feat(us-026): smart model assignment via demand×coverage scoring

/v1/network/assign now scores models by (demand_rpm + 1) × (coverage_deficit + 0.01)
so high-traffic, under-covered models are preferred when assigning new nodes.
Response includes price_per_token: 0.0 (reserved for future pricing protocol).
--memory MB flag added to node CLI to override autodetected VRAM budget for
shard assignment without changing hardware detection for inference.

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

packages/node/meshnet_node/startup.py

@@ -141,6 +141,7 @@ def run_startup(
     advertise_host: str | None = None,
     contracts: Any | None = None,
     route_timeout: float = 30.0,
+    vram_mb_override: int | None = None,
 ) -> StubNodeServer | TorchNodeServer:
     """Execute the full startup sequence and return a running node server.
 
@@ -177,7 +178,10 @@ def run_startup(
     gpu_name: str | None = hw.get("gpu_name")
     vram_mb: int = hw.get("vram_mb", 0)
 
-    if device == "cpu":
+    if vram_mb_override is not None:
+        vram_mb = vram_mb_override
+        print(f"  Memory budget overridden to {vram_mb} MB via --memory", flush=True)
+    elif device == "cpu":
         print("  WARNING: No CUDA GPU detected — running in CPU mode", flush=True)
     else:
         print(f"  GPU: {gpu_name} ({vram_mb} MB VRAM)", flush=True)