feat: implement DGR-006 tensor bundle boundary

packages/node/meshnet_node/native_protocol/generated/shard_runtime_pb2.pyi

@@ -12,6 +12,13 @@ class SchemaVersion(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
     SCHEMA_VERSION_UNSPECIFIED: _ClassVar[SchemaVersion]
     SCHEMA_VERSION_1: _ClassVar[SchemaVersion]
 
+class ArchitectureType(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
+    __slots__ = ()
+    ARCHITECTURE_TYPE_UNSPECIFIED: _ClassVar[ArchitectureType]
+    ARCHITECTURE_TYPE_DENSE: _ClassVar[ArchitectureType]
+    ARCHITECTURE_TYPE_MOE: _ClassVar[ArchitectureType]
+    ARCHITECTURE_TYPE_MLA: _ClassVar[ArchitectureType]
+
 class DType(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
     __slots__ = ()
     DTYPE_UNSPECIFIED: _ClassVar[DType]
@@ -80,6 +87,10 @@ class ServingState(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
     SERVING_STATE_NOT_SERVING: _ClassVar[ServingState]
 SCHEMA_VERSION_UNSPECIFIED: SchemaVersion
 SCHEMA_VERSION_1: SchemaVersion
+ARCHITECTURE_TYPE_UNSPECIFIED: ArchitectureType
+ARCHITECTURE_TYPE_DENSE: ArchitectureType
+ARCHITECTURE_TYPE_MOE: ArchitectureType
+ARCHITECTURE_TYPE_MLA: ArchitectureType
 DTYPE_UNSPECIFIED: DType
 DTYPE_BFLOAT16: DType
 DTYPE_FLOAT16: DType
@@ -165,12 +176,16 @@ class NamedTensor(_message.Message):
     def __init__(self, name: _Optional[str] = ..., shape: _Optional[_Iterable[int]] = ..., dtype: _Optional[_Union[DType, str]] = ..., byte_order: _Optional[_Union[ByteOrder, str]] = ..., total_bytes: _Optional[int] = ..., compression: _Optional[_Union[Compression, str]] = ..., checksum: _Optional[_Union[Checksum, _Mapping]] = ..., fragments: _Optional[_Iterable[_Union[TensorFragment, _Mapping]]] = ...) -> None: ...
 
 class TensorBundle(_message.Message):
-    __slots__ = ("bundle_version", "tensors")
+    __slots__ = ("bundle_version", "tensors", "architecture", "boundary_point")
     BUNDLE_VERSION_FIELD_NUMBER: _ClassVar[int]
     TENSORS_FIELD_NUMBER: _ClassVar[int]
+    ARCHITECTURE_FIELD_NUMBER: _ClassVar[int]
+    BOUNDARY_POINT_FIELD_NUMBER: _ClassVar[int]
     bundle_version: int
     tensors: _containers.RepeatedCompositeFieldContainer[NamedTensor]
-    def __init__(self, bundle_version: _Optional[int] = ..., tensors: _Optional[_Iterable[_Union[NamedTensor, _Mapping]]] = ...) -> None: ...
+    architecture: ArchitectureType
+    boundary_point: str
+    def __init__(self, bundle_version: _Optional[int] = ..., tensors: _Optional[_Iterable[_Union[NamedTensor, _Mapping]]] = ..., architecture: _Optional[_Union[ArchitectureType, str]] = ..., boundary_point: _Optional[str] = ...) -> None: ...
 
 class Fingerprint(_message.Message):
     __slots__ = ("model_artifact_digest", "runtime_recipe_digest", "recipe_id", "recipe_version", "catalogue_version")
@@ -327,20 +342,64 @@ class ActivationChunk(_message.Message):
     def __init__(self, envelope: _Optional[_Union[Envelope, _Mapping]] = ..., bundle: _Optional[_Union[TensorBundle, _Mapping]] = ...) -> None: ...
 
 class DecodeStep(_message.Message):
-    __slots__ = ("idempotency_step", "position", "expected_past_len", "tensor", "work_id", "deadline_unix_nanos")
+    __slots__ = ("idempotency_step", "position", "expected_past_len", "tensor", "work_id", "deadline_unix_nanos", "bundle")
     IDEMPOTENCY_STEP_FIELD_NUMBER: _ClassVar[int]
     POSITION_FIELD_NUMBER: _ClassVar[int]
     EXPECTED_PAST_LEN_FIELD_NUMBER: _ClassVar[int]
     TENSOR_FIELD_NUMBER: _ClassVar[int]
     WORK_ID_FIELD_NUMBER: _ClassVar[int]
     DEADLINE_UNIX_NANOS_FIELD_NUMBER: _ClassVar[int]
+    BUNDLE_FIELD_NUMBER: _ClassVar[int]
     idempotency_step: int
     position: int
     expected_past_len: int
     tensor: NamedTensor
     work_id: str
     deadline_unix_nanos: int
-    def __init__(self, idempotency_step: _Optional[int] = ..., position: _Optional[int] = ..., expected_past_len: _Optional[int] = ..., tensor: _Optional[_Union[NamedTensor, _Mapping]] = ..., work_id: _Optional[str] = ..., deadline_unix_nanos: _Optional[int] = ...) -> None: ...
+    bundle: TensorBundle
+    def __init__(self, idempotency_step: _Optional[int] = ..., position: _Optional[int] = ..., expected_past_len: _Optional[int] = ..., tensor: _Optional[_Union[NamedTensor, _Mapping]] = ..., work_id: _Optional[str] = ..., deadline_unix_nanos: _Optional[int] = ..., bundle: _Optional[_Union[TensorBundle, _Mapping]] = ...) -> None: ...
+
+class RequestRecipeIdentity(_message.Message):
+    __slots__ = ("request_id", "runtime_recipe_digest", "chat_template_id", "chat_template_version", "reasoning_mode", "architecture")
+    REQUEST_ID_FIELD_NUMBER: _ClassVar[int]
+    RUNTIME_RECIPE_DIGEST_FIELD_NUMBER: _ClassVar[int]
+    CHAT_TEMPLATE_ID_FIELD_NUMBER: _ClassVar[int]
+    CHAT_TEMPLATE_VERSION_FIELD_NUMBER: _ClassVar[int]
+    REASONING_MODE_FIELD_NUMBER: _ClassVar[int]
+    ARCHITECTURE_FIELD_NUMBER: _ClassVar[int]
+    request_id: str
+    runtime_recipe_digest: str
+    chat_template_id: str
+    chat_template_version: str
+    reasoning_mode: str
+    architecture: ArchitectureType
+    def __init__(self, request_id: _Optional[str] = ..., runtime_recipe_digest: _Optional[str] = ..., chat_template_id: _Optional[str] = ..., chat_template_version: _Optional[str] = ..., reasoning_mode: _Optional[str] = ..., architecture: _Optional[_Union[ArchitectureType, str]] = ...) -> None: ...
+
+class SamplingParameters(_message.Message):
+    __slots__ = ("temperature", "top_p", "top_k", "seed", "greedy")
+    TEMPERATURE_FIELD_NUMBER: _ClassVar[int]
+    TOP_P_FIELD_NUMBER: _ClassVar[int]
+    TOP_K_FIELD_NUMBER: _ClassVar[int]
+    SEED_FIELD_NUMBER: _ClassVar[int]
+    GREEDY_FIELD_NUMBER: _ClassVar[int]
+    temperature: float
+    top_p: float
+    top_k: int
+    seed: int
+    greedy: bool
+    def __init__(self, temperature: _Optional[float] = ..., top_p: _Optional[float] = ..., top_k: _Optional[int] = ..., seed: _Optional[int] = ..., greedy: _Optional[bool] = ...) -> None: ...
+
+class TailResult(_message.Message):
+    __slots__ = ("identity", "sampling", "logits", "sampled_token_id")
+    IDENTITY_FIELD_NUMBER: _ClassVar[int]
+    SAMPLING_FIELD_NUMBER: _ClassVar[int]
+    LOGITS_FIELD_NUMBER: _ClassVar[int]
+    SAMPLED_TOKEN_ID_FIELD_NUMBER: _ClassVar[int]
+    identity: RequestRecipeIdentity
+    sampling: SamplingParameters
+    logits: TensorBundle
+    sampled_token_id: int
+    def __init__(self, identity: _Optional[_Union[RequestRecipeIdentity, _Mapping]] = ..., sampling: _Optional[_Union[SamplingParameters, _Mapping]] = ..., logits: _Optional[_Union[TensorBundle, _Mapping]] = ..., sampled_token_id: _Optional[int] = ...) -> None: ...
 
 class ReleaseSignal(_message.Message):
     __slots__ = ("route_session_id", "route_epoch", "work_id")
@@ -409,18 +468,20 @@ class SessionRequest(_message.Message):
     def __init__(self, open: _Optional[_Union[SessionOpen, _Mapping]] = ..., chunk: _Optional[_Union[ActivationChunk, _Mapping]] = ..., decode: _Optional[_Union[DecodeStep, _Mapping]] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., release: _Optional[_Union[ReleaseSignal, _Mapping]] = ..., cancel: _Optional[_Union[CancelSignal, _Mapping]] = ...) -> None: ...
 
 class SessionResponse(_message.Message):
-    __slots__ = ("accepted", "chunk", "ack", "flow_control", "status")
+    __slots__ = ("accepted", "chunk", "ack", "flow_control", "status", "tail_result")
     ACCEPTED_FIELD_NUMBER: _ClassVar[int]
     CHUNK_FIELD_NUMBER: _ClassVar[int]
     ACK_FIELD_NUMBER: _ClassVar[int]
     FLOW_CONTROL_FIELD_NUMBER: _ClassVar[int]
     STATUS_FIELD_NUMBER: _ClassVar[int]
+    TAIL_RESULT_FIELD_NUMBER: _ClassVar[int]
     accepted: SessionAccepted
     chunk: ActivationChunk
     ack: Ack
     flow_control: FlowControl
     status: ShardStatus
-    def __init__(self, accepted: _Optional[_Union[SessionAccepted, _Mapping]] = ..., chunk: _Optional[_Union[ActivationChunk, _Mapping]] = ..., ack: _Optional[_Union[Ack, _Mapping]] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., status: _Optional[_Union[ShardStatus, _Mapping]] = ...) -> None: ...
+    tail_result: TailResult
+    def __init__(self, accepted: _Optional[_Union[SessionAccepted, _Mapping]] = ..., chunk: _Optional[_Union[ActivationChunk, _Mapping]] = ..., ack: _Optional[_Union[Ack, _Mapping]] = ..., flow_control: _Optional[_Union[FlowControl, _Mapping]] = ..., status: _Optional[_Union[ShardStatus, _Mapping]] = ..., tail_result: _Optional[_Union[TailResult, _Mapping]] = ...) -> None: ...
 
 class CapabilityRequest(_message.Message):
     __slots__ = ("schema_version",)