tests on dash

packages/tracker/meshnet_tracker/server.py

@@ -1276,6 +1276,35 @@ def _scale_demanded_models_locked(server: "_TrackerHTTPServer") -> None:
             break
 
 
+def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> dict | None:
+    """Queue an explicitly requested model on the best available joined node."""
+    resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
+    if preset is None or not preset.get("hf_repo"):
+        return None
+    required_start, required_end = _preset_layer_bounds(preset)
+    total_layers = required_end - required_start + 1
+    for host in _memory_pool_map(server)["hosts"]:
+        if host["spare_slots"] <= 0:
+            continue
+        host_nodes = [server.registry[item["node_id"]] for item in host["loaded"] if item["node_id"] in server.registry]
+        if not host_nodes:
+            continue
+        anchor = max(host_nodes, key=lambda node: node.benchmark_tokens_per_sec)
+        if anchor.status != "ready" or anchor.pending_new_assignment is not None:
+            continue
+        capacity = min(_node_layer_capacity(anchor, preset), total_layers)
+        if capacity <= 0:
+            continue
+        quantization = _node_quantization(anchor, preset)
+        shard_end = min(required_end, required_start + capacity - 1)
+        directive = _add_shard_directive(anchor, str(preset["hf_repo"]), required_start, shard_end, quantization)
+        anchor.pending_new_assignment = directive
+        anchor.pending_directives.append(directive)
+        _tracker_log(server, "info", "model load requested", node_id=anchor.node_id, model=resolved_name, hf_repo=preset["hf_repo"], shard=f"{required_start}-{shard_end}")
+        return {"node_id": anchor.node_id, "model": resolved_name, "hf_repo": preset["hf_repo"], "shard_start": required_start, "shard_end": shard_end}
+    return None
+
+
 def _deployment_summary(nodes: list[_NodeEntry], preset: dict | None) -> dict:
     if preset is None:
         return {"recommended": False}
@@ -2672,6 +2701,9 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         if self.path == "/v1/benchmark/hop-penalty":
             self._handle_benchmark_hop_penalty()
             return
+        if self.path == "/v1/models/load":
+            self._handle_model_load_request()
+            return
         if self.path == "/v1/calibration/toploc/run":
             self._handle_toploc_calibration_run()
             return
@@ -4294,6 +4326,25 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
             server.gossip.merge({k: float(v) for k, v in body.items()})
         self._send_json(200, {})
 
+    def _handle_model_load_request(self):
+        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
+        if not self._require_role("admin"):
+            return
+        body = self._read_json_body()
+        if body is None:
+            return
+        model = body.get("model")
+        if not isinstance(model, str) or not model.strip():
+            self._send_json(400, {"error": "model is required"})
+            return
+        with server.lock:
+            self._purge_expired_nodes()
+            assignment = _request_model_load_locked(server, model)
+        if assignment is None:
+            self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
+            return
+        self._send_json(202, {"status": "queued", "assignment": assignment})
+
     def _handle_stats(self):
         server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
         if server.stats is None: