story: DGR-043 Expose GGUF compatibility and measured cost inputs to existing routing

packages/node/meshnet_node/native_registration.py

@@ -12,7 +12,7 @@ from collections.abc import Callable
 from dataclasses import dataclass
 from typing import Any
 
-from .capability import ExecutionCapacity, build_capability_report
+from .capability import ExecutionCapacity, RoutingMeasurements, build_capability_report
 from .native_worker_supervisor import NativeWorkerProbe, NativeWorkerSpec, NativeWorkerSupervisor
 from .runtime_recipe import ShardIdentity
 
@@ -33,6 +33,7 @@ class NativeShardRegistration:
     device: str
     capacity: ExecutionCapacity
     duration_ms: int = 0
+    routing: RoutingMeasurements | None = None
 
     def __post_init__(self) -> None:
         if not self.endpoint:
@@ -104,8 +105,9 @@ class NativeShardRegistration:
             duration_ms=self.duration_ms,
             identity=self.identity,
             capacity=self.capacity,
+            routing=self.routing,
         )
-        return {
+        payload = {
             "endpoint": self.endpoint,
             "model": self.model_id.rsplit("/", 1)[-1],
             "hf_repo": self.model_id,
@@ -118,6 +120,15 @@ class NativeShardRegistration:
             "ram_bytes": self.capacity.memory_capacity_bytes or 0,
             "max_loaded_shards": 1,
         }
+        # These are the tracker’s established dynamic scoring inputs.  The
+        # exact same optional report can be sent by any backend; no native
+        # route or balancing branch is introduced here.
+        if self.routing is not None:
+            if self.routing.tokens_per_second is not None:
+                payload["benchmark_tokens_per_sec"] = self.routing.tokens_per_second
+            if self.routing.queue_depth is not None:
+                payload["queue_depth"] = self.routing.queue_depth
+        return payload
 
 
 RegistrationSender = Callable[[dict[str, Any]], None]