feat(dashboard): live GPU health scoring + real KPIs

- Added /metrics/gpu-health endpoint with live health scores (VRAM 40%, temp 30%, load 30%)
- Added /metrics/latency endpoint for dashboard KPIs
- Added GPU_LABELS for human-readable model names
- Dashboard v2: rewired to real data endpoints
  - KPI cards: GPUs online, circuit trips, avg latency, req/min, active requests
  - Health scores from actual gpu_health_score() function
  - Rolling 60-sample history chart (real data, no simulation)
  - Status: green/yellow/red based on tripped circuits
  - No CDN dependency (pure CSS)
  - Auto-refresh every 15s
- nginx: /dashboard/ serves static files with cache headers
- docker-compose: dashboard volume mount

Co-authored-by: Abiba <abiba@sysloggh.com>

router/router.py

@@ -31,6 +31,13 @@ GPU_URLS = {
     "gemma-4-12b": GPU_LIGHT_URL,
 }
 # Max concurrent requests per GPU (based on llama.cpp --parallel)
+
+GPU_LABELS = {
+    "qwen3.6-35B-A3B": "Qwen3.6 35B (Strix Halo)",
+    "qwen3.6-27B-code": "Qwen3.6 27B Code (RTX 3090)",
+    "gemma-4-12b": "Gemma-4 12B (RTX 5070)",
+}
+
 GPU_MAX_CONCURRENT = {
     "qwen3.6-35B-A3B": 2,   # 2 slots (cross-agent spread prevents overheating)
     "qwen3.6-27B-code": 2,  # 2 slots (128K context frees VRAM)
@@ -815,6 +822,55 @@ def metrics_circuit_breaker():
             }
     return jsonify(result)
 
+
+@app.route("/metrics/gpu-health")
+def metrics_gpu_health():
+    """Live GPU health scores + circuit breaker + KPIs."""
+    result = {"gpus": [], "ts": time.time()}
+    for model in GPU_URLS:
+        h = check_gpu_health(model, sidecar_timeout=1.5, gpu_timeout=1)
+        score = gpu_health_score(model)
+        active = gpu_active_count(model)
+        max_c = GPU_MAX_CONCURRENT.get(model, 1)
+        cb_tripped = bool(r and r.exists("circuit:" + model + ":open"))
+        cb_count = int(r.get("circuit:" + model + ":count") or 0) if r else 0
+        result["gpus"].append({
+            "id": model,
+            "label": GPU_LABELS.get(model, model),
+            "status": h.get("status", "unknown"),
+            "vram_pct": h.get("vram_pct", 0),
+            "temp_c": h.get("temp_c", 0),
+            "vram_used_mb": h.get("vram_used_mb", 0),
+            "vram_total_mb": h.get("vram_total_mb", 0),
+            "gpu_name": h.get("gpu_name", model),
+            "health_score": round(score, 1),
+            "active_requests": active,
+            "max_concurrent": max_c,
+            "circuit_tripped": cb_tripped,
+            "circuit_trip_count": cb_count
+        })
+    online = sum(1 for g in result["gpus"] if g["status"] in ("healthy", "saturated"))
+    trips = sum(g["circuit_trip_count"] for g in result["gpus"])
+    result["kpi"] = {"gpus_online": online, "total_trips": trips, "total_gpus": len(GPU_URLS)}
+    return jsonify(result)
+
+@app.route("/metrics/latency")
+def metrics_latency():
+    """Lightweight latency summary for dashboard KPIs."""
+    if not r: return jsonify({"avg_ms": 0, "requests_per_min": 0})
+    recent = []
+    for x in (r.lrange("routes:recent", 0, 49) or []):
+        try: recent.append(json.loads(x))
+        except: pass
+    if not recent: return jsonify({"avg_ms": 0, "requests_per_min": 0, "count": 0})
+    now = time.time()
+    last_min = [x for x in recent if now - x.get("ts", 0) < 60]
+    latencies = [x.get("queue_ms", 0) + x.get("inference_ms", 0) for x in last_min if "inference_ms" in x]
+    return jsonify({
+        "avg_ms": round(sum(latencies) / len(latencies), 1) if latencies else 0,
+        "requests_per_min": len(last_min),
+        "count": len(recent)
+    })
 @app.route("/stream")
 def stream():
     def ev():