: str,
+    email: str,
+    password: str,
+    path: str,
+    headers: dict,
+    **kwargs: Any,
+) -> tuple[httpx.Response, dict]:
+    """Perform a request; if the cached token was rejected, refresh and retry once.
+
+    Returns the response and the (possibly updated) headers dict, so callers
+    can reuse the fresh token for any further requests in the same session.
+    """
+    resp = await client.request(method, f"{api_url}{path}", headers=headers, **kwargs)
+    if resp.status_code == 401:
+        token = await _get_token(client, api_url, email, password, force_refresh=True)
+        headers = {**headers, "Authorization": f"Bearer {token}"}
+        resp = await client.request(method, f"{api_url}{path}", headers=headers, **kwargs)
+    return resp, headers
+
+
 async def test_npm_connection(api_url: str, email: str, password: str) -> dict[str, Any]:
     """Test connectivity to NPM by logging in and listing proxy hosts.
 
@@ -103,9 +169,11 @@ async def test_npm_connection(api_url: str, email: str, password: str) -> dict[s
     """
     try:
         async with httpx.AsyncClient(timeout=NPM_TIMEOUT) as client:
-            token = await _npm_login(client, api_url, email, password)
+            token = await _get_token(client, api_url, email, password)
             headers = {"Authorization": f"Bearer {token}"}
-            resp = await client.get(f"{api_url}/nginx/proxy-hosts", headers=headers)
+            resp, headers = await _request_with_reauth(
+                client, "GET", api_url, email, password, "/nginx/proxy-hosts", headers
+            )
             if resp.status_code == 200:
                 count = len(resp.json())
                 return {"ok": True, "message": f"Connected. Login OK. {count} proxy hosts found."}
@@ -136,9 +204,11 @@ async def list_certificates(api_url: str, email: str, password: str) -> dict[str
     """
     try:
         async with httpx.AsyncClient(timeout=NPM_TIMEOUT) as client:
-            token = await _npm_login(client, api_url, email, password)
+            token = await _get_token(client, api_url, email, password)
             headers = {"Authorization": f"Bearer {token}"}
-            resp = await client.get(f"{api_url}/nginx/certificates", headers=headers)
+            resp, headers = await _request_with_reauth(
+                client, "GET", api_url, email, password, "/nginx/certificates", headers
+            )
             if resp.status_code == 200:
                 result = []
                 for cert in resp.json():
@@ -263,10 +333,14 @@ async def create_proxy_host(
             "location ^~ /management.ManagementService/ {\n"
             f"    grpc_pass grpc://{forward_host}:{forward_port};\n"
             "    grpc_set_header Host $host;\n"
+            "    grpc_read_timeout 3600s;\n"
+            "    grpc_send_timeout 3600s;\n"
             "}\n"
             "location ^~ /signalexchange.SignalExchange/ {\n"
             f"    grpc_pass grpc://{forward_host}:{forward_port};\n"
             "    grpc_set_header Host $host;\n"
+            "    grpc_read_timeout 3600s;\n"
+            "    grpc_send_timeout 3600s;\n"
             "}\n"
         ),
         "meta": {
@@ -278,14 +352,15 @@ async def create_proxy_host(
 
     try:
         async with httpx.AsyncClient(timeout=180) as client:  # Long timeout for LE cert
-            token = await _npm_login(client, api_url, npm_email, npm_password)
+            token = await _get_token(client, api_url, npm_email, npm_password)
             headers = {
                 "Authorization": f"Bearer {token}",
                 "Content-Type": "application/json",
             }
 
-            resp = await client.post(
-                f"{api_url}/nginx/proxy-hosts", json=payload, headers=headers
+            resp, headers = await _request_with_reauth(
+                client, "POST", api_url, npm_email, npm_password,
+                "/nginx/proxy-hosts", headers, json=payload,
             )
             if resp.status_code in (200, 201):
                 data = resp.json()
@@ -538,14 +613,15 @@ async def create_stream(
 
     try:
         async with httpx.AsyncClient(timeout=NPM_TIMEOUT) as client:
-            token = await _npm_login(client, api_url, npm_email, npm_password)
+            token = await _get_token(client, api_url, npm_email, npm_password)
             headers = {
                 "Authorization": f"Bearer {token}",
                 "Content-Type": "application/json",
             }
 
-            resp = await client.post(
-                f"{api_url}/nginx/streams", json=payload, headers=headers
+            resp, headers = await _request_with_reauth(
+                client, "POST", api_url, npm_email, npm_password,
+                "/nginx/streams", headers, json=payload,
             )
             if resp.status_code in (200, 201):
                 data = resp.json()
@@ -583,10 +659,11 @@ async def delete_stream(
     """
     try:
         async with httpx.AsyncClient(timeout=NPM_TIMEOUT) as client:
-            token = await _npm_login(client, api_url, npm_email, npm_password)
+            token = await _get_token(client, api_url, npm_email, npm_password)
             headers = {"Authorization": f"Bearer {token}"}
-            resp = await client.delete(
-                f"{api_url}/nginx/streams/{stream_id}", headers=headers
+            resp, headers = await _request_with_reauth(
+                client, "DELETE", api_url, npm_email, npm_password,
+                f"/nginx/streams/{stream_id}", headers,
             )
             if resp.status_code in (200, 204):
                 logger.info("Deleted NPM stream %d", stream_id)
@@ -619,10 +696,11 @@ async def delete_proxy_host(
     """
     try:
         async with httpx.AsyncClient(timeout=NPM_TIMEOUT) as client:
-            token = await _npm_login(client, api_url, npm_email, npm_password)
+            token = await _get_token(client, api_url, npm_email, npm_password)
             headers = {"Authorization": f"Bearer {token}"}
-            resp = await client.delete(
-                f"{api_url}/nginx/proxy-hosts/{proxy_id}", headers=headers
+            resp, headers = await _request_with_reauth(
+                client, "DELETE", api_url, npm_email, npm_password,
+                f"/nginx/proxy-hosts/{proxy_id}", headers,
             )
             if resp.status_code in (200, 204):
                 logger.info("Deleted NPM proxy host %d", proxy_id)

app/services/update_service.py

@@ -20,6 +20,32 @@ SERVICE_NAME = "netbird-msp-appliance"
 
 logger = logging.getLogger(__name__)
 
+# In-memory progress tracker for the currently running (or last) update.
+# The container gets replaced mid-update, so this deliberately does NOT need
+# to survive a restart — the frontend detects completion by polling until the
+# app comes back up and reports a new version, not by reading a final status
+# here. It exists so the UI can show *something* other than a frozen spinner
+# while the backup/pull/build steps are in progress.
+_update_status: dict[str, Any] = {
+    "state": "idle",  # idle | running | failed
+    "step": "",
+    "message": "",
+    "started_at": None,
+}
+
+
+def get_update_status() -> dict[str, Any]:
+    """Return a snapshot of the current update progress."""
+    return dict(_update_status)
+
+
+def _set_status(state: str, step: str, message: str = "") -> None:
+    _update_status["state"] = state
+    _update_status["step"] = step
+    _update_status["message"] = message
+    if step == "backup":
+        _update_status["started_at"] = datetime.utcnow().isoformat()
+
 
 def _get_compose_project_name() -> str:
     """Detect the compose project name from the running container's labels.
@@ -233,10 +259,12 @@ def trigger_update(config: Any, db_path: str) -> dict:
         Dict with ok (bool), message, backup path, and pulled_branch.
     """
     # 1. Backup database before any changes
+    _set_status("running", "backup", "Datenbank wird gesichert …")
     try:
         backup_path = backup_database(db_path)
     except Exception as exc:
         logger.error("Database backup failed: %s", exc)
+        _set_status("failed", "backup", f"Database backup failed: {exc}")
         return {"ok": False, "message": f"Database backup failed: {exc}", "backup": None}
 
     # 2. Build git pull command (embed token in URL if provided)
@@ -252,6 +280,7 @@ def trigger_update(config: Any, db_path: str) -> dict:
         pull_cmd = ["git", "-C", SOURCE_DIR, "pull", "origin", branch]
 
     # 3. Git pull (synchronous — must complete before rebuild)
+    _set_status("running", "pull", f"Code wird von Branch '{branch}' geholt …")
     # Ensure .git directory is owned by the process user (root inside container).
     # The .git dir may be owned by the host user after manual operations.
     try:
@@ -270,13 +299,16 @@ def trigger_update(config: Any, db_path: str) -> dict:
             timeout=120,
         )
     except subprocess.TimeoutExpired:
+        _set_status("failed", "pull", "git pull timed out after 120s.")
         return {"ok": False, "message": "git pull timed out after 120s.", "backup": backup_path}
     except Exception as exc:
+        _set_status("failed", "pull", f"git pull error: {exc}")
         return {"ok": False, "message": f"git pull error: {exc}", "backup": backup_path}
 
     if result.returncode != 0:
         stderr = result.stderr.strip()[:500]
         logger.error("git pull failed (exit %d): %s", result.returncode, stderr)
+        _set_status("failed", "pull", f"git pull failed: {stderr}")
         return {
             "ok": False,
             "message": f"git pull failed: {stderr}",
@@ -348,6 +380,7 @@ def trigger_update(config: Any, db_path: str) -> dict:
         SERVICE_NAME,
     ]
     logger.info("Phase A: building new image …")
+    _set_status("running", "build", "Docker-Image wird gebaut (kann mehrere Minuten dauern) …")
     try:
         build_result = subprocess.run(
             build_cmd,
@@ -360,15 +393,18 @@ def trigger_update(config: Any, db_path: str) -> dict:
             f.write(build_result.stderr)
         if build_result.returncode != 0:
             logger.error("Image build failed: %s", build_result.stderr[:500])
+            _set_status("failed", "build", f"Image build failed: {build_result.stderr[:300]}")
             return {
                 "ok": False,
                 "message": f"Image build failed: {build_result.stderr[:300]}",
                 "backup": backup_path,
             }
     except subprocess.TimeoutExpired:
+        _set_status("failed", "build", "Image build timed out after 600s.")
         return {"ok": False, "message": "Image build timed out after 600s.", "backup": backup_path}
 
     logger.info("Phase A complete — image built successfully.")
+    _set_status("running", "restart", "Container wird neu gestartet …")
 
     # Phase B — swap the container using a helper container.
     #    When compose recreates our container, ALL processes inside die (PID namespace
@@ -388,6 +424,7 @@ def trigger_update(config: Any, db_path: str) -> dict:
             raise ValueError("Could not find /app-source mount")
     except Exception as exc:
         logger.error("Failed to discover host source path: %s", exc)
+        _set_status("failed", "restart", f"Could not find host source path: {exc}")
         return {"ok": False, "message": f"Could not find host source path: {exc}", "backup": backup_path}
 
     logger.info("Host source directory: %s", host_source_dir)
@@ -426,6 +463,10 @@ def trigger_update(config: Any, db_path: str) -> dict:
         )
         if result.returncode != 0:
             logger.error("Failed to start updater container: %s", result.stderr.strip())
+            _set_status(
+                "failed", "restart",
+                f"Update-Container konnte nicht gestartet werden: {result.stderr.strip()[:200]}",
+            )
             return {
                 "ok": False,
                 "message": f"Update-Container konnte nicht gestartet werden: {result.stderr.strip()[:200]}",
@@ -434,6 +475,7 @@ def trigger_update(config: Any, db_path: str) -> dict:
         logger.info("Phase B: updater container started — this container will restart in ~5s.")
     except Exception as exc:
         logger.error("Failed to launch updater: %s", exc)
+        _set_status("failed", "restart", f"Updater launch failed: {exc}")
         return {"ok": False, "message": f"Updater launch failed: {exc}", "backup": backup_path}
 
     return {

static/css/styles.css

@@ -1,5 +1,25 @@
 /* NetBird MSP Appliance - Custom Styles */
 
+/* Sortable table headers */
+.sortable-th {
+    cursor: pointer;
+    user-select: none;
+    white-space: nowrap;
+}
+
+.sortable-th:hover {
+    color: var(--bs-primary);
+}
+
+.sortable-th .sort-icon {
+    opacity: 0.35;
+}
+
+.sortable-th.sort-asc .sort-icon,
+.sortable-th.sort-desc .sort-icon {
+    opacity: 1;
+}
+
 /* i18n FOUC prevention */
 body.i18n-loading #login-page,
 body.i18n-loading #app-page {

static/index.html

@@ -254,13 +254,13 @@
                         <table class="table table-hover mb-0">
                             <thead class="table-light">
                                 <tr>
-                                    <th data-i18n="dashboard.thId">ID</th>
-                                    <th data-i18n="dashboard.thName">Name</th>
-                                    <th data-i18n="dashboard.thSubdomain">Subdomain</th>
-                                    <th data-i18n="dashboard.thStatus">Status</th>
+                                    <th class="sortable-th" data-sort-col="id" onclick="setCustomerSort('id')"><span data-i18n="dashboard.thId">ID</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
+                                    <th class="sortable-th" data-sort-col="name" onclick="setCustomerSort('name')"><span data-i18n="dashboard.thName">Name</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
+                                    <th class="sortable-th" data-sort-col="subdomain" onclick="setCustomerSort('subdomain')"><span data-i18n="dashboard.thSubdomain">Subdomain</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
+                                    <th class="sortable-th" data-sort-col="status" onclick="setCustomerSort('status')"><span data-i18n="dashboard.thStatus">Status</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
                                     <th data-i18n="dashboard.thDashboard">Dashboard</th>
-                                    <th data-i18n="dashboard.thDevices">Devices</th>
-                                    <th data-i18n="dashboard.thCreated">Created</th>
+                                    <th class="sortable-th" data-sort-col="max_devices" onclick="setCustomerSort('max_devices')"><span data-i18n="dashboard.thDevices">Devices</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
+                                    <th class="sortable-th" data-sort-col="created_at" onclick="setCustomerSort('created_at')"><span data-i18n="dashboard.thCreated">Created</span><i class="bi bi-arrow-down-up sort-icon ms-1"></i></th>
                                     <th data-i18n="dashboard.thActions">Actions</th>
                                 </tr>
                             </thead>

static/js/app.js

@@ -12,6 +12,8 @@ let currentPage = 'dashboard';
 let currentCustomerId = null;
 let currentCustomerData = null;
 let customersPage = 1;
+let customersSortBy = 'id';
+let customersSortOrder = 'asc';
 let brandingData = { branding_name: 'NetBird MSP Appliance', branding_logo_path: null, version: 'alpha-1.1' };
 let azureConfig = { azure_enabled: false };
 
@@ -458,7 +460,7 @@ async function loadStats() {
 async function loadCustomers() {
     const search = document.getElementById('search-input').value;
     const status = document.getElementById('status-filter').value;
-    let url = `/customers?page=${customersPage}&per_page=25`;
+    let url = `/customers?page=${customersPage}&per_page=25&sort_by=${customersSortBy}&sort_order=${customersSortOrder}`;
     if (search) url += `&search=${encodeURIComponent(search)}`;
     if (status) url += `&status=${encodeURIComponent(status)}`;
 
@@ -470,7 +472,32 @@ async function loadCustomers() {
     }
 }
 
+function setCustomerSort(column) {
+    if (customersSortBy === column) {
+        customersSortOrder = customersSortOrder === 'asc' ? 'desc' : 'asc';
+    } else {
+        customersSortBy = column;
+        customersSortOrder = 'asc';
+    }
+    customersPage = 1;
+    loadCustomers();
+}
+
+function updateSortHeaders() {
+    document.querySelectorAll('.sortable-th').forEach(th => {
+        const col = th.getAttribute('data-sort-col');
+        const icon = th.querySelector('.sort-icon');
+        th.classList.remove('sort-asc', 'sort-desc');
+        if (icon) icon.className = 'bi bi-arrow-down-up sort-icon ms-1';
+        if (col === customersSortBy) {
+            th.classList.add(customersSortOrder === 'asc' ? 'sort-asc' : 'sort-desc');
+            if (icon) icon.className = `bi bi-arrow-${customersSortOrder === 'asc' ? 'up' : 'down'} sort-icon ms-1`;
+        }
+    });
+}
+
 function renderCustomersTable(data) {
+    updateSortHeaders();
     const tbody = document.getElementById('customers-table-body');
     if (!data.items || data.items.length === 0) {
         tbody.innerHTML = `<tr><td colspan="8" class="text-center text-muted py-4">${t('dashboard.noCustomers')}</td></tr>`;
@@ -669,9 +696,9 @@ async function confirmDeleteCustomer() {
 // ---------------------------------------------------------------------------
 // Customer Actions (start/stop/restart/deploy)
 // ---------------------------------------------------------------------------
-async function customerAction(id, action) {
+async function customerAction(id, action, name) {
     if (action === 'deploy') {
-        showRedeployModal(id);
+        showRedeployModal(id, name);
         return;
     }
     try {
@@ -683,9 +710,12 @@ async function customerAction(id, action) {
     }
 }
 
-function showRedeployModal(id) {
-    const row = document.querySelector(`tr[data-customer-id="${id}"]`);
-    const name = row ? row.querySelector('td')?.textContent?.trim() : `#${id}`;
+function showRedeployModal(id, name) {
+    // Prefer passed name, fallback to dashboard table row, then ID
+    if (!name) {
+        const row = document.querySelector(`tr[data-customer-id="${id}"]`);
+        name = row ? row.querySelector('td')?.textContent?.trim() : `#${id}`;
+    }
     document.getElementById('redeploy-customer-id').value = id;
     document.getElementById('redeploy-customer-name').textContent = name;
     new bootstrap.Modal(document.getElementById('redeploy-modal')).show();
@@ -786,7 +816,7 @@ async function viewCustomer(id) {
                     <button class="btn btn-success btn-sm me-1" onclick="customerAction(${id},'start')"><i class="bi bi-play-circle me-1"></i>${t('customer.start')}</button>
                     <button class="btn btn-warning btn-sm me-1" onclick="customerAction(${id},'stop')"><i class="bi bi-stop-circle me-1"></i>${t('customer.stop')}</button>
                     <button class="btn btn-info btn-sm me-1" onclick="customerAction(${id},'restart')"><i class="bi bi-arrow-repeat me-1"></i>${t('customer.restart')}</button>
-                    <button class="btn btn-outline-primary btn-sm me-1" onclick="customerAction(${id},'deploy')"><i class="bi bi-rocket me-1"></i>${t('customer.reDeploy')}</button>
+                    <button class="btn btn-outline-primary btn-sm me-1" data-customer-name="${esc(data.name)}" onclick="customerAction(${id},'deploy',this.dataset.customerName)"><i class="bi bi-rocket me-1"></i>${t('customer.reDeploy')}</button>
                     <button class="btn btn-outline-warning btn-sm" id="btn-update-images-detail" onclick="updateCustomerImagesFromDetail(${id})">
                         <span id="update-detail-spinner" class="spinner-border spinner-border-sm d-none me-1"></span>
                         <i class="bi bi-arrow-repeat me-1"></i>${t('customer.updateImages')}
@@ -1371,11 +1401,12 @@ async function loadVersionInfo() {
 
         if (needsUpdate) {
             html += `<div class="mt-3">
-                <button class="btn btn-warning" onclick="triggerUpdate()">
+                <button class="btn btn-warning" id="update-trigger-btn" onclick="triggerUpdate()">
                     <span class="spinner-border spinner-border-sm d-none me-1" id="update-spinner"></span>
                     <i class="bi bi-arrow-repeat me-1"></i>${t('settings.triggerUpdate')}
                 </button>
                 <div class="text-muted small mt-1">${t('settings.updateWarning')}</div>
+                <div class="small mt-2 d-none" id="update-progress-text"></div>
             </div>`;
         }
         el.innerHTML = html;
@@ -1387,14 +1418,76 @@ async function loadVersionInfo() {
 async function triggerUpdate() {
     if (!confirm(t('settings.confirmUpdate'))) return;
     const spinner = document.getElementById('update-spinner');
+    const btn = document.getElementById('update-trigger-btn');
+    const progressText = document.getElementById('update-progress-text');
+    const setProgress = (msg) => {
+        if (!progressText) return;
+        progressText.classList.remove('d-none');
+        progressText.textContent = msg;
+    };
+    const stopUpdateUi = () => {
+        if (spinner) spinner.classList.add('d-none');
+        if (btn) btn.disabled = false;
+    };
+
     if (spinner) spinner.classList.remove('d-none');
+    if (btn) btn.disabled = true;
+    setProgress(t('settings.updateStepStarting'));
+
     try {
         const data = await api('POST', '/settings/update');
         showSettingsAlert('success', data.message || t('messages.updateStarted'));
     } catch (err) {
         showSettingsAlert('danger', t('errors.failed', { error: err.message }));
-        if (spinner) spinner.classList.add('d-none');
+        stopUpdateUi();
+        return;
     }
+
+    // Phase 1: poll build/pull progress until the container restarts
+    // (connection drops, which is expected and is our cue to move to phase 2).
+    const stepLabelKey = {
+        backup: 'settings.updateStepBackup',
+        pull: 'settings.updateStepPull',
+        build: 'settings.updateStepBuild',
+        restart: 'settings.updateStepRestart',
+    };
+    for (let i = 0; i < 200; i++) {
+        await new Promise(r => setTimeout(r, 2000));
+        try {
+            const st = await api('GET', '/settings/update/status');
+            if (st.state === 'failed') {
+                showSettingsAlert('danger', st.message || t('errors.requestFailed'));
+                stopUpdateUi();
+                return;
+            }
+            setProgress(t(stepLabelKey[st.step] || 'settings.updateStepStarting') + (st.message ? ` — ${st.message}` : ''));
+        } catch (err) {
+            // Connection dropped — the container is very likely mid-restart. Move on.
+            break;
+        }
+    }
+
+    // Phase 2: wait for the app to come back up, then reload version info.
+    setProgress(t('settings.updateStepReconnecting'));
+    for (let i = 0; i < 90; i++) {
+        await new Promise(r => setTimeout(r, 2000));
+        try {
+            await api('GET', '/settings/version');
+            setProgress(t('settings.updateStepDone'));
+            stopUpdateUi();
+            showSettingsAlert('success', t('settings.updateStepDone'));
+            await loadVersionInfo();
+            return;
+        } catch (err) {
+            // still restarting — keep polling
+        }
+    }
+
+    // Gave up waiting — surface this instead of spinning forever.
+    stopUpdateUi();
+    setProgress('');
+    if (progressText) progressText.classList.add('d-none');
+    showSettingsAlert('warning', t('settings.updateStepTimeout'));
 }
 
 // ---------------------------------------------------------------------------

static/lang/de.json

@@ -230,6 +230,14 @@
     "triggerUpdate": "Update starten",
     "updateWarning": "Die App ist während des Rebuilds ca. 60 Sekunden nicht verfügbar.",
     "confirmUpdate": "Update jetzt starten? Die Datenbank wird zuerst gesichert. Die App startet neu (~60 Sekunden Ausfallzeit).",
+    "updateStepStarting": "Update wird gestartet …",
+    "updateStepBackup": "Datenbank wird gesichert …",
+    "updateStepPull": "Code wird geholt …",
+    "updateStepBuild": "Docker-Image wird gebaut (kann mehrere Minuten dauern) …",
+    "updateStepRestart": "Container wird neu gestartet …",
+    "updateStepReconnecting": "Container startet neu — warte auf Verbindung …",
+    "updateStepDone": "Update abgeschlossen.",
+    "updateStepTimeout": "Update läuft länger als erwartet. Bitte Server-Logs prüfen oder die Seite in ein paar Minuten neu laden.",
     "gitTitle": "Git-Repository Einstellungen",
     "gitRepoUrl": "Repository URL",
     "gitRepoUrlHint": "Wird für Versionsprüfungen und One-Click-Updates via Gitea API verwendet.",

static/lang/en.json

@@ -262,6 +262,14 @@
     "triggerUpdate": "Start Update",
     "updateWarning": "The app will be unavailable for ~60 seconds during rebuild.",
     "confirmUpdate": "Start the update now? The database will be backed up first. The app will restart (~60 seconds downtime).",
+    "updateStepStarting": "Starting update …",
+    "updateStepBackup": "Backing up database …",
+    "updateStepPull": "Fetching code …",
+    "updateStepBuild": "Building Docker image (can take several minutes) …",
+    "updateStepRestart": "Restarting container …",
+    "updateStepReconnecting": "Container is restarting — waiting for connection …",
+    "updateStepDone": "Update complete.",
+    "updateStepTimeout": "Update is taking longer than expected. Check the server logs or reload this page in a few minutes.",
     "gitTitle": "Git Repository Settings",
     "gitRepoUrl": "Repository URL",
     "gitRepoUrlHint": "Used for version checks and one-click updates via Gitea API.",