[verified] fix: preserve tracker precision eligibility

tests/test_real_model_backend.py

@@ -32,6 +32,15 @@ from meshnet_node.model_backend import (
 from meshnet_node.torch_server import TorchNodeServer
 
 
+def _require_functional_torch():
+    """Skip tensor-behaviour tests when the installed torch namespace is incomplete."""
+    torch = pytest.importorskip("torch")
+    required = ("tensor", "zeros", "ones", "arange", "bfloat16", "long")
+    if not all(hasattr(torch, name) for name in required):
+        pytest.skip("requires a functional PyTorch tensor runtime")
+    return torch
+
+
 class _FakeBackend:
     model_id = "fake-model"
     total_layers = 12
@@ -526,13 +535,14 @@ def test_distributed_generating_log_includes_tps(capsys):
     out = capsys.readouterr().out
     assert "generating step=1/1" in out
     assert " tps=" in out
-    assert "generation complete tokens=1" in out
+    assert "generation complete session=" in out
+    assert "tokens=1" in out
     assert out.count("generating step=1/1") == 1
 
 
 def test_int_tensor_header_serializes_torch_tensors():
     "Int tensor header serializes torch tensors\n\nTags: model, node, real-inference"
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
 
     header = _int_tensor_header(torch.tensor([[1, 2, 3]], dtype=torch.long))
 
@@ -544,7 +554,7 @@ def test_bfloat16_wire_decode_views_owned_bytes_without_float32_round_trip():
 
     Tags: model, performance, wire
     """
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
     body = torch.tensor([[1, 2]], dtype=torch.bfloat16).view(torch.uint8).numpy().tobytes()
 
     decoded = _tensor_from_bfloat16_bytes(body, [1, 2], torch)
@@ -555,7 +565,7 @@ def test_bfloat16_wire_decode_views_owned_bytes_without_float32_round_trip():
 
 def test_decoder_attention_mask_is_causal_float_mask():
     "Decoder attention mask is causal float mask\n\nTags: model, node, real-inference"
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
 
     hidden_states = torch.zeros((1, 3, 8), dtype=torch.bfloat16)
     mask = _decoder_attention_mask(torch.ones((1, 3), dtype=torch.long), hidden_states, torch)
@@ -573,7 +583,7 @@ def test_call_layer_passes_rotary_position_embeddings():
             assert kwargs["position_embeddings"] == "rotary"
             return hidden_states
 
-    hidden, cache_state = _call_layer(
+    hidden = _call_layer(
         NeedsPositionEmbeddings(),
         "hidden",
         attention_mask=None,
@@ -582,7 +592,6 @@ def test_call_layer_passes_rotary_position_embeddings():
     )
 
     assert hidden == "hidden"
-    assert cache_state is None
 
 
 def _fake_cache_shard(torch, *, max_sessions=16, ttl=600.0):
@@ -618,7 +627,7 @@ def _fake_cache_shard(torch, *, max_sessions=16, ttl=600.0):
 
 def test_shard_cache_prefill_then_decode_reuses_opaque_layer_state():
     "Shard cache prefill then decode reuses opaque layer state\n\nTags: cache, model, node, real-inference"
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
     shard = _fake_cache_shard(torch)
 
     prefill_hidden = torch.zeros((1, 4, 2), dtype=torch.bfloat16)
@@ -658,7 +667,7 @@ def test_shard_cache_prefill_then_decode_reuses_opaque_layer_state():
 
 def test_shard_cache_decode_miss_is_explicit():
     "Shard cache decode miss is explicit\n\nTags: cache, model, node, real-inference"
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
     shard = _fake_cache_shard(torch)
 
     with pytest.raises(KVCacheMiss):
@@ -674,7 +683,7 @@ def test_shard_cache_decode_miss_is_explicit():
 
 def test_shard_cache_lru_bounds_sessions():
     "Shard cache lru bounds sessions\n\nTags: cache, model, node, real-inference"
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
     shard = _fake_cache_shard(torch, max_sessions=1)
 
     for session in ("old", "new"):
@@ -1154,7 +1163,7 @@ def test_torch_model_shard_prefers_partial_loader_for_local_snapshot(tmp_path, m
         "torch",
         types.SimpleNamespace(
             cuda=types.SimpleNamespace(is_available=lambda: False),
-            device=lambda value: value,
+            device=lambda value: types.SimpleNamespace(type=value),
             bfloat16="bf16",
         ),
     )
@@ -1194,7 +1203,7 @@ def test_two_node_gpt2_completion_is_deterministic():
     "Two node gpt2 completion is deterministic\n\nTags: model, node, real-inference"
     if os.environ.get("CI"):
         pytest.skip("GPT-2 integration test is skipped in CI")
-    torch = pytest.importorskip("torch")
+    torch = _require_functional_torch()
     pytest.importorskip("transformers")
     pytest.importorskip("safetensors")
     pytest.importorskip("accelerate")