try fix model loading quen3.6-35b

tests/test_node_startup.py

@@ -1646,6 +1646,106 @@ def test_preset_model_startup_honors_pinned_shard_range(tmp_path, monkeypatch):
         tracker.stop()
 
 
+def test_preset_startup_rejects_pinned_shard_above_memory_budget(tmp_path, monkeypatch):
+    """Pinned layer ranges that exceed the node memory budget fail before model load."""
+    import meshnet_node.startup as startup_mod
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 8 * 1024},
+    )
+
+    tracker = TrackerServer(model_presets={
+        "big-model": {
+            "layers_start": 0,
+            "layers_end": 39,
+            "hf_repo": "org/big-model",
+            "bytes_per_layer": {"bfloat16": 2 * 1024 * 1024 * 1024},
+        },
+    })
+    tracker_port = tracker.start()
+    tracker_url = f"http://127.0.0.1:{tracker_port}"
+    try:
+        with pytest.raises(ValueError, match="Pinned shard layers 0–39"):
+            run_startup(
+                tracker_url=tracker_url,
+                model="big-model",
+                shard_start=0,
+                shard_end=39,
+                wallet_path=tmp_path / "wallet.json",
+                cache_dir=tmp_path / "shards",
+            )
+    finally:
+        tracker.stop()
+
+
+def test_preset_model_with_hf_repo_loads_torch_backend(tmp_path, monkeypatch, capsys):
+    """Named presets that advertise hf_repo must load TorchNodeServer, not the stub server."""
+    import meshnet_node.startup as startup_mod
+
+    class FakeBackend:
+        total_layers = 16
+
+    torch_calls: list[dict] = []
+
+    class FakeTorchNodeServer:
+        def __init__(self, **kwargs):
+            torch_calls.append(kwargs)
+            self.backend = FakeBackend()
+            self.port = None
+            self.chat_completion_count = 0
+            self.tracker_node_id = None
+
+        def start(self):
+            self.port = 7002
+            return self.port
+
+        def stop(self):
+            pass
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 16 * 1024},
+    )
+    monkeypatch.setattr(startup_mod, "TorchNodeServer", FakeTorchNodeServer)
+    monkeypatch.setattr(startup_mod, "StubNodeServer", lambda **_kw: (_ for _ in ()).throw(AssertionError("preset with hf_repo must not use StubNodeServer")))
+
+    model_dir = tmp_path / "node-shards" / "tiny-llama"
+    model_dir.mkdir(parents=True)
+    (model_dir / "config.json").write_text('{"num_hidden_layers": 16}')
+    monkeypatch.setattr(startup_mod, "download_shard", lambda *_a, **_kw: model_dir)
+
+    tracker = TrackerServer(model_presets={
+        "tiny-llama": {"layers_start": 0, "layers_end": 15, "hf_repo": "org/tiny-llama-shards"}
+    })
+    tracker_port = tracker.start()
+    tracker_url = f"http://127.0.0.1:{tracker_port}"
+    try:
+        node = run_startup(
+            tracker_url=tracker_url,
+            model="tiny-llama",
+            wallet_path=tmp_path / "wallet.json",
+            cache_dir=tmp_path / "node-shards",
+        )
+        try:
+            assert len(torch_calls) == 1
+            assert torch_calls[0]["model_id"] == "org/tiny-llama-shards"
+            assert torch_calls[0]["cache_dir"] == model_dir
+            output = capsys.readouterr().out
+            assert "Loading real PyTorch model shard..." in output
+            assert "Model ID:     org/tiny-llama-shards" in output
+            network_map = _get_json(f"{tracker_url}/v1/network/map")
+            registered = network_map["nodes"][0]
+            assert registered["hf_repo"] == "org/tiny-llama-shards"
+            assert registered["num_layers"] == 16
+        finally:
+            node.stop()
+    finally:
+        tracker.stop()
+
+
 def test_torch_startup_retries_registration_when_tracker_unreachable(
     tmp_path,
     monkeypatch,