md rework. new code

tests/test_node_startup.py

@@ -1680,6 +1680,66 @@ def test_preset_startup_rejects_pinned_shard_above_memory_budget(tmp_path, monke
         tracker.stop()
 
 
+def test_network_auto_join_clips_oversized_cpu_assignment(tmp_path, monkeypatch, capsys):
+    """Old trackers may assign too many CPU layers; node clips before model load."""
+    import meshnet_node.startup as startup_mod
+
+    torch_calls: list[dict] = []
+    registrations: list[dict] = []
+
+    class FakeBackend:
+        total_layers = 40
+
+    class FakeTorchNodeServer:
+        def __init__(self, **kwargs):
+            torch_calls.append(kwargs)
+            self.backend = FakeBackend()
+            self.tracker_node_id = None
+
+        def start(self):
+            return 7000
+
+        def stop(self):
+            pass
+
+    oversized_assignment = {
+        "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+        "model": "qwen3.6-35b-a3b",
+        "shard_start": 0,
+        "shard_end": 36,
+        "num_layers": 40,
+        "gap_found": False,
+        "bytes_per_layer": {"bfloat16": 1_797_594_419},
+        "model_sources": [],
+    }
+
+    monkeypatch.setattr(
+        startup_mod,
+        "detect_hardware",
+        lambda: {"device": "cpu", "gpu_name": None, "vram_mb": 0, "ram_mb": 79 * 1024},
+    )
+    monkeypatch.setattr(startup_mod, "TorchNodeServer", FakeTorchNodeServer)
+    monkeypatch.setattr(startup_mod, "_get_json", lambda *_args, **_kwargs: oversized_assignment)
+    monkeypatch.setattr(startup_mod, "_post_json", lambda _url, payload: registrations.append(payload) or {"node_id": "n1"})
+    monkeypatch.setattr(startup_mod, "_start_heartbeat", lambda *_args, **_kwargs: None)
+    monkeypatch.setattr(startup_mod, "model_metadata_for", lambda *_args, **_kwargs: {"num_layers": 40})
+
+    node = run_startup(
+        tracker_url="http://127.0.0.1:8080",
+        wallet_path=tmp_path / "wallet.json",
+        tracker_source_disabled=True,
+    )
+    try:
+        assert torch_calls[0]["shard_start"] == 0
+        assert torch_calls[0]["shard_end"] == 24
+        assert registrations[0]["shard_end"] == 24
+        output = capsys.readouterr().out
+        assert "CPU-safe runtime budget fits 25/40 layers" in output
+        assert "layers 0-24" in output
+    finally:
+        node.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
@@ -1996,6 +2056,55 @@ def test_network_assign_gap_found_field():
         tracker.stop()
 
 
+def test_network_assign_uses_conservative_cpu_runtime_budget():
+    """CPU assignments leave headroom for partial-load overhead, not just raw weights."""
+    import json as _json
+    import urllib.request as _ur
+
+    tracker = TrackerServer(model_presets={
+        "qwen3.6-35b-a3b": {
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "aliases": ["unsloth/Qwen3.6-35B-A3B"],
+            "layers_start": 0,
+            "layers_end": 39,
+            "recommended": True,
+            "bytes_per_layer": {"bfloat16": 1_797_594_419},
+        },
+    })
+    port = tracker.start()
+    try:
+        data = _json.dumps({
+            "endpoint": "http://127.0.0.1:9200",
+            "model": "qwen3.6-35b-a3b",
+            "hf_repo": "unsloth/Qwen3.6-35B-A3B",
+            "num_layers": 40,
+            "shard_start": 0,
+            "shard_end": 39,
+            "hardware_profile": {},
+            "score": 1.0,
+        }).encode()
+        req = _ur.Request(
+            f"http://127.0.0.1:{port}/v1/nodes/register",
+            data=data,
+            headers={"Content-Type": "application/json"},
+            method="POST",
+        )
+        with _ur.urlopen(req) as r:
+            r.read()
+
+        resp = _get_json(
+            f"http://127.0.0.1:{port}/v1/network/assign"
+            "?device=cpu&vram_mb=0&ram_mb=80896"
+            "&hf_repo=unsloth/Qwen3.6-35B-A3B"
+        )
+
+        assert resp["gap_found"] is False
+        assert resp["shard_start"] == 0
+        assert resp["shard_end"] == 24
+    finally:
+        tracker.stop()
+
+
 def test_route_finds_hf_model_across_two_nodes():
     """Tracker /v1/route returns ordered route for HF model even without a preset."""
     import json as _json