perf: tracker injects pre-resolved route; node skips redundant tracker query

When the tracker proxies /v1/chat/completions to a first-shard node it
already holds the full registry picture. It now resolves the downstream
route inline via _select_route, strips the proxied node, and sends the
result as X-Meshnet-Route header alongside the request body.

The first-shard node reads this header in _get_remaining_route and
returns it directly, skipping the second tracker HTTP call entirely.
Falls back to the tracker query transparently when the header is absent
(direct node-to-node calls or older tracker versions).

Reduces per-inference tracker round-trips from 2 to 1.

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

packages/tracker/meshnet_tracker/server.py

@@ -606,10 +606,33 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         node = candidates[int(time.time() * 1000) % len(candidates)]
         target_url = f"{node.endpoint}/v1/chat/completions"
 
+        # Pre-resolve the downstream route so the first-shard node skips its own
+        # tracker query.  We already hold the full registry picture — no need for
+        # a second round-trip.
+        route_model = node.hf_repo or node.model or model
+        with server.lock:
+            if route_model in server.model_presets:
+                preset = server.model_presets[route_model]
+                rs, re = _preset_layer_bounds(preset)
+                all_nodes: list = [n for n in server.registry.values() if n.model == route_model]
+            else:
+                all_nodes = [
+                    n for n in server.registry.values()
+                    if (n.hf_repo == route_model or n.model == route_model)
+                    and n.shard_start is not None and n.num_layers is not None
+                ]
+                rs, re = 0, (max((n.num_layers for n in all_nodes), default=1) - 1)
+        route_nodes, _ = _select_route(all_nodes, rs, re)
+        # Strip the first-shard node we're about to proxy to — it's already handling the request.
+        downstream_urls = json.dumps([n.endpoint for n in route_nodes if n.endpoint != node.endpoint])
+
         req = urllib.request.Request(
             target_url,
             data=raw_body,
-            headers={"Content-Type": "application/json"},
+            headers={
+                "Content-Type": "application/json",
+                "X-Meshnet-Route": downstream_urls,
+            },
             method="POST",
         )
         # Copy Authorization header from client if present