feat: checkpoint distributed gguf runtime stories

tests/test_node_admission.py

@@ -22,6 +22,7 @@ import pytest
 
 from meshnet_node.admission import (
     REASON_BACKEND_MISMATCH,
+    REASON_COMPATIBILITY_MISMATCH,
     REASON_MODEL_MISMATCH,
     REASON_NO_REPORT,
     REASON_NOT_PASSED,
@@ -68,11 +69,26 @@ class _FakeBackend:
     total_layers = 24
     hidden_size = 8
 
-    def __init__(self, *, shard_start=0, shard_end=23, device="cpu", forward_error=None):
+    def __init__(
+        self,
+        *,
+        shard_start=0,
+        shard_end=23,
+        device="cpu",
+        forward_error=None,
+        loaded_shard_start=None,
+        loaded_shard_end=None,
+        owns_embedding=None,
+        owns_final_head=None,
+    ):
         self.shard_start = shard_start
         self.shard_end = shard_end
         self.is_head = shard_start == 0
         self.is_tail = shard_end == self.total_layers - 1
+        self.loaded_shard_start = shard_start if loaded_shard_start is None else loaded_shard_start
+        self.loaded_shard_end = shard_end if loaded_shard_end is None else loaded_shard_end
+        self.owns_embedding = self.is_head if owns_embedding is None else owns_embedding
+        self.owns_final_head = self.is_tail if owns_final_head is None else owns_final_head
         self.device = _FakeDevice(device)
         self.model_id = MODEL
         self._forward_error = forward_error
@@ -192,6 +208,17 @@ def test_a_passing_report_from_another_backend_or_device_is_refused():
     assert exc.value.reason == REASON_BACKEND_MISMATCH
 
 
+def test_a_passing_report_with_the_wrong_cache_layout_is_refused():
+    "The compatibility fingerprint fails closed when cache layout changes.\n\nTags: node, admission"
+    ctx = _context()
+    report = capability_report_for(ctx, cache_layout="local-hot-kv")
+
+    with pytest.raises(CapabilityAdmissionError) as exc:
+        admit(AdmissionRequirement.for_context(ctx), report)
+
+    assert exc.value.reason == REASON_COMPATIBILITY_MISMATCH
+
+
 def test_a_report_older_than_the_freshness_window_is_refused():
     "Hardware, drivers and weights move; an old proof is not a current one.\n\nTags: node, admission"
     ctx = _context()
@@ -371,10 +398,31 @@ def test_a_matching_passing_report_registers_and_travels_with_the_payload(startu
     assert report["status"] == "passed"
     assert report["model"]["model_id"] == MODEL
     assert (report["shard"]["start"], report["shard"]["end"]) == (0, 23)
+    assert report["shard"]["owns_embedding"] is True
+    assert report["shard"]["owns_final_head"] is True
     assert report["recipe"]["recipe_id"] == DEFAULT_RECIPE_ID
     assert report["backend"]["device"] == "cpu"
 
 
+def test_capability_report_prefers_backend_loaded_range_over_cli_claims():
+    "The proof reports the model's loaded range, not the CLI's requested range.\n\nTags: node, admission"
+    backend = _FakeBackend(
+        shard_start=0,
+        shard_end=23,
+        loaded_shard_start=8,
+        loaded_shard_end=15,
+        owns_embedding=False,
+        owns_final_head=True,
+    )
+    report = capability_report_for(
+        _context(backend=backend, shard_start=0, shard_end=23),
+    )
+
+    assert (report.shard.start, report.shard.end) == (8, 15)
+    assert report.shard.owns_embedding is False
+    assert report.shard.owns_final_head is True
+
+
 def test_the_served_backend_is_loaded_with_the_recipe_that_was_validated(startup_env):
     "The recipe named in the report is the one the serving backend actually ran.\n\nTags: node, admission, startup"
     node = _start(recipe_id="eager-attention")