feat: add NVIDIA Graphics tab with GPU monitoring via nvidia-smi and configurable binary path

Add graphics_snapshot() function to query GPU details using nvidia-smi with 5s timeout. Parse GPU metrics including model, driver, UUID, serial, temperature, utilization, VRAM, power, clocks, and compute processes. Add NVIDIA_SMI_BIN environment variable with default "nvidia-smi". Add /api/graphics endpoint returning GPU data with error handling. Add Graphics navigation tab with purple expansion-card icon

app.py

@@ -43,6 +43,7 @@ DATASTORE_PATH = os.environ.get("DATASTORE_PATH", "/nesflix").rstrip("/") or "/"
 RAID_DEVICE = os.environ.get("RAID_DEVICE", "/dev/md127")
 HOST_DEVICE_PATH = os.environ.get("HOST_DEVICE_PATH", "/host-dev")
 HOST_SYS_PATH = os.environ.get("HOST_SYS_PATH", "/host-sys")
+NVIDIA_SMI_BIN = os.environ.get("NVIDIA_SMI_BIN", "nvidia-smi")
 STORAGE_CACHE_SECONDS = int(os.environ.get("STORAGE_CACHE_SECONDS", "900"))
 SMART_ENABLED = os.environ.get("SMART_ENABLED", "false").lower() in {"1", "true", "yes", "on"}
 LOG_FILE = os.environ.get("LOG_FILE", "/data/media-max.log")
@@ -353,6 +354,40 @@ def io_pressure():
     except (OSError, ValueError):
         return {"some": {}, "full": {}, "available": False}
 
+def graphics_snapshot():
+    """Read NVIDIA GPU details with short, non-blocking subprocess timeouts."""
+    query = "index,name,uuid,serial,pci.bus_id,driver_version,pstate,temperature.gpu,utilization.gpu,utilization.memory,memory.total,memory.used,memory.free,power.draw,power.limit,fan.speed,clocks.current.graphics,clocks.current.memory,clocks.max.graphics,clocks.max.memory,compute_mode"
+    try:
+        result = subprocess.run([NVIDIA_SMI_BIN, f"--query-gpu={query}", "--format=csv,noheader,nounits"], capture_output=True, text=True, timeout=5, check=False)
+    except (OSError, subprocess.SubprocessError):
+        return {"available": False, "gpus": [], "processes": [], "error": "NVIDIA SMI nicht verfügbar"}
+    if result.returncode != 0 or not result.stdout.strip():
+        return {"available": False, "gpus": [], "processes": [], "error": "Keine NVIDIA-GPU erkannt"}
+    fields = query.split(",")
+    gpus = []
+    for line in result.stdout.splitlines():
+        values = [value.strip() for value in line.split(",")]
+        if len(values) < len(fields):
+            continue
+        gpu = dict(zip(fields, values))
+        for key in ("index", "temperature.gpu", "utilization.gpu", "utilization.memory", "memory.total", "memory.used", "memory.free", "clocks.current.graphics", "clocks.current.memory", "clocks.max.graphics", "clocks.max.memory"):
+            try: gpu[key] = int(float(gpu[key]))
+            except (TypeError, ValueError): gpu[key] = None
+        for key in ("power.draw", "power.limit"):
+            try: gpu[key] = round(float(gpu[key]), 1)
+            except (TypeError, ValueError): gpu[key] = None
+        gpus.append(gpu)
+    processes = []
+    try:
+        proc = subprocess.run([NVIDIA_SMI_BIN, "--query-compute-apps=pid,process_name,used_gpu_memory", "--format=csv,noheader,nounits"], capture_output=True, text=True, timeout=5, check=False)
+        for line in proc.stdout.splitlines():
+            values = [value.strip() for value in line.split(",")]
+            if len(values) >= 3:
+                processes.append({"pid": values[0], "name": values[1], "memory": values[2]})
+    except (OSError, subprocess.SubprocessError):
+        pass
+    return {"available": bool(gpus), "gpus": gpus, "processes": processes, "error": None if gpus else "Keine NVIDIA-GPU erkannt", "updated_at": time.time()}
+
 def smart_status(device):
     if not SMART_ENABLED:
         return "Nicht aktiviert"
@@ -992,6 +1027,14 @@ def datastore():
         log.error("Datastore konnte nicht abgefragt werden: %s", error_summary(exc))
         return jsonify({"storage": {"error": "Datastore momentan nicht verfügbar", "path": DATASTORE_PATH, "categories": []}, "raid": {"status": "failed", "label": "FAILED", "error": "RAID-Status momentan nicht verfügbar"}}), 500
 
+@app.get("/api/graphics")
+def graphics():
+    try:
+        return jsonify(graphics_snapshot())
+    except Exception as exc:
+        log.error("GPU-Status konnte nicht abgefragt werden: %s", error_summary(exc))
+        return jsonify({"available": False, "gpus": [], "processes": [], "error": "GPU-Status momentan nicht verfügbar"})
+
 @app.get("/health")
 def health(): return jsonify({"ok":True, "radarr_url":RADARR_URL, "sonarr_enabled":bool(SONARR_URL and SONARR_API_KEY), "sab_enabled":bool(SAB_URL and SAB_API_KEY)})