feat: implement DGR-006 tensor bundle boundary

tests/test_native_shard_protocol.py

@@ -34,6 +34,8 @@ from meshnet_node.native_protocol import (
     ProtocolError,
     checksum_of,
     decode_bundle,
+    decode_step_bundle,
+    encode_decode_step,
     decode_tensor,
     default_flow_control,
     encode_bundle,
@@ -429,7 +431,7 @@ def test_decode_fast_path_is_much_smaller_than_a_full_envelope_chunk():
             idempotency_step=9,
             position=1024,
             expected_past_len=1024,
-            tensor=tensor,
+            bundle=encode_bundle([tensor]),
             work_id="work-7f3a",
         )
     )
@@ -443,7 +445,48 @@ def test_decode_fast_path_is_much_smaller_than_a_full_envelope_chunk():
     )
 
     assert len(fast.SerializeToString()) * 2 < len(full.SerializeToString())
-    assert decode_tensor(fast.decode.tensor) == hidden
+    assert decode_step_bundle(fast.decode) == {HIDDEN_STATES: hidden}
+
+
+def test_decode_fast_path_preserves_legacy_one_tensor_compatibility():
+    tensor = encode_tensor(HIDDEN_STATES, b"\x01\x02" * 8, [1, 1, 8], pb.DTYPE_BFLOAT16)
+    legacy = pb.DecodeStep(tensor=tensor)
+
+    assert decode_step_bundle(legacy) == {HIDDEN_STATES: b"\x01\x02" * 8}
+
+
+def test_decode_bundle_wins_over_legacy_tensor_and_can_carry_sidebands():
+    hidden = encode_tensor(HIDDEN_STATES, b"\x01\x02" * 8, [1, 1, 8], pb.DTYPE_BFLOAT16)
+    sideband = encode_tensor("index_topk", b"\x00" * 4, [1], pb.DTYPE_INT32)
+    decode = pb.DecodeStep(tensor=hidden, bundle=encode_bundle([hidden, sideband]))
+
+    assert decode_step_bundle(decode) == {
+        HIDDEN_STATES: b"\x01\x02" * 8,
+        "index_topk": b"\x00" * 4,
+    }
+
+
+def test_decode_writer_uses_compact_tensor_only_for_a_certified_one_tensor_bundle():
+    hidden = encode_tensor(HIDDEN_STATES, b"\x01\x02" * 8, [1, 1, 8], pb.DTYPE_BFLOAT16)
+    compact = encode_decode_step(
+        encode_bundle([hidden]), idempotency_step=1, position=1, expected_past_len=1, work_id="w"
+    )
+    sideband = encode_tensor("index_topk", b"\x00" * 4, [1], pb.DTYPE_INT32)
+    expanded = encode_decode_step(
+        encode_bundle([hidden, sideband]), idempotency_step=1, position=1, expected_past_len=1, work_id="w"
+    )
+
+    assert compact.HasField("tensor") and not compact.HasField("bundle")
+    assert expanded.HasField("bundle") and not expanded.HasField("tensor")
+
+
+def test_schema_exposes_typed_tail_result_and_bound_sampling_identity():
+    assert {"identity", "sampling", "logits", "sampled_token_id"} <= set(
+        pb.TailResult.DESCRIPTOR.fields_by_name
+    )
+    assert {"request_id", "runtime_recipe_digest", "chat_template_id", "chat_template_version", "reasoning_mode"} <= set(
+        pb.RequestRecipeIdentity.DESCRIPTOR.fields_by_name
+    )
 
 
 def test_flow_control_defaults_bound_the_queue_and_the_message():
@@ -491,6 +534,20 @@ def test_committed_vectors_still_encode_as_promised():
     report = (conformance.TESTDATA_DIR / conformance.GOLDEN_CAPABILITY_REPORT).read_bytes()
     assert conformance.serialize(conformance.canonical_capability_report()) == report
 
+    decode = (conformance.TESTDATA_DIR / conformance.GOLDEN_DECODE_STEP).read_bytes()
+    assert conformance.serialize(conformance.canonical_decode_step()) == decode
+
+
+def test_decode_golden_preserves_the_multi_tensor_boundary():
+    golden = (conformance.TESTDATA_DIR / conformance.GOLDEN_DECODE_STEP).read_bytes()
+    request = pb.SessionRequest.FromString(golden)
+
+    assert request.decode.idempotency_step == 43
+    assert decode_step_bundle(request.decode) == {
+        HIDDEN_STATES: bytes(range(16)),
+        "index_topk": (3).to_bytes(4, "little"),
+    }
+
 
 def test_golden_session_request_round_trips_with_every_field_intact():
     golden = (conformance.TESTDATA_DIR / conformance.GOLDEN_SESSION_REQUEST).read_bytes()