feat: DGR-002 - Adopt the versioned gRPC Shard protocol

2026-07-13 16:00:49 +03:00
parent efec84efef
commit 30dcf953fe
22 changed files with 3615 additions and 17 deletions
--- a/.scratch/distributed-gguf-runtime/evidence/DGR-002/protocol.json
+++ b/.scratch/distributed-gguf-runtime/evidence/DGR-002/protocol.json
@@ -0,0 +1,84 @@
+{
+  "schema_version": "SCHEMA_VERSION_1",
+  "bundle_version": 1,
+  "proto_path": "packages/node/native/proto/shard_runtime.proto",
+  "proto_sha256": "077ee34961ab787c67457b1a373f73ec3d577f67086d6bc6a32435f37395b7d6",
+  "protoc": "grpc_tools 1.82.1 (python) / protobuf 33.1 (C++)",
+  "service": {
+    "GetCapability": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Health": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Session": {
+      "client_streaming": true,
+      "server_streaming": true
+    },
+    "Release": {
+      "client_streaming": false,
+      "server_streaming": false
+    },
+    "Cancel": {
+      "client_streaming": false,
+      "server_streaming": false
+    }
+  },
+  "envelope_fields": [
+    "cache_expectation",
+    "chunk",
+    "deadline_unix_nanos",
+    "fingerprint",
+    "idempotency_step",
+    "phase",
+    "position",
+    "route_epoch",
+    "route_session_id",
+    "schema_version",
+    "shard_range",
+    "work_id"
+  ],
+  "named_tensor_fields": [
+    "byte_order",
+    "checksum",
+    "compression",
+    "dtype",
+    "fragments",
+    "name",
+    "shape",
+    "total_bytes"
+  ],
+  "phases": [
+    "PHASE_UNSPECIFIED",
+    "PHASE_PREFILL",
+    "PHASE_DECODE",
+    "PHASE_RELEASE",
+    "PHASE_CANCEL"
+  ],
+  "error_codes": [
+    "ERROR_CODE_UNSPECIFIED",
+    "ERROR_CODE_SCHEMA_UNSUPPORTED",
+    "ERROR_CODE_FINGERPRINT_MISMATCH",
+    "ERROR_CODE_EPOCH_STALE",
+    "ERROR_CODE_SHARD_RANGE_MISMATCH",
+    "ERROR_CODE_CACHE_MISS",
+    "ERROR_CODE_RESOURCE_EXHAUSTED",
+    "ERROR_CODE_PAYLOAD_CORRUPT",
+    "ERROR_CODE_CANCELLED",
+    "ERROR_CODE_DEADLINE_EXCEEDED",
+    "ERROR_CODE_FLOW_CONTROL_VIOLATION",
+    "ERROR_CODE_INTERNAL"
+  ],
+  "bounds": {
+    "max_prefill_chunk_tokens": 128,
+    "max_chunk_bytes": 4194304,
+    "max_fragment_bytes": 1048576,
+    "max_inflight_chunks": 8
+  },
+  "golden_vectors": {
+    "session_request_golden.binpb": "c2c3df8a717ddeae7bd99624d2c7f34c09a518988de990237fe313b75cff0817",
+    "capability_report_golden.binpb": "71ac5f150775f398515b43a63596a5cbe8d2ad607e7e4de56bd44fbe7987080c"
+  }
+}